Kenneth W Chen <kenneth.w.chen@intel.com>
Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com>
Koushik <raghavendra.koushik@neterion.com>
+Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski@samsung.com>
Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski.k@gmail.com>
Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Leonid I Ananiev <leonid.i.ananiev@intel.com>
Viresh Kumar <vireshk@kernel.org> <viresh.kumar@st.com>
Viresh Kumar <vireshk@kernel.org> <viresh.linux@gmail.com>
Viresh Kumar <vireshk@kernel.org> <viresh.kumar2@arm.com>
+Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com>
+Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@parallels.com>
Takashi YOSHII <takashi.yoshii.zj@renesas.com>
Yusuke Goda <goda.yusuke@renesas.com>
Gustavo Padovan <gustavo@las.ic.unicamp.br>
# Note: This documents additional properties of any device beyond what
# is documented in Documentation/sysfs-rules.txt
-What: /sys/devices/*/of_path
+What: /sys/devices/*/of_node
Date: February 2015
Contact: Device Tree mailing list <devicetree@vger.kernel.org>
Description:
min_vecs argument set to this limit, and the PCI core will return -ENOSPC
if it can't meet the minimum number of vectors.
-The flags argument should normally be set to 0, but can be used to pass the
-PCI_IRQ_NOMSI and PCI_IRQ_NOMSIX flag in case a device claims to support
-MSI or MSI-X, but the support is broken, or to pass PCI_IRQ_NOLEGACY in
-case the device does not support legacy interrupt lines.
-
-By default this function will spread the interrupts around the available
-CPUs, but this feature can be disabled by passing the PCI_IRQ_NOAFFINITY
-flag.
+The flags argument is used to specify which type of interrupt can be used
+by the device and the driver (PCI_IRQ_LEGACY, PCI_IRQ_MSI, PCI_IRQ_MSIX).
+A convenient short-hand (PCI_IRQ_ALL_TYPES) is also available to ask for
+any possible kind of interrupt. If the PCI_IRQ_AFFINITY flag is set,
+pci_alloc_irq_vectors() will spread the interrupts around the available CPUs.
To get the Linux IRQ numbers passed to request_irq() and free_irq() and the
vectors, use the following function:
capped to the supported limit, so there is no need to query the number of
vectors supported beforehand:
- nvec = pci_alloc_irq_vectors(pdev, 1, nvec, 0);
+ nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_ALL_TYPES)
if (nvec < 0)
goto out_err;
number to pci_alloc_irq_vectors() function as both 'min_vecs' and
'max_vecs' parameters:
- ret = pci_alloc_irq_vectors(pdev, nvec, nvec, 0);
+ ret = pci_alloc_irq_vectors(pdev, nvec, nvec, PCI_IRQ_ALL_TYPES);
if (ret < 0)
goto out_err;
the single MSI mode for a device. It could be done by passing two 1s as
'min_vecs' and 'max_vecs':
- ret = pci_alloc_irq_vectors(pdev, 1, 1, 0);
+ ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES);
if (ret < 0)
goto out_err;
Some devices might not support using legacy line interrupts, in which case
-the PCI_IRQ_NOLEGACY flag can be used to fail the request if the platform
-can't provide MSI or MSI-X interrupts:
+the driver can specify that only MSI or MSI-X is acceptable:
- nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_NOLEGACY);
+ nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_MSI | PCI_IRQ_MSIX);
if (nvec < 0)
goto out_err;
The ID table is an array of struct pci_device_id entries ending with an
all-zero entry. Definitions with static const are generally preferred.
-Use of the deprecated macro DEFINE_PCI_DEVICE_TABLE should be avoided.
Each entry consists of:
directory provides configuration templates for all documented
events, that can be used with perf tool. For example "xp_valid_flit"
is an equivalent of "type=0x8,event=0x4". Other parameters must be
-explicitly specified. For events originating from device, "node"
-defines its index. All crosspoint events require "xp" (index),
-"port" (device port number) and "vc" (virtual channel ID) and
-"dir" (direction). Watchpoints (special "event" value 0xfe) also
-require comparator values ("cmp_l" and "cmp_h") and "mask", being
-index of the comparator mask.
+explicitly specified.
+For events originating from device, "node" defines its index.
+
+Crosspoint PMU events require "xp" (index), "bus" (bus number)
+and "vc" (virtual channel ID).
+
+Crosspoint watchpoint-based events (special "event" value 0xfe)
+require "xp" and "vc" as as above plus "port" (device port index),
+"dir" (transmit/receive direction), comparator values ("cmp_l"
+and "cmp_h") and "mask", being index of the comparator mask.
Masks are defined separately from the event description
(due to limited number of the config values) in the "cmp_mask"
directory, with first 8 configurable by user and additional
| ARM | Cortex-A57 | #832075 | ARM64_ERRATUM_832075 |
| ARM | Cortex-A57 | #852523 | N/A |
| ARM | Cortex-A57 | #834220 | ARM64_ERRATUM_834220 |
+| ARM | Cortex-A72 | #853709 | N/A |
| ARM | MMU-500 | #841119,#826419 | N/A |
| | | | |
| Cavium | ThunderX ITS | #22375, #24313 | CAVIUM_ERRATUM_22375 |
This file allows to turn off the disk entropy contribution. Default
value of this file is '1'(on).
+dax (RO)
+--------
+This file indicates whether the device supports Direct Access (DAX),
+used by CPU-addressable storage to bypass the pagecache. It shows '1'
+if true, '0' if not.
+
discard_granularity (RO)
-----------------------
This shows the size of internal allocation of the device in bytes, if
-------------------
This is the hardware sector size of the device, in bytes.
+io_poll (RW)
+------------
+When read, this file shows the total number of block IO polls and how
+many returned success. Writing '0' to this file will disable polling
+for this device. Writing any non-zero value will enable this feature.
+
iostats (RW)
-------------
This file is used to control (on/off) the iostats accounting of the
setting from "write back" to "write through", since that will also
eliminate cache flushes issued by the kernel.
+write_same_max_bytes (RO)
+-------------------------
+This is the number of bytes the device can write in a single write-same
+command. A value of '0' means write-same is not supported by this
+device.
+
Jens Axboe <jens.axboe@oracle.com>, February 2009
todo_include_todos = False
primary_domain = 'C'
-highlight_language = 'C'
+highlight_language = 'guess'
# -- Options for HTML output ----------------------------------------------
Power management options (ACPI, APM) --->
CPU Frequency scaling --->
[*] CPU Frequency scaling
- <*> CPU frequency translation statistics
+ [*] CPU frequency translation statistics
[*] CPU frequency translation statistics details
- vref-supply: The regulator supply ADC reference voltage.
- #io-channel-cells: Should be 1, see ../iio-bindings.txt
+Optional properties:
+- resets: Must contain an entry for each entry in reset-names if need support
+ this option. See ../reset/reset.txt for details.
+- reset-names: Must include the name "saradc-apb".
+
Example:
saradc: saradc@2006c000 {
compatible = "rockchip,saradc";
interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cru SCLK_SARADC>, <&cru PCLK_SARADC>;
clock-names = "saradc", "apb_pclk";
+ resets = <&cru SRST_SARADC>;
+ reset-names = "saradc-apb";
#io-channel-cells = <1>;
vref-supply = <&vcc18>;
};
- touchscreen-size-y : See touchscreen.txt
Optional properties:
+- firmware-name : File basename (string) for board specific firmware
- touchscreen-inverted-x : See touchscreen.txt
- touchscreen-inverted-y : See touchscreen.txt
- touchscreen-swapped-x-y : See touchscreen.txt
subsystem (mmcss) inside the FlashSS (available in STiH407 SoC
family).
-- clock-names: Should be "mmc".
+- clock-names: Should be "mmc" and "icn". (NB: The latter is not compulsory)
See: Documentation/devicetree/bindings/resource-names.txt
- clocks: Phandle to the clock.
See: Documentation/devicetree/bindings/clock/clock-bindings.txt
- auto-flow-control: one way to enable automatic flow control support. The
driver is allowed to detect support for the capability even without this
property.
-- {rts,cts,dtr,dsr,rng,dcd}-gpios: specify a GPIO for RTS/CTS/DTR/DSR/RI/DCD
- line respectively. It will use specified GPIO instead of the peripheral
- function pin for the UART feature. If unsure, don't specify this property.
Note:
* fsl,ns16550:
interrupts = <10>;
reg-shift = <2>;
};
-
-Example for OMAP UART using GPIO-based modem control signals:
-
- uart4: serial@49042000 {
- compatible = "ti,omap3-uart";
- reg = <0x49042000 0x400>;
- interrupts = <80>;
- ti,hwmods = "uart4";
- clock-frequency = <48000000>;
- cts-gpios = <&gpio3 5 GPIO_ACTIVE_LOW>;
- rts-gpios = <&gpio3 6 GPIO_ACTIVE_LOW>;
- dtr-gpios = <&gpio1 12 GPIO_ACTIVE_LOW>;
- dsr-gpios = <&gpio1 13 GPIO_ACTIVE_LOW>;
- dcd-gpios = <&gpio1 14 GPIO_ACTIVE_LOW>;
- rng-gpios = <&gpio1 15 GPIO_ACTIVE_LOW>;
- };
- interrupts: Interrupt number for McPDM
- interrupt-parent: The parent interrupt controller
- ti,hwmods: Name of the hwmod associated to the McPDM
-- clocks: phandle for the pdmclk provider, likely <&twl6040>
-- clock-names: Must be "pdmclk"
Example:
interrupt-parent = <&gic>;
ti,hwmods = "mcpdm";
};
-
-In board DTS file the pdmclk needs to be added:
-
-&mcpdm {
- clocks = <&twl6040>;
- clock-names = "pdmclk";
- status = "okay";
-};
Required properties:
- #cooling-cells: Used to provide cooling device specific information
Type: unsigned while referring to it. Must be at least 2, in order
- Size: one cell to specify minimum and maximum cooling state used
+ Size: one cell to specify minimum and maximum cooling state used
in the reference. The first cell is the minimum
cooling state requested and the second cell is
the maximum cooling state requested in the reference.
Optional property:
- contribution: The cooling contribution to the thermal zone of the
Type: unsigned referred cooling device at the referred trip point.
- Size: one cell The contribution is a ratio of the sum
+ Size: one cell The contribution is a ratio of the sum
of all cooling contributions within a thermal zone.
Note: Using the THERMAL_NO_LIMIT (-1UL) constant in the cooling-device phandle
Size: one cell
- thermal-sensors: A list of thermal sensor phandles and sensor specifier
- Type: list of used while monitoring the thermal zone.
+ Type: list of used while monitoring the thermal zone.
phandles + sensor
specifier
<&adc>; /* pcb north */
/* hotspot = 100 * bandgap - 120 * adc + 484 */
- coefficients = <100 -120 484>;
+ coefficients = <100 -120 484>;
trips {
...
thermal-sensors = <&adc>;
/* hotspot = 1 * adc + 6000 */
- coefficients = <1 6000>;
+ coefficients = <1 6000>;
(d) - Board thermal
moves it over to the old name. The new file may be on a different
filesystem, so both st_dev and st_ino of the file may change.
-Any open files referring to this inode will access the old data and
-metadata. Similarly any file locks obtained before copy_up will not
-apply to the copied up file.
+Any open files referring to this inode will access the old data.
-On a file opened with O_RDONLY fchmod(2), fchown(2), futimesat(2) and
-fsetxattr(2) will fail with EROFS.
+Any file locks (and leases) obtained before copy_up will not apply
+to the copied up file.
If a file with multiple hard links is copied up, then this will
"break" the link. Changes will not be propagated to other names
implemented in this driver.
Specification of the chip can be found here:
-ftp:///pub/Mainboard-OEM-Sales/Services/Software&Tools/Linux_SystemMonitoring&Watchdog&GPIO/BMC-Teutates_Specification_V1.21.pdf
-ftp:///pub/Mainboard-OEM-Sales/Services/Software&Tools/Linux_SystemMonitoring&Watchdog&GPIO/Fujitsu_mainboards-1-Sensors_HowTo-en-US.pdf
+ftp://ftp.ts.fujitsu.com/pub/Mainboard-OEM-Sales/Services/Software&Tools/Linux_SystemMonitoring&Watchdog&GPIO/BMC-Teutates_Specification_V1.21.pdf
+ftp://ftp.ts.fujitsu.com/pub/Mainboard-OEM-Sales/Services/Software&Tools/Linux_SystemMonitoring&Watchdog&GPIO/Fujitsu_mainboards-1-Sensors_HowTo-en-US.pdf
* Catch the slave interrupts and send appropriate i2c_slave_events to the backend.
+Note that most hardware supports being master _and_ slave on the same bus. So,
+if you extend a bus driver, please make sure that the driver supports that as
+well. In almost all cases, slave support does not need to disable the master
+functionality.
+
Check the i2c-rcar driver as an example.
Cross-referencing from reStructuredText
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-.. highlight:: none
-
To cross-reference the functions and types defined in the kernel-doc comments
from reStructuredText documents, please use the `Sphinx C Domain`_
references. For example::
Function documentation
----------------------
-.. highlight:: c
-
The general format of a function and function-like macro kernel-doc comment is::
/**
Converting DocBook to Sphinx
----------------------------
-.. highlight:: none
-
Over time, we expect all of the documents under ``Documentation/DocBook`` to be
converted to Sphinx and reStructuredText. For most DocBook XML documents, a good
enough solution is to use the simple ``Documentation/sphinx/tmplcvt`` script,
PAGE_SIZE is used as alignment.
PCI-PCI bridge can be specified, if resource
windows need to be expanded.
+ To specify the alignment for several
+ instances of a device, the PCI vendor,
+ device, subvendor, and subdevice may be
+ specified, e.g., 4096@pci:8086:9c22:103c:198f
ecrc= Enable/disable PCIe ECRC (transaction layer
end-to-end CRC checking).
bios: Use BIOS/firmware settings. This is the
- ``flags``
- - Flags. No flags are defined yet, so set this to 0.
+ - Flags. See :ref:`cec-log-addrs-flags` for a list of available flags.
- .. row 7
give the CEC framework more information about the device type, even
though the framework won't use it directly in the CEC message.
+.. _cec-log-addrs-flags:
+
+.. flat-table:: Flags for struct cec_log_addrs
+ :header-rows: 0
+ :stub-columns: 0
+ :widths: 3 1 4
+
+
+ - .. _`CEC-LOG-ADDRS-FL-ALLOW-UNREG-FALLBACK`:
+
+ - ``CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK``
+
+ - 1
+
+ - By default if no logical address of the requested type can be claimed, then
+ it will go back to the unconfigured state. If this flag is set, then it will
+ fallback to the Unregistered logical address. Note that if the Unregistered
+ logical address was explicitly requested, then this flag has no effect.
+
.. _cec-versions:
.. flat-table:: CEC Versions
- ``phys_addr``
- - The current physical address.
+ - The current physical address. This is ``CEC_PHYS_ADDR_INVALID`` if no
+ valid physical address is set.
- .. row 2
- ``log_addr_mask``
- - The current set of claimed logical addresses.
+ - The current set of claimed logical addresses. This is 0 if no logical
+ addresses are claimed or if ``phys_addr`` is ``CEC_PHYS_ADDR_INVALID``.
+ If bit 15 is set (``1 << CEC_LOG_ADDR_UNREGISTERED``) then this device
+ has the unregistered logical address. In that case all other bits are 0.
TODO
====
-The platform device problem
----------------------------
-DSA is currently implemented as a platform device driver which is far from ideal
-as was discussed in this thread:
-
-http://permalink.gmane.org/gmane.linux.network/329848
-
-This basically prevents the device driver model to be properly used and applied,
-and support non-MDIO, non-MMIO Ethernet connected switches.
-
-Another problem with the platform device driver approach is that it prevents the
-use of a modular switch drivers build due to a circular dependency, illustrated
-here:
-
-http://comments.gmane.org/gmane.linux.network/345803
-
-Attempts of reworking this has been done here:
-
-https://lwn.net/Articles/643149/
-
Making SWITCHDEV and DSA converge towards an unified codebase
-------------------------------------------------------------
Data messages can have their contents extracted with the usual bunch of
socket buffer manipulation functions. A data message can be determined to
be the last one in a sequence with rxrpc_kernel_is_data_last(). When a
- data message has been used up, rxrpc_kernel_data_delivered() should be
- called on it..
+ data message has been used up, rxrpc_kernel_data_consumed() should be
+ called on it.
- Non-data messages should be handled to rxrpc_kernel_free_skb() to dispose
- of. It is possible to get extra refs on all types of message for later
- freeing, but this may pin the state of a call until the message is finally
- freed.
+ Messages should be handled to rxrpc_kernel_free_skb() to dispose of. It
+ is possible to get extra refs on all types of message for later freeing,
+ but this may pin the state of a call until the message is finally freed.
(*) Accept an incoming call.
Other errors may be returned if the call had been aborted (-ECONNABORTED)
or had timed out (-ETIME).
- (*) Record the delivery of a data message and free it.
+ (*) Record the delivery of a data message.
- void rxrpc_kernel_data_delivered(struct sk_buff *skb);
+ void rxrpc_kernel_data_consumed(struct rxrpc_call *call,
+ struct sk_buff *skb);
- This is used to record a data message as having been delivered and to
- update the ACK state for the call. The socket buffer will be freed.
+ This is used to record a data message as having been consumed and to
+ update the ACK state for the call. The message must still be passed to
+ rxrpc_kernel_free_skb() for disposal by the caller.
(*) Free a message.
Again, if you find the offending module(s), it(they) must be unloaded every time
before hibernation, and please report the problem with it(them).
-c) Advanced debugging
+c) Using the "test_resume" hibernation option
+
+/sys/power/disk generally tells the kernel what to do after creating a
+hibernation image. One of the available options is "test_resume" which
+causes the just created image to be used for immediate restoration. Namely,
+after doing:
+
+# echo test_resume > /sys/power/disk
+# echo disk > /sys/power/state
+
+a hibernation image will be created and a resume from it will be triggered
+immediately without involving the platform firmware in any way.
+
+That test can be used to check if failures to resume from hibernation are
+related to bad interactions with the platform firmware. That is, if the above
+works every time, but resume from actual hibernation does not work or is
+unreliable, the platform firmware may be responsible for the failures.
+
+On architectures and platforms that support using different kernels to restore
+hibernation images (that is, the kernel used to read the image from storage and
+load it into memory is different from the one included in the image) or support
+kernel address space randomization, it also can be used to check if failures
+to resume may be related to the differences between the restore and image
+kernels.
+
+d) Advanced debugging
In case that hibernation does not work on your system even in the minimal
configuration and compiling more drivers as modules is not practical or some
-Power Management Interface
-
-
-The power management subsystem provides a unified sysfs interface to
-userspace, regardless of what architecture or platform one is
-running. The interface exists in /sys/power/ directory (assuming sysfs
-is mounted at /sys).
-
-/sys/power/state controls system power state. Reading from this file
-returns what states are supported, which is hard-coded to 'freeze',
-'standby' (Power-On Suspend), 'mem' (Suspend-to-RAM), and 'disk'
-(Suspend-to-Disk).
-
-Writing to this file one of those strings causes the system to
-transition into that state. Please see the file
-Documentation/power/states.txt for a description of each of those
-states.
-
-
-/sys/power/disk controls the operating mode of the suspend-to-disk
-mechanism. Suspend-to-disk can be handled in several ways. We have a
-few options for putting the system to sleep - using the platform driver
-(e.g. ACPI or other suspend_ops), powering off the system or rebooting the
-system (for testing).
-
-Additionally, /sys/power/disk can be used to turn on one of the two testing
-modes of the suspend-to-disk mechanism: 'testproc' or 'test'. If the
-suspend-to-disk mechanism is in the 'testproc' mode, writing 'disk' to
-/sys/power/state will cause the kernel to disable nonboot CPUs and freeze
-tasks, wait for 5 seconds, unfreeze tasks and enable nonboot CPUs. If it is
-in the 'test' mode, writing 'disk' to /sys/power/state will cause the kernel
-to disable nonboot CPUs and freeze tasks, shrink memory, suspend devices, wait
-for 5 seconds, resume devices, unfreeze tasks and enable nonboot CPUs. Then,
-we are able to look in the log messages and work out, for example, which code
-is being slow and which device drivers are misbehaving.
-
-Reading from this file will display all supported modes and the currently
-selected one in brackets, for example
-
- [shutdown] reboot test testproc
-
-Writing to this file will accept one of
-
- 'platform' (only if the platform supports it)
- 'shutdown'
- 'reboot'
- 'testproc'
- 'test'
-
-/sys/power/image_size controls the size of the image created by
-the suspend-to-disk mechanism. It can be written a string
-representing a non-negative integer that will be used as an upper
-limit of the image size, in bytes. The suspend-to-disk mechanism will
-do its best to ensure the image size will not exceed that number. However,
-if this turns out to be impossible, it will try to suspend anyway using the
-smallest image possible. In particular, if "0" is written to this file, the
-suspend image will be as small as possible.
-
-Reading from this file will display the current image size limit, which
-is set to 2/5 of available RAM by default.
-
-/sys/power/pm_trace controls the code which saves the last PM event point in
-the RTC across reboots, so that you can debug a machine that just hangs
-during suspend (or more commonly, during resume). Namely, the RTC is only
-used to save the last PM event point if this file contains '1'. Initially it
-contains '0' which may be changed to '1' by writing a string representing a
-nonzero integer into it.
-
-To use this debugging feature you should attempt to suspend the machine, then
-reboot it and run
-
- dmesg -s 1000000 | grep 'hash matches'
-
-CAUTION: Using it will cause your machine's real-time (CMOS) clock to be
-set to a random invalid time after a resume.
+Power Management Interface for System Sleep
+
+Copyright (c) 2016 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+
+The power management subsystem provides userspace with a unified sysfs interface
+for system sleep regardless of the underlying system architecture or platform.
+The interface is located in the /sys/power/ directory (assuming that sysfs is
+mounted at /sys).
+
+/sys/power/state is the system sleep state control file.
+
+Reading from it returns a list of supported sleep states, encoded as:
+
+'freeze' (Suspend-to-Idle)
+'standby' (Power-On Suspend)
+'mem' (Suspend-to-RAM)
+'disk' (Suspend-to-Disk)
+
+Suspend-to-Idle is always supported. Suspend-to-Disk is always supported
+too as long the kernel has been configured to support hibernation at all
+(ie. CONFIG_HIBERNATION is set in the kernel configuration file). Support
+for Suspend-to-RAM and Power-On Suspend depends on the capabilities of the
+platform.
+
+If one of the strings listed in /sys/power/state is written to it, the system
+will attempt to transition into the corresponding sleep state. Refer to
+Documentation/power/states.txt for a description of each of those states.
+
+/sys/power/disk controls the operating mode of hibernation (Suspend-to-Disk).
+Specifically, it tells the kernel what to do after creating a hibernation image.
+
+Reading from it returns a list of supported options encoded as:
+
+'platform' (put the system into sleep using a platform-provided method)
+'shutdown' (shut the system down)
+'reboot' (reboot the system)
+'suspend' (trigger a Suspend-to-RAM transition)
+'test_resume' (resume-after-hibernation test mode)
+
+The currently selected option is printed in square brackets.
+
+The 'platform' option is only available if the platform provides a special
+mechanism to put the system to sleep after creating a hibernation image (ACPI
+does that, for example). The 'suspend' option is available if Suspend-to-RAM
+is supported. Refer to Documentation/power/basic_pm_debugging.txt for the
+description of the 'test_resume' option.
+
+To select an option, write the string representing it to /sys/power/disk.
+
+/sys/power/image_size controls the size of hibernation images.
+
+It can be written a string representing a non-negative integer that will be
+used as a best-effort upper limit of the image size, in bytes. The hibernation
+core will do its best to ensure that the image size will not exceed that number.
+However, if that turns out to be impossible to achieve, a hibernation image will
+still be created and its size will be as small as possible. In particular,
+writing '0' to this file will enforce hibernation images to be as small as
+possible.
+
+Reading from this file returns the current image size limit, which is set to
+around 2/5 of available RAM by default.
+
+/sys/power/pm_trace controls the PM trace mechanism saving the last suspend
+or resume event point in the RTC across reboots.
+
+It helps to debug hard lockups or reboots due to device driver failures that
+occur during system suspend or resume (which is more common) more effectively.
+
+If /sys/power/pm_trace contains '1', the fingerprint of each suspend/resume
+event point in turn will be stored in the RTC memory (overwriting the actual
+RTC information), so it will survive a system crash if one occurs right after
+storing it and it can be used later to identify the driver that caused the crash
+to happen (see Documentation/power/s2ram.txt for more information).
+
+Initially it contains '0' which may be changed to '1' by writing a string
+representing a nonzero integer into it.
For signals taken in non-TM or suspended mode, we use the
normal/non-checkpointed stack pointer.
+Any transaction initiated inside a sighandler and suspended on return
+from the sighandler to the kernel will get reclaimed and discarded.
Failure cause codes used by kernel
==================================
III. Module parameters
+- 'dma_timeout' - DMA transfer completion timeout (in msec, default value 3000).
+ This parameter set a maximum completion wait time for SYNC mode DMA
+ transfer requests and for RIO_WAIT_FOR_ASYNC ioctl requests.
+
- 'dbg_level' - This parameter allows to control amount of debug information
generated by this device driver. This parameter is formed by set of
bit masks that correspond to the specific functional blocks.
caption a.headerlink { opacity: 0; }
caption a.headerlink:hover { opacity: 1; }
- /* inline literal: drop the borderbox and red color */
+ /* inline literal: drop the borderbox, padding and red color */
code, .rst-content tt, .rst-content code {
color: inherit;
border: none;
+ padding: unset;
background: inherit;
font-size: 85%;
}
M: Sumit Semwal <sumit.semwal@linaro.org>
L: devel@driverdev.osuosl.org
S: Supported
+F: Documentation/devicetree/bindings/staging/ion/
F: drivers/staging/android/ion
F: drivers/staging/android/uapi/ion.h
F: drivers/staging/android/uapi/ion_test.h
F: drivers/gpu/drm/arc/
F: Documentation/devicetree/bindings/display/snps,arcpgu.txt
+ARM ARCHITECTED TIMER DRIVER
+M: Mark Rutland <mark.rutland@arm.com>
+M: Marc Zyngier <marc.zyngier@arm.com>
+L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S: Maintained
+F: arch/arm/include/asm/arch_timer.h
+F: arch/arm64/include/asm/arch_timer.h
+F: drivers/clocksource/arm_arch_timer.c
+
ARM HDLCD DRM DRIVER
M: Liviu Dudau <liviu.dudau@arm.com>
S: Supported
ARM/Annapurna Labs ALPINE ARCHITECTURE
M: Tsahee Zidenberg <tsahee@annapurnalabs.com>
M: Antoine Tenart <antoine.tenart@free-electrons.com>
+L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
F: arch/arm/mach-alpine/
F: arch/arm/boot/dts/alpine*
ARM/SAMSUNG EXYNOS ARM ARCHITECTURES
M: Kukjin Kim <kgene@kernel.org>
-M: Krzysztof Kozlowski <k.kozlowski@samsung.com>
+M: Krzysztof Kozlowski <krzk@kernel.org>
+R: Javier Martinez Canillas <javier@osg.samsung.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
S: Maintained
F: drivers/*/*s5pv210*
F: drivers/memory/samsung/*
F: drivers/soc/samsung/*
-F: drivers/spi/spi-s3c*
F: Documentation/arm/Samsung/
F: Documentation/devicetree/bindings/arm/samsung/
F: Documentation/devicetree/bindings/sram/samsung-sram.txt
ARM/UNIPHIER ARCHITECTURE
M: Masahiro Yamada <yamada.masahiro@socionext.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-uniphier.git
S: Maintained
F: arch/arm/boot/dts/uniphier*
F: arch/arm/include/asm/hardware/cache-uniphier.h
BONDING DRIVER
M: Jay Vosburgh <j.vosburgh@gmail.com>
M: Veaceslav Falico <vfalico@gmail.com>
-M: Andy Gospodarek <gospo@cumulusnetworks.com>
+M: Andy Gospodarek <andy@greyhouse.net>
L: netdev@vger.kernel.org
W: http://sourceforge.net/projects/bonding/
S: Supported
F: kernel/bpf/
BROADCOM B44 10/100 ETHERNET DRIVER
-M: Gary Zambrano <zambrano@broadcom.com>
+M: Michael Chan <michael.chan@broadcom.com>
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/broadcom/b44.*
CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)
M: Johannes Weiner <hannes@cmpxchg.org>
M: Michal Hocko <mhocko@kernel.org>
-M: Vladimir Davydov <vdavydov@virtuozzo.com>
+M: Vladimir Davydov <vdavydov.dev@gmail.com>
L: cgroups@vger.kernel.org
L: linux-mm@kvack.org
S: Maintained
F: drivers/net/wan/cosa*
CPMAC ETHERNET DRIVER
-M: Florian Fainelli <florian@openwrt.org>
+M: Florian Fainelli <f.fainelli@gmail.com>
L: netdev@vger.kernel.org
S: Maintained
F: drivers/net/ethernet/ti/cpmac.c
S: Maintained
F: drivers/edac/sb_edac.c
+EDAC-SKYLAKE
+M: Tony Luck <tony.luck@intel.com>
+L: linux-edac@vger.kernel.org
+S: Maintained
+F: drivers/edac/skx_edac.c
+
EDAC-XGENE
APPLIED MICRO (APM) X-GENE SOC EDAC
M: Loc Ho <lho@apm.com>
F: drivers/cpufreq/intel_pstate.c
INTEL FRAMEBUFFER DRIVER (excluding 810 and 815)
-M: Maik Broemme <mbroemme@plusserver.de>
+M: Maik Broemme <mbroemme@libmpq.org>
L: linux-fbdev@vger.kernel.org
S: Maintained
F: Documentation/fb/intelfb.txt
F: sound/soc/codecs/max9860.*
MAXIM MUIC CHARGER DRIVERS FOR EXYNOS BASED BOARDS
-M: Krzysztof Kozlowski <k.kozlowski@samsung.com>
+M: Krzysztof Kozlowski <krzk@kernel.org>
+M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
L: linux-pm@vger.kernel.org
S: Supported
F: drivers/power/max14577_charger.c
MAXIM PMIC AND MUIC DRIVERS FOR EXYNOS BASED BOARDS
M: Chanwoo Choi <cw00.choi@samsung.com>
-M: Krzysztof Kozlowski <k.kozlowski@samsung.com>
+M: Krzysztof Kozlowski <krzk@kernel.org>
+M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
L: linux-kernel@vger.kernel.org
S: Supported
F: drivers/*/max14577*.c
S: Supported
W: https://github.com/SoftRoCE/rxe-dev/wiki/rxe-dev:-Home
Q: http://patchwork.kernel.org/project/linux-rdma/list/
-F: drivers/infiniband/hw/rxe/
+F: drivers/infiniband/sw/rxe/
F: include/uapi/rdma/rdma_user_rxe.h
MEMBARRIER SUPPORT
W: https://fedorahosted.org/dropwatch/
F: net/core/drop_monitor.c
+NETWORKING [DSA]
+M: Andrew Lunn <andrew@lunn.ch>
+M: Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+M: Florian Fainelli <f.fainelli@gmail.com>
+S: Maintained
+F: net/dsa/
+F: include/net/dsa.h
+F: drivers/net/dsa/
+
NETWORKING [GENERAL]
M: "David S. Miller" <davem@davemloft.net>
L: netdev@vger.kernel.org
PIN CONTROLLER - SAMSUNG
M: Tomasz Figa <tomasz.figa@gmail.com>
-M: Krzysztof Kozlowski <k.kozlowski@samsung.com>
+M: Krzysztof Kozlowski <krzk@kernel.org>
M: Sylwester Nawrocki <s.nawrocki@samsung.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
F: drivers/platform/x86/samsung-laptop.c
SAMSUNG AUDIO (ASoC) DRIVERS
-M: Krzysztof Kozlowski <k.kozlowski@samsung.com>
+M: Krzysztof Kozlowski <krzk@kernel.org>
M: Sangbeom Kim <sbkim73@samsung.com>
M: Sylwester Nawrocki <s.nawrocki@samsung.com>
L: alsa-devel@alsa-project.org (moderated for non-subscribers)
SAMSUNG MULTIFUNCTION PMIC DEVICE DRIVERS
M: Sangbeom Kim <sbkim73@samsung.com>
-M: Krzysztof Kozlowski <k.kozlowski@samsung.com>
+M: Krzysztof Kozlowski <krzk@kernel.org>
+M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
L: linux-kernel@vger.kernel.org
L: linux-samsung-soc@vger.kernel.org
S: Supported
L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
F: drivers/clk/samsung/
+SAMSUNG SPI DRIVERS
+M: Kukjin Kim <kgene@kernel.org>
+M: Krzysztof Kozlowski <krzk@kernel.org>
+M: Andi Shyti <andi.shyti@samsung.com>
+L: linux-spi@vger.kernel.org
+L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
+S: Maintained
+F: Documentation/devicetree/bindings/spi/spi-samsung.txt
+F: drivers/spi/spi-s3c*
+F: include/linux/platform_data/spi-s3c64xx.h
+
SAMSUNG SXGBE DRIVERS
M: Byungho An <bh74.an@samsung.com>
M: Girish K S <ks.giri@samsung.com>
F: drivers/staging/vt665?/
STAGING - WILC1000 WIFI DRIVER
-M: Johnny Kim <johnny.kim@atmel.com>
-M: Austin Shin <austin.shin@atmel.com>
-M: Chris Park <chris.park@atmel.com>
-M: Tony Cho <tony.cho@atmel.com>
-M: Glen Lee <glen.lee@atmel.com>
-M: Leo Kim <leo.kim@atmel.com>
+M: Aditya Shankar <aditya.shankar@microchip.com>
+M: Ganesh Krishna <ganesh.krishna@microchip.com>
L: linux-wireless@vger.kernel.org
S: Supported
F: drivers/staging/wilc1000/
F: net/8021q/
VLYNQ BUS
-M: Florian Fainelli <florian@openwrt.org>
+M: Florian Fainelli <f.fainelli@gmail.com>
L: openwrt-devel@lists.openwrt.org (subscribers-only)
S: Maintained
F: drivers/vlynq/vlynq.c
VERSION = 4
PATCHLEVEL = 8
SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc8
NAME = Psychotic Stoned Sheep
# *DOCUMENTATION*
# Tell gcc to never replace conditional load with a non-conditional one
KBUILD_CFLAGS += $(call cc-option,--param=allow-store-data-races=0)
-PHONY += gcc-plugins
-gcc-plugins: scripts_basic
-ifdef CONFIG_GCC_PLUGINS
- $(Q)$(MAKE) $(build)=scripts/gcc-plugins
-endif
- @:
-
include scripts/Makefile.gcc-plugins
ifdef CONFIG_READABLE_ASM
results in the system call being skipped immediately.
- seccomp syscall wired up
- For best performance, an arch should use seccomp_phase1 and
- seccomp_phase2 directly. It should call seccomp_phase1 for all
- syscalls if TIF_SECCOMP is set, but seccomp_phase1 does not
- need to be called from a ptrace-safe context. It must then
- call seccomp_phase2 if seccomp_phase1 returns anything other
- than SECCOMP_PHASE1_OK or SECCOMP_PHASE1_SKIP.
-
- As an additional optimization, an arch may provide seccomp_data
- directly to seccomp_phase1; this avoids multiple calls
- to the syscall_xyz helpers for every syscall.
-
config SECCOMP_FILTER
def_bool y
depends on HAVE_ARCH_SECCOMP_FILTER && SECCOMP && NET
endchoice
+config HAVE_ARCH_WITHIN_STACK_FRAMES
+ bool
+ help
+ An architecture should select this if it can walk the kernel stack
+ frames to determine if an object is part of either the arguments
+ or local variables (i.e. that it excludes saved return addresses,
+ and similar) by implementing an inline arch_within_stack_frames(),
+ which is used by CONFIG_HARDENED_USERCOPY.
+
config HAVE_CONTEXT_TRACKING
bool
help
return __cu_len;
}
-extern inline long
-__copy_tofrom_user(void *to, const void *from, long len, const void __user *validate)
-{
- if (__access_ok((unsigned long)validate, len, get_fs()))
- len = __copy_tofrom_user_nocheck(to, from, len);
- return len;
-}
-
#define __copy_to_user(to, from, n) \
({ \
__chk_user_ptr(to); \
#define __copy_to_user_inatomic __copy_to_user
#define __copy_from_user_inatomic __copy_from_user
-
extern inline long
copy_to_user(void __user *to, const void *from, long n)
{
- return __copy_tofrom_user((__force void *)to, from, n, to);
+ if (likely(__access_ok((unsigned long)to, n, get_fs())))
+ n = __copy_tofrom_user_nocheck((__force void *)to, from, n);
+ return n;
}
extern inline long
copy_from_user(void *to, const void __user *from, long n)
{
- return __copy_tofrom_user(to, (__force void *)from, n, from);
+ if (likely(__access_ok((unsigned long)from, n, get_fs())))
+ n = __copy_tofrom_user_nocheck(to, (__force void *)from, n);
+ else
+ memset(to, 0, n);
+ return n;
}
extern void __do_clear_user(void);
#ifdef CONFIG_ARC_CURR_IN_REG
; Retrieve orig r25 and save it with rest of callee_regs
- ld.as r12, [r12, PT_user_r25]
+ ld r12, [r12, PT_user_r25]
PUSH r12
#else
PUSH r25
; SP is back to start of pt_regs
#ifdef CONFIG_ARC_CURR_IN_REG
- st.as r12, [sp, PT_user_r25]
+ st r12, [sp, PT_user_r25]
#endif
.endm
.endm
.macro IRQ_ENABLE scratch
+ TRACE_ASM_IRQ_ENABLE
lr \scratch, [status32]
or \scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
flag \scratch
- TRACE_ASM_IRQ_ENABLE
.endm
#endif /* __ASSEMBLY__ */
#define pte_page(pte) pfn_to_page(pte_pfn(pte))
#define mk_pte(page, prot) pfn_pte(page_to_pfn(page), prot)
-#define pfn_pte(pfn, prot) (__pte(((pte_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+#define pfn_pte(pfn, prot) __pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
/* Don't use virt_to_pfn for macros below: could cause truncations for PAE40*/
#define pte_pfn(pte) (pte_val(pte) >> PAGE_SHIFT)
"2: ;nop\n" \
" .section .fixup, \"ax\"\n" \
" .align 4\n" \
- "3: mov %0, %3\n" \
+ "3: # return -EFAULT\n" \
+ " mov %0, %3\n" \
+ " # zero out dst ptr\n" \
+ " mov %1, 0\n" \
" j 2b\n" \
" .previous\n" \
" .section __ex_table, \"a\"\n" \
"2: ;nop\n" \
" .section .fixup, \"ax\"\n" \
" .align 4\n" \
- "3: mov %0, %3\n" \
+ "3: # return -EFAULT\n" \
+ " mov %0, %3\n" \
+ " # zero out dst ptr\n" \
+ " mov %1, 0\n" \
+ " mov %R1, 0\n" \
" j 2b\n" \
" .previous\n" \
" .section __ex_table, \"a\"\n" \
/* Machine specific ELF Hdr flags */
#define EF_ARC_OSABI_MSK 0x00000f00
-#define EF_ARC_OSABI_ORIG 0x00000000 /* MUST be zero for back-compat */
-#define EF_ARC_OSABI_CURRENT 0x00000300 /* v3 (no legacy syscalls) */
+
+#define EF_ARC_OSABI_V3 0x00000300 /* v3 (no legacy syscalls) */
+#define EF_ARC_OSABI_V4 0x00000400 /* v4 (64bit data any reg align) */
+
+#if __GNUC__ < 6
+#define EF_ARC_OSABI_CURRENT EF_ARC_OSABI_V3
+#else
+#define EF_ARC_OSABI_CURRENT EF_ARC_OSABI_V4
+#endif
typedef unsigned long elf_greg_t;
typedef unsigned long elf_fpregset_t;
extern void __divdf3(void);
extern void __floatunsidf(void);
extern void __floatunsisf(void);
+extern void __udivdi3(void);
EXPORT_SYMBOL(__ashldi3);
EXPORT_SYMBOL(__ashrdi3);
EXPORT_SYMBOL(__divdf3);
EXPORT_SYMBOL(__floatunsidf);
EXPORT_SYMBOL(__floatunsisf);
+EXPORT_SYMBOL(__udivdi3);
/* ARC optimised assembler routines */
EXPORT_SYMBOL(memset);
}
eflags = x->e_flags;
- if ((eflags & EF_ARC_OSABI_MSK) < EF_ARC_OSABI_CURRENT) {
+ if ((eflags & EF_ARC_OSABI_MSK) != EF_ARC_OSABI_CURRENT) {
pr_err("ABI mismatch - you need newer toolchain\n");
force_sigsegv(SIGSEGV, current);
return 0;
cpu->dccm.base_addr, TO_KB(cpu->dccm.sz),
cpu->iccm.base_addr, TO_KB(cpu->iccm.sz));
- n += scnprintf(buf + n, len - n,
- "OS ABI [v3]\t: no-legacy-syscalls\n");
+ n += scnprintf(buf + n, len - n, "OS ABI [v%d]\t: %s\n",
+ EF_ARC_OSABI_CURRENT >> 8,
+ EF_ARC_OSABI_CURRENT == EF_ARC_OSABI_V3 ?
+ "no-legacy-syscalls" : "64-bit data any register aligned");
return buf;
}
printk(arc_cache_mumbojumbo(0, str, sizeof(str)));
+ /*
+ * Only master CPU needs to execute rest of function:
+ * - Assume SMP so all cores will have same cache config so
+ * any geomtry checks will be same for all
+ * - IOC setup / dma callbacks only need to be setup once
+ */
+ if (cpu)
+ return;
+
if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE)) {
struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache;
return kmap_high(page);
}
+EXPORT_SYMBOL(kmap);
void *kmap_atomic(struct page *page)
{
select HARDIRQS_SW_RESEND
select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
+ select HAVE_ARCH_HARDENED_USERCOPY
select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
select HAVE_ARCH_MMAP_RND_BITS if MMU
platdirs := $(patsubst %,arch/arm/plat-%/,$(sort $(plat-y)))
ifneq ($(CONFIG_ARCH_MULTIPLATFORM),y)
+ifneq ($(CONFIG_ARM_SINGLE_ARMV7M),y)
ifeq ($(KBUILD_SRC),)
KBUILD_CPPFLAGS += $(patsubst %,-I%include,$(machdirs) $(platdirs))
else
KBUILD_CPPFLAGS += $(patsubst %,-I$(srctree)/%include,$(machdirs) $(platdirs))
endif
endif
+endif
export TEXT_OFFSET GZFLAGS MMUEXT
#address-cells = <1>;
#size-cells = <1>;
- elm_id = <&elm>;
+ ti,elm-id = <&elm>;
};
};
#address-cells = <1>;
#size-cells = <1>;
- elm_id = <&elm>;
+ ti,elm-id = <&elm>;
/* MTD partition table */
partition@0 {
gpmc,wr-access-ns = <30>;
gpmc,wr-data-mux-bus-ns = <0>;
- elm_id = <&elm>;
+ ti,elm-id = <&elm>;
#address-cells = <1>;
#size-cells = <1>;
* associativity as these may be erroneously set
* up by boot loader(s).
*/
- cache-size = <1048576>; // 1MB
- cache-sets = <4096>;
+ cache-size = <131072>; // 128KB
+ cache-sets = <512>;
cache-line-size = <32>;
arm,parity-disable;
- arm,tag-latency = <1>;
- arm,data-latency = <1 1>;
- arm,dirty-latency = <1>;
+ arm,tag-latency = <1 1 1>;
+ arm,data-latency = <1 1 1>;
};
scu: scu@1f000000 {
port@0 {
reg = <0>;
- label = "lan1";
+ label = "lan5";
};
port@1 {
reg = <1>;
- label = "lan2";
+ label = "lan4";
};
port@2 {
port@3 {
reg = <3>;
- label = "lan4";
+ label = "lan2";
};
port@4 {
reg = <4>;
- label = "lan5";
+ label = "lan1";
};
port@5 {
/ {
memory {
+ device_type = "memory";
reg = <0 0x10000000>;
};
#include <dt-bindings/clock/bcm2835.h>
#include <dt-bindings/clock/bcm2835-aux.h>
#include <dt-bindings/gpio/gpio.h>
-#include "skeleton.dtsi"
/* This include file covers the common peripherals and configuration between
* bcm2835 and bcm2836 implementations, leaving the CPU configuration to
compatible = "brcm,bcm2835";
model = "BCM2835";
interrupt-parent = <&intc>;
+ #address-cells = <1>;
+ #size-cells = <1>;
chosen {
bootargs = "earlyprintk console=ttyAMA0";
samsung,dw-mshc-ciu-div = <3>;
samsung,dw-mshc-sdr-timing = <0 4>;
samsung,dw-mshc-ddr-timing = <0 2>;
- samsung,dw-mshc-hs400-timing = <0 2>;
- samsung,read-strobe-delay = <90>;
pinctrl-names = "default";
pinctrl-0 = <&sd0_clk &sd0_cmd &sd0_bus1 &sd0_bus4 &sd0_bus8 &sd0_cd>;
bus-width = <8>;
cap-mmc-highspeed;
mmc-hs200-1_8v;
- mmc-hs400-1_8v;
vmmc-supply = <&ldo20_reg>;
vqmmc-supply = <&ldo11_reg>;
};
clocks = <&clks IMX6QDL_CLK_SPDIF_GCLK>, <&clks IMX6QDL_CLK_OSC>,
<&clks IMX6QDL_CLK_SPDIF>, <&clks IMX6QDL_CLK_ASRC>,
<&clks IMX6QDL_CLK_DUMMY>, <&clks IMX6QDL_CLK_ESAI_EXTAL>,
- <&clks IMX6QDL_CLK_IPG>, <&clks IMX6QDL_CLK_MLB>,
+ <&clks IMX6QDL_CLK_IPG>, <&clks IMX6QDL_CLK_DUMMY>,
<&clks IMX6QDL_CLK_DUMMY>, <&clks IMX6QDL_CLK_SPBA>;
clock-names = "core", "rxtx0",
"rxtx1", "rxtx2",
cd-gpios = <&gpio7 11 GPIO_ACTIVE_LOW>;
no-1-8-v;
keep-power-in-suspend;
- enable-sdio-wakup;
+ wakeup-source;
status = "okay";
};
ti,y-min = /bits/ 16 <0>;
ti,y-max = /bits/ 16 <0>;
ti,pressure-max = /bits/ 16 <0>;
- ti,x-plat-ohms = /bits/ 16 <400>;
+ ti,x-plate-ohms = /bits/ 16 <400>;
wakeup-source;
};
};
};
syscon {
- compatible = "arm,integrator-ap-syscon";
+ compatible = "arm,integrator-ap-syscon", "syscon";
reg = <0x11000000 0x100>;
interrupt-parent = <&pic>;
/* These are the logical module IRQs */
};
syscon {
- compatible = "arm,integrator-cp-syscon";
+ compatible = "arm,integrator-cp-syscon", "syscon";
reg = <0xcb000000 0x100>;
};
cpu_on = <0x84000003>;
};
- psci {
- compatible = "arm,psci";
- method = "smc";
- cpu_suspend = <0x84000001>;
- cpu_off = <0x84000002>;
- cpu_on = <0x84000003>;
- };
-
soc {
#address-cells = <1>;
#size-cells = <1>;
partition@e0000 {
label = "u-boot environment";
- reg = <0xe0000 0x100000>;
+ reg = <0xe0000 0x20000>;
};
partition@100000 {
};
};
+&pciec {
+ status = "okay";
+};
+
&pcie0 {
status = "okay";
};
ranges = <0 0 0x00000000 0x1000000>; /* CS0: 16MB for NAND */
nand@0,0 {
- linux,mtd-name = "micron,mt29f4g16abbda3w";
+ compatible = "ti,omap2-nand";
reg = <0 0 4>; /* CS0, offset 0, IO size 4 */
+ interrupt-parent = <&gpmc>;
+ interrupts = <0 IRQ_TYPE_NONE>, /* fifoevent */
+ <1 IRQ_TYPE_NONE>; /* termcount */
+ linux,mtd-name = "micron,mt29f4g16abbda3w";
nand-bus-width = <16>;
ti,nand-ecc-opt = "bch8";
+ rb-gpios = <&gpmc 0 GPIO_ACTIVE_HIGH>; /* gpmc_wait0 */
gpmc,sync-clk-ps = <0>;
gpmc,cs-on-ns = <0>;
gpmc,cs-rd-off-ns = <44>;
gpmc,wr-access-ns = <40>;
gpmc,wr-data-mux-bus-ns = <0>;
gpmc,device-width = <2>;
-
- gpmc,page-burst-access-ns = <5>;
- gpmc,cycle2cycle-delay-ns = <50>;
-
#address-cells = <1>;
#size-cells = <1>;
linux,mtd-name = "micron,mt29f4g16abbda3w";
nand-bus-width = <16>;
ti,nand-ecc-opt = "bch8";
+ rb-gpios = <&gpmc 0 GPIO_ACTIVE_HIGH>; /* gpmc_wait0 */
gpmc,sync-clk-ps = <0>;
gpmc,cs-on-ns = <0>;
gpmc,cs-rd-off-ns = <44>;
};
&gpmc {
- ranges = <0 0 0x00000000 0x20000000>;
+ ranges = <0 0 0x30000000 0x1000000>, /* CS0 */
+ <4 0 0x2b000000 0x1000000>, /* CS4 */
+ <5 0 0x2c000000 0x1000000>; /* CS5 */
nand@0,0 {
compatible = "ti,omap2-nand";
#include "omap-gpmc-smsc9221.dtsi"
&gpmc {
- ranges = <5 0 0x2c000000 0x1000000>; /* CS5 */
-
ethernet@gpmc {
reg = <5 0 0xff>;
interrupt-parent = <&gpio6>;
#include "omap-gpmc-smsc9221.dtsi"
&gpmc {
- ranges = <5 0 0x2c000000 0x1000000>; /* CS5 */
-
ethernet@gpmc {
reg = <5 0 0xff>;
interrupt-parent = <&gpio6>;
#include "omap-gpmc-smsc9221.dtsi"
&gpmc {
- ranges = <4 0 0x2b000000 0x1000000>, /* CS4 */
- <5 0 0x2c000000 0x1000000>; /* CS5 */
-
smsc1: ethernet@gpmc {
reg = <5 0 0xff>;
interrupt-parent = <&gpio6>;
clock-names = "saradc", "apb_pclk";
interrupts = <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>;
#io-channel-cells = <1>;
+ resets = <&cru SRST_SARADC>;
+ reset-names = "saradc-apb";
status = "disabled";
};
#io-channel-cells = <1>;
clocks = <&cru SCLK_SARADC>, <&cru PCLK_SARADC>;
clock-names = "saradc", "apb_pclk";
+ resets = <&cru SRST_SARADC>;
+ reset-names = "saradc-apb";
status = "disabled";
};
#io-channel-cells = <1>;
clocks = <&cru SCLK_SARADC>, <&cru PCLK_SARADC>;
clock-names = "saradc", "apb_pclk";
+ resets = <&cru SRST_SARADC>;
+ reset-names = "saradc-apb";
status = "disabled";
};
interrupt-names = "mmcirq";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_mmc0>;
- clock-names = "mmc";
- clocks = <&clk_s_c0_flexgen CLK_MMC_0>;
+ clock-names = "mmc", "icn";
+ clocks = <&clk_s_c0_flexgen CLK_MMC_0>,
+ <&clk_s_c0_flexgen CLK_RX_ICN_HVA>;
bus-width = <8>;
non-removable;
};
interrupt-names = "mmcirq";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_sd1>;
- clock-names = "mmc";
- clocks = <&clk_s_c0_flexgen CLK_MMC_1>;
+ clock-names = "mmc", "icn";
+ clocks = <&clk_s_c0_flexgen CLK_MMC_1>,
+ <&clk_s_c0_flexgen CLK_RX_ICN_HVA>;
resets = <&softreset STIH407_MMC1_SOFTRESET>;
bus-width = <4>;
};
compatible = "st,st-ohci-300x";
reg = <0x9a03c00 0x100>;
interrupts = <GIC_SPI 180 IRQ_TYPE_NONE>;
- clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>;
+ clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>,
+ <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>;
resets = <&powerdown STIH407_USB2_PORT0_POWERDOWN>,
<&softreset STIH407_USB2_PORT0_SOFTRESET>;
reset-names = "power", "softreset";
interrupts = <GIC_SPI 151 IRQ_TYPE_NONE>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_usb0>;
- clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>;
+ clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>,
+ <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>;
resets = <&powerdown STIH407_USB2_PORT0_POWERDOWN>,
<&softreset STIH407_USB2_PORT0_SOFTRESET>;
reset-names = "power", "softreset";
compatible = "st,st-ohci-300x";
reg = <0x9a83c00 0x100>;
interrupts = <GIC_SPI 181 IRQ_TYPE_NONE>;
- clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>;
+ clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>,
+ <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>;
resets = <&powerdown STIH407_USB2_PORT1_POWERDOWN>,
<&softreset STIH407_USB2_PORT1_SOFTRESET>;
reset-names = "power", "softreset";
interrupts = <GIC_SPI 153 IRQ_TYPE_NONE>;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_usb1>;
- clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>;
+ clocks = <&clk_s_c0_flexgen CLK_TX_ICN_DISP_0>,
+ <&clk_s_c0_flexgen CLK_RX_ICN_DISP_0>;
resets = <&powerdown STIH407_USB2_PORT1_POWERDOWN>,
<&softreset STIH407_USB2_PORT1_SOFTRESET>;
reset-names = "power", "softreset";
trips {
cpu_alert0: cpu_alert0 {
/* milliCelsius */
- temperature = <850000>;
+ temperature = <85000>;
hysteresis = <2000>;
type = "passive";
};
palmas: tps65913@58 {
compatible = "ti,palmas";
reg = <0x58>;
- interrupts = <0 86 IRQ_TYPE_LEVEL_LOW>;
+ interrupts = <0 86 IRQ_TYPE_LEVEL_HIGH>;
#interrupt-cells = <2>;
interrupt-controller;
palmas: pmic@58 {
compatible = "ti,palmas";
reg = <0x58>;
- interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_LOW>;
+ interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
#interrupt-cells = <2>;
interrupt-controller;
palmas: pmic@58 {
compatible = "ti,palmas";
reg = <0x58>;
- interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_LOW>;
+ interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
#interrupt-cells = <2>;
interrupt-controller;
static void locomo_handler(struct irq_desc *desc)
{
- struct locomo *lchip = irq_desc_get_chip_data(desc);
+ struct locomo *lchip = irq_desc_get_handler_data(desc);
int req, i;
/* Acknowledge the parent IRQ */
* Install handler for IRQ_LOCOMO_HW.
*/
irq_set_irq_type(lchip->irq, IRQ_TYPE_EDGE_FALLING);
- irq_set_chip_data(lchip->irq, lchip);
- irq_set_chained_handler(lchip->irq, locomo_handler);
+ irq_set_chained_handler_and_data(lchip->irq, locomo_handler, lchip);
/* Install handlers for IRQ_LOCOMO_* */
for ( ; irq <= lchip->irq_base + 3; irq++) {
* specifies that S0ReadyInt and S1ReadyInt should be '1'.
*/
sa1111_writel(0, irqbase + SA1111_INTPOL0);
- sa1111_writel(SA1111_IRQMASK_HI(IRQ_S0_READY_NINT) |
- SA1111_IRQMASK_HI(IRQ_S1_READY_NINT),
+ sa1111_writel(BIT(IRQ_S0_READY_NINT & 31) |
+ BIT(IRQ_S1_READY_NINT & 31),
irqbase + SA1111_INTPOL1);
/* clear all IRQs */
if (sachip->irq != NO_IRQ) {
ret = sa1111_setup_irq(sachip, pd->irq_base);
if (ret)
- goto err_unmap;
+ goto err_clk;
}
#ifdef CONFIG_ARCH_SA1100
return 0;
+ err_clk:
+ clk_disable(sachip->clk);
err_unmap:
iounmap(sachip->base);
err_clk_unprep:
#ifdef CONFIG_PM
-static int sa1111_suspend(struct platform_device *dev, pm_message_t state)
+static int sa1111_suspend_noirq(struct device *dev)
{
- struct sa1111 *sachip = platform_get_drvdata(dev);
+ struct sa1111 *sachip = dev_get_drvdata(dev);
struct sa1111_save_data *save;
unsigned long flags;
unsigned int val;
* restored by their respective drivers, and must be called
* via LDM after this function.
*/
-static int sa1111_resume(struct platform_device *dev)
+static int sa1111_resume_noirq(struct device *dev)
{
- struct sa1111 *sachip = platform_get_drvdata(dev);
+ struct sa1111 *sachip = dev_get_drvdata(dev);
struct sa1111_save_data *save;
unsigned long flags, id;
void __iomem *base;
id = sa1111_readl(sachip->base + SA1111_SKID);
if ((id & SKID_ID_MASK) != SKID_SA1111_ID) {
__sa1111_remove(sachip);
- platform_set_drvdata(dev, NULL);
+ dev_set_drvdata(dev, NULL);
kfree(save);
return 0;
}
}
#else
-#define sa1111_suspend NULL
-#define sa1111_resume NULL
+#define sa1111_suspend_noirq NULL
+#define sa1111_resume_noirq NULL
#endif
static int sa1111_probe(struct platform_device *pdev)
return -EINVAL;
irq = platform_get_irq(pdev, 0);
if (irq < 0)
- return -ENXIO;
+ return irq;
return __sa1111_probe(&pdev->dev, mem, irq);
}
return 0;
}
+static struct dev_pm_ops sa1111_pm_ops = {
+ .suspend_noirq = sa1111_suspend_noirq,
+ .resume_noirq = sa1111_resume_noirq,
+};
+
/*
* Not sure if this should be on the system bus or not yet.
* We really want some way to register a system device at
static struct platform_driver sa1111_device_driver = {
.probe = sa1111_probe,
.remove = sa1111_remove,
- .suspend = sa1111_suspend,
- .resume = sa1111_resume,
.driver = {
.name = "sa1111",
+ .pm = &sa1111_pm_ops,
},
};
# CONFIG_IOMMU_SUPPORT is not set
CONFIG_FIRMWARE_MEMMAP=y
CONFIG_FANOTIFY=y
-CONFIG_PRINTK_TIME=1
+CONFIG_PRINTK_TIME=y
CONFIG_DYNAMIC_DEBUG=y
CONFIG_STRIP_ASM_SYMS=y
CONFIG_PAGE_POISONING=y
# CONFIG_IOMMU_SUPPORT is not set
CONFIG_FIRMWARE_MEMMAP=y
CONFIG_FANOTIFY=y
-CONFIG_PRINTK_TIME=1
+CONFIG_PRINTK_TIME=y
CONFIG_DYNAMIC_DEBUG=y
CONFIG_STRIP_ASM_SYMS=y
CONFIG_PAGE_POISONING=y
CONFIG_USB_XHCI_HCD=y
CONFIG_USB_STORAGE=y
CONFIG_USB_DWC3=y
+CONFIG_NOP_USB_XCEIV=y
CONFIG_KEYSTONE_USB_PHY=y
CONFIG_NEW_LEDS=y
CONFIG_LEDS_CLASS=y
CONFIG_DMA_BCM2835=y
CONFIG_DMA_OMAP=y
CONFIG_QCOM_BAM_DMA=y
-CONFIG_XILINX_VDMA=y
+CONFIG_XILINX_DMA=y
CONFIG_DMA_SUN6I=y
CONFIG_STAGING=y
CONFIG_SENSORS_ISL29018=y
err = blkcipher_walk_done(desc, &walk,
walk.nbytes % AES_BLOCK_SIZE);
}
- if (nbytes) {
+ if (walk.nbytes % AES_BLOCK_SIZE) {
u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
u8 __aligned(8) tail[AES_BLOCK_SIZE];
#define PMD_SECT_WB (PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
#define PMD_SECT_MINICACHE (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE)
#define PMD_SECT_WBWA (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
+#define PMD_SECT_CACHE_MASK (PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
#define PMD_SECT_NONSHARED_DEV (PMD_SECT_TEX(2))
/*
#define PMD_SECT_WT (_AT(pmdval_t, 2) << 2) /* normal inner write-through */
#define PMD_SECT_WB (_AT(pmdval_t, 3) << 2) /* normal inner write-back */
#define PMD_SECT_WBWA (_AT(pmdval_t, 7) << 2) /* normal inner write-alloc */
+#define PMD_SECT_CACHE_MASK (_AT(pmdval_t, 7) << 2)
/*
* + Level 3 descriptor (PTE)
static inline unsigned long __must_check
__copy_from_user(void *to, const void __user *from, unsigned long n)
{
- unsigned int __ua_flags = uaccess_save_and_enable();
+ unsigned int __ua_flags;
+
+ check_object_size(to, n, false);
+ __ua_flags = uaccess_save_and_enable();
n = arm_copy_from_user(to, from, n);
uaccess_restore(__ua_flags);
return n;
__copy_to_user(void __user *to, const void *from, unsigned long n)
{
#ifndef CONFIG_UACCESS_WITH_MEMCPY
- unsigned int __ua_flags = uaccess_save_and_enable();
+ unsigned int __ua_flags;
+
+ check_object_size(from, n, true);
+ __ua_flags = uaccess_save_and_enable();
n = arm_copy_to_user(to, from, n);
uaccess_restore(__ua_flags);
return n;
#else
+ check_object_size(from, n, true);
return arm_copy_to_user(to, from, n);
#endif
}
bl __und_fault
__und_svc_finish:
+ get_thread_info tsk
ldr r5, [sp, #S_PSR] @ Get SVC cpsr
svc_exit r5 @ return from exception
UNWIND(.fnend )
and r7, #0x1f @ Preserve HPMN
mcr p15, 4, r7, c1, c1, 1 @ HDCR
+ @ Make sure NS-SVC is initialised appropriately
+ mrc p15, 0, r7, c1, c0, 0 @ SCTLR
+ orr r7, #(1 << 5) @ CP15 barriers enabled
+ bic r7, #(3 << 7) @ Clear SED/ITD for v8 (RES0 for v7)
+ bic r7, #(3 << 19) @ WXN and UWXN disabled
+ mcr p15, 0, r7, c1, c0, 0 @ SCTLR
+
+ mrc p15, 0, r7, c0, c0, 0 @ MIDR
+ mcr p15, 4, r7, c0, c0, 0 @ VPIDR
+
+ mrc p15, 0, r7, c0, c0, 5 @ MPIDR
+ mcr p15, 4, r7, c0, c0, 5 @ VMPIDR
+
#if !defined(ZIMAGE) && defined(CONFIG_ARM_ARCH_TIMER)
@ make CNTP_* and CNTPCT accessible from PL1
mrc p15, 0, r7, c0, c1, 1 @ ID_PFR1
mm_segment_t fs;
long ret, err, i;
- if (maxevents <= 0 || maxevents > (INT_MAX/sizeof(struct epoll_event)))
+ if (maxevents <= 0 ||
+ maxevents > (INT_MAX/sizeof(*kbuf)) ||
+ maxevents > (INT_MAX/sizeof(*events)))
return -EINVAL;
+ if (!access_ok(VERIFY_WRITE, events, sizeof(*events) * maxevents))
+ return -EFAULT;
kbuf = kmalloc(sizeof(*kbuf) * maxevents, GFP_KERNEL);
if (!kbuf)
return -ENOMEM;
if (nsops < 1 || nsops > SEMOPM)
return -EINVAL;
+ if (!access_ok(VERIFY_READ, tsops, sizeof(*tsops) * nsops))
+ return -EFAULT;
sops = kmalloc(sizeof(*sops) * nsops, GFP_KERNEL);
if (!sops)
return -ENOMEM;
{
int i;
- kvm_free_stage2_pgd(kvm);
-
for (i = 0; i < KVM_MAX_VCPUS; ++i) {
if (kvm->vcpus[i]) {
kvm_arch_vcpu_free(kvm->vcpus[i]);
switch (ioctl) {
case KVM_CREATE_IRQCHIP: {
+ int ret;
if (!vgic_present)
return -ENXIO;
- return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
+ mutex_lock(&kvm->lock);
+ ret = kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
+ mutex_unlock(&kvm->lock);
+ return ret;
}
case KVM_ARM_SET_DEVICE_ADDR: {
struct kvm_arm_device_addr dev_addr;
smp_rmb();
pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writable);
- if (is_error_pfn(pfn))
+ if (is_error_noslot_pfn(pfn))
return -EFAULT;
if (kvm_is_device_pfn(pfn)) {
kern_hyp_va(PAGE_OFFSET), kern_hyp_va(~0UL));
if (hyp_idmap_start >= kern_hyp_va(PAGE_OFFSET) &&
- hyp_idmap_start < kern_hyp_va(~0UL)) {
+ hyp_idmap_start < kern_hyp_va(~0UL) &&
+ hyp_idmap_start != (unsigned long)__hyp_idmap_text_start) {
/*
* The idmap page is intersecting with the VA space,
* it is not safe to continue further.
void kvm_arch_flush_shadow_all(struct kvm *kvm)
{
+ kvm_free_stage2_pgd(kvm);
}
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
menuconfig ARCH_CLPS711X
bool "Cirrus Logic EP721x/EP731x-based"
depends on ARCH_MULTI_V4T
- select ARCH_REQUIRE_GPIOLIB
select AUTO_ZRELADDR
select CLKSRC_OF
select CLPS711X_TIMER
select COMMON_CLK
select CPU_ARM720T
select GENERIC_CLOCKEVENTS
+ select GPIOLIB
select MFD_SYSCON
select OF_IRQ
select USE_OF
return -ENOMEM;
}
+ /*
+ * Clear the OF_POPULATED flag set in of_irq_init so that
+ * later the Exynos PMU platform device won't be skipped.
+ */
+ of_node_clear_flag(node, OF_POPULATED);
+
return 0;
}
for (i = 0; i < IMR_NUM; i++)
writel_relaxed(~0, gpc_base + GPC_IMR1 + i * 4);
+ /*
+ * Clear the OF_POPULATED flag set in of_irq_init so that
+ * later the GPC power domain driver will not be skipped.
+ */
+ of_node_clear_flag(node, OF_POPULATED);
+
return 0;
}
IRQCHIP_DECLARE(imx_gpc, "fsl,imx6q-gpc", imx_gpc_init);
if (parent == NULL)
pr_warn("failed to initialize soc device\n");
+ of_platform_default_populate(NULL, NULL, parent);
imx6ul_enet_init();
imx_anatop_init();
imx6ul_pm_init();
val &= ~BM_CLPCR_SBYOS;
if (cpu_is_imx6sl())
val |= BM_CLPCR_BYPASS_PMIC_READY;
- if (cpu_is_imx6sl() || cpu_is_imx6sx())
+ if (cpu_is_imx6sl() || cpu_is_imx6sx() || cpu_is_imx6ul())
val |= BM_CLPCR_BYP_MMDC_CH0_LPM_HS;
else
val |= BM_CLPCR_BYP_MMDC_CH1_LPM_HS;
val |= 0x3 << BP_CLPCR_STBY_COUNT;
val |= BM_CLPCR_VSTBY;
val |= BM_CLPCR_SBYOS;
- if (cpu_is_imx6sl())
+ if (cpu_is_imx6sl() || cpu_is_imx6sx())
val |= BM_CLPCR_BYPASS_PMIC_READY;
if (cpu_is_imx6sl() || cpu_is_imx6sx() || cpu_is_imx6ul())
val |= BM_CLPCR_BYP_MMDC_CH0_LPM_HS;
-ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \
- -I$(srctree)/arch/arm/plat-orion/include
+ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/arch/arm/plat-orion/include
AFLAGS_coherency_ll.o := -Wa,-march=armv7-a
CFLAGS_pmsu.o := -march=armv7-a
{
int i = 0;
- if (!clkctrl_offs)
- return 0;
-
omap_test_timeout(_is_module_ready(inst, clkctrl_offs),
MAX_MODULE_READY_TIME, i);
{
int i = 0;
- if (!clkctrl_offs)
- return 0;
-
omap_test_timeout((_clkctrl_idlest(inst, clkctrl_offs) ==
CLKCTRL_IDLEST_DISABLED),
MAX_MODULE_READY_TIME, i);
{
int i = 0;
- if (!clkctrl_offs)
- return 0;
-
omap_test_timeout(_is_module_ready(part, inst, clkctrl_offs),
MAX_MODULE_READY_TIME, i);
{
int i = 0;
- if (!clkctrl_offs)
- return 0;
-
omap_test_timeout((_clkctrl_idlest(part, inst, clkctrl_offs) ==
CLKCTRL_IDLEST_DISABLED),
MAX_MODULE_DISABLE_TIME, i);
if (oh->flags & HWMOD_NO_IDLEST)
return 0;
+ if (!oh->prcm.omap4.clkctrl_offs &&
+ !(oh->prcm.omap4.flags & HWMOD_OMAP4_ZERO_CLKCTRL_OFFSET))
+ return 0;
+
return omap_cm_wait_module_idle(oh->clkdm->prcm_partition,
oh->clkdm->cm_inst,
oh->prcm.omap4.clkctrl_offs, 0);
if (!_find_mpu_rt_port(oh))
return 0;
+ if (!oh->prcm.omap4.clkctrl_offs &&
+ !(oh->prcm.omap4.flags & HWMOD_OMAP4_ZERO_CLKCTRL_OFFSET))
+ return 0;
+
/* XXX check module SIDLEMODE, hardreset status */
return omap_cm_wait_module_ready(oh->clkdm->prcm_partition,
* HWMOD_OMAP4_NO_CONTEXT_LOSS_BIT: Some IP blocks don't have a PRCM
* module-level context loss register associated with them; this
* flag bit should be set in those cases
+ * HWMOD_OMAP4_ZERO_CLKCTRL_OFFSET: Some IP blocks have a valid CLKCTRL
+ * offset of zero; this flag bit should be set in those cases to
+ * distinguish from hwmods that have no clkctrl offset.
*/
#define HWMOD_OMAP4_NO_CONTEXT_LOSS_BIT (1 << 0)
+#define HWMOD_OMAP4_ZERO_CLKCTRL_OFFSET (1 << 1)
/**
* struct omap_hwmod_omap4_prcm - OMAP4-specific PRCM data
#define CLKCTRL(oh, clkctrl) ((oh).prcm.omap4.clkctrl_offs = (clkctrl))
#define RSTCTRL(oh, rstctrl) ((oh).prcm.omap4.rstctrl_offs = (rstctrl))
#define RSTST(oh, rstst) ((oh).prcm.omap4.rstst_offs = (rstst))
+#define PRCM_FLAGS(oh, flag) ((oh).prcm.omap4.flags = (flag))
/*
* 'l3' class
CLKCTRL(am33xx_i2c1_hwmod, AM33XX_CM_WKUP_I2C0_CLKCTRL_OFFSET);
CLKCTRL(am33xx_wd_timer1_hwmod, AM33XX_CM_WKUP_WDT1_CLKCTRL_OFFSET);
CLKCTRL(am33xx_rtc_hwmod, AM33XX_CM_RTC_RTC_CLKCTRL_OFFSET);
+ PRCM_FLAGS(am33xx_rtc_hwmod, HWMOD_OMAP4_ZERO_CLKCTRL_OFFSET);
CLKCTRL(am33xx_mmc2_hwmod, AM33XX_CM_PER_MMC2_CLKCTRL_OFFSET);
CLKCTRL(am33xx_gpmc_hwmod, AM33XX_CM_PER_GPMC_CLKCTRL_OFFSET);
CLKCTRL(am33xx_l4_ls_hwmod, AM33XX_CM_PER_L4LS_CLKCTRL_OFFSET);
* display serial interface controller
*/
+static struct omap_hwmod_class_sysconfig omap3xxx_dsi_sysc = {
+ .rev_offs = 0x0000,
+ .sysc_offs = 0x0010,
+ .syss_offs = 0x0014,
+ .sysc_flags = (SYSC_HAS_AUTOIDLE | SYSC_HAS_CLOCKACTIVITY |
+ SYSC_HAS_ENAWAKEUP | SYSC_HAS_SIDLEMODE |
+ SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS),
+ .idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART),
+ .sysc_fields = &omap_hwmod_sysc_type1,
+};
+
static struct omap_hwmod_class omap3xxx_dsi_hwmod_class = {
.name = "dsi",
+ .sysc = &omap3xxx_dsi_sysc,
};
static struct omap_hwmod_irq_info omap3xxx_dsi1_irqs[] = {
config MACH_OX810SE
bool "Support OX810SE Based Products"
+ select ARCH_HAS_RESET_CONTROLLER
select COMMON_CLK_OXNAS
select CPU_ARM926T
select MFD_SYSCON
select OXNAS_RPS_TIMER
select PINCTRL_OXNAS
+ select RESET_CONTROLLER
select RESET_OXNAS
select VERSATILE_FPGA_IRQ
help
*/
#include <linux/kernel.h>
+#include <linux/module.h> /* symbol_get ; symbol_put */
#include <linux/init.h>
#include <linux/platform_device.h>
#include <linux/major.h>
};
static struct smc91x_platdata smc91x_platdata = {
- .flags = SMC91X_USE_32BIT | SMC91X_USE_DMA | SMC91X_NOWAIT,
+ .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+ SMC91X_USE_DMA | SMC91X_NOWAIT,
};
static struct platform_device smc91x_device = {
// no D+ pullup; lubbock can't connect/disconnect in software
};
+static void lubbock_init_pcmcia(void)
+{
+ struct clk *clk;
+
+ /* Add an alias for the SA1111 PCMCIA clock */
+ clk = clk_get_sys("pxa2xx-pcmcia", NULL);
+ if (!IS_ERR(clk)) {
+ clkdev_create(clk, NULL, "1800");
+ clk_put(clk);
+ }
+}
+
static struct resource sa1111_resources[] = {
[0] = {
.start = 0x10000000,
pxa_set_btuart_info(NULL);
pxa_set_stuart_info(NULL);
+ lubbock_init_pcmcia();
+
clk_add_alias("SA1111_CLK", NULL, "GPIO11_CLK", NULL);
pxa_set_udc_info(&udc_info);
pxa_set_fb_info(NULL, &sharp_lm8v31);
*/
#include <linux/kernel.h>
+#include <linux/module.h> /* symbol_get ; symbol_put */
#include <linux/platform_device.h>
#include <linux/delay.h>
#include <linux/gpio_keys.h>
};
static struct smc91x_platdata xcep_smc91x_info = {
- .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT | SMC91X_USE_DMA,
+ .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+ SMC91X_NOWAIT | SMC91X_USE_DMA,
};
static struct platform_device smc91x_device = {
#
# Makefile for the linux kernel.
#
-ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \
- -I$(srctree)/arch/arm/plat-versatile/include
+ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/arch/arm/plat-versatile/include
obj-y := core.o
obj-$(CONFIG_REALVIEW_DT) += realview-dt.o
};
static struct smc91x_platdata smc91x_platdata = {
- .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+ .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+ SMC91X_NOWAIT,
};
static struct platform_device realview_eth_device = {
#
# Licensed under GPLv2
-ccflags-$(CONFIG_ARCH_MULTIPLATFORM) += -I$(srctree)/$(src)/include -I$(srctree)/arch/arm/plat-samsung/include
+ccflags-$(CONFIG_ARCH_MULTIPLATFORM) += -I$(srctree)/arch/arm/plat-samsung/include
# Core
}
static struct clkops clk_36864_ops = {
+ .enable = clk_cpu_enable,
+ .disable = clk_cpu_disable,
.get_rate = clk_36864_get_rate,
};
CLKDEV_INIT(NULL, "OSTIMER0", &clk_36864),
};
-static int __init sa11xx_clk_init(void)
+int __init sa11xx_clk_init(void)
{
clkdev_add_table(sa11xx_clkregs, ARRAY_SIZE(sa11xx_clkregs));
return 0;
}
-core_initcall(sa11xx_clk_init);
#include <mach/hardware.h>
#include <mach/irqs.h>
+#include <mach/reset.h>
#include "generic.h"
#include <clocksource/pxa.h>
void sa11x0_restart(enum reboot_mode mode, const char *cmd)
{
+ clear_reset_status(RESET_STATUS_ALL);
+
if (mode == REBOOT_SOFT) {
/* Jump into ROM at address 0 */
soft_restart(0);
sa11x0_init_irq_nodt(IRQ_GPIO0_SC, irq_resource.start);
sa1100_init_gpio();
+ sa11xx_clk_init();
}
/*
#else
static inline int sa11x0_pm_init(void) { return 0; }
#endif
+
+int sa11xx_clk_init(void);
};
static struct smc91x_platdata smc91x_platdata = {
- .flags = SMC91X_USE_16BIT | SMC91X_NOWAIT,
+ .flags = SMC91X_USE_16BIT | SMC91X_USE_8BIT | SMC91X_NOWAIT,
};
static struct platform_device smc91x_device = {
bool __init shmobile_smp_init_fallback_ops(void)
{
/* fallback on PSCI/smp_ops if no other DT based method is detected */
+ if (!IS_ENABLED(CONFIG_SMP))
+ return false;
+
return platform_can_secondary_boot() ? true : false;
}
#define REGULATOR_IRQ_MASK BIT(2) /* IRQ2, active low */
-static void __iomem *irqc;
-
-static const u8 da9063_mask_regs[] = {
- DA9063_REG_IRQ_MASK_A,
- DA9063_REG_IRQ_MASK_B,
- DA9063_REG_IRQ_MASK_C,
- DA9063_REG_IRQ_MASK_D,
-};
-
-/* DA9210 System Control and Event Registers */
+/* start of DA9210 System Control and Event Registers */
#define DA9210_REG_MASK_A 0x54
-#define DA9210_REG_MASK_B 0x55
-
-static const u8 da9210_mask_regs[] = {
- DA9210_REG_MASK_A,
- DA9210_REG_MASK_B,
-};
-
-static void da9xxx_mask_irqs(struct i2c_client *client, const u8 regs[],
- unsigned int nregs)
-{
- unsigned int i;
- dev_info(&client->dev, "Masking %s interrupt sources\n", client->name);
+static void __iomem *irqc;
- for (i = 0; i < nregs; i++) {
- int error = i2c_smbus_write_byte_data(client, regs[i], ~0);
- if (error) {
- dev_err(&client->dev, "i2c error %d\n", error);
- return;
- }
- }
-}
+/* first byte sets the memory pointer, following are consecutive reg values */
+static u8 da9063_irq_clr[] = { DA9063_REG_IRQ_MASK_A, 0xff, 0xff, 0xff, 0xff };
+static u8 da9210_irq_clr[] = { DA9210_REG_MASK_A, 0xff, 0xff };
+
+static struct i2c_msg da9xxx_msgs[2] = {
+ {
+ .addr = 0x58,
+ .len = ARRAY_SIZE(da9063_irq_clr),
+ .buf = da9063_irq_clr,
+ }, {
+ .addr = 0x68,
+ .len = ARRAY_SIZE(da9210_irq_clr),
+ .buf = da9210_irq_clr,
+ },
+};
static int regulator_quirk_notify(struct notifier_block *nb,
unsigned long action, void *data)
client = to_i2c_client(dev);
dev_dbg(dev, "Detected %s\n", client->name);
- if ((client->addr == 0x58 && !strcmp(client->name, "da9063")))
- da9xxx_mask_irqs(client, da9063_mask_regs,
- ARRAY_SIZE(da9063_mask_regs));
- else if (client->addr == 0x68 && !strcmp(client->name, "da9210"))
- da9xxx_mask_irqs(client, da9210_mask_regs,
- ARRAY_SIZE(da9210_mask_regs));
+ if ((client->addr == 0x58 && !strcmp(client->name, "da9063")) ||
+ (client->addr == 0x68 && !strcmp(client->name, "da9210"))) {
+ int ret;
+
+ dev_info(&client->dev, "clearing da9063/da9210 interrupts\n");
+ ret = i2c_transfer(client->adapter, da9xxx_msgs, ARRAY_SIZE(da9xxx_msgs));
+ if (ret != ARRAY_SIZE(da9xxx_msgs))
+ dev_err(&client->dev, "i2c error %d\n", ret);
+ }
mon = ioread32(irqc + IRQC_MONITOR);
if (mon & REGULATOR_IRQ_MASK)
initial_pmd_value = pmd;
- pmd &= PMD_SECT_TEX(1) | PMD_SECT_BUFFERABLE | PMD_SECT_CACHEABLE;
+ pmd &= PMD_SECT_CACHE_MASK;
for (i = 0; i < ARRAY_SIZE(cache_policies); i++)
if (cache_policies[i].pmd == pmd) {
{
void *ptr = (void *)__get_free_pages(PGALLOC_GFP, get_order(sz));
- BUG_ON(!ptr);
+ if (!ptr || !pgtable_page_ctor(virt_to_page(ptr)))
+ BUG();
return ptr;
}
{
phys_addr_t memblock_limit = 0;
int highmem = 0;
- phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1;
+ u64 vmalloc_limit;
struct memblock_region *reg;
bool should_use_highmem = false;
+ /*
+ * Let's use our own (unoptimized) equivalent of __pa() that is
+ * not affected by wrap-arounds when sizeof(phys_addr_t) == 4.
+ * The result is used as the upper bound on physical memory address
+ * and may itself be outside the valid range for which phys_addr_t
+ * and therefore __pa() is defined.
+ */
+ vmalloc_limit = (u64)(uintptr_t)vmalloc_min - PAGE_OFFSET + PHYS_OFFSET;
+
for_each_memblock(memory, reg) {
phys_addr_t block_start = reg->base;
phys_addr_t block_end = reg->base + reg->size;
if (reg->size > size_limit) {
phys_addr_t overlap_size = reg->size - size_limit;
- pr_notice("Truncating RAM at %pa-%pa to -%pa",
- &block_start, &block_end, &vmalloc_limit);
- memblock_remove(vmalloc_limit, overlap_size);
+ pr_notice("Truncating RAM at %pa-%pa",
+ &block_start, &block_end);
block_end = vmalloc_limit;
+ pr_cont(" to -%pa", &block_end);
+ memblock_remove(vmalloc_limit, overlap_size);
should_use_highmem = true;
}
}
#include <asm/hwcap.h>
#include <asm/pgtable-hwdef.h>
#include <asm/pgtable.h>
+#include <asm/memory.h>
#include "proc-macros.S"
static struct vcpu_info __percpu *xen_vcpu_info;
/* Linux <-> Xen vCPU id mapping */
-DEFINE_PER_CPU(int, xen_vcpu_id) = -1;
+DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
/* These are unused until we support booting "pre-ballooned" */
pr_info("Xen: initializing cpu%d\n", cpu);
vcpup = per_cpu_ptr(xen_vcpu_info, cpu);
- /* Direct vCPU id mapping for ARM guests. */
- per_cpu(xen_vcpu_id, cpu) = cpu;
-
info.mfn = virt_to_gfn(vcpup);
info.offset = xen_offset_in_page(vcpup);
{
struct xen_add_to_physmap xatp;
struct shared_info *shared_info_page = NULL;
+ int cpu;
if (!xen_domain())
return 0;
return -ENOMEM;
/* Direct vCPU id mapping for ARM guests. */
- per_cpu(xen_vcpu_id, 0) = 0;
+ for_each_possible_cpu(cpu)
+ per_cpu(xen_vcpu_id, cpu) = cpu;
xen_auto_xlat_grant_frames.count = gnttab_max_grant_frames();
if (xen_xlate_map_ballooned_pages(&xen_auto_xlat_grant_frames.pfn,
select HAVE_ALIGNED_STRUCT_PAGE if SLUB
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_BITREVERSE
+ select HAVE_ARCH_HARDENED_USERCOPY
select HAVE_ARCH_HUGE_VMAP
select HAVE_ARCH_JUMP_LABEL
select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP && !(ARM64_16K_PAGES && ARM64_VA_BITS_48)
config ARCH_ALPINE
bool "Annapurna Labs Alpine platform"
- select ALPINE_MSI
+ select ALPINE_MSI if PCI
help
This enables support for the Annapurna Labs Alpine
Soc family.
config ARCH_HISI
bool "Hisilicon SoC Family"
select ARM_TIMER_SP804
- select HISILICON_IRQ_MBIGEN
+ select HISILICON_IRQ_MBIGEN if PCI
help
This enables support for Hisilicon ARMv8 SoC family
/* Local timer */
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 13 0xf01>,
- <1 14 0xf01>,
- <1 11 0xf01>,
- <1 10 0xf01>;
+ interrupts = <1 13 0xf08>,
+ <1 14 0xf08>,
+ <1 11 0xf08>,
+ <1 10 0xf08>;
};
timer0: timer0@ffc03000 {
timer {
compatible = "arm,armv8-timer";
interrupts = <GIC_PPI 13
- (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_EDGE_RISING)>,
+ (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 14
- (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_EDGE_RISING)>,
+ (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 11
- (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_EDGE_RISING)>,
+ (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 10
- (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_EDGE_RISING)>;
+ (GIC_CPU_MASK_RAW(0xff) | IRQ_TYPE_LEVEL_LOW)>;
};
xtal: xtal-clk {
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 0 0xff01>, /* Secure Phys IRQ */
- <1 13 0xff01>, /* Non-secure Phys IRQ */
- <1 14 0xff01>, /* Virt IRQ */
- <1 15 0xff01>; /* Hyp IRQ */
+ interrupts = <1 0 0xff08>, /* Secure Phys IRQ */
+ <1 13 0xff08>, /* Non-secure Phys IRQ */
+ <1 14 0xff08>, /* Virt IRQ */
+ <1 15 0xff08>; /* Hyp IRQ */
clock-frequency = <50000000>;
};
--- /dev/null
+../../../../arm/boot/dts/bcm2835-rpi.dtsi
\ No newline at end of file
/dts-v1/;
#include "bcm2837.dtsi"
-#include "../../../../arm/boot/dts/bcm2835-rpi.dtsi"
-#include "../../../../arm/boot/dts/bcm283x-rpi-smsc9514.dtsi"
+#include "bcm2835-rpi.dtsi"
+#include "bcm283x-rpi-smsc9514.dtsi"
/ {
compatible = "raspberrypi,3-model-b", "brcm,bcm2837";
-#include "../../../../arm/boot/dts/bcm283x.dtsi"
+#include "bcm283x.dtsi"
/ {
compatible = "brcm,bcm2836";
--- /dev/null
+../../../../arm/boot/dts/bcm283x-rpi-smsc9514.dtsi
\ No newline at end of file
--- /dev/null
+../../../../arm/boot/dts/bcm283x.dtsi
\ No newline at end of file
timer {
compatible = "arm,armv8-timer";
interrupts = <GIC_PPI 13 (GIC_CPU_MASK_RAW(0xff) |
- IRQ_TYPE_EDGE_RISING)>,
+ IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 14 (GIC_CPU_MASK_RAW(0xff) |
- IRQ_TYPE_EDGE_RISING)>,
+ IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 11 (GIC_CPU_MASK_RAW(0xff) |
- IRQ_TYPE_EDGE_RISING)>,
+ IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 10 (GIC_CPU_MASK_RAW(0xff) |
- IRQ_TYPE_EDGE_RISING)>;
+ IRQ_TYPE_LEVEL_LOW)>;
};
pmu {
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 13 0xff01>,
- <1 14 0xff01>,
- <1 11 0xff01>,
- <1 10 0xff01>;
+ interrupts = <1 13 4>,
+ <1 14 4>,
+ <1 11 4>,
+ <1 10 4>;
};
pmu {
/dts-v1/;
#include "exynos7.dtsi"
#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/clock/samsung,s2mps11.h>
/ {
model = "Samsung Exynos7 Espresso board based on EXYNOS7";
&rtc {
status = "okay";
+ clocks = <&clock_ccore PCLK_RTC>, <&s2mps15_osc S2MPS11_CLK_AP>;
+ clock-names = "rtc", "rtc_src";
};
&watchdog {
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 13 0xff01>,
- <1 14 0xff01>,
- <1 11 0xff01>,
- <1 10 0xff01>;
+ interrupts = <1 13 0xff08>,
+ <1 14 0xff08>,
+ <1 11 0xff08>,
+ <1 10 0xff08>;
};
pmu_system_controller: system-controller@105c0000 {
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 13 0x1>, /* Physical Secure PPI */
- <1 14 0x1>, /* Physical Non-Secure PPI */
- <1 11 0x1>, /* Virtual PPI */
- <1 10 0x1>; /* Hypervisor PPI */
+ interrupts = <1 13 0xf08>, /* Physical Secure PPI */
+ <1 14 0xf08>, /* Physical Non-Secure PPI */
+ <1 11 0xf08>, /* Virtual PPI */
+ <1 10 0xf08>; /* Hypervisor PPI */
};
pmu {
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 13 0x8>, /* Physical Secure PPI, active-low */
- <1 14 0x8>, /* Physical Non-Secure PPI, active-low */
- <1 11 0x8>, /* Virtual PPI, active-low */
- <1 10 0x8>; /* Hypervisor PPI, active-low */
+ interrupts = <1 13 4>, /* Physical Secure PPI, active-low */
+ <1 14 4>, /* Physical Non-Secure PPI, active-low */
+ <1 11 4>, /* Virtual PPI, active-low */
+ <1 10 4>; /* Hypervisor PPI, active-low */
};
pmu {
timer {
compatible = "arm,armv8-timer";
- interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>,
- <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>,
- <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>,
- <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_EDGE_RISING)>;
+ interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+ <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+ <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>,
+ <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>;
};
odmi: odmi@300000 {
#io-channel-cells = <1>;
clocks = <&cru SCLK_SARADC>, <&cru PCLK_SARADC>;
clock-names = "saradc", "apb_pclk";
+ resets = <&cru SRST_SARADC>;
+ reset-names = "saradc-apb";
status = "disabled";
};
timer {
compatible = "arm,armv8-timer";
- interrupts = <1 13 0xf01>,
- <1 14 0xf01>,
- <1 11 0xf01>,
- <1 10 0xf01>;
+ interrupts = <1 13 4>,
+ <1 14 4>,
+ <1 11 4>,
+ <1 10 4>;
};
soc {
timer {
compatible = "arm,armv8-timer";
interrupt-parent = <&gic>;
- interrupts = <1 13 0xf01>,
- <1 14 0xf01>,
- <1 11 0xf01>,
- <1 10 0xf01>;
+ interrupts = <1 13 0xf08>,
+ <1 14 0xf08>,
+ <1 11 0xf08>,
+ <1 10 0xf08>;
};
amba_apu {
-# CONFIG_LOCALVERSION_AUTO is not set
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
CONFIG_AUDIT=y
CONFIG_LOG_BUF_SHIFT=14
CONFIG_MEMCG=y
CONFIG_MEMCG_SWAP=y
+CONFIG_BLK_CGROUP=y
+CONFIG_CGROUP_PIDS=y
CONFIG_CGROUP_HUGETLB=y
-# CONFIG_UTS_NS is not set
-# CONFIG_IPC_NS is not set
-# CONFIG_NET_NS is not set
+CONFIG_CPUSETS=y
+CONFIG_CGROUP_DEVICE=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_PERF=y
+CONFIG_USER_NS=y
CONFIG_SCHED_AUTOGROUP=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_KALLSYMS_ALL=y
CONFIG_KSM=y
CONFIG_TRANSPARENT_HUGEPAGE=y
CONFIG_CMA=y
+CONFIG_SECCOMP=y
CONFIG_XEN=y
CONFIG_KEXEC=y
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
CONFIG_PACKET=y
CONFIG_UNIX=y
CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_IP_PNP_BOOTP=y
-# CONFIG_IPV6 is not set
+CONFIG_IPV6=m
+CONFIG_NETFILTER=y
+CONFIG_NF_CONNTRACK=m
+CONFIG_NF_CONNTRACK_EVENTS=y
+CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
+CONFIG_NETFILTER_XT_TARGET_LOG=m
+CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m
+CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
+CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_IP_NF_IPTABLES=m
+CONFIG_IP_NF_FILTER=m
+CONFIG_IP_NF_TARGET_REJECT=m
+CONFIG_IP_NF_NAT=m
+CONFIG_IP_NF_TARGET_MASQUERADE=m
+CONFIG_IP_NF_MANGLE=m
+CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_IP6_NF_IPTABLES=m
+CONFIG_IP6_NF_FILTER=m
+CONFIG_IP6_NF_TARGET_REJECT=m
+CONFIG_IP6_NF_MANGLE=m
+CONFIG_IP6_NF_NAT=m
+CONFIG_IP6_NF_TARGET_MASQUERADE=m
+CONFIG_BRIDGE=m
+CONFIG_BRIDGE_VLAN_FILTERING=y
+CONFIG_VLAN_8021Q=m
+CONFIG_VLAN_8021Q_GVRP=y
+CONFIG_VLAN_8021Q_MVRP=y
CONFIG_BPF_JIT=y
CONFIG_CFG80211=m
CONFIG_MAC80211=m
CONFIG_MTD_M25P80=y
CONFIG_MTD_SPI_NOR=y
CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_NBD=m
CONFIG_VIRTIO_BLK=y
CONFIG_SRAM=y
# CONFIG_SCSI_PROC_FS is not set
CONFIG_PATA_PLATFORM=y
CONFIG_PATA_OF_PLATFORM=y
CONFIG_NETDEVICES=y
+CONFIG_MACVLAN=m
+CONFIG_MACVTAP=m
CONFIG_TUN=y
+CONFIG_VETH=m
CONFIG_VIRTIO_NET=y
CONFIG_AMD_XGBE=y
CONFIG_NET_XGENE=y
CONFIG_PWM_SAMSUNG=y
CONFIG_EXT2_FS=y
CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_BTRFS_FS=m
+CONFIG_BTRFS_FS_POSIX_ACL=y
CONFIG_FANOTIFY=y
CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
CONFIG_QUOTA=y
CONFIG_AUTOFS4_FS=y
-CONFIG_FUSE_FS=y
-CONFIG_CUSE=y
+CONFIG_FUSE_FS=m
+CONFIG_CUSE=m
+CONFIG_OVERLAY_FS=m
CONFIG_VFAT_FS=y
CONFIG_TMPFS=y
CONFIG_HUGETLBFS=y
err = blkcipher_walk_done(desc, &walk,
walk.nbytes % AES_BLOCK_SIZE);
}
- if (nbytes) {
+ if (walk.nbytes % AES_BLOCK_SIZE) {
u8 *tdst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
u8 *tsrc = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
u8 __aligned(8) tail[AES_BLOCK_SIZE];
#define AARCH64_BREAK_KGDB_DYN_DBG \
(AARCH64_BREAK_MON | (KGDB_DYN_DBG_BRK_IMM << 5))
-#define KGDB_DYN_BRK_INS_BYTE(x) \
- ((AARCH64_BREAK_KGDB_DYN_DBG >> (8 * (x))) & 0xff)
#define CACHE_FLUSH_IS_SAFE 1
#define __ARCH_WANT_KPROBES_INSN_SLOT
#define MAX_INSN_SIZE 1
-#define MAX_STACK_SIZE 128
#define flush_insn_slot(p) do { } while (0)
#define kretprobe_blacklist_size 0
struct prev_kprobe prev_kprobe;
struct kprobe_step_ctx ss_ctx;
struct pt_regs jprobe_saved_regs;
- char jprobes_stack[MAX_STACK_SIZE];
};
void arch_remove_kprobe(struct kprobe *);
#define _percpu_read(pcp) \
({ \
typeof(pcp) __retval; \
- preempt_disable(); \
+ preempt_disable_notrace(); \
__retval = (typeof(pcp))__percpu_read(raw_cpu_ptr(&(pcp)), \
sizeof(pcp)); \
- preempt_enable(); \
+ preempt_enable_notrace(); \
__retval; \
})
#define _percpu_write(pcp, val) \
do { \
- preempt_disable(); \
+ preempt_disable_notrace(); \
__percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), \
sizeof(pcp)); \
- preempt_enable(); \
+ preempt_enable_notrace(); \
} while(0) \
#define _pcp_protect(operation, pcp, val) \
#define arch_read_relax(lock) cpu_relax()
#define arch_write_relax(lock) cpu_relax()
+/*
+ * Accesses appearing in program order before a spin_lock() operation
+ * can be reordered with accesses inside the critical section, by virtue
+ * of arch_spin_lock being constructed using acquire semantics.
+ *
+ * In cases where this is problematic (e.g. try_to_wake_up), an
+ * smp_mb__before_spinlock() can restore the required ordering.
+ */
+#define smp_mb__before_spinlock() smp_mb()
+
#endif /* __ASM_SPINLOCK_H */
static inline unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n)
{
kasan_check_write(to, n);
- return __arch_copy_from_user(to, from, n);
+ check_object_size(to, n, false);
+ return __arch_copy_from_user(to, from, n);
}
static inline unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n)
{
kasan_check_read(from, n);
- return __arch_copy_to_user(to, from, n);
+ check_object_size(from, n, true);
+ return __arch_copy_to_user(to, from, n);
}
static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n)
{
kasan_check_write(to, n);
- if (access_ok(VERIFY_READ, from, n))
+ if (access_ok(VERIFY_READ, from, n)) {
+ check_object_size(to, n, false);
n = __arch_copy_from_user(to, from, n);
- else /* security hole - plug it */
+ } else /* security hole - plug it */
memset(to, 0, n);
return n;
}
{
kasan_check_read(from, n);
- if (access_ok(VERIFY_WRITE, to, n))
+ if (access_ok(VERIFY_WRITE, to, n)) {
+ check_object_size(from, n, true);
n = __arch_copy_to_user(to, from, n);
+ }
return n;
}
lsr x24, x1, #ESR_ELx_EC_SHIFT // exception class
cmp x24, #ESR_ELx_EC_DABT_CUR // data abort in EL1
b.eq el1_da
+ cmp x24, #ESR_ELx_EC_IABT_CUR // instruction abort in EL1
+ b.eq el1_ia
cmp x24, #ESR_ELx_EC_SYS64 // configurable trap
b.eq el1_undef
cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception
cmp x24, #ESR_ELx_EC_BREAKPT_CUR // debug exception in EL1
b.ge el1_dbg
b el1_inv
+
+el1_ia:
+ /*
+ * Fall through to the Data abort case
+ */
el1_da:
/*
* Data abort handling
isb
bl __create_page_tables // recreate kernel mapping
+ tlbi vmalle1 // Remove any stale TLB entries
+ dsb nsh
+
msr sctlr_el1, x19 // re-enable the MMU
isb
ic iallu // flush instructions fetched
#include <asm/sections.h>
#include <asm/smp.h>
#include <asm/suspend.h>
+#include <asm/sysreg.h>
#include <asm/virt.h>
/*
set_pte(pte, __pte(virt_to_phys((void *)dst) |
pgprot_val(PAGE_KERNEL_EXEC)));
- /* Load our new page tables */
- asm volatile("msr ttbr0_el1, %0;"
- "isb;"
- "tlbi vmalle1is;"
- "dsb ish;"
- "isb" : : "r"(virt_to_phys(pgd)));
+ /*
+ * Load our new page tables. A strict BBM approach requires that we
+ * ensure that TLBs are free of any entries that may overlap with the
+ * global mappings we are about to install.
+ *
+ * For a real hibernate/resume cycle TTBR0 currently points to a zero
+ * page, but TLBs may contain stale ASID-tagged entries (e.g. for EFI
+ * runtime services), while for a userspace-driven test_resume cycle it
+ * points to userspace page tables (and we must point it at a zero page
+ * ourselves). Elsewhere we only (un)install the idmap with preemption
+ * disabled, so T0SZ should be as required regardless.
+ */
+ cpu_set_reserved_ttbr0();
+ local_flush_tlb_all();
+ write_sysreg(virt_to_phys(pgd), ttbr0_el1);
+ isb();
*phys_dst_addr = virt_to_phys((void *)dst);
void __noreturn (*hibernate_exit)(phys_addr_t, phys_addr_t, void *,
void *, phys_addr_t, phys_addr_t);
+ /*
+ * Restoring the memory image will overwrite the ttbr1 page tables.
+ * Create a second copy of just the linear map, and use this when
+ * restoring.
+ */
+ tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC);
+ if (!tmp_pg_dir) {
+ pr_err("Failed to allocate memory for temporary page tables.");
+ rc = -ENOMEM;
+ goto out;
+ }
+ rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0);
+ if (rc)
+ goto out;
+
+ /*
+ * Since we only copied the linear map, we need to find restore_pblist's
+ * linear map address.
+ */
+ lm_restore_pblist = LMADDR(restore_pblist);
+
+ /*
+ * We need a zero page that is zero before & after resume in order to
+ * to break before make on the ttbr1 page tables.
+ */
+ zero_page = (void *)get_safe_page(GFP_ATOMIC);
+ if (!zero_page) {
+ pr_err("Failed to allocate zero page.");
+ rc = -ENOMEM;
+ goto out;
+ }
+
/*
* Locate the exit code in the bottom-but-one page, so that *NULL
* still has disastrous affects.
*/
__flush_dcache_area(hibernate_exit, exit_size);
- /*
- * Restoring the memory image will overwrite the ttbr1 page tables.
- * Create a second copy of just the linear map, and use this when
- * restoring.
- */
- tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC);
- if (!tmp_pg_dir) {
- pr_err("Failed to allocate memory for temporary page tables.");
- rc = -ENOMEM;
- goto out;
- }
- rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0);
- if (rc)
- goto out;
-
- /*
- * Since we only copied the linear map, we need to find restore_pblist's
- * linear map address.
- */
- lm_restore_pblist = LMADDR(restore_pblist);
-
/*
* KASLR will cause the el2 vectors to be in a different location in
* the resumed kernel. Load hibernate's temporary copy into el2.
__hyp_set_vectors(el2_vectors);
}
- /*
- * We need a zero page that is zero before & after resume in order to
- * to break before make on the ttbr1 page tables.
- */
- zero_page = (void *)get_safe_page(GFP_ATOMIC);
-
hibernate_exit(virt_to_phys(tmp_pg_dir), resume_hdr.ttbr1_el1,
resume_hdr.reenter_kernel, lm_restore_pblist,
resume_hdr.__hyp_stub_vectors, virt_to_phys(zero_page));
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/bug.h>
#include <linux/irq.h>
#include <linux/kdebug.h>
#include <linux/kgdb.h>
#include <linux/kprobes.h>
+#include <asm/debug-monitors.h>
+#include <asm/insn.h>
#include <asm/traps.h>
struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
unregister_die_notifier(&kgdb_notifier);
}
-/*
- * ARM instructions are always in LE.
- * Break instruction is encoded in LE format
- */
-struct kgdb_arch arch_kgdb_ops = {
- .gdb_bpt_instr = {
- KGDB_DYN_BRK_INS_BYTE(0),
- KGDB_DYN_BRK_INS_BYTE(1),
- KGDB_DYN_BRK_INS_BYTE(2),
- KGDB_DYN_BRK_INS_BYTE(3),
- }
-};
+struct kgdb_arch arch_kgdb_ops;
+
+int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
+{
+ int err;
+
+ BUILD_BUG_ON(AARCH64_INSN_SIZE != BREAK_INSTR_SIZE);
+
+ err = aarch64_insn_read((void *)bpt->bpt_addr, (u32 *)bpt->saved_instr);
+ if (err)
+ return err;
+
+ return aarch64_insn_write((void *)bpt->bpt_addr,
+ (u32)AARCH64_BREAK_KGDB_DYN_DBG);
+}
+
+int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
+{
+ return aarch64_insn_write((void *)bpt->bpt_addr,
+ *(u32 *)bpt->saved_instr);
+}
static void __kprobes
post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *);
-static inline unsigned long min_stack_size(unsigned long addr)
-{
- unsigned long size;
-
- if (on_irq_stack(addr, raw_smp_processor_id()))
- size = IRQ_STACK_PTR(raw_smp_processor_id()) - addr;
- else
- size = (unsigned long)current_thread_info() + THREAD_START_SP - addr;
-
- return min(size, FIELD_SIZEOF(struct kprobe_ctlblk, jprobes_stack));
-}
-
static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
{
/* prepare insn slot */
{
struct jprobe *jp = container_of(p, struct jprobe, kp);
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
- long stack_ptr = kernel_stack_pointer(regs);
kcb->jprobe_saved_regs = *regs;
/*
- * As Linus pointed out, gcc assumes that the callee
- * owns the argument space and could overwrite it, e.g.
- * tailcall optimization. So, to be absolutely safe
- * we also save and restore enough stack bytes to cover
- * the argument area.
+ * Since we can't be sure where in the stack frame "stacked"
+ * pass-by-value arguments are stored we just don't try to
+ * duplicate any of the stack. Do not use jprobes on functions that
+ * use more than 64 bytes (after padding each to an 8 byte boundary)
+ * of arguments, or pass individual arguments larger than 16 bytes.
*/
- kasan_disable_current();
- memcpy(kcb->jprobes_stack, (void *)stack_ptr,
- min_stack_size(stack_ptr));
- kasan_enable_current();
instruction_pointer_set(regs, (unsigned long) jp->entry);
preempt_disable();
}
unpause_graph_tracing();
*regs = kcb->jprobe_saved_regs;
- kasan_disable_current();
- memcpy((void *)stack_addr, kcb->jprobes_stack,
- min_stack_size(stack_addr));
- kasan_enable_current();
preempt_enable_no_resched();
return 1;
}
bl el2_setup // if in EL2 drop to EL1 cleanly
/* enable the MMU early - so we can access sleep_save_stash by va */
adr_l lr, __enable_mmu /* __cpu_setup will return here */
- ldr x27, =_cpu_resume /* __enable_mmu will branch here */
+ adr_l x27, _resume_switched /* __enable_mmu will branch here */
adrp x25, idmap_pg_dir
adrp x26, swapper_pg_dir
b __cpu_setup
ENDPROC(cpu_resume)
+ .pushsection ".idmap.text", "ax"
+_resume_switched:
+ ldr x8, =_cpu_resume
+ br x8
+ENDPROC(_resume_switched)
+ .ltorg
+ .popsection
+
ENTRY(_cpu_resume)
mrs x1, mpidr_el1
adrp x8, mpidr_hash
return ret;
}
-static void smp_store_cpu_info(unsigned int cpuid)
-{
- store_cpu_topology(cpuid);
- numa_store_cpu_info(cpuid);
-}
-
/*
* This is the secondary CPU boot entry. We're using this CPUs
* idle thread stack, but a set of temporary page tables.
*/
notify_cpu_starting(cpu);
- smp_store_cpu_info(cpu);
+ store_cpu_topology(cpu);
/*
* OK, now it's safe to let the boot CPU continue. Wait for
acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
acpi_parse_gic_cpu_interface, 0);
- if (cpu_count > NR_CPUS)
- pr_warn("no. of cores (%d) greater than configured maximum of %d - clipping\n",
- cpu_count, NR_CPUS);
+ if (cpu_count > nr_cpu_ids)
+ pr_warn("Number of cores (%d) exceeds configured maximum of %d - clipping\n",
+ cpu_count, nr_cpu_ids);
if (!bootcpu_valid) {
pr_err("missing boot CPU MPIDR, not enabling secondaries\n");
* with entries in cpu_logical_map while initializing the cpus.
* If the cpu set-up fails, invalidate the cpu_logical_map entry.
*/
- for (i = 1; i < NR_CPUS; i++) {
+ for (i = 1; i < nr_cpu_ids; i++) {
if (cpu_logical_map(i) != INVALID_HWID) {
if (smp_cpu_setup(i))
cpu_logical_map(i) = INVALID_HWID;
{
int err;
unsigned int cpu;
+ unsigned int this_cpu;
init_cpu_topology();
- smp_store_cpu_info(smp_processor_id());
+ this_cpu = smp_processor_id();
+ store_cpu_topology(this_cpu);
+ numa_store_cpu_info(this_cpu);
/*
* If UP is mandated by "nosmp" (which implies "maxcpus=0"), don't set
continue;
set_cpu_present(cpu, true);
+ numa_store_cpu_info(cpu);
}
}
/*
* We must restore the 32-bit state before the sysregs, thanks
- * to Cortex-A57 erratum #852523.
+ * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72).
*/
__sysreg32_restore_state(vcpu);
__sysreg_restore_guest_state(guest_ctxt);
* Architected system registers.
* Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
*
- * We could trap ID_DFR0 and tell the guest we don't support performance
- * monitoring. Unfortunately the patch to make the kernel check ID_DFR0 was
- * NAKed, so it will read the PMCR anyway.
- *
- * Therefore we tell the guest we have 0 counters. Unfortunately, we
- * must always support PMCCNTR (the cycle counter): we just RAZ/WI for
- * all PM registers, which doesn't crash the guest kernel at least.
- *
* Debug handling: We do trap most, if not all debug related system
* registers. The implementation is good enough to ensure that a guest
* can use these with minimal performance degradation. The drawback is
{ Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 },
/* ICC_SRE */
- { Op1( 0), CRn(12), CRm(12), Op2( 5), trap_raz_wi },
+ { Op1( 0), CRn(12), CRm(12), Op2( 5), access_gic_sre },
{ Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID },
static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start)
{
- pte_t *pte = pte_offset_kernel(pmd, 0);
+ pte_t *pte = pte_offset_kernel(pmd, 0UL);
unsigned long addr;
unsigned i;
static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
{
- pmd_t *pmd = pmd_offset(pud, 0);
+ pmd_t *pmd = pmd_offset(pud, 0UL);
unsigned long addr;
unsigned i;
static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
{
- pud_t *pud = pud_offset(pgd, 0);
+ pud_t *pud = pud_offset(pgd, 0UL);
unsigned long addr;
unsigned i;
}
#endif
+static bool is_el1_instruction_abort(unsigned int esr)
+{
+ return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR;
+}
+
/*
* The kernel tried to access some page that wasn't present.
*/
{
/*
* Are we prepared to handle this kernel fault?
+ * We are almost certainly not prepared to handle instruction faults.
*/
- if (fixup_exception(regs))
+ if (!is_el1_instruction_abort(esr) && fixup_exception(regs))
return;
/*
unsigned int ec = ESR_ELx_EC(esr);
unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE;
- return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM);
+ return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM) ||
+ (ec == ESR_ELx_EC_IABT_CUR && fsc_type == ESR_ELx_FSC_PERM);
}
static bool is_el0_instruction_abort(unsigned int esr)
if (regs->orig_addr_limit == KERNEL_DS)
die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
+ if (is_el1_instruction_abort(esr))
+ die("Attempting to execute userspace memory", regs, esr);
+
if (!search_exception_tables(regs->pc))
die("Accessing user space memory outside uaccess.h routines", regs, esr);
}
#include <linux/module.h>
#include <linux/of.h>
+#include <asm/acpi.h>
+
struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
EXPORT_SYMBOL(node_data);
nodemask_t numa_nodes_parsed __initdata;
msr tcr_el1, x8
msr vbar_el1, x9
+
+ /*
+ * __cpu_setup() cleared MDSCR_EL1.MDE and friends, before unmasking
+ * debug exceptions. By restoring MDSCR_EL1 here, we may take a debug
+ * exception. Mask them until local_dbg_restore() in cpu_suspend()
+ * resets them.
+ */
+ disable_dbg
msr mdscr_el1, x10
+
msr sctlr_el1, x12
/*
* Restore oslsr_el1 by writing oslar_el1
extern __kernel_size_t copy_to_user(void __user *to, const void *from,
__kernel_size_t n);
-extern __kernel_size_t copy_from_user(void *to, const void __user *from,
+extern __kernel_size_t ___copy_from_user(void *to, const void __user *from,
__kernel_size_t n);
static inline __kernel_size_t __copy_to_user(void __user *to, const void *from,
{
return __copy_user(to, (const void __force *)from, n);
}
+static inline __kernel_size_t copy_from_user(void *to,
+ const void __user *from,
+ __kernel_size_t n)
+{
+ size_t res = ___copy_from_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
+}
#define __copy_to_user_inatomic __copy_to_user
#define __copy_from_user_inatomic __copy_from_user
/*
* Userspace access stuff.
*/
-EXPORT_SYMBOL(copy_from_user);
+EXPORT_SYMBOL(___copy_from_user);
EXPORT_SYMBOL(copy_to_user);
EXPORT_SYMBOL(__copy_user);
EXPORT_SYMBOL(strncpy_from_user);
*/
.text
.align 1
- .global copy_from_user
- .type copy_from_user, @function
-copy_from_user:
+ .global ___copy_from_user
+ .type ___copy_from_user, @function
+___copy_from_user:
branch_if_kernel r8, __copy_user
ret_if_privileged r8, r11, r10, r10
rjmp __copy_user
- .size copy_from_user, . - copy_from_user
+ .size ___copy_from_user, . - ___copy_from_user
.global copy_to_user
.type copy_to_user, @function
static inline unsigned long __must_check
copy_from_user(void *to, const void __user *from, unsigned long n)
{
- if (access_ok(VERIFY_READ, from, n))
+ if (likely(access_ok(VERIFY_READ, from, n))) {
memcpy(to, (const void __force *)from, n);
- else
- return n;
- return 0;
+ return 0;
+ }
+ memset(to, 0, n);
+ return n;
}
static inline unsigned long __must_check
#include <linux/smc91x.h>
static struct smc91x_platdata smc91x_info = {
- .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+ .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+ SMC91X_NOWAIT,
.leda = RPC_LED_100_10,
.ledb = RPC_LED_TX_RX,
};
#include <linux/smc91x.h>
static struct smc91x_platdata smc91x_info = {
- .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT,
+ .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT |
+ SMC91X_NOWAIT,
.leda = RPC_LED_100_10,
.ledb = RPC_LED_TX_RX,
};
extern unsigned long __copy_user_zeroing(void *to, const void __user *from, unsigned long n);
extern unsigned long __do_clear_user(void __user *to, unsigned long n);
-static inline unsigned long
-__generic_copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- if (access_ok(VERIFY_WRITE, to, n))
- return __copy_user(to, from, n);
- return n;
-}
-
-static inline unsigned long
-__generic_copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- if (access_ok(VERIFY_READ, from, n))
- return __copy_user_zeroing(to, from, n);
- return n;
-}
-
-static inline unsigned long
-__generic_clear_user(void __user *to, unsigned long n)
-{
- if (access_ok(VERIFY_WRITE, to, n))
- return __do_clear_user(to, n);
- return n;
-}
-
static inline long
__strncpy_from_user(char *dst, const char __user *src, long count)
{
else if (n == 24)
__asm_copy_from_user_24(to, from, ret);
else
- ret = __generic_copy_from_user(to, from, n);
+ ret = __copy_user_zeroing(to, from, n);
return ret;
}
else if (n == 24)
__asm_copy_to_user_24(to, from, ret);
else
- ret = __generic_copy_to_user(to, from, n);
+ ret = __copy_user(to, from, n);
return ret;
}
else if (n == 24)
__asm_clear_24(to, ret);
else
- ret = __generic_clear_user(to, n);
+ ret = __do_clear_user(to, n);
return ret;
}
-#define clear_user(to, n) \
- (__builtin_constant_p(n) ? \
- __constant_clear_user(to, n) : \
- __generic_clear_user(to, n))
+static inline size_t clear_user(void __user *to, size_t n)
+{
+ if (unlikely(!access_ok(VERIFY_WRITE, to, n)))
+ return n;
+ if (__builtin_constant_p(n))
+ return __constant_clear_user(to, n);
+ else
+ return __do_clear_user(to, n);
+}
-#define copy_from_user(to, from, n) \
- (__builtin_constant_p(n) ? \
- __constant_copy_from_user(to, from, n) : \
- __generic_copy_from_user(to, from, n))
+static inline size_t copy_from_user(void *to, const void __user *from, size_t n)
+{
+ if (unlikely(!access_ok(VERIFY_READ, from, n))) {
+ memset(to, 0, n);
+ return n;
+ }
+ if (__builtin_constant_p(n))
+ return __constant_copy_from_user(to, from, n);
+ else
+ return __copy_user_zeroing(to, from, n);
+}
-#define copy_to_user(to, from, n) \
- (__builtin_constant_p(n) ? \
- __constant_copy_to_user(to, from, n) : \
- __generic_copy_to_user(to, from, n))
+static inline size_t copy_to_user(void __user *to, const void *from, size_t n)
+{
+ if (unlikely(!access_ok(VERIFY_WRITE, to, n)))
+ return n;
+ if (__builtin_constant_p(n))
+ return __constant_copy_to_user(to, from, n);
+ else
+ return __copy_user(to, from, n);
+}
/* We let the __ versions of copy_from/to_user inline, because they're often
* used in fast paths and have only a small space overhead.
extern long __memset_user(void *dst, unsigned long count);
extern long __memcpy_user(void *dst, const void *src, unsigned long count);
-#define clear_user(dst,count) __memset_user(____force(dst), (count))
+#define __clear_user(dst,count) __memset_user(____force(dst), (count))
#define __copy_from_user_inatomic(to, from, n) __memcpy_user((to), ____force(from), (n))
#define __copy_to_user_inatomic(to, from, n) __memcpy_user(____force(to), (from), (n))
#else
-#define clear_user(dst,count) (memset(____force(dst), 0, (count)), 0)
+#define __clear_user(dst,count) (memset(____force(dst), 0, (count)), 0)
#define __copy_from_user_inatomic(to, from, n) (memcpy((to), ____force(from), (n)), 0)
#define __copy_to_user_inatomic(to, from, n) (memcpy(____force(to), (from), (n)), 0)
#endif
-#define __clear_user clear_user
+static inline unsigned long __must_check
+clear_user(void __user *to, unsigned long n)
+{
+ if (likely(__access_ok(to, n)))
+ n = __clear_user(to, n);
+ return n;
+}
static inline unsigned long __must_check
__copy_to_user(void __user *to, const void *from, unsigned long n)
#ifdef __KERNEL__
+#include <linux/types.h>
+
/* H8/300 internal I/O functions */
#define __raw_readb __raw_readb
{
long res = __strnlen_user(src, n);
- /* return from strnlen can't be zero -- that would be rubbish. */
+ if (unlikely(!res))
+ return -EFAULT;
if (res > n) {
copy_from_user(dst, src, n);
select MODULES_USE_ELF_RELA
select ARCH_USE_CMPXCHG_LOCKREF
select HAVE_ARCH_AUDITSYSCALL
+ select HAVE_ARCH_HARDENED_USERCOPY
default y
help
The Itanium Processor Family is Intel's 64-bit successor to
static inline unsigned long
__copy_to_user (void __user *to, const void *from, unsigned long count)
{
+ check_object_size(from, count, true);
+
return __copy_user(to, (__force void __user *) from, count);
}
static inline unsigned long
__copy_from_user (void *to, const void __user *from, unsigned long count)
{
+ check_object_size(to, count, false);
+
return __copy_user((__force void __user *) to, from, count);
}
const void *__cu_from = (from); \
long __cu_len = (n); \
\
- if (__access_ok(__cu_to, __cu_len, get_fs())) \
- __cu_len = __copy_user(__cu_to, (__force void __user *) __cu_from, __cu_len); \
+ if (__access_ok(__cu_to, __cu_len, get_fs())) { \
+ check_object_size(__cu_from, __cu_len, true); \
+ __cu_len = __copy_user(__cu_to, (__force void __user *) __cu_from, __cu_len); \
+ } \
__cu_len; \
})
-#define copy_from_user(to, from, n) \
-({ \
- void *__cu_to = (to); \
- const void __user *__cu_from = (from); \
- long __cu_len = (n); \
- \
- __chk_user_ptr(__cu_from); \
- if (__access_ok(__cu_from, __cu_len, get_fs())) \
- __cu_len = __copy_user((__force void __user *) __cu_to, __cu_from, __cu_len); \
- __cu_len; \
-})
+static inline unsigned long
+copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+ check_object_size(to, n, false);
+ if (likely(__access_ok(from, n, get_fs())))
+ n = __copy_user((__force void __user *) to, from, n);
+ else
+ memset(to, 0, n);
+ return n;
+}
#define __copy_in_user(to, from, size) __copy_user((to), (from), (size))
#define __get_user_nocheck(x, ptr, size) \
({ \
long __gu_err = 0; \
- unsigned long __gu_val; \
+ unsigned long __gu_val = 0; \
might_fault(); \
__get_user_size(__gu_val, (ptr), (size), __gu_err); \
(x) = (__force __typeof__(*(ptr)))__gu_val; \
static inline void adjustformat(struct pt_regs *regs)
{
- ((struct switch_stack *)regs - 1)->a5 = current->mm->start_data;
/*
* set format byte to make stack appear modulo 4, which it will
* be when doing the rte
static inline unsigned long
copy_from_user(void *to, const void __user *from, unsigned long n)
{
- if (access_ok(VERIFY_READ, from, n))
+ if (likely(access_ok(VERIFY_READ, from, n)))
return __copy_user_zeroing(to, from, n);
+ memset(to, 0, n);
return n;
}
free_all_bootmem();
mem_init_print_info(NULL);
- show_mem(0);
}
void free_initmem(void)
#define __get_user(x, ptr) \
({ \
- unsigned long __gu_val; \
+ unsigned long __gu_val = 0; \
/*unsigned long __gu_ptr = (unsigned long)(ptr);*/ \
long __gu_err; \
switch (sizeof(*(ptr))) { \
static inline long copy_from_user(void *to,
const void __user *from, unsigned long n)
{
+ unsigned long res = n;
might_fault();
- if (access_ok(VERIFY_READ, from, n))
- return __copy_from_user(to, from, n);
- return n;
+ if (likely(access_ok(VERIFY_READ, from, n)))
+ res = __copy_from_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
}
#define __copy_to_user(to, from, n) \
select ARCH_CLOCKSOURCE_DATA
select HANDLE_DOMAIN_IRQ
select HAVE_EXIT_THREAD
+ select HAVE_REGS_AND_STACK_ACCESS_API
menu "Machine selection"
help
Add several files to the debugfs to test spinlock speed.
-if CPU_MIPSR6
-
-choice
- prompt "Compact branch policy"
- default MIPS_COMPACT_BRANCHES_OPTIMAL
-
-config MIPS_COMPACT_BRANCHES_NEVER
- bool "Never (force delay slot branches)"
- help
- Pass the -mcompact-branches=never flag to the compiler in order to
- force it to always emit branches with delay slots, and make no use
- of the compact branch instructions introduced by MIPSr6. This is
- useful if you suspect there may be an issue with compact branches in
- either the compiler or the CPU.
-
-config MIPS_COMPACT_BRANCHES_OPTIMAL
- bool "Optimal (use where beneficial)"
- help
- Pass the -mcompact-branches=optimal flag to the compiler in order for
- it to make use of compact branch instructions where it deems them
- beneficial, and use branches with delay slots elsewhere. This is the
- default compiler behaviour, and should be used unless you have a
- reason to choose otherwise.
-
-config MIPS_COMPACT_BRANCHES_ALWAYS
- bool "Always (force compact branches)"
- help
- Pass the -mcompact-branches=always flag to the compiler in order to
- force it to always emit compact branches, making no use of branch
- instructions with delay slots. This can result in more compact code
- which may be beneficial in some scenarios.
-
-endchoice
-
-endif # CPU_MIPSR6
-
config SCACHE_DEBUGFS
bool "L2 cache debugfs entries"
depends on DEBUG_FS
toolchain-virt := $(call cc-option-yn,$(mips-cflags) -mvirt)
cflags-$(toolchain-virt) += -DTOOLCHAIN_SUPPORTS_VIRT
-cflags-$(CONFIG_MIPS_COMPACT_BRANCHES_NEVER) += -mcompact-branches=never
-cflags-$(CONFIG_MIPS_COMPACT_BRANCHES_OPTIMAL) += -mcompact-branches=optimal
-cflags-$(CONFIG_MIPS_COMPACT_BRANCHES_ALWAYS) += -mcompact-branches=always
-
#
# Firmware support
#
struct clk *clk;
clk = clk_register_fixed_factor(NULL, name, parent_name, 0, mult, div);
- if (!clk)
+ if (IS_ERR(clk))
panic("failed to allocate %s clock structure", name);
return clk;
{
return of_platform_bus_probe(NULL, octeon_ids, NULL);
}
-device_initcall(octeon_publish_devices);
+arch_initcall(octeon_publish_devices);
MODULE_AUTHOR("David Daney <ddaney@caviumnetworks.com>");
MODULE_LICENSE("GPL");
ldc1 $f28, THREAD_FPR28(\thread)
ldc1 $f30, THREAD_FPR30(\thread)
ctc1 \tmp, fcr31
+ .set pop
.endm
.macro fpu_restore_16odd thread
static inline bool __should_swizzle_bits(volatile void *a)
{
extern const bool octeon_should_swizzle_table[];
+ u64 did = ((u64)(uintptr_t)a >> 40) & 0xff;
- unsigned long did = ((unsigned long)a >> 40) & 0xff;
return octeon_should_swizzle_table[did];
}
#define __should_swizzle_bits(a) false
-static inline bool __should_swizzle_addr(unsigned long p)
+static inline bool __should_swizzle_addr(u64 p)
{
/* boot bus? */
return ((p >> 40) & 0xff) == 0;
#define CP0_EBASE $15, 1
.macro kernel_entry_setup
+#ifdef CONFIG_SMP
mfc0 t0, CP0_EBASE
andi t0, t0, 0x3ff # CPUNum
beqz t0, 1f
# CPUs other than zero goto smp_bootstrap
j smp_bootstrap
+#endif /* CONFIG_SMP */
1:
.endm
*/
static inline unsigned long ___pa(unsigned long x)
{
- if (config_enabled(CONFIG_64BIT)) {
+ if (IS_ENABLED(CONFIG_64BIT)) {
/*
* For MIPS64 the virtual address may either be in one of
* the compatibility segements ckseg0 or ckseg1, or it may
return x < CKSEG0 ? XPHYSADDR(x) : CPHYSADDR(x);
}
- if (!config_enabled(CONFIG_EVA)) {
+ if (!IS_ENABLED(CONFIG_EVA)) {
/*
* We're using the standard MIPS32 legacy memory map, ie.
* the address x is going to be in kseg0 or kseg1. We can
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/thread_info.h>
+#include <linux/string.h>
#include <asm/asm-eva.h>
/*
__cu_len = __invoke_copy_from_user(__cu_to, \
__cu_from, \
__cu_len); \
+ } else { \
+ memset(__cu_to, 0, __cu_len); \
} \
} \
__cu_len; \
regs->regs[31] = r31;
regs->cp0_epc = epc;
if (!used_math()) { /* First time FPU user. */
+ preempt_disable();
err = init_fpu();
+ preempt_enable();
set_used_math();
}
lose_fpu(1); /* Save FPU state for the emulator. */
return -EOPNOTSUPP;
/* Avoid inadvertently triggering emulation */
- if ((value & PR_FP_MODE_FR) && cpu_has_fpu &&
- !(current_cpu_data.fpu_id & MIPS_FPIR_F64))
+ if ((value & PR_FP_MODE_FR) && raw_cpu_has_fpu &&
+ !(raw_current_cpu_data.fpu_id & MIPS_FPIR_F64))
return -EOPNOTSUPP;
- if ((value & PR_FP_MODE_FRE) && cpu_has_fpu && !cpu_has_fre)
+ if ((value & PR_FP_MODE_FRE) && raw_cpu_has_fpu && !cpu_has_fre)
return -EOPNOTSUPP;
/* FR = 0 not supported in MIPS R6 */
- if (!(value & PR_FP_MODE_FR) && cpu_has_fpu && cpu_has_mips_r6)
+ if (!(value & PR_FP_MODE_FR) && raw_cpu_has_fpu && cpu_has_mips_r6)
return -EOPNOTSUPP;
/* Proceed with the mode switch */
int x = boot_mem_map.nr_map;
int i;
+ /*
+ * If the region reaches the top of the physical address space, adjust
+ * the size slightly so that (start + size) doesn't overflow
+ */
+ if (start + size - 1 == (phys_addr_t)ULLONG_MAX)
+ --size;
+
/* Sanity check */
if (start + size < start) {
pr_warn("Trying to add an invalid memory region, skipped\n");
cpumask_set_cpu(cpu, &cpu_coherent_mask);
notify_cpu_starting(cpu);
+ cpumask_set_cpu(cpu, &cpu_callin_map);
+ synchronise_count_slave(cpu);
+
set_cpu_online(cpu, true);
set_cpu_sibling_map(cpu);
calculate_cpu_foreign_map();
- cpumask_set_cpu(cpu, &cpu_callin_map);
-
- synchronise_count_slave(cpu);
-
/*
* irq will be enabled in ->smp_finish(), enabling it too early
* is dangerous.
return NOTIFY_DONE;
switch (val) {
- case DIE_BREAK:
+ case DIE_UPROBE:
if (uprobe_pre_sstep_notifier(regs))
return NOTIFY_STOP;
break;
static void __init init_vdso_image(struct mips_vdso_image *image)
{
unsigned long num_pages, i;
+ unsigned long data_pfn;
BUG_ON(!PAGE_ALIGNED(image->data));
BUG_ON(!PAGE_ALIGNED(image->size));
num_pages = image->size / PAGE_SIZE;
- for (i = 0; i < num_pages; i++) {
- image->mapping.pages[i] =
- virt_to_page(image->data + (i * PAGE_SIZE));
- }
+ data_pfn = __phys_to_pfn(__pa_symbol(image->data));
+ for (i = 0; i < num_pages; i++)
+ image->mapping.pages[i] = pfn_to_page(data_pfn + i);
}
static int __init init_vdso(void)
preempt_disable();
if (KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG0) {
- if (kvm_mips_host_tlb_lookup(vcpu, va) < 0)
- kvm_mips_handle_kseg0_tlb_fault(va, vcpu);
+ if (kvm_mips_host_tlb_lookup(vcpu, va) < 0 &&
+ kvm_mips_handle_kseg0_tlb_fault(va, vcpu)) {
+ kvm_err("%s: handling mapped kseg0 tlb fault for %lx, vcpu: %p, ASID: %#lx\n",
+ __func__, va, vcpu, read_c0_entryhi());
+ er = EMULATE_FAIL;
+ preempt_enable();
+ goto done;
+ }
} else if ((KVM_GUEST_KSEGX(va) < KVM_GUEST_KSEG0) ||
KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG23) {
int index;
run, vcpu);
preempt_enable();
goto dont_update_pc;
- } else {
- /*
- * We fault an entry from the guest tlb to the
- * shadow host TLB
- */
- kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb);
+ }
+ /*
+ * We fault an entry from the guest tlb to the
+ * shadow host TLB
+ */
+ if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb)) {
+ kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n",
+ __func__, va, index, vcpu,
+ read_c0_entryhi());
+ er = EMULATE_FAIL;
+ preempt_enable();
+ goto done;
}
}
} else {
* OK we have a Guest TLB entry, now inject it into the
* shadow host TLB
*/
- kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb);
+ if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb)) {
+ kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n",
+ __func__, va, index, vcpu,
+ read_c0_entryhi());
+ er = EMULATE_FAIL;
+ }
}
}
srcu_idx = srcu_read_lock(&kvm->srcu);
pfn = gfn_to_pfn(kvm, gfn);
- if (is_error_pfn(pfn)) {
+ if (is_error_noslot_pfn(pfn)) {
kvm_err("Couldn't get pfn for gfn %#llx!\n", gfn);
err = -EFAULT;
goto out;
}
gfn = (KVM_GUEST_CPHYSADDR(badvaddr) >> PAGE_SHIFT);
- if (gfn >= kvm->arch.guest_pmap_npages) {
+ if ((gfn | 1) >= kvm->arch.guest_pmap_npages) {
kvm_err("%s: Invalid gfn: %#llx, BadVaddr: %#lx\n", __func__,
gfn, badvaddr);
kvm_mips_dump_host_tlbs();
unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0;
struct kvm *kvm = vcpu->kvm;
kvm_pfn_t pfn0, pfn1;
+ gfn_t gfn0, gfn1;
+ long tlb_lo[2];
int ret;
- if ((tlb->tlb_hi & VPN2_MASK) == 0) {
- pfn0 = 0;
- pfn1 = 0;
- } else {
- if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo[0])
- >> PAGE_SHIFT) < 0)
- return -1;
-
- if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo[1])
- >> PAGE_SHIFT) < 0)
- return -1;
-
- pfn0 = kvm->arch.guest_pmap[
- mips3_tlbpfn_to_paddr(tlb->tlb_lo[0]) >> PAGE_SHIFT];
- pfn1 = kvm->arch.guest_pmap[
- mips3_tlbpfn_to_paddr(tlb->tlb_lo[1]) >> PAGE_SHIFT];
+ tlb_lo[0] = tlb->tlb_lo[0];
+ tlb_lo[1] = tlb->tlb_lo[1];
+
+ /*
+ * The commpage address must not be mapped to anything else if the guest
+ * TLB contains entries nearby, or commpage accesses will break.
+ */
+ if (!((tlb->tlb_hi ^ KVM_GUEST_COMMPAGE_ADDR) &
+ VPN2_MASK & (PAGE_MASK << 1)))
+ tlb_lo[(KVM_GUEST_COMMPAGE_ADDR >> PAGE_SHIFT) & 1] = 0;
+
+ gfn0 = mips3_tlbpfn_to_paddr(tlb_lo[0]) >> PAGE_SHIFT;
+ gfn1 = mips3_tlbpfn_to_paddr(tlb_lo[1]) >> PAGE_SHIFT;
+ if (gfn0 >= kvm->arch.guest_pmap_npages ||
+ gfn1 >= kvm->arch.guest_pmap_npages) {
+ kvm_err("%s: Invalid gfn: [%#llx, %#llx], EHi: %#lx\n",
+ __func__, gfn0, gfn1, tlb->tlb_hi);
+ kvm_mips_dump_guest_tlbs(vcpu);
+ return -1;
}
+ if (kvm_mips_map_page(kvm, gfn0) < 0)
+ return -1;
+
+ if (kvm_mips_map_page(kvm, gfn1) < 0)
+ return -1;
+
+ pfn0 = kvm->arch.guest_pmap[gfn0];
+ pfn1 = kvm->arch.guest_pmap[gfn1];
+
/* Get attributes from the Guest TLB */
entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) |
((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) |
- (tlb->tlb_lo[0] & ENTRYLO_D) |
- (tlb->tlb_lo[0] & ENTRYLO_V);
+ (tlb_lo[0] & ENTRYLO_D) |
+ (tlb_lo[0] & ENTRYLO_V);
entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) |
((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) |
- (tlb->tlb_lo[1] & ENTRYLO_D) |
- (tlb->tlb_lo[1] & ENTRYLO_V);
+ (tlb_lo[1] & ENTRYLO_D) |
+ (tlb_lo[1] & ENTRYLO_V);
kvm_debug("@ %#lx tlb_lo0: 0x%08lx tlb_lo1: 0x%08lx\n", vcpu->arch.pc,
tlb->tlb_lo[0], tlb->tlb_lo[1]);
local_irq_restore(flags);
return KVM_INVALID_INST;
}
- kvm_mips_handle_mapped_seg_tlb_fault(vcpu,
- &vcpu->arch.
- guest_tlb[index]);
+ if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu,
+ &vcpu->arch.guest_tlb[index])) {
+ kvm_err("%s: handling mapped seg tlb fault failed for %p, index: %u, vcpu: %p, ASID: %#lx\n",
+ __func__, opc, index, vcpu,
+ read_c0_entryhi());
+ kvm_mips_dump_guest_tlbs(vcpu);
+ local_irq_restore(flags);
+ return KVM_INVALID_INST;
+ }
inst = *(opc);
}
local_irq_restore(flags);
/* Set EPC to return to post-branch instruction */
xcp->cp0_epc = current->thread.bd_emu_cont_pc;
pr_debug("dsemulret to 0x%08lx\n", xcp->cp0_epc);
+ MIPS_FPU_EMU_INC_STATS(ds_emul);
return true;
}
* If address-based cache ops don't require an SMP call, then
* use them exclusively for small flushes.
*/
- size = start - end;
+ size = end - start;
cache_size = icache_size;
if (!cpu_has_ic_fills_f_dc) {
size *= 2;
{
struct maar_config cfg[BOOT_MEM_MAP_MAX];
unsigned i, num_configured, num_cfg = 0;
- phys_addr_t skip;
for (i = 0; i < boot_mem_map.nr_map; i++) {
switch (boot_mem_map.map[i].type) {
continue;
}
- skip = 0x10000 - (boot_mem_map.map[i].addr & 0xffff);
-
+ /* Round lower up */
cfg[num_cfg].lower = boot_mem_map.map[i].addr;
- cfg[num_cfg].lower += skip;
+ cfg[num_cfg].lower = (cfg[num_cfg].lower + 0xffff) & ~0xffff;
- cfg[num_cfg].upper = cfg[num_cfg].lower;
- cfg[num_cfg].upper += boot_mem_map.map[i].size - 1;
- cfg[num_cfg].upper -= skip;
+ /* Round upper down */
+ cfg[num_cfg].upper = boot_mem_map.map[i].addr +
+ boot_mem_map.map[i].size;
+ cfg[num_cfg].upper = (cfg[num_cfg].upper & ~0xffff) - 1;
cfg[num_cfg].attrs = MIPS_MAAR_S;
num_cfg++;
"2:\n" \
" .section .fixup,\"ax\"\n" \
"3:\n\t" \
+ " mov 0,%1\n" \
" mov %3,%0\n" \
" jmp 2b\n" \
" .previous\n" \
* as published by the Free Software Foundation; either version
* 2 of the Licence, or (at your option) any later version.
*/
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
unsigned long
__generic_copy_to_user(void *to, const void *from, unsigned long n)
{
if (access_ok(VERIFY_READ, from, n))
__copy_user_zeroing(to, from, n);
+ else
+ memset(to, 0, n);
return n;
}
static inline long copy_from_user(void *to, const void __user *from,
unsigned long n)
{
- if (!access_ok(VERIFY_READ, from, n))
- return n;
- return __copy_from_user(to, from, n);
+ unsigned long res = n;
+ if (access_ok(VERIFY_READ, from, n))
+ res = __copy_from_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
}
static inline long copy_to_user(void __user *to, const void *from,
#define __get_user_unknown(val, size, ptr, err) do { \
err = 0; \
- if (copy_from_user(&(val), ptr, size)) { \
+ if (__copy_from_user(&(val), ptr, size)) { \
err = -EFAULT; \
} \
} while (0)
({ \
long __gu_err = -EFAULT; \
const __typeof__(*(ptr)) __user *__gu_ptr = (ptr); \
- unsigned long __gu_val; \
+ unsigned long __gu_val = 0; \
__get_user_common(__gu_val, sizeof(*(ptr)), __gu_ptr, __gu_err);\
(x) = (__force __typeof__(x))__gu_val; \
__gu_err; \
static inline unsigned long
copy_from_user(void *to, const void *from, unsigned long n)
{
- unsigned long over;
-
- if (access_ok(VERIFY_READ, from, n))
- return __copy_tofrom_user(to, from, n);
- if ((unsigned long)from < TASK_SIZE) {
- over = (unsigned long)from + n - TASK_SIZE;
- return __copy_tofrom_user(to, from, n - over) + over;
- }
- return n;
+ unsigned long res = n;
+
+ if (likely(access_ok(VERIFY_READ, from, n)))
+ res = __copy_tofrom_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
}
static inline unsigned long
copy_to_user(void *to, const void *from, unsigned long n)
{
- unsigned long over;
-
- if (access_ok(VERIFY_WRITE, to, n))
- return __copy_tofrom_user(to, from, n);
- if ((unsigned long)to < TASK_SIZE) {
- over = (unsigned long)to + n - TASK_SIZE;
- return __copy_tofrom_user(to, from, n - over) + over;
- }
+ if (likely(access_ok(VERIFY_WRITE, to, n)))
+ n = __copy_tofrom_user(to, from, n);
return n;
}
static inline __must_check unsigned long
clear_user(void *addr, unsigned long size)
{
-
- if (access_ok(VERIFY_WRITE, addr, size))
- return __clear_user(addr, size);
- if ((unsigned long)addr < TASK_SIZE) {
- unsigned long over = (unsigned long)addr + size - TASK_SIZE;
- return __clear_user(addr, size - over) + over;
- }
+ if (likely(access_ok(VERIFY_WRITE, addr, size)))
+ size = __clear_user(addr, size);
return size;
}
config PARISC
def_bool y
- select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
select ARCH_MIGHT_HAVE_PC_PARPORT
select HAVE_IDE
select HAVE_OPROFILE
CONFIG_PROVE_RCU_DELAY=y
CONFIG_DEBUG_BLOCK_EXT_DEVT=y
CONFIG_LATENCYTOP=y
-CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
CONFIG_KEYS=y
# CONFIG_CRYPTO_HW is not set
CONFIG_FONTS=y
CONFIG_BOOTPARAM_HUNG_TASK_PANIC=y
# CONFIG_SCHED_DEBUG is not set
CONFIG_TIMER_STATS=y
-CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
CONFIG_CRYPTO_MANAGER=y
CONFIG_CRYPTO_ECB=m
CONFIG_CRYPTO_PCBC=m
#include <asm-generic/uaccess-unaligned.h>
#include <linux/bug.h>
+#include <linux/string.h>
#define VERIFY_READ 0
#define VERIFY_WRITE 1
#define __copy_to_user_inatomic __copy_to_user
#define __copy_from_user_inatomic __copy_from_user
-extern void copy_from_user_overflow(void)
-#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
- __compiletime_error("copy_from_user() buffer size is not provably correct")
-#else
- __compiletime_warning("copy_from_user() buffer size is not provably correct")
-#endif
-;
+extern void __compiletime_error("usercopy buffer size is too small")
+__bad_copy_user(void);
+
+static inline void copy_user_overflow(int size, unsigned long count)
+{
+ WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
+}
static inline unsigned long __must_check copy_from_user(void *to,
const void __user *from,
unsigned long n)
{
int sz = __compiletime_object_size(to);
- int ret = -EFAULT;
+ unsigned long ret = n;
- if (likely(sz == -1 || !__builtin_constant_p(n) || sz >= n))
+ if (likely(sz == -1 || sz >= n))
ret = __copy_from_user(to, from, n);
- else
- copy_from_user_overflow();
+ else if (!__builtin_constant_p(n))
+ copy_user_overflow(sz, n);
+ else
+ __bad_copy_user();
+ if (unlikely(ret))
+ memset(to + (n - ret), 0, ret);
return ret;
}
#define ENOTCONN 235 /* Transport endpoint is not connected */
#define ESHUTDOWN 236 /* Cannot send after transport endpoint shutdown */
#define ETOOMANYREFS 237 /* Too many references: cannot splice */
-#define EREFUSED ECONNREFUSED /* for HP's NFS apparently */
#define ETIMEDOUT 238 /* Connection timed out */
#define ECONNREFUSED 239 /* Connection refused */
-#define EREMOTERELEASE 240 /* Remote peer released connection */
+#define EREFUSED ECONNREFUSED /* for HP's NFS apparently */
+#define EREMOTERELEASE 240 /* Remote peer released connection */
#define EHOSTDOWN 241 /* Host is down */
#define EHOSTUNREACH 242 /* No route to host */
DEFINE_PER_CPU(struct cpuinfo_parisc, cpu_data);
-extern int update_cr16_clocksource(void); /* from time.c */
-
/*
** PARISC CPU driver - claim "device" and initialize CPU data structures.
**
}
#endif
- /* If we've registered more than one cpu,
- * we'll use the jiffies clocksource since cr16
- * is not synchronized between CPUs.
- */
- update_cr16_clocksource();
-
return 0;
}
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
-int update_cr16_clocksource(void)
-{
- /* since the cr16 cycle counters are not synchronized across CPUs,
- we'll check if we should switch to a safe clocksource: */
- if (clocksource_cr16.rating != 0 && num_online_cpus() > 1) {
- clocksource_change_rating(&clocksource_cr16, 0);
- return 1;
- }
-
- return 0;
-}
-
void __init start_cpu_itimer(void)
{
unsigned int cpu = smp_processor_id();
select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS
select GENERIC_CPU_AUTOPROBE
select HAVE_VIRT_CPU_ACCOUNTING
+ select HAVE_ARCH_HARDENED_USERCOPY
config GENERIC_CSUM
def_bool CPU_LITTLE_ENDIAN
UTS_MACHINE := $(OLDARCH)
ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y)
-override CC += -mlittle-endian
-ifneq ($(cc-name),clang)
-override CC += -mno-strict-align
-endif
-override AS += -mlittle-endian
override LD += -EL
-override CROSS32CC += -mlittle-endian
override CROSS32AS += -mlittle-endian
LDEMULATION := lppc
GNUTARGET := powerpcle
MULTIPLEWORD := -mno-multiple
KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-save-toc-indirect)
else
-ifeq ($(call cc-option-yn,-mbig-endian),y)
-override CC += -mbig-endian
-override AS += -mbig-endian
-endif
override LD += -EB
LDEMULATION := ppc
GNUTARGET := powerpc
MULTIPLEWORD := -mmultiple
endif
+cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mbig-endian)
+cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mlittle-endian
+ifneq ($(cc-name),clang)
+ cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mno-strict-align
+endif
+
+aflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mbig-endian)
+aflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mlittle-endian
+
ifeq ($(HAS_BIARCH),y)
override AS += -a$(CONFIG_WORD_SIZE)
override LD += -m elf$(CONFIG_WORD_SIZE)$(LDEMULATION)
KBUILD_AFLAGS += $(cpu-as-y)
KBUILD_CFLAGS += $(cpu-as-y)
+KBUILD_AFLAGS += $(aflags-y)
+KBUILD_CFLAGS += $(cflags-y)
+
head-y := arch/powerpc/kernel/head_$(CONFIG_WORD_SIZE).o
head-$(CONFIG_8xx) := arch/powerpc/kernel/head_8xx.o
head-$(CONFIG_40x) := arch/powerpc/kernel/head_40x.o
#include <linux/module.h>
#include <linux/string.h>
#include <linux/kernel.h>
+#include <linux/cpufeature.h>
#include <asm/switch_to.h>
#define CHKSUM_BLOCK_SIZE 1
crypto_unregister_shash(&alg);
}
-module_init(crc32c_vpmsum_mod_init);
+module_cpu_feature_match(PPC_MODULE_FEATURE_VEC_CRYPTO, crc32c_vpmsum_mod_init);
module_exit(crc32c_vpmsum_mod_fini);
MODULE_AUTHOR("Anton Blanchard <anton@samba.org>");
#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECKS
#include <linux/jump_label.h>
-#define NUM_CPU_FTR_KEYS 64
+#define NUM_CPU_FTR_KEYS BITS_PER_LONG
extern struct static_key_true cpu_feature_keys[NUM_CPU_FTR_KEYS];
#endif
+/* Idle state entry routines */
+#ifdef CONFIG_PPC_P7_NAP
+#define IDLE_STATE_ENTER_SEQ(IDLE_INST) \
+ /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \
+ std r0,0(r1); \
+ ptesync; \
+ ld r0,0(r1); \
+1: cmp cr0,r0,r0; \
+ bne 1b; \
+ IDLE_INST; \
+ b .
+#endif /* CONFIG_PPC_P7_NAP */
+
#endif
#ifndef __ASSEMBLY__
#include <linux/cpumask.h>
+#include <asm/cpu_has_feature.h>
/*
* Mapping of threads to cores
#ifndef __ASSEMBLY__
void apply_feature_fixups(void);
+void setup_feature_keys(void);
#endif
#endif /* __ASM_POWERPC_FEATURE_FIXUPS_H */
#ifndef __ASM_PPC64_HMI_H__
#define __ASM_PPC64_HMI_H__
-#ifdef CONFIG_PPC_BOOK3S_64
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
#define CORE_TB_RESYNC_REQ_BIT 63
#define MAX_SUBCORE_PER_CORE 4
*/
u16 in_mce;
u8 hmi_event_available; /* HMI event is available */
- /*
- * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for
- * more details
- */
- struct sibling_subcore_state *sibling_subcore_state;
#endif
/* Stuff for accurate time accounting */
struct kvmppc_book3s_shadow_vcpu shadow_vcpu;
#endif
struct kvmppc_host_state kvm_hstate;
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+ /*
+ * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for
+ * more details
+ */
+ struct sibling_subcore_state *sibling_subcore_state;
+#endif
#endif
};
/* Allocate & free a PCI host bridge structure */
extern struct pci_controller *pcibios_alloc_controller(struct device_node *dev);
extern void pcibios_free_controller(struct pci_controller *phb);
+extern void pcibios_free_controller_deferred(struct pci_host_bridge *bridge);
#ifdef CONFIG_PCI
extern int pcibios_vaddr_is_ioport(void __iomem *address);
static inline void __giveup_spe(struct task_struct *t) { }
#endif
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-extern void flush_tmregs_to_thread(struct task_struct *);
-#else
-static inline void flush_tmregs_to_thread(struct task_struct *t)
-{
-}
-#endif
-
static inline void clear_task_ebb(struct task_struct *t)
{
#ifdef CONFIG_PPC_BOOK3S_64
static inline unsigned long copy_from_user(void *to,
const void __user *from, unsigned long n)
{
- unsigned long over;
-
- if (access_ok(VERIFY_READ, from, n))
+ if (likely(access_ok(VERIFY_READ, from, n))) {
+ check_object_size(to, n, false);
return __copy_tofrom_user((__force void __user *)to, from, n);
- if ((unsigned long)from < TASK_SIZE) {
- over = (unsigned long)from + n - TASK_SIZE;
- return __copy_tofrom_user((__force void __user *)to, from,
- n - over) + over;
}
+ memset(to, 0, n);
return n;
}
static inline unsigned long copy_to_user(void __user *to,
const void *from, unsigned long n)
{
- unsigned long over;
-
- if (access_ok(VERIFY_WRITE, to, n))
+ if (access_ok(VERIFY_WRITE, to, n)) {
+ check_object_size(from, n, true);
return __copy_tofrom_user(to, (__force void __user *)from, n);
- if ((unsigned long)to < TASK_SIZE) {
- over = (unsigned long)to + n - TASK_SIZE;
- return __copy_tofrom_user(to, (__force void __user *)from,
- n - over) + over;
}
return n;
}
if (ret == 0)
return 0;
}
+
+ check_object_size(to, n, false);
+
return __copy_tofrom_user((__force void __user *)to, from, n);
}
if (ret == 0)
return 0;
}
+
+ check_object_size(from, n, true);
+
return __copy_tofrom_user(to, (__force const void __user *)from, n);
}
might_fault();
if (likely(access_ok(VERIFY_WRITE, addr, size)))
return __clear_user(addr, size);
- if ((unsigned long)addr < TASK_SIZE) {
- unsigned long over = (unsigned long)addr + size - TASK_SIZE;
- return __clear_user(addr, size - over) + over;
- }
return size;
}
extern void xics_kexec_teardown_cpu(int secondary);
extern void xics_migrate_irqs_away(void);
extern void icp_native_eoi(struct irq_data *d);
+extern int xics_set_irq_type(struct irq_data *d, unsigned int flow_type);
+extern int xics_retrigger(struct irq_data *data);
#ifdef CONFIG_SMP
extern int xics_get_irq_server(unsigned int virq, const struct cpumask *cpumask,
unsigned int strict_check);
obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o
obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o
-obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o hmi.o
+obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o
obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o
obj-$(CONFIG_PPC64) += vdso64/
obj-$(CONFIG_ALTIVEC) += vecemu.o
int n = 0, l = 0;
char buffer[128];
- n += scnprintf(buf+n, len-n, "%04x:%02x:%02x:%01x\n",
+ n += scnprintf(buf+n, len-n, "%04x:%02x:%02x.%01x\n",
edev->phb->global_number, pdn->busno,
PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
- pr_warn("EEH: of node=%04x:%02x:%02x:%01x\n",
+ pr_warn("EEH: of node=%04x:%02x:%02x.%01x\n",
edev->phb->global_number, pdn->busno,
PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
tabort_syscall:
/* Firstly we need to enable TM in the kernel */
mfmsr r10
- li r13, 1
- rldimi r10, r13, MSR_TM_LG, 63-MSR_TM_LG
+ li r9, 1
+ rldimi r10, r9, MSR_TM_LG, 63-MSR_TM_LG
mtmsrd r10, 0
/* tabort, this dooms the transaction, nothing else */
- li r13, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
- TABORT(R13)
+ li r9, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
+ TABORT(R9)
/*
* Return directly to userspace. We have corrupted user register state,
* resume after the tbegin of the aborted transaction with the
* checkpointed register state.
*/
- li r13, MSR_RI
- andc r10, r10, r13
+ li r9, MSR_RI
+ andc r10, r10, r9
mtmsrd r10, 1
mtspr SPRN_SRR0, r11
mtspr SPRN_SRR1, r12
* vector
*/
SET_SCRATCH0(r13) /* save r13 */
-#ifdef CONFIG_PPC_P7_NAP
-BEGIN_FTR_SECTION
- /* Running native on arch 2.06 or later, check if we are
- * waking up from nap. We only handle no state loss and
- * supervisor state loss. We do -not- handle hypervisor
- * state loss at this time.
+ /*
+ * Running native on arch 2.06 or later, we may wakeup from winkle
+ * inside machine check. If yes, then last bit of HSPGR0 would be set
+ * to 1. Hence clear it unconditionally.
*/
- mfspr r13,SPRN_SRR1
- rlwinm. r13,r13,47-31,30,31
- OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR)
- beq 9f
-
- mfspr r13,SPRN_SRR1
- rlwinm. r13,r13,47-31,30,31
- /* waking up from powersave (nap) state */
- cmpwi cr1,r13,2
- /* Total loss of HV state is fatal. let's just stay stuck here */
- OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR)
- bgt cr1,.
-9:
- OPT_SET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR)
-END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-#endif /* CONFIG_PPC_P7_NAP */
+ GET_PACA(r13)
+ clrrdi r13,r13,1
+ SET_PACA(r13)
EXCEPTION_PROLOG_0(PACA_EXMC)
BEGIN_FTR_SECTION
b machine_check_powernv_early
EXCEPTION_PROLOG_0(PACA_EXMC)
machine_check_pSeries_0:
EXCEPTION_PROLOG_1(PACA_EXMC, KVMTEST, 0x200)
- EXCEPTION_PROLOG_PSERIES_1(machine_check_common, EXC_STD)
+ /*
+ * The following is essentially EXCEPTION_PROLOG_PSERIES_1 with the
+ * difference that MSR_RI is not enabled, because PACA_EXMC is being
+ * used, so nested machine check corrupts it. machine_check_common
+ * enables MSR_RI.
+ */
+ ld r12,PACAKBASE(r13)
+ ld r10,PACAKMSR(r13)
+ xori r10,r10,MSR_RI
+ mfspr r11,SPRN_SRR0
+ LOAD_HANDLER(r12, machine_check_common)
+ mtspr SPRN_SRR0,r12
+ mfspr r12,SPRN_SRR1
+ mtspr SPRN_SRR1,r10
+ rfid
+ b . /* prevent speculative execution */
+
KVM_HANDLER_SKIP(PACA_EXMC, EXC_STD, 0x200)
KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300)
KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380)
machine_check_common:
mfspr r10,SPRN_DAR
- std r10,PACA_EXGEN+EX_DAR(r13)
+ std r10,PACA_EXMC+EX_DAR(r13)
mfspr r10,SPRN_DSISR
- stw r10,PACA_EXGEN+EX_DSISR(r13)
+ stw r10,PACA_EXMC+EX_DSISR(r13)
EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC)
FINISH_NAP
RECONCILE_IRQ_STATE(r10, r11)
- ld r3,PACA_EXGEN+EX_DAR(r13)
- lwz r4,PACA_EXGEN+EX_DSISR(r13)
+ ld r3,PACA_EXMC+EX_DAR(r13)
+ lwz r4,PACA_EXMC+EX_DSISR(r13)
+ /* Enable MSR_RI when finished with PACA_EXMC */
+ li r10,MSR_RI
+ mtmsrd r10,1
std r3,_DAR(r1)
std r4,_DSISR(r1)
bl save_nvgprs
* Check if thread was in power saving mode. We come here when any
* of the following is true:
* a. thread wasn't in power saving mode
- * b. thread was in power saving mode with no state loss or
- * supervisor state loss
+ * b. thread was in power saving mode with no state loss,
+ * supervisor state loss or hypervisor state loss.
*
- * Go back to nap again if (b) is true.
+ * Go back to nap/sleep/winkle mode again if (b) is true.
*/
rlwinm. r11,r12,47-31,30,31 /* Was it in power saving mode? */
beq 4f /* No, it wasn;t */
/* Thread was in power saving mode. Go back to nap again. */
cmpwi r11,2
- bne 3f
- /* Supervisor state loss */
+ blt 3f
+ /* Supervisor/Hypervisor state loss */
li r0,1
stb r0,PACA_NAPSTATELOST(r13)
3: bl machine_check_queue_event
MACHINE_CHECK_HANDLER_WINDUP
GET_PACA(r13)
ld r1,PACAR1(r13)
- li r3,PNV_THREAD_NAP
- b pnv_enter_arch207_idle_mode
+ /*
+ * Check what idle state this CPU was in and go back to same mode
+ * again.
+ */
+ lbz r3,PACA_THREAD_IDLE_STATE(r13)
+ cmpwi r3,PNV_THREAD_NAP
+ bgt 10f
+ IDLE_STATE_ENTER_SEQ(PPC_NAP)
+ /* No return */
+10:
+ cmpwi r3,PNV_THREAD_SLEEP
+ bgt 2f
+ IDLE_STATE_ENTER_SEQ(PPC_SLEEP)
+ /* No return */
+
+2:
+ /*
+ * Go back to winkle. Please note that this thread was woken up in
+ * machine check from winkle and have not restored the per-subcore
+ * state. Hence before going back to winkle, set last bit of HSPGR0
+ * to 1. This will make sure that if this thread gets woken up
+ * again at reset vector 0x100 then it will get chance to restore
+ * the subcore state.
+ */
+ ori r13,r13,1
+ SET_PACA(r13)
+ IDLE_STATE_ENTER_SEQ(PPC_WINKLE)
+ /* No return */
4:
#endif
/*
+++ /dev/null
-/*
- * Hypervisor Maintenance Interrupt (HMI) handling.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.
- *
- * Copyright 2015 IBM Corporation
- * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
- */
-
-#undef DEBUG
-
-#include <linux/types.h>
-#include <linux/compiler.h>
-#include <asm/paca.h>
-#include <asm/hmi.h>
-
-void wait_for_subcore_guest_exit(void)
-{
- int i;
-
- /*
- * NULL bitmap pointer indicates that KVM module hasn't
- * been loaded yet and hence no guests are running.
- * If no KVM is in use, no need to co-ordinate among threads
- * as all of them will always be in host and no one is going
- * to modify TB other than the opal hmi handler.
- * Hence, just return from here.
- */
- if (!local_paca->sibling_subcore_state)
- return;
-
- for (i = 0; i < MAX_SUBCORE_PER_CORE; i++)
- while (local_paca->sibling_subcore_state->in_guest[i])
- cpu_relax();
-}
-
-void wait_for_tb_resync(void)
-{
- if (!local_paca->sibling_subcore_state)
- return;
-
- while (test_bit(CORE_TB_RESYNC_REQ_BIT,
- &local_paca->sibling_subcore_state->flags))
- cpu_relax();
-}
PSSCR_PSLL_MASK | PSSCR_TR_MASK | \
PSSCR_MTL_MASK
-/* Idle state entry routines */
-
-#define IDLE_STATE_ENTER_SEQ(IDLE_INST) \
- /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \
- std r0,0(r1); \
- ptesync; \
- ld r0,0(r1); \
-1: cmp cr0,r0,r0; \
- bne 1b; \
- IDLE_INST; \
- b .
-
.text
/*
* cr3 - set to gt if waking up with partial/complete hypervisor state loss
*/
_GLOBAL(pnv_restore_hyp_resource)
- ld r2,PACATOC(r13);
BEGIN_FTR_SECTION
+ ld r2,PACATOC(r13);
/*
* POWER ISA 3. Use PSSCR to determine if we
* are waking up from deep idle state
*/
clrldi r5,r13,63
clrrdi r13,r13,1
+
+ /* Now that we are sure r13 is corrected, load TOC */
+ ld r2,PACATOC(r13);
cmpwi cr4,r5,1
mtspr SPRN_HSPRG0,r13
*
* r13 - PACA
* cr3 - gt if waking up with partial/complete hypervisor state loss
- * cr4 - eq if waking up from complete hypervisor state loss.
+ * cr4 - gt or eq if waking up from complete hypervisor state loss.
*/
_GLOBAL(pnv_wakeup_tb_loss)
ld r1,PACAR1(r13)
* At this stage
* cr2 - eq if first thread to wakeup in core
* cr3- gt if waking up with partial/complete hypervisor state loss
- * cr4 - eq if waking up from complete hypervisor state loss.
+ * cr4 - gt or eq if waking up from complete hypervisor state loss.
*/
ori r15,r15,PNV_CORE_IDLE_LOCK_BIT
* If waking up from sleep, subcore state is not lost. Hence
* skip subcore state restore
*/
- bne cr4,subcore_state_restored
+ blt cr4,subcore_state_restored
/* Restore per-subcore state */
ld r4,_SDR1(r1)
* If waking up from sleep, per core state is not lost, skip to
* clear_lock.
*/
- bne cr4,clear_lock
+ blt cr4,clear_lock
/*
* First thread in the core to wake up and its waking up with
* If waking up from sleep, hypervisor state is not lost. Hence
* skip hypervisor state restore.
*/
- bne cr4,hypervisor_state_restored
+ blt cr4,hypervisor_state_restored
/* Waking up from winkle */
#include <linux/kprobes.h>
#include <linux/ptrace.h>
#include <linux/preempt.h>
-#include <linux/module.h>
+#include <linux/extable.h>
#include <linux/kdebug.h>
#include <linux/slab.h>
#include <asm/code-patching.h>
mce->in_use = 1;
mce->initiator = MCE_INITIATOR_CPU;
- if (handled)
+ /* Mark it recovered if we have handled it and MSR(RI=1). */
+ if (handled && (regs->msr & MSR_RI))
mce->disposition = MCE_DISPOSITION_RECOVERED;
else
mce->disposition = MCE_DISPOSITION_NOT_RECOVERED;
static int get_phb_number(struct device_node *dn)
{
int ret, phb_id = -1;
+ u32 prop_32;
u64 prop;
/*
* reading "ibm,opal-phbid", only present in OPAL environment.
*/
ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop);
- if (ret)
- ret = of_property_read_u32_index(dn, "reg", 1, (u32 *)&prop);
+ if (ret) {
+ ret = of_property_read_u32_index(dn, "reg", 1, &prop_32);
+ prop = prop_32;
+ }
if (!ret)
phb_id = (int)(prop & (MAX_PHBS - 1));
}
EXPORT_SYMBOL_GPL(pcibios_free_controller);
+/*
+ * This function is used to call pcibios_free_controller()
+ * in a deferred manner: a callback from the PCI subsystem.
+ *
+ * _*DO NOT*_ call pcibios_free_controller() explicitly if
+ * this is used (or it may access an invalid *phb pointer).
+ *
+ * The callback occurs when all references to the root bus
+ * are dropped (e.g., child buses/devices and their users).
+ *
+ * It's called as .release_fn() of 'struct pci_host_bridge'
+ * which is associated with the 'struct pci_controller.bus'
+ * (root bus) - it expects .release_data to hold a pointer
+ * to 'struct pci_controller'.
+ *
+ * In order to use it, register .release_fn()/release_data
+ * like this:
+ *
+ * pci_set_host_bridge_release(bridge,
+ * pcibios_free_controller_deferred
+ * (void *) phb);
+ *
+ * e.g. in the pcibios_root_bridge_prepare() callback from
+ * pci_create_root_bus().
+ */
+void pcibios_free_controller_deferred(struct pci_host_bridge *bridge)
+{
+ struct pci_controller *phb = (struct pci_controller *)
+ bridge->release_data;
+
+ pr_debug("domain %d, dynamic %d\n", phb->global_number, phb->is_dynamic);
+
+ pcibios_free_controller(phb);
+}
+EXPORT_SYMBOL_GPL(pcibios_free_controller_deferred);
+
/*
* The function is used to return the minimal alignment
* for memory or I/O windows of the associated P2P bridge.
#endif
}
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-void flush_tmregs_to_thread(struct task_struct *tsk)
-{
- /*
- * Process self tracing is not yet supported through
- * ptrace interface. Ptrace generic code should have
- * prevented this from happening in the first place.
- * Warn once here with the message, if some how it
- * is attempted.
- */
- WARN_ONCE(tsk == current,
- "Not expecting ptrace on self: TM regs may be incorrect\n");
-
- /*
- * If task is not current, it should have been flushed
- * already to it's thread_struct during __switch_to().
- */
-}
-#endif
-
struct task_struct *__switch_to(struct task_struct *prev,
struct task_struct *new)
{
OV4_MIN_ENT_CAP, /* minimum VP entitled capacity */
/* option vector 5: PAPR/OF options */
- VECTOR_LENGTH(18), /* length */
+ VECTOR_LENGTH(21), /* length */
0, /* don't ignore, don't halt */
OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) |
OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) |
0,
0,
OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) |
- OV5_FEAT(OV5_PFO_HW_842),
- OV5_FEAT(OV5_SUB_PROCESSORS),
+ OV5_FEAT(OV5_PFO_HW_842), /* Byte 17 */
+ 0, /* Byte 18 */
+ 0, /* Byte 19 */
+ 0, /* Byte 20 */
+ OV5_FEAT(OV5_SUB_PROCESSORS), /* Byte 21 */
/* option vector 6: IBM PAPR hints */
VECTOR_LENGTH(3), /* length */
/* Don't print anything after quiesce under OPAL, it crashes OFW */
if (of_platform != PLATFORM_OPAL) {
- prom_printf("Booting Linux via __start() ...\n");
+ prom_printf("Booting Linux via __start() @ 0x%lx ...\n", kbase);
prom_debug("->dt_header_start=0x%x\n", hdr);
}
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/switch_to.h>
+#include <asm/tm.h>
#define CREATE_TRACE_POINTS
#include <trace/events/syscalls.h>
REG_OFFSET_END,
};
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+static void flush_tmregs_to_thread(struct task_struct *tsk)
+{
+ /*
+ * If task is not current, it will have been flushed already to
+ * it's thread_struct during __switch_to().
+ *
+ * A reclaim flushes ALL the state.
+ */
+
+ if (tsk == current && MSR_TM_SUSPENDED(mfmsr()))
+ tm_reclaim_current(TM_CAUSE_SIGNAL);
+
+}
+#else
+static inline void flush_tmregs_to_thread(struct task_struct *tsk) { }
+#endif
+
/**
* regs_query_register_offset() - query register offset from its name
* @name: the name of a register
* and we are running with enough of the MMU enabled to have our
* proper kernel virtual addresses
*
- * Find out what kind of machine we're on and save any data we need
- * from the early boot process (devtree is copied on pmac by prom_init()).
- * This is called very early on the boot process, after a minimal
- * MMU environment has been set up but before MMU_init is called.
+ * We do the initial parsing of the flat device-tree and prepares
+ * for the MMU to be fully initialized.
*/
extern unsigned int memset_nocache_branch; /* Insn to be replaced by NOP */
notrace void __init machine_init(u64 dt_ptr)
{
+ /* Configure static keys first, now that we're relocated. */
+ setup_feature_keys();
+
/* Enable early debugging if any specified (see udbg.h) */
udbg_early_init();
/* Apply all the dynamic patching */
apply_feature_fixups();
+ setup_feature_keys();
/* Initialize the hash table or TLB handling */
early_init_mmu();
(regs->gpr[1] + __SIGNAL_FRAMESIZE + 16);
if (!access_ok(VERIFY_READ, rt_sf, sizeof(*rt_sf)))
goto bad;
+
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /*
+ * If there is a transactional state then throw it away.
+ * The purpose of a sigreturn is to destroy all traces of the
+ * signal frame, this includes any transactional state created
+ * within in. We only check for suspended as we can never be
+ * active in the kernel, we are active, there is nothing better to
+ * do than go ahead and Bad Thing later.
+ * The cause is not important as there will never be a
+ * recheckpoint so it's not user visible.
+ */
+ if (MSR_TM_SUSPENDED(mfmsr()))
+ tm_reclaim_current(0);
+
if (__get_user(tmp, &rt_sf->uc.uc_link))
goto bad;
uc_transact = (struct ucontext __user *)(uintptr_t)tmp;
if (__copy_from_user(&set, &uc->uc_sigmask, sizeof(set)))
goto badframe;
set_current_blocked(&set);
+
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+ /*
+ * If there is a transactional state then throw it away.
+ * The purpose of a sigreturn is to destroy all traces of the
+ * signal frame, this includes any transactional state created
+ * within in. We only check for suspended as we can never be
+ * active in the kernel, we are active, there is nothing better to
+ * do than go ahead and Bad Thing later.
+ * The cause is not important as there will never be a
+ * recheckpoint so it's not user visible.
+ */
+ if (MSR_TM_SUSPENDED(mfmsr()))
+ tm_reclaim_current(0);
+
if (__get_user(msr, &uc->uc_mcontext.gp_regs[PT_MSR]))
goto badframe;
if (MSR_TM_ACTIVE(msr)) {
/* Update sibling maps */
base = cpu_first_thread_sibling(cpu);
- for (i = 0; i < threads_per_core; i++) {
+ for (i = 0; i < threads_per_core && base + i < nr_cpu_ids; i++) {
cpumask_clear_cpu(cpu, cpu_sibling_mask(base + i));
cpumask_clear_cpu(base + i, cpu_sibling_mask(cpu));
cpumask_clear_cpu(cpu, cpu_core_mask(base + i));
#include <linux/user.h>
#include <linux/interrupt.h>
#include <linux/init.h>
-#include <linux/module.h>
+#include <linux/extable.h>
+#include <linux/module.h> /* print_modules */
#include <linux/prctl.h>
#include <linux/delay.h>
#include <linux/kprobes.h>
#include <linux/security.h>
#include <linux/memblock.h>
+#include <asm/cpu_has_feature.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
#include <asm/mmu.h>
$(obj)/vdso32_wrapper.o : $(obj)/vdso32.so
# link rule for the .so file, .lds has to be first
-$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32)
+$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) FORCE
$(call if_changed,vdso32ld)
# strip rule for the .so file
$(call if_changed,objcopy)
# assembly rules for the .S files
-$(obj-vdso32): %.o: %.S
+$(obj-vdso32): %.o: %.S FORCE
$(call if_changed_dep,vdso32as)
# actual build commands
quiet_cmd_vdso32ld = VDSO32L $@
- cmd_vdso32ld = $(CROSS32CC) $(c_flags) -Wl,-T $^ -o $@
+ cmd_vdso32ld = $(CROSS32CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
quiet_cmd_vdso32as = VDSO32A $@
cmd_vdso32as = $(CROSS32CC) $(a_flags) -c -o $@ $<
$(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
# link rule for the .so file, .lds has to be first
-$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64)
+$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE
$(call if_changed,vdso64ld)
# strip rule for the .so file
$(call if_changed,objcopy)
# assembly rules for the .S files
-$(obj-vdso64): %.o: %.S
+$(obj-vdso64): %.o: %.S FORCE
$(call if_changed_dep,vdso64as)
# actual build commands
quiet_cmd_vdso64ld = VDSO64L $@
- cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $^ -o $@
+ cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^)
quiet_cmd_vdso64as = VDSO64A $@
cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $<
ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
+ book3s_hv_hmi.o \
book3s_hv_rmhandlers.o \
book3s_hv_rm_mmu.o \
book3s_hv_ras.o \
--- /dev/null
+/*
+ * Hypervisor Maintenance Interrupt (HMI) handling.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.
+ *
+ * Copyright 2015 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#undef DEBUG
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <asm/paca.h>
+#include <asm/hmi.h>
+
+void wait_for_subcore_guest_exit(void)
+{
+ int i;
+
+ /*
+ * NULL bitmap pointer indicates that KVM module hasn't
+ * been loaded yet and hence no guests are running.
+ * If no KVM is in use, no need to co-ordinate among threads
+ * as all of them will always be in host and no one is going
+ * to modify TB other than the opal hmi handler.
+ * Hence, just return from here.
+ */
+ if (!local_paca->sibling_subcore_state)
+ return;
+
+ for (i = 0; i < MAX_SUBCORE_PER_CORE; i++)
+ while (local_paca->sibling_subcore_state->in_guest[i])
+ cpu_relax();
+}
+
+void wait_for_tb_resync(void)
+{
+ if (!local_paca->sibling_subcore_state)
+ return;
+
+ while (test_bit(CORE_TB_RESYNC_REQ_BIT,
+ &local_paca->sibling_subcore_state->flags))
+ cpu_relax();
+}
xics->kvm = kvm;
/* Already there ? */
- mutex_lock(&kvm->lock);
if (kvm->arch.xics)
ret = -EEXIST;
else
kvm->arch.xics = xics;
- mutex_unlock(&kvm->lock);
if (ret) {
kfree(xics);
return ret;
}
- xics_debugfs_init(xics);
-
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
if (cpu_has_feature(CPU_FTR_ARCH_206)) {
/* Enable real mode support */
return 0;
}
+static void kvmppc_xics_init(struct kvm_device *dev)
+{
+ struct kvmppc_xics *xics = (struct kvmppc_xics *)dev->private;
+
+ xics_debugfs_init(xics);
+}
+
struct kvm_device_ops kvm_xics_ops = {
.name = "kvm-xics",
.create = kvmppc_xics_create,
+ .init = kvmppc_xics_init,
.destroy = kvmppc_xics_free,
.set_attr = xics_set_attr,
.get_attr = xics_get_attr,
stw r7,12(r1)
stw r8,8(r1)
- andi. r0,r4,1 /* is destination address even ? */
- cmplwi cr7,r0,0
addic r12,r6,0
addi r6,r4,-4
neg r0,r4
addi r4,r3,-4
andi. r0,r0,CACHELINE_MASK /* # bytes to start of cache line */
+ crset 4*cr7+eq
beq 58f
cmplw 0,r5,r0 /* is this more than total to do? */
blt 63f /* if not much to do */
+ rlwinm r7,r6,3,0x8
+ rlwnm r12,r12,r7,0,31 /* odd destination address: rotate one byte */
+ cmplwi cr7,r7,0 /* is destination address even ? */
andi. r8,r0,3 /* get it word-aligned first */
mtctr r8
beq+ 61f
66: addze r3,r12
addi r1,r1,16
beqlr+ cr7
- rlwinm r3,r3,8,0,31 /* swap bytes for odd destination */
+ rlwinm r3,r3,8,0,31 /* odd destination address: rotate one byte */
blr
/* read fault */
&__start___fw_ftr_fixup, &__stop___fw_ftr_fixup);
#endif
do_final_fixups();
+}
+void __init setup_feature_keys(void)
+{
/*
* Initialise jump label. This causes all the cpu/mmu_has_feature()
* checks to take on their correct polarity based on the current set of
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/highmem.h>
-#include <linux/module.h>
+#include <linux/extable.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <linux/perf_event.h>
END_MMU_FTR_SECTION_IFCLR(MMU_FTR_1T_SEGMENT)
b slb_finish_load_1T
-0:
+0: /*
+ * For userspace addresses, make sure this is region 0.
+ */
+ cmpdi r9, 0
+ bne 8f
+
/* when using slices, we extract the psize off the slice bitmaps
* and then we need to get the sllp encoding off the mmu_psize_defs
* array.
.remove = mpc512x_lpbfifo_remove,
.driver = {
.name = DRV_NAME,
- .owner = THIS_MODULE,
.of_match_table = mpc512x_lpbfifo_match,
},
};
static struct i2c_driver mcu_driver = {
.driver = {
.name = "mcu-mpc8349emitx",
- .owner = THIS_MODULE,
.of_match_table = mcu_of_match_table,
},
.probe = mcu_probe,
gang = alloc_spu_gang();
SPUFS_I(inode)->i_ctx = NULL;
SPUFS_I(inode)->i_gang = gang;
- if (!gang)
+ if (!gang) {
+ ret = -ENOMEM;
goto out_iput;
+ }
inode->i_op = &simple_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
#include <linux/tty.h>
#include <linux/serial_core.h>
#include <linux/of_platform.h>
-#include <linux/module.h>
+#include <linux/extable.h>
#include <asm/time.h>
#include <asm/machdep.h>
#include <linux/pci.h>
#include <linux/kdev_t.h>
#include <linux/console.h>
-#include <linux/module.h>
+#include <linux/extable.h>
#include <linux/delay.h>
#include <linux/irq.h>
#include <linux/seq_file.h>
if (dev->vendor == 0x1959 && dev->device == 0xa007 &&
!firmware_has_feature(FW_FEATURE_LPAR)) {
dev->dev.archdata.dma_ops = &dma_direct_ops;
+ /*
+ * Set the coherent DMA mask to prevent the iommu
+ * being used unnecessarily
+ */
+ dev->dev.coherent_dma_mask = DMA_BIT_MASK(44);
return;
}
#endif
uint32_t dump_id, dump_size, dump_type;
struct dump_obj *dump;
char name[22];
+ struct kobject *kobj;
rc = dump_read_info(&dump_id, &dump_size, &dump_type);
if (rc != OPAL_SUCCESS)
* that gracefully and not create two conflicting
* entries.
*/
- if (kset_find_obj(dump_kset, name))
+ kobj = kset_find_obj(dump_kset, name);
+ if (kobj) {
+ /* Drop reference added by kset_find_obj() */
+ kobject_put(kobj);
return 0;
+ }
dump = create_dump_obj(dump_id, dump_size, dump_type);
if (!dump)
uint64_t elog_type;
int rc;
char name[2+16+1];
+ struct kobject *kobj;
rc = opal_get_elog_size(&id, &size, &type);
if (rc != OPAL_SUCCESS) {
* that gracefully and not create two conflicting
* entries.
*/
- if (kset_find_obj(elog_kset, name))
+ kobj = kset_find_obj(elog_kset, name);
+ if (kobj) {
+ /* Drop reference added by kset_find_obj() */
+ kobject_put(kobj);
return IRQ_HANDLED;
+ }
create_elog_obj(log_id, elog_size, elog_type);
}
/* Install interrupt handler */
- rc = request_irq(virq, opal_interrupt, 0, "opal", NULL);
+ rc = request_irq(virq, opal_interrupt, IRQF_TRIGGER_LOW,
+ "opal", NULL);
if (rc) {
irq_dispose_mapping(virq);
pr_warn("Error %d requesting irq %d (0x%x)\n",
if (!(regs->msr & MSR_RI)) {
/* If MSR_RI isn't set, we cannot recover */
+ pr_err("Machine check interrupt unrecoverable: MSR(RI=0)\n");
recovered = 0;
} else if (evt->disposition == MCE_DISPOSITION_RECOVERED) {
/* Platform corrected itself */
}
early_param("iommu", iommu_setup);
-static inline bool pnv_pci_is_mem_pref_64(unsigned long flags)
+static inline bool pnv_pci_is_m64(struct pnv_phb *phb, struct resource *r)
{
- return ((flags & (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH)) ==
- (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH));
+ /*
+ * WARNING: We cannot rely on the resource flags. The Linux PCI
+ * allocation code sometimes decides to put a 64-bit prefetchable
+ * BAR in the 32-bit window, so we have to compare the addresses.
+ *
+ * For simplicity we only test resource start.
+ */
+ return (r->start >= phb->ioda.m64_base &&
+ r->start < (phb->ioda.m64_base + phb->ioda.m64_size));
+}
+
+static inline bool pnv_pci_is_m64_flags(unsigned long resource_flags)
+{
+ unsigned long flags = (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH);
+
+ return (resource_flags & flags) == flags;
}
static struct pnv_ioda_pe *pnv_ioda_init_pe(struct pnv_phb *phb, int pe_no)
static struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb)
{
- unsigned long pe = phb->ioda.total_pe_num - 1;
+ long pe;
for (pe = phb->ioda.total_pe_num - 1; pe >= 0; pe--) {
if (!test_and_set_bit(pe, phb->ioda.pe_alloc))
static void pnv_ioda_free_pe(struct pnv_ioda_pe *pe)
{
struct pnv_phb *phb = pe->phb;
+ unsigned int pe_num = pe->pe_number;
WARN_ON(pe->pdev);
memset(pe, 0, sizeof(struct pnv_ioda_pe));
- clear_bit(pe->pe_number, phb->ioda.pe_alloc);
+ clear_bit(pe_num, phb->ioda.pe_alloc);
}
/* The default M64 BAR is shared by all PEs */
sgsz = phb->ioda.m64_segsize;
for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
r = &pdev->resource[i];
- if (!r->parent || !pnv_pci_is_mem_pref_64(r->flags))
+ if (!r->parent || !pnv_pci_is_m64(phb, r))
continue;
start = _ALIGN_DOWN(r->start - base, sgsz);
unsigned shift, unsigned long index,
unsigned long npages)
{
- __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, false);
+ __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, rm);
unsigned long start, end, inc;
/* We'll invalidate DMA address in PE scope */
pnv_pci_link_table_and_group(phb->hose->node, num,
tbl, &pe->table_group);
- pnv_pci_phb3_tce_invalidate_pe(pe);
+ pnv_pci_ioda2_tce_invalidate_pe(pe);
return 0;
}
if (ret)
pe_warn(pe, "Unmapping failed, ret = %ld\n", ret);
else
- pnv_pci_phb3_tce_invalidate_pe(pe);
+ pnv_pci_ioda2_tce_invalidate_pe(pe);
pnv_pci_unlink_table_and_group(table_group->tables[num], table_group);
res = &pdev->resource[i + PCI_IOV_RESOURCES];
if (!res->flags || res->parent)
continue;
- if (!pnv_pci_is_mem_pref_64(res->flags)) {
+ if (!pnv_pci_is_m64_flags(res->flags)) {
dev_warn(&pdev->dev, "Don't support SR-IOV with"
" non M64 VF BAR%d: %pR. \n",
i, res);
index++;
}
} else if ((res->flags & IORESOURCE_MEM) &&
- !pnv_pci_is_mem_pref_64(res->flags)) {
+ !pnv_pci_is_m64(phb, res)) {
region.start = res->start -
phb->hose->mem_offset[0] -
phb->ioda.m32_pci_base;
bridge = bridge->bus->self;
}
- /* We fail back to M32 if M64 isn't supported */
- if (phb->ioda.m64_segsize &&
- pnv_pci_is_mem_pref_64(type))
+ /*
+ * We fall back to M32 if M64 isn't supported. We enforce the M64
+ * alignment for any 64-bit resource, PCIe doesn't care and
+ * bridges only do 64-bit prefetchable anyway.
+ */
+ if (phb->ioda.m64_segsize && pnv_pci_is_m64_flags(type))
return phb->ioda.m64_segsize;
if (type & IORESOURCE_MEM)
return phb->ioda.m32_segsize;
w = NULL;
if (r->flags & type & IORESOURCE_IO)
w = &hose->io_resource;
- else if (pnv_pci_is_mem_pref_64(r->flags) &&
+ else if (pnv_pci_is_m64(phb, r) &&
(type & IORESOURCE_PREFETCH) &&
phb->ioda.m64_segsize)
w = &hose->mem_resources[1];
struct pnv_phb *phb = pe->phb;
struct pnv_ioda_pe *slave, *tmp;
- /* Release slave PEs in compound PE */
- if (pe->flags & PNV_IODA_PE_MASTER) {
- list_for_each_entry_safe(slave, tmp, &pe->slaves, list)
- pnv_ioda_release_pe(slave);
- }
-
list_del(&pe->list);
switch (phb->type) {
case PNV_PHB_IODA1:
pnv_ioda_release_pe_seg(pe);
pnv_ioda_deconfigure_pe(pe->phb, pe);
- pnv_ioda_free_pe(pe);
+
+ /* Release slave PEs in the compound PE */
+ if (pe->flags & PNV_IODA_PE_MASTER) {
+ list_for_each_entry_safe(slave, tmp, &pe->slaves, list) {
+ list_del(&slave->list);
+ pnv_ioda_free_pe(slave);
+ }
+ }
+
+ /*
+ * The PE for root bus can be removed because of hotplug in EEH
+ * recovery for fenced PHB error. We need to mark the PE dead so
+ * that it can be populated again in PCI hot add path. The PE
+ * shouldn't be destroyed as it's the global reserved resource.
+ */
+ if (phb->ioda.root_pe_populated &&
+ phb->ioda.root_pe_idx == pe->pe_number)
+ phb->ioda.root_pe_populated = false;
+ else
+ pnv_ioda_free_pe(pe);
}
static void pnv_pci_release_device(struct pci_dev *pdev)
if (!pdn || pdn->pe_number == IODA_INVALID_PE)
return;
+ /*
+ * PCI hotplug can happen as part of EEH error recovery. The @pdn
+ * isn't removed and added afterwards in this scenario. We should
+ * set the PE number in @pdn to an invalid one. Otherwise, the PE's
+ * device count is decreased on removing devices while failing to
+ * be increased on adding devices. It leads to unbalanced PE's device
+ * count and eventually make normal PCI hotplug path broken.
+ */
pe = &phb->ioda.pe_array[pdn->pe_number];
+ pdn->pe_number = IODA_INVALID_PE;
+
WARN_ON(--pe->device_count < 0);
if (pe->device_count == 0)
pnv_ioda_release_pe(pe);
return dlpar_update_device_tree_lmb(lmb);
}
-static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb)
-{
- unsigned long section_nr;
- struct mem_section *mem_sect;
- struct memory_block *mem_block;
-
- section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr));
- mem_sect = __nr_to_section(section_nr);
-
- mem_block = find_memory_block(mem_sect);
- return mem_block;
-}
-
#ifdef CONFIG_MEMORY_HOTREMOVE
static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size)
{
static int dlpar_add_lmb(struct of_drconf_cell *);
+static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb)
+{
+ unsigned long section_nr;
+ struct mem_section *mem_sect;
+ struct memory_block *mem_block;
+
+ section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr));
+ mem_sect = __nr_to_section(section_nr);
+
+ mem_block = find_memory_block(mem_sect);
+ return mem_block;
+}
+
static int dlpar_remove_lmb(struct of_drconf_cell *lmb)
{
struct memory_block *mem_block;
bus = bridge->bus;
+ /* Rely on the pcibios_free_controller_deferred() callback. */
+ pci_set_host_bridge_release(bridge, pcibios_free_controller_deferred,
+ (void *) pci_bus_to_host(bus));
+
dn = pcibios_get_phb_of_node(bus);
if (!dn)
return 0;
release_resource(res);
}
- /* Free pci_controller data structure */
- pcibios_free_controller(phb);
+ /*
+ * The pci_controller data structure is freed by
+ * the pcibios_free_controller_deferred() callback;
+ * see pseries_root_bridge_prepare().
+ */
return 0;
}
#include <linux/root_dev.h>
#include <linux/of.h>
#include <linux/of_pci.h>
-#include <linux/kexec.h>
#include <asm/mmu.h>
#include <asm/processor.h>
#include <asm/eeh.h>
#include <asm/reg.h>
#include <asm/plpar_wrappers.h>
+#include <asm/kexec.h>
#include "pseries.h"
static void cpm1_gpio16_save_regs(struct of_mm_gpio_chip *mm_gc)
{
- struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
+ struct cpm1_gpio16_chip *cpm1_gc =
+ container_of(mm_gc, struct cpm1_gpio16_chip, mm_gc);
struct cpm_ioport16 __iomem *iop = mm_gc->regs;
cpm1_gc->cpdata = in_be16(&iop->dat);
static void cpm1_gpio32_save_regs(struct of_mm_gpio_chip *mm_gc)
{
- struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc);
+ struct cpm1_gpio32_chip *cpm1_gc =
+ container_of(mm_gc, struct cpm1_gpio32_chip, mm_gc);
struct cpm_ioport32b __iomem *iop = mm_gc->regs;
cpm1_gc->cpdata = in_be32(&iop->dat);
static void cpm2_gpio32_save_regs(struct of_mm_gpio_chip *mm_gc)
{
- struct cpm2_gpio32_chip *cpm2_gc = gpiochip_get_data(&mm_gc->gc);
+ struct cpm2_gpio32_chip *cpm2_gc =
+ container_of(mm_gc, struct cpm2_gpio32_chip, mm_gc);
struct cpm2_ioports __iomem *iop = mm_gc->regs;
cpm2_gc->cpdata = in_be32(&iop->dat);
*/
#include <linux/init.h>
-#include <linux/module.h>
+#include <linux/extable.h>
#include <linux/types.h>
#include <linux/dma-mapping.h>
#include <linux/interrupt.h>
config PPC_XICS
def_bool n
select PPC_SMP_MUXED_IPI
+ select HARDIRQS_SW_RESEND
config PPC_ICP_NATIVE
def_bool n
static void icp_opal_teardown_cpu(void)
{
- int cpu = smp_processor_id();
+ int hw_cpu = hard_smp_processor_id();
/* Clear any pending IPI */
- opal_int_set_mfrr(cpu, 0xff);
+ opal_int_set_mfrr(hw_cpu, 0xff);
}
static void icp_opal_flush_ipi(void)
static void icp_opal_cause_ipi(int cpu, unsigned long data)
{
- opal_int_set_mfrr(cpu, IPI_PRIORITY);
+ int hw_cpu = get_hard_smp_processor_id(cpu);
+
+ opal_int_set_mfrr(hw_cpu, IPI_PRIORITY);
}
static irqreturn_t icp_opal_ipi_action(int irq, void *dev_id)
{
- int cpu = smp_processor_id();
+ int hw_cpu = hard_smp_processor_id();
- opal_int_set_mfrr(cpu, 0xff);
+ opal_int_set_mfrr(hw_cpu, 0xff);
return smp_ipi_demux();
}
.irq_mask = ics_opal_mask_irq,
.irq_unmask = ics_opal_unmask_irq,
.irq_eoi = NULL, /* Patched at init time */
- .irq_set_affinity = ics_opal_set_affinity
+ .irq_set_affinity = ics_opal_set_affinity,
+ .irq_set_type = xics_set_irq_type,
+ .irq_retrigger = xics_retrigger,
};
static int ics_opal_map(struct ics *ics, unsigned int virq);
.irq_mask = ics_rtas_mask_irq,
.irq_unmask = ics_rtas_unmask_irq,
.irq_eoi = NULL, /* Patched at init time */
- .irq_set_affinity = ics_rtas_set_affinity
+ .irq_set_affinity = ics_rtas_set_affinity,
+ .irq_set_type = xics_set_irq_type,
+ .irq_retrigger = xics_retrigger,
};
static int ics_rtas_map(struct ics *ics, unsigned int virq)
pr_devel("xics: map virq %d, hwirq 0x%lx\n", virq, hw);
- /* They aren't all level sensitive but we just don't really know */
- irq_set_status_flags(virq, IRQ_LEVEL);
+ /*
+ * Mark interrupts as edge sensitive by default so that resend
+ * actually works. The device-tree parsing will turn the LSIs
+ * back to level.
+ */
+ irq_clear_status_flags(virq, IRQ_LEVEL);
/* Don't call into ICS for IPIs */
if (hw == XICS_IPI) {
irq_hw_number_t *out_hwirq, unsigned int *out_flags)
{
- /* Current xics implementation translates everything
- * to level. It is not technically right for MSIs but this
- * is irrelevant at this point. We might get smarter in the future
- */
*out_hwirq = intspec[0];
- *out_flags = IRQ_TYPE_LEVEL_LOW;
+ /*
+ * If intsize is at least 2, we look for the type in the second cell,
+ * we assume the LSB indicates a level interrupt.
+ */
+ if (intsize > 1) {
+ if (intspec[1] & 1)
+ *out_flags = IRQ_TYPE_LEVEL_LOW;
+ else
+ *out_flags = IRQ_TYPE_EDGE_RISING;
+ } else
+ *out_flags = IRQ_TYPE_LEVEL_LOW;
+
+ return 0;
+}
+
+int xics_set_irq_type(struct irq_data *d, unsigned int flow_type)
+{
+ /*
+ * We only support these. This has really no effect other than setting
+ * the corresponding descriptor bits mind you but those will in turn
+ * affect the resend function when re-enabling an edge interrupt.
+ *
+ * Set set the default to edge as explained in map().
+ */
+ if (flow_type == IRQ_TYPE_DEFAULT || flow_type == IRQ_TYPE_NONE)
+ flow_type = IRQ_TYPE_EDGE_RISING;
+
+ if (flow_type != IRQ_TYPE_EDGE_RISING &&
+ flow_type != IRQ_TYPE_LEVEL_LOW)
+ return -EINVAL;
+
+ irqd_set_trigger_type(d, flow_type);
+
+ return IRQ_SET_MASK_OK_NOCOPY;
+}
+
+int xics_retrigger(struct irq_data *data)
+{
+ /*
+ * We need to push a dummy CPPR when retriggering, since the subsequent
+ * EOI will try to pop it. Passing 0 works, as the function hard codes
+ * the priority value anyway.
+ */
+ xics_push_cppr(0);
+
+ /* Tell the core to do a soft retrigger */
return 0;
}
config S390
def_bool y
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
- select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_GCOV_PROFILE_ALL
select HAVE_ALIGNED_STRUCT_PAGE if SLUB
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_EARLY_PFN_TO_NID
+ select HAVE_ARCH_HARDENED_USERCOPY
select HAVE_ARCH_JUMP_LABEL
select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES
select HAVE_ARCH_SECCOMP_FILTER
Select this option if you want to run the kernel as a guest under
the KVM hypervisor.
+config S390_GUEST_OLD_TRANSPORT
+ def_bool y
+ prompt "Guest support for old s390 virtio transport (DEPRECATED)"
+ depends on S390_GUEST
+ help
+ Enable this option to add support for the old s390-virtio
+ transport (i.e. virtio devices NOT based on virtio-ccw). This
+ type of virtio devices is only available on the experimental
+ kuli userspace or with old (< 2.6) qemu. If you are running
+ with a modern version of qemu (which supports virtio-ccw since
+ 1.4 and uses it by default since version 2.4), you probably won't
+ need this.
+
endmenu
lg %r15,.Lstack-.LPG1(%r13)
aghi %r15,-160
brasl %r14,decompress_kernel
- # setup registers for memory mover & branch to target
+ # Set up registers for memory mover. We move the decompressed image to
+ # 0x11000, starting at offset 0x11000 in the decompressed image so
+ # that code living at 0x11000 in the image will end up at 0x11000 in
+ # memory.
lgr %r4,%r2
lg %r2,.Loffset-.LPG1(%r13)
la %r4,0(%r2,%r4)
lg %r3,.Lmvsize-.LPG1(%r13)
lgr %r5,%r3
- # move the memory mover someplace safe
+ # Move the memory mover someplace safe so it doesn't overwrite itself.
la %r1,0x200
mvc 0(mover_end-mover,%r1),mover-.LPG1(%r13)
- # decompress image is started at 0x11000
+ # When the memory mover is done we pass control to
+ # arch/s390/kernel/head64.S:startup_continue which lives at 0x11000 in
+ # the decompressed image.
lgr %r6,%r2
br %r1
mover:
CONFIG_FAULT_INJECTION_DEBUG_FS=y
CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y
CONFIG_LATENCYTOP=y
-CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
CONFIG_IRQSOFF_TRACER=y
CONFIG_PREEMPT_TRACER=y
CONFIG_SCHED_TRACER=y
CONFIG_CRYPTO_DES_S390=m
CONFIG_CRYPTO_AES_S390=m
CONFIG_CRYPTO_GHASH_S390=m
-CONFIG_CRYPTO_CRC32_S390=m
+CONFIG_CRYPTO_CRC32_S390=y
CONFIG_ASYMMETRIC_KEY_TYPE=y
CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
CONFIG_X509_CERTIFICATE_PARSER=m
CONFIG_CPU_NOTIFIER_ERROR_INJECT=m
CONFIG_PM_NOTIFIER_ERROR_INJECT=m
CONFIG_LATENCYTOP=y
-CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
CONFIG_BLK_DEV_IO_TRACE=y
# CONFIG_KPROBE_EVENT is not set
CONFIG_TRACE_ENUM_MAP_FILE=y
CONFIG_CRYPTO_DES_S390=m
CONFIG_CRYPTO_AES_S390=m
CONFIG_CRYPTO_GHASH_S390=m
-CONFIG_CRYPTO_CRC32_S390=m
+CONFIG_CRYPTO_CRC32_S390=y
CONFIG_ASYMMETRIC_KEY_TYPE=y
CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
CONFIG_X509_CERTIFICATE_PARSER=m
CONFIG_RCU_TORTURE_TEST=m
CONFIG_RCU_CPU_STALL_TIMEOUT=60
CONFIG_LATENCYTOP=y
-CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
CONFIG_SCHED_TRACER=y
CONFIG_FTRACE_SYSCALLS=y
CONFIG_STACK_TRACER=y
CONFIG_CRYPTO_DES_S390=m
CONFIG_CRYPTO_AES_S390=m
CONFIG_CRYPTO_GHASH_S390=m
-CONFIG_CRYPTO_CRC32_S390=m
+CONFIG_CRYPTO_CRC32_S390=y
CONFIG_ASYMMETRIC_KEY_TYPE=y
CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
CONFIG_X509_CERTIFICATE_PARSER=m
struct kernel_fpu vxstate; \
unsigned long prealign, aligned, remaining; \
\
+ if (datalen < VX_MIN_LEN + VX_ALIGN_MASK) \
+ return ___crc32_sw(crc, data, datalen); \
+ \
if ((unsigned long)data & VX_ALIGN_MASK) { \
prealign = VX_ALIGNMENT - \
((unsigned long)data & VX_ALIGN_MASK); \
data = (void *)((unsigned long)data + prealign); \
} \
\
- if (datalen < VX_MIN_LEN) \
- return ___crc32_sw(crc, data, datalen); \
- \
aligned = datalen & ~VX_ALIGN_MASK; \
remaining = datalen & VX_ALIGN_MASK; \
\
CONFIG_RCU_CPU_STALL_TIMEOUT=60
CONFIG_RCU_TRACE=y
CONFIG_LATENCYTOP=y
-CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
CONFIG_SCHED_TRACER=y
CONFIG_FTRACE_SYSCALLS=y
CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
CONFIG_CRYPTO_SHA512_S390=m
CONFIG_CRYPTO_DES_S390=m
CONFIG_CRYPTO_AES_S390=m
-CONFIG_CRYPTO_CRC32_S390=m
+CONFIG_CRYPTO_CRC32_S390=y
CONFIG_CRC7=m
# CONFIG_XZ_DEC_X86 is not set
# CONFIG_XZ_DEC_POWERPC is not set
__chk_user_ptr(ptr); \
switch (sizeof(*(ptr))) { \
case 1: { \
- unsigned char __x; \
+ unsigned char __x = 0; \
__gu_err = __get_user_fn(&__x, ptr, \
sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 2: { \
- unsigned short __x; \
+ unsigned short __x = 0; \
__gu_err = __get_user_fn(&__x, ptr, \
sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 4: { \
- unsigned int __x; \
+ unsigned int __x = 0; \
__gu_err = __get_user_fn(&__x, ptr, \
sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
break; \
}; \
case 8: { \
- unsigned long long __x; \
+ unsigned long long __x = 0; \
__gu_err = __get_user_fn(&__x, ptr, \
sizeof(*(ptr))); \
(x) = *(__force __typeof__(*(ptr)) *) &__x; \
#define __put_user_unaligned __put_user
#define __get_user_unaligned __get_user
+extern void __compiletime_error("usercopy buffer size is too small")
+__bad_copy_user(void);
+
+static inline void copy_user_overflow(int size, unsigned long count)
+{
+ WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
+}
+
/**
* copy_to_user: - Copy a block of data into user space.
* @to: Destination address, in user space.
return __copy_to_user(to, from, n);
}
-void copy_from_user_overflow(void)
-#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
-__compiletime_warning("copy_from_user() buffer size is not provably correct")
-#endif
-;
-
/**
* copy_from_user: - Copy a block of data from user space.
* @to: Destination address, in kernel space.
might_fault();
if (unlikely(sz != -1 && sz < n)) {
- copy_from_user_overflow();
+ if (!__builtin_constant_p(n))
+ copy_user_overflow(sz, n);
+ else
+ __bad_copy_user();
return n;
}
return __copy_from_user(to, from, n);
l %r15,.Lstack-.LPG0(%r13)
ahi %r15,-STACK_FRAME_OVERHEAD
brasl %r14,verify_facilities
- /* Continue with startup code in head64.S */
+# For uncompressed images, continue in
+# arch/s390/kernel/head64.S. For compressed images, continue in
+# arch/s390/boot/compressed/head.S.
jg startup_continue
.Lstack:
#endif
}
} else if (MACHINE_IS_KVM) {
- if (sclp.has_vt220 &&
- config_enabled(CONFIG_SCLP_VT220_CONSOLE))
+ if (sclp.has_vt220 && IS_ENABLED(CONFIG_SCLP_VT220_CONSOLE))
SET_CONSOLE_VT220;
- else if (sclp.has_linemode &&
- config_enabled(CONFIG_SCLP_CONSOLE))
+ else if (sclp.has_linemode && IS_ENABLED(CONFIG_SCLP_CONSOLE))
SET_CONSOLE_SCLP;
else
SET_CONSOLE_HVC;
KVM_SYNC_CRS |
KVM_SYNC_ARCH0 |
KVM_SYNC_PFAULT;
+ kvm_s390_set_prefix(vcpu, 0);
if (test_kvm_facility(vcpu->kvm, 64))
vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
/* fprs can be synchronized via vrs, even if the guest has no vx. With
return -EINVAL;
current->thread.fpu.fpc = fpu->fpc;
if (MACHINE_HAS_VX)
- convert_fp_to_vx(current->thread.fpu.vxrs, (freg_t *)fpu->fprs);
+ convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs,
+ (freg_t *) fpu->fprs);
else
- memcpy(current->thread.fpu.fprs, &fpu->fprs, sizeof(fpu->fprs));
+ memcpy(vcpu->run->s.regs.fprs, &fpu->fprs, sizeof(fpu->fprs));
return 0;
}
/* make sure we have the latest values */
save_fpu_regs();
if (MACHINE_HAS_VX)
- convert_vx_to_fp((freg_t *)fpu->fprs, current->thread.fpu.vxrs);
+ convert_vx_to_fp((freg_t *) fpu->fprs,
+ (__vector128 *) vcpu->run->s.regs.vrs);
else
- memcpy(fpu->fprs, current->thread.fpu.fprs, sizeof(fpu->fprs));
+ memcpy(fpu->fprs, vcpu->run->s.regs.fprs, sizeof(fpu->fprs));
fpu->fpc = current->thread.fpu.fpc;
return 0;
}
rc = gmap_mprotect_notify(vcpu->arch.gmap,
kvm_s390_get_prefix(vcpu),
PAGE_SIZE * 2, PROT_WRITE);
- if (rc)
+ if (rc) {
+ kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
return rc;
+ }
goto retry;
}
/* Validity 0x0044 will be checked by SIE */
if (rc)
goto unpin;
- scb_s->gvrd = hpa;
+ scb_s->riccbd = hpa;
}
return 0;
unpin:
EXPORT_SYMBOL(strrchr);
static inline int clcle(const char *s1, unsigned long l1,
- const char *s2, unsigned long l2,
- int *diff)
+ const char *s2, unsigned long l2)
{
register unsigned long r2 asm("2") = (unsigned long) s1;
- register unsigned long r3 asm("3") = (unsigned long) l2;
+ register unsigned long r3 asm("3") = (unsigned long) l1;
register unsigned long r4 asm("4") = (unsigned long) s2;
register unsigned long r5 asm("5") = (unsigned long) l2;
int cc;
" srl %0,28"
: "=&d" (cc), "+a" (r2), "+a" (r3),
"+a" (r4), "+a" (r5) : : "cc");
- *diff = *(char *)r2 - *(char *)r4;
return cc;
}
return (char *) s1;
l1 = __strend(s1) - s1;
while (l1-- >= l2) {
- int cc, dummy;
+ int cc;
- cc = clcle(s1, l1, s2, l2, &dummy);
+ cc = clcle(s1, l2, s2, l2);
if (!cc)
return (char *) s1;
s1++;
*/
int memcmp(const void *cs, const void *ct, size_t n)
{
- int ret, diff;
+ int ret;
- ret = clcle(cs, n, ct, n, &diff);
+ ret = clcle(cs, n, ct, n);
if (ret)
- ret = diff;
+ ret = ret == 1 ? -1 : 1;
return ret;
}
EXPORT_SYMBOL(memcmp);
unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n)
{
+ check_object_size(to, n, false);
if (static_branch_likely(&have_mvcos))
return copy_from_user_mvcos(to, from, n);
return copy_from_user_mvcp(to, from, n);
unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n)
{
+ check_object_size(from, n, true);
if (static_branch_likely(&have_mvcos))
return copy_to_user_mvcos(to, from, n);
return copy_to_user_mvcs(to, from, n);
int rc = -EINVAL;
pgd_t *pgdp;
+ if (addr == end)
+ return 0;
if (end >= MODULES_END)
return -EINVAL;
mutex_lock(&cpa_mutex);
__get_user_asm(val, "lw", ptr); \
break; \
case 8: \
- if ((copy_from_user((void *)&val, ptr, 8)) == 0) \
+ if (__copy_from_user((void *)&val, ptr, 8) == 0) \
__gu_err = 0; \
else \
__gu_err = -EFAULT; \
\
if (likely(access_ok(VERIFY_READ, __gu_ptr, size))) \
__get_user_common((x), size, __gu_ptr); \
+ else \
+ (x) = 0; \
\
__gu_err; \
})
"2:\n" \
".section .fixup,\"ax\"\n" \
"3:li %0, %4\n" \
+ "li %1, 0\n" \
"j 2b\n" \
".previous\n" \
".section __ex_table,\"a\"\n" \
static inline unsigned long
copy_from_user(void *to, const void *from, unsigned long len)
{
- unsigned long over;
+ unsigned long res = len;
- if (access_ok(VERIFY_READ, from, len))
- return __copy_tofrom_user(to, from, len);
+ if (likely(access_ok(VERIFY_READ, from, len)))
+ res = __copy_tofrom_user(to, from, len);
- if ((unsigned long)from < TASK_SIZE) {
- over = (unsigned long)from + len - TASK_SIZE;
- return __copy_tofrom_user(to, from, len - over) + over;
- }
- return len;
+ if (unlikely(res))
+ memset(to + (len - res), 0, res);
+
+ return res;
}
static inline unsigned long
copy_to_user(void *to, const void *from, unsigned long len)
{
- unsigned long over;
-
- if (access_ok(VERIFY_WRITE, to, len))
- return __copy_tofrom_user(to, from, len);
+ if (likely(access_ok(VERIFY_WRITE, to, len)))
+ len = __copy_tofrom_user(to, from, len);
- if ((unsigned long)to < TASK_SIZE) {
- over = (unsigned long)to + len - TASK_SIZE;
- return __copy_tofrom_user(to, from, len - over) + over;
- }
return len;
}
-#define __copy_from_user(to, from, len) \
- __copy_tofrom_user((to), (from), (len))
+static inline unsigned long
+__copy_from_user(void *to, const void *from, unsigned long len)
+{
+ unsigned long left = __copy_tofrom_user(to, from, len);
+ if (unlikely(left))
+ memset(to + (len - left), 0, left);
+ return left;
+}
#define __copy_to_user(to, from, len) \
__copy_tofrom_user((to), (from), (len))
static inline unsigned long
__copy_from_user_inatomic(void *to, const void *from, unsigned long len)
{
- return __copy_from_user(to, from, len);
+ return __copy_tofrom_user(to, from, len);
}
-#define __copy_in_user(to, from, len) __copy_from_user(to, from, len)
+#define __copy_in_user(to, from, len) __copy_tofrom_user(to, from, len)
static inline unsigned long
copy_in_user(void *to, const void *from, unsigned long len)
{
if (access_ok(VERIFY_READ, from, len) &&
access_ok(VERFITY_WRITE, to, len))
- return copy_from_user(to, from, len);
+ return __copy_tofrom_user(to, from, len);
}
/*
" movco.l %0, @%3 \n" \
" bf 1b \n" \
" synco \n" \
- : "=&z" (temp), "=&z" (res) \
+ : "=&z" (temp), "=&r" (res) \
: "r" (i), "r" (&v->counter) \
: "t"); \
\
__kernel_size_t __copy_size = (__kernel_size_t) n;
if (__copy_size && __access_ok(__copy_from, __copy_size))
- return __copy_user(to, from, __copy_size);
+ __copy_size = __copy_user(to, from, __copy_size);
+
+ if (unlikely(__copy_size))
+ memset(to + (n - __copy_size), 0, __copy_size);
return __copy_size;
}
#define __get_user_size(x,ptr,size,retval) \
do { \
retval = 0; \
+ x = 0; \
switch (size) { \
case 1: \
retval = __get_user_asm_b((void *)&x, \
select OLD_SIGSUSPEND
select ARCH_HAS_SG_CHAIN
select CPU_NO_EFFICIENT_FFS
+ select HAVE_ARCH_HARDENED_USERCOPY
config SPARC32
def_bool !64BIT
static inline unsigned long copy_to_user(void __user *to, const void *from, unsigned long n)
{
- if (n && __access_ok((unsigned long) to, n))
+ if (n && __access_ok((unsigned long) to, n)) {
+ check_object_size(from, n, true);
return __copy_user(to, (__force void __user *) from, n);
- else
+ } else
return n;
}
static inline unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n)
{
+ check_object_size(from, n, true);
return __copy_user(to, (__force void __user *) from, n);
}
static inline unsigned long copy_from_user(void *to, const void __user *from, unsigned long n)
{
- if (n && __access_ok((unsigned long) from, n))
+ if (n && __access_ok((unsigned long) from, n)) {
+ check_object_size(to, n, false);
return __copy_user((__force void __user *) to, from, n);
- else
+ } else {
+ memset(to, 0, n);
return n;
+ }
}
static inline unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n)
static inline unsigned long __must_check
copy_from_user(void *to, const void __user *from, unsigned long size)
{
- unsigned long ret = ___copy_from_user(to, from, size);
+ unsigned long ret;
+ check_object_size(to, size, false);
+
+ ret = ___copy_from_user(to, from, size);
if (unlikely(ret))
ret = copy_from_user_fixup(to, from, size);
static inline unsigned long __must_check
copy_to_user(void __user *to, const void *from, unsigned long size)
{
- unsigned long ret = ___copy_to_user(to, from, size);
+ unsigned long ret;
+
+ check_object_size(from, size, true);
+ ret = ___copy_to_user(to, from, size);
if (unlikely(ret))
ret = copy_to_user_fixup(to, from, size);
return ret;
config TILE
def_bool y
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
- select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAVE_NMI_SAFE_CMPXCHG
select ARCH_WANT_FRAME_POINTERS
return n;
}
-#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
-/*
- * There are still unprovable places in the generic code as of 2.6.34, so this
- * option is not really compatible with -Werror, which is more useful in
- * general.
- */
-extern void copy_from_user_overflow(void)
- __compiletime_warning("copy_from_user() size is not provably correct");
+extern void __compiletime_error("usercopy buffer size is too small")
+__bad_copy_user(void);
+
+static inline void copy_user_overflow(int size, unsigned long count)
+{
+ WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
+}
static inline unsigned long __must_check copy_from_user(void *to,
const void __user *from,
if (likely(sz == -1 || sz >= n))
n = _copy_from_user(to, from, n);
+ else if (!__builtin_constant_p(n))
+ copy_user_overflow(sz, n);
else
- copy_from_user_overflow();
+ __bad_copy_user();
return n;
}
-#else
-#define copy_from_user _copy_from_user
-#endif
#ifdef __tilegx__
/**
.altinstr_replacement : { *(.altinstr_replacement) }
/* .exit.text is discard at runtime, not link time, to deal with references
from .altinstructions and .eh_frame */
- .exit.text : { *(.exit.text) }
+ .exit.text : { EXIT_TEXT }
.exit.data : { *(.exit.data) }
.preinit_array : {
PT_REGS_SET_SYSCALL_RETURN(regs, -ENOSYS);
if (syscall_trace_enter(regs))
- return;
+ goto out;
/* Do the seccomp check after ptrace; failures should be fast. */
if (secure_computing(NULL) == -1)
- return;
+ goto out;
- /* Update the syscall number after orig_ax has potentially been updated
- * with ptrace.
- */
- UPT_SYSCALL_NR(r) = PT_SYSCALL_NR(r->gp);
syscall = UPT_SYSCALL_NR(r);
-
if (syscall >= 0 && syscall <= __NR_syscall_max)
PT_REGS_SET_SYSCALL_RETURN(regs,
EXECUTE_SYSCALL(syscall, regs));
+out:
syscall_trace_leave(regs);
}
}
static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
- bool write, bool foreign)
+ bool write, bool execute, bool foreign)
{
/* by default, allow everything */
return true;
select ARCH_DISCARD_MEMBLOCK
select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
- select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FAST_MULTIPLIER
select HAVE_ALIGNED_STRUCT_PAGE if SLUB
select HAVE_AOUT if X86_32
select HAVE_ARCH_AUDITSYSCALL
+ select HAVE_ARCH_HARDENED_USERCOPY
select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE
select HAVE_ARCH_JUMP_LABEL
select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP
select HAVE_ARCH_SOFT_DIRTY if X86_64
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+ select HAVE_ARCH_WITHIN_STACK_FRAMES
select HAVE_EBPF_JIT if X86_64
select HAVE_CC_STACKPROTECTOR
select HAVE_CMPXCHG_DOUBLE
return status;
}
-static efi_status_t exit_boot(struct boot_params *boot_params,
- void *handle, bool is64)
-{
- struct efi_info *efi = &boot_params->efi_info;
- unsigned long map_sz, key, desc_size;
- efi_memory_desc_t *mem_map;
+struct exit_boot_struct {
+ struct boot_params *boot_params;
+ struct efi_info *efi;
struct setup_data *e820ext;
- const char *signature;
__u32 e820ext_size;
- __u32 nr_desc, prev_nr_desc;
- efi_status_t status;
- __u32 desc_version;
- bool called_exit = false;
- u8 nr_entries;
- int i;
-
- nr_desc = 0;
- e820ext = NULL;
- e820ext_size = 0;
-
-get_map:
- status = efi_get_memory_map(sys_table, &mem_map, &map_sz, &desc_size,
- &desc_version, &key);
-
- if (status != EFI_SUCCESS)
- return status;
-
- prev_nr_desc = nr_desc;
- nr_desc = map_sz / desc_size;
- if (nr_desc > prev_nr_desc &&
- nr_desc > ARRAY_SIZE(boot_params->e820_map)) {
- u32 nr_e820ext = nr_desc - ARRAY_SIZE(boot_params->e820_map);
-
- status = alloc_e820ext(nr_e820ext, &e820ext, &e820ext_size);
- if (status != EFI_SUCCESS)
- goto free_mem_map;
+ bool is64;
+};
- efi_call_early(free_pool, mem_map);
- goto get_map; /* Allocated memory, get map again */
+static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
+ struct efi_boot_memmap *map,
+ void *priv)
+{
+ static bool first = true;
+ const char *signature;
+ __u32 nr_desc;
+ efi_status_t status;
+ struct exit_boot_struct *p = priv;
+
+ if (first) {
+ nr_desc = *map->buff_size / *map->desc_size;
+ if (nr_desc > ARRAY_SIZE(p->boot_params->e820_map)) {
+ u32 nr_e820ext = nr_desc -
+ ARRAY_SIZE(p->boot_params->e820_map);
+
+ status = alloc_e820ext(nr_e820ext, &p->e820ext,
+ &p->e820ext_size);
+ if (status != EFI_SUCCESS)
+ return status;
+ }
+ first = false;
}
- signature = is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
- memcpy(&efi->efi_loader_signature, signature, sizeof(__u32));
+ signature = p->is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
+ memcpy(&p->efi->efi_loader_signature, signature, sizeof(__u32));
- efi->efi_systab = (unsigned long)sys_table;
- efi->efi_memdesc_size = desc_size;
- efi->efi_memdesc_version = desc_version;
- efi->efi_memmap = (unsigned long)mem_map;
- efi->efi_memmap_size = map_sz;
+ p->efi->efi_systab = (unsigned long)sys_table_arg;
+ p->efi->efi_memdesc_size = *map->desc_size;
+ p->efi->efi_memdesc_version = *map->desc_ver;
+ p->efi->efi_memmap = (unsigned long)*map->map;
+ p->efi->efi_memmap_size = *map->map_size;
#ifdef CONFIG_X86_64
- efi->efi_systab_hi = (unsigned long)sys_table >> 32;
- efi->efi_memmap_hi = (unsigned long)mem_map >> 32;
+ p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32;
+ p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32;
#endif
+ return EFI_SUCCESS;
+}
+
+static efi_status_t exit_boot(struct boot_params *boot_params,
+ void *handle, bool is64)
+{
+ unsigned long map_sz, key, desc_size, buff_size;
+ efi_memory_desc_t *mem_map;
+ struct setup_data *e820ext;
+ __u32 e820ext_size;
+ efi_status_t status;
+ __u32 desc_version;
+ struct efi_boot_memmap map;
+ struct exit_boot_struct priv;
+
+ map.map = &mem_map;
+ map.map_size = &map_sz;
+ map.desc_size = &desc_size;
+ map.desc_ver = &desc_version;
+ map.key_ptr = &key;
+ map.buff_size = &buff_size;
+ priv.boot_params = boot_params;
+ priv.efi = &boot_params->efi_info;
+ priv.e820ext = NULL;
+ priv.e820ext_size = 0;
+ priv.is64 = is64;
+
/* Might as well exit boot services now */
- status = efi_call_early(exit_boot_services, handle, key);
- if (status != EFI_SUCCESS) {
- /*
- * ExitBootServices() will fail if any of the event
- * handlers change the memory map. In which case, we
- * must be prepared to retry, but only once so that
- * we're guaranteed to exit on repeated failures instead
- * of spinning forever.
- */
- if (called_exit)
- goto free_mem_map;
-
- called_exit = true;
- efi_call_early(free_pool, mem_map);
- goto get_map;
- }
+ status = efi_exit_boot_services(sys_table, handle, &map, &priv,
+ exit_boot_func);
+ if (status != EFI_SUCCESS)
+ return status;
+ e820ext = priv.e820ext;
+ e820ext_size = priv.e820ext_size;
/* Historic? */
boot_params->alt_mem_k = 32 * 1024;
return status;
return EFI_SUCCESS;
-
-free_mem_map:
- efi_call_early(free_pool, mem_map);
- return status;
}
/*
CONFIG_NOHIGHMEM=y
+# CONFIG_HIGHMEM4G is not set
+# CONFIG_HIGHMEM64G is not set
req = cast_mcryptd_ctx_to_req(req_ctx);
if (irqs_disabled())
- rctx->complete(&req->base, ret);
+ req_ctx->complete(&req->base, ret);
else {
local_bh_disable();
- rctx->complete(&req->base, ret);
+ req_ctx->complete(&req->base, ret);
local_bh_enable();
}
}
vpinsrd $1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0
vpinsrd $2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0
vpinsrd $3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0
- movl _args_digest+4*32(state, idx, 4), tmp2_w
+ vmovd _args_digest(state , idx, 4) , %xmm0
vpinsrd $1, _args_digest+5*32(state, idx, 4), %xmm1, %xmm1
vpinsrd $2, _args_digest+6*32(state, idx, 4), %xmm1, %xmm1
vpinsrd $3, _args_digest+7*32(state, idx, 4), %xmm1, %xmm1
- vmovdqu %xmm0, _result_digest(job_rax)
- movl tmp2_w, _result_digest+1*16(job_rax)
+ vmovdqu %xmm0, _result_digest(job_rax)
+ offset = (_result_digest + 1*16)
+ vmovdqu %xmm1, offset(job_rax)
pop %rbx
req = cast_mcryptd_ctx_to_req(req_ctx);
if (irqs_disabled())
- rctx->complete(&req->base, ret);
+ req_ctx->complete(&req->base, ret);
else {
local_bh_disable();
- rctx->complete(&req->base, ret);
+ req_ctx->complete(&req->base, ret);
local_bh_enable();
}
}
OBJECT_FILES_NON_STANDARD_entry_$(BITS).o := y
OBJECT_FILES_NON_STANDARD_entry_64_compat.o := y
+CFLAGS_syscall_64.o += -Wno-override-init
+CFLAGS_syscall_32.o += -Wno-override-init
obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
obj-y += common.o
jne opportunistic_sysret_failed
/*
- * SYSRET can't restore RF. SYSRET can restore TF, but unlike IRET,
- * restoring TF results in a trap from userspace immediately after
- * SYSRET. This would cause an infinite loop whenever #DB happens
- * with register state that satisfies the opportunistic SYSRET
- * conditions. For example, single-stepping this user code:
+ * SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot
+ * restore RF properly. If the slowpath sets it for whatever reason, we
+ * need to restore it correctly.
+ *
+ * SYSRET can restore TF, but unlike IRET, restoring TF results in a
+ * trap from userspace immediately after SYSRET. This would cause an
+ * infinite loop whenever #DB happens with register state that satisfies
+ * the opportunistic SYSRET conditions. For example, single-stepping
+ * this user code:
*
* movq $stuck_here, %rcx
* pushfq
.endm
#endif
+/* Make sure APIC interrupt handlers end up in the irqentry section: */
+#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN)
+# define PUSH_SECTION_IRQENTRY .pushsection .irqentry.text, "ax"
+# define POP_SECTION_IRQENTRY .popsection
+#else
+# define PUSH_SECTION_IRQENTRY
+# define POP_SECTION_IRQENTRY
+#endif
+
.macro apicinterrupt num sym do_sym
+PUSH_SECTION_IRQENTRY
apicinterrupt3 \num \sym \do_sym
trace_apicinterrupt \num \sym
+POP_SECTION_IRQENTRY
.endm
#ifdef CONFIG_SMP
{
[PERF_COUNT_HW_CPU_CYCLES] = 0x0076,
[PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
- [PERF_COUNT_HW_CACHE_REFERENCES] = 0x0080,
- [PERF_COUNT_HW_CACHE_MISSES] = 0x0081,
+ [PERF_COUNT_HW_CACHE_REFERENCES] = 0x077d,
+ [PERF_COUNT_HW_CACHE_MISSES] = 0x077e,
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2,
[PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3,
[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00d0, /* "Decoder empty" event */
#define COUNTER_SHIFT 16
+static HLIST_HEAD(uncore_unused_list);
+
struct amd_uncore {
int id;
int refcnt;
cpumask_t *active_mask;
struct pmu *pmu;
struct perf_event *events[MAX_COUNTERS];
- struct amd_uncore *free_when_cpu_online;
+ struct hlist_node node;
};
static struct amd_uncore * __percpu *amd_uncore_nb;
uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL;
uncore_nb->active_mask = &amd_nb_active_mask;
uncore_nb->pmu = &amd_nb_pmu;
+ uncore_nb->id = -1;
*per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb;
}
uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL;
uncore_l2->active_mask = &amd_l2_active_mask;
uncore_l2->pmu = &amd_l2_pmu;
+ uncore_l2->id = -1;
*per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2;
}
continue;
if (this->id == that->id) {
- that->free_when_cpu_online = this;
+ hlist_add_head(&this->node, &uncore_unused_list);
this = that;
break;
}
return 0;
}
+static void uncore_clean_online(void)
+{
+ struct amd_uncore *uncore;
+ struct hlist_node *n;
+
+ hlist_for_each_entry_safe(uncore, n, &uncore_unused_list, node) {
+ hlist_del(&uncore->node);
+ kfree(uncore);
+ }
+}
+
static void uncore_online(unsigned int cpu,
struct amd_uncore * __percpu *uncores)
{
struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu);
- kfree(uncore->free_when_cpu_online);
- uncore->free_when_cpu_online = NULL;
+ uncore_clean_online();
if (cpu == uncore->cpu)
cpumask_set_cpu(cpu, uncore->active_mask);
struct bts_ctx {
struct perf_output_handle handle;
struct debug_store ds_back;
- int started;
+ int state;
+};
+
+/* BTS context states: */
+enum {
+ /* no ongoing AUX transactions */
+ BTS_STATE_STOPPED = 0,
+ /* AUX transaction is on, BTS tracing is disabled */
+ BTS_STATE_INACTIVE,
+ /* AUX transaction is on, BTS tracing is running */
+ BTS_STATE_ACTIVE,
};
static DEFINE_PER_CPU(struct bts_ctx, bts_ctx);
static int
bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle);
+/*
+ * Ordering PMU callbacks wrt themselves and the PMI is done by means
+ * of bts::state, which:
+ * - is set when bts::handle::event is valid, that is, between
+ * perf_aux_output_begin() and perf_aux_output_end();
+ * - is zero otherwise;
+ * - is ordered against bts::handle::event with a compiler barrier.
+ */
+
static void __bts_event_start(struct perf_event *event)
{
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
/*
* local barrier to make sure that ds configuration made it
- * before we enable BTS
+ * before we enable BTS and bts::state goes ACTIVE
*/
wmb();
+ /* INACTIVE/STOPPED -> ACTIVE */
+ WRITE_ONCE(bts->state, BTS_STATE_ACTIVE);
+
intel_pmu_enable_bts(config);
}
__bts_event_start(event);
- /* PMI handler: this counter is running and likely generating PMIs */
- ACCESS_ONCE(bts->started) = 1;
-
return;
fail_end_stop:
event->hw.state = PERF_HES_STOPPED;
}
-static void __bts_event_stop(struct perf_event *event)
+static void __bts_event_stop(struct perf_event *event, int state)
{
+ struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+
+ /* ACTIVE -> INACTIVE(PMI)/STOPPED(->stop()) */
+ WRITE_ONCE(bts->state, state);
+
/*
* No extra synchronization is mandated by the documentation to have
* BTS data stores globally visible.
*/
intel_pmu_disable_bts();
-
- if (event->hw.state & PERF_HES_STOPPED)
- return;
-
- ACCESS_ONCE(event->hw.state) |= PERF_HES_STOPPED;
}
static void bts_event_stop(struct perf_event *event, int flags)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
- struct bts_buffer *buf = perf_get_aux(&bts->handle);
+ struct bts_buffer *buf = NULL;
+ int state = READ_ONCE(bts->state);
- /* PMI handler: don't restart this counter */
- ACCESS_ONCE(bts->started) = 0;
+ if (state == BTS_STATE_ACTIVE)
+ __bts_event_stop(event, BTS_STATE_STOPPED);
- __bts_event_stop(event);
+ if (state != BTS_STATE_STOPPED)
+ buf = perf_get_aux(&bts->handle);
+
+ event->hw.state |= PERF_HES_STOPPED;
if (flags & PERF_EF_UPDATE) {
bts_update(bts);
bts->handle.head =
local_xchg(&buf->data_size,
buf->nr_pages << PAGE_SHIFT);
+
perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
!!local_xchg(&buf->lost, 0));
}
void intel_bts_enable_local(void)
{
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+ int state = READ_ONCE(bts->state);
+
+ /*
+ * Here we transition from INACTIVE to ACTIVE;
+ * if we instead are STOPPED from the interrupt handler,
+ * stay that way. Can't be ACTIVE here though.
+ */
+ if (WARN_ON_ONCE(state == BTS_STATE_ACTIVE))
+ return;
+
+ if (state == BTS_STATE_STOPPED)
+ return;
- if (bts->handle.event && bts->started)
+ if (bts->handle.event)
__bts_event_start(bts->handle.event);
}
{
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+ /*
+ * Here we transition from ACTIVE to INACTIVE;
+ * do nothing for STOPPED or INACTIVE.
+ */
+ if (READ_ONCE(bts->state) != BTS_STATE_ACTIVE)
+ return;
+
if (bts->handle.event)
- __bts_event_stop(bts->handle.event);
+ __bts_event_stop(bts->handle.event, BTS_STATE_INACTIVE);
}
static int
return 0;
head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1);
- if (WARN_ON_ONCE(head != local_read(&buf->head)))
- return -EINVAL;
phys = &buf->buf[buf->cur_buf];
space = phys->offset + phys->displacement + phys->size - head;
int intel_bts_interrupt(void)
{
+ struct debug_store *ds = this_cpu_ptr(&cpu_hw_events)->ds;
struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
struct perf_event *event = bts->handle.event;
struct bts_buffer *buf;
s64 old_head;
- int err;
+ int err = -ENOSPC, handled = 0;
- if (!event || !bts->started)
- return 0;
+ /*
+ * The only surefire way of knowing if this NMI is ours is by checking
+ * the write ptr against the PMI threshold.
+ */
+ if (ds && (ds->bts_index >= ds->bts_interrupt_threshold))
+ handled = 1;
+
+ /*
+ * this is wrapped in intel_bts_enable_local/intel_bts_disable_local,
+ * so we can only be INACTIVE or STOPPED
+ */
+ if (READ_ONCE(bts->state) == BTS_STATE_STOPPED)
+ return handled;
buf = perf_get_aux(&bts->handle);
+ if (!buf)
+ return handled;
+
/*
* Skip snapshot counters: they don't use the interrupt, but
* there's no other way of telling, because the pointer will
* keep moving
*/
- if (!buf || buf->snapshot)
+ if (buf->snapshot)
return 0;
old_head = local_read(&buf->head);
/* no new data */
if (old_head == local_read(&buf->head))
- return 0;
+ return handled;
perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0),
!!local_xchg(&buf->lost, 0));
buf = perf_aux_output_begin(&bts->handle, event);
- if (!buf)
- return 1;
+ if (buf)
+ err = bts_buffer_reset(buf, &bts->handle);
+
+ if (err) {
+ WRITE_ONCE(bts->state, BTS_STATE_STOPPED);
- err = bts_buffer_reset(buf, &bts->handle);
- if (err)
- perf_aux_output_end(&bts->handle, 0, false);
+ if (buf) {
+ /*
+ * BTS_STATE_STOPPED should be visible before
+ * cleared handle::event
+ */
+ barrier();
+ perf_aux_output_end(&bts->handle, 0, false);
+ }
+ }
return 1;
}
if (!boot_cpu_has(X86_FEATURE_DTES64) || !x86_pmu.bts)
return -ENODEV;
- bts_pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_ITRACE;
+ bts_pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_ITRACE |
+ PERF_PMU_CAP_EXCLUSIVE;
bts_pmu.task_ctx_nr = perf_sw_context;
bts_pmu.event_init = bts_event_init;
bts_pmu.add = bts_event_add;
* disabled state if called consecutively.
*
* During consecutive calls, the same disable value will be written to related
- * registers, so the PMU state remains unchanged. hw.state in
- * intel_bts_disable_local will remain PERF_HES_STOPPED too in consecutive
- * calls.
+ * registers, so the PMU state remains unchanged.
+ *
+ * intel_bts events don't coexist with intel PMU's BTS events because of
+ * x86_add_exclusive(x86_lbr_exclusive_lbr); there's no need to keep them
+ * disabled around intel PMU's event batching etc, only inside the PMI handler.
*/
static void __intel_pmu_disable_all(void)
{
if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
intel_pmu_disable_bts();
- else
- intel_bts_disable_local();
intel_pmu_pebs_disable_all();
}
return;
intel_pmu_enable_bts(event->hw.config);
- } else
- intel_bts_enable_local();
+ }
}
static void intel_pmu_enable_all(int added)
*/
if (!x86_pmu.late_ack)
apic_write(APIC_LVTPC, APIC_DM_NMI);
+ intel_bts_disable_local();
__intel_pmu_disable_all();
handled = intel_pmu_drain_bts_buffer();
handled += intel_bts_interrupt();
/* Only restore PMU state when it's active. See x86_pmu_disable(). */
if (cpuc->enabled)
__intel_pmu_enable_all(0, true);
+ intel_bts_enable_local();
/*
* Only unmask the NMI after the overflow counters
static void init_mbm_sample(u32 rmid, u32 evt_type);
static void __intel_mbm_event_count(void *info);
+static bool is_cqm_event(int e)
+{
+ return (e == QOS_L3_OCCUP_EVENT_ID);
+}
+
static bool is_mbm_event(int e)
{
return (e >= QOS_MBM_TOTAL_EVENT_ID && e <= QOS_MBM_LOCAL_EVENT_ID);
(event->attr.config > QOS_MBM_LOCAL_EVENT_ID))
return -EINVAL;
+ if ((is_cqm_event(event->attr.config) && !cqm_enabled) ||
+ (is_mbm_event(event->attr.config) && !mbm_enabled))
+ return -EINVAL;
+
/* unsupported modes and filters */
if (event->attr.exclude_user ||
event->attr.exclude_kernel ||
struct pebs_record_nhm *p = at;
u64 pebs_status;
- /* PEBS v3 has accurate status bits */
+ pebs_status = p->status & cpuc->pebs_enabled;
+ pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
+
+ /* PEBS v3 has more accurate status bits */
if (x86_pmu.intel_cap.pebs_format >= 3) {
- for_each_set_bit(bit, (unsigned long *)&p->status,
- MAX_PEBS_EVENTS)
+ for_each_set_bit(bit, (unsigned long *)&pebs_status,
+ x86_pmu.max_pebs_events)
counts[bit]++;
continue;
}
- pebs_status = p->status & cpuc->pebs_enabled;
- pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
-
/*
* On some CPUs the PEBS status can be zero when PEBS is
* racing with clearing of GLOBAL_STATUS.
continue;
event = cpuc->events[bit];
- WARN_ON_ONCE(!event);
- WARN_ON_ONCE(!event->attr.precise_ip);
+ if (WARN_ON_ONCE(!event))
+ continue;
+
+ if (WARN_ON_ONCE(!event->attr.precise_ip))
+ continue;
/* log dropped samples number */
if (error[bit])
event->hw.addr_filters = NULL;
}
+static inline bool valid_kernel_ip(unsigned long ip)
+{
+ return virt_addr_valid(ip) && kernel_ip(ip);
+}
+
static int pt_event_addr_filters_validate(struct list_head *filters)
{
struct perf_addr_filter *filter;
list_for_each_entry(filter, filters, entry) {
/* PT doesn't support single address triggers */
- if (!filter->range)
+ if (!filter->range || !filter->size)
return -EOPNOTSUPP;
- if (!filter->inode && !kernel_ip(filter->offset))
- return -EINVAL;
+ if (!filter->inode) {
+ if (!valid_kernel_ip(filter->offset))
+ return -EINVAL;
+
+ if (!valid_kernel_ip(filter->offset + filter->size))
+ return -EINVAL;
+ }
if (++range > pt_cap_get(PT_CAP_num_address_ranges))
return -EOPNOTSUPP;
} else {
/* apply the offset */
msr_a = filter->offset + offs[range];
- msr_b = filter->size + msr_a;
+ msr_b = filter->size + msr_a - 1;
}
filters->filter[range].msr_a = msr_a;
}
}
+static void snb_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+ wrmsrl(SNB_UNC_PERF_GLOBAL_CTL,
+ SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL);
+}
+
static void snb_uncore_msr_exit_box(struct intel_uncore_box *box)
{
if (box->pmu->pmu_idx == 0)
static struct intel_uncore_ops snb_uncore_msr_ops = {
.init_box = snb_uncore_msr_init_box,
+ .enable_box = snb_uncore_msr_enable_box,
.exit_box = snb_uncore_msr_exit_box,
.disable_event = snb_uncore_msr_disable_event,
.enable_event = snb_uncore_msr_enable_event,
}
}
+static void skl_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+ wrmsrl(SKL_UNC_PERF_GLOBAL_CTL,
+ SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL);
+}
+
static void skl_uncore_msr_exit_box(struct intel_uncore_box *box)
{
if (box->pmu->pmu_idx == 0)
static struct intel_uncore_ops skl_uncore_msr_ops = {
.init_box = skl_uncore_msr_init_box,
+ .enable_box = skl_uncore_msr_enable_box,
.exit_box = skl_uncore_msr_exit_box,
.disable_event = snb_uncore_msr_disable_event,
.enable_event = snb_uncore_msr_enable_event,
static struct intel_uncore_type hswep_uncore_ha = {
.name = "ha",
- .num_counters = 5,
+ .num_counters = 4,
.num_boxes = 2,
.perf_ctr_bits = 48,
SNBEP_UNCORE_PCI_COMMON_INIT(),
static struct intel_uncore_type hswep_uncore_imc = {
.name = "imc",
- .num_counters = 5,
+ .num_counters = 4,
.num_boxes = 8,
.perf_ctr_bits = 48,
.fixed_ctr_bits = 48,
static struct intel_uncore_type hswep_uncore_qpi = {
.name = "qpi",
- .num_counters = 5,
+ .num_counters = 4,
.num_boxes = 3,
.perf_ctr_bits = 48,
.perf_ctr = SNBEP_PCI_PMON_CTR0,
static struct intel_uncore_type hswep_uncore_r3qpi = {
.name = "r3qpi",
- .num_counters = 4,
+ .num_counters = 3,
.num_boxes = 3,
.perf_ctr_bits = 44,
.constraints = hswep_uncore_r3qpi_constraints,
static struct intel_uncore_type bdx_uncore_imc = {
.name = "imc",
- .num_counters = 5,
+ .num_counters = 4,
.num_boxes = 8,
.perf_ctr_bits = 48,
.fixed_ctr_bits = 48,
void register_lapic_address(unsigned long address);
extern void setup_boot_APIC_clock(void);
extern void setup_secondary_APIC_clock(void);
+extern void lapic_update_tsc_freq(void);
extern int APIC_init_uniprocessor(void);
#ifdef CONFIG_X86_64
static inline void disable_local_APIC(void) { }
# define setup_boot_APIC_clock x86_init_noop
# define setup_secondary_APIC_clock x86_init_noop
+static inline void lapic_update_tsc_freq(void) { }
#endif /* !CONFIG_X86_LOCAL_APIC */
#ifdef CONFIG_X86_X2APIC
#ifdef CONFIG_SMP
unsigned int irq_resched_count;
unsigned int irq_call_count;
- /*
- * irq_tlb_count is double-counted in irq_call_count, so it must be
- * subtracted from irq_call_count when displaying irq_call_count
- */
unsigned int irq_tlb_count;
#endif
#ifdef CONFIG_X86_THERMAL_VECTOR
void *(*alloc_pgt_page)(void *); /* allocate buf for page table */
void *context; /* context for alloc_pgt_page */
unsigned long pmd_flag; /* page flag for PMD entry */
- bool kernel_mapping; /* kernel mapping or ident mapping */
+ unsigned long offset; /* ident mapping offset */
};
int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
- unsigned long addr, unsigned long end);
+ unsigned long pstart, unsigned long pend);
#endif /* _ASM_X86_INIT_H */
*
* | ... | 11| 10| 9|8|7|6|5| 4| 3|2|1|0| <- bit number
* | ... |SW3|SW2|SW1|G|L|D|A|CD|WT|U|W|P| <- bit names
- * | OFFSET (14->63) | TYPE (10-13) |0|X|X|X| X| X|X|X|0| <- swp entry
+ * | OFFSET (14->63) | TYPE (9-13) |0|X|X|X| X| X|X|X|0| <- swp entry
*
* G (8) is aliased and used as a PROT_NONE indicator for
* !present ptes. We need to start storing swap entries above
#define SWP_TYPE_FIRST_BIT (_PAGE_BIT_PROTNONE + 1)
#define SWP_TYPE_BITS 5
/* Place the offset above the type: */
-#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS + 1)
+#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS)
#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
extern unsigned char secondary_startup_64[];
#endif
+static inline size_t real_mode_size_needed(void)
+{
+ if (real_mode_header)
+ return 0; /* already allocated. */
+
+ return ALIGN(real_mode_blob_end - real_mode_blob, PAGE_SIZE);
+}
+
+void set_real_mode_mem(phys_addr_t mem, size_t size);
void reserve_real_mode(void);
-void setup_real_mode(void);
#endif /* _ARCH_X86_REALMODE_H */
return sp;
}
+/*
+ * Walks up the stack frames to make sure that the specified object is
+ * entirely contained by a single stack frame.
+ *
+ * Returns:
+ * 1 if within a frame
+ * -1 if placed across a frame boundary (or outside stack)
+ * 0 unable to determine (no frame pointers, etc)
+ */
+static inline int arch_within_stack_frames(const void * const stack,
+ const void * const stackend,
+ const void *obj, unsigned long len)
+{
+#if defined(CONFIG_FRAME_POINTER)
+ const void *frame = NULL;
+ const void *oldframe;
+
+ oldframe = __builtin_frame_address(1);
+ if (oldframe)
+ frame = __builtin_frame_address(2);
+ /*
+ * low ----------------------------------------------> high
+ * [saved bp][saved ip][args][local vars][saved bp][saved ip]
+ * ^----------------^
+ * allow copies only within here
+ */
+ while (stack <= frame && frame < stackend) {
+ /*
+ * If obj + len extends past the last frame, this
+ * check won't pass and the next frame will be 0,
+ * causing us to bail out and correctly report
+ * the copy as invalid.
+ */
+ if (obj + len <= frame)
+ return obj >= oldframe + 2 * sizeof(void *) ? 1 : -1;
+ oldframe = frame;
+ frame = *(const void * const *)frame;
+ }
+ return -1;
+#else
+ return 0;
+#endif
+}
+
#else /* !__ASSEMBLY__ */
#ifdef CONFIG_X86_64
static inline void __native_flush_tlb(void)
{
+ /*
+ * If current->mm == NULL then we borrow a mm which may change during a
+ * task switch and therefore we must not be preempted while we write CR3
+ * back:
+ */
+ preempt_disable();
native_write_cr3(native_read_cr3());
+ preempt_enable();
}
static inline void __native_flush_tlb_global_irq_disabled(void)
#define __get_user_asm_ex(x, addr, itype, rtype, ltype) \
asm volatile("1: mov"itype" %1,%"rtype"0\n" \
"2:\n" \
- _ASM_EXTABLE_EX(1b, 2b) \
+ ".section .fixup,\"ax\"\n" \
+ "3:xor"itype" %"rtype"0,%"rtype"0\n" \
+ " jmp 2b\n" \
+ ".previous\n" \
+ _ASM_EXTABLE_EX(1b, 3b) \
: ltype(x) : "m" (__m(addr)))
#define __put_user_nocheck(x, ptr, size) \
unsigned long __must_check _copy_to_user(void __user *to, const void *from,
unsigned n);
-#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
-# define copy_user_diag __compiletime_error
-#else
-# define copy_user_diag __compiletime_warning
-#endif
-
-extern void copy_user_diag("copy_from_user() buffer size is too small")
-copy_from_user_overflow(void);
-extern void copy_user_diag("copy_to_user() buffer size is too small")
-copy_to_user_overflow(void) __asm__("copy_from_user_overflow");
-
-#undef copy_user_diag
-
-#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
-
-extern void
-__compiletime_warning("copy_from_user() buffer size is not provably correct")
-__copy_from_user_overflow(void) __asm__("copy_from_user_overflow");
-#define __copy_from_user_overflow(size, count) __copy_from_user_overflow()
-
-extern void
-__compiletime_warning("copy_to_user() buffer size is not provably correct")
-__copy_to_user_overflow(void) __asm__("copy_from_user_overflow");
-#define __copy_to_user_overflow(size, count) __copy_to_user_overflow()
-
-#else
+extern void __compiletime_error("usercopy buffer size is too small")
+__bad_copy_user(void);
-static inline void
-__copy_from_user_overflow(int size, unsigned long count)
+static inline void copy_user_overflow(int size, unsigned long count)
{
WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
}
-#define __copy_to_user_overflow __copy_from_user_overflow
-
-#endif
-
-static inline unsigned long __must_check
+static __always_inline unsigned long __must_check
copy_from_user(void *to, const void __user *from, unsigned long n)
{
int sz = __compiletime_object_size(to);
kasan_check_write(to, n);
- /*
- * While we would like to have the compiler do the checking for us
- * even in the non-constant size case, any false positives there are
- * a problem (especially when DEBUG_STRICT_USER_COPY_CHECKS, but even
- * without - the [hopefully] dangerous looking nature of the warning
- * would make people go look at the respecitive call sites over and
- * over again just to find that there's no problem).
- *
- * And there are cases where it's just not realistic for the compiler
- * to prove the count to be in range. For example when multiple call
- * sites of a helper function - perhaps in different source files -
- * all doing proper range checking, yet the helper function not doing
- * so again.
- *
- * Therefore limit the compile time checking to the constant size
- * case, and do only runtime checking for non-constant sizes.
- */
-
- if (likely(sz < 0 || sz >= n))
+ if (likely(sz < 0 || sz >= n)) {
+ check_object_size(to, n, false);
n = _copy_from_user(to, from, n);
- else if(__builtin_constant_p(n))
- copy_from_user_overflow();
+ } else if (!__builtin_constant_p(n))
+ copy_user_overflow(sz, n);
else
- __copy_from_user_overflow(sz, n);
+ __bad_copy_user();
return n;
}
-static inline unsigned long __must_check
+static __always_inline unsigned long __must_check
copy_to_user(void __user *to, const void *from, unsigned long n)
{
int sz = __compiletime_object_size(from);
might_fault();
- /* See the comment in copy_from_user() above. */
- if (likely(sz < 0 || sz >= n))
+ if (likely(sz < 0 || sz >= n)) {
+ check_object_size(from, n, true);
n = _copy_to_user(to, from, n);
- else if(__builtin_constant_p(n))
- copy_to_user_overflow();
+ } else if (!__builtin_constant_p(n))
+ copy_user_overflow(sz, n);
else
- __copy_to_user_overflow(sz, n);
+ __bad_copy_user();
return n;
}
-#undef __copy_from_user_overflow
-#undef __copy_to_user_overflow
-
/*
* We rely on the nested NMI work to allow atomic faults from the NMI path; the
* nested NMI paths are careful to preserve CR2.
#define user_access_begin() __uaccess_begin()
#define user_access_end() __uaccess_end()
-#define unsafe_put_user(x, ptr) \
-({ \
+#define unsafe_put_user(x, ptr, err_label) \
+do { \
int __pu_err; \
__put_user_size((x), (ptr), sizeof(*(ptr)), __pu_err, -EFAULT); \
- __builtin_expect(__pu_err, 0); \
-})
+ if (unlikely(__pu_err)) goto err_label; \
+} while (0)
-#define unsafe_get_user(x, ptr) \
-({ \
+#define unsafe_get_user(x, ptr, err_label) \
+do { \
int __gu_err; \
unsigned long __gu_val; \
__get_user_size(__gu_val, (ptr), sizeof(*(ptr)), __gu_err, -EFAULT); \
(x) = (__force __typeof__(*(ptr)))__gu_val; \
- __builtin_expect(__gu_err, 0); \
-})
+ if (unlikely(__gu_err)) goto err_label; \
+} while (0)
#endif /* _ASM_X86_UACCESS_H */
static __always_inline unsigned long __must_check
__copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
{
+ check_object_size(from, n, true);
return __copy_to_user_ll(to, from, n);
}
__copy_from_user(void *to, const void __user *from, unsigned long n)
{
might_fault();
+ check_object_size(to, n, false);
if (__builtin_constant_p(n)) {
unsigned long ret;
{
int ret = 0;
+ check_object_size(dst, size, false);
if (!__builtin_constant_p(size))
return copy_user_generic(dst, (__force void *)src, size);
switch (size) {
{
int ret = 0;
+ check_object_size(src, size, true);
if (!__builtin_constant_p(size))
return copy_user_generic((__force void *)dst, src, size);
switch (size) {
u16 nasid; /* HNasid */
u16 sockid; /* Socket ID, high bits of APIC ID */
u16 pnode; /* Index to MMR and GRU spaces */
- u32 pxm; /* ACPI proximity domain number */
+ u32 unused2;
u32 limit; /* PA bits 56:26 (UV_GAM_RANGE_SHFT) */
};
#define UV_SYSTAB_VERSION_UV4 0x400 /* UV4 BIOS base version */
#define UV_SYSTAB_VERSION_UV4_1 0x401 /* + gpa_shift */
#define UV_SYSTAB_VERSION_UV4_2 0x402 /* + TYPE_NVRAM/WINDOW/MBOX */
-#define UV_SYSTAB_VERSION_UV4_LATEST UV_SYSTAB_VERSION_UV4_2
+#define UV_SYSTAB_VERSION_UV4_3 0x403 /* - GAM Range PXM Value */
+#define UV_SYSTAB_VERSION_UV4_LATEST UV_SYSTAB_VERSION_UV4_3
#define UV_SYSTAB_TYPE_UNUSED 0 /* End of table (offset == 0) */
#define UV_SYSTAB_TYPE_GAM_PARAMS 1 /* GAM PARAM conversions */
/* Clock divisor */
#define APIC_DIVISOR 16
-#define TSC_DIVISOR 32
+#define TSC_DIVISOR 8
/*
* This function sets up the local APIC timer, with a timeout of
CLOCK_EVT_FEAT_DUMMY);
levt->set_next_event = lapic_next_deadline;
clockevents_config_and_register(levt,
- (tsc_khz / TSC_DIVISOR) * 1000,
+ tsc_khz * (1000 / TSC_DIVISOR),
0xF, ~0UL);
} else
clockevents_register_device(levt);
}
+/*
+ * Install the updated TSC frequency from recalibration at the TSC
+ * deadline clockevent devices.
+ */
+static void __lapic_update_tsc_freq(void *info)
+{
+ struct clock_event_device *levt = this_cpu_ptr(&lapic_events);
+
+ if (!this_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
+ return;
+
+ clockevents_update_freq(levt, tsc_khz * (1000 / TSC_DIVISOR));
+}
+
+void lapic_update_tsc_freq(void)
+{
+ /*
+ * The clockevent device's ->mult and ->shift can both be
+ * changed. In order to avoid races, schedule the frequency
+ * update code on each CPU.
+ */
+ on_each_cpu(__lapic_update_tsc_freq, NULL, 0);
+}
+
/*
* In this functions we calibrate APIC bus clocks to the external timer.
*
unsigned long flags;
int ret, ir_stat;
+ if (skip_ioapic_setup)
+ return;
+
ir_stat = irq_remapping_prepare();
if (ir_stat < 0 && !x2apic_supported())
return;
return -EINVAL;
}
- num_processors++;
if (apicid == boot_cpu_physical_apicid) {
/*
* x86_bios_cpu_apicid is required to have processors listed
pr_warning("APIC: Package limit reached. Processor %d/0x%x ignored.\n",
thiscpu, apicid);
+
disabled_cpus++;
return -ENOSPC;
}
+ num_processors++;
+
/*
* Validate version
*/
/*
* At CPU state changes, update the x2apic cluster sibling info.
*/
-int x2apic_prepare_cpu(unsigned int cpu)
+static int x2apic_prepare_cpu(unsigned int cpu)
{
if (!zalloc_cpumask_var(&per_cpu(cpus_in_cluster, cpu), GFP_KERNEL))
return -ENOMEM;
return 0;
}
-int x2apic_dead_cpu(unsigned int this_cpu)
+static int x2apic_dead_cpu(unsigned int this_cpu)
{
int cpu;
static int x2apic_cluster_probe(void)
{
int cpu = smp_processor_id();
+ int ret;
if (!x2apic_mode)
return 0;
+ ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE",
+ x2apic_prepare_cpu, x2apic_dead_cpu);
+ if (ret < 0) {
+ pr_err("Failed to register X2APIC_PREPARE\n");
+ return 0;
+ }
cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, cpu));
- cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE",
- x2apic_prepare_cpu, x2apic_dead_cpu);
return 1;
}
if (strncmp(oem_id, "SGI", 3) != 0)
return 0;
+ if (numa_off) {
+ pr_err("UV: NUMA is off, disabling UV support\n");
+ return 0;
+ }
+
/* Setup early hub type field in uv_hub_info for Node 0 */
uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0;
struct uv_gam_range_entry *gre = uv_gre_table;
struct uv_gam_range_s *grt;
unsigned long last_limit = 0, ram_limit = 0;
- int bytes, i, sid, lsid = -1;
+ int bytes, i, sid, lsid = -1, indx = 0, lindx = -1;
if (!gre)
return;
}
sid = gre->sockid - _min_socket;
if (lsid < sid) { /* new range */
- grt = &_gr_table[sid];
- grt->base = lsid;
+ grt = &_gr_table[indx];
+ grt->base = lindx;
grt->nasid = gre->nasid;
grt->limit = last_limit = gre->limit;
lsid = sid;
+ lindx = indx++;
continue;
}
if (lsid == sid && !ram_limit) { /* update range */
}
if (!ram_limit) { /* non-contiguous ram range */
grt++;
- grt->base = sid - 1;
+ grt->base = lindx;
grt->nasid = gre->nasid;
grt->limit = last_limit = gre->limit;
continue;
for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
if (!index) {
pr_info("UV: GAM Range Table...\n");
- pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s %3s\n",
+ pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n",
"Range", "", "Size", "Type", "NASID",
- "SID", "PN", "PXM");
+ "SID", "PN");
}
pr_info(
- "UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x %3d\n",
+ "UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x\n",
index++,
(unsigned long)lgre << UV_GAM_RANGE_SHFT,
(unsigned long)gre->limit << UV_GAM_RANGE_SHFT,
((unsigned long)(gre->limit - lgre)) >>
(30 - UV_GAM_RANGE_SHFT), /* 64M -> 1G */
- gre->type, gre->nasid, gre->sockid,
- gre->pnode, gre->pxm);
+ gre->type, gre->nasid, gre->sockid, gre->pnode);
lgre = gre->limit;
if (sock_min > gre->sockid)
_pnode_to_socket[i] = SOCK_EMPTY;
/* fill in pnode/node/addr conversion list values */
- pr_info("UV: GAM Building socket/pnode/pxm conversion tables\n");
+ pr_info("UV: GAM Building socket/pnode conversion tables\n");
for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
if (gre->type == UV_GAM_RANGE_TYPE_HOLE)
continue;
if (_socket_to_pnode[i] != SOCK_EMPTY)
continue; /* duplicate */
_socket_to_pnode[i] = gre->pnode;
- _socket_to_node[i] = gre->pxm;
i = gre->pnode - minpnode;
_pnode_to_socket[i] = gre->sockid;
pr_info(
- "UV: sid:%02x type:%d nasid:%04x pn:%02x pxm:%2d pn2s:%2x\n",
+ "UV: sid:%02x type:%d nasid:%04x pn:%02x pn2s:%2x\n",
gre->sockid, gre->type, gre->nasid,
_socket_to_pnode[gre->sockid - minsock],
- _socket_to_node[gre->sockid - minsock],
_pnode_to_socket[gre->pnode - minpnode]);
}
- /* check socket -> node values */
+ /* Set socket -> node values */
lnid = -1;
for_each_present_cpu(cpu) {
int nid = cpu_to_node(cpu);
lnid = nid;
apicid = per_cpu(x86_cpu_to_apicid, cpu);
sockid = apicid >> uv_cpuid.socketid_shift;
- i = sockid - minsock;
-
- if (nid != _socket_to_node[i]) {
- pr_warn(
- "UV: %02x: type:%d socket:%02x PXM:%02x != node:%2d\n",
- i, sockid, gre->type, _socket_to_node[i], nid);
- _socket_to_node[i] = nid;
- }
+ _socket_to_node[sockid - minsock] = nid;
+ pr_info("UV: sid:%02x: apicid:%04x node:%2d\n",
+ sockid, apicid, nid);
}
/* Setup physical blade to pnode translation from GAM Range Table */
set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
}
+#define MSR_AMD64_DE_CFG 0xC0011029
+
+static void init_amd_ln(struct cpuinfo_x86 *c)
+{
+ /*
+ * Apply erratum 665 fix unconditionally so machines without a BIOS
+ * fix work.
+ */
+ msr_set_bit(MSR_AMD64_DE_CFG, 31);
+}
+
static void init_amd_bd(struct cpuinfo_x86 *c)
{
u64 value;
case 6: init_amd_k7(c); break;
case 0xf: init_amd_k8(c); break;
case 0x10: init_amd_gh(c); break;
+ case 0x12: init_amd_ln(c); break;
case 0x15: init_amd_bd(c); break;
}
*/
static u8 *container;
static size_t container_size;
+static bool ucode_builtin;
static u32 ucode_new_rev;
static u8 amd_ucode_patch[PATCH_MAX_SIZE];
void __init load_ucode_amd_bsp(unsigned int family)
{
struct cpio_data cp;
+ bool *builtin;
void **data;
size_t *size;
#ifdef CONFIG_X86_32
data = (void **)__pa_nodebug(&ucode_cpio.data);
size = (size_t *)__pa_nodebug(&ucode_cpio.size);
+ builtin = (bool *)__pa_nodebug(&ucode_builtin);
#else
data = &ucode_cpio.data;
size = &ucode_cpio.size;
+ builtin = &ucode_builtin;
#endif
- if (!load_builtin_amd_microcode(&cp, family))
+ *builtin = load_builtin_amd_microcode(&cp, family);
+ if (!*builtin)
cp = find_ucode_in_initrd();
if (!(cp.data && cp.size))
unsigned int cpu = smp_processor_id();
struct equiv_cpu_entry *eq;
struct microcode_amd *mc;
+ u8 *cont = container;
u32 rev, eax;
u16 eq_id;
if (check_current_patch_level(&rev, false))
return;
+ /* Add CONFIG_RANDOMIZE_MEMORY offset. */
+ if (!ucode_builtin)
+ cont += PAGE_OFFSET - __PAGE_OFFSET_BASE;
+
eax = cpuid_eax(0x00000001);
- eq = (struct equiv_cpu_entry *)(container + CONTAINER_HDR_SZ);
+ eq = (struct equiv_cpu_entry *)(cont + CONTAINER_HDR_SZ);
eq_id = find_equiv_id(eq, eax);
if (!eq_id)
else
container = cont_va;
+ /* Add CONFIG_RANDOMIZE_MEMORY offset. */
+ if (!ucode_builtin)
+ container += PAGE_OFFSET - __PAGE_OFFSET_BASE;
+
eax = cpuid_eax(0x00000001);
eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
return get_xsave_addr(&fpu->state.xsave, xsave_state);
}
-
-/*
- * Set xfeatures (aka XSTATE_BV) bit for a feature that we want
- * to take out of its "init state". This will ensure that an
- * XRSTOR actually restores the state.
- */
-static void fpu__xfeature_set_non_init(struct xregs_state *xsave,
- int xstate_feature_mask)
-{
- xsave->header.xfeatures |= xstate_feature_mask;
-}
-
-/*
- * This function is safe to call whether the FPU is in use or not.
- *
- * Note that this only works on the current task.
- *
- * Inputs:
- * @xsave_state: state which is defined in xsave.h (e.g. XFEATURE_MASK_FP,
- * XFEATURE_MASK_SSE, etc...)
- * @xsave_state_ptr: a pointer to a copy of the state that you would
- * like written in to the current task's FPU xsave state. This pointer
- * must not be located in the current tasks's xsave area.
- * Output:
- * address of the state in the xsave area or NULL if the state
- * is not present or is in its 'init state'.
- */
-static void fpu__xfeature_set_state(int xstate_feature_mask,
- void *xstate_feature_src, size_t len)
-{
- struct xregs_state *xsave = ¤t->thread.fpu.state.xsave;
- struct fpu *fpu = ¤t->thread.fpu;
- void *dst;
-
- if (!boot_cpu_has(X86_FEATURE_XSAVE)) {
- WARN_ONCE(1, "%s() attempted with no xsave support", __func__);
- return;
- }
-
- /*
- * Tell the FPU code that we need the FPU state to be in
- * 'fpu' (not in the registers), and that we need it to
- * be stable while we write to it.
- */
- fpu__current_fpstate_write_begin();
-
- /*
- * This method *WILL* *NOT* work for compact-format
- * buffers. If the 'xstate_feature_mask' is unset in
- * xcomp_bv then we may need to move other feature state
- * "up" in the buffer.
- */
- if (xsave->header.xcomp_bv & xstate_feature_mask) {
- WARN_ON_ONCE(1);
- goto out;
- }
-
- /* find the location in the xsave buffer of the desired state */
- dst = __raw_xsave_addr(&fpu->state.xsave, xstate_feature_mask);
-
- /*
- * Make sure that the pointer being passed in did not
- * come from the xsave buffer itself.
- */
- WARN_ONCE(xstate_feature_src == dst, "set from xsave buffer itself");
-
- /* put the caller-provided data in the location */
- memcpy(dst, xstate_feature_src, len);
-
- /*
- * Mark the xfeature so that the CPU knows there is state
- * in the buffer now.
- */
- fpu__xfeature_set_non_init(xsave, xstate_feature_mask);
-out:
- /*
- * We are done writing to the 'fpu'. Reenable preeption
- * and (possibly) move the fpstate back in to the fpregs.
- */
- fpu__current_fpstate_write_end();
-}
-
#define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2)
#define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1)
/*
- * This will go out and modify the XSAVE buffer so that PKRU is
- * set to a particular state for access to 'pkey'.
- *
- * PKRU state does affect kernel access to user memory. We do
- * not modfiy PKRU *itself* here, only the XSAVE state that will
- * be restored in to PKRU when we return back to userspace.
+ * This will go out and modify PKRU register to set the access
+ * rights for @pkey to @init_val.
*/
int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
unsigned long init_val)
{
- struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
- struct pkru_state *old_pkru_state;
- struct pkru_state new_pkru_state;
+ u32 old_pkru;
int pkey_shift = (pkey * PKRU_BITS_PER_PKEY);
u32 new_pkru_bits = 0;
*/
if (!boot_cpu_has(X86_FEATURE_OSPKE))
return -EINVAL;
+ /*
+ * For most XSAVE components, this would be an arduous task:
+ * brining fpstate up to date with fpregs, updating fpstate,
+ * then re-populating fpregs. But, for components that are
+ * never lazily managed, we can just access the fpregs
+ * directly. PKRU is never managed lazily, so we can just
+ * manipulate it directly. Make sure it stays that way.
+ */
+ WARN_ON_ONCE(!use_eager_fpu());
/* Set the bits we need in PKRU: */
if (init_val & PKEY_DISABLE_ACCESS)
/* Shift the bits in to the correct place in PKRU for pkey: */
new_pkru_bits <<= pkey_shift;
- /* Locate old copy of the state in the xsave buffer: */
- old_pkru_state = get_xsave_addr(xsave, XFEATURE_MASK_PKRU);
-
- /*
- * When state is not in the buffer, it is in the init
- * state, set it manually. Otherwise, copy out the old
- * state.
- */
- if (!old_pkru_state)
- new_pkru_state.pkru = 0;
- else
- new_pkru_state.pkru = old_pkru_state->pkru;
-
- /* Mask off any old bits in place: */
- new_pkru_state.pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift);
-
- /* Set the newly-requested bits: */
- new_pkru_state.pkru |= new_pkru_bits;
-
- /*
- * We could theoretically live without zeroing pkru.pad.
- * The current XSAVE feature state definition says that
- * only bytes 0->3 are used. But we do not want to
- * chance leaking kernel stack out to userspace in case a
- * memcpy() of the whole xsave buffer was done.
- *
- * They're in the same cacheline anyway.
- */
- new_pkru_state.pad = 0;
+ /* Get old PKRU and mask off any old bits in place: */
+ old_pkru = read_pkru();
+ old_pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift);
- fpu__xfeature_set_state(XFEATURE_MASK_PKRU, &new_pkru_state, sizeof(new_pkru_state));
+ /* Write old part along with new part: */
+ write_pkru(old_pkru | new_pkru_bits);
return 0;
}
/* Initialize 32bit specific setup functions */
x86_init.resources.reserve_resources = i386_reserve_resources;
x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc;
-
- reserve_bios_regions();
}
asmlinkage __visible void __init i386_start_kernel(void)
copy_bootdata(__va(real_mode_data));
x86_early_init_platform_quirks();
- reserve_bios_regions();
switch (boot_params.hdr.hardware_subarch) {
case X86_SUBARCH_INTEL_MID:
memset(&curr_time, 0, sizeof(struct rtc_time));
if (hpet_rtc_flags & (RTC_UIE | RTC_AIE))
- mc146818_set_time(&curr_time);
+ mc146818_get_time(&curr_time);
if (hpet_rtc_flags & RTC_UIE &&
curr_time.tm_sec != hpet_prev_update_sec) {
seq_puts(p, " Rescheduling interrupts\n");
seq_printf(p, "%*s: ", prec, "CAL");
for_each_online_cpu(j)
- seq_printf(p, "%10u ", irq_stats(j)->irq_call_count -
- irq_stats(j)->irq_tlb_count);
+ seq_printf(p, "%10u ", irq_stats(j)->irq_call_count);
seq_puts(p, " Function call interrupts\n");
seq_printf(p, "%*s: ", prec, "TLB");
for_each_online_cpu(j)
put_cpu();
x86_platform.calibrate_tsc = kvm_get_tsc_khz;
+ x86_platform.calibrate_cpu = kvm_get_tsc_khz;
x86_platform.get_wallclock = kvm_get_wallclock;
x86_platform.set_wallclock = kvm_set_wallclock;
#ifdef CONFIG_X86_LOCAL_APIC
".popsection");
/* identity function, which can be inlined */
-u32 _paravirt_ident_32(u32 x)
+u32 notrace _paravirt_ident_32(u32 x)
{
return x;
}
-u64 _paravirt_ident_64(u64 x)
+u64 notrace _paravirt_ident_64(u64 x)
{
return x;
}
x86_init.oem.arch_setup();
- kernel_randomize_memory();
-
iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
setup_memory_map();
parse_setup_data();
max_possible_pfn = max_pfn;
+ /*
+ * Define random base addresses for memory sections after max_pfn is
+ * defined and before each memory section base is used.
+ */
+ kernel_randomize_memory();
+
#ifdef CONFIG_X86_32
/* max_low_pfn get updated here */
find_low_pfn_range();
efi_find_mirror();
}
+ reserve_bios_regions();
+
/*
* The EFI specification says that boot service code won't be called
* after ExitBootServices(). This is, in fact, a lie.
early_trap_pf_init();
- setup_real_mode();
+ /*
+ * Update mmu_cr4_features (and, indirectly, trampoline_cr4_features)
+ * with the current CR4 value. This may not be necessary, but
+ * auditing all the early-boot CR4 manipulation would be needed to
+ * rule it out.
+ */
+ if (boot_cpu_data.cpuid_level >= 0)
+ /* A CPU has %cr4 if and only if it has CPUID. */
+ mmu_cr4_features = __read_cr4();
memblock_set_current_limit(get_max_mapped());
kasan_init();
- if (boot_cpu_data.cpuid_level >= 0) {
- /* A CPU has %cr4 if and only if it has CPUID */
- mmu_cr4_features = __read_cr4();
- if (trampoline_cr4_features)
- *trampoline_cr4_features = mmu_cr4_features;
- }
-
#ifdef CONFIG_X86_32
/* sync back kernel address range */
clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
/* Logical package management. We might want to allocate that dynamically */
static int *physical_to_logical_pkg __read_mostly;
static unsigned long *physical_package_map __read_mostly;;
-static unsigned long *logical_package_map __read_mostly;
static unsigned int max_physical_pkg_id __read_mostly;
unsigned int __max_logical_packages __read_mostly;
EXPORT_SYMBOL(__max_logical_packages);
+static unsigned int logical_packages __read_mostly;
+static bool logical_packages_frozen __read_mostly;
/* Maximum number of SMT threads on any online core */
int __max_smt_threads __read_mostly;
if (test_and_set_bit(pkg, physical_package_map))
goto found;
- new = find_first_zero_bit(logical_package_map, __max_logical_packages);
- if (new >= __max_logical_packages) {
+ if (logical_packages_frozen) {
physical_to_logical_pkg[pkg] = -1;
- pr_warn("APIC(%x) Package %u exceeds logical package map\n",
+ pr_warn("APIC(%x) Package %u exceeds logical package max\n",
apicid, pkg);
return -ENOSPC;
}
- set_bit(new, logical_package_map);
+
+ new = logical_packages++;
pr_info("APIC(%x) Converting physical %u to logical package %u\n",
apicid, pkg, new);
physical_to_logical_pkg[pkg] = new;
}
__max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus);
+ logical_packages = 0;
/*
* Possibly larger than what we need as the number of apic ids per
memset(physical_to_logical_pkg, 0xff, size);
size = BITS_TO_LONGS(max_physical_pkg_id) * sizeof(unsigned long);
physical_package_map = kzalloc(size, GFP_KERNEL);
- size = BITS_TO_LONGS(__max_logical_packages) * sizeof(unsigned long);
- logical_package_map = kzalloc(size, GFP_KERNEL);
-
- pr_info("Max logical packages: %u\n", __max_logical_packages);
for_each_present_cpu(cpu) {
unsigned int apicid = apic->cpu_present_to_apicid(cpu);
set_cpu_possible(cpu, false);
set_cpu_present(cpu, false);
}
+
+ if (logical_packages > __max_logical_packages) {
+ pr_warn("Detected more packages (%u), then computed by BIOS data (%u).\n",
+ logical_packages, __max_logical_packages);
+ logical_packages_frozen = true;
+ __max_logical_packages = logical_packages;
+ }
+
+ pr_info("Max logical packages: %u\n", __max_logical_packages);
}
void __init smp_store_boot_cpu_info(void)
#include <asm/nmi.h>
#include <asm/x86_init.h>
#include <asm/geode.h>
+#include <asm/apic.h>
unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */
EXPORT_SYMBOL(cpu_khz);
(unsigned long)tsc_khz / 1000,
(unsigned long)tsc_khz % 1000);
+ /* Inform the TSC deadline clockevent devices about the recalibration */
+ lapic_update_tsc_freq();
+
out:
if (boot_cpu_has(X86_FEATURE_ART))
art_related_clocksource = &clocksource_tsc;
*cursor &= 0xfe;
}
/*
- * Similar treatment for VEX3 prefix.
- * TODO: add XOP/EVEX treatment when insn decoder supports them
+ * Similar treatment for VEX3/EVEX prefix.
+ * TODO: add XOP treatment when insn decoder supports them
*/
- if (insn->vex_prefix.nbytes == 3) {
+ if (insn->vex_prefix.nbytes >= 3) {
/*
* vex2: c5 rvvvvLpp (has no b bit)
* vex3/xop: c4/8f rxbmmmmm wvvvvLpp
* evex: 62 rxbR00mm wvvvv1pp zllBVaaa
- * (evex will need setting of both b and x since
- * in non-sib encoding evex.x is 4th bit of MODRM.rm)
- * Setting VEX3.b (setting because it has inverted meaning):
+ * Setting VEX3.b (setting because it has inverted meaning).
+ * Setting EVEX.x since (in non-SIB encoding) EVEX.x
+ * is the 4th bit of MODRM.rm, and needs the same treatment.
+ * For VEX3-encoded insns, VEX3.x value has no effect in
+ * non-SIB encoding, the change is superfluous but harmless.
*/
cursor = auprobe->insn + insn_offset_vex_prefix(insn) + 1;
- *cursor |= 0x20;
+ *cursor |= 0x60;
}
/*
reg = MODRM_REG(insn); /* Fetch modrm.reg */
reg2 = 0xff; /* Fetch vex.vvvv */
- if (insn->vex_prefix.nbytes == 2)
- reg2 = insn->vex_prefix.bytes[1];
- else if (insn->vex_prefix.nbytes == 3)
+ if (insn->vex_prefix.nbytes)
reg2 = insn->vex_prefix.bytes[2];
/*
- * TODO: add XOP, EXEV vvvv reading.
+ * TODO: add XOP vvvv reading.
*
* vex.vvvv field is in bits 6-3, bits are inverted.
* But in 32-bit mode, high-order bit may be ignored.
{
bool new_val, old_val;
struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
+ struct dest_map *dest_map = &ioapic->rtc_status.dest_map;
union kvm_ioapic_redirect_entry *e;
e = &ioapic->redirtbl[RTC_GSI];
return;
new_val = kvm_apic_pending_eoi(vcpu, e->fields.vector);
- old_val = test_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
+ old_val = test_bit(vcpu->vcpu_id, dest_map->map);
if (new_val == old_val)
return;
if (new_val) {
- __set_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
+ __set_bit(vcpu->vcpu_id, dest_map->map);
+ dest_map->vectors[vcpu->vcpu_id] = e->fields.vector;
ioapic->rtc_status.pending_eoi++;
} else {
- __clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map.map);
+ __clear_bit(vcpu->vcpu_id, dest_map->map);
ioapic->rtc_status.pending_eoi--;
rtc_status_pending_eoi_check_valid(ioapic);
}
static struct kvm_event_hw_type_mapping amd_event_mapping[] = {
[0] = { 0x76, 0x00, PERF_COUNT_HW_CPU_CYCLES },
[1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS },
- [2] = { 0x80, 0x00, PERF_COUNT_HW_CACHE_REFERENCES },
- [3] = { 0x81, 0x00, PERF_COUNT_HW_CACHE_MISSES },
+ [2] = { 0x7d, 0x07, PERF_COUNT_HW_CACHE_REFERENCES },
+ [3] = { 0x7e, 0x07, PERF_COUNT_HW_CACHE_MISSES },
[4] = { 0xc2, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
[5] = { 0xc3, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
[6] = { 0xd0, 0x00, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND },
struct list_head vmcs02_pool;
int vmcs02_num;
u64 vmcs01_tsc_offset;
+ bool change_vmcs01_virtual_x2apic_mode;
/* L2 must run next, and mustn't decide to exit to L1. */
bool nested_run_pending;
/*
bool pi_pending;
u16 posted_intr_nv;
+ unsigned long *msr_bitmap;
+
struct hrtimer preemption_timer;
bool preemption_timer_expired;
static unsigned long *vmx_msr_bitmap_longmode;
static unsigned long *vmx_msr_bitmap_legacy_x2apic;
static unsigned long *vmx_msr_bitmap_longmode_x2apic;
-static unsigned long *vmx_msr_bitmap_nested;
static unsigned long *vmx_vmread_bitmap;
static unsigned long *vmx_vmwrite_bitmap;
new.control) != old.control);
}
+static void decache_tsc_multiplier(struct vcpu_vmx *vmx)
+{
+ vmx->current_tsc_ratio = vmx->vcpu.arch.tsc_scaling_ratio;
+ vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
+}
+
/*
* Switches to specified vcpu, until a matching vcpu_put(), but assumes
* vcpu mutex is already taken.
/* Setup TSC multiplier */
if (kvm_has_tsc_control &&
- vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) {
- vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio;
- vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
- }
+ vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio)
+ decache_tsc_multiplier(vmx);
vmx_vcpu_pi_load(vcpu, cpu);
vmx->host_pkru = read_pkru();
unsigned long *msr_bitmap;
if (is_guest_mode(vcpu))
- msr_bitmap = vmx_msr_bitmap_nested;
+ msr_bitmap = to_vmx(vcpu)->nested.msr_bitmap;
else if (cpu_has_secondary_exec_ctrls() &&
(vmcs_read32(SECONDARY_VM_EXEC_CONTROL) &
SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) {
if (!vmx_msr_bitmap_longmode_x2apic)
goto out4;
- if (nested) {
- vmx_msr_bitmap_nested =
- (unsigned long *)__get_free_page(GFP_KERNEL);
- if (!vmx_msr_bitmap_nested)
- goto out5;
- }
-
vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
if (!vmx_vmread_bitmap)
goto out6;
memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE);
memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE);
- if (nested)
- memset(vmx_msr_bitmap_nested, 0xff, PAGE_SIZE);
if (setup_vmcs_config(&vmcs_config) < 0) {
r = -EIO;
out7:
free_page((unsigned long)vmx_vmread_bitmap);
out6:
- if (nested)
- free_page((unsigned long)vmx_msr_bitmap_nested);
-out5:
free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
out4:
free_page((unsigned long)vmx_msr_bitmap_longmode);
free_page((unsigned long)vmx_io_bitmap_a);
free_page((unsigned long)vmx_vmwrite_bitmap);
free_page((unsigned long)vmx_vmread_bitmap);
- if (nested)
- free_page((unsigned long)vmx_msr_bitmap_nested);
free_kvm_area();
}
return 1;
}
+ if (cpu_has_vmx_msr_bitmap()) {
+ vmx->nested.msr_bitmap =
+ (unsigned long *)__get_free_page(GFP_KERNEL);
+ if (!vmx->nested.msr_bitmap)
+ goto out_msr_bitmap;
+ }
+
vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL);
if (!vmx->nested.cached_vmcs12)
- return -ENOMEM;
+ goto out_cached_vmcs12;
if (enable_shadow_vmcs) {
shadow_vmcs = alloc_vmcs();
- if (!shadow_vmcs) {
- kfree(vmx->nested.cached_vmcs12);
- return -ENOMEM;
- }
+ if (!shadow_vmcs)
+ goto out_shadow_vmcs;
/* mark vmcs as shadow */
shadow_vmcs->revision_id |= (1u << 31);
/* init shadow vmcs */
skip_emulated_instruction(vcpu);
nested_vmx_succeed(vcpu);
return 1;
+
+out_shadow_vmcs:
+ kfree(vmx->nested.cached_vmcs12);
+
+out_cached_vmcs12:
+ free_page((unsigned long)vmx->nested.msr_bitmap);
+
+out_msr_bitmap:
+ return -ENOMEM;
}
/*
vmx->nested.vmxon = false;
free_vpid(vmx->nested.vpid02);
nested_release_vmcs12(vmx);
+ if (vmx->nested.msr_bitmap) {
+ free_page((unsigned long)vmx->nested.msr_bitmap);
+ vmx->nested.msr_bitmap = NULL;
+ }
if (enable_shadow_vmcs)
free_vmcs(vmx->nested.current_shadow_vmcs);
kfree(vmx->nested.cached_vmcs12);
{
u32 sec_exec_control;
+ /* Postpone execution until vmcs01 is the current VMCS. */
+ if (is_guest_mode(vcpu)) {
+ to_vmx(vcpu)->nested.change_vmcs01_virtual_x2apic_mode = true;
+ return;
+ }
+
/*
* There is not point to enable virtualize x2apic without enable
* apicv
{
int msr;
struct page *page;
- unsigned long *msr_bitmap;
+ unsigned long *msr_bitmap_l1;
+ unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.msr_bitmap;
+ /* This shortcut is ok because we support only x2APIC MSRs so far. */
if (!nested_cpu_has_virt_x2apic_mode(vmcs12))
return false;
WARN_ON(1);
return false;
}
- msr_bitmap = (unsigned long *)kmap(page);
- if (!msr_bitmap) {
+ msr_bitmap_l1 = (unsigned long *)kmap(page);
+ if (!msr_bitmap_l1) {
nested_release_page_clean(page);
WARN_ON(1);
return false;
}
+ memset(msr_bitmap_l0, 0xff, PAGE_SIZE);
+
if (nested_cpu_has_virt_x2apic_mode(vmcs12)) {
if (nested_cpu_has_apic_reg_virt(vmcs12))
for (msr = 0x800; msr <= 0x8ff; msr++)
nested_vmx_disable_intercept_for_msr(
- msr_bitmap,
- vmx_msr_bitmap_nested,
+ msr_bitmap_l1, msr_bitmap_l0,
msr, MSR_TYPE_R);
- /* TPR is allowed */
- nested_vmx_disable_intercept_for_msr(msr_bitmap,
- vmx_msr_bitmap_nested,
+
+ nested_vmx_disable_intercept_for_msr(
+ msr_bitmap_l1, msr_bitmap_l0,
APIC_BASE_MSR + (APIC_TASKPRI >> 4),
MSR_TYPE_R | MSR_TYPE_W);
+
if (nested_cpu_has_vid(vmcs12)) {
- /* EOI and self-IPI are allowed */
nested_vmx_disable_intercept_for_msr(
- msr_bitmap,
- vmx_msr_bitmap_nested,
+ msr_bitmap_l1, msr_bitmap_l0,
APIC_BASE_MSR + (APIC_EOI >> 4),
MSR_TYPE_W);
nested_vmx_disable_intercept_for_msr(
- msr_bitmap,
- vmx_msr_bitmap_nested,
+ msr_bitmap_l1, msr_bitmap_l0,
APIC_BASE_MSR + (APIC_SELF_IPI >> 4),
MSR_TYPE_W);
}
- } else {
- /*
- * Enable reading intercept of all the x2apic
- * MSRs. We should not rely on vmcs12 to do any
- * optimizations here, it may have been modified
- * by L1.
- */
- for (msr = 0x800; msr <= 0x8ff; msr++)
- __vmx_enable_intercept_for_msr(
- vmx_msr_bitmap_nested,
- msr,
- MSR_TYPE_R);
-
- __vmx_enable_intercept_for_msr(
- vmx_msr_bitmap_nested,
- APIC_BASE_MSR + (APIC_TASKPRI >> 4),
- MSR_TYPE_W);
- __vmx_enable_intercept_for_msr(
- vmx_msr_bitmap_nested,
- APIC_BASE_MSR + (APIC_EOI >> 4),
- MSR_TYPE_W);
- __vmx_enable_intercept_for_msr(
- vmx_msr_bitmap_nested,
- APIC_BASE_MSR + (APIC_SELF_IPI >> 4),
- MSR_TYPE_W);
}
kunmap(page);
nested_release_page_clean(page);
}
if (cpu_has_vmx_msr_bitmap() &&
- exec_control & CPU_BASED_USE_MSR_BITMAPS) {
- nested_vmx_merge_msr_bitmap(vcpu, vmcs12);
- /* MSR_BITMAP will be set by following vmx_set_efer. */
- } else
+ exec_control & CPU_BASED_USE_MSR_BITMAPS &&
+ nested_vmx_merge_msr_bitmap(vcpu, vmcs12))
+ ; /* MSR_BITMAP will be set by following vmx_set_efer. */
+ else
exec_control &= ~CPU_BASED_USE_MSR_BITMAPS;
/*
vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset);
else
vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset);
+ if (kvm_has_tsc_control)
+ decache_tsc_multiplier(vmx);
if (enable_vpid) {
/*
else
vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
PIN_BASED_VMX_PREEMPTION_TIMER);
+ if (kvm_has_tsc_control)
+ decache_tsc_multiplier(vmx);
+
+ if (vmx->nested.change_vmcs01_virtual_x2apic_mode) {
+ vmx->nested.change_vmcs01_virtual_x2apic_mode = false;
+ vmx_set_virtual_x2apic_mode(vcpu,
+ vcpu->arch.apic_base & X2APIC_ENABLE);
+ }
/* This is needed for same reason as it was needed in prepare_vmcs02 */
vmx->host_rsp = 0;
if (tsc_delta < 0)
mark_tsc_unstable("KVM discovered backwards TSC");
- if (kvm_lapic_hv_timer_in_use(vcpu) &&
- kvm_x86_ops->set_hv_timer(vcpu,
- kvm_get_lapic_tscdeadline_msr(vcpu)))
- kvm_lapic_switch_to_sw_timer(vcpu);
if (check_tsc_unstable()) {
u64 offset = kvm_compute_tsc_offset(vcpu,
vcpu->arch.last_guest_tsc);
kvm_x86_ops->write_tsc_offset(vcpu, offset);
vcpu->arch.tsc_catchup = 1;
}
+ if (kvm_lapic_hv_timer_in_use(vcpu) &&
+ kvm_x86_ops->set_hv_timer(vcpu,
+ kvm_get_lapic_tscdeadline_msr(vcpu)))
+ kvm_lapic_switch_to_sw_timer(vcpu);
/*
* On a host with synchronized TSC, there is no need to update
* kvmclock on vcpu->cpu migration
ENTRY(__sw_hweight64)
#ifdef CONFIG_X86_64
+ pushq %rdi
pushq %rdx
movq %rdi, %rdx # w -> t
shrq $56, %rax # w = w_tmp >> 56
popq %rdx
+ popq %rdi
ret
#else /* CONFIG_X86_32 */
/* We're getting an u64 arg in (%eax,%edx): unsigned long hweight64(__u64 w) */
#include <asm/cpufeature.h>
#include <asm/setup.h>
-#define debug_putstr(v) early_printk(v)
+#define debug_putstr(v) early_printk("%s", v)
#define has_cpuflag(f) boot_cpu_has(f)
#define get_boot_seed() kaslr_offset()
#endif
* included by both the compressed kernel and the regular kernel.
*/
-static void ident_pmd_init(unsigned long pmd_flag, pmd_t *pmd_page,
+static void ident_pmd_init(struct x86_mapping_info *info, pmd_t *pmd_page,
unsigned long addr, unsigned long end)
{
addr &= PMD_MASK;
for (; addr < end; addr += PMD_SIZE) {
pmd_t *pmd = pmd_page + pmd_index(addr);
- if (!pmd_present(*pmd))
- set_pmd(pmd, __pmd(addr | pmd_flag));
+ if (pmd_present(*pmd))
+ continue;
+
+ set_pmd(pmd, __pmd((addr - info->offset) | info->pmd_flag));
}
}
if (pud_present(*pud)) {
pmd = pmd_offset(pud, 0);
- ident_pmd_init(info->pmd_flag, pmd, addr, next);
+ ident_pmd_init(info, pmd, addr, next);
continue;
}
pmd = (pmd_t *)info->alloc_pgt_page(info->context);
if (!pmd)
return -ENOMEM;
- ident_pmd_init(info->pmd_flag, pmd, addr, next);
+ ident_pmd_init(info, pmd, addr, next);
set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
}
}
int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
- unsigned long addr, unsigned long end)
+ unsigned long pstart, unsigned long pend)
{
+ unsigned long addr = pstart + info->offset;
+ unsigned long end = pend + info->offset;
unsigned long next;
int result;
- int off = info->kernel_mapping ? pgd_index(__PAGE_OFFSET) : 0;
for (; addr < end; addr = next) {
- pgd_t *pgd = pgd_page + pgd_index(addr) + off;
+ pgd_t *pgd = pgd_page + pgd_index(addr);
pud_t *pud;
next = (addr & PGDIR_MASK) + PGDIR_SIZE;
return __va(pfn << PAGE_SHIFT);
}
-/* need 3 4k for initial PMD_SIZE, 3 4k for 0-ISA_END_ADDRESS */
-#define INIT_PGT_BUF_SIZE (6 * PAGE_SIZE)
+/*
+ * By default need 3 4k for initial PMD_SIZE, 3 4k for 0-ISA_END_ADDRESS.
+ * With KASLR memory randomization, depending on the machine e820 memory
+ * and the PUD alignment. We may need twice more pages when KASLR memory
+ * randomization is enabled.
+ */
+#ifndef CONFIG_RANDOMIZE_MEMORY
+#define INIT_PGD_PAGE_COUNT 6
+#else
+#define INIT_PGD_PAGE_COUNT 12
+#endif
+#define INIT_PGT_BUF_SIZE (INIT_PGD_PAGE_COUNT * PAGE_SIZE)
RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE);
void __init early_alloc_pgt_buf(void)
{
*/
static inline bool kaslr_memory_enabled(void)
{
- return kaslr_enabled() && !config_enabled(CONFIG_KASAN);
+ return kaslr_enabled() && !IS_ENABLED(CONFIG_KASAN);
}
/* Initialize base and padding for each memory region randomized with KASLR */
* add padding if needed (especially for memory hotplug support).
*/
BUG_ON(kaslr_regions[0].base != &page_offset_base);
- memory_tb = ((max_pfn << PAGE_SHIFT) >> TB_SHIFT) +
+ memory_tb = DIV_ROUND_UP(max_pfn << PAGE_SHIFT, 1UL << TB_SHIFT) +
CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING;
/* Adapt phyiscal memory region size based on available memory */
}
}
-static int populate_pmd(struct cpa_data *cpa,
- unsigned long start, unsigned long end,
- unsigned num_pages, pud_t *pud, pgprot_t pgprot)
+static long populate_pmd(struct cpa_data *cpa,
+ unsigned long start, unsigned long end,
+ unsigned num_pages, pud_t *pud, pgprot_t pgprot)
{
- unsigned int cur_pages = 0;
+ long cur_pages = 0;
pmd_t *pmd;
pgprot_t pmd_pgprot;
return num_pages;
}
-static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
- pgprot_t pgprot)
+static long populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
+ pgprot_t pgprot)
{
pud_t *pud;
unsigned long end;
- int cur_pages = 0;
+ long cur_pages = 0;
pgprot_t pud_pgprot;
end = start + (cpa->numpages << PAGE_SHIFT);
/* Map trailing leftover */
if (start < end) {
- int tmp;
+ long tmp;
pud = pud_offset(pgd, start);
if (pud_none(*pud))
pgprot_t pgprot = __pgprot(_KERNPG_TABLE);
pud_t *pud = NULL; /* shut up gcc */
pgd_t *pgd_entry;
- int ret;
+ long ret;
pgd_entry = cpa->pgd + pgd_index(addr);
static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
{
- int ret, numpages = cpa->numpages;
+ unsigned long numpages = cpa->numpages;
+ int ret;
while (numpages) {
/*
}
/*
- * prot is passed in as a parameter for the new mapping. If the vma has a
- * linear pfn mapping for the entire range reserve the entire vma range with
- * single reserve_pfn_range call.
+ * prot is passed in as a parameter for the new mapping. If the vma has
+ * a linear pfn mapping for the entire range, or no vma is provided,
+ * reserve the entire pfn + size range with single reserve_pfn_range
+ * call.
*/
int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
unsigned long pfn, unsigned long addr, unsigned long size)
enum page_cache_mode pcm;
/* reserve the whole chunk starting from paddr */
- if (addr == vma->vm_start && size == (vma->vm_end - vma->vm_start)) {
+ if (!vma || (addr == vma->vm_start
+ && size == (vma->vm_end - vma->vm_start))) {
int ret;
ret = reserve_pfn_range(paddr, size, prot, 0);
- if (!ret)
+ if (ret == 0 && vma)
vma->vm_flags |= VM_PAT;
return ret;
}
resource_size_t paddr;
unsigned long prot;
- if (!(vma->vm_flags & VM_PAT))
+ if (vma && !(vma->vm_flags & VM_PAT))
return;
/* free the chunk starting from pfn or the whole chunk */
size = vma->vm_end - vma->vm_start;
}
free_pfn_range(paddr, size);
- vma->vm_flags &= ~VM_PAT;
+ if (vma)
+ vma->vm_flags &= ~VM_PAT;
}
/*
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_zone);
/*
- * Broadwell EP Home Agent BARs erroneously return non-zero values when read.
+ * Device [8086:2fc0]
+ * Erratum HSE43
+ * CONFIG_TDP_NOMINAL CSR Implemented at Incorrect Offset
+ * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v3-spec-update.html
*
- * See http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v4-spec-update.html
- * entry BDF2.
+ * Devices [8086:6f60,6fa0,6fc0]
+ * Erratum BDF2
+ * PCI BARs in the Home Agent Will Return Non-Zero Values During Enumeration
+ * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v4-spec-update.html
*/
-static void pci_bdwep_bar(struct pci_dev *dev)
+static void pci_invalid_bar(struct pci_dev *dev)
{
dev->non_compliant_bars = 1;
}
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_bdwep_bar);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_bdwep_bar);
-DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_bdwep_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_invalid_bar);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_invalid_bar);
* @node: list item for parent traversal.
* @rcu: RCU callback item for freeing.
* @irq: back pointer to parent.
+ * @enabled: true if driver enabled IRQ
* @virq: the virtual IRQ value provided to the requesting driver.
*
* Every MSI/MSI-X IRQ requested for a device in a VMD domain will be mapped to
struct list_head node;
struct rcu_head rcu;
struct vmd_irq_list *irq;
+ bool enabled;
unsigned int virq;
};
unsigned long flags;
raw_spin_lock_irqsave(&list_lock, flags);
+ WARN_ON(vmdirq->enabled);
list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list);
+ vmdirq->enabled = true;
raw_spin_unlock_irqrestore(&list_lock, flags);
data->chip->irq_unmask(data);
data->chip->irq_mask(data);
raw_spin_lock_irqsave(&list_lock, flags);
- list_del_rcu(&vmdirq->node);
- INIT_LIST_HEAD_RCU(&vmdirq->node);
+ if (vmdirq->enabled) {
+ list_del_rcu(&vmdirq->node);
+ vmdirq->enabled = false;
+ }
raw_spin_unlock_irqrestore(&list_lock, flags);
}
* text and allocate a new stack because we can't rely on the
* stack pointer being < 4GB.
*/
- if (!IS_ENABLED(CONFIG_EFI_MIXED))
+ if (!IS_ENABLED(CONFIG_EFI_MIXED) || efi_is_native())
return 0;
/*
for_each_efi_memory_desc(md) {
unsigned long long start = md->phys_addr;
unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+ size_t rm_size;
if (md->type != EFI_BOOT_SERVICES_CODE &&
md->type != EFI_BOOT_SERVICES_DATA)
if (md->attribute & EFI_MEMORY_RUNTIME)
continue;
+ /*
+ * Nasty quirk: if all sub-1MB memory is used for boot
+ * services, we can get here without having allocated the
+ * real mode trampoline. It's too late to hand boot services
+ * memory back to the memblock allocator, so instead
+ * try to manually allocate the trampoline if needed.
+ *
+ * I've seen this on a Dell XPS 13 9350 with firmware
+ * 1.4.4 with SGX enabled booting Linux via Fedora 24's
+ * grub2-efi on a hard disk. (And no, I don't know why
+ * this happened, but Linux should still try to boot rather
+ * panicing early.)
+ */
+ rm_size = real_mode_size_needed();
+ if (rm_size && (start + rm_size) < (1<<20) && size >= rm_size) {
+ set_real_mode_mem(start, rm_size);
+ start += rm_size;
+ size -= rm_size;
+ }
+
free_bootmem_late(start, size);
}
void uv_bios_init(void)
{
uv_systab = NULL;
- if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || !efi.uv_systab) {
+ if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) ||
+ !efi.uv_systab || efi_runtime_disabled()) {
pr_crit("UV: UVsystab: missing\n");
return;
}
return;
}
+ /* Starting with UV4 the UV systab size is variable */
if (uv_systab->revision >= UV_SYSTAB_VERSION_UV4) {
+ int size = uv_systab->size;
+
iounmap(uv_systab);
- uv_systab = ioremap(efi.uv_systab, uv_systab->size);
+ uv_systab = ioremap(efi.uv_systab, size);
if (!uv_systab) {
- pr_err("UV: UVsystab: ioremap(%d) failed!\n",
- uv_systab->size);
+ pr_err("UV: UVsystab: ioremap(%d) failed!\n", size);
return;
}
}
struct x86_mapping_info info = {
.alloc_pgt_page = alloc_pgt_page,
.pmd_flag = __PAGE_KERNEL_LARGE_EXEC,
- .kernel_mapping = true,
+ .offset = __PAGE_OFFSET,
};
unsigned long mstart, mend;
pgd_t *pgd;
return result;
}
- temp_level4_pgt = (unsigned long)pgd - __PAGE_OFFSET;
+ temp_level4_pgt = __pa(pgd);
return 0;
}
#include <linux/io.h>
+#include <linux/slab.h>
#include <linux/memblock.h>
#include <asm/cacheflush.h>
#include <asm/pgtable.h>
#include <asm/realmode.h>
+#include <asm/tlbflush.h>
struct real_mode_header *real_mode_header;
u32 *trampoline_cr4_features;
/* Hold the pgd entry used on booting additional CPUs */
pgd_t trampoline_pgd_entry;
+void __init set_real_mode_mem(phys_addr_t mem, size_t size)
+{
+ void *base = __va(mem);
+
+ real_mode_header = (struct real_mode_header *) base;
+ printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n",
+ base, (unsigned long long)mem, size);
+}
+
void __init reserve_real_mode(void)
{
phys_addr_t mem;
- unsigned char *base;
- size_t size = PAGE_ALIGN(real_mode_blob_end - real_mode_blob);
+ size_t size = real_mode_size_needed();
+
+ if (!size)
+ return;
+
+ WARN_ON(slab_is_available());
/* Has to be under 1M so we can execute real-mode AP code. */
mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE);
- if (!mem)
- panic("Cannot allocate trampoline\n");
+ if (!mem) {
+ pr_info("No sub-1M memory is available for the trampoline\n");
+ return;
+ }
- base = __va(mem);
memblock_reserve(mem, size);
- real_mode_header = (struct real_mode_header *) base;
- printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n",
- base, (unsigned long long)mem, size);
+ set_real_mode_mem(mem, size);
}
-void __init setup_real_mode(void)
+static void __init setup_real_mode(void)
{
u16 real_mode_seg;
const u32 *rel;
trampoline_header->start = (u64) secondary_startup_64;
trampoline_cr4_features = &trampoline_header->cr4;
- *trampoline_cr4_features = __read_cr4();
+ *trampoline_cr4_features = mmu_cr4_features;
trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd);
trampoline_pgd[0] = trampoline_pgd_entry.pgd;
* need to mark it executable at do_pre_smp_initcalls() at least,
* thus run it as a early_initcall().
*/
-static int __init set_real_mode_permissions(void)
+static void __init set_real_mode_permissions(void)
{
unsigned char *base = (unsigned char *) real_mode_header;
size_t size = PAGE_ALIGN(real_mode_blob_end - real_mode_blob);
set_memory_nx((unsigned long) base, size >> PAGE_SHIFT);
set_memory_ro((unsigned long) base, ro_size >> PAGE_SHIFT);
set_memory_x((unsigned long) text_start, text_size >> PAGE_SHIFT);
+}
+
+static int __init init_real_mode(void)
+{
+ if (!real_mode_header)
+ panic("Real mode trampoline was not allocated");
+
+ setup_real_mode();
+ set_real_mode_permissions();
return 0;
}
-early_initcall(set_real_mode_permissions);
+early_initcall(init_real_mode);
case EAX:
case EIP:
case UESP:
+ break;
case ORIG_EAX:
+ /* Update the syscall number. */
+ UPT_SYSCALL_NR(&child->thread.regs.regs) = value;
break;
case FS:
if (value && (value & 3) != 3)
case RSI:
case RDI:
case RBP:
+ break;
+
case ORIG_RAX:
+ /* Update the syscall number. */
+ UPT_SYSCALL_NR(&child->thread.regs.regs) = value;
break;
case FS:
DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
/* Linux <-> Xen vCPU id mapping */
-DEFINE_PER_CPU(int, xen_vcpu_id) = -1;
+DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
enum xen_domain_type xen_domain_type = XEN_NATIVE;
bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector;
bio->bi_iter.bi_size = bio_src->bi_iter.bi_size;
- if (bio_op(bio) == REQ_OP_DISCARD)
- goto integrity_clone;
-
- if (bio_op(bio) == REQ_OP_WRITE_SAME) {
+ switch (bio_op(bio)) {
+ case REQ_OP_DISCARD:
+ case REQ_OP_SECURE_ERASE:
+ break;
+ case REQ_OP_WRITE_SAME:
bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
- goto integrity_clone;
+ break;
+ default:
+ bio_for_each_segment(bv, bio_src, iter)
+ bio->bi_io_vec[bio->bi_vcnt++] = bv;
+ break;
}
- bio_for_each_segment(bv, bio_src, iter)
- bio->bi_io_vec[bio->bi_vcnt++] = bv;
-
-integrity_clone:
if (bio_integrity(bio_src)) {
int ret;
* Discards need a mutable bio_vec to accommodate the payload
* required by the DSM TRIM and UNMAP commands.
*/
- if (bio_op(bio) == REQ_OP_DISCARD)
+ if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE)
split = bio_clone_bioset(bio, gfp, bs);
else
split = bio_clone_fast(bio, gfp, bs);
void blk_set_queue_dying(struct request_queue *q)
{
- queue_flag_set_unlocked(QUEUE_FLAG_DYING, q);
+ spin_lock_irq(q->queue_lock);
+ queue_flag_set(QUEUE_FLAG_DYING, q);
+ spin_unlock_irq(q->queue_lock);
if (q->mq_ops)
blk_mq_wake_waiters(q);
bool do_split = true;
struct bio *new = NULL;
const unsigned max_sectors = get_max_io_size(q, bio);
+ unsigned bvecs = 0;
bio_for_each_segment(bv, bio, iter) {
+ /*
+ * With arbitrary bio size, the incoming bio may be very
+ * big. We have to split the bio into small bios so that
+ * each holds at most BIO_MAX_PAGES bvecs because
+ * bio_clone() can fail to allocate big bvecs.
+ *
+ * It should have been better to apply the limit per
+ * request queue in which bio_clone() is involved,
+ * instead of globally. The biggest blocker is the
+ * bio_clone() in bio bounce.
+ *
+ * If bio is splitted by this reason, we should have
+ * allowed to continue bios merging, but don't do
+ * that now for making the change simple.
+ *
+ * TODO: deal with bio bounce's bio_clone() gracefully
+ * and convert the global limit into per-queue limit.
+ */
+ if (bvecs++ >= BIO_MAX_PAGES)
+ goto split;
+
/*
* If the queue doesn't support SG gaps and adding this
* offset would create a gap, disallow it.
struct bio *split, *res;
unsigned nsegs;
- if (bio_op(*bio) == REQ_OP_DISCARD)
+ switch (bio_op(*bio)) {
+ case REQ_OP_DISCARD:
+ case REQ_OP_SECURE_ERASE:
split = blk_bio_discard_split(q, *bio, bs, &nsegs);
- else if (bio_op(*bio) == REQ_OP_WRITE_SAME)
+ break;
+ case REQ_OP_WRITE_SAME:
split = blk_bio_write_same_split(q, *bio, bs, &nsegs);
- else
+ break;
+ default:
split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs);
+ break;
+ }
/* physical segments can be figured out during splitting */
res = split ? split : *bio;
* This should probably be returning 0, but blk_add_request_payload()
* (Christoph!!!!)
*/
- if (bio_op(bio) == REQ_OP_DISCARD)
+ if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE)
return 1;
if (bio_op(bio) == REQ_OP_WRITE_SAME)
nsegs = 0;
cluster = blk_queue_cluster(q);
- if (bio_op(bio) == REQ_OP_DISCARD) {
+ switch (bio_op(bio)) {
+ case REQ_OP_DISCARD:
+ case REQ_OP_SECURE_ERASE:
/*
* This is a hack - drivers should be neither modifying the
* biovec, nor relying on bi_vcnt - but because of
* a payload we need to set up here (thank you Christoph) and
* bi_vcnt is really the only way of telling if we need to.
*/
-
- if (bio->bi_vcnt)
- goto single_segment;
-
- return 0;
- }
-
- if (bio_op(bio) == REQ_OP_WRITE_SAME) {
-single_segment:
+ if (!bio->bi_vcnt)
+ return 0;
+ /* Fall through */
+ case REQ_OP_WRITE_SAME:
*sg = sglist;
bvec = bio_iovec(bio);
sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset);
return 1;
+ default:
+ break;
}
for_each_bio(bio)
if (ret)
return ERR_PTR(ret);
+ /*
+ * Check if the hardware context is actually mapped to anything.
+ * If not tell the caller that it should skip this queue.
+ */
hctx = q->queue_hw_ctx[hctx_idx];
+ if (!blk_mq_hw_queue_mapped(hctx)) {
+ ret = -EXDEV;
+ goto out_queue_exit;
+ }
ctx = __blk_mq_get_ctx(q, cpumask_first(hctx->cpumask));
blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
rq = __blk_mq_alloc_request(&alloc_data, rw, 0);
if (!rq) {
- blk_queue_exit(q);
- return ERR_PTR(-EWOULDBLOCK);
+ ret = -EWOULDBLOCK;
+ goto out_queue_exit;
}
return rq;
+
+out_queue_exit:
+ blk_queue_exit(q);
+ return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
struct list_head *dptr;
int queued;
- WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask));
-
if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
return;
+ WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) &&
+ cpu_online(hctx->next_cpu));
+
hctx->run++;
/*
EXPORT_SYMBOL(blk_mq_delay_queue);
static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
- struct blk_mq_ctx *ctx,
struct request *rq,
bool at_head)
{
+ struct blk_mq_ctx *ctx = rq->mq_ctx;
+
trace_block_rq_insert(hctx->queue, rq);
if (at_head)
{
struct blk_mq_ctx *ctx = rq->mq_ctx;
- __blk_mq_insert_req_list(hctx, ctx, rq, at_head);
+ __blk_mq_insert_req_list(hctx, rq, at_head);
blk_mq_hctx_mark_pending(hctx, ctx);
}
void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
- bool async)
+ bool async)
{
+ struct blk_mq_ctx *ctx = rq->mq_ctx;
struct request_queue *q = rq->q;
struct blk_mq_hw_ctx *hctx;
- struct blk_mq_ctx *ctx = rq->mq_ctx, *current_ctx;
-
- current_ctx = blk_mq_get_ctx(q);
- if (!cpu_online(ctx->cpu))
- rq->mq_ctx = ctx = current_ctx;
hctx = q->mq_ops->map_queue(q, ctx->cpu);
if (run_queue)
blk_mq_run_hw_queue(hctx, async);
-
- blk_mq_put_ctx(current_ctx);
}
static void blk_mq_insert_requests(struct request_queue *q,
{
struct blk_mq_hw_ctx *hctx;
- struct blk_mq_ctx *current_ctx;
trace_block_unplug(q, depth, !from_schedule);
- current_ctx = blk_mq_get_ctx(q);
-
- if (!cpu_online(ctx->cpu))
- ctx = current_ctx;
hctx = q->mq_ops->map_queue(q, ctx->cpu);
/*
struct request *rq;
rq = list_first_entry(list, struct request, queuelist);
+ BUG_ON(rq->mq_ctx != ctx);
list_del_init(&rq->queuelist);
- rq->mq_ctx = ctx;
- __blk_mq_insert_req_list(hctx, ctx, rq, false);
+ __blk_mq_insert_req_list(hctx, rq, false);
}
blk_mq_hctx_mark_pending(hctx, ctx);
spin_unlock(&ctx->lock);
blk_mq_run_hw_queue(hctx, from_schedule);
- blk_mq_put_ctx(current_ctx);
}
static int plug_ctx_cmp(void *priv, struct list_head *a, struct list_head *b)
return 0;
}
+/*
+ * 'cpu' is going away. splice any existing rq_list entries from this
+ * software queue to the hw queue dispatch list, and ensure that it
+ * gets run.
+ */
static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu)
{
- struct request_queue *q = hctx->queue;
struct blk_mq_ctx *ctx;
LIST_HEAD(tmp);
- /*
- * Move ctx entries to new CPU, if this one is going away.
- */
- ctx = __blk_mq_get_ctx(q, cpu);
+ ctx = __blk_mq_get_ctx(hctx->queue, cpu);
spin_lock(&ctx->lock);
if (!list_empty(&ctx->rq_list)) {
if (list_empty(&tmp))
return NOTIFY_OK;
- ctx = blk_mq_get_ctx(q);
- spin_lock(&ctx->lock);
-
- while (!list_empty(&tmp)) {
- struct request *rq;
-
- rq = list_first_entry(&tmp, struct request, queuelist);
- rq->mq_ctx = ctx;
- list_move_tail(&rq->queuelist, &ctx->rq_list);
- }
-
- hctx = q->mq_ops->map_queue(q, ctx->cpu);
- blk_mq_hctx_mark_pending(hctx, ctx);
-
- spin_unlock(&ctx->lock);
+ spin_lock(&hctx->lock);
+ list_splice_tail_init(&tmp, &hctx->dispatch);
+ spin_unlock(&hctx->lock);
blk_mq_run_hw_queue(hctx, true);
- blk_mq_put_ctx(ctx);
return NOTIFY_OK;
}
/*
* If previous slice expired, start a new one otherwise renew/extend
* existing slice to make sure it is at least throtl_slice interval
- * long since now.
+ * long since now. New slice is started only for empty throttle group.
+ * If there is queued bio, that means there should be an active
+ * slice and it should be extended instead.
*/
- if (throtl_slice_used(tg, rw))
+ if (throtl_slice_used(tg, rw) && !(tg->service_queue.nr_queued[rw]))
throtl_start_new_slice(tg, rw);
else {
if (time_before(tg->slice_end[rw], jiffies + throtl_slice))
list_for_each_prev(entry, &q->queue_head) {
struct request *pos = list_entry_rq(entry);
- if ((req_op(rq) == REQ_OP_DISCARD) != (req_op(pos) == REQ_OP_DISCARD))
+ if (req_op(rq) != req_op(pos))
break;
if (rq_data_dir(rq) != rq_data_dir(pos))
break;
config CRYPT_CRC32C_VPMSUM
tristate "CRC32c CRC algorithm (powerpc64)"
- depends on PPC64
+ depends on PPC64 && ALTIVEC
select CRYPTO_HASH
select CRC32
help
return blkcipher_walk_done(desc, walk, -EINVAL);
}
+ bsize = min(walk->walk_blocksize, n);
+
walk->flags &= ~(BLKCIPHER_WALK_SLOW | BLKCIPHER_WALK_COPY |
BLKCIPHER_WALK_DIFF);
if (!scatterwalk_aligned(&walk->in, walk->alignmask) ||
}
}
- bsize = min(walk->walk_blocksize, n);
n = scatterwalk_clamp(&walk->in, n);
n = scatterwalk_clamp(&walk->out, n);
static int cryptd_hash_import(struct ahash_request *req, const void *in)
{
- struct cryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
+ struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+ struct cryptd_hash_ctx *ctx = crypto_ahash_ctx(tfm);
+ struct shash_desc *desc = cryptd_shash_desc(req);
+
+ desc->tfm = ctx->child;
+ desc->flags = req->base.flags;
- return crypto_shash_import(&rctx->desc, in);
+ return crypto_shash_import(desc, in);
}
static int cryptd_create_hash(struct crypto_template *tmpl, struct rtattr **tb,
rctx = aead_request_ctx(req);
compl = rctx->complete;
+ tfm = crypto_aead_reqtfm(req);
+
if (unlikely(err == -EINPROGRESS))
goto out;
aead_request_set_tfm(req, child);
err = crypt( req );
out:
- tfm = crypto_aead_reqtfm(req);
ctx = crypto_aead_ctx(tfm);
refcnt = atomic_read(&ctx->refcnt);
/*
* echainiv: Encrypted Chain IV Generator
*
- * This generator generates an IV based on a sequence number by xoring it
- * with a salt and then encrypting it with the same key as used to encrypt
+ * This generator generates an IV based on a sequence number by multiplying
+ * it with a salt and then encrypting it with the same key as used to encrypt
* the plain text. This algorithm requires that the block size be equal
* to the IV size. It is mainly useful for CBC.
*
#include <linux/err.h>
#include <linux/init.h>
#include <linux/kernel.h>
-#include <linux/mm.h>
#include <linux/module.h>
-#include <linux/percpu.h>
-#include <linux/spinlock.h>
+#include <linux/slab.h>
#include <linux/string.h>
-#define MAX_IV_SIZE 16
-
-static DEFINE_PER_CPU(u32 [MAX_IV_SIZE / sizeof(u32)], echainiv_iv);
-
-/* We don't care if we get preempted and read/write IVs from the next CPU. */
-static void echainiv_read_iv(u8 *dst, unsigned size)
-{
- u32 *a = (u32 *)dst;
- u32 __percpu *b = echainiv_iv;
-
- for (; size >= 4; size -= 4) {
- *a++ = this_cpu_read(*b);
- b++;
- }
-}
-
-static void echainiv_write_iv(const u8 *src, unsigned size)
-{
- const u32 *a = (const u32 *)src;
- u32 __percpu *b = echainiv_iv;
-
- for (; size >= 4; size -= 4) {
- this_cpu_write(*b, *a);
- a++;
- b++;
- }
-}
-
-static void echainiv_encrypt_complete2(struct aead_request *req, int err)
-{
- struct aead_request *subreq = aead_request_ctx(req);
- struct crypto_aead *geniv;
- unsigned int ivsize;
-
- if (err == -EINPROGRESS)
- return;
-
- if (err)
- goto out;
-
- geniv = crypto_aead_reqtfm(req);
- ivsize = crypto_aead_ivsize(geniv);
-
- echainiv_write_iv(subreq->iv, ivsize);
-
- if (req->iv != subreq->iv)
- memcpy(req->iv, subreq->iv, ivsize);
-
-out:
- if (req->iv != subreq->iv)
- kzfree(subreq->iv);
-}
-
-static void echainiv_encrypt_complete(struct crypto_async_request *base,
- int err)
-{
- struct aead_request *req = base->data;
-
- echainiv_encrypt_complete2(req, err);
- aead_request_complete(req, err);
-}
-
static int echainiv_encrypt(struct aead_request *req)
{
struct crypto_aead *geniv = crypto_aead_reqtfm(req);
struct aead_geniv_ctx *ctx = crypto_aead_ctx(geniv);
struct aead_request *subreq = aead_request_ctx(req);
- crypto_completion_t compl;
- void *data;
+ __be64 nseqno;
+ u64 seqno;
u8 *info;
unsigned int ivsize = crypto_aead_ivsize(geniv);
int err;
aead_request_set_tfm(subreq, ctx->child);
- compl = echainiv_encrypt_complete;
- data = req;
info = req->iv;
if (req->src != req->dst) {
return err;
}
- if (unlikely(!IS_ALIGNED((unsigned long)info,
- crypto_aead_alignmask(geniv) + 1))) {
- info = kmalloc(ivsize, req->base.flags &
- CRYPTO_TFM_REQ_MAY_SLEEP ? GFP_KERNEL:
- GFP_ATOMIC);
- if (!info)
- return -ENOMEM;
-
- memcpy(info, req->iv, ivsize);
- }
-
- aead_request_set_callback(subreq, req->base.flags, compl, data);
+ aead_request_set_callback(subreq, req->base.flags,
+ req->base.complete, req->base.data);
aead_request_set_crypt(subreq, req->dst, req->dst,
req->cryptlen, info);
aead_request_set_ad(subreq, req->assoclen);
- crypto_xor(info, ctx->salt, ivsize);
+ memcpy(&nseqno, info + ivsize - 8, 8);
+ seqno = be64_to_cpu(nseqno);
+ memset(info, 0, ivsize);
+
scatterwalk_map_and_copy(info, req->dst, req->assoclen, ivsize, 1);
- echainiv_read_iv(info, ivsize);
- err = crypto_aead_encrypt(subreq);
- echainiv_encrypt_complete2(req, err);
- return err;
+ do {
+ u64 a;
+
+ memcpy(&a, ctx->salt + ivsize - 8, 8);
+
+ a |= 1;
+ a *= seqno;
+
+ memcpy(info + ivsize - 8, &a, 8);
+ } while ((ivsize -= 8));
+
+ return crypto_aead_encrypt(subreq);
}
static int echainiv_decrypt(struct aead_request *req)
alg = crypto_spawn_aead_alg(spawn);
err = -EINVAL;
- if (inst->alg.ivsize & (sizeof(u32) - 1) ||
- inst->alg.ivsize > MAX_IV_SIZE)
+ if (inst->alg.ivsize & (sizeof(u64) - 1) || !inst->alg.ivsize)
goto free_inst;
inst->alg.encrypt = echainiv_encrypt;
inst->alg.init = aead_init_geniv;
inst->alg.exit = aead_exit_geniv;
- inst->alg.base.cra_alignmask |= __alignof__(u32) - 1;
inst->alg.base.cra_ctxsize = sizeof(struct aead_geniv_ctx);
inst->alg.base.cra_ctxsize += inst->alg.ivsize;
struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
struct pkcs1pad_ctx *ctx = akcipher_tfm_ctx(tfm);
struct pkcs1pad_request *req_ctx = akcipher_request_ctx(req);
+ unsigned int dst_len;
unsigned int pos;
-
- if (err == -EOVERFLOW)
- /* Decrypted value had no leading 0 byte */
- err = -EINVAL;
+ u8 *out_buf;
if (err)
goto done;
- if (req_ctx->child_req.dst_len != ctx->key_size - 1) {
- err = -EINVAL;
+ err = -EINVAL;
+ dst_len = req_ctx->child_req.dst_len;
+ if (dst_len < ctx->key_size - 1)
goto done;
+
+ out_buf = req_ctx->out_buf;
+ if (dst_len == ctx->key_size) {
+ if (out_buf[0] != 0x00)
+ /* Decrypted value had no leading 0 byte */
+ goto done;
+
+ dst_len--;
+ out_buf++;
}
- if (req_ctx->out_buf[0] != 0x02) {
- err = -EINVAL;
+ if (out_buf[0] != 0x02)
goto done;
- }
- for (pos = 1; pos < req_ctx->child_req.dst_len; pos++)
- if (req_ctx->out_buf[pos] == 0x00)
+
+ for (pos = 1; pos < dst_len; pos++)
+ if (out_buf[pos] == 0x00)
break;
- if (pos < 9 || pos == req_ctx->child_req.dst_len) {
- err = -EINVAL;
+ if (pos < 9 || pos == dst_len)
goto done;
- }
pos++;
- if (req->dst_len < req_ctx->child_req.dst_len - pos)
+ err = 0;
+
+ if (req->dst_len < dst_len - pos)
err = -EOVERFLOW;
- req->dst_len = req_ctx->child_req.dst_len - pos;
+ req->dst_len = dst_len - pos;
if (!err)
sg_copy_from_buffer(req->dst,
sg_nents_for_len(req->dst, req->dst_len),
- req_ctx->out_buf + pos, req->dst_len);
+ out_buf + pos, req->dst_len);
done:
kzfree(req_ctx->out_buf);
#define ROTL64(x, y) (((x) << (y)) | ((x) >> (64 - (y))))
static const u64 keccakf_rndc[24] = {
- 0x0000000000000001, 0x0000000000008082, 0x800000000000808a,
- 0x8000000080008000, 0x000000000000808b, 0x0000000080000001,
- 0x8000000080008081, 0x8000000000008009, 0x000000000000008a,
- 0x0000000000000088, 0x0000000080008009, 0x000000008000000a,
- 0x000000008000808b, 0x800000000000008b, 0x8000000000008089,
- 0x8000000000008003, 0x8000000000008002, 0x8000000000000080,
- 0x000000000000800a, 0x800000008000000a, 0x8000000080008081,
- 0x8000000000008080, 0x0000000080000001, 0x8000000080008008
+ 0x0000000000000001ULL, 0x0000000000008082ULL, 0x800000000000808aULL,
+ 0x8000000080008000ULL, 0x000000000000808bULL, 0x0000000080000001ULL,
+ 0x8000000080008081ULL, 0x8000000000008009ULL, 0x000000000000008aULL,
+ 0x0000000000000088ULL, 0x0000000080008009ULL, 0x000000008000000aULL,
+ 0x000000008000808bULL, 0x800000000000008bULL, 0x8000000000008089ULL,
+ 0x8000000000008003ULL, 0x8000000000008002ULL, 0x8000000000000080ULL,
+ 0x000000000000800aULL, 0x800000008000000aULL, 0x8000000080008081ULL,
+ 0x8000000000008080ULL, 0x0000000080000001ULL, 0x8000000080008008ULL
};
static const int keccakf_rotc[24] = {
{
struct nfit_blk_mmio *mmio = &nfit_blk->mmio[DCR];
u64 offset = nfit_blk->stat_offset + mmio->size * bw;
+ const u32 STATUS_MASK = 0x80000037;
if (mmio->num_lines)
offset = to_interleave_offset(offset, mmio);
- return readl(mmio->addr.base + offset);
+ return readl(mmio->addr.base + offset) & STATUS_MASK;
}
static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw,
list_for_each_entry(nfit_spa, &acpi_desc->spas, list) {
struct acpi_nfit_system_address *spa = nfit_spa->spa;
- if (nfit_spa_type(spa) == NFIT_SPA_PM)
+ if (nfit_spa_type(spa) != NFIT_SPA_PM)
continue;
/* find the spa that covers the mce addr */
if (spa->address > mce->addr)
static struct acpi_probe_entry *ape;
static int acpi_probe_count;
-static DEFINE_SPINLOCK(acpi_probe_lock);
+static DEFINE_MUTEX(acpi_probe_mutex);
static int __init acpi_match_madt(struct acpi_subtable_header *header,
const unsigned long end)
if (acpi_disabled)
return 0;
- spin_lock(&acpi_probe_lock);
+ mutex_lock(&acpi_probe_mutex);
for (ape = ap_head; nr; ape++, nr--) {
if (ACPI_COMPARE_NAME(ACPI_SIG_MADT, ape->id)) {
acpi_probe_count = 0;
count++;
}
}
- spin_unlock(&acpi_probe_lock);
+ mutex_unlock(&acpi_probe_mutex);
return count;
}
/* Do not receive interrupts sent by dummy ports */
if (!pp) {
- disable_irq(irq + i);
+ disable_irq(irq);
continue;
}
ap->ioaddr.altstatus_addr = base + 0x1E;
ap->ioaddr.bmdma_addr = base;
ata_sff_std_ports(&ap->ioaddr);
- ap->pflags = ATA_PFLAG_PIO32 | ATA_PFLAG_PIO32CHANGE;
+ ap->pflags |= ATA_PFLAG_PIO32 | ATA_PFLAG_PIO32CHANGE;
ninja32_program(base);
/* FIXME: Should we disable them at remove ? */
int (*callback)(struct device *);
int retval;
- trace_rpm_idle(dev, rpmflags);
+ trace_rpm_idle_rcuidle(dev, rpmflags);
retval = rpm_check_suspend_allowed(dev);
if (retval < 0)
; /* Conditions are wrong. */
dev->power.request_pending = true;
queue_work(pm_wq, &dev->power.work);
}
- trace_rpm_return_int(dev, _THIS_IP_, 0);
+ trace_rpm_return_int_rcuidle(dev, _THIS_IP_, 0);
return 0;
}
wake_up_all(&dev->power.wait_queue);
out:
- trace_rpm_return_int(dev, _THIS_IP_, retval);
+ trace_rpm_return_int_rcuidle(dev, _THIS_IP_, retval);
return retval ? retval : rpm_suspend(dev, rpmflags | RPM_AUTO);
}
struct device *parent = NULL;
int retval;
- trace_rpm_suspend(dev, rpmflags);
+ trace_rpm_suspend_rcuidle(dev, rpmflags);
repeat:
retval = rpm_check_suspend_allowed(dev);
}
out:
- trace_rpm_return_int(dev, _THIS_IP_, retval);
+ trace_rpm_return_int_rcuidle(dev, _THIS_IP_, retval);
return retval;
struct device *parent = NULL;
int retval = 0;
- trace_rpm_resume(dev, rpmflags);
+ trace_rpm_resume_rcuidle(dev, rpmflags);
repeat:
if (dev->power.runtime_error)
spin_lock_irq(&dev->power.lock);
}
- trace_rpm_return_int(dev, _THIS_IP_, retval);
+ trace_rpm_return_int_rcuidle(dev, _THIS_IP_, retval);
return retval;
}
unsigned int new_base_reg, new_top_reg;
unsigned int min, max;
unsigned int max_dist;
+ unsigned int dist, best_dist = UINT_MAX;
max_dist = map->reg_stride * sizeof(*rbnode_tmp) /
map->cache_word_size;
&base_reg, &top_reg);
if (base_reg <= max && top_reg >= min) {
- new_base_reg = min(reg, base_reg);
- new_top_reg = max(reg, top_reg);
- } else {
- if (max < base_reg)
- node = node->rb_left;
+ if (reg < base_reg)
+ dist = base_reg - reg;
+ else if (reg > top_reg)
+ dist = reg - top_reg;
else
- node = node->rb_right;
-
- continue;
+ dist = 0;
+ if (dist < best_dist) {
+ rbnode = rbnode_tmp;
+ best_dist = dist;
+ new_base_reg = min(reg, base_reg);
+ new_top_reg = max(reg, top_reg);
+ }
}
- ret = regcache_rbtree_insert_to_block(map, rbnode_tmp,
+ /*
+ * Keep looking, we want to choose the closest block,
+ * otherwise we might end up creating overlapping
+ * blocks, which breaks the rbtree.
+ */
+ if (reg < base_reg)
+ node = node->rb_left;
+ else if (reg > top_reg)
+ node = node->rb_right;
+ else
+ break;
+ }
+
+ if (rbnode) {
+ ret = regcache_rbtree_insert_to_block(map, rbnode,
new_base_reg,
new_top_reg, reg,
value);
if (ret)
return ret;
- rbtree_ctx->cached_rbnode = rbnode_tmp;
+ rbtree_ctx->cached_rbnode = rbnode;
return 0;
}
/* calculate the size of reg_defaults */
for (count = 0, i = 0; i < map->num_reg_defaults_raw; i++)
- if (!regmap_volatile(map, i * map->reg_stride))
+ if (regmap_readable(map, i * map->reg_stride) &&
+ !regmap_volatile(map, i * map->reg_stride))
count++;
- /* all registers are volatile, so just bypass */
+ /* all registers are unreadable or volatile, so just bypass */
if (!count) {
map->cache_bypass = true;
return 0;
ret = map->bus->write(map->bus_context, buf, len);
kfree(buf);
+ } else if (ret != 0 && !map->cache_bypass && map->format.parse_val) {
+ /* regcache_drop_region() takes lock that we already have,
+ * thus call map->cache_ops->drop() directly
+ */
+ if (map->cache_ops && map->cache_ops->drop)
+ map->cache_ops->drop(map, reg, reg + 1);
}
trace_regmap_hw_write_done(map, reg, val_len / map->format.val_bytes);
if (UFDCS->rawcmd == 1)
UFDCS->rawcmd = 2;
- if (mode & (FMODE_READ|FMODE_WRITE)) {
- UDRS->last_checked = 0;
- clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
- check_disk_change(bdev);
- if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags))
- goto out;
- if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags))
+ if (!(mode & FMODE_NDELAY)) {
+ if (mode & (FMODE_READ|FMODE_WRITE)) {
+ UDRS->last_checked = 0;
+ clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
+ check_disk_change(bdev);
+ if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags))
+ goto out;
+ if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags))
+ goto out;
+ }
+ res = -EROFS;
+ if ((mode & FMODE_WRITE) &&
+ !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags))
goto out;
}
-
- res = -EROFS;
-
- if ((mode & FMODE_WRITE) &&
- !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags))
- goto out;
-
mutex_unlock(&open_lock);
mutex_unlock(&floppy_mutex);
return 0;
bool need_put = !!rbd_dev->opts;
ceph_oid_destroy(&rbd_dev->header_oid);
+ ceph_oloc_destroy(&rbd_dev->header_oloc);
rbd_put_client(rbd_dev->rbd_client);
rbd_spec_put(rbd_dev->spec);
}
spec->pool_id = (u64)rc;
- /* The ceph file layout needs to fit pool id in 32 bits */
-
- if (spec->pool_id > (u64)U32_MAX) {
- rbd_warn(NULL, "pool id too large (%llu > %u)",
- (unsigned long long)spec->pool_id, U32_MAX);
- rc = -EIO;
- goto err_out_client;
- }
-
rbd_dev = rbd_dev_create(rbdc, spec, rbd_opts);
if (!rbd_dev) {
rc = -ENOMEM;
num_vqs = 1;
vblk->vqs = kmalloc(sizeof(*vblk->vqs) * num_vqs, GFP_KERNEL);
- if (!vblk->vqs) {
- err = -ENOMEM;
- goto out;
- }
+ if (!vblk->vqs)
+ return -ENOMEM;
names = kmalloc(sizeof(*names) * num_vqs, GFP_KERNEL);
- if (!names)
- goto err_names;
-
callbacks = kmalloc(sizeof(*callbacks) * num_vqs, GFP_KERNEL);
- if (!callbacks)
- goto err_callbacks;
-
vqs = kmalloc(sizeof(*vqs) * num_vqs, GFP_KERNEL);
- if (!vqs)
- goto err_vqs;
+ if (!names || !callbacks || !vqs) {
+ err = -ENOMEM;
+ goto out;
+ }
for (i = 0; i < num_vqs; i++) {
callbacks[i] = virtblk_done;
/* Discover virtqueues and write information to configuration. */
err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names);
if (err)
- goto err_find_vqs;
+ goto out;
for (i = 0; i < num_vqs; i++) {
spin_lock_init(&vblk->vqs[i].lock);
}
vblk->num_vqs = num_vqs;
- err_find_vqs:
+out:
kfree(vqs);
- err_vqs:
kfree(callbacks);
- err_callbacks:
kfree(names);
- err_names:
if (err)
kfree(vblk->vqs);
- out:
return err;
}
struct mutex mutex;
struct xenbus_device *xbdev;
struct gendisk *gd;
+ u16 sector_size;
+ unsigned int physical_sector_size;
int vdevice;
blkif_vdev_t handle;
enum blkif_state connected;
.map_queue = blk_mq_map_queue,
};
+static void blkif_set_queue_limits(struct blkfront_info *info)
+{
+ struct request_queue *rq = info->rq;
+ struct gendisk *gd = info->gd;
+ unsigned int segments = info->max_indirect_segments ? :
+ BLKIF_MAX_SEGMENTS_PER_REQUEST;
+
+ queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
+
+ if (info->feature_discard) {
+ queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq);
+ blk_queue_max_discard_sectors(rq, get_capacity(gd));
+ rq->limits.discard_granularity = info->discard_granularity;
+ rq->limits.discard_alignment = info->discard_alignment;
+ if (info->feature_secdiscard)
+ queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq);
+ }
+
+ /* Hard sector size and max sectors impersonate the equiv. hardware. */
+ blk_queue_logical_block_size(rq, info->sector_size);
+ blk_queue_physical_block_size(rq, info->physical_sector_size);
+ blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512);
+
+ /* Each segment in a request is up to an aligned page in size. */
+ blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
+ blk_queue_max_segment_size(rq, PAGE_SIZE);
+
+ /* Ensure a merged request will fit in a single I/O ring slot. */
+ blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG);
+
+ /* Make sure buffer addresses are sector-aligned. */
+ blk_queue_dma_alignment(rq, 511);
+
+ /* Make sure we don't use bounce buffers. */
+ blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY);
+}
+
static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
- unsigned int physical_sector_size,
- unsigned int segments)
+ unsigned int physical_sector_size)
{
struct request_queue *rq;
struct blkfront_info *info = gd->private_data;
}
rq->queuedata = info;
- queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
-
- if (info->feature_discard) {
- queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq);
- blk_queue_max_discard_sectors(rq, get_capacity(gd));
- rq->limits.discard_granularity = info->discard_granularity;
- rq->limits.discard_alignment = info->discard_alignment;
- if (info->feature_secdiscard)
- queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq);
- }
-
- /* Hard sector size and max sectors impersonate the equiv. hardware. */
- blk_queue_logical_block_size(rq, sector_size);
- blk_queue_physical_block_size(rq, physical_sector_size);
- blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512);
-
- /* Each segment in a request is up to an aligned page in size. */
- blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
- blk_queue_max_segment_size(rq, PAGE_SIZE);
-
- /* Ensure a merged request will fit in a single I/O ring slot. */
- blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG);
-
- /* Make sure buffer addresses are sector-aligned. */
- blk_queue_dma_alignment(rq, 511);
-
- /* Make sure we don't use bounce buffers. */
- blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY);
-
- gd->queue = rq;
+ info->rq = gd->queue = rq;
+ info->gd = gd;
+ info->sector_size = sector_size;
+ info->physical_sector_size = physical_sector_size;
+ blkif_set_queue_limits(info);
return 0;
}
gd->private_data = info;
set_capacity(gd, capacity);
- if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size,
- info->max_indirect_segments ? :
- BLKIF_MAX_SEGMENTS_PER_REQUEST)) {
+ if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size)) {
del_gendisk(gd);
goto release;
}
- info->rq = gd->queue;
- info->gd = gd;
-
xlvbd_flush(info);
if (vdisk_info & VDISK_READONLY)
rinfo->ring_ref[i] = GRANT_INVALID_REF;
}
}
- free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * PAGE_SIZE));
+ free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * XEN_PAGE_SIZE));
rinfo->ring.sring = NULL;
if (rinfo->irq)
struct split_bio *split_bio;
blkfront_gather_backend_features(info);
+ /* Reset limits changed by blk_mq_update_nr_hw_queues(). */
+ blkif_set_queue_limits(info);
segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST;
- blk_queue_max_segments(info->rq, segs);
+ blk_queue_max_segments(info->rq, segs / GRANTS_PER_PSEG);
for (r_index = 0; r_index < info->nr_rings; r_index++) {
struct blkfront_ring_info *rinfo = &info->rinfo[r_index];
if (err) {
xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s",
info->xbdev->otherend);
- return;
+ goto fail;
}
xenbus_switch_state(info->xbdev, XenbusStateConnected);
device_add_disk(&info->xbdev->dev, info->gd);
info->is_ready = 1;
+ return;
+
+fail:
+ blkif_free(info, 0);
+ return;
}
/**
CCI5xx_GLOBAL_EVENT_EXT_ATTR_ENTRY(cci_wrq, 0xB),
CCI5xx_GLOBAL_EVENT_EXT_ATTR_ENTRY(cci_snoop_cd_hs, 0xC),
CCI5xx_GLOBAL_EVENT_EXT_ATTR_ENTRY(cci_rq_stall_addr_hazard, 0xD),
- CCI5xx_GLOBAL_EVENT_EXT_ATTR_ENTRY(cci_snopp_rq_stall_tt_full, 0xE),
+ CCI5xx_GLOBAL_EVENT_EXT_ATTR_ENTRY(cci_snoop_rq_stall_tt_full, 0xE),
CCI5xx_GLOBAL_EVENT_EXT_ATTR_ENTRY(cci_snoop_rq_tzmp1_prot, 0xF),
NULL
};
struct arm_ccn_component *xp;
struct arm_ccn_dt dt;
+ int mn_id;
};
static DEFINE_MUTEX(arm_ccn_mutex);
#define CCN_CONFIG_TYPE(_config) (((_config) >> 8) & 0xff)
#define CCN_CONFIG_EVENT(_config) (((_config) >> 16) & 0xff)
#define CCN_CONFIG_PORT(_config) (((_config) >> 24) & 0x3)
+#define CCN_CONFIG_BUS(_config) (((_config) >> 24) & 0x3)
#define CCN_CONFIG_VC(_config) (((_config) >> 26) & 0x7)
#define CCN_CONFIG_DIR(_config) (((_config) >> 29) & 0x1)
#define CCN_CONFIG_MASK(_config) (((_config) >> 30) & 0xf)
static CCN_FORMAT_ATTR(type, "config:8-15");
static CCN_FORMAT_ATTR(event, "config:16-23");
static CCN_FORMAT_ATTR(port, "config:24-25");
+static CCN_FORMAT_ATTR(bus, "config:24-25");
static CCN_FORMAT_ATTR(vc, "config:26-28");
static CCN_FORMAT_ATTR(dir, "config:29-29");
static CCN_FORMAT_ATTR(mask, "config:30-33");
&arm_ccn_pmu_format_attr_type.attr.attr,
&arm_ccn_pmu_format_attr_event.attr.attr,
&arm_ccn_pmu_format_attr_port.attr.attr,
+ &arm_ccn_pmu_format_attr_bus.attr.attr,
&arm_ccn_pmu_format_attr_vc.attr.attr,
&arm_ccn_pmu_format_attr_dir.attr.attr,
&arm_ccn_pmu_format_attr_mask.attr.attr,
static ssize_t arm_ccn_pmu_event_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
+ struct arm_ccn *ccn = pmu_to_arm_ccn(dev_get_drvdata(dev));
struct arm_ccn_pmu_event *event = container_of(attr,
struct arm_ccn_pmu_event, attr);
ssize_t res;
break;
case CCN_TYPE_XP:
res += snprintf(buf + res, PAGE_SIZE - res,
- ",xp=?,port=?,vc=?,dir=?");
+ ",xp=?,vc=?");
if (event->event == CCN_EVENT_WATCHPOINT)
res += snprintf(buf + res, PAGE_SIZE - res,
- ",cmp_l=?,cmp_h=?,mask=?");
+ ",port=?,dir=?,cmp_l=?,cmp_h=?,mask=?");
+ else
+ res += snprintf(buf + res, PAGE_SIZE - res,
+ ",bus=?");
+
+ break;
+ case CCN_TYPE_MN:
+ res += snprintf(buf + res, PAGE_SIZE - res, ",node=%d", ccn->mn_id);
break;
default:
res += snprintf(buf + res, PAGE_SIZE - res, ",node=?");
}
static struct arm_ccn_pmu_event arm_ccn_pmu_events[] = {
- CCN_EVENT_MN(eobarrier, "dir=0,vc=0,cmp_h=0x1c00", CCN_IDX_MASK_OPCODE),
- CCN_EVENT_MN(ecbarrier, "dir=0,vc=0,cmp_h=0x1e00", CCN_IDX_MASK_OPCODE),
- CCN_EVENT_MN(dvmop, "dir=0,vc=0,cmp_h=0x2800", CCN_IDX_MASK_OPCODE),
+ CCN_EVENT_MN(eobarrier, "dir=1,vc=0,cmp_h=0x1c00", CCN_IDX_MASK_OPCODE),
+ CCN_EVENT_MN(ecbarrier, "dir=1,vc=0,cmp_h=0x1e00", CCN_IDX_MASK_OPCODE),
+ CCN_EVENT_MN(dvmop, "dir=1,vc=0,cmp_h=0x2800", CCN_IDX_MASK_OPCODE),
CCN_EVENT_HNI(txdatflits, "dir=1,vc=3", CCN_IDX_MASK_ANY),
CCN_EVENT_HNI(rxdatflits, "dir=0,vc=3", CCN_IDX_MASK_ANY),
CCN_EVENT_HNI(txreqflits, "dir=1,vc=0", CCN_IDX_MASK_ANY),
if (has_branch_stack(event) || event->attr.exclude_user ||
event->attr.exclude_kernel || event->attr.exclude_hv ||
- event->attr.exclude_idle) {
+ event->attr.exclude_idle || event->attr.exclude_host ||
+ event->attr.exclude_guest) {
dev_warn(ccn->dev, "Can't exclude execution levels!\n");
- return -EOPNOTSUPP;
+ return -EINVAL;
}
if (event->cpu < 0) {
/* Validate node/xp vs topology */
switch (type) {
+ case CCN_TYPE_MN:
+ if (node_xp != ccn->mn_id) {
+ dev_warn(ccn->dev, "Invalid MN ID %d!\n", node_xp);
+ return -EINVAL;
+ }
+ break;
case CCN_TYPE_XP:
if (node_xp >= ccn->num_xps) {
dev_warn(ccn->dev, "Invalid XP ID %d!\n", node_xp);
struct arm_ccn_component *xp;
u32 val, dt_cfg;
+ /* Nothing to do for cycle counter */
+ if (hw->idx == CCN_IDX_PMU_CYCLE_COUNTER)
+ return;
+
if (CCN_CONFIG_TYPE(event->attr.config) == CCN_TYPE_XP)
xp = &ccn->xp[CCN_CONFIG_XP(event->attr.config)];
else
arm_ccn_pmu_read_counter(ccn, hw->idx));
hw->state = 0;
- /*
- * Pin the timer, so that the overflows are handled by the chosen
- * event->cpu (this is the same one as presented in "cpumask"
- * attribute).
- */
- if (!ccn->irq)
- hrtimer_start(&ccn->dt.hrtimer, arm_ccn_pmu_timer_period(),
- HRTIMER_MODE_REL_PINNED);
-
/* Set the DT bus input, engaging the counter */
arm_ccn_pmu_xp_dt_config(event, 1);
}
static void arm_ccn_pmu_event_stop(struct perf_event *event, int flags)
{
- struct arm_ccn *ccn = pmu_to_arm_ccn(event->pmu);
struct hw_perf_event *hw = &event->hw;
- u64 timeout;
/* Disable counting, setting the DT bus to pass-through mode */
arm_ccn_pmu_xp_dt_config(event, 0);
- if (!ccn->irq)
- hrtimer_cancel(&ccn->dt.hrtimer);
-
- /* Let the DT bus drain */
- timeout = arm_ccn_pmu_read_counter(ccn, CCN_IDX_PMU_CYCLE_COUNTER) +
- ccn->num_xps;
- while (arm_ccn_pmu_read_counter(ccn, CCN_IDX_PMU_CYCLE_COUNTER) <
- timeout)
- cpu_relax();
-
if (flags & PERF_EF_UPDATE)
arm_ccn_pmu_event_update(event);
/* Comparison values */
writel(cmp_l & 0xffffffff, source->base + CCN_XP_DT_CMP_VAL_L(wp));
- writel((cmp_l >> 32) & 0xefffffff,
+ writel((cmp_l >> 32) & 0x7fffffff,
source->base + CCN_XP_DT_CMP_VAL_L(wp) + 4);
writel(cmp_h & 0xffffffff, source->base + CCN_XP_DT_CMP_VAL_H(wp));
writel((cmp_h >> 32) & 0x0fffffff,
/* Mask */
writel(mask_l & 0xffffffff, source->base + CCN_XP_DT_CMP_MASK_L(wp));
- writel((mask_l >> 32) & 0xefffffff,
+ writel((mask_l >> 32) & 0x7fffffff,
source->base + CCN_XP_DT_CMP_MASK_L(wp) + 4);
writel(mask_h & 0xffffffff, source->base + CCN_XP_DT_CMP_MASK_H(wp));
writel((mask_h >> 32) & 0x0fffffff,
hw->event_base = CCN_XP_DT_CONFIG__DT_CFG__XP_PMU_EVENT(hw->config_base);
id = (CCN_CONFIG_VC(event->attr.config) << 4) |
- (CCN_CONFIG_PORT(event->attr.config) << 3) |
+ (CCN_CONFIG_BUS(event->attr.config) << 3) |
(CCN_CONFIG_EVENT(event->attr.config) << 0);
val = readl(source->base + CCN_XP_PMU_EVENT_SEL);
spin_unlock(&ccn->dt.config_lock);
}
+static int arm_ccn_pmu_active_counters(struct arm_ccn *ccn)
+{
+ return bitmap_weight(ccn->dt.pmu_counters_mask,
+ CCN_NUM_PMU_EVENT_COUNTERS + 1);
+}
+
static int arm_ccn_pmu_event_add(struct perf_event *event, int flags)
{
int err;
struct hw_perf_event *hw = &event->hw;
+ struct arm_ccn *ccn = pmu_to_arm_ccn(event->pmu);
err = arm_ccn_pmu_event_alloc(event);
if (err)
return err;
+ /*
+ * Pin the timer, so that the overflows are handled by the chosen
+ * event->cpu (this is the same one as presented in "cpumask"
+ * attribute).
+ */
+ if (!ccn->irq && arm_ccn_pmu_active_counters(ccn) == 1)
+ hrtimer_start(&ccn->dt.hrtimer, arm_ccn_pmu_timer_period(),
+ HRTIMER_MODE_REL_PINNED);
+
arm_ccn_pmu_event_config(event);
hw->state = PERF_HES_STOPPED;
static void arm_ccn_pmu_event_del(struct perf_event *event, int flags)
{
+ struct arm_ccn *ccn = pmu_to_arm_ccn(event->pmu);
+
arm_ccn_pmu_event_stop(event, PERF_EF_UPDATE);
arm_ccn_pmu_event_release(event);
+
+ if (!ccn->irq && arm_ccn_pmu_active_counters(ccn) == 0)
+ hrtimer_cancel(&ccn->dt.hrtimer);
}
static void arm_ccn_pmu_event_read(struct perf_event *event)
arm_ccn_pmu_event_update(event);
}
+static void arm_ccn_pmu_enable(struct pmu *pmu)
+{
+ struct arm_ccn *ccn = pmu_to_arm_ccn(pmu);
+
+ u32 val = readl(ccn->dt.base + CCN_DT_PMCR);
+ val |= CCN_DT_PMCR__PMU_EN;
+ writel(val, ccn->dt.base + CCN_DT_PMCR);
+}
+
+static void arm_ccn_pmu_disable(struct pmu *pmu)
+{
+ struct arm_ccn *ccn = pmu_to_arm_ccn(pmu);
+
+ u32 val = readl(ccn->dt.base + CCN_DT_PMCR);
+ val &= ~CCN_DT_PMCR__PMU_EN;
+ writel(val, ccn->dt.base + CCN_DT_PMCR);
+}
+
static irqreturn_t arm_ccn_pmu_overflow_handler(struct arm_ccn_dt *dt)
{
u32 pmovsr = readl(dt->base + CCN_DT_PMOVSR);
.start = arm_ccn_pmu_event_start,
.stop = arm_ccn_pmu_event_stop,
.read = arm_ccn_pmu_event_read,
+ .pmu_enable = arm_ccn_pmu_enable,
+ .pmu_disable = arm_ccn_pmu_disable,
};
/* No overflow interrupt? Have to use a timer instead. */
switch (type) {
case CCN_TYPE_MN:
+ ccn->mn_id = id;
+ return 0;
case CCN_TYPE_DT:
return 0;
case CCN_TYPE_XP:
/* Can set 'disable' bits, so can acknowledge interrupts */
writel(CCN_MN_ERRINT_STATUS__PMU_EVENTS__ENABLE,
ccn->base + CCN_MN_ERRINT_STATUS);
- err = devm_request_irq(ccn->dev, irq, arm_ccn_irq_handler, 0,
- dev_name(ccn->dev), ccn);
+ err = devm_request_irq(ccn->dev, irq, arm_ccn_irq_handler,
+ IRQF_NOBALANCING | IRQF_NO_THREAD,
+ dev_name(ccn->dev), ccn);
if (err)
return err;
parent = class_find_device(vexpress_config_class, NULL, bridge,
vexpress_config_node_match);
+ of_node_put(bridge);
if (WARN_ON(!parent))
return -ENODEV;
config HW_RANDOM_MXC_RNGA
tristate "Freescale i.MX RNGA Random Number Generator"
- depends on ARCH_HAS_RNGA
+ depends on SOC_IMX31
default HW_RANDOM
---help---
This driver provides kernel-side support for the Random Number
goto out;
rc = tpm2_do_selftest(chip);
- if (rc != TPM2_RC_INITIALIZE) {
+ if (rc != 0 && rc != TPM2_RC_INITIALIZE) {
dev_err(&chip->dev, "TPM self test failed\n");
goto out;
}
}
}
- return rc;
out:
if (rc > 0)
rc = -ENODEV;
*/
struct virtqueue *c_ivq, *c_ovq;
+ /*
+ * A control packet buffer for guest->host requests, protected
+ * by c_ovq_lock.
+ */
+ struct virtio_console_control cpkt;
+
/* Array of per-port IO virtqueues */
struct virtqueue **in_vqs, **out_vqs;
unsigned int event, unsigned int value)
{
struct scatterlist sg[1];
- struct virtio_console_control cpkt;
struct virtqueue *vq;
unsigned int len;
if (!use_multiport(portdev))
return 0;
- cpkt.id = cpu_to_virtio32(portdev->vdev, port_id);
- cpkt.event = cpu_to_virtio16(portdev->vdev, event);
- cpkt.value = cpu_to_virtio16(portdev->vdev, value);
-
vq = portdev->c_ovq;
- sg_init_one(sg, &cpkt, sizeof(cpkt));
-
spin_lock(&portdev->c_ovq_lock);
- if (virtqueue_add_outbuf(vq, sg, 1, &cpkt, GFP_ATOMIC) == 0) {
+
+ portdev->cpkt.id = cpu_to_virtio32(portdev->vdev, port_id);
+ portdev->cpkt.event = cpu_to_virtio16(portdev->vdev, event);
+ portdev->cpkt.value = cpu_to_virtio16(portdev->vdev, value);
+
+ sg_init_one(sg, &portdev->cpkt, sizeof(struct virtio_console_control));
+
+ if (virtqueue_add_outbuf(vq, sg, 1, &portdev->cpkt, GFP_ATOMIC) == 0) {
virtqueue_kick(vq);
while (!virtqueue_get_buf(vq, &len)
&& !virtqueue_is_broken(vq))
cpu_relax();
}
+
spin_unlock(&portdev->c_ovq_lock);
return 0;
}
DEF_FIXED(".s1", CLK_S1, CLK_PLL1_DIV2, 3, 1),
DEF_FIXED(".s2", CLK_S2, CLK_PLL1_DIV2, 4, 1),
DEF_FIXED(".s3", CLK_S3, CLK_PLL1_DIV2, 6, 1),
+ DEF_FIXED(".sdsrc", CLK_SDSRC, CLK_PLL1_DIV2, 2, 1),
/* Core Clock Outputs */
DEF_FIXED("ztr", R8A7795_CLK_ZTR, CLK_PLL1_DIV2, 6, 1),
DEF_FIXED("s3d2", R8A7795_CLK_S3D2, CLK_S3, 2, 1),
DEF_FIXED("s3d4", R8A7795_CLK_S3D4, CLK_S3, 4, 1),
- DEF_GEN3_SD("sd0", R8A7795_CLK_SD0, CLK_PLL1_DIV2, 0x0074),
- DEF_GEN3_SD("sd1", R8A7795_CLK_SD1, CLK_PLL1_DIV2, 0x0078),
- DEF_GEN3_SD("sd2", R8A7795_CLK_SD2, CLK_PLL1_DIV2, 0x0268),
- DEF_GEN3_SD("sd3", R8A7795_CLK_SD3, CLK_PLL1_DIV2, 0x026c),
+ DEF_GEN3_SD("sd0", R8A7795_CLK_SD0, CLK_SDSRC, 0x0074),
+ DEF_GEN3_SD("sd1", R8A7795_CLK_SD1, CLK_SDSRC, 0x0078),
+ DEF_GEN3_SD("sd2", R8A7795_CLK_SD2, CLK_SDSRC, 0x0268),
+ DEF_GEN3_SD("sd3", R8A7795_CLK_SD3, CLK_SDSRC, 0x026c),
DEF_FIXED("cl", R8A7795_CLK_CL, CLK_PLL1_DIV2, 48, 1),
DEF_FIXED("cp", R8A7795_CLK_CP, CLK_EXTAL, 2, 1),
/* perihp */
GATE(0, "cpll_aclk_perihp_src", "cpll", CLK_IGNORE_UNUSED,
- RK3399_CLKGATE_CON(5), 0, GFLAGS),
- GATE(0, "gpll_aclk_perihp_src", "gpll", CLK_IGNORE_UNUSED,
RK3399_CLKGATE_CON(5), 1, GFLAGS),
+ GATE(0, "gpll_aclk_perihp_src", "gpll", CLK_IGNORE_UNUSED,
+ RK3399_CLKGATE_CON(5), 0, GFLAGS),
COMPOSITE(ACLK_PERIHP, "aclk_perihp", mux_aclk_perihp_p, CLK_IGNORE_UNUSED,
RK3399_CLKSEL_CON(14), 7, 1, MFLAGS, 0, 5, DFLAGS,
RK3399_CLKGATE_CON(5), 2, GFLAGS),
RK3399_CLKGATE_CON(6), 14, GFLAGS),
GATE(0, "cpll_aclk_emmc_src", "cpll", CLK_IGNORE_UNUSED,
- RK3399_CLKGATE_CON(6), 12, GFLAGS),
- GATE(0, "gpll_aclk_emmc_src", "gpll", CLK_IGNORE_UNUSED,
RK3399_CLKGATE_CON(6), 13, GFLAGS),
+ GATE(0, "gpll_aclk_emmc_src", "gpll", CLK_IGNORE_UNUSED,
+ RK3399_CLKGATE_CON(6), 12, GFLAGS),
COMPOSITE_NOGATE(ACLK_EMMC, "aclk_emmc", mux_aclk_emmc_p, CLK_IGNORE_UNUSED,
RK3399_CLKSEL_CON(21), 7, 1, MFLAGS, 0, 5, DFLAGS),
GATE(ACLK_EMMC_CORE, "aclk_emmccore", "aclk_emmc", CLK_IGNORE_UNUSED,
/* vio */
COMPOSITE(ACLK_VIO, "aclk_vio", mux_pll_src_cpll_gpll_ppll_p, CLK_IGNORE_UNUSED,
RK3399_CLKSEL_CON(42), 6, 2, MFLAGS, 0, 5, DFLAGS,
- RK3399_CLKGATE_CON(11), 10, GFLAGS),
+ RK3399_CLKGATE_CON(11), 0, GFLAGS),
COMPOSITE_NOMUX(PCLK_VIO, "pclk_vio", "aclk_vio", 0,
RK3399_CLKSEL_CON(43), 0, 5, DFLAGS,
RK3399_CLKGATE_CON(11), 1, GFLAGS),
"hclk_perilp1",
"hclk_perilp1_noc",
"aclk_dmac0_perilp",
+ "aclk_emmc_noc",
"gpll_hclk_perilp1_src",
"gpll_aclk_perilp0_src",
"gpll_aclk_perihp_src",
[RST_BUS_I2S1] = { 0x2d0, BIT(13) },
[RST_BUS_I2S2] = { 0x2d0, BIT(14) },
- [RST_BUS_I2C0] = { 0x2d4, BIT(0) },
- [RST_BUS_I2C1] = { 0x2d4, BIT(1) },
- [RST_BUS_I2C2] = { 0x2d4, BIT(2) },
- [RST_BUS_UART0] = { 0x2d4, BIT(16) },
- [RST_BUS_UART1] = { 0x2d4, BIT(17) },
- [RST_BUS_UART2] = { 0x2d4, BIT(18) },
- [RST_BUS_UART3] = { 0x2d4, BIT(19) },
- [RST_BUS_SCR] = { 0x2d4, BIT(20) },
+ [RST_BUS_I2C0] = { 0x2d8, BIT(0) },
+ [RST_BUS_I2C1] = { 0x2d8, BIT(1) },
+ [RST_BUS_I2C2] = { 0x2d8, BIT(2) },
+ [RST_BUS_UART0] = { 0x2d8, BIT(16) },
+ [RST_BUS_UART1] = { 0x2d8, BIT(17) },
+ [RST_BUS_UART2] = { 0x2d8, BIT(18) },
+ [RST_BUS_UART3] = { 0x2d8, BIT(19) },
+ [RST_BUS_SCR] = { 0x2d8, BIT(20) },
};
static const struct sunxi_ccu_desc sun8i_h3_ccu_desc = {
return;
WARN_ON(readl_relaxed_poll_timeout(common->base + common->reg, reg,
- !(reg & lock), 100, 70000));
+ reg & lock, 100, 70000));
}
int sunxi_ccu_probe(struct device_node *node, void __iomem *reg,
#include "ccu_gate.h"
#include "ccu_nk.h"
-void ccu_nk_find_best(unsigned long parent, unsigned long rate,
- unsigned int max_n, unsigned int max_k,
- unsigned int *n, unsigned int *k)
+static void ccu_nk_find_best(unsigned long parent, unsigned long rate,
+ unsigned int max_n, unsigned int max_k,
+ unsigned int *n, unsigned int *k)
{
unsigned long best_rate = 0;
unsigned int best_k = 0, best_n = 0;
SUN4I_PLL2_PRE_DIV_WIDTH,
CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO,
&sun4i_a10_pll2_lock);
- if (!prediv_clk) {
+ if (IS_ERR(prediv_clk)) {
pr_err("Couldn't register the prediv clock\n");
goto err_free_array;
}
&mult->hw, &clk_multiplier_ops,
&gate->hw, &clk_gate_ops,
CLK_SET_RATE_PARENT);
- if (!base_clk) {
+ if (IS_ERR(base_clk)) {
pr_err("Couldn't register the base multiplier clock\n");
goto err_free_multiplier;
}
return;
reg = of_io_request_and_map(node, 0, of_node_full_name(node));
- if (!reg) {
+ if (IS_ERR(reg)) {
pr_err("Could not get registers for sun8i-mbus-clk\n");
goto err_free_parents;
}
.div_nmp = &pllp_nmp,
.freq_table = pll_d_freq_table,
.flags = TEGRA_PLL_HAS_CPCON | TEGRA_PLL_SET_LFCON |
- TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE,
+ TEGRA_PLL_HAS_LOCK_ENABLE,
};
static struct tegra_clk_pll_params pll_d2_params = {
.div_nmp = &pllp_nmp,
.freq_table = pll_d_freq_table,
.flags = TEGRA_PLL_HAS_CPCON | TEGRA_PLL_SET_LFCON |
- TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE,
+ TEGRA_PLL_HAS_LOCK_ENABLE,
};
static const struct pdiv_map pllu_p[] = {
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
+
+#define pr_fmt(fmt) "arm_arch_timer: " fmt
+
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/device.h>
arch_timer_ppi[PHYS_NONSECURE_PPI]);
}
+static u32 check_ppi_trigger(int irq)
+{
+ u32 flags = irq_get_trigger_type(irq);
+
+ if (flags != IRQF_TRIGGER_HIGH && flags != IRQF_TRIGGER_LOW) {
+ pr_warn("WARNING: Invalid trigger for IRQ%d, assuming level low\n", irq);
+ pr_warn("WARNING: Please fix your firmware\n");
+ flags = IRQF_TRIGGER_LOW;
+ }
+
+ return flags;
+}
+
static int arch_timer_starting_cpu(unsigned int cpu)
{
struct clock_event_device *clk = this_cpu_ptr(arch_timer_evt);
+ u32 flags;
__arch_timer_setup(ARCH_CP15_TIMER, clk);
- enable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], 0);
+ flags = check_ppi_trigger(arch_timer_ppi[arch_timer_uses_ppi]);
+ enable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], flags);
- if (arch_timer_has_nonsecure_ppi())
- enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], 0);
+ if (arch_timer_has_nonsecure_ppi()) {
+ flags = check_ppi_trigger(arch_timer_ppi[PHYS_NONSECURE_PPI]);
+ enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], flags);
+ }
arch_counter_set_user_access();
if (evtstrm_enable)
}
-static void
+static int
kona_timer_get_counter(void __iomem *timer_base, uint32_t *msw, uint32_t *lsw)
{
- int loop_limit = 4;
+ int loop_limit = 3;
/*
* Read 64-bit free running counter
* if new hi-word is equal to previously read hi-word then stop.
*/
- while (--loop_limit) {
+ do {
*msw = readl(timer_base + KONA_GPTIMER_STCHI_OFFSET);
*lsw = readl(timer_base + KONA_GPTIMER_STCLO_OFFSET);
if (*msw == readl(timer_base + KONA_GPTIMER_STCHI_OFFSET))
break;
- }
+ } while (--loop_limit);
if (!loop_limit) {
pr_err("bcm_kona_timer: getting counter failed.\n");
pr_err(" Timer will be impacted\n");
+ return -ETIMEDOUT;
}
- return;
+ return 0;
}
static int kona_timer_set_next_event(unsigned long clc,
uint32_t lsw, msw;
uint32_t reg;
+ int ret;
- kona_timer_get_counter(timers.tmr_regs, &msw, &lsw);
+ ret = kona_timer_get_counter(timers.tmr_regs, &msw, &lsw);
+ if (ret)
+ return ret;
/* Load the "next" event tick value */
writel(lsw + clc, timers.tmr_regs + KONA_GPTIMER_STCM0_OFFSET);
gic_start_count();
}
-static void __init gic_clocksource_of_init(struct device_node *node)
+static int __init gic_clocksource_of_init(struct device_node *node)
{
struct clk *clk;
int ret;
#include <linux/of_irq.h>
#include <linux/sched_clock.h>
+#include <clocksource/pxa.h>
+
#include <asm/div64.h>
#define OSMR0 0x00 /* OS Timer 0 Match Register */
.set_next_event = sun4i_clkevt_next_event,
};
+static void sun4i_timer_clear_interrupt(void)
+{
+ writel(TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_ST_REG);
+}
static irqreturn_t sun4i_timer_interrupt(int irq, void *dev_id)
{
struct clock_event_device *evt = (struct clock_event_device *)dev_id;
- writel(0x1, timer_base + TIMER_IRQ_ST_REG);
+ sun4i_timer_clear_interrupt();
evt->event_handler(evt);
return IRQ_HANDLED;
/* Make sure timer is stopped before playing with interrupts */
sun4i_clkevt_time_stop(0);
+ /* clear timer0 interrupt */
+ sun4i_timer_clear_interrupt();
+
sun4i_clockevent.cpumask = cpu_possible_mask;
sun4i_clockevent.irq = irq;
struct clk *clk = of_clk_get_by_name(np, "fixed");
int ret;
- clk = of_clk_get(np, 0);
if (IS_ERR(clk)) {
pr_err("Failed to get clock");
return PTR_ERR(clk);
rate = clk_get_rate(fast_clk);
/* Disable irq's for clocksource usage */
- gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 0);
- gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 1);
- gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 2);
- gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 3);
+ gpt_writel(pcs_gpt.base, 0, TIMER_IRQ_MASK, 0);
+ gpt_writel(pcs_gpt.base, 0, TIMER_IRQ_MASK, 1);
+ gpt_writel(pcs_gpt.base, 0, TIMER_IRQ_MASK, 2);
+ gpt_writel(pcs_gpt.base, 0, TIMER_IRQ_MASK, 3);
/* Enable timer block */
writel(TIMER_ME_GLOBAL, pcs_gpt.base);
static int __init at91sam926x_pit_dt_init(struct device_node *node)
{
struct pit_data *data;
+ int ret;
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (!data)
return PTR_ERR(data->mck);
}
+ ret = clk_prepare_enable(data->mck);
+ if (ret) {
+ pr_err("Unable to enable mck\n");
+ return ret;
+ }
+
/* Get the interrupts property */
data->irq = irq_of_parse_and_map(node, 0);
if (!data->irq) {
{ .compatible = "ti,omap5", },
{ .compatible = "xlnx,zynq-7000", },
+
+ { }
};
static int __init cpufreq_dt_platdev_init(void)
/* Use following macros for conversions between pstate_id and index */
static inline int idx_to_pstate(unsigned int i)
{
+ if (unlikely(i >= powernv_pstate_info.nr_pstates)) {
+ pr_warn_once("index %u is out of bound\n", i);
+ return powernv_freqs[powernv_pstate_info.nominal].driver_data;
+ }
+
return powernv_freqs[i].driver_data;
}
static inline unsigned int pstate_to_idx(int pstate)
{
+ int min = powernv_freqs[powernv_pstate_info.min].driver_data;
+ int max = powernv_freqs[powernv_pstate_info.max].driver_data;
+
+ if (min > 0) {
+ if (unlikely((pstate < max) || (pstate > min))) {
+ pr_warn_once("pstate %d is out of bound\n", pstate);
+ return powernv_pstate_info.nominal;
+ }
+ } else {
+ if (unlikely((pstate > max) || (pstate < min))) {
+ pr_warn_once("pstate %d is out of bound\n", pstate);
+ return powernv_pstate_info.nominal;
+ }
+ }
/*
* abs() is deliberately used so that is works with
* both monotonically increasing and decreasing
} else {
gpstate_idx = calc_global_pstate(gpstates->elapsed_time,
gpstates->highest_lpstate_idx,
- freq_data.pstate_id);
+ gpstates->last_lpstate_idx);
}
/*
OP_ALG_AAI_CTR_MOD128);
const bool is_rfc3686 = alg->caam.rfc3686;
+ if (!ctx->authsize)
+ return 0;
+
/* NULL encryption / decryption */
if (!ctx->enckeylen)
return aead_null_set_sh_desc(aead);
/* Read and write assoclen bytes */
append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
- append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
+ if (alg->caam.geniv)
+ append_math_add_imm_u32(desc, VARSEQOUTLEN, REG3, IMM, ivsize);
+ else
+ append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
/* Skip assoc data */
append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
append_seq_fifo_load(desc, 0, FIFOLD_CLASS_CLASS2 | FIFOLD_TYPE_MSG |
KEY_VLF);
+ if (alg->caam.geniv) {
+ append_seq_load(desc, ivsize, LDST_CLASS_1_CCB |
+ LDST_SRCDST_BYTE_CONTEXT |
+ (ctx1_iv_off << LDST_OFFSET_SHIFT));
+ append_move(desc, MOVE_SRC_CLASS1CTX | MOVE_DEST_CLASS2INFIFO |
+ (ctx1_iv_off << MOVE_OFFSET_SHIFT) | ivsize);
+ }
+
/* Load Counter into CONTEXT1 reg */
if (is_rfc3686)
append_load_imm_u32(desc, be32_to_cpu(1), LDST_IMM |
keys_fit_inline = true;
/* aead_givencrypt shared descriptor */
- desc = ctx->sh_desc_givenc;
+ desc = ctx->sh_desc_enc;
/* Note: Context registers are saved. */
init_sh_desc_key_aead(desc, ctx, keys_fit_inline, is_rfc3686);
append_operation(desc, ctx->class2_alg_type |
OP_ALG_AS_INITFINAL | OP_ALG_ENCRYPT);
- /* ivsize + cryptlen = seqoutlen - authsize */
- append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize);
-
/* Read and write assoclen bytes */
append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ);
append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ);
+ /* ivsize + cryptlen = seqoutlen - authsize */
+ append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize);
+
/* Skip assoc data */
append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF);
ctx->sh_desc_enc_dma = dma_map_single(jrdev, desc,
desc_bytes(desc),
DMA_TO_DEVICE);
- if (dma_mapping_error(jrdev, ctx->sh_desc_givenc_dma)) {
+ if (dma_mapping_error(jrdev, ctx->sh_desc_enc_dma)) {
dev_err(jrdev, "unable to map shared descriptor\n");
return -ENOMEM;
}
init_aead_job(req, edesc, all_contig, encrypt);
- if (ivsize && (is_rfc3686 || !(alg->caam.geniv && encrypt)))
+ if (ivsize && ((is_rfc3686 && encrypt) || !alg->caam.geniv))
append_load_as_imm(desc, req->iv, ivsize,
LDST_CLASS_1_CCB |
LDST_SRCDST_BYTE_CONTEXT |
return ret;
}
-static int aead_givdecrypt(struct aead_request *req)
-{
- struct crypto_aead *aead = crypto_aead_reqtfm(req);
- unsigned int ivsize = crypto_aead_ivsize(aead);
-
- if (req->cryptlen < ivsize)
- return -EINVAL;
-
- req->cryptlen -= ivsize;
- req->assoclen += ivsize;
-
- return aead_decrypt(req);
-}
-
/*
* allocate and map the ablkcipher extended descriptor for ablkcipher
*/
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = AES_BLOCK_SIZE,
.maxauthsize = MD5_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = AES_BLOCK_SIZE,
.maxauthsize = SHA1_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = AES_BLOCK_SIZE,
.maxauthsize = SHA224_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = AES_BLOCK_SIZE,
.maxauthsize = SHA256_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = AES_BLOCK_SIZE,
.maxauthsize = SHA384_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = AES_BLOCK_SIZE,
.maxauthsize = SHA512_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = DES3_EDE_BLOCK_SIZE,
.maxauthsize = MD5_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = DES3_EDE_BLOCK_SIZE,
.maxauthsize = SHA1_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = DES3_EDE_BLOCK_SIZE,
.maxauthsize = SHA224_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = DES3_EDE_BLOCK_SIZE,
.maxauthsize = SHA256_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = DES3_EDE_BLOCK_SIZE,
.maxauthsize = SHA384_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = DES3_EDE_BLOCK_SIZE,
.maxauthsize = SHA512_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = DES_BLOCK_SIZE,
.maxauthsize = MD5_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = DES_BLOCK_SIZE,
.maxauthsize = SHA1_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = DES_BLOCK_SIZE,
.maxauthsize = SHA224_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = DES_BLOCK_SIZE,
.maxauthsize = SHA256_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = DES_BLOCK_SIZE,
.maxauthsize = SHA384_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = DES_BLOCK_SIZE,
.maxauthsize = SHA512_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = CTR_RFC3686_IV_SIZE,
.maxauthsize = MD5_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = CTR_RFC3686_IV_SIZE,
.maxauthsize = SHA1_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = CTR_RFC3686_IV_SIZE,
.maxauthsize = SHA224_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = CTR_RFC3686_IV_SIZE,
.maxauthsize = SHA256_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = CTR_RFC3686_IV_SIZE,
.maxauthsize = SHA384_DIGEST_SIZE,
},
.setkey = aead_setkey,
.setauthsize = aead_setauthsize,
.encrypt = aead_encrypt,
- .decrypt = aead_givdecrypt,
+ .decrypt = aead_decrypt,
.ivsize = CTR_RFC3686_IV_SIZE,
.maxauthsize = SHA512_DIGEST_SIZE,
},
template->name);
snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
template->driver_name);
+ t_alg->ahash_alg.setkey = NULL;
}
alg->cra_module = THIS_MODULE;
alg->cra_init = caam_hash_cra_init;
.setkey = qat_alg_ablkcipher_xts_setkey,
.decrypt = qat_alg_ablkcipher_decrypt,
.encrypt = qat_alg_ablkcipher_encrypt,
- .min_keysize = AES_MIN_KEY_SIZE,
- .max_keysize = AES_MAX_KEY_SIZE,
+ .min_keysize = 2 * AES_MIN_KEY_SIZE,
+ .max_keysize = 2 * AES_MAX_KEY_SIZE,
.ivsize = AES_BLOCK_SIZE,
},
},
blkcipher_walk_init(&walk, dst, src, nbytes);
- iv = (u8 *)walk.iv;
ret = blkcipher_walk_virt(desc, &walk);
+ iv = walk.iv;
memset(tweak, 0, AES_BLOCK_SIZE);
aes_p8_encrypt(iv, tweak, &ctx->tweak_key);
}
pgoff = linear_page_index(vma, pmd_addr);
- phys = pgoff_to_phys(dax_dev, pgoff, PAGE_SIZE);
+ phys = pgoff_to_phys(dax_dev, pgoff, PMD_SIZE);
if (phys == -1) {
dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__,
pgoff);
if (rc)
return rc;
+ /* adjust the dax_region resource to the start of data */
+ res.start += le64_to_cpu(pfn_sb->dataoff);
+
nd_region = to_nd_region(dev->parent);
dax_region = alloc_dax_region(dev, nd_region->id, &res,
le32_to_cpu(pfn_sb->align), addr, PFN_DEV|PFN_MAP);
err_clk_disable:
clk_disable_unprepare(atxdmac->clk);
err_free_irq:
- free_irq(atxdmac->irq, atxdmac->dma.dev);
+ free_irq(atxdmac->irq, atxdmac);
return ret;
}
dma_async_device_unregister(&atxdmac->dma);
clk_disable_unprepare(atxdmac->clk);
- free_irq(atxdmac->irq, atxdmac->dma.dev);
+ free_irq(atxdmac->irq, atxdmac);
for (i = 0; i < atxdmac->dma.chancnt; i++) {
struct at_xdmac_chan *atchan = &atxdmac->chan[i];
rc = of_property_read_u32(np, "reg", &off);
if (rc) {
dev_err(dev, "Reg property not found in JQ node\n");
+ of_node_put(np);
return -ENODEV;
}
/* Find out the Job Rings present under each JQ */
{
struct mdc_dma *mdma;
struct resource *res;
- const struct of_device_id *match;
unsigned int i;
u32 val;
int ret;
return -ENOMEM;
platform_set_drvdata(pdev, mdma);
- match = of_match_device(mdc_dma_of_match, &pdev->dev);
- mdma->soc = match->data;
+ mdma->soc = of_device_get_match_data(&pdev->dev);
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
mdma->regs = devm_ioremap_resource(&pdev->dev, res);
vd_last_issued = list_entry(vc->desc_issued.prev,
struct virt_dma_desc, node);
pxad_desc_chain(vd_last_issued, vd);
- if (is_chan_running(chan) || is_desc_completed(vd_last_issued))
+ if (is_chan_running(chan) || is_desc_completed(vd))
return true;
}
struct virt_dma_desc *vd, *tmp;
unsigned int dcsr;
unsigned long flags;
+ bool vd_completed;
dma_cookie_t last_started = 0;
BUG_ON(!chan);
spin_lock_irqsave(&chan->vc.lock, flags);
list_for_each_entry_safe(vd, tmp, &chan->vc.desc_issued, node) {
+ vd_completed = is_desc_completed(vd);
dev_dbg(&chan->vc.chan.dev->device,
- "%s(): checking txd %p[%x]: completed=%d\n",
- __func__, vd, vd->tx.cookie, is_desc_completed(vd));
+ "%s(): checking txd %p[%x]: completed=%d dcsr=0x%x\n",
+ __func__, vd, vd->tx.cookie, vd_completed,
+ dcsr);
last_started = vd->tx.cookie;
if (to_pxad_sw_desc(vd)->cyclic) {
vchan_cyclic_callback(vd);
break;
}
- if (is_desc_completed(vd)) {
+ if (vd_completed) {
list_del(&vd->node);
vchan_cookie_complete(vd);
} else {
{
struct usb_dmac_chan *chan = dev;
irqreturn_t ret = IRQ_NONE;
- u32 mask = USB_DMACHCR_TE;
- u32 check_bits = USB_DMACHCR_TE | USB_DMACHCR_SP;
+ u32 mask = 0;
u32 chcr;
+ bool xfer_end = false;
spin_lock(&chan->vc.lock);
chcr = usb_dmac_chan_read(chan, USB_DMACHCR);
- if (chcr & check_bits)
- mask |= USB_DMACHCR_DE | check_bits;
+ if (chcr & (USB_DMACHCR_TE | USB_DMACHCR_SP)) {
+ mask |= USB_DMACHCR_DE | USB_DMACHCR_TE | USB_DMACHCR_SP;
+ if (chcr & USB_DMACHCR_DE)
+ xfer_end = true;
+ ret |= IRQ_HANDLED;
+ }
if (chcr & USB_DMACHCR_NULL) {
/* An interruption of TE will happen after we set FTE */
mask |= USB_DMACHCR_NULL;
chcr |= USB_DMACHCR_FTE;
ret |= IRQ_HANDLED;
}
- usb_dmac_chan_write(chan, USB_DMACHCR, chcr & ~mask);
+ if (mask)
+ usb_dmac_chan_write(chan, USB_DMACHCR, chcr & ~mask);
- if (chcr & check_bits) {
+ if (xfer_end)
usb_dmac_isr_transfer_end(chan);
- ret |= IRQ_HANDLED;
- }
spin_unlock(&chan->vc.lock);
Support for error detection and correction the Intel
Sandy Bridge, Ivy Bridge and Haswell Integrated Memory Controllers.
+config EDAC_SKX
+ tristate "Intel Skylake server Integrated MC"
+ depends on EDAC_MM_EDAC && PCI && X86_64 && X86_MCE_INTEL
+ depends on PCI_MMCONFIG
+ help
+ Support for error detection and correction the Intel
+ Skylake server Integrated Memory Controllers.
+
config EDAC_MPC85XX
tristate "Freescale MPC83xx / MPC85xx"
depends on EDAC_MM_EDAC && FSL_SOC
obj-$(CONFIG_EDAC_I7300) += i7300_edac.o
obj-$(CONFIG_EDAC_I7CORE) += i7core_edac.o
obj-$(CONFIG_EDAC_SBRIDGE) += sb_edac.o
+obj-$(CONFIG_EDAC_SKX) += skx_edac.o
obj-$(CONFIG_EDAC_E7XXX) += e7xxx_edac.o
obj-$(CONFIG_EDAC_E752X) += e752x_edac.o
obj-$(CONFIG_EDAC_I82443BXGX) += i82443bxgx_edac.o
/* Knight's Landing Support */
/*
* KNL's memory channels are swizzled between memory controllers.
- * MC0 is mapped to CH3,5,6 and MC1 is mapped to CH0,1,2
+ * MC0 is mapped to CH3,4,5 and MC1 is mapped to CH0,1,2
*/
-#define knl_channel_remap(channel) ((channel + 3) % 6)
+#define knl_channel_remap(mc, chan) ((mc) ? (chan) : (chan) + 3)
/* Memory controller, TAD tables, error injection - 2-8-0, 2-9-0 (2 of these) */
#define PCI_DEVICE_ID_INTEL_KNL_IMC_MC 0x7840
mc = GET_BITFIELD(reg, entry*3, (entry*3)+2);
chan = GET_BITFIELD(reg, (entry*2) + 18, (entry*2) + 18 + 1);
- return knl_channel_remap(mc*3 + chan);
+ return knl_channel_remap(mc, chan);
}
/*
} else {
char A = *("A");
- channel = knl_channel_remap(channel);
+ /*
+ * Reported channel is in range 0-2, so we can't map it
+ * back to mc. To figure out mc we check machine check
+ * bank register that reported this error.
+ * bank15 means mc0 and bank16 means mc1.
+ */
+ channel = knl_channel_remap(m->bank == 16, channel);
channel_mask = 1 << channel;
+
snprintf(msg, sizeof(msg),
"%s%s err_code:%04x:%04x channel:%d (DIMM_%c)",
overflow ? " OVERFLOW" : "",
--- /dev/null
+/*
+ * EDAC driver for Intel(R) Xeon(R) Skylake processors
+ * Copyright (c) 2016, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/pci_ids.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/edac.h>
+#include <linux/mmzone.h>
+#include <linux/smp.h>
+#include <linux/bitmap.h>
+#include <linux/math64.h>
+#include <linux/mod_devicetable.h>
+#include <asm/cpu_device_id.h>
+#include <asm/processor.h>
+#include <asm/mce.h>
+
+#include "edac_core.h"
+
+#define SKX_REVISION " Ver: 1.0 "
+
+/*
+ * Debug macros
+ */
+#define skx_printk(level, fmt, arg...) \
+ edac_printk(level, "skx", fmt, ##arg)
+
+#define skx_mc_printk(mci, level, fmt, arg...) \
+ edac_mc_chipset_printk(mci, level, "skx", fmt, ##arg)
+
+/*
+ * Get a bit field at register value <v>, from bit <lo> to bit <hi>
+ */
+#define GET_BITFIELD(v, lo, hi) \
+ (((v) & GENMASK_ULL((hi), (lo))) >> (lo))
+
+static LIST_HEAD(skx_edac_list);
+
+static u64 skx_tolm, skx_tohm;
+
+#define NUM_IMC 2 /* memory controllers per socket */
+#define NUM_CHANNELS 3 /* channels per memory controller */
+#define NUM_DIMMS 2 /* Max DIMMS per channel */
+
+#define MASK26 0x3FFFFFF /* Mask for 2^26 */
+#define MASK29 0x1FFFFFFF /* Mask for 2^29 */
+
+/*
+ * Each cpu socket contains some pci devices that provide global
+ * information, and also some that are local to each of the two
+ * memory controllers on the die.
+ */
+struct skx_dev {
+ struct list_head list;
+ u8 bus[4];
+ struct pci_dev *sad_all;
+ struct pci_dev *util_all;
+ u32 mcroute;
+ struct skx_imc {
+ struct mem_ctl_info *mci;
+ u8 mc; /* system wide mc# */
+ u8 lmc; /* socket relative mc# */
+ u8 src_id, node_id;
+ struct skx_channel {
+ struct pci_dev *cdev;
+ struct skx_dimm {
+ u8 close_pg;
+ u8 bank_xor_enable;
+ u8 fine_grain_bank;
+ u8 rowbits;
+ u8 colbits;
+ } dimms[NUM_DIMMS];
+ } chan[NUM_CHANNELS];
+ } imc[NUM_IMC];
+};
+static int skx_num_sockets;
+
+struct skx_pvt {
+ struct skx_imc *imc;
+};
+
+struct decoded_addr {
+ struct skx_dev *dev;
+ u64 addr;
+ int socket;
+ int imc;
+ int channel;
+ u64 chan_addr;
+ int sktways;
+ int chanways;
+ int dimm;
+ int rank;
+ int channel_rank;
+ u64 rank_address;
+ int row;
+ int column;
+ int bank_address;
+ int bank_group;
+};
+
+static struct skx_dev *get_skx_dev(u8 bus, u8 idx)
+{
+ struct skx_dev *d;
+
+ list_for_each_entry(d, &skx_edac_list, list) {
+ if (d->bus[idx] == bus)
+ return d;
+ }
+
+ return NULL;
+}
+
+enum munittype {
+ CHAN0, CHAN1, CHAN2, SAD_ALL, UTIL_ALL, SAD
+};
+
+struct munit {
+ u16 did;
+ u16 devfn[NUM_IMC];
+ u8 busidx;
+ u8 per_socket;
+ enum munittype mtype;
+};
+
+/*
+ * List of PCI device ids that we need together with some device
+ * number and function numbers to tell which memory controller the
+ * device belongs to.
+ */
+static const struct munit skx_all_munits[] = {
+ { 0x2054, { }, 1, 1, SAD_ALL },
+ { 0x2055, { }, 1, 1, UTIL_ALL },
+ { 0x2040, { PCI_DEVFN(10, 0), PCI_DEVFN(12, 0) }, 2, 2, CHAN0 },
+ { 0x2044, { PCI_DEVFN(10, 4), PCI_DEVFN(12, 4) }, 2, 2, CHAN1 },
+ { 0x2048, { PCI_DEVFN(11, 0), PCI_DEVFN(13, 0) }, 2, 2, CHAN2 },
+ { 0x208e, { }, 1, 0, SAD },
+ { }
+};
+
+/*
+ * We use the per-socket device 0x2016 to count how many sockets are present,
+ * and to detemine which PCI buses are associated with each socket. Allocate
+ * and build the full list of all the skx_dev structures that we need here.
+ */
+static int get_all_bus_mappings(void)
+{
+ struct pci_dev *pdev, *prev;
+ struct skx_dev *d;
+ u32 reg;
+ int ndev = 0;
+
+ prev = NULL;
+ for (;;) {
+ pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x2016, prev);
+ if (!pdev)
+ break;
+ ndev++;
+ d = kzalloc(sizeof(*d), GFP_KERNEL);
+ if (!d) {
+ pci_dev_put(pdev);
+ return -ENOMEM;
+ }
+ pci_read_config_dword(pdev, 0xCC, ®);
+ d->bus[0] = GET_BITFIELD(reg, 0, 7);
+ d->bus[1] = GET_BITFIELD(reg, 8, 15);
+ d->bus[2] = GET_BITFIELD(reg, 16, 23);
+ d->bus[3] = GET_BITFIELD(reg, 24, 31);
+ edac_dbg(2, "busses: %x, %x, %x, %x\n",
+ d->bus[0], d->bus[1], d->bus[2], d->bus[3]);
+ list_add_tail(&d->list, &skx_edac_list);
+ skx_num_sockets++;
+ prev = pdev;
+ }
+
+ return ndev;
+}
+
+static int get_all_munits(const struct munit *m)
+{
+ struct pci_dev *pdev, *prev;
+ struct skx_dev *d;
+ u32 reg;
+ int i = 0, ndev = 0;
+
+ prev = NULL;
+ for (;;) {
+ pdev = pci_get_device(PCI_VENDOR_ID_INTEL, m->did, prev);
+ if (!pdev)
+ break;
+ ndev++;
+ if (m->per_socket == NUM_IMC) {
+ for (i = 0; i < NUM_IMC; i++)
+ if (m->devfn[i] == pdev->devfn)
+ break;
+ if (i == NUM_IMC)
+ goto fail;
+ }
+ d = get_skx_dev(pdev->bus->number, m->busidx);
+ if (!d)
+ goto fail;
+
+ /* Be sure that the device is enabled */
+ if (unlikely(pci_enable_device(pdev) < 0)) {
+ skx_printk(KERN_ERR,
+ "Couldn't enable %04x:%04x\n", PCI_VENDOR_ID_INTEL, m->did);
+ goto fail;
+ }
+
+ switch (m->mtype) {
+ case CHAN0: case CHAN1: case CHAN2:
+ pci_dev_get(pdev);
+ d->imc[i].chan[m->mtype].cdev = pdev;
+ break;
+ case SAD_ALL:
+ pci_dev_get(pdev);
+ d->sad_all = pdev;
+ break;
+ case UTIL_ALL:
+ pci_dev_get(pdev);
+ d->util_all = pdev;
+ break;
+ case SAD:
+ /*
+ * one of these devices per core, including cores
+ * that don't exist on this SKU. Ignore any that
+ * read a route table of zero, make sure all the
+ * non-zero values match.
+ */
+ pci_read_config_dword(pdev, 0xB4, ®);
+ if (reg != 0) {
+ if (d->mcroute == 0)
+ d->mcroute = reg;
+ else if (d->mcroute != reg) {
+ skx_printk(KERN_ERR,
+ "mcroute mismatch\n");
+ goto fail;
+ }
+ }
+ ndev--;
+ break;
+ }
+
+ prev = pdev;
+ }
+
+ return ndev;
+fail:
+ pci_dev_put(pdev);
+ return -ENODEV;
+}
+
+const struct x86_cpu_id skx_cpuids[] = {
+ { X86_VENDOR_INTEL, 6, 0x55, 0, 0 }, /* Skylake */
+ { }
+};
+MODULE_DEVICE_TABLE(x86cpu, skx_cpuids);
+
+static u8 get_src_id(struct skx_dev *d)
+{
+ u32 reg;
+
+ pci_read_config_dword(d->util_all, 0xF0, ®);
+
+ return GET_BITFIELD(reg, 12, 14);
+}
+
+static u8 skx_get_node_id(struct skx_dev *d)
+{
+ u32 reg;
+
+ pci_read_config_dword(d->util_all, 0xF4, ®);
+
+ return GET_BITFIELD(reg, 0, 2);
+}
+
+static int get_dimm_attr(u32 reg, int lobit, int hibit, int add, int minval,
+ int maxval, char *name)
+{
+ u32 val = GET_BITFIELD(reg, lobit, hibit);
+
+ if (val < minval || val > maxval) {
+ edac_dbg(2, "bad %s = %d (raw=%x)\n", name, val, reg);
+ return -EINVAL;
+ }
+ return val + add;
+}
+
+#define IS_DIMM_PRESENT(mtr) GET_BITFIELD((mtr), 15, 15)
+
+#define numrank(reg) get_dimm_attr((reg), 12, 13, 0, 1, 2, "ranks")
+#define numrow(reg) get_dimm_attr((reg), 2, 4, 12, 1, 6, "rows")
+#define numcol(reg) get_dimm_attr((reg), 0, 1, 10, 0, 2, "cols")
+
+static int get_width(u32 mtr)
+{
+ switch (GET_BITFIELD(mtr, 8, 9)) {
+ case 0:
+ return DEV_X4;
+ case 1:
+ return DEV_X8;
+ case 2:
+ return DEV_X16;
+ }
+ return DEV_UNKNOWN;
+}
+
+static int skx_get_hi_lo(void)
+{
+ struct pci_dev *pdev;
+ u32 reg;
+
+ pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x2034, NULL);
+ if (!pdev) {
+ edac_dbg(0, "Can't get tolm/tohm\n");
+ return -ENODEV;
+ }
+
+ pci_read_config_dword(pdev, 0xD0, ®);
+ skx_tolm = reg;
+ pci_read_config_dword(pdev, 0xD4, ®);
+ skx_tohm = reg;
+ pci_read_config_dword(pdev, 0xD8, ®);
+ skx_tohm |= (u64)reg << 32;
+
+ pci_dev_put(pdev);
+ edac_dbg(2, "tolm=%llx tohm=%llx\n", skx_tolm, skx_tohm);
+
+ return 0;
+}
+
+static int get_dimm_info(u32 mtr, u32 amap, struct dimm_info *dimm,
+ struct skx_imc *imc, int chan, int dimmno)
+{
+ int banks = 16, ranks, rows, cols, npages;
+ u64 size;
+
+ if (!IS_DIMM_PRESENT(mtr))
+ return 0;
+ ranks = numrank(mtr);
+ rows = numrow(mtr);
+ cols = numcol(mtr);
+
+ /*
+ * Compute size in 8-byte (2^3) words, then shift to MiB (2^20)
+ */
+ size = ((1ull << (rows + cols + ranks)) * banks) >> (20 - 3);
+ npages = MiB_TO_PAGES(size);
+
+ edac_dbg(0, "mc#%d: channel %d, dimm %d, %lld Mb (%d pages) bank: %d, rank: %d, row: %#x, col: %#x\n",
+ imc->mc, chan, dimmno, size, npages,
+ banks, ranks, rows, cols);
+
+ imc->chan[chan].dimms[dimmno].close_pg = GET_BITFIELD(mtr, 0, 0);
+ imc->chan[chan].dimms[dimmno].bank_xor_enable = GET_BITFIELD(mtr, 9, 9);
+ imc->chan[chan].dimms[dimmno].fine_grain_bank = GET_BITFIELD(amap, 0, 0);
+ imc->chan[chan].dimms[dimmno].rowbits = rows;
+ imc->chan[chan].dimms[dimmno].colbits = cols;
+
+ dimm->nr_pages = npages;
+ dimm->grain = 32;
+ dimm->dtype = get_width(mtr);
+ dimm->mtype = MEM_DDR4;
+ dimm->edac_mode = EDAC_SECDED; /* likely better than this */
+ snprintf(dimm->label, sizeof(dimm->label), "CPU_SrcID#%u_MC#%u_Chan#%u_DIMM#%u",
+ imc->src_id, imc->lmc, chan, dimmno);
+
+ return 1;
+}
+
+#define SKX_GET_MTMTR(dev, reg) \
+ pci_read_config_dword((dev), 0x87c, ®)
+
+static bool skx_check_ecc(struct pci_dev *pdev)
+{
+ u32 mtmtr;
+
+ SKX_GET_MTMTR(pdev, mtmtr);
+
+ return !!GET_BITFIELD(mtmtr, 2, 2);
+}
+
+static int skx_get_dimm_config(struct mem_ctl_info *mci)
+{
+ struct skx_pvt *pvt = mci->pvt_info;
+ struct skx_imc *imc = pvt->imc;
+ struct dimm_info *dimm;
+ int i, j;
+ u32 mtr, amap;
+ int ndimms;
+
+ for (i = 0; i < NUM_CHANNELS; i++) {
+ ndimms = 0;
+ pci_read_config_dword(imc->chan[i].cdev, 0x8C, &amap);
+ for (j = 0; j < NUM_DIMMS; j++) {
+ dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms,
+ mci->n_layers, i, j, 0);
+ pci_read_config_dword(imc->chan[i].cdev,
+ 0x80 + 4*j, &mtr);
+ ndimms += get_dimm_info(mtr, amap, dimm, imc, i, j);
+ }
+ if (ndimms && !skx_check_ecc(imc->chan[0].cdev)) {
+ skx_printk(KERN_ERR, "ECC is disabled on imc %d\n", imc->mc);
+ return -ENODEV;
+ }
+ }
+
+ return 0;
+}
+
+static void skx_unregister_mci(struct skx_imc *imc)
+{
+ struct mem_ctl_info *mci = imc->mci;
+
+ if (!mci)
+ return;
+
+ edac_dbg(0, "MC%d: mci = %p\n", imc->mc, mci);
+
+ /* Remove MC sysfs nodes */
+ edac_mc_del_mc(mci->pdev);
+
+ edac_dbg(1, "%s: free mci struct\n", mci->ctl_name);
+ kfree(mci->ctl_name);
+ edac_mc_free(mci);
+}
+
+static int skx_register_mci(struct skx_imc *imc)
+{
+ struct mem_ctl_info *mci;
+ struct edac_mc_layer layers[2];
+ struct pci_dev *pdev = imc->chan[0].cdev;
+ struct skx_pvt *pvt;
+ int rc;
+
+ /* allocate a new MC control structure */
+ layers[0].type = EDAC_MC_LAYER_CHANNEL;
+ layers[0].size = NUM_CHANNELS;
+ layers[0].is_virt_csrow = false;
+ layers[1].type = EDAC_MC_LAYER_SLOT;
+ layers[1].size = NUM_DIMMS;
+ layers[1].is_virt_csrow = true;
+ mci = edac_mc_alloc(imc->mc, ARRAY_SIZE(layers), layers,
+ sizeof(struct skx_pvt));
+
+ if (unlikely(!mci))
+ return -ENOMEM;
+
+ edac_dbg(0, "MC#%d: mci = %p\n", imc->mc, mci);
+
+ /* Associate skx_dev and mci for future usage */
+ imc->mci = mci;
+ pvt = mci->pvt_info;
+ pvt->imc = imc;
+
+ mci->ctl_name = kasprintf(GFP_KERNEL, "Skylake Socket#%d IMC#%d",
+ imc->node_id, imc->lmc);
+ mci->mtype_cap = MEM_FLAG_DDR4;
+ mci->edac_ctl_cap = EDAC_FLAG_NONE;
+ mci->edac_cap = EDAC_FLAG_NONE;
+ mci->mod_name = "skx_edac.c";
+ mci->dev_name = pci_name(imc->chan[0].cdev);
+ mci->mod_ver = SKX_REVISION;
+ mci->ctl_page_to_phys = NULL;
+
+ rc = skx_get_dimm_config(mci);
+ if (rc < 0)
+ goto fail;
+
+ /* record ptr to the generic device */
+ mci->pdev = &pdev->dev;
+
+ /* add this new MC control structure to EDAC's list of MCs */
+ if (unlikely(edac_mc_add_mc(mci))) {
+ edac_dbg(0, "MC: failed edac_mc_add_mc()\n");
+ rc = -EINVAL;
+ goto fail;
+ }
+
+ return 0;
+
+fail:
+ kfree(mci->ctl_name);
+ edac_mc_free(mci);
+ imc->mci = NULL;
+ return rc;
+}
+
+#define SKX_MAX_SAD 24
+
+#define SKX_GET_SAD(d, i, reg) \
+ pci_read_config_dword((d)->sad_all, 0x60 + 8 * (i), ®)
+#define SKX_GET_ILV(d, i, reg) \
+ pci_read_config_dword((d)->sad_all, 0x64 + 8 * (i), ®)
+
+#define SKX_SAD_MOD3MODE(sad) GET_BITFIELD((sad), 30, 31)
+#define SKX_SAD_MOD3(sad) GET_BITFIELD((sad), 27, 27)
+#define SKX_SAD_LIMIT(sad) (((u64)GET_BITFIELD((sad), 7, 26) << 26) | MASK26)
+#define SKX_SAD_MOD3ASMOD2(sad) GET_BITFIELD((sad), 5, 6)
+#define SKX_SAD_ATTR(sad) GET_BITFIELD((sad), 3, 4)
+#define SKX_SAD_INTERLEAVE(sad) GET_BITFIELD((sad), 1, 2)
+#define SKX_SAD_ENABLE(sad) GET_BITFIELD((sad), 0, 0)
+
+#define SKX_ILV_REMOTE(tgt) (((tgt) & 8) == 0)
+#define SKX_ILV_TARGET(tgt) ((tgt) & 7)
+
+static bool skx_sad_decode(struct decoded_addr *res)
+{
+ struct skx_dev *d = list_first_entry(&skx_edac_list, typeof(*d), list);
+ u64 addr = res->addr;
+ int i, idx, tgt, lchan, shift;
+ u32 sad, ilv;
+ u64 limit, prev_limit;
+ int remote = 0;
+
+ /* Simple sanity check for I/O space or out of range */
+ if (addr >= skx_tohm || (addr >= skx_tolm && addr < BIT_ULL(32))) {
+ edac_dbg(0, "Address %llx out of range\n", addr);
+ return false;
+ }
+
+restart:
+ prev_limit = 0;
+ for (i = 0; i < SKX_MAX_SAD; i++) {
+ SKX_GET_SAD(d, i, sad);
+ limit = SKX_SAD_LIMIT(sad);
+ if (SKX_SAD_ENABLE(sad)) {
+ if (addr >= prev_limit && addr <= limit)
+ goto sad_found;
+ }
+ prev_limit = limit + 1;
+ }
+ edac_dbg(0, "No SAD entry for %llx\n", addr);
+ return false;
+
+sad_found:
+ SKX_GET_ILV(d, i, ilv);
+
+ switch (SKX_SAD_INTERLEAVE(sad)) {
+ case 0:
+ idx = GET_BITFIELD(addr, 6, 8);
+ break;
+ case 1:
+ idx = GET_BITFIELD(addr, 8, 10);
+ break;
+ case 2:
+ idx = GET_BITFIELD(addr, 12, 14);
+ break;
+ case 3:
+ idx = GET_BITFIELD(addr, 30, 32);
+ break;
+ }
+
+ tgt = GET_BITFIELD(ilv, 4 * idx, 4 * idx + 3);
+
+ /* If point to another node, find it and start over */
+ if (SKX_ILV_REMOTE(tgt)) {
+ if (remote) {
+ edac_dbg(0, "Double remote!\n");
+ return false;
+ }
+ remote = 1;
+ list_for_each_entry(d, &skx_edac_list, list) {
+ if (d->imc[0].src_id == SKX_ILV_TARGET(tgt))
+ goto restart;
+ }
+ edac_dbg(0, "Can't find node %d\n", SKX_ILV_TARGET(tgt));
+ return false;
+ }
+
+ if (SKX_SAD_MOD3(sad) == 0)
+ lchan = SKX_ILV_TARGET(tgt);
+ else {
+ switch (SKX_SAD_MOD3MODE(sad)) {
+ case 0:
+ shift = 6;
+ break;
+ case 1:
+ shift = 8;
+ break;
+ case 2:
+ shift = 12;
+ break;
+ default:
+ edac_dbg(0, "illegal mod3mode\n");
+ return false;
+ }
+ switch (SKX_SAD_MOD3ASMOD2(sad)) {
+ case 0:
+ lchan = (addr >> shift) % 3;
+ break;
+ case 1:
+ lchan = (addr >> shift) % 2;
+ break;
+ case 2:
+ lchan = (addr >> shift) % 2;
+ lchan = (lchan << 1) | ~lchan;
+ break;
+ case 3:
+ lchan = ((addr >> shift) % 2) << 1;
+ break;
+ }
+ lchan = (lchan << 1) | (SKX_ILV_TARGET(tgt) & 1);
+ }
+
+ res->dev = d;
+ res->socket = d->imc[0].src_id;
+ res->imc = GET_BITFIELD(d->mcroute, lchan * 3, lchan * 3 + 2);
+ res->channel = GET_BITFIELD(d->mcroute, lchan * 2 + 18, lchan * 2 + 19);
+
+ edac_dbg(2, "%llx: socket=%d imc=%d channel=%d\n",
+ res->addr, res->socket, res->imc, res->channel);
+ return true;
+}
+
+#define SKX_MAX_TAD 8
+
+#define SKX_GET_TADBASE(d, mc, i, reg) \
+ pci_read_config_dword((d)->imc[mc].chan[0].cdev, 0x850 + 4 * (i), ®)
+#define SKX_GET_TADWAYNESS(d, mc, i, reg) \
+ pci_read_config_dword((d)->imc[mc].chan[0].cdev, 0x880 + 4 * (i), ®)
+#define SKX_GET_TADCHNILVOFFSET(d, mc, ch, i, reg) \
+ pci_read_config_dword((d)->imc[mc].chan[ch].cdev, 0x90 + 4 * (i), ®)
+
+#define SKX_TAD_BASE(b) ((u64)GET_BITFIELD((b), 12, 31) << 26)
+#define SKX_TAD_SKT_GRAN(b) GET_BITFIELD((b), 4, 5)
+#define SKX_TAD_CHN_GRAN(b) GET_BITFIELD((b), 6, 7)
+#define SKX_TAD_LIMIT(b) (((u64)GET_BITFIELD((b), 12, 31) << 26) | MASK26)
+#define SKX_TAD_OFFSET(b) ((u64)GET_BITFIELD((b), 4, 23) << 26)
+#define SKX_TAD_SKTWAYS(b) (1 << GET_BITFIELD((b), 10, 11))
+#define SKX_TAD_CHNWAYS(b) (GET_BITFIELD((b), 8, 9) + 1)
+
+/* which bit used for both socket and channel interleave */
+static int skx_granularity[] = { 6, 8, 12, 30 };
+
+static u64 skx_do_interleave(u64 addr, int shift, int ways, u64 lowbits)
+{
+ addr >>= shift;
+ addr /= ways;
+ addr <<= shift;
+
+ return addr | (lowbits & ((1ull << shift) - 1));
+}
+
+static bool skx_tad_decode(struct decoded_addr *res)
+{
+ int i;
+ u32 base, wayness, chnilvoffset;
+ int skt_interleave_bit, chn_interleave_bit;
+ u64 channel_addr;
+
+ for (i = 0; i < SKX_MAX_TAD; i++) {
+ SKX_GET_TADBASE(res->dev, res->imc, i, base);
+ SKX_GET_TADWAYNESS(res->dev, res->imc, i, wayness);
+ if (SKX_TAD_BASE(base) <= res->addr && res->addr <= SKX_TAD_LIMIT(wayness))
+ goto tad_found;
+ }
+ edac_dbg(0, "No TAD entry for %llx\n", res->addr);
+ return false;
+
+tad_found:
+ res->sktways = SKX_TAD_SKTWAYS(wayness);
+ res->chanways = SKX_TAD_CHNWAYS(wayness);
+ skt_interleave_bit = skx_granularity[SKX_TAD_SKT_GRAN(base)];
+ chn_interleave_bit = skx_granularity[SKX_TAD_CHN_GRAN(base)];
+
+ SKX_GET_TADCHNILVOFFSET(res->dev, res->imc, res->channel, i, chnilvoffset);
+ channel_addr = res->addr - SKX_TAD_OFFSET(chnilvoffset);
+
+ if (res->chanways == 3 && skt_interleave_bit > chn_interleave_bit) {
+ /* Must handle channel first, then socket */
+ channel_addr = skx_do_interleave(channel_addr, chn_interleave_bit,
+ res->chanways, channel_addr);
+ channel_addr = skx_do_interleave(channel_addr, skt_interleave_bit,
+ res->sktways, channel_addr);
+ } else {
+ /* Handle socket then channel. Preserve low bits from original address */
+ channel_addr = skx_do_interleave(channel_addr, skt_interleave_bit,
+ res->sktways, res->addr);
+ channel_addr = skx_do_interleave(channel_addr, chn_interleave_bit,
+ res->chanways, res->addr);
+ }
+
+ res->chan_addr = channel_addr;
+
+ edac_dbg(2, "%llx: chan_addr=%llx sktways=%d chanways=%d\n",
+ res->addr, res->chan_addr, res->sktways, res->chanways);
+ return true;
+}
+
+#define SKX_MAX_RIR 4
+
+#define SKX_GET_RIRWAYNESS(d, mc, ch, i, reg) \
+ pci_read_config_dword((d)->imc[mc].chan[ch].cdev, \
+ 0x108 + 4 * (i), ®)
+#define SKX_GET_RIRILV(d, mc, ch, idx, i, reg) \
+ pci_read_config_dword((d)->imc[mc].chan[ch].cdev, \
+ 0x120 + 16 * idx + 4 * (i), ®)
+
+#define SKX_RIR_VALID(b) GET_BITFIELD((b), 31, 31)
+#define SKX_RIR_LIMIT(b) (((u64)GET_BITFIELD((b), 1, 11) << 29) | MASK29)
+#define SKX_RIR_WAYS(b) (1 << GET_BITFIELD((b), 28, 29))
+#define SKX_RIR_CHAN_RANK(b) GET_BITFIELD((b), 16, 19)
+#define SKX_RIR_OFFSET(b) ((u64)(GET_BITFIELD((b), 2, 15) << 26))
+
+static bool skx_rir_decode(struct decoded_addr *res)
+{
+ int i, idx, chan_rank;
+ int shift;
+ u32 rirway, rirlv;
+ u64 rank_addr, prev_limit = 0, limit;
+
+ if (res->dev->imc[res->imc].chan[res->channel].dimms[0].close_pg)
+ shift = 6;
+ else
+ shift = 13;
+
+ for (i = 0; i < SKX_MAX_RIR; i++) {
+ SKX_GET_RIRWAYNESS(res->dev, res->imc, res->channel, i, rirway);
+ limit = SKX_RIR_LIMIT(rirway);
+ if (SKX_RIR_VALID(rirway)) {
+ if (prev_limit <= res->chan_addr &&
+ res->chan_addr <= limit)
+ goto rir_found;
+ }
+ prev_limit = limit;
+ }
+ edac_dbg(0, "No RIR entry for %llx\n", res->addr);
+ return false;
+
+rir_found:
+ rank_addr = res->chan_addr >> shift;
+ rank_addr /= SKX_RIR_WAYS(rirway);
+ rank_addr <<= shift;
+ rank_addr |= res->chan_addr & GENMASK_ULL(shift - 1, 0);
+
+ res->rank_address = rank_addr;
+ idx = (res->chan_addr >> shift) % SKX_RIR_WAYS(rirway);
+
+ SKX_GET_RIRILV(res->dev, res->imc, res->channel, idx, i, rirlv);
+ res->rank_address = rank_addr - SKX_RIR_OFFSET(rirlv);
+ chan_rank = SKX_RIR_CHAN_RANK(rirlv);
+ res->channel_rank = chan_rank;
+ res->dimm = chan_rank / 4;
+ res->rank = chan_rank % 4;
+
+ edac_dbg(2, "%llx: dimm=%d rank=%d chan_rank=%d rank_addr=%llx\n",
+ res->addr, res->dimm, res->rank,
+ res->channel_rank, res->rank_address);
+ return true;
+}
+
+static u8 skx_close_row[] = {
+ 15, 16, 17, 18, 20, 21, 22, 28, 10, 11, 12, 13, 29, 30, 31, 32, 33
+};
+static u8 skx_close_column[] = {
+ 3, 4, 5, 14, 19, 23, 24, 25, 26, 27
+};
+static u8 skx_open_row[] = {
+ 14, 15, 16, 20, 28, 21, 22, 23, 24, 25, 26, 27, 29, 30, 31, 32, 33
+};
+static u8 skx_open_column[] = {
+ 3, 4, 5, 6, 7, 8, 9, 10, 11, 12
+};
+static u8 skx_open_fine_column[] = {
+ 3, 4, 5, 7, 8, 9, 10, 11, 12, 13
+};
+
+static int skx_bits(u64 addr, int nbits, u8 *bits)
+{
+ int i, res = 0;
+
+ for (i = 0; i < nbits; i++)
+ res |= ((addr >> bits[i]) & 1) << i;
+ return res;
+}
+
+static int skx_bank_bits(u64 addr, int b0, int b1, int do_xor, int x0, int x1)
+{
+ int ret = GET_BITFIELD(addr, b0, b0) | (GET_BITFIELD(addr, b1, b1) << 1);
+
+ if (do_xor)
+ ret ^= GET_BITFIELD(addr, x0, x0) | (GET_BITFIELD(addr, x1, x1) << 1);
+
+ return ret;
+}
+
+static bool skx_mad_decode(struct decoded_addr *r)
+{
+ struct skx_dimm *dimm = &r->dev->imc[r->imc].chan[r->channel].dimms[r->dimm];
+ int bg0 = dimm->fine_grain_bank ? 6 : 13;
+
+ if (dimm->close_pg) {
+ r->row = skx_bits(r->rank_address, dimm->rowbits, skx_close_row);
+ r->column = skx_bits(r->rank_address, dimm->colbits, skx_close_column);
+ r->column |= 0x400; /* C10 is autoprecharge, always set */
+ r->bank_address = skx_bank_bits(r->rank_address, 8, 9, dimm->bank_xor_enable, 22, 28);
+ r->bank_group = skx_bank_bits(r->rank_address, 6, 7, dimm->bank_xor_enable, 20, 21);
+ } else {
+ r->row = skx_bits(r->rank_address, dimm->rowbits, skx_open_row);
+ if (dimm->fine_grain_bank)
+ r->column = skx_bits(r->rank_address, dimm->colbits, skx_open_fine_column);
+ else
+ r->column = skx_bits(r->rank_address, dimm->colbits, skx_open_column);
+ r->bank_address = skx_bank_bits(r->rank_address, 18, 19, dimm->bank_xor_enable, 22, 23);
+ r->bank_group = skx_bank_bits(r->rank_address, bg0, 17, dimm->bank_xor_enable, 20, 21);
+ }
+ r->row &= (1u << dimm->rowbits) - 1;
+
+ edac_dbg(2, "%llx: row=%x col=%x bank_addr=%d bank_group=%d\n",
+ r->addr, r->row, r->column, r->bank_address,
+ r->bank_group);
+ return true;
+}
+
+static bool skx_decode(struct decoded_addr *res)
+{
+
+ return skx_sad_decode(res) && skx_tad_decode(res) &&
+ skx_rir_decode(res) && skx_mad_decode(res);
+}
+
+#ifdef CONFIG_EDAC_DEBUG
+/*
+ * Debug feature. Make /sys/kernel/debug/skx_edac_test/addr.
+ * Write an address to this file to exercise the address decode
+ * logic in this driver.
+ */
+static struct dentry *skx_test;
+static u64 skx_fake_addr;
+
+static int debugfs_u64_set(void *data, u64 val)
+{
+ struct decoded_addr res;
+
+ res.addr = val;
+ skx_decode(&res);
+
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n");
+
+static struct dentry *mydebugfs_create(const char *name, umode_t mode,
+ struct dentry *parent, u64 *value)
+{
+ return debugfs_create_file(name, mode, parent, value, &fops_u64_wo);
+}
+
+static void setup_skx_debug(void)
+{
+ skx_test = debugfs_create_dir("skx_edac_test", NULL);
+ mydebugfs_create("addr", S_IWUSR, skx_test, &skx_fake_addr);
+}
+
+static void teardown_skx_debug(void)
+{
+ debugfs_remove_recursive(skx_test);
+}
+#else
+static void setup_skx_debug(void)
+{
+}
+
+static void teardown_skx_debug(void)
+{
+}
+#endif /*CONFIG_EDAC_DEBUG*/
+
+static void skx_mce_output_error(struct mem_ctl_info *mci,
+ const struct mce *m,
+ struct decoded_addr *res)
+{
+ enum hw_event_mc_err_type tp_event;
+ char *type, *optype, msg[256];
+ bool ripv = GET_BITFIELD(m->mcgstatus, 0, 0);
+ bool overflow = GET_BITFIELD(m->status, 62, 62);
+ bool uncorrected_error = GET_BITFIELD(m->status, 61, 61);
+ bool recoverable;
+ u32 core_err_cnt = GET_BITFIELD(m->status, 38, 52);
+ u32 mscod = GET_BITFIELD(m->status, 16, 31);
+ u32 errcode = GET_BITFIELD(m->status, 0, 15);
+ u32 optypenum = GET_BITFIELD(m->status, 4, 6);
+
+ recoverable = GET_BITFIELD(m->status, 56, 56);
+
+ if (uncorrected_error) {
+ if (ripv) {
+ type = "FATAL";
+ tp_event = HW_EVENT_ERR_FATAL;
+ } else {
+ type = "NON_FATAL";
+ tp_event = HW_EVENT_ERR_UNCORRECTED;
+ }
+ } else {
+ type = "CORRECTED";
+ tp_event = HW_EVENT_ERR_CORRECTED;
+ }
+
+ /*
+ * According with Table 15-9 of the Intel Architecture spec vol 3A,
+ * memory errors should fit in this mask:
+ * 000f 0000 1mmm cccc (binary)
+ * where:
+ * f = Correction Report Filtering Bit. If 1, subsequent errors
+ * won't be shown
+ * mmm = error type
+ * cccc = channel
+ * If the mask doesn't match, report an error to the parsing logic
+ */
+ if (!((errcode & 0xef80) == 0x80)) {
+ optype = "Can't parse: it is not a mem";
+ } else {
+ switch (optypenum) {
+ case 0:
+ optype = "generic undef request error";
+ break;
+ case 1:
+ optype = "memory read error";
+ break;
+ case 2:
+ optype = "memory write error";
+ break;
+ case 3:
+ optype = "addr/cmd error";
+ break;
+ case 4:
+ optype = "memory scrubbing error";
+ break;
+ default:
+ optype = "reserved";
+ break;
+ }
+ }
+
+ snprintf(msg, sizeof(msg),
+ "%s%s err_code:%04x:%04x socket:%d imc:%d rank:%d bg:%d ba:%d row:%x col:%x",
+ overflow ? " OVERFLOW" : "",
+ (uncorrected_error && recoverable) ? " recoverable" : "",
+ mscod, errcode,
+ res->socket, res->imc, res->rank,
+ res->bank_group, res->bank_address, res->row, res->column);
+
+ edac_dbg(0, "%s\n", msg);
+
+ /* Call the helper to output message */
+ edac_mc_handle_error(tp_event, mci, core_err_cnt,
+ m->addr >> PAGE_SHIFT, m->addr & ~PAGE_MASK, 0,
+ res->channel, res->dimm, -1,
+ optype, msg);
+}
+
+static int skx_mce_check_error(struct notifier_block *nb, unsigned long val,
+ void *data)
+{
+ struct mce *mce = (struct mce *)data;
+ struct decoded_addr res;
+ struct mem_ctl_info *mci;
+ char *type;
+
+ if (get_edac_report_status() == EDAC_REPORTING_DISABLED)
+ return NOTIFY_DONE;
+
+ /* ignore unless this is memory related with an address */
+ if ((mce->status & 0xefff) >> 7 != 1 || !(mce->status & MCI_STATUS_ADDRV))
+ return NOTIFY_DONE;
+
+ res.addr = mce->addr;
+ if (!skx_decode(&res))
+ return NOTIFY_DONE;
+ mci = res.dev->imc[res.imc].mci;
+
+ if (mce->mcgstatus & MCG_STATUS_MCIP)
+ type = "Exception";
+ else
+ type = "Event";
+
+ skx_mc_printk(mci, KERN_DEBUG, "HANDLING MCE MEMORY ERROR\n");
+
+ skx_mc_printk(mci, KERN_DEBUG, "CPU %d: Machine Check %s: %Lx "
+ "Bank %d: %016Lx\n", mce->extcpu, type,
+ mce->mcgstatus, mce->bank, mce->status);
+ skx_mc_printk(mci, KERN_DEBUG, "TSC %llx ", mce->tsc);
+ skx_mc_printk(mci, KERN_DEBUG, "ADDR %llx ", mce->addr);
+ skx_mc_printk(mci, KERN_DEBUG, "MISC %llx ", mce->misc);
+
+ skx_mc_printk(mci, KERN_DEBUG, "PROCESSOR %u:%x TIME %llu SOCKET "
+ "%u APIC %x\n", mce->cpuvendor, mce->cpuid,
+ mce->time, mce->socketid, mce->apicid);
+
+ skx_mce_output_error(mci, mce, &res);
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block skx_mce_dec = {
+ .notifier_call = skx_mce_check_error,
+};
+
+static void skx_remove(void)
+{
+ int i, j;
+ struct skx_dev *d, *tmp;
+
+ edac_dbg(0, "\n");
+
+ list_for_each_entry_safe(d, tmp, &skx_edac_list, list) {
+ list_del(&d->list);
+ for (i = 0; i < NUM_IMC; i++) {
+ skx_unregister_mci(&d->imc[i]);
+ for (j = 0; j < NUM_CHANNELS; j++)
+ pci_dev_put(d->imc[i].chan[j].cdev);
+ }
+ pci_dev_put(d->util_all);
+ pci_dev_put(d->sad_all);
+
+ kfree(d);
+ }
+}
+
+/*
+ * skx_init:
+ * make sure we are running on the correct cpu model
+ * search for all the devices we need
+ * check which DIMMs are present.
+ */
+int __init skx_init(void)
+{
+ const struct x86_cpu_id *id;
+ const struct munit *m;
+ int rc = 0, i;
+ u8 mc = 0, src_id, node_id;
+ struct skx_dev *d;
+
+ edac_dbg(2, "\n");
+
+ id = x86_match_cpu(skx_cpuids);
+ if (!id)
+ return -ENODEV;
+
+ rc = skx_get_hi_lo();
+ if (rc)
+ return rc;
+
+ rc = get_all_bus_mappings();
+ if (rc < 0)
+ goto fail;
+ if (rc == 0) {
+ edac_dbg(2, "No memory controllers found\n");
+ return -ENODEV;
+ }
+
+ for (m = skx_all_munits; m->did; m++) {
+ rc = get_all_munits(m);
+ if (rc < 0)
+ goto fail;
+ if (rc != m->per_socket * skx_num_sockets) {
+ edac_dbg(2, "Expected %d, got %d of %x\n",
+ m->per_socket * skx_num_sockets, rc, m->did);
+ rc = -ENODEV;
+ goto fail;
+ }
+ }
+
+ list_for_each_entry(d, &skx_edac_list, list) {
+ src_id = get_src_id(d);
+ node_id = skx_get_node_id(d);
+ edac_dbg(2, "src_id=%d node_id=%d\n", src_id, node_id);
+ for (i = 0; i < NUM_IMC; i++) {
+ d->imc[i].mc = mc++;
+ d->imc[i].lmc = i;
+ d->imc[i].src_id = src_id;
+ d->imc[i].node_id = node_id;
+ rc = skx_register_mci(&d->imc[i]);
+ if (rc < 0)
+ goto fail;
+ }
+ }
+
+ /* Ensure that the OPSTATE is set correctly for POLL or NMI */
+ opstate_init();
+
+ setup_skx_debug();
+
+ mce_register_decode_chain(&skx_mce_dec);
+
+ return 0;
+fail:
+ skx_remove();
+ return rc;
+}
+
+static void __exit skx_exit(void)
+{
+ edac_dbg(2, "\n");
+ mce_unregister_decode_chain(&skx_mce_dec);
+ skx_remove();
+ teardown_skx_debug();
+}
+
+module_init(skx_init);
+module_exit(skx_exit);
+
+module_param(edac_op_state, int, 0444);
+MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI");
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Tony Luck");
+MODULE_DESCRIPTION("MC Driver for Intel Skylake server processors");
struct mbox_client *cl = &pchan->cl;
struct device_node *shmem = of_parse_phandle(np, "shmem", idx);
- if (of_address_to_resource(shmem, 0, &res)) {
+ ret = of_address_to_resource(shmem, 0, &res);
+ of_node_put(shmem);
+ if (ret) {
dev_err(dev, "failed to get SCPI payload mem resource\n");
- ret = -EINVAL;
goto err;
}
ret = device_register(dmi_dev);
if (ret)
- goto fail_free_dmi_dev;
+ goto fail_put_dmi_dev;
return 0;
-fail_free_dmi_dev:
- kfree(dmi_dev);
-fail_class_unregister:
+fail_put_dmi_dev:
+ put_device(dmi_dev);
+fail_class_unregister:
class_unregister(&dmi_class);
return ret;
#include <linux/slab.h>
#include <linux/mutex.h>
#include <linux/efi.h>
+#include <linux/vmalloc.h>
#define NO_FURTHER_WRITE_ACTION -1
int ret;
void *cap_hdr_temp;
- cap_hdr_temp = kmap(cap_info->pages[0]);
+ cap_hdr_temp = vmap(cap_info->pages, cap_info->index,
+ VM_MAP, PAGE_KERNEL);
if (!cap_hdr_temp) {
- pr_debug("%s: kmap() failed\n", __func__);
+ pr_debug("%s: vmap() failed\n", __func__);
return -EFAULT;
}
ret = efi_capsule_update(cap_hdr_temp, cap_info->pages);
- kunmap(cap_info->pages[0]);
+ vunmap(cap_hdr_temp);
if (ret) {
pr_err("%s: efi_capsule_update() failed\n", __func__);
return ret;
* map the capsule described by @capsule with its data in @pages and
* send it to the firmware via the UpdateCapsule() runtime service.
*
- * @capsule must be a virtual mapping of the first page in @pages
- * (@pages[0]) in the kernel address space. That is, a
- * capsule_header_t that describes the entire contents of the capsule
+ * @capsule must be a virtual mapping of the complete capsule update in the
+ * kernel address space, as the capsule can be consumed immediately.
+ * A capsule_header_t that describes the entire contents of the capsule
* must be at the start of the first data page.
*
* Even though this function will validate that the firmware supports
}
if (subnode) {
- node = of_get_flat_dt_subnode_by_name(node, subnode);
- if (node < 0)
+ int err = of_get_flat_dt_subnode_by_name(node, subnode);
+
+ if (err < 0)
return 0;
+
+ node = err;
}
return __find_uefi_params(node, info, dt_params[i].params);
#define EFI_ALLOC_ALIGN EFI_PAGE_SIZE
#endif
+#define EFI_MMAP_NR_SLACK_SLOTS 8
+
struct file_info {
efi_file_handle_t *handle;
u64 size;
}
}
+static inline bool mmap_has_headroom(unsigned long buff_size,
+ unsigned long map_size,
+ unsigned long desc_size)
+{
+ unsigned long slack = buff_size - map_size;
+
+ return slack / desc_size >= EFI_MMAP_NR_SLACK_SLOTS;
+}
+
efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg,
- efi_memory_desc_t **map,
- unsigned long *map_size,
- unsigned long *desc_size,
- u32 *desc_ver,
- unsigned long *key_ptr)
+ struct efi_boot_memmap *map)
{
efi_memory_desc_t *m = NULL;
efi_status_t status;
unsigned long key;
u32 desc_version;
- *map_size = sizeof(*m) * 32;
+ *map->desc_size = sizeof(*m);
+ *map->map_size = *map->desc_size * 32;
+ *map->buff_size = *map->map_size;
again:
- /*
- * Add an additional efi_memory_desc_t because we're doing an
- * allocation which may be in a new descriptor region.
- */
- *map_size += sizeof(*m);
status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
- *map_size, (void **)&m);
+ *map->map_size, (void **)&m);
if (status != EFI_SUCCESS)
goto fail;
- *desc_size = 0;
+ *map->desc_size = 0;
key = 0;
- status = efi_call_early(get_memory_map, map_size, m,
- &key, desc_size, &desc_version);
- if (status == EFI_BUFFER_TOO_SMALL) {
+ status = efi_call_early(get_memory_map, map->map_size, m,
+ &key, map->desc_size, &desc_version);
+ if (status == EFI_BUFFER_TOO_SMALL ||
+ !mmap_has_headroom(*map->buff_size, *map->map_size,
+ *map->desc_size)) {
efi_call_early(free_pool, m);
+ /*
+ * Make sure there is some entries of headroom so that the
+ * buffer can be reused for a new map after allocations are
+ * no longer permitted. Its unlikely that the map will grow to
+ * exceed this headroom once we are ready to trigger
+ * ExitBootServices()
+ */
+ *map->map_size += *map->desc_size * EFI_MMAP_NR_SLACK_SLOTS;
+ *map->buff_size = *map->map_size;
goto again;
}
if (status != EFI_SUCCESS)
efi_call_early(free_pool, m);
- if (key_ptr && status == EFI_SUCCESS)
- *key_ptr = key;
- if (desc_ver && status == EFI_SUCCESS)
- *desc_ver = desc_version;
+ if (map->key_ptr && status == EFI_SUCCESS)
+ *map->key_ptr = key;
+ if (map->desc_ver && status == EFI_SUCCESS)
+ *map->desc_ver = desc_version;
fail:
- *map = m;
+ *map->map = m;
return status;
}
unsigned long get_dram_base(efi_system_table_t *sys_table_arg)
{
efi_status_t status;
- unsigned long map_size;
+ unsigned long map_size, buff_size;
unsigned long membase = EFI_ERROR;
struct efi_memory_map map;
efi_memory_desc_t *md;
+ struct efi_boot_memmap boot_map;
- status = efi_get_memory_map(sys_table_arg, (efi_memory_desc_t **)&map.map,
- &map_size, &map.desc_size, NULL, NULL);
+ boot_map.map = (efi_memory_desc_t **)&map.map;
+ boot_map.map_size = &map_size;
+ boot_map.desc_size = &map.desc_size;
+ boot_map.desc_ver = NULL;
+ boot_map.key_ptr = NULL;
+ boot_map.buff_size = &buff_size;
+
+ status = efi_get_memory_map(sys_table_arg, &boot_map);
if (status != EFI_SUCCESS)
return membase;
unsigned long size, unsigned long align,
unsigned long *addr, unsigned long max)
{
- unsigned long map_size, desc_size;
+ unsigned long map_size, desc_size, buff_size;
efi_memory_desc_t *map;
efi_status_t status;
unsigned long nr_pages;
u64 max_addr = 0;
int i;
+ struct efi_boot_memmap boot_map;
+
+ boot_map.map = ↦
+ boot_map.map_size = &map_size;
+ boot_map.desc_size = &desc_size;
+ boot_map.desc_ver = NULL;
+ boot_map.key_ptr = NULL;
+ boot_map.buff_size = &buff_size;
- status = efi_get_memory_map(sys_table_arg, &map, &map_size, &desc_size,
- NULL, NULL);
+ status = efi_get_memory_map(sys_table_arg, &boot_map);
if (status != EFI_SUCCESS)
goto fail;
unsigned long size, unsigned long align,
unsigned long *addr)
{
- unsigned long map_size, desc_size;
+ unsigned long map_size, desc_size, buff_size;
efi_memory_desc_t *map;
efi_status_t status;
unsigned long nr_pages;
int i;
+ struct efi_boot_memmap boot_map;
- status = efi_get_memory_map(sys_table_arg, &map, &map_size, &desc_size,
- NULL, NULL);
+ boot_map.map = ↦
+ boot_map.map_size = &map_size;
+ boot_map.desc_size = &desc_size;
+ boot_map.desc_ver = NULL;
+ boot_map.key_ptr = NULL;
+ boot_map.buff_size = &buff_size;
+
+ status = efi_get_memory_map(sys_table_arg, &boot_map);
if (status != EFI_SUCCESS)
goto fail;
*cmd_line_len = options_bytes;
return (char *)cmdline_addr;
}
+
+/*
+ * Handle calling ExitBootServices according to the requirements set out by the
+ * spec. Obtains the current memory map, and returns that info after calling
+ * ExitBootServices. The client must specify a function to perform any
+ * processing of the memory map data prior to ExitBootServices. A client
+ * specific structure may be passed to the function via priv. The client
+ * function may be called multiple times.
+ */
+efi_status_t efi_exit_boot_services(efi_system_table_t *sys_table_arg,
+ void *handle,
+ struct efi_boot_memmap *map,
+ void *priv,
+ efi_exit_boot_map_processing priv_func)
+{
+ efi_status_t status;
+
+ status = efi_get_memory_map(sys_table_arg, map);
+
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ status = priv_func(sys_table_arg, map, priv);
+ if (status != EFI_SUCCESS)
+ goto free_map;
+
+ status = efi_call_early(exit_boot_services, handle, *map->key_ptr);
+
+ if (status == EFI_INVALID_PARAMETER) {
+ /*
+ * The memory map changed between efi_get_memory_map() and
+ * exit_boot_services(). Per the UEFI Spec v2.6, Section 6.4:
+ * EFI_BOOT_SERVICES.ExitBootServices we need to get the
+ * updated map, and try again. The spec implies one retry
+ * should be sufficent, which is confirmed against the EDK2
+ * implementation. Per the spec, we can only invoke
+ * get_memory_map() and exit_boot_services() - we cannot alloc
+ * so efi_get_memory_map() cannot be used, and we must reuse
+ * the buffer. For all practical purposes, the headroom in the
+ * buffer should account for any changes in the map so the call
+ * to get_memory_map() is expected to succeed here.
+ */
+ *map->map_size = *map->buff_size;
+ status = efi_call_early(get_memory_map,
+ map->map_size,
+ *map->map,
+ map->key_ptr,
+ map->desc_size,
+ map->desc_ver);
+
+ /* exit_boot_services() was called, thus cannot free */
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ status = priv_func(sys_table_arg, map, priv);
+ /* exit_boot_services() was called, thus cannot free */
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ status = efi_call_early(exit_boot_services, handle, *map->key_ptr);
+ }
+
+ /* exit_boot_services() was called, thus cannot free */
+ if (status != EFI_SUCCESS)
+ goto fail;
+
+ return EFI_SUCCESS;
+
+free_map:
+ efi_call_early(free_pool, *map->map);
+fail:
+ return status;
+}
#define EFI_FDT_ALIGN EFI_PAGE_SIZE
#endif
+struct exit_boot_struct {
+ efi_memory_desc_t *runtime_map;
+ int *runtime_entry_count;
+};
+
+static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
+ struct efi_boot_memmap *map,
+ void *priv)
+{
+ struct exit_boot_struct *p = priv;
+ /*
+ * Update the memory map with virtual addresses. The function will also
+ * populate @runtime_map with copies of just the EFI_MEMORY_RUNTIME
+ * entries so that we can pass it straight to SetVirtualAddressMap()
+ */
+ efi_get_virtmap(*map->map, *map->map_size, *map->desc_size,
+ p->runtime_map, p->runtime_entry_count);
+
+ return EFI_SUCCESS;
+}
+
/*
* Allocate memory for a new FDT, then add EFI, commandline, and
* initrd related fields to the FDT. This routine increases the
unsigned long fdt_addr,
unsigned long fdt_size)
{
- unsigned long map_size, desc_size;
+ unsigned long map_size, desc_size, buff_size;
u32 desc_ver;
unsigned long mmap_key;
efi_memory_desc_t *memory_map, *runtime_map;
unsigned long new_fdt_size;
efi_status_t status;
int runtime_entry_count = 0;
+ struct efi_boot_memmap map;
+ struct exit_boot_struct priv;
+
+ map.map = &runtime_map;
+ map.map_size = &map_size;
+ map.desc_size = &desc_size;
+ map.desc_ver = &desc_ver;
+ map.key_ptr = &mmap_key;
+ map.buff_size = &buff_size;
/*
* Get a copy of the current memory map that we will use to prepare
* subsequent allocations adding entries, since they could not affect
* the number of EFI_MEMORY_RUNTIME regions.
*/
- status = efi_get_memory_map(sys_table, &runtime_map, &map_size,
- &desc_size, &desc_ver, &mmap_key);
+ status = efi_get_memory_map(sys_table, &map);
if (status != EFI_SUCCESS) {
pr_efi_err(sys_table, "Unable to retrieve UEFI memory map.\n");
return status;
pr_efi(sys_table,
"Exiting boot services and installing virtual address map...\n");
+ map.map = &memory_map;
/*
* Estimate size of new FDT, and allocate memory for it. We
* will allocate a bigger buffer if this ends up being too
* we can get the memory map key needed for
* exit_boot_services().
*/
- status = efi_get_memory_map(sys_table, &memory_map, &map_size,
- &desc_size, &desc_ver, &mmap_key);
+ status = efi_get_memory_map(sys_table, &map);
if (status != EFI_SUCCESS)
goto fail_free_new_fdt;
}
}
- /*
- * Update the memory map with virtual addresses. The function will also
- * populate @runtime_map with copies of just the EFI_MEMORY_RUNTIME
- * entries so that we can pass it straight into SetVirtualAddressMap()
- */
- efi_get_virtmap(memory_map, map_size, desc_size, runtime_map,
- &runtime_entry_count);
-
- /* Now we are ready to exit_boot_services.*/
- status = sys_table->boottime->exit_boot_services(handle, mmap_key);
+ sys_table->boottime->free_pool(memory_map);
+ priv.runtime_map = runtime_map;
+ priv.runtime_entry_count = &runtime_entry_count;
+ status = efi_exit_boot_services(sys_table, handle, &map, &priv,
+ exit_boot_func);
if (status == EFI_SUCCESS) {
efi_set_virtual_address_map_t *svam;
unsigned long random_seed)
{
unsigned long map_size, desc_size, total_slots = 0, target_slot;
+ unsigned long buff_size;
efi_status_t status;
efi_memory_desc_t *memory_map;
int map_offset;
+ struct efi_boot_memmap map;
- status = efi_get_memory_map(sys_table_arg, &memory_map, &map_size,
- &desc_size, NULL, NULL);
+ map.map = &memory_map;
+ map.map_size = &map_size;
+ map.desc_size = &desc_size;
+ map.desc_ver = NULL;
+ map.key_ptr = NULL;
+ map.buff_size = &buff_size;
+
+ status = efi_get_memory_map(sys_table_arg, &map);
if (status != EFI_SUCCESS)
return status;
config OF_GPIO
def_bool y
depends on OF
+ depends on HAS_IOMEM
config GPIO_ACPI
def_bool y
config GPIO_ETRAXFS
bool "Axis ETRAX FS General I/O"
depends on CRIS || COMPILE_TEST
- depends on OF
+ depends on OF_GPIO
select GPIO_GENERIC
select GPIOLIB_IRQCHIP
help
config GPIO_GRGPIO
tristate "Aeroflex Gaisler GRGPIO support"
- depends on OF
+ depends on OF_GPIO
select GPIO_GENERIC
select IRQ_DOMAIN
help
config GPIO_MVEBU
def_bool y
depends on PLAT_ORION
- depends on OF
+ depends on OF_GPIO
select GENERIC_IRQ_CHIP
config GPIO_MXC
bool "NVIDIA Tegra GPIO support"
default ARCH_TEGRA
depends on ARCH_TEGRA || COMPILE_TEST
- depends on OF
+ depends on OF_GPIO
help
Say yes here to support GPIO pins on NVIDIA Tegra SoCs.
config GPIO_74X164
tristate "74x164 serial-in/parallel-out 8-bits shift register"
- depends on OF
+ depends on OF_GPIO
help
Driver for 74x164 compatible serial-in/parallel-out 8-outputs
shift registers. This driver can be used to provide access
config GPIO_MCP23S08
tristate "Microchip MCP23xxx I/O expander"
+ depends on OF_GPIO
select GPIOLIB_IRQCHIP
help
SPI/I2C driver for Microchip MCP23S08/MCP23S17/MCP23008/MCP23017
ts->chip.parent = dev;
ts->chip.owner = THIS_MODULE;
+ ret = gpiochip_add_data(&ts->chip, ts);
+ if (ret)
+ goto exit_destroy;
+
/*
* initialize pullups according to platform data and cache the
* register values for later use.
}
}
- ret = gpiochip_add_data(&ts->chip, ts);
- if (ret)
- goto exit_destroy;
-
return ret;
exit_destroy:
mcp->chip.direction_output = mcp23s08_direction_output;
mcp->chip.set = mcp23s08_set;
mcp->chip.dbg_show = mcp23s08_dbg_show;
-#ifdef CONFIG_OF
+#ifdef CONFIG_OF_GPIO
mcp->chip.of_gpio_n_cells = 2;
mcp->chip.of_node = dev->of_node;
#endif
{
irq_set_chip_and_handler(irq, &sa1100_gpio_irq_chip,
handle_edge_irq);
- irq_set_noprobe(irq);
+ irq_set_probe(irq);
return 0;
}
#include <linux/errno.h>
#include <linux/module.h>
#include <linux/io.h>
-#include <linux/io-mapping.h>
#include <linux/gpio/consumer.h>
#include <linux/of.h>
#include <linux/of_address.h>
/* custom LRU management */
struct amdgpu_mman_lru log2_size[AMDGPU_TTM_LRU_SIZE];
+ /* guard for log2_size array, don't add anything in between */
+ struct amdgpu_mman_lru guard;
};
int amdgpu_copy_buffer(struct amdgpu_ring *ring,
void amdgpu_gart_table_vram_unpin(struct amdgpu_device *adev);
int amdgpu_gart_init(struct amdgpu_device *adev);
void amdgpu_gart_fini(struct amdgpu_device *adev);
-void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset,
+void amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
int pages);
-int amdgpu_gart_bind(struct amdgpu_device *adev, unsigned offset,
+int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
int pages, struct page **pagelist,
dma_addr_t *dma_addr, uint32_t flags);
(le16_to_cpu(path->usConnObjectId) &
OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT;
+ /* Skip TV/CV support */
+ if ((le16_to_cpu(path->usDeviceTag) ==
+ ATOM_DEVICE_TV1_SUPPORT) ||
+ (le16_to_cpu(path->usDeviceTag) ==
+ ATOM_DEVICE_CV_SUPPORT))
+ continue;
+
+ if (con_obj_id >= ARRAY_SIZE(object_connector_convert)) {
+ DRM_ERROR("invalid con_obj_id %d for device tag 0x%04x\n",
+ con_obj_id, le16_to_cpu(path->usDeviceTag));
+ continue;
+ }
+
connector_type =
object_connector_convert[con_obj_id];
connector_object_id = con_obj_id;
atpx->is_hybrid = false;
if (valid_bits & ATPX_MS_HYBRID_GFX_SUPPORTED) {
printk("ATPX Hybrid Graphics\n");
-#if 1
- /* This is a temporary hack until the D3 cold support
- * makes it upstream. The ATPX power_control method seems
- * to still work on even if the system should be using
- * the new standardized hybrid D3 cold ACPI interface.
- */
- atpx->functions.power_cntl = true;
-#else
atpx->functions.power_cntl = false;
-#endif
atpx->is_hybrid = true;
}
* Unbinds the requested pages from the gart page table and
* replaces them with the dummy page (all asics).
*/
-void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset,
+void amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
int pages)
{
unsigned t;
* (all asics).
* Returns 0 for success, -EINVAL for failure.
*/
-int amdgpu_gart_bind(struct amdgpu_device *adev, unsigned offset,
+int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
int pages, struct page **pagelist, dma_addr_t *dma_addr,
uint32_t flags)
{
int amdgpu_ib_ring_tests(struct amdgpu_device *adev)
{
unsigned i;
- int r;
+ int r, ret = 0;
for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
struct amdgpu_ring *ring = adev->rings[i];
} else {
/* still not good, but we can live with it */
DRM_ERROR("amdgpu: failed testing IB on ring %d (%d).\n", i, r);
+ ret = r;
}
}
}
- return 0;
+ return ret;
}
/*
struct drm_device *ddev = dev_get_drvdata(dev);
struct amdgpu_device *adev = ddev->dev_private;
char *table = NULL;
- int size, i;
+ int size;
if (adev->pp_enabled)
size = amdgpu_dpm_get_pp_table(adev, &table);
if (size >= PAGE_SIZE)
size = PAGE_SIZE - 1;
- for (i = 0; i < size; i++) {
- sprintf(buf + i, "%02x", table[i]);
- }
- sprintf(buf + i, "\n");
+ memcpy(buf, table, size);
return size;
}
adev = amdgpu_get_adev(bo->bdev);
ring = adev->mman.buffer_funcs_ring;
- old_start = old_mem->start << PAGE_SHIFT;
- new_start = new_mem->start << PAGE_SHIFT;
+ old_start = (u64)old_mem->start << PAGE_SHIFT;
+ new_start = (u64)new_mem->start << PAGE_SHIFT;
switch (old_mem->mem_type) {
case TTM_PL_VRAM:
if (unlikely(r)) {
goto out_cleanup;
}
- r = ttm_bo_move_ttm(bo, true, no_wait_gpu, new_mem);
+ r = ttm_bo_move_ttm(bo, true, interruptible, no_wait_gpu, new_mem);
out_cleanup:
ttm_bo_mem_put(bo, &tmp_mem);
return r;
if (unlikely(r)) {
return r;
}
- r = ttm_bo_move_ttm(bo, true, no_wait_gpu, &tmp_mem);
+ r = ttm_bo_move_ttm(bo, true, interruptible, no_wait_gpu, &tmp_mem);
if (unlikely(r)) {
goto out_cleanup;
}
struct list_head *res = lru->lru[tbo->mem.mem_type];
lru->lru[tbo->mem.mem_type] = &tbo->lru;
+ while ((++lru)->lru[tbo->mem.mem_type] == res)
+ lru->lru[tbo->mem.mem_type] = &tbo->lru;
return res;
}
struct list_head *res = lru->swap_lru;
lru->swap_lru = &tbo->swap;
+ while ((++lru)->swap_lru == res)
+ lru->swap_lru = &tbo->swap;
return res;
}
lru->swap_lru = &adev->mman.bdev.glob->swap_lru;
}
+ for (j = 0; j < TTM_NUM_MEM_TYPES; ++j)
+ adev->mman.guard.lru[j] = NULL;
+ adev->mman.guard.swap_lru = NULL;
+
adev->mman.initialized = true;
r = ttm_bo_init_mm(&adev->mman.bdev, TTM_PL_VRAM,
adev->mc.real_vram_size >> PAGE_SHIFT);
r = 0;
}
-error:
fence_put(fence);
+
+error:
return r;
}
r = amd_sched_entity_init(&ring->sched, &vm->entity,
rq, amdgpu_sched_jobs);
if (r)
- return r;
+ goto err;
vm->page_directory_fence = NULL;
error_free_sched_entity:
amd_sched_entity_fini(&ring->sched, &vm->entity);
+err:
+ drm_free_large(vm->page_tables);
+
return r;
}
break;
case CHIP_KAVERI:
case CHIP_KABINI:
+ case CHIP_MULLINS:
default: BUG();
}
static void cik_sdma_set_irq_funcs(struct amdgpu_device *adev);
static void cik_sdma_set_buffer_funcs(struct amdgpu_device *adev);
static void cik_sdma_set_vm_pte_funcs(struct amdgpu_device *adev);
+static int cik_sdma_soft_reset(void *handle);
MODULE_FIRMWARE("radeon/bonaire_sdma.bin");
MODULE_FIRMWARE("radeon/bonaire_sdma1.bin");
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ cik_sdma_soft_reset(handle);
+
return cik_sdma_hw_init(adev);
}
u64 wb_gpu_addr;
u32 *buf;
struct bonaire_mqd *mqd;
-
- gfx_v7_0_cp_compute_enable(adev, true);
+ struct amdgpu_ring *ring;
/* fix up chicken bits */
tmp = RREG32(mmCP_CPF_DEBUG);
/* init the queues. Just two for now. */
for (i = 0; i < adev->gfx.num_compute_rings; i++) {
- struct amdgpu_ring *ring = &adev->gfx.compute_ring[i];
+ ring = &adev->gfx.compute_ring[i];
if (ring->mqd_obj == NULL) {
r = amdgpu_bo_create(adev,
amdgpu_bo_unreserve(ring->mqd_obj);
ring->ready = true;
+ }
+
+ gfx_v7_0_cp_compute_enable(adev, true);
+
+ for (i = 0; i < adev->gfx.num_compute_rings; i++) {
+ ring = &adev->gfx.compute_ring[i];
+
r = amdgpu_ring_test_ring(ring);
if (r)
ring->ready = false;
static const u32 golden_settings_polaris11_a11[] =
{
- mmCB_HW_CONTROL, 0xfffdf3cf, 0x00006208,
+ mmCB_HW_CONTROL, 0x0000f3cf, 0x00007208,
+ mmCB_HW_CONTROL_2, 0x0f000000, 0x0f000000,
mmCB_HW_CONTROL_3, 0x000001ff, 0x00000040,
mmDB_DEBUG2, 0xf00fffff, 0x00000400,
mmPA_SC_ENHANCE, 0xffffffff, 0x20000001,
mmPA_SC_RASTER_CONFIG_1, 0x0000003f, 0x00000000,
mmRLC_CGCG_CGLS_CTRL, 0x00000003, 0x0001003c,
mmRLC_CGCG_CGLS_CTRL_3D, 0xffffffff, 0x0001003c,
- mmSQ_CONFIG, 0x07f80000, 0x07180000,
+ mmSQ_CONFIG, 0x07f80000, 0x01180000,
mmTA_CNTL_AUX, 0x000f000f, 0x000b0000,
mmTCC_CTRL, 0x00100000, 0xf31fff7f,
mmTCP_ADDR_CONFIG, 0x000003ff, 0x000000f3,
static const u32 golden_settings_polaris10_a11[] =
{
mmATC_MISC_CG, 0x000c0fc0, 0x000c0200,
- mmCB_HW_CONTROL, 0xfffdf3cf, 0x00007208,
- mmCB_HW_CONTROL_2, 0, 0x0f000000,
+ mmCB_HW_CONTROL, 0x0001f3cf, 0x00007208,
+ mmCB_HW_CONTROL_2, 0x0f000000, 0x0f000000,
mmCB_HW_CONTROL_3, 0x000001ff, 0x00000040,
mmDB_DEBUG2, 0xf00fffff, 0x00000400,
mmPA_SC_ENHANCE, 0xffffffff, 0x20000001,
mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000,
mmPA_SC_RASTER_CONFIG, 0x3f3fffff, 0x00000002,
mmPA_SC_RASTER_CONFIG_1, 0x0000003f, 0x00000000,
+ mmRLC_CGCG_CGLS_CTRL, 0x00000003, 0x0000003c,
mmSQ_RANDOM_WAVE_PRI, 0x001fffff, 0x000006fd,
mmTA_CNTL_AUX, 0x000f000f, 0x000b0000,
mmTCC_CTRL, 0x00100000, 0xf31fff7f,
mmGB_GPU_ID, 0x0000000f, 0x00000000,
mmPA_SC_ENHANCE, 0xffffffff, 0x00000001,
mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000,
+ mmRLC_CGCG_CGLS_CTRL, 0x00000003, 0x0000003c,
mmSQ_RANDOM_WAVE_PRI, 0x001fffff, 0x000006fd,
mmTA_CNTL_AUX, 0x000f000f, 0x00010000,
+ mmTCC_CTRL, 0x00100000, 0xf31fff7f,
mmTCC_EXE_DISABLE, 0x00000002, 0x00000002,
mmTCP_ADDR_CONFIG, 0x0000000f, 0x000000f3,
mmTCP_CHAN_STEER_LO, 0xffffffff, 0x00001302
break;
case CHIP_KAVERI:
case CHIP_KABINI:
+ case CHIP_MULLINS:
return 0;
default: BUG();
}
mmMC_MEM_POWER_LS, 0xffffffff, 0x00000104
};
+static const u32 golden_settings_stoney_common[] =
+{
+ mmMC_HUB_RDREQ_UVD, MC_HUB_RDREQ_UVD__PRESCALE_MASK, 0x00000004,
+ mmMC_RD_GRP_OTH, MC_RD_GRP_OTH__UVD_MASK, 0x00600000
+};
static void gmc_v8_0_init_golden_registers(struct amdgpu_device *adev)
{
amdgpu_program_register_sequence(adev,
stoney_mgcg_cgcg_init,
(const u32)ARRAY_SIZE(stoney_mgcg_cgcg_init));
+ amdgpu_program_register_sequence(adev,
+ golden_settings_stoney_common,
+ (const u32)ARRAY_SIZE(golden_settings_stoney_common));
break;
default:
break;
DRM_ERROR("amdgpu: IB test timed out\n");
r = -ETIMEDOUT;
goto err1;
- } else if (r) {
+ } else if (r < 0) {
DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
goto err1;
}
sizeof(u32)) + inx;
pr_debug("kfd: get kernel queue doorbell\n"
- " doorbell offset == 0x%08d\n"
+ " doorbell offset == 0x%08X\n"
" kernel address == 0x%08lX\n",
*doorbell_off, (uintptr_t)(kfd->doorbell_kernel_ptr + inx));
spin_lock(&sched->job_list_lock);
s_job = list_first_entry_or_null(&sched->ring_mirror_list,
struct amd_sched_job, node);
- if (s_job)
+ if (s_job && sched->timeout != MAX_SCHEDULE_TIMEOUT)
schedule_delayed_work(&s_job->work_tdr, sched->timeout);
list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
atmel_hlcdc_crtc_finish_page_flip(drm_crtc_to_atmel_hlcdc_crtc(c));
}
-void atmel_hlcdc_crtc_reset(struct drm_crtc *crtc)
+static void atmel_hlcdc_crtc_reset(struct drm_crtc *crtc)
{
struct atmel_hlcdc_crtc_state *state;
u32 *coeff_tab = heo_upscaling_ycoef;
u32 max_memsize;
- if (state->crtc_w < state->src_w)
+ if (state->crtc_h < state->src_h)
coeff_tab = heo_downscaling_ycoef;
for (i = 0; i < ARRAY_SIZE(heo_upscaling_ycoef); i++)
atmel_hlcdc_layer_update_cfg(&plane->layer,
33 + i,
0xffffffff,
coeff_tab[i]);
- factor = ((8 * 256 * state->src_w) - (256 * 4)) /
- state->crtc_w;
+ factor = ((8 * 256 * state->src_h) - (256 * 4)) /
+ state->crtc_h;
factor++;
- max_memsize = ((factor * state->crtc_w) + (256 * 4)) /
+ max_memsize = ((factor * state->crtc_h) + (256 * 4)) /
2048;
- if (max_memsize > state->src_w)
+ if (max_memsize > state->src_h)
factor--;
factor_reg |= (factor << 16) | 0x80000000;
}
goto out;
}
+ /*
+ * cirrus_modeset_init() is initializing/registering the emulated fbdev
+ * and DRM internals can access/test some of the fields in
+ * mode_config->funcs as part of the fbdev registration process.
+ * Make sure dev->mode_config.funcs is properly set to avoid
+ * dereferencing a NULL pointer.
+ * FIXME: mode_config.funcs assignment should probably be done in
+ * cirrus_modeset_init() (that's a common pattern seen in other DRM
+ * drivers).
+ */
+ dev->mode_config.funcs = &cirrus_mode_funcs;
r = cirrus_modeset_init(cdev);
if (r) {
dev_err(&dev->pdev->dev, "Fatal error during modeset init: %d\n", r);
goto out;
}
- dev->mode_config.funcs = (void *)&cirrus_mode_funcs;
-
return 0;
out:
cirrus_driver_unload(dev);
val,
-1,
&replaced);
- state->color_mgmt_changed = replaced;
+ state->color_mgmt_changed |= replaced;
return ret;
} else if (property == config->ctm_property) {
ret = drm_atomic_replace_property_blob_from_id(crtc,
val,
sizeof(struct drm_color_ctm),
&replaced);
- state->color_mgmt_changed = replaced;
+ state->color_mgmt_changed |= replaced;
return ret;
} else if (property == config->gamma_lut_property) {
ret = drm_atomic_replace_property_blob_from_id(crtc,
val,
-1,
&replaced);
- state->color_mgmt_changed = replaced;
+ state->color_mgmt_changed |= replaced;
return ret;
} else if (crtc->funcs->atomic_set_property)
return crtc->funcs->atomic_set_property(crtc, state, property, val);
struct drm_connector *connector;
int ret;
- mutex_lock(&dev->mode_config.mutex);
-
- drm_for_each_connector(connector, dev) {
+ /* FIXME: taking the mode config mutex ends up in a clash with
+ * fbcon/backlight registration */
+ list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
ret = drm_connector_register(connector);
if (ret)
goto err;
}
- mutex_unlock(&dev->mode_config.mutex);
-
return 0;
err:
struct drm_pending_vblank_event *e = NULL;
int ret = -EINVAL;
+ if (!drm_core_check_feature(dev, DRIVER_MODESET))
+ return -EINVAL;
+
if (page_flip->flags & ~DRM_MODE_PAGE_FLIP_FLAGS ||
page_flip->reserved != 0)
return -EINVAL;
#define EDID_QUIRK_FORCE_8BPC (1 << 8)
/* Force 12bpc */
#define EDID_QUIRK_FORCE_12BPC (1 << 9)
+/* Force 6bpc */
+#define EDID_QUIRK_FORCE_6BPC (1 << 10)
struct detailed_mode_closure {
struct drm_connector *connector;
/* Unknown Acer */
{ "ACR", 2423, EDID_QUIRK_FIRST_DETAILED_PREFERRED },
+ /* AEO model 0 reports 8 bpc, but is a 6 bpc panel */
+ { "AEO", 0, EDID_QUIRK_FORCE_6BPC },
+
/* Belinea 10 15 55 */
{ "MAX", 1516, EDID_QUIRK_PREFER_LARGE_60 },
{ "MAX", 0x77e, EDID_QUIRK_PREFER_LARGE_60 },
/* HDMI deep color modes supported? Assign to info, if so */
drm_assign_hdmi_deep_color_info(edid, info, connector);
+ /*
+ * Digital sink with "DFP 1.x compliant TMDS" according to EDID 1.3?
+ *
+ * For such displays, the DFP spec 1.0, section 3.10 "EDID support"
+ * tells us to assume 8 bpc color depth if the EDID doesn't have
+ * extensions which tell otherwise.
+ */
+ if ((info->bpc == 0) && (edid->revision < 4) &&
+ (edid->input & DRM_EDID_DIGITAL_TYPE_DVI)) {
+ info->bpc = 8;
+ DRM_DEBUG("%s: Assigning DFP sink color depth as %d bpc.\n",
+ connector->name, info->bpc);
+ }
+
/* Only defined for 1.4 with digital displays */
if (edid->revision < 4)
return;
drm_add_display_info(edid, &connector->display_info, connector);
+ if (quirks & EDID_QUIRK_FORCE_6BPC)
+ connector->display_info.bpc = 6;
+
if (quirks & EDID_QUIRK_FORCE_8BPC)
connector->display_info.bpc = 8;
/* Sometimes user space wants everything disabled, so don't steal the
* display if there's a master. */
- if (lockless_dereference(dev->master))
+ if (READ_ONCE(dev->master))
return false;
drm_for_each_crtc(crtc, dev) {
return 0;
}
+#if defined(CONFIG_X86) || defined(CONFIG_IA64)
typedef struct drm_mode_fb_cmd232 {
u32 fb_id;
u32 width;
return 0;
}
+#endif
static drm_ioctl_compat_t *drm_compat_ioctls[] = {
[DRM_IOCTL_NR(DRM_IOCTL_VERSION32)] = compat_drm_version,
[DRM_IOCTL_NR(DRM_IOCTL_UPDATE_DRAW32)] = compat_drm_update_draw,
#endif
[DRM_IOCTL_NR(DRM_IOCTL_WAIT_VBLANK32)] = compat_drm_wait_vblank,
+#if defined(CONFIG_X86) || defined(CONFIG_IA64)
[DRM_IOCTL_NR(DRM_IOCTL_MODE_ADDFB232)] = compat_drm_mode_addfb2,
+#endif
};
/**
if (ret < 0)
return ret;
- mutex_lock(&gpu->lock);
-
/*
* TODO
*
if (unlikely(event == ~0U)) {
DRM_ERROR("no free event\n");
ret = -EBUSY;
- goto out_unlock;
+ goto out_pm_put;
}
fence = etnaviv_gpu_fence_alloc(gpu);
if (!fence) {
event_free(gpu, event);
ret = -ENOMEM;
- goto out_unlock;
+ goto out_pm_put;
}
+ mutex_lock(&gpu->lock);
+
gpu->event[event].fence = fence;
submit->fence = fence->seqno;
gpu->active_fence = submit->fence;
hangcheck_timer_reset(gpu);
ret = 0;
-out_unlock:
mutex_unlock(&gpu->lock);
+out_pm_put:
etnaviv_gpu_pm_put(gpu);
return ret;
flags = exynos_gem->flags;
/*
- * without iommu support, not support physically non-continuous memory
- * for framebuffer.
+ * Physically non-contiguous memory type for framebuffer is not
+ * supported without IOMMU.
*/
if (IS_NONCONTIG_BUFFER(flags)) {
- DRM_ERROR("cannot use this gem memory type for fb.\n");
+ DRM_ERROR("Non-contiguous GEM memory is not supported.\n");
return -EINVAL;
}
return 0;
}
-#ifdef CONFIG_PM_SLEEP
-static int fimc_suspend(struct device *dev)
-{
- struct fimc_context *ctx = get_fimc_context(dev);
-
- DRM_DEBUG_KMS("id[%d]\n", ctx->id);
-
- if (pm_runtime_suspended(dev))
- return 0;
-
- return fimc_clk_ctrl(ctx, false);
-}
-
-static int fimc_resume(struct device *dev)
-{
- struct fimc_context *ctx = get_fimc_context(dev);
-
- DRM_DEBUG_KMS("id[%d]\n", ctx->id);
-
- if (!pm_runtime_suspended(dev))
- return fimc_clk_ctrl(ctx, true);
-
- return 0;
-}
-#endif
-
static int fimc_runtime_suspend(struct device *dev)
{
struct fimc_context *ctx = get_fimc_context(dev);
#endif
static const struct dev_pm_ops fimc_pm_ops = {
- SET_SYSTEM_SLEEP_PM_OPS(fimc_suspend, fimc_resume)
+ SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+ pm_runtime_force_resume)
SET_RUNTIME_PM_OPS(fimc_runtime_suspend, fimc_runtime_resume, NULL)
};
return 0;
}
-#ifdef CONFIG_PM_SLEEP
-static int g2d_suspend(struct device *dev)
+#ifdef CONFIG_PM
+static int g2d_runtime_suspend(struct device *dev)
{
struct g2d_data *g2d = dev_get_drvdata(dev);
flush_work(&g2d->runqueue_work);
- return 0;
-}
-
-static int g2d_resume(struct device *dev)
-{
- struct g2d_data *g2d = dev_get_drvdata(dev);
-
- g2d->suspended = false;
- g2d_exec_runqueue(g2d);
-
- return 0;
-}
-#endif
-
-#ifdef CONFIG_PM
-static int g2d_runtime_suspend(struct device *dev)
-{
- struct g2d_data *g2d = dev_get_drvdata(dev);
-
clk_disable_unprepare(g2d->gate_clk);
return 0;
if (ret < 0)
dev_warn(dev, "failed to enable clock.\n");
+ g2d->suspended = false;
+ g2d_exec_runqueue(g2d);
+
return ret;
}
#endif
static const struct dev_pm_ops g2d_pm_ops = {
- SET_SYSTEM_SLEEP_PM_OPS(g2d_suspend, g2d_resume)
+ SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+ pm_runtime_force_resume)
SET_RUNTIME_PM_OPS(g2d_runtime_suspend, g2d_runtime_resume, NULL)
};
return 0;
}
-#ifdef CONFIG_PM_SLEEP
-static int gsc_suspend(struct device *dev)
-{
- struct gsc_context *ctx = get_gsc_context(dev);
-
- DRM_DEBUG_KMS("id[%d]\n", ctx->id);
-
- if (pm_runtime_suspended(dev))
- return 0;
-
- return gsc_clk_ctrl(ctx, false);
-}
-
-static int gsc_resume(struct device *dev)
-{
- struct gsc_context *ctx = get_gsc_context(dev);
-
- DRM_DEBUG_KMS("id[%d]\n", ctx->id);
-
- if (!pm_runtime_suspended(dev))
- return gsc_clk_ctrl(ctx, true);
-
- return 0;
-}
-#endif
-
-#ifdef CONFIG_PM
-static int gsc_runtime_suspend(struct device *dev)
+static int __maybe_unused gsc_runtime_suspend(struct device *dev)
{
struct gsc_context *ctx = get_gsc_context(dev);
return gsc_clk_ctrl(ctx, false);
}
-static int gsc_runtime_resume(struct device *dev)
+static int __maybe_unused gsc_runtime_resume(struct device *dev)
{
struct gsc_context *ctx = get_gsc_context(dev);
return gsc_clk_ctrl(ctx, true);
}
-#endif
static const struct dev_pm_ops gsc_pm_ops = {
- SET_SYSTEM_SLEEP_PM_OPS(gsc_suspend, gsc_resume)
+ SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+ pm_runtime_force_resume)
SET_RUNTIME_PM_OPS(gsc_runtime_suspend, gsc_runtime_resume, NULL)
};
return 0;
}
-
-#ifdef CONFIG_PM_SLEEP
-static int rotator_suspend(struct device *dev)
-{
- struct rot_context *rot = dev_get_drvdata(dev);
-
- if (pm_runtime_suspended(dev))
- return 0;
-
- return rotator_clk_crtl(rot, false);
-}
-
-static int rotator_resume(struct device *dev)
-{
- struct rot_context *rot = dev_get_drvdata(dev);
-
- if (!pm_runtime_suspended(dev))
- return rotator_clk_crtl(rot, true);
-
- return 0;
-}
-#endif
-
static int rotator_runtime_suspend(struct device *dev)
{
struct rot_context *rot = dev_get_drvdata(dev);
#endif
static const struct dev_pm_ops rotator_pm_ops = {
- SET_SYSTEM_SLEEP_PM_OPS(rotator_suspend, rotator_resume)
+ SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+ pm_runtime_force_resume)
SET_RUNTIME_PM_OPS(rotator_runtime_suspend, rotator_runtime_resume,
NULL)
};
intel_runtime_pm_enable(dev_priv);
+ /* Everything is in place, we can now relax! */
+ DRM_INFO("Initialized %s %d.%d.%d %s for %s on minor %d\n",
+ driver.name, driver.major, driver.minor, driver.patchlevel,
+ driver.date, pci_name(pdev), dev_priv->drm.primary->index);
+
intel_runtime_pm_put(dev_priv);
return 0;
struct i915_ctx_hang_stats hang_stats;
- /* Unique identifier for this context, used by the hw for tracking */
unsigned long flags;
#define CONTEXT_NO_ZEROMAP BIT(0)
#define CONTEXT_NO_ERROR_CAPTURE BIT(1)
- unsigned hw_id;
+
+ /* Unique identifier for this context, used by the hw for tracking */
+ unsigned int hw_id;
u32 user_handle;
u32 ggtt_alignment;
enum modeset_restore modeset_restore;
struct mutex modeset_restore_lock;
struct drm_atomic_state *modeset_restore_state;
+ struct drm_modeset_acquire_ctx reset_ctx;
struct list_head vm_list; /* Global list of all address spaces */
struct i915_ggtt ggtt; /* VM representing the global address space */
struct i915_suspend_saved_registers regfile;
struct vlv_s0ix_state vlv_s0ix_state;
+ enum {
+ I915_SKL_SAGV_UNKNOWN = 0,
+ I915_SKL_SAGV_DISABLED,
+ I915_SKL_SAGV_ENABLED,
+ I915_SKL_SAGV_NOT_CONTROLLED
+ } skl_sagv_status;
+
struct {
/*
* Raw watermark latency values:
/* belongs in i915_gem_gtt.h */
static inline void i915_gem_chipset_flush(struct drm_i915_private *dev_priv)
{
+ wmb();
if (INTEL_GEN(dev_priv) < 6)
intel_gtt_chipset_flush();
}
ret = i915_gem_shmem_pread(dev, obj, args, file);
/* pread for non shmem backed objects */
- if (ret == -EFAULT || ret == -ENODEV)
+ if (ret == -EFAULT || ret == -ENODEV) {
+ intel_runtime_pm_get(to_i915(dev));
ret = i915_gem_gtt_pread(dev, obj, args->size,
args->offset, args->data_ptr);
+ intel_runtime_pm_put(to_i915(dev));
+ }
out:
drm_gem_object_unreference(&obj->base);
* textures). Fallback to the shmem path in that case. */
}
- if (ret == -EFAULT) {
+ if (ret == -EFAULT || ret == -ENOSPC) {
if (obj->phys_handle)
ret = i915_gem_phys_pwrite(obj, args, file);
else if (i915_gem_object_has_struct_page(obj))
}
intel_ring_init_seqno(engine, engine->last_submitted_seqno);
+
+ engine->i915->gt.active_engines &= ~intel_engine_flag(engine);
}
void i915_gem_reset(struct drm_device *dev)
for_each_engine(engine, dev_priv)
i915_gem_reset_engine_cleanup(engine);
+ mod_delayed_work(dev_priv->wq, &dev_priv->gt.idle_work, 0);
i915_gem_context_reset(dev);
{
const unsigned other_rings = ~intel_engine_flag(req->engine);
struct i915_vma *vma;
- uint32_t flush_domains = 0;
- bool flush_chipset = false;
int ret;
list_for_each_entry(vma, vmas, exec_list) {
}
if (obj->base.write_domain & I915_GEM_DOMAIN_CPU)
- flush_chipset |= i915_gem_clflush_object(obj, false);
-
- flush_domains |= obj->base.write_domain;
+ i915_gem_clflush_object(obj, false);
}
- if (flush_chipset)
- i915_gem_chipset_flush(req->engine->i915);
-
- if (flush_domains & I915_GEM_DOMAIN_GTT)
- wmb();
+ /* Unconditionally flush any chipset caches (for streaming writes). */
+ i915_gem_chipset_flush(req->engine->i915);
/* Unconditionally invalidate gpu caches and ensure that we do flush
* any residual writes from the previous batch.
has_full_48bit_ppgtt =
IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) >= 9;
- if (intel_vgpu_active(dev_priv))
- has_full_ppgtt = false; /* emulation is too hard */
+ if (intel_vgpu_active(dev_priv)) {
+ /* emulation is too hard */
+ has_full_ppgtt = false;
+ has_full_48bit_ppgtt = false;
+ }
if (!has_aliasing_ppgtt)
return 0;
return 0;
}
- if (INTEL_GEN(dev_priv) >= 8 && i915.enable_execlists)
+ if (INTEL_GEN(dev_priv) >= 8 && i915.enable_execlists && has_full_ppgtt)
return has_full_48bit_ppgtt ? 3 : 2;
else
return has_aliasing_ppgtt ? 1 : 0;
struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt;
ppgtt->base.cleanup(&ppgtt->base);
+ kfree(ppgtt);
}
i915_gem_cleanup_stolen(dev);
#define BALANCE_LEG_MASK(port) (7<<(8+3*(port)))
/* Balance leg disable bits */
#define BALANCE_LEG_DISABLE_SHIFT 23
+#define BALANCE_LEG_DISABLE(port) (1 << (23 + (port)))
/*
* Fence registers
#define GEN6_PCODE_MAILBOX _MMIO(0x138124)
#define GEN6_PCODE_READY (1<<31)
+#define GEN6_PCODE_ERROR_MASK 0xFF
+#define GEN6_PCODE_SUCCESS 0x0
+#define GEN6_PCODE_ILLEGAL_CMD 0x1
+#define GEN6_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE 0x2
+#define GEN6_PCODE_TIMEOUT 0x3
+#define GEN6_PCODE_UNIMPLEMENTED_CMD 0xFF
+#define GEN7_PCODE_TIMEOUT 0x2
+#define GEN7_PCODE_ILLEGAL_DATA 0x3
+#define GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE 0x10
#define GEN6_PCODE_WRITE_RC6VIDS 0x4
#define GEN6_PCODE_READ_RC6VIDS 0x5
#define GEN6_ENCODE_RC6_VID(mv) (((mv) - 245) / 5)
#define HSW_PCODE_DE_WRITE_FREQ_REQ 0x17
#define DISPLAY_IPS_CONTROL 0x19
#define HSW_PCODE_DYNAMIC_DUTY_CYCLE_CONTROL 0x1A
+#define GEN9_PCODE_SAGV_CONTROL 0x21
+#define GEN9_SAGV_DISABLE 0x0
+#define GEN9_SAGV_IS_DISABLED 0x1
+#define GEN9_SAGV_ENABLE 0x3
#define GEN6_PCODE_DATA _MMIO(0x138128)
#define GEN6_PCODE_FREQ_IA_RATIO_SHIFT 8
#define GEN6_PCODE_FREQ_RING_RATIO_SHIFT 16
BUILD_BUG_ON(sizeof(struct vgt_if) != VGT_PVINFO_SIZE);
- if (!IS_HASWELL(dev_priv))
- return;
-
magic = __raw_i915_read64(dev_priv, vgtif_reg(magic));
if (magic != VGT_MAGIC)
return;
if (!IS_SKYLAKE(dev_priv) && !IS_KABYLAKE(dev_priv))
return;
+ i915_audio_component_get_power(dev);
+
/*
* Enable/disable generating the codec wake signal, overriding the
* internal logic to generate the codec wake to controller.
I915_WRITE(HSW_AUD_CHICKENBIT, tmp);
usleep_range(1000, 1500);
}
+
+ i915_audio_component_put_power(dev);
}
/* Get CDCLK in kHz */
!IS_HASWELL(dev_priv))
return 0;
+ i915_audio_component_get_power(dev);
mutex_lock(&dev_priv->av_mutex);
/* 1. get the pipe */
intel_encoder = dev_priv->dig_port_map[port];
unlock:
mutex_unlock(&dev_priv->av_mutex);
+ i915_audio_component_put_power(dev);
return err;
}
* be moved to FW_FAILED.
*/
-#define I915_CSR_KBL "i915/kbl_dmc_ver1.bin"
+#define I915_CSR_KBL "i915/kbl_dmc_ver1_01.bin"
MODULE_FIRMWARE(I915_CSR_KBL);
#define KBL_CSR_VERSION_REQUIRED CSR_VERSION(1, 1)
-#define I915_CSR_SKL "i915/skl_dmc_ver1.bin"
+#define I915_CSR_SKL "i915/skl_dmc_ver1_26.bin"
MODULE_FIRMWARE(I915_CSR_SKL);
-#define SKL_CSR_VERSION_REQUIRED CSR_VERSION(1, 23)
+#define SKL_CSR_VERSION_REQUIRED CSR_VERSION(1, 26)
-#define I915_CSR_BXT "i915/bxt_dmc_ver1.bin"
+#define I915_CSR_BXT "i915/bxt_dmc_ver1_07.bin"
MODULE_FIRMWARE(I915_CSR_BXT);
#define BXT_CSR_VERSION_REQUIRED CSR_VERSION(1, 7)
static const struct ddi_buf_trans skl_u_ddi_translations_dp[] = {
{ 0x0000201B, 0x000000A2, 0x0 },
{ 0x00005012, 0x00000088, 0x0 },
- { 0x80007011, 0x000000CD, 0x0 },
+ { 0x80007011, 0x000000CD, 0x1 },
{ 0x80009010, 0x000000C0, 0x1 },
{ 0x0000201B, 0x0000009D, 0x0 },
{ 0x80005012, 0x000000C0, 0x1 },
static const struct ddi_buf_trans skl_y_ddi_translations_dp[] = {
{ 0x00000018, 0x000000A2, 0x0 },
{ 0x00005012, 0x00000088, 0x0 },
- { 0x80007011, 0x000000CD, 0x0 },
+ { 0x80007011, 0x000000CD, 0x3 },
{ 0x80009010, 0x000000C0, 0x3 },
{ 0x00000018, 0x0000009D, 0x0 },
{ 0x80005012, 0x000000C0, 0x3 },
}
}
+static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port port)
+{
+ int n_hdmi_entries;
+ int hdmi_level;
+ int hdmi_default_entry;
+
+ hdmi_level = dev_priv->vbt.ddi_port_info[port].hdmi_level_shift;
+
+ if (IS_BROXTON(dev_priv))
+ return hdmi_level;
+
+ if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+ skl_get_buf_trans_hdmi(dev_priv, &n_hdmi_entries);
+ hdmi_default_entry = 8;
+ } else if (IS_BROADWELL(dev_priv)) {
+ n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi);
+ hdmi_default_entry = 7;
+ } else if (IS_HASWELL(dev_priv)) {
+ n_hdmi_entries = ARRAY_SIZE(hsw_ddi_translations_hdmi);
+ hdmi_default_entry = 6;
+ } else {
+ WARN(1, "ddi translation table missing\n");
+ n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi);
+ hdmi_default_entry = 7;
+ }
+
+ /* Choose a good default if VBT is badly populated */
+ if (hdmi_level == HDMI_LEVEL_SHIFT_UNKNOWN ||
+ hdmi_level >= n_hdmi_entries)
+ hdmi_level = hdmi_default_entry;
+
+ return hdmi_level;
+}
+
/*
* Starting with Haswell, DDI port buffers must be programmed with correct
* values in advance. The buffer values are different for FDI and DP modes,
{
struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
u32 iboost_bit = 0;
- int i, n_hdmi_entries, n_dp_entries, n_edp_entries, hdmi_default_entry,
+ int i, n_hdmi_entries, n_dp_entries, n_edp_entries,
size;
int hdmi_level;
enum port port;
const struct ddi_buf_trans *ddi_translations;
port = intel_ddi_get_encoder_port(encoder);
- hdmi_level = dev_priv->vbt.ddi_port_info[port].hdmi_level_shift;
+ hdmi_level = intel_ddi_hdmi_level(dev_priv, port);
if (IS_BROXTON(dev_priv)) {
if (encoder->type != INTEL_OUTPUT_HDMI)
skl_get_buf_trans_edp(dev_priv, &n_edp_entries);
ddi_translations_hdmi =
skl_get_buf_trans_hdmi(dev_priv, &n_hdmi_entries);
- hdmi_default_entry = 8;
/* If we're boosting the current, set bit 31 of trans1 */
if (dev_priv->vbt.ddi_port_info[port].hdmi_boost_level ||
dev_priv->vbt.ddi_port_info[port].dp_boost_level)
n_dp_entries = ARRAY_SIZE(bdw_ddi_translations_dp);
n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi);
- hdmi_default_entry = 7;
} else if (IS_HASWELL(dev_priv)) {
ddi_translations_fdi = hsw_ddi_translations_fdi;
ddi_translations_dp = hsw_ddi_translations_dp;
ddi_translations_hdmi = hsw_ddi_translations_hdmi;
n_dp_entries = n_edp_entries = ARRAY_SIZE(hsw_ddi_translations_dp);
n_hdmi_entries = ARRAY_SIZE(hsw_ddi_translations_hdmi);
- hdmi_default_entry = 6;
} else {
WARN(1, "ddi translation table missing\n");
ddi_translations_edp = bdw_ddi_translations_dp;
n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_edp);
n_dp_entries = ARRAY_SIZE(bdw_ddi_translations_dp);
n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi);
- hdmi_default_entry = 7;
}
switch (encoder->type) {
if (encoder->type != INTEL_OUTPUT_HDMI)
return;
- /* Choose a good default if VBT is badly populated */
- if (hdmi_level == HDMI_LEVEL_SHIFT_UNKNOWN ||
- hdmi_level >= n_hdmi_entries)
- hdmi_level = hdmi_default_entry;
-
/* Entry 9 is for HDMI: */
I915_WRITE(DDI_BUF_TRANS_LO(port, i),
ddi_translations_hdmi[hdmi_level].trans1 | iboost_bit);
TRANS_CLK_SEL_DISABLED);
}
-static void skl_ddi_set_iboost(struct drm_i915_private *dev_priv,
- u32 level, enum port port, int type)
+static void _skl_ddi_set_iboost(struct drm_i915_private *dev_priv,
+ enum port port, uint8_t iboost)
{
+ u32 tmp;
+
+ tmp = I915_READ(DISPIO_CR_TX_BMU_CR0);
+ tmp &= ~(BALANCE_LEG_MASK(port) | BALANCE_LEG_DISABLE(port));
+ if (iboost)
+ tmp |= iboost << BALANCE_LEG_SHIFT(port);
+ else
+ tmp |= BALANCE_LEG_DISABLE(port);
+ I915_WRITE(DISPIO_CR_TX_BMU_CR0, tmp);
+}
+
+static void skl_ddi_set_iboost(struct intel_encoder *encoder, u32 level)
+{
+ struct intel_digital_port *intel_dig_port = enc_to_dig_port(&encoder->base);
+ struct drm_i915_private *dev_priv = to_i915(intel_dig_port->base.base.dev);
+ enum port port = intel_dig_port->port;
+ int type = encoder->type;
const struct ddi_buf_trans *ddi_translations;
uint8_t iboost;
uint8_t dp_iboost, hdmi_iboost;
int n_entries;
- u32 reg;
/* VBT may override standard boost values */
dp_iboost = dev_priv->vbt.ddi_port_info[port].dp_boost_level;
return;
}
- reg = I915_READ(DISPIO_CR_TX_BMU_CR0);
- reg &= ~BALANCE_LEG_MASK(port);
- reg &= ~(1 << (BALANCE_LEG_DISABLE_SHIFT + port));
-
- if (iboost)
- reg |= iboost << BALANCE_LEG_SHIFT(port);
- else
- reg |= 1 << (BALANCE_LEG_DISABLE_SHIFT + port);
+ _skl_ddi_set_iboost(dev_priv, port, iboost);
- I915_WRITE(DISPIO_CR_TX_BMU_CR0, reg);
+ if (port == PORT_A && intel_dig_port->max_lanes == 4)
+ _skl_ddi_set_iboost(dev_priv, PORT_E, iboost);
}
static void bxt_ddi_vswing_sequence(struct drm_i915_private *dev_priv,
level = translate_signal_level(signal_levels);
if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
- skl_ddi_set_iboost(dev_priv, level, port, encoder->type);
+ skl_ddi_set_iboost(encoder, level);
else if (IS_BROXTON(dev_priv))
bxt_ddi_vswing_sequence(dev_priv, level, port, encoder->type);
intel_dp_stop_link_train(intel_dp);
} else if (type == INTEL_OUTPUT_HDMI) {
struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
+ int level = intel_ddi_hdmi_level(dev_priv, port);
+
+ if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
+ skl_ddi_set_iboost(intel_encoder, level);
intel_hdmi->set_infoframes(encoder,
crtc->config->has_hdmi_sink,
for_each_crtc(dev, crtc) {
struct intel_plane *plane = to_intel_plane(crtc->primary);
- struct intel_plane_state *plane_state;
-
- drm_modeset_lock_crtc(crtc, &plane->base);
- plane_state = to_intel_plane_state(plane->base.state);
+ struct intel_plane_state *plane_state =
+ to_intel_plane_state(plane->base.state);
if (plane_state->visible)
plane->update_plane(&plane->base,
to_intel_crtc_state(crtc->state),
plane_state);
+ }
+}
+
+static int
+__intel_display_resume(struct drm_device *dev,
+ struct drm_atomic_state *state)
+{
+ struct drm_crtc_state *crtc_state;
+ struct drm_crtc *crtc;
+ int i, ret;
+
+ intel_modeset_setup_hw_state(dev);
+ i915_redisable_vga(dev);
+
+ if (!state)
+ return 0;
- drm_modeset_unlock_crtc(crtc);
+ for_each_crtc_in_state(state, crtc, crtc_state, i) {
+ /*
+ * Force recalculation even if we restore
+ * current state. With fast modeset this may not result
+ * in a modeset when the state is compatible.
+ */
+ crtc_state->mode_changed = true;
}
+
+ /* ignore any reset values/BIOS leftovers in the WM registers */
+ to_intel_atomic_state(state)->skip_intermediate_wm = true;
+
+ ret = drm_atomic_commit(state);
+
+ WARN_ON(ret == -EDEADLK);
+ return ret;
}
void intel_prepare_reset(struct drm_i915_private *dev_priv)
{
+ struct drm_device *dev = &dev_priv->drm;
+ struct drm_modeset_acquire_ctx *ctx = &dev_priv->reset_ctx;
+ struct drm_atomic_state *state;
+ int ret;
+
/* no reset support for gen2 */
if (IS_GEN2(dev_priv))
return;
- /* reset doesn't touch the display */
+ /*
+ * Need mode_config.mutex so that we don't
+ * trample ongoing ->detect() and whatnot.
+ */
+ mutex_lock(&dev->mode_config.mutex);
+ drm_modeset_acquire_init(ctx, 0);
+ while (1) {
+ ret = drm_modeset_lock_all_ctx(dev, ctx);
+ if (ret != -EDEADLK)
+ break;
+
+ drm_modeset_backoff(ctx);
+ }
+
+ /* reset doesn't touch the display, but flips might get nuked anyway, */
if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv))
return;
- drm_modeset_lock_all(&dev_priv->drm);
/*
* Disabling the crtcs gracefully seems nicer. Also the
* g33 docs say we should at least disable all the planes.
*/
- intel_display_suspend(&dev_priv->drm);
+ state = drm_atomic_helper_duplicate_state(dev, ctx);
+ if (IS_ERR(state)) {
+ ret = PTR_ERR(state);
+ state = NULL;
+ DRM_ERROR("Duplicating state failed with %i\n", ret);
+ goto err;
+ }
+
+ ret = drm_atomic_helper_disable_all(dev, ctx);
+ if (ret) {
+ DRM_ERROR("Suspending crtc's failed with %i\n", ret);
+ goto err;
+ }
+
+ dev_priv->modeset_restore_state = state;
+ state->acquire_ctx = ctx;
+ return;
+
+err:
+ drm_atomic_state_free(state);
}
void intel_finish_reset(struct drm_i915_private *dev_priv)
{
+ struct drm_device *dev = &dev_priv->drm;
+ struct drm_modeset_acquire_ctx *ctx = &dev_priv->reset_ctx;
+ struct drm_atomic_state *state = dev_priv->modeset_restore_state;
+ int ret;
+
/*
* Flips in the rings will be nuked by the reset,
* so complete all pending flips so that user space
if (IS_GEN2(dev_priv))
return;
+ dev_priv->modeset_restore_state = NULL;
+
/* reset doesn't touch the display */
if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv)) {
/*
* FIXME: Atomic will make this obsolete since we won't schedule
* CS-based flips (which might get lost in gpu resets) any more.
*/
- intel_update_primary_planes(&dev_priv->drm);
- return;
- }
-
- /*
- * The display has been reset as well,
- * so need a full re-initialization.
- */
- intel_runtime_pm_disable_interrupts(dev_priv);
- intel_runtime_pm_enable_interrupts(dev_priv);
+ intel_update_primary_planes(dev);
+ } else {
+ /*
+ * The display has been reset as well,
+ * so need a full re-initialization.
+ */
+ intel_runtime_pm_disable_interrupts(dev_priv);
+ intel_runtime_pm_enable_interrupts(dev_priv);
- intel_modeset_init_hw(&dev_priv->drm);
+ intel_modeset_init_hw(dev);
- spin_lock_irq(&dev_priv->irq_lock);
- if (dev_priv->display.hpd_irq_setup)
- dev_priv->display.hpd_irq_setup(dev_priv);
- spin_unlock_irq(&dev_priv->irq_lock);
+ spin_lock_irq(&dev_priv->irq_lock);
+ if (dev_priv->display.hpd_irq_setup)
+ dev_priv->display.hpd_irq_setup(dev_priv);
+ spin_unlock_irq(&dev_priv->irq_lock);
- intel_display_resume(&dev_priv->drm);
+ ret = __intel_display_resume(dev, state);
+ if (ret)
+ DRM_ERROR("Restoring old state failed with %i\n", ret);
- intel_hpd_init(dev_priv);
+ intel_hpd_init(dev_priv);
+ }
- drm_modeset_unlock_all(&dev_priv->drm);
+ drm_modeset_drop_locks(ctx);
+ drm_modeset_acquire_fini(ctx);
+ mutex_unlock(&dev->mode_config.mutex);
}
static bool intel_crtc_has_pending_flip(struct drm_crtc *crtc)
static bool skl_cdclk_wait_for_pcu_ready(struct drm_i915_private *dev_priv)
{
- unsigned int i;
-
- for (i = 0; i < 15; i++) {
- if (skl_cdclk_pcu_ready(dev_priv))
- return true;
- udelay(10);
- }
-
- return false;
+ return _wait_for(skl_cdclk_pcu_ready(dev_priv), 3000, 10) == 0;
}
static void skl_set_cdclk(struct drm_i915_private *dev_priv, int cdclk, int vco)
pipe_config->pipe_bpp = connector->base.display_info.bpc*3;
}
- /* Clamp bpp to default limit on screens without EDID 1.4 */
- if (connector->base.display_info.bpc == 0) {
- int type = connector->base.connector_type;
- int clamp_bpp = 24;
-
- /* Fall back to 18 bpp when DP sink capability is unknown. */
- if (type == DRM_MODE_CONNECTOR_DisplayPort ||
- type == DRM_MODE_CONNECTOR_eDP)
- clamp_bpp = 18;
-
- if (bpp > clamp_bpp) {
- DRM_DEBUG_KMS("clamping display bpp (was %d) to default limit of %d\n",
- bpp, clamp_bpp);
- pipe_config->pipe_bpp = clamp_bpp;
- }
+ /* Clamp bpp to 8 on screens without EDID 1.4 */
+ if (connector->base.display_info.bpc == 0 && bpp > 24) {
+ DRM_DEBUG_KMS("clamping display bpp (was %d) to default limit of 24\n",
+ bpp);
+ pipe_config->pipe_bpp = 24;
}
}
intel_state->cdclk_pll_vco != dev_priv->cdclk_pll.vco))
dev_priv->display.modeset_commit_cdclk(state);
+ /*
+ * SKL workaround: bspec recommends we disable the SAGV when we
+ * have more then one pipe enabled
+ */
+ if (IS_SKYLAKE(dev_priv) && !skl_can_enable_sagv(state))
+ skl_disable_sagv(dev_priv);
+
intel_modeset_verify_disabled(dev);
}
intel_modeset_verify_crtc(crtc, old_crtc_state, crtc->state);
}
+ if (IS_SKYLAKE(dev_priv) && intel_state->modeset &&
+ skl_can_enable_sagv(state))
+ skl_enable_sagv(dev_priv);
+
drm_atomic_helper_commit_hw_done(state);
if (intel_state->modeset)
struct drm_atomic_state *state = dev_priv->modeset_restore_state;
struct drm_modeset_acquire_ctx ctx;
int ret;
- bool setup = false;
dev_priv->modeset_restore_state = NULL;
+ if (state)
+ state->acquire_ctx = &ctx;
/*
* This is a cludge because with real atomic modeset mode_config.mutex
mutex_lock(&dev->mode_config.mutex);
drm_modeset_acquire_init(&ctx, 0);
-retry:
- ret = drm_modeset_lock_all_ctx(dev, &ctx);
-
- if (ret == 0 && !setup) {
- setup = true;
-
- intel_modeset_setup_hw_state(dev);
- i915_redisable_vga(dev);
- }
-
- if (ret == 0 && state) {
- struct drm_crtc_state *crtc_state;
- struct drm_crtc *crtc;
- int i;
-
- state->acquire_ctx = &ctx;
-
- /* ignore any reset values/BIOS leftovers in the WM registers */
- to_intel_atomic_state(state)->skip_intermediate_wm = true;
-
- for_each_crtc_in_state(state, crtc, crtc_state, i) {
- /*
- * Force recalculation even if we restore
- * current state. With fast modeset this may not result
- * in a modeset when the state is compatible.
- */
- crtc_state->mode_changed = true;
- }
-
- ret = drm_atomic_commit(state);
- }
+ while (1) {
+ ret = drm_modeset_lock_all_ctx(dev, &ctx);
+ if (ret != -EDEADLK)
+ break;
- if (ret == -EDEADLK) {
drm_modeset_backoff(&ctx);
- goto retry;
}
+ if (!ret)
+ ret = __intel_display_resume(dev, state);
+
drm_modeset_drop_locks(&ctx);
drm_modeset_acquire_fini(&ctx);
mutex_unlock(&dev->mode_config.mutex);
void skl_wm_get_hw_state(struct drm_device *dev);
void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv,
struct skl_ddb_allocation *ddb /* out */);
+bool skl_can_enable_sagv(struct drm_atomic_state *state);
+int skl_enable_sagv(struct drm_i915_private *dev_priv);
+int skl_disable_sagv(struct drm_i915_private *dev_priv);
uint32_t ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config);
bool ilk_disable_lp_wm(struct drm_device *dev);
int sanitize_rc6_option(struct drm_i915_private *dev_priv, int enable_rc6);
return;
}
- drm_encoder_cleanup(&intel_encoder->base);
kfree(intel_dvo);
kfree(intel_connector);
}
if (i915.enable_fbc >= 0)
return !!i915.enable_fbc;
+ if (!HAS_FBC(dev_priv))
+ return 0;
+
if (IS_BROADWELL(dev_priv))
return 1;
return 0;
}
+static bool need_fbc_vtd_wa(struct drm_i915_private *dev_priv)
+{
+#ifdef CONFIG_INTEL_IOMMU
+ /* WaFbcTurnOffFbcWhenHyperVisorIsUsed:skl,bxt */
+ if (intel_iommu_gfx_mapped &&
+ (IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv))) {
+ DRM_INFO("Disabling framebuffer compression (FBC) to prevent screen flicker with VT-d enabled\n");
+ return true;
+ }
+#endif
+
+ return false;
+}
+
/**
* intel_fbc_init - Initialize FBC
* @dev_priv: the i915 device
fbc->active = false;
fbc->work.scheduled = false;
+ if (need_fbc_vtd_wa(dev_priv))
+ mkwrite_device_info(dev_priv)->has_fbc = false;
+
i915.enable_fbc = intel_sanitize_fbc_option(dev_priv);
DRM_DEBUG_KMS("Sanitized enable_fbc value: %d\n", i915.enable_fbc);
struct intel_fbdev *ifbdev = dev_priv->fbdev;
struct fb_info *info;
- if (!ifbdev)
+ if (!ifbdev || !ifbdev->fb)
return;
info = ifbdev->helper.fbdev;
void intel_fbdev_output_poll_changed(struct drm_device *dev)
{
- struct drm_i915_private *dev_priv = to_i915(dev);
- if (dev_priv->fbdev)
- drm_fb_helper_hotplug_event(&dev_priv->fbdev->helper);
+ struct intel_fbdev *ifbdev = to_i915(dev)->fbdev;
+
+ if (ifbdev && ifbdev->fb)
+ drm_fb_helper_hotplug_event(&ifbdev->helper);
}
void intel_fbdev_restore_mode(struct drm_device *dev)
{
- int ret;
- struct drm_i915_private *dev_priv = to_i915(dev);
- struct intel_fbdev *ifbdev = dev_priv->fbdev;
- struct drm_fb_helper *fb_helper;
+ struct intel_fbdev *ifbdev = to_i915(dev)->fbdev;
if (!ifbdev)
return;
intel_fbdev_sync(ifbdev);
+ if (!ifbdev->fb)
+ return;
- fb_helper = &ifbdev->helper;
-
- ret = drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper);
- if (ret) {
+ if (drm_fb_helper_restore_fbdev_mode_unlocked(&ifbdev->helper)) {
DRM_DEBUG("failed to restore crtc mode\n");
} else {
- mutex_lock(&fb_helper->dev->struct_mutex);
+ mutex_lock(&dev->struct_mutex);
intel_fb_obj_invalidate(ifbdev->fb->obj, ORIGIN_GTT);
- mutex_unlock(&fb_helper->dev->struct_mutex);
+ mutex_unlock(&dev->struct_mutex);
}
}
return err;
}
+static int intel_use_opregion_panel_type_callback(const struct dmi_system_id *id)
+{
+ DRM_INFO("Using panel type from OpRegion on %s\n", id->ident);
+ return 1;
+}
+
+static const struct dmi_system_id intel_use_opregion_panel_type[] = {
+ {
+ .callback = intel_use_opregion_panel_type_callback,
+ .ident = "Conrac GmbH IX45GM2",
+ .matches = {DMI_MATCH(DMI_SYS_VENDOR, "Conrac GmbH"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "IX45GM2"),
+ },
+ },
+ { }
+};
+
int
intel_opregion_get_panel_type(struct drm_i915_private *dev_priv)
{
return -ENODEV;
}
+ /*
+ * So far we know that some machined must use it, others must not use it.
+ * There doesn't seem to be any way to determine which way to go, except
+ * via a quirk list :(
+ */
+ if (!dmi_check_system(intel_use_opregion_panel_type)) {
+ DRM_DEBUG_KMS("Ignoring OpRegion panel type (%d)\n", ret - 1);
+ return -ENODEV;
+ }
+
/*
* FIXME On Dell XPS 13 9350 the OpRegion panel type (0) gives us
* low vswing for eDP, whereas the VBT panel type (2) gives us normal
#define SKL_DDB_SIZE 896 /* in blocks */
#define BXT_DDB_SIZE 512
+#define SKL_SAGV_BLOCK_TIME 30 /* µs */
/*
* Return the index of a plane in the SKL DDB and wm result arrays. Primary
}
}
+/*
+ * SAGV dynamically adjusts the system agent voltage and clock frequencies
+ * depending on power and performance requirements. The display engine access
+ * to system memory is blocked during the adjustment time. Because of the
+ * blocking time, having this enabled can cause full system hangs and/or pipe
+ * underruns if we don't meet all of the following requirements:
+ *
+ * - <= 1 pipe enabled
+ * - All planes can enable watermarks for latencies >= SAGV engine block time
+ * - We're not using an interlaced display configuration
+ */
+int
+skl_enable_sagv(struct drm_i915_private *dev_priv)
+{
+ int ret;
+
+ if (dev_priv->skl_sagv_status == I915_SKL_SAGV_NOT_CONTROLLED ||
+ dev_priv->skl_sagv_status == I915_SKL_SAGV_ENABLED)
+ return 0;
+
+ DRM_DEBUG_KMS("Enabling the SAGV\n");
+ mutex_lock(&dev_priv->rps.hw_lock);
+
+ ret = sandybridge_pcode_write(dev_priv, GEN9_PCODE_SAGV_CONTROL,
+ GEN9_SAGV_ENABLE);
+
+ /* We don't need to wait for the SAGV when enabling */
+ mutex_unlock(&dev_priv->rps.hw_lock);
+
+ /*
+ * Some skl systems, pre-release machines in particular,
+ * don't actually have an SAGV.
+ */
+ if (ret == -ENXIO) {
+ DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n");
+ dev_priv->skl_sagv_status = I915_SKL_SAGV_NOT_CONTROLLED;
+ return 0;
+ } else if (ret < 0) {
+ DRM_ERROR("Failed to enable the SAGV\n");
+ return ret;
+ }
+
+ dev_priv->skl_sagv_status = I915_SKL_SAGV_ENABLED;
+ return 0;
+}
+
+static int
+skl_do_sagv_disable(struct drm_i915_private *dev_priv)
+{
+ int ret;
+ uint32_t temp = GEN9_SAGV_DISABLE;
+
+ ret = sandybridge_pcode_read(dev_priv, GEN9_PCODE_SAGV_CONTROL,
+ &temp);
+ if (ret)
+ return ret;
+ else
+ return temp & GEN9_SAGV_IS_DISABLED;
+}
+
+int
+skl_disable_sagv(struct drm_i915_private *dev_priv)
+{
+ int ret, result;
+
+ if (dev_priv->skl_sagv_status == I915_SKL_SAGV_NOT_CONTROLLED ||
+ dev_priv->skl_sagv_status == I915_SKL_SAGV_DISABLED)
+ return 0;
+
+ DRM_DEBUG_KMS("Disabling the SAGV\n");
+ mutex_lock(&dev_priv->rps.hw_lock);
+
+ /* bspec says to keep retrying for at least 1 ms */
+ ret = wait_for(result = skl_do_sagv_disable(dev_priv), 1);
+ mutex_unlock(&dev_priv->rps.hw_lock);
+
+ if (ret == -ETIMEDOUT) {
+ DRM_ERROR("Request to disable SAGV timed out\n");
+ return -ETIMEDOUT;
+ }
+
+ /*
+ * Some skl systems, pre-release machines in particular,
+ * don't actually have an SAGV.
+ */
+ if (result == -ENXIO) {
+ DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n");
+ dev_priv->skl_sagv_status = I915_SKL_SAGV_NOT_CONTROLLED;
+ return 0;
+ } else if (result < 0) {
+ DRM_ERROR("Failed to disable the SAGV\n");
+ return result;
+ }
+
+ dev_priv->skl_sagv_status = I915_SKL_SAGV_DISABLED;
+ return 0;
+}
+
+bool skl_can_enable_sagv(struct drm_atomic_state *state)
+{
+ struct drm_device *dev = state->dev;
+ struct drm_i915_private *dev_priv = to_i915(dev);
+ struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
+ struct drm_crtc *crtc;
+ enum pipe pipe;
+ int level, plane;
+
+ /*
+ * SKL workaround: bspec recommends we disable the SAGV when we have
+ * more then one pipe enabled
+ *
+ * If there are no active CRTCs, no additional checks need be performed
+ */
+ if (hweight32(intel_state->active_crtcs) == 0)
+ return true;
+ else if (hweight32(intel_state->active_crtcs) > 1)
+ return false;
+
+ /* Since we're now guaranteed to only have one active CRTC... */
+ pipe = ffs(intel_state->active_crtcs) - 1;
+ crtc = dev_priv->pipe_to_crtc_mapping[pipe];
+
+ if (crtc->state->mode.flags & DRM_MODE_FLAG_INTERLACE)
+ return false;
+
+ for_each_plane(dev_priv, pipe, plane) {
+ /* Skip this plane if it's not enabled */
+ if (intel_state->wm_results.plane[pipe][plane][0] == 0)
+ continue;
+
+ /* Find the highest enabled wm level for this plane */
+ for (level = ilk_wm_max_level(dev);
+ intel_state->wm_results.plane[pipe][plane][level] == 0; --level)
+ { }
+
+ /*
+ * If any of the planes on this pipe don't enable wm levels
+ * that incur memory latencies higher then 30µs we can't enable
+ * the SAGV
+ */
+ if (dev_priv->wm.skl_latency[level] < SKL_SAGV_BLOCK_TIME)
+ return false;
+ }
+
+ return true;
+}
+
static void
skl_ddb_get_pipe_allocation_limits(struct drm_device *dev,
const struct intel_crtc_state *cstate,
total_data_rate += intel_cstate->wm.skl.plane_y_data_rate[id];
}
- WARN_ON(cstate->plane_mask && total_data_rate == 0);
-
return total_data_rate;
}
plane_bytes_per_line *= 4;
plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512);
plane_blocks_per_line /= 4;
+ } else if (tiling == DRM_FORMAT_MOD_NONE) {
+ plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512) + 1;
} else {
plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512);
}
* pretend that all pipes switched active status so that we'll
* ensure a full DDB recompute.
*/
- if (dev_priv->wm.distrust_bios_wm)
+ if (dev_priv->wm.distrust_bios_wm) {
+ ret = drm_modeset_lock(&dev->mode_config.connection_mutex,
+ state->acquire_ctx);
+ if (ret)
+ return ret;
+
intel_state->active_pipe_changes = ~0;
+ /*
+ * We usually only initialize intel_state->active_crtcs if we
+ * we're doing a modeset; make sure this field is always
+ * initialized during the sanitization process that happens
+ * on the first commit too.
+ */
+ if (!intel_state->modeset)
+ intel_state->active_crtcs = dev_priv->active_crtcs;
+ }
+
/*
* If the modeset changes which CRTC's are active, we need to
* recompute the DDB allocation for *all* active pipes, even
ret = skl_allocate_pipe_ddb(cstate, ddb);
if (ret)
return ret;
+
+ ret = drm_atomic_add_affected_planes(state, &intel_crtc->base);
+ if (ret)
+ return ret;
}
return 0;
}
+static void
+skl_copy_wm_for_pipe(struct skl_wm_values *dst,
+ struct skl_wm_values *src,
+ enum pipe pipe)
+{
+ dst->wm_linetime[pipe] = src->wm_linetime[pipe];
+ memcpy(dst->plane[pipe], src->plane[pipe],
+ sizeof(dst->plane[pipe]));
+ memcpy(dst->plane_trans[pipe], src->plane_trans[pipe],
+ sizeof(dst->plane_trans[pipe]));
+
+ dst->ddb.pipe[pipe] = src->ddb.pipe[pipe];
+ memcpy(dst->ddb.y_plane[pipe], src->ddb.y_plane[pipe],
+ sizeof(dst->ddb.y_plane[pipe]));
+ memcpy(dst->ddb.plane[pipe], src->ddb.plane[pipe],
+ sizeof(dst->ddb.plane[pipe]));
+}
+
static int
skl_compute_wm(struct drm_atomic_state *state)
{
struct drm_device *dev = crtc->dev;
struct drm_i915_private *dev_priv = to_i915(dev);
struct skl_wm_values *results = &dev_priv->wm.skl_results;
+ struct skl_wm_values *hw_vals = &dev_priv->wm.skl_hw;
struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state);
struct skl_pipe_wm *pipe_wm = &cstate->wm.skl.optimal;
+ int pipe;
if ((results->dirty_pipes & drm_crtc_mask(crtc)) == 0)
return;
skl_write_wm_values(dev_priv, results);
skl_flush_wm_values(dev_priv, results);
- /* store the new configuration */
- dev_priv->wm.skl_hw = *results;
+ /*
+ * Store the new configuration (but only for the pipes that have
+ * changed; the other values weren't recomputed).
+ */
+ for_each_pipe_masked(dev_priv, pipe, results->dirty_pipes)
+ skl_copy_wm_for_pipe(hw_vals, results, pipe);
mutex_unlock(&dev_priv->wm.wm_mutex);
}
else
gen6_set_rps(dev_priv, dev_priv->rps.idle_freq);
dev_priv->rps.last_adj = 0;
- I915_WRITE(GEN6_PMINTRMSK, 0xffffffff);
+ I915_WRITE(GEN6_PMINTRMSK,
+ gen6_sanitize_rps_pm_mask(dev_priv, ~0));
}
mutex_unlock(&dev_priv->rps.hw_lock);
void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv)
{
- if (IS_CHERRYVIEW(dev_priv))
- return;
- else if (IS_VALLEYVIEW(dev_priv))
+ if (IS_VALLEYVIEW(dev_priv))
valleyview_cleanup_gt_powersave(dev_priv);
if (!i915.enable_rc6)
}
}
+static inline int gen6_check_mailbox_status(struct drm_i915_private *dev_priv)
+{
+ uint32_t flags =
+ I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_ERROR_MASK;
+
+ switch (flags) {
+ case GEN6_PCODE_SUCCESS:
+ return 0;
+ case GEN6_PCODE_UNIMPLEMENTED_CMD:
+ case GEN6_PCODE_ILLEGAL_CMD:
+ return -ENXIO;
+ case GEN6_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE:
+ case GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE:
+ return -EOVERFLOW;
+ case GEN6_PCODE_TIMEOUT:
+ return -ETIMEDOUT;
+ default:
+ MISSING_CASE(flags)
+ return 0;
+ }
+}
+
+static inline int gen7_check_mailbox_status(struct drm_i915_private *dev_priv)
+{
+ uint32_t flags =
+ I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_ERROR_MASK;
+
+ switch (flags) {
+ case GEN6_PCODE_SUCCESS:
+ return 0;
+ case GEN6_PCODE_ILLEGAL_CMD:
+ return -ENXIO;
+ case GEN7_PCODE_TIMEOUT:
+ return -ETIMEDOUT;
+ case GEN7_PCODE_ILLEGAL_DATA:
+ return -EINVAL;
+ case GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE:
+ return -EOVERFLOW;
+ default:
+ MISSING_CASE(flags);
+ return 0;
+ }
+}
+
int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val)
{
+ int status;
+
WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
/* GEN6_PCODE_* are outside of the forcewake domain, we can
*val = I915_READ_FW(GEN6_PCODE_DATA);
I915_WRITE_FW(GEN6_PCODE_DATA, 0);
+ if (INTEL_GEN(dev_priv) > 6)
+ status = gen7_check_mailbox_status(dev_priv);
+ else
+ status = gen6_check_mailbox_status(dev_priv);
+
+ if (status) {
+ DRM_DEBUG_DRIVER("warning: pcode (read) mailbox access failed: %d\n",
+ status);
+ return status;
+ }
+
return 0;
}
int sandybridge_pcode_write(struct drm_i915_private *dev_priv,
- u32 mbox, u32 val)
+ u32 mbox, u32 val)
{
+ int status;
+
WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock));
/* GEN6_PCODE_* are outside of the forcewake domain, we can
I915_WRITE_FW(GEN6_PCODE_DATA, 0);
+ if (INTEL_GEN(dev_priv) > 6)
+ status = gen7_check_mailbox_status(dev_priv);
+ else
+ status = gen6_check_mailbox_status(dev_priv);
+
+ if (status) {
+ DRM_DEBUG_DRIVER("warning: pcode (write) mailbox access failed: %d\n",
+ status);
+ return status;
+ }
+
return 0;
}
struct drm_i915_private *dev_priv = to_i915(dev);
uint32_t max_sleep_time = 0x1f;
- /* Lately it was identified that depending on panel idle frame count
- * calculated at HW can be off by 1. So let's use what came
- * from VBT + 1.
- * There are also other cases where panel demands at least 4
- * but VBT is not being set. To cover these 2 cases lets use
- * at least 5 when VBT isn't set to be on the safest side.
+ /*
+ * Let's respect VBT in case VBT asks a higher idle_frame value.
+ * Let's use 6 as the minimum to cover all known cases including
+ * the off-by-one issue that HW has in some cases. Also there are
+ * cases where sink should be able to train
+ * with the 5 or 6 idle patterns.
*/
- uint32_t idle_frames = dev_priv->vbt.psr.idle_frames + 1;
+ uint32_t idle_frames = max(6, dev_priv->vbt.psr.idle_frames);
uint32_t val = EDP_PSR_ENABLE;
val |= max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT;
I915_WRITE(GEN8_L3SQCREG1, L3_GENERAL_PRIO_CREDITS(62) |
L3_HIGH_PRIO_CREDITS(2));
- /* WaInsertDummyPushConstPs:bxt */
- if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_B0))
+ /* WaToEnableHwFixForPushConstHWBug:bxt */
+ if (IS_BXT_REVID(dev_priv, BXT_REVID_C0, REVID_FOREVER))
WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) |
GEN8_LQSC_RO_PERF_DIS);
- /* WaInsertDummyPushConstPs:kbl */
- if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0))
+ /* WaToEnableHwFixForPushConstHWBug:kbl */
+ if (IS_KBL_REVID(dev_priv, KBL_REVID_C0, REVID_FOREVER))
WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION);
drm_fbdev_cma_hotplug_event(imxdrm->fbhelper);
}
+static int imx_drm_atomic_check(struct drm_device *dev,
+ struct drm_atomic_state *state)
+{
+ int ret;
+
+ ret = drm_atomic_helper_check_modeset(dev, state);
+ if (ret)
+ return ret;
+
+ ret = drm_atomic_helper_check_planes(dev, state);
+ if (ret)
+ return ret;
+
+ /*
+ * Check modeset again in case crtc_state->mode_changed is
+ * updated in plane's ->atomic_check callback.
+ */
+ ret = drm_atomic_helper_check_modeset(dev, state);
+ if (ret)
+ return ret;
+
+ return ret;
+}
+
static const struct drm_mode_config_funcs imx_drm_mode_config_funcs = {
.fb_create = drm_fb_cma_create,
.output_poll_changed = imx_drm_output_poll_changed,
- .atomic_check = drm_atomic_helper_check,
+ .atomic_check = imx_drm_atomic_check,
.atomic_commit = drm_atomic_helper_commit,
};
crtc->state->event = NULL;
}
spin_unlock_irq(&crtc->dev->event_lock);
+
+ drm_crtc_vblank_off(crtc);
}
static void imx_drm_crtc_reset(struct drm_crtc *crtc)
static void ipu_crtc_atomic_begin(struct drm_crtc *crtc,
struct drm_crtc_state *old_crtc_state)
{
+ drm_crtc_vblank_on(crtc);
+
spin_lock_irq(&crtc->dev->event_lock);
if (crtc->state->event) {
WARN_ON(drm_crtc_vblank_get(crtc));
return -EINVAL;
/*
- * since we cannot touch active IDMAC channels, we do not support
- * resizing the enabled plane or changing its format
+ * We support resizing active plane or changing its format by
+ * forcing CRTC mode change and disabling-enabling plane in plane's
+ * ->atomic_update callback.
*/
if (old_fb && (state->src_w != old_state->src_w ||
state->src_h != old_state->src_h ||
fb->pixel_format != old_fb->pixel_format))
- return -EINVAL;
+ crtc_state->mode_changed = true;
eba = drm_plane_state_to_eba(state);
return -EINVAL;
if (old_fb && fb->pitches[0] != old_fb->pitches[0])
- return -EINVAL;
+ crtc_state->mode_changed = true;
switch (fb->pixel_format) {
case DRM_FORMAT_YUV420:
return -EINVAL;
if (old_fb && old_fb->pitches[1] != fb->pitches[1])
- return -EINVAL;
+ crtc_state->mode_changed = true;
}
return 0;
enum ipu_color_space ics;
if (old_state->fb) {
- ipu_plane_atomic_set_base(ipu_plane, old_state);
- return;
+ struct drm_crtc_state *crtc_state = state->crtc->state;
+
+ if (!crtc_state->mode_changed) {
+ ipu_plane_atomic_set_base(ipu_plane, old_state);
+ return;
+ }
+
+ ipu_disable_plane(plane);
}
switch (ipu_plane->dp_flow) {
tristate "DRM Support for Mediatek SoCs"
depends on DRM
depends on ARCH_MEDIATEK || (ARM && COMPILE_TEST)
+ depends on COMMON_CLK
+ depends on HAVE_ARM_SMCCC
+ depends on OF
select DRM_GEM_CMA_HELPER
select DRM_KMS_HELPER
select DRM_MIPI_DSI
struct shrinker shrinker;
struct msm_vblank_ctrl vblank_ctrl;
+
+ /* task holding struct_mutex.. currently only used in submit path
+ * to detect and reject faults from copy_from_user() for submit
+ * ioctl.
+ */
+ struct task_struct *struct_mutex_task;
};
struct msm_format {
{
struct drm_gem_object *obj = vma->vm_private_data;
struct drm_device *dev = obj->dev;
+ struct msm_drm_private *priv = dev->dev_private;
struct page **pages;
unsigned long pfn;
pgoff_t pgoff;
int ret;
+ /* This should only happen if userspace tries to pass a mmap'd
+ * but unfaulted gem bo vaddr into submit ioctl, triggering
+ * a page fault while struct_mutex is already held. This is
+ * not a valid use-case so just bail.
+ */
+ if (priv->struct_mutex_task == current)
+ return VM_FAULT_SIGBUS;
+
/* Make sure we don't parallel update on a fault, nor move or remove
* something from beneath our feet
*/
kfree(submit);
}
+static inline unsigned long __must_check
+copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
+{
+ if (access_ok(VERIFY_READ, from, n))
+ return __copy_from_user_inatomic(to, from, n);
+ return -EFAULT;
+}
+
static int submit_lookup_objects(struct msm_gem_submit *submit,
struct drm_msm_gem_submit *args, struct drm_file *file)
{
int ret = 0;
spin_lock(&file->table_lock);
+ pagefault_disable();
for (i = 0; i < args->nr_bos; i++) {
struct drm_msm_gem_submit_bo submit_bo;
*/
submit->bos[i].flags = 0;
- ret = copy_from_user(&submit_bo, userptr, sizeof(submit_bo));
- if (ret) {
- ret = -EFAULT;
- goto out_unlock;
+ ret = copy_from_user_inatomic(&submit_bo, userptr, sizeof(submit_bo));
+ if (unlikely(ret)) {
+ pagefault_enable();
+ spin_unlock(&file->table_lock);
+ ret = copy_from_user(&submit_bo, userptr, sizeof(submit_bo));
+ if (ret)
+ goto out;
+ spin_lock(&file->table_lock);
+ pagefault_disable();
}
if (submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) {
}
out_unlock:
- submit->nr_bos = i;
+ pagefault_enable();
spin_unlock(&file->table_lock);
+out:
+ submit->nr_bos = i;
+
return ret;
}
if (ret)
return ret;
+ priv->struct_mutex_task = current;
+
submit = submit_create(dev, gpu, args->nr_bos, args->nr_cmds);
if (!submit) {
ret = -ENOMEM;
if (ret)
msm_gem_submit_free(submit);
out_unlock:
+ priv->struct_mutex_task = NULL;
mutex_unlock(&dev->struct_mutex);
return ret;
}
if (!parent_pdev)
return false;
+ if (!parent_pdev->bridge_d3) {
+ /*
+ * Parent PCI bridge is currently not power managed.
+ * Since userspace can change these afterwards to be on
+ * the safe side we stick with _DSM and prevent usage of
+ * _PR3 from the bridge.
+ */
+ pci_d3cold_disable(pdev);
+ return false;
+ }
+
parent_adev = ACPI_COMPANION(&parent_pdev->dev);
if (!parent_adev)
return false;
if (ret)
goto out;
- ret = ttm_bo_move_ttm(bo, true, no_wait_gpu, new_mem);
+ ret = ttm_bo_move_ttm(bo, true, intr, no_wait_gpu, new_mem);
out:
ttm_bo_mem_put(bo, &tmp_mem);
return ret;
if (ret)
return ret;
- ret = ttm_bo_move_ttm(bo, true, no_wait_gpu, &tmp_mem);
+ ret = ttm_bo_move_ttm(bo, true, intr, no_wait_gpu, &tmp_mem);
if (ret)
goto out;
}
}
+#ifdef CONFIG_DRM_FBDEV_EMULATION
static struct fb_deferred_io qxl_defio = {
.delay = QXL_DIRTY_DELAY,
.deferred_io = drm_fb_helper_deferred_io,
};
+#endif
static struct fb_ops qxlfb_ops = {
.owner = THIS_MODULE,
goto out_destroy_fbi;
}
+#ifdef CONFIG_DRM_FBDEV_EMULATION
info->fbdefio = &qxl_defio;
fb_deferred_io_init(info);
+#endif
qdev->fbdev_info = info;
qdev->fbdev_qfb = &qfbdev->qfb;
if (radeon_crtc->ss.refdiv) {
radeon_crtc->pll_flags |= RADEON_PLL_USE_REF_DIV;
radeon_crtc->pll_reference_div = radeon_crtc->ss.refdiv;
- if (rdev->family >= CHIP_RV770)
+ if (ASIC_IS_AVIVO(rdev) &&
+ rdev->family != CHIP_RS780 &&
+ rdev->family != CHIP_RS880)
radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV;
}
}
atpx->is_hybrid = false;
if (valid_bits & ATPX_MS_HYBRID_GFX_SUPPORTED) {
printk("ATPX Hybrid Graphics\n");
-#if 1
- /* This is a temporary hack until the D3 cold support
- * makes it upstream. The ATPX power_control method seems
- * to still work on even if the system should be using
- * the new standardized hybrid D3 cold ACPI interface.
- */
- atpx->functions.power_cntl = true;
-#else
atpx->functions.power_cntl = false;
-#endif
atpx->is_hybrid = true;
}
rdev = radeon_get_rdev(bo->bdev);
ridx = radeon_copy_ring_index(rdev);
- old_start = old_mem->start << PAGE_SHIFT;
- new_start = new_mem->start << PAGE_SHIFT;
+ old_start = (u64)old_mem->start << PAGE_SHIFT;
+ new_start = (u64)new_mem->start << PAGE_SHIFT;
switch (old_mem->mem_type) {
case TTM_PL_VRAM:
if (unlikely(r)) {
goto out_cleanup;
}
- r = ttm_bo_move_ttm(bo, true, no_wait_gpu, new_mem);
+ r = ttm_bo_move_ttm(bo, true, interruptible, no_wait_gpu, new_mem);
out_cleanup:
ttm_bo_mem_put(bo, &tmp_mem);
return r;
if (unlikely(r)) {
return r;
}
- r = ttm_bo_move_ttm(bo, true, no_wait_gpu, &tmp_mem);
+ r = ttm_bo_move_ttm(bo, true, interruptible, no_wait_gpu, &tmp_mem);
if (unlikely(r)) {
goto out_cleanup;
}
/* Link drm_bridge to encoder */
bridge->encoder = encoder;
+ encoder->bridge = bridge;
ret = drm_bridge_attach(rcdu->ddev, bridge);
if (ret) {
.destroy = tegra_output_encoder_destroy,
};
+static void tegra_dsi_unprepare(struct tegra_dsi *dsi)
+{
+ int err;
+
+ if (dsi->slave)
+ tegra_dsi_unprepare(dsi->slave);
+
+ err = tegra_mipi_disable(dsi->mipi);
+ if (err < 0)
+ dev_err(dsi->dev, "failed to disable MIPI calibration: %d\n",
+ err);
+
+ pm_runtime_put(dsi->dev);
+}
+
static void tegra_dsi_encoder_disable(struct drm_encoder *encoder)
{
struct tegra_output *output = encoder_to_output(encoder);
tegra_dsi_disable(dsi);
- pm_runtime_put(dsi->dev);
+ tegra_dsi_unprepare(dsi);
+}
+
+static void tegra_dsi_prepare(struct tegra_dsi *dsi)
+{
+ int err;
+
+ pm_runtime_get_sync(dsi->dev);
+
+ err = tegra_mipi_enable(dsi->mipi);
+ if (err < 0)
+ dev_err(dsi->dev, "failed to enable MIPI calibration: %d\n",
+ err);
+
+ err = tegra_dsi_pad_calibrate(dsi);
+ if (err < 0)
+ dev_err(dsi->dev, "MIPI calibration failed: %d\n", err);
+
+ if (dsi->slave)
+ tegra_dsi_prepare(dsi->slave);
}
static void tegra_dsi_encoder_enable(struct drm_encoder *encoder)
struct tegra_dsi *dsi = to_dsi(output);
struct tegra_dsi_state *state;
u32 value;
- int err;
-
- pm_runtime_get_sync(dsi->dev);
- err = tegra_dsi_pad_calibrate(dsi);
- if (err < 0)
- dev_err(dsi->dev, "MIPI calibration failed: %d\n", err);
+ tegra_dsi_prepare(dsi);
state = tegra_dsi_get_state(dsi);
if (!(old_man->flags & TTM_MEMTYPE_FLAG_FIXED) &&
!(new_man->flags & TTM_MEMTYPE_FLAG_FIXED))
- ret = ttm_bo_move_ttm(bo, evict, no_wait_gpu, mem);
+ ret = ttm_bo_move_ttm(bo, evict, interruptible, no_wait_gpu,
+ mem);
else if (bdev->driver->move)
ret = bdev->driver->move(bo, evict, interruptible,
no_wait_gpu, mem);
}
int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
- bool evict,
+ bool evict, bool interruptible,
bool no_wait_gpu, struct ttm_mem_reg *new_mem)
{
struct ttm_tt *ttm = bo->ttm;
int ret;
if (old_mem->mem_type != TTM_PL_SYSTEM) {
+ ret = ttm_bo_wait(bo, interruptible, no_wait_gpu);
+
+ if (unlikely(ret != 0)) {
+ if (ret != -ERESTARTSYS)
+ pr_err("Failed to expire sync object before unbinding TTM\n");
+ return ret;
+ }
+
ttm_tt_unbind(ttm);
ttm_bo_free_old_node(bo);
ttm_flag_masked(&old_mem->placement, TTM_PL_FLAG_SYSTEM,
ufbdev->fb_count++;
+#ifdef CONFIG_DRM_FBDEV_EMULATION
if (fb_defio && (info->fbdefio == NULL)) {
/* enable defio at last moment if not disabled by client */
info->fbdefio = fbdefio;
fb_deferred_io_init(info);
}
+#endif
pr_notice("open /dev/fb%d user=%d fb_info=%p count=%d\n",
info->node, user, info, ufbdev->fb_count);
ufbdev->fb_count--;
+#ifdef CONFIG_DRM_FBDEV_EMULATION
if ((ufbdev->fb_count == 0) && (info->fbdefio)) {
fb_deferred_io_cleanup(info);
kfree(info->fbdefio);
info->fbdefio = NULL;
info->fbops->fb_mmap = udl_fb_mmap;
}
+#endif
pr_warn("released /dev/fb%d user=%d count=%d\n",
info->node, user, ufbdev->fb_count);
return &vc4->bo_cache.size_list[page_index];
}
-void vc4_bo_cache_purge(struct drm_device *dev)
+static void vc4_bo_cache_purge(struct drm_device *dev)
{
struct vc4_dev *vc4 = to_vc4_dev(dev);
switch (args->param) {
case DRM_VC4_PARAM_V3D_IDENT0:
ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev);
- if (ret)
+ if (ret < 0)
return ret;
args->value = V3D_READ(V3D_IDENT0);
pm_runtime_put(&vc4->v3d->pdev->dev);
break;
case DRM_VC4_PARAM_V3D_IDENT1:
ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev);
- if (ret)
+ if (ret < 0)
return ret;
args->value = V3D_READ(V3D_IDENT1);
pm_runtime_put(&vc4->v3d->pdev->dev);
break;
case DRM_VC4_PARAM_V3D_IDENT2:
ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev);
- if (ret)
+ if (ret < 0)
return ret;
args->value = V3D_READ(V3D_IDENT2);
pm_runtime_put(&vc4->v3d->pdev->dev);
struct vc4_exec_info, head);
}
+static inline struct vc4_exec_info *
+vc4_last_render_job(struct vc4_dev *vc4)
+{
+ if (list_empty(&vc4->render_job_list))
+ return NULL;
+ return list_last_entry(&vc4->render_job_list,
+ struct vc4_exec_info, head);
+}
+
/**
* struct vc4_texture_sample_info - saves the offsets into the UBO for texture
* setup parameters.
return -EINVAL;
}
- exec->bo = kcalloc(exec->bo_count, sizeof(struct drm_gem_cma_object *),
- GFP_KERNEL);
+ exec->bo = drm_calloc_large(exec->bo_count,
+ sizeof(struct drm_gem_cma_object *));
if (!exec->bo) {
DRM_ERROR("Failed to allocate validated BO pointers\n");
return -ENOMEM;
spin_unlock(&file_priv->table_lock);
fail:
- kfree(handles);
- return 0;
+ drm_free_large(handles);
+ return ret;
}
static int
* read the contents back for validation, and I think the
* bo->vaddr is uncached access.
*/
- temp = kmalloc(temp_size, GFP_KERNEL);
+ temp = drm_malloc_ab(temp_size, 1);
if (!temp) {
DRM_ERROR("Failed to allocate storage for copying "
"in bin/render CLs.\n");
ret = vc4_validate_shader_recs(dev, exec);
fail:
- kfree(temp);
+ drm_free_large(temp);
return ret;
}
if (exec->bo) {
for (i = 0; i < exec->bo_count; i++)
drm_gem_object_unreference_unlocked(&exec->bo[i]->base);
- kfree(exec->bo);
+ drm_free_large(exec->bo);
}
while (!list_empty(&exec->unref_list)) {
vc4->overflow_mem = NULL;
}
- vc4_bo_cache_destroy(dev);
-
if (vc4->hang_state)
vc4_free_hang_state(dev, vc4->hang_state);
+
+ vc4_bo_cache_destroy(dev);
}
spin_lock_irqsave(&vc4->job_lock, irqflags);
current_exec = vc4_first_bin_job(vc4);
+ if (!current_exec)
+ current_exec = vc4_last_render_job(vc4);
if (current_exec) {
- vc4->overflow_mem->seqno = vc4->finished_seqno + 1;
+ vc4->overflow_mem->seqno = current_exec->seqno;
list_add_tail(&vc4->overflow_mem->unref_head,
¤t_exec->unref_list);
vc4->overflow_mem = NULL;
* of uniforms on each side. However, this scheme is easy to
* validate so it's all we allow for now.
*/
-
- if (QPU_GET_FIELD(inst, QPU_SIG) != QPU_SIG_NONE) {
+ switch (QPU_GET_FIELD(inst, QPU_SIG)) {
+ case QPU_SIG_NONE:
+ case QPU_SIG_SCOREBOARD_UNLOCK:
+ case QPU_SIG_COLOR_LOAD:
+ case QPU_SIG_LOAD_TMU0:
+ case QPU_SIG_LOAD_TMU1:
+ break;
+ default:
DRM_ERROR("uniforms address change must be "
"normal math\n");
return false;
dev->pads = args.args[0];
dev->device = device;
- mutex_lock(&dev->mipi->lock);
-
- if (dev->mipi->usage_count++ == 0) {
- err = tegra_mipi_power_up(dev->mipi);
- if (err < 0) {
- dev_err(dev->mipi->dev,
- "failed to power up MIPI bricks: %d\n",
- err);
- return ERR_PTR(err);
- }
- }
-
- mutex_unlock(&dev->mipi->lock);
-
return dev;
put:
void tegra_mipi_free(struct tegra_mipi_device *device)
{
- int err;
+ platform_device_put(device->pdev);
+ kfree(device);
+}
+EXPORT_SYMBOL(tegra_mipi_free);
- mutex_lock(&device->mipi->lock);
+int tegra_mipi_enable(struct tegra_mipi_device *dev)
+{
+ int err = 0;
- if (--device->mipi->usage_count == 0) {
- err = tegra_mipi_power_down(device->mipi);
- if (err < 0) {
- /*
- * Not much that can be done here, so an error message
- * will have to do.
- */
- dev_err(device->mipi->dev,
- "failed to power down MIPI bricks: %d\n",
- err);
- }
- }
+ mutex_lock(&dev->mipi->lock);
- mutex_unlock(&device->mipi->lock);
+ if (dev->mipi->usage_count++ == 0)
+ err = tegra_mipi_power_up(dev->mipi);
+
+ mutex_unlock(&dev->mipi->lock);
+
+ return err;
- platform_device_put(device->pdev);
- kfree(device);
}
-EXPORT_SYMBOL(tegra_mipi_free);
+EXPORT_SYMBOL(tegra_mipi_enable);
+
+int tegra_mipi_disable(struct tegra_mipi_device *dev)
+{
+ int err = 0;
+
+ mutex_lock(&dev->mipi->lock);
+
+ if (--dev->mipi->usage_count == 0)
+ err = tegra_mipi_power_down(dev->mipi);
+
+ mutex_unlock(&dev->mipi->lock);
+
+ return err;
+
+}
+EXPORT_SYMBOL(tegra_mipi_disable);
static int tegra_mipi_wait(struct tegra_mipi *mipi)
{
struct it87_data {
const struct attribute_group *groups[7];
enum chips type;
- u16 features;
+ u32 features;
u8 peci_mask;
u8 old_peci_mask;
&sensor_dev_attr_in10_input.dev_attr.attr, /* 41 */
&sensor_dev_attr_in11_input.dev_attr.attr, /* 41 */
&sensor_dev_attr_in12_input.dev_attr.attr, /* 41 */
+ NULL
};
static const struct attribute_group it87_group_in = {
#define AT91_I2C_TIMEOUT msecs_to_jiffies(100) /* transfer timeout */
#define AT91_I2C_DMA_THRESHOLD 8 /* enable DMA if transfer size is bigger than this threshold */
#define AUTOSUSPEND_TIMEOUT 2000
+#define AT91_I2C_MAX_ALT_CMD_DATA_SIZE 256
/* AT91 TWI register definitions */
#define AT91_TWI_CR 0x0000 /* Control Register */
unsigned twi_cwgr_reg;
struct at91_twi_pdata *pdata;
bool use_dma;
+ bool use_alt_cmd;
bool recv_len_abort;
u32 fifo_size;
struct at91_twi_dma dma;
/* send stop when last byte has been written */
if (--dev->buf_len == 0)
- if (!dev->pdata->has_alt_cmd)
+ if (!dev->use_alt_cmd)
at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_STOP);
dev_dbg(dev->dev, "wrote 0x%x, to go %d\n", *dev->buf, dev->buf_len);
* we just have to enable TXCOMP one.
*/
at91_twi_write(dev, AT91_TWI_IER, AT91_TWI_TXCOMP);
- if (!dev->pdata->has_alt_cmd)
+ if (!dev->use_alt_cmd)
at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_STOP);
}
}
/* send stop if second but last byte has been read */
- if (!dev->pdata->has_alt_cmd && dev->buf_len == 1)
+ if (!dev->use_alt_cmd && dev->buf_len == 1)
at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_STOP);
dev_dbg(dev->dev, "read 0x%x, to go %d\n", *dev->buf, dev->buf_len);
dma_unmap_single(dev->dev, sg_dma_address(&dev->dma.sg[0]),
dev->buf_len, DMA_FROM_DEVICE);
- if (!dev->pdata->has_alt_cmd) {
+ if (!dev->use_alt_cmd) {
/* The last two bytes have to be read without using dma */
dev->buf += dev->buf_len - 2;
dev->buf_len = 2;
struct dma_chan *chan_rx = dma->chan_rx;
size_t buf_len;
- buf_len = (dev->pdata->has_alt_cmd) ? dev->buf_len : dev->buf_len - 2;
+ buf_len = (dev->use_alt_cmd) ? dev->buf_len : dev->buf_len - 2;
dma->direction = DMA_FROM_DEVICE;
/* Keep in mind that we won't use dma to read the last two bytes */
unsigned start_flags = AT91_TWI_START;
/* if only one byte is to be read, immediately stop transfer */
- if (!has_alt_cmd && dev->buf_len <= 1 &&
+ if (!dev->use_alt_cmd && dev->buf_len <= 1 &&
!(dev->msg->flags & I2C_M_RECV_LEN))
start_flags |= AT91_TWI_STOP;
at91_twi_write(dev, AT91_TWI_CR, start_flags);
int ret;
unsigned int_addr_flag = 0;
struct i2c_msg *m_start = msg;
- bool is_read, use_alt_cmd = false;
+ bool is_read;
dev_dbg(&adap->dev, "at91_xfer: processing %d messages:\n", num);
at91_twi_write(dev, AT91_TWI_IADR, internal_address);
}
+ dev->use_alt_cmd = false;
is_read = (m_start->flags & I2C_M_RD);
if (dev->pdata->has_alt_cmd) {
- if (m_start->len > 0) {
+ if (m_start->len > 0 &&
+ m_start->len < AT91_I2C_MAX_ALT_CMD_DATA_SIZE) {
at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_ACMEN);
at91_twi_write(dev, AT91_TWI_ACR,
AT91_TWI_ACR_DATAL(m_start->len) |
((is_read) ? AT91_TWI_ACR_DIR : 0));
- use_alt_cmd = true;
+ dev->use_alt_cmd = true;
} else {
at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_ACMDIS);
}
at91_twi_write(dev, AT91_TWI_MMR,
(m_start->addr << 16) |
int_addr_flag |
- ((!use_alt_cmd && is_read) ? AT91_TWI_MREAD : 0));
+ ((!dev->use_alt_cmd && is_read) ? AT91_TWI_MREAD : 0));
dev->buf_len = m_start->len;
dev->buf = m_start->buf;
if (status & BIT(IS_M_START_BUSY_SHIFT)) {
iproc_i2c->xfer_is_done = 1;
- complete_all(&iproc_i2c->done);
+ complete(&iproc_i2c->done);
}
writel(status, iproc_i2c->base + IS_OFFSET);
dev->base + TXFCR_OFFSET);
writel(status & ~ISR_RESERVED_MASK, dev->base + ISR_OFFSET);
- complete_all(&dev->done);
+ complete(&dev->done);
return IRQ_HANDLED;
}
if (rc < 0) {
dev_err(dev->device,
"restart cmd failed rc = %d\n", rc);
- goto xfer_send_stop;
+ goto xfer_send_stop;
}
}
return IRQ_NONE;
brcmstb_i2c_enable_disable_irq(dev, INT_DISABLE);
- complete_all(&dev->done);
+ complete(&dev->done);
dev_dbg(dev->device, "isr handled");
return IRQ_HANDLED;
* depending on the scaling direction.
*
* Return: NOTIFY_STOP if the rate change should be aborted, NOTIFY_OK
- * to acknowedge the change, NOTIFY_DONE if the notification is
+ * to acknowledge the change, NOTIFY_DONE if the notification is
* considered irrelevant.
*/
static int cdns_i2c_clk_notifier_cb(struct notifier_block *nb, unsigned long
msg->outsize = request_len;
msg->insize = response_len;
- result = cros_ec_cmd_xfer(bus->ec, msg);
+ result = cros_ec_cmd_xfer_status(bus->ec, msg);
if (result < 0) {
dev_err(dev, "Error transferring EC i2c message %d\n", result);
goto exit;
dev_dbg(dev->dev, "Fast-mode HCNT:LCNT = %d:%d\n", hcnt, lcnt);
/* Configure SDA Hold Time if required */
- if (dev->sda_hold_time) {
- reg = dw_readl(dev, DW_IC_COMP_VERSION);
- if (reg >= DW_IC_SDA_HOLD_MIN_VERS)
+ reg = dw_readl(dev, DW_IC_COMP_VERSION);
+ if (reg >= DW_IC_SDA_HOLD_MIN_VERS) {
+ if (dev->sda_hold_time) {
dw_writel(dev, dev->sda_hold_time, DW_IC_SDA_HOLD);
- else
- dev_warn(dev->dev,
- "Hardware too old to adjust SDA hold time.");
+ } else {
+ /* Keep previous hold time setting if no one set it */
+ dev->sda_hold_time = dw_readl(dev, DW_IC_SDA_HOLD);
+ }
+ } else {
+ dev_warn(dev->dev,
+ "Hardware too old to adjust SDA hold time.\n");
}
/* Configure Tx/Rx FIFO threshold levels */
/* Set the number of I2C channel instance */
adap_info->ch_num = id->driver_data;
- ret = request_irq(pdev->irq, pch_i2c_handler, IRQF_SHARED,
- KBUILD_MODNAME, adap_info);
- if (ret) {
- pch_pci_err(pdev, "request_irq FAILED\n");
- goto err_request_irq;
- }
-
for (i = 0; i < adap_info->ch_num; i++) {
pch_adap = &adap_info->pch_data[i].pch_adapter;
adap_info->pch_i2c_suspended = false;
pch_adap->dev.of_node = pdev->dev.of_node;
pch_adap->dev.parent = &pdev->dev;
+ }
+
+ ret = request_irq(pdev->irq, pch_i2c_handler, IRQF_SHARED,
+ KBUILD_MODNAME, adap_info);
+ if (ret) {
+ pch_pci_err(pdev, "request_irq FAILED\n");
+ goto err_request_irq;
+ }
+
+ for (i = 0; i < adap_info->ch_num; i++) {
+ pch_adap = &adap_info->pch_data[i].pch_adapter;
pch_i2c_init(&adap_info->pch_data[i]);
meson_i2c_add_token(i2c, TOKEN_STOP);
} else {
i2c->state = STATE_IDLE;
- complete_all(&i2c->done);
+ complete(&i2c->done);
}
}
dev_dbg(i2c->dev, "error bit set\n");
i2c->error = -ENXIO;
i2c->state = STATE_IDLE;
- complete_all(&i2c->done);
+ complete(&i2c->done);
goto out;
}
break;
case STATE_STOP:
i2c->state = STATE_IDLE;
- complete_all(&i2c->done);
+ complete(&i2c->done);
break;
case STATE_IDLE:
break;
if (!clock_frequency_present) {
dev_err(&pdev->dev,
"Missing required parameter 'opencores,ip-clock-frequency'\n");
+ clk_disable_unprepare(i2c->clk);
return -ENODEV;
}
i2c->ip_clock_khz = clock_frequency / 1000;
default:
dev_err(&pdev->dev, "Unsupported I/O width (%d)\n",
i2c->reg_io_width);
- return -EINVAL;
+ ret = -EINVAL;
+ goto err_clk;
}
}
ret = ocores_init(&pdev->dev, i2c);
if (ret)
- return ret;
+ goto err_clk;
init_waitqueue_head(&i2c->wait);
ret = devm_request_irq(&pdev->dev, irq, ocores_isr, 0,
pdev->name, i2c);
if (ret) {
dev_err(&pdev->dev, "Cannot claim IRQ\n");
- return ret;
+ goto err_clk;
}
/* hook up driver to tree */
ret = i2c_add_adapter(&i2c->adap);
if (ret) {
dev_err(&pdev->dev, "Failed to add adapter\n");
- return ret;
+ goto err_clk;
}
/* add in known devices to the bus */
}
return 0;
+
+err_clk:
+ clk_disable_unprepare(i2c->clk);
+ return ret;
}
static int ocores_i2c_remove(struct platform_device *pdev)
#ifdef CONFIG_PM_SLEEP
static int qup_i2c_suspend(struct device *device)
{
- qup_i2c_pm_suspend_runtime(device);
+ if (!pm_runtime_suspended(device))
+ return qup_i2c_pm_suspend_runtime(device);
return 0;
}
}
dma_addr = dma_map_single(chan->device->dev, buf, len, dir);
- if (dma_mapping_error(dev, dma_addr)) {
+ if (dma_mapping_error(chan->device->dev, dma_addr)) {
dev_dbg(dev, "dma map failed, using PIO\n");
return;
}
* Code adapted from i2c-cadence.c.
*
* Return: NOTIFY_STOP if the rate change should be aborted, NOTIFY_OK
- * to acknowedge the change, NOTIFY_DONE if the notification is
+ * to acknowledge the change, NOTIFY_DONE if the notification is
* considered irrelevant.
*/
static int rk3x_i2c_clk_notifier_cb(struct notifier_block *nb, unsigned long
return ret < 0 ? ret : num;
}
+static __maybe_unused int rk3x_i2c_resume(struct device *dev)
+{
+ struct rk3x_i2c *i2c = dev_get_drvdata(dev);
+
+ rk3x_i2c_adapt_div(i2c, clk_get_rate(i2c->clk));
+
+ return 0;
+}
+
static u32 rk3x_i2c_func(struct i2c_adapter *adap)
{
return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | I2C_FUNC_PROTOCOL_MANGLING;
return 0;
}
+static SIMPLE_DEV_PM_OPS(rk3x_i2c_pm_ops, NULL, rk3x_i2c_resume);
+
static struct platform_driver rk3x_i2c_driver = {
.probe = rk3x_i2c_probe,
.remove = rk3x_i2c_remove,
.driver = {
.name = "rk3x-i2c",
.of_match_table = rk3x_i2c_match,
+ .pm = &rk3x_i2c_pm_ops,
},
};
return;
dma_addr = dma_map_single(chan->device->dev, pd->msg->buf, pd->msg->len, dir);
- if (dma_mapping_error(pd->dev, dma_addr)) {
+ if (dma_mapping_error(chan->device->dev, dma_addr)) {
dev_dbg(pd->dev, "dma map failed, using PIO\n");
return;
}
struct i2c_demux_pinctrl_chan chan[];
};
-static struct property status_okay = { .name = "status", .length = 3, .value = "ok" };
-
static int i2c_demux_master_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num)
{
struct i2c_demux_pinctrl_priv *priv = adap->algo_data;
adap = of_find_i2c_adapter_by_node(priv->chan[new_chan].parent_np);
if (!adap) {
ret = -ENODEV;
- goto err;
+ goto err_with_revert;
}
p = devm_pinctrl_get_select(adap->dev.parent, priv->bus_name);
err_with_put:
i2c_put_adapter(adap);
+ err_with_revert:
+ of_changeset_revert(&priv->chan[new_chan].chgset);
err:
dev_err(priv->dev, "failed to setup demux-adapter %d (%d)\n", new_chan, ret);
+ priv->cur_chan = -EINVAL;
return ret;
}
{
struct device_node *np = pdev->dev.of_node;
struct i2c_demux_pinctrl_priv *priv;
+ struct property *props;
int num_chan, i, j, err;
num_chan = of_count_phandle_with_args(np, "i2c-parent", NULL);
priv = devm_kzalloc(&pdev->dev, sizeof(*priv)
+ num_chan * sizeof(struct i2c_demux_pinctrl_chan), GFP_KERNEL);
- if (!priv)
+
+ props = devm_kcalloc(&pdev->dev, num_chan, sizeof(*props), GFP_KERNEL);
+
+ if (!priv || !props)
return -ENOMEM;
err = of_property_read_string(np, "i2c-bus-name", &priv->bus_name);
}
priv->chan[i].parent_np = adap_np;
+ props[i].name = devm_kstrdup(&pdev->dev, "status", GFP_KERNEL);
+ props[i].value = devm_kstrdup(&pdev->dev, "ok", GFP_KERNEL);
+ props[i].length = 3;
+
of_changeset_init(&priv->chan[i].chgset);
- of_changeset_update_property(&priv->chan[i].chgset, adap_np, &status_okay);
+ of_changeset_update_property(&priv->chan[i].chgset, adap_np, &props[i]);
}
priv->num_chan = num_chan;
/* Only select the channel if its different from the last channel */
if (data->last_chan != regval) {
ret = pca954x_reg_write(muxc->parent, client, regval);
- data->last_chan = regval;
+ data->last_chan = ret ? 0 : regval;
}
return ret;
config BMA220
tristate "Bosch BMA220 3-Axis Accelerometer Driver"
depends on SPI
+ select IIO_BUFFER
+ select IIO_TRIGGERED_BUFFER
help
Say yes here to add support for the Bosch BMA220 triaxial
acceleration sensor.
config STK8BA50
tristate "Sensortek STK8BA50 3-Axis Accelerometer Driver"
depends on I2C
- depends on IIO_TRIGGER
+ select IIO_BUFFER
+ select IIO_TRIGGERED_BUFFER
help
Say yes here to get support for the Sensortek STK8BA50 3-axis
accelerometer.
if (ret < 0)
return ret;
- ret = iio_triggered_buffer_setup(indio_dev, NULL,
+ ret = iio_triggered_buffer_setup(indio_dev, iio_pollfunc_store_time,
bma220_trigger_handler, NULL);
if (ret < 0) {
dev_err(&spi->dev, "iio triggered buffer setup failed\n");
#define BMC150_ACCEL_REG_PMU_BW 0x10
#define BMC150_ACCEL_DEF_BW 125
+#define BMC150_ACCEL_REG_RESET 0x14
+#define BMC150_ACCEL_RESET_VAL 0xB6
+
#define BMC150_ACCEL_REG_INT_MAP_0 0x19
#define BMC150_ACCEL_INT_MAP_0_BIT_SLOPE BIT(2)
int ret, i;
unsigned int val;
+ /*
+ * Reset chip to get it in a known good state. A delay of 1.8ms after
+ * reset is required according to the data sheets of supported chips.
+ */
+ regmap_write(data->regmap, BMC150_ACCEL_REG_RESET,
+ BMC150_ACCEL_RESET_VAL);
+ usleep_range(1800, 2500);
+
ret = regmap_read(data->regmap, BMC150_ACCEL_REG_CHIP_ID, &val);
if (ret < 0) {
dev_err(dev, "Error: Reading chip id\n");
if (ret < 0)
goto error_ret;
*val = ret;
+ ret = IIO_VAL_INT;
break;
case IIO_CHAN_INFO_SCALE:
ret = spi_w8r8(st->us, KXSD9_READ(KXSD9_REG_CTRL_C));
if (ret < 0)
goto error_ret;
+ *val = 0;
*val2 = kxsd9_micro_scales[ret & KXSD9_FS_MASK];
ret = IIO_VAL_INT_PLUS_MICRO;
break;
config ROCKCHIP_SARADC
tristate "Rockchip SARADC driver"
depends on ARCH_ROCKCHIP || (ARM && COMPILE_TEST)
+ depends on RESET_CONTROLLER
help
Say yes here to build support for the SARADC found in SoCs from
Rockchip.
static const struct iio_info ad7991_info = {
.read_raw = &ad799x_read_raw,
.driver_module = THIS_MODULE,
+ .update_scan_mode = ad799x_update_scan_mode,
};
static const struct iio_info ad7993_4_7_8_noirq_info = {
st->ts_bufferedmeasure = false;
input_report_key(st->ts_input, BTN_TOUCH, 0);
input_sync(st->ts_input);
- } else if (status & AT91_ADC_EOC(3)) {
- /* Conversion finished */
+ } else if (status & AT91_ADC_EOC(3) && st->ts_input) {
+ /* Conversion finished and we've a touchscreen */
if (st->ts_bufferedmeasure) {
/*
* Last measurement is always discarded, since it can
#include <linux/of_device.h>
#include <linux/clk.h>
#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/reset.h>
#include <linux/regulator/consumer.h>
#include <linux/iio/iio.h>
struct clk *clk;
struct completion completion;
struct regulator *vref;
+ struct reset_control *reset;
const struct rockchip_saradc_data *data;
u16 last_val;
};
};
MODULE_DEVICE_TABLE(of, rockchip_saradc_match);
+/**
+ * Reset SARADC Controller.
+ */
+static void rockchip_saradc_reset_controller(struct reset_control *reset)
+{
+ reset_control_assert(reset);
+ usleep_range(10, 20);
+ reset_control_deassert(reset);
+}
+
static int rockchip_saradc_probe(struct platform_device *pdev)
{
struct rockchip_saradc *info = NULL;
if (IS_ERR(info->regs))
return PTR_ERR(info->regs);
+ /*
+ * The reset should be an optional property, as it should work
+ * with old devicetrees as well
+ */
+ info->reset = devm_reset_control_get(&pdev->dev, "saradc-apb");
+ if (IS_ERR(info->reset)) {
+ ret = PTR_ERR(info->reset);
+ if (ret != -ENOENT)
+ return ret;
+
+ dev_dbg(&pdev->dev, "no reset control found\n");
+ info->reset = NULL;
+ }
+
init_completion(&info->completion);
irq = platform_get_irq(pdev, 0);
return PTR_ERR(info->vref);
}
+ if (info->reset)
+ rockchip_saradc_reset_controller(info->reset);
+
/*
* Use a default value for the converter clock.
* This may become user-configurable in the future.
#ifdef CONFIG_OF
static int ads1015_get_channels_config_of(struct i2c_client *client)
{
- struct ads1015_data *data = i2c_get_clientdata(client);
+ struct iio_dev *indio_dev = i2c_get_clientdata(client);
+ struct ads1015_data *data = iio_priv(indio_dev);
struct device_node *node;
if (!client->dev.of_node ||
struct tiadc_device {
struct ti_tscadc_dev *mfd_tscadc;
+ struct mutex fifo1_lock; /* to protect fifo access */
int channels;
u8 channel_line[8];
u8 channel_step[8];
int *val, int *val2, long mask)
{
struct tiadc_device *adc_dev = iio_priv(indio_dev);
+ int ret = IIO_VAL_INT;
int i, map_val;
unsigned int fifo1count, read, stepid;
bool found = false;
if (!step_en)
return -EINVAL;
+ mutex_lock(&adc_dev->fifo1_lock);
fifo1count = tiadc_readl(adc_dev, REG_FIFO1CNT);
while (fifo1count--)
tiadc_readl(adc_dev, REG_FIFO1);
am335x_tsc_se_set_once(adc_dev->mfd_tscadc, step_en);
- timeout = jiffies + usecs_to_jiffies
+ timeout = jiffies + msecs_to_jiffies
(IDLE_TIMEOUT * adc_dev->channels);
/* Wait for Fifo threshold interrupt */
while (1) {
if (time_after(jiffies, timeout)) {
am335x_tsc_se_adc_done(adc_dev->mfd_tscadc);
- return -EAGAIN;
+ ret = -EAGAIN;
+ goto err_unlock;
}
}
map_val = adc_dev->channel_step[chan->scan_index];
am335x_tsc_se_adc_done(adc_dev->mfd_tscadc);
if (found == false)
- return -EBUSY;
- return IIO_VAL_INT;
+ ret = -EBUSY;
+
+err_unlock:
+ mutex_unlock(&adc_dev->fifo1_lock);
+ return ret;
}
static const struct iio_info tiadc_info = {
tiadc_step_config(indio_dev);
tiadc_writel(adc_dev, REG_FIFO1THR, FIFO1_THRESHOLD);
+ mutex_init(&adc_dev->fifo1_lock);
err = tiadc_channel_init(indio_dev, adc_dev->channels);
if (err < 0)
break;
case IIO_ELECTRICALCONDUCTIVITY:
*val = 1; /* 0.00001 */
- *val = 100000;
+ *val2 = 100000;
break;
case IIO_CONCENTRATION:
*val = 0; /* 0.000000001 */
{HID_USAGE_SENSOR_ALS, 0, 1, 0},
{HID_USAGE_SENSOR_ALS, HID_USAGE_SENSOR_UNITS_LUX, 1, 0},
- {HID_USAGE_SENSOR_PRESSURE, 0, 100000, 0},
- {HID_USAGE_SENSOR_PRESSURE, HID_USAGE_SENSOR_UNITS_PASCAL, 1, 0},
+ {HID_USAGE_SENSOR_PRESSURE, 0, 100, 0},
+ {HID_USAGE_SENSOR_PRESSURE, HID_USAGE_SENSOR_UNITS_PASCAL, 0, 1000},
};
static int pow_10(unsigned power)
unsigned int out_state;
};
+/**
+ * struct stx104_dev - STX104 device private data structure
+ * @indio_dev: IIO device
+ * @chip: instance of the gpio_chip
+ */
+struct stx104_dev {
+ struct iio_dev *indio_dev;
+ struct gpio_chip *chip;
+};
+
static int stx104_read_raw(struct iio_dev *indio_dev,
struct iio_chan_spec const *chan, int *val, int *val2, long mask)
{
static int stx104_gpio_get_direction(struct gpio_chip *chip,
unsigned int offset)
{
+ /* GPIO 0-3 are input only, while the rest are output only */
if (offset < 4)
return 1;
struct iio_dev *indio_dev;
struct stx104_iio *priv;
struct stx104_gpio *stx104gpio;
+ struct stx104_dev *stx104dev;
int err;
indio_dev = devm_iio_device_alloc(dev, sizeof(*priv));
if (!stx104gpio)
return -ENOMEM;
+ stx104dev = devm_kzalloc(dev, sizeof(*stx104dev), GFP_KERNEL);
+ if (!stx104dev)
+ return -ENOMEM;
+
if (!devm_request_region(dev, base[id], STX104_EXTENT,
dev_name(dev))) {
dev_err(dev, "Unable to lock port addresses (0x%X-0x%X)\n",
outw(0, base[id] + 4);
outw(0, base[id] + 6);
- err = devm_iio_device_register(dev, indio_dev);
- if (err) {
- dev_err(dev, "IIO device registering failed (%d)\n", err);
- return err;
- }
-
stx104gpio->chip.label = dev_name(dev);
stx104gpio->chip.parent = dev;
stx104gpio->chip.owner = THIS_MODULE;
spin_lock_init(&stx104gpio->lock);
- dev_set_drvdata(dev, stx104gpio);
+ stx104dev->indio_dev = indio_dev;
+ stx104dev->chip = &stx104gpio->chip;
+ dev_set_drvdata(dev, stx104dev);
err = gpiochip_add_data(&stx104gpio->chip, stx104gpio);
if (err) {
return err;
}
+ err = iio_device_register(indio_dev);
+ if (err) {
+ dev_err(dev, "IIO device registering failed (%d)\n", err);
+ gpiochip_remove(&stx104gpio->chip);
+ return err;
+ }
+
return 0;
}
static int stx104_remove(struct device *dev, unsigned int id)
{
- struct stx104_gpio *const stx104gpio = dev_get_drvdata(dev);
+ struct stx104_dev *const stx104dev = dev_get_drvdata(dev);
- gpiochip_remove(&stx104gpio->chip);
+ iio_device_unregister(stx104dev->indio_dev);
+ gpiochip_remove(stx104dev->chip);
return 0;
}
config AM2315
tristate "Aosong AM2315 relative humidity and temperature sensor"
depends on I2C
+ select IIO_BUFFER
+ select IIO_TRIGGERED_BUFFER
help
If you say yes here you get support for the Aosong AM2315
relative humidity and ambient temperature sensor.
indio_dev->channels = am2315_channels;
indio_dev->num_channels = ARRAY_SIZE(am2315_channels);
- ret = iio_triggered_buffer_setup(indio_dev, NULL,
+ ret = iio_triggered_buffer_setup(indio_dev, iio_pollfunc_store_time,
am2315_trigger_handler, NULL);
if (ret < 0) {
dev_err(&client->dev, "iio triggered buffer setup failed\n");
struct i2c_client *client = data->client;
int delay = data->adc_int_us[chan->address];
int ret;
- int val;
+ __be16 val;
/* start measurement */
ret = i2c_smbus_write_byte(client, chan->address);
/* wait for integration time to pass */
usleep_range(delay, delay + 1000);
- /*
- * i2c_smbus_read_word_data cannot() be used here due to the command
- * value not being understood and causes NAKs preventing any reading
- * from being accessed.
- */
- ret = i2c_smbus_read_byte(client);
+ /* read measurement */
+ ret = i2c_master_recv(data->client, (char *)&val, sizeof(val));
if (ret < 0) {
- dev_err(&client->dev, "cannot read high byte measurement");
+ dev_err(&client->dev, "cannot read sensor data\n");
return ret;
}
- val = ret << 8;
-
- ret = i2c_smbus_read_byte(client);
- if (ret < 0) {
- dev_err(&client->dev, "cannot read low byte measurement");
- return ret;
- }
- val |= ret;
-
- return val;
+ return be16_to_cpu(val);
}
static int hdc100x_get_heater_status(struct hdc100x_data *data)
struct iio_dev *indio_dev;
struct hdc100x_data *data;
- if (!i2c_check_functionality(client->adapter,
- I2C_FUNC_SMBUS_WORD_DATA | I2C_FUNC_SMBUS_BYTE))
+ if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_WORD_DATA |
+ I2C_FUNC_SMBUS_BYTE | I2C_FUNC_I2C))
return -EOPNOTSUPP;
indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*data));
{
struct iio_dev *indio_dev = filp->private_data;
struct iio_buffer *rb = indio_dev->buffer;
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
size_t datum_size;
size_t to_wait;
- int ret;
+ int ret = 0;
if (!indio_dev->info)
return -ENODEV;
else
to_wait = min_t(size_t, n / datum_size, rb->watermark);
+ add_wait_queue(&rb->pollq, &wait);
do {
- ret = wait_event_interruptible(rb->pollq,
- iio_buffer_ready(indio_dev, rb, to_wait, n / datum_size));
- if (ret)
- return ret;
+ if (!indio_dev->info) {
+ ret = -ENODEV;
+ break;
+ }
- if (!indio_dev->info)
- return -ENODEV;
+ if (!iio_buffer_ready(indio_dev, rb, to_wait, n / datum_size)) {
+ if (signal_pending(current)) {
+ ret = -ERESTARTSYS;
+ break;
+ }
+
+ wait_woken(&wait, TASK_INTERRUPTIBLE,
+ MAX_SCHEDULE_TIMEOUT);
+ continue;
+ }
ret = rb->access->read_first_n(rb, n, buf);
if (ret == 0 && (filp->f_flags & O_NONBLOCK))
ret = -EAGAIN;
- } while (ret == 0);
+ } while (ret == 0);
+ remove_wait_queue(&rb->pollq, &wait);
return ret;
}
return sprintf(buf, "%d.%09u\n", vals[0], vals[1]);
case IIO_VAL_FRACTIONAL:
tmp = div_s64((s64)vals[0] * 1000000000LL, vals[1]);
- vals[1] = do_div(tmp, 1000000000LL);
- vals[0] = tmp;
- return sprintf(buf, "%d.%09u\n", vals[0], vals[1]);
+ vals[0] = (int)div_s64_rem(tmp, 1000000000, &vals[1]);
+ return sprintf(buf, "%d.%09u\n", vals[0], abs(vals[1]));
case IIO_VAL_FRACTIONAL_LOG2:
tmp = (s64)vals[0] * 1000000000LL >> vals[1];
vals[1] = do_div(tmp, 1000000000LL);
config BH1780
tristate "ROHM BH1780 ambient light sensor"
depends on I2C
- depends on !SENSORS_BH1780
help
Say Y here to build support for the ROHM BH1780GLI ambient
light sensor.
tristate "MAX44000 Ambient and Infrared Proximity Sensor"
depends on I2C
select REGMAP_I2C
+ select IIO_BUFFER
+ select IIO_TRIGGERED_BUFFER
help
Say Y here if you want to build support for Maxim Integrated's
MAX44000 ambient and infrared proximity sensor device.
data->vdda = devm_regulator_get(dev, "vdda");
if (IS_ERR(data->vdda)) {
dev_err(dev, "failed to get VDDA regulator\n");
- ret = PTR_ERR(data->vddd);
+ ret = PTR_ERR(data->vdda);
goto out_disable_vddd;
}
ret = regulator_enable(data->vdda);
#ifdef CONFIG_PM
static int bmp280_runtime_suspend(struct device *dev)
{
- struct bmp280_data *data = dev_get_drvdata(dev);
+ struct iio_dev *indio_dev = dev_get_drvdata(dev);
+ struct bmp280_data *data = iio_priv(indio_dev);
int ret;
ret = regulator_disable(data->vdda);
static int bmp280_runtime_resume(struct device *dev)
{
- struct bmp280_data *data = dev_get_drvdata(dev);
+ struct iio_dev *indio_dev = dev_get_drvdata(dev);
+ struct bmp280_data *data = iio_priv(indio_dev);
int ret;
ret = regulator_enable(data->vddd);
return ret;
}
- ret = iio_triggered_buffer_setup(indio_dev, NULL,
+ ret = iio_triggered_buffer_setup(indio_dev, iio_pollfunc_store_time,
&as3935_trigger_handler, NULL);
if (ret) {
if (addr->dev_addr.bound_dev_if) {
ndev = dev_get_by_index(&init_net, addr->dev_addr.bound_dev_if);
- if (!ndev)
- return -ENODEV;
+ if (!ndev) {
+ ret = -ENODEV;
+ goto err2;
+ }
if (ndev->flags & IFF_LOOPBACK) {
dev_put(ndev);
- if (!id_priv->id.device->get_netdev)
- return -EOPNOTSUPP;
+ if (!id_priv->id.device->get_netdev) {
+ ret = -EOPNOTSUPP;
+ goto err2;
+ }
ndev = id_priv->id.device->get_netdev(id_priv->id.device,
id_priv->id.port_num);
- if (!ndev)
- return -ENODEV;
+ if (!ndev) {
+ ret = -ENODEV;
+ goto err2;
+ }
}
route->path_rec->net = &init_net;
atomic_t refcount;
enum mcast_group_state state;
struct ib_sa_query *query;
- int query_id;
u16 pkey_index;
u8 leave_state;
int retries;
member->multicast.comp_mask,
3000, GFP_KERNEL, join_handler, group,
&group->query);
- if (ret >= 0) {
- group->query_id = ret;
- ret = 0;
- }
- return ret;
+ return (ret > 0) ? 0 : ret;
}
static int send_leave(struct mcast_group *group, u8 leave_state)
IB_SA_MCMEMBER_REC_JOIN_STATE,
3000, GFP_KERNEL, leave_handler,
group, &group->query);
- if (ret >= 0) {
- group->query_id = ret;
- ret = 0;
- }
- return ret;
+ return (ret > 0) ? 0 : ret;
}
static void join_group(struct mcast_group *group, struct mcast_member *member,
spin_lock_irqsave(&ep->com.dev->lock, flags);
_remove_handle(ep->com.dev, &ep->com.dev->hwtid_idr, ep->hwtid, 0);
+ if (idr_is_empty(&ep->com.dev->hwtid_idr))
+ wake_up(&ep->com.dev->wait);
spin_unlock_irqrestore(&ep->com.dev->lock, flags);
}
(ep->mpa_pkt + sizeof(*mpa));
ep->ird = ntohs(mpa_v2_params->ird) &
MPA_V2_IRD_ORD_MASK;
+ ep->ird = min_t(u32, ep->ird,
+ cur_max_read_depth(ep->com.dev));
ep->ord = ntohs(mpa_v2_params->ord) &
MPA_V2_IRD_ORD_MASK;
+ ep->ord = min_t(u32, ep->ord,
+ cur_max_read_depth(ep->com.dev));
PDBG("%s initiator ird %u ord %u\n", __func__, ep->ird,
ep->ord);
if (ntohs(mpa_v2_params->ird) & MPA_V2_PEER2PEER_MODEL)
}
ep->l2t = cxgb4_l2t_get(cdev->rdev.lldi.l2t,
n, pdev, rt_tos2priority(tos));
- if (!ep->l2t)
+ if (!ep->l2t) {
+ dev_put(pdev);
goto out;
+ }
ep->mtu = pdev->mtu;
ep->tx_chan = cxgb4_port_chan(pdev);
ep->smac_idx = cxgb4_tp_smt_idx(adapter_type,
if (ep->mpa_attr.version == 2 && ep->mpa_attr.enhanced_rdma_conn) {
if (conn_param->ord > ep->ird) {
if (RELAXED_IRD_NEGOTIATION) {
- ep->ord = ep->ird;
+ conn_param->ord = ep->ird;
} else {
ep->ird = conn_param->ird;
ep->ord = conn_param->ord;
int c4iw_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
{
struct c4iw_cq *chp;
- int ret;
+ int ret = 0;
unsigned long flag;
chp = to_c4iw_cq(ibcq);
spin_lock_irqsave(&chp->lock, flag);
- ret = t4_arm_cq(&chp->cq,
- (flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED);
+ t4_arm_cq(&chp->cq,
+ (flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED);
+ if (flags & IB_CQ_REPORT_MISSED_EVENTS)
+ ret = t4_cq_notempty(&chp->cq);
spin_unlock_irqrestore(&chp->lock, flag);
- if (ret && !(flags & IB_CQ_REPORT_MISSED_EVENTS))
- ret = 0;
return ret;
}
static void c4iw_dealloc(struct uld_ctx *ctx)
{
c4iw_rdev_close(&ctx->dev->rdev);
+ WARN_ON_ONCE(!idr_is_empty(&ctx->dev->cqidr));
idr_destroy(&ctx->dev->cqidr);
+ WARN_ON_ONCE(!idr_is_empty(&ctx->dev->qpidr));
idr_destroy(&ctx->dev->qpidr);
+ WARN_ON_ONCE(!idr_is_empty(&ctx->dev->mmidr));
idr_destroy(&ctx->dev->mmidr);
+ wait_event(ctx->dev->wait, idr_is_empty(&ctx->dev->hwtid_idr));
idr_destroy(&ctx->dev->hwtid_idr);
idr_destroy(&ctx->dev->stid_idr);
idr_destroy(&ctx->dev->atid_idr);
mutex_init(&devp->rdev.stats.lock);
mutex_init(&devp->db_mutex);
INIT_LIST_HEAD(&devp->db_fc_list);
+ init_waitqueue_head(&devp->wait);
devp->avail_ird = devp->rdev.lldi.max_ird_adapter;
if (c4iw_debugfs_root) {
struct idr stid_idr;
struct list_head db_fc_list;
u32 avail_ird;
+ wait_queue_head_t wait;
};
static inline struct c4iw_dev *to_c4iw_dev(struct ib_device *ibdev)
return 0;
}
-void _free_qp(struct kref *kref)
+static void _free_qp(struct kref *kref)
{
struct c4iw_qp *qhp;
return (CQE_GENBIT(cqe) == cq->gen);
}
+static inline int t4_cq_notempty(struct t4_cq *cq)
+{
+ return cq->sw_in_use || t4_valid_cqe(cq, &cq->queue[cq->cidx]);
+}
+
static inline int t4_next_hw_cqe(struct t4_cq *cq, struct t4_cqe **cqe)
{
int ret;
#include <linux/topology.h>
#include <linux/cpumask.h>
#include <linux/module.h>
-#include <linux/cpumask.h>
#include "hfi.h"
#include "affinity.h"
size_t count)
{
struct hfi1_affinity_node *entry;
- struct cpumask mask;
+ cpumask_var_t mask;
int ret, i;
spin_lock(&node_affinity.lock);
if (!entry)
return -EINVAL;
- ret = cpulist_parse(buf, &mask);
+ ret = zalloc_cpumask_var(&mask, GFP_KERNEL);
+ if (!ret)
+ return -ENOMEM;
+
+ ret = cpulist_parse(buf, mask);
if (ret)
- return ret;
+ goto out;
- if (!cpumask_subset(&mask, cpu_online_mask) || cpumask_empty(&mask)) {
+ if (!cpumask_subset(mask, cpu_online_mask) || cpumask_empty(mask)) {
dd_dev_warn(dd, "Invalid CPU mask\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
}
mutex_lock(&sdma_affinity_mutex);
/* reset the SDMA interrupt affinity details */
init_cpu_mask_set(&entry->def_intr);
- cpumask_copy(&entry->def_intr.mask, &mask);
+ cpumask_copy(&entry->def_intr.mask, mask);
/*
* Reassign the affinity for each SDMA interrupt.
*/
if (ret)
break;
}
-
mutex_unlock(&sdma_affinity_mutex);
+out:
+ free_cpumask_var(mask);
return ret ? ret : strnlen(buf, PAGE_SIZE);
}
write_csr(dd, DC_LCB_CFG_TX_FIFOS_RESET, 0x00);
}
+/*
+ * Perform a test read on the QSFP. Return 0 on success, -ERRNO
+ * on error.
+ */
+static int test_qsfp_read(struct hfi1_pportdata *ppd)
+{
+ int ret;
+ u8 status;
+
+ /* report success if not a QSFP */
+ if (ppd->port_type != PORT_TYPE_QSFP)
+ return 0;
+
+ /* read byte 2, the status byte */
+ ret = one_qsfp_read(ppd, ppd->dd->hfi1_id, 2, &status, 1);
+ if (ret < 0)
+ return ret;
+ if (ret != 1)
+ return -EIO;
+
+ return 0; /* success */
+}
+
+/*
+ * Values for QSFP retry.
+ *
+ * Give up after 10s (20 x 500ms). The overall timeout was empirically
+ * arrived at from experience on a large cluster.
+ */
+#define MAX_QSFP_RETRIES 20
+#define QSFP_RETRY_WAIT 500 /* msec */
+
+/*
+ * Try a QSFP read. If it fails, schedule a retry for later.
+ * Called on first link activation after driver load.
+ */
+static void try_start_link(struct hfi1_pportdata *ppd)
+{
+ if (test_qsfp_read(ppd)) {
+ /* read failed */
+ if (ppd->qsfp_retry_count >= MAX_QSFP_RETRIES) {
+ dd_dev_err(ppd->dd, "QSFP not responding, giving up\n");
+ return;
+ }
+ dd_dev_info(ppd->dd,
+ "QSFP not responding, waiting and retrying %d\n",
+ (int)ppd->qsfp_retry_count);
+ ppd->qsfp_retry_count++;
+ queue_delayed_work(ppd->hfi1_wq, &ppd->start_link_work,
+ msecs_to_jiffies(QSFP_RETRY_WAIT));
+ return;
+ }
+ ppd->qsfp_retry_count = 0;
+
+ /*
+ * Tune the SerDes to a ballpark setting for optimal signal and bit
+ * error rate. Needs to be done before starting the link.
+ */
+ tune_serdes(ppd);
+ start_link(ppd);
+}
+
+/*
+ * Workqueue function to start the link after a delay.
+ */
+void handle_start_link(struct work_struct *work)
+{
+ struct hfi1_pportdata *ppd = container_of(work, struct hfi1_pportdata,
+ start_link_work.work);
+ try_start_link(ppd);
+}
+
int bringup_serdes(struct hfi1_pportdata *ppd)
{
struct hfi1_devdata *dd = ppd->dd;
set_qsfp_int_n(ppd, 1);
}
- /*
- * Tune the SerDes to a ballpark setting for
- * optimal signal and bit error rate
- * Needs to be done before starting the link
- */
- tune_serdes(ppd);
-
- return start_link(ppd);
+ try_start_link(ppd);
+ return 0;
}
void hfi1_quiet_serdes(struct hfi1_pportdata *ppd)
ppd->driver_link_ready = 0;
ppd->link_enabled = 0;
+ ppd->qsfp_retry_count = MAX_QSFP_RETRIES; /* prevent more retries */
+ flush_delayed_work(&ppd->start_link_work);
+ cancel_delayed_work_sync(&ppd->start_link_work);
+
ppd->offline_disabled_reason =
HFI1_ODR_MASK(OPA_LINKDOWN_REASON_SMA_DISABLED);
set_link_down_reason(ppd, OPA_LINKDOWN_REASON_SMA_DISABLED, 0,
*/
static int set_up_context_variables(struct hfi1_devdata *dd)
{
- int num_kernel_contexts;
+ unsigned long num_kernel_contexts;
int total_contexts;
int ret;
unsigned ngroups;
*/
if (num_kernel_contexts > (dd->chip_send_contexts - num_vls - 1)) {
dd_dev_err(dd,
- "Reducing # kernel rcv contexts to: %d, from %d\n",
+ "Reducing # kernel rcv contexts to: %d, from %lu\n",
(int)(dd->chip_send_contexts - num_vls - 1),
- (int)num_kernel_contexts);
+ num_kernel_contexts);
num_kernel_contexts = dd->chip_send_contexts - num_vls - 1;
}
/*
void handle_link_down(struct work_struct *work);
void handle_link_downgrade(struct work_struct *work);
void handle_link_bounce(struct work_struct *work);
+void handle_start_link(struct work_struct *work);
void handle_sma_message(struct work_struct *work);
void reset_qsfp(struct hfi1_pportdata *ppd);
void qsfp_event(struct work_struct *work);
static struct dentry *hfi1_dbg_root;
+/* wrappers to enforce srcu in seq file */
+static ssize_t hfi1_seq_read(
+ struct file *file,
+ char __user *buf,
+ size_t size,
+ loff_t *ppos)
+{
+ struct dentry *d = file->f_path.dentry;
+ int srcu_idx;
+ ssize_t r;
+
+ r = debugfs_use_file_start(d, &srcu_idx);
+ if (likely(!r))
+ r = seq_read(file, buf, size, ppos);
+ debugfs_use_file_finish(srcu_idx);
+ return r;
+}
+
+static loff_t hfi1_seq_lseek(
+ struct file *file,
+ loff_t offset,
+ int whence)
+{
+ struct dentry *d = file->f_path.dentry;
+ int srcu_idx;
+ loff_t r;
+
+ r = debugfs_use_file_start(d, &srcu_idx);
+ if (likely(!r))
+ r = seq_lseek(file, offset, whence);
+ debugfs_use_file_finish(srcu_idx);
+ return r;
+}
+
#define private2dd(file) (file_inode(file)->i_private)
#define private2ppd(file) (file_inode(file)->i_private)
static const struct file_operations _##name##_file_ops = { \
.owner = THIS_MODULE, \
.open = _##name##_open, \
- .read = seq_read, \
- .llseek = seq_lseek, \
+ .read = hfi1_seq_read, \
+ .llseek = hfi1_seq_lseek, \
.release = seq_release \
}
DEBUGFS_FILE_CREATE(#name, parent, data, &_##name##_file_ops, S_IRUGO)
static void *_opcode_stats_seq_start(struct seq_file *s, loff_t *pos)
-__acquires(RCU)
{
struct hfi1_opcode_stats_perctx *opstats;
- rcu_read_lock();
if (*pos >= ARRAY_SIZE(opstats->stats))
return NULL;
return pos;
}
static void _opcode_stats_seq_stop(struct seq_file *s, void *v)
-__releases(RCU)
{
- rcu_read_unlock();
}
static int _opcode_stats_seq_show(struct seq_file *s, void *v)
DEBUGFS_FILE_OPS(ctx_stats);
static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos)
-__acquires(RCU)
+ __acquires(RCU)
{
struct qp_iter *iter;
loff_t n = *pos;
- rcu_read_lock();
iter = qp_iter_init(s->private);
+
+ /* stop calls rcu_read_unlock */
+ rcu_read_lock();
+
if (!iter)
return NULL;
- while (n--) {
+ do {
if (qp_iter_next(iter)) {
kfree(iter);
return NULL;
}
- }
+ } while (n--);
return iter;
}
static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr,
loff_t *pos)
+ __must_hold(RCU)
{
struct qp_iter *iter = iter_ptr;
}
static void _qp_stats_seq_stop(struct seq_file *s, void *iter_ptr)
-__releases(RCU)
+ __releases(RCU)
{
rcu_read_unlock();
}
DEBUGFS_FILE_OPS(qp_stats);
static void *_sdes_seq_start(struct seq_file *s, loff_t *pos)
-__acquires(RCU)
{
struct hfi1_ibdev *ibd;
struct hfi1_devdata *dd;
- rcu_read_lock();
ibd = (struct hfi1_ibdev *)s->private;
dd = dd_from_dev(ibd);
if (!dd->per_sdma || *pos >= dd->num_sdma)
}
static void _sdes_seq_stop(struct seq_file *s, void *v)
-__releases(RCU)
{
- rcu_read_unlock();
}
static int _sdes_seq_show(struct seq_file *s, void *v)
struct hfi1_devdata *dd;
ssize_t rval;
- rcu_read_lock();
dd = private2dd(file);
avail = hfi1_read_cntrs(dd, NULL, &counters);
rval = simple_read_from_buffer(buf, count, ppos, counters, avail);
- rcu_read_unlock();
return rval;
}
struct hfi1_devdata *dd;
ssize_t rval;
- rcu_read_lock();
dd = private2dd(file);
avail = hfi1_read_cntrs(dd, &names, NULL);
rval = simple_read_from_buffer(buf, count, ppos, names, avail);
- rcu_read_unlock();
return rval;
}
struct hfi1_devdata *dd;
ssize_t rval;
- rcu_read_lock();
dd = private2dd(file);
avail = hfi1_read_portcntrs(dd->pport, &names, NULL);
rval = simple_read_from_buffer(buf, count, ppos, names, avail);
- rcu_read_unlock();
return rval;
}
struct hfi1_pportdata *ppd;
ssize_t rval;
- rcu_read_lock();
ppd = private2ppd(file);
avail = hfi1_read_portcntrs(ppd, NULL, &counters);
rval = simple_read_from_buffer(buf, count, ppos, counters, avail);
- rcu_read_unlock();
return rval;
}
int used;
int i;
- rcu_read_lock();
ppd = private2ppd(file);
dd = ppd->dd;
size = PAGE_SIZE;
used = 0;
tmp = kmalloc(size, GFP_KERNEL);
- if (!tmp) {
- rcu_read_unlock();
+ if (!tmp)
return -ENOMEM;
- }
scratch0 = read_csr(dd, ASIC_CFG_SCRATCH);
used += scnprintf(tmp + used, size - used,
used += scnprintf(tmp + used, size - used, "Write bits to clear\n");
ret = simple_read_from_buffer(buf, count, ppos, tmp, used);
- rcu_read_unlock();
kfree(tmp);
return ret;
}
u64 scratch0;
u64 clear;
- rcu_read_lock();
ppd = private2ppd(file);
dd = ppd->dd;
buff = kmalloc(count + 1, GFP_KERNEL);
- if (!buff) {
- ret = -ENOMEM;
- goto do_return;
- }
+ if (!buff)
+ return -ENOMEM;
ret = copy_from_user(buff, buf, count);
if (ret > 0) {
do_free:
kfree(buff);
- do_return:
- rcu_read_unlock();
return ret;
}
char *tmp;
int ret;
- rcu_read_lock();
ppd = private2ppd(file);
tmp = kmalloc(PAGE_SIZE, GFP_KERNEL);
- if (!tmp) {
- rcu_read_unlock();
+ if (!tmp)
return -ENOMEM;
- }
ret = qsfp_dump(ppd, tmp, PAGE_SIZE);
if (ret > 0)
ret = simple_read_from_buffer(buf, count, ppos, tmp, ret);
- rcu_read_unlock();
kfree(tmp);
return ret;
}
int offset;
int total_written;
- rcu_read_lock();
ppd = private2ppd(file);
/* byte offset format: [offsetSize][i2cAddr][offsetHigh][offsetLow] */
offset = *ppos & 0xffff;
/* explicitly reject invalid address 0 to catch cp and cat */
- if (i2c_addr == 0) {
- ret = -EINVAL;
- goto _return;
- }
+ if (i2c_addr == 0)
+ return -EINVAL;
buff = kmalloc(count, GFP_KERNEL);
- if (!buff) {
- ret = -ENOMEM;
- goto _return;
- }
+ if (!buff)
+ return -ENOMEM;
ret = copy_from_user(buff, buf, count);
if (ret > 0) {
_free:
kfree(buff);
- _return:
- rcu_read_unlock();
return ret;
}
int offset;
int total_read;
- rcu_read_lock();
ppd = private2ppd(file);
/* byte offset format: [offsetSize][i2cAddr][offsetHigh][offsetLow] */
offset = *ppos & 0xffff;
/* explicitly reject invalid address 0 to catch cp and cat */
- if (i2c_addr == 0) {
- ret = -EINVAL;
- goto _return;
- }
+ if (i2c_addr == 0)
+ return -EINVAL;
buff = kmalloc(count, GFP_KERNEL);
- if (!buff) {
- ret = -ENOMEM;
- goto _return;
- }
+ if (!buff)
+ return -ENOMEM;
total_read = i2c_read(ppd, target, i2c_addr, offset, buff, count);
if (total_read < 0) {
_free:
kfree(buff);
- _return:
- rcu_read_unlock();
return ret;
}
int ret;
int total_written;
- rcu_read_lock();
- if (*ppos + count > QSFP_PAGESIZE * 4) { /* base page + page00-page03 */
- ret = -EINVAL;
- goto _return;
- }
+ if (*ppos + count > QSFP_PAGESIZE * 4) /* base page + page00-page03 */
+ return -EINVAL;
ppd = private2ppd(file);
buff = kmalloc(count, GFP_KERNEL);
- if (!buff) {
- ret = -ENOMEM;
- goto _return;
- }
+ if (!buff)
+ return -ENOMEM;
ret = copy_from_user(buff, buf, count);
if (ret > 0) {
ret = -EFAULT;
goto _free;
}
-
total_written = qsfp_write(ppd, target, *ppos, buff, count);
if (total_written < 0) {
ret = total_written;
_free:
kfree(buff);
- _return:
- rcu_read_unlock();
return ret;
}
int ret;
int total_read;
- rcu_read_lock();
if (*ppos + count > QSFP_PAGESIZE * 4) { /* base page + page00-page03 */
ret = -EINVAL;
goto _return;
_free:
kfree(buff);
_return:
- rcu_read_unlock();
return ret;
}
debugfs_remove_recursive(ibd->hfi1_ibdev_dbg);
out:
ibd->hfi1_ibdev_dbg = NULL;
- synchronize_rcu();
}
/*
};
static void *_driver_stats_names_seq_start(struct seq_file *s, loff_t *pos)
-__acquires(RCU)
{
- rcu_read_lock();
if (*pos >= ARRAY_SIZE(hfi1_statnames))
return NULL;
return pos;
}
static void _driver_stats_names_seq_stop(struct seq_file *s, void *v)
-__releases(RCU)
{
- rcu_read_unlock();
}
static int _driver_stats_names_seq_show(struct seq_file *s, void *v)
DEBUGFS_FILE_OPS(driver_stats_names);
static void *_driver_stats_seq_start(struct seq_file *s, loff_t *pos)
-__acquires(RCU)
{
- rcu_read_lock();
if (*pos >= ARRAY_SIZE(hfi1_statnames))
return NULL;
return pos;
}
static void _driver_stats_seq_stop(struct seq_file *s, void *v)
-__releases(RCU)
{
- rcu_read_unlock();
}
static u64 hfi1_sps_ints(void)
}
static inline int set_armed_to_active(struct hfi1_ctxtdata *rcd,
- struct hfi1_packet packet,
+ struct hfi1_packet *packet,
struct hfi1_devdata *dd)
{
struct work_struct *lsaw = &rcd->ppd->linkstate_active_work;
- struct hfi1_message_header *hdr = hfi1_get_msgheader(packet.rcd->dd,
- packet.rhf_addr);
+ struct hfi1_message_header *hdr = hfi1_get_msgheader(packet->rcd->dd,
+ packet->rhf_addr);
+ u8 etype = rhf_rcv_type(packet->rhf);
- if (hdr2sc(hdr, packet.rhf) != 0xf) {
+ if (etype == RHF_RCV_TYPE_IB && hdr2sc(hdr, packet->rhf) != 0xf) {
int hwstate = read_logical_state(dd);
if (hwstate != LSTATE_ACTIVE) {
/* Auto activate link on non-SC15 packet receive */
if (unlikely(rcd->ppd->host_link_state ==
HLS_UP_ARMED) &&
- set_armed_to_active(rcd, packet, dd))
+ set_armed_to_active(rcd, &packet, dd))
goto bail;
last = process_rcv_packet(&packet, thread);
}
if (fd) {
fd->rec_cpu_num = -1; /* no cpu affinity by default */
fd->mm = current->mm;
+ atomic_inc(&fd->mm->mm_count);
}
fp->private_data = fd;
ret = assign_ctxt(fp, &uinfo);
if (ret < 0)
return ret;
- setup_ctxt(fp);
+ ret = setup_ctxt(fp);
if (ret)
return ret;
ret = user_init(fp);
mutex_unlock(&hfi1_mutex);
hfi1_free_ctxtdata(dd, uctxt);
done:
+ mmdrop(fdata->mm);
kobject_put(&dd->kobj);
kfree(fdata);
return 0;
struct work_struct freeze_work;
struct work_struct link_downgrade_work;
struct work_struct link_bounce_work;
+ struct delayed_work start_link_work;
/* host link state variables */
struct mutex hls_lock;
u32 host_link_state;
u8 linkinit_reason;
u8 local_tx_rate; /* rate given to 8051 firmware */
u8 last_pstate; /* info only */
+ u8 qsfp_retry_count;
/* placeholders for IB MAD packet settings */
u8 overrun_threshold;
((!!(rhf_dc_info(rhf))) << 4);
}
+#define HFI1_JKEY_WIDTH 16
+#define HFI1_JKEY_MASK (BIT(16) - 1)
+#define HFI1_ADMIN_JKEY_RANGE 32
+
+/*
+ * J_KEYs are split and allocated in the following groups:
+ * 0 - 31 - users with administrator privileges
+ * 32 - 63 - kernel protocols using KDETH packets
+ * 64 - 65535 - all other users using KDETH packets
+ */
static inline u16 generate_jkey(kuid_t uid)
{
- return from_kuid(current_user_ns(), uid) & 0xffff;
+ u16 jkey = from_kuid(current_user_ns(), uid) & HFI1_JKEY_MASK;
+
+ if (capable(CAP_SYS_ADMIN))
+ jkey &= HFI1_ADMIN_JKEY_RANGE - 1;
+ else if (jkey < 64)
+ jkey |= BIT(HFI1_JKEY_WIDTH - 1);
+
+ return jkey;
}
/*
struct hfi1_devdata *hfi1_init_dd(struct pci_dev *,
const struct pci_device_id *);
void hfi1_free_devdata(struct hfi1_devdata *);
-void cc_state_reclaim(struct rcu_head *rcu);
struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, size_t extra);
/* LED beaconing functions */
extern unsigned int hfi1_cu;
extern unsigned int user_credit_return_threshold;
extern int num_user_contexts;
-extern unsigned n_krcvqs;
+extern unsigned long n_krcvqs;
extern uint krcvqs[];
extern int krcvqsset;
extern uint kdeth_qp;
MODULE_PARM_DESC(krcvqs, "Array of the number of non-control kernel receive queues by VL");
/* computed based on above array */
-unsigned n_krcvqs;
+unsigned long n_krcvqs;
static unsigned hfi1_rcvarr_split = 25;
module_param_named(rcvarr_split, hfi1_rcvarr_split, uint, S_IRUGO);
INIT_WORK(&ppd->link_downgrade_work, handle_link_downgrade);
INIT_WORK(&ppd->sma_message_work, handle_sma_message);
INIT_WORK(&ppd->link_bounce_work, handle_link_bounce);
+ INIT_DELAYED_WORK(&ppd->start_link_work, handle_start_link);
INIT_WORK(&ppd->linkstate_active_work, receive_interrupt_work);
INIT_WORK(&ppd->qsfp_info.qsfp_work, qsfp_event);
spin_unlock(&ppd->cc_state_lock);
if (cc_state)
- call_rcu(&cc_state->rcu, cc_state_reclaim);
+ kfree_rcu(cc_state, rcu);
}
free_credit_return(dd);
u32 len = OPA_AM_CI_LEN(am) + 1;
int ret;
+ if (dd->pport->port_type != PORT_TYPE_QSFP) {
+ smp->status |= IB_SMP_INVALID_FIELD;
+ return reply((struct ib_mad_hdr *)smp);
+ }
+
#define __CI_PAGE_SIZE BIT(7) /* 128 bytes */
#define __CI_PAGE_MASK ~(__CI_PAGE_SIZE - 1)
#define __CI_PAGE_NUM(a) ((a) & __CI_PAGE_MASK)
u8 lq, num_vls;
u8 res_lli, res_ler;
u64 port_mask;
- unsigned long port_num;
+ u8 port_num;
unsigned long vl;
u32 vl_select_mask;
int vfi;
*/
port_mask = be64_to_cpu(req->port_select_mask[3]);
port_num = find_first_bit((unsigned long *)&port_mask,
- sizeof(port_mask));
+ sizeof(port_mask) * 8);
- if ((u8)port_num != port) {
+ if (port_num != port) {
pmp->mad_hdr.status |= IB_SMP_INVALID_FIELD;
return reply((struct ib_mad_hdr *)pmp);
}
*/
port_mask = be64_to_cpu(req->port_select_mask[3]);
port_num = find_first_bit((unsigned long *)&port_mask,
- sizeof(port_mask));
+ sizeof(port_mask) * 8);
if (port_num != port) {
pmp->mad_hdr.status |= IB_SMP_INVALID_FIELD;
*/
port_mask = be64_to_cpu(req->port_select_mask[3]);
port_num = find_first_bit((unsigned long *)&port_mask,
- sizeof(port_mask));
+ sizeof(port_mask) * 8);
if (port_num != port) {
pmp->mad_hdr.status |= IB_SMP_INVALID_FIELD;
*/
port_mask = be64_to_cpu(req->port_select_mask[3]);
port_num = find_first_bit((unsigned long *)&port_mask,
- sizeof(port_mask));
+ sizeof(port_mask) * 8);
if (port_num != port) {
pmp->mad_hdr.status |= IB_SMP_INVALID_FIELD;
spin_unlock(&ppd->cc_state_lock);
- call_rcu(&old_cc_state->rcu, cc_state_reclaim);
+ kfree_rcu(old_cc_state, rcu);
}
static int __subn_set_opa_cong_setting(struct opa_smp *smp, u32 am, u8 *data,
return reply((struct ib_mad_hdr *)smp);
}
-void cc_state_reclaim(struct rcu_head *rcu)
-{
- struct cc_state *cc_state = container_of(rcu, struct cc_state, rcu);
-
- kfree(cc_state);
-}
-
static int __subn_set_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data,
struct ib_device *ibdev, u8 port,
u32 *resp_len)
read_extra_bytes(pbuf, from, to_fill);
from += to_fill;
nbytes -= to_fill;
+ /* may not be enough valid bytes left to align */
+ if (extra > nbytes)
+ extra = nbytes;
/* ...now write carry */
dest = pbuf->start + (pbuf->qw_written * sizeof(u64));
read_low_bytes(pbuf, from, extra);
from += extra;
nbytes -= extra;
+ /*
+ * If no bytes are left, return early - we are done.
+ * NOTE: This short-circuit is *required* because
+ * "extra" may have been reduced in size and "from"
+ * is not aligned, as required when leaving this
+ * if block.
+ */
+ if (nbytes == 0)
+ return;
}
/* at this point, from is QW aligned */
iter->dev = dev;
iter->specials = dev->rdi.ibdev.phys_port_cnt * 2;
- if (qp_iter_next(iter)) {
- kfree(iter);
- return NULL;
- }
return iter;
}
u8 *data)
{
struct hfi1_pportdata *ppd;
- u32 excess_len = 0;
- int ret = 0;
+ u32 excess_len = len;
+ int ret = 0, offset = 0;
if (port_num > dd->num_pports || port_num < 1) {
dd_dev_info(dd, "%s: Invalid port number %d\n",
}
memcpy(data, &ppd->qsfp_info.cache[addr], len);
+
+ if (addr <= QSFP_MONITOR_VAL_END &&
+ (addr + len) >= QSFP_MONITOR_VAL_START) {
+ /* Overlap with the dynamic channel monitor range */
+ if (addr < QSFP_MONITOR_VAL_START) {
+ if (addr + len <= QSFP_MONITOR_VAL_END)
+ len = addr + len - QSFP_MONITOR_VAL_START;
+ else
+ len = QSFP_MONITOR_RANGE;
+ offset = QSFP_MONITOR_VAL_START - addr;
+ addr = QSFP_MONITOR_VAL_START;
+ } else if (addr == QSFP_MONITOR_VAL_START) {
+ offset = 0;
+ if (addr + len > QSFP_MONITOR_VAL_END)
+ len = QSFP_MONITOR_RANGE;
+ } else {
+ offset = 0;
+ if (addr + len > QSFP_MONITOR_VAL_END)
+ len = QSFP_MONITOR_VAL_END - addr + 1;
+ }
+ /* Refresh the values of the dynamic monitors from the cable */
+ ret = one_qsfp_read(ppd, dd->hfi1_id, addr, data + offset, len);
+ if (ret != len) {
+ ret = -EAGAIN;
+ goto set_zeroes;
+ }
+ }
+
return 0;
set_zeroes:
/* Defined fields that Intel requires of qualified cables */
/* Byte 0 is Identifier, not checked */
/* Byte 1 is reserved "status MSB" */
+#define QSFP_MONITOR_VAL_START 22
+#define QSFP_MONITOR_VAL_END 81
+#define QSFP_MONITOR_RANGE (QSFP_MONITOR_VAL_END - QSFP_MONITOR_VAL_START + 1)
#define QSFP_TX_CTRL_BYTE_OFFS 86
#define QSFP_PWR_CTRL_BYTE_OFFS 93
#define QSFP_CDR_CTRL_BYTE_OFFS 98
#define KDETH_HCRC_LOWER_SHIFT 24
#define KDETH_HCRC_LOWER_MASK 0xff
+#define AHG_KDETH_INTR_SHIFT 12
+
#define PBC2LRH(x) ((((x) & 0xfff) << 2) - 4)
#define LRH2PBC(x) ((((x) >> 2) + 1) & 0xfff)
/* Clear KDETH.SH on last packet */
if (unlikely(tx->flags & TXREQ_FLAGS_REQ_LAST_PKT)) {
val |= cpu_to_le16(KDETH_GET(hdr->kdeth.ver_tid_offset,
- INTR) >> 16);
+ INTR) <<
+ AHG_KDETH_INTR_SHIFT);
val &= cpu_to_le16(~(1U << 13));
AHG_HEADER_SET(req->ahg, diff, 7, 16, 14, val);
} else {
struct i40e_client *client;
struct i40iw_hw hw;
struct i40iw_cm_core cm_core;
- unsigned long *mem_resources;
+ u8 *mem_resources;
unsigned long *allocated_qps;
unsigned long *allocated_cqs;
unsigned long *allocated_mrs;
*next = resource_num + 1;
if (*next == max_resources)
*next = 0;
- spin_unlock_irqrestore(&iwdev->resource_lock, flags);
*req_resource_num = resource_num;
+ spin_unlock_irqrestore(&iwdev->resource_lock, flags);
return 0;
}
buf += hdr_len;
}
- if (pd_len)
- memcpy(buf, pdata->addr, pd_len);
+ if (pdata && pdata->addr)
+ memcpy(buf, pdata->addr, pdata->size);
atomic_set(&sqbuf->refcount, 1);
return 0;
}
-/**
- * i40iw_loopback_nop - Send a nop
- * @qp: associated hw qp
- */
-static void i40iw_loopback_nop(struct i40iw_sc_qp *qp)
-{
- u64 *wqe;
- u64 header;
-
- wqe = qp->qp_uk.sq_base->elem;
- set_64bit_val(wqe, 0, 0);
- set_64bit_val(wqe, 8, 0);
- set_64bit_val(wqe, 16, 0);
-
- header = LS_64(I40IWQP_OP_NOP, I40IWQPSQ_OPCODE) |
- LS_64(0, I40IWQPSQ_SIGCOMPL) |
- LS_64(qp->qp_uk.swqe_polarity, I40IWQPSQ_VALID);
- set_64bit_val(wqe, 24, header);
-}
-
/**
* i40iw_qp_disconnect - free qp and close cm
* @iwqp: associate qp for the connection
} else {
if (iwqp->page)
iwqp->sc_qp.qp_uk.sq_base = kmap(iwqp->page);
- i40iw_loopback_nop(&iwqp->sc_qp);
+ dev->iw_priv_qp_ops->qp_send_lsmm(&iwqp->sc_qp, NULL, 0, 0);
}
if (iwqp->page)
info.dont_send_fin = false;
if (iwqp->sc_qp.term_flags && (state == I40IW_QP_STATE_ERROR))
info.reset_tcp_conn = true;
+ iwqp->hw_iwarp_state = state;
i40iw_hw_modify_qp(iwqp->iwdev, iwqp, &info, 0);
}
.notifier_call = i40iw_net_event
};
-static int i40iw_notifiers_registered;
+static atomic_t i40iw_notifiers_registered;
/**
* i40iw_find_i40e_handler - find a handler given a client info
*/
static void i40iw_register_notifiers(void)
{
- if (!i40iw_notifiers_registered) {
+ if (atomic_inc_return(&i40iw_notifiers_registered) == 1) {
register_inetaddr_notifier(&i40iw_inetaddr_notifier);
register_inet6addr_notifier(&i40iw_inetaddr6_notifier);
register_netevent_notifier(&i40iw_net_notifier);
}
- i40iw_notifiers_registered++;
}
/**
i40iw_del_macip_entry(iwdev, (u8)iwdev->mac_ip_table_idx);
/* fallthrough */
case INET_NOTIFIER:
- if (i40iw_notifiers_registered > 0) {
- i40iw_notifiers_registered--;
+ if (!atomic_dec_return(&i40iw_notifiers_registered)) {
unregister_netevent_notifier(&i40iw_net_notifier);
unregister_inetaddr_notifier(&i40iw_inetaddr_notifier);
unregister_inet6addr_notifier(&i40iw_inetaddr6_notifier);
enum i40iw_status_code status;
struct i40iw_handler *hdl;
+ hdl = i40iw_find_netdev(ldev->netdev);
+ if (hdl)
+ return 0;
+
hdl = kzalloc(sizeof(*hdl), GFP_KERNEL);
if (!hdl)
return -ENOMEM;
{
if (!mem)
return I40IW_ERR_PARAM;
+ /*
+ * mem->va points to the parent of mem, so both mem and mem->va
+ * can not be touched once mem->va is freed
+ */
kfree(mem->va);
- mem->va = NULL;
return 0;
}
return &iwqp->ibqp;
error:
i40iw_free_qp_resources(iwdev, iwqp, qp_num);
- kfree(mem);
return ERR_PTR(err_code);
}
}
if (iwpbl->pbl_allocated)
i40iw_free_pble(iwdev->pble_rsrc, palloc);
- kfree(iwpbl->iwmr);
- iwpbl->iwmr = NULL;
+ kfree(iwmr);
return 0;
}
checksum == cpu_to_be16(0xffff);
}
-static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct ib_wc *wc,
- unsigned tail, struct mlx4_cqe *cqe, int is_eth)
+static void use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct ib_wc *wc,
+ unsigned tail, struct mlx4_cqe *cqe, int is_eth)
{
struct mlx4_ib_proxy_sqp_hdr *hdr;
wc->slid = be16_to_cpu(hdr->tun.slid_mac_47_32);
wc->sl = (u8) (be16_to_cpu(hdr->tun.sl_vid) >> 12);
}
-
- return 0;
}
static void mlx4_ib_qp_sw_comp(struct mlx4_ib_qp *qp, int num_entries,
is_error = (cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) ==
MLX4_CQE_OPCODE_ERROR;
- if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == MLX4_OPCODE_NOP &&
- is_send)) {
- pr_warn("Completion for NOP opcode detected!\n");
- return -EINVAL;
- }
-
/* Resize CQ in progress */
if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == MLX4_CQE_OPCODE_RESIZE)) {
if (cq->resize_buf) {
*/
mqp = __mlx4_qp_lookup(to_mdev(cq->ibcq.device)->dev,
be32_to_cpu(cqe->vlan_my_qpn));
- if (unlikely(!mqp)) {
- pr_warn("CQ %06x with entry for unknown QPN %06x\n",
- cq->mcq.cqn, be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_QPN_MASK);
- return -EINVAL;
- }
-
*cur_qp = to_mibqp(mqp);
}
/* SRQ is also in the radix tree */
msrq = mlx4_srq_lookup(to_mdev(cq->ibcq.device)->dev,
srq_num);
- if (unlikely(!msrq)) {
- pr_warn("CQ %06x with entry for unknown SRQN %06x\n",
- cq->mcq.cqn, srq_num);
- return -EINVAL;
- }
}
if (is_send) {
if (mlx4_is_mfunc(to_mdev(cq->ibcq.device)->dev)) {
if ((*cur_qp)->mlx4_ib_qp_type &
(MLX4_IB_QPT_PROXY_SMI_OWNER |
- MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI))
- return use_tunnel_data(*cur_qp, cq, wc, tail,
- cqe, is_eth);
+ MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI)) {
+ use_tunnel_data(*cur_qp, cq, wc, tail, cqe,
+ is_eth);
+ return 0;
+ }
}
wc->slid = be16_to_cpu(cqe->rlid);
struct mlx4_ib_qp *cur_qp = NULL;
unsigned long flags;
int npolled;
- int err = 0;
struct mlx4_ib_dev *mdev = to_mdev(cq->ibcq.device);
spin_lock_irqsave(&cq->lock, flags);
}
for (npolled = 0; npolled < num_entries; ++npolled) {
- err = mlx4_ib_poll_one(cq, &cur_qp, wc + npolled);
- if (err)
+ if (mlx4_ib_poll_one(cq, &cur_qp, wc + npolled))
break;
}
out:
spin_unlock_irqrestore(&cq->lock, flags);
- if (err == 0 || err == -EAGAIN)
- return npolled;
- else
- return err;
+ return npolled;
}
int mlx4_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
/* Generate GUID changed event */
if (changed_attr & MLX4_EQ_PORT_INFO_GID_PFX_CHANGE_MASK) {
+ if (mlx4_is_master(dev->dev)) {
+ union ib_gid gid;
+ int err = 0;
+
+ if (!eqe->event.port_mgmt_change.params.port_info.gid_prefix)
+ err = __mlx4_ib_query_gid(&dev->ib_dev, port, 0, &gid, 1);
+ else
+ gid.global.subnet_prefix =
+ eqe->event.port_mgmt_change.params.port_info.gid_prefix;
+ if (err) {
+ pr_warn("Could not change QP1 subnet prefix for port %d: query_gid error (%d)\n",
+ port, err);
+ } else {
+ pr_debug("Changing QP1 subnet prefix for port %d. old=0x%llx. new=0x%llx\n",
+ port,
+ (u64)atomic64_read(&dev->sriov.demux[port - 1].subnet_prefix),
+ be64_to_cpu(gid.global.subnet_prefix));
+ atomic64_set(&dev->sriov.demux[port - 1].subnet_prefix,
+ be64_to_cpu(gid.global.subnet_prefix));
+ }
+ }
mlx4_ib_dispatch_event(dev, port, IB_EVENT_GID_CHANGE);
/*if master, notify all slaves*/
if (mlx4_is_master(dev->dev))
if (err)
goto demux_err;
dev->sriov.demux[i].guid_cache[0] = gid.global.interface_id;
+ atomic64_set(&dev->sriov.demux[i].subnet_prefix,
+ be64_to_cpu(gid.global.subnet_prefix));
err = alloc_pv_object(dev, mlx4_master_func_num(dev->dev), i + 1,
&dev->sriov.sqps[i]);
if (err)
bool per_port = !!(ibdev->dev->caps.flags2 &
MLX4_DEV_CAP_FLAG2_DIAG_PER_PORT);
+ if (mlx4_is_slave(ibdev->dev))
+ return 0;
+
for (i = 0; i < MLX4_DIAG_COUNTERS_TYPES; i++) {
/* i == 1 means we are building port counters */
if (i && !per_port)
if (!group->members[i])
leave_state |= (1 << i);
- return leave_state & (group->rec.scope_join_state & 7);
+ return leave_state & (group->rec.scope_join_state & 0xf);
}
static int join_group(struct mcast_group *group, int slave, u8 join_mask)
} else
mcg_warn_group(group, "DRIVER BUG\n");
} else if (group->state == MCAST_LEAVE_SENT) {
- if (group->rec.scope_join_state & 7)
- group->rec.scope_join_state &= 0xf8;
+ if (group->rec.scope_join_state & 0xf)
+ group->rec.scope_join_state &= 0xf0;
group->state = MCAST_IDLE;
mutex_unlock(&group->lock);
if (release_group(group, 1))
static int handle_join_req(struct mcast_group *group, u8 join_mask,
struct mcast_req *req)
{
- u8 group_join_state = group->rec.scope_join_state & 7;
+ u8 group_join_state = group->rec.scope_join_state & 0xf;
int ref = 0;
u16 status;
struct ib_sa_mcmember_data *sa_data = (struct ib_sa_mcmember_data *)req->sa_mad.data;
u8 cur_join_state;
resp_join_state = ((struct ib_sa_mcmember_data *)
- group->response_sa_mad.data)->scope_join_state & 7;
- cur_join_state = group->rec.scope_join_state & 7;
+ group->response_sa_mad.data)->scope_join_state & 0xf;
+ cur_join_state = group->rec.scope_join_state & 0xf;
if (method == IB_MGMT_METHOD_GET_RESP) {
/* successfull join */
req = list_first_entry(&group->pending_list, struct mcast_req,
group_list);
sa_data = (struct ib_sa_mcmember_data *)req->sa_mad.data;
- req_join_state = sa_data->scope_join_state & 0x7;
+ req_join_state = sa_data->scope_join_state & 0xf;
/* For a leave request, we will immediately answer the VF, and
* update our internal counters. The actual leave will be sent
struct workqueue_struct *wq;
struct workqueue_struct *ud_wq;
spinlock_t ud_lock;
- __be64 subnet_prefix;
+ atomic64_t subnet_prefix;
__be64 guid_cache[128];
struct mlx4_ib_dev *dev;
/* the following lock protects both mcg_table and mcg_mgid0_list */
sqp->ud_header.grh.flow_label =
ah->av.ib.sl_tclass_flowlabel & cpu_to_be32(0xfffff);
sqp->ud_header.grh.hop_limit = ah->av.ib.hop_limit;
- if (is_eth)
+ if (is_eth) {
memcpy(sqp->ud_header.grh.source_gid.raw, sgid.raw, 16);
- else {
- if (mlx4_is_mfunc(to_mdev(ib_dev)->dev)) {
- /* When multi-function is enabled, the ib_core gid
- * indexes don't necessarily match the hw ones, so
- * we must use our own cache */
- sqp->ud_header.grh.source_gid.global.subnet_prefix =
- to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1].
- subnet_prefix;
- sqp->ud_header.grh.source_gid.global.interface_id =
- to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1].
- guid_cache[ah->av.ib.gid_index];
- } else
- ib_get_cached_gid(ib_dev,
- be32_to_cpu(ah->av.ib.port_pd) >> 24,
- ah->av.ib.gid_index,
- &sqp->ud_header.grh.source_gid, NULL);
+ } else {
+ if (mlx4_is_mfunc(to_mdev(ib_dev)->dev)) {
+ /* When multi-function is enabled, the ib_core gid
+ * indexes don't necessarily match the hw ones, so
+ * we must use our own cache
+ */
+ sqp->ud_header.grh.source_gid.global.subnet_prefix =
+ cpu_to_be64(atomic64_read(&(to_mdev(ib_dev)->sriov.
+ demux[sqp->qp.port - 1].
+ subnet_prefix)));
+ sqp->ud_header.grh.source_gid.global.interface_id =
+ to_mdev(ib_dev)->sriov.demux[sqp->qp.port - 1].
+ guid_cache[ah->av.ib.gid_index];
+ } else {
+ ib_get_cached_gid(ib_dev,
+ be32_to_cpu(ah->av.ib.port_pd) >> 24,
+ ah->av.ib.gid_index,
+ &sqp->ud_header.grh.source_gid, NULL);
+ }
}
memcpy(sqp->ud_header.grh.destination_gid.raw,
ah->av.ib.dgid, 16);
* from the table.
*/
mqp = __mlx5_qp_lookup(dev->mdev, qpn);
- if (unlikely(!mqp)) {
- mlx5_ib_warn(dev, "CQE@CQ %06x for unknown QPN %6x\n",
- cq->mcq.cqn, qpn);
- return -EINVAL;
- }
-
*cur_qp = to_mibqp(mqp);
}
read_lock(&dev->mdev->priv.mkey_table.lock);
mmkey = __mlx5_mr_lookup(dev->mdev,
mlx5_base_mkey(be32_to_cpu(sig_err_cqe->mkey)));
- if (unlikely(!mmkey)) {
- read_unlock(&dev->mdev->priv.mkey_table.lock);
- mlx5_ib_warn(dev, "CQE@CQ %06x for unknown MR %6x\n",
- cq->mcq.cqn, be32_to_cpu(sig_err_cqe->mkey));
- return -EINVAL;
- }
-
mr = to_mibmr(mmkey);
get_sig_err_item(sig_err_cqe, &mr->sig->err_item);
mr->sig->sig_err_exists = true;
unsigned long flags;
int soft_polled = 0;
int npolled;
- int err = 0;
spin_lock_irqsave(&cq->lock, flags);
if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
soft_polled = poll_soft_wc(cq, num_entries, wc);
for (npolled = 0; npolled < num_entries - soft_polled; npolled++) {
- err = mlx5_poll_one(cq, &cur_qp, wc + soft_polled + npolled);
- if (err)
+ if (mlx5_poll_one(cq, &cur_qp, wc + soft_polled + npolled))
break;
}
out:
spin_unlock_irqrestore(&cq->lock, flags);
- if (err == 0 || err == -EAGAIN)
- return soft_polled + npolled;
- else
- return err;
+ return soft_polled + npolled;
}
int mlx5_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
#include <linux/pci.h>
#include <linux/dma-mapping.h>
#include <linux/slab.h>
-#include <linux/io-mapping.h>
#if defined(CONFIG_X86)
#include <asm/pat.h>
#endif
static int mlx5_use_mad_ifc(struct mlx5_ib_dev *dev)
{
- return !MLX5_CAP_GEN(dev->mdev, ib_virt);
+ if (MLX5_CAP_GEN(dev->mdev, port_type) == MLX5_CAP_PORT_TYPE_IB)
+ return !MLX5_CAP_GEN(dev->mdev, ib_virt);
+ return 0;
}
enum {
dmac_47_16),
ib_spec->eth.val.dst_mac);
+ ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_c,
+ smac_47_16),
+ ib_spec->eth.mask.src_mac);
+ ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_v,
+ smac_47_16),
+ ib_spec->eth.val.src_mac);
+
if (ib_spec->eth.mask.vlan_tag) {
MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
vlan_tag, 1);
int domain)
{
struct mlx5_ib_dev *dev = to_mdev(qp->device);
+ struct mlx5_ib_qp *mqp = to_mqp(qp);
struct mlx5_ib_flow_handler *handler = NULL;
struct mlx5_flow_destination *dst = NULL;
struct mlx5_ib_flow_prio *ft_prio;
}
dst->type = MLX5_FLOW_DESTINATION_TYPE_TIR;
- dst->tir_num = to_mqp(qp)->raw_packet_qp.rq.tirn;
+ if (mqp->flags & MLX5_IB_QP_RSS)
+ dst->tir_num = mqp->rss_qp.tirn;
+ else
+ dst->tir_num = mqp->raw_packet_qp.rq.tirn;
if (flow_attr->type == IB_FLOW_ATTR_NORMAL) {
if (flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP) {
addr = addr >> page_shift;
tmp = (unsigned long)addr;
- m = find_first_bit(&tmp, sizeof(tmp));
+ m = find_first_bit(&tmp, BITS_PER_LONG);
skip = 1 << m;
mask = skip - 1;
i = 0;
for (k = 0; k < len; k++) {
if (!(i & mask)) {
tmp = (unsigned long)pfn;
- m = min_t(unsigned long, m, find_first_bit(&tmp, sizeof(tmp)));
+ m = min_t(unsigned long, m, find_first_bit(&tmp, BITS_PER_LONG));
skip = 1 << m;
mask = skip - 1;
base = pfn;
} else {
if (base + p != pfn) {
tmp = (unsigned long)p;
- m = find_first_bit(&tmp, sizeof(tmp));
+ m = find_first_bit(&tmp, BITS_PER_LONG);
skip = 1 << m;
mask = skip - 1;
base = pfn;
/* QP uses 1 as its source QP number */
MLX5_IB_QP_SQPN_QP1 = 1 << 6,
MLX5_IB_QP_CAP_SCATTER_FCS = 1 << 7,
+ MLX5_IB_QP_RSS = 1 << 8,
};
struct mlx5_umr_wr {
kvfree(in);
/* qpn is reserved for that QP */
qp->trans_qp.base.mqp.qpn = 0;
+ qp->flags |= MLX5_IB_QP_RSS;
return 0;
err:
struct ib_send_wr *wr, unsigned *idx,
int *size, int nreq)
{
- int err = 0;
-
- if (unlikely(mlx5_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq))) {
- err = -ENOMEM;
- return err;
- }
+ if (unlikely(mlx5_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq)))
+ return -ENOMEM;
*idx = qp->sq.cur_post & (qp->sq.wqe_cnt - 1);
*seg = mlx5_get_send_wqe(qp, *idx);
*seg += sizeof(**ctrl);
*size = sizeof(**ctrl) / 16;
- return err;
+ return 0;
}
static void finish_wqe(struct mlx5_ib_qp *qp,
num_sge = wr->num_sge;
if (unlikely(num_sge > qp->sq.max_gs)) {
mlx5_ib_warn(dev, "\n");
- err = -ENOMEM;
+ err = -EINVAL;
*bad_wr = wr;
goto out;
}
attr->max_srq =
(rsp->max_srq_rpir_qps & OCRDMA_MBX_QUERY_CFG_MAX_SRQ_MASK) >>
OCRDMA_MBX_QUERY_CFG_MAX_SRQ_OFFSET;
- attr->max_send_sge = ((rsp->max_write_send_sge &
+ attr->max_send_sge = ((rsp->max_recv_send_sge &
OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_MASK) >>
OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_SHIFT);
- attr->max_recv_sge = (rsp->max_write_send_sge &
- OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_MASK) >>
- OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_SHIFT;
+ attr->max_recv_sge = (rsp->max_recv_send_sge &
+ OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_MASK) >>
+ OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_SHIFT;
attr->max_srq_sge = (rsp->max_srq_rqe_sge &
OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_MASK) >>
OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_OFFSET;
- attr->max_rdma_sge = (rsp->max_write_send_sge &
- OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_MASK) >>
- OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_SHIFT;
+ attr->max_rdma_sge = (rsp->max_wr_rd_sge &
+ OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_MASK) >>
+ OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_SHIFT;
attr->max_ord_per_qp = (rsp->max_ird_ord_per_qp &
OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_MASK) >>
OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_SHIFT;
OCRDMA_MBX_QUERY_CFG_L3_TYPE_MASK = 0x18,
OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_SHIFT = 0,
OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_MASK = 0xFFFF,
- OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_SHIFT = 16,
- OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_MASK = 0xFFFF <<
- OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_SHIFT,
+ OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_SHIFT = 16,
+ OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_MASK = 0xFFFF <<
+ OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_SHIFT,
OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_SHIFT = 0,
OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_MASK = 0xFFFF,
OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_OFFSET = 0,
OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_MASK = 0xFFFF <<
OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_OFFSET,
+ OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_SHIFT = 0,
+ OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_MASK = 0xFFFF,
};
struct ocrdma_mbx_query_config {
struct ocrdma_mbx_rsp rsp;
u32 qp_srq_cq_ird_ord;
u32 max_pd_ca_ack_delay;
- u32 max_write_send_sge;
+ u32 max_recv_send_sge;
u32 max_ird_ord_per_qp;
u32 max_shared_ird_ord;
u32 max_mr;
u32 max_wqes_rqes_per_q;
u32 max_cq_cqes_per_cq;
u32 max_srq_rqe_sge;
+ u32 max_wr_rd_sge;
+ u32 ird_pgsz_num_pages;
};
struct ocrdma_fw_ver_rsp {
IB_DEVICE_SYS_IMAGE_GUID |
IB_DEVICE_LOCAL_DMA_LKEY |
IB_DEVICE_MEM_MGT_EXTENSIONS;
- attr->max_sge = dev->attr.max_send_sge;
- attr->max_sge_rd = attr->max_sge;
+ attr->max_sge = min(dev->attr.max_send_sge, dev->attr.max_recv_sge);
+ attr->max_sge_rd = dev->attr.max_rdma_sge;
attr->max_cq = dev->attr.max_cq;
attr->max_cqe = dev->attr.max_cqe;
attr->max_mr = dev->attr.max_mr;
DEBUGFS_FILE(ctx_stats)
static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos)
+ __acquires(RCU)
{
struct qib_qp_iter *iter;
loff_t n = *pos;
- rcu_read_lock();
iter = qib_qp_iter_init(s->private);
+
+ /* stop calls rcu_read_unlock */
+ rcu_read_lock();
+
if (!iter)
return NULL;
- while (n--) {
+ do {
if (qib_qp_iter_next(iter)) {
kfree(iter);
return NULL;
}
- }
+ } while (n--);
return iter;
}
static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr,
loff_t *pos)
+ __must_hold(RCU)
{
struct qib_qp_iter *iter = iter_ptr;
}
static void _qp_stats_seq_stop(struct seq_file *s, void *iter_ptr)
+ __releases(RCU)
{
rcu_read_unlock();
}
pos = *ppos;
- if (pos != 0) {
- ret = -EINVAL;
- goto bail;
- }
-
- if (count != sizeof(struct qib_flash)) {
- ret = -EINVAL;
- goto bail;
- }
-
- tmp = kmalloc(count, GFP_KERNEL);
- if (!tmp) {
- ret = -ENOMEM;
- goto bail;
- }
+ if (pos != 0 || count != sizeof(struct qib_flash))
+ return -EINVAL;
- if (copy_from_user(tmp, buf, count)) {
- ret = -EFAULT;
- goto bail_tmp;
- }
+ tmp = memdup_user(buf, count);
+ if (IS_ERR(tmp))
+ return PTR_ERR(tmp);
dd = private2dd(file);
if (qib_eeprom_write(dd, pos, tmp, count)) {
bail_tmp:
kfree(tmp);
-
-bail:
return ret;
}
return NULL;
iter->dev = dev;
- if (qib_qp_iter_next(iter)) {
- kfree(iter);
- return NULL;
- }
return iter;
}
return err;
}
- if (pci_register_driver(&usnic_ib_pci_driver)) {
+ err = pci_register_driver(&usnic_ib_pci_driver);
+ if (err) {
usnic_err("Unable to register with PCI\n");
goto out_umem_fini;
}
{
rvt_deinit_mregion(&mr->mr);
rvt_free_lkey(&mr->mr);
- vfree(mr);
+ kfree(mr);
}
/**
free_qpn(&rdi->qp_dev->qpn_table, qp->ibqp.qp_num);
bail_rq_wq:
- vfree(qp->r_rq.wq);
+ if (!qp->ip)
+ vfree(qp->r_rq.wq);
bail_driver_priv:
rdi->driver_f.qp_priv_free(rdi, qp);
return err;
}
- err = rxe_net_init();
+ err = rxe_net_ipv4_init();
if (err) {
- pr_err("rxe: unable to init\n");
+ pr_err("rxe: unable to init ipv4 tunnel\n");
rxe_cache_exit();
- return err;
+ goto exit;
+ }
+
+ err = rxe_net_ipv6_init();
+ if (err) {
+ pr_err("rxe: unable to init ipv6 tunnel\n");
+ rxe_cache_exit();
+ goto exit;
}
+
+ err = register_netdevice_notifier(&rxe_net_notifier);
+ if (err) {
+ pr_err("rxe: Failed to rigister netdev notifier\n");
+ goto exit;
+ }
+
pr_info("rxe: loaded\n");
return 0;
+
+exit:
+ rxe_release_udp_tunnel(recv_sockets.sk4);
+ rxe_release_udp_tunnel(recv_sockets.sk6);
+ return err;
}
static void __exit rxe_module_exit(void)
qp->req.need_retry = 1;
rxe_run_task(&qp->req.task, 1);
}
+
+ if (pkt) {
+ rxe_drop_ref(pkt->qp);
+ kfree_skb(skb);
+ }
+
goto exit;
+
} else {
wqe->status = IB_WC_RETRY_EXC_ERR;
state = COMPST_ERROR;
case COMPST_ERROR:
do_complete(qp, wqe);
rxe_qp_error(qp);
+
+ if (pkt) {
+ rxe_drop_ref(pkt->qp);
+ kfree_skb(skb);
+ }
+
goto exit;
}
}
return sock;
}
-static void rxe_release_udp_tunnel(struct socket *sk)
+void rxe_release_udp_tunnel(struct socket *sk)
{
- udp_tunnel_sock_release(sk);
+ if (sk)
+ udp_tunnel_sock_release(sk);
}
static void prepare_udp_hdr(struct sk_buff *skb, __be16 src_port,
return NOTIFY_OK;
}
-static struct notifier_block rxe_net_notifier = {
+struct notifier_block rxe_net_notifier = {
.notifier_call = rxe_notify,
};
-int rxe_net_init(void)
+int rxe_net_ipv4_init(void)
{
- int err;
-
spin_lock_init(&dev_list_lock);
- recv_sockets.sk6 = rxe_setup_udp_tunnel(&init_net,
- htons(ROCE_V2_UDP_DPORT), true);
- if (IS_ERR(recv_sockets.sk6)) {
- recv_sockets.sk6 = NULL;
- pr_err("rxe: Failed to create IPv6 UDP tunnel\n");
- return -1;
- }
-
recv_sockets.sk4 = rxe_setup_udp_tunnel(&init_net,
- htons(ROCE_V2_UDP_DPORT), false);
+ htons(ROCE_V2_UDP_DPORT), false);
if (IS_ERR(recv_sockets.sk4)) {
- rxe_release_udp_tunnel(recv_sockets.sk6);
recv_sockets.sk4 = NULL;
- recv_sockets.sk6 = NULL;
pr_err("rxe: Failed to create IPv4 UDP tunnel\n");
return -1;
}
- err = register_netdevice_notifier(&rxe_net_notifier);
- if (err) {
- rxe_release_udp_tunnel(recv_sockets.sk6);
- rxe_release_udp_tunnel(recv_sockets.sk4);
- pr_err("rxe: Failed to rigister netdev notifier\n");
- }
-
- return err;
+ return 0;
}
-void rxe_net_exit(void)
+int rxe_net_ipv6_init(void)
{
- if (recv_sockets.sk6)
- rxe_release_udp_tunnel(recv_sockets.sk6);
+#if IS_ENABLED(CONFIG_IPV6)
- if (recv_sockets.sk4)
- rxe_release_udp_tunnel(recv_sockets.sk4);
+ spin_lock_init(&dev_list_lock);
+ recv_sockets.sk6 = rxe_setup_udp_tunnel(&init_net,
+ htons(ROCE_V2_UDP_DPORT), true);
+ if (IS_ERR(recv_sockets.sk6)) {
+ recv_sockets.sk6 = NULL;
+ pr_err("rxe: Failed to create IPv6 UDP tunnel\n");
+ return -1;
+ }
+#endif
+ return 0;
+}
+
+void rxe_net_exit(void)
+{
+ rxe_release_udp_tunnel(recv_sockets.sk6);
+ rxe_release_udp_tunnel(recv_sockets.sk4);
unregister_netdevice_notifier(&rxe_net_notifier);
}
};
extern struct rxe_recv_sockets recv_sockets;
+extern struct notifier_block rxe_net_notifier;
+void rxe_release_udp_tunnel(struct socket *sk);
struct rxe_dev *rxe_net_add(struct net_device *ndev);
-int rxe_net_init(void);
+int rxe_net_ipv4_init(void);
+int rxe_net_ipv6_init(void);
void rxe_net_exit(void);
#endif /* RXE_NET_H */
* make a copy of the skb to post to the next qp
*/
skb_copy = (mce->qp_list.next != &mcg->qp_list) ?
- skb_clone(skb, GFP_KERNEL) : NULL;
+ skb_clone(skb, GFP_ATOMIC) : NULL;
pkt->qp = qp;
rxe_add_ref(qp);
}
static void update_wqe_state(struct rxe_qp *qp,
- struct rxe_send_wqe *wqe,
- struct rxe_pkt_info *pkt,
- enum wqe_state *prev_state)
+ struct rxe_send_wqe *wqe,
+ struct rxe_pkt_info *pkt)
{
- enum wqe_state prev_state_ = wqe->state;
-
if (pkt->mask & RXE_END_MASK) {
if (qp_type(qp) == IB_QPT_RC)
wqe->state = wqe_state_pending;
} else {
wqe->state = wqe_state_processing;
}
-
- *prev_state = prev_state_;
}
-static void update_state(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
- struct rxe_pkt_info *pkt, int payload)
+static void update_wqe_psn(struct rxe_qp *qp,
+ struct rxe_send_wqe *wqe,
+ struct rxe_pkt_info *pkt,
+ int payload)
{
/* number of packets left to send including current one */
int num_pkt = (wqe->dma.resid + payload + qp->mtu - 1) / qp->mtu;
qp->req.psn = (wqe->first_psn + num_pkt) & BTH_PSN_MASK;
else
qp->req.psn = (qp->req.psn + 1) & BTH_PSN_MASK;
+}
- qp->req.opcode = pkt->opcode;
+static void save_state(struct rxe_send_wqe *wqe,
+ struct rxe_qp *qp,
+ struct rxe_send_wqe *rollback_wqe,
+ struct rxe_qp *rollback_qp)
+{
+ rollback_wqe->state = wqe->state;
+ rollback_wqe->first_psn = wqe->first_psn;
+ rollback_wqe->last_psn = wqe->last_psn;
+ rollback_qp->req.psn = qp->req.psn;
+}
+static void rollback_state(struct rxe_send_wqe *wqe,
+ struct rxe_qp *qp,
+ struct rxe_send_wqe *rollback_wqe,
+ struct rxe_qp *rollback_qp)
+{
+ wqe->state = rollback_wqe->state;
+ wqe->first_psn = rollback_wqe->first_psn;
+ wqe->last_psn = rollback_wqe->last_psn;
+ qp->req.psn = rollback_qp->req.psn;
+}
+
+static void update_state(struct rxe_qp *qp, struct rxe_send_wqe *wqe,
+ struct rxe_pkt_info *pkt, int payload)
+{
+ qp->req.opcode = pkt->opcode;
if (pkt->mask & RXE_END_MASK)
qp->req.wqe_index = next_index(qp->sq.queue, qp->req.wqe_index);
int mtu;
int opcode;
int ret;
- enum wqe_state prev_state;
+ struct rxe_qp rollback_qp;
+ struct rxe_send_wqe rollback_wqe;
next_wqe:
if (unlikely(!qp->valid || qp->req.state == QP_STATE_ERROR))
goto err;
}
- update_wqe_state(qp, wqe, &pkt, &prev_state);
+ /*
+ * To prevent a race on wqe access between requester and completer,
+ * wqe members state and psn need to be set before calling
+ * rxe_xmit_packet().
+ * Otherwise, completer might initiate an unjustified retry flow.
+ */
+ save_state(wqe, qp, &rollback_wqe, &rollback_qp);
+ update_wqe_state(qp, wqe, &pkt);
+ update_wqe_psn(qp, wqe, &pkt, payload);
ret = rxe_xmit_packet(to_rdev(qp->ibqp.device), qp, &pkt, skb);
if (ret) {
qp->need_req_skb = 1;
kfree_skb(skb);
- wqe->state = prev_state;
+ rollback_state(wqe, qp, &rollback_wqe, &rollback_qp);
if (ret == -EAGAIN) {
rxe_run_task(&qp->req.task, 1);
free_rd_atomic_resource(qp, res);
rxe_advance_resp_resource(qp);
+ memcpy(SKB_TO_PKT(skb), &ack_pkt, sizeof(skb->cb));
+
res->type = RXE_ATOMIC_MASK;
res->atomic.skb = skb;
- res->first_psn = qp->resp.psn;
- res->last_psn = qp->resp.psn;
- res->cur_psn = qp->resp.psn;
+ res->first_psn = ack_pkt.psn;
+ res->last_psn = ack_pkt.psn;
+ res->cur_psn = ack_pkt.psn;
rc = rxe_xmit_packet(rxe, qp, &ack_pkt, skb_copy);
if (rc) {
rc = RESPST_CLEANUP;
goto out;
}
- bth_set_psn(SKB_TO_PKT(skb_copy),
- qp->resp.psn - 1);
+
/* Resend the result. */
rc = rxe_xmit_packet(to_rdev(qp->ibqp.device), qp,
pkt, skb_copy);
struct ipoib_ah *address, u32 qpn);
void ipoib_reap_ah(struct work_struct *work);
+struct ipoib_path *__path_find(struct net_device *dev, void *gid);
void ipoib_mark_paths_invalid(struct net_device *dev);
void ipoib_flush_paths(struct net_device *dev);
int ipoib_check_sm_sendonly_fullmember_support(struct ipoib_dev_priv *priv);
}
}
+#define QPN_AND_OPTIONS_OFFSET 4
+
static void ipoib_cm_tx_start(struct work_struct *work)
{
struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv,
struct ipoib_neigh *neigh;
struct ipoib_cm_tx *p;
unsigned long flags;
+ struct ipoib_path *path;
int ret;
struct ib_sa_path_rec pathrec;
p = list_entry(priv->cm.start_list.next, typeof(*p), list);
list_del_init(&p->list);
neigh = p->neigh;
+
qpn = IPOIB_QPN(neigh->daddr);
+ /*
+ * As long as the search is with these 2 locks,
+ * path existence indicates its validity.
+ */
+ path = __path_find(dev, neigh->daddr + QPN_AND_OPTIONS_OFFSET);
+ if (!path) {
+ pr_info("%s ignore not valid path %pI6\n",
+ __func__,
+ neigh->daddr + QPN_AND_OPTIONS_OFFSET);
+ goto free_neigh;
+ }
memcpy(&pathrec, &p->path->pathrec, sizeof pathrec);
spin_unlock_irqrestore(&priv->lock, flags);
spin_lock_irqsave(&priv->lock, flags);
if (ret) {
+free_neigh:
neigh = p->neigh;
if (neigh) {
neigh->cm = NULL;
}
if (level == IPOIB_FLUSH_LIGHT) {
+ int oper_up;
ipoib_mark_paths_invalid(dev);
+ /* Set IPoIB operation as down to prevent races between:
+ * the flush flow which leaves MCG and on the fly joins
+ * which can happen during that time. mcast restart task
+ * should deal with join requests we missed.
+ */
+ oper_up = test_and_clear_bit(IPOIB_FLAG_OPER_UP, &priv->flags);
ipoib_mcast_dev_flush(dev);
+ if (oper_up)
+ set_bit(IPOIB_FLAG_OPER_UP, &priv->flags);
ipoib_flush_ah(dev);
}
return -EINVAL;
}
-static struct ipoib_path *__path_find(struct net_device *dev, void *gid)
+struct ipoib_path *__path_find(struct net_device *dev, void *gid)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct rb_node *n = priv->path_tree.rb_node;
INIT_LIST_HEAD(&isert_conn->node);
init_completion(&isert_conn->login_comp);
init_completion(&isert_conn->login_req_comp);
+ init_waitqueue_head(&isert_conn->rem_wait);
kref_init(&isert_conn->kref);
mutex_init(&isert_conn->mutex);
INIT_WORK(&isert_conn->release_work, isert_release_work);
isert_conn->login_rsp_buf = kzalloc(ISER_RX_PAYLOAD_SIZE, GFP_KERNEL);
if (!isert_conn->login_rsp_buf) {
- isert_err("Unable to allocate isert_conn->login_rspbuf\n");
+ ret = -ENOMEM;
goto out_unmap_login_req_buf;
}
BUG_ON(!device);
isert_free_rx_descriptors(isert_conn);
- if (isert_conn->cm_id)
+ if (isert_conn->cm_id &&
+ !isert_conn->dev_removed)
rdma_destroy_id(isert_conn->cm_id);
if (isert_conn->qp) {
isert_device_put(device);
- kfree(isert_conn);
+ if (isert_conn->dev_removed)
+ wake_up_interruptible(&isert_conn->rem_wait);
+ else
+ kfree(isert_conn);
}
static void
isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
{
struct isert_np *isert_np = cma_id->context;
+ struct isert_conn *isert_conn;
int ret = 0;
isert_info("%s (%d): status %d id %p np %p\n",
break;
case RDMA_CM_EVENT_ADDR_CHANGE: /* FALLTHRU */
case RDMA_CM_EVENT_DISCONNECTED: /* FALLTHRU */
- case RDMA_CM_EVENT_DEVICE_REMOVAL: /* FALLTHRU */
case RDMA_CM_EVENT_TIMEWAIT_EXIT: /* FALLTHRU */
ret = isert_disconnected_handler(cma_id, event->event);
break;
+ case RDMA_CM_EVENT_DEVICE_REMOVAL:
+ isert_conn = cma_id->qp->qp_context;
+ isert_conn->dev_removed = true;
+ isert_disconnected_handler(cma_id, event->event);
+ wait_event_interruptible(isert_conn->rem_wait,
+ isert_conn->state == ISER_CONN_DOWN);
+ kfree(isert_conn);
+ /*
+ * return non-zero from the callback to destroy
+ * the rdma cm id
+ */
+ return 1;
case RDMA_CM_EVENT_REJECTED: /* FALLTHRU */
case RDMA_CM_EVENT_UNREACHABLE: /* FALLTHRU */
case RDMA_CM_EVENT_CONNECT_ERROR:
struct work_struct release_work;
bool logout_posted;
bool snd_w_inv;
+ wait_queue_head_t rem_wait;
+ bool dev_removed;
};
#define ISERT_MAX_CQ 64
if (ret)
goto err_query_port;
+ snprintf(sport->port_guid, sizeof(sport->port_guid),
+ "0x%016llx%016llx",
+ be64_to_cpu(sport->gid.global.subnet_prefix),
+ be64_to_cpu(sport->gid.global.interface_id));
+
if (!sport->mad_agent) {
memset(®_req, 0, sizeof(reg_req));
reg_req.mgmt_class = IB_MGMT_CLASS_DEVICE_MGMT;
sdev->device->name, i);
goto err_ring;
}
- snprintf(sport->port_guid, sizeof(sport->port_guid),
- "0x%016llx%016llx",
- be64_to_cpu(sport->gid.global.subnet_prefix),
- be64_to_cpu(sport->gid.global.interface_id));
}
spin_lock(&srpt_dev_lock);
/* Reset the KBC controller to clear all previous status.*/
reset_control_assert(kbc->rst);
udelay(100);
- reset_control_assert(kbc->rst);
+ reset_control_deassert(kbc->rst);
udelay(100);
tegra_kbc_config_pins(kbc);
goto free_struct_buff;
reg = find_first_bit(rdesc->presense_map, RMI_REG_DESC_PRESENSE_BITS);
- map_offset = 0;
for (i = 0; i < rdesc->num_registers; i++) {
struct rmi_register_desc_item *item = &rdesc->registers[i];
int reg_size = struct_buf[offset];
item->reg = reg;
item->reg_size = reg_size;
+ map_offset = 0;
+
do {
for (b = 0; b < 7; b++) {
if (struct_buf[offset] & (0x1 << b))
serio->write = i8042_aux_write;
serio->start = i8042_start;
serio->stop = i8042_stop;
+ serio->ps2_cmd_mutex = &i8042_mutex;
serio->port_data = port;
serio->dev.parent = &i8042_platform_device->dev;
if (idx < 0) {
ads784x_hwmon_unregister(spi, ts);
- regulator_disable(ts->reg);
regulator_put(ts->reg);
if (!ts->get_pendown_state) {
data->max_fingers = 5; /* Most devices handle up-to 5 fingers */
}
- error = device_property_read_string(dev, "touchscreen-fw-name", &str);
+ error = device_property_read_string(dev, "firmware-name", &str);
if (!error)
- snprintf(data->fw_name, sizeof(data->fw_name), "%s", str);
+ snprintf(data->fw_name, sizeof(data->fw_name),
+ "silead/%s", str);
else
dev_dbg(dev, "Firmware file name read error. Using default.");
}
if (!acpi_id)
return -ENODEV;
- snprintf(data->fw_name, sizeof(data->fw_name), "%s.fw",
- acpi_id->id);
+ snprintf(data->fw_name, sizeof(data->fw_name),
+ "silead/%s.fw", acpi_id->id);
for (i = 0; i < strlen(data->fw_name); i++)
data->fw_name[i] = tolower(data->fw_name[i]);
} else {
- snprintf(data->fw_name, sizeof(data->fw_name), "%s.fw",
- id->name);
+ snprintf(data->fw_name, sizeof(data->fw_name),
+ "silead/%s.fw", id->name);
}
return 0;
static int silead_ts_set_default_fw_name(struct silead_ts_data *data,
const struct i2c_device_id *id)
{
- snprintf(data->fw_name, sizeof(data->fw_name), "%s.fw", id->name);
+ snprintf(data->fw_name, sizeof(data->fw_name),
+ "silead/%s.fw", id->name);
return 0;
}
#endif
return -ENODEV;
/* Power GPIO pin */
- data->gpio_power = gpiod_get_optional(dev, "power", GPIOD_OUT_LOW);
+ data->gpio_power = devm_gpiod_get_optional(dev, "power", GPIOD_OUT_LOW);
if (IS_ERR(data->gpio_power)) {
if (PTR_ERR(data->gpio_power) != -EPROBE_DEFER)
dev_err(dev, "Shutdown GPIO request failed\n");
* We may have concurrent producers, so we need to be careful
* not to touch any of the shadow cmdq state.
*/
- queue_read(cmd, Q_ENT(q, idx), q->ent_dwords);
+ queue_read(cmd, Q_ENT(q, cons), q->ent_dwords);
dev_err(smmu->dev, "skipping command in error state:\n");
for (i = 0; i < ARRAY_SIZE(cmd); ++i)
dev_err(smmu->dev, "\t0x%016llx\n", (unsigned long long)cmd[i]);
return;
}
- queue_write(cmd, Q_ENT(q, idx), q->ent_dwords);
+ queue_write(Q_ENT(q, cons), cmd, q->ent_dwords);
}
static void arm_smmu_cmdq_issue_cmd(struct arm_smmu_device *smmu,
case STRTAB_STE_0_CFG_S2_TRANS:
ste_live = true;
break;
+ case STRTAB_STE_0_CFG_ABORT:
+ if (disable_bypass)
+ break;
default:
BUG(); /* STE corruption */
}
static irqreturn_t arm_smmu_context_fault(int irq, void *dev)
{
- int flags, ret;
- u32 fsr, fsynr, resume;
+ u32 fsr, fsynr;
unsigned long iova;
struct iommu_domain *domain = dev;
struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
if (!(fsr & FSR_FAULT))
return IRQ_NONE;
- if (fsr & FSR_IGN)
- dev_err_ratelimited(smmu->dev,
- "Unexpected context fault (fsr 0x%x)\n",
- fsr);
-
fsynr = readl_relaxed(cb_base + ARM_SMMU_CB_FSYNR0);
- flags = fsynr & FSYNR0_WNR ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ;
-
iova = readq_relaxed(cb_base + ARM_SMMU_CB_FAR);
- if (!report_iommu_fault(domain, smmu->dev, iova, flags)) {
- ret = IRQ_HANDLED;
- resume = RESUME_RETRY;
- } else {
- dev_err_ratelimited(smmu->dev,
- "Unhandled context fault: iova=0x%08lx, fsynr=0x%x, cb=%d\n",
- iova, fsynr, cfg->cbndx);
- ret = IRQ_NONE;
- resume = RESUME_TERMINATE;
- }
-
- /* Clear the faulting FSR */
- writel(fsr, cb_base + ARM_SMMU_CB_FSR);
- /* Retry or terminate any stalled transactions */
- if (fsr & FSR_SS)
- writel_relaxed(resume, cb_base + ARM_SMMU_CB_RESUME);
+ dev_err_ratelimited(smmu->dev,
+ "Unhandled context fault: fsr=0x%x, iova=0x%08lx, fsynr=0x%x, cb=%d\n",
+ fsr, iova, fsynr, cfg->cbndx);
- return ret;
+ writel(fsr, cb_base + ARM_SMMU_CB_FSR);
+ return IRQ_HANDLED;
}
static irqreturn_t arm_smmu_global_fault(int irq, void *dev)
}
/* SCTLR */
- reg = SCTLR_CFCFG | SCTLR_CFIE | SCTLR_CFRE | SCTLR_M | SCTLR_EAE_SBOP;
+ reg = SCTLR_CFIE | SCTLR_CFRE | SCTLR_M | SCTLR_EAE_SBOP;
if (stage1)
reg |= SCTLR_S1_ASIDPNE;
#ifdef __BIG_ENDIAN
if (!iovad)
return;
- put_iova_domain(iovad);
+ if (iovad->granule)
+ put_iova_domain(iovad);
kfree(iovad);
domain->iova_cookie = NULL;
}
}
}
-static struct iova *__alloc_iova(struct iova_domain *iovad, size_t size,
+static struct iova *__alloc_iova(struct iommu_domain *domain, size_t size,
dma_addr_t dma_limit)
{
+ struct iova_domain *iovad = domain->iova_cookie;
unsigned long shift = iova_shift(iovad);
unsigned long length = iova_align(iovad, size) >> shift;
+ if (domain->geometry.force_aperture)
+ dma_limit = min(dma_limit, domain->geometry.aperture_end);
/*
* Enforce size-alignment to be safe - there could perhaps be an
* attribute to control this per-device, or at least per-domain...
if (!pages)
return NULL;
- iova = __alloc_iova(iovad, size, dev->coherent_dma_mask);
+ iova = __alloc_iova(domain, size, dev->coherent_dma_mask);
if (!iova)
goto out_free_pages;
phys_addr_t phys = page_to_phys(page) + offset;
size_t iova_off = iova_offset(iovad, phys);
size_t len = iova_align(iovad, size + iova_off);
- struct iova *iova = __alloc_iova(iovad, len, dma_get_mask(dev));
+ struct iova *iova = __alloc_iova(domain, len, dma_get_mask(dev));
if (!iova)
return DMA_ERROR_CODE;
prev = s;
}
- iova = __alloc_iova(iovad, iova_len, dma_get_mask(dev));
+ iova = __alloc_iova(domain, iova_len, dma_get_mask(dev));
if (!iova)
goto out_restore_sg;
int prot = IOMMU_READ;
arm_v7s_iopte attr = pte >> ARM_V7S_ATTR_SHIFT(lvl);
- if (attr & ARM_V7S_PTE_AP_RDONLY)
+ if (!(attr & ARM_V7S_PTE_AP_RDONLY))
prot |= IOMMU_WRITE;
if ((attr & (ARM_V7S_TEX_MASK << ARM_V7S_TEX_SHIFT)) == 0)
prot |= IOMMU_MMIO;
else if (pte & ARM_V7S_ATTR_C)
prot |= IOMMU_CACHE;
+ if (pte & ARM_V7S_ATTR_XN(lvl))
+ prot |= IOMMU_NOEXEC;
return prot;
}
bool enable_4GB;
};
-static int compare_of(struct device *dev, void *data)
+static inline int compare_of(struct device *dev, void *data)
{
return dev->of_node == data;
}
-static int mtk_iommu_bind(struct device *dev)
+static inline int mtk_iommu_bind(struct device *dev)
{
struct mtk_iommu_data *data = dev_get_drvdata(dev);
return component_bind_all(dev, &data->smi_imu);
}
-static void mtk_iommu_unbind(struct device *dev)
+static inline void mtk_iommu_unbind(struct device *dev)
{
struct mtk_iommu_data *data = dev_get_drvdata(dev);
{
struct irq_domain_chip_generic *dgc = d->gc;
struct irq_chip_generic *gc;
+ unsigned long flags;
unsigned smr;
int idx;
int ret;
gc = dgc->gc[idx];
- irq_gc_lock(gc);
+ irq_gc_lock_irqsave(gc, flags);
smr = irq_reg_readl(gc, AT91_AIC_SMR(*out_hwirq));
aic_common_set_priority(intspec[2], &smr);
irq_reg_writel(gc, smr, AT91_AIC_SMR(*out_hwirq));
- irq_gc_unlock(gc);
+ irq_gc_unlock_irqrestore(gc, flags);
return ret;
}
unsigned int *out_type)
{
struct irq_chip_generic *bgc = irq_get_domain_generic_chip(d, 0);
+ unsigned long flags;
unsigned smr;
int ret;
if (ret)
return ret;
- irq_gc_lock(bgc);
+ irq_gc_lock_irqsave(bgc, flags);
irq_reg_writel(bgc, *out_hwirq, AT91_AIC5_SSR);
smr = irq_reg_readl(bgc, AT91_AIC5_SMR);
aic_common_set_priority(intspec[2], &smr);
irq_reg_writel(bgc, smr, AT91_AIC5_SMR);
- irq_gc_unlock(bgc);
+ irq_gc_unlock_irqrestore(bgc, flags);
return ret;
}
u32 val;
val = readl_relaxed(base + GITS_CTLR);
- if (val & GITS_CTLR_QUIESCENT)
+ /*
+ * GIC architecture specification requires the ITS to be both
+ * disabled and quiescent for writes to GITS_BASER<n> or
+ * GITS_CBASER to not have UNPREDICTABLE results.
+ */
+ if ((val & GITS_CTLR_QUIESCENT) && !(val & GITS_CTLR_ENABLE))
return 0;
/* Disable the generation of all interrupts to this ITS */
static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask,
unsigned long cluster_id)
{
- int cpu = *base_cpu;
+ int next_cpu, cpu = *base_cpu;
unsigned long mpidr = cpu_logical_map(cpu);
u16 tlist = 0;
tlist |= 1 << (mpidr & 0xf);
- cpu = cpumask_next(cpu, mask);
- if (cpu >= nr_cpu_ids)
+ next_cpu = cpumask_next(cpu, mask);
+ if (next_cpu >= nr_cpu_ids)
goto out;
+ cpu = next_cpu;
mpidr = cpu_logical_map(cpu);
#endif
#ifdef CONFIG_CPU_PM
+/* Check whether it's single security state view */
+static bool gic_dist_security_disabled(void)
+{
+ return readl_relaxed(gic_data.dist_base + GICD_CTLR) & GICD_CTLR_DS;
+}
+
static int gic_cpu_pm_notifier(struct notifier_block *self,
unsigned long cmd, void *v)
{
if (cmd == CPU_PM_EXIT) {
- gic_enable_redist(true);
+ if (gic_dist_security_disabled())
+ gic_enable_redist(true);
gic_cpu_sys_reg_init();
- } else if (cmd == CPU_PM_ENTER) {
+ } else if (cmd == CPU_PM_ENTER && gic_dist_security_disabled()) {
gic_write_grpen1(0);
gic_enable_redist(false);
}
int cpu;
unsigned long flags, map = 0;
+ if (unlikely(nr_cpu_ids == 1)) {
+ /* Only one CPU? let's do a self-IPI... */
+ writel_relaxed(2 << 24 | irq,
+ gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT);
+ return;
+ }
+
raw_spin_lock_irqsave(&irq_controller_lock, flags);
/* Convert our logical CPU mask into a physical one. */
if (!gic_local_irq_is_routable(intr))
return -EPERM;
- /*
- * HACK: These are all really percpu interrupts, but the rest
- * of the MIPS kernel code does not use the percpu IRQ API for
- * the CP0 timer and performance counter interrupts.
- */
- switch (intr) {
- case GIC_LOCAL_INT_TIMER:
- case GIC_LOCAL_INT_PERFCTR:
- case GIC_LOCAL_INT_FDC:
- irq_set_chip_and_handler(virq,
- &gic_all_vpes_local_irq_controller,
- handle_percpu_irq);
- break;
- default:
- irq_set_chip_and_handler(virq,
- &gic_local_irq_controller,
- handle_percpu_devid_irq);
- irq_set_percpu_devid(virq);
- break;
- }
-
spin_lock_irqsave(&gic_lock, flags);
for (i = 0; i < gic_vpes; i++) {
u32 val = GIC_MAP_TO_PIN_MSK | gic_cpu_pin;
unsigned long flags;
int i;
- irq_set_chip_and_handler(virq, &gic_level_irq_controller,
- handle_level_irq);
-
spin_lock_irqsave(&gic_lock, flags);
gic_map_to_pin(intr, gic_cpu_pin);
gic_map_to_vpe(intr, mips_cm_vp_id(vpe));
return 0;
}
-static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq,
- irq_hw_number_t hw)
+static int gic_setup_dev_chip(struct irq_domain *d, unsigned int virq,
+ unsigned int hwirq)
{
- if (GIC_HWIRQ_TO_LOCAL(hw) < GIC_NUM_LOCAL_INTRS)
- return gic_local_irq_domain_map(d, virq, hw);
- return gic_shared_irq_domain_map(d, virq, hw, 0);
+ struct irq_chip *chip;
+ int err;
+
+ if (hwirq >= GIC_SHARED_HWIRQ_BASE) {
+ err = irq_domain_set_hwirq_and_chip(d, virq, hwirq,
+ &gic_level_irq_controller,
+ NULL);
+ } else {
+ switch (GIC_HWIRQ_TO_LOCAL(hwirq)) {
+ case GIC_LOCAL_INT_TIMER:
+ case GIC_LOCAL_INT_PERFCTR:
+ case GIC_LOCAL_INT_FDC:
+ /*
+ * HACK: These are all really percpu interrupts, but
+ * the rest of the MIPS kernel code does not use the
+ * percpu IRQ API for them.
+ */
+ chip = &gic_all_vpes_local_irq_controller;
+ irq_set_handler(virq, handle_percpu_irq);
+ break;
+
+ default:
+ chip = &gic_local_irq_controller;
+ irq_set_handler(virq, handle_percpu_devid_irq);
+ irq_set_percpu_devid(virq);
+ break;
+ }
+
+ err = irq_domain_set_hwirq_and_chip(d, virq, hwirq,
+ chip, NULL);
+ }
+
+ return err;
}
static int gic_irq_domain_alloc(struct irq_domain *d, unsigned int virq,
int cpu, ret, i;
if (spec->type == GIC_DEVICE) {
- /* verify that it doesn't conflict with an IPI irq */
- if (test_bit(spec->hwirq, ipi_resrv))
+ /* verify that shared irqs don't conflict with an IPI irq */
+ if ((spec->hwirq >= GIC_SHARED_HWIRQ_BASE) &&
+ test_bit(GIC_HWIRQ_TO_SHARED(spec->hwirq), ipi_resrv))
return -EBUSY;
- hwirq = GIC_SHARED_TO_HWIRQ(spec->hwirq);
-
- return irq_domain_set_hwirq_and_chip(d, virq, hwirq,
- &gic_level_irq_controller,
- NULL);
+ return gic_setup_dev_chip(d, virq, spec->hwirq);
} else {
base_hwirq = find_first_bit(ipi_resrv, gic_shared_intrs);
if (base_hwirq == gic_shared_intrs) {
hwirq = GIC_SHARED_TO_HWIRQ(base_hwirq + i);
ret = irq_domain_set_hwirq_and_chip(d, virq + i, hwirq,
- &gic_edge_irq_controller,
+ &gic_level_irq_controller,
NULL);
if (ret)
goto error;
+ irq_set_handler(virq + i, handle_level_irq);
+
ret = gic_shared_irq_domain_map(d, virq + i, hwirq, cpu);
if (ret)
goto error;
}
static const struct irq_domain_ops gic_irq_domain_ops = {
- .map = gic_irq_domain_map,
.alloc = gic_irq_domain_alloc,
.free = gic_irq_domain_free,
.match = gic_irq_domain_match,
struct irq_fwspec *fwspec = arg;
struct gic_irq_spec spec = {
.type = GIC_DEVICE,
- .hwirq = fwspec->param[1],
};
int i, ret;
- bool is_shared = fwspec->param[0] == GIC_SHARED;
- if (is_shared) {
- ret = irq_domain_alloc_irqs_parent(d, virq, nr_irqs, &spec);
- if (ret)
- return ret;
- }
-
- for (i = 0; i < nr_irqs; i++) {
- irq_hw_number_t hwirq;
+ if (fwspec->param[0] == GIC_SHARED)
+ spec.hwirq = GIC_SHARED_TO_HWIRQ(fwspec->param[1]);
+ else
+ spec.hwirq = GIC_LOCAL_TO_HWIRQ(fwspec->param[1]);
- if (is_shared)
- hwirq = GIC_SHARED_TO_HWIRQ(spec.hwirq + i);
- else
- hwirq = GIC_LOCAL_TO_HWIRQ(spec.hwirq + i);
+ ret = irq_domain_alloc_irqs_parent(d, virq, nr_irqs, &spec);
+ if (ret)
+ return ret;
- ret = irq_domain_set_hwirq_and_chip(d, virq + i,
- hwirq,
- &gic_level_irq_controller,
- NULL);
+ for (i = 0; i < nr_irqs; i++) {
+ ret = gic_setup_dev_chip(d, virq + i, spec.hwirq + i);
if (ret)
goto error;
}
return;
}
+static void gic_dev_domain_activate(struct irq_domain *domain,
+ struct irq_data *d)
+{
+ if (GIC_HWIRQ_TO_LOCAL(d->hwirq) < GIC_NUM_LOCAL_INTRS)
+ gic_local_irq_domain_map(domain, d->irq, d->hwirq);
+ else
+ gic_shared_irq_domain_map(domain, d->irq, d->hwirq, 0);
+}
+
static struct irq_domain_ops gic_dev_domain_ops = {
.xlate = gic_dev_domain_xlate,
.alloc = gic_dev_domain_alloc,
.free = gic_dev_domain_free,
+ .activate = gic_dev_domain_activate,
};
static int gic_ipi_domain_xlate(struct irq_domain *d, struct device_node *ctrlr,
static struct i2c_driver ams_i2c_driver = {
.driver = {
.name = "ams",
- .owner = THIS_MODULE,
},
.probe = ams_i2c_probe,
.remove = ams_i2c_remove,
.remove = wf_pm112_remove,
.driver = {
.name = "windfarm",
- .owner = THIS_MODULE,
},
};
.remove = wf_pm72_remove,
.driver = {
.name = "windfarm",
- .owner = THIS_MODULE,
},
};
.remove = wf_rm31_remove,
.driver = {
.name = "windfarm",
- .owner = THIS_MODULE,
},
};
config BCM_PDC_MBOX
tristate "Broadcom PDC Mailbox"
depends on ARM64 || COMPILE_TEST
+ depends on HAS_DMA
default ARCH_BCM_IPROC
help
Mailbox implementation for the Broadcom PDC ring manager,
* this directory for a SPU.
* @pdcs: PDC state structure
*/
-void pdc_setup_debugfs(struct pdc_state *pdcs)
+static void pdc_setup_debugfs(struct pdc_state *pdcs)
{
char spu_stats_name[16];
&pdc_debugfs_stats);
}
-void pdc_free_debugfs(void)
+static void pdc_free_debugfs(void)
{
if (debugfs_dir && simple_empty(debugfs_dir)) {
debugfs_remove_recursive(debugfs_dir);
{
struct pdc_state *pdcs = chan->con_priv;
- if (pdcs)
- dev_dbg(&pdcs->pdev->dev,
- "Shutdown mailbox channel for PDC %u", pdcs->pdc_idx);
+ if (!pdcs)
+ return;
+ dev_dbg(&pdcs->pdev->dev,
+ "Shutdown mailbox channel for PDC %u", pdcs->pdc_idx);
pdc_ring_free(pdcs);
}
if (!d->nr_stripes ||
d->nr_stripes > INT_MAX ||
d->nr_stripes > SIZE_MAX / sizeof(atomic_t)) {
- pr_err("nr_stripes too large");
+ pr_err("nr_stripes too large or invalid: %u (start sector beyond end of disk?)",
+ (unsigned)d->nr_stripes);
return -ENOMEM;
}
free = roundup_pow_of_two(ca->sb.nbuckets) >> 10;
if (!init_fifo(&ca->free[RESERVE_BTREE], 8, GFP_KERNEL) ||
- !init_fifo(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) ||
+ !init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) ||
!init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL) ||
!init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL) ||
!init_fifo(&ca->free_inc, free << 2, GFP_KERNEL) ||
struct block_device *bdev, struct cache *ca)
{
char name[BDEVNAME_SIZE];
- const char *err = NULL;
+ const char *err = NULL; /* must be set for any error case */
int ret = 0;
memcpy(&ca->sb, sb, sizeof(struct cache_sb));
ca->discard = CACHE_DISCARD(&ca->sb);
ret = cache_alloc(ca);
- if (ret != 0)
+ if (ret != 0) {
+ if (ret == -ENOMEM)
+ err = "cache_alloc(): -ENOMEM";
+ else
+ err = "cache_alloc(): unknown error";
goto err;
+ }
if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache")) {
err = "error calling kobject_add";
static ssize_t
location_store(struct mddev *mddev, const char *buf, size_t len)
{
+ int rv;
+ rv = mddev_lock(mddev);
+ if (rv)
+ return rv;
if (mddev->pers) {
- if (!mddev->pers->quiesce)
- return -EBUSY;
- if (mddev->recovery || mddev->sync_thread)
- return -EBUSY;
+ if (!mddev->pers->quiesce) {
+ rv = -EBUSY;
+ goto out;
+ }
+ if (mddev->recovery || mddev->sync_thread) {
+ rv = -EBUSY;
+ goto out;
+ }
}
if (mddev->bitmap || mddev->bitmap_info.file ||
mddev->bitmap_info.offset) {
/* bitmap already configured. Only option is to clear it */
- if (strncmp(buf, "none", 4) != 0)
- return -EBUSY;
+ if (strncmp(buf, "none", 4) != 0) {
+ rv = -EBUSY;
+ goto out;
+ }
if (mddev->pers) {
mddev->pers->quiesce(mddev, 1);
bitmap_destroy(mddev);
/* nothing to be done */;
else if (strncmp(buf, "file:", 5) == 0) {
/* Not supported yet */
- return -EINVAL;
+ rv = -EINVAL;
+ goto out;
} else {
- int rv;
if (buf[0] == '+')
rv = kstrtoll(buf+1, 10, &offset);
else
rv = kstrtoll(buf, 10, &offset);
if (rv)
- return rv;
- if (offset == 0)
- return -EINVAL;
+ goto out;
+ if (offset == 0) {
+ rv = -EINVAL;
+ goto out;
+ }
if (mddev->bitmap_info.external == 0 &&
mddev->major_version == 0 &&
- offset != mddev->bitmap_info.default_offset)
- return -EINVAL;
+ offset != mddev->bitmap_info.default_offset) {
+ rv = -EINVAL;
+ goto out;
+ }
mddev->bitmap_info.offset = offset;
if (mddev->pers) {
struct bitmap *bitmap;
mddev->pers->quiesce(mddev, 0);
if (rv) {
bitmap_destroy(mddev);
- return rv;
+ goto out;
}
}
}
set_bit(MD_CHANGE_DEVS, &mddev->flags);
md_wakeup_thread(mddev->thread);
}
+ rv = 0;
+out:
+ mddev_unlock(mddev);
+ if (rv)
+ return rv;
return len;
}
__cache_size_refresh();
mutex_unlock(&dm_bufio_clients_lock);
- dm_bufio_wq = create_singlethread_workqueue("dm_bufio_cache");
+ dm_bufio_wq = alloc_workqueue("dm_bufio_cache", WQ_MEM_RECLAIM, 0);
if (!dm_bufio_wq)
return -ENOMEM;
u8 key[0];
};
-#define MIN_IOS 16
+#define MIN_IOS 64
static void clone_init(struct dm_crypt_io *, struct bio *);
static void kcryptd_queue_crypt(struct dm_crypt_io *io);
unsigned i;
int err;
- cc->tfms = kmalloc(cc->tfms_count * sizeof(struct crypto_skcipher *),
+ cc->tfms = kzalloc(cc->tfms_count * sizeof(struct crypto_skcipher *),
GFP_KERNEL);
if (!cc->tfms)
return -ENOMEM;
return DM_MAPIO_REMAPPED;
}
+ /*
+ * Check if bio is too large, split as needed.
+ */
+ if (unlikely(bio->bi_iter.bi_size > (BIO_MAX_PAGES << PAGE_SHIFT)) &&
+ bio_data_dir(bio) == WRITE)
+ dm_accept_partial_bio(bio, ((BIO_MAX_PAGES << PAGE_SHIFT) >> SECTOR_SHIFT));
+
io = dm_per_bio_data(bio, cc->per_bio_data_size);
crypt_io_init(io, cc, bio, dm_target_offset(ti, bio->bi_iter.bi_sector));
io->ctx.req = (struct skcipher_request *)(io + 1);
pb->bio_submitted = true;
/*
- * Map reads as normal only if corrupt_bio_byte set.
+ * Error reads if neither corrupt_bio_byte or drop_writes are set.
+ * Otherwise, flakey_end_io() will decide if the reads should be modified.
*/
if (bio_data_dir(bio) == READ) {
- /* If flags were specified, only corrupt those that match. */
- if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) &&
- all_corrupt_bio_flags_match(bio, fc))
- goto map_bio;
- else
+ if (!fc->corrupt_bio_byte && !test_bit(DROP_WRITES, &fc->flags))
return -EIO;
+ goto map_bio;
}
/*
struct flakey_c *fc = ti->private;
struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
- /*
- * Corrupt successful READs while in down state.
- */
if (!error && pb->bio_submitted && (bio_data_dir(bio) == READ)) {
- if (fc->corrupt_bio_byte)
+ if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) &&
+ all_corrupt_bio_flags_match(bio, fc)) {
+ /*
+ * Corrupt successful matching READs while in down state.
+ */
corrupt_bio_data(bio, fc);
- else
+
+ } else if (!test_bit(DROP_WRITES, &fc->flags)) {
+ /*
+ * Error read during the down_interval if drop_writes
+ * wasn't configured.
+ */
return -EIO;
+ }
}
return error;
goto out;
sector++;
- bio = bio_alloc(GFP_KERNEL, block->vec_cnt);
+ atomic_inc(&lc->io_blocks);
+ bio = bio_alloc(GFP_KERNEL, min(block->vec_cnt, BIO_MAX_PAGES));
if (!bio) {
DMERR("Couldn't alloc log bio");
goto error;
}
- atomic_inc(&lc->io_blocks);
bio->bi_iter.bi_size = 0;
bio->bi_iter.bi_sector = sector;
bio->bi_bdev = lc->logdev->bdev;
if (ret != block->vecs[i].bv_len) {
atomic_inc(&lc->io_blocks);
submit_bio(bio);
- bio = bio_alloc(GFP_KERNEL, block->vec_cnt - i);
+ bio = bio_alloc(GFP_KERNEL, min(block->vec_cnt - i, BIO_MAX_PAGES));
if (!bio) {
DMERR("Couldn't alloc log bio");
goto error;
goto bad;
}
- ret = -EINVAL;
lc->log_kthread = kthread_run(log_writes_kthread, lc, "log-write");
- if (!lc->log_kthread) {
+ if (IS_ERR(lc->log_kthread)) {
+ ret = PTR_ERR(lc->log_kthread);
ti->error = "Couldn't alloc kthread";
dm_put_device(ti, lc->dev);
dm_put_device(ti, lc->logdev);
core->nr_regions = le64_to_cpu(disk->nr_regions);
}
-static int rw_header(struct log_c *lc, int rw)
+static int rw_header(struct log_c *lc, int op)
{
- lc->io_req.bi_op = rw;
+ lc->io_req.bi_op = op;
+ lc->io_req.bi_op_flags = 0;
return dm_io(&lc->io_req, 1, &lc->header_location, NULL);
}
{
int r;
- r = rw_header(log, READ);
+ r = rw_header(log, REQ_OP_READ);
if (r)
return r;
header_to_disk(&lc->header, lc->disk_header);
/* write the new header */
- r = rw_header(lc, WRITE);
+ r = rw_header(lc, REQ_OP_WRITE);
if (!r) {
r = flush_header(lc);
if (r)
log_clear_bit(lc, lc->clean_bits, i);
}
- r = rw_header(lc, WRITE);
+ r = rw_header(lc, REQ_OP_WRITE);
if (r)
fail_log_device(lc);
else {
#define RT_FLAG_RS_BITMAP_LOADED 2
#define RT_FLAG_UPDATE_SBS 3
#define RT_FLAG_RESHAPE_RS 4
-#define RT_FLAG_KEEP_RS_FROZEN 5
/* Array elements of 64 bit needed for rebuild/failed disk bits */
#define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8)
{
unsigned long min_region_size = rs->ti->len / (1 << 21);
+ if (rs_is_raid0(rs))
+ return 0;
+
if (!region_size) {
/*
* Choose a reasonable default. All figures in sectors.
rebuild_cnt++;
switch (rs->raid_type->level) {
+ case 0:
+ break;
case 1:
if (rebuild_cnt >= rs->md.raid_disks)
goto too_many;
case 0:
break;
default:
+ /*
+ * We have to keep any raid0 data/metadata device pairs or
+ * the MD raid0 personality will fail to start the array.
+ */
+ if (rs_is_raid0(rs))
+ continue;
+
dev = container_of(rdev, struct raid_dev, rdev);
if (dev->meta_dev)
dm_put_device(ti, dev->meta_dev);
} else {
/* Process raid1 without delta_disks */
mddev->raid_disks = rs->raid_disks;
- set_bit(RT_FLAG_KEEP_RS_FROZEN, &rs->runtime_flags);
reshape = false;
}
} else {
if (reshape) {
set_bit(RT_FLAG_RESHAPE_RS, &rs->runtime_flags);
set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
- set_bit(RT_FLAG_KEEP_RS_FROZEN, &rs->runtime_flags);
} else if (mddev->raid_disks < rs->raid_disks)
/* Create new superblocks and bitmaps, if any new disks */
set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
goto bad;
set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags);
- set_bit(RT_FLAG_KEEP_RS_FROZEN, &rs->runtime_flags);
/* Takeover ain't recovery, so disable recovery */
rs_setup_recovery(rs, MaxSector);
rs_set_new(rs);
{
struct raid_set *rs = ti->private;
- if (test_and_clear_bit(RT_FLAG_RS_RESUMED, &rs->runtime_flags)) {
- if (!rs->md.suspended)
- mddev_suspend(&rs->md);
- rs->md.ro = 1;
- }
+ if (!rs->md.suspended)
+ mddev_suspend(&rs->md);
+
+ rs->md.ro = 1;
}
static void attempt_restore_of_faulty_devices(struct raid_set *rs)
{
int i;
- uint64_t failed_devices, cleared_failed_devices = 0;
+ uint64_t cleared_failed_devices[DISKS_ARRAY_ELEMS];
unsigned long flags;
+ bool cleared = false;
struct dm_raid_superblock *sb;
+ struct mddev *mddev = &rs->md;
struct md_rdev *r;
+ /* RAID personalities have to provide hot add/remove methods or we need to bail out. */
+ if (!mddev->pers || !mddev->pers->hot_add_disk || !mddev->pers->hot_remove_disk)
+ return;
+
+ memset(cleared_failed_devices, 0, sizeof(cleared_failed_devices));
+
for (i = 0; i < rs->md.raid_disks; i++) {
r = &rs->dev[i].rdev;
if (test_bit(Faulty, &r->flags) && r->sb_page &&
* ourselves.
*/
if ((r->raid_disk >= 0) &&
- (r->mddev->pers->hot_remove_disk(r->mddev, r) != 0))
+ (mddev->pers->hot_remove_disk(mddev, r) != 0))
/* Failed to revive this device, try next */
continue;
clear_bit(Faulty, &r->flags);
clear_bit(WriteErrorSeen, &r->flags);
clear_bit(In_sync, &r->flags);
- if (r->mddev->pers->hot_add_disk(r->mddev, r)) {
+ if (mddev->pers->hot_add_disk(mddev, r)) {
r->raid_disk = -1;
r->saved_raid_disk = -1;
r->flags = flags;
} else {
r->recovery_offset = 0;
- cleared_failed_devices |= 1 << i;
+ set_bit(i, (void *) cleared_failed_devices);
+ cleared = true;
}
}
}
- if (cleared_failed_devices) {
+
+ /* If any failed devices could be cleared, update all sbs failed_devices bits */
+ if (cleared) {
+ uint64_t failed_devices[DISKS_ARRAY_ELEMS];
+
rdev_for_each(r, &rs->md) {
sb = page_address(r->sb_page);
- failed_devices = le64_to_cpu(sb->failed_devices);
- failed_devices &= ~cleared_failed_devices;
- sb->failed_devices = cpu_to_le64(failed_devices);
+ sb_retrieve_failed_devices(sb, failed_devices);
+
+ for (i = 0; i < DISKS_ARRAY_ELEMS; i++)
+ failed_devices[i] &= ~cleared_failed_devices[i];
+
+ sb_update_failed_devices(sb, failed_devices);
}
}
}
* devices are reachable again.
*/
attempt_restore_of_faulty_devices(rs);
- } else {
- mddev->ro = 0;
- mddev->in_sync = 0;
+ }
- /*
- * When passing in flags to the ctr, we expect userspace
- * to reset them because they made it to the superblocks
- * and reload the mapping anyway.
- *
- * -> only unfreeze recovery in case of a table reload or
- * we'll have a bogus recovery/reshape position
- * retrieved from the superblock by the ctr because
- * the ongoing recovery/reshape will change it after read.
- */
- if (!test_bit(RT_FLAG_KEEP_RS_FROZEN, &rs->runtime_flags))
- clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+ mddev->ro = 0;
+ mddev->in_sync = 0;
- if (mddev->suspended)
- mddev_resume(mddev);
- }
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+
+ if (mddev->suspended)
+ mddev_resume(mddev);
}
static struct target_type raid_target = {
struct path_info *pi = NULL;
struct dm_path *current_path = NULL;
+ local_irq_save(flags);
current_path = *this_cpu_ptr(s->current_path);
if (current_path) {
percpu_counter_dec(&s->repeat_count);
- if (percpu_counter_read_positive(&s->repeat_count) > 0)
+ if (percpu_counter_read_positive(&s->repeat_count) > 0) {
+ local_irq_restore(flags);
return current_path;
+ }
}
- spin_lock_irqsave(&s->lock, flags);
+ spin_lock(&s->lock);
if (!list_empty(&s->valid_paths)) {
pi = list_entry(s->valid_paths.next, struct path_info, list);
list_move_tail(&pi->list, &s->valid_paths);
goto err;
}
cinfo->ack_lockres = lockres_init(mddev, "ack", ack_bast, 0);
- if (!cinfo->ack_lockres)
+ if (!cinfo->ack_lockres) {
+ ret = -ENOMEM;
goto err;
+ }
/* get sync CR lock on ACK. */
if (dlm_lock_sync(cinfo->ack_lockres, DLM_LOCK_CR))
pr_err("md-cluster: failed to get a sync CR lock on ACK!(%d)\n",
pr_info("md-cluster: Joined cluster %s slot %d\n", str, cinfo->slot_number);
snprintf(str, 64, "bitmap%04d", cinfo->slot_number - 1);
cinfo->bitmap_lockres = lockres_init(mddev, str, NULL, 1);
- if (!cinfo->bitmap_lockres)
+ if (!cinfo->bitmap_lockres) {
+ ret = -ENOMEM;
goto err;
+ }
if (dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW)) {
pr_err("Failed to get bitmap lock\n");
ret = -EINVAL;
}
cinfo->resync_lockres = lockres_init(mddev, "resync", NULL, 0);
- if (!cinfo->resync_lockres)
+ if (!cinfo->resync_lockres) {
+ ret = -ENOMEM;
goto err;
+ }
return 0;
err:
mddev->new_chunk_sectors = mddev->chunk_sectors;
}
- if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL) {
+ if (le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)
set_bit(MD_HAS_JOURNAL, &mddev->flags);
- if (mddev->recovery_cp == MaxSector)
- set_bit(MD_JOURNAL_CLEAN, &mddev->flags);
- }
} else if (mddev->pers == NULL) {
/* Insist of good event counter while assembling, except for
* spares (which don't need an event count) */
working++;
if (test_bit(In_sync, &rdev->flags))
insync++;
+ else if (test_bit(Journal, &rdev->flags))
+ /* TODO: add journal count to md_u.h */
+ ;
else
spare++;
}
int md_setup_cluster(struct mddev *mddev, int nodes)
{
- int err;
-
- err = request_module("md-cluster");
- if (err) {
- pr_err("md-cluster module not found.\n");
- return -ENOENT;
- }
-
+ if (!md_cluster_ops)
+ request_module("md-cluster");
spin_lock(&pers_lock);
+ /* ensure module won't be unloaded */
if (!md_cluster_ops || !try_module_get(md_cluster_mod)) {
+ pr_err("can't find md-cluster module or get it's reference.\n");
spin_unlock(&pers_lock);
return -ENOENT;
}
*/
do {
+ int mddev2_minor = -1;
mddev->curr_resync = 2;
try_again:
prepare_to_wait(&resync_wait, &wq, TASK_INTERRUPTIBLE);
if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
mddev2->curr_resync >= mddev->curr_resync) {
- printk(KERN_INFO "md: delaying %s of %s"
- " until %s has finished (they"
- " share one or more physical units)\n",
- desc, mdname(mddev), mdname(mddev2));
+ if (mddev2_minor != mddev2->md_minor) {
+ mddev2_minor = mddev2->md_minor;
+ printk(KERN_INFO "md: delaying %s of %s"
+ " until %s has finished (they"
+ " share one or more physical units)\n",
+ desc, mdname(mddev),
+ mdname(mddev2));
+ }
mddev_put(mddev2);
if (signal_pending(current))
flush_signals(current);
static void md_start_sync(struct work_struct *ws)
{
struct mddev *mddev = container_of(ws, struct mddev, del_work);
- int ret = 0;
mddev->sync_thread = md_register_thread(md_do_sync,
mddev,
"resync");
if (!mddev->sync_thread) {
- if (!(mddev_is_clustered(mddev) && ret == -EAGAIN))
- printk(KERN_ERR "%s: could not start resync"
- " thread...\n",
- mdname(mddev));
+ printk(KERN_ERR "%s: could not start resync thread...\n",
+ mdname(mddev));
/* leave the spares where they are, it shouldn't hurt */
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
int max_sectors;
int sectors;
+ md_write_start(mddev, bio);
+
/*
* Register the new request and wait if the reconstruction
* thread has put up a bar for new requests.
return;
}
- md_write_start(mddev, bio);
-
do {
/*
while (sect_to_write) {
struct bio *wbio;
+ sector_t wsector;
if (sectors > sect_to_write)
sectors = sect_to_write;
/* Write at 'sector' for 'sectors' */
wbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
bio_trim(wbio, sector - bio->bi_iter.bi_sector, sectors);
- wbio->bi_iter.bi_sector = (r10_bio->devs[i].addr+
- choose_data_offset(r10_bio, rdev) +
- (sector - r10_bio->sector));
+ wsector = r10_bio->devs[i].addr + (sector - r10_bio->sector);
+ wbio->bi_iter.bi_sector = wsector +
+ choose_data_offset(r10_bio, rdev);
wbio->bi_bdev = rdev->bdev;
bio_set_op_attrs(wbio, REQ_OP_WRITE, 0);
if (submit_bio_wait(wbio) < 0)
/* Failure! */
- ok = rdev_set_badblocks(rdev, sector,
+ ok = rdev_set_badblocks(rdev, wsector,
sectors, 0)
&& ok;
spinlock_t no_space_stripes_lock;
bool need_cache_flush;
- bool in_teardown;
};
/*
mddev = log->rdev->mddev;
/*
- * This is to avoid a deadlock. r5l_quiesce holds reconfig_mutex and
- * wait for this thread to finish. This thread waits for
- * MD_CHANGE_PENDING clear, which is supposed to be done in
- * md_check_recovery(). md_check_recovery() tries to get
- * reconfig_mutex. Since r5l_quiesce already holds the mutex,
- * md_check_recovery() fails, so the PENDING never get cleared. The
- * in_teardown check workaround this issue.
+ * Discard could zero data, so before discard we must make sure
+ * superblock is updated to new log tail. Updating superblock (either
+ * directly call md_update_sb() or depend on md thread) must hold
+ * reconfig mutex. On the other hand, raid5_quiesce is called with
+ * reconfig_mutex hold. The first step of raid5_quiesce() is waitting
+ * for all IO finish, hence waitting for reclaim thread, while reclaim
+ * thread is calling this function and waitting for reconfig mutex. So
+ * there is a deadlock. We workaround this issue with a trylock.
+ * FIXME: we could miss discard if we can't take reconfig mutex
*/
- if (!log->in_teardown) {
- set_mask_bits(&mddev->flags, 0,
- BIT(MD_CHANGE_DEVS) | BIT(MD_CHANGE_PENDING));
- md_wakeup_thread(mddev->thread);
- wait_event(mddev->sb_wait,
- !test_bit(MD_CHANGE_PENDING, &mddev->flags) ||
- log->in_teardown);
- /*
- * r5l_quiesce could run after in_teardown check and hold
- * mutex first. Superblock might get updated twice.
- */
- if (log->in_teardown)
- md_update_sb(mddev, 1);
- } else {
- WARN_ON(!mddev_is_locked(mddev));
- md_update_sb(mddev, 1);
- }
+ set_mask_bits(&mddev->flags, 0,
+ BIT(MD_CHANGE_DEVS) | BIT(MD_CHANGE_PENDING));
+ if (!mddev_trylock(mddev))
+ return;
+ md_update_sb(mddev, 1);
+ mddev_unlock(mddev);
/* discard IO error really doesn't matter, ignore it */
if (log->last_checkpoint < end) {
if (!log || state == 2)
return;
if (state == 0) {
- log->in_teardown = 0;
/*
* This is a special case for hotadd. In suspend, the array has
* no journal. In resume, journal is initialized as well as the
log->reclaim_thread = md_register_thread(r5l_reclaim_thread,
log->rdev->mddev, "reclaim");
} else if (state == 1) {
- /*
- * at this point all stripes are finished, so io_unit is at
- * least in STRIPE_END state
- */
- log->in_teardown = 1;
/* make sure r5l_write_super_and_discard_space exits */
mddev = log->rdev->mddev;
wake_up(&mddev->sb_wait);
{
struct stripe_head *sh;
int hash = stripe_hash_locks_hash(sector);
+ int inc_empty_inactive_list_flag;
pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector);
atomic_inc(&conf->active_stripes);
BUG_ON(list_empty(&sh->lru) &&
!test_bit(STRIPE_EXPANDING, &sh->state));
+ inc_empty_inactive_list_flag = 0;
+ if (!list_empty(conf->inactive_list + hash))
+ inc_empty_inactive_list_flag = 1;
list_del_init(&sh->lru);
+ if (list_empty(conf->inactive_list + hash) && inc_empty_inactive_list_flag)
+ atomic_inc(&conf->empty_inactive_list_nr);
if (sh->group) {
sh->group->stripes_cnt--;
sh->group = NULL;
sector_t head_sector, tmp_sec;
int hash;
int dd_idx;
+ int inc_empty_inactive_list_flag;
/* Don't cross chunks, so stripe pd_idx/qd_idx is the same */
tmp_sec = sh->sector;
atomic_inc(&conf->active_stripes);
BUG_ON(list_empty(&head->lru) &&
!test_bit(STRIPE_EXPANDING, &head->state));
+ inc_empty_inactive_list_flag = 0;
+ if (!list_empty(conf->inactive_list + hash))
+ inc_empty_inactive_list_flag = 1;
list_del_init(&head->lru);
+ if (list_empty(conf->inactive_list + hash) && inc_empty_inactive_list_flag)
+ atomic_inc(&conf->empty_inactive_list_nr);
if (head->group) {
head->group->stripes_cnt--;
head->group = NULL;
set_bit(STRIPE_IO_STARTED, &sh->state);
- bio_reset(bi);
bi->bi_bdev = rdev->bdev;
bio_set_op_attrs(bi, op, op_flags);
bi->bi_end_io = op_is_write(op)
set_bit(STRIPE_IO_STARTED, &sh->state);
- bio_reset(rbi);
rbi->bi_bdev = rrdev->bdev;
bio_set_op_attrs(rbi, op, op_flags);
BUG_ON(!op_is_write(op));
put_cpu();
}
-static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp)
+static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp,
+ int disks)
{
struct stripe_head *sh;
+ int i;
sh = kmem_cache_zalloc(sc, gfp);
if (sh) {
INIT_LIST_HEAD(&sh->batch_list);
INIT_LIST_HEAD(&sh->lru);
atomic_set(&sh->count, 1);
+ for (i = 0; i < disks; i++) {
+ struct r5dev *dev = &sh->dev[i];
+
+ bio_init(&dev->req);
+ dev->req.bi_io_vec = &dev->vec;
+ dev->req.bi_max_vecs = 1;
+
+ bio_init(&dev->rreq);
+ dev->rreq.bi_io_vec = &dev->rvec;
+ dev->rreq.bi_max_vecs = 1;
+ }
}
return sh;
}
{
struct stripe_head *sh;
- sh = alloc_stripe(conf->slab_cache, gfp);
+ sh = alloc_stripe(conf->slab_cache, gfp, conf->pool_size);
if (!sh)
return 0;
mutex_lock(&conf->cache_size_mutex);
for (i = conf->max_nr_stripes; i; i--) {
- nsh = alloc_stripe(sc, GFP_KERNEL);
+ nsh = alloc_stripe(sc, GFP_KERNEL, newsize);
if (!nsh)
break;
(unsigned long long)sh->sector, i, atomic_read(&sh->count),
bi->bi_error);
if (i == disks) {
+ bio_reset(bi);
BUG();
return;
}
}
}
rdev_dec_pending(rdev, conf->mddev);
+ bio_reset(bi);
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
raid5_release_stripe(sh);
(unsigned long long)sh->sector, i, atomic_read(&sh->count),
bi->bi_error);
if (i == disks) {
+ bio_reset(bi);
BUG();
return;
}
if (sh->batch_head && bi->bi_error && !replacement)
set_bit(STRIPE_BATCH_ERR, &sh->batch_head->state);
+ bio_reset(bi);
if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
{
struct r5dev *dev = &sh->dev[i];
- bio_init(&dev->req);
- dev->req.bi_io_vec = &dev->vec;
- dev->req.bi_max_vecs = 1;
- dev->req.bi_private = sh;
-
- bio_init(&dev->rreq);
- dev->rreq.bi_io_vec = &dev->rvec;
- dev->rreq.bi_max_vecs = 1;
- dev->rreq.bi_private = sh;
-
dev->flags = 0;
dev->sector = raid5_compute_blocknr(sh, i, previous);
}
}
if (!bio_list_empty(&s.return_bi)) {
- if (test_bit(MD_CHANGE_PENDING, &conf->mddev->flags)) {
+ if (test_bit(MD_CHANGE_PENDING, &conf->mddev->flags) &&
+ (s.failed <= conf->max_degraded ||
+ conf->mddev->external == 0)) {
spin_lock_irq(&conf->device_lock);
bio_list_merge(&conf->return_bi, &s.return_bi);
spin_unlock_irq(&conf->device_lock);
}
conf->min_nr_stripes = NR_STRIPES;
+ if (mddev->reshape_position != MaxSector) {
+ int stripes = max_t(int,
+ ((mddev->chunk_sectors << 9) / STRIPE_SIZE) * 4,
+ ((mddev->new_chunk_sectors << 9) / STRIPE_SIZE) * 4);
+ conf->min_nr_stripes = max(NR_STRIPES, stripes);
+ if (conf->min_nr_stripes != NR_STRIPES)
+ printk(KERN_INFO
+ "md/raid:%s: force stripe size %d for reshape\n",
+ mdname(mddev), conf->min_nr_stripes);
+ }
memory = conf->min_nr_stripes * (sizeof(struct stripe_head) +
max_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024;
atomic_set(&conf->empty_inactive_list_nr, NR_STRIPE_HASH_LOCKS);
if (IS_ERR(conf))
return PTR_ERR(conf);
- if (test_bit(MD_HAS_JOURNAL, &mddev->flags) && !journal_dev) {
- printk(KERN_ERR "md/raid:%s: journal disk is missing, force array readonly\n",
- mdname(mddev));
- mddev->ro = 1;
- set_disk_ro(mddev->gendisk, 1);
+ if (test_bit(MD_HAS_JOURNAL, &mddev->flags)) {
+ if (!journal_dev) {
+ pr_err("md/raid:%s: journal disk is missing, force array readonly\n",
+ mdname(mddev));
+ mddev->ro = 1;
+ set_disk_ro(mddev->gendisk, 1);
+ } else if (mddev->recovery_cp == MaxSector)
+ set_bit(MD_JOURNAL_CLEAN, &mddev->flags);
}
conf->min_offset_diff = min_offset_diff;
u8 tag = edid[i] >> 5;
u8 len = edid[i] & 0x1f;
- if (tag == 3 && len >= 5 && i + len <= end)
+ if (tag == 3 && len >= 5 && i + len <= end &&
+ edid[i + 1] == 0x03 &&
+ edid[i + 2] == 0x0c &&
+ edid[i + 3] == 0x00)
return i + 4;
i += len + 1;
} while (i < end);
q->mem_ops = &vb2_dma_sg_memops;
q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
q->lock = &dev->lock;
+ q->dev = &dev->pci->dev;
err = vb2_queue_init(q);
if (err < 0)
q->buf_struct_size = sizeof(struct saa7134_buf);
q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
q->lock = &dev->lock;
+ q->dev = &dev->pci->dev;
ret = vb2_queue_init(q);
if (ret) {
vb2_dvb_dealloc_frontends(&dev->frontends);
q->buf_struct_size = sizeof(struct saa7134_buf);
q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
q->lock = &dev->lock;
+ q->dev = &dev->pci->dev;
err = vb2_queue_init(q);
if (err)
return err;
config VIDEO_MEDIATEK_VCODEC
tristate "Mediatek Video Codec driver"
depends on MTK_IOMMU || COMPILE_TEST
- depends on VIDEO_DEV && VIDEO_V4L2
+ depends on VIDEO_DEV && VIDEO_V4L2 && HAS_DMA
depends on ARCH_MEDIATEK || COMPILE_TEST
select VIDEOBUF2_DMA_CONTIG
select V4L2_MEM2MEM_DEV
#include <media/v4l2-ioctl.h>
#include <media/videobuf2-core.h>
-#include "mtk_vcodec_util.h"
#define MTK_VCODEC_DRV_NAME "mtk_vcodec_drv"
#define MTK_VCODEC_ENC_NAME "mtk-vcodec-enc"
struct mtk_q_data *q_data;
int ret, i;
struct mtk_video_fmt *fmt;
- unsigned int pitch_w_div16;
struct v4l2_pix_format_mplane *pix_fmt_mp = &f->fmt.pix_mp;
vq = v4l2_m2m_get_vq(ctx->m2m_ctx, f->type);
q_data->coded_width = f->fmt.pix_mp.width;
q_data->coded_height = f->fmt.pix_mp.height;
- pitch_w_div16 = DIV_ROUND_UP(q_data->visible_width, 16);
- if (pitch_w_div16 % 8 != 0) {
- /* Adjust returned width/height, so application could correctly
- * allocate hw required memory
- */
- q_data->visible_height += 32;
- vidioc_try_fmt(f, q_data->fmt);
- }
-
q_data->field = f->fmt.pix_mp.field;
ctx->colorspace = f->fmt.pix_mp.colorspace;
ctx->ycbcr_enc = f->fmt.pix_mp.ycbcr_enc;
{
struct mtk_vcodec_ctx *ctx = priv;
int ret;
- struct vb2_buffer *dst_buf;
+ struct vb2_buffer *src_buf, *dst_buf;
+ struct vb2_v4l2_buffer *dst_vb2_v4l2, *src_vb2_v4l2;
struct mtk_vcodec_mem bs_buf;
struct venc_done_result enc_result;
mtk_v4l2_err("venc_if_encode failed=%d", ret);
return -EINVAL;
}
+ src_buf = v4l2_m2m_next_src_buf(ctx->m2m_ctx);
+ if (src_buf) {
+ src_vb2_v4l2 = to_vb2_v4l2_buffer(src_buf);
+ dst_vb2_v4l2 = to_vb2_v4l2_buffer(dst_buf);
+ dst_buf->timestamp = src_buf->timestamp;
+ dst_vb2_v4l2->timecode = src_vb2_v4l2->timecode;
+ } else {
+ mtk_v4l2_err("No timestamp for the header buffer.");
+ }
ctx->state = MTK_STATE_HEADER;
dst_buf->planes[0].bytesused = enc_result.bs_size;
struct mtk_vcodec_mem bs_buf;
struct venc_done_result enc_result;
int ret, i;
- struct vb2_v4l2_buffer *vb2_v4l2;
+ struct vb2_v4l2_buffer *dst_vb2_v4l2, *src_vb2_v4l2;
/* check dst_buf, dst_buf may be removed in device_run
* to stored encdoe header so we need check dst_buf and
ret = venc_if_encode(ctx, VENC_START_OPT_ENCODE_FRAME,
&frm_buf, &bs_buf, &enc_result);
- vb2_v4l2 = container_of(dst_buf, struct vb2_v4l2_buffer, vb2_buf);
+ src_vb2_v4l2 = to_vb2_v4l2_buffer(src_buf);
+ dst_vb2_v4l2 = to_vb2_v4l2_buffer(dst_buf);
+
+ dst_buf->timestamp = src_buf->timestamp;
+ dst_vb2_v4l2->timecode = src_vb2_v4l2->timecode;
+
if (enc_result.is_key_frm)
- vb2_v4l2->flags |= V4L2_BUF_FLAG_KEYFRAME;
+ dst_vb2_v4l2->flags |= V4L2_BUF_FLAG_KEYFRAME;
if (ret) {
v4l2_m2m_buf_done(to_vb2_v4l2_buffer(src_buf),
0, V4L2_MPEG_VIDEO_HEADER_MODE_SEPARATE);
v4l2_ctrl_new_std_menu(handler, ops, V4L2_CID_MPEG_VIDEO_H264_PROFILE,
V4L2_MPEG_VIDEO_H264_PROFILE_HIGH,
- 0, V4L2_MPEG_VIDEO_H264_PROFILE_MAIN);
+ 0, V4L2_MPEG_VIDEO_H264_PROFILE_HIGH);
v4l2_ctrl_new_std_menu(handler, ops, V4L2_CID_MPEG_VIDEO_H264_LEVEL,
V4L2_MPEG_VIDEO_H264_LEVEL_4_2,
0, V4L2_MPEG_VIDEO_H264_LEVEL_4_0);
void mtk_vcodec_enc_release(struct mtk_vcodec_ctx *ctx)
{
- venc_if_deinit(ctx);
+ int ret = venc_if_deinit(ctx);
+
+ if (ret)
+ mtk_v4l2_err("venc_if_deinit failed=%d", ret);
+
+ ctx->state = MTK_STATE_FREE;
}
mtk_v4l2_debug(1, "[%d] encoder", ctx->id);
mutex_lock(&dev->dev_mutex);
+ /*
+ * Call v4l2_m2m_ctx_release to make sure the worker thread is not
+ * running after venc_if_deinit.
+ */
+ v4l2_m2m_ctx_release(ctx->m2m_ctx);
mtk_vcodec_enc_release(ctx);
v4l2_fh_del(&ctx->fh);
v4l2_fh_exit(&ctx->fh);
v4l2_ctrl_handler_free(&ctx->ctrl_hdl);
- v4l2_m2m_ctx_release(ctx->m2m_ctx);
list_del_init(&ctx->list);
dev->num_instances--;
#define _MTK_VCODEC_INTR_H_
#define MTK_INST_IRQ_RECEIVED 0x1
-#define MTK_INST_WORK_THREAD_ABORT_DONE 0x2
struct mtk_vcodec_ctx;
/*
* struct venc_h264_vpu_config - Structure for h264 encoder configuration
+ * AP-W/R : AP is writer/reader on this item
+ * VPU-W/R: VPU is write/reader on this item
* @input_fourcc: input fourcc
* @bitrate: target bitrate (in bps)
* @pic_w: picture width. Picture size is visible stream resolution, in pixels,
/*
* struct venc_h264_vpu_buf - Structure for buffer information
- * @align: buffer alignment (in bytes)
+ * AP-W/R : AP is writer/reader on this item
+ * VPU-W/R: VPU is write/reader on this item
* @iova: IO virtual address
* @vpua: VPU side memory addr which is used by RC_CODE
* @size: buffer size (in bytes)
*/
struct venc_h264_vpu_buf {
- u32 align;
u32 iova;
u32 vpua;
u32 size;
/*
* struct venc_h264_vsi - Structure for VPU driver control and info share
+ * AP-W/R : AP is writer/reader on this item
+ * VPU-W/R: VPU is write/reader on this item
* This structure is allocated in VPU side and shared to AP side.
* @config: h264 encoder configuration
* @work_bufs: working buffer information in VPU side
struct mtk_vcodec_ctx *ctx;
};
-static inline void h264_write_reg(struct venc_h264_inst *inst, u32 addr,
- u32 val)
-{
- writel(val, inst->hw_base + addr);
-}
-
static inline u32 h264_read_reg(struct venc_h264_inst *inst, u32 addr)
{
return readl(inst->hw_base + addr);
return 40;
case V4L2_MPEG_VIDEO_H264_LEVEL_4_1:
return 41;
+ case V4L2_MPEG_VIDEO_H264_LEVEL_4_2:
+ return 42;
default:
mtk_vcodec_debug(inst, "unsupported level %d", level);
return 31;
/*
* struct venc_vp8_vpu_config - Structure for vp8 encoder configuration
+ * AP-W/R : AP is writer/reader on this item
+ * VPU-W/R: VPU is write/reader on this item
* @input_fourcc: input fourcc
* @bitrate: target bitrate (in bps)
* @pic_w: picture width. Picture size is visible stream resolution, in pixels,
};
/*
- * struct venc_vp8_vpu_buf -Structure for buffer information
- * @align: buffer alignment (in bytes)
+ * struct venc_vp8_vpu_buf - Structure for buffer information
+ * AP-W/R : AP is writer/reader on this item
+ * VPU-W/R: VPU is write/reader on this item
* @iova: IO virtual address
* @vpua: VPU side memory addr which is used by RC_CODE
* @size: buffer size (in bytes)
*/
struct venc_vp8_vpu_buf {
- u32 align;
u32 iova;
u32 vpua;
u32 size;
/*
* struct venc_vp8_vsi - Structure for VPU driver control and info share
+ * AP-W/R : AP is writer/reader on this item
+ * VPU-W/R: VPU is write/reader on this item
* This structure is allocated in VPU side and shared to AP side.
* @config: vp8 encoder configuration
* @work_bufs: working buffer information in VPU side
struct mtk_vcodec_ctx *ctx;
};
-static inline void vp8_enc_write_reg(struct venc_vp8_inst *inst, u32 addr,
- u32 val)
-{
- writel(val, inst->hw_base + addr);
-}
-
static inline u32 vp8_enc_read_reg(struct venc_vp8_inst *inst, u32 addr)
{
return readl(inst->hw_base + addr);
*/
int rcar_fcp_enable(struct rcar_fcp_device *fcp)
{
+ int error;
+
if (!fcp)
return 0;
- return pm_runtime_get_sync(fcp->dev);
+ error = pm_runtime_get_sync(fcp->dev);
+ if (error < 0)
+ return error;
+
+ return 0;
}
EXPORT_SYMBOL_GPL(rcar_fcp_enable);
return 0;
}
-static int gpmc_probe_dt_children(struct platform_device *pdev)
+static void gpmc_probe_dt_children(struct platform_device *pdev)
{
int ret;
struct device_node *child;
else
ret = gpmc_probe_generic_child(pdev, child);
- if (ret)
- return ret;
+ if (ret) {
+ dev_err(&pdev->dev, "failed to probe DT child '%s': %d\n",
+ child->name, ret);
+ }
}
-
- return 0;
}
#else
static int gpmc_probe_dt(struct platform_device *pdev)
return 0;
}
-static int gpmc_probe_dt_children(struct platform_device *pdev)
+static void gpmc_probe_dt_children(struct platform_device *pdev)
{
- return 0;
}
#endif /* CONFIG_OF */
goto setup_irq_failed;
}
- rc = gpmc_probe_dt_children(pdev);
- if (rc < 0) {
- dev_err(gpmc->dev, "failed to probe DT children\n");
- goto dt_children_failed;
- }
+ gpmc_probe_dt_children(pdev);
return 0;
-dt_children_failed:
- gpmc_free_irq(gpmc);
setup_irq_failed:
gpmc_gpio_exit(gpmc);
gpio_init_failed:
This driver can also be built as a module. If so, the module
will be called tsl2550.
-config SENSORS_BH1780
- tristate "ROHM BH1780GLI ambient light sensor"
- depends on I2C && SYSFS
- help
- If you say yes here you get support for the ROHM BH1780GLI
- ambient light sensor.
-
- This driver can also be built as a module. If so, the module
- will be called bh1780gli.
-
config SENSORS_BH1770
tristate "BH1770GLC / SFH7770 combined ALS - Proximity sensor"
depends on I2C
obj-$(CONFIG_TIFM_7XX1) += tifm_7xx1.o
obj-$(CONFIG_PHANTOM) += phantom.o
obj-$(CONFIG_QCOM_COINCELL) += qcom-coincell.o
-obj-$(CONFIG_SENSORS_BH1780) += bh1780gli.o
obj-$(CONFIG_SENSORS_BH1770) += bh1770glc.o
obj-$(CONFIG_SENSORS_APDS990X) += apds990x.o
obj-$(CONFIG_SGI_IOC4) += ioc4.o
OBJCOPYFLAGS_lkdtm_rodata_objcopy.o := \
--set-section-flags .text=alloc,readonly \
--rename-section .text=.rodata
-$(obj)/lkdtm_rodata_objcopy.o: $(obj)/lkdtm_rodata.o
+targets += lkdtm_rodata.o lkdtm_rodata_objcopy.o
+$(obj)/lkdtm_rodata_objcopy.o: $(obj)/lkdtm_rodata.o FORCE
$(call if_changed,objcopy)
+++ /dev/null
-/*
- * bh1780gli.c
- * ROHM Ambient Light Sensor Driver
- *
- * Copyright (C) 2010 Texas Instruments
- * Author: Hemanth V <hemanthv@ti.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program. If not, see <http://www.gnu.org/licenses/>.
- */
-#include <linux/i2c.h>
-#include <linux/slab.h>
-#include <linux/mutex.h>
-#include <linux/platform_device.h>
-#include <linux/delay.h>
-#include <linux/module.h>
-#include <linux/of.h>
-
-#define BH1780_REG_CONTROL 0x80
-#define BH1780_REG_PARTID 0x8A
-#define BH1780_REG_MANFID 0x8B
-#define BH1780_REG_DLOW 0x8C
-#define BH1780_REG_DHIGH 0x8D
-
-#define BH1780_REVMASK (0xf)
-#define BH1780_POWMASK (0x3)
-#define BH1780_POFF (0x0)
-#define BH1780_PON (0x3)
-
-/* power on settling time in ms */
-#define BH1780_PON_DELAY 2
-
-struct bh1780_data {
- struct i2c_client *client;
- int power_state;
- /* lock for sysfs operations */
- struct mutex lock;
-};
-
-static int bh1780_write(struct bh1780_data *ddata, u8 reg, u8 val, char *msg)
-{
- int ret = i2c_smbus_write_byte_data(ddata->client, reg, val);
- if (ret < 0)
- dev_err(&ddata->client->dev,
- "i2c_smbus_write_byte_data failed error %d Register (%s)\n",
- ret, msg);
- return ret;
-}
-
-static int bh1780_read(struct bh1780_data *ddata, u8 reg, char *msg)
-{
- int ret = i2c_smbus_read_byte_data(ddata->client, reg);
- if (ret < 0)
- dev_err(&ddata->client->dev,
- "i2c_smbus_read_byte_data failed error %d Register (%s)\n",
- ret, msg);
- return ret;
-}
-
-static ssize_t bh1780_show_lux(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct platform_device *pdev = to_platform_device(dev);
- struct bh1780_data *ddata = platform_get_drvdata(pdev);
- int lsb, msb;
-
- lsb = bh1780_read(ddata, BH1780_REG_DLOW, "DLOW");
- if (lsb < 0)
- return lsb;
-
- msb = bh1780_read(ddata, BH1780_REG_DHIGH, "DHIGH");
- if (msb < 0)
- return msb;
-
- return sprintf(buf, "%d\n", (msb << 8) | lsb);
-}
-
-static ssize_t bh1780_show_power_state(struct device *dev,
- struct device_attribute *attr,
- char *buf)
-{
- struct platform_device *pdev = to_platform_device(dev);
- struct bh1780_data *ddata = platform_get_drvdata(pdev);
- int state;
-
- state = bh1780_read(ddata, BH1780_REG_CONTROL, "CONTROL");
- if (state < 0)
- return state;
-
- return sprintf(buf, "%d\n", state & BH1780_POWMASK);
-}
-
-static ssize_t bh1780_store_power_state(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct platform_device *pdev = to_platform_device(dev);
- struct bh1780_data *ddata = platform_get_drvdata(pdev);
- unsigned long val;
- int error;
-
- error = kstrtoul(buf, 0, &val);
- if (error)
- return error;
-
- if (val < BH1780_POFF || val > BH1780_PON)
- return -EINVAL;
-
- mutex_lock(&ddata->lock);
-
- error = bh1780_write(ddata, BH1780_REG_CONTROL, val, "CONTROL");
- if (error < 0) {
- mutex_unlock(&ddata->lock);
- return error;
- }
-
- msleep(BH1780_PON_DELAY);
- ddata->power_state = val;
- mutex_unlock(&ddata->lock);
-
- return count;
-}
-
-static DEVICE_ATTR(lux, S_IRUGO, bh1780_show_lux, NULL);
-
-static DEVICE_ATTR(power_state, S_IWUSR | S_IRUGO,
- bh1780_show_power_state, bh1780_store_power_state);
-
-static struct attribute *bh1780_attributes[] = {
- &dev_attr_power_state.attr,
- &dev_attr_lux.attr,
- NULL
-};
-
-static const struct attribute_group bh1780_attr_group = {
- .attrs = bh1780_attributes,
-};
-
-static int bh1780_probe(struct i2c_client *client,
- const struct i2c_device_id *id)
-{
- int ret;
- struct bh1780_data *ddata;
- struct i2c_adapter *adapter = to_i2c_adapter(client->dev.parent);
-
- if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE))
- return -EIO;
-
- ddata = devm_kzalloc(&client->dev, sizeof(struct bh1780_data),
- GFP_KERNEL);
- if (ddata == NULL)
- return -ENOMEM;
-
- ddata->client = client;
- i2c_set_clientdata(client, ddata);
-
- ret = bh1780_read(ddata, BH1780_REG_PARTID, "PART ID");
- if (ret < 0)
- return ret;
-
- dev_info(&client->dev, "Ambient Light Sensor, Rev : %d\n",
- (ret & BH1780_REVMASK));
-
- mutex_init(&ddata->lock);
-
- return sysfs_create_group(&client->dev.kobj, &bh1780_attr_group);
-}
-
-static int bh1780_remove(struct i2c_client *client)
-{
- sysfs_remove_group(&client->dev.kobj, &bh1780_attr_group);
-
- return 0;
-}
-
-#ifdef CONFIG_PM_SLEEP
-static int bh1780_suspend(struct device *dev)
-{
- struct bh1780_data *ddata;
- int state, ret;
- struct i2c_client *client = to_i2c_client(dev);
-
- ddata = i2c_get_clientdata(client);
- state = bh1780_read(ddata, BH1780_REG_CONTROL, "CONTROL");
- if (state < 0)
- return state;
-
- ddata->power_state = state & BH1780_POWMASK;
-
- ret = bh1780_write(ddata, BH1780_REG_CONTROL, BH1780_POFF,
- "CONTROL");
-
- if (ret < 0)
- return ret;
-
- return 0;
-}
-
-static int bh1780_resume(struct device *dev)
-{
- struct bh1780_data *ddata;
- int state, ret;
- struct i2c_client *client = to_i2c_client(dev);
-
- ddata = i2c_get_clientdata(client);
- state = ddata->power_state;
- ret = bh1780_write(ddata, BH1780_REG_CONTROL, state,
- "CONTROL");
-
- if (ret < 0)
- return ret;
-
- return 0;
-}
-#endif /* CONFIG_PM_SLEEP */
-
-static SIMPLE_DEV_PM_OPS(bh1780_pm, bh1780_suspend, bh1780_resume);
-
-static const struct i2c_device_id bh1780_id[] = {
- { "bh1780", 0 },
- { },
-};
-
-MODULE_DEVICE_TABLE(i2c, bh1780_id);
-
-#ifdef CONFIG_OF
-static const struct of_device_id of_bh1780_match[] = {
- { .compatible = "rohm,bh1780gli", },
- {},
-};
-
-MODULE_DEVICE_TABLE(of, of_bh1780_match);
-#endif
-
-static struct i2c_driver bh1780_driver = {
- .probe = bh1780_probe,
- .remove = bh1780_remove,
- .id_table = bh1780_id,
- .driver = {
- .name = "bh1780",
- .pm = &bh1780_pm,
- .of_match_table = of_match_ptr(of_bh1780_match),
- },
-};
-
-module_i2c_driver(bh1780_driver);
-
-MODULE_DESCRIPTION("BH1780GLI Ambient Light Sensor Driver");
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Hemanth V <hemanthv@ti.com>");
*/
mutex_lock(&afu->contexts_lock);
idr_preload(GFP_KERNEL);
- i = idr_alloc(&ctx->afu->contexts_idr, ctx,
- ctx->afu->adapter->native->sl_ops->min_pe,
+ i = idr_alloc(&ctx->afu->contexts_idr, ctx, ctx->afu->adapter->min_pe,
ctx->afu->num_procs, GFP_NOWAIT);
idr_preload_end();
mutex_unlock(&afu->contexts_lock);
u64 (*timebase_read)(struct cxl *adapter);
int capi_mode;
bool needs_reset_before_disable;
- int min_pe;
};
struct cxl_native {
struct bin_attribute cxl_attr;
int adapter_num;
int user_irqs;
+ int min_pe;
u64 ps_size;
u16 psl_rev;
u16 base_image;
return fail_psl_irq(afu, &irq_info);
}
-void native_irq_wait(struct cxl_context *ctx)
+static void native_irq_wait(struct cxl_context *ctx)
{
u64 dsisr;
int timeout = 1000;
static int init_implementation_adapter_psl_regs(struct cxl *adapter, struct pci_dev *dev)
{
- u64 psl_dsnctl;
+ u64 psl_dsnctl, psl_fircntl;
u64 chipid;
u64 capp_unit_id;
int rc;
cxl_p1_write(adapter, CXL_PSL_RESLCKTO, 0x20000000200ULL);
/* snoop write mask */
cxl_p1_write(adapter, CXL_PSL_SNWRALLOC, 0x00000000FFFFFFFFULL);
- /* set fir_accum */
- cxl_p1_write(adapter, CXL_PSL_FIR_CNTL, 0x0800000000000000ULL);
+ /* set fir_cntl to recommended value for production env */
+ psl_fircntl = (0x2ULL << (63-3)); /* ce_report */
+ psl_fircntl |= (0x1ULL << (63-6)); /* FIR_report */
+ psl_fircntl |= 0x1ULL; /* ce_thresh */
+ cxl_p1_write(adapter, CXL_PSL_FIR_CNTL, psl_fircntl);
/* for debugging with trace arrays */
cxl_p1_write(adapter, CXL_PSL_TRACE, 0x0000FF7C00000000ULL);
.write_timebase_ctrl = write_timebase_ctrl_xsl,
.timebase_read = timebase_read_xsl,
.capi_mode = OPAL_PHB_CAPI_MODE_DMA,
- .min_pe = 1, /* Workaround for Mellanox CX4 HW bug */
};
static void set_sl_ops(struct cxl *adapter, struct pci_dev *dev)
{
if (dev->vendor == PCI_VENDOR_ID_MELLANOX && dev->device == 0x1013) {
+ /* Mellanox CX-4 */
dev_info(&adapter->dev, "Device uses an XSL\n");
adapter->native->sl_ops = &xsl_ops;
+ adapter->min_pe = 1; /* Workaround for CX-4 hardware bug */
} else {
dev_info(&adapter->dev, "Device uses a PSL\n");
adapter->native->sl_ops = &psl_ops;
/* Setup the PHB using arch provided callback */
phb->ops = &cxl_pcie_pci_ops;
phb->cfg_addr = NULL;
- phb->cfg_data = 0;
+ phb->cfg_data = NULL;
phb->private_data = afu;
phb->controller_ops = cxl_pci_controller_ops;
if (phb->bus == NULL)
return -ENXIO;
+ /* Set release hook on root bus */
+ pci_set_host_bridge_release(to_pci_host_bridge(phb->bus->bridge),
+ pcibios_free_controller_deferred,
+ (void *) phb);
+
/* Claim resources. This might need some rework as well depending
* whether we are doing probe-only or not, like assigning unassigned
* resources etc...
afu->phb = NULL;
pci_remove_root_bus(phb->bus);
- pcibios_free_controller(phb);
+ /*
+ * We don't free phb here - that's handled by
+ * pcibios_free_controller_deferred()
+ */
}
static bool _cxl_pci_is_vphb_device(struct pci_controller *phb)
*/
#include "lkdtm.h"
-void lkdtm_rodata_do_nothing(void)
+void notrace lkdtm_rodata_do_nothing(void)
{
/* Does nothing. We just want an architecture agnostic "return". */
}
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
-static size_t cache_size = 1024;
+/*
+ * Many of the tests here end up using const sizes, but those would
+ * normally be ignored by hardened usercopy, so force the compiler
+ * into choosing the non-const path to make sure we trigger the
+ * hardened usercopy checks by added "unconst" to all the const copies,
+ * and making sure "cache_size" isn't optimized into a const.
+ */
+static volatile size_t unconst = 0;
+static volatile size_t cache_size = 1024;
static struct kmem_cache *bad_cache;
static const unsigned char test_text[] = "This is a test.\n";
/* This is a pointer to outside our current stack frame. */
if (bad_frame) {
- bad_stack = do_usercopy_stack_callee((uintptr_t)bad_stack);
+ bad_stack = do_usercopy_stack_callee((uintptr_t)&bad_stack);
} else {
/* Put start address just inside stack. */
bad_stack = task_stack_page(current) + THREAD_SIZE;
if (to_user) {
pr_info("attempting good copy_to_user of local stack\n");
if (copy_to_user((void __user *)user_addr, good_stack,
- sizeof(good_stack))) {
+ unconst + sizeof(good_stack))) {
pr_warn("copy_to_user failed unexpectedly?!\n");
goto free_user;
}
pr_info("attempting bad copy_to_user of distant stack\n");
if (copy_to_user((void __user *)user_addr, bad_stack,
- sizeof(good_stack))) {
+ unconst + sizeof(good_stack))) {
pr_warn("copy_to_user failed, but lacked Oops\n");
goto free_user;
}
pr_info("attempting good copy_from_user of local stack\n");
if (copy_from_user(good_stack, (void __user *)user_addr,
- sizeof(good_stack))) {
+ unconst + sizeof(good_stack))) {
pr_warn("copy_from_user failed unexpectedly?!\n");
goto free_user;
}
pr_info("attempting bad copy_from_user of distant stack\n");
if (copy_from_user(bad_stack, (void __user *)user_addr,
- sizeof(good_stack))) {
+ unconst + sizeof(good_stack))) {
pr_warn("copy_from_user failed, but lacked Oops\n");
goto free_user;
}
{
unsigned long user_addr;
unsigned char *one, *two;
- const size_t size = 1024;
+ size_t size = unconst + 1024;
one = kmalloc(size, GFP_KERNEL);
two = kmalloc(size, GFP_KERNEL);
pr_info("attempting good copy_to_user from kernel rodata\n");
if (copy_to_user((void __user *)user_addr, test_text,
- sizeof(test_text))) {
+ unconst + sizeof(test_text))) {
pr_warn("copy_to_user failed unexpectedly?!\n");
goto free_user;
}
pr_info("attempting bad copy_to_user from kernel text\n");
- if (copy_to_user((void __user *)user_addr, vm_mmap, PAGE_SIZE)) {
+ if (copy_to_user((void __user *)user_addr, vm_mmap,
+ unconst + PAGE_SIZE)) {
pr_warn("copy_to_user failed, but lacked Oops\n");
goto free_user;
}
static bool mei_me_fw_type_sps(struct pci_dev *pdev)
{
u32 reg;
- /* Read ME FW Status check for SPS Firmware */
- pci_read_config_dword(pdev, PCI_CFG_HFS_1, ®);
+ unsigned int devfn;
+
+ /*
+ * Read ME FW Status register to check for SPS Firmware
+ * The SPS FW is only signaled in pci function 0
+ */
+ devfn = PCI_DEVFN(PCI_SLOT(pdev->devfn), 0);
+ pci_bus_read_config_dword(pdev->bus, devfn, PCI_CFG_HFS_1, ®);
trace_mei_pci_cfg_read(&pdev->dev, "PCI_CFG_HFS_1", PCI_CFG_HFS_1, reg);
/* if bits [19:16] = 15, running SPS Firmware */
return (reg & 0xf0000) == 0xf0000;
{MEI_PCI_DEVICE(MEI_DEV_ID_SPT, mei_me_pch8_cfg)},
{MEI_PCI_DEVICE(MEI_DEV_ID_SPT_2, mei_me_pch8_cfg)},
- {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H, mei_me_pch8_cfg)},
- {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H_2, mei_me_pch8_cfg)},
+ {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H, mei_me_pch8_sps_cfg)},
+ {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H_2, mei_me_pch8_sps_cfg)},
{MEI_PCI_DEVICE(MEI_DEV_ID_BXT_M, mei_me_pch8_cfg)},
{MEI_PCI_DEVICE(MEI_DEV_ID_APL_I, mei_me_pch8_cfg)},
break;
if (req_op(next) == REQ_OP_DISCARD ||
+ req_op(next) == REQ_OP_SECURE_ERASE ||
req_op(next) == REQ_OP_FLUSH)
break;
struct mmc_card *card = md->queue.card;
struct mmc_host *host = card->host;
unsigned long flags;
+ bool req_is_special = mmc_req_is_special(req);
if (req && !mq->mqrq_prev->req)
/* claim host only for the first request */
}
out:
- if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) ||
- mmc_req_is_special(req))
+ if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) || req_is_special)
/*
* Release host when there are no more requests
* and after special request(discard, flush) is done.
/*
* We only like normal block requests and discards.
*/
- if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD) {
+ if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD &&
+ req_op(req) != REQ_OP_SECURE_ERASE) {
blk_dump_rq_flags(req, "MMC bad request");
return BLKPREP_KILL;
}
spin_unlock_irq(q->queue_lock);
if (req || mq->mqrq_prev->req) {
+ bool req_is_special = mmc_req_is_special(req);
+
set_current_state(TASK_RUNNING);
mq->issue_fn(mq, req);
cond_resched();
* has been finished. Do not assign it to previous
* request.
*/
- if (mmc_req_is_special(req))
+ if (req_is_special)
mq->mqrq_cur->req = NULL;
mq->mqrq_prev->brq.mrq.data = NULL;
static inline bool mmc_req_is_special(struct request *req)
{
return req &&
- (req_op(req) == REQ_OP_FLUSH || req_op(req) == REQ_OP_DISCARD);
+ (req_op(req) == REQ_OP_FLUSH ||
+ req_op(req) == REQ_OP_DISCARD ||
+ req_op(req) == REQ_OP_SECURE_ERASE);
}
struct request;
div = (host->bus_hz != clock) ? DIV_ROUND_UP(div, 2) : 0;
- dev_info(&slot->mmc->class_dev,
- "Bus speed (slot %d) = %dHz (slot req %dHz, actual %dHZ div = %d)\n",
- slot->id, host->bus_hz, clock,
- div ? ((host->bus_hz / div) >> 1) :
- host->bus_hz, div);
+ if (clock != slot->__clk_old || force_clkinit)
+ dev_info(&slot->mmc->class_dev,
+ "Bus speed (slot %d) = %dHz (slot req %dHz, actual %dHZ div = %d)\n",
+ slot->id, host->bus_hz, clock,
+ div ? ((host->bus_hz / div) >> 1) :
+ host->bus_hz, div);
/* disable clock */
mci_writel(host, CLKENA, 0);
/* inform CIU */
mci_send_cmd(slot, sdmmc_cmd_bits, 0);
+
+ /* keep the last clock value that was requested from core */
+ slot->__clk_old = clock;
}
host->current_speed = clock;
* @queue_node: List node for placing this node in the @queue list of
* &struct dw_mci.
* @clock: Clock rate configured by set_ios(). Protected by host->lock.
+ * @__clk_old: The last clock value that was requested from core.
+ * Keeping track of this helps us to avoid spamming the console.
* @flags: Random state bits associated with the slot.
* @id: Number of this slot.
* @sdio_id: Number of this slot in the SDIO interrupt registers.
struct list_head queue_node;
unsigned int clock;
+ unsigned int __clk_old;
unsigned long flags;
#define DW_MMC_CARD_PRESENT 0
/* Only reconfigure if we have a different burst size */
if (*bp != burst) {
- struct dma_slave_config cfg;
-
- cfg.src_addr = host->phys_base + OMAP_MMC_REG(host, DATA);
- cfg.dst_addr = host->phys_base + OMAP_MMC_REG(host, DATA);
- cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
- cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
- cfg.src_maxburst = burst;
- cfg.dst_maxburst = burst;
+ struct dma_slave_config cfg = {
+ .src_addr = host->phys_base +
+ OMAP_MMC_REG(host, DATA),
+ .dst_addr = host->phys_base +
+ OMAP_MMC_REG(host, DATA),
+ .src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES,
+ .dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES,
+ .src_maxburst = burst,
+ .dst_maxburst = burst,
+ };
if (dmaengine_slave_config(c, &cfg))
goto use_pio;
static int omap_hsmmc_setup_dma_transfer(struct omap_hsmmc_host *host,
struct mmc_request *req)
{
- struct dma_slave_config cfg;
struct dma_async_tx_descriptor *tx;
int ret = 0, i;
struct mmc_data *data = req->data;
struct dma_chan *chan;
+ struct dma_slave_config cfg = {
+ .src_addr = host->mapbase + OMAP_HSMMC_DATA,
+ .dst_addr = host->mapbase + OMAP_HSMMC_DATA,
+ .src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES,
+ .dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES,
+ .src_maxburst = data->blksz / 4,
+ .dst_maxburst = data->blksz / 4,
+ };
/* Sanity check: all the SG entries must be aligned by block size. */
for (i = 0; i < data->sg_len; i++) {
chan = omap_hsmmc_get_dma_chan(host, data);
- cfg.src_addr = host->mapbase + OMAP_HSMMC_DATA;
- cfg.dst_addr = host->mapbase + OMAP_HSMMC_DATA;
- cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
- cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
- cfg.src_maxburst = data->blksz / 4;
- cfg.dst_maxburst = data->blksz / 4;
-
ret = dmaengine_slave_config(chan, &cfg);
if (ret)
return ret;
struct st_mmc_platform_data {
struct reset_control *rstc;
+ struct clk *icnclk;
void __iomem *top_ioaddr;
};
struct sdhci_host *host;
struct st_mmc_platform_data *pdata;
struct sdhci_pltfm_host *pltfm_host;
- struct clk *clk;
+ struct clk *clk, *icnclk;
int ret = 0;
u16 host_version;
struct resource *res;
return PTR_ERR(clk);
}
+ /* ICN clock isn't compulsory, but use it if it's provided. */
+ icnclk = devm_clk_get(&pdev->dev, "icn");
+ if (IS_ERR(icnclk))
+ icnclk = NULL;
+
rstc = devm_reset_control_get(&pdev->dev, NULL);
if (IS_ERR(rstc))
rstc = NULL;
}
clk_prepare_enable(clk);
+ clk_prepare_enable(icnclk);
/* Configure the FlashSS Top registers for setting eMMC TX/RX delay */
res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
}
pltfm_host->clk = clk;
+ pdata->icnclk = icnclk;
/* Configure the Arasan HC inside the flashSS */
st_mmcss_cconfig(np, host);
return 0;
err_out:
+ clk_disable_unprepare(icnclk);
clk_disable_unprepare(clk);
err_of:
sdhci_pltfm_free(pdev);
ret = sdhci_pltfm_unregister(pdev);
+ clk_disable_unprepare(pdata->icnclk);
+
if (rstc)
reset_control_assert(rstc);
if (pdata->rstc)
reset_control_assert(pdata->rstc);
+ clk_disable_unprepare(pdata->icnclk);
clk_disable_unprepare(pltfm_host->clk);
out:
return ret;
struct device_node *np = dev->of_node;
clk_prepare_enable(pltfm_host->clk);
+ clk_prepare_enable(pdata->icnclk);
if (pdata->rstc)
reset_control_deassert(pdata->rstc);
u8 *data, u32 bytes)
{
dma_addr_t addr;
- u32 *p, len, i;
+ u8 *p;
+ u32 len, i, val;
int ret = 0;
addr = dma_map_single(ecc->dev, data, bytes, DMA_TO_DEVICE);
/* Program ECC bytes to OOB: per sector oob = FDM + ECC + SPARE */
len = (config->strength * ECC_PARITY_BITS + 7) >> 3;
- p = (u32 *)(data + bytes);
+ p = data + bytes;
/* write the parity bytes generated by the ECC back to the OOB region */
- for (i = 0; i < len; i++)
- p[i] = readl(ecc->regs + ECC_ENCPAR(i));
+ for (i = 0; i < len; i++) {
+ if ((i % 4) == 0)
+ val = readl(ecc->regs + ECC_ENCPAR(i / 4));
+ p[i] = (val >> ((i % 4) * 8)) & 0xff;
+ }
timeout:
dma_unmap_single(ecc->dev, addr, bytes, DMA_TO_DEVICE);
#define NFI_FSM_MASK (0xf << 16)
#define NFI_ADDRCNTR (0x70)
#define CNTR_MASK GENMASK(16, 12)
+#define ADDRCNTR_SEC_SHIFT (12)
+#define ADDRCNTR_SEC(val) \
+ (((val) & CNTR_MASK) >> ADDRCNTR_SEC_SHIFT)
#define NFI_STRADDR (0x80)
#define NFI_BYTELEN (0x84)
#define NFI_CSEL (0x90)
}
ret = readl_poll_timeout_atomic(nfc->regs + NFI_ADDRCNTR, reg,
- (reg & CNTR_MASK) >= chip->ecc.steps,
+ ADDRCNTR_SEC(reg) >= chip->ecc.steps,
10, MTK_TIMEOUT);
if (ret)
dev_err(dev, "hwecc write timeout\n");
dev_warn(nfc->dev, "read ahb/dma done timeout\n");
rc = readl_poll_timeout_atomic(nfc->regs + NFI_BYTELEN, reg,
- (reg & CNTR_MASK) >= sectors, 10,
+ ADDRCNTR_SEC(reg) >= sectors, 10,
MTK_TIMEOUT);
if (rc < 0) {
dev_err(nfc->dev, "subpage done timeout\n");
struct nand_chip *nand_chip = mtd_to_nand(mtd);
int stepsize = nand_chip->ecc.bytes == 9 ? 16 : 26;
- if (section > nand_chip->ecc.steps)
+ if (section >= nand_chip->ecc.steps)
return -ERANGE;
if (!section) {
MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner; "
"0 for slow, 1 for fast");
module_param(ad_select, charp, 0);
-MODULE_PARM_DESC(ad_select, "803.ad aggregation selection logic; "
+MODULE_PARM_DESC(ad_select, "802.3ad aggregation selection logic; "
"0 for stable (default), 1 for bandwidth, "
"2 for count");
module_param(min_links, int, 0);
slave_dev->name);
}
- /* already enslaved */
- if (slave_dev->flags & IFF_SLAVE) {
- netdev_dbg(bond_dev, "Error: Device was already enslaved\n");
+ /* already in-use? */
+ if (netdev_is_rx_handler_busy(slave_dev)) {
+ netdev_err(bond_dev,
+ "Error: Device is in use and cannot be enslaved\n");
return -EBUSY;
}
struct flexcan_priv *priv = netdev_priv(dev);
int err;
- err = flexcan_chip_disable(priv);
- if (err)
- return err;
-
if (netif_running(dev)) {
+ err = flexcan_chip_disable(priv);
+ if (err)
+ return err;
netif_stop_queue(dev);
netif_device_detach(dev);
}
{
struct net_device *dev = dev_get_drvdata(device);
struct flexcan_priv *priv = netdev_priv(dev);
+ int err;
priv->can.state = CAN_STATE_ERROR_ACTIVE;
if (netif_running(dev)) {
netif_device_attach(dev);
netif_start_queue(dev);
+ err = flexcan_chip_enable(priv);
+ if (err)
+ return err;
}
- return flexcan_chip_enable(priv);
+ return 0;
}
static SIMPLE_DEV_PM_OPS(flexcan_pm_ops, flexcan_suspend, flexcan_resume);
#define IFI_CANFD_TIME_SET_TIMEA_4_12_6_6 BIT(15)
#define IFI_CANFD_TDELAY 0x1c
+#define IFI_CANFD_TDELAY_DEFAULT 0xb
+#define IFI_CANFD_TDELAY_MASK 0x3fff
+#define IFI_CANFD_TDELAY_ABS BIT(14)
+#define IFI_CANFD_TDELAY_EN BIT(15)
#define IFI_CANFD_ERROR 0x20
#define IFI_CANFD_ERROR_TX_OFFSET 0
struct ifi_canfd_priv *priv = netdev_priv(ndev);
const struct can_bittiming *bt = &priv->can.bittiming;
const struct can_bittiming *dbt = &priv->can.data_bittiming;
- u16 brp, sjw, tseg1, tseg2;
+ u16 brp, sjw, tseg1, tseg2, tdc;
/* Configure bit timing */
brp = bt->brp - 2;
(brp << IFI_CANFD_TIME_PRESCALE_OFF) |
(sjw << IFI_CANFD_TIME_SJW_OFF_7_9_8_8),
priv->base + IFI_CANFD_FTIME);
+
+ /* Configure transmitter delay */
+ tdc = (dbt->brp * (dbt->phase_seg1 + 1)) & IFI_CANFD_TDELAY_MASK;
+ writel(IFI_CANFD_TDELAY_EN | IFI_CANFD_TDELAY_ABS | tdc,
+ priv->base + IFI_CANFD_TDELAY);
}
static void ifi_canfd_set_filter(struct net_device *ndev, const u32 id,
* BCM5325 and BCM5365 share most definitions below
*/
#define B53_ARLTBL_MAC_VID_ENTRY(n) (0x10 * (n))
-#define ARLTBL_MAC_MASK 0xffffffffffff
+#define ARLTBL_MAC_MASK 0xffffffffffffULL
#define ARLTBL_VID_S 48
#define ARLTBL_VID_MASK_25 0xff
#define ARLTBL_VID_MASK 0xfff
static inline void intrl2_##which##_mask_clear(struct bcm_sf2_priv *priv, \
u32 mask) \
{ \
- intrl2_##which##_writel(priv, mask, INTRL2_CPU_MASK_CLEAR); \
priv->irq##which##_mask &= ~(mask); \
+ intrl2_##which##_writel(priv, mask, INTRL2_CPU_MASK_CLEAR); \
} \
static inline void intrl2_##which##_mask_set(struct bcm_sf2_priv *priv, \
u32 mask) \
return ret;
}
+ /* Rate Control: disable ingress rate limiting. */
if (mv88e6xxx_6352_family(chip) || mv88e6xxx_6351_family(chip) ||
mv88e6xxx_6165_family(chip) || mv88e6xxx_6097_family(chip) ||
- mv88e6xxx_6185_family(chip) || mv88e6xxx_6095_family(chip) ||
mv88e6xxx_6320_family(chip)) {
- /* Rate Control: disable ingress rate limiting. */
ret = _mv88e6xxx_reg_write(chip, REG_PORT(port),
PORT_RATE_CONTROL, 0x0001);
if (ret)
return ret;
+ } else if (mv88e6xxx_6185_family(chip) || mv88e6xxx_6095_family(chip)) {
+ ret = _mv88e6xxx_reg_write(chip, REG_PORT(port),
+ PORT_RATE_CONTROL, 0x0000);
+ if (ret)
+ return ret;
}
/* Port Control 1: disable trunking, disable sending
return err;
}
+#ifdef CONFIG_NET_DSA_HWMON
static int mv88e6xxx_mdio_page_read(struct dsa_switch *ds, int port, int page,
int reg)
{
return ret;
}
+#endif
static int mv88e6xxx_port_to_mdio_addr(struct mv88e6xxx_chip *chip, int port)
{
netdev_err(ndev, "Could not connect to PHY\n");
return -ENODEV;
}
+#else
+ return -ENODEV;
#endif
}
priv->dev = dev;
priv->regs = devm_ioremap_resource(dev, &res_regs);
- if (IS_ERR(priv->regs))
- return PTR_ERR(priv->regs);
+ if (IS_ERR(priv->regs)) {
+ err = PTR_ERR(priv->regs);
+ goto out_put_node;
+ }
dev_dbg(dev, "Registers base address is 0x%p\n", priv->regs);
.driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG },
{ PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_E2400),
.driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG },
+ { PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_E2500),
+ .driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG },
{ PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_AR8162),
.driver_data = ALX_DEV_QUIRK_MSI_INTX_DISABLE_BUG },
{ PCI_VDEVICE(ATTANSIC, ALX_DEV_ID_AR8171) },
#define ALX_DEV_ID_AR8161 0x1091
#define ALX_DEV_ID_E2200 0xe091
#define ALX_DEV_ID_E2400 0xe0a1
+#define ALX_DEV_ID_E2500 0xe0b1
#define ALX_DEV_ID_AR8162 0x1090
#define ALX_DEV_ID_AR8171 0x10A1
#define ALX_DEV_ID_AR8172 0x10A0
if (!bgmac_is_bcm4707_family(core)) {
mii_bus = bcma_mdio_mii_register(core, bgmac->phyaddr);
- if (!IS_ERR(mii_bus)) {
+ if (IS_ERR(mii_bus)) {
err = PTR_ERR(mii_bus);
goto err;
}
struct bnx2 *bp = netdev_priv(dev);
int rc;
- rc = bnx2_request_firmware(bp);
- if (rc < 0)
- goto out;
-
netif_carrier_off(dev);
bnx2_disable_int(bp);
bnx2_free_irq(bp);
bnx2_free_mem(bp);
bnx2_del_napi(bp);
- bnx2_release_firmware(bp);
goto out;
}
pci_set_drvdata(pdev, dev);
+ rc = bnx2_request_firmware(bp);
+ if (rc < 0)
+ goto error;
+
+
+ bnx2_reset_chip(bp, BNX2_DRV_MSG_CODE_RESET);
memcpy(dev->dev_addr, bp->mac_addr, ETH_ALEN);
dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG |
return 0;
error:
+ bnx2_release_firmware(bp);
pci_iounmap(pdev, bp->regview);
pci_release_regions(pdev);
pci_disable_device(pdev);
(bp->common.bc_ver & 0xff00) >> 8,
(bp->common.bc_ver & 0xff));
+ if (pci_channel_offline(bp->pdev)) {
+ BNX2X_ERR("Cannot dump MCP info while in PCI error\n");
+ return;
+ }
+
val = REG_RD(bp, MCP_REG_MCPR_CPU_PROGRAM_COUNTER);
if (val == REG_RD(bp, MCP_REG_MCPR_CPU_PROGRAM_COUNTER))
BNX2X_ERR("%s" "MCP PC at 0x%x\n", lvl, val);
/* Release IRQs */
bnx2x_free_irq(bp);
- /* Reset the chip */
- rc = bnx2x_reset_hw(bp, reset_code);
- if (rc)
- BNX2X_ERR("HW_RESET failed\n");
+ /* Reset the chip, unless PCI function is offline. If we reach this
+ * point following a PCI error handling, it means device is really
+ * in a bad state and we're about to remove it, so reset the chip
+ * is not a good idea.
+ */
+ if (!pci_channel_offline(bp->pdev)) {
+ rc = bnx2x_reset_hw(bp, reset_code);
+ if (rc)
+ BNX2X_ERR("HW_RESET failed\n");
+ }
/* Report UNLOAD_DONE to MCP */
bnx2x_send_unload_done(bp, keep_link);
push_len = (length + sizeof(*tx_push) + 7) / 8;
if (push_len > 16) {
__iowrite64_copy(txr->tx_doorbell, tx_push_buf, 16);
- __iowrite64_copy(txr->tx_doorbell + 4, tx_push_buf + 1,
- push_len - 16);
+ __iowrite32_copy(txr->tx_doorbell + 4, tx_push_buf + 1,
+ (push_len - 16) << 1);
} else {
__iowrite64_copy(txr->tx_doorbell, tx_push_buf,
push_len);
info->data = TG3_RSS_MAX_NUM_QS;
}
- /* The first interrupt vector only
- * handles link interrupts.
- */
- info->data -= 1;
return 0;
default:
}
if ((ec->rx_coalesce_usecs > MAX_RXCOL_TICKS) ||
+ (!ec->rx_coalesce_usecs) ||
(ec->tx_coalesce_usecs > MAX_TXCOL_TICKS) ||
+ (!ec->tx_coalesce_usecs) ||
(ec->rx_max_coalesced_frames > MAX_RXMAX_FRAMES) ||
(ec->tx_max_coalesced_frames > MAX_TXMAX_FRAMES) ||
(ec->rx_coalesce_usecs_irq > max_rxcoal_tick_int) ||
(ec->stats_block_coalesce_usecs < min_stat_coal_ticks))
return -EINVAL;
- /* No rx interrupts will be generated if both are zero */
- if ((ec->rx_coalesce_usecs == 0) &&
- (ec->rx_max_coalesced_frames == 0))
- return -EINVAL;
-
- /* No tx interrupts will be generated if both are zero */
- if ((ec->tx_coalesce_usecs == 0) &&
- (ec->tx_max_coalesced_frames == 0))
- return -EINVAL;
-
/* Only copy relevant parameters, ignore all others. */
tp->coal.rx_coalesce_usecs = ec->rx_coalesce_usecs;
tp->coal.tx_coalesce_usecs = ec->tx_coalesce_usecs;
#define BNAD_NUM_TXF_COUNTERS 12
#define BNAD_NUM_RXF_COUNTERS 10
#define BNAD_NUM_CQ_COUNTERS (3 + 5)
-#define BNAD_NUM_RXQ_COUNTERS 6
+#define BNAD_NUM_RXQ_COUNTERS 7
#define BNAD_NUM_TXQ_COUNTERS 5
-#define BNAD_ETHTOOL_STATS_NUM \
- (sizeof(struct rtnl_link_stats64) / sizeof(u64) + \
- sizeof(struct bnad_drv_stats) / sizeof(u64) + \
- offsetof(struct bfi_enet_stats, rxf_stats[0]) / sizeof(u64))
-
-static const char *bnad_net_stats_strings[BNAD_ETHTOOL_STATS_NUM] = {
+static const char *bnad_net_stats_strings[] = {
"rx_packets",
"tx_packets",
"rx_bytes",
"tx_dropped",
"multicast",
"collisions",
-
"rx_length_errors",
- "rx_over_errors",
"rx_crc_errors",
"rx_frame_errors",
- "rx_fifo_errors",
- "rx_missed_errors",
-
- "tx_aborted_errors",
- "tx_carrier_errors",
"tx_fifo_errors",
- "tx_heartbeat_errors",
- "tx_window_errors",
-
- "rx_compressed",
- "tx_compressed",
"netif_queue_stop",
"netif_queue_wakeup",
"fc_tx_fid_parity_errors",
};
+#define BNAD_ETHTOOL_STATS_NUM ARRAY_SIZE(bnad_net_stats_strings)
+
static int
bnad_get_settings(struct net_device *netdev, struct ethtool_cmd *cmd)
{
string += ETH_GSTRING_LEN;
sprintf(string, "rxq%d_allocbuf_failed", q_num);
string += ETH_GSTRING_LEN;
+ sprintf(string, "rxq%d_mapbuf_failed", q_num);
+ string += ETH_GSTRING_LEN;
sprintf(string, "rxq%d_producer_index", q_num);
string += ETH_GSTRING_LEN;
sprintf(string, "rxq%d_consumer_index", q_num);
sprintf(string, "rxq%d_allocbuf_failed",
q_num);
string += ETH_GSTRING_LEN;
+ sprintf(string, "rxq%d_mapbuf_failed",
+ q_num);
+ string += ETH_GSTRING_LEN;
sprintf(string, "rxq%d_producer_index",
q_num);
string += ETH_GSTRING_LEN;
u64 *buf)
{
struct bnad *bnad = netdev_priv(netdev);
- int i, j, bi;
+ int i, j, bi = 0;
unsigned long flags;
- struct rtnl_link_stats64 *net_stats64;
+ struct rtnl_link_stats64 net_stats64;
u64 *stats64;
u32 bmap;
* under the same lock
*/
spin_lock_irqsave(&bnad->bna_lock, flags);
- bi = 0;
- memset(buf, 0, stats->n_stats * sizeof(u64));
-
- net_stats64 = (struct rtnl_link_stats64 *)buf;
- bnad_netdev_qstats_fill(bnad, net_stats64);
- bnad_netdev_hwstats_fill(bnad, net_stats64);
- bi = sizeof(*net_stats64) / sizeof(u64);
+ memset(&net_stats64, 0, sizeof(net_stats64));
+ bnad_netdev_qstats_fill(bnad, &net_stats64);
+ bnad_netdev_hwstats_fill(bnad, &net_stats64);
+
+ buf[bi++] = net_stats64.rx_packets;
+ buf[bi++] = net_stats64.tx_packets;
+ buf[bi++] = net_stats64.rx_bytes;
+ buf[bi++] = net_stats64.tx_bytes;
+ buf[bi++] = net_stats64.rx_errors;
+ buf[bi++] = net_stats64.tx_errors;
+ buf[bi++] = net_stats64.rx_dropped;
+ buf[bi++] = net_stats64.tx_dropped;
+ buf[bi++] = net_stats64.multicast;
+ buf[bi++] = net_stats64.collisions;
+ buf[bi++] = net_stats64.rx_length_errors;
+ buf[bi++] = net_stats64.rx_crc_errors;
+ buf[bi++] = net_stats64.rx_frame_errors;
+ buf[bi++] = net_stats64.tx_fifo_errors;
/* Get netif_queue_stopped from stack */
bnad->stats.drv_stats.netif_queue_stopped = netif_queue_stopped(netdev);
return 0;
}
+static inline int macb_clear_csum(struct sk_buff *skb)
+{
+ /* no change for packets without checksum offloading */
+ if (skb->ip_summed != CHECKSUM_PARTIAL)
+ return 0;
+
+ /* make sure we can modify the header */
+ if (unlikely(skb_cow_head(skb, 0)))
+ return -1;
+
+ /* initialize checksum field
+ * This is required - at least for Zynq, which otherwise calculates
+ * wrong UDP header checksums for UDP packets with UDP data len <=2
+ */
+ *(__sum16 *)(skb_checksum_start(skb) + skb->csum_offset) = 0;
+ return 0;
+}
+
static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
u16 queue_index = skb_get_queue_mapping(skb);
return NETDEV_TX_BUSY;
}
+ if (macb_clear_csum(skb)) {
+ dev_kfree_skb_any(skb);
+ return NETDEV_TX_OK;
+ }
+
/* Map socket buffer for DMA transfer */
if (!macb_tx_map(bp, queue, skb)) {
dev_kfree_skb_any(skb);
#define MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII 0x00000004
#define MACB_CAPS_NO_GIGABIT_HALF 0x00000008
#define MACB_CAPS_USRIO_DISABLED 0x00000010
+#define MACB_CAPS_JUMBO 0x00000020
#define MACB_CAPS_FIFO_MODE 0x10000000
#define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000
#define MACB_CAPS_SG_DISABLED 0x40000000
#define MACB_CAPS_MACB_IS_GEM 0x80000000
-#define MACB_CAPS_JUMBO 0x00000010
/* Bit manipulation macros */
#define MACB_BIT(name) \
u8 sqs_id;
bool sqs_mode;
bool hw_tso;
+ bool t88;
/* Receive buffer alloc */
u32 rb_page_offset;
int lmac;
u64 lmac_cfg;
- /* Max value that can be set is 60 */
- if (size > 60)
- size = 60;
+ /* There is a issue in HW where-in while sending GSO sized
+ * pkts as part of TSO, if pkt len falls below this size
+ * NIC will zero PAD packet and also updates IP total length.
+ * Hence set this value to lessthan min pkt size of MAC+IP+TCP
+ * headers, BGX will do the padding to transmit 64 byte pkt.
+ */
+ if (size > 52)
+ size = 52;
for (lmac = 0; lmac < (MAX_BGX_PER_CN88XX * MAX_LMAC_PER_BGX); lmac++) {
lmac_cfg = nic_reg_read(nic, NIC_PF_LMAC_0_7_CFG | (lmac << 3));
#define NIC_QSET_SQ_0_7_DOOR (0x010838)
#define NIC_QSET_SQ_0_7_STATUS (0x010840)
#define NIC_QSET_SQ_0_7_DEBUG (0x010848)
-#define NIC_QSET_SQ_0_7_CNM_CHG (0x010860)
#define NIC_QSET_SQ_0_7_STAT_0_1 (0x010900)
#define NIC_QSET_RBDR_0_1_CFG (0x010C00)
p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_DOOR, q);
p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_STATUS, q);
p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_DEBUG, q);
- p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_CNM_CHG, q);
+ /* Padding, was NIC_QSET_SQ_0_7_CNM_CHG, which
+ * produces bus errors when read
+ */
+ p[i++] = 0;
p[i++] = nicvf_queue_reg_read(nic, NIC_QSET_SQ_0_7_STAT_0_1, q);
reg_offset = NIC_QSET_SQ_0_7_STAT_0_1 | (1 << 3);
p[i++] = nicvf_queue_reg_read(nic, reg_offset, q);
struct nicvf *nic = netdev_priv(netdev);
struct snd_queue *sq;
struct sq_hdr_subdesc *hdr;
+ struct sq_hdr_subdesc *tso_sqe;
sq = &nic->qs->sq[cqe_tx->sq_idx];
nicvf_check_cqe_tx_errs(nic, cq, cqe_tx);
skb = (struct sk_buff *)sq->skbuff[cqe_tx->sqe_ptr];
- /* For TSO offloaded packets only one SQE will have a valid SKB */
if (skb) {
+ /* Check for dummy descriptor used for HW TSO offload on 88xx */
+ if (hdr->dont_send) {
+ /* Get actual TSO descriptors and free them */
+ tso_sqe =
+ (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, hdr->rsvd2);
+ nicvf_put_sq_desc(sq, tso_sqe->subdesc_cnt + 1);
+ }
nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1);
prefetch(skb);
dev_consume_skb_any(skb);
sq->skbuff[cqe_tx->sqe_ptr] = (u64)NULL;
} else {
- /* In case of HW TSO, HW sends a CQE for each segment of a TSO
- * packet instead of a single CQE for the whole TSO packet
- * transmitted. Each of this CQE points to the same SQE, so
- * avoid freeing same SQE multiple times.
+ /* In case of SW TSO on 88xx, only last segment will have
+ * a SKB attached, so just free SQEs here.
*/
if (!nic->hw_tso)
nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1);
struct net_device *netdev;
struct nicvf *nic;
int err, qcount;
+ u16 sdevid;
err = pci_enable_device(pdev);
if (err) {
if (!pass1_silicon(nic->pdev))
nic->hw_tso = true;
+ pci_read_config_word(nic->pdev, PCI_SUBSYSTEM_ID, &sdevid);
+ if (sdevid == 0xA134)
+ nic->t88 = true;
+
/* Check if this VF is in QS only mode */
if (nic->sqs_mode)
return 0;
return num_edescs + sh->gso_segs;
}
+#define POST_CQE_DESC_COUNT 2
+
/* Get the number of SQ descriptors needed to xmit this skb */
static int nicvf_sq_subdesc_required(struct nicvf *nic, struct sk_buff *skb)
{
return subdesc_cnt;
}
+ /* Dummy descriptors to get TSO pkt completion notification */
+ if (nic->t88 && nic->hw_tso && skb_shinfo(skb)->gso_size)
+ subdesc_cnt += POST_CQE_DESC_COUNT;
+
if (skb_shinfo(skb)->nr_frags)
subdesc_cnt += skb_shinfo(skb)->nr_frags;
struct sq_hdr_subdesc *hdr;
hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, qentry);
- sq->skbuff[qentry] = (u64)skb;
-
memset(hdr, 0, SND_QUEUE_DESC_SIZE);
hdr->subdesc_type = SQ_DESC_TYPE_HEADER;
- /* Enable notification via CQE after processing SQE */
- hdr->post_cqe = 1;
- /* No of subdescriptors following this */
- hdr->subdesc_cnt = subdesc_cnt;
+
+ if (nic->t88 && nic->hw_tso && skb_shinfo(skb)->gso_size) {
+ /* post_cqe = 0, to avoid HW posting a CQE for every TSO
+ * segment transmitted on 88xx.
+ */
+ hdr->subdesc_cnt = subdesc_cnt - POST_CQE_DESC_COUNT;
+ } else {
+ sq->skbuff[qentry] = (u64)skb;
+ /* Enable notification via CQE after processing SQE */
+ hdr->post_cqe = 1;
+ /* No of subdescriptors following this */
+ hdr->subdesc_cnt = subdesc_cnt;
+ }
hdr->tot_len = len;
/* Offload checksum calculation to HW */
gather->addr = data;
}
+/* Add HDR + IMMEDIATE subdescriptors right after descriptors of a TSO
+ * packet so that a CQE is posted as a notifation for transmission of
+ * TSO packet.
+ */
+static inline void nicvf_sq_add_cqe_subdesc(struct snd_queue *sq, int qentry,
+ int tso_sqe, struct sk_buff *skb)
+{
+ struct sq_imm_subdesc *imm;
+ struct sq_hdr_subdesc *hdr;
+
+ sq->skbuff[qentry] = (u64)skb;
+
+ hdr = (struct sq_hdr_subdesc *)GET_SQ_DESC(sq, qentry);
+ memset(hdr, 0, SND_QUEUE_DESC_SIZE);
+ hdr->subdesc_type = SQ_DESC_TYPE_HEADER;
+ /* Enable notification via CQE after processing SQE */
+ hdr->post_cqe = 1;
+ /* There is no packet to transmit here */
+ hdr->dont_send = 1;
+ hdr->subdesc_cnt = POST_CQE_DESC_COUNT - 1;
+ hdr->tot_len = 1;
+ /* Actual TSO header SQE index, needed for cleanup */
+ hdr->rsvd2 = tso_sqe;
+
+ qentry = nicvf_get_nxt_sqentry(sq, qentry);
+ imm = (struct sq_imm_subdesc *)GET_SQ_DESC(sq, qentry);
+ memset(imm, 0, SND_QUEUE_DESC_SIZE);
+ imm->subdesc_type = SQ_DESC_TYPE_IMMEDIATE;
+ imm->len = 1;
+}
+
/* Segment a TSO packet into 'gso_size' segments and append
* them to SQ for transfer
*/
int nicvf_sq_append_skb(struct nicvf *nic, struct sk_buff *skb)
{
int i, size;
- int subdesc_cnt;
+ int subdesc_cnt, tso_sqe = 0;
int sq_num, qentry;
struct queue_set *qs;
struct snd_queue *sq;
/* Add SQ header subdesc */
nicvf_sq_add_hdr_subdesc(nic, sq, qentry, subdesc_cnt - 1,
skb, skb->len);
+ tso_sqe = qentry;
/* Add SQ gather subdescs */
qentry = nicvf_get_nxt_sqentry(sq, qentry);
}
doorbell:
+ if (nic->t88 && skb_shinfo(skb)->gso_size) {
+ qentry = nicvf_get_nxt_sqentry(sq, qentry);
+ nicvf_sq_add_cqe_subdesc(sq, qentry, tso_sqe, skb);
+ }
+
/* make sure all memory stores are done before ringing doorbell */
smp_wmb();
unsigned short supported; /* link capabilities */
unsigned short advertising; /* advertised capabilities */
unsigned short lp_advertising; /* peer advertised capabilities */
- unsigned short requested_speed; /* speed user has requested */
- unsigned short speed; /* actual link speed */
+ unsigned int requested_speed; /* speed user has requested */
+ unsigned int speed; /* actual link speed */
unsigned char requested_fc; /* flow control user has requested */
unsigned char fc; /* actual link flow control */
unsigned char autoneg; /* autonegotiating? */
.resume = eeh_resume,
};
+/* Return true if the Link Configuration supports "High Speeds" (those greater
+ * than 1Gb/s).
+ */
static inline bool is_x_10g_port(const struct link_config *lc)
{
- return (lc->supported & FW_PORT_CAP_SPEED_10G) != 0 ||
- (lc->supported & FW_PORT_CAP_SPEED_40G) != 0;
+ unsigned int speeds, high_speeds;
+
+ speeds = FW_PORT_CAP_SPEED_V(FW_PORT_CAP_SPEED_G(lc->supported));
+ high_speeds = speeds & ~(FW_PORT_CAP_SPEED_100M | FW_PORT_CAP_SPEED_1G);
+
+ return high_speeds != 0;
}
static inline void init_rspq(struct adapter *adap, struct sge_rspq *q,
#endif
int ciq_size;
+ /* Reduce memory usage in kdump environment, disable all offload.
+ */
+ if (is_kdump_kernel())
+ adap->params.offload = 0;
+
for_each_port(adap, i)
n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg);
#ifdef CONFIG_CHELSIO_T4_DCB
if (q10g > netif_get_num_default_rss_queues())
q10g = netif_get_num_default_rss_queues();
- /* Reduce memory usage in kdump environment, disable all offload.
- */
- if (is_kdump_kernel())
- adap->params.offload = 0;
-
for_each_port(adap, i) {
struct port_info *pi = adap2pinfo(adap, i);
bufp += sprintf(bufp, "1000/");
if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_10G)
bufp += sprintf(bufp, "10G/");
+ if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_25G)
+ bufp += sprintf(bufp, "25G/");
if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_40G)
bufp += sprintf(bufp, "40G/");
+ if (pi->link_cfg.supported & FW_PORT_CAP_SPEED_100G)
+ bufp += sprintf(bufp, "100G/");
if (bufp != buf)
--bufp;
sprintf(bufp, "BASE-%s", t4_get_port_type_description(pi->port_type));
}
#define ADVERT_MASK (FW_PORT_CAP_SPEED_100M | FW_PORT_CAP_SPEED_1G |\
- FW_PORT_CAP_SPEED_10G | FW_PORT_CAP_SPEED_40G | \
+ FW_PORT_CAP_SPEED_10G | FW_PORT_CAP_SPEED_25G | \
+ FW_PORT_CAP_SPEED_40G | FW_PORT_CAP_SPEED_100G | \
FW_PORT_CAP_ANEG)
/**
speed = 1000;
else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_10G))
speed = 10000;
+ else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_25G))
+ speed = 25000;
else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_40G))
speed = 40000;
+ else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_100G))
+ speed = 100000;
lc = &pi->link_cfg;
FW_PORT_CAP_802_3_ASM_DIR = 0x8000,
};
+#define FW_PORT_CAP_SPEED_S 0
+#define FW_PORT_CAP_SPEED_M 0x3f
+#define FW_PORT_CAP_SPEED_V(x) ((x) << FW_PORT_CAP_SPEED_S)
+#define FW_PORT_CAP_SPEED_G(x) \
+ (((x) >> FW_PORT_CAP_SPEED_S) & FW_PORT_CAP_SPEED_M)
+
enum fw_port_mdi {
FW_PORT_CAP_MDI_UNCHANGED,
FW_PORT_CAP_MDI_AUTO,
unsigned int supported; /* link capabilities */
unsigned int advertising; /* advertised capabilities */
unsigned short lp_advertising; /* peer advertised capabilities */
- unsigned short requested_speed; /* speed user has requested */
- unsigned short speed; /* actual link speed */
+ unsigned int requested_speed; /* speed user has requested */
+ unsigned int speed; /* actual link speed */
unsigned char requested_fc; /* flow control user has requested */
unsigned char fc; /* actual link flow control */
unsigned char autoneg; /* autonegotiating? */
return (lc->supported & FW_PORT_CAP_SPEED_10G) != 0;
}
+/* Return true if the Link Configuration supports "High Speeds" (those greater
+ * than 1Gb/s).
+ */
static inline bool is_x_10g_port(const struct link_config *lc)
{
- return (lc->supported & FW_PORT_CAP_SPEED_10G) != 0 ||
- (lc->supported & FW_PORT_CAP_SPEED_40G) != 0;
+ unsigned int speeds, high_speeds;
+
+ speeds = FW_PORT_CAP_SPEED_V(FW_PORT_CAP_SPEED_G(lc->supported));
+ high_speeds = speeds & ~(FW_PORT_CAP_SPEED_100M | FW_PORT_CAP_SPEED_1G);
+
+ return high_speeds != 0;
}
static inline unsigned int core_ticks_per_usec(const struct adapter *adapter)
}
#define ADVERT_MASK (FW_PORT_CAP_SPEED_100M | FW_PORT_CAP_SPEED_1G |\
- FW_PORT_CAP_SPEED_10G | FW_PORT_CAP_SPEED_40G | \
- FW_PORT_CAP_SPEED_100G | FW_PORT_CAP_ANEG)
+ FW_PORT_CAP_SPEED_10G | FW_PORT_CAP_SPEED_25G | \
+ FW_PORT_CAP_SPEED_40G | FW_PORT_CAP_SPEED_100G | \
+ FW_PORT_CAP_ANEG)
/**
* init_link_config - initialize a link's SW state
speed = 1000;
else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_10G))
speed = 10000;
+ else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_25G))
+ speed = 25000;
else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_40G))
speed = 40000;
+ else if (stat & FW_PORT_CMD_LSPEED_V(FW_PORT_CAP_SPEED_100G))
+ speed = 100000;
/*
* Scan all of our "ports" (Virtual Interfaces) looking for
dm9000_open(struct net_device *dev)
{
struct board_info *db = netdev_priv(dev);
+ unsigned int irq_flags = irq_get_trigger_type(dev->irq);
if (netif_msg_ifup(db))
dev_dbg(db->dev, "enabling %s\n", dev->name);
/* If there is no IRQ type specified, tell the user that this is a
* problem
*/
- if (irq_get_trigger_type(dev->irq) == IRQF_TRIGGER_NONE)
+ if (irq_flags == IRQF_TRIGGER_NONE)
dev_warn(db->dev, "WARNING: no IRQ resource flags set.\n");
+ irq_flags |= IRQF_SHARED;
+
/* GPIO0 on pre-activate PHY, Reg 1F is not set by reset */
iow(db, DM9000_GPR, 0); /* REG_1F bit0 activate phyxcer */
mdelay(1); /* delay needs by DM9000B */
/* Initialize DM9000 board */
dm9000_init_dm9000(dev);
- if (request_irq(dev->irq, dm9000_interrupt, IRQF_SHARED,
- dev->name, dev))
+ if (request_irq(dev->irq, dm9000_interrupt, irq_flags, dev->name, dev))
return -EAGAIN;
/* Now that we have an interrupt handler hooked up we can unmask
* our interrupts
{
unsigned int size = lstatus & BD_LENGTH_MASK;
struct page *page = rxb->page;
+ bool last = !!(lstatus & BD_LFLAG(RXBD_LAST));
/* Remove the FCS from the packet length */
- if (likely(lstatus & BD_LFLAG(RXBD_LAST)))
+ if (last)
size -= ETH_FCS_LEN;
- if (likely(first))
+ if (likely(first)) {
skb_put(skb, size);
- else
- skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
- rxb->page_offset + RXBUF_ALIGNMENT,
- size, GFAR_RXB_TRUESIZE);
+ } else {
+ /* the last fragments' length contains the full frame length */
+ if (last)
+ size -= skb->len;
+
+ /* in case the last fragment consisted only of the FCS */
+ if (size > 0)
+ skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
+ rxb->page_offset + RXBUF_ALIGNMENT,
+ size, GFAR_RXB_TRUESIZE);
+ }
/* try reuse page */
if (unlikely(page_count(page) != 1))
#define DEFAULT_RX_LFC_THR 16
#define DEFAULT_LFC_PTVVAL 4
-#define GFAR_RXB_SIZE 1536
+/* prevent fragmenation by HW in DSA environments */
+#define GFAR_RXB_SIZE roundup(1536 + 8, 64)
#define GFAR_SKBFRAG_SIZE (RXBUF_ALIGNMENT + GFAR_RXB_SIZE \
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
#define GFAR_RXB_TRUESIZE 2048
{"gmac_rx_octets_total_ok", MAC_STATS_FIELD_OFF(rx_good_bytes)},
{"gmac_rx_octets_bad", MAC_STATS_FIELD_OFF(rx_bad_bytes)},
{"gmac_rx_uc_pkts", MAC_STATS_FIELD_OFF(rx_uc_pkts)},
- {"gamc_rx_mc_pkts", MAC_STATS_FIELD_OFF(rx_mc_pkts)},
+ {"gmac_rx_mc_pkts", MAC_STATS_FIELD_OFF(rx_mc_pkts)},
{"gmac_rx_bc_pkts", MAC_STATS_FIELD_OFF(rx_bc_pkts)},
{"gmac_rx_pkts_64octets", MAC_STATS_FIELD_OFF(rx_64bytes)},
{"gmac_rx_pkts_65to127", MAC_STATS_FIELD_OFF(rx_65to127)},
static void hns_ppe_uninit_hw(struct hns_ppe_cb *ppe_cb)
{
u32 port;
- struct dsaf_device *dsaf_dev = ppe_cb->ppe_common_cb->dsaf_dev;
if (ppe_cb->ppe_common_cb) {
+ struct dsaf_device *dsaf_dev = ppe_cb->ppe_common_cb->dsaf_dev;
+
port = ppe_cb->index;
dsaf_dev->misc_op->ppe_srst(dsaf_dev, port, 0);
}
dev->mcast_pending = 1;
return;
}
+
+ mutex_lock(&dev->link_lock);
__emac_set_multicast_list(dev);
+ mutex_unlock(&dev->link_lock);
+}
+
+static int emac_set_mac_address(struct net_device *ndev, void *sa)
+{
+ struct emac_instance *dev = netdev_priv(ndev);
+ struct sockaddr *addr = sa;
+ struct emac_regs __iomem *p = dev->emacp;
+
+ if (!is_valid_ether_addr(addr->sa_data))
+ return -EADDRNOTAVAIL;
+
+ mutex_lock(&dev->link_lock);
+
+ memcpy(ndev->dev_addr, addr->sa_data, ndev->addr_len);
+
+ emac_rx_disable(dev);
+ emac_tx_disable(dev);
+ out_be32(&p->iahr, (ndev->dev_addr[0] << 8) | ndev->dev_addr[1]);
+ out_be32(&p->ialr, (ndev->dev_addr[2] << 24) |
+ (ndev->dev_addr[3] << 16) | (ndev->dev_addr[4] << 8) |
+ ndev->dev_addr[5]);
+ emac_tx_enable(dev);
+ emac_rx_enable(dev);
+
+ mutex_unlock(&dev->link_lock);
+
+ return 0;
}
static int emac_resize_rx_ring(struct emac_instance *dev, int new_mtu)
.ndo_do_ioctl = emac_ioctl,
.ndo_tx_timeout = emac_tx_timeout,
.ndo_validate_addr = eth_validate_addr,
- .ndo_set_mac_address = eth_mac_addr,
+ .ndo_set_mac_address = emac_set_mac_address,
.ndo_start_xmit = emac_start_xmit,
.ndo_change_mtu = eth_change_mtu,
};
.ndo_do_ioctl = emac_ioctl,
.ndo_tx_timeout = emac_tx_timeout,
.ndo_validate_addr = eth_validate_addr,
- .ndo_set_mac_address = eth_mac_addr,
+ .ndo_set_mac_address = emac_set_mac_address,
.ndo_start_xmit = emac_start_xmit_sg,
.ndo_change_mtu = emac_change_mtu,
};
| FLAG2_DISABLE_ASPM_L0S
| FLAG2_DISABLE_ASPM_L1
| FLAG2_NO_DISABLE_RX
- | FLAG2_DMA_BURST,
+ | FLAG2_DMA_BURST
+ | FLAG2_CHECK_SYSTIM_OVERFLOW,
.pba = 32,
.max_hw_frame_size = DEFAULT_JUMBO,
.get_variants = e1000_get_variants_82571,
| FLAG_HAS_CTRLEXT_ON_LOAD,
.flags2 = FLAG2_DISABLE_ASPM_L0S
| FLAG2_DISABLE_ASPM_L1
- | FLAG2_NO_DISABLE_RX,
+ | FLAG2_NO_DISABLE_RX
+ | FLAG2_CHECK_SYSTIM_OVERFLOW,
.pba = 32,
.max_hw_frame_size = DEFAULT_JUMBO,
.get_variants = e1000_get_variants_82571,
#define FLAG2_PCIM2PCI_ARBITER_WA BIT(11)
#define FLAG2_DFLT_CRC_STRIPPING BIT(12)
#define FLAG2_CHECK_RX_HWTSTAMP BIT(13)
+#define FLAG2_CHECK_SYSTIM_OVERFLOW BIT(14)
#define E1000_RX_DESC_PS(R, i) \
(&(((union e1000_rx_desc_packet_split *)((R).desc))[i]))
| FLAG_HAS_JUMBO_FRAMES
| FLAG_APME_IN_WUC,
.flags2 = FLAG2_HAS_PHY_STATS
- | FLAG2_HAS_EEE,
+ | FLAG2_HAS_EEE
+ | FLAG2_CHECK_SYSTIM_OVERFLOW,
.pba = 26,
.max_hw_frame_size = 9022,
.get_variants = e1000_get_variants_ich8lan,
clear_bit(__E1000_RESETTING, &adapter->state);
}
+/**
+ * e1000e_sanitize_systim - sanitize raw cycle counter reads
+ * @hw: pointer to the HW structure
+ * @systim: cycle_t value read, sanitized and returned
+ *
+ * Errata for 82574/82583 possible bad bits read from SYSTIMH/L:
+ * check to see that the time is incrementing at a reasonable
+ * rate and is a multiple of incvalue.
+ **/
+static cycle_t e1000e_sanitize_systim(struct e1000_hw *hw, cycle_t systim)
+{
+ u64 time_delta, rem, temp;
+ cycle_t systim_next;
+ u32 incvalue;
+ int i;
+
+ incvalue = er32(TIMINCA) & E1000_TIMINCA_INCVALUE_MASK;
+ for (i = 0; i < E1000_MAX_82574_SYSTIM_REREADS; i++) {
+ /* latch SYSTIMH on read of SYSTIML */
+ systim_next = (cycle_t)er32(SYSTIML);
+ systim_next |= (cycle_t)er32(SYSTIMH) << 32;
+
+ time_delta = systim_next - systim;
+ temp = time_delta;
+ /* VMWare users have seen incvalue of zero, don't div / 0 */
+ rem = incvalue ? do_div(temp, incvalue) : (time_delta != 0);
+
+ systim = systim_next;
+
+ if ((time_delta < E1000_82574_SYSTIM_EPSILON) && (rem == 0))
+ break;
+ }
+
+ return systim;
+}
+
/**
* e1000e_cyclecounter_read - read raw cycle counter (used by time counter)
* @cc: cyclecounter structure
cc);
struct e1000_hw *hw = &adapter->hw;
u32 systimel, systimeh;
- cycle_t systim, systim_next;
+ cycle_t systim;
/* SYSTIMH latching upon SYSTIML read does not work well.
* This means that if SYSTIML overflows after we read it but before
* we read SYSTIMH, the value of SYSTIMH has been incremented and we
systim = (cycle_t)systimel;
systim |= (cycle_t)systimeh << 32;
- if ((hw->mac.type == e1000_82574) || (hw->mac.type == e1000_82583)) {
- u64 time_delta, rem, temp;
- u32 incvalue;
- int i;
-
- /* errata for 82574/82583 possible bad bits read from SYSTIMH/L
- * check to see that the time is incrementing at a reasonable
- * rate and is a multiple of incvalue
- */
- incvalue = er32(TIMINCA) & E1000_TIMINCA_INCVALUE_MASK;
- for (i = 0; i < E1000_MAX_82574_SYSTIM_REREADS; i++) {
- /* latch SYSTIMH on read of SYSTIML */
- systim_next = (cycle_t)er32(SYSTIML);
- systim_next |= (cycle_t)er32(SYSTIMH) << 32;
-
- time_delta = systim_next - systim;
- temp = time_delta;
- /* VMWare users have seen incvalue of zero, don't div / 0 */
- rem = incvalue ? do_div(temp, incvalue) : (time_delta != 0);
-
- systim = systim_next;
+ if (adapter->flags2 & FLAG2_CHECK_SYSTIM_OVERFLOW)
+ systim = e1000e_sanitize_systim(hw, systim);
- if ((time_delta < E1000_82574_SYSTIM_EPSILON) &&
- (rem == 0))
- break;
- }
- }
return systim;
}
void i40e_notify_client_of_netdev_open(struct i40e_vsi *vsi)
{
struct i40e_client_instance *cdev;
+ int ret = 0;
if (!vsi)
return;
"Cannot locate client instance open routine\n");
continue;
}
- cdev->client->ops->open(&cdev->lan_info, cdev->client);
+ if (!(test_bit(__I40E_CLIENT_INSTANCE_OPENED,
+ &cdev->state))) {
+ ret = cdev->client->ops->open(&cdev->lan_info,
+ cdev->client);
+ if (!ret)
+ set_bit(__I40E_CLIENT_INSTANCE_OPENED,
+ &cdev->state);
+ }
}
}
mutex_unlock(&i40e_client_instance_mutex);
* i40e_client_add_instance - add a client instance struct to the instance list
* @pf: pointer to the board struct
* @client: pointer to a client struct in the client list.
+ * @existing: if there was already an existing instance
*
- * Returns cdev ptr on success, NULL on failure
+ * Returns cdev ptr on success or if already exists, NULL on failure
**/
static
struct i40e_client_instance *i40e_client_add_instance(struct i40e_pf *pf,
- struct i40e_client *client)
+ struct i40e_client *client,
+ bool *existing)
{
struct i40e_client_instance *cdev;
struct netdev_hw_addr *mac = NULL;
mutex_lock(&i40e_client_instance_mutex);
list_for_each_entry(cdev, &i40e_client_instances, list) {
if ((cdev->lan_info.pf == pf) && (cdev->client == client)) {
- cdev = NULL;
+ *existing = true;
goto out;
}
}
{
struct i40e_client_instance *cdev;
struct i40e_client *client;
+ bool existing = false;
int ret = 0;
if (!(pf->flags & I40E_FLAG_SERVICE_CLIENT_REQUESTED))
/* check if L2 VSI is up, if not we are not ready */
if (test_bit(__I40E_DOWN, &pf->vsi[pf->lan_vsi]->state))
continue;
+ } else {
+ dev_warn(&pf->pdev->dev, "This client %s is being instanciated at probe\n",
+ client->name);
}
/* Add the client instance to the instance list */
- cdev = i40e_client_add_instance(pf, client);
+ cdev = i40e_client_add_instance(pf, client, &existing);
if (!cdev)
continue;
- /* Also up the ref_cnt of no. of instances of this client */
- atomic_inc(&client->ref_cnt);
- dev_info(&pf->pdev->dev, "Added instance of Client %s to PF%d bus=0x%02x func=0x%02x\n",
- client->name, pf->hw.pf_id,
- pf->hw.bus.device, pf->hw.bus.func);
+ if (!existing) {
+ /* Also up the ref_cnt for no. of instances of this
+ * client.
+ */
+ atomic_inc(&client->ref_cnt);
+ dev_info(&pf->pdev->dev, "Added instance of Client %s to PF%d bus=0x%02x func=0x%02x\n",
+ client->name, pf->hw.pf_id,
+ pf->hw.bus.device, pf->hw.bus.func);
+ }
/* Send an Open request to the client */
atomic_inc(&cdev->ref_cnt);
pf->hw.pf_id, pf->hw.bus.device, pf->hw.bus.func);
/* Since in some cases register may have happened before a device gets
- * added, we can schedule a subtask to go initiate the clients.
+ * added, we can schedule a subtask to go initiate the clients if
+ * they can be launched at probe time.
*/
pf->flags |= I40E_FLAG_SERVICE_CLIENT_REQUESTED;
i40e_service_event_schedule(pf);
**/
static u8 i40e_dcb_get_num_tc(struct i40e_dcbx_config *dcbcfg)
{
+ int i, tc_unused = 0;
u8 num_tc = 0;
- int i;
+ u8 ret = 0;
/* Scan the ETS Config Priority Table to find
* traffic class enabled for a given priority
- * and use the traffic class index to get the
- * number of traffic classes enabled
+ * and create a bitmask of enabled TCs
*/
- for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
- if (dcbcfg->etscfg.prioritytable[i] > num_tc)
- num_tc = dcbcfg->etscfg.prioritytable[i];
- }
+ for (i = 0; i < I40E_MAX_USER_PRIORITY; i++)
+ num_tc |= BIT(dcbcfg->etscfg.prioritytable[i]);
- /* Traffic class index starts from zero so
- * increment to return the actual count
+ /* Now scan the bitmask to check for
+ * contiguous TCs starting with TC0
*/
- return num_tc + 1;
+ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
+ if (num_tc & BIT(i)) {
+ if (!tc_unused) {
+ ret++;
+ } else {
+ pr_err("Non-contiguous TC - Disabling DCB\n");
+ return 1;
+ }
+ } else {
+ tc_unused = 1;
+ }
+ }
+
+ /* There is always at least TC0 */
+ if (!ret)
+ ret = 1;
+
+ return ret;
}
/**
DCB_CAP_DCBX_VER_IEEE;
pf->flags |= I40E_FLAG_DCB_CAPABLE;
- /* Enable DCB tagging only when more than one TC */
+ /* Enable DCB tagging only when more than one TC
+ * or explicitly disable if only one TC
+ */
if (i40e_dcb_get_num_tc(&hw->local_dcbx_config) > 1)
pf->flags |= I40E_FLAG_DCB_ENABLED;
+ else
+ pf->flags &= ~I40E_FLAG_DCB_ENABLED;
dev_dbg(&pf->pdev->dev,
"DCBX offload is supported for this PF.\n");
}
wr32(&pf->hw, I40E_GLLAN_TSOMSK_L, be32_to_cpu(TCP_FLAG_CWR) >> 16);
udp_tunnel_get_rx_info(netdev);
- i40e_notify_client_of_netdev_open(vsi);
return 0;
}
u8 type;
/* Not DCB capable or capability disabled */
- if (!(pf->flags & I40E_FLAG_DCB_CAPABLE))
+ if (!(pf->flags & I40E_FLAG_DCB_ENABLED))
return ret;
/* Ignore if event is not for Nearest Bridge */
#endif
I40E_FLAG_RSS_ENABLED |
I40E_FLAG_DCB_CAPABLE |
+ I40E_FLAG_DCB_ENABLED |
I40E_FLAG_SRIOV_ENABLED |
I40E_FLAG_FD_SB_ENABLED |
I40E_FLAG_FD_ATR_ENABLED |
I40E_FLAG_FD_SB_ENABLED |
I40E_FLAG_FD_ATR_ENABLED |
I40E_FLAG_DCB_CAPABLE |
+ I40E_FLAG_DCB_ENABLED |
I40E_FLAG_SRIOV_ENABLED |
I40E_FLAG_VMDQ_ENABLED);
} else if (!(pf->flags & (I40E_FLAG_RSS_ENABLED |
/* Not enough queues for all TCs */
if ((pf->flags & I40E_FLAG_DCB_CAPABLE) &&
(queues_left < I40E_MAX_TRAFFIC_CLASS)) {
- pf->flags &= ~I40E_FLAG_DCB_CAPABLE;
+ pf->flags &= ~(I40E_FLAG_DCB_CAPABLE |
+ I40E_FLAG_DCB_ENABLED);
dev_info(&pf->pdev->dev, "not enough queues for DCB. DCB is disabled.\n");
}
pf->num_lan_qps = max_t(int, pf->rss_size_max,
err = i40e_init_pf_dcb(pf);
if (err) {
dev_info(&pdev->dev, "DCB init failed %d, disabled\n", err);
- pf->flags &= ~I40E_FLAG_DCB_CAPABLE;
+ pf->flags &= ~(I40E_FLAG_DCB_CAPABLE & I40E_FLAG_DCB_ENABLED);
/* Continue without DCB enabled */
}
#endif /* CONFIG_I40E_DCB */
}
}
- shhwtstamps.hwtstamp = ktime_sub_ns(shhwtstamps.hwtstamp, adjust);
+ shhwtstamps.hwtstamp =
+ ktime_add_ns(shhwtstamps.hwtstamp, adjust);
skb_tstamp_tx(adapter->ptp_tx_skb, &shhwtstamps);
dev_kfree_skb_any(adapter->ptp_tx_skb);
struct sk_buff *skb)
{
__le64 *regval = (__le64 *)va;
+ struct igb_adapter *adapter = q_vector->adapter;
+ int adjust = 0;
/* The timestamp is recorded in little endian format.
* DWORD: 0 1 2 3
* Field: Reserved Reserved SYSTIML SYSTIMH
*/
- igb_ptp_systim_to_hwtstamp(q_vector->adapter, skb_hwtstamps(skb),
+ igb_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb),
le64_to_cpu(regval[1]));
+
+ /* adjust timestamp for the RX latency based on link speed */
+ if (adapter->hw.mac.type == e1000_i210) {
+ switch (adapter->link_speed) {
+ case SPEED_10:
+ adjust = IGB_I210_RX_LATENCY_10;
+ break;
+ case SPEED_100:
+ adjust = IGB_I210_RX_LATENCY_100;
+ break;
+ case SPEED_1000:
+ adjust = IGB_I210_RX_LATENCY_1000;
+ break;
+ }
+ }
+ skb_hwtstamps(skb)->hwtstamp =
+ ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust);
}
/**
}
}
skb_hwtstamps(skb)->hwtstamp =
- ktime_add_ns(skb_hwtstamps(skb)->hwtstamp, adjust);
+ ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust);
/* Update the last_rx_timestamp timer in order to enable watchdog check
* for error case of latched timestamp on a dropped packet.
}
/* was that the last pool using this rar? */
- if (mpsar_lo == 0 && mpsar_hi == 0 && rar != 0)
+ if (mpsar_lo == 0 && mpsar_hi == 0 &&
+ rar != 0 && rar != hw->mac.san_mac_rar_index)
hw->mac.ops.clear_rar(hw, rar);
+
return 0;
}
struct ixgbe_hw *hw = &adapter->hw;
u32 vlnctrl, i;
+ vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL);
+
switch (hw->mac.type) {
case ixgbe_mac_82599EB:
case ixgbe_mac_X540:
/* fall through */
case ixgbe_mac_82598EB:
/* legacy case, we can just disable VLAN filtering */
- vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL);
- vlnctrl &= ~(IXGBE_VLNCTRL_VFE | IXGBE_VLNCTRL_CFIEN);
+ vlnctrl &= ~IXGBE_VLNCTRL_VFE;
IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
return;
}
/* Set flag so we don't redo unnecessary work */
adapter->flags2 |= IXGBE_FLAG2_VLAN_PROMISC;
+ /* For VMDq and SR-IOV we must leave VLAN filtering enabled */
+ vlnctrl |= IXGBE_VLNCTRL_VFE;
+ IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
+
/* Add PF to all active pools */
for (i = IXGBE_VLVF_ENTRIES; --i;) {
u32 reg_offset = IXGBE_VLVFB(i * 2 + VMDQ_P(0) / 32);
struct ixgbe_hw *hw = &adapter->hw;
u32 vlnctrl, i;
+ /* Set VLAN filtering to enabled */
+ vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL);
+ vlnctrl |= IXGBE_VLNCTRL_VFE;
+ IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
+
switch (hw->mac.type) {
case ixgbe_mac_82599EB:
case ixgbe_mac_X540:
break;
/* fall through */
case ixgbe_mac_82598EB:
- vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL);
- vlnctrl &= ~IXGBE_VLNCTRL_CFIEN;
- vlnctrl |= IXGBE_VLNCTRL_VFE;
- IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl);
return;
}
struct tcf_exts *exts, u64 *action, u8 *queue)
{
const struct tc_action *a;
+ LIST_HEAD(actions);
int err;
if (tc_no_actions(exts))
return -EINVAL;
- tc_for_each_action(a, exts) {
+ tcf_exts_to_list(exts, &actions);
+ list_for_each_entry(a, &actions, list) {
/* Drop action */
if (is_tcf_gact_shot(a)) {
/* copy netdev features into list of user selectable features */
netdev->hw_features |= netdev->features |
+ NETIF_F_HW_VLAN_CTAG_FILTER |
NETIF_F_HW_VLAN_CTAG_RX |
NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_RXALL |
MTK_ETHTOOL_STAT(rx_flow_control_packets),
};
+static const char * const mtk_clks_source_name[] = {
+ "ethif", "esw", "gp1", "gp2"
+};
+
void mtk_w32(struct mtk_eth *eth, u32 val, unsigned reg)
{
__raw_writel(val, eth->base + reg);
case PHY_INTERFACE_MODE_MII:
ge_mode = 1;
break;
- case PHY_INTERFACE_MODE_RMII:
+ case PHY_INTERFACE_MODE_REVMII:
ge_mode = 2;
break;
+ case PHY_INTERFACE_MODE_RMII:
+ if (!mac->id)
+ goto err_phy;
+ ge_mode = 3;
+ break;
default:
- dev_err(eth->dev, "invalid phy_mode\n");
- return -1;
+ goto err_phy;
}
/* put the gmac into the right mode */
mac->phy_dev->autoneg = AUTONEG_ENABLE;
mac->phy_dev->speed = 0;
mac->phy_dev->duplex = 0;
+
+ if (of_phy_is_fixed_link(mac->of_node))
+ mac->phy_dev->supported |=
+ SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+
mac->phy_dev->supported &= PHY_GBIT_FEATURES | SUPPORTED_Pause |
SUPPORTED_Asym_Pause;
mac->phy_dev->advertising = mac->phy_dev->supported |
ADVERTISED_Autoneg;
phy_start_aneg(mac->phy_dev);
+ of_node_put(np);
+
return 0;
+
+err_phy:
+ of_node_put(np);
+ dev_err(eth->dev, "invalid phy_mode\n");
+ return -EINVAL;
}
static int mtk_mdio_init(struct mtk_eth *eth)
{
struct device_node *mii_np;
- int err;
+ int ret;
mii_np = of_get_child_by_name(eth->dev->of_node, "mdio-bus");
if (!mii_np) {
}
if (!of_device_is_available(mii_np)) {
- err = 0;
+ ret = -ENODEV;
goto err_put_node;
}
- eth->mii_bus = mdiobus_alloc();
+ eth->mii_bus = devm_mdiobus_alloc(eth->dev);
if (!eth->mii_bus) {
- err = -ENOMEM;
+ ret = -ENOMEM;
goto err_put_node;
}
eth->mii_bus->parent = eth->dev;
snprintf(eth->mii_bus->id, MII_BUS_ID_SIZE, "%s", mii_np->name);
- err = of_mdiobus_register(eth->mii_bus, mii_np);
- if (err)
- goto err_free_bus;
-
- return 0;
-
-err_free_bus:
- mdiobus_free(eth->mii_bus);
+ ret = of_mdiobus_register(eth->mii_bus, mii_np);
err_put_node:
of_node_put(mii_np);
- eth->mii_bus = NULL;
- return err;
+ return ret;
}
static void mtk_mdio_cleanup(struct mtk_eth *eth)
return;
mdiobus_unregister(eth->mii_bus);
- of_node_put(eth->mii_bus->dev.of_node);
- mdiobus_free(eth->mii_bus);
}
static inline void mtk_irq_disable(struct mtk_eth *eth, u32 mask)
return &ring->buf[idx];
}
-static void mtk_tx_unmap(struct device *dev, struct mtk_tx_buf *tx_buf)
+static void mtk_tx_unmap(struct mtk_eth *eth, struct mtk_tx_buf *tx_buf)
{
if (tx_buf->flags & MTK_TX_FLAGS_SINGLE0) {
- dma_unmap_single(dev,
+ dma_unmap_single(eth->dev,
dma_unmap_addr(tx_buf, dma_addr0),
dma_unmap_len(tx_buf, dma_len0),
DMA_TO_DEVICE);
} else if (tx_buf->flags & MTK_TX_FLAGS_PAGE0) {
- dma_unmap_page(dev,
+ dma_unmap_page(eth->dev,
dma_unmap_addr(tx_buf, dma_addr0),
dma_unmap_len(tx_buf, dma_len0),
DMA_TO_DEVICE);
dma_addr_t mapped_addr;
unsigned int nr_frags;
int i, n_desc = 1;
- u32 txd4 = 0;
+ u32 txd4 = 0, fport;
itxd = ring->next_free;
if (itxd == ring->last_free)
return -ENOMEM;
/* set the forward port */
- txd4 |= (mac->id + 1) << TX_DMA_FPORT_SHIFT;
+ fport = (mac->id + 1) << TX_DMA_FPORT_SHIFT;
+ txd4 |= fport;
tx_buf = mtk_desc_to_tx_buf(ring, itxd);
memset(tx_buf, 0, sizeof(*tx_buf));
if (skb_vlan_tag_present(skb))
txd4 |= TX_DMA_INS_VLAN | skb_vlan_tag_get(skb);
- mapped_addr = dma_map_single(&dev->dev, skb->data,
+ mapped_addr = dma_map_single(eth->dev, skb->data,
skb_headlen(skb), DMA_TO_DEVICE);
- if (unlikely(dma_mapping_error(&dev->dev, mapped_addr)))
+ if (unlikely(dma_mapping_error(eth->dev, mapped_addr)))
return -ENOMEM;
WRITE_ONCE(itxd->txd1, mapped_addr);
n_desc++;
frag_map_size = min(frag_size, MTK_TX_DMA_BUF_LEN);
- mapped_addr = skb_frag_dma_map(&dev->dev, frag, offset,
+ mapped_addr = skb_frag_dma_map(eth->dev, frag, offset,
frag_map_size,
DMA_TO_DEVICE);
- if (unlikely(dma_mapping_error(&dev->dev, mapped_addr)))
+ if (unlikely(dma_mapping_error(eth->dev, mapped_addr)))
goto err_dma;
if (i == nr_frags - 1 &&
WRITE_ONCE(txd->txd3, (TX_DMA_SWC |
TX_DMA_PLEN0(frag_map_size) |
last_frag * TX_DMA_LS0));
- WRITE_ONCE(txd->txd4, 0);
+ WRITE_ONCE(txd->txd4, fport);
tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC;
tx_buf = mtk_desc_to_tx_buf(ring, txd);
tx_buf = mtk_desc_to_tx_buf(ring, itxd);
/* unmap dma */
- mtk_tx_unmap(&dev->dev, tx_buf);
+ mtk_tx_unmap(eth, tx_buf);
itxd->txd3 = TX_DMA_LS0 | TX_DMA_OWNER_CPU;
itxd = mtk_qdma_phys_to_virt(ring, itxd->txd2);
netdev->stats.rx_dropped++;
goto release_desc;
}
- dma_addr = dma_map_single(ð->netdev[mac]->dev,
+ dma_addr = dma_map_single(eth->dev,
new_data + NET_SKB_PAD,
ring->buf_size,
DMA_FROM_DEVICE);
- if (unlikely(dma_mapping_error(&netdev->dev, dma_addr))) {
+ if (unlikely(dma_mapping_error(eth->dev, dma_addr))) {
skb_free_frag(new_data);
netdev->stats.rx_dropped++;
goto release_desc;
/* receive data */
skb = build_skb(data, ring->frag_size);
if (unlikely(!skb)) {
- put_page(virt_to_head_page(new_data));
+ skb_free_frag(new_data);
netdev->stats.rx_dropped++;
goto release_desc;
}
skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
- dma_unmap_single(&netdev->dev, trxd.rxd1,
+ dma_unmap_single(eth->dev, trxd.rxd1,
ring->buf_size, DMA_FROM_DEVICE);
pktlen = RX_DMA_GET_PLEN0(trxd.rxd2);
skb->dev = netdev;
done[mac]++;
budget--;
}
- mtk_tx_unmap(eth->dev, tx_buf);
+ mtk_tx_unmap(eth, tx_buf);
ring->last_free = desc;
atomic_inc(&ring->free_count);
if (ring->buf) {
for (i = 0; i < MTK_DMA_SIZE; i++)
- mtk_tx_unmap(eth->dev, &ring->buf[i]);
+ mtk_tx_unmap(eth, &ring->buf[i]);
kfree(ring->buf);
ring->buf = NULL;
}
struct mtk_eth *eth = mac->hw;
phy_disconnect(mac->phy_dev);
- mtk_mdio_cleanup(eth);
mtk_irq_disable(eth, ~0);
- free_irq(eth->irq[1], dev);
- free_irq(eth->irq[2], dev);
}
static int mtk_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
goto free_netdev;
}
spin_lock_init(&mac->hw_stats->stats_lock);
+ u64_stats_init(&mac->hw_stats->syncp);
mac->hw_stats->reg_offset = id * MTK_STAT_OFFSET;
SET_NETDEV_DEV(eth->netdev[id], eth->dev);
if (!eth)
return -ENOMEM;
+ eth->dev = &pdev->dev;
eth->base = devm_ioremap_resource(&pdev->dev, res);
if (IS_ERR(eth->base))
return PTR_ERR(eth->base);
return -ENXIO;
}
}
+ for (i = 0; i < ARRAY_SIZE(eth->clks); i++) {
+ eth->clks[i] = devm_clk_get(eth->dev,
+ mtk_clks_source_name[i]);
+ if (IS_ERR(eth->clks[i])) {
+ if (PTR_ERR(eth->clks[i]) == -EPROBE_DEFER)
+ return -EPROBE_DEFER;
+ return -ENODEV;
+ }
+ }
- eth->clk_ethif = devm_clk_get(&pdev->dev, "ethif");
- eth->clk_esw = devm_clk_get(&pdev->dev, "esw");
- eth->clk_gp1 = devm_clk_get(&pdev->dev, "gp1");
- eth->clk_gp2 = devm_clk_get(&pdev->dev, "gp2");
- if (IS_ERR(eth->clk_esw) || IS_ERR(eth->clk_gp1) ||
- IS_ERR(eth->clk_gp2) || IS_ERR(eth->clk_ethif))
- return -ENODEV;
-
- clk_prepare_enable(eth->clk_ethif);
- clk_prepare_enable(eth->clk_esw);
- clk_prepare_enable(eth->clk_gp1);
- clk_prepare_enable(eth->clk_gp2);
+ clk_prepare_enable(eth->clks[MTK_CLK_ETHIF]);
+ clk_prepare_enable(eth->clks[MTK_CLK_ESW]);
+ clk_prepare_enable(eth->clks[MTK_CLK_GP1]);
+ clk_prepare_enable(eth->clks[MTK_CLK_GP2]);
- eth->dev = &pdev->dev;
eth->msg_enable = netif_msg_init(mtk_msg_level, MTK_DEFAULT_MSG_ENABLE);
INIT_WORK(ð->pending_work, mtk_pending_work);
static int mtk_remove(struct platform_device *pdev)
{
struct mtk_eth *eth = platform_get_drvdata(pdev);
+ int i;
- clk_disable_unprepare(eth->clk_ethif);
- clk_disable_unprepare(eth->clk_esw);
- clk_disable_unprepare(eth->clk_gp1);
- clk_disable_unprepare(eth->clk_gp2);
+ /* stop all devices to make sure that dma is properly shut down */
+ for (i = 0; i < MTK_MAC_COUNT; i++) {
+ if (!eth->netdev[i])
+ continue;
+ mtk_stop(eth->netdev[i]);
+ }
+
+ clk_disable_unprepare(eth->clks[MTK_CLK_ETHIF]);
+ clk_disable_unprepare(eth->clks[MTK_CLK_ESW]);
+ clk_disable_unprepare(eth->clks[MTK_CLK_GP1]);
+ clk_disable_unprepare(eth->clks[MTK_CLK_GP2]);
netif_napi_del(ð->tx_napi);
netif_napi_del(ð->rx_napi);
mtk_cleanup(eth);
+ mtk_mdio_cleanup(eth);
platform_set_drvdata(pdev, NULL);
return 0;
{ .compatible = "mediatek,mt7623-eth" },
{},
};
+MODULE_DEVICE_TABLE(of, of_mtk_match);
static struct platform_driver mtk_driver = {
.probe = mtk_probe,
MTK_TX_FLAGS_PAGE0 = 0x02,
};
+/* This enum allows us to identify how the clock is defined on the array of the
+ * clock in the order
+ */
+enum mtk_clks_map {
+ MTK_CLK_ETHIF,
+ MTK_CLK_ESW,
+ MTK_CLK_GP1,
+ MTK_CLK_GP2,
+ MTK_CLK_MAX
+};
+
/* struct mtk_tx_buf - This struct holds the pointers to the memory pointed at
* by the TX descriptor s
* @skb: The SKB pointer of the packet being sent
* @scratch_ring: Newer SoCs need memory for a second HW managed TX ring
* @phy_scratch_ring: physical address of scratch_ring
* @scratch_head: The scratch memory that scratch_ring points to.
- * @clk_ethif: The ethif clock
- * @clk_esw: The switch clock
- * @clk_gp1: The gmac1 clock
- * @clk_gp2: The gmac2 clock
+ * @clks: clock array for all clocks required
* @mii_bus: If there is a bus we need to create an instance for it
* @pending_work: The workqueue used to reset the dma ring
*/
struct mtk_tx_dma *scratch_ring;
dma_addr_t phy_scratch_ring;
void *scratch_head;
- struct clk *clk_ethif;
- struct clk *clk_esw;
- struct clk *clk_gp1;
- struct clk *clk_gp2;
+ struct clk *clks[MTK_CLK_MAX];
+
struct mii_bus *mii_bus;
struct work_struct pending_work;
};
*cap = true;
break;
case DCB_CAP_ATTR_DCBX:
- *cap = priv->cee_params.dcbx_cap;
+ *cap = priv->dcbx_cap;
break;
case DCB_CAP_ATTR_PFC_TCS:
*cap = 1 << mlx4_max_tc(priv->mdev->dev);
{
struct mlx4_en_priv *priv = netdev_priv(netdev);
- return priv->cee_params.dcb_cfg.pfc_state;
+ return priv->cee_config.pfc_state;
}
static void mlx4_en_dcbnl_setpfcstate(struct net_device *netdev, u8 state)
{
struct mlx4_en_priv *priv = netdev_priv(netdev);
- priv->cee_params.dcb_cfg.pfc_state = state;
+ priv->cee_config.pfc_state = state;
}
static void mlx4_en_dcbnl_get_pfc_cfg(struct net_device *netdev, int priority,
{
struct mlx4_en_priv *priv = netdev_priv(netdev);
- *setting = priv->cee_params.dcb_cfg.tc_config[priority].dcb_pfc;
+ *setting = priv->cee_config.dcb_pfc[priority];
}
static void mlx4_en_dcbnl_set_pfc_cfg(struct net_device *netdev, int priority,
{
struct mlx4_en_priv *priv = netdev_priv(netdev);
- priv->cee_params.dcb_cfg.tc_config[priority].dcb_pfc = setting;
- priv->cee_params.dcb_cfg.pfc_state = true;
+ priv->cee_config.dcb_pfc[priority] = setting;
+ priv->cee_config.pfc_state = true;
}
static int mlx4_en_dcbnl_getnumtcs(struct net_device *netdev, int tcid, u8 *num)
{
struct mlx4_en_priv *priv = netdev_priv(netdev);
struct mlx4_en_dev *mdev = priv->mdev;
- struct mlx4_en_cee_config *dcb_cfg = &priv->cee_params.dcb_cfg;
- int err = 0;
- if (!(priv->cee_params.dcbx_cap & DCB_CAP_DCBX_VER_CEE))
- return -EINVAL;
+ if (!(priv->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+ return 1;
- if (dcb_cfg->pfc_state) {
+ if (priv->cee_config.pfc_state) {
int tc;
priv->prof->rx_pause = 0;
for (tc = 0; tc < CEE_DCBX_MAX_PRIO; tc++) {
u8 tc_mask = 1 << tc;
- switch (dcb_cfg->tc_config[tc].dcb_pfc) {
+ switch (priv->cee_config.dcb_pfc[tc]) {
case pfc_disabled:
priv->prof->tx_ppp &= ~tc_mask;
priv->prof->rx_ppp &= ~tc_mask;
en_dbg(DRV, priv, "Set pfc off\n");
}
- err = mlx4_SET_PORT_general(mdev->dev, priv->port,
- priv->rx_skb_size + ETH_FCS_LEN,
- priv->prof->tx_pause,
- priv->prof->tx_ppp,
- priv->prof->rx_pause,
- priv->prof->rx_ppp);
- if (err)
+ if (mlx4_SET_PORT_general(mdev->dev, priv->port,
+ priv->rx_skb_size + ETH_FCS_LEN,
+ priv->prof->tx_pause,
+ priv->prof->tx_ppp,
+ priv->prof->rx_pause,
+ priv->prof->rx_ppp)) {
en_err(priv, "Failed setting pause params\n");
- return err;
+ return 1;
+ }
+
+ return 0;
}
static u8 mlx4_en_dcbnl_get_state(struct net_device *dev)
struct mlx4_en_priv *priv = netdev_priv(dev);
int num_tcs = 0;
- if (!(priv->cee_params.dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+ if (!(priv->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
return 1;
if (!!(state) == !!(priv->flags & MLX4_EN_FLAG_DCB_ENABLED))
priv->flags &= ~MLX4_EN_FLAG_DCB_ENABLED;
}
- return mlx4_en_setup_tc(dev, num_tcs);
+ if (mlx4_en_setup_tc(dev, num_tcs))
+ return 1;
+
+ return 0;
}
/* On success returns a non-zero 802.1p user priority bitmap
.selector = idtype,
.protocol = id,
};
- if (!(priv->cee_params.dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+ if (!(priv->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
return 0;
return dcb_getapp(netdev, &app);
struct mlx4_en_priv *priv = netdev_priv(netdev);
struct dcb_app app;
- if (!(priv->cee_params.dcbx_cap & DCB_CAP_DCBX_VER_CEE))
+ if (!(priv->dcbx_cap & DCB_CAP_DCBX_VER_CEE))
return -EINVAL;
memset(&app, 0, sizeof(struct dcb_app));
{
struct mlx4_en_priv *priv = netdev_priv(dev);
- return priv->cee_params.dcbx_cap;
+ return priv->dcbx_cap;
}
static u8 mlx4_en_dcbnl_setdcbx(struct net_device *dev, u8 mode)
struct ieee_ets ets = {0};
struct ieee_pfc pfc = {0};
- if (mode == priv->cee_params.dcbx_cap)
+ if (mode == priv->dcbx_cap)
return 0;
if ((mode & DCB_CAP_DCBX_LLD_MANAGED) ||
!(mode & DCB_CAP_DCBX_HOST))
goto err;
- priv->cee_params.dcbx_cap = mode;
+ priv->dcbx_cap = mode;
ets.ets_cap = IEEE_8021QAZ_MAX_TCS;
pfc.pfc_cap = IEEE_8021QAZ_MAX_TCS;
#ifdef CONFIG_MLX4_EN_DCB
if (!mlx4_is_slave(priv->mdev->dev)) {
if (up) {
- priv->flags |= MLX4_EN_FLAG_DCB_ENABLED;
+ if (priv->dcbx_cap)
+ priv->flags |= MLX4_EN_FLAG_DCB_ENABLED;
} else {
priv->flags &= ~MLX4_EN_FLAG_DCB_ENABLED;
- priv->cee_params.dcb_cfg.pfc_state = false;
+ priv->cee_config.pfc_state = false;
}
}
#endif /* CONFIG_MLX4_EN_DCB */
struct mlx4_en_priv *priv;
int i;
int err;
-#ifdef CONFIG_MLX4_EN_DCB
- struct tc_configuration *tc;
-#endif
dev = alloc_etherdev_mqs(sizeof(struct mlx4_en_priv),
MAX_TX_RINGS, MAX_RX_RINGS);
priv->msg_enable = MLX4_EN_MSG_LEVEL;
#ifdef CONFIG_MLX4_EN_DCB
if (!mlx4_is_slave(priv->mdev->dev)) {
- priv->cee_params.dcbx_cap = DCB_CAP_DCBX_VER_CEE |
- DCB_CAP_DCBX_HOST |
- DCB_CAP_DCBX_VER_IEEE;
+ priv->dcbx_cap = DCB_CAP_DCBX_VER_CEE | DCB_CAP_DCBX_HOST |
+ DCB_CAP_DCBX_VER_IEEE;
priv->flags |= MLX4_EN_DCB_ENABLED;
- priv->cee_params.dcb_cfg.pfc_state = false;
+ priv->cee_config.pfc_state = false;
- for (i = 0; i < MLX4_EN_NUM_UP; i++) {
- tc = &priv->cee_params.dcb_cfg.tc_config[i];
- tc->dcb_pfc = pfc_disabled;
- }
+ for (i = 0; i < MLX4_EN_NUM_UP; i++)
+ priv->cee_config.dcb_pfc[i] = pfc_disabled;
if (mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_ETS_CFG) {
dev->dcbnl_ops = &mlx4_en_dcbnl_ops;
real_size = get_real_size(skb, shinfo, dev, &lso_header_size,
&inline_ok, &fragptr);
if (unlikely(!real_size))
- goto tx_drop;
+ goto tx_drop_count;
/* Align descriptor to TXBB size */
desc_size = ALIGN(real_size, TXBB_SIZE);
if (unlikely(nr_txbb > MAX_DESC_TXBBS)) {
if (netif_msg_tx_err(priv))
en_warn(priv, "Oversized header or SG list\n");
- goto tx_drop;
+ goto tx_drop_count;
}
bf_ok = ring->bf_enabled;
PCI_DMA_TODEVICE);
}
+tx_drop_count:
+ ring->tx_dropped++;
tx_drop:
dev_kfree_skb_any(skb);
- ring->tx_dropped++;
return NETDEV_TX_OK;
}
goto tx_drop;
if (mlx4_en_is_tx_ring_full(ring))
- goto tx_drop;
+ goto tx_drop_count;
/* fetch ring->cons far ahead before needing it to avoid stall */
ring_cons = READ_ONCE(ring->cons);
return NETDEV_TX_OK;
-tx_drop:
+tx_drop_count:
ring->tx_dropped++;
+tx_drop:
return NETDEV_TX_BUSY;
}
return 0;
err_out_unmap:
- while (i >= 0)
- mlx4_free_eq(dev, &priv->eq_table.eq[i--]);
+ while (i > 0)
+ mlx4_free_eq(dev, &priv->eq_table.eq[--i]);
#ifdef CONFIG_RFS_ACCEL
for (i = 1; i <= dev->caps.num_ports; i++) {
if (mlx4_priv(dev)->port[i].rmap) {
mlx4_err(dev, "Failed to create mtu file for port %d\n", port);
device_remove_file(&info->dev->persist->pdev->dev,
&info->port_attr);
+ devlink_port_unregister(&info->devlink_port);
info->port = -1;
}
device_remove_file(&info->dev->persist->pdev->dev, &info->port_attr);
device_remove_file(&info->dev->persist->pdev->dev,
&info->port_mtu_attr);
+ devlink_port_unregister(&info->devlink_port);
+
#ifdef CONFIG_RFS_ACCEL
free_irq_cpu_rmap(info->rmap);
info->rmap = NULL;
pfc_enabled_rx
};
-struct tc_configuration {
- enum dcb_pfc_type dcb_pfc;
-};
-
struct mlx4_en_cee_config {
bool pfc_state;
- struct tc_configuration tc_config[MLX4_EN_NUM_UP];
+ enum dcb_pfc_type dcb_pfc[MLX4_EN_NUM_UP];
};
-
-struct mlx4_en_cee_params {
- u8 dcbx_cap;
- struct mlx4_en_cee_config dcb_cfg;
-};
-
#endif
struct ethtool_flow_id {
struct ieee_ets ets;
u16 maxrate[IEEE_8021QAZ_MAX_TCS];
enum dcbnl_cndd_states cndd_state[IEEE_8021QAZ_MAX_TCS];
- struct mlx4_en_cee_params cee_params;
+ struct mlx4_en_cee_config cee_config;
+ u8 dcbx_cap;
#endif
#ifdef CONFIG_RFS_ACCEL
spinlock_t filters_lock;
#define MLX4_FLAG_V_IGNORE_FCS_MASK 0x2
#define MLX4_IGNORE_FCS_MASK 0x1
-#define MLNX4_TX_MAX_NUMBER 8
+#define MLX4_TC_MAX_NUMBER 8
void mlx4_init_mac_table(struct mlx4_dev *dev, struct mlx4_mac_table *table)
{
u8 num_tc = dev->caps.max_tc_eth;
if (!num_tc)
- num_tc = MLNX4_TX_MAX_NUMBER;
+ num_tc = MLX4_TC_MAX_NUMBER;
return num_tc;
}
return cmd->cmd_buf + (idx << cmd->log_stride);
}
-static u8 xor8_buf(void *buf, int len)
+static u8 xor8_buf(void *buf, size_t offset, int len)
{
u8 *ptr = buf;
u8 sum = 0;
int i;
+ int end = len + offset;
- for (i = 0; i < len; i++)
+ for (i = offset; i < end; i++)
sum ^= ptr[i];
return sum;
static int verify_block_sig(struct mlx5_cmd_prot_block *block)
{
- if (xor8_buf(block->rsvd0, sizeof(*block) - sizeof(block->data) - 1) != 0xff)
+ size_t rsvd0_off = offsetof(struct mlx5_cmd_prot_block, rsvd0);
+ int xor_len = sizeof(*block) - sizeof(block->data) - 1;
+
+ if (xor8_buf(block, rsvd0_off, xor_len) != 0xff)
return -EINVAL;
- if (xor8_buf(block, sizeof(*block)) != 0xff)
+ if (xor8_buf(block, 0, sizeof(*block)) != 0xff)
return -EINVAL;
return 0;
}
-static void calc_block_sig(struct mlx5_cmd_prot_block *block, u8 token,
- int csum)
+static void calc_block_sig(struct mlx5_cmd_prot_block *block)
{
- block->token = token;
- if (csum) {
- block->ctrl_sig = ~xor8_buf(block->rsvd0, sizeof(*block) -
- sizeof(block->data) - 2);
- block->sig = ~xor8_buf(block, sizeof(*block) - 1);
- }
+ int ctrl_xor_len = sizeof(*block) - sizeof(block->data) - 2;
+ size_t rsvd0_off = offsetof(struct mlx5_cmd_prot_block, rsvd0);
+
+ block->ctrl_sig = ~xor8_buf(block, rsvd0_off, ctrl_xor_len);
+ block->sig = ~xor8_buf(block, 0, sizeof(*block) - 1);
}
-static void calc_chain_sig(struct mlx5_cmd_msg *msg, u8 token, int csum)
+static void calc_chain_sig(struct mlx5_cmd_msg *msg)
{
struct mlx5_cmd_mailbox *next = msg->next;
-
- while (next) {
- calc_block_sig(next->buf, token, csum);
+ int size = msg->len;
+ int blen = size - min_t(int, sizeof(msg->first.data), size);
+ int n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1)
+ / MLX5_CMD_DATA_BLOCK_SIZE;
+ int i = 0;
+
+ for (i = 0; i < n && next; i++) {
+ calc_block_sig(next->buf);
next = next->next;
}
}
static void set_signature(struct mlx5_cmd_work_ent *ent, int csum)
{
- ent->lay->sig = ~xor8_buf(ent->lay, sizeof(*ent->lay));
- calc_chain_sig(ent->in, ent->token, csum);
- calc_chain_sig(ent->out, ent->token, csum);
+ ent->lay->sig = ~xor8_buf(ent->lay, 0, sizeof(*ent->lay));
+ if (csum) {
+ calc_chain_sig(ent->in);
+ calc_chain_sig(ent->out);
+ }
}
static void poll_timeout(struct mlx5_cmd_work_ent *ent)
struct mlx5_cmd_mailbox *next = ent->out->next;
int err;
u8 sig;
+ int size = ent->out->len;
+ int blen = size - min_t(int, sizeof(ent->out->first.data), size);
+ int n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1)
+ / MLX5_CMD_DATA_BLOCK_SIZE;
+ int i = 0;
- sig = xor8_buf(ent->lay, sizeof(*ent->lay));
+ sig = xor8_buf(ent->lay, 0, sizeof(*ent->lay));
if (sig != 0xff)
return -EINVAL;
- while (next) {
+ for (i = 0; i < n && next; i++) {
err = verify_block_sig(next->buf);
if (err)
return err;
spin_unlock_irqrestore(&cmd->alloc_lock, flags);
}
- ent->token = alloc_token(cmd);
cmd->ent_arr[ent->idx] = ent;
lay = get_inst(cmd, ent->idx);
ent->lay = lay;
static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
struct mlx5_cmd_msg *out, void *uout, int uout_size,
mlx5_cmd_cbk_t callback,
- void *context, int page_queue, u8 *status)
+ void *context, int page_queue, u8 *status,
+ u8 token)
{
struct mlx5_cmd *cmd = &dev->cmd;
struct mlx5_cmd_work_ent *ent;
if (IS_ERR(ent))
return PTR_ERR(ent);
+ ent->token = token;
+
if (!callback)
init_completion(&ent->done);
.write = dbg_write,
};
-static int mlx5_copy_to_msg(struct mlx5_cmd_msg *to, void *from, int size)
+static int mlx5_copy_to_msg(struct mlx5_cmd_msg *to, void *from, int size,
+ u8 token)
{
struct mlx5_cmd_prot_block *block;
struct mlx5_cmd_mailbox *next;
memcpy(block->data, from, copy);
from += copy;
size -= copy;
+ block->token = token;
next = next->next;
}
}
static struct mlx5_cmd_msg *mlx5_alloc_cmd_msg(struct mlx5_core_dev *dev,
- gfp_t flags, int size)
+ gfp_t flags, int size,
+ u8 token)
{
struct mlx5_cmd_mailbox *tmp, *head = NULL;
struct mlx5_cmd_prot_block *block;
tmp->next = head;
block->next = cpu_to_be64(tmp->next ? tmp->next->dma : 0);
block->block_num = cpu_to_be32(n - i - 1);
+ block->token = token;
head = tmp;
}
msg->next = head;
}
if (IS_ERR(msg))
- msg = mlx5_alloc_cmd_msg(dev, gfp, in_size);
+ msg = mlx5_alloc_cmd_msg(dev, gfp, in_size, 0);
return msg;
}
int err;
u8 status = 0;
u32 drv_synd;
+ u8 token;
if (pci_channel_offline(dev->pdev) ||
dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
return err;
}
- err = mlx5_copy_to_msg(inb, in, in_size);
+ token = alloc_token(&dev->cmd);
+
+ err = mlx5_copy_to_msg(inb, in, in_size, token);
if (err) {
mlx5_core_warn(dev, "err %d\n", err);
goto out_in;
}
- outb = mlx5_alloc_cmd_msg(dev, gfp, out_size);
+ outb = mlx5_alloc_cmd_msg(dev, gfp, out_size, token);
if (IS_ERR(outb)) {
err = PTR_ERR(outb);
goto out_in;
}
err = mlx5_cmd_invoke(dev, inb, outb, out, out_size, callback, context,
- pages_queue, &status);
+ pages_queue, &status, token);
if (err)
goto out_out;
INIT_LIST_HEAD(&cmd->cache.med.head);
for (i = 0; i < NUM_LONG_LISTS; i++) {
- msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, LONG_LIST_SIZE);
+ msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, LONG_LIST_SIZE, 0);
if (IS_ERR(msg)) {
err = PTR_ERR(msg);
goto ex_err;
}
for (i = 0; i < NUM_MED_LISTS; i++) {
- msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, MED_LIST_SIZE);
+ msg = mlx5_alloc_cmd_msg(dev, GFP_KERNEL, MED_LIST_SIZE, 0);
if (IS_ERR(msg)) {
err = PTR_ERR(msg);
goto ex_err;
#define MLX5_MPWRQ_PAGES_PER_WQE BIT(MLX5_MPWRQ_WQE_PAGE_ORDER)
#define MLX5_MPWRQ_STRIDES_PER_PAGE (MLX5_MPWRQ_NUM_STRIDES >> \
MLX5_MPWRQ_WQE_PAGE_ORDER)
-#define MLX5_CHANNEL_MAX_NUM_MTTS (ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8) * \
- BIT(MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW))
+
+#define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2)
+#define MLX5E_REQUIRED_MTTS(rqs, wqes)\
+ (rqs * wqes * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8))
+#define MLX5E_VALID_NUM_MTTS(num_mtts) (MLX5_MTT_OCTW(num_mtts) <= U16_MAX)
+
#define MLX5_UMR_ALIGN (2048)
#define MLX5_MPWRQ_SMALL_PACKET_THRESHOLD (128)
};
enum {
- MLX5E_RQ_STATE_POST_WQES_ENABLE,
+ MLX5E_RQ_STATE_FLUSH,
MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS,
- MLX5E_RQ_STATE_FLUSH_TIMEOUT,
MLX5E_RQ_STATE_AM,
};
unsigned long state;
int ix;
+ u32 mpwqe_mtt_offset;
struct mlx5e_rx_am am; /* Adaptive Moderation */
};
enum {
- MLX5E_SQ_STATE_WAKE_TXQ_ENABLE,
+ MLX5E_SQ_STATE_FLUSH,
MLX5E_SQ_STATE_BF_ENABLE,
- MLX5E_SQ_STATE_TX_TIMEOUT,
};
struct mlx5e_ico_wqe_info {
bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
void mlx5e_free_tx_descs(struct mlx5e_sq *sq);
-void mlx5e_free_rx_descs(struct mlx5e_rq *rq);
void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
MLX5E_MAX_NUM_CHANNELS);
}
-static inline int mlx5e_get_mtt_octw(int npages)
-{
- return ALIGN(npages, 8) / 2;
-}
-
extern const struct ethtool_ops mlx5e_ethtool_ops;
#ifdef CONFIG_MLX5_CORE_EN_DCB
extern const struct dcbnl_rtnl_ops mlx5e_dcbnl_ops;
struct mlx5e_tir *tir;
void *in;
int inlen;
- int err;
+ int err = 0;
inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
in = mlx5_vzalloc(inlen);
list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) {
err = mlx5_core_modify_tir(mdev, tir->tirn, in, inlen);
if (err)
- return err;
+ goto out;
}
+out:
kvfree(in);
- return 0;
+ return err;
}
return mlx5_set_port_tc_bw_alloc(mdev, tc_tx_bw);
}
-static int mlx5e_dbcnl_validate_ets(struct ieee_ets *ets)
+static int mlx5e_dbcnl_validate_ets(struct net_device *netdev,
+ struct ieee_ets *ets)
{
int bw_sum = 0;
int i;
/* Validate Priority */
for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
- if (ets->prio_tc[i] >= MLX5E_MAX_PRIORITY)
+ if (ets->prio_tc[i] >= MLX5E_MAX_PRIORITY) {
+ netdev_err(netdev,
+ "Failed to validate ETS: priority value greater than max(%d)\n",
+ MLX5E_MAX_PRIORITY);
return -EINVAL;
+ }
}
/* Validate Bandwidth Sum */
for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) {
- if (!ets->tc_tx_bw[i])
+ if (!ets->tc_tx_bw[i]) {
+ netdev_err(netdev,
+ "Failed to validate ETS: BW 0 is illegal\n");
return -EINVAL;
+ }
bw_sum += ets->tc_tx_bw[i];
}
}
- if (bw_sum != 0 && bw_sum != 100)
+ if (bw_sum != 0 && bw_sum != 100) {
+ netdev_err(netdev,
+ "Failed to validate ETS: BW sum is illegal\n");
return -EINVAL;
+ }
return 0;
}
struct mlx5e_priv *priv = netdev_priv(netdev);
int err;
- err = mlx5e_dbcnl_validate_ets(ets);
+ err = mlx5e_dbcnl_validate_ets(netdev, ets);
if (err)
return err;
if (mlx5e_query_global_pause_combined(priv)) {
for (i = 0; i < NUM_PPORT_PER_PRIO_PFC_COUNTERS; i++) {
data[idx++] = MLX5E_READ_CTR64_BE(&priv->stats.pport.per_prio_counters[0],
- pport_per_prio_pfc_stats_desc, 0);
+ pport_per_prio_pfc_stats_desc, i);
}
}
sq_stats_desc, j);
}
+static u32 mlx5e_rx_wqes_to_packets(struct mlx5e_priv *priv, int rq_wq_type,
+ int num_wqe)
+{
+ int packets_per_wqe;
+ int stride_size;
+ int num_strides;
+ int wqe_size;
+
+ if (rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
+ return num_wqe;
+
+ stride_size = 1 << priv->params.mpwqe_log_stride_sz;
+ num_strides = 1 << priv->params.mpwqe_log_num_strides;
+ wqe_size = stride_size * num_strides;
+
+ packets_per_wqe = wqe_size /
+ ALIGN(ETH_DATA_LEN, stride_size);
+ return (1 << (order_base_2(num_wqe * packets_per_wqe) - 1));
+}
+
+static u32 mlx5e_packets_to_rx_wqes(struct mlx5e_priv *priv, int rq_wq_type,
+ int num_packets)
+{
+ int packets_per_wqe;
+ int stride_size;
+ int num_strides;
+ int wqe_size;
+ int num_wqes;
+
+ if (rq_wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
+ return num_packets;
+
+ stride_size = 1 << priv->params.mpwqe_log_stride_sz;
+ num_strides = 1 << priv->params.mpwqe_log_num_strides;
+ wqe_size = stride_size * num_strides;
+
+ num_packets = (1 << order_base_2(num_packets));
+
+ packets_per_wqe = wqe_size /
+ ALIGN(ETH_DATA_LEN, stride_size);
+ num_wqes = DIV_ROUND_UP(num_packets, packets_per_wqe);
+ return 1 << (order_base_2(num_wqes));
+}
+
static void mlx5e_get_ringparam(struct net_device *dev,
struct ethtool_ringparam *param)
{
struct mlx5e_priv *priv = netdev_priv(dev);
int rq_wq_type = priv->params.rq_wq_type;
- param->rx_max_pending = 1 << mlx5_max_log_rq_size(rq_wq_type);
+ param->rx_max_pending = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
+ 1 << mlx5_max_log_rq_size(rq_wq_type));
param->tx_max_pending = 1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE;
- param->rx_pending = 1 << priv->params.log_rq_size;
+ param->rx_pending = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
+ 1 << priv->params.log_rq_size);
param->tx_pending = 1 << priv->params.log_sq_size;
}
struct mlx5e_priv *priv = netdev_priv(dev);
bool was_opened;
int rq_wq_type = priv->params.rq_wq_type;
+ u32 rx_pending_wqes;
+ u32 min_rq_size;
+ u32 max_rq_size;
u16 min_rx_wqes;
u8 log_rq_size;
u8 log_sq_size;
+ u32 num_mtts;
int err = 0;
if (param->rx_jumbo_pending) {
__func__);
return -EINVAL;
}
- if (param->rx_pending < (1 << mlx5_min_log_rq_size(rq_wq_type))) {
+
+ min_rq_size = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
+ 1 << mlx5_min_log_rq_size(rq_wq_type));
+ max_rq_size = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
+ 1 << mlx5_max_log_rq_size(rq_wq_type));
+ rx_pending_wqes = mlx5e_packets_to_rx_wqes(priv, rq_wq_type,
+ param->rx_pending);
+
+ if (param->rx_pending < min_rq_size) {
netdev_info(dev, "%s: rx_pending (%d) < min (%d)\n",
__func__, param->rx_pending,
- 1 << mlx5_min_log_rq_size(rq_wq_type));
+ min_rq_size);
return -EINVAL;
}
- if (param->rx_pending > (1 << mlx5_max_log_rq_size(rq_wq_type))) {
+ if (param->rx_pending > max_rq_size) {
netdev_info(dev, "%s: rx_pending (%d) > max (%d)\n",
__func__, param->rx_pending,
- 1 << mlx5_max_log_rq_size(rq_wq_type));
+ max_rq_size);
return -EINVAL;
}
+
+ num_mtts = MLX5E_REQUIRED_MTTS(priv->params.num_channels,
+ rx_pending_wqes);
+ if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
+ !MLX5E_VALID_NUM_MTTS(num_mtts)) {
+ netdev_info(dev, "%s: rx_pending (%d) request can't be satisfied, try to reduce.\n",
+ __func__, param->rx_pending);
+ return -EINVAL;
+ }
+
if (param->tx_pending < (1 << MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)) {
netdev_info(dev, "%s: tx_pending (%d) < min (%d)\n",
__func__, param->tx_pending,
return -EINVAL;
}
- log_rq_size = order_base_2(param->rx_pending);
+ log_rq_size = order_base_2(rx_pending_wqes);
log_sq_size = order_base_2(param->tx_pending);
- min_rx_wqes = mlx5_min_rx_wqes(rq_wq_type, param->rx_pending);
+ min_rx_wqes = mlx5_min_rx_wqes(rq_wq_type, rx_pending_wqes);
if (log_rq_size == priv->params.log_rq_size &&
log_sq_size == priv->params.log_sq_size &&
unsigned int count = ch->combined_count;
bool arfs_enabled;
bool was_opened;
+ u32 num_mtts;
int err = 0;
if (!count) {
return -EINVAL;
}
+ num_mtts = MLX5E_REQUIRED_MTTS(count, BIT(priv->params.log_rq_size));
+ if (priv->params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
+ !MLX5E_VALID_NUM_MTTS(num_mtts)) {
+ netdev_info(dev, "%s: rx count (%d) request can't be satisfied, try to reduce.\n",
+ __func__, count);
+ return -EINVAL;
+ }
+
if (priv->params.num_channels == count)
return 0;
static void ptys2ethtool_supported_link(unsigned long *supported_modes,
u32 eth_proto_cap)
{
+ unsigned long proto_cap = eth_proto_cap;
int proto;
- for_each_set_bit(proto, (unsigned long *)ð_proto_cap, MLX5E_LINK_MODES_NUMBER)
+ for_each_set_bit(proto, &proto_cap, MLX5E_LINK_MODES_NUMBER)
bitmap_or(supported_modes, supported_modes,
ptys2ethtool_table[proto].supported,
__ETHTOOL_LINK_MODE_MASK_NBITS);
static void ptys2ethtool_adver_link(unsigned long *advertising_modes,
u32 eth_proto_cap)
{
+ unsigned long proto_cap = eth_proto_cap;
int proto;
- for_each_set_bit(proto, (unsigned long *)ð_proto_cap, MLX5E_LINK_MODES_NUMBER)
+ for_each_set_bit(proto, &proto_cap, MLX5E_LINK_MODES_NUMBER)
bitmap_or(advertising_modes, advertising_modes,
ptys2ethtool_table[proto].advertised,
__ETHTOOL_LINK_MODE_MASK_NBITS);
#include "eswitch.h"
#include "vxlan.h"
-enum {
- MLX5_EN_QP_FLUSH_TIMEOUT_MS = 5000,
- MLX5_EN_QP_FLUSH_MSLEEP_QUANT = 20,
- MLX5_EN_QP_FLUSH_MAX_ITER = MLX5_EN_QP_FLUSH_TIMEOUT_MS /
- MLX5_EN_QP_FLUSH_MSLEEP_QUANT,
-};
-
struct mlx5e_rq_param {
u32 rqc[MLX5_ST_SZ_DW(rqc)];
struct mlx5_wq_param wq;
s->tx_queue_stopped += sq_stats->stopped;
s->tx_queue_wake += sq_stats->wake;
s->tx_queue_dropped += sq_stats->dropped;
+ s->tx_xmit_more += sq_stats->xmit_more;
s->tx_csum_partial_inner += sq_stats->csum_partial_inner;
tx_offload_none += sq_stats->csum_none;
}
rq->alloc_wqe = mlx5e_alloc_rx_mpwqe;
rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe;
+ rq->mpwqe_mtt_offset = c->ix *
+ MLX5E_REQUIRED_MTTS(1, BIT(priv->params.log_rq_size));
+
rq->mpwqe_stride_sz = BIT(priv->params.mpwqe_log_stride_sz);
rq->mpwqe_num_strides = BIT(priv->params.mpwqe_log_num_strides);
rq->wqe_sz = rq->mpwqe_stride_sz * rq->mpwqe_num_strides;
MLX5_SET(rqc, rqc, cqn, rq->cq.mcq.cqn);
MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RST);
- MLX5_SET(rqc, rqc, flush_in_error_en, 1);
MLX5_SET(rqc, rqc, vsd, priv->params.vlan_strip_disable);
MLX5_SET(wq, wq, log_wq_pg_sz, rq->wq_ctrl.buf.page_shift -
MLX5_ADAPTER_PAGE_SHIFT);
return -ETIMEDOUT;
}
+static void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
+{
+ struct mlx5_wq_ll *wq = &rq->wq;
+ struct mlx5e_rx_wqe *wqe;
+ __be16 wqe_ix_be;
+ u16 wqe_ix;
+
+ /* UMR WQE (if in progress) is always at wq->head */
+ if (test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state))
+ mlx5e_free_rx_fragmented_mpwqe(rq, &rq->wqe_info[wq->head]);
+
+ while (!mlx5_wq_ll_is_empty(wq)) {
+ wqe_ix_be = *wq->tail_next;
+ wqe_ix = be16_to_cpu(wqe_ix_be);
+ wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_ix);
+ rq->dealloc_wqe(rq, wqe_ix);
+ mlx5_wq_ll_pop(&rq->wq, wqe_ix_be,
+ &wqe->next.next_wqe_index);
+ }
+}
+
static int mlx5e_open_rq(struct mlx5e_channel *c,
struct mlx5e_rq_param *param,
struct mlx5e_rq *rq)
if (param->am_enabled)
set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
- set_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state);
-
sq->ico_wqe_info[pi].opcode = MLX5_OPCODE_NOP;
sq->ico_wqe_info[pi].num_wqebbs = 1;
mlx5e_send_nop(sq, true); /* trigger mlx5e_post_rx_wqes() */
static void mlx5e_close_rq(struct mlx5e_rq *rq)
{
- int tout = 0;
- int err;
-
- clear_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state);
+ set_bit(MLX5E_RQ_STATE_FLUSH, &rq->state);
napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */
-
- err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RDY, MLX5_RQC_STATE_ERR);
- while (!mlx5_wq_ll_is_empty(&rq->wq) && !err &&
- tout++ < MLX5_EN_QP_FLUSH_MAX_ITER)
- msleep(MLX5_EN_QP_FLUSH_MSLEEP_QUANT);
-
- if (err || tout == MLX5_EN_QP_FLUSH_MAX_ITER)
- set_bit(MLX5E_RQ_STATE_FLUSH_TIMEOUT, &rq->state);
-
- /* avoid destroying rq before mlx5e_poll_rx_cq() is done with it */
- napi_synchronize(&rq->channel->napi);
-
cancel_work_sync(&rq->am.work);
mlx5e_disable_rq(rq);
goto err_disable_sq;
if (sq->txq) {
- set_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state);
netdev_tx_reset_queue(sq->txq);
netif_tx_start_queue(sq->txq);
}
static void mlx5e_close_sq(struct mlx5e_sq *sq)
{
- int tout = 0;
- int err;
+ set_bit(MLX5E_SQ_STATE_FLUSH, &sq->state);
+ /* prevent netif_tx_wake_queue */
+ napi_synchronize(&sq->channel->napi);
if (sq->txq) {
- clear_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state);
- /* prevent netif_tx_wake_queue */
- napi_synchronize(&sq->channel->napi);
netif_tx_disable_queue(sq->txq);
- /* ensure hw is notified of all pending wqes */
+ /* last doorbell out, godspeed .. */
if (mlx5e_sq_has_room_for(sq, 1))
mlx5e_send_nop(sq, true);
-
- err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY,
- MLX5_SQC_STATE_ERR, false, 0);
- if (err)
- set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
- }
-
- /* wait till sq is empty, unless a TX timeout occurred on this SQ */
- while (sq->cc != sq->pc &&
- !test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state)) {
- msleep(MLX5_EN_QP_FLUSH_MSLEEP_QUANT);
- if (tout++ > MLX5_EN_QP_FLUSH_MAX_ITER)
- set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
}
- /* avoid destroying sq before mlx5e_poll_tx_cq() is done with it */
- napi_synchronize(&sq->channel->napi);
-
- mlx5e_free_tx_descs(sq);
mlx5e_disable_sq(sq);
+ mlx5e_free_tx_descs(sq);
mlx5e_destroy_sq(sq);
}
netif_set_real_num_tx_queues(netdev, num_txqs);
netif_set_real_num_rx_queues(netdev, priv->params.num_channels);
- err = mlx5e_set_dev_port_mtu(netdev);
- if (err)
- goto err_clear_state_opened_flag;
-
err = mlx5e_open_channels(priv);
if (err) {
netdev_err(netdev, "%s: mlx5e_open_channels failed, %d\n",
u16 max_mtu;
u16 min_mtu;
int err = 0;
+ bool reset;
mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
mutex_lock(&priv->state_lock);
+ reset = !priv->params.lro_en &&
+ (priv->params.rq_wq_type !=
+ MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ);
+
was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
- if (was_opened)
+ if (was_opened && reset)
mlx5e_close_locked(netdev);
netdev->mtu = new_mtu;
+ mlx5e_set_dev_port_mtu(netdev);
- if (was_opened)
+ if (was_opened && reset)
err = mlx5e_open_locked(netdev);
mutex_unlock(&priv->state_lock);
if (!netif_xmit_stopped(netdev_get_tx_queue(dev, i)))
continue;
sched_work = true;
- set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
+ set_bit(MLX5E_SQ_STATE_FLUSH, &sq->state);
netdev_err(dev, "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x\n",
i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc);
}
struct mlx5_create_mkey_mbox_in *in;
struct mlx5_mkey_seg *mkc;
int inlen = sizeof(*in);
- u64 npages =
- priv->profile->max_nch(mdev) * MLX5_CHANNEL_MAX_NUM_MTTS;
+ u64 npages = MLX5E_REQUIRED_MTTS(priv->profile->max_nch(mdev),
+ BIT(MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE_MPW));
int err;
in = mlx5_vzalloc(inlen);
MLX5_PERM_LOCAL_WRITE |
MLX5_ACCESS_MODE_MTT;
+ npages = min_t(u32, ALIGN(U16_MAX, 4) * 2, npages);
+
mkc->qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
mkc->flags_pd = cpu_to_be32(mdev->mlx5e_res.pdn);
mkc->len = cpu_to_be64(npages << PAGE_SHIFT);
- mkc->xlt_oct_size = cpu_to_be32(mlx5e_get_mtt_octw(npages));
+ mkc->xlt_oct_size = cpu_to_be32(MLX5_MTT_OCTW(npages));
mkc->log2_page_size = PAGE_SHIFT;
err = mlx5_core_create_mkey(mdev, &priv->umr_mkey, in, inlen, NULL,
queue_work(priv->wq, &priv->set_rx_mode_work);
if (MLX5_CAP_GEN(mdev, vport_group_manager)) {
+ mlx5_query_nic_vport_mac_address(mdev, 0, rep.hw_id);
rep.load = mlx5e_nic_rep_load;
rep.unload = mlx5e_nic_rep_unload;
rep.vport = 0;
mlx5e_init_l2_addr(priv);
+ mlx5e_set_dev_port_mtu(netdev);
+
err = register_netdev(netdev);
if (err) {
mlx5_core_err(mdev, "register_netdev failed, %d\n", err);
struct mlx5_eswitch *esw = mdev->priv.eswitch;
int total_vfs = MLX5_TOTAL_VPORTS(mdev);
int vport;
+ u8 mac[ETH_ALEN];
if (!MLX5_CAP_GEN(mdev, vport_group_manager))
return;
+ mlx5_query_nic_vport_mac_address(mdev, 0, mac);
+
for (vport = 1; vport < total_vfs; vport++) {
struct mlx5_eswitch_rep rep;
rep.load = mlx5e_vport_rep_load;
rep.unload = mlx5e_vport_rep_unload;
rep.vport = vport;
+ ether_addr_copy(rep.hw_id, mac);
mlx5_eswitch_register_vport_rep(esw, &rep);
}
}
int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr)
{
struct mlx5e_priv *priv = netdev_priv(dev);
+ struct mlx5_eswitch_rep *rep = priv->ppriv;
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
- u8 mac[ETH_ALEN];
if (esw->mode == SRIOV_NONE)
return -EOPNOTSUPP;
switch (attr->id) {
case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
- mlx5_query_nic_vport_mac_address(priv->mdev, 0, mac);
attr->u.ppid.id_len = ETH_ALEN;
- memcpy(&attr->u.ppid.id, &mac, ETH_ALEN);
+ ether_addr_copy(attr->u.ppid.id, rep->hw_id);
break;
default:
return -EOPNOTSUPP;
}
}
-static u16 mlx5e_get_wqe_mtt_offset(u16 rq_ix, u16 wqe_ix)
+static u32 mlx5e_get_wqe_mtt_offset(struct mlx5e_rq *rq, u16 wqe_ix)
{
- return rq_ix * MLX5_CHANNEL_MAX_NUM_MTTS +
+ return rq->mpwqe_mtt_offset +
wqe_ix * ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8);
}
struct mlx5_wqe_data_seg *dseg = &wqe->data;
struct mlx5e_mpw_info *wi = &rq->wqe_info[ix];
u8 ds_cnt = DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_DS);
- u16 umr_wqe_mtt_offset = mlx5e_get_wqe_mtt_offset(rq->ix, ix);
+ u32 umr_wqe_mtt_offset = mlx5e_get_wqe_mtt_offset(rq, ix);
memset(wqe, 0, sizeof(*wqe));
cseg->opmod_idx_opcode =
ucseg->flags = MLX5_UMR_TRANSLATION_OFFSET_EN;
ucseg->klm_octowords =
- cpu_to_be16(mlx5e_get_mtt_octw(MLX5_MPWRQ_PAGES_PER_WQE));
+ cpu_to_be16(MLX5_MTT_OCTW(MLX5_MPWRQ_PAGES_PER_WQE));
ucseg->bsf_octowords =
- cpu_to_be16(mlx5e_get_mtt_octw(umr_wqe_mtt_offset));
+ cpu_to_be16(MLX5_MTT_OCTW(umr_wqe_mtt_offset));
ucseg->mkey_mask = cpu_to_be64(MLX5_MKEY_MASK_FREE);
dseg->lkey = sq->mkey_be;
{
struct mlx5e_mpw_info *wi = &rq->wqe_info[ix];
int mtt_sz = mlx5e_get_wqe_mtt_sz();
- u32 dma_offset = mlx5e_get_wqe_mtt_offset(rq->ix, ix) << PAGE_SHIFT;
+ u64 dma_offset = (u64)mlx5e_get_wqe_mtt_offset(rq, ix) << PAGE_SHIFT;
int i;
wi->umr.dma_info = kmalloc(sizeof(*wi->umr.dma_info) *
struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(wq, wq->head);
clear_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state);
+
+ if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state))) {
+ mlx5e_free_rx_fragmented_mpwqe(rq, &rq->wqe_info[wq->head]);
+ return;
+ }
+
mlx5_wq_ll_push(wq, be16_to_cpu(wqe->next.next_wqe_index));
rq->stats.mpwqe_frag++;
wi->free_wqe(rq, wi);
}
-void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
-{
- struct mlx5_wq_ll *wq = &rq->wq;
- struct mlx5e_rx_wqe *wqe;
- __be16 wqe_ix_be;
- u16 wqe_ix;
-
- while (!mlx5_wq_ll_is_empty(wq)) {
- wqe_ix_be = *wq->tail_next;
- wqe_ix = be16_to_cpu(wqe_ix_be);
- wqe = mlx5_wq_ll_get_wqe(&rq->wq, wqe_ix);
- rq->dealloc_wqe(rq, wqe_ix);
- mlx5_wq_ll_pop(&rq->wq, wqe_ix_be,
- &wqe->next.next_wqe_index);
- }
-}
-
#define RQ_CANNOT_POST(rq) \
- (!test_bit(MLX5E_RQ_STATE_POST_WQES_ENABLE, &rq->state) || \
- test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state))
+ (test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state) || \
+ test_bit(MLX5E_RQ_STATE_UMR_WQE_IN_PROGRESS, &rq->state))
bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)
{
static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe,
u32 cqe_bcnt)
{
- struct ethhdr *eth = (struct ethhdr *)(skb->data);
- struct iphdr *ipv4 = (struct iphdr *)(skb->data + ETH_HLEN);
- struct ipv6hdr *ipv6 = (struct ipv6hdr *)(skb->data + ETH_HLEN);
+ struct ethhdr *eth = (struct ethhdr *)(skb->data);
+ struct iphdr *ipv4;
+ struct ipv6hdr *ipv6;
struct tcphdr *tcp;
+ int network_depth = 0;
+ __be16 proto;
+ u16 tot_len;
u8 l4_hdr_type = get_cqe_l4_hdr_type(cqe);
int tcp_ack = ((CQE_L4_HDR_TYPE_TCP_ACK_NO_DATA == l4_hdr_type) ||
(CQE_L4_HDR_TYPE_TCP_ACK_AND_DATA == l4_hdr_type));
- u16 tot_len = cqe_bcnt - ETH_HLEN;
+ skb->mac_len = ETH_HLEN;
+ proto = __vlan_get_protocol(skb, eth->h_proto, &network_depth);
+
+ ipv4 = (struct iphdr *)(skb->data + network_depth);
+ ipv6 = (struct ipv6hdr *)(skb->data + network_depth);
+ tot_len = cqe_bcnt - network_depth;
- if (eth->h_proto == htons(ETH_P_IP)) {
- tcp = (struct tcphdr *)(skb->data + ETH_HLEN +
+ if (proto == htons(ETH_P_IP)) {
+ tcp = (struct tcphdr *)(skb->data + network_depth +
sizeof(struct iphdr));
ipv6 = NULL;
skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
} else {
- tcp = (struct tcphdr *)(skb->data + ETH_HLEN +
+ tcp = (struct tcphdr *)(skb->data + network_depth +
sizeof(struct ipv6hdr));
ipv4 = NULL;
skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq);
int work_done = 0;
- if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH_TIMEOUT, &rq->state)))
+ if (unlikely(test_bit(MLX5E_RQ_STATE_FLUSH, &rq->state)))
return 0;
if (cq->decmprs_left)
u64 tx_queue_stopped;
u64 tx_queue_wake;
u64 tx_queue_dropped;
+ u64 tx_xmit_more;
u64 rx_wqe_err;
u64 rx_mpwqe_filler;
u64 rx_mpwqe_frag;
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_stopped) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_dropped) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xmit_more) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_frag) },
/* commonly accessed in data path */
u64 packets;
u64 bytes;
+ u64 xmit_more;
u64 tso_packets;
u64 tso_bytes;
u64 tso_inner_packets;
{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, stopped) },
{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) },
{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, dropped) },
+ { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, xmit_more) },
};
#define NUM_SW_COUNTERS ARRAY_SIZE(sw_stats_desc)
if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
struct flow_dissector_key_control *key =
skb_flow_dissector_target(f->dissector,
- FLOW_DISSECTOR_KEY_BASIC,
+ FLOW_DISSECTOR_KEY_CONTROL,
f->key);
addr_type = key->addr_type;
}
u32 *action, u32 *flow_tag)
{
const struct tc_action *a;
+ LIST_HEAD(actions);
if (tc_no_actions(exts))
return -EINVAL;
*flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
*action = 0;
- tc_for_each_action(a, exts) {
+ tcf_exts_to_list(exts, &actions);
+ list_for_each_entry(a, &actions, list) {
/* Only support a single action per rule */
if (*action)
return -EINVAL;
u32 *action, u32 *dest_vport)
{
const struct tc_action *a;
+ LIST_HEAD(actions);
if (tc_no_actions(exts))
return -EINVAL;
*action = 0;
- tc_for_each_action(a, exts) {
+ tcf_exts_to_list(exts, &actions);
+ list_for_each_entry(a, &actions, list) {
/* Only support a single action per rule */
if (*action)
return -EINVAL;
struct mlx5e_tc_flow *flow;
struct tc_action *a;
struct mlx5_fc *counter;
+ LIST_HEAD(actions);
u64 bytes;
u64 packets;
u64 lastuse;
mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse);
- tc_for_each_action(a, f->exts)
+ tcf_exts_to_list(f->exts, &actions);
+ list_for_each_entry(a, &actions, list)
tcf_action_stats_update(a, bytes, packets, lastuse);
return 0;
sq->stats.stopped++;
}
+ sq->stats.xmit_more += skb->xmit_more;
if (!skb->xmit_more || netif_xmit_stopped(sq->txq)) {
int bf_sz = 0;
return mlx5e_sq_xmit(sq, skb);
}
-void mlx5e_free_tx_descs(struct mlx5e_sq *sq)
-{
- struct mlx5e_tx_wqe_info *wi;
- struct sk_buff *skb;
- u16 ci;
- int i;
-
- while (sq->cc != sq->pc) {
- ci = sq->cc & sq->wq.sz_m1;
- skb = sq->skb[ci];
- wi = &sq->wqe_info[ci];
-
- if (!skb) { /* nop */
- sq->cc++;
- continue;
- }
-
- for (i = 0; i < wi->num_dma; i++) {
- struct mlx5e_sq_dma *dma =
- mlx5e_dma_get(sq, sq->dma_fifo_cc++);
-
- mlx5e_tx_dma_unmap(sq->pdev, dma);
- }
-
- dev_kfree_skb_any(skb);
- sq->cc += wi->num_wqebbs;
- }
-}
-
bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
{
struct mlx5e_sq *sq;
sq = container_of(cq, struct mlx5e_sq, cq);
- if (unlikely(test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state)))
+ if (unlikely(test_bit(MLX5E_SQ_STATE_FLUSH, &sq->state)))
return false;
npkts = 0;
netdev_tx_completed_queue(sq->txq, npkts, nbytes);
if (netif_tx_queue_stopped(sq->txq) &&
- mlx5e_sq_has_room_for(sq, MLX5E_SQ_STOP_ROOM) &&
- likely(test_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state))) {
- netif_tx_wake_queue(sq->txq);
- sq->stats.wake++;
+ mlx5e_sq_has_room_for(sq, MLX5E_SQ_STOP_ROOM)) {
+ netif_tx_wake_queue(sq->txq);
+ sq->stats.wake++;
}
return (i == MLX5E_TX_CQ_POLL_BUDGET);
}
+
+void mlx5e_free_tx_descs(struct mlx5e_sq *sq)
+{
+ struct mlx5e_tx_wqe_info *wi;
+ struct sk_buff *skb;
+ u16 ci;
+ int i;
+
+ while (sq->cc != sq->pc) {
+ ci = sq->cc & sq->wq.sz_m1;
+ skb = sq->skb[ci];
+ wi = &sq->wqe_info[ci];
+
+ if (!skb) { /* nop */
+ sq->cc++;
+ continue;
+ }
+
+ for (i = 0; i < wi->num_dma; i++) {
+ struct mlx5e_sq_dma *dma =
+ mlx5e_dma_get(sq, sq->dma_fifo_cc++);
+
+ mlx5e_tx_dma_unmap(sq->pdev, dma);
+ }
+
+ dev_kfree_skb_any(skb);
+ sq->cc += wi->num_wqebbs;
+ }
+}
static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq)
{
+ struct mlx5e_sq *sq = container_of(cq, struct mlx5e_sq, cq);
struct mlx5_wq_cyc *wq;
struct mlx5_cqe64 *cqe;
- struct mlx5e_sq *sq;
u16 sqcc;
+ if (unlikely(test_bit(MLX5E_SQ_STATE_FLUSH, &sq->state)))
+ return;
+
cqe = mlx5e_get_cqe(cq);
if (likely(!cqe))
return;
- sq = container_of(cq, struct mlx5e_sq, cq);
wq = &sq->wq;
/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
esw_debug(esw->dev, "Enabling VPORT(%d)\n", vport_num);
- if (vport_num) { /* Only VFs need ACLs for VST and spoofchk filtering */
+ /* Only VFs need ACLs for VST and spoofchk filtering */
+ if (vport_num && esw->mode == SRIOV_LEGACY) {
esw_vport_ingress_config(esw, vport);
esw_vport_egress_config(esw, vport);
}
*/
esw_vport_change_handle_locked(vport);
vport->enabled_events = 0;
- if (vport_num) {
+ if (vport_num && esw->mode == SRIOV_LEGACY) {
esw_vport_disable_egress_acl(esw, vport);
esw_vport_disable_ingress_acl(esw, vport);
}
abort:
esw_enable_vport(esw, 0, UC_ADDR_CHANGE);
+ esw->mode = SRIOV_NONE;
return err;
}
vport, err);
mutex_lock(&esw->state_lock);
- if (evport->enabled)
+ if (evport->enabled && esw->mode == SRIOV_LEGACY)
err = esw_vport_ingress_config(esw, evport);
mutex_unlock(&esw->state_lock);
return err;
mutex_lock(&esw->state_lock);
evport->vlan = vlan;
evport->qos = qos;
- if (evport->enabled) {
+ if (evport->enabled && esw->mode == SRIOV_LEGACY) {
err = esw_vport_ingress_config(esw, evport);
if (err)
goto out;
mutex_lock(&esw->state_lock);
pschk = evport->spoofchk;
evport->spoofchk = spoofchk;
- if (evport->enabled)
+ if (evport->enabled && esw->mode == SRIOV_LEGACY) {
err = esw_vport_ingress_config(esw, evport);
- if (err)
- evport->spoofchk = pschk;
+ if (err)
+ evport->spoofchk = pschk;
+ }
mutex_unlock(&esw->state_lock);
return err;
void *priv_data;
struct list_head vport_sqs_list;
bool valid;
+ u8 hw_id[ETH_ALEN];
};
struct mlx5_esw_offload {
dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
dest.vport_num = vport;
- flow_rule = mlx5_add_flow_rule(esw->fdb_table.fdb, spec,
+ flow_rule = mlx5_add_flow_rule(esw->fdb_table.offloads.fdb, spec,
MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,
0, &dest);
if (IS_ERR(flow_rule))
static int esw_offloads_start(struct mlx5_eswitch *esw)
{
- int err, num_vfs = esw->dev->priv.sriov.num_vfs;
+ int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs;
if (esw->mode != SRIOV_LEGACY) {
esw_warn(esw->dev, "Can't set offloads mode, SRIOV legacy not enabled\n");
mlx5_eswitch_disable_sriov(esw);
err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_OFFLOADS);
- if (err)
- esw_warn(esw->dev, "Failed set eswitch to offloads, err %d\n", err);
+ if (err) {
+ esw_warn(esw->dev, "Failed setting eswitch to offloads, err %d\n", err);
+ err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY);
+ if (err1)
+ esw_warn(esw->dev, "Failed setting eswitch back to legacy, err %d\n", err);
+ }
return err;
}
static int esw_offloads_stop(struct mlx5_eswitch *esw)
{
- int err, num_vfs = esw->dev->priv.sriov.num_vfs;
+ int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs;
mlx5_eswitch_disable_sriov(esw);
err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY);
- if (err)
- esw_warn(esw->dev, "Failed set eswitch legacy mode. err %d\n", err);
+ if (err) {
+ esw_warn(esw->dev, "Failed setting eswitch to legacy, err %d\n", err);
+ err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_OFFLOADS);
+ if (err1)
+ esw_warn(esw->dev, "Failed setting eswitch back to offloads, err %d\n", err);
+ }
return err;
}
esw_destroy_offloads_fdb_table(esw);
}
-static int mlx5_esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
+static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
{
switch (mode) {
case DEVLINK_ESWITCH_MODE_LEGACY:
return 0;
}
+static int esw_mode_to_devlink(u16 mlx5_mode, u16 *mode)
+{
+ switch (mlx5_mode) {
+ case SRIOV_LEGACY:
+ *mode = DEVLINK_ESWITCH_MODE_LEGACY;
+ break;
+ case SRIOV_OFFLOADS:
+ *mode = DEVLINK_ESWITCH_MODE_SWITCHDEV;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode)
{
struct mlx5_core_dev *dev;
if (cur_mlx5_mode == SRIOV_NONE)
return -EOPNOTSUPP;
- if (mlx5_esw_mode_from_devlink(mode, &mlx5_mode))
+ if (esw_mode_from_devlink(mode, &mlx5_mode))
return -EINVAL;
if (cur_mlx5_mode == mlx5_mode)
if (dev->priv.eswitch->mode == SRIOV_NONE)
return -EOPNOTSUPP;
- *mode = dev->priv.eswitch->mode;
-
- return 0;
+ return esw_mode_to_devlink(dev->priv.eswitch->mode, mode);
}
void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw,
mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, u16 id, int num)
{
struct mlx5_cmd_fc_bulk *b;
- int outlen = sizeof(*b) +
+ int outlen =
MLX5_ST_SZ_BYTES(query_flow_counter_out) +
MLX5_ST_SZ_BYTES(traffic_counter) * num;
- b = kzalloc(outlen, GFP_KERNEL);
+ b = kzalloc(sizeof(*b) + outlen, GFP_KERNEL);
if (!b)
return NULL;
LEFTOVERS_NUM_PRIOS)
#define ETHTOOL_PRIO_NUM_LEVELS 1
-#define ETHTOOL_NUM_PRIOS 10
+#define ETHTOOL_NUM_PRIOS 11
#define ETHTOOL_MIN_LEVEL (KERNEL_MIN_LEVEL + ETHTOOL_NUM_PRIOS)
/* Vlan, mac, ttc, aRFS */
#define KERNEL_NIC_PRIO_NUM_LEVELS 4
for (node = &first->node; node; node = rb_next(node)) {
struct mlx5_fc *counter = rb_entry(node, struct mlx5_fc, node);
struct mlx5_fc_cache *c = &counter->cache;
+ u64 packets;
+ u64 bytes;
if (counter->id > last_id)
break;
mlx5_cmd_fc_bulk_get(dev, b,
- counter->id, &c->packets, &c->bytes);
+ counter->id, &packets, &bytes);
+
+ if (c->packets == packets)
+ continue;
+
+ c->packets = packets;
+ c->bytes = bytes;
+ c->lastuse = jiffies;
}
out:
dev_info(&pdev->dev, "%s was called\n", __func__);
mlx5_enter_error_state(dev);
mlx5_unload_one(dev, priv);
+ pci_save_state(pdev);
mlx5_pci_disable_device(dev);
return state == pci_channel_io_perm_failure ?
PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET;
}
-static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev)
-{
- struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
- int err = 0;
-
- dev_info(&pdev->dev, "%s was called\n", __func__);
-
- err = mlx5_pci_enable_device(dev);
- if (err) {
- dev_err(&pdev->dev, "%s: mlx5_pci_enable_device failed with error code: %d\n"
- , __func__, err);
- return PCI_ERS_RESULT_DISCONNECT;
- }
- pci_set_master(pdev);
- pci_set_power_state(pdev, PCI_D0);
- pci_restore_state(pdev);
-
- return err ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
-}
-
-void mlx5_disable_device(struct mlx5_core_dev *dev)
-{
- mlx5_pci_err_detected(dev->pdev, 0);
-}
-
/* wait for the device to show vital signs by waiting
* for the health counter to start counting.
*/
return -ETIMEDOUT;
}
-static void mlx5_pci_resume(struct pci_dev *pdev)
+static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev)
{
struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
- struct mlx5_priv *priv = &dev->priv;
int err;
dev_info(&pdev->dev, "%s was called\n", __func__);
- pci_save_state(pdev);
- err = wait_vital(pdev);
+ err = mlx5_pci_enable_device(dev);
if (err) {
+ dev_err(&pdev->dev, "%s: mlx5_pci_enable_device failed with error code: %d\n"
+ , __func__, err);
+ return PCI_ERS_RESULT_DISCONNECT;
+ }
+
+ pci_set_master(pdev);
+ pci_restore_state(pdev);
+
+ if (wait_vital(pdev)) {
dev_err(&pdev->dev, "%s: wait_vital timed out\n", __func__);
- return;
+ return PCI_ERS_RESULT_DISCONNECT;
}
+ return PCI_ERS_RESULT_RECOVERED;
+}
+
+void mlx5_disable_device(struct mlx5_core_dev *dev)
+{
+ mlx5_pci_err_detected(dev->pdev, 0);
+}
+
+static void mlx5_pci_resume(struct pci_dev *pdev)
+{
+ struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
+ struct mlx5_priv *priv = &dev->priv;
+ int err;
+
+ dev_info(&pdev->dev, "%s was called\n", __func__);
+
err = mlx5_load_one(dev, priv);
if (err)
dev_err(&pdev->dev, "%s: mlx5_load_one failed with error code: %d\n"
#define MLXSW_PORT_PHY_BITS_MASK (MLXSW_PORT_MAX_PHY_PORTS - 1)
#define MLXSW_PORT_CPU_PORT 0x0
+#define MLXSW_PORT_ROUTER_PORT (MLXSW_PORT_MAX_PHY_PORTS + 2)
#define MLXSW_PORT_DONT_CARE (MLXSW_PORT_MAX_PORTS)
*/
MLXSW_ITEM32(reg, ritr, ipv6_fe, 0x04, 28, 1);
+/* reg_ritr_lb_en
+ * Loop-back filter enable for unicast packets.
+ * If the flag is set then loop-back filter for unicast packets is
+ * implemented on the RIF. Multicast packets are always subject to
+ * loop-back filtering.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, lb_en, 0x04, 24, 1);
+
/* reg_ritr_virtual_router
* Virtual router ID associated with the router interface.
* Access: RW
mlxsw_reg_ritr_op_set(payload, op);
mlxsw_reg_ritr_rif_set(payload, rif);
mlxsw_reg_ritr_ipv4_fe_set(payload, 1);
+ mlxsw_reg_ritr_lb_en_set(payload, 1);
mlxsw_reg_ritr_mtu_set(payload, mtu);
mlxsw_reg_ritr_if_mac_memcpy_to(payload, mac);
}
{
MLXSW_REG_ZERO(ralue, payload);
mlxsw_reg_ralue_protocol_set(payload, protocol);
+ mlxsw_reg_ralue_op_set(payload, op);
mlxsw_reg_ralue_virtual_router_set(payload, virtual_router);
mlxsw_reg_ralue_prefix_len_set(payload, prefix_len);
mlxsw_reg_ralue_entry_type_set(payload,
#include <generated/utsrelease.h>
#include <net/pkt_cls.h>
#include <net/tc_act/tc_mirred.h>
+#include <net/netevent.h>
#include "spectrum.h"
#include "core.h"
kfree(mlxsw_sp_vport);
}
-int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto,
- u16 vid)
+static int mlxsw_sp_port_add_vid(struct net_device *dev,
+ __be16 __always_unused proto, u16 vid)
{
struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
struct mlxsw_sp_port *mlxsw_sp_vport;
if (!vid)
return 0;
- if (mlxsw_sp_port_vport_find(mlxsw_sp_port, vid)) {
- netdev_warn(dev, "VID=%d already configured\n", vid);
+ if (mlxsw_sp_port_vport_find(mlxsw_sp_port, vid))
return 0;
- }
mlxsw_sp_vport = mlxsw_sp_port_vport_create(mlxsw_sp_port, vid);
- if (!mlxsw_sp_vport) {
- netdev_err(dev, "Failed to create vPort for VID=%d\n", vid);
+ if (!mlxsw_sp_vport)
return -ENOMEM;
- }
/* When adding the first VLAN interface on a bridged port we need to
* transition all the active 802.1Q bridge VLANs to use explicit
*/
if (list_is_singular(&mlxsw_sp_port->vports_list)) {
err = mlxsw_sp_port_vp_mode_trans(mlxsw_sp_port);
- if (err) {
- netdev_err(dev, "Failed to set to Virtual mode\n");
+ if (err)
goto err_port_vp_mode_trans;
- }
}
err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, false);
- if (err) {
- netdev_err(dev, "Failed to disable learning for VID=%d\n", vid);
+ if (err)
goto err_port_vid_learning_set;
- }
err = mlxsw_sp_port_vlan_set(mlxsw_sp_vport, vid, vid, true, untagged);
- if (err) {
- netdev_err(dev, "Failed to set VLAN membership for VID=%d\n",
- vid);
+ if (err)
goto err_port_add_vid;
- }
return 0;
struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
struct mlxsw_sp_port *mlxsw_sp_vport;
struct mlxsw_sp_fid *f;
- int err;
/* VLAN 0 is removed from HW filter when device goes down, but
* it is reserved in our case, so simply return.
return 0;
mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid);
- if (!mlxsw_sp_vport) {
- netdev_warn(dev, "VID=%d does not exist\n", vid);
+ if (WARN_ON(!mlxsw_sp_vport))
return 0;
- }
- err = mlxsw_sp_port_vlan_set(mlxsw_sp_vport, vid, vid, false, false);
- if (err) {
- netdev_err(dev, "Failed to set VLAN membership for VID=%d\n",
- vid);
- return err;
- }
+ mlxsw_sp_port_vlan_set(mlxsw_sp_vport, vid, vid, false, false);
- err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, true);
- if (err) {
- netdev_err(dev, "Failed to enable learning for VID=%d\n", vid);
- return err;
- }
+ mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, true);
/* Drop FID reference. If this was the last reference the
* resources will be freed.
* transition all active 802.1Q bridge VLANs to use VID to FID
* mappings and set port's mode to VLAN mode.
*/
- if (list_is_singular(&mlxsw_sp_port->vports_list)) {
- err = mlxsw_sp_port_vlan_mode_trans(mlxsw_sp_port);
- if (err) {
- netdev_err(dev, "Failed to set to VLAN mode\n");
- return err;
- }
- }
+ if (list_is_singular(&mlxsw_sp_port->vports_list))
+ mlxsw_sp_port_vlan_mode_trans(mlxsw_sp_port);
mlxsw_sp_port_vport_destroy(mlxsw_sp_vport);
bool ingress)
{
const struct tc_action *a;
+ LIST_HEAD(actions);
int err;
if (!tc_single_action(cls->exts)) {
return -ENOTSUPP;
}
- tc_for_each_action(a, cls->exts) {
+ tcf_exts_to_list(cls->exts, &actions);
+ list_for_each_entry(a, &actions, list) {
if (!is_tcf_mirred_mirror(a) || protocol != htons(ETH_P_ALL))
return -ENOTSUPP;
return 0;
}
+static int mlxsw_sp_port_pvid_vport_create(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+ mlxsw_sp_port->pvid = 1;
+
+ return mlxsw_sp_port_add_vid(mlxsw_sp_port->dev, 0, 1);
+}
+
+static int mlxsw_sp_port_pvid_vport_destroy(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+ return mlxsw_sp_port_kill_vid(mlxsw_sp_port->dev, 0, 1);
+}
+
static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
bool split, u8 module, u8 width, u8 lane)
{
dev->netdev_ops = &mlxsw_sp_port_netdev_ops;
dev->ethtool_ops = &mlxsw_sp_port_ethtool_ops;
+ err = mlxsw_sp_port_swid_set(mlxsw_sp_port, 0);
+ if (err) {
+ dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set SWID\n",
+ mlxsw_sp_port->local_port);
+ goto err_port_swid_set;
+ }
+
err = mlxsw_sp_port_dev_addr_init(mlxsw_sp_port);
if (err) {
dev_err(mlxsw_sp->bus_info->dev, "Port %d: Unable to init port mac address\n",
goto err_port_system_port_mapping_set;
}
- err = mlxsw_sp_port_swid_set(mlxsw_sp_port, 0);
- if (err) {
- dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set SWID\n",
- mlxsw_sp_port->local_port);
- goto err_port_swid_set;
- }
-
err = mlxsw_sp_port_speed_by_width_set(mlxsw_sp_port, width);
if (err) {
dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to enable speeds\n",
goto err_port_dcb_init;
}
+ err = mlxsw_sp_port_pvid_vport_create(mlxsw_sp_port);
+ if (err) {
+ dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to create PVID vPort\n",
+ mlxsw_sp_port->local_port);
+ goto err_port_pvid_vport_create;
+ }
+
mlxsw_sp_port_switchdev_init(mlxsw_sp_port);
+ mlxsw_sp->ports[local_port] = mlxsw_sp_port;
err = register_netdev(dev);
if (err) {
dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to register netdev\n",
goto err_core_port_init;
}
- err = mlxsw_sp_port_vlan_init(mlxsw_sp_port);
- if (err)
- goto err_port_vlan_init;
-
- mlxsw_sp->ports[local_port] = mlxsw_sp_port;
return 0;
-err_port_vlan_init:
- mlxsw_core_port_fini(&mlxsw_sp_port->core_port);
err_core_port_init:
unregister_netdev(dev);
err_register_netdev:
+ mlxsw_sp->ports[local_port] = NULL;
+ mlxsw_sp_port_switchdev_fini(mlxsw_sp_port);
+ mlxsw_sp_port_pvid_vport_destroy(mlxsw_sp_port);
+err_port_pvid_vport_create:
+ mlxsw_sp_port_dcb_fini(mlxsw_sp_port);
err_port_dcb_init:
err_port_ets_init:
err_port_buffers_init:
err_port_admin_status_set:
err_port_mtu_set:
err_port_speed_by_width_set:
-err_port_swid_set:
err_port_system_port_mapping_set:
err_dev_addr_init:
+ mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT);
+err_port_swid_set:
free_percpu(mlxsw_sp_port->pcpu_stats);
err_alloc_stats:
kfree(mlxsw_sp_port->untagged_vlans);
if (!mlxsw_sp_port)
return;
- mlxsw_sp->ports[local_port] = NULL;
mlxsw_core_port_fini(&mlxsw_sp_port->core_port);
unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */
- mlxsw_sp_port_dcb_fini(mlxsw_sp_port);
- mlxsw_sp_port_kill_vid(mlxsw_sp_port->dev, 0, 1);
+ mlxsw_sp->ports[local_port] = NULL;
mlxsw_sp_port_switchdev_fini(mlxsw_sp_port);
+ mlxsw_sp_port_pvid_vport_destroy(mlxsw_sp_port);
+ mlxsw_sp_port_dcb_fini(mlxsw_sp_port);
mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT);
mlxsw_sp_port_module_unmap(mlxsw_sp, mlxsw_sp_port->local_port);
free_percpu(mlxsw_sp_port->pcpu_stats);
.local_port = MLXSW_PORT_DONT_CARE,
.trap_id = MLXSW_TRAP_ID_ARPUC,
},
+ {
+ .func = mlxsw_sp_rx_listener_func,
+ .local_port = MLXSW_PORT_DONT_CARE,
+ .trap_id = MLXSW_TRAP_ID_MTUERROR,
+ },
+ {
+ .func = mlxsw_sp_rx_listener_func,
+ .local_port = MLXSW_PORT_DONT_CARE,
+ .trap_id = MLXSW_TRAP_ID_TTLERROR,
+ },
+ {
+ .func = mlxsw_sp_rx_listener_func,
+ .local_port = MLXSW_PORT_DONT_CARE,
+ .trap_id = MLXSW_TRAP_ID_LBERROR,
+ },
+ {
+ .func = mlxsw_sp_rx_listener_func,
+ .local_port = MLXSW_PORT_DONT_CARE,
+ .trap_id = MLXSW_TRAP_ID_OSPF,
+ },
{
.func = mlxsw_sp_rx_listener_func,
.local_port = MLXSW_PORT_DONT_CARE,
return mlxsw_sp_fid_find(mlxsw_sp, fid);
}
+static enum mlxsw_flood_table_type mlxsw_sp_flood_table_type_get(u16 fid)
+{
+ return mlxsw_sp_fid_is_vfid(fid) ? MLXSW_REG_SFGC_TABLE_TYPE_FID :
+ MLXSW_REG_SFGC_TABLE_TYPE_FID_OFFEST;
+}
+
+static u16 mlxsw_sp_flood_table_index_get(u16 fid)
+{
+ return mlxsw_sp_fid_is_vfid(fid) ? mlxsw_sp_fid_to_vfid(fid) : fid;
+}
+
+static int mlxsw_sp_router_port_flood_set(struct mlxsw_sp *mlxsw_sp, u16 fid,
+ bool set)
+{
+ enum mlxsw_flood_table_type table_type;
+ char *sftr_pl;
+ u16 index;
+ int err;
+
+ sftr_pl = kmalloc(MLXSW_REG_SFTR_LEN, GFP_KERNEL);
+ if (!sftr_pl)
+ return -ENOMEM;
+
+ table_type = mlxsw_sp_flood_table_type_get(fid);
+ index = mlxsw_sp_flood_table_index_get(fid);
+ mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BM, index, table_type,
+ 1, MLXSW_PORT_ROUTER_PORT, set);
+ err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl);
+
+ kfree(sftr_pl);
+ return err;
+}
+
static enum mlxsw_reg_ritr_if_type mlxsw_sp_rif_type_get(u16 fid)
{
if (mlxsw_sp_fid_is_vfid(fid))
if (rif == MLXSW_SP_RIF_MAX)
return -ERANGE;
- err = mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, true);
+ err = mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, true);
if (err)
return err;
+ err = mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, true);
+ if (err)
+ goto err_rif_bridge_op;
+
err = mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, true);
if (err)
goto err_rif_fdb_op;
mlxsw_sp_rif_fdb_op(mlxsw_sp, l3_dev->dev_addr, f->fid, false);
err_rif_fdb_op:
mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false);
+err_rif_bridge_op:
+ mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false);
return err;
}
mlxsw_sp_rif_bridge_op(mlxsw_sp, l3_dev, f->fid, rif, false);
+ mlxsw_sp_router_port_flood_set(mlxsw_sp, f->fid, false);
+
netdev_dbg(l3_dev, "RIF=%d destroyed\n", rif);
}
.priority = 10, /* Must be called before FIB notifier block */
};
+static struct notifier_block mlxsw_sp_router_netevent_nb __read_mostly = {
+ .notifier_call = mlxsw_sp_router_netevent_event,
+};
+
static int __init mlxsw_sp_module_init(void)
{
int err;
register_netdevice_notifier(&mlxsw_sp_netdevice_nb);
register_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
+ register_netevent_notifier(&mlxsw_sp_router_netevent_nb);
+
err = mlxsw_core_driver_register(&mlxsw_sp_driver);
if (err)
goto err_core_driver_register;
return 0;
err_core_driver_register:
+ unregister_netevent_notifier(&mlxsw_sp_router_netevent_nb);
+ unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
unregister_netdevice_notifier(&mlxsw_sp_netdevice_nb);
return err;
}
static void __exit mlxsw_sp_module_exit(void)
{
mlxsw_core_driver_unregister(&mlxsw_sp_driver);
+ unregister_netevent_notifier(&mlxsw_sp_router_netevent_nb);
unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
unregister_netdevice_notifier(&mlxsw_sp_netdevice_nb);
}
u16 vid);
int mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin,
u16 vid_end, bool is_member, bool untagged);
-int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto,
- u16 vid);
int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 fid,
bool set);
void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port);
struct neighbour *n);
void mlxsw_sp_router_neigh_destroy(struct net_device *dev,
struct neighbour *n);
+int mlxsw_sp_router_netevent_event(struct notifier_block *unused,
+ unsigned long event, void *ptr);
int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count);
void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index);
MLXSW_SP_CPU_PORT_SB_CM,
MLXSW_SP_CPU_PORT_SB_CM,
MLXSW_SP_CPU_PORT_SB_CM,
- MLXSW_SP_CPU_PORT_SB_CM,
+ MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(10000), 0, 0),
MLXSW_SP_CPU_PORT_SB_CM,
MLXSW_SP_CPU_PORT_SB_CM,
MLXSW_SP_CPU_PORT_SB_CM,
u8 local_port = mlxsw_sp_port->local_port;
u8 pg_buff = tc_index;
enum mlxsw_reg_sbxx_dir dir = pool_type;
- u8 pool = pool_index;
+ u8 pool = pool_get(pool_index);
u32 max_buff;
int err;
+ if (dir != dir_get(pool_index))
+ return -EINVAL;
+
err = mlxsw_sp_sb_threshold_in(mlxsw_sp, pool, dir,
threshold, &max_buff);
if (err)
return err;
- if (pool_type == DEVLINK_SB_POOL_TYPE_EGRESS) {
- if (pool < MLXSW_SP_SB_POOL_COUNT)
- return -EINVAL;
- pool -= MLXSW_SP_SB_POOL_COUNT;
- } else if (pool >= MLXSW_SP_SB_POOL_COUNT) {
- return -EINVAL;
- }
return mlxsw_sp_sb_cm_write(mlxsw_sp, local_port, pg_buff, dir,
0, max_buff, pool);
}
char pfcc_pl[MLXSW_REG_PFCC_LEN];
mlxsw_reg_pfcc_pack(pfcc_pl, mlxsw_sp_port->local_port);
+ mlxsw_reg_pfcc_pprx_set(pfcc_pl, mlxsw_sp_port->link.rx_pause);
+ mlxsw_reg_pfcc_pptx_set(pfcc_pl, mlxsw_sp_port->link.tx_pause);
mlxsw_reg_pfcc_prio_pack(pfcc_pl, pfc->pfc_en);
return mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core, MLXSW_REG(pfcc),
struct ieee_pfc *pfc)
{
struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+ bool pause_en = mlxsw_sp_port_is_pause_en(mlxsw_sp_port);
int err;
- if ((mlxsw_sp_port->link.tx_pause || mlxsw_sp_port->link.rx_pause) &&
- pfc->pfc_en) {
+ if (pause_en && pfc->pfc_en) {
netdev_err(dev, "PAUSE frames already enabled on port\n");
return -EINVAL;
}
err = __mlxsw_sp_port_headroom_set(mlxsw_sp_port, dev->mtu,
mlxsw_sp_port->dcb.ets->prio_tc,
- false, pfc);
+ pause_en, pfc);
if (err) {
netdev_err(dev, "Failed to configure port's headroom for PFC\n");
return err;
err_port_pfc_set:
__mlxsw_sp_port_headroom_set(mlxsw_sp_port, dev->mtu,
- mlxsw_sp_port->dcb.ets->prio_tc, false,
+ mlxsw_sp_port->dcb.ets->prio_tc, pause_en,
mlxsw_sp_port->dcb.pfc);
return err;
}
}
struct mlxsw_sp_fib_key {
+ struct net_device *dev;
unsigned char addr[sizeof(struct in6_addr)];
unsigned char prefix_len;
};
struct rhash_head ht_node;
struct mlxsw_sp_fib_key key;
enum mlxsw_sp_fib_entry_type type;
- u8 added:1;
+ unsigned int ref_count;
u16 rif; /* used for action local */
struct mlxsw_sp_vr *vr;
struct list_head nexthop_group_node;
static struct mlxsw_sp_fib_entry *
mlxsw_sp_fib_entry_create(struct mlxsw_sp_fib *fib, const void *addr,
- size_t addr_len, unsigned char prefix_len)
+ size_t addr_len, unsigned char prefix_len,
+ struct net_device *dev)
{
struct mlxsw_sp_fib_entry *fib_entry;
fib_entry = kzalloc(sizeof(*fib_entry), GFP_KERNEL);
if (!fib_entry)
return NULL;
+ fib_entry->key.dev = dev;
memcpy(fib_entry->key.addr, addr, addr_len);
fib_entry->key.prefix_len = prefix_len;
return fib_entry;
static struct mlxsw_sp_fib_entry *
mlxsw_sp_fib_entry_lookup(struct mlxsw_sp_fib *fib, const void *addr,
- size_t addr_len, unsigned char prefix_len)
+ size_t addr_len, unsigned char prefix_len,
+ struct net_device *dev)
{
- struct mlxsw_sp_fib_key key = {{ 0 } };
+ struct mlxsw_sp_fib_key key;
+ memset(&key, 0, sizeof(key));
+ key.dev = dev;
memcpy(key.addr, addr, addr_len);
key.prefix_len = prefix_len;
return rhashtable_lookup_fast(&fib->ht, &key, mlxsw_sp_fib_ht_params);
return 0;
}
- r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+ r = mlxsw_sp_rif_find_by_dev(mlxsw_sp, n->dev);
if (WARN_ON(!r))
return -EINVAL;
mlxsw_sp_port_dev_put(mlxsw_sp_port);
}
-static int mlxsw_sp_router_netevent_event(struct notifier_block *unused,
- unsigned long event, void *ptr)
+int mlxsw_sp_router_netevent_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
{
struct mlxsw_sp_neigh_entry *neigh_entry;
struct mlxsw_sp_port *mlxsw_sp_port;
return NOTIFY_DONE;
}
-static struct notifier_block mlxsw_sp_router_netevent_nb __read_mostly = {
- .notifier_call = mlxsw_sp_router_netevent_event,
-};
-
static int mlxsw_sp_neigh_init(struct mlxsw_sp *mlxsw_sp)
{
int err;
*/
mlxsw_sp_router_neighs_update_interval_init(mlxsw_sp);
- err = register_netevent_notifier(&mlxsw_sp_router_netevent_nb);
- if (err)
- goto err_register_netevent_notifier;
-
/* Create the delayed works for the activity_update */
INIT_DELAYED_WORK(&mlxsw_sp->router.neighs_update.dw,
mlxsw_sp_router_neighs_update_work);
mlxsw_core_schedule_dw(&mlxsw_sp->router.neighs_update.dw, 0);
mlxsw_core_schedule_dw(&mlxsw_sp->router.nexthop_probe_dw, 0);
return 0;
-
-err_register_netevent_notifier:
- rhashtable_destroy(&mlxsw_sp->router.neigh_ht);
- return err;
}
static void mlxsw_sp_neigh_fini(struct mlxsw_sp *mlxsw_sp)
{
cancel_delayed_work_sync(&mlxsw_sp->router.neighs_update.dw);
cancel_delayed_work_sync(&mlxsw_sp->router.nexthop_probe_dw);
- unregister_netevent_notifier(&mlxsw_sp_router_netevent_nb);
rhashtable_destroy(&mlxsw_sp->router.neigh_ht);
}
return err;
mlxsw_sp_lpm_init(mlxsw_sp);
mlxsw_sp_vrs_init(mlxsw_sp);
- return mlxsw_sp_neigh_init(mlxsw_sp);
+ err = mlxsw_sp_neigh_init(mlxsw_sp);
+ if (err)
+ goto err_neigh_init;
+ return 0;
+
+err_neigh_init:
+ __mlxsw_sp_router_fini(mlxsw_sp);
+ return err;
}
void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
static int mlxsw_sp_fib_entry_update(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib_entry *fib_entry)
{
- enum mlxsw_reg_ralue_op op;
-
- op = !fib_entry->added ? MLXSW_REG_RALUE_OP_WRITE_WRITE :
- MLXSW_REG_RALUE_OP_WRITE_UPDATE;
- return mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry, op);
+ return mlxsw_sp_fib_entry_op(mlxsw_sp, fib_entry,
+ MLXSW_REG_RALUE_OP_WRITE_WRITE);
}
static int mlxsw_sp_fib_entry_del(struct mlxsw_sp *mlxsw_sp,
const struct mlxsw_sp_router_fib4_add_info *info = data;
struct mlxsw_sp_fib_entry *fib_entry = info->fib_entry;
struct mlxsw_sp *mlxsw_sp = info->mlxsw_sp;
+ struct mlxsw_sp_vr *vr = fib_entry->vr;
mlxsw_sp_fib_entry_destroy(fib_entry);
- mlxsw_sp_vr_put(mlxsw_sp, fib_entry->vr);
+ mlxsw_sp_vr_put(mlxsw_sp, vr);
kfree(info);
}
mlxsw_sp_nexthop_group_put(mlxsw_sp, fib_entry);
}
-static int
-mlxsw_sp_router_fib4_add_prepare(struct mlxsw_sp_port *mlxsw_sp_port,
- const struct switchdev_obj_ipv4_fib *fib4,
- struct switchdev_trans *trans)
+static struct mlxsw_sp_fib_entry *
+mlxsw_sp_fib_entry_get(struct mlxsw_sp *mlxsw_sp,
+ const struct switchdev_obj_ipv4_fib *fib4)
{
- struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
- struct mlxsw_sp_router_fib4_add_info *info;
struct mlxsw_sp_fib_entry *fib_entry;
+ struct fib_info *fi = fib4->fi;
struct mlxsw_sp_vr *vr;
int err;
vr = mlxsw_sp_vr_get(mlxsw_sp, fib4->dst_len, fib4->tb_id,
MLXSW_SP_L3_PROTO_IPV4);
if (IS_ERR(vr))
- return PTR_ERR(vr);
+ return ERR_CAST(vr);
+ fib_entry = mlxsw_sp_fib_entry_lookup(vr->fib, &fib4->dst,
+ sizeof(fib4->dst),
+ fib4->dst_len, fi->fib_dev);
+ if (fib_entry) {
+ /* Already exists, just take a reference */
+ fib_entry->ref_count++;
+ return fib_entry;
+ }
fib_entry = mlxsw_sp_fib_entry_create(vr->fib, &fib4->dst,
- sizeof(fib4->dst), fib4->dst_len);
+ sizeof(fib4->dst),
+ fib4->dst_len, fi->fib_dev);
if (!fib_entry) {
err = -ENOMEM;
goto err_fib_entry_create;
}
fib_entry->vr = vr;
+ fib_entry->ref_count = 1;
err = mlxsw_sp_router_fib4_entry_init(mlxsw_sp, fib4, fib_entry);
if (err)
goto err_fib4_entry_init;
+ return fib_entry;
+
+err_fib4_entry_init:
+ mlxsw_sp_fib_entry_destroy(fib_entry);
+err_fib_entry_create:
+ mlxsw_sp_vr_put(mlxsw_sp, vr);
+
+ return ERR_PTR(err);
+}
+
+static struct mlxsw_sp_fib_entry *
+mlxsw_sp_fib_entry_find(struct mlxsw_sp *mlxsw_sp,
+ const struct switchdev_obj_ipv4_fib *fib4)
+{
+ struct mlxsw_sp_vr *vr;
+
+ vr = mlxsw_sp_vr_find(mlxsw_sp, fib4->tb_id, MLXSW_SP_L3_PROTO_IPV4);
+ if (!vr)
+ return NULL;
+
+ return mlxsw_sp_fib_entry_lookup(vr->fib, &fib4->dst,
+ sizeof(fib4->dst), fib4->dst_len,
+ fib4->fi->fib_dev);
+}
+
+void mlxsw_sp_fib_entry_put(struct mlxsw_sp *mlxsw_sp,
+ struct mlxsw_sp_fib_entry *fib_entry)
+{
+ struct mlxsw_sp_vr *vr = fib_entry->vr;
+
+ if (--fib_entry->ref_count == 0) {
+ mlxsw_sp_router_fib4_entry_fini(mlxsw_sp, fib_entry);
+ mlxsw_sp_fib_entry_destroy(fib_entry);
+ }
+ mlxsw_sp_vr_put(mlxsw_sp, vr);
+}
+
+static int
+mlxsw_sp_router_fib4_add_prepare(struct mlxsw_sp_port *mlxsw_sp_port,
+ const struct switchdev_obj_ipv4_fib *fib4,
+ struct switchdev_trans *trans)
+{
+ struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+ struct mlxsw_sp_router_fib4_add_info *info;
+ struct mlxsw_sp_fib_entry *fib_entry;
+ int err;
+
+ fib_entry = mlxsw_sp_fib_entry_get(mlxsw_sp, fib4);
+ if (IS_ERR(fib_entry))
+ return PTR_ERR(fib_entry);
+
info = kmalloc(sizeof(*info), GFP_KERNEL);
if (!info) {
err = -ENOMEM;
return 0;
err_alloc_info:
- mlxsw_sp_router_fib4_entry_fini(mlxsw_sp, fib_entry);
-err_fib4_entry_init:
- mlxsw_sp_fib_entry_destroy(fib_entry);
-err_fib_entry_create:
- mlxsw_sp_vr_put(mlxsw_sp, vr);
+ mlxsw_sp_fib_entry_put(mlxsw_sp, fib_entry);
return err;
}
fib_entry = info->fib_entry;
kfree(info);
+ if (fib_entry->ref_count != 1)
+ return 0;
+
vr = fib_entry->vr;
- err = mlxsw_sp_fib_entry_insert(fib_entry->vr->fib, fib_entry);
+ err = mlxsw_sp_fib_entry_insert(vr->fib, fib_entry);
if (err)
goto err_fib_entry_insert;
- err = mlxsw_sp_fib_entry_update(mlxsw_sp, fib_entry);
+ err = mlxsw_sp_fib_entry_update(mlxsw_sp_port->mlxsw_sp, fib_entry);
if (err)
goto err_fib_entry_add;
return 0;
err_fib_entry_add:
mlxsw_sp_fib_entry_remove(vr->fib, fib_entry);
err_fib_entry_insert:
- mlxsw_sp_router_fib4_entry_fini(mlxsw_sp, fib_entry);
- mlxsw_sp_fib_entry_destroy(fib_entry);
- mlxsw_sp_vr_put(mlxsw_sp, vr);
+ mlxsw_sp_fib_entry_put(mlxsw_sp, fib_entry);
return err;
}
{
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
struct mlxsw_sp_fib_entry *fib_entry;
- struct mlxsw_sp_vr *vr;
- vr = mlxsw_sp_vr_find(mlxsw_sp, fib4->tb_id, MLXSW_SP_L3_PROTO_IPV4);
- if (!vr) {
- dev_warn(mlxsw_sp->bus_info->dev, "Failed to find virtual router for FIB4 entry being removed.\n");
- return -ENOENT;
- }
- fib_entry = mlxsw_sp_fib_entry_lookup(vr->fib, &fib4->dst,
- sizeof(fib4->dst), fib4->dst_len);
+ fib_entry = mlxsw_sp_fib_entry_find(mlxsw_sp, fib4);
if (!fib_entry) {
dev_warn(mlxsw_sp->bus_info->dev, "Failed to find FIB4 entry being removed.\n");
return -ENOENT;
}
- mlxsw_sp_fib_entry_del(mlxsw_sp_port->mlxsw_sp, fib_entry);
- mlxsw_sp_fib_entry_remove(vr->fib, fib_entry);
- mlxsw_sp_router_fib4_entry_fini(mlxsw_sp, fib_entry);
- mlxsw_sp_fib_entry_destroy(fib_entry);
- mlxsw_sp_vr_put(mlxsw_sp, vr);
+
+ if (fib_entry->ref_count == 1) {
+ mlxsw_sp_fib_entry_del(mlxsw_sp, fib_entry);
+ mlxsw_sp_fib_entry_remove(fib_entry->vr->fib, fib_entry);
+ }
+
+ mlxsw_sp_fib_entry_put(mlxsw_sp, fib_entry);
return 0;
}
}
static int __mlxsw_sp_port_flood_set(struct mlxsw_sp_port *mlxsw_sp_port,
- u16 idx_begin, u16 idx_end, bool set,
- bool only_uc)
+ u16 idx_begin, u16 idx_end, bool uc_set,
+ bool bm_set)
{
struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
u16 local_port = mlxsw_sp_port->local_port;
return -ENOMEM;
mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_UC, idx_begin,
- table_type, range, local_port, set);
+ table_type, range, local_port, uc_set);
err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl);
if (err)
goto buffer_out;
- /* Flooding control allows one to decide whether a given port will
- * flood unicast traffic for which there is no FDB entry.
- */
- if (only_uc)
- goto buffer_out;
-
mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_BM, idx_begin,
- table_type, range, local_port, set);
+ table_type, range, local_port, bm_set);
err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl);
if (err)
goto err_flood_bm_set;
- else
- goto buffer_out;
+
+ goto buffer_out;
err_flood_bm_set:
mlxsw_reg_sftr_pack(sftr_pl, MLXSW_SP_FLOOD_TABLE_UC, idx_begin,
- table_type, range, local_port, !set);
+ table_type, range, local_port, !uc_set);
mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sftr), sftr_pl);
buffer_out:
kfree(sftr_pl);
* the start of the vFIDs range.
*/
vfid = mlxsw_sp_fid_to_vfid(fid);
- return __mlxsw_sp_port_flood_set(mlxsw_sp_vport, vfid, vfid, set,
- false);
+ return __mlxsw_sp_port_flood_set(mlxsw_sp_vport, vfid, vfid, set, set);
}
static int mlxsw_sp_port_attr_br_flags_set(struct mlxsw_sp_port *mlxsw_sp_port,
kfree(f);
+ mlxsw_sp_fid_map(mlxsw_sp, fid, false);
+
mlxsw_sp_fid_op(mlxsw_sp, fid, false);
}
{
struct mlxsw_sp_fid *f;
+ if (test_bit(fid, mlxsw_sp_port->active_vlans))
+ return 0;
+
f = mlxsw_sp_fid_find(mlxsw_sp_port->mlxsw_sp, fid);
if (!f) {
f = mlxsw_sp_fid_create(mlxsw_sp_port->mlxsw_sp, fid);
}
err = __mlxsw_sp_port_flood_set(mlxsw_sp_port, fid_begin, fid_end,
- true, false);
+ mlxsw_sp_port->uc_flood, true);
if (err)
goto err_port_flood_set;
}
static int __mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port,
- u16 vid_begin, u16 vid_end, bool init)
+ u16 vid_begin, u16 vid_end)
{
struct net_device *dev = mlxsw_sp_port->dev;
u16 vid, pvid;
int err;
- if (!init && !mlxsw_sp_port->bridged)
+ if (!mlxsw_sp_port->bridged)
return -EINVAL;
err = __mlxsw_sp_port_vlans_set(mlxsw_sp_port, vid_begin, vid_end,
return err;
}
- if (init)
- goto out;
-
pvid = mlxsw_sp_port->pvid;
if (pvid >= vid_begin && pvid <= vid_end) {
err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, 0);
mlxsw_sp_port_fid_leave(mlxsw_sp_port, vid_begin, vid_end);
-out:
/* Changing activity bits only if HW operation succeded */
for (vid = vid_begin; vid <= vid_end; vid++)
clear_bit(vid, mlxsw_sp_port->active_vlans);
static int mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port,
const struct switchdev_obj_port_vlan *vlan)
{
- return __mlxsw_sp_port_vlans_del(mlxsw_sp_port,
- vlan->vid_begin, vlan->vid_end, false);
+ return __mlxsw_sp_port_vlans_del(mlxsw_sp_port, vlan->vid_begin,
+ vlan->vid_end);
}
void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port)
u16 vid;
for_each_set_bit(vid, mlxsw_sp_port->active_vlans, VLAN_N_VID)
- __mlxsw_sp_port_vlans_del(mlxsw_sp_port, vid, vid, false);
+ __mlxsw_sp_port_vlans_del(mlxsw_sp_port, vid, vid);
}
static int
mlxsw_sp_fdb_fini(mlxsw_sp);
}
-int mlxsw_sp_port_vlan_init(struct mlxsw_sp_port *mlxsw_sp_port)
-{
- struct net_device *dev = mlxsw_sp_port->dev;
- int err;
-
- /* Allow only untagged packets to ingress and tag them internally
- * with VID 1.
- */
- mlxsw_sp_port->pvid = 1;
- err = __mlxsw_sp_port_vlans_del(mlxsw_sp_port, 0, VLAN_N_VID - 1,
- true);
- if (err) {
- netdev_err(dev, "Unable to init VLANs\n");
- return err;
- }
-
- /* Add implicit VLAN interface in the device, so that untagged
- * packets will be classified to the default vFID.
- */
- err = mlxsw_sp_port_add_vid(dev, 0, 1);
- if (err)
- netdev_err(dev, "Failed to configure default vFID\n");
-
- return err;
-}
-
void mlxsw_sp_port_switchdev_init(struct mlxsw_sp_port *mlxsw_sp_port)
{
mlxsw_sp_port->dev->switchdev_ops = &mlxsw_sp_port_switchdev_ops;
MLXSW_TRAP_ID_IGMP_V3_REPORT = 0x34,
MLXSW_TRAP_ID_ARPBC = 0x50,
MLXSW_TRAP_ID_ARPUC = 0x51,
+ MLXSW_TRAP_ID_MTUERROR = 0x52,
+ MLXSW_TRAP_ID_TTLERROR = 0x53,
+ MLXSW_TRAP_ID_LBERROR = 0x54,
+ MLXSW_TRAP_ID_OSPF = 0x55,
MLXSW_TRAP_ID_IP2ME = 0x5F,
MLXSW_TRAP_ID_RTR_INGRESS0 = 0x70,
MLXSW_TRAP_ID_HOST_MISS_IPV4 = 0x90,
* Chris Telfer <chris.telfer@netronome.com>
*/
-#include <linux/version.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/init.h>
nfp_net_set_hash(nn->netdev, skb, rxd);
- /* Pad small frames to minimum */
- if (skb_put_padto(skb, 60))
- break;
-
/* Stats update */
u64_stats_update_begin(&r_vec->rx_sync);
r_vec->rx_pkts++;
nn->rx_rings = kcalloc(nn->num_rx_rings, sizeof(*nn->rx_rings),
GFP_KERNEL);
- if (!nn->rx_rings)
+ if (!nn->rx_rings) {
+ err = -ENOMEM;
goto err_free_lsc;
+ }
nn->tx_rings = kcalloc(nn->num_tx_rings, sizeof(*nn->tx_rings),
GFP_KERNEL);
- if (!nn->tx_rings)
+ if (!nn->tx_rings) {
+ err = -ENOMEM;
goto err_free_rx_rings;
+ }
for (r = 0; r < nn->num_r_vecs; r++) {
err = nfp_net_prepare_vector(nn, &nn->r_vecs[r], r);
* Brad Petrus <brad.petrus@netronome.com>
*/
-#include <linux/version.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
* Rolf Neugebauer <rolf.neugebauer@netronome.com>
*/
-#include <linux/version.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/init.h>
}
nfp_net_get_fw_version(&fw_ver, ctrl_bar);
- if (fw_ver.class != NFP_NET_CFG_VERSION_CLASS_GENERIC) {
+ if (fw_ver.resv || fw_ver.class != NFP_NET_CFG_VERSION_CLASS_GENERIC) {
dev_err(&pdev->dev, "Unknown Firmware ABI %d.%d.%d.%d\n",
fw_ver.resv, fw_ver.class, fw_ver.major, fw_ver.minor);
err = -EINVAL;
}
/* Determine stride */
- if (nfp_net_fw_ver_eq(&fw_ver, 0, 0, 0, 0) ||
- nfp_net_fw_ver_eq(&fw_ver, 0, 0, 0, 1) ||
- nfp_net_fw_ver_eq(&fw_ver, 0, 0, 0x12, 0x48)) {
+ if (nfp_net_fw_ver_eq(&fw_ver, 0, 0, 0, 1)) {
stride = 2;
tx_bar_no = NFP_NET_Q0_BAR;
rx_bar_no = NFP_NET_Q1_BAR;
mac[5] = tmp >> 8;
}
-static void __lpc_eth_clock_enable(struct netdata_local *pldat, bool enable)
-{
- if (enable)
- clk_prepare_enable(pldat->clk);
- else
- clk_disable_unprepare(pldat->clk);
-}
-
static void __lpc_params_setup(struct netdata_local *pldat)
{
u32 tmp;
writel(0, LPC_ENET_MAC2(pldat->net_base));
spin_unlock_irqrestore(&pldat->lock, flags);
- __lpc_eth_clock_enable(pldat, false);
+ clk_disable_unprepare(pldat->clk);
return 0;
}
static int lpc_eth_open(struct net_device *ndev)
{
struct netdata_local *pldat = netdev_priv(ndev);
+ int ret;
if (netif_msg_ifup(pldat))
dev_dbg(&pldat->pdev->dev, "enabling %s\n", ndev->name);
- __lpc_eth_clock_enable(pldat, true);
+ ret = clk_prepare_enable(pldat->clk);
+ if (ret)
+ return ret;
/* Suspended PHY makes LPC ethernet core block, so resume now */
phy_resume(ndev->phydev);
}
/* Enable network clock */
- __lpc_eth_clock_enable(pldat, true);
+ ret = clk_prepare_enable(pldat->clk);
+ if (ret)
+ goto err_out_clk_put;
/* Map IO space */
pldat->net_base = ioremap(res->start, resource_size(res));
iounmap(pldat->net_base);
err_out_disable_clocks:
clk_disable_unprepare(pldat->clk);
+err_out_clk_put:
clk_put(pldat->clk);
err_out_free_dev:
free_netdev(ndev);
static inline u8 qed_concrete_to_sw_fid(struct qed_dev *cdev,
u32 concrete_fid)
{
+ u8 vfid = GET_FIELD(concrete_fid, PXP_CONCRETE_FID_VFID);
u8 pfid = GET_FIELD(concrete_fid, PXP_CONCRETE_FID_PFID);
+ u8 vf_valid = GET_FIELD(concrete_fid,
+ PXP_CONCRETE_FID_VFVALID);
+ u8 sw_fid;
- return pfid;
+ if (vf_valid)
+ sw_fid = vfid + MAX_NUM_PFS;
+ else
+ sw_fid = pfid;
+
+ return sw_fid;
}
#define PURE_LB_TC 8
#include "qed_dcbx.h"
#include "qed_hsi.h"
#include "qed_sp.h"
+#include "qed_sriov.h"
#ifdef CONFIG_DCB
#include <linux/qed/qed_eth_if.h>
#endif
DCBX_APP_SF_ETHTYPE);
}
+static bool qed_dcbx_ieee_app_ethtype(u32 app_info_bitmap)
+{
+ u8 mfw_val = QED_MFW_GET_FIELD(app_info_bitmap, DCBX_APP_SF_IEEE);
+
+ /* Old MFW */
+ if (mfw_val == DCBX_APP_SF_IEEE_RESERVED)
+ return qed_dcbx_app_ethtype(app_info_bitmap);
+
+ return !!(mfw_val == DCBX_APP_SF_IEEE_ETHTYPE);
+}
+
static bool qed_dcbx_app_port(u32 app_info_bitmap)
{
return !!(QED_MFW_GET_FIELD(app_info_bitmap, DCBX_APP_SF) ==
DCBX_APP_SF_PORT);
}
-static bool qed_dcbx_default_tlv(u32 app_info_bitmap, u16 proto_id)
+static bool qed_dcbx_ieee_app_port(u32 app_info_bitmap, u8 type)
{
- return !!(qed_dcbx_app_ethtype(app_info_bitmap) &&
- proto_id == QED_ETH_TYPE_DEFAULT);
+ u8 mfw_val = QED_MFW_GET_FIELD(app_info_bitmap, DCBX_APP_SF_IEEE);
+
+ /* Old MFW */
+ if (mfw_val == DCBX_APP_SF_IEEE_RESERVED)
+ return qed_dcbx_app_port(app_info_bitmap);
+
+ return !!(mfw_val == type || mfw_val == DCBX_APP_SF_IEEE_TCP_UDP_PORT);
}
-static bool qed_dcbx_iscsi_tlv(u32 app_info_bitmap, u16 proto_id)
+static bool qed_dcbx_default_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee)
{
- return !!(qed_dcbx_app_port(app_info_bitmap) &&
- proto_id == QED_TCP_PORT_ISCSI);
+ bool ethtype;
+
+ if (ieee)
+ ethtype = qed_dcbx_ieee_app_ethtype(app_info_bitmap);
+ else
+ ethtype = qed_dcbx_app_ethtype(app_info_bitmap);
+
+ return !!(ethtype && (proto_id == QED_ETH_TYPE_DEFAULT));
}
-static bool qed_dcbx_fcoe_tlv(u32 app_info_bitmap, u16 proto_id)
+static bool qed_dcbx_iscsi_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee)
{
- return !!(qed_dcbx_app_ethtype(app_info_bitmap) &&
- proto_id == QED_ETH_TYPE_FCOE);
+ bool port;
+
+ if (ieee)
+ port = qed_dcbx_ieee_app_port(app_info_bitmap,
+ DCBX_APP_SF_IEEE_TCP_PORT);
+ else
+ port = qed_dcbx_app_port(app_info_bitmap);
+
+ return !!(port && (proto_id == QED_TCP_PORT_ISCSI));
}
-static bool qed_dcbx_roce_tlv(u32 app_info_bitmap, u16 proto_id)
+static bool qed_dcbx_fcoe_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee)
{
- return !!(qed_dcbx_app_ethtype(app_info_bitmap) &&
- proto_id == QED_ETH_TYPE_ROCE);
+ bool ethtype;
+
+ if (ieee)
+ ethtype = qed_dcbx_ieee_app_ethtype(app_info_bitmap);
+ else
+ ethtype = qed_dcbx_app_ethtype(app_info_bitmap);
+
+ return !!(ethtype && (proto_id == QED_ETH_TYPE_FCOE));
}
-static bool qed_dcbx_roce_v2_tlv(u32 app_info_bitmap, u16 proto_id)
+static bool qed_dcbx_roce_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee)
{
- return !!(qed_dcbx_app_port(app_info_bitmap) &&
- proto_id == QED_UDP_PORT_TYPE_ROCE_V2);
+ bool ethtype;
+
+ if (ieee)
+ ethtype = qed_dcbx_ieee_app_ethtype(app_info_bitmap);
+ else
+ ethtype = qed_dcbx_app_ethtype(app_info_bitmap);
+
+ return !!(ethtype && (proto_id == QED_ETH_TYPE_ROCE));
+}
+
+static bool qed_dcbx_roce_v2_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee)
+{
+ bool port;
+
+ if (ieee)
+ port = qed_dcbx_ieee_app_port(app_info_bitmap,
+ DCBX_APP_SF_IEEE_UDP_PORT);
+ else
+ port = qed_dcbx_app_port(app_info_bitmap);
+
+ return !!(port && (proto_id == QED_UDP_PORT_TYPE_ROCE_V2));
}
static void
static bool
qed_dcbx_get_app_protocol_type(struct qed_hwfn *p_hwfn,
u32 app_prio_bitmap,
- u16 id, enum dcbx_protocol_type *type)
+ u16 id, enum dcbx_protocol_type *type, bool ieee)
{
- if (qed_dcbx_fcoe_tlv(app_prio_bitmap, id)) {
+ if (qed_dcbx_fcoe_tlv(app_prio_bitmap, id, ieee)) {
*type = DCBX_PROTOCOL_FCOE;
- } else if (qed_dcbx_roce_tlv(app_prio_bitmap, id)) {
+ } else if (qed_dcbx_roce_tlv(app_prio_bitmap, id, ieee)) {
*type = DCBX_PROTOCOL_ROCE;
- } else if (qed_dcbx_iscsi_tlv(app_prio_bitmap, id)) {
+ } else if (qed_dcbx_iscsi_tlv(app_prio_bitmap, id, ieee)) {
*type = DCBX_PROTOCOL_ISCSI;
- } else if (qed_dcbx_default_tlv(app_prio_bitmap, id)) {
+ } else if (qed_dcbx_default_tlv(app_prio_bitmap, id, ieee)) {
*type = DCBX_PROTOCOL_ETH;
- } else if (qed_dcbx_roce_v2_tlv(app_prio_bitmap, id)) {
+ } else if (qed_dcbx_roce_v2_tlv(app_prio_bitmap, id, ieee)) {
*type = DCBX_PROTOCOL_ROCE_V2;
} else {
*type = DCBX_MAX_PROTOCOL_TYPE;
qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn,
struct qed_dcbx_results *p_data,
struct dcbx_app_priority_entry *p_tbl,
- u32 pri_tc_tbl, int count, bool dcbx_enabled)
+ u32 pri_tc_tbl, int count, u8 dcbx_version)
{
u8 tc, priority_map;
enum dcbx_protocol_type type;
+ bool enable, ieee;
u16 protocol_id;
int priority;
- bool enable;
int i;
DP_VERBOSE(p_hwfn, QED_MSG_DCB, "Num APP entries = %d\n", count);
+ ieee = (dcbx_version == DCBX_CONFIG_VERSION_IEEE);
/* Parse APP TLV */
for (i = 0; i < count; i++) {
protocol_id = QED_MFW_GET_FIELD(p_tbl[i].entry,
tc = QED_DCBX_PRIO2TC(pri_tc_tbl, priority);
if (qed_dcbx_get_app_protocol_type(p_hwfn, p_tbl[i].entry,
- protocol_id, &type)) {
+ protocol_id, &type, ieee)) {
/* ETH always have the enable bit reset, as it gets
* vlan information per packet. For other protocols,
* should be set according to the dcbx_enabled
struct dcbx_ets_feature *p_ets;
struct qed_hw_info *p_info;
u32 pri_tc_tbl, flags;
- bool dcbx_enabled;
+ u8 dcbx_version;
int num_entries;
int rc = 0;
- /* If DCBx version is non zero, then negotiation was
- * successfuly performed
- */
flags = p_hwfn->p_dcbx_info->operational.flags;
- dcbx_enabled = !!QED_MFW_GET_FIELD(flags, DCBX_CONFIG_VERSION);
+ dcbx_version = QED_MFW_GET_FIELD(flags, DCBX_CONFIG_VERSION);
p_app = &p_hwfn->p_dcbx_info->operational.features.app;
p_tbl = p_app->app_pri_tbl;
num_entries = QED_MFW_GET_FIELD(p_app->flags, DCBX_APP_NUM_ENTRIES);
rc = qed_dcbx_process_tlv(p_hwfn, &data, p_tbl, pri_tc_tbl,
- num_entries, dcbx_enabled);
+ num_entries, dcbx_version);
if (rc)
return rc;
p_info->num_tc = QED_MFW_GET_FIELD(p_ets->flags, DCBX_ETS_MAX_TCS);
data.pf_id = p_hwfn->rel_pf_id;
- data.dcbx_enabled = dcbx_enabled;
+ data.dcbx_enabled = !!dcbx_version;
qed_dcbx_dp_protocol(p_hwfn, &data);
qed_dcbx_get_app_data(struct qed_hwfn *p_hwfn,
struct dcbx_app_priority_feature *p_app,
struct dcbx_app_priority_entry *p_tbl,
- struct qed_dcbx_params *p_params)
+ struct qed_dcbx_params *p_params, bool ieee)
{
struct qed_app_entry *entry;
u8 pri_map;
DCBX_APP_NUM_ENTRIES);
for (i = 0; i < DCBX_MAX_APP_PROTOCOL; i++) {
entry = &p_params->app_entry[i];
- entry->ethtype = !(QED_MFW_GET_FIELD(p_tbl[i].entry,
- DCBX_APP_SF));
+ if (ieee) {
+ u8 sf_ieee;
+ u32 val;
+
+ sf_ieee = QED_MFW_GET_FIELD(p_tbl[i].entry,
+ DCBX_APP_SF_IEEE);
+ switch (sf_ieee) {
+ case DCBX_APP_SF_IEEE_RESERVED:
+ /* Old MFW */
+ val = QED_MFW_GET_FIELD(p_tbl[i].entry,
+ DCBX_APP_SF);
+ entry->sf_ieee = val ?
+ QED_DCBX_SF_IEEE_TCP_UDP_PORT :
+ QED_DCBX_SF_IEEE_ETHTYPE;
+ break;
+ case DCBX_APP_SF_IEEE_ETHTYPE:
+ entry->sf_ieee = QED_DCBX_SF_IEEE_ETHTYPE;
+ break;
+ case DCBX_APP_SF_IEEE_TCP_PORT:
+ entry->sf_ieee = QED_DCBX_SF_IEEE_TCP_PORT;
+ break;
+ case DCBX_APP_SF_IEEE_UDP_PORT:
+ entry->sf_ieee = QED_DCBX_SF_IEEE_UDP_PORT;
+ break;
+ case DCBX_APP_SF_IEEE_TCP_UDP_PORT:
+ entry->sf_ieee = QED_DCBX_SF_IEEE_TCP_UDP_PORT;
+ break;
+ }
+ } else {
+ entry->ethtype = !(QED_MFW_GET_FIELD(p_tbl[i].entry,
+ DCBX_APP_SF));
+ }
+
pri_map = QED_MFW_GET_FIELD(p_tbl[i].entry, DCBX_APP_PRI_MAP);
entry->prio = ffs(pri_map) - 1;
entry->proto_id = QED_MFW_GET_FIELD(p_tbl[i].entry,
DCBX_APP_PROTOCOL_ID);
qed_dcbx_get_app_protocol_type(p_hwfn, p_tbl[i].entry,
entry->proto_id,
- &entry->proto_type);
+ &entry->proto_type, ieee);
}
DP_VERBOSE(p_hwfn, QED_MSG_DCB,
bw_map[1] = be32_to_cpu(p_ets->tc_bw_tbl[1]);
tsa_map[0] = be32_to_cpu(p_ets->tc_tsa_tbl[0]);
tsa_map[1] = be32_to_cpu(p_ets->tc_tsa_tbl[1]);
- pri_map = be32_to_cpu(p_ets->pri_tc_tbl[0]);
+ pri_map = p_ets->pri_tc_tbl[0];
for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++) {
p_params->ets_tc_bw_tbl[i] = ((u8 *)bw_map)[i];
p_params->ets_tc_tsa_tbl[i] = ((u8 *)tsa_map)[i];
struct dcbx_app_priority_feature *p_app,
struct dcbx_app_priority_entry *p_tbl,
struct dcbx_ets_feature *p_ets,
- u32 pfc, struct qed_dcbx_params *p_params)
+ u32 pfc, struct qed_dcbx_params *p_params, bool ieee)
{
- qed_dcbx_get_app_data(p_hwfn, p_app, p_tbl, p_params);
+ qed_dcbx_get_app_data(p_hwfn, p_app, p_tbl, p_params, ieee);
qed_dcbx_get_ets_data(p_hwfn, p_ets, p_params);
qed_dcbx_get_pfc_data(p_hwfn, pfc, p_params);
}
p_feat = &p_hwfn->p_dcbx_info->local_admin.features;
qed_dcbx_get_common_params(p_hwfn, &p_feat->app,
p_feat->app.app_pri_tbl, &p_feat->ets,
- p_feat->pfc, ¶ms->local.params);
+ p_feat->pfc, ¶ms->local.params, false);
params->local.valid = true;
}
p_feat = &p_hwfn->p_dcbx_info->remote.features;
qed_dcbx_get_common_params(p_hwfn, &p_feat->app,
p_feat->app.app_pri_tbl, &p_feat->ets,
- p_feat->pfc, ¶ms->remote.params);
+ p_feat->pfc, ¶ms->remote.params, false);
params->remote.valid = true;
}
qed_dcbx_get_common_params(p_hwfn, &p_feat->app,
p_feat->app.app_pri_tbl, &p_feat->ets,
- p_feat->pfc, ¶ms->operational.params);
+ p_feat->pfc, ¶ms->operational.params,
+ p_operational->ieee);
qed_dcbx_get_priority_info(p_hwfn, &p_operational->app_prio, p_results);
err = QED_MFW_GET_FIELD(p_feat->app.flags, DCBX_APP_ERROR);
p_operational->err = err;
struct qed_ptt *p_ptt;
int rc;
+ if (IS_VF(p_hwfn->cdev))
+ return -EINVAL;
+
p_ptt = qed_ptt_acquire(p_hwfn);
if (!p_ptt)
return -EBUSY;
if (p_params->pfc.prio[i])
pfc_map |= BIT(i);
+ *pfc &= ~DCBX_PFC_PRI_EN_BITMAP_MASK;
*pfc |= (pfc_map << DCBX_PFC_PRI_EN_BITMAP_SHIFT);
DP_VERBOSE(p_hwfn, QED_MSG_DCB, "pfc = 0x%x\n", *pfc);
val = (((u32)p_params->ets_pri_tc_tbl[i]) << ((7 - i) * 4));
p_ets->pri_tc_tbl[0] |= val;
}
- p_ets->pri_tc_tbl[0] = cpu_to_be32(p_ets->pri_tc_tbl[0]);
for (i = 0; i < 2; i++) {
p_ets->tc_bw_tbl[i] = cpu_to_be32(p_ets->tc_bw_tbl[i]);
p_ets->tc_tsa_tbl[i] = cpu_to_be32(p_ets->tc_tsa_tbl[i]);
static void
qed_dcbx_set_app_data(struct qed_hwfn *p_hwfn,
struct dcbx_app_priority_feature *p_app,
- struct qed_dcbx_params *p_params)
+ struct qed_dcbx_params *p_params, bool ieee)
{
u32 *entry;
int i;
for (i = 0; i < DCBX_MAX_APP_PROTOCOL; i++) {
entry = &p_app->app_pri_tbl[i].entry;
- *entry &= ~DCBX_APP_SF_MASK;
- if (p_params->app_entry[i].ethtype)
- *entry |= ((u32)DCBX_APP_SF_ETHTYPE <<
- DCBX_APP_SF_SHIFT);
- else
- *entry |= ((u32)DCBX_APP_SF_PORT << DCBX_APP_SF_SHIFT);
+ *entry = 0;
+ if (ieee) {
+ *entry &= ~(DCBX_APP_SF_IEEE_MASK | DCBX_APP_SF_MASK);
+ switch (p_params->app_entry[i].sf_ieee) {
+ case QED_DCBX_SF_IEEE_ETHTYPE:
+ *entry |= ((u32)DCBX_APP_SF_IEEE_ETHTYPE <<
+ DCBX_APP_SF_IEEE_SHIFT);
+ *entry |= ((u32)DCBX_APP_SF_ETHTYPE <<
+ DCBX_APP_SF_SHIFT);
+ break;
+ case QED_DCBX_SF_IEEE_TCP_PORT:
+ *entry |= ((u32)DCBX_APP_SF_IEEE_TCP_PORT <<
+ DCBX_APP_SF_IEEE_SHIFT);
+ *entry |= ((u32)DCBX_APP_SF_PORT <<
+ DCBX_APP_SF_SHIFT);
+ break;
+ case QED_DCBX_SF_IEEE_UDP_PORT:
+ *entry |= ((u32)DCBX_APP_SF_IEEE_UDP_PORT <<
+ DCBX_APP_SF_IEEE_SHIFT);
+ *entry |= ((u32)DCBX_APP_SF_PORT <<
+ DCBX_APP_SF_SHIFT);
+ break;
+ case QED_DCBX_SF_IEEE_TCP_UDP_PORT:
+ *entry |= ((u32)DCBX_APP_SF_IEEE_TCP_UDP_PORT <<
+ DCBX_APP_SF_IEEE_SHIFT);
+ *entry |= ((u32)DCBX_APP_SF_PORT <<
+ DCBX_APP_SF_SHIFT);
+ break;
+ }
+ } else {
+ *entry &= ~DCBX_APP_SF_MASK;
+ if (p_params->app_entry[i].ethtype)
+ *entry |= ((u32)DCBX_APP_SF_ETHTYPE <<
+ DCBX_APP_SF_SHIFT);
+ else
+ *entry |= ((u32)DCBX_APP_SF_PORT <<
+ DCBX_APP_SF_SHIFT);
+ }
+
*entry &= ~DCBX_APP_PROTOCOL_ID_MASK;
*entry |= ((u32)p_params->app_entry[i].proto_id <<
DCBX_APP_PROTOCOL_ID_SHIFT);
struct dcbx_local_params *local_admin,
struct qed_dcbx_set *params)
{
+ bool ieee = false;
+
local_admin->flags = 0;
memcpy(&local_admin->features,
&p_hwfn->p_dcbx_info->operational.features,
sizeof(local_admin->features));
- if (params->enabled)
+ if (params->enabled) {
local_admin->config = params->ver_num;
- else
+ ieee = !!(params->ver_num & DCBX_CONFIG_VERSION_IEEE);
+ } else {
local_admin->config = DCBX_CONFIG_VERSION_DISABLED;
+ }
if (params->override_flags & QED_DCBX_OVERRIDE_PFC_CFG)
qed_dcbx_set_pfc_data(p_hwfn, &local_admin->features.pfc,
if (params->override_flags & QED_DCBX_OVERRIDE_APP_CFG)
qed_dcbx_set_app_data(p_hwfn, &local_admin->features.app,
- ¶ms->config.params);
+ ¶ms->config.params, ieee);
}
int qed_dcbx_config_params(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
return 0;
}
- dcbx_info = kmalloc(sizeof(*dcbx_info), GFP_KERNEL);
+ dcbx_info = kzalloc(sizeof(*dcbx_info), GFP_KERNEL);
if (!dcbx_info) {
DP_ERR(p_hwfn, "Failed to allocate struct qed_dcbx_info\n");
return -ENOMEM;
{
struct qed_dcbx_get *dcbx_info;
- dcbx_info = kmalloc(sizeof(*dcbx_info), GFP_KERNEL);
+ dcbx_info = kzalloc(sizeof(*dcbx_info), GFP_KERNEL);
if (!dcbx_info) {
DP_ERR(hwfn->cdev, "Failed to allocate memory for dcbx_info\n");
return NULL;
if ((entry->ethtype == ethtype) && (entry->proto_id == idval))
break;
/* First empty slot */
- if (!entry->proto_id)
+ if (!entry->proto_id) {
+ dcbx_set.config.params.num_app_entries++;
break;
+ }
}
if (i == QED_DCBX_MAX_APP_PROTOCOL) {
(entry->proto_id == app->protocol))
break;
/* First empty slot */
- if (!entry->proto_id)
+ if (!entry->proto_id) {
+ dcbx_set.config.params.num_app_entries++;
break;
+ }
}
if (i == QED_DCBX_MAX_APP_PROTOCOL) {
#define DCBX_APP_SF_SHIFT 8
#define DCBX_APP_SF_ETHTYPE 0
#define DCBX_APP_SF_PORT 1
+#define DCBX_APP_SF_IEEE_MASK 0x0000f000
+#define DCBX_APP_SF_IEEE_SHIFT 12
+#define DCBX_APP_SF_IEEE_RESERVED 0
+#define DCBX_APP_SF_IEEE_ETHTYPE 1
+#define DCBX_APP_SF_IEEE_TCP_PORT 2
+#define DCBX_APP_SF_IEEE_UDP_PORT 3
+#define DCBX_APP_SF_IEEE_TCP_UDP_PORT 4
+
#define DCBX_APP_PROTOCOL_ID_MASK 0xffff0000
#define DCBX_APP_PROTOCOL_ID_SHIFT 16
};
p_drv_version = &union_data.drv_version;
p_drv_version->version = p_ver->version;
- for (i = 0; i < MCP_DRV_VER_STR_SIZE - 1; i += 4) {
- val = cpu_to_be32(p_ver->name[i]);
+ for (i = 0; i < (MCP_DRV_VER_STR_SIZE - 4) / sizeof(u32); i++) {
+ val = cpu_to_be32(*((u32 *)&p_ver->name[i * sizeof(u32)]));
*(__be32 *)&p_drv_version->name[i * sizeof(u32)] = val;
}
txq->tx_db.data.bd_prod =
cpu_to_le16(qed_chain_get_prod_idx(&txq->tx_pbl));
- if (!skb->xmit_more || netif_tx_queue_stopped(netdev_txq))
+ if (!skb->xmit_more || netif_xmit_stopped(netdev_txq))
qede_update_tx_producer(txq);
if (unlikely(qed_chain_get_elem_left(&txq->tx_pbl)
< (MAX_SKB_FRAGS + 1))) {
+ if (skb->xmit_more)
+ qede_update_tx_producer(txq);
+
netif_tx_stop_queue(netdev_txq);
DP_VERBOSE(edev, NETIF_MSG_TX_QUEUED,
"Stop queue was called\n");
edev->ops->register_ops(cdev, &qede_ll_ops, edev);
#ifdef CONFIG_DCB
- qede_set_dcbnl_ops(edev->ndev);
+ if (!IS_VF(edev))
+ qede_set_dcbnl_ops(edev->ndev);
#endif
INIT_DELAYED_WORK(&edev->sp_task, qede_sp_task);
#define _QLCNIC_LINUX_MAJOR 5
#define _QLCNIC_LINUX_MINOR 3
-#define _QLCNIC_LINUX_SUBVERSION 64
-#define QLCNIC_LINUX_VERSIONID "5.3.64"
+#define _QLCNIC_LINUX_SUBVERSION 65
+#define QLCNIC_LINUX_VERSIONID "5.3.65"
#define QLCNIC_DRV_IDC_VER 0x01
#define QLCNIC_DRIVER_VERSION ((_QLCNIC_LINUX_MAJOR << 16) |\
(_QLCNIC_LINUX_MINOR << 8) | (_QLCNIC_LINUX_SUBVERSION))
#define QLCNIC_RESPONSE_DESC 0x05
#define QLCNIC_LRO_DESC 0x12
-#define QLCNIC_TX_POLL_BUDGET 128
#define QLCNIC_TCP_HDR_SIZE 20
#define QLCNIC_TCP_TS_OPTION_SIZE 12
#define QLCNIC_FETCH_RING_ID(handle) ((handle) >> 63)
struct qlcnic_host_tx_ring *tx_ring;
struct qlcnic_adapter *adapter;
- budget = QLCNIC_TX_POLL_BUDGET;
tx_ring = container_of(napi, struct qlcnic_host_tx_ring, napi);
adapter = tx_ring->adapter;
work_done = qlcnic_process_cmd_ring(adapter, tx_ring, budget);
spinlock_t vlan_list_lock; /* Lock for VLAN list */
};
-struct qlcnic_async_work_list {
+struct qlcnic_async_cmd {
struct list_head list;
- struct work_struct work;
- void *ptr;
struct qlcnic_cmd_args *cmd;
};
struct workqueue_struct *bc_trans_wq;
struct workqueue_struct *bc_async_wq;
struct workqueue_struct *bc_flr_wq;
- struct list_head async_list;
+ struct qlcnic_adapter *adapter;
+ struct list_head async_cmd_list;
+ struct work_struct vf_async_work;
+ spinlock_t queue_lock; /* async_cmd_list queue lock */
};
struct qlcnic_sriov {
#define QLC_83XX_VF_RESET_FAIL_THRESH 8
#define QLC_BC_CMD_MAX_RETRY_CNT 5
+static void qlcnic_sriov_handle_async_issue_cmd(struct work_struct *work);
static void qlcnic_sriov_vf_free_mac_list(struct qlcnic_adapter *);
static int qlcnic_sriov_alloc_bc_mbx_args(struct qlcnic_cmd_args *, u32);
static void qlcnic_sriov_vf_poll_dev_state(struct work_struct *);
}
bc->bc_async_wq = wq;
- INIT_LIST_HEAD(&bc->async_list);
+ INIT_LIST_HEAD(&bc->async_cmd_list);
+ INIT_WORK(&bc->vf_async_work, qlcnic_sriov_handle_async_issue_cmd);
+ spin_lock_init(&bc->queue_lock);
+ bc->adapter = adapter;
for (i = 0; i < num_vfs; i++) {
vf = &sriov->vf_info[i];
void qlcnic_sriov_cleanup_async_list(struct qlcnic_back_channel *bc)
{
- struct list_head *head = &bc->async_list;
- struct qlcnic_async_work_list *entry;
+ struct list_head *head = &bc->async_cmd_list;
+ struct qlcnic_async_cmd *entry;
flush_workqueue(bc->bc_async_wq);
+ cancel_work_sync(&bc->vf_async_work);
+
+ spin_lock(&bc->queue_lock);
while (!list_empty(head)) {
- entry = list_entry(head->next, struct qlcnic_async_work_list,
+ entry = list_entry(head->next, struct qlcnic_async_cmd,
list);
- cancel_work_sync(&entry->work);
list_del(&entry->list);
+ kfree(entry->cmd);
kfree(entry);
}
+ spin_unlock(&bc->queue_lock);
}
void qlcnic_sriov_vf_set_multi(struct net_device *netdev)
static void qlcnic_sriov_handle_async_issue_cmd(struct work_struct *work)
{
- struct qlcnic_async_work_list *entry;
- struct qlcnic_adapter *adapter;
+ struct qlcnic_async_cmd *entry, *tmp;
+ struct qlcnic_back_channel *bc;
struct qlcnic_cmd_args *cmd;
+ struct list_head *head;
+ LIST_HEAD(del_list);
+
+ bc = container_of(work, struct qlcnic_back_channel, vf_async_work);
+ head = &bc->async_cmd_list;
+
+ spin_lock(&bc->queue_lock);
+ list_splice_init(head, &del_list);
+ spin_unlock(&bc->queue_lock);
+
+ list_for_each_entry_safe(entry, tmp, &del_list, list) {
+ list_del(&entry->list);
+ cmd = entry->cmd;
+ __qlcnic_sriov_issue_cmd(bc->adapter, cmd);
+ kfree(entry);
+ }
+
+ if (!list_empty(head))
+ queue_work(bc->bc_async_wq, &bc->vf_async_work);
- entry = container_of(work, struct qlcnic_async_work_list, work);
- adapter = entry->ptr;
- cmd = entry->cmd;
- __qlcnic_sriov_issue_cmd(adapter, cmd);
return;
}
-static struct qlcnic_async_work_list *
-qlcnic_sriov_get_free_node_async_work(struct qlcnic_back_channel *bc)
+static struct qlcnic_async_cmd *
+qlcnic_sriov_alloc_async_cmd(struct qlcnic_back_channel *bc,
+ struct qlcnic_cmd_args *cmd)
{
- struct list_head *node;
- struct qlcnic_async_work_list *entry = NULL;
- u8 empty = 0;
+ struct qlcnic_async_cmd *entry = NULL;
- list_for_each(node, &bc->async_list) {
- entry = list_entry(node, struct qlcnic_async_work_list, list);
- if (!work_pending(&entry->work)) {
- empty = 1;
- break;
- }
- }
+ entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
+ if (!entry)
+ return NULL;
- if (!empty) {
- entry = kzalloc(sizeof(struct qlcnic_async_work_list),
- GFP_ATOMIC);
- if (entry == NULL)
- return NULL;
- list_add_tail(&entry->list, &bc->async_list);
- }
+ entry->cmd = cmd;
+
+ spin_lock(&bc->queue_lock);
+ list_add_tail(&entry->list, &bc->async_cmd_list);
+ spin_unlock(&bc->queue_lock);
return entry;
}
static void qlcnic_sriov_schedule_async_cmd(struct qlcnic_back_channel *bc,
- work_func_t func, void *data,
struct qlcnic_cmd_args *cmd)
{
- struct qlcnic_async_work_list *entry = NULL;
+ struct qlcnic_async_cmd *entry = NULL;
- entry = qlcnic_sriov_get_free_node_async_work(bc);
- if (!entry)
+ entry = qlcnic_sriov_alloc_async_cmd(bc, cmd);
+ if (!entry) {
+ qlcnic_free_mbx_args(cmd);
+ kfree(cmd);
return;
+ }
- entry->ptr = data;
- entry->cmd = cmd;
- INIT_WORK(&entry->work, func);
- queue_work(bc->bc_async_wq, &entry->work);
+ queue_work(bc->bc_async_wq, &bc->vf_async_work);
}
static int qlcnic_sriov_async_issue_cmd(struct qlcnic_adapter *adapter,
if (adapter->need_fw_reset)
return -EIO;
- qlcnic_sriov_schedule_async_cmd(bc, qlcnic_sriov_handle_async_issue_cmd,
- adapter, cmd);
+ qlcnic_sriov_schedule_async_cmd(bc, cmd);
+
return 0;
}
unsigned int rx_tail = cp->rx_tail;
int rx;
-rx_status_loop:
rx = 0;
+rx_status_loop:
cpw16(IntrStatus, cp_rx_intr_mask);
while (rx < budget) {
[ARSTR] = 0x0000,
[TSU_CTRST] = 0x0004,
+ [TSU_FWSLC] = 0x0038,
[TSU_VTAG0] = 0x0058,
[TSU_ADSBSY] = 0x0060,
[TSU_TEN] = 0x0064,
+ [TSU_POST1] = 0x0070,
+ [TSU_POST2] = 0x0074,
+ [TSU_POST3] = 0x0078,
+ [TSU_POST4] = 0x007c,
[TSU_ADRH0] = 0x0100,
[TXNLCR0] = 0x0080,
{
if (sh_eth_is_rz_fast_ether(mdp)) {
sh_eth_tsu_write(mdp, 0, TSU_TEN); /* Disable all CAM entry */
+ sh_eth_tsu_write(mdp, TSU_FWSLC_POSTENU | TSU_FWSLC_POSTENL,
+ TSU_FWSLC); /* Enable POST registers */
return;
}
}
#if BITS_PER_LONG == 64
+ BUILD_BUG_ON(BITS_TO_LONGS(EF10_STAT_COUNT) != 2);
mask[0] = raw_mask[0];
mask[1] = raw_mask[1];
#else
+ BUILD_BUG_ON(BITS_TO_LONGS(EF10_STAT_COUNT) != 3);
mask[0] = raw_mask[0] & 0xffffffff;
mask[1] = raw_mask[0] >> 32;
mask[2] = raw_mask[1] & 0xffffffff;
- mask[3] = raw_mask[1] >> 32;
#endif
}
if (pd) {
memcpy(&lp->cfg, pd, sizeof(lp->cfg));
lp->io_shift = SMC91X_IO_SHIFT(lp->cfg.flags);
+
+ if (!SMC_8BIT(lp) && !SMC_16BIT(lp)) {
+ dev_err(&pdev->dev,
+ "at least one of 8-bit or 16-bit access support is required.\n");
+ ret = -ENXIO;
+ goto out_free_netdev;
+ }
}
#if IS_BUILTIN(CONFIG_OF)
#include <linux/dmaengine.h>
#include <linux/smc91x.h>
+/*
+ * Any 16-bit access is performed with two 8-bit accesses if the hardware
+ * can't do it directly. Most registers are 16-bit so those are mandatory.
+ */
+#define SMC_outw_b(x, a, r) \
+ do { \
+ unsigned int __val16 = (x); \
+ unsigned int __reg = (r); \
+ SMC_outb(__val16, a, __reg); \
+ SMC_outb(__val16 >> 8, a, __reg + (1 << SMC_IO_SHIFT)); \
+ } while (0)
+
+#define SMC_inw_b(a, r) \
+ ({ \
+ unsigned int __val16; \
+ unsigned int __reg = r; \
+ __val16 = SMC_inb(a, __reg); \
+ __val16 |= SMC_inb(a, __reg + (1 << SMC_IO_SHIFT)) << 8; \
+ __val16; \
+ })
+
/*
* Define your architecture specific bus configuration parameters here.
*/
#define SMC_IO_SHIFT (lp->io_shift)
#define SMC_inb(a, r) readb((a) + (r))
-#define SMC_inw(a, r) readw((a) + (r))
+#define SMC_inw(a, r) \
+ ({ \
+ unsigned int __smc_r = r; \
+ SMC_16BIT(lp) ? readw((a) + __smc_r) : \
+ SMC_8BIT(lp) ? SMC_inw_b(a, __smc_r) : \
+ ({ BUG(); 0; }); \
+ })
+
#define SMC_inl(a, r) readl((a) + (r))
#define SMC_outb(v, a, r) writeb(v, (a) + (r))
+#define SMC_outw(v, a, r) \
+ do { \
+ unsigned int __v = v, __smc_r = r; \
+ if (SMC_16BIT(lp)) \
+ __SMC_outw(__v, a, __smc_r); \
+ else if (SMC_8BIT(lp)) \
+ SMC_outw_b(__v, a, __smc_r); \
+ else \
+ BUG(); \
+ } while (0)
+
#define SMC_outl(v, a, r) writel(v, (a) + (r))
+#define SMC_insb(a, r, p, l) readsb((a) + (r), p, l)
+#define SMC_outsb(a, r, p, l) writesb((a) + (r), p, l)
#define SMC_insw(a, r, p, l) readsw((a) + (r), p, l)
#define SMC_outsw(a, r, p, l) writesw((a) + (r), p, l)
#define SMC_insl(a, r, p, l) readsl((a) + (r), p, l)
#define SMC_IRQ_FLAGS (-1) /* from resource */
/* We actually can't write halfwords properly if not word aligned */
-static inline void SMC_outw(u16 val, void __iomem *ioaddr, int reg)
+static inline void __SMC_outw(u16 val, void __iomem *ioaddr, int reg)
{
if ((machine_is_mainstone() || machine_is_stargate2() ||
machine_is_pxa_idp()) && reg & 2) {
#if ! SMC_CAN_USE_16BIT
-/*
- * Any 16-bit access is performed with two 8-bit accesses if the hardware
- * can't do it directly. Most registers are 16-bit so those are mandatory.
- */
-#define SMC_outw(x, ioaddr, reg) \
- do { \
- unsigned int __val16 = (x); \
- SMC_outb( __val16, ioaddr, reg ); \
- SMC_outb( __val16 >> 8, ioaddr, reg + (1 << SMC_IO_SHIFT));\
- } while (0)
-#define SMC_inw(ioaddr, reg) \
- ({ \
- unsigned int __val16; \
- __val16 = SMC_inb( ioaddr, reg ); \
- __val16 |= SMC_inb( ioaddr, reg + (1 << SMC_IO_SHIFT)) << 8; \
- __val16; \
- })
-
+#define SMC_outw(x, ioaddr, reg) SMC_outw_b(x, ioaddr, reg)
+#define SMC_inw(ioaddr, reg) SMC_inw_b(ioaddr, reg)
#define SMC_insw(a, r, p, l) BUG()
#define SMC_outsw(a, r, p, l) BUG()
#endif
#if ! SMC_CAN_USE_8BIT
+#undef SMC_inb
#define SMC_inb(ioaddr, reg) ({ BUG(); 0; })
+#undef SMC_outb
#define SMC_outb(x, ioaddr, reg) BUG()
#define SMC_insb(a, r, p, l) BUG()
#define SMC_outsb(a, r, p, l) BUG()
goto err_out_free_bus_2;
}
- if (smsc911x_mii_probe(dev) < 0) {
- SMSC_WARN(pdata, probe, "Error registering mii bus");
- goto err_out_unregister_bus_3;
- }
-
return 0;
-err_out_unregister_bus_3:
- mdiobus_unregister(pdata->mii_bus);
err_out_free_bus_2:
mdiobus_free(pdata->mii_bus);
err_out_1:
smsc911x_reg_write(pdata, INT_STS, 0xFFFFFFFF);
}
+static irqreturn_t smsc911x_irqhandler(int irq, void *dev_id)
+{
+ struct net_device *dev = dev_id;
+ struct smsc911x_data *pdata = netdev_priv(dev);
+ u32 intsts = smsc911x_reg_read(pdata, INT_STS);
+ u32 inten = smsc911x_reg_read(pdata, INT_EN);
+ int serviced = IRQ_NONE;
+ u32 temp;
+
+ if (unlikely(intsts & inten & INT_STS_SW_INT_)) {
+ temp = smsc911x_reg_read(pdata, INT_EN);
+ temp &= (~INT_EN_SW_INT_EN_);
+ smsc911x_reg_write(pdata, INT_EN, temp);
+ smsc911x_reg_write(pdata, INT_STS, INT_STS_SW_INT_);
+ pdata->software_irq_signal = 1;
+ smp_wmb();
+ serviced = IRQ_HANDLED;
+ }
+
+ if (unlikely(intsts & inten & INT_STS_RXSTOP_INT_)) {
+ /* Called when there is a multicast update scheduled and
+ * it is now safe to complete the update */
+ SMSC_TRACE(pdata, intr, "RX Stop interrupt");
+ smsc911x_reg_write(pdata, INT_STS, INT_STS_RXSTOP_INT_);
+ if (pdata->multicast_update_pending)
+ smsc911x_rx_multicast_update_workaround(pdata);
+ serviced = IRQ_HANDLED;
+ }
+
+ if (intsts & inten & INT_STS_TDFA_) {
+ temp = smsc911x_reg_read(pdata, FIFO_INT);
+ temp |= FIFO_INT_TX_AVAIL_LEVEL_;
+ smsc911x_reg_write(pdata, FIFO_INT, temp);
+ smsc911x_reg_write(pdata, INT_STS, INT_STS_TDFA_);
+ netif_wake_queue(dev);
+ serviced = IRQ_HANDLED;
+ }
+
+ if (unlikely(intsts & inten & INT_STS_RXE_)) {
+ SMSC_TRACE(pdata, intr, "RX Error interrupt");
+ smsc911x_reg_write(pdata, INT_STS, INT_STS_RXE_);
+ serviced = IRQ_HANDLED;
+ }
+
+ if (likely(intsts & inten & INT_STS_RSFL_)) {
+ if (likely(napi_schedule_prep(&pdata->napi))) {
+ /* Disable Rx interrupts */
+ temp = smsc911x_reg_read(pdata, INT_EN);
+ temp &= (~INT_EN_RSFL_EN_);
+ smsc911x_reg_write(pdata, INT_EN, temp);
+ /* Schedule a NAPI poll */
+ __napi_schedule(&pdata->napi);
+ } else {
+ SMSC_WARN(pdata, rx_err, "napi_schedule_prep failed");
+ }
+ serviced = IRQ_HANDLED;
+ }
+
+ return serviced;
+}
+
static int smsc911x_open(struct net_device *dev)
{
struct smsc911x_data *pdata = netdev_priv(dev);
unsigned int timeout;
unsigned int temp;
unsigned int intcfg;
+ int retval;
+ int irq_flags;
- /* if the phy is not yet registered, retry later*/
+ /* find and start the given phy */
if (!dev->phydev) {
- SMSC_WARN(pdata, hw, "phy_dev is NULL");
- return -EAGAIN;
+ retval = smsc911x_mii_probe(dev);
+ if (retval < 0) {
+ SMSC_WARN(pdata, probe, "Error starting phy");
+ goto out;
+ }
}
/* Reset the LAN911x */
- if (smsc911x_soft_reset(pdata)) {
+ retval = smsc911x_soft_reset(pdata);
+ if (retval) {
SMSC_WARN(pdata, hw, "soft reset failed");
- return -EIO;
+ goto mii_free_out;
}
smsc911x_reg_write(pdata, HW_CFG, 0x00050000);
pdata->software_irq_signal = 0;
smp_wmb();
+ irq_flags = irq_get_trigger_type(dev->irq);
+ retval = request_irq(dev->irq, smsc911x_irqhandler,
+ irq_flags | IRQF_SHARED, dev->name, dev);
+ if (retval) {
+ SMSC_WARN(pdata, probe,
+ "Unable to claim requested irq: %d", dev->irq);
+ goto mii_free_out;
+ }
+
temp = smsc911x_reg_read(pdata, INT_EN);
temp |= INT_EN_SW_INT_EN_;
smsc911x_reg_write(pdata, INT_EN, temp);
if (!pdata->software_irq_signal) {
netdev_warn(dev, "ISR failed signaling test (IRQ %d)\n",
dev->irq);
- return -ENODEV;
+ retval = -ENODEV;
+ goto irq_stop_out;
}
SMSC_TRACE(pdata, ifup, "IRQ handler passed test using IRQ %d",
dev->irq);
netif_start_queue(dev);
return 0;
+
+irq_stop_out:
+ free_irq(dev->irq, dev);
+mii_free_out:
+ phy_disconnect(dev->phydev);
+ dev->phydev = NULL;
+out:
+ return retval;
}
/* Entry point for stopping the interface */
dev->stats.rx_dropped += smsc911x_reg_read(pdata, RX_DROP);
smsc911x_tx_update_txcounters(dev);
+ free_irq(dev->irq, dev);
+
/* Bring the PHY down */
- if (dev->phydev)
+ if (dev->phydev) {
phy_stop(dev->phydev);
+ phy_disconnect(dev->phydev);
+ dev->phydev = NULL;
+ }
+ netif_carrier_off(dev);
SMSC_TRACE(pdata, ifdown, "Interface stopped");
return 0;
spin_unlock_irqrestore(&pdata->mac_lock, flags);
}
-static irqreturn_t smsc911x_irqhandler(int irq, void *dev_id)
-{
- struct net_device *dev = dev_id;
- struct smsc911x_data *pdata = netdev_priv(dev);
- u32 intsts = smsc911x_reg_read(pdata, INT_STS);
- u32 inten = smsc911x_reg_read(pdata, INT_EN);
- int serviced = IRQ_NONE;
- u32 temp;
-
- if (unlikely(intsts & inten & INT_STS_SW_INT_)) {
- temp = smsc911x_reg_read(pdata, INT_EN);
- temp &= (~INT_EN_SW_INT_EN_);
- smsc911x_reg_write(pdata, INT_EN, temp);
- smsc911x_reg_write(pdata, INT_STS, INT_STS_SW_INT_);
- pdata->software_irq_signal = 1;
- smp_wmb();
- serviced = IRQ_HANDLED;
- }
-
- if (unlikely(intsts & inten & INT_STS_RXSTOP_INT_)) {
- /* Called when there is a multicast update scheduled and
- * it is now safe to complete the update */
- SMSC_TRACE(pdata, intr, "RX Stop interrupt");
- smsc911x_reg_write(pdata, INT_STS, INT_STS_RXSTOP_INT_);
- if (pdata->multicast_update_pending)
- smsc911x_rx_multicast_update_workaround(pdata);
- serviced = IRQ_HANDLED;
- }
-
- if (intsts & inten & INT_STS_TDFA_) {
- temp = smsc911x_reg_read(pdata, FIFO_INT);
- temp |= FIFO_INT_TX_AVAIL_LEVEL_;
- smsc911x_reg_write(pdata, FIFO_INT, temp);
- smsc911x_reg_write(pdata, INT_STS, INT_STS_TDFA_);
- netif_wake_queue(dev);
- serviced = IRQ_HANDLED;
- }
-
- if (unlikely(intsts & inten & INT_STS_RXE_)) {
- SMSC_TRACE(pdata, intr, "RX Error interrupt");
- smsc911x_reg_write(pdata, INT_STS, INT_STS_RXE_);
- serviced = IRQ_HANDLED;
- }
-
- if (likely(intsts & inten & INT_STS_RSFL_)) {
- if (likely(napi_schedule_prep(&pdata->napi))) {
- /* Disable Rx interrupts */
- temp = smsc911x_reg_read(pdata, INT_EN);
- temp &= (~INT_EN_RSFL_EN_);
- smsc911x_reg_write(pdata, INT_EN, temp);
- /* Schedule a NAPI poll */
- __napi_schedule(&pdata->napi);
- } else {
- SMSC_WARN(pdata, rx_err, "napi_schedule_prep failed");
- }
- serviced = IRQ_HANDLED;
- }
-
- return serviced;
-}
-
#ifdef CONFIG_NET_POLL_CONTROLLER
static void smsc911x_poll_controller(struct net_device *dev)
{
pdata = netdev_priv(dev);
BUG_ON(!pdata);
BUG_ON(!pdata->ioaddr);
- BUG_ON(!dev->phydev);
+ WARN_ON(dev->phydev);
SMSC_TRACE(pdata, ifdown, "Stopping driver");
- phy_disconnect(dev->phydev);
mdiobus_unregister(pdata->mii_bus);
mdiobus_free(pdata->mii_bus);
unregister_netdev(dev);
- free_irq(dev->irq, dev);
res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
"smsc911x-memory");
if (!res)
struct smsc911x_data *pdata;
struct smsc911x_platform_config *config = dev_get_platdata(&pdev->dev);
struct resource *res;
- unsigned int intcfg = 0;
- int res_size, irq, irq_flags;
+ int res_size, irq;
int retval;
res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
pdata = netdev_priv(dev);
dev->irq = irq;
- irq_flags = irq_get_trigger_type(irq);
pdata->ioaddr = ioremap_nocache(res->start, res_size);
pdata->dev = dev;
if (retval < 0)
goto out_disable_resources;
- /* configure irq polarity and type before connecting isr */
- if (pdata->config.irq_polarity == SMSC911X_IRQ_POLARITY_ACTIVE_HIGH)
- intcfg |= INT_CFG_IRQ_POL_;
-
- if (pdata->config.irq_type == SMSC911X_IRQ_TYPE_PUSH_PULL)
- intcfg |= INT_CFG_IRQ_TYPE_;
-
- smsc911x_reg_write(pdata, INT_CFG, intcfg);
-
- /* Ensure interrupts are globally disabled before connecting ISR */
- smsc911x_disable_irq_chip(dev);
+ netif_carrier_off(dev);
- retval = request_irq(dev->irq, smsc911x_irqhandler,
- irq_flags | IRQF_SHARED, dev->name, dev);
+ retval = smsc911x_mii_init(pdev, dev);
if (retval) {
- SMSC_WARN(pdata, probe,
- "Unable to claim requested irq: %d", dev->irq);
+ SMSC_WARN(pdata, probe, "Error %i initialising mii", retval);
goto out_disable_resources;
}
- netif_carrier_off(dev);
-
retval = register_netdev(dev);
if (retval) {
SMSC_WARN(pdata, probe, "Error %i registering device", retval);
- goto out_free_irq;
+ goto out_disable_resources;
} else {
SMSC_TRACE(pdata, probe,
"Network interface: \"%s\"", dev->name);
}
- retval = smsc911x_mii_init(pdev, dev);
- if (retval) {
- SMSC_WARN(pdata, probe, "Error %i initialising mii", retval);
- goto out_unregister_netdev_5;
- }
-
spin_lock_irq(&pdata->mac_lock);
/* Check if mac address has been specified when bringing interface up */
return 0;
-out_unregister_netdev_5:
- unregister_netdev(dev);
-out_free_irq:
- free_irq(dev->irq, dev);
out_disable_resources:
pm_runtime_put(&pdev->dev);
pm_runtime_disable(&pdev->dev);
}
if (mode & WAKE_UCAST) {
pr_debug("GMAC: WOL on global unicast\n");
- pmt |= global_unicast;
+ pmt |= power_down | global_unicast | wake_up_frame_en;
}
writel(pmt, ioaddr + GMAC_PMT);
}
if (mode & WAKE_UCAST) {
pr_debug("GMAC: WOL on global unicast\n");
- pmt |= global_unicast;
+ pmt |= power_down | global_unicast | wake_up_frame_en;
}
writel(pmt, ioaddr + GMAC_PMT);
lp->mii_bus->read = &dwceqos_mdio_read;
lp->mii_bus->write = &dwceqos_mdio_write;
lp->mii_bus->priv = lp;
- lp->mii_bus->parent = &lp->ndev->dev;
+ lp->mii_bus->parent = &lp->pdev->dev;
of_address_to_resource(lp->pdev->dev.of_node, 0, &res);
snprintf(lp->mii_bus->id, MII_BUS_ID_SIZE, "%.8llx",
DWCEQOS_MMC_CTRL_RSTONRD);
dwceqos_enable_mmc_interrupt(lp);
- /* Enable Interrupts */
- dwceqos_write(lp, REG_DWCEQOS_DMA_CH0_IE,
- DWCEQOS_DMA_CH0_IE_NIE |
- DWCEQOS_DMA_CH0_IE_RIE | DWCEQOS_DMA_CH0_IE_TIE |
- DWCEQOS_DMA_CH0_IE_AIE |
- DWCEQOS_DMA_CH0_IE_FBEE);
-
+ dwceqos_write(lp, REG_DWCEQOS_DMA_CH0_IE, 0);
dwceqos_write(lp, REG_DWCEQOS_MAC_IE, 0);
dwceqos_write(lp, REG_DWCEQOS_MAC_CFG, DWCEQOS_MAC_CFG_IPC |
netif_start_queue(ndev);
tasklet_enable(&lp->tx_bdreclaim_tasklet);
+ /* Enable Interrupts -- do this only after we enable NAPI and the
+ * tasklet.
+ */
+ dwceqos_write(lp, REG_DWCEQOS_DMA_CH0_IE,
+ DWCEQOS_DMA_CH0_IE_NIE |
+ DWCEQOS_DMA_CH0_IE_RIE | DWCEQOS_DMA_CH0_IE_TIE |
+ DWCEQOS_DMA_CH0_IE_AIE |
+ DWCEQOS_DMA_CH0_IE_FBEE);
+
return 0;
}
ndev->features = ndev->hw_features;
- netif_napi_add(ndev, &lp->napi, dwceqos_rx_poll, NAPI_POLL_WEIGHT);
-
- ret = register_netdev(ndev);
- if (ret) {
- dev_err(&pdev->dev, "Cannot register net device, aborting.\n");
- goto err_out_clk_dis_aper;
- }
-
lp->phy_ref_clk = devm_clk_get(&pdev->dev, "phy_ref_clk");
if (IS_ERR(lp->phy_ref_clk)) {
dev_err(&pdev->dev, "phy_ref_clk clock not found.\n");
ret = PTR_ERR(lp->phy_ref_clk);
- goto err_out_unregister_netdev;
+ goto err_out_clk_dis_aper;
}
ret = clk_prepare_enable(lp->phy_ref_clk);
if (ret) {
dev_err(&pdev->dev, "Unable to enable device clock.\n");
- goto err_out_unregister_netdev;
+ goto err_out_clk_dis_aper;
}
lp->phy_node = of_parse_phandle(lp->pdev->dev.of_node,
ret = of_phy_register_fixed_link(lp->pdev->dev.of_node);
if (ret < 0) {
dev_err(&pdev->dev, "invalid fixed-link");
- goto err_out_unregister_clk_notifier;
+ goto err_out_clk_dis_phy;
}
lp->phy_node = of_node_get(lp->pdev->dev.of_node);
ret = of_get_phy_mode(lp->pdev->dev.of_node);
if (ret < 0) {
dev_err(&lp->pdev->dev, "error in getting phy i/f\n");
- goto err_out_unregister_clk_notifier;
+ goto err_out_clk_dis_phy;
}
lp->phy_interface = ret;
ret = dwceqos_mii_init(lp);
if (ret) {
dev_err(&lp->pdev->dev, "error in dwceqos_mii_init\n");
- goto err_out_unregister_clk_notifier;
+ goto err_out_clk_dis_phy;
}
ret = dwceqos_mii_probe(ndev);
if (ret != 0) {
netdev_err(ndev, "mii_probe fail.\n");
ret = -ENXIO;
- goto err_out_unregister_clk_notifier;
+ goto err_out_clk_dis_phy;
}
dwceqos_set_umac_addr(lp, lp->ndev->dev_addr, 0);
if (ret) {
dev_err(&lp->pdev->dev, "Unable to retrieve DT, error %d\n",
ret);
- goto err_out_unregister_clk_notifier;
+ goto err_out_clk_dis_phy;
}
dev_info(&lp->pdev->dev, "pdev->id %d, baseaddr 0x%08lx, irq %d\n",
pdev->id, ndev->base_addr, ndev->irq);
if (ret) {
dev_err(&lp->pdev->dev, "Unable to request IRQ %d, error %d\n",
ndev->irq, ret);
- goto err_out_unregister_clk_notifier;
+ goto err_out_clk_dis_phy;
}
if (netif_msg_probe(lp))
netdev_dbg(ndev, "net_local@%p\n", lp);
+ netif_napi_add(ndev, &lp->napi, dwceqos_rx_poll, NAPI_POLL_WEIGHT);
+
+ ret = register_netdev(ndev);
+ if (ret) {
+ dev_err(&pdev->dev, "Cannot register net device, aborting.\n");
+ goto err_out_clk_dis_phy;
+ }
+
return 0;
-err_out_unregister_clk_notifier:
+err_out_clk_dis_phy:
clk_disable_unprepare(lp->phy_ref_clk);
-err_out_unregister_netdev:
- unregister_netdev(ndev);
err_out_clk_dis_aper:
clk_disable_unprepare(lp->apb_pclk);
err_out_free_netdev:
if ((readl(nic->regs + FPGA_VER) & 0xFFF) >= 378) {
err = pci_enable_msi(pdev);
if (err)
- pr_err("Can't eneble msi. error is %d\n", err);
+ pr_err("Can't enable msi. error is %d\n", err);
else
nic->irq_type = IRQ_MSI;
} else
netif_receive_skb(skb);
ndev->stats.rx_bytes += len;
ndev->stats.rx_packets++;
+ kmemleak_not_leak(new_skb);
} else {
ndev->stats.rx_dropped++;
new_skb = skb;
kfree_skb(skb);
goto err_cleanup;
}
+ kmemleak_not_leak(skb);
}
/* continue even if we didn't manage to submit all
* receive descs
static void tsi108_timed_checker(unsigned long dev_ptr);
+#ifdef DEBUG
static void dump_eth_one(struct net_device *dev)
{
struct tsi108_prv_data *data = netdev_priv(dev);
TSI_READ(TSI108_EC_RXESTAT),
TSI_READ(TSI108_EC_RXERR), data->rxpending);
}
+#endif
/* Synchronization is needed between the thread and up/down events.
* Note that the PHY is accessed through the same registers for both
lp->rx_ping_pong = get_bool(ofdev, "xlnx,rx-ping-pong");
mac_address = of_get_mac_address(ofdev->dev.of_node);
- if (mac_address)
+ if (mac_address) {
/* Set the MAC address. */
memcpy(ndev->dev_addr, mac_address, ETH_ALEN);
- else
- dev_warn(dev, "No MAC address found\n");
+ } else {
+ dev_warn(dev, "No MAC address found, using random\n");
+ eth_hw_addr_random(ndev);
+ }
/* Clear the Tx CSR's in case this is a restart */
__raw_writel(0, lp->base_addr + XEL_TSR_OFFSET);
u32 event;
};
-struct garp_wrk {
- struct work_struct dwrk;
- struct net_device *netdev;
- struct netvsc_device *netvsc_dev;
-};
-
/* The context of the netvsc device */
struct net_device_context {
/* point back to our device context */
struct work_struct work;
u32 msg_enable; /* debug level */
- struct garp_wrk gwrk;
struct netvsc_stats __percpu *tx_stats;
struct netvsc_stats __percpu *rx_stats;
/* the device is going away */
bool start_remove;
+
+ /* State to manage the associated VF interface. */
+ struct net_device *vf_netdev;
+ bool vf_inject;
+ atomic_t vf_use_cnt;
+ /* 1: allocated, serial number is valid. 0: not allocated */
+ u32 vf_alloc;
+ /* Serial number of the VF to team with */
+ u32 vf_serial;
};
/* Per netvsc device */
u32 max_pkt; /* max number of pkt in one send, e.g. 8 */
u32 pkt_align; /* alignment bytes, e.g. 8 */
- /* 1: allocated, serial number is valid. 0: not allocated */
- u32 vf_alloc;
- /* Serial number of the VF to team with */
- u32 vf_serial;
atomic_t open_cnt;
- /* State to manage the associated VF interface. */
- bool vf_inject;
- struct net_device *vf_netdev;
- atomic_t vf_use_cnt;
};
static inline struct netvsc_device *
init_waitqueue_head(&net_device->wait_drain);
net_device->destroy = false;
atomic_set(&net_device->open_cnt, 0);
- atomic_set(&net_device->vf_use_cnt, 0);
net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT;
net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT;
- net_device->vf_netdev = NULL;
- net_device->vf_inject = false;
-
return net_device;
}
nvscdev->send_table[i] = tab[i];
}
-static void netvsc_send_vf(struct netvsc_device *nvdev,
+static void netvsc_send_vf(struct net_device_context *net_device_ctx,
struct nvsp_message *nvmsg)
{
- nvdev->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated;
- nvdev->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial;
+ net_device_ctx->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated;
+ net_device_ctx->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial;
}
static inline void netvsc_receive_inband(struct hv_device *hdev,
- struct netvsc_device *nvdev,
- struct nvsp_message *nvmsg)
+ struct net_device_context *net_device_ctx,
+ struct nvsp_message *nvmsg)
{
switch (nvmsg->hdr.msg_type) {
case NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE:
break;
case NVSP_MSG4_TYPE_SEND_VF_ASSOCIATION:
- netvsc_send_vf(nvdev, nvmsg);
+ netvsc_send_vf(net_device_ctx, nvmsg);
break;
}
}
struct vmpacket_descriptor *desc)
{
struct nvsp_message *nvmsg;
+ struct net_device_context *net_device_ctx = netdev_priv(ndev);
nvmsg = (struct nvsp_message *)((unsigned long)
desc + (desc->offset8 << 3));
break;
case VM_PKT_DATA_INBAND:
- netvsc_receive_inband(device, net_device, nvmsg);
+ netvsc_receive_inband(device, net_device_ctx, nvmsg);
break;
default:
struct sk_buff *skb;
struct sk_buff *vf_skb;
struct netvsc_stats *rx_stats;
- struct netvsc_device *netvsc_dev = net_device_ctx->nvdev;
u32 bytes_recvd = packet->total_data_buflen;
int ret = 0;
if (!net || net->reg_state != NETREG_REGISTERED)
return NVSP_STAT_FAIL;
- if (READ_ONCE(netvsc_dev->vf_inject)) {
- atomic_inc(&netvsc_dev->vf_use_cnt);
- if (!READ_ONCE(netvsc_dev->vf_inject)) {
+ if (READ_ONCE(net_device_ctx->vf_inject)) {
+ atomic_inc(&net_device_ctx->vf_use_cnt);
+ if (!READ_ONCE(net_device_ctx->vf_inject)) {
/*
* We raced; just move on.
*/
- atomic_dec(&netvsc_dev->vf_use_cnt);
+ atomic_dec(&net_device_ctx->vf_use_cnt);
goto vf_injection_done;
}
* the host). Deliver these via the VF interface
* in the guest.
*/
- vf_skb = netvsc_alloc_recv_skb(netvsc_dev->vf_netdev, packet,
- csum_info, *data, vlan_tci);
+ vf_skb = netvsc_alloc_recv_skb(net_device_ctx->vf_netdev,
+ packet, csum_info, *data,
+ vlan_tci);
if (vf_skb != NULL) {
- ++netvsc_dev->vf_netdev->stats.rx_packets;
- netvsc_dev->vf_netdev->stats.rx_bytes += bytes_recvd;
+ ++net_device_ctx->vf_netdev->stats.rx_packets;
+ net_device_ctx->vf_netdev->stats.rx_bytes +=
+ bytes_recvd;
netif_receive_skb(vf_skb);
} else {
++net->stats.rx_dropped;
ret = NVSP_STAT_FAIL;
}
- atomic_dec(&netvsc_dev->vf_use_cnt);
+ atomic_dec(&net_device_ctx->vf_use_cnt);
return ret;
}
free_netdev(netdev);
}
-static void netvsc_notify_peers(struct work_struct *wrk)
-{
- struct garp_wrk *gwrk;
-
- gwrk = container_of(wrk, struct garp_wrk, dwrk);
-
- netdev_notify_peers(gwrk->netdev);
-
- atomic_dec(&gwrk->netvsc_dev->vf_use_cnt);
-}
-
static struct net_device *get_netvsc_net_device(char *mac)
{
struct net_device *dev, *found = NULL;
net_device_ctx = netdev_priv(ndev);
netvsc_dev = net_device_ctx->nvdev;
- if (netvsc_dev == NULL)
+ if (!netvsc_dev || net_device_ctx->vf_netdev)
return NOTIFY_DONE;
netdev_info(ndev, "VF registering: %s\n", vf_netdev->name);
* Take a reference on the module.
*/
try_module_get(THIS_MODULE);
- netvsc_dev->vf_netdev = vf_netdev;
+ net_device_ctx->vf_netdev = vf_netdev;
return NOTIFY_OK;
}
+static void netvsc_inject_enable(struct net_device_context *net_device_ctx)
+{
+ net_device_ctx->vf_inject = true;
+}
+
+static void netvsc_inject_disable(struct net_device_context *net_device_ctx)
+{
+ net_device_ctx->vf_inject = false;
+
+ /* Wait for currently active users to drain out. */
+ while (atomic_read(&net_device_ctx->vf_use_cnt) != 0)
+ udelay(50);
+}
static int netvsc_vf_up(struct net_device *vf_netdev)
{
net_device_ctx = netdev_priv(ndev);
netvsc_dev = net_device_ctx->nvdev;
- if ((netvsc_dev == NULL) || (netvsc_dev->vf_netdev == NULL))
+ if (!netvsc_dev || !net_device_ctx->vf_netdev)
return NOTIFY_DONE;
netdev_info(ndev, "VF up: %s\n", vf_netdev->name);
- netvsc_dev->vf_inject = true;
+ netvsc_inject_enable(net_device_ctx);
/*
* Open the device before switching data path.
netif_carrier_off(ndev);
- /*
- * Now notify peers. We are scheduling work to
- * notify peers; take a reference to prevent
- * the VF interface from vanishing.
- */
- atomic_inc(&netvsc_dev->vf_use_cnt);
- net_device_ctx->gwrk.netdev = vf_netdev;
- net_device_ctx->gwrk.netvsc_dev = netvsc_dev;
- schedule_work(&net_device_ctx->gwrk.dwrk);
+ /* Now notify peers through VF device. */
+ call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, vf_netdev);
return NOTIFY_OK;
}
net_device_ctx = netdev_priv(ndev);
netvsc_dev = net_device_ctx->nvdev;
- if ((netvsc_dev == NULL) || (netvsc_dev->vf_netdev == NULL))
+ if (!netvsc_dev || !net_device_ctx->vf_netdev)
return NOTIFY_DONE;
netdev_info(ndev, "VF down: %s\n", vf_netdev->name);
- netvsc_dev->vf_inject = false;
- /*
- * Wait for currently active users to
- * drain out.
- */
-
- while (atomic_read(&netvsc_dev->vf_use_cnt) != 0)
- udelay(50);
+ netvsc_inject_disable(net_device_ctx);
netvsc_switch_datapath(ndev, false);
netdev_info(ndev, "Data path switched from VF: %s\n", vf_netdev->name);
rndis_filter_close(netvsc_dev);
netif_carrier_on(ndev);
- /*
- * Notify peers.
- */
- atomic_inc(&netvsc_dev->vf_use_cnt);
- net_device_ctx->gwrk.netdev = ndev;
- net_device_ctx->gwrk.netvsc_dev = netvsc_dev;
- schedule_work(&net_device_ctx->gwrk.dwrk);
+
+ /* Now notify peers through netvsc device. */
+ call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, ndev);
return NOTIFY_OK;
}
net_device_ctx = netdev_priv(ndev);
netvsc_dev = net_device_ctx->nvdev;
- if (netvsc_dev == NULL)
+ if (!netvsc_dev || !net_device_ctx->vf_netdev)
return NOTIFY_DONE;
netdev_info(ndev, "VF unregistering: %s\n", vf_netdev->name);
-
- netvsc_dev->vf_netdev = NULL;
+ netvsc_inject_disable(net_device_ctx);
+ net_device_ctx->vf_netdev = NULL;
module_put(THIS_MODULE);
return NOTIFY_OK;
}
INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change);
INIT_WORK(&net_device_ctx->work, do_set_multicast);
- INIT_WORK(&net_device_ctx->gwrk.dwrk, netvsc_notify_peers);
spin_lock_init(&net_device_ctx->lock);
INIT_LIST_HEAD(&net_device_ctx->reconfig_events);
+ atomic_set(&net_device_ctx->vf_use_cnt, 0);
+ net_device_ctx->vf_netdev = NULL;
+ net_device_ctx->vf_inject = false;
+
net->netdev_ops = &device_ops;
net->hw_features = NETVSC_HW_FEATURES;
{
struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
- /* Avoid Vlan, Bonding dev with same MAC registering as VF */
- if (event_dev->priv_flags & (IFF_802_1Q_VLAN | IFF_BONDING))
+ /* Avoid Vlan dev with same MAC registering as VF */
+ if (event_dev->priv_flags & IFF_802_1Q_VLAN)
+ return NOTIFY_DONE;
+
+ /* Avoid Bonding master dev with same MAC registering as VF */
+ if (event_dev->priv_flags & IFF_BONDING &&
+ event_dev->flags & IFF_MASTER)
return NOTIFY_DONE;
switch (event) {
struct pcpu_secy_stats __percpu *stats;
struct list_head secys;
struct gro_cells gro_cells;
+ unsigned int nest_level;
};
/**
#define MACSEC_FEATURES \
(NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST)
+static struct lock_class_key macsec_netdev_addr_lock_key;
+
static int macsec_dev_init(struct net_device *dev)
{
struct macsec_dev *macsec = macsec_priv(dev);
return macsec_priv(dev)->real_dev->ifindex;
}
+
+static int macsec_get_nest_level(struct net_device *dev)
+{
+ return macsec_priv(dev)->nest_level;
+}
+
+
static const struct net_device_ops macsec_netdev_ops = {
.ndo_init = macsec_dev_init,
.ndo_uninit = macsec_dev_uninit,
.ndo_start_xmit = macsec_start_xmit,
.ndo_get_stats64 = macsec_get_stats64,
.ndo_get_iflink = macsec_get_iflink,
+ .ndo_get_lock_subclass = macsec_get_nest_level,
};
static const struct device_type macsec_type = {
}
}
+static void macsec_common_dellink(struct net_device *dev, struct list_head *head)
+{
+ struct macsec_dev *macsec = macsec_priv(dev);
+ struct net_device *real_dev = macsec->real_dev;
+
+ unregister_netdevice_queue(dev, head);
+ list_del_rcu(&macsec->secys);
+ macsec_del_dev(macsec);
+ netdev_upper_dev_unlink(real_dev, dev);
+
+ macsec_generation++;
+}
+
static void macsec_dellink(struct net_device *dev, struct list_head *head)
{
struct macsec_dev *macsec = macsec_priv(dev);
struct net_device *real_dev = macsec->real_dev;
struct macsec_rxh_data *rxd = macsec_data_rtnl(real_dev);
- macsec_generation++;
+ macsec_common_dellink(dev, head);
- unregister_netdevice_queue(dev, head);
- list_del_rcu(&macsec->secys);
if (list_empty(&rxd->secys)) {
netdev_rx_handler_unregister(real_dev);
kfree(rxd);
}
-
- macsec_del_dev(macsec);
}
static int register_macsec_dev(struct net_device *real_dev,
dev_hold(real_dev);
+ macsec->nest_level = dev_get_nest_level(real_dev) + 1;
+ netdev_lockdep_set_classes(dev);
+ lockdep_set_class_and_subclass(&dev->addr_list_lock,
+ &macsec_netdev_addr_lock_key,
+ macsec_get_nest_level(dev));
+
+ err = netdev_upper_dev_link(real_dev, dev);
+ if (err < 0)
+ goto unregister;
+
/* need to be already registered so that ->init has run and
* the MAC addr is set
*/
if (rx_handler && sci_exists(real_dev, sci)) {
err = -EBUSY;
- goto unregister;
+ goto unlink;
}
err = macsec_add_dev(dev, sci, icv_len);
if (err)
- goto unregister;
+ goto unlink;
if (data)
macsec_changelink_common(dev, data);
del_dev:
macsec_del_dev(macsec);
+unlink:
+ netdev_upper_dev_unlink(real_dev, dev);
unregister:
unregister_netdevice(dev);
return err;
rxd = macsec_data_rtnl(real_dev);
list_for_each_entry_safe(m, n, &rxd->secys, secys) {
- macsec_dellink(m->secy.netdev, &head);
+ macsec_common_dellink(m->secy.netdev, &head);
}
+
+ netdev_rx_handler_unregister(real_dev);
+ kfree(rxd);
+
unregister_netdevice_many(&head);
break;
}
vlan->dev = dev;
vlan->port = port;
vlan->set_features = MACVLAN_FEATURES;
- vlan->nest_level = dev_get_nest_level(lowerdev, netif_is_macvlan) + 1;
+ vlan->nest_level = dev_get_nest_level(lowerdev) + 1;
vlan->mode = MACVLAN_MODE_VEPA;
if (data && data[IFLA_MACVLAN_MODE])
rtnl_unlock();
synchronize_rcu();
- skb_array_cleanup(&q->skb_array);
sock_put(&q->sk);
}
static void macvtap_sock_destruct(struct sock *sk)
{
struct macvtap_queue *q = container_of(sk, struct macvtap_queue, sk);
- struct sk_buff *skb;
- while ((skb = skb_array_consume(&q->skb_array)) != NULL)
- kfree_skb(skb);
+ skb_array_cleanup(&q->skb_array);
}
static int macvtap_open(struct inode *inode, struct file *file)
config MDIO_XGENE
tristate "APM X-Gene SoC MDIO bus controller"
+ depends on ARCH_XGENE || COMPILE_TEST
help
This module provides a driver for the MDIO busses found in the
APM X-Gene SoC's.
mdiobus_unregister(mdio_bus);
mdiobus_free(mdio_bus);
- if (dev->of_node) {
- if (IS_ERR(pdata->clk))
- clk_disable_unprepare(pdata->clk);
- }
+ if (dev->of_node)
+ clk_disable_unprepare(pdata->clk);
return 0;
}
data[i] = kszphy_get_stat(phydev, i);
}
-static int kszphy_resume(struct phy_device *phydev)
+static int kszphy_suspend(struct phy_device *phydev)
{
- int value;
+ /* Disable PHY Interrupts */
+ if (phy_interrupt_is_valid(phydev)) {
+ phydev->interrupts = PHY_INTERRUPT_DISABLED;
+ if (phydev->drv->config_intr)
+ phydev->drv->config_intr(phydev);
+ }
- mutex_lock(&phydev->lock);
+ return genphy_suspend(phydev);
+}
- value = phy_read(phydev, MII_BMCR);
- phy_write(phydev, MII_BMCR, value & ~BMCR_PDOWN);
+static int kszphy_resume(struct phy_device *phydev)
+{
+ genphy_resume(phydev);
- kszphy_config_intr(phydev);
- mutex_unlock(&phydev->lock);
+ /* Enable PHY Interrupts */
+ if (phy_interrupt_is_valid(phydev)) {
+ phydev->interrupts = PHY_INTERRUPT_ENABLED;
+ if (phydev->drv->config_intr)
+ phydev->drv->config_intr(phydev);
+ }
return 0;
}
.get_sset_count = kszphy_get_sset_count,
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
- .suspend = genphy_suspend,
+ .suspend = kszphy_suspend,
.resume = kszphy_resume,
}, {
.phy_id = PHY_ID_KSZ8061,
.get_strings = kszphy_get_strings,
.get_stats = kszphy_get_stats,
.suspend = genphy_suspend,
- .resume = genphy_resume,
+ .resume = kszphy_resume,
}, {
.phy_id = PHY_ID_KSZ8873MLL,
.phy_id_mask = MICREL_PHY_ID_MASK,
int phy_start_interrupts(struct phy_device *phydev)
{
atomic_set(&phydev->irq_disable, 0);
- if (request_irq(phydev->irq, phy_interrupt, 0, "phy_interrupt",
- phydev) < 0) {
+ if (request_irq(phydev->irq, phy_interrupt,
+ IRQF_SHARED,
+ "phy_interrupt",
+ phydev) < 0) {
pr_warn("%s: Can't get IRQ %d (PHY)\n",
phydev->mdio.bus->name, phydev->irq);
phydev->irq = PHY_POLL;
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
#include <linux/filter.h>
#include <linux/if_team.h>
+static rx_handler_result_t lb_receive(struct team *team, struct team_port *port,
+ struct sk_buff *skb)
+{
+ if (unlikely(skb->protocol == htons(ETH_P_SLOW))) {
+ /* LACPDU packets should go to exact delivery */
+ const unsigned char *dest = eth_hdr(skb)->h_dest;
+
+ if (is_link_local_ether_addr(dest) && dest[5] == 0x02)
+ return RX_HANDLER_EXACT;
+ }
+ return RX_HANDLER_ANOTHER;
+}
+
struct lb_priv;
typedef struct team_port *lb_select_tx_port_func_t(struct team *,
.port_enter = lb_port_enter,
.port_leave = lb_port_leave,
.port_disabled = lb_port_disabled,
+ .receive = lb_receive,
.transmit = lb_transmit,
};
if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC)))
goto drop;
- if (skb->sk && sk_fullsock(skb->sk)) {
- sock_tx_timestamp(skb->sk, skb->sk->sk_tsflags,
- &skb_shinfo(skb)->tx_flags);
- sw_tx_timestamp(skb);
- }
+ skb_tx_timestamp(skb);
/* Orphan the skb - required as we might hang on to it
* for indefinite time.
struct net_device *netdev;
const eth_addr_t bcast_addr = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF };
int result = 0;
+ int rv = -EIO;
dev_dbg(dev,
"Kawasaki Device Probe (Device number:%d): 0x%4.4x:0x%4.4x:0x%4.4x\n",
kaweth = netdev_priv(netdev);
kaweth->dev = udev;
kaweth->net = netdev;
+ kaweth->intf = intf;
spin_lock_init(&kaweth->device_lock);
init_waitqueue_head(&kaweth->term_wait);
/* Download the firmware */
dev_info(dev, "Downloading firmware...\n");
kaweth->firmware_buf = (__u8 *)__get_free_page(GFP_KERNEL);
+ if (!kaweth->firmware_buf) {
+ rv = -ENOMEM;
+ goto err_free_netdev;
+ }
if ((result = kaweth_download_firmware(kaweth,
"kaweth/new_code.bin",
100,
dev_dbg(dev, "Initializing net device.\n");
- kaweth->intf = intf;
-
kaweth->tx_urb = usb_alloc_urb(0, GFP_KERNEL);
if (!kaweth->tx_urb)
goto err_free_netdev;
err_free_netdev:
free_netdev(netdev);
- return -EIO;
+ return rv;
}
/****************************************************************
#define NETNEXT_VERSION "08"
/* Information for net */
-#define NET_VERSION "5"
+#define NET_VERSION "6"
#define DRIVER_VERSION "v1." NETNEXT_VERSION "." NET_VERSION
#define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
}
}
+static inline void r8152_mmd_indirect(struct r8152 *tp, u16 dev, u16 reg)
+{
+ ocp_reg_write(tp, OCP_EEE_AR, FUN_ADDR | dev);
+ ocp_reg_write(tp, OCP_EEE_DATA, reg);
+ ocp_reg_write(tp, OCP_EEE_AR, FUN_DATA | dev);
+}
+
+static u16 r8152_mmd_read(struct r8152 *tp, u16 dev, u16 reg)
+{
+ u16 data;
+
+ r8152_mmd_indirect(tp, dev, reg);
+ data = ocp_reg_read(tp, OCP_EEE_DATA);
+ ocp_reg_write(tp, OCP_EEE_AR, 0x0000);
+
+ return data;
+}
+
+static void r8152_mmd_write(struct r8152 *tp, u16 dev, u16 reg, u16 data)
+{
+ r8152_mmd_indirect(tp, dev, reg);
+ ocp_reg_write(tp, OCP_EEE_DATA, data);
+ ocp_reg_write(tp, OCP_EEE_AR, 0x0000);
+}
+
+static void r8152_eee_en(struct r8152 *tp, bool enable)
+{
+ u16 config1, config2, config3;
+ u32 ocp_data;
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_EEE_CR);
+ config1 = ocp_reg_read(tp, OCP_EEE_CONFIG1) & ~sd_rise_time_mask;
+ config2 = ocp_reg_read(tp, OCP_EEE_CONFIG2);
+ config3 = ocp_reg_read(tp, OCP_EEE_CONFIG3) & ~fast_snr_mask;
+
+ if (enable) {
+ ocp_data |= EEE_RX_EN | EEE_TX_EN;
+ config1 |= EEE_10_CAP | EEE_NWAY_EN | TX_QUIET_EN | RX_QUIET_EN;
+ config1 |= sd_rise_time(1);
+ config2 |= RG_DACQUIET_EN | RG_LDVQUIET_EN;
+ config3 |= fast_snr(42);
+ } else {
+ ocp_data &= ~(EEE_RX_EN | EEE_TX_EN);
+ config1 &= ~(EEE_10_CAP | EEE_NWAY_EN | TX_QUIET_EN |
+ RX_QUIET_EN);
+ config1 |= sd_rise_time(7);
+ config2 &= ~(RG_DACQUIET_EN | RG_LDVQUIET_EN);
+ config3 |= fast_snr(511);
+ }
+
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_EEE_CR, ocp_data);
+ ocp_reg_write(tp, OCP_EEE_CONFIG1, config1);
+ ocp_reg_write(tp, OCP_EEE_CONFIG2, config2);
+ ocp_reg_write(tp, OCP_EEE_CONFIG3, config3);
+}
+
+static void r8152b_enable_eee(struct r8152 *tp)
+{
+ r8152_eee_en(tp, true);
+ r8152_mmd_write(tp, MDIO_MMD_AN, MDIO_AN_EEE_ADV, MDIO_EEE_100TX);
+}
+
+static void r8152b_enable_fc(struct r8152 *tp)
+{
+ u16 anar;
+
+ anar = r8152_mdio_read(tp, MII_ADVERTISE);
+ anar |= ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM;
+ r8152_mdio_write(tp, MII_ADVERTISE, anar);
+}
+
static void rtl8152_disable(struct r8152 *tp)
{
r8152_aldps_en(tp, false);
static void r8152b_hw_phy_cfg(struct r8152 *tp)
{
- u16 data;
-
- data = r8152_mdio_read(tp, MII_BMCR);
- if (data & BMCR_PDOWN) {
- data &= ~BMCR_PDOWN;
- r8152_mdio_write(tp, MII_BMCR, data);
- }
+ r8152b_enable_eee(tp);
+ r8152_aldps_en(tp, true);
+ r8152b_enable_fc(tp);
set_bit(PHY_RESET, &tp->flags);
}
ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, ocp_data);
}
+static void r8153_aldps_en(struct r8152 *tp, bool enable)
+{
+ u16 data;
+
+ data = ocp_reg_read(tp, OCP_POWER_CFG);
+ if (enable) {
+ data |= EN_ALDPS;
+ ocp_reg_write(tp, OCP_POWER_CFG, data);
+ } else {
+ data &= ~EN_ALDPS;
+ ocp_reg_write(tp, OCP_POWER_CFG, data);
+ msleep(20);
+ }
+}
+
+static void r8153_eee_en(struct r8152 *tp, bool enable)
+{
+ u32 ocp_data;
+ u16 config;
+
+ ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_EEE_CR);
+ config = ocp_reg_read(tp, OCP_EEE_CFG);
+
+ if (enable) {
+ ocp_data |= EEE_RX_EN | EEE_TX_EN;
+ config |= EEE10_EN;
+ } else {
+ ocp_data &= ~(EEE_RX_EN | EEE_TX_EN);
+ config &= ~EEE10_EN;
+ }
+
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_EEE_CR, ocp_data);
+ ocp_reg_write(tp, OCP_EEE_CFG, config);
+}
+
static void r8153_hw_phy_cfg(struct r8152 *tp)
{
u32 ocp_data;
u16 data;
- if (tp->version == RTL_VER_03 || tp->version == RTL_VER_04 ||
- tp->version == RTL_VER_05)
- ocp_reg_write(tp, OCP_ADC_CFG, CKADSEL_L | ADC_EN | EN_EMI_L);
+ /* disable ALDPS before updating the PHY parameters */
+ r8153_aldps_en(tp, false);
- data = r8152_mdio_read(tp, MII_BMCR);
- if (data & BMCR_PDOWN) {
- data &= ~BMCR_PDOWN;
- r8152_mdio_write(tp, MII_BMCR, data);
- }
+ /* disable EEE before updating the PHY parameters */
+ r8153_eee_en(tp, false);
+ ocp_reg_write(tp, OCP_EEE_ADV, 0);
if (tp->version == RTL_VER_03) {
data = ocp_reg_read(tp, OCP_EEE_CFG);
sram_write(tp, SRAM_10M_AMP1, 0x00af);
sram_write(tp, SRAM_10M_AMP2, 0x0208);
+ r8153_eee_en(tp, true);
+ ocp_reg_write(tp, OCP_EEE_ADV, MDIO_EEE_1000T | MDIO_EEE_100TX);
+
+ r8153_aldps_en(tp, true);
+ r8152b_enable_fc(tp);
+
set_bit(PHY_RESET, &tp->flags);
}
ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, ocp_data);
}
-static void r8153_aldps_en(struct r8152 *tp, bool enable)
-{
- u16 data;
-
- data = ocp_reg_read(tp, OCP_POWER_CFG);
- if (enable) {
- data |= EN_ALDPS;
- ocp_reg_write(tp, OCP_POWER_CFG, data);
- } else {
- data &= ~EN_ALDPS;
- ocp_reg_write(tp, OCP_POWER_CFG, data);
- msleep(20);
- }
-}
-
static void rtl8153_disable(struct r8152 *tp)
{
r8153_aldps_en(tp, false);
return res;
}
-static inline void r8152_mmd_indirect(struct r8152 *tp, u16 dev, u16 reg)
-{
- ocp_reg_write(tp, OCP_EEE_AR, FUN_ADDR | dev);
- ocp_reg_write(tp, OCP_EEE_DATA, reg);
- ocp_reg_write(tp, OCP_EEE_AR, FUN_DATA | dev);
-}
-
-static u16 r8152_mmd_read(struct r8152 *tp, u16 dev, u16 reg)
-{
- u16 data;
-
- r8152_mmd_indirect(tp, dev, reg);
- data = ocp_reg_read(tp, OCP_EEE_DATA);
- ocp_reg_write(tp, OCP_EEE_AR, 0x0000);
-
- return data;
-}
-
-static void r8152_mmd_write(struct r8152 *tp, u16 dev, u16 reg, u16 data)
-{
- r8152_mmd_indirect(tp, dev, reg);
- ocp_reg_write(tp, OCP_EEE_DATA, data);
- ocp_reg_write(tp, OCP_EEE_AR, 0x0000);
-}
-
-static void r8152_eee_en(struct r8152 *tp, bool enable)
-{
- u16 config1, config2, config3;
- u32 ocp_data;
-
- ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_EEE_CR);
- config1 = ocp_reg_read(tp, OCP_EEE_CONFIG1) & ~sd_rise_time_mask;
- config2 = ocp_reg_read(tp, OCP_EEE_CONFIG2);
- config3 = ocp_reg_read(tp, OCP_EEE_CONFIG3) & ~fast_snr_mask;
-
- if (enable) {
- ocp_data |= EEE_RX_EN | EEE_TX_EN;
- config1 |= EEE_10_CAP | EEE_NWAY_EN | TX_QUIET_EN | RX_QUIET_EN;
- config1 |= sd_rise_time(1);
- config2 |= RG_DACQUIET_EN | RG_LDVQUIET_EN;
- config3 |= fast_snr(42);
- } else {
- ocp_data &= ~(EEE_RX_EN | EEE_TX_EN);
- config1 &= ~(EEE_10_CAP | EEE_NWAY_EN | TX_QUIET_EN |
- RX_QUIET_EN);
- config1 |= sd_rise_time(7);
- config2 &= ~(RG_DACQUIET_EN | RG_LDVQUIET_EN);
- config3 |= fast_snr(511);
- }
-
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_EEE_CR, ocp_data);
- ocp_reg_write(tp, OCP_EEE_CONFIG1, config1);
- ocp_reg_write(tp, OCP_EEE_CONFIG2, config2);
- ocp_reg_write(tp, OCP_EEE_CONFIG3, config3);
-}
-
-static void r8152b_enable_eee(struct r8152 *tp)
-{
- r8152_eee_en(tp, true);
- r8152_mmd_write(tp, MDIO_MMD_AN, MDIO_AN_EEE_ADV, MDIO_EEE_100TX);
-}
-
-static void r8153_eee_en(struct r8152 *tp, bool enable)
-{
- u32 ocp_data;
- u16 config;
-
- ocp_data = ocp_read_word(tp, MCU_TYPE_PLA, PLA_EEE_CR);
- config = ocp_reg_read(tp, OCP_EEE_CFG);
-
- if (enable) {
- ocp_data |= EEE_RX_EN | EEE_TX_EN;
- config |= EEE10_EN;
- } else {
- ocp_data &= ~(EEE_RX_EN | EEE_TX_EN);
- config &= ~EEE10_EN;
- }
-
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_EEE_CR, ocp_data);
- ocp_reg_write(tp, OCP_EEE_CFG, config);
-}
-
-static void r8153_enable_eee(struct r8152 *tp)
-{
- r8153_eee_en(tp, true);
- ocp_reg_write(tp, OCP_EEE_ADV, MDIO_EEE_1000T | MDIO_EEE_100TX);
-}
-
-static void r8152b_enable_fc(struct r8152 *tp)
-{
- u16 anar;
-
- anar = r8152_mdio_read(tp, MII_ADVERTISE);
- anar |= ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM;
- r8152_mdio_write(tp, MII_ADVERTISE, anar);
-}
-
static void rtl_tally_reset(struct r8152 *tp)
{
u32 ocp_data;
static void r8152b_init(struct r8152 *tp)
{
u32 ocp_data;
+ u16 data;
if (test_bit(RTL8152_UNPLUG, &tp->flags))
return;
+ data = r8152_mdio_read(tp, MII_BMCR);
+ if (data & BMCR_PDOWN) {
+ data &= ~BMCR_PDOWN;
+ r8152_mdio_write(tp, MII_BMCR, data);
+ }
+
r8152_aldps_en(tp, false);
if (tp->version == RTL_VER_01) {
SPDWN_RXDV_MSK | SPDWN_LINKCHG_MSK;
ocp_write_word(tp, MCU_TYPE_PLA, PLA_GPHY_INTR_IMR, ocp_data);
- r8152b_enable_eee(tp);
- r8152_aldps_en(tp, true);
- r8152b_enable_fc(tp);
rtl_tally_reset(tp);
/* enable rx aggregation */
static void r8153_init(struct r8152 *tp)
{
u32 ocp_data;
+ u16 data;
int i;
if (test_bit(RTL8152_UNPLUG, &tp->flags))
return;
- r8153_aldps_en(tp, false);
r8153_u1u2en(tp, false);
for (i = 0; i < 500; i++) {
msleep(20);
}
+ if (tp->version == RTL_VER_03 || tp->version == RTL_VER_04 ||
+ tp->version == RTL_VER_05)
+ ocp_reg_write(tp, OCP_ADC_CFG, CKADSEL_L | ADC_EN | EN_EMI_L);
+
+ data = r8152_mdio_read(tp, MII_BMCR);
+ if (data & BMCR_PDOWN) {
+ data &= ~BMCR_PDOWN;
+ r8152_mdio_write(tp, MII_BMCR, data);
+ }
+
+ for (i = 0; i < 500; i++) {
+ ocp_data = ocp_reg_read(tp, OCP_PHY_STATUS) & PHY_STAT_MASK;
+ if (ocp_data == PHY_STAT_LAN_ON)
+ break;
+ msleep(20);
+ }
+
usb_disable_lpm(tp->udev);
r8153_u2p3en(tp, false);
ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, 0);
ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL4, 0);
- r8153_enable_eee(tp);
- r8153_aldps_en(tp, true);
- r8152b_enable_fc(tp);
rtl_tally_reset(tp);
r8153_u2p3en(tp, true);
}
{
struct Vmxnet3_TxDataDesc *tdd;
- tdd = tq->data_ring.base + tq->tx_ring.next2fill;
+ tdd = (struct Vmxnet3_TxDataDesc *)((u8 *)tq->data_ring.base +
+ tq->tx_ring.next2fill *
+ tq->txdata_desc_size);
memcpy(tdd->data, skb->data, ctx->copy_size);
netdev_dbg(adapter->netdev,
/*
* Version numbers
*/
-#define VMXNET3_DRIVER_VERSION_STRING "1.4.9.0-k"
+#define VMXNET3_DRIVER_VERSION_STRING "1.4.a.0-k"
/* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */
-#define VMXNET3_DRIVER_VERSION_NUM 0x01040900
+#define VMXNET3_DRIVER_VERSION_NUM 0x01040a00
#if defined(CONFIG_PCI_MSI)
/* RSS only makes sense if MSI-X is supported. */
fl4.flowi4_mark = skb->mark;
fl4.flowi4_proto = IPPROTO_UDP;
fl4.daddr = daddr;
- fl4.saddr = vxlan->cfg.saddr.sin.sin_addr.s_addr;
+ fl4.saddr = *saddr;
rt = ip_route_output_key(vxlan->net, &fl4);
if (!IS_ERR(rt)) {
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = oif;
fl6.daddr = *daddr;
- fl6.saddr = vxlan->cfg.saddr.sin6.sin6_addr;
+ fl6.saddr = *saddr;
fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tos), label);
fl6.flowi6_mark = skb->mark;
fl6.flowi6_proto = IPPROTO_UDP;
struct rtable *rt = NULL;
const struct iphdr *old_iph;
union vxlan_addr *dst;
- union vxlan_addr remote_ip;
+ union vxlan_addr remote_ip, local_ip;
+ union vxlan_addr *src;
struct vxlan_metadata _md;
struct vxlan_metadata *md = &_md;
__be16 src_port = 0, dst_port;
dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port;
vni = rdst->remote_vni;
dst = &rdst->remote_ip;
+ src = &vxlan->cfg.saddr;
dst_cache = &rdst->dst_cache;
} else {
if (!info) {
dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port;
vni = vxlan_tun_id_to_vni(info->key.tun_id);
remote_ip.sa.sa_family = ip_tunnel_info_af(info);
- if (remote_ip.sa.sa_family == AF_INET)
+ if (remote_ip.sa.sa_family == AF_INET) {
remote_ip.sin.sin_addr.s_addr = info->key.u.ipv4.dst;
- else
+ local_ip.sin.sin_addr.s_addr = info->key.u.ipv4.src;
+ } else {
remote_ip.sin6.sin6_addr = info->key.u.ipv6.dst;
+ local_ip.sin6.sin6_addr = info->key.u.ipv6.src;
+ }
dst = &remote_ip;
+ src = &local_ip;
dst_cache = &info->dst_cache;
}
}
if (dst->sa.sa_family == AF_INET) {
- __be32 saddr;
-
if (!vxlan->vn4_sock)
goto drop;
sk = vxlan->vn4_sock->sock->sk;
rt = vxlan_get_route(vxlan, skb,
rdst ? rdst->remote_ifindex : 0, tos,
- dst->sin.sin_addr.s_addr, &saddr,
+ dst->sin.sin_addr.s_addr,
+ &src->sin.sin_addr.s_addr,
dst_cache, info);
if (IS_ERR(rt)) {
netdev_dbg(dev, "no route to %pI4\n",
}
/* Bypass encapsulation if the destination is local */
- if (rt->rt_flags & RTCF_LOCAL &&
+ if (!info && rt->rt_flags & RTCF_LOCAL &&
!(rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) {
struct vxlan_dev *dst_vxlan;
if (err < 0)
goto xmit_tx_error;
- udp_tunnel_xmit_skb(rt, sk, skb, saddr,
+ udp_tunnel_xmit_skb(rt, sk, skb, src->sin.sin_addr.s_addr,
dst->sin.sin_addr.s_addr, tos, ttl, df,
src_port, dst_port, xnet, !udp_sum);
#if IS_ENABLED(CONFIG_IPV6)
} else {
struct dst_entry *ndst;
- struct in6_addr saddr;
u32 rt6i_flags;
if (!vxlan->vn6_sock)
ndst = vxlan6_get_route(vxlan, skb,
rdst ? rdst->remote_ifindex : 0, tos,
- label, &dst->sin6.sin6_addr, &saddr,
+ label, &dst->sin6.sin6_addr,
+ &src->sin6.sin6_addr,
dst_cache, info);
if (IS_ERR(ndst)) {
netdev_dbg(dev, "no route to %pI6\n",
/* Bypass encapsulation if the destination is local */
rt6i_flags = ((struct rt6_info *)ndst)->rt6i_flags;
- if (rt6i_flags & RTF_LOCAL &&
+ if (!info && rt6i_flags & RTF_LOCAL &&
!(rt6i_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) {
struct vxlan_dev *dst_vxlan;
return;
}
udp_tunnel6_xmit_skb(ndst, sk, skb, dev,
- &saddr, &dst->sin6.sin6_addr, tos, ttl,
+ &src->sin6.sin6_addr,
+ &dst->sin6.sin6_addr, tos, ttl,
label, src_port, dst_port, !udp_sum);
#endif
}
struct net_device *lowerdev = NULL;
if (conf->flags & VXLAN_F_GPE) {
- if (conf->flags & ~VXLAN_F_ALLOWED_GPE)
- return -EINVAL;
/* For now, allow GPE only together with COLLECT_METADATA.
* This can be relaxed later; in such case, the other side
* of the PtP link will have to be provided.
*/
- if (!(conf->flags & VXLAN_F_COLLECT_METADATA))
+ if ((conf->flags & ~VXLAN_F_ALLOWED_GPE) ||
+ !(conf->flags & VXLAN_F_COLLECT_METADATA)) {
+ pr_info("unsupported combination of extensions\n");
return -EINVAL;
+ }
vxlan_raw_setup(dev);
} else {
dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
needed_headroom = lowerdev->hard_header_len;
+ } else if (vxlan_addr_multicast(&dst->remote_ip)) {
+ pr_info("multicast destination requires interface to be specified\n");
+ return -EINVAL;
}
if (conf->mtu) {
tmp->cfg.saddr.sa.sa_family == AF_INET6) == use_ipv6 &&
tmp->cfg.dst_port == vxlan->cfg.dst_port &&
(tmp->flags & VXLAN_F_RCV_FLAGS) ==
- (vxlan->flags & VXLAN_F_RCV_FLAGS))
- return -EEXIST;
+ (vxlan->flags & VXLAN_F_RCV_FLAGS)) {
+ pr_info("duplicate VNI %u\n", be32_to_cpu(conf->vni));
+ return -EEXIST;
+ }
}
dev->ethtool_ops = &vxlan_ethtool_ops;
struct nlattr *tb[], struct nlattr *data[])
{
struct vxlan_config conf;
- int err;
memset(&conf, 0, sizeof(conf));
if (tb[IFLA_MTU])
conf.mtu = nla_get_u32(tb[IFLA_MTU]);
- err = vxlan_dev_configure(src_net, dev, &conf);
- switch (err) {
- case -ENODEV:
- pr_info("ifindex %d does not exist\n", conf.remote_ifindex);
- break;
-
- case -EPERM:
- pr_info("IPv6 is disabled via sysctl\n");
- break;
-
- case -EEXIST:
- pr_info("duplicate VNI %u\n", be32_to_cpu(conf.vni));
- break;
-
- case -EINVAL:
- pr_info("unsupported combination of extensions\n");
- break;
- }
-
- return err;
+ return vxlan_dev_configure(src_net, dev, &conf);
}
static void vxlan_dellink(struct net_device *dev, struct list_head *head)
static int ath10k_htt_rx_handle_amsdu(struct ath10k_htt *htt)
{
struct ath10k *ar = htt->ar;
- static struct ieee80211_rx_status rx_status;
+ struct ieee80211_rx_status *rx_status = &htt->rx_status;
struct sk_buff_head amsdu;
int ret;
return ret;
}
- ath10k_htt_rx_h_ppdu(ar, &amsdu, &rx_status, 0xffff);
+ ath10k_htt_rx_h_ppdu(ar, &amsdu, rx_status, 0xffff);
ath10k_htt_rx_h_unchain(ar, &amsdu, ret > 0);
- ath10k_htt_rx_h_filter(ar, &amsdu, &rx_status);
- ath10k_htt_rx_h_mpdu(ar, &amsdu, &rx_status);
- ath10k_htt_rx_h_deliver(ar, &amsdu, &rx_status);
+ ath10k_htt_rx_h_filter(ar, &amsdu, rx_status);
+ ath10k_htt_rx_h_mpdu(ar, &amsdu, rx_status);
+ ath10k_htt_rx_h_deliver(ar, &amsdu, rx_status);
return 0;
}
pci_hard_reset = ath10k_pci_qca988x_chip_reset;
break;
case QCA9887_1_0_DEVICE_ID:
- dev_warn(&pdev->dev, "QCA9887 support is still experimental, there are likely bugs. You have been warned.\n");
hw_rev = ATH10K_HW_QCA9887;
pci_ps = false;
pci_soft_reset = ath10k_pci_warm_reset;
return -EINVAL;
}
+ ath9k_gpio_cap_init(ah);
+
if (AR_SREV_9485(ah) ||
AR_SREV_9285(ah) ||
AR_SREV_9330(ah) ||
else
pCap->hw_caps &= ~ATH9K_HW_CAP_HT;
- ath9k_gpio_cap_init(ah);
-
if (AR_SREV_9160_10_OR_LATER(ah) || AR_SREV_9100(ah))
pCap->rts_aggr_limit = ATH_AMPDU_LIMIT_MAX;
else
if (!ath_complete_reset(sc, false))
ah->reset_power_on = false;
- if (ah->led_pin >= 0)
+ if (ah->led_pin >= 0) {
ath9k_hw_set_gpio(ah, ah->led_pin,
(ah->config.led_active_high) ? 1 : 0);
+ ath9k_hw_gpio_request_out(ah, ah->led_pin, NULL,
+ AR_GPIO_OUTPUT_MUX_AS_OUTPUT);
+ }
/*
* Reset key cache to sane defaults (all entries cleared) instead of
spin_lock_bh(&sc->sc_pcu_lock);
- if (ah->led_pin >= 0)
+ if (ah->led_pin >= 0) {
ath9k_hw_set_gpio(ah, ah->led_pin,
(ah->config.led_active_high) ? 0 : 1);
+ ath9k_hw_gpio_request_in(ah, ah->led_pin, NULL);
+ }
ath_prepare_reset(sc);
bool changed = (iter_data.primary_sta != ctx->primary_sta);
if (iter_data.primary_sta) {
+ iter_data.primary_beacon_vif = iter_data.primary_sta;
iter_data.beacons = true;
ath9k_set_assoc_state(sc, iter_data.primary_sta,
changed);
struct ath_common *common = ath9k_hw_common(sc->sc_ah);
int ret = 0;
- if (old_state == IEEE80211_STA_AUTH &&
- new_state == IEEE80211_STA_ASSOC) {
+ if (old_state == IEEE80211_STA_NOTEXIST &&
+ new_state == IEEE80211_STA_NONE) {
ret = ath9k_sta_add(hw, vif, sta);
ath_dbg(common, CONFIG,
"Add station: %pM\n", sta->addr);
- } else if (old_state == IEEE80211_STA_ASSOC &&
- new_state == IEEE80211_STA_AUTH) {
+ } else if (old_state == IEEE80211_STA_NONE &&
+ new_state == IEEE80211_STA_NOTEXIST) {
ret = ath9k_sta_remove(hw, vif, sta);
ath_dbg(common, CONFIG,
"Remove station: %pM\n", sta->addr);
(u8 *)&settings->beacon.head[ie_offset],
settings->beacon.head_len - ie_offset,
WLAN_EID_SSID);
- if (!ssid_ie)
+ if (!ssid_ie || ssid_ie->len > IEEE80211_MAX_SSID_LEN)
return -EINVAL;
memcpy(ssid_le.SSID, ssid_ie->data, ssid_ie->len);
ifevent->action, ifevent->flags, ifevent->ifidx,
ifevent->bsscfgidx);
- mutex_lock(&event->vif_event_lock);
+ spin_lock(&event->vif_event_lock);
event->action = ifevent->action;
vif = event->vif;
case BRCMF_E_IF_ADD:
/* waiting process may have timed out */
if (!cfg->vif_event.vif) {
- mutex_unlock(&event->vif_event_lock);
+ spin_unlock(&event->vif_event_lock);
return -EBADF;
}
ifp->ndev->ieee80211_ptr = &vif->wdev;
SET_NETDEV_DEV(ifp->ndev, wiphy_dev(cfg->wiphy));
}
- mutex_unlock(&event->vif_event_lock);
+ spin_unlock(&event->vif_event_lock);
wake_up(&event->vif_wq);
return 0;
case BRCMF_E_IF_DEL:
- mutex_unlock(&event->vif_event_lock);
+ spin_unlock(&event->vif_event_lock);
/* event may not be upon user request */
if (brcmf_cfg80211_vif_event_armed(cfg))
wake_up(&event->vif_wq);
return 0;
case BRCMF_E_IF_CHANGE:
- mutex_unlock(&event->vif_event_lock);
+ spin_unlock(&event->vif_event_lock);
wake_up(&event->vif_wq);
return 0;
default:
- mutex_unlock(&event->vif_event_lock);
+ spin_unlock(&event->vif_event_lock);
break;
}
return -EINVAL;
static void init_vif_event(struct brcmf_cfg80211_vif_event *event)
{
init_waitqueue_head(&event->vif_wq);
- mutex_init(&event->vif_event_lock);
+ spin_lock_init(&event->vif_event_lock);
}
static s32 brcmf_dongle_roam(struct brcmf_if *ifp)
{
u8 evt_action;
- mutex_lock(&event->vif_event_lock);
+ spin_lock(&event->vif_event_lock);
evt_action = event->action;
- mutex_unlock(&event->vif_event_lock);
+ spin_unlock(&event->vif_event_lock);
return evt_action == action;
}
{
struct brcmf_cfg80211_vif_event *event = &cfg->vif_event;
- mutex_lock(&event->vif_event_lock);
+ spin_lock(&event->vif_event_lock);
event->vif = vif;
event->action = 0;
- mutex_unlock(&event->vif_event_lock);
+ spin_unlock(&event->vif_event_lock);
}
bool brcmf_cfg80211_vif_event_armed(struct brcmf_cfg80211_info *cfg)
struct brcmf_cfg80211_vif_event *event = &cfg->vif_event;
bool armed;
- mutex_lock(&event->vif_event_lock);
+ spin_lock(&event->vif_event_lock);
armed = event->vif != NULL;
- mutex_unlock(&event->vif_event_lock);
+ spin_unlock(&event->vif_event_lock);
return armed;
}
*/
struct brcmf_cfg80211_vif_event {
wait_queue_head_t vif_wq;
- struct mutex vif_event_lock;
+ spinlock_t vif_event_lock;
u8 action;
struct brcmf_cfg80211_vif *vif;
};
* serious troublesome side effects. The p2p module will clean
* up the ifp if needed.
*/
- brcmf_p2p_ifp_removed(ifp);
+ brcmf_p2p_ifp_removed(ifp, rtnl_locked);
kfree(ifp);
}
}
return err;
}
-void brcmf_p2p_ifp_removed(struct brcmf_if *ifp)
+void brcmf_p2p_ifp_removed(struct brcmf_if *ifp, bool rtnl_locked)
{
struct brcmf_cfg80211_info *cfg;
struct brcmf_cfg80211_vif *vif;
vif = ifp->vif;
cfg = wdev_to_cfg(&vif->wdev);
cfg->p2p.bss_idx[P2PAPI_BSSCFG_DEVICE].vif = NULL;
- rtnl_lock();
+ if (!rtnl_locked)
+ rtnl_lock();
cfg80211_unregister_wdev(&vif->wdev);
- rtnl_unlock();
+ if (!rtnl_locked)
+ rtnl_unlock();
brcmf_free_vif(vif);
}
int brcmf_p2p_del_vif(struct wiphy *wiphy, struct wireless_dev *wdev);
int brcmf_p2p_ifchange(struct brcmf_cfg80211_info *cfg,
enum brcmf_fil_p2p_if_types if_type);
-void brcmf_p2p_ifp_removed(struct brcmf_if *ifp);
+void brcmf_p2p_ifp_removed(struct brcmf_if *ifp, bool rtnl_locked);
int brcmf_p2p_start_device(struct wiphy *wiphy, struct wireless_dev *wdev);
void brcmf_p2p_stop_device(struct wiphy *wiphy, struct wireless_dev *wdev);
int brcmf_p2p_scan_prep(struct wiphy *wiphy,
}
mvm->fw_dbg_conf = conf_id;
- return ret;
+
+ return 0;
}
{
u32 trig_vif = le32_to_cpu(trig->vif_type);
- return trig_vif == IWL_FW_DBG_CONF_VIF_ANY || vif->type == trig_vif;
+ return trig_vif == IWL_FW_DBG_CONF_VIF_ANY ||
+ ieee80211_vif_type_p2p(vif) == trig_vif;
}
static inline bool
hw->wiphy->features |= NL80211_FEATURE_P2P_GO_CTWIN |
NL80211_FEATURE_LOW_PRIORITY_SCAN |
NL80211_FEATURE_P2P_GO_OPPPS |
+ NL80211_FEATURE_AP_MODE_CHAN_WIDTH_CHANGE |
NL80211_FEATURE_DYNAMIC_SMPS |
NL80211_FEATURE_STATIC_SMPS |
NL80211_FEATURE_SUPPORTS_WMM_ADMISSION;
static inline struct iwl_mvm_vif *
iwl_mvm_vif_from_mac80211(struct ieee80211_vif *vif)
{
+ if (!vif)
+ return NULL;
return (void *)vif->drv_priv;
}
int hdrlen = ieee80211_hdrlen(hdr->frame_control);
int queue;
+ /* IWL_MVM_OFFCHANNEL_QUEUE is used for ROC packets that can be used
+ * in 2 different types of vifs, P2P & STATION. P2P uses the offchannel
+ * queue. STATION (HS2.0) uses the auxiliary context of the FW,
+ * and hence needs to be sent on the aux queue
+ */
+ if (IEEE80211_SKB_CB(skb)->hw_queue == IWL_MVM_OFFCHANNEL_QUEUE &&
+ skb_info->control.vif->type == NL80211_IFTYPE_STATION)
+ IEEE80211_SKB_CB(skb)->hw_queue = mvm->aux_queue;
+
memcpy(&info, skb->cb, sizeof(info));
if (WARN_ON_ONCE(info.flags & IEEE80211_TX_CTL_AMPDU))
/* This holds the amsdu headers length */
skb_info->driver_data[0] = (void *)(uintptr_t)0;
- /*
- * IWL_MVM_OFFCHANNEL_QUEUE is used for ROC packets that can be used
- * in 2 different types of vifs, P2P & STATION. P2P uses the offchannel
- * queue. STATION (HS2.0) uses the auxiliary context of the FW,
- * and hence needs to be sent on the aux queue
- */
- if (IEEE80211_SKB_CB(skb)->hw_queue == IWL_MVM_OFFCHANNEL_QUEUE &&
- info.control.vif->type == NL80211_IFTYPE_STATION)
- IEEE80211_SKB_CB(skb)->hw_queue = mvm->aux_queue;
-
queue = info.hw_queue;
/*
do {
/* Check if AMSDU can accommodate this MSDU */
- if (skb_tailroom(skb_aggr) < (skb_src->len + LLC_SNAP_LEN))
+ if ((skb_aggr->len + skb_src->len + LLC_SNAP_LEN) >
+ adapter->tx_buf_size)
break;
skb_src = skb_dequeue(&pra_list->skb_head);
mutex_unlock(&wl->mutex);
}
-static u32 wlcore_op_get_expected_throughput(struct ieee80211_sta *sta)
+static u32 wlcore_op_get_expected_throughput(struct ieee80211_hw *hw,
+ struct ieee80211_sta *sta)
{
struct wl1271_station *wl_sta = (struct wl1271_station *)sta->drv_priv;
- struct wl1271 *wl = wl_sta->wl;
+ struct wl1271 *wl = hw->priv;
u8 hlid = wl_sta->hlid;
/* return in units of Kbps */
be->dev = dev;
dev_set_drvdata(&dev->dev, be);
+ be->state = XenbusStateInitialising;
+ err = xenbus_switch_state(dev, XenbusStateInitialising);
+ if (err)
+ goto fail;
+
sg = 1;
do {
be->hotplug_script = script;
- err = xenbus_switch_state(dev, XenbusStateInitWait);
- if (err)
- goto fail;
-
- be->state = XenbusStateInitWait;
/* This kicks hotplug scripts, so do it immediately. */
err = backend_create_xenvif(be);
/* Handle backend state transitions:
*
- * The backend state starts in InitWait and the following transitions are
+ * The backend state starts in Initialising and the following transitions are
* allowed.
*
- * InitWait -> Connected
- *
- * ^ \ |
- * | \ |
- * | \ |
- * | \ |
- * | \ |
- * | \ |
- * | V V
+ * Initialising -> InitWait -> Connected
+ * \
+ * \ ^ \ |
+ * \ | \ |
+ * \ | \ |
+ * \ | \ |
+ * \ | \ |
+ * \ | \ |
+ * V | V V
*
- * Closed <-> Closing
+ * Closed <-> Closing
*
* The state argument specifies the eventual state of the backend and the
* function transitions to that state via the shortest path.
{
while (be->state != state) {
switch (be->state) {
+ case XenbusStateInitialising:
+ switch (state) {
+ case XenbusStateInitWait:
+ case XenbusStateConnected:
+ case XenbusStateClosing:
+ backend_switch_state(be, XenbusStateInitWait);
+ break;
+ case XenbusStateClosed:
+ backend_switch_state(be, XenbusStateClosed);
+ break;
+ default:
+ BUG();
+ }
+ break;
case XenbusStateClosed:
switch (state) {
case XenbusStateInitWait:
}
}
set_capacity(btt->btt_disk, btt->nlba * btt->sector_size >> 9);
+ btt->nd_btt->size = btt->nlba * (u64)btt->sector_size;
revalidate_disk(btt->btt_disk);
return 0;
}
static DEVICE_ATTR_RW(namespace);
+static ssize_t size_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct nd_btt *nd_btt = to_nd_btt(dev);
+ ssize_t rc;
+
+ device_lock(dev);
+ if (dev->driver)
+ rc = sprintf(buf, "%llu\n", nd_btt->size);
+ else {
+ /* no size to convey if the btt instance is disabled */
+ rc = -ENXIO;
+ }
+ device_unlock(dev);
+
+ return rc;
+}
+static DEVICE_ATTR_RO(size);
+
static struct attribute *nd_btt_attributes[] = {
&dev_attr_sector_size.attr,
&dev_attr_namespace.attr,
&dev_attr_uuid.attr,
+ &dev_attr_size.attr,
NULL,
};
return -ENXIO;
nd_desc = nvdimm_bus->nd_desc;
+ /*
+ * if ndctl does not exist, it's PMEM_LEGACY and
+ * we want to just pretend everything is handled.
+ */
if (!nd_desc->ndctl)
- return -ENXIO;
+ return len;
memset(&ars_cap, 0, sizeof(ars_cap));
ars_cap.address = phys;
struct nd_namespace_common *ndns;
struct btt *btt;
unsigned long lbasize;
+ u64 size;
u8 *uuid;
int id;
};
config NVME_RDMA
tristate "NVM Express over Fabrics RDMA host driver"
- depends on INFINIBAND
- depends on BLK_DEV_NVME
+ depends on INFINIBAND && BLOCK
+ select NVME_CORE
select NVME_FABRICS
select SG_POOL
help
bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
enum nvme_ctrl_state new_state)
{
- enum nvme_ctrl_state old_state = ctrl->state;
+ enum nvme_ctrl_state old_state;
bool changed = false;
spin_lock_irq(&ctrl->lock);
+
+ old_state = ctrl->state;
switch (new_state) {
case NVME_CTRL_LIVE:
switch (old_state) {
default:
break;
}
- spin_unlock_irq(&ctrl->lock);
if (changed)
ctrl->state = new_state;
+ spin_unlock_irq(&ctrl->lock);
+
return changed;
}
EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0,
NVME_QID_ANY, 0, 0);
- if (ret >= 0)
+ if (ret >= 0 && result)
*result = le32_to_cpu(cqe.result);
return ret;
}
ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0,
NVME_QID_ANY, 0, 0);
- if (ret >= 0)
+ if (ret >= 0 && result)
*result = le32_to_cpu(cqe.result);
return ret;
}
mutex_lock(&nvmf_hosts_mutex);
host = __nvmf_host_find(hostnqn);
- if (host)
+ if (host) {
+ kref_get(&host->ref);
goto out_unlock;
+ }
host = kmalloc(sizeof(*host), GFP_KERNEL);
if (!host)
kref_init(&host->ref);
memcpy(host->nqn, hostnqn, NVMF_NQN_SIZE);
- uuid_le_gen(&host->id);
+ uuid_be_gen(&host->id);
list_add_tail(&host->list, &nvmf_hosts);
out_unlock:
return NULL;
kref_init(&host->ref);
- uuid_le_gen(&host->id);
+ uuid_be_gen(&host->id);
snprintf(host->nqn, NVMF_NQN_SIZE,
- "nqn.2014-08.org.nvmexpress:NVMf:uuid:%pUl", &host->id);
+ "nqn.2014-08.org.nvmexpress:NVMf:uuid:%pUb", &host->id);
mutex_lock(&nvmf_hosts_mutex);
list_add_tail(&host->list, &nvmf_hosts);
cmd.connect.opcode = nvme_fabrics_command;
cmd.connect.fctype = nvme_fabrics_type_connect;
cmd.connect.qid = 0;
- cmd.connect.sqsize = cpu_to_le16(ctrl->sqsize);
+
+ /*
+ * fabrics spec sets a minimum of depth 32 for admin queue,
+ * so set the queue with this depth always until
+ * justification otherwise.
+ */
+ cmd.connect.sqsize = cpu_to_le16(NVMF_AQ_DEPTH - 1);
+
/*
* Set keep-alive timeout in seconds granularity (ms * 1000)
* and add a grace period for controller kato enforcement
if (!data)
return -ENOMEM;
- memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_le));
+ memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_be));
data->cntlid = cpu_to_le16(0xffff);
strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE);
strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE);
if (!data)
return -ENOMEM;
- memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_le));
+ memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_be));
data->cntlid = cpu_to_le16(ctrl->cntlid);
strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE);
strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE);
struct kref ref;
struct list_head list;
char nqn[NVMF_NQN_SIZE];
- uuid_le id;
+ uuid_be id;
};
/**
reinit_completion(&dev->ioq_wait);
retry:
timeout = ADMIN_TIMEOUT;
- for (; i > 0; i--) {
- struct nvme_queue *nvmeq = dev->queues[i];
-
- if (!pass)
- nvme_suspend_queue(nvmeq);
- if (nvme_delete_queue(nvmeq, opcode))
+ for (; i > 0; i--, sent++)
+ if (nvme_delete_queue(dev->queues[i], opcode))
break;
- ++sent;
- }
+
while (sent--) {
timeout = wait_for_completion_io_timeout(&dev->ioq_wait, timeout);
if (timeout == 0)
nvme_stop_queues(&dev->ctrl);
csts = readl(dev->bar + NVME_REG_CSTS);
}
+
+ for (i = dev->queue_count - 1; i > 0; i--)
+ nvme_suspend_queue(dev->queues[i]);
+
if (csts & NVME_CSTS_CFS || !(csts & NVME_CSTS_RDY)) {
- for (i = dev->queue_count - 1; i >= 0; i--) {
- struct nvme_queue *nvmeq = dev->queues[i];
- nvme_suspend_queue(nvmeq);
- }
+ /* A device might become IO incapable very soon during
+ * probe, before the admin queue is configured. Thus,
+ * queue_count can be 0 here.
+ */
+ if (dev->queue_count)
+ nvme_suspend_queue(dev->queues[0]);
} else {
nvme_disable_io_queues(dev);
nvme_disable_admin_queue(dev, shutdown);
.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
{ PCI_DEVICE(0x1c58, 0x0003), /* HGST adapter */
.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
+ { PCI_DEVICE(0x1c5f, 0x0540), /* Memblaze Pblaze4 adapter */
+ .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
{ 0, }
* more details.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include <linux/delay.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/err.h>
#include <linux/string.h>
-#include <linux/jiffies.h>
#include <linux/atomic.h>
#include <linux/blk-mq.h>
#include <linux/types.h>
#include <linux/mutex.h>
#include <linux/scatterlist.h>
#include <linux/nvme.h>
-#include <linux/t10-pi.h>
#include <asm/unaligned.h>
#include <rdma/ib_verbs.h>
#define NVME_RDMA_MAX_INLINE_SEGMENTS 1
-#define NVME_RDMA_MAX_PAGES_PER_MR 512
-
-#define NVME_RDMA_DEF_RECONNECT_DELAY 20
-
/*
* We handle AEN commands ourselves and don't even let the
* block layer know about them.
u32 num_sge;
int nents;
bool inline_data;
- bool need_inval;
struct ib_reg_wr reg_wr;
struct ib_cqe reg_cqe;
struct nvme_rdma_queue *queue;
enum nvme_rdma_queue_flags {
NVME_RDMA_Q_CONNECTED = (1 << 0),
+ NVME_RDMA_IB_QUEUE_ALLOCATED = (1 << 1),
+ NVME_RDMA_Q_DELETING = (1 << 2),
};
struct nvme_rdma_queue {
static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
struct rdma_cm_event *event);
static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc);
-static int __nvme_rdma_del_ctrl(struct nvme_rdma_ctrl *ctrl);
/* XXX: really should move to a generic header sooner or later.. */
static inline void put_unaligned_le24(u32 val, u8 *p)
struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
int ret = 0;
- if (!req->need_inval)
+ if (!req->mr->need_inval)
goto out;
ib_dereg_mr(req->mr);
if (IS_ERR(req->mr)) {
ret = PTR_ERR(req->mr);
req->mr = NULL;
+ goto out;
}
- req->need_inval = false;
+ req->mr->need_inval = false;
out:
return ret;
static void nvme_rdma_destroy_queue_ib(struct nvme_rdma_queue *queue)
{
- struct nvme_rdma_device *dev = queue->device;
- struct ib_device *ibdev = dev->dev;
+ struct nvme_rdma_device *dev;
+ struct ib_device *ibdev;
+
+ if (!test_and_clear_bit(NVME_RDMA_IB_QUEUE_ALLOCATED, &queue->flags))
+ return;
+ dev = queue->device;
+ ibdev = dev->dev;
rdma_destroy_qp(queue->cm_id);
ib_free_cq(queue->ib_cq);
ret = -ENOMEM;
goto out_destroy_qp;
}
+ set_bit(NVME_RDMA_IB_QUEUE_ALLOCATED, &queue->flags);
return 0;
goto out_destroy_cm_id;
}
+ clear_bit(NVME_RDMA_Q_DELETING, &queue->flags);
set_bit(NVME_RDMA_Q_CONNECTED, &queue->flags);
return 0;
out_destroy_cm_id:
+ nvme_rdma_destroy_queue_ib(queue);
rdma_destroy_id(queue->cm_id);
return ret;
}
static void nvme_rdma_stop_and_free_queue(struct nvme_rdma_queue *queue)
{
- if (!test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags))
+ if (test_and_set_bit(NVME_RDMA_Q_DELETING, &queue->flags))
return;
nvme_rdma_stop_queue(queue);
nvme_rdma_free_queue(queue);
int i, ret;
for (i = 1; i < ctrl->queue_count; i++) {
- ret = nvme_rdma_init_queue(ctrl, i, ctrl->ctrl.sqsize);
+ ret = nvme_rdma_init_queue(ctrl, i,
+ ctrl->ctrl.opts->queue_size);
if (ret) {
dev_info(ctrl->ctrl.device,
"failed to initialize i/o queue: %d\n", ret);
return 0;
out_free_queues:
- for (; i >= 1; i--)
+ for (i--; i >= 1; i--)
nvme_rdma_stop_and_free_queue(&ctrl->queues[i]);
return ret;
list_del(&ctrl->list);
mutex_unlock(&nvme_rdma_ctrl_mutex);
- if (ctrl->ctrl.tagset) {
- blk_cleanup_queue(ctrl->ctrl.connect_q);
- blk_mq_free_tag_set(&ctrl->tag_set);
- nvme_rdma_dev_put(ctrl->device);
- }
kfree(ctrl->queues);
nvmf_free_options(nctrl->opts);
free_ctrl:
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
WARN_ON_ONCE(!changed);
- if (ctrl->queue_count > 1)
+ if (ctrl->queue_count > 1) {
nvme_start_queues(&ctrl->ctrl);
+ nvme_queue_scan(&ctrl->ctrl);
+ nvme_queue_async_events(&ctrl->ctrl);
+ }
dev_info(ctrl->ctrl.device, "Successfully reconnected\n");
{
struct nvme_rdma_ctrl *ctrl = container_of(work,
struct nvme_rdma_ctrl, err_work);
+ int i;
nvme_stop_keep_alive(&ctrl->ctrl);
+
+ for (i = 0; i < ctrl->queue_count; i++)
+ clear_bit(NVME_RDMA_Q_CONNECTED, &ctrl->queues[i].flags);
+
if (ctrl->queue_count > 1)
nvme_stop_queues(&ctrl->ctrl);
blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
if (!blk_rq_bytes(rq))
return;
- if (req->need_inval) {
+ if (req->mr->need_inval) {
res = nvme_rdma_inv_rkey(queue, req);
if (res < 0) {
dev_err(ctrl->ctrl.device,
IB_ACCESS_REMOTE_READ |
IB_ACCESS_REMOTE_WRITE;
- req->need_inval = true;
+ req->mr->need_inval = true;
sg->addr = cpu_to_le64(req->mr->iova);
put_unaligned_le24(req->mr->length, sg->length);
req->num_sge = 1;
req->inline_data = false;
- req->need_inval = false;
+ req->mr->need_inval = false;
c->common.flags |= NVME_CMD_SGL_METABUF;
if ((wc->wc_flags & IB_WC_WITH_INVALIDATE) &&
wc->ex.invalidate_rkey == req->mr->rkey)
- req->need_inval = false;
+ req->mr->need_inval = false;
blk_mq_complete_request(rq, status);
{
struct nvme_rdma_ctrl *ctrl = queue->ctrl;
struct rdma_conn_param param = { };
- struct nvme_rdma_cm_req priv;
+ struct nvme_rdma_cm_req priv = { };
int ret;
param.qp_num = queue->qp->qp_num;
priv.recfmt = cpu_to_le16(NVME_RDMA_CM_FMT_1_0);
priv.qid = cpu_to_le16(nvme_rdma_queue_idx(queue));
- priv.hrqsize = cpu_to_le16(queue->queue_size);
- priv.hsqsize = cpu_to_le16(queue->queue_size);
+ /*
+ * set the admin queue depth to the minimum size
+ * specified by the Fabrics standard.
+ */
+ if (priv.qid == 0) {
+ priv.hrqsize = cpu_to_le16(NVMF_AQ_DEPTH);
+ priv.hsqsize = cpu_to_le16(NVMF_AQ_DEPTH - 1);
+ } else {
+ /*
+ * current interpretation of the fabrics spec
+ * is at minimum you make hrqsize sqsize+1, or a
+ * 1's based representation of sqsize.
+ */
+ priv.hrqsize = cpu_to_le16(queue->queue_size);
+ priv.hsqsize = cpu_to_le16(queue->ctrl->ctrl.sqsize);
+ }
ret = rdma_connect(queue->cm_id, ¶m);
if (ret) {
return ret;
}
-/**
- * nvme_rdma_device_unplug() - Handle RDMA device unplug
- * @queue: Queue that owns the cm_id that caught the event
- *
- * DEVICE_REMOVAL event notifies us that the RDMA device is about
- * to unplug so we should take care of destroying our RDMA resources.
- * This event will be generated for each allocated cm_id.
- *
- * In our case, the RDMA resources are managed per controller and not
- * only per queue. So the way we handle this is we trigger an implicit
- * controller deletion upon the first DEVICE_REMOVAL event we see, and
- * hold the event inflight until the controller deletion is completed.
- *
- * One exception that we need to handle is the destruction of the cm_id
- * that caught the event. Since we hold the callout until the controller
- * deletion is completed, we'll deadlock if the controller deletion will
- * call rdma_destroy_id on this queue's cm_id. Thus, we claim ownership
- * of destroying this queue before-hand, destroy the queue resources
- * after the controller deletion completed with the exception of destroying
- * the cm_id implicitely by returning a non-zero rc to the callout.
- */
-static int nvme_rdma_device_unplug(struct nvme_rdma_queue *queue)
-{
- struct nvme_rdma_ctrl *ctrl = queue->ctrl;
- int ret, ctrl_deleted = 0;
-
- /* First disable the queue so ctrl delete won't free it */
- if (!test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags))
- goto out;
-
- /* delete the controller */
- ret = __nvme_rdma_del_ctrl(ctrl);
- if (!ret) {
- dev_warn(ctrl->ctrl.device,
- "Got rdma device removal event, deleting ctrl\n");
- flush_work(&ctrl->delete_work);
-
- /* Return non-zero so the cm_id will destroy implicitly */
- ctrl_deleted = 1;
-
- /* Free this queue ourselves */
- rdma_disconnect(queue->cm_id);
- ib_drain_qp(queue->qp);
- nvme_rdma_destroy_queue_ib(queue);
- }
-
-out:
- return ctrl_deleted;
-}
-
static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
struct rdma_cm_event *ev)
{
nvme_rdma_error_recovery(queue->ctrl);
break;
case RDMA_CM_EVENT_DEVICE_REMOVAL:
- /* return 1 means impliciy CM ID destroy */
- return nvme_rdma_device_unplug(queue);
+ /* device removal is handled via the ib_client API */
+ break;
default:
dev_err(queue->ctrl->ctrl.device,
"Unexpected RDMA CM event (%d)\n", ev->event);
if (rq->cmd_type == REQ_TYPE_FS && req_op(rq) == REQ_OP_FLUSH)
flush = true;
ret = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge,
- req->need_inval ? &req->reg_wr.wr : NULL, flush);
+ req->mr->need_inval ? &req->reg_wr.wr : NULL, flush);
if (ret) {
nvme_rdma_unmap_data(queue, rq);
goto err;
nvme_rdma_free_io_queues(ctrl);
}
- if (ctrl->ctrl.state == NVME_CTRL_LIVE)
+ if (test_bit(NVME_RDMA_Q_CONNECTED, &ctrl->queues[0].flags))
nvme_shutdown_ctrl(&ctrl->ctrl);
blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
nvme_rdma_destroy_admin_queue(ctrl);
}
+static void __nvme_rdma_remove_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown)
+{
+ nvme_uninit_ctrl(&ctrl->ctrl);
+ if (shutdown)
+ nvme_rdma_shutdown_ctrl(ctrl);
+
+ if (ctrl->ctrl.tagset) {
+ blk_cleanup_queue(ctrl->ctrl.connect_q);
+ blk_mq_free_tag_set(&ctrl->tag_set);
+ nvme_rdma_dev_put(ctrl->device);
+ }
+
+ nvme_put_ctrl(&ctrl->ctrl);
+}
+
static void nvme_rdma_del_ctrl_work(struct work_struct *work)
{
struct nvme_rdma_ctrl *ctrl = container_of(work,
struct nvme_rdma_ctrl, delete_work);
- nvme_remove_namespaces(&ctrl->ctrl);
- nvme_rdma_shutdown_ctrl(ctrl);
- nvme_uninit_ctrl(&ctrl->ctrl);
- nvme_put_ctrl(&ctrl->ctrl);
+ __nvme_rdma_remove_ctrl(ctrl, true);
}
static int __nvme_rdma_del_ctrl(struct nvme_rdma_ctrl *ctrl)
static int nvme_rdma_del_ctrl(struct nvme_ctrl *nctrl)
{
struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
- int ret;
+ int ret = 0;
+ /*
+ * Keep a reference until all work is flushed since
+ * __nvme_rdma_del_ctrl can free the ctrl mem
+ */
+ if (!kref_get_unless_zero(&ctrl->ctrl.kref))
+ return -EBUSY;
ret = __nvme_rdma_del_ctrl(ctrl);
- if (ret)
- return ret;
-
- flush_work(&ctrl->delete_work);
-
- return 0;
+ if (!ret)
+ flush_work(&ctrl->delete_work);
+ nvme_put_ctrl(&ctrl->ctrl);
+ return ret;
}
static void nvme_rdma_remove_ctrl_work(struct work_struct *work)
struct nvme_rdma_ctrl *ctrl = container_of(work,
struct nvme_rdma_ctrl, delete_work);
- nvme_remove_namespaces(&ctrl->ctrl);
- nvme_uninit_ctrl(&ctrl->ctrl);
- nvme_put_ctrl(&ctrl->ctrl);
+ __nvme_rdma_remove_ctrl(ctrl, false);
}
static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
if (ctrl->queue_count > 1) {
nvme_start_queues(&ctrl->ctrl);
nvme_queue_scan(&ctrl->ctrl);
+ nvme_queue_async_events(&ctrl->ctrl);
}
return;
memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
ctrl->tag_set.ops = &nvme_rdma_mq_ops;
- ctrl->tag_set.queue_depth = ctrl->ctrl.sqsize;
+ ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size;
ctrl->tag_set.reserved_tags = 1; /* fabric connect */
ctrl->tag_set.numa_node = NUMA_NO_NODE;
ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
spin_lock_init(&ctrl->lock);
ctrl->queue_count = opts->nr_io_queues + 1; /* +1 for admin queue */
- ctrl->ctrl.sqsize = opts->queue_size;
+ ctrl->ctrl.sqsize = opts->queue_size - 1;
ctrl->ctrl.kato = opts->kato;
ret = -ENOMEM;
.create_ctrl = nvme_rdma_create_ctrl,
};
+static void nvme_rdma_add_one(struct ib_device *ib_device)
+{
+}
+
+static void nvme_rdma_remove_one(struct ib_device *ib_device, void *client_data)
+{
+ struct nvme_rdma_ctrl *ctrl;
+
+ /* Delete all controllers using this device */
+ mutex_lock(&nvme_rdma_ctrl_mutex);
+ list_for_each_entry(ctrl, &nvme_rdma_ctrl_list, list) {
+ if (ctrl->device->dev != ib_device)
+ continue;
+ dev_info(ctrl->ctrl.device,
+ "Removing ctrl: NQN \"%s\", addr %pISp\n",
+ ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
+ __nvme_rdma_del_ctrl(ctrl);
+ }
+ mutex_unlock(&nvme_rdma_ctrl_mutex);
+
+ flush_workqueue(nvme_rdma_wq);
+}
+
+static struct ib_client nvme_rdma_ib_client = {
+ .name = "nvme_rdma",
+ .add = nvme_rdma_add_one,
+ .remove = nvme_rdma_remove_one
+};
+
static int __init nvme_rdma_init_module(void)
{
+ int ret;
+
nvme_rdma_wq = create_workqueue("nvme_rdma_wq");
if (!nvme_rdma_wq)
return -ENOMEM;
+ ret = ib_register_client(&nvme_rdma_ib_client);
+ if (ret) {
+ destroy_workqueue(nvme_rdma_wq);
+ return ret;
+ }
+
nvmf_register_transport(&nvme_rdma_transport);
return 0;
}
static void __exit nvme_rdma_cleanup_module(void)
{
- struct nvme_rdma_ctrl *ctrl;
-
nvmf_unregister_transport(&nvme_rdma_transport);
-
- mutex_lock(&nvme_rdma_ctrl_mutex);
- list_for_each_entry(ctrl, &nvme_rdma_ctrl_list, list)
- __nvme_rdma_del_ctrl(ctrl);
- mutex_unlock(&nvme_rdma_ctrl_mutex);
-
+ ib_unregister_client(&nvme_rdma_ib_client);
destroy_workqueue(nvme_rdma_wq);
}
config NVME_TARGET_LOOP
tristate "NVMe loopback device support"
- depends on BLK_DEV_NVME
depends on NVME_TARGET
+ select NVME_CORE
select NVME_FABRICS
select SG_POOL
help
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
-#include <linux/random.h>
#include <generated/utsrelease.h>
#include "nvmet.h"
{
struct nvmet_ctrl *ctrl = req->sq->ctrl;
struct nvme_id_ctrl *id;
- u64 serial;
u16 status = 0;
id = kzalloc(sizeof(*id), GFP_KERNEL);
id->vid = 0;
id->ssvid = 0;
- /* generate a random serial number as our controllers are ephemeral: */
- get_random_bytes(&serial, sizeof(serial));
memset(id->sn, ' ', sizeof(id->sn));
- snprintf(id->sn, sizeof(id->sn), "%llx", serial);
+ snprintf(id->sn, sizeof(id->sn), "%llx", ctrl->serial);
memset(id->mn, ' ', sizeof(id->mn));
strncpy((char *)id->mn, "Linux", sizeof(id->mn));
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
+#include <linux/random.h>
#include "nvmet.h"
static struct nvmet_fabrics_ops *nvmet_transports[NVMF_TRTYPE_MAX];
memcpy(ctrl->subsysnqn, subsysnqn, NVMF_NQN_SIZE);
memcpy(ctrl->hostnqn, hostnqn, NVMF_NQN_SIZE);
+ /* generate a random serial number as our controllers are ephemeral: */
+ get_random_bytes(&ctrl->serial, sizeof(ctrl->serial));
+
kref_init(&ctrl->ref);
ctrl->subsys = subsys;
struct nvme_loop_ctrl *ctrl = container_of(work,
struct nvme_loop_ctrl, delete_work);
- nvme_remove_namespaces(&ctrl->ctrl);
- nvme_loop_shutdown_ctrl(ctrl);
nvme_uninit_ctrl(&ctrl->ctrl);
+ nvme_loop_shutdown_ctrl(ctrl);
nvme_put_ctrl(&ctrl->ctrl);
}
nvme_loop_destroy_admin_queue(ctrl);
out_disable:
dev_warn(ctrl->ctrl.device, "Removing after reset failure\n");
- nvme_remove_namespaces(&ctrl->ctrl);
nvme_uninit_ctrl(&ctrl->ctrl);
nvme_put_ctrl(&ctrl->ctrl);
}
memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
ctrl->tag_set.ops = &nvme_loop_mq_ops;
- ctrl->tag_set.queue_depth = ctrl->ctrl.sqsize;
+ ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size;
ctrl->tag_set.reserved_tags = 1; /* fabric connect */
ctrl->tag_set.numa_node = NUMA_NO_NODE;
ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
ret = -ENOMEM;
- ctrl->ctrl.sqsize = opts->queue_size;
+ ctrl->ctrl.sqsize = opts->queue_size - 1;
ctrl->ctrl.kato = opts->kato;
ctrl->queues = kcalloc(opts->nr_io_queues + 1, sizeof(*ctrl->queues),
struct mutex lock;
u64 cap;
+ u64 serial;
u32 cc;
u32 csts;
NVMET_RDMA_Q_CONNECTING,
NVMET_RDMA_Q_LIVE,
NVMET_RDMA_Q_DISCONNECTING,
+ NVMET_RDMA_IN_DEVICE_REMOVAL,
};
struct nvmet_rdma_queue {
if (!len)
return 0;
- /* use the already allocated data buffer if possible */
- if (len <= NVMET_RDMA_INLINE_DATA_SIZE && rsp->queue->host_qid) {
- nvmet_rdma_use_inline_sg(rsp, len, 0);
- } else {
- status = nvmet_rdma_alloc_sgl(&rsp->req.sg, &rsp->req.sg_cnt,
- len);
- if (status)
- return status;
- }
+ status = nvmet_rdma_alloc_sgl(&rsp->req.sg, &rsp->req.sg_cnt,
+ len);
+ if (status)
+ return status;
ret = rdma_rw_ctx_init(&rsp->rw, cm_id->qp, cm_id->port_num,
rsp->req.sg, rsp->req.sg_cnt, 0, addr, key,
container_of(w, struct nvmet_rdma_queue, release_work);
struct rdma_cm_id *cm_id = queue->cm_id;
struct nvmet_rdma_device *dev = queue->dev;
+ enum nvmet_rdma_queue_state state = queue->state;
nvmet_rdma_free_queue(queue);
- rdma_destroy_id(cm_id);
+
+ if (state != NVMET_RDMA_IN_DEVICE_REMOVAL)
+ rdma_destroy_id(cm_id);
+
kref_put(&dev->ref, nvmet_rdma_free_dev);
}
queue->host_qid = le16_to_cpu(req->qid);
/*
- * req->hsqsize corresponds to our recv queue size
+ * req->hsqsize corresponds to our recv queue size plus 1
* req->hrqsize corresponds to our send queue size
*/
- queue->recv_queue_size = le16_to_cpu(req->hsqsize);
+ queue->recv_queue_size = le16_to_cpu(req->hsqsize) + 1;
queue->send_queue_size = le16_to_cpu(req->hrqsize);
if (!queue->host_qid && queue->recv_queue_size > NVMF_AQ_DEPTH)
switch (queue->state) {
case NVMET_RDMA_Q_CONNECTING:
case NVMET_RDMA_Q_LIVE:
- disconnect = true;
queue->state = NVMET_RDMA_Q_DISCONNECTING;
+ case NVMET_RDMA_IN_DEVICE_REMOVAL:
+ disconnect = true;
break;
case NVMET_RDMA_Q_DISCONNECTING:
break;
schedule_work(&queue->release_work);
}
+/**
+ * nvme_rdma_device_removal() - Handle RDMA device removal
+ * @queue: nvmet rdma queue (cm id qp_context)
+ * @addr: nvmet address (cm_id context)
+ *
+ * DEVICE_REMOVAL event notifies us that the RDMA device is about
+ * to unplug so we should take care of destroying our RDMA resources.
+ * This event will be generated for each allocated cm_id.
+ *
+ * Note that this event can be generated on a normal queue cm_id
+ * and/or a device bound listener cm_id (where in this case
+ * queue will be null).
+ *
+ * we claim ownership on destroying the cm_id. For queues we move
+ * the queue state to NVMET_RDMA_IN_DEVICE_REMOVAL and for port
+ * we nullify the priv to prevent double cm_id destruction and destroying
+ * the cm_id implicitely by returning a non-zero rc to the callout.
+ */
+static int nvmet_rdma_device_removal(struct rdma_cm_id *cm_id,
+ struct nvmet_rdma_queue *queue)
+{
+ unsigned long flags;
+
+ if (!queue) {
+ struct nvmet_port *port = cm_id->context;
+
+ /*
+ * This is a listener cm_id. Make sure that
+ * future remove_port won't invoke a double
+ * cm_id destroy. use atomic xchg to make sure
+ * we don't compete with remove_port.
+ */
+ if (xchg(&port->priv, NULL) != cm_id)
+ return 0;
+ } else {
+ /*
+ * This is a queue cm_id. Make sure that
+ * release queue will not destroy the cm_id
+ * and schedule all ctrl queues removal (only
+ * if the queue is not disconnecting already).
+ */
+ spin_lock_irqsave(&queue->state_lock, flags);
+ if (queue->state != NVMET_RDMA_Q_DISCONNECTING)
+ queue->state = NVMET_RDMA_IN_DEVICE_REMOVAL;
+ spin_unlock_irqrestore(&queue->state_lock, flags);
+ nvmet_rdma_queue_disconnect(queue);
+ flush_scheduled_work();
+ }
+
+ /*
+ * We need to return 1 so that the core will destroy
+ * it's own ID. What a great API design..
+ */
+ return 1;
+}
+
static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id,
struct rdma_cm_event *event)
{
break;
case RDMA_CM_EVENT_ADDR_CHANGE:
case RDMA_CM_EVENT_DISCONNECTED:
- case RDMA_CM_EVENT_DEVICE_REMOVAL:
case RDMA_CM_EVENT_TIMEWAIT_EXIT:
- /*
- * We can get the device removal callback even for a
- * CM ID that we aren't actually using. In that case
- * the context pointer is NULL, so we shouldn't try
- * to disconnect a non-existing queue. But we also
- * need to return 1 so that the core will destroy
- * it's own ID. What a great API design..
- */
- if (queue)
- nvmet_rdma_queue_disconnect(queue);
- else
- ret = 1;
+ nvmet_rdma_queue_disconnect(queue);
+ break;
+ case RDMA_CM_EVENT_DEVICE_REMOVAL:
+ ret = nvmet_rdma_device_removal(cm_id, queue);
break;
case RDMA_CM_EVENT_REJECTED:
case RDMA_CM_EVENT_UNREACHABLE:
static void nvmet_rdma_remove_port(struct nvmet_port *port)
{
- struct rdma_cm_id *cm_id = port->priv;
+ struct rdma_cm_id *cm_id = xchg(&port->priv, NULL);
- rdma_destroy_id(cm_id);
+ if (cm_id)
+ rdma_destroy_id(cm_id);
}
static struct nvmet_fabrics_ops nvmet_rdma_ops = {
*/
err:
- if (it.node)
- of_node_put(it.node);
+ of_node_put(it.node);
return rc;
}
const struct device_node *parent, int port_reg, int reg)
{
struct of_endpoint endpoint;
- struct device_node *node, *prev_node = NULL;
-
- while (1) {
- node = of_graph_get_next_endpoint(parent, prev_node);
- of_node_put(prev_node);
- if (!node)
- break;
+ struct device_node *node = NULL;
+ for_each_endpoint_of_node(parent, node) {
of_graph_parse_endpoint(node, &endpoint);
if (((port_reg == -1) || (endpoint.port == port_reg)) &&
((reg == -1) || (endpoint.id == reg)))
return node;
-
- prev_node = node;
}
return NULL;
pr_warning("End of tree marker overwritten: %08x\n",
be32_to_cpup(mem + size));
- if (detached) {
+ if (detached && mynodes) {
of_node_set_flag(*mynodes, OF_DETACHED);
pr_debug("unflattened tree is detached\n");
}
list_del(&desc->list);
+ of_node_set_flag(desc->dev, OF_POPULATED);
+
pr_debug("of_irq_init: init %s (%p), parent %p\n",
desc->dev->full_name,
desc->dev, desc->interrupt_parent);
ret = desc->irq_init_cb(desc->dev,
desc->interrupt_parent);
if (ret) {
+ of_node_clear_flag(desc->dev, OF_POPULATED);
kfree(desc);
continue;
}
* its children can get processed in a subsequent pass.
*/
list_add_tail(&desc->list, &intc_parent_list);
-
- of_node_set_flag(desc->dev, OF_POPULATED);
}
/* Get the next pending parent that might have children */
}
EXPORT_SYMBOL_GPL(of_platform_default_populate);
+#ifndef CONFIG_PPC
static int __init of_platform_default_populate_init(void)
{
struct device_node *node;
return 0;
}
arch_initcall_sync(of_platform_default_populate_init);
+#endif
static int of_platform_device_destroy(struct device *dev, void *data)
{
bridge->release_fn = release_fn;
bridge->release_data = release_data;
}
+EXPORT_SYMBOL_GPL(pci_set_host_bridge_release);
void pcibios_resource_to_bus(struct pci_bus *bus, struct pci_bus_region *region,
struct resource *res)
nvec = maxvec;
for (;;) {
- if (!(flags & PCI_IRQ_NOAFFINITY)) {
+ if (flags & PCI_IRQ_AFFINITY) {
dev->irq_affinity = irq_create_affinity_mask(&nvec);
if (nvec < minvec)
return -ENOSPC;
**/
int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec)
{
- return __pci_enable_msi_range(dev, minvec, maxvec, PCI_IRQ_NOAFFINITY);
+ return __pci_enable_msi_range(dev, minvec, maxvec, 0);
}
EXPORT_SYMBOL(pci_enable_msi_range);
return -ERANGE;
for (;;) {
- if (!(flags & PCI_IRQ_NOAFFINITY)) {
+ if (flags & PCI_IRQ_AFFINITY) {
dev->irq_affinity = irq_create_affinity_mask(&nvec);
if (nvec < minvec)
return -ENOSPC;
int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries,
int minvec, int maxvec)
{
- return __pci_enable_msix_range(dev, entries, minvec, maxvec,
- PCI_IRQ_NOAFFINITY);
+ return __pci_enable_msix_range(dev, entries, minvec, maxvec, 0);
}
EXPORT_SYMBOL(pci_enable_msix_range);
{
int vecs = -ENOSPC;
- if (!(flags & PCI_IRQ_NOMSIX)) {
+ if (flags & PCI_IRQ_MSIX) {
vecs = __pci_enable_msix_range(dev, NULL, min_vecs, max_vecs,
flags);
if (vecs > 0)
return vecs;
}
- if (!(flags & PCI_IRQ_NOMSI)) {
+ if (flags & PCI_IRQ_MSI) {
vecs = __pci_enable_msi_range(dev, min_vecs, max_vecs, flags);
if (vecs > 0)
return vecs;
}
/* use legacy irq if allowed */
- if (!(flags & PCI_IRQ_NOLEGACY) && min_vecs == 1)
+ if ((flags & PCI_IRQ_LEGACY) && min_vecs == 1) {
+ pci_intx(dev, 1);
return 1;
+ }
+
return vecs;
}
EXPORT_SYMBOL(pci_alloc_irq_vectors);
if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
pci_msi_domain_update_chip_ops(info);
+ info->flags |= MSI_FLAG_ACTIVATE_EARLY;
+
domain = msi_create_irq_domain(fwnode, info, parent);
if (!domain)
return NULL;
if (nhi->vendor != PCI_VENDOR_ID_INTEL
|| (nhi->device != PCI_DEVICE_ID_INTEL_LIGHT_RIDGE &&
nhi->device != PCI_DEVICE_ID_INTEL_CACTUS_RIDGE_4C &&
+ nhi->device != PCI_DEVICE_ID_INTEL_FALCON_RIDGE_2C_NHI &&
nhi->device != PCI_DEVICE_ID_INTEL_FALCON_RIDGE_4C_NHI)
- || nhi->subsystem_vendor != 0x2222
- || nhi->subsystem_device != 0x1111)
+ || nhi->class != PCI_CLASS_SYSTEM_OTHER << 8)
goto out;
dev_info(&dev->dev, "quirk: waiting for thunderbolt to reestablish PCI tunnels...\n");
device_pm_wait_for_dev(&dev->dev, &nhi->dev);
DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_INTEL,
PCI_DEVICE_ID_INTEL_CACTUS_RIDGE_4C,
quirk_apple_wait_for_thunderbolt);
+DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_INTEL,
+ PCI_DEVICE_ID_INTEL_FALCON_RIDGE_2C_BRIDGE,
+ quirk_apple_wait_for_thunderbolt);
DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_INTEL,
PCI_DEVICE_ID_INTEL_FALCON_RIDGE_4C_BRIDGE,
quirk_apple_wait_for_thunderbolt);
list_del(&dev->bus_list);
up_write(&pci_bus_sem);
+ pci_bridge_d3_device_removed(dev);
pci_free_resources(dev);
put_device(&dev->dev);
}
dev->subordinate = NULL;
}
- pci_bridge_d3_device_removed(dev);
-
pci_destroy_dev(dev);
}
/************************ runtime PM support ***************************/
-static int pcmcia_dev_suspend(struct device *dev, pm_message_t state);
+static int pcmcia_dev_suspend(struct device *dev);
static int pcmcia_dev_resume(struct device *dev);
static int runtime_suspend(struct device *dev)
int rc;
device_lock(dev);
- rc = pcmcia_dev_suspend(dev, PMSG_SUSPEND);
+ rc = pcmcia_dev_suspend(dev);
device_unlock(dev);
return rc;
}
/* PM support, also needed for reset */
-static int pcmcia_dev_suspend(struct device *dev, pm_message_t state)
+static int pcmcia_dev_suspend(struct device *dev)
{
struct pcmcia_device *p_dev = to_pcmcia_dev(dev);
struct pcmcia_driver *p_drv = NULL;
.remove_dev = &pcmcia_bus_remove_socket,
};
+static const struct dev_pm_ops pcmcia_bus_pm_ops = {
+ SET_SYSTEM_SLEEP_PM_OPS(pcmcia_dev_suspend, pcmcia_dev_resume)
+};
struct bus_type pcmcia_bus_type = {
.name = "pcmcia",
.dev_groups = pcmcia_dev_groups,
.probe = pcmcia_device_probe,
.remove = pcmcia_device_remove,
- .suspend = pcmcia_dev_suspend,
- .resume = pcmcia_dev_resume,
+ .pm = &pcmcia_bus_pm_ops,
};
}
#endif
-void pxa2xx_configure_sockets(struct device *dev)
+void pxa2xx_configure_sockets(struct device *dev, struct pcmcia_low_level *ops)
{
- struct pcmcia_low_level *ops = dev->platform_data;
/*
* We have at least one socket, so set MECR:CIT
* (Card Is There)
goto err1;
}
- pxa2xx_configure_sockets(&dev->dev);
+ pxa2xx_configure_sockets(&dev->dev, ops);
dev_set_drvdata(&dev->dev, sinfo);
return 0;
static int pxa2xx_drv_pcmcia_resume(struct device *dev)
{
- pxa2xx_configure_sockets(dev);
+ struct pcmcia_low_level *ops = (struct pcmcia_low_level *)dev->platform_data;
+
+ pxa2xx_configure_sockets(dev, ops);
return 0;
}
int pxa2xx_drv_pcmcia_add_one(struct soc_pcmcia_socket *skt);
void pxa2xx_drv_pcmcia_ops(struct pcmcia_low_level *ops);
-void pxa2xx_configure_sockets(struct device *dev);
+void pxa2xx_configure_sockets(struct device *dev, struct pcmcia_low_level *ops);
int pcmcia_badge4_init(struct sa1111_dev *dev)
{
- int ret = -ENODEV;
-
- if (machine_is_badge4()) {
- printk(KERN_INFO
- "%s: badge4_pcmvcc=%d, badge4_pcmvpp=%d, badge4_cfvcc=%d\n",
- __func__,
- badge4_pcmvcc, badge4_pcmvpp, badge4_cfvcc);
-
- sa11xx_drv_pcmcia_ops(&badge4_pcmcia_ops);
- ret = sa1111_pcmcia_add(dev, &badge4_pcmcia_ops,
- sa11xx_drv_pcmcia_add_one);
- }
-
- return ret;
+ printk(KERN_INFO
+ "%s: badge4_pcmvcc=%d, badge4_pcmvpp=%d, badge4_cfvcc=%d\n",
+ __func__,
+ badge4_pcmvcc, badge4_pcmvpp, badge4_cfvcc);
+
+ sa11xx_drv_pcmcia_ops(&badge4_pcmcia_ops);
+ return sa1111_pcmcia_add(dev, &badge4_pcmcia_ops,
+ sa11xx_drv_pcmcia_add_one);
}
static int __init pcmv_setup(char *s)
#include <mach/hardware.h>
#include <asm/hardware/sa1111.h>
+#include <asm/mach-types.h>
#include <asm/irq.h>
#include "sa1111_generic.h"
sa1111_writel(PCSSR_S0_SLEEP | PCSSR_S1_SLEEP, base + PCSSR);
sa1111_writel(PCCR_S0_FLT | PCCR_S1_FLT, base + PCCR);
+ ret = -ENODEV;
#ifdef CONFIG_SA1100_BADGE4
- pcmcia_badge4_init(dev);
+ if (machine_is_badge4())
+ ret = pcmcia_badge4_init(dev);
#endif
#ifdef CONFIG_SA1100_JORNADA720
- pcmcia_jornada720_init(dev);
+ if (machine_is_jornada720())
+ ret = pcmcia_jornada720_init(dev);
#endif
#ifdef CONFIG_ARCH_LUBBOCK
- pcmcia_lubbock_init(dev);
+ if (machine_is_lubbock())
+ ret = pcmcia_lubbock_init(dev);
#endif
#ifdef CONFIG_ASSABET_NEPONSET
- pcmcia_neponset_init(dev);
+ if (machine_is_assabet())
+ ret = pcmcia_neponset_init(dev);
#endif
- return 0;
+
+ if (ret) {
+ release_mem_region(dev->res.start, 512);
+ sa1111_disable_device(dev);
+ }
+
+ return ret;
}
static int pcmcia_remove(struct sa1111_dev *dev)
int pcmcia_jornada720_init(struct sa1111_dev *sadev)
{
- int ret = -ENODEV;
+ unsigned int pin = GPIO_A0 | GPIO_A1 | GPIO_A2 | GPIO_A3;
- if (machine_is_jornada720()) {
- unsigned int pin = GPIO_A0 | GPIO_A1 | GPIO_A2 | GPIO_A3;
+ /* Fixme: why messing around with SA11x0's GPIO1? */
+ GRER |= 0x00000002;
- GRER |= 0x00000002;
+ /* Set GPIO_A<3:1> to be outputs for PCMCIA/CF power controller: */
+ sa1111_set_io_dir(sadev, pin, 0, 0);
+ sa1111_set_io(sadev, pin, 0);
+ sa1111_set_sleep_io(sadev, pin, 0);
- /* Set GPIO_A<3:1> to be outputs for PCMCIA/CF power controller: */
- sa1111_set_io_dir(sadev, pin, 0, 0);
- sa1111_set_io(sadev, pin, 0);
- sa1111_set_sleep_io(sadev, pin, 0);
-
- sa11xx_drv_pcmcia_ops(&jornada720_pcmcia_ops);
- ret = sa1111_pcmcia_add(sadev, &jornada720_pcmcia_ops,
- sa11xx_drv_pcmcia_add_one);
- }
-
- return ret;
+ sa11xx_drv_pcmcia_ops(&jornada720_pcmcia_ops);
+ return sa1111_pcmcia_add(sadev, &jornada720_pcmcia_ops,
+ sa11xx_drv_pcmcia_add_one);
}
int pcmcia_lubbock_init(struct sa1111_dev *sadev)
{
- int ret = -ENODEV;
-
- if (machine_is_lubbock()) {
- /*
- * Set GPIO_A<3:0> to be outputs for the MAX1600,
- * and switch to standby mode.
- */
- sa1111_set_io_dir(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0, 0);
- sa1111_set_io(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0);
- sa1111_set_sleep_io(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0);
-
- /* Set CF Socket 1 power to standby mode. */
- lubbock_set_misc_wr((1 << 15) | (1 << 14), 0);
+ /*
+ * Set GPIO_A<3:0> to be outputs for the MAX1600,
+ * and switch to standby mode.
+ */
+ sa1111_set_io_dir(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0, 0);
+ sa1111_set_io(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0);
+ sa1111_set_sleep_io(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0);
- pxa2xx_drv_pcmcia_ops(&lubbock_pcmcia_ops);
- pxa2xx_configure_sockets(&sadev->dev);
- ret = sa1111_pcmcia_add(sadev, &lubbock_pcmcia_ops,
- pxa2xx_drv_pcmcia_add_one);
- }
+ /* Set CF Socket 1 power to standby mode. */
+ lubbock_set_misc_wr((1 << 15) | (1 << 14), 0);
- return ret;
+ pxa2xx_drv_pcmcia_ops(&lubbock_pcmcia_ops);
+ pxa2xx_configure_sockets(&sadev->dev, &lubbock_pcmcia_ops);
+ return sa1111_pcmcia_add(sadev, &lubbock_pcmcia_ops,
+ pxa2xx_drv_pcmcia_add_one);
}
MODULE_LICENSE("GPL");
int pcmcia_neponset_init(struct sa1111_dev *sadev)
{
- int ret = -ENODEV;
-
- if (machine_is_assabet()) {
- /*
- * Set GPIO_A<3:0> to be outputs for the MAX1600,
- * and switch to standby mode.
- */
- sa1111_set_io_dir(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0, 0);
- sa1111_set_io(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0);
- sa1111_set_sleep_io(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0);
- sa11xx_drv_pcmcia_ops(&neponset_pcmcia_ops);
- ret = sa1111_pcmcia_add(sadev, &neponset_pcmcia_ops,
- sa11xx_drv_pcmcia_add_one);
- }
-
- return ret;
+ /*
+ * Set GPIO_A<3:0> to be outputs for the MAX1600,
+ * and switch to standby mode.
+ */
+ sa1111_set_io_dir(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0, 0);
+ sa1111_set_io(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0);
+ sa1111_set_sleep_io(sadev, GPIO_A0|GPIO_A1|GPIO_A2|GPIO_A3, 0);
+ sa11xx_drv_pcmcia_ops(&neponset_pcmcia_ops);
+ return sa1111_pcmcia_add(sadev, &neponset_pcmcia_ops,
+ sa11xx_drv_pcmcia_add_one);
}
sa1100_pcmcia_show_timing(struct soc_pcmcia_socket *skt, char *buf)
{
struct soc_pcmcia_timing timing;
- unsigned int clock = clk_get_rate(skt->clk);
+ unsigned int clock = clk_get_rate(skt->clk) / 1000;
unsigned long mecr = MECR;
char *p = buf;
soc_common_pcmcia_get_timing(skt, &timing);
- p+=sprintf(p, "I/O : %u (%u)\n", timing.io,
+ p+=sprintf(p, "I/O : %uns (%uns)\n", timing.io,
sa1100_pcmcia_cmd_time(clock, MECR_BSIO_GET(mecr, skt->nr)));
- p+=sprintf(p, "attribute: %u (%u)\n", timing.attr,
+ p+=sprintf(p, "attribute: %uns (%uns)\n", timing.attr,
sa1100_pcmcia_cmd_time(clock, MECR_BSA_GET(mecr, skt->nr)));
- p+=sprintf(p, "common : %u (%u)\n", timing.mem,
+ p+=sprintf(p, "common : %uns (%uns)\n", timing.mem,
sa1100_pcmcia_cmd_time(clock, MECR_BSM_GET(mecr, skt->nr)));
return p - buf;
stat |= skt->cs_state.Vcc ? SS_POWERON : 0;
if (skt->cs_state.flags & SS_IOCARD)
- stat |= state.bvd1 ? SS_STSCHG : 0;
+ stat |= state.bvd1 ? 0 : SS_STSCHG;
else {
if (state.bvd1 == 0)
stat |= SS_BATDEAD;
return 0;
}
-static DEFINE_MUTEX(arm_pmu_mutex);
+static DEFINE_SPINLOCK(arm_pmu_lock);
static LIST_HEAD(arm_pmu_list);
/*
{
struct arm_pmu *pmu;
- mutex_lock(&arm_pmu_mutex);
+ spin_lock(&arm_pmu_lock);
list_for_each_entry(pmu, &arm_pmu_list, entry) {
if (!cpumask_test_cpu(cpu, &pmu->supported_cpus))
if (pmu->reset)
pmu->reset(pmu);
}
- mutex_unlock(&arm_pmu_mutex);
+ spin_unlock(&arm_pmu_lock);
return 0;
}
if (!cpu_hw_events)
return -ENOMEM;
- mutex_lock(&arm_pmu_mutex);
+ spin_lock(&arm_pmu_lock);
list_add_tail(&cpu_pmu->entry, &arm_pmu_list);
- mutex_unlock(&arm_pmu_mutex);
+ spin_unlock(&arm_pmu_lock);
err = cpu_pm_pmu_register(cpu_pmu);
if (err)
return 0;
out_unregister:
- mutex_lock(&arm_pmu_mutex);
+ spin_lock(&arm_pmu_lock);
list_del(&cpu_pmu->entry);
- mutex_unlock(&arm_pmu_mutex);
+ spin_unlock(&arm_pmu_lock);
free_percpu(cpu_hw_events);
return err;
}
static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu)
{
cpu_pm_pmu_unregister(cpu_pmu);
- mutex_lock(&arm_pmu_mutex);
+ spin_lock(&arm_pmu_lock);
list_del(&cpu_pmu->entry);
- mutex_unlock(&arm_pmu_mutex);
+ spin_unlock(&arm_pmu_lock);
free_percpu(cpu_pmu->hw_events);
}
if (i > 0 && spi != using_spi) {
pr_err("PPI/SPI IRQ type mismatch for %s!\n",
dn->name);
+ of_node_put(dn);
kfree(irqs);
return -EINVAL;
}
/* If we didn't manage to parse anything, try the interrupt affinity */
if (cpumask_weight(&pmu->supported_cpus) == 0) {
- if (!using_spi) {
+ int irq = platform_get_irq(pdev, 0);
+
+ if (irq >= 0 && irq_is_percpu(irq)) {
/* If using PPIs, check the affinity of the partition */
- int ret, irq;
+ int ret;
- irq = platform_get_irq(pdev, 0);
ret = irq_get_percpu_devid_partition(irq, &pmu->supported_cpus);
if (ret) {
kfree(irqs);
rc = -ENODEV;
};
- return 0;
+ return rc;
}
static const struct phy_ops phy_ops = {
#include <linux/power_supply.h>
#include <linux/regulator/consumer.h>
#include <linux/reset.h>
+#include <linux/usb/of.h>
#include <linux/workqueue.h>
#define REG_ISCR 0x00
struct sun4i_usb_phy_data {
void __iomem *base;
const struct sun4i_usb_phy_cfg *cfg;
+ enum usb_dr_mode dr_mode;
struct mutex mutex;
struct sun4i_usb_phy {
struct phy *phy;
bool regulator_on;
int index;
} phys[MAX_PHYS];
+ int first_phy;
/* phy0 / otg related variables */
struct extcon_dev *extcon;
bool phy0_init;
sun4i_usb_phy0_update_iscr(_phy, 0, ISCR_DPDM_PULLUP_EN);
sun4i_usb_phy0_update_iscr(_phy, 0, ISCR_ID_PULLUP_EN);
- if (data->id_det_gpio) {
- /* OTG mode, force ISCR and cable state updates */
- data->id_det = -1;
- data->vbus_det = -1;
- queue_delayed_work(system_wq, &data->detect, 0);
- } else {
- /* Host only mode */
- sun4i_usb_phy0_set_id_detect(_phy, 0);
- sun4i_usb_phy0_set_vbus_detect(_phy, 1);
- }
+ /* Force ISCR and cable state updates */
+ data->id_det = -1;
+ data->vbus_det = -1;
+ queue_delayed_work(system_wq, &data->detect, 0);
}
return 0;
return 0;
}
+static int sun4i_usb_phy0_get_id_det(struct sun4i_usb_phy_data *data)
+{
+ switch (data->dr_mode) {
+ case USB_DR_MODE_OTG:
+ return gpiod_get_value_cansleep(data->id_det_gpio);
+ case USB_DR_MODE_HOST:
+ return 0;
+ case USB_DR_MODE_PERIPHERAL:
+ default:
+ return 1;
+ }
+}
+
static int sun4i_usb_phy0_get_vbus_det(struct sun4i_usb_phy_data *data)
{
if (data->vbus_det_gpio)
struct phy *phy0 = data->phys[0].phy;
int id_det, vbus_det, id_notify = 0, vbus_notify = 0;
- id_det = gpiod_get_value_cansleep(data->id_det_gpio);
+ if (phy0 == NULL)
+ return;
+
+ id_det = sun4i_usb_phy0_get_id_det(data);
vbus_det = sun4i_usb_phy0_get_vbus_det(data);
mutex_lock(&phy0->mutex);
* without vbus detection report vbus low for long enough for
* the musb-ip to end the current device session.
*/
- if (!sun4i_usb_phy0_have_vbus_det(data) && id_det == 0) {
+ if (data->dr_mode == USB_DR_MODE_OTG &&
+ !sun4i_usb_phy0_have_vbus_det(data) && id_det == 0) {
sun4i_usb_phy0_set_vbus_detect(phy0, 0);
msleep(200);
sun4i_usb_phy0_set_vbus_detect(phy0, 1);
* without vbus detection report vbus low for long enough to
* the musb-ip to end the current host session.
*/
- if (!sun4i_usb_phy0_have_vbus_det(data) && id_det == 1) {
+ if (data->dr_mode == USB_DR_MODE_OTG &&
+ !sun4i_usb_phy0_have_vbus_det(data) && id_det == 1) {
mutex_lock(&phy0->mutex);
sun4i_usb_phy0_set_vbus_detect(phy0, 0);
msleep(1000);
{
struct sun4i_usb_phy_data *data = dev_get_drvdata(dev);
- if (args->args[0] >= data->cfg->num_phys)
+ if (args->args[0] < data->first_phy ||
+ args->args[0] >= data->cfg->num_phys)
return ERR_PTR(-ENODEV);
return data->phys[args->args[0]].phy;
return -EPROBE_DEFER;
}
- /* vbus_det without id_det makes no sense, and is not supported */
- if (sun4i_usb_phy0_have_vbus_det(data) && !data->id_det_gpio) {
- dev_err(dev, "usb0_id_det missing or invalid\n");
- return -ENODEV;
- }
-
- if (data->id_det_gpio) {
+ data->dr_mode = of_usb_get_dr_mode_by_phy(np, 0);
+ switch (data->dr_mode) {
+ case USB_DR_MODE_OTG:
+ /* otg without id_det makes no sense, and is not supported */
+ if (!data->id_det_gpio) {
+ dev_err(dev, "usb0_id_det missing or invalid\n");
+ return -ENODEV;
+ }
+ /* fall through */
+ case USB_DR_MODE_HOST:
+ case USB_DR_MODE_PERIPHERAL:
data->extcon = devm_extcon_dev_allocate(dev,
sun4i_usb_phy0_cable);
if (IS_ERR(data->extcon))
dev_err(dev, "failed to register extcon: %d\n", ret);
return ret;
}
+ break;
+ default:
+ dev_info(dev, "dr_mode unknown, not registering usb phy0\n");
+ data->first_phy = 1;
}
- for (i = 0; i < data->cfg->num_phys; i++) {
+ for (i = data->first_phy; i < data->cfg->num_phys; i++) {
struct sun4i_usb_phy *phy = data->phys + i;
char name[16];
}
phy->hsic_clk = devm_clk_get(dev, "hsic_12M");
- if (IS_ERR(phy->clk)) {
+ if (IS_ERR(phy->hsic_clk)) {
dev_err(dev, "failed to get hsic_12M clock\n");
- return PTR_ERR(phy->clk);
+ return PTR_ERR(phy->hsic_clk);
}
phy->reset = devm_reset_control_get(dev, "hsic");
offset += range->npins;
}
- /* Mask and clear all interrupts */
- chv_writel(0, pctrl->regs + CHV_INTMASK);
+ /* Clear all interrupts */
chv_writel(0xffff, pctrl->regs + CHV_INTSTAT);
ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, 0,
- handle_simple_irq, IRQ_TYPE_NONE);
+ handle_bad_irq, IRQ_TYPE_NONE);
if (ret) {
dev_err(pctrl->dev, "failed to add IRQ chip\n");
goto fail;
#include <linux/bitops.h>
#include <linux/err.h>
+#include <linux/io.h>
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/pinctrl/pinconf.h>
return PTR_ERR(pc->pcdev);
}
- ret = meson_gpiolib_register(pc);
- if (ret) {
- pinctrl_unregister(pc->pcdev);
- return ret;
- }
-
- return 0;
+ return meson_gpiolib_register(pc);
}
static struct platform_driver meson_pinctrl_driver = {
spin_lock_irqsave(&gpio_dev->lock, flags);
pin_reg = readl(gpio_dev->base + offset * 4);
- /*
- * Suppose BIOS or Bootloader sets specific debounce for the
- * GPIO. if not, set debounce to be 2.75ms and remove glitch.
- */
- if ((pin_reg & DB_TMR_OUT_MASK) == 0) {
- pin_reg |= 0xf;
- pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF);
- pin_reg |= DB_TYPE_REMOVE_GLITCH << DB_CNTRL_OFF;
- pin_reg &= ~BIT(DB_TMR_LARGE_OFF);
- }
-
pin_reg &= ~BIT(OUTPUT_ENABLE_OFF);
writel(pin_reg, gpio_dev->base + offset * 4);
spin_unlock_irqrestore(&gpio_dev->lock, flags);
spin_lock_irqsave(&gpio_dev->lock, flags);
pin_reg = readl(gpio_dev->base + (d->hwirq)*4);
- /*
- Suppose BIOS or Bootloader sets specific debounce for the
- GPIO. if not, set debounce to be 2.75ms.
- */
- if ((pin_reg & DB_TMR_OUT_MASK) == 0) {
- pin_reg |= 0xf;
- pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF);
- pin_reg &= ~BIT(DB_TMR_LARGE_OFF);
- }
pin_reg |= BIT(INTERRUPT_ENABLE_OFF);
pin_reg |= BIT(INTERRUPT_MASK_OFF);
writel(pin_reg, gpio_dev->base + (d->hwirq)*4);
PADS_FUNCTION_SELECT2, 12, 0x3),
MFIO_MUX_PIN_GROUP(83, MIPS_PLL_LOCK, MIPS_TRACE_DATA, USB_DEBUG,
PADS_FUNCTION_SELECT2, 14, 0x3),
- MFIO_MUX_PIN_GROUP(84, SYS_PLL_LOCK, MIPS_TRACE_DATA, USB_DEBUG,
+ MFIO_MUX_PIN_GROUP(84, AUDIO_PLL_LOCK, MIPS_TRACE_DATA, USB_DEBUG,
PADS_FUNCTION_SELECT2, 16, 0x3),
- MFIO_MUX_PIN_GROUP(85, WIFI_PLL_LOCK, MIPS_TRACE_DATA, SDHOST_DEBUG,
+ MFIO_MUX_PIN_GROUP(85, RPU_V_PLL_LOCK, MIPS_TRACE_DATA, SDHOST_DEBUG,
PADS_FUNCTION_SELECT2, 18, 0x3),
- MFIO_MUX_PIN_GROUP(86, BT_PLL_LOCK, MIPS_TRACE_DATA, SDHOST_DEBUG,
+ MFIO_MUX_PIN_GROUP(86, RPU_L_PLL_LOCK, MIPS_TRACE_DATA, SDHOST_DEBUG,
PADS_FUNCTION_SELECT2, 20, 0x3),
- MFIO_MUX_PIN_GROUP(87, RPU_V_PLL_LOCK, DREQ2, SOCIF_DEBUG,
+ MFIO_MUX_PIN_GROUP(87, SYS_PLL_LOCK, DREQ2, SOCIF_DEBUG,
PADS_FUNCTION_SELECT2, 22, 0x3),
- MFIO_MUX_PIN_GROUP(88, RPU_L_PLL_LOCK, DREQ3, SOCIF_DEBUG,
+ MFIO_MUX_PIN_GROUP(88, WIFI_PLL_LOCK, DREQ3, SOCIF_DEBUG,
PADS_FUNCTION_SELECT2, 24, 0x3),
- MFIO_MUX_PIN_GROUP(89, AUDIO_PLL_LOCK, DREQ4, DREQ5,
+ MFIO_MUX_PIN_GROUP(89, BT_PLL_LOCK, DREQ4, DREQ5,
PADS_FUNCTION_SELECT2, 26, 0x3),
PIN_GROUP(TCK, "tck"),
PIN_GROUP(TRSTN, "trstn"),
{
struct pistachio_pinctrl *pctl;
struct resource *res;
- int ret;
pctl = devm_kzalloc(&pdev->dev, sizeof(*pctl), GFP_KERNEL);
if (!pctl)
return PTR_ERR(pctl->pctldev);
}
- ret = pistachio_gpio_register(pctl);
- if (ret < 0) {
- pinctrl_unregister(pctl->pctldev);
- return ret;
- }
-
- return 0;
+ return pistachio_gpio_register(pctl);
}
static struct platform_driver pistachio_pinctrl_driver = {
SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 8),
SUNXI_FUNCTION(0x0, "gpio_in"),
SUNXI_FUNCTION(0x1, "gpio_out"),
- SUNXI_FUNCTION(0x2, "uart2"), /* RTS */
+ SUNXI_FUNCTION(0x2, "uart1"), /* RTS */
SUNXI_FUNCTION_IRQ_BANK(0x4, 2, 8)), /* PG_EINT8 */
SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 9),
SUNXI_FUNCTION(0x0, "gpio_in"),
SUNXI_FUNCTION(0x1, "gpio_out"),
- SUNXI_FUNCTION(0x2, "uart2"), /* CTS */
+ SUNXI_FUNCTION(0x2, "uart1"), /* CTS */
SUNXI_FUNCTION_IRQ_BANK(0x4, 2, 9)), /* PG_EINT9 */
SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 10),
SUNXI_FUNCTION(0x0, "gpio_in"),
SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 8),
SUNXI_FUNCTION(0x0, "gpio_in"),
SUNXI_FUNCTION(0x1, "gpio_out"),
- SUNXI_FUNCTION(0x2, "uart2"), /* RTS */
+ SUNXI_FUNCTION(0x2, "uart1"), /* RTS */
SUNXI_FUNCTION_IRQ_BANK(0x4, 1, 8)), /* PG_EINT8 */
SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 9),
SUNXI_FUNCTION(0x0, "gpio_in"),
SUNXI_FUNCTION(0x1, "gpio_out"),
- SUNXI_FUNCTION(0x2, "uart2"), /* CTS */
+ SUNXI_FUNCTION(0x2, "uart1"), /* CTS */
SUNXI_FUNCTION_IRQ_BANK(0x4, 1, 9)), /* PG_EINT9 */
SUNXI_PIN(SUNXI_PINCTRL_PIN(G, 10),
SUNXI_FUNCTION(0x0, "gpio_in"),
/*
* Generic driver for the OLPC Embedded Controller.
*
+ * Author: Andres Salomon <dilinger@queued.net>
+ *
* Copyright (C) 2011-2012 One Laptop per Child Foundation.
*
* Licensed under the GPL v2 or later.
#include <linux/platform_device.h>
#include <linux/slab.h>
#include <linux/workqueue.h>
-#include <linux/module.h>
+#include <linux/init.h>
#include <linux/list.h>
#include <linux/olpc-ec.h>
#include <asm/olpc.h>
{
return platform_driver_register(&olpc_ec_plat_driver);
}
-
arch_initcall(olpc_ec_init_module);
-
-MODULE_AUTHOR("Andres Salomon <dilinger@queued.net>");
-MODULE_LICENSE("GPL");
/* BIOS error detected */
{ KE_IGNORE, 0xe00d, { KEY_RESERVED } },
- /* Unknown, defined in ACPI DSDT */
- /* { KE_IGNORE, 0xe00e, { KEY_RESERVED } }, */
+ /* Battery was removed or inserted */
+ { KE_IGNORE, 0xe00e, { KEY_RESERVED } },
/* Wifi Catcher */
{ KE_KEY, 0xe011, { KEY_PROG2 } },
/* Moorestown PMIC GPIO (access through IPC) driver
* Copyright (c) 2008 - 2009, Intel Corporation.
*
+ * Author: Alek Du <alek.du@intel.com>
+ *
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
#define pr_fmt(fmt) "%s: " fmt, __func__
-#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
{
return platform_driver_register(&platform_pmic_gpio_driver);
}
-
subsys_initcall(platform_pmic_gpio_init);
-
-MODULE_AUTHOR("Alek Du <alek.du@intel.com>");
-MODULE_DESCRIPTION("Intel Moorestown PMIC GPIO driver");
-MODULE_LICENSE("GPL v2");
}
static inline void max17042_read_model_data(struct max17042_chip *chip,
- u8 addr, u32 *data, int size)
+ u8 addr, u16 *data, int size)
{
struct regmap *map = chip->regmap;
int i;
+ u32 tmp;
- for (i = 0; i < size; i++)
- regmap_read(map, addr + i, &data[i]);
+ for (i = 0; i < size; i++) {
+ regmap_read(map, addr + i, &tmp);
+ data[i] = (u16)tmp;
+ }
}
static inline int max17042_model_data_compare(struct max17042_chip *chip,
{
int ret;
int table_size = ARRAY_SIZE(chip->pdata->config_data->cell_char_tbl);
- u32 *temp_data;
+ u16 *temp_data;
temp_data = kcalloc(table_size, sizeof(*temp_data), GFP_KERNEL);
if (!temp_data)
ret = max17042_model_data_compare(
chip,
chip->pdata->config_data->cell_char_tbl,
- (u16 *)temp_data,
+ temp_data,
table_size);
max10742_lock_model(chip);
{
int i;
int table_size = ARRAY_SIZE(chip->pdata->config_data->cell_char_tbl);
- u32 *temp_data;
+ u16 *temp_data;
int ret = 0;
temp_data = kcalloc(table_size, sizeof(*temp_data), GFP_KERNEL);
config SYSCON_REBOOT_MODE
tristate "Generic SYSCON regmap reboot mode driver"
depends on OF
+ depends on MFD_SYSCON
select REBOOT_MODE
- select MFD_SYSCON
help
Say y here will enable reboot mode driver. This will
get reboot mode arguments and store it in SYSCON mapped
if (of_property_read_u32(np, "reboot-offset", &reboot_offset) < 0) {
pr_err("failed to find reboot-offset property\n");
+ iounmap(base);
return -EINVAL;
}
err = register_restart_handler(&hisi_restart_nb);
- if (err)
+ if (err) {
dev_err(&pdev->dev, "cannot register restart handler (err=%d)\n",
err);
+ iounmap(base);
+ }
return err;
}
if (!charger)
return -ENOMEM;
+ platform_set_drvdata(pdev, charger);
charger->tps = tps;
charger->dev = &pdev->dev;
} else if (ibw_start < (ib_win->rstart + ib_win->size) &&
(ibw_start + ibw_size) > ib_win->rstart) {
/* Return error if address translation involved */
- if (direct && ib_win->xlat) {
+ if (!direct || ib_win->xlat) {
ret = -EFAULT;
break;
}
static struct rio_channel *riocm_ch_accept(u16 ch_id, u16 *new_ch_id,
long timeout)
{
- struct rio_channel *ch = NULL;
- struct rio_channel *new_ch = NULL;
+ struct rio_channel *ch;
+ struct rio_channel *new_ch;
struct conn_req *req;
struct cm_peer *peer;
int found = 0;
spin_unlock_bh(&ch->lock);
riocm_put_channel(ch);
+ ch = NULL;
kfree(req);
down_read(&rdev_sem);
if (!found) {
/* If peer device object not found, simply ignore the request */
err = -ENODEV;
- goto err_nodev;
+ goto err_put_new_ch;
}
new_ch->rdev = peer->rdev;
*new_ch_id = new_ch->id;
return new_ch;
+
+err_put_new_ch:
+ spin_lock_bh(&idr_lock);
+ idr_remove(&ch_idr, new_ch->id);
+ spin_unlock_bh(&idr_lock);
+ riocm_put_channel(new_ch);
+
err_put:
- riocm_put_channel(ch);
-err_nodev:
- if (new_ch) {
- spin_lock_bh(&idr_lock);
- idr_remove(&ch_idr, new_ch->id);
- spin_unlock_bh(&idr_lock);
- riocm_put_channel(new_ch);
- }
+ if (ch)
+ riocm_put_channel(ch);
*new_ch_id = 0;
return ERR_PTR(err);
}
{
struct rio_channel *ch;
unsigned int i;
+ LIST_HEAD(list);
riocm_debug(EXIT, ".");
+ /*
+ * If there are any channels left in connected state send
+ * close notification to the connection partner.
+ * First build a list of channels that require a closing
+ * notification because function riocm_send_close() should
+ * be called outside of spinlock protected code.
+ */
spin_lock_bh(&idr_lock);
idr_for_each_entry(&ch_idr, ch, i) {
- riocm_debug(EXIT, "close ch %d", ch->id);
- if (ch->state == RIO_CM_CONNECTED)
- riocm_send_close(ch);
+ if (ch->state == RIO_CM_CONNECTED) {
+ riocm_debug(EXIT, "close ch %d", ch->id);
+ idr_remove(&ch_idr, ch->id);
+ list_add(&ch->ch_node, &list);
+ }
}
spin_unlock_bh(&idr_lock);
+ list_for_each_entry(ch, &list, ch_node)
+ riocm_send_close(ch);
+
return NOTIFY_DONE;
}
* max14577.c - Regulator driver for the Maxim 14577/77836
*
* Copyright (C) 2013,2014 Samsung Electronics
- * Krzysztof Kozlowski <k.kozlowski@samsung.com>
+ * Krzysztof Kozlowski <krzk@kernel.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
}
module_exit(max14577_regulator_exit);
-MODULE_AUTHOR("Krzysztof Kozlowski <k.kozlowski@samsung.com>");
+MODULE_AUTHOR("Krzysztof Kozlowski <krzk@kernel.org>");
MODULE_DESCRIPTION("Maxim 14577/77836 regulator driver");
MODULE_LICENSE("GPL");
MODULE_ALIAS("platform:max14577-regulator");
*
* Copyright (C) 2013-2015 Samsung Electronics
* Jonghwa Lee <jonghwa3.lee@samsung.com>
- * Krzysztof Kozlowski <k.kozlowski.k@gmail.com>
+ * Krzysztof Kozlowski <krzk@kernel.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
MODULE_DESCRIPTION("MAXIM 77693/77843 regulator driver");
MODULE_AUTHOR("Jonghwa Lee <jonghwa3.lee@samsung.com>");
-MODULE_AUTHOR("Krzysztof Kozlowski <k.kozlowski.k@gmail.com>");
+MODULE_AUTHOR("Krzysztof Kozlowski <krzk@kernel.org>");
MODULE_LICENSE("GPL");
static const struct regulator_desc pma8084_ftsmps = {
.linear_ranges = (struct regulator_linear_range[]) {
REGULATOR_LINEAR_RANGE(350000, 0, 184, 5000),
- REGULATOR_LINEAR_RANGE(700000, 185, 339, 10000),
+ REGULATOR_LINEAR_RANGE(1280000, 185, 261, 10000),
},
.n_linear_ranges = 2,
- .n_voltages = 340,
+ .n_voltages = 262,
.ops = &rpm_smps_ldo_ops,
};
static const struct regulator_desc pma8084_pldo = {
.linear_ranges = (struct regulator_linear_range[]) {
- REGULATOR_LINEAR_RANGE(750000, 0, 30, 25000),
- REGULATOR_LINEAR_RANGE(1500000, 31, 99, 50000),
+ REGULATOR_LINEAR_RANGE( 750000, 0, 63, 12500),
+ REGULATOR_LINEAR_RANGE(1550000, 64, 126, 25000),
+ REGULATOR_LINEAR_RANGE(3100000, 127, 163, 50000),
},
- .n_linear_ranges = 2,
- .n_voltages = 100,
+ .n_linear_ranges = 3,
+ .n_voltages = 164,
.ops = &rpm_smps_ldo_ops,
};
static const struct regulator_desc pm8841_ftsmps = {
.linear_ranges = (struct regulator_linear_range[]) {
REGULATOR_LINEAR_RANGE(350000, 0, 184, 5000),
- REGULATOR_LINEAR_RANGE(700000, 185, 339, 10000),
+ REGULATOR_LINEAR_RANGE(1280000, 185, 261, 10000),
},
.n_linear_ranges = 2,
- .n_voltages = 340,
+ .n_voltages = 262,
.ops = &rpm_smps_ldo_ops,
};
static const struct regulator_desc pm8941_boost = {
.linear_ranges = (struct regulator_linear_range[]) {
- REGULATOR_LINEAR_RANGE(4000000, 0, 15, 100000),
+ REGULATOR_LINEAR_RANGE(4000000, 0, 30, 50000),
},
.n_linear_ranges = 1,
- .n_voltages = 16,
+ .n_voltages = 31,
.ops = &rpm_smps_ldo_ops,
};
static const struct regulator_desc pm8941_pldo = {
.linear_ranges = (struct regulator_linear_range[]) {
- REGULATOR_LINEAR_RANGE( 750000, 0, 30, 25000),
- REGULATOR_LINEAR_RANGE(1500000, 31, 99, 50000),
+ REGULATOR_LINEAR_RANGE( 750000, 0, 63, 12500),
+ REGULATOR_LINEAR_RANGE(1550000, 64, 126, 25000),
+ REGULATOR_LINEAR_RANGE(3100000, 127, 163, 50000),
},
- .n_linear_ranges = 2,
- .n_voltages = 100,
+ .n_linear_ranges = 3,
+ .n_voltages = 164,
.ops = &rpm_smps_ldo_ops,
};
u8 *sense = NULL;
int expires;
+ cqr = (struct dasd_ccw_req *) intparm;
if (IS_ERR(irb)) {
switch (PTR_ERR(irb)) {
case -EIO:
+ if (cqr && cqr->status == DASD_CQR_CLEAR_PENDING) {
+ device = (struct dasd_device *) cqr->startdev;
+ cqr->status = DASD_CQR_CLEARED;
+ dasd_device_clear_timer(device);
+ wake_up(&dasd_flush_wq);
+ dasd_schedule_device_bh(device);
+ return;
+ }
break;
case -ETIMEDOUT:
DBF_EVENT_DEVID(DBF_WARNING, cdev, "%s: "
}
now = get_tod_clock();
- cqr = (struct dasd_ccw_req *) intparm;
/* check for conditions that should be handled immediately */
if (!cqr ||
!(scsw_dstat(&irb->scsw) == (DEV_STAT_CHN_END | DEV_STAT_DEV_END) &&
return PTR_ERR(cqr);
}
+ cqr->lpm = lpum;
+retry:
cqr->startdev = device;
cqr->memdev = device;
cqr->block = NULL;
(prssdp + 1);
memcpy(messages, message_buf,
sizeof(struct dasd_rssd_messages));
+ } else if (cqr->lpm) {
+ /*
+ * on z/VM we might not be able to do I/O on the requested path
+ * but instead we get the required information on any path
+ * so retry with open path mask
+ */
+ cqr->lpm = 0;
+ goto retry;
} else
DBF_EVENT_DEVID(DBF_WARNING, device->cdev,
"Reading messages failed with rc=%d\n"
priv->state = DEV_STATE_NOT_OPER;
priv->dev_id.devno = sch->schib.pmcw.dev;
priv->dev_id.ssid = sch->schid.ssid;
- priv->schid = sch->schid;
INIT_WORK(&priv->todo_work, ccw_device_todo);
INIT_LIST_HEAD(&priv->cmb_list);
put_device(&old_sch->dev);
/* Initialize new subchannel. */
spin_lock_irq(sch->lock);
- cdev->private->schid = sch->schid;
cdev->ccwlock = sch->lock;
if (!sch_is_pseudo_sch(sch))
sch_set_cdev(sch, cdev);
static void
ccw_device_msg_control_check(struct ccw_device *cdev, struct irb *irb)
{
+ struct subchannel *sch = to_subchannel(cdev->dev.parent);
char dbf_text[15];
if (!scsw_is_valid_cstat(&irb->scsw) ||
"received"
" ... device %04x on subchannel 0.%x.%04x, dev_stat "
": %02X sch_stat : %02X\n",
- cdev->private->dev_id.devno, cdev->private->schid.ssid,
- cdev->private->schid.sch_no,
+ cdev->private->dev_id.devno, sch->schid.ssid,
+ sch->schid.sch_no,
scsw_dstat(&irb->scsw), scsw_cstat(&irb->scsw));
- sprintf(dbf_text, "chk%x", cdev->private->schid.sch_no);
+ sprintf(dbf_text, "chk%x", sch->schid.sch_no);
CIO_TRACE_EVENT(0, dbf_text);
CIO_HEX_EVENT(0, irb, sizeof(struct irb));
}
int state; /* device state */
atomic_t onoff;
struct ccw_dev_id dev_id; /* device id */
- struct subchannel_id schid; /* subchannel number */
struct ccw_request req; /* internal I/O request */
int iretry;
u8 pgid_valid_mask; /* mask of valid PGIDs */
q->qdio_error = 0;
}
+static inline int qdio_tasklet_schedule(struct qdio_q *q)
+{
+ if (likely(q->irq_ptr->state == QDIO_IRQ_STATE_ACTIVE)) {
+ tasklet_schedule(&q->tasklet);
+ return 0;
+ }
+ return -EPERM;
+}
+
static void __qdio_inbound_processing(struct qdio_q *q)
{
qperf_inc(q, tasklet_inbound);
if (!qdio_inbound_q_done(q)) {
/* means poll time is not yet over */
qperf_inc(q, tasklet_inbound_resched);
- if (likely(q->irq_ptr->state != QDIO_IRQ_STATE_STOPPED)) {
- tasklet_schedule(&q->tasklet);
+ if (!qdio_tasklet_schedule(q))
return;
- }
}
qdio_stop_polling(q);
*/
if (!qdio_inbound_q_done(q)) {
qperf_inc(q, tasklet_inbound_resched2);
- if (likely(q->irq_ptr->state != QDIO_IRQ_STATE_STOPPED))
- tasklet_schedule(&q->tasklet);
+ qdio_tasklet_schedule(q);
}
}
* is noticed and outbound_handler is called after some time.
*/
if (qdio_outbound_q_done(q))
- del_timer(&q->u.out.timer);
+ del_timer_sync(&q->u.out.timer);
else
- if (!timer_pending(&q->u.out.timer))
+ if (!timer_pending(&q->u.out.timer) &&
+ likely(q->irq_ptr->state == QDIO_IRQ_STATE_ACTIVE))
mod_timer(&q->u.out.timer, jiffies + 10 * HZ);
return;
sched:
- if (unlikely(q->irq_ptr->state == QDIO_IRQ_STATE_STOPPED))
- return;
- tasklet_schedule(&q->tasklet);
+ qdio_tasklet_schedule(q);
}
/* outbound tasklet */
{
struct qdio_q *q = (struct qdio_q *)data;
- if (unlikely(q->irq_ptr->state == QDIO_IRQ_STATE_STOPPED))
- return;
- tasklet_schedule(&q->tasklet);
+ qdio_tasklet_schedule(q);
}
static inline void qdio_check_outbound_after_thinint(struct qdio_q *q)
for_each_output_queue(q->irq_ptr, out, i)
if (!qdio_outbound_q_done(out))
- tasklet_schedule(&out->tasklet);
+ qdio_tasklet_schedule(out);
}
static void __tiqdio_inbound_processing(struct qdio_q *q)
if (!qdio_inbound_q_done(q)) {
qperf_inc(q, tasklet_inbound_resched);
- if (likely(q->irq_ptr->state != QDIO_IRQ_STATE_STOPPED)) {
- tasklet_schedule(&q->tasklet);
+ if (!qdio_tasklet_schedule(q))
return;
- }
}
qdio_stop_polling(q);
*/
if (!qdio_inbound_q_done(q)) {
qperf_inc(q, tasklet_inbound_resched2);
- if (likely(q->irq_ptr->state != QDIO_IRQ_STATE_STOPPED))
- tasklet_schedule(&q->tasklet);
+ qdio_tasklet_schedule(q);
}
}
int i;
struct qdio_q *q;
- if (unlikely(irq_ptr->state == QDIO_IRQ_STATE_STOPPED))
+ if (unlikely(irq_ptr->state != QDIO_IRQ_STATE_ACTIVE))
return;
for_each_input_queue(irq_ptr, q, i) {
continue;
if (need_siga_sync(q) && need_siga_sync_out_after_pci(q))
qdio_siga_sync_q(q);
- tasklet_schedule(&q->tasklet);
+ qdio_tasklet_schedule(q);
}
}
struct irb *irb)
{
struct qdio_irq *irq_ptr = cdev->private->qdio_data;
+ struct subchannel_id schid;
int cstat, dstat;
if (!intparm || !irq_ptr) {
- DBF_ERROR("qint:%4x", cdev->private->schid.sch_no);
+ ccw_device_get_schid(cdev, &schid);
+ DBF_ERROR("qint:%4x", schid.sch_no);
return;
}
int qdio_get_ssqd_desc(struct ccw_device *cdev,
struct qdio_ssqd_desc *data)
{
+ struct subchannel_id schid;
if (!cdev || !cdev->private)
return -EINVAL;
- DBF_EVENT("get ssqd:%4x", cdev->private->schid.sch_no);
- return qdio_setup_get_ssqd(NULL, &cdev->private->schid, data);
+ ccw_device_get_schid(cdev, &schid);
+ DBF_EVENT("get ssqd:%4x", schid.sch_no);
+ return qdio_setup_get_ssqd(NULL, &schid, data);
}
EXPORT_SYMBOL_GPL(qdio_get_ssqd_desc);
tasklet_kill(&q->tasklet);
for_each_output_queue(irq_ptr, q, i) {
- del_timer(&q->u.out.timer);
+ del_timer_sync(&q->u.out.timer);
tasklet_kill(&q->tasklet);
}
}
int qdio_shutdown(struct ccw_device *cdev, int how)
{
struct qdio_irq *irq_ptr = cdev->private->qdio_data;
+ struct subchannel_id schid;
int rc;
- unsigned long flags;
if (!irq_ptr)
return -ENODEV;
WARN_ON_ONCE(irqs_disabled());
- DBF_EVENT("qshutdown:%4x", cdev->private->schid.sch_no);
+ ccw_device_get_schid(cdev, &schid);
+ DBF_EVENT("qshutdown:%4x", schid.sch_no);
mutex_lock(&irq_ptr->setup_mutex);
/*
qdio_shutdown_debug_entries(irq_ptr);
/* cleanup subchannel */
- spin_lock_irqsave(get_ccwdev_lock(cdev), flags);
+ spin_lock_irq(get_ccwdev_lock(cdev));
if (how & QDIO_FLAG_CLEANUP_USING_CLEAR)
rc = ccw_device_clear(cdev, QDIO_DOING_CLEANUP);
}
qdio_set_state(irq_ptr, QDIO_IRQ_STATE_CLEANUP);
- spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
+ spin_unlock_irq(get_ccwdev_lock(cdev));
wait_event_interruptible_timeout(cdev->private->wait_q,
irq_ptr->state == QDIO_IRQ_STATE_INACTIVE ||
irq_ptr->state == QDIO_IRQ_STATE_ERR,
10 * HZ);
- spin_lock_irqsave(get_ccwdev_lock(cdev), flags);
+ spin_lock_irq(get_ccwdev_lock(cdev));
no_cleanup:
qdio_shutdown_thinint(irq_ptr);
/* restore interrupt handler */
if ((void *)cdev->handler == (void *)qdio_int_handler)
cdev->handler = irq_ptr->orig_handler;
- spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
+ spin_unlock_irq(get_ccwdev_lock(cdev));
qdio_set_state(irq_ptr, QDIO_IRQ_STATE_INACTIVE);
mutex_unlock(&irq_ptr->setup_mutex);
int qdio_free(struct ccw_device *cdev)
{
struct qdio_irq *irq_ptr = cdev->private->qdio_data;
+ struct subchannel_id schid;
if (!irq_ptr)
return -ENODEV;
- DBF_EVENT("qfree:%4x", cdev->private->schid.sch_no);
+ ccw_device_get_schid(cdev, &schid);
+ DBF_EVENT("qfree:%4x", schid.sch_no);
DBF_DEV_EVENT(DBF_ERR, irq_ptr, "dbf abandoned");
mutex_lock(&irq_ptr->setup_mutex);
*/
int qdio_allocate(struct qdio_initialize *init_data)
{
+ struct subchannel_id schid;
struct qdio_irq *irq_ptr;
- DBF_EVENT("qallocate:%4x", init_data->cdev->private->schid.sch_no);
+ ccw_device_get_schid(init_data->cdev, &schid);
+ DBF_EVENT("qallocate:%4x", schid.sch_no);
if ((init_data->no_input_qs && !init_data->input_handler) ||
(init_data->no_output_qs && !init_data->output_handler))
*/
int qdio_establish(struct qdio_initialize *init_data)
{
- struct qdio_irq *irq_ptr;
struct ccw_device *cdev = init_data->cdev;
- unsigned long saveflags;
+ struct subchannel_id schid;
+ struct qdio_irq *irq_ptr;
int rc;
- DBF_EVENT("qestablish:%4x", cdev->private->schid.sch_no);
+ ccw_device_get_schid(cdev, &schid);
+ DBF_EVENT("qestablish:%4x", schid.sch_no);
irq_ptr = cdev->private->qdio_data;
if (!irq_ptr)
return -ENODEV;
- if (cdev->private->state != DEV_STATE_ONLINE)
- return -EINVAL;
-
mutex_lock(&irq_ptr->setup_mutex);
qdio_setup_irq(init_data);
irq_ptr->ccw.count = irq_ptr->equeue.count;
irq_ptr->ccw.cda = (u32)((addr_t)irq_ptr->qdr);
- spin_lock_irqsave(get_ccwdev_lock(cdev), saveflags);
+ spin_lock_irq(get_ccwdev_lock(cdev));
ccw_device_set_options_mask(cdev, 0);
rc = ccw_device_start(cdev, &irq_ptr->ccw, QDIO_DOING_ESTABLISH, 0, 0);
+ spin_unlock_irq(get_ccwdev_lock(cdev));
if (rc) {
DBF_ERROR("%4x est IO ERR", irq_ptr->schid.sch_no);
DBF_ERROR("rc:%4x", rc);
- }
- spin_unlock_irqrestore(get_ccwdev_lock(cdev), saveflags);
-
- if (rc) {
mutex_unlock(&irq_ptr->setup_mutex);
qdio_shutdown(cdev, QDIO_FLAG_CLEANUP_USING_CLEAR);
return rc;
*/
int qdio_activate(struct ccw_device *cdev)
{
+ struct subchannel_id schid;
struct qdio_irq *irq_ptr;
int rc;
- unsigned long saveflags;
- DBF_EVENT("qactivate:%4x", cdev->private->schid.sch_no);
+ ccw_device_get_schid(cdev, &schid);
+ DBF_EVENT("qactivate:%4x", schid.sch_no);
irq_ptr = cdev->private->qdio_data;
if (!irq_ptr)
return -ENODEV;
- if (cdev->private->state != DEV_STATE_ONLINE)
- return -EINVAL;
-
mutex_lock(&irq_ptr->setup_mutex);
if (irq_ptr->state == QDIO_IRQ_STATE_INACTIVE) {
rc = -EBUSY;
irq_ptr->ccw.count = irq_ptr->aqueue.count;
irq_ptr->ccw.cda = 0;
- spin_lock_irqsave(get_ccwdev_lock(cdev), saveflags);
+ spin_lock_irq(get_ccwdev_lock(cdev));
ccw_device_set_options(cdev, CCWDEV_REPORT_ALL);
rc = ccw_device_start(cdev, &irq_ptr->ccw, QDIO_DOING_ACTIVATE,
0, DOIO_DENY_PREFETCH);
+ spin_unlock_irq(get_ccwdev_lock(cdev));
if (rc) {
DBF_ERROR("%4x act IO ERR", irq_ptr->schid.sch_no);
DBF_ERROR("rc:%4x", rc);
- }
- spin_unlock_irqrestore(get_ccwdev_lock(cdev), saveflags);
-
- if (rc)
goto out;
+ }
if (is_thinint_irq(irq_ptr))
tiqdio_add_input_queues(irq_ptr);
/* in case of SIGA errors we must process the error immediately */
if (used >= q->u.out.scan_threshold || rc)
- tasklet_schedule(&q->tasklet);
+ qdio_tasklet_schedule(q);
else
/* free the SBALs in case of no further traffic */
- if (!timer_pending(&q->u.out.timer))
+ if (!timer_pending(&q->u.out.timer) &&
+ likely(q->irq_ptr->state == QDIO_IRQ_STATE_ACTIVE))
mod_timer(&q->u.out.timer, jiffies + HZ);
return rc;
}
__u16, __u16,
enum qeth_prot_versions);
int qeth_set_features(struct net_device *, netdev_features_t);
+int qeth_recover_features(struct net_device *);
netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t);
/* exports for OSN */
int e;
e = 0;
- while (buffer->element[e].addr) {
+ while ((e < QDIO_MAX_ELEMENTS_PER_BUFFER) &&
+ buffer->element[e].addr) {
unsigned long phys_aob_addr;
phys_aob_addr = (unsigned long) buffer->element[e].addr;
return rc;
}
+/* try to restore device features on a device after recovery */
+int qeth_recover_features(struct net_device *dev)
+{
+ struct qeth_card *card = dev->ml_priv;
+ netdev_features_t recover = dev->features;
+
+ if (recover & NETIF_F_IP_CSUM) {
+ if (qeth_set_ipa_csum(card, 1, IPA_OUTBOUND_CHECKSUM))
+ recover ^= NETIF_F_IP_CSUM;
+ }
+ if (recover & NETIF_F_RXCSUM) {
+ if (qeth_set_ipa_csum(card, 1, IPA_INBOUND_CHECKSUM))
+ recover ^= NETIF_F_RXCSUM;
+ }
+ if (recover & NETIF_F_TSO) {
+ if (qeth_set_ipa_tso(card, 1))
+ recover ^= NETIF_F_TSO;
+ }
+
+ if (recover == dev->features)
+ return 0;
+
+ dev_warn(&card->gdev->dev,
+ "Device recovery failed to restore all offload features\n");
+ dev->features = recover;
+ return -EIO;
+}
+EXPORT_SYMBOL_GPL(qeth_recover_features);
+
int qeth_set_features(struct net_device *dev, netdev_features_t features)
{
struct qeth_card *card = dev->ml_priv;
card->dev->hw_features |= NETIF_F_RXCSUM;
card->dev->vlan_features |= NETIF_F_RXCSUM;
}
- /* Turn on SG per default */
- card->dev->features |= NETIF_F_SG;
}
card->info.broadcast_capable = 1;
qeth_l2_request_initial_mac(card);
card->dev->gso_max_size = (QETH_MAX_BUFFER_ELEMENTS(card) - 1) *
PAGE_SIZE;
- card->dev->gso_max_segs = (QETH_MAX_BUFFER_ELEMENTS(card) - 1);
SET_NETDEV_DEV(card->dev, &card->gdev->dev);
netif_napi_add(card->dev, &card->napi, qeth_l2_poll, QETH_NAPI_WEIGHT);
netif_carrier_off(card->dev);
}
/* this also sets saved unicast addresses */
qeth_l2_set_rx_mode(card->dev);
+ rtnl_lock();
+ qeth_recover_features(card->dev);
+ rtnl_unlock();
}
/* let user_space know that device is online */
kobject_uevent(&gdev->dev.kobj, KOBJ_CHANGE);
if (addr->in_progress)
return -EINPROGRESS;
+ if (!qeth_card_hw_is_reachable(card)) {
+ addr->disp_flag = QETH_DISP_ADDR_DELETE;
+ return 0;
+ }
+
rc = qeth_l3_deregister_addr_entry(card, addr);
hash_del(&addr->hnode);
hash_add(card->ip_htable, &addr->hnode,
qeth_l3_ipaddr_hash(addr));
+ if (!qeth_card_hw_is_reachable(card)) {
+ addr->disp_flag = QETH_DISP_ADDR_ADD;
+ return 0;
+ }
+
/* qeth_l3_register_addr_entry can go to sleep
* if we add a IPV4 addr. It is caused by the reason
* that SETIP ipa cmd starts ARP staff for IPV4 addr.
int i;
int rc;
- QETH_CARD_TEXT(card, 4, "recoverip");
+ QETH_CARD_TEXT(card, 4, "recovrip");
spin_lock_bh(&card->ip_lock);
hash_for_each_safe(card->ip_htable, i, tmp, addr, hnode) {
- if (addr->disp_flag == QETH_DISP_ADDR_ADD) {
+ if (addr->disp_flag == QETH_DISP_ADDR_DELETE) {
+ qeth_l3_deregister_addr_entry(card, addr);
+ hash_del(&addr->hnode);
+ kfree(addr);
+ } else if (addr->disp_flag == QETH_DISP_ADDR_ADD) {
if (addr->proto == QETH_PROT_IPV4) {
addr->in_progress = 1;
spin_unlock_bh(&card->ip_lock);
if (!rc) {
addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
- if (addr->ref_counter < 1) {
+ if (addr->ref_counter < 1)
qeth_l3_delete_ip(card, addr);
- kfree(addr);
- }
} else {
hash_del(&addr->hnode);
kfree(addr);
spin_lock_bh(&card->ip_lock);
- if (!qeth_l3_ip_from_hash(card, ipaddr))
+ if (qeth_l3_ip_from_hash(card, ipaddr))
rc = -EEXIST;
else
qeth_l3_add_ip(card, ipaddr);
spin_lock_bh(&card->ip_lock);
- if (!qeth_l3_ip_from_hash(card, ipaddr))
+ if (qeth_l3_ip_from_hash(card, ipaddr))
rc = -EEXIST;
else
qeth_l3_add_ip(card, ipaddr);
card->dev->vlan_features = NETIF_F_SG |
NETIF_F_RXCSUM | NETIF_F_IP_CSUM |
NETIF_F_TSO;
- card->dev->features = NETIF_F_SG;
}
}
} else if (card->info.type == QETH_CARD_TYPE_IQD) {
netif_keep_dst(card->dev);
card->dev->gso_max_size = (QETH_MAX_BUFFER_ELEMENTS(card) - 1) *
PAGE_SIZE;
- card->dev->gso_max_segs = (QETH_MAX_BUFFER_ELEMENTS(card) - 1);
SET_NETDEV_DEV(card->dev, &card->gdev->dev);
netif_napi_add(card->dev, &card->napi, qeth_l3_poll, QETH_NAPI_WEIGHT);
else
dev_open(card->dev);
qeth_l3_set_multicast_list(card->dev);
+ qeth_recover_features(card->dev);
rtnl_unlock();
}
qeth_trace_features(card);
addr->u.a6.pfxlen = 0;
addr->type = QETH_IP_TYPE_NORMAL;
+ spin_lock_bh(&card->ip_lock);
qeth_l3_delete_ip(card, addr);
+ spin_unlock_bh(&card->ip_lock);
kfree(addr);
}
addr->type = QETH_IP_TYPE_NORMAL;
} else
return -ENOMEM;
+
+ spin_lock_bh(&card->ip_lock);
qeth_l3_add_ip(card, addr);
+ spin_unlock_bh(&card->ip_lock);
kfree(addr);
return count;
# it under the terms of the GNU General Public License (version 2 only)
# as published by the Free Software Foundation.
-obj-$(CONFIG_S390_GUEST) += kvm_virtio.o virtio_ccw.o
+s390-virtio-objs := virtio_ccw.o
+ifdef CONFIG_S390_GUEST_OLD_TRANSPORT
+s390-virtio-objs += kvm_virtio.o
+endif
+obj-$(CONFIG_S390_GUEST) += $(s390-virtio-objs)
if (test_devices_support(total_memory_size) < 0)
return -ENODEV;
+ pr_warn("The s390-virtio transport is deprecated. Please switch to a modern host providing virtio-ccw.\n");
+
rc = vmem_add_mapping(total_memory_size, PAGE_SIZE);
if (rc)
return rc;
}
/* code for early console output with virtio_console */
-static __init int early_put_chars(u32 vtermno, const char *buf, int count)
+static int early_put_chars(u32 vtermno, const char *buf, int count)
{
char scratch[17];
unsigned int len = count;
struct fib *fibptr;
struct hw_fib * hw_fib = (struct hw_fib *)0;
dma_addr_t hw_fib_pa = (dma_addr_t)0LL;
- unsigned size;
+ unsigned int size, osize;
int retval;
if (dev->in_reset) {
* will not overrun the buffer when we copy the memory. Return
* an error if we would.
*/
- size = le16_to_cpu(kfib->header.Size) + sizeof(struct aac_fibhdr);
+ osize = size = le16_to_cpu(kfib->header.Size) +
+ sizeof(struct aac_fibhdr);
if (size < le16_to_cpu(kfib->header.SenderSize))
size = le16_to_cpu(kfib->header.SenderSize);
if (size > dev->max_fib_size) {
goto cleanup;
}
+ /* Sanity check the second copy */
+ if ((osize != le16_to_cpu(kfib->header.Size) +
+ sizeof(struct aac_fibhdr))
+ || (size < le16_to_cpu(kfib->header.SenderSize))) {
+ retval = -EINVAL;
+ goto cleanup;
+ }
+
if (kfib->header.Command == cpu_to_le16(TakeABreakPt)) {
aac_adapter_interrupt(dev);
/*
/* Get sense key string or NULL if not available */
const char *
-scsi_sense_key_string(unsigned char key) {
- if (key <= 0xE)
+scsi_sense_key_string(unsigned char key)
+{
+ if (key < ARRAY_SIZE(snstext))
return snstext[key];
return NULL;
}
mutex_unlock(&fip->ctlr_mutex);
drop:
- kfree(skb);
+ kfree_skb(skb);
return rc;
}
__ipr_remove(pdev);
return rc;
}
+ spin_lock_irqsave(ioa_cfg->host->host_lock, flags);
+ ioa_cfg->scan_enabled = 1;
+ schedule_work(&ioa_cfg->work_q);
+ spin_unlock_irqrestore(ioa_cfg->host->host_lock, flags);
- scsi_scan_host(ioa_cfg->host);
ioa_cfg->iopoll_weight = ioa_cfg->chip_cfg->iopoll_weight;
if (ioa_cfg->iopoll_weight && ioa_cfg->sis64 && ioa_cfg->nvectors > 1) {
}
}
- spin_lock_irqsave(ioa_cfg->host->host_lock, flags);
- ioa_cfg->scan_enabled = 1;
- schedule_work(&ioa_cfg->work_q);
- spin_unlock_irqrestore(ioa_cfg->host->host_lock, flags);
+ scsi_scan_host(ioa_cfg->host);
+
return 0;
}
/* Find first memory bar */
bar_list = pci_select_bars(instance->pdev, IORESOURCE_MEM);
instance->bar = find_first_bit(&bar_list, sizeof(unsigned long));
- if (pci_request_selected_regions(instance->pdev, instance->bar,
+ if (pci_request_selected_regions(instance->pdev, 1<<instance->bar,
"megasas: LSI")) {
dev_printk(KERN_DEBUG, &instance->pdev->dev, "IO memory region busy!\n");
return -EBUSY;
iounmap(instance->reg_set);
fail_ioremap:
- pci_release_selected_regions(instance->pdev, instance->bar);
+ pci_release_selected_regions(instance->pdev, 1<<instance->bar);
return -EINVAL;
}
iounmap(instance->reg_set);
- pci_release_selected_regions(instance->pdev, instance->bar);
+ pci_release_selected_regions(instance->pdev, 1<<instance->bar);
}
/**
iounmap(instance->reg_set);
- pci_release_selected_regions(instance->pdev, instance->bar);
+ pci_release_selected_regions(instance->pdev, 1<<instance->bar);
}
/**
} else
ioc->msix96_vector = 0;
+ if (ioc->is_warpdrive) {
+ ioc->reply_post_host_index[0] = (resource_size_t __iomem *)
+ &ioc->chip->ReplyPostHostIndex;
+
+ for (i = 1; i < ioc->cpu_msix_table_sz; i++)
+ ioc->reply_post_host_index[i] =
+ (resource_size_t __iomem *)
+ ((u8 __iomem *)&ioc->chip->Doorbell + (0x4000 + ((i - 1)
+ * 4)));
+ }
+
list_for_each_entry(reply_q, &ioc->reply_queue_list, list)
pr_info(MPT3SAS_FMT "%s: IRQ %d\n",
reply_q->name, ((ioc->msix_enable) ? "PCI-MSI-X enabled" :
if (r)
goto out_free_resources;
- if (ioc->is_warpdrive) {
- ioc->reply_post_host_index[0] = (resource_size_t __iomem *)
- &ioc->chip->ReplyPostHostIndex;
-
- for (i = 1; i < ioc->cpu_msix_table_sz; i++)
- ioc->reply_post_host_index[i] =
- (resource_size_t __iomem *)
- ((u8 __iomem *)&ioc->chip->Doorbell + (0x4000 + ((i - 1)
- * 4)));
- }
-
pci_set_drvdata(ioc->pdev, ioc->shost);
r = _base_get_ioc_facts(ioc, CAN_SLEEP);
if (r)
{"IBM", "Universal Xport", "*", BLIST_NO_ULD_ATTACH},
{"SUN", "Universal Xport", "*", BLIST_NO_ULD_ATTACH},
{"DELL", "Universal Xport", "*", BLIST_NO_ULD_ATTACH},
+ {"STK", "Universal Xport", "*", BLIST_NO_ULD_ATTACH},
+ {"NETAPP", "Universal Xport", "*", BLIST_NO_ULD_ATTACH},
+ {"LSI", "Universal Xport", "*", BLIST_NO_ULD_ATTACH},
+ {"ENGENIO", "Universal Xport", "*", BLIST_NO_ULD_ATTACH},
{"SMSC", "USB 2 HS-CF", NULL, BLIST_SPARSELUN | BLIST_INQUIRY_36},
{"SONY", "CD-ROM CDU-8001", NULL, BLIST_BORKEN},
{"SONY", "TSL", NULL, BLIST_FORCELUN}, /* DDS3 & DDS4 autoloaders */
return 0;
}
-/**
- * is_sas_attached - check if device is SAS attached
- * @sdev: scsi device to check
- *
- * returns true if the device is SAS attached
- */
-int is_sas_attached(struct scsi_device *sdev)
-{
- struct Scsi_Host *shost = sdev->host;
-
- return shost->transportt->host_attrs.ac.class ==
- &sas_host_class.class;
-}
-EXPORT_SYMBOL(is_sas_attached);
-
-
/**
* sas_remove_children - tear down a devices SAS data structures
* @dev: device belonging to the sas object
ses_enclosure_data_process(edev, to_scsi_device(edev->edev.parent), 0);
- if (is_sas_attached(sdev))
+ if (scsi_is_sas_rphy(&sdev->sdev_gendev))
efd.addr = sas_get_address(sdev);
if (efd.addr) {
if (!edev)
return;
+ enclosure_unregister(edev);
+
ses_dev = edev->scratch;
edev->scratch = NULL;
kfree(edev->component[0].scratch);
put_device(&edev->edev);
- enclosure_unregister(edev);
}
static void ses_intf_remove(struct device *cdev,
scsi_host_put(sh);
}
-static DEFINE_PCI_DEVICE_TABLE(wd719x_pci_table) = {
+static const struct pci_device_id wd719x_pci_table[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_WD, 0x3296) },
{}
};
clk_disable_unprepare(spfi->sys_clk);
}
- spi_master_put(master);
-
return 0;
}
pm_runtime_disable(&pdev->dev);
mtk_spi_reset(mdata);
- spi_master_put(master);
return 0;
}
return PTR_ERR(ssp->clk);
memset(&pi, 0, sizeof(pi));
+ pi.fwnode = dev->dev.fwnode;
pi.parent = &dev->dev;
pi.name = "pxa2xx-spi";
pi.id = ssp->port_id;
pm_runtime_put_noidle(&pdev->dev);
pm_runtime_disable(&pdev->dev);
- spi_master_put(master);
return 0;
}
for (k = 0; k < ARRAY_SIZE(sh_msiof_spi_div_table); k++) {
brps = DIV_ROUND_UP(div, sh_msiof_spi_div_table[k].div);
+ /* SCR_BRDV_DIV_1 is valid only if BRPS is x 1/1 or x 1/2 */
+ if (sh_msiof_spi_div_table[k].div == 1 && brps > 2)
+ continue;
if (brps <= 32) /* max of brdv is 32 */
break;
}
struct spi_transfer *xfer;
bool keep_cs = false;
int ret = 0;
- unsigned long ms = 1;
+ unsigned long long ms = 1;
struct spi_statistics *statm = &master->statistics;
struct spi_statistics *stats = &msg->spi->statistics;
if (ret > 0) {
ret = 0;
- ms = xfer->len * 8 * 1000 / xfer->speed_hz;
+ ms = 8LL * 1000LL * xfer->len;
+ do_div(ms, xfer->speed_hz);
ms += ms + 100; /* some tolerance */
+ if (ms > UINT_MAX)
+ ms = UINT_MAX;
+
ms = wait_for_completion_timeout(&master->xfer_completion,
msecs_to_jiffies(ms));
}
if (ret < 0) {
dev_err(&master->dev, "Failed to power device: %d\n",
ret);
+ mutex_unlock(&master->io_mutex);
return;
}
}
if (master->auto_runtime_pm)
pm_runtime_put(master->dev.parent);
+ mutex_unlock(&master->io_mutex);
return;
}
}
break;
case CMDF_ROUND_DOWN:
divisor = ns / PCI1760_PWM_TIMEBASE;
+ break;
default:
return -EINVAL;
}
#define N_CHANS 8
-enum waveform_state_bits {
- WAVEFORM_AI_RUNNING,
- WAVEFORM_AO_RUNNING
-};
-
/* Data unique to this driver */
struct waveform_private {
struct timer_list ai_timer; /* timer for AI commands */
unsigned int wf_amplitude; /* waveform amplitude in microvolts */
unsigned int wf_period; /* waveform period in microseconds */
unsigned int wf_current; /* current time in waveform period */
- unsigned long state_bits;
unsigned int ai_scan_period; /* AI scan period in usec */
unsigned int ai_convert_period; /* AI conversion period in usec */
struct timer_list ao_timer; /* timer for AO commands */
unsigned int nsamples;
unsigned int time_increment;
- /* check command is still active */
- if (!test_bit(WAVEFORM_AI_RUNNING, &devpriv->state_bits))
- return;
-
now = ktime_to_us(ktime_get());
nsamples = comedi_nsamples_left(s, UINT_MAX);
*/
devpriv->ai_timer.expires =
jiffies + usecs_to_jiffies(devpriv->ai_convert_period) + 1;
-
- /* mark command as active */
- smp_mb__before_atomic();
- set_bit(WAVEFORM_AI_RUNNING, &devpriv->state_bits);
- smp_mb__after_atomic();
add_timer(&devpriv->ai_timer);
return 0;
}
{
struct waveform_private *devpriv = dev->private;
- /* mark command as no longer active */
- clear_bit(WAVEFORM_AI_RUNNING, &devpriv->state_bits);
- smp_mb__after_atomic();
- /* cannot call del_timer_sync() as may be called from timer routine */
- del_timer(&devpriv->ai_timer);
+ if (in_softirq()) {
+ /* Assume we were called from the timer routine itself. */
+ del_timer(&devpriv->ai_timer);
+ } else {
+ del_timer_sync(&devpriv->ai_timer);
+ }
return 0;
}
u64 scans_since;
unsigned int scans_avail = 0;
- /* check command is still active */
- if (!test_bit(WAVEFORM_AO_RUNNING, &devpriv->state_bits))
- return;
-
/* determine number of scan periods since last time */
now = ktime_to_us(ktime_get());
scans_since = now - devpriv->ao_last_scan_time;
devpriv->ao_last_scan_time = ktime_to_us(ktime_get());
devpriv->ao_timer.expires =
jiffies + usecs_to_jiffies(devpriv->ao_scan_period);
-
- /* mark command as active */
- smp_mb__before_atomic();
- set_bit(WAVEFORM_AO_RUNNING, &devpriv->state_bits);
- smp_mb__after_atomic();
add_timer(&devpriv->ao_timer);
return 1;
struct waveform_private *devpriv = dev->private;
s->async->inttrig = NULL;
- /* mark command as no longer active */
- clear_bit(WAVEFORM_AO_RUNNING, &devpriv->state_bits);
- smp_mb__after_atomic();
- /* cannot call del_timer_sync() as may be called from timer routine */
- del_timer(&devpriv->ao_timer);
+ if (in_softirq()) {
+ /* Assume we were called from the timer routine itself. */
+ del_timer(&devpriv->ao_timer);
+ } else {
+ del_timer_sync(&devpriv->ao_timer);
+ }
return 0;
}
const struct daq200_boardtype *board;
int i;
- if (pcidev->subsystem_device != PCI_VENDOR_ID_IOTECH)
+ if (pcidev->subsystem_vendor != PCI_VENDOR_ID_IOTECH)
return NULL;
for (i = 0; i < ARRAY_SIZE(boardtypes); i++) {
s = &dev->subdevices[0];
s->type = COMEDI_SUBD_AI;
s->subdev_flags = SDF_READABLE |
- (it->options[2] == 1) ? SDF_DIFF :
- (it->options[2] == 2) ? SDF_COMMON : SDF_GROUND;
+ ((it->options[2] == 1) ? SDF_DIFF :
+ (it->options[2] == 2) ? SDF_COMMON : SDF_GROUND);
s->n_chan = (it->options[2] == 1) ? 8 : 16;
s->maxdata = 0x0fff;
s->range_table = board->is_pgh ? &dt2811_pgh_ai_ranges
int i;
static const int timeout = 1000;
- if (trig_num != cmd->start_arg)
+ /*
+ * Require trig_num == cmd->start_arg when cmd->start_src == TRIG_INT.
+ * For backwards compatibility, also allow trig_num == 0 when
+ * cmd->start_src != TRIG_INT (i.e. when cmd->start_src == TRIG_EXT);
+ * in that case, the internal trigger is being used as a pre-trigger
+ * before the external trigger.
+ */
+ if (!(trig_num == cmd->start_arg ||
+ (trig_num == 0 && cmd->start_src != TRIG_INT)))
return -EINVAL;
/*
s->maxdata = (devpriv->is_m_series) ? 0xffffffff
: 0x00ffffff;
s->insn_read = ni_tio_insn_read;
- s->insn_write = ni_tio_insn_read;
+ s->insn_write = ni_tio_insn_write;
s->insn_config = ni_tio_insn_config;
#ifdef PCIDMA
if (dev->irq && devpriv->mite) {
mutex_lock(&indio_dev->mlock);
switch ((u32)this_attr->address) {
case AD5933_OUT_RANGE:
+ ret = -EINVAL;
for (i = 0; i < 4; i++)
if (val == st->range_avail[i]) {
st->ctrl_hb &= ~AD5933_CTRL_RANGE(0x3);
ret = ad5933_cmd(st, 0);
break;
}
- ret = -EINVAL;
break;
case AD5933_IN_PGA_GAIN:
if (sysfs_streq(buf, "1")) {
struct inode *inode = NULL;
__u64 bits = 0;
int rc = 0;
+ struct dentry *alias;
/* NB 1 request reference will be taken away by ll_intent_lock()
* when I return
*/
}
- /* Only hash *de if it is unhashed (new dentry).
- * Atoimc_open may passing hashed dentries for open.
- */
- if (d_unhashed(*de)) {
- struct dentry *alias;
-
- alias = ll_splice_alias(inode, *de);
- if (IS_ERR(alias)) {
- rc = PTR_ERR(alias);
- goto out;
- }
- *de = alias;
- } else if (!it_disposition(it, DISP_LOOKUP_NEG) &&
- !it_disposition(it, DISP_OPEN_CREATE)) {
- /* With DISP_OPEN_CREATE dentry will be
- * instantiated in ll_create_it.
- */
- LASSERT(!d_inode(*de));
- d_instantiate(*de, inode);
+ alias = ll_splice_alias(inode, *de);
+ if (IS_ERR(alias)) {
+ rc = PTR_ERR(alias);
+ goto out;
}
+ *de = alias;
if (!it_disposition(it, DISP_LOOKUP_NEG)) {
/* we have lookup look - unhide dentry */
dentry, PFID(ll_inode2fid(dir)), dir, file, open_flags, mode,
*opened);
+ /* Only negative dentries enter here */
+ LASSERT(!d_inode(dentry));
+
+ if (!d_in_lookup(dentry)) {
+ /* A valid negative dentry that just passed revalidation,
+ * there's little point to try and open it server-side,
+ * even though there's a minuscle chance it might succeed.
+ * Either way it's a valid race to just return -ENOENT here.
+ */
+ if (!(open_flags & O_CREAT))
+ return -ENOENT;
+
+ /* Otherwise we just unhash it to be rehashed afresh via
+ * lookup if necessary
+ */
+ d_drop(dentry);
+ }
+
it = kzalloc(sizeof(*it), GFP_NOFS);
if (!it)
return -ENOMEM;
Other TODOs:
+- There are two possible replies to CEC_MSG_INITIATE_ARC. How to handle that?
- Add a flag to inhibit passing CEC RC messages to the rc subsystem.
Applications should be able to choose this when calling S_LOG_ADDRS.
- If the reply field of cec_msg is set then when the reply arrives it
u64 ts = ktime_get_ns();
struct cec_fh *fh;
- mutex_lock(&adap->devnode.fhs_lock);
+ mutex_lock(&adap->devnode.lock);
list_for_each_entry(fh, &adap->devnode.fhs, list)
cec_queue_event_fh(fh, ev, ts);
- mutex_unlock(&adap->devnode.fhs_lock);
+ mutex_unlock(&adap->devnode.lock);
}
/*
u32 monitor_mode = valid_la ? CEC_MODE_MONITOR :
CEC_MODE_MONITOR_ALL;
- mutex_lock(&adap->devnode.fhs_lock);
+ mutex_lock(&adap->devnode.lock);
list_for_each_entry(fh, &adap->devnode.fhs, list) {
if (fh->mode_follower >= monitor_mode)
cec_queue_msg_fh(fh, msg);
}
- mutex_unlock(&adap->devnode.fhs_lock);
+ mutex_unlock(&adap->devnode.lock);
}
/*
{
struct cec_fh *fh;
- mutex_lock(&adap->devnode.fhs_lock);
+ mutex_lock(&adap->devnode.lock);
list_for_each_entry(fh, &adap->devnode.fhs, list) {
if (fh->mode_follower == CEC_MODE_FOLLOWER)
cec_queue_msg_fh(fh, msg);
}
- mutex_unlock(&adap->devnode.fhs_lock);
+ mutex_unlock(&adap->devnode.lock);
}
/* Notify userspace of an adapter state change. */
if (!valid_la || msg->len <= 1)
return;
+ if (adap->log_addrs.log_addr_mask == 0)
+ return;
+
/*
* Process the message on the protocol level. If is_reply is true,
* then cec_receive_notify() won't pass on the reply to the listener(s)
dprintk(1, "could not claim LA %d\n", i);
}
+ if (adap->log_addrs.log_addr_mask == 0 &&
+ !(las->flags & CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK))
+ goto unconfigure;
+
configured:
if (adap->log_addrs.log_addr_mask == 0) {
/* Fall back to unregistered */
las->log_addr[0] = CEC_LOG_ADDR_UNREGISTERED;
las->log_addr_mask = 1 << las->log_addr[0];
+ for (i = 1; i < las->num_log_addrs; i++)
+ las->log_addr[i] = CEC_LOG_ADDR_INVALID;
}
adap->is_configured = true;
adap->is_configuring = false;
cec_report_features(adap, i);
cec_report_phys_addr(adap, i);
}
+ for (i = las->num_log_addrs; i < CEC_MAX_LOG_ADDRS; i++)
+ las->log_addr[i] = CEC_LOG_ADDR_INVALID;
mutex_lock(&adap->lock);
adap->kthread_config = NULL;
mutex_unlock(&adap->lock);
u8 init_laddr = cec_msg_initiator(msg);
u8 devtype = cec_log_addr2dev(adap, dest_laddr);
int la_idx = cec_log_addr2idx(adap, dest_laddr);
- bool is_directed = la_idx >= 0;
bool from_unregistered = init_laddr == 0xf;
struct cec_msg tx_cec_msg = { };
* Unprocessed messages are aborted if userspace isn't doing
* any processing either.
*/
- if (is_directed && !is_reply && !adap->follower_cnt &&
+ if (!is_broadcast && !is_reply && !adap->follower_cnt &&
!adap->cec_follower && msg->msg[1] != CEC_MSG_FEATURE_ABORT)
return cec_feature_abort(adap, msg);
break;
return -ENOTTY;
if (copy_from_user(&log_addrs, parg, sizeof(log_addrs)))
return -EFAULT;
- log_addrs.flags = 0;
+ log_addrs.flags &= CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK;
mutex_lock(&adap->lock);
if (!adap->is_configuring &&
(!log_addrs.num_log_addrs || !adap->is_configured) &&
void __user *parg = (void __user *)arg;
if (!devnode->registered)
- return -EIO;
+ return -ENODEV;
switch (cmd) {
case CEC_ADAP_G_CAPS:
filp->private_data = fh;
- mutex_lock(&devnode->fhs_lock);
+ mutex_lock(&devnode->lock);
/* Queue up initial state events */
ev_state.state_change.phys_addr = adap->phys_addr;
ev_state.state_change.log_addr_mask = adap->log_addrs.log_addr_mask;
cec_queue_event_fh(fh, &ev_state, 0);
list_add(&fh->list, &devnode->fhs);
- mutex_unlock(&devnode->fhs_lock);
+ mutex_unlock(&devnode->lock);
return 0;
}
cec_monitor_all_cnt_dec(adap);
mutex_unlock(&adap->lock);
- mutex_lock(&devnode->fhs_lock);
+ mutex_lock(&devnode->lock);
list_del(&fh->list);
- mutex_unlock(&devnode->fhs_lock);
+ mutex_unlock(&devnode->lock);
/* Unhook pending transmits from this filehandle. */
mutex_lock(&adap->lock);
{
/*
* Check if the cec device is available. This needs to be done with
- * the cec_devnode_lock held to prevent an open/unregister race:
+ * the devnode->lock held to prevent an open/unregister race:
* without the lock, the device could be unregistered and freed between
* the devnode->registered check and get_device() calls, leading to
* a crash.
*/
- mutex_lock(&cec_devnode_lock);
+ mutex_lock(&devnode->lock);
/*
* return ENXIO if the cec device has been removed
* already or if it is not registered anymore.
*/
if (!devnode->registered) {
- mutex_unlock(&cec_devnode_lock);
+ mutex_unlock(&devnode->lock);
return -ENXIO;
}
/* and increase the device refcount */
get_device(&devnode->dev);
- mutex_unlock(&cec_devnode_lock);
+ mutex_unlock(&devnode->lock);
return 0;
}
void cec_put_device(struct cec_devnode *devnode)
{
- mutex_lock(&cec_devnode_lock);
put_device(&devnode->dev);
- mutex_unlock(&cec_devnode_lock);
}
/* Called when the last user of the cec device exits. */
struct cec_devnode *devnode = to_cec_devnode(cd);
mutex_lock(&cec_devnode_lock);
-
/* Mark device node number as free */
clear_bit(devnode->minor, cec_devnode_nums);
-
mutex_unlock(&cec_devnode_lock);
+
cec_delete_adapter(to_cec_adapter(devnode));
}
/* Initialization */
INIT_LIST_HEAD(&devnode->fhs);
- mutex_init(&devnode->fhs_lock);
+ mutex_init(&devnode->lock);
/* Part 1: Find a free minor number */
mutex_lock(&cec_devnode_lock);
cdev_del:
cdev_del(&devnode->cdev);
clr_bit:
+ mutex_lock(&cec_devnode_lock);
clear_bit(devnode->minor, cec_devnode_nums);
+ mutex_unlock(&cec_devnode_lock);
return ret;
}
{
struct cec_fh *fh;
+ mutex_lock(&devnode->lock);
+
/* Check if devnode was never registered or already unregistered */
- if (!devnode->registered || devnode->unregistered)
+ if (!devnode->registered || devnode->unregistered) {
+ mutex_unlock(&devnode->lock);
return;
+ }
- mutex_lock(&devnode->fhs_lock);
list_for_each_entry(fh, &devnode->fhs, list)
wake_up_interruptible(&fh->wait);
- mutex_unlock(&devnode->fhs_lock);
devnode->registered = false;
devnode->unregistered = true;
+ mutex_unlock(&devnode->lock);
+
device_del(&devnode->dev);
cdev_del(&devnode->cdev);
put_device(&devnode->dev);
cec_transmit_done(pulse8->adap, CEC_TX_STATUS_OK,
0, 0, 0, 0);
break;
- case MSGCODE_TRANSMIT_FAILED_LINE:
- cec_transmit_done(pulse8->adap, CEC_TX_STATUS_ARB_LOST,
- 1, 0, 0, 0);
- break;
case MSGCODE_TRANSMIT_FAILED_ACK:
cec_transmit_done(pulse8->adap, CEC_TX_STATUS_NACK,
0, 1, 0, 0);
break;
+ case MSGCODE_TRANSMIT_FAILED_LINE:
case MSGCODE_TRANSMIT_FAILED_TIMEOUT_DATA:
case MSGCODE_TRANSMIT_FAILED_TIMEOUT_LINE:
cec_transmit_done(pulse8->adap, CEC_TX_STATUS_ERROR,
case MSGCODE_TRANSMIT_FAILED_TIMEOUT_LINE:
schedule_work(&pulse8->work);
break;
+ case MSGCODE_HIGH_ERROR:
+ case MSGCODE_LOW_ERROR:
+ case MSGCODE_RECEIVE_FAILED:
case MSGCODE_TIMEOUT_ERROR:
break;
case MSGCODE_COMMAND_ACCEPTED:
int err;
cmd[0] = MSGCODE_TRANSMIT_IDLETIME;
- cmd[1] = 3;
+ cmd[1] = signal_free_time;
err = pulse8_send_and_wait(pulse8, cmd, 2,
MSGCODE_COMMAND_ACCEPTED, 1);
cmd[0] = MSGCODE_TRANSMIT_ACK_POLARITY;
if (!hif_workqueue) {
netdev_err(vif->ndev, "Failed to create workqueue\n");
result = -ENOMEM;
- goto _fail_mq_;
+ goto _fail_;
}
setup_timer(&periodic_rssi, GetPeriodicRSSI,
clients_count++;
-_fail_mq_:
destroy_workqueue(hif_workqueue);
_fail_:
return result;
mutex_unlock(&wl->hif_cs);
}
if (&wl->txq_event)
- wait_for_completion(&wl->txq_event);
+ complete(&wl->txq_event);
wlan_deinitialize_threads(dev);
deinit_irq(dev);
struct wilc_priv *priv;
struct wilc_vif *vif;
u32 i = 0;
- u32 associatedsta = 0;
+ u32 associatedsta = ~0;
u32 inactive_time = 0;
priv = wiphy_priv(wiphy);
vif = netdev_priv(dev);
}
}
- if (associatedsta == -1) {
+ if (associatedsta == ~0) {
netdev_err(dev, "sta required is not associated\n");
return -ENOENT;
}
if (!ccdev)
return ERR_PTR(-ENOMEM);
+ mutex_init(&ccdev->lock);
ccdev->dev = dev;
ccdev->clk = devm_clk_get(dev, clock_name);
if (IS_ERR(ccdev->clk))
}
/* Bind cpufreq callbacks to thermal cooling device ops */
+
static struct thermal_cooling_device_ops cpufreq_cooling_ops = {
.get_max_state = cpufreq_get_max_state,
.get_cur_state = cpufreq_get_cur_state,
.set_cur_state = cpufreq_set_cur_state,
};
+static struct thermal_cooling_device_ops cpufreq_power_cooling_ops = {
+ .get_max_state = cpufreq_get_max_state,
+ .get_cur_state = cpufreq_get_cur_state,
+ .set_cur_state = cpufreq_set_cur_state,
+ .get_requested_power = cpufreq_get_requested_power,
+ .state2power = cpufreq_state2power,
+ .power2state = cpufreq_power2state,
+};
+
/* Notifier for cpufreq policy change */
static struct notifier_block thermal_cpufreq_notifier_block = {
.notifier_call = cpufreq_thermal_notifier,
struct cpumask temp_mask;
unsigned int freq, i, num_cpus;
int ret;
+ struct thermal_cooling_device_ops *cooling_ops;
cpumask_and(&temp_mask, clip_cpus, cpu_online_mask);
policy = cpufreq_cpu_get(cpumask_first(&temp_mask));
cpumask_copy(&cpufreq_dev->allowed_cpus, clip_cpus);
if (capacitance) {
- cpufreq_cooling_ops.get_requested_power =
- cpufreq_get_requested_power;
- cpufreq_cooling_ops.state2power = cpufreq_state2power;
- cpufreq_cooling_ops.power2state = cpufreq_power2state;
cpufreq_dev->plat_get_static_power = plat_static_func;
ret = build_dyn_power_table(cpufreq_dev, capacitance);
cool_dev = ERR_PTR(ret);
goto free_table;
}
+
+ cooling_ops = &cpufreq_power_cooling_ops;
+ } else {
+ cooling_ops = &cpufreq_cooling_ops;
}
ret = get_idr(&cpufreq_idr, &cpufreq_dev->id);
cpufreq_dev->id);
cool_dev = thermal_of_cooling_device_register(np, dev_name, cpufreq_dev,
- &cpufreq_cooling_ops);
+ cooling_ops);
if (IS_ERR(cool_dev))
goto remove_idr;
instance->target = get_target_state(tz, cdev, percentage,
cur_trip_level);
+ mutex_lock(&instance->cdev->lock);
instance->cdev->updated = false;
+ mutex_unlock(&instance->cdev->lock);
thermal_cdev_update(cdev);
}
return 0;
dev_dbg(&instance->cdev->device, "target=%d\n",
(int)instance->target);
+ mutex_lock(&instance->cdev->lock);
instance->cdev->updated = false; /* cdev needs update */
+ mutex_unlock(&instance->cdev->lock);
}
mutex_unlock(&tz->lock);
static int imx_thermal_probe(struct platform_device *pdev)
{
- const struct of_device_id *of_id =
- of_match_device(of_imx_thermal_match, &pdev->dev);
struct imx_thermal_data *data;
struct regmap *map;
int measure_freq;
}
data->tempmon = map;
- data->socdata = of_id->data;
+ data->socdata = of_device_get_match_data(&pdev->dev);
/* make sure the IRQ flag is clear before enabling irq on i.MX6SX */
if (data->socdata->version == TEMPMON_IMX6SX) {
.remove = int3406_thermal_remove,
.driver = {
.name = "int3406 thermal",
- .owner = THIS_MODULE,
.acpi_match_table = int3406_thermal_match,
},
};
#include <linux/init.h>
#include <linux/pci.h>
#include <linux/thermal.h>
+#include <linux/pm.h>
/* Intel PCH thermal Device IDs */
#define PCH_THERMAL_DID_WPT 0x9CA4 /* Wildcat Point */
unsigned long crt_temp;
int hot_trip_id;
unsigned long hot_temp;
+ bool bios_enabled;
};
static int pch_wpt_init(struct pch_thermal_device *ptd, int *nr_trips)
*nr_trips = 0;
/* Check if BIOS has already enabled thermal sensor */
- if (WPT_TSS_TSDSS & readb(ptd->hw_base + WPT_TSS))
+ if (WPT_TSS_TSDSS & readb(ptd->hw_base + WPT_TSS)) {
+ ptd->bios_enabled = true;
goto read_trips;
+ }
tsel = readb(ptd->hw_base + WPT_TSEL);
/*
return 0;
}
+static int pch_wpt_suspend(struct pch_thermal_device *ptd)
+{
+ u8 tsel;
+
+ if (ptd->bios_enabled)
+ return 0;
+
+ tsel = readb(ptd->hw_base + WPT_TSEL);
+
+ writeb(tsel & 0xFE, ptd->hw_base + WPT_TSEL);
+
+ return 0;
+}
+
+static int pch_wpt_resume(struct pch_thermal_device *ptd)
+{
+ u8 tsel;
+
+ if (ptd->bios_enabled)
+ return 0;
+
+ tsel = readb(ptd->hw_base + WPT_TSEL);
+
+ writeb(tsel | WPT_TSEL_ETS, ptd->hw_base + WPT_TSEL);
+
+ return 0;
+}
+
struct pch_dev_ops {
int (*hw_init)(struct pch_thermal_device *ptd, int *nr_trips);
int (*get_temp)(struct pch_thermal_device *ptd, int *temp);
+ int (*suspend)(struct pch_thermal_device *ptd);
+ int (*resume)(struct pch_thermal_device *ptd);
};
static const struct pch_dev_ops pch_dev_ops_wpt = {
.hw_init = pch_wpt_init,
.get_temp = pch_wpt_get_temp,
+ .suspend = pch_wpt_suspend,
+ .resume = pch_wpt_resume,
};
static int pch_thermal_get_temp(struct thermal_zone_device *tzd, int *temp)
pci_disable_device(pdev);
}
+static int intel_pch_thermal_suspend(struct device *device)
+{
+ struct pci_dev *pdev = to_pci_dev(device);
+ struct pch_thermal_device *ptd = pci_get_drvdata(pdev);
+
+ return ptd->ops->suspend(ptd);
+}
+
+static int intel_pch_thermal_resume(struct device *device)
+{
+ struct pci_dev *pdev = to_pci_dev(device);
+ struct pch_thermal_device *ptd = pci_get_drvdata(pdev);
+
+ return ptd->ops->resume(ptd);
+}
+
static struct pci_device_id intel_pch_thermal_id[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_WPT) },
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_SKL) },
};
MODULE_DEVICE_TABLE(pci, intel_pch_thermal_id);
+static const struct dev_pm_ops intel_pch_pm_ops = {
+ .suspend = intel_pch_thermal_suspend,
+ .resume = intel_pch_thermal_resume,
+};
+
static struct pci_driver intel_pch_thermal_driver = {
.name = "intel_pch_thermal",
.id_table = intel_pch_thermal_id,
.probe = intel_pch_thermal_probe,
.remove = intel_pch_thermal_remove,
+ .driver.pm = &intel_pch_pm_ops,
};
module_pci_driver(intel_pch_thermal_driver);
int sleeptime;
unsigned long target_jiffies;
unsigned int guard;
- unsigned int compensation = 0;
+ unsigned int compensated_ratio;
int interval; /* jiffies to sleep for each attempt */
unsigned int duration_jiffies = msecs_to_jiffies(duration);
unsigned int window_size_now;
* c-states, thus we need to compensate the injected idle ratio
* to achieve the actual target reported by the HW.
*/
- compensation = get_compensation(target_ratio);
- interval = duration_jiffies*100/(target_ratio+compensation);
+ compensated_ratio = target_ratio +
+ get_compensation(target_ratio);
+ if (compensated_ratio <= 0)
+ compensated_ratio = 1;
+ interval = duration_jiffies * 100 / compensated_ratio;
/* align idle time */
target_jiffies = roundup(jiffies, interval);
goto exit_set;
} else if (set_target_ratio > 0 && new_target_ratio == 0) {
pr_info("Stop forced idle injection\n");
- set_target_ratio = 0;
end_power_clamp();
+ set_target_ratio = 0;
} else /* adjust currently running */ {
set_target_ratio = new_target_ratio;
/* make new set_target_ratio visible to other cpus */
continue;
instance->target = 0;
+ mutex_lock(&instance->cdev->lock);
instance->cdev->updated = false;
+ mutex_unlock(&instance->cdev->lock);
thermal_cdev_update(instance->cdev);
}
}
if (IS_ERR(priv->zone)) {
dev_err(dev, "can't register thermal zone\n");
ret = PTR_ERR(priv->zone);
+ priv->zone = NULL;
goto error_unregister;
}
update_passive_instance(tz, trip_type, -1);
instance->initialized = true;
+ mutex_lock(&instance->cdev->lock);
instance->cdev->updated = false; /* cdev needs update */
+ mutex_unlock(&instance->cdev->lock);
}
mutex_unlock(&tz->lock);
return ret;
instance->target = state;
+ mutex_lock(&cdev->lock);
cdev->updated = false;
+ mutex_unlock(&cdev->lock);
thermal_cdev_update(cdev);
return 0;
struct thermal_instance *instance;
unsigned long target = 0;
+ mutex_lock(&cdev->lock);
/* cooling device is updated*/
- if (cdev->updated)
+ if (cdev->updated) {
+ mutex_unlock(&cdev->lock);
return;
+ }
- mutex_lock(&cdev->lock);
/* Make sure cdev enters the deepest cooling state */
list_for_each_entry(instance, &cdev->thermal_instances, cdev_node) {
dev_dbg(&cdev->device, "zone%d->target=%lu\n",
if (instance->target > target)
target = instance->target;
}
- mutex_unlock(&cdev->lock);
cdev->ops->set_cur_state(cdev, target);
cdev->updated = true;
+ mutex_unlock(&cdev->lock);
trace_cdev_update(cdev, target);
dev_dbg(&cdev->device, "set to state %lu\n", target);
}
return result;
}
+EXPORT_SYMBOL_GPL(thermal_add_hwmon_sysfs);
void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz)
{
hwmon_device_unregister(hwmon->device);
kfree(hwmon);
}
+EXPORT_SYMBOL_GPL(thermal_remove_hwmon_sysfs);
.device = PCI_DEVICE_ID_INTEL_CACTUS_RIDGE_4C,
.subvendor = 0x2222, .subdevice = 0x1111,
},
+ {
+ .class = PCI_CLASS_SYSTEM_OTHER << 8, .class_mask = ~0,
+ .vendor = PCI_VENDOR_ID_INTEL,
+ .device = PCI_DEVICE_ID_INTEL_FALCON_RIDGE_2C_NHI,
+ .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID,
+ },
{
.class = PCI_CLASS_SYSTEM_OTHER << 8, .class_mask = ~0,
.vendor = PCI_VENDOR_ID_INTEL,
if (sw->config.device_id != PCI_DEVICE_ID_INTEL_LIGHT_RIDGE &&
sw->config.device_id != PCI_DEVICE_ID_INTEL_CACTUS_RIDGE_4C &&
- sw->config.device_id != PCI_DEVICE_ID_INTEL_PORT_RIDGE)
+ sw->config.device_id != PCI_DEVICE_ID_INTEL_PORT_RIDGE &&
+ sw->config.device_id != PCI_DEVICE_ID_INTEL_FALCON_RIDGE_2C_BRIDGE &&
+ sw->config.device_id != PCI_DEVICE_ID_INTEL_FALCON_RIDGE_4C_BRIDGE)
tb_sw_warn(sw, "unsupported switch device id %#x\n",
sw->config.device_id);
#include <linux/serial_reg.h>
#include <linux/dmaengine.h>
-#include "../serial_mctrl_gpio.h"
-
struct uart_8250_dma {
int (*tx_dma)(struct uart_8250_port *p);
int (*rx_dma)(struct uart_8250_port *p);
static inline void serial8250_out_MCR(struct uart_8250_port *up, int value)
{
- int mctrl_gpio = 0;
-
serial_out(up, UART_MCR, value);
-
- if (value & UART_MCR_RTS)
- mctrl_gpio |= TIOCM_RTS;
- if (value & UART_MCR_DTR)
- mctrl_gpio |= TIOCM_DTR;
-
- mctrl_gpio_set(up->gpios, mctrl_gpio);
}
static inline int serial8250_in_MCR(struct uart_8250_port *up)
{
- int mctrl, mctrl_gpio = 0;
-
- mctrl = serial_in(up, UART_MCR);
-
- /* save current MCR values */
- if (mctrl & UART_MCR_RTS)
- mctrl_gpio |= TIOCM_RTS;
- if (mctrl & UART_MCR_DTR)
- mctrl_gpio |= TIOCM_DTR;
-
- mctrl_gpio = mctrl_gpio_get_outputs(up->gpios, &mctrl_gpio);
-
- if (mctrl_gpio & TIOCM_RTS)
- mctrl |= UART_MCR_RTS;
- else
- mctrl &= ~UART_MCR_RTS;
-
- if (mctrl_gpio & TIOCM_DTR)
- mctrl |= UART_MCR_DTR;
- else
- mctrl &= ~UART_MCR_DTR;
-
- return mctrl;
+ return serial_in(up, UART_MCR);
}
#if defined(__alpha__) && !defined(CONFIG_PCI)
uart = serial8250_find_match_or_unused(&up->port);
if (uart && uart->port.type != PORT_8250_CIR) {
- struct mctrl_gpios *gpios;
-
if (uart->port.dev)
uart_remove_one_port(&serial8250_reg, &uart->port);
if (up->port.flags & UPF_FIXED_TYPE)
uart->port.type = up->port.type;
- gpios = mctrl_gpio_init(&uart->port, 0);
- if (IS_ERR(gpios)) {
- if (PTR_ERR(gpios) != -ENOSYS)
- return PTR_ERR(gpios);
- } else
- uart->gpios = gpios;
-
serial8250_set_defaults(uart);
/* Possibly override default I/O functions. */
#define IO_ADDR2 0x60
#define LDN 0x7
-#define IRQ_MODE 0x70
+#define FINTEK_IRQ_MODE 0x70
#define IRQ_SHARE BIT(4)
#define IRQ_MODE_MASK (BIT(6) | BIT(5))
#define IRQ_LEVEL_LOW 0
outb(LDN, pdata->base_port + ADDR_PORT);
outb(pdata->index, pdata->base_port + DATA_PORT);
- outb(IRQ_MODE, pdata->base_port + ADDR_PORT);
+ outb(FINTEK_IRQ_MODE, pdata->base_port + ADDR_PORT);
tmp = inb(pdata->base_port + DATA_PORT);
tmp &= ~IRQ_MODE_MASK;
unsigned long w = BIT(24) - 1;
unsigned long mul, div;
+ /* Gracefully handle the B0 case: fall back to B9600 */
+ fuart = fuart ? fuart : 9600 * 16;
+
if (mid->board->freq < fuart) {
/* Find prescaler value that satisfies Fuart < Fref */
if (mid->board->freq > baud)
serial8250_do_set_mctrl(port, mctrl);
- if (IS_ERR_OR_NULL(mctrl_gpio_to_gpiod(up->gpios,
- UART_GPIO_RTS))) {
- /*
- * Turn off autoRTS if RTS is lowered and restore autoRTS
- * setting if RTS is raised
- */
- lcr = serial_in(up, UART_LCR);
- serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B);
- if ((mctrl & TIOCM_RTS) && (port->status & UPSTAT_AUTORTS))
- priv->efr |= UART_EFR_RTS;
- else
- priv->efr &= ~UART_EFR_RTS;
- serial_out(up, UART_EFR, priv->efr);
- serial_out(up, UART_LCR, lcr);
- }
+ /*
+ * Turn off autoRTS if RTS is lowered and restore autoRTS setting
+ * if RTS is raised
+ */
+ lcr = serial_in(up, UART_LCR);
+ serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B);
+ if ((mctrl & TIOCM_RTS) && (port->status & UPSTAT_AUTORTS))
+ priv->efr |= UART_EFR_RTS;
+ else
+ priv->efr &= ~UART_EFR_RTS;
+ serial_out(up, UART_EFR, priv->efr);
+ serial_out(up, UART_LCR, lcr);
}
/*
priv->efr = 0;
up->port.status &= ~(UPSTAT_AUTOCTS | UPSTAT_AUTORTS | UPSTAT_AUTOXOFF);
- if (termios->c_cflag & CRTSCTS && up->port.flags & UPF_HARD_FLOW
- && IS_ERR_OR_NULL(mctrl_gpio_to_gpiod(up->gpios,
- UART_GPIO_RTS))) {
+ if (termios->c_cflag & CRTSCTS && up->port.flags & UPF_HARD_FLOW) {
/* Enable AUTOCTS (autoRTS is enabled when RTS is raised) */
up->port.status |= UPSTAT_AUTOCTS | UPSTAT_AUTORTS;
priv->efr |= UART_EFR_CTS;
#define PCI_DEVICE_ID_PERICOM_PI7C9X7954 0x7954
#define PCI_DEVICE_ID_PERICOM_PI7C9X7958 0x7958
+#define PCI_VENDOR_ID_ACCESIO 0x494f
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM_2SDB 0x1051
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_COM_2S 0x1053
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM_4SDB 0x105C
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_COM_4S 0x105E
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM232_2DB 0x1091
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_COM232_2 0x1093
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM232_4DB 0x1099
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_COM232_4 0x109B
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM_2SMDB 0x10D1
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_COM_2SM 0x10D3
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM_4SMDB 0x10DA
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_COM_4SM 0x10DC
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM485_1 0x1108
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM422_2 0x1110
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM485_2 0x1111
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM422_4 0x1118
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM485_4 0x1119
+#define PCI_DEVICE_ID_ACCESIO_PCIE_ICM_2S 0x1152
+#define PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4S 0x115A
+#define PCI_DEVICE_ID_ACCESIO_PCIE_ICM232_2 0x1190
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM232_2 0x1191
+#define PCI_DEVICE_ID_ACCESIO_PCIE_ICM232_4 0x1198
+#define PCI_DEVICE_ID_ACCESIO_MPCIE_ICM232_4 0x1199
+#define PCI_DEVICE_ID_ACCESIO_PCIE_ICM_2SM 0x11D0
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM422_4 0x105A
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM485_4 0x105B
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM422_8 0x106A
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM485_8 0x106B
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM232_4 0x1098
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM232_8 0x10A9
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM_4SM 0x10D9
+#define PCI_DEVICE_ID_ACCESIO_PCIE_COM_8SM 0x10E9
+#define PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4SM 0x11D8
+
+
+
/* Unknown vendors/cards - this should not be in linux/pci_ids.h */
#define PCI_SUBDEVICE_ID_UNKNOWN_0x1584 0x1584
#define PCI_SUBDEVICE_ID_UNKNOWN_0x1588 0x1588
PCI_ANY_ID, PCI_ANY_ID,
0,
0, pbn_pericom_PI7C9X7958 },
+ /*
+ * ACCES I/O Products quad
+ */
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM_2SDB,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_COM_2S,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM_4SDB,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_COM_4S,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM232_2DB,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_COM232_2,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM232_4DB,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_COM232_4,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM_2SMDB,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_COM_2SM,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM_4SMDB,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_COM_4SM,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM485_1,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM422_2,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM485_2,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM422_4,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM485_4,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_ICM_2S,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4S,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_ICM232_2,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM232_2,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_ICM232_4,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_MPCIE_ICM232_4,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_ICM_2SM,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7954 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM422_4,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7958 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM485_4,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7958 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM422_8,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7958 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM485_8,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7958 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM232_4,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7958 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM232_8,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7958 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM_4SM,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7958 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_COM_8SM,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7958 },
+ { PCI_VENDOR_ID_ACCESIO, PCI_DEVICE_ID_ACCESIO_PCIE_ICM_4SM,
+ PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+ pbn_pericom_PI7C9X7958 },
/*
* Topic TP560 Data/Fax/Voice 56k modem (reported by Evan Clarke)
*/
if (up->bugs & UART_BUG_NOMSR)
return;
- mctrl_gpio_disable_ms(up->gpios);
-
up->ier &= ~UART_IER_MSI;
serial_port_out(port, UART_IER, up->ier);
}
if (up->bugs & UART_BUG_NOMSR)
return;
- mctrl_gpio_enable_ms(up->gpios);
-
up->ier |= UART_IER_MSI;
serial8250_rpm_get(up);
ret |= TIOCM_DSR;
if (status & UART_MSR_CTS)
ret |= TIOCM_CTS;
-
- return mctrl_gpio_get(up->gpios, &ret);
+ return ret;
}
EXPORT_SYMBOL_GPL(serial8250_do_get_mctrl);
config SERIAL_8250
tristate "8250/16550 and compatible serial support"
select SERIAL_CORE
- select SERIAL_MCTRL_GPIO if GPIOLIB
---help---
This selects whether you want to include the driver for the standard
serial ports. The standard answer is Y. People who might say N
int retval;
struct ci_hw_ep *hwep;
+ /*
+ * Unexpected USB controller behavior, caused by bad signal integrity
+ * or ground reference problems, can lead to isr_setup_status_phase
+ * being called with ci->status equal to NULL.
+ * If this situation occurs, you should review your USB hardware design.
+ */
+ if (WARN_ON_ONCE(!ci->status))
+ return -EPIPE;
+
hwep = (ci->ep0_dir == TX) ? ci->ep0out : ci->ep0in;
ci->status->context = ci;
ci->status->complete = isr_setup_status_complete;
{
struct ci_hdrc *ci = container_of(_gadget, struct ci_hdrc, gadget);
- /* Data+ pullup controlled by OTG state machine in OTG fsm mode */
- if (ci_otg_is_fsm_mode(ci))
+ /*
+ * Data+ pullup controlled by OTG state machine in OTG fsm mode;
+ * and don't touch Data+ in host mode for dual role config.
+ */
+ if (ci_otg_is_fsm_mode(ci) || ci->role == CI_ROLE_HOST)
return 0;
pm_runtime_get_sync(&ci->gadget.dev);
spin_lock_init(&acm->write_lock);
spin_lock_init(&acm->read_lock);
mutex_init(&acm->mutex);
- acm->rx_endpoint = usb_rcvbulkpipe(usb_dev, epread->bEndpointAddress);
acm->is_int_ep = usb_endpoint_xfer_int(epread);
if (acm->is_int_ep)
acm->bInterval = epread->bInterval;
urb->transfer_dma = rb->dma;
if (acm->is_int_ep) {
usb_fill_int_urb(urb, acm->dev,
- acm->rx_endpoint,
+ usb_rcvintpipe(usb_dev, epread->bEndpointAddress),
rb->base,
acm->readsize,
acm_read_bulk_callback, rb,
acm->bInterval);
} else {
usb_fill_bulk_urb(urb, acm->dev,
- acm->rx_endpoint,
+ usb_rcvbulkpipe(usb_dev, epread->bEndpointAddress),
rb->base,
acm->readsize,
acm_read_bulk_callback, rb);
struct acm_rb read_buffers[ACM_NR];
struct acm_wb *putbuffer; /* for acm_tty_put_char() */
int rx_buflimit;
- int rx_endpoint;
spinlock_t read_lock;
int write_used; /* number of non-empty write buffers */
int transmitting;
ep, buffer, size);
}
+static const unsigned short low_speed_maxpacket_maxes[4] = {
+ [USB_ENDPOINT_XFER_CONTROL] = 8,
+ [USB_ENDPOINT_XFER_ISOC] = 0,
+ [USB_ENDPOINT_XFER_BULK] = 0,
+ [USB_ENDPOINT_XFER_INT] = 8,
+};
+static const unsigned short full_speed_maxpacket_maxes[4] = {
+ [USB_ENDPOINT_XFER_CONTROL] = 64,
+ [USB_ENDPOINT_XFER_ISOC] = 1023,
+ [USB_ENDPOINT_XFER_BULK] = 64,
+ [USB_ENDPOINT_XFER_INT] = 64,
+};
+static const unsigned short high_speed_maxpacket_maxes[4] = {
+ [USB_ENDPOINT_XFER_CONTROL] = 64,
+ [USB_ENDPOINT_XFER_ISOC] = 1024,
+ [USB_ENDPOINT_XFER_BULK] = 512,
+ [USB_ENDPOINT_XFER_INT] = 1024,
+};
+static const unsigned short super_speed_maxpacket_maxes[4] = {
+ [USB_ENDPOINT_XFER_CONTROL] = 512,
+ [USB_ENDPOINT_XFER_ISOC] = 1024,
+ [USB_ENDPOINT_XFER_BULK] = 1024,
+ [USB_ENDPOINT_XFER_INT] = 1024,
+};
+
static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum,
int asnum, struct usb_host_interface *ifp, int num_ep,
unsigned char *buffer, int size)
struct usb_endpoint_descriptor *d;
struct usb_host_endpoint *endpoint;
int n, i, j, retval;
+ unsigned int maxp;
+ const unsigned short *maxpacket_maxes;
d = (struct usb_endpoint_descriptor *) buffer;
buffer += d->bLength;
memcpy(&endpoint->desc, d, n);
INIT_LIST_HEAD(&endpoint->urb_list);
- /* Fix up bInterval values outside the legal range. Use 32 ms if no
- * proper value can be guessed. */
+ /*
+ * Fix up bInterval values outside the legal range.
+ * Use 10 or 8 ms if no proper value can be guessed.
+ */
i = 0; /* i = min, j = max, n = default */
j = 255;
if (usb_endpoint_xfer_int(d)) {
case USB_SPEED_SUPER_PLUS:
case USB_SPEED_SUPER:
case USB_SPEED_HIGH:
- /* Many device manufacturers are using full-speed
+ /*
+ * Many device manufacturers are using full-speed
* bInterval values in high-speed interrupt endpoint
- * descriptors. Try to fix those and fall back to a
- * 32 ms default value otherwise. */
+ * descriptors. Try to fix those and fall back to an
+ * 8-ms default value otherwise.
+ */
n = fls(d->bInterval*8);
if (n == 0)
- n = 9; /* 32 ms = 2^(9-1) uframes */
+ n = 7; /* 8 ms = 2^(7-1) uframes */
j = 16;
/*
}
break;
default: /* USB_SPEED_FULL or _LOW */
- /* For low-speed, 10 ms is the official minimum.
+ /*
+ * For low-speed, 10 ms is the official minimum.
* But some "overclocked" devices might want faster
- * polling so we'll allow it. */
- n = 32;
+ * polling so we'll allow it.
+ */
+ n = 10;
break;
}
} else if (usb_endpoint_xfer_isoc(d)) {
j = 16;
switch (to_usb_device(ddev)->speed) {
case USB_SPEED_HIGH:
- n = 9; /* 32 ms = 2^(9-1) uframes */
+ n = 7; /* 8 ms = 2^(7-1) uframes */
break;
default: /* USB_SPEED_FULL */
- n = 6; /* 32 ms = 2^(6-1) frames */
+ n = 4; /* 8 ms = 2^(4-1) frames */
break;
}
}
endpoint->desc.wMaxPacketSize = cpu_to_le16(8);
}
+ /* Validate the wMaxPacketSize field */
+ maxp = usb_endpoint_maxp(&endpoint->desc);
+
+ /* Find the highest legal maxpacket size for this endpoint */
+ i = 0; /* additional transactions per microframe */
+ switch (to_usb_device(ddev)->speed) {
+ case USB_SPEED_LOW:
+ maxpacket_maxes = low_speed_maxpacket_maxes;
+ break;
+ case USB_SPEED_FULL:
+ maxpacket_maxes = full_speed_maxpacket_maxes;
+ break;
+ case USB_SPEED_HIGH:
+ /* Bits 12..11 are allowed only for HS periodic endpoints */
+ if (usb_endpoint_xfer_int(d) || usb_endpoint_xfer_isoc(d)) {
+ i = maxp & (BIT(12) | BIT(11));
+ maxp &= ~i;
+ }
+ /* fallthrough */
+ default:
+ maxpacket_maxes = high_speed_maxpacket_maxes;
+ break;
+ case USB_SPEED_SUPER:
+ case USB_SPEED_SUPER_PLUS:
+ maxpacket_maxes = super_speed_maxpacket_maxes;
+ break;
+ }
+ j = maxpacket_maxes[usb_endpoint_type(&endpoint->desc)];
+
+ if (maxp > j) {
+ dev_warn(ddev, "config %d interface %d altsetting %d endpoint 0x%X has invalid maxpacket %d, setting to %d\n",
+ cfgno, inum, asnum, d->bEndpointAddress, maxp, j);
+ maxp = j;
+ endpoint->desc.wMaxPacketSize = cpu_to_le16(i | maxp);
+ }
+
/*
* Some buggy high speed devices have bulk endpoints using
* maxpacket sizes other than 512. High speed HCDs may not
*/
if (to_usb_device(ddev)->speed == USB_SPEED_HIGH
&& usb_endpoint_xfer_bulk(d)) {
- unsigned maxp;
-
- maxp = usb_endpoint_maxp(&endpoint->desc) & 0x07ff;
if (maxp != 512)
dev_warn(ddev, "config %d interface %d altsetting %d "
"bulk endpoint 0x%X has invalid maxpacket %d\n",
goto error_decrease_mem;
}
- mem = usb_alloc_coherent(ps->dev, size, GFP_USER, &dma_handle);
+ mem = usb_alloc_coherent(ps->dev, size, GFP_USER | __GFP_NOWARN,
+ &dma_handle);
if (!mem) {
ret = -ENOMEM;
goto error_free_usbm;
as->urb->start_frame = uurb->start_frame;
as->urb->number_of_packets = number_of_packets;
as->urb->stream_id = stream_id;
- if (uurb->type == USBDEVFS_URB_TYPE_ISO ||
- ps->dev->speed == USB_SPEED_HIGH)
- as->urb->interval = 1 << min(15, ep->desc.bInterval - 1);
- else
- as->urb->interval = ep->desc.bInterval;
+
+ if (ep->desc.bInterval) {
+ if (uurb->type == USBDEVFS_URB_TYPE_ISO ||
+ ps->dev->speed == USB_SPEED_HIGH ||
+ ps->dev->speed >= USB_SPEED_SUPER)
+ as->urb->interval = 1 <<
+ min(15, ep->desc.bInterval - 1);
+ else
+ as->urb->interval = ep->desc.bInterval;
+ }
+
as->urb->context = as;
as->urb->complete = async_completed;
for (totlen = u = 0; u < number_of_packets; u++) {
if (file->f_mode & FMODE_WRITE && !list_empty(&ps->async_completed))
mask |= POLLOUT | POLLWRNORM;
if (!connected(ps))
- mask |= POLLERR | POLLHUP;
+ mask |= POLLHUP;
+ if (list_empty(&ps->list))
+ mask |= POLLERR;
return mask;
}
/* Continue a partial initialization */
if (type == HUB_INIT2 || type == HUB_INIT3) {
- device_lock(hub->intfdev);
+ device_lock(&hdev->dev);
/* Was the hub disconnected while we were waiting? */
- if (hub->disconnected) {
- device_unlock(hub->intfdev);
- kref_put(&hub->kref, hub_release);
- return;
- }
+ if (hub->disconnected)
+ goto disconnected;
if (type == HUB_INIT2)
goto init2;
goto init3;
queue_delayed_work(system_power_efficient_wq,
&hub->init_work,
msecs_to_jiffies(delay));
- device_unlock(hub->intfdev);
+ device_unlock(&hdev->dev);
return; /* Continues at init3: below */
} else {
msleep(delay);
/* Scan all ports that need attention */
kick_hub_wq(hub);
- /* Allow autosuspend if it was suppressed */
- if (type <= HUB_INIT3)
+ if (type == HUB_INIT2 || type == HUB_INIT3) {
+ /* Allow autosuspend if it was suppressed */
+ disconnected:
usb_autopm_put_interface_async(to_usb_interface(hub->intfdev));
-
- if (type == HUB_INIT2 || type == HUB_INIT3)
- device_unlock(hub->intfdev);
+ device_unlock(&hdev->dev);
+ }
kref_put(&hub->kref, hub_release);
}
struct usb_device *hdev = hub->hdev;
int i;
- cancel_delayed_work_sync(&hub->init_work);
-
/* hub_wq and related activity won't re-trigger */
hub->quiescing = 1;
void *priv;
int irq;
struct clk *clk;
+ struct reset_control *reset;
unsigned int queuing_high_bandwidth:1;
unsigned int srp_success:1;
#include <linux/platform_device.h>
#include <linux/phy/phy.h>
#include <linux/platform_data/s3c-hsotg.h>
+#include <linux/reset.h>
#include <linux/usb/of.h>
{
int i, ret;
+ hsotg->reset = devm_reset_control_get_optional(hsotg->dev, "dwc2");
+ if (IS_ERR(hsotg->reset)) {
+ ret = PTR_ERR(hsotg->reset);
+ switch (ret) {
+ case -ENOENT:
+ case -ENOTSUPP:
+ hsotg->reset = NULL;
+ break;
+ default:
+ dev_err(hsotg->dev, "error getting reset control %d\n",
+ ret);
+ return ret;
+ }
+ }
+
+ if (hsotg->reset)
+ reset_control_deassert(hsotg->reset);
+
/* Set default UTMI width */
hsotg->phyif = GUSBCFG_PHYIF16;
if (hsotg->ll_hw_enabled)
dwc2_lowlevel_hw_disable(hsotg);
+ if (hsotg->reset)
+ reset_control_assert(hsotg->reset);
+
return 0;
}
}
pm_runtime_mark_last_busy(dev);
+ pm_runtime_put(dev);
return 0;
}
int ret;
ret = sprintf(str, "ep%d%s: ", epnum >> 1,
- (epnum & 1) ? "in" : "in");
+ (epnum & 1) ? "in" : "out");
if (ret < 0)
return "UNKNOWN";
if (!simple->clks)
return -ENOMEM;
+ platform_set_drvdata(pdev, simple);
simple->dev = dev;
for (i = 0; i < simple->num_clocks; i++) {
#define PCI_DEVICE_ID_INTEL_BXT 0x0aaa
#define PCI_DEVICE_ID_INTEL_BXT_M 0x1aaa
#define PCI_DEVICE_ID_INTEL_APL 0x5aaa
+#define PCI_DEVICE_ID_INTEL_KBP 0xa2b0
static const struct acpi_gpio_params reset_gpios = { 0, 0, false };
static const struct acpi_gpio_params cs_gpios = { 1, 0, false };
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BXT), },
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BXT_M), },
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_APL), },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBP), },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_NL_USB), },
{ } /* Terminating Entry */
};
return -EBUSY;
}
+static int dwc3_pci_runtime_resume(struct device *dev)
+{
+ struct platform_device *dwc3 = dev_get_drvdata(dev);
+
+ return pm_runtime_get(&dwc3->dev);
+}
+#endif /* CONFIG_PM */
+
+#ifdef CONFIG_PM_SLEEP
static int dwc3_pci_pm_dummy(struct device *dev)
{
/*
*/
return 0;
}
-#endif /* CONFIG_PM */
+#endif /* CONFIG_PM_SLEEP */
static struct dev_pm_ops dwc3_pci_dev_pm_ops = {
SET_SYSTEM_SLEEP_PM_OPS(dwc3_pci_pm_dummy, dwc3_pci_pm_dummy)
- SET_RUNTIME_PM_OPS(dwc3_pci_runtime_suspend, dwc3_pci_pm_dummy,
+ SET_RUNTIME_PM_OPS(dwc3_pci_runtime_suspend, dwc3_pci_runtime_resume,
NULL)
};
if (!req->request.no_interrupt && !chain)
trb->ctrl |= DWC3_TRB_CTRL_IOC | DWC3_TRB_CTRL_ISP_IMI;
- if (last)
+ if (last && !usb_endpoint_xfer_isoc(dep->endpoint.desc))
trb->ctrl |= DWC3_TRB_CTRL_LST;
if (chain)
static int __dwc3_gadget_wakeup(struct dwc3 *dwc)
{
- unsigned long timeout;
+ int retries;
int ret;
u32 reg;
}
/* poll until Link State changes to ON */
- timeout = jiffies + msecs_to_jiffies(100);
+ retries = 20000;
- while (!time_after(jiffies, timeout)) {
+ while (retries--) {
reg = dwc3_readl(dwc->regs, DWC3_DSTS);
/* in HS, means ON */
static int __dwc3_cleanup_done_trbs(struct dwc3 *dwc, struct dwc3_ep *dep,
struct dwc3_request *req, struct dwc3_trb *trb,
- const struct dwc3_event_depevt *event, int status)
+ const struct dwc3_event_depevt *event, int status,
+ int chain)
{
unsigned int count;
unsigned int s_pkt = 0;
dep->queued_requests--;
trace_dwc3_complete_trb(dep, trb);
+ /*
+ * If we're in the middle of series of chained TRBs and we
+ * receive a short transfer along the way, DWC3 will skip
+ * through all TRBs including the last TRB in the chain (the
+ * where CHN bit is zero. DWC3 will also avoid clearing HWO
+ * bit and SW has to do it manually.
+ *
+ * We're going to do that here to avoid problems of HW trying
+ * to use bogus TRBs for transfers.
+ */
+ if (chain && (trb->ctrl & DWC3_TRB_CTRL_HWO))
+ trb->ctrl &= ~DWC3_TRB_CTRL_HWO;
+
if ((trb->ctrl & DWC3_TRB_CTRL_HWO) && status != -ESHUTDOWN)
- /*
- * We continue despite the error. There is not much we
- * can do. If we don't clean it up we loop forever. If
- * we skip the TRB then it gets overwritten after a
- * while since we use them in a ring buffer. A BUG()
- * would help. Lets hope that if this occurs, someone
- * fixes the root cause instead of looking away :)
- */
- dev_err(dwc->dev, "%s's TRB (%p) still owned by HW\n",
- dep->name, trb);
+ return 1;
+
count = trb->size & DWC3_TRB_SIZE_MASK;
if (dep->direction) {
s_pkt = 1;
}
- /*
- * We assume here we will always receive the entire data block
- * which we should receive. Meaning, if we program RX to
- * receive 4K but we receive only 2K, we assume that's all we
- * should receive and we simply bounce the request back to the
- * gadget driver for further processing.
- */
- req->request.actual += req->request.length - count;
- if (s_pkt)
+ if (s_pkt && !chain)
return 1;
if ((event->status & DEPEVT_STATUS_LST) &&
(trb->ctrl & (DWC3_TRB_CTRL_LST |
struct dwc3_trb *trb;
unsigned int slot;
unsigned int i;
+ int count = 0;
int ret;
do {
+ int chain;
+
req = next_request(&dep->started_list);
if (WARN_ON_ONCE(!req))
return 1;
+ chain = req->request.num_mapped_sgs > 0;
i = 0;
do {
slot = req->first_trb_index + i;
slot++;
slot %= DWC3_TRB_NUM;
trb = &dep->trb_pool[slot];
+ count += trb->size & DWC3_TRB_SIZE_MASK;
ret = __dwc3_cleanup_done_trbs(dwc, dep, req, trb,
- event, status);
+ event, status, chain);
if (ret)
break;
} while (++i < req->request.num_mapped_sgs);
+ /*
+ * We assume here we will always receive the entire data block
+ * which we should receive. Meaning, if we program RX to
+ * receive 4K but we receive only 2K, we assume that's all we
+ * should receive and we simply bounce the request back to the
+ * gadget driver for further processing.
+ */
+ req->request.actual += req->request.length - count;
dwc3_gadget_giveback(dep, req, status);
if (ret)
break;
case USB_RECIP_ENDPOINT:
+ if (!cdev->config)
+ break;
endp = ((w_index & 0x80) >> 3) | (w_index & 0x0f);
list_for_each_entry(f, &cdev->config->functions, list) {
if (test_bit(endp, f->endpoints))
cdev->os_desc_req = usb_ep_alloc_request(ep0, GFP_KERNEL);
if (!cdev->os_desc_req) {
- ret = PTR_ERR(cdev->os_desc_req);
+ ret = -ENOMEM;
goto end;
}
/* OS feature descriptor length <= 4kB */
cdev->os_desc_req->buf = kmalloc(4096, GFP_KERNEL);
if (!cdev->os_desc_req->buf) {
- ret = PTR_ERR(cdev->os_desc_req->buf);
+ ret = -ENOMEM;
kfree(cdev->os_desc_req);
goto end;
}
{
struct gadget_info *gi = to_gadget_info(item);
+ mutex_lock(&gi->lock);
unregister_gadget(gi);
+ mutex_unlock(&gi->lock);
}
EXPORT_SYMBOL_GPL(unregister_gadget_item);
{
struct sk_buff *skb2 = NULL;
struct usb_ep *in = port->in_ep;
- int padlen = 0;
- u16 len = skb->len;
+ int headroom, tailroom, padlen = 0;
+ u16 len;
- int headroom = skb_headroom(skb);
- int tailroom = skb_tailroom(skb);
+ if (!skb)
+ return NULL;
+
+ len = skb->len;
+ headroom = skb_headroom(skb);
+ tailroom = skb_tailroom(skb);
/* When (len + EEM_HLEN + ETH_FCS_LEN) % in->maxpacket) is 0,
* stick two bytes of zero-length EEM packet on the end.
{
struct sk_buff *skb2;
+ if (!skb)
+ return NULL;
+
skb2 = skb_realloc_headroom(skb, sizeof(struct rndis_packet_msg_type));
rndis_add_hdr(skb2);
{
rndis_reset_cmplt_type *resp;
rndis_resp_t *r;
+ u8 *xbuf;
+ u32 length;
+
+ /* drain the response queue */
+ while ((xbuf = rndis_get_next_response(params, &length)))
+ rndis_free_response(params, xbuf);
r = rndis_add_response(params, sizeof(rndis_reset_cmplt_type));
if (!r)
/* Multi frame CDC protocols may store the frame for
* later which is not a dropped frame.
*/
- if (dev->port_usb->supports_multi_frame)
+ if (dev->port_usb &&
+ dev->port_usb->supports_multi_frame)
goto multiframe;
goto drop;
}
*/
{
struct list_head *pool = &port->write_pool;
- struct usb_ep *in = port->port_usb->in;
+ struct usb_ep *in;
int status = 0;
bool do_tty_wake = false;
+ if (!port->port_usb)
+ return status;
+
+ in = port->port_usb->in;
+
while (!port->write_busy && !list_empty(pool)) {
struct usb_request *req;
int len;
if (!data) {
kfree(*class_array);
*class_array = NULL;
- ret = PTR_ERR(data);
+ ret = -ENOMEM;
goto unlock;
}
cl_arr = *class_array;
*/
spin_lock_irq(&epdata->dev->lock);
value = -ENODEV;
- if (unlikely(epdata->ep))
+ if (unlikely(epdata->ep == NULL))
goto fail;
req = usb_ep_alloc_request(epdata->ep, GFP_ATOMIC);
}
if (is_sync_kiocb(iocb)) {
value = ep_io(epdata, buf, len);
- if (value >= 0 && copy_to_iter(buf, value, to))
+ if (value >= 0 && (copy_to_iter(buf, value, to) != value))
value = -EFAULT;
} else {
struct kiocb_priv *priv = kzalloc(sizeof *priv, GFP_KERNEL);
return;
if (req->num_mapped_sgs) {
- dma_unmap_sg(dev, req->sg, req->num_mapped_sgs,
+ dma_unmap_sg(dev, req->sg, req->num_sgs,
is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
req->num_mapped_sgs = 0;
if (ret != -EPROBE_DEFER)
list_del(&driver->pending);
if (ret)
- goto err4;
+ goto err5;
break;
}
}
return 0;
+err5:
+ device_del(&udc->dev);
+
err4:
list_del(&udc->list);
mutex_unlock(&udc_lock);
tmp = in_be16(&udc->usb_param->frame_n);
if (tmp & 0x8000)
- tmp = tmp & 0x07ff;
- else
- tmp = -EINVAL;
-
- return (int)tmp;
+ return tmp & 0x07ff;
+ return -EINVAL;
}
static int fsl_qe_start(struct usb_gadget *gadget,
struct qe_ep *ep;
if (wValue != 0 || wLength != 0
- || pipe > USB_MAX_ENDPOINTS)
+ || pipe >= USB_MAX_ENDPOINTS)
break;
ep = &udc->eps[pipe];
/* DRD_CON */
#define DRD_CON_PERI_CON BIT(24)
+#define DRD_CON_VBOUT BIT(0)
/* USB_INT_ENA_1 and USB_INT_STA_1 */
#define USB_INT_1_B3_PLLWKUP BIT(31)
{
/* FIXME: How to change host / peripheral mode as well? */
usb3_set_bit(usb3, DRD_CON_PERI_CON, USB3_DRD_CON);
+ usb3_clear_bit(usb3, DRD_CON_VBOUT, USB3_DRD_CON);
usb3_write(usb3, ~0, USB3_USB_INT_STA_1);
usb3_enable_irq_1(usb3, USB_INT_1_VBUS_CNG);
int port = HCS_N_PORTS(ehci->hcs_params);
while (port--) {
- ehci_writel(ehci, PORT_RWC_BITS,
- &ehci->regs->port_status[port]);
spin_unlock_irq(&ehci->lock);
ehci_port_power(ehci, port, false);
spin_lock_irq(&ehci->lock);
+ ehci_writel(ehci, PORT_RWC_BITS,
+ &ehci->regs->port_status[port]);
}
}
if (pin_number > 7)
return;
- mask = 1u << pin_number;
+ mask = 1u << (pin_number % 4);
idx = pin_number / 4;
if (value)
ret = 0;
virt_dev = xhci->devs[slot_id];
+ if (!virt_dev)
+ return -ENODEV;
+
cmd = xhci_alloc_command(xhci, false, true, GFP_NOIO);
if (!cmd) {
xhci_dbg(xhci, "Couldn't allocate command structure.\n");
usb_remove_hcd(xhci->shared_hcd);
usb_put_hcd(xhci->shared_hcd);
}
- usb_hcd_pci_remove(dev);
/* Workaround for spurious wakeups at shutdown with HSW */
if (xhci->quirks & XHCI_SPURIOUS_WAKEUP)
pci_set_power_state(dev, PCI_D3hot);
+
+ usb_hcd_pci_remove(dev);
}
#ifdef CONFIG_PM
spin_lock_irqsave(&xhci->lock, flags);
ep->stop_cmds_pending--;
+ if (xhci->xhc_state & XHCI_STATE_REMOVING) {
+ spin_unlock_irqrestore(&xhci->lock, flags);
+ return;
+ }
if (xhci->xhc_state & XHCI_STATE_DYING) {
xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
"Stop EP timer ran, but another timer marked "
spin_unlock_irqrestore(&xhci->lock, flags);
xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
"Calling usb_hc_died()");
- usb_hc_died(xhci_to_hcd(xhci)->primary_hcd);
+ usb_hc_died(xhci_to_hcd(xhci));
xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb,
"xHCI host controller is dead.");
}
cmd = list_entry(xhci->cmd_list.next, struct xhci_command, cmd_list);
- if (cmd->command_trb != xhci->cmd_ring->dequeue) {
- xhci_err(xhci,
- "Command completion event does not match command\n");
- return;
- }
-
del_timer(&xhci->cmd_timer);
trace_xhci_cmd_completion(cmd_trb, (struct xhci_generic_trb *) event);
xhci_handle_stopped_cmd_ring(xhci, cmd);
return;
}
+
+ if (cmd->command_trb != xhci->cmd_ring->dequeue) {
+ xhci_err(xhci,
+ "Command completion event does not match command\n");
+ return;
+ }
+
/*
* Host aborted the command ring, check if the current command was
* supposed to be aborted, otherwise continue normally.
send_addr = addr;
/* Queue the TRBs, even if they are zero-length */
- for (enqd_len = 0; enqd_len < full_len; enqd_len += trb_buff_len) {
+ for (enqd_len = 0; first_trb || enqd_len < full_len;
+ enqd_len += trb_buff_len) {
field = TRB_TYPE(TRB_NORMAL);
/* TRB buffer should not cross 64KB boundaries */
{
char data[30 *3 + 4];
char *d = data;
- int m = (sizeof(data) - 1) / 3;
+ int m = (sizeof(data) - 1) / 3 - 1;
int bytes_read = 0;
int retry_on_empty = 10;
int retry_on_timeout = 5;
int i = 0;
char data[30 *3 + 4];
char *d = data;
- int m = (sizeof(data) - 1) / 3;
+ int m = (sizeof(data) - 1) / 3 - 1;
int l = 0;
struct u132_target *target = &ftdi->target[ed];
struct u132_command *command = &ftdi->command[
if (packet_bytes > 2) {
char diag[30 *3 + 4];
char *d = diag;
- int m = (sizeof(diag) - 1) / 3;
+ int m = (sizeof(diag) - 1) / 3 - 1;
char *b = ftdi->bulk_in_buffer;
int bytes_read = 0;
diag[0] = 0;
if (packet_bytes > 2) {
char diag[30 *3 + 4];
char *d = diag;
- int m = (sizeof(diag) - 1) / 3;
+ int m = (sizeof(diag) - 1) / 3 - 1;
char *b = ftdi->bulk_in_buffer;
int bytes_read = 0;
unsigned char c = 0;
if (packet_bytes > 2) {
char diag[30 *3 + 4];
char *d = diag;
- int m = (sizeof(diag) - 1) / 3;
+ int m = (sizeof(diag) - 1) / 3 - 1;
char *b = ftdi->bulk_in_buffer;
int bytes_read = 0;
diag[0] = 0;
{
struct usb_sg_request *req = (struct usb_sg_request *) _req;
- req->status = -ETIMEDOUT;
usb_sg_cancel(req);
}
mod_timer(&sg_timer, jiffies +
msecs_to_jiffies(SIMPLE_IO_TIMEOUT));
usb_sg_wait(req);
- del_timer_sync(&sg_timer);
- retval = req->status;
+ if (!del_timer_sync(&sg_timer))
+ retval = -ETIMEDOUT;
+ else
+ retval = req->status;
/* FIXME check resulting data pattern */
ktime_get_ts64(&start);
retval = usbtest_do_ioctl(intf, param_32);
- if (retval)
+ if (retval < 0)
goto free_mutex;
ktime_get_ts64(&end);
config USB_MUSB_TUSB6010
tristate "TUSB6010"
depends on HAS_IOMEM
- depends on ARCH_OMAP2PLUS || COMPILE_TEST
+ depends on (ARCH_OMAP2PLUS || COMPILE_TEST) && !BLACKFIN
depends on NOP_USB_XCEIV = USB_MUSB_HDRC # both built-in or both modules
config USB_MUSB_OMAP2PLUS
u32 temp;
int retval = 0;
unsigned long flags;
+ bool start_musb = false;
spin_lock_irqsave(&musb->lock, flags);
* logic relating to VBUS power-up.
*/
if (!hcd->self.is_b_host && musb_has_gadget(musb))
- musb_start(musb);
+ start_musb = true;
break;
case USB_PORT_FEAT_RESET:
musb_port_reset(musb, true);
retval = -EPIPE;
}
spin_unlock_irqrestore(&musb->lock, flags);
+
+ if (start_musb)
+ musb_start(musb);
+
return retval;
}
int usb_gen_phy_init(struct usb_phy *phy)
{
struct usb_phy_generic *nop = dev_get_drvdata(phy->dev);
+ int ret;
if (!IS_ERR(nop->vcc)) {
if (regulator_enable(nop->vcc))
dev_err(phy->dev, "Failed to enable power\n");
}
- if (!IS_ERR(nop->clk))
- clk_prepare_enable(nop->clk);
+ if (!IS_ERR(nop->clk)) {
+ ret = clk_prepare_enable(nop->clk);
+ if (ret)
+ return ret;
+ }
nop_reset(nop);
(rev >> 4) & 0xf, rev & 0xf, config->extcon, otg_dev->id,
otg_dev->vbus);
+ platform_set_drvdata(pdev, otg_dev);
+
return 0;
}
if (gpio > 0)
dparam->enable_gpio = gpio;
- if (dparam->type == USBHS_TYPE_RCAR_GEN2)
+ if (dparam->type == USBHS_TYPE_RCAR_GEN2 ||
+ dparam->type == USBHS_TYPE_RCAR_GEN3)
dparam->has_usb_dmac = 1;
return info;
/* use PIO if packet is less than pio_dma_border or pipe is DCP */
if ((len < usbhs_get_dparam(priv, pio_dma_border)) ||
- usbhs_pipe_is_dcp(pipe))
+ usbhs_pipe_type_is(pipe, USB_ENDPOINT_XFER_ISOC))
goto usbhsf_pio_prepare_push;
/* check data length if this driver don't use USB-DMAC */
/* use PIO if packet is less than pio_dma_border or pipe is DCP */
if ((pkt->length < usbhs_get_dparam(priv, pio_dma_border)) ||
- usbhs_pipe_is_dcp(pipe))
+ usbhs_pipe_type_is(pipe, USB_ENDPOINT_XFER_ISOC))
goto usbhsf_pio_prepare_pop;
fifo = usbhsf_get_dma_fifo(priv, pkt);
if (usbhs_mod_is_host(priv))
usbhs_write(priv, INTSTS1, ~irq_state.intsts1 & INTSTS1_MAGIC);
- usbhs_write(priv, BRDYSTS, ~irq_state.brdysts);
+ /*
+ * The driver should not clear the xxxSTS after the line of
+ * "call irq callback functions" because each "if" statement is
+ * possible to call the callback function for avoiding any side effects.
+ */
+ if (irq_state.intsts0 & BRDY)
+ usbhs_write(priv, BRDYSTS, ~irq_state.brdysts);
usbhs_write(priv, NRDYSTS, ~irq_state.nrdysts);
- usbhs_write(priv, BEMPSTS, ~irq_state.bempsts);
+ if (irq_state.intsts0 & BEMP)
+ usbhs_write(priv, BEMPSTS, ~irq_state.bempsts);
/*
* call irq callback functions
* use dmaengine if possible.
* It will use pio handler if impossible.
*/
- if (usb_endpoint_dir_in(desc))
+ if (usb_endpoint_dir_in(desc)) {
pipe->handler = &usbhs_fifo_dma_push_handler;
- else
+ } else {
pipe->handler = &usbhs_fifo_dma_pop_handler;
+ usbhs_xxxsts_clear(priv, BRDYSTS,
+ usbhs_pipe_number(pipe));
+ }
ret = 0;
}
gpriv->transceiver = usb_get_phy(USB_PHY_TYPE_UNDEFINED);
dev_info(dev, "%stransceiver found\n",
- gpriv->transceiver ? "" : "no ");
+ !IS_ERR(gpriv->transceiver) ? "" : "no ");
/*
* CAUTION
{ USB_DEVICE(FTDI_VID, FTDI_ELV_TFD128_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_ELV_FM3RX_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_ELV_WS777_PID) },
+ { USB_DEVICE(FTDI_VID, FTDI_PALMSENS_PID) },
+ { USB_DEVICE(FTDI_VID, FTDI_IVIUM_XSTAT_PID) },
{ USB_DEVICE(FTDI_VID, LINX_SDMUSBQSS_PID) },
{ USB_DEVICE(FTDI_VID, LINX_MASTERDEVEL2_PID) },
{ USB_DEVICE(FTDI_VID, LINX_FUTURE_0_PID) },
{ USB_DEVICE(ICPDAS_VID, ICPDAS_I7560U_PID) },
{ USB_DEVICE(ICPDAS_VID, ICPDAS_I7561U_PID) },
{ USB_DEVICE(ICPDAS_VID, ICPDAS_I7563U_PID) },
+ { USB_DEVICE(WICED_VID, WICED_USB20706V2_PID) },
{ } /* Terminating entry */
};
#define FTDI_4N_GALAXY_DE_2_PID 0xF3C1
#define FTDI_4N_GALAXY_DE_3_PID 0xF3C2
+/*
+ * Ivium Technologies product IDs
+ */
+#define FTDI_PALMSENS_PID 0xf440
+#define FTDI_IVIUM_XSTAT_PID 0xf441
+
/*
* Linx Technologies product ids
*/
#define INTREPID_VALUECAN_PID 0x0601
#define INTREPID_NEOVI_PID 0x0701
+/*
+ * WICED USB UART
+ */
+#define WICED_VID 0x0A5C
+#define WICED_USB20706V2_PID 0x6422
+
/*
* Definitions for ID TECH (www.idt-net.com) devices
*/
if (urb->transfer_buffer == NULL) {
urb->transfer_buffer = kmalloc(URB_TRANSFER_BUFFER_SIZE,
- GFP_KERNEL);
+ GFP_ATOMIC);
if (!urb->transfer_buffer)
goto exit;
}
}
if (urb->transfer_buffer == NULL) {
- urb->transfer_buffer =
- kmalloc(URB_TRANSFER_BUFFER_SIZE, GFP_KERNEL);
+ urb->transfer_buffer = kmalloc(URB_TRANSFER_BUFFER_SIZE,
+ GFP_ATOMIC);
if (!urb->transfer_buffer)
goto exit;
}
#define TELIT_PRODUCT_LE920 0x1200
#define TELIT_PRODUCT_LE910 0x1201
#define TELIT_PRODUCT_LE910_USBCFG4 0x1206
+#define TELIT_PRODUCT_LE920A4_1207 0x1207
+#define TELIT_PRODUCT_LE920A4_1208 0x1208
+#define TELIT_PRODUCT_LE920A4_1211 0x1211
+#define TELIT_PRODUCT_LE920A4_1212 0x1212
+#define TELIT_PRODUCT_LE920A4_1213 0x1213
+#define TELIT_PRODUCT_LE920A4_1214 0x1214
/* ZTE PRODUCTS */
#define ZTE_VENDOR_ID 0x19d2
#define VIATELECOM_VENDOR_ID 0x15eb
#define VIATELECOM_PRODUCT_CDS7 0x0001
+/* WeTelecom products */
+#define WETELECOM_VENDOR_ID 0x22de
+#define WETELECOM_PRODUCT_WMD200 0x6801
+#define WETELECOM_PRODUCT_6802 0x6802
+#define WETELECOM_PRODUCT_WMD300 0x6803
+
struct option_blacklist_info {
/* bitmask of interface numbers blacklisted for send_setup */
const unsigned long sendsetup;
.reserved = BIT(1) | BIT(5),
};
+static const struct option_blacklist_info telit_le920a4_blacklist_1 = {
+ .sendsetup = BIT(0),
+ .reserved = BIT(1),
+};
+
static const struct option_blacklist_info telit_le922_blacklist_usbcfg0 = {
.sendsetup = BIT(2),
.reserved = BIT(0) | BIT(1) | BIT(3),
.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920),
.driver_info = (kernel_ulong_t)&telit_le920_blacklist },
+ { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1207) },
+ { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1208),
+ .driver_info = (kernel_ulong_t)&telit_le920a4_blacklist_1 },
+ { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1211),
+ .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 },
+ { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1212),
+ .driver_info = (kernel_ulong_t)&telit_le920a4_blacklist_1 },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1213, 0xff) },
+ { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1214),
+ .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 },
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */
{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0002, 0xff, 0xff, 0xff),
.driver_info = (kernel_ulong_t)&net_intf1_blacklist },
.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */
{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */
+ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x7e11, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/A3 */
{ USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) }, /* OLICARD300 - MT6225 */
{ USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) },
{ USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) },
+ { USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD200, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_6802, 0xff, 0xff, 0xff) },
+ { USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD300, 0xff, 0xff, 0xff) },
{ } /* Terminating entry */
};
MODULE_DEVICE_TABLE(usb, option_ids);
/* Infineon Flashloader driver */
#define FLASHLOADER_IDS() \
{ USB_DEVICE_INTERFACE_CLASS(0x058b, 0x0041, USB_CLASS_CDC_DATA) }, \
- { USB_DEVICE(0x8087, 0x0716) }
+ { USB_DEVICE(0x8087, 0x0716) }, \
+ { USB_DEVICE(0x8087, 0x0801) }
DEVICE(flashloader, FLASHLOADER_IDS);
/* Google Serial USB SubClass */
rc = usb_register(udriver);
if (rc)
- return rc;
+ goto failed_usb_register;
for (sd = serial_drivers; *sd; ++sd) {
(*sd)->usb_driver = udriver;
while (sd-- > serial_drivers)
usb_serial_deregister(*sd);
usb_deregister(udriver);
+failed_usb_register:
+ kfree(udriver);
return rc;
}
EXPORT_SYMBOL_GPL(usb_serial_register_drivers);
}
static int vfio_pci_set_ctx_trigger_single(struct eventfd_ctx **ctx,
- uint32_t flags, void *data)
+ unsigned int count, uint32_t flags,
+ void *data)
{
- int32_t fd = *(int32_t *)data;
-
- if (!(flags & VFIO_IRQ_SET_DATA_TYPE_MASK))
- return -EINVAL;
-
/* DATA_NONE/DATA_BOOL enables loopback testing */
if (flags & VFIO_IRQ_SET_DATA_NONE) {
- if (*ctx)
- eventfd_signal(*ctx, 1);
- return 0;
+ if (*ctx) {
+ if (count) {
+ eventfd_signal(*ctx, 1);
+ } else {
+ eventfd_ctx_put(*ctx);
+ *ctx = NULL;
+ }
+ return 0;
+ }
} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
- uint8_t trigger = *(uint8_t *)data;
+ uint8_t trigger;
+
+ if (!count)
+ return -EINVAL;
+
+ trigger = *(uint8_t *)data;
if (trigger && *ctx)
eventfd_signal(*ctx, 1);
- return 0;
- }
- /* Handle SET_DATA_EVENTFD */
- if (fd == -1) {
- if (*ctx)
- eventfd_ctx_put(*ctx);
- *ctx = NULL;
return 0;
- } else if (fd >= 0) {
- struct eventfd_ctx *efdctx;
- efdctx = eventfd_ctx_fdget(fd);
- if (IS_ERR(efdctx))
- return PTR_ERR(efdctx);
- if (*ctx)
- eventfd_ctx_put(*ctx);
- *ctx = efdctx;
+ } else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
+ int32_t fd;
+
+ if (!count)
+ return -EINVAL;
+
+ fd = *(int32_t *)data;
+ if (fd == -1) {
+ if (*ctx)
+ eventfd_ctx_put(*ctx);
+ *ctx = NULL;
+ } else if (fd >= 0) {
+ struct eventfd_ctx *efdctx;
+
+ efdctx = eventfd_ctx_fdget(fd);
+ if (IS_ERR(efdctx))
+ return PTR_ERR(efdctx);
+
+ if (*ctx)
+ eventfd_ctx_put(*ctx);
+
+ *ctx = efdctx;
+ }
return 0;
- } else
- return -EINVAL;
+ }
+
+ return -EINVAL;
}
static int vfio_pci_set_err_trigger(struct vfio_pci_device *vdev,
unsigned index, unsigned start,
unsigned count, uint32_t flags, void *data)
{
- if (index != VFIO_PCI_ERR_IRQ_INDEX)
+ if (index != VFIO_PCI_ERR_IRQ_INDEX || start != 0 || count > 1)
return -EINVAL;
- /*
- * We should sanitize start & count, but that wasn't caught
- * originally, so this IRQ index must forever ignore them :-(
- */
-
- return vfio_pci_set_ctx_trigger_single(&vdev->err_trigger, flags, data);
+ return vfio_pci_set_ctx_trigger_single(&vdev->err_trigger,
+ count, flags, data);
}
static int vfio_pci_set_req_trigger(struct vfio_pci_device *vdev,
unsigned index, unsigned start,
unsigned count, uint32_t flags, void *data)
{
- if (index != VFIO_PCI_REQ_IRQ_INDEX || start != 0 || count != 1)
+ if (index != VFIO_PCI_REQ_IRQ_INDEX || start != 0 || count > 1)
return -EINVAL;
- return vfio_pci_set_ctx_trigger_single(&vdev->req_trigger, flags, data);
+ return vfio_pci_set_ctx_trigger_single(&vdev->req_trigger,
+ count, flags, data);
}
int vfio_pci_set_irqs_ioctl(struct vfio_pci_device *vdev, uint32_t flags,
struct scatterlist *tvc_prot_sgl;
struct page **tvc_upages;
/* Pointer to response header iovec */
- struct iovec *tvc_resp_iov;
+ struct iovec tvc_resp_iov;
/* Pointer to vhost_scsi for our device */
struct vhost_scsi *tvc_vhost;
/* Pointer to vhost_virtqueue for the cmd */
memcpy(v_rsp.sense, cmd->tvc_sense_buf,
se_cmd->scsi_sense_length);
- iov_iter_init(&iov_iter, READ, cmd->tvc_resp_iov,
+ iov_iter_init(&iov_iter, READ, &cmd->tvc_resp_iov,
cmd->tvc_in_iovs, sizeof(v_rsp));
ret = copy_to_iter(&v_rsp, sizeof(v_rsp), &iov_iter);
if (likely(ret == sizeof(v_rsp))) {
}
cmd->tvc_vhost = vs;
cmd->tvc_vq = vq;
- cmd->tvc_resp_iov = &vq->iov[out];
+ cmd->tvc_resp_iov = vq->iov[out];
cmd->tvc_in_iovs = in;
pr_debug("vhost_scsi got command opcode: %#02x, lun: %d\n",
{
void *priv = NULL;
long err;
- struct vhost_memory *memory;
+ struct vhost_umem *umem;
mutex_lock(&n->dev.mutex);
err = vhost_dev_check_owner(&n->dev);
if (err)
goto done;
- memory = vhost_dev_reset_owner_prepare();
- if (!memory) {
+ umem = vhost_dev_reset_owner_prepare();
+ if (!umem) {
err = -ENOMEM;
goto done;
}
vhost_test_stop(n, &priv);
vhost_test_flush(n);
- vhost_dev_reset_owner(&n->dev, memory);
+ vhost_dev_reset_owner(&n->dev, umem);
done:
mutex_unlock(&n->dev.mutex);
return err;
vhost_disable_notify(&vsock->dev, vq);
for (;;) {
+ u32 len;
+
if (!vhost_vsock_more_replies(vsock)) {
/* Stop tx until the device processes already
* pending replies. Leave tx virtqueue
continue;
}
+ len = pkt->len;
+
/* Only accept correctly addressed packets */
if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid)
virtio_transport_recv_pkt(pkt);
else
virtio_transport_free_pkt(pkt);
- vhost_add_used(vq, head, sizeof(pkt->hdr) + pkt->len);
+ vhost_add_used(vq, head, sizeof(pkt->hdr) + len);
added = true;
}
* making all of the arch DMA ops work on the vring device itself
* is a mess. For now, we use the parent device for DMA ops.
*/
-struct device *vring_dma_dev(const struct vring_virtqueue *vq)
+static struct device *vring_dma_dev(const struct vring_virtqueue *vq)
{
return vq->vq.vdev->dev.parent;
}
* host should service the ring ASAP. */
if (out_sgs)
vq->notify(&vq->vq);
+ if (indirect)
+ kfree(desc);
END_USE(vq);
return -ENOSPC;
}
if (indirect)
kfree(desc);
+ END_USE(vq);
return -EIO;
}
rc = -ENOMEM;
goto out;
}
- } else {
+ } else if (msg_type == XS_TRANSACTION_END) {
list_for_each_entry(trans, &u->transactions, list)
if (trans->handle.id == u->u.msg.tx_id)
break;
case 1:
_debug("extract FID count");
ret = afs_extract_data(call, skb, last, &call->tmp, 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ if (ret < 0)
+ return ret;
call->count = ntohl(call->tmp);
_debug("FID count: %u", call->count);
_debug("extract FID array");
ret = afs_extract_data(call, skb, last, call->buffer,
call->count * 3 * 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ if (ret < 0)
+ return ret;
_debug("unmarshall FID array");
call->request = kcalloc(call->count,
case 3:
_debug("extract CB count");
ret = afs_extract_data(call, skb, last, &call->tmp, 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ if (ret < 0)
+ return ret;
tmp = ntohl(call->tmp);
_debug("CB count: %u", tmp);
_debug("extract CB array");
ret = afs_extract_data(call, skb, last, call->request,
call->count * 3 * 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ if (ret < 0)
+ return ret;
_debug("unmarshall CB array");
cb = call->request;
call->unmarshall++;
case 5:
- _debug("trailer");
- if (skb->len != 0)
- return -EBADMSG;
+ ret = afs_data_complete(call, skb, last);
+ if (ret < 0)
+ return ret;
/* Record that the message was unmarshalled successfully so
* that the call destructor can know do the callback breaking
break;
}
- if (!last)
- return 0;
call->state = AFS_CALL_REPLYING;
{
struct afs_server *server;
struct in_addr addr;
+ int ret;
_enter(",{%u},%d", skb->len, last);
- if (skb->len > 0)
- return -EBADMSG;
- if (!last)
- return 0;
+ ret = afs_data_complete(call, skb, last);
+ if (ret < 0)
+ return ret;
/* no unmarshalling required */
call->state = AFS_CALL_REPLYING;
_enter(",{%u},%d", skb->len, last);
+ /* There are some arguments that we ignore */
+ afs_data_consumed(call, skb);
if (!last)
- return 0;
+ return -EAGAIN;
/* no unmarshalling required */
call->state = AFS_CALL_REPLYING;
static int afs_deliver_cb_probe(struct afs_call *call, struct sk_buff *skb,
bool last)
{
+ int ret;
+
_enter(",{%u},%d", skb->len, last);
- if (skb->len > 0)
- return -EBADMSG;
- if (!last)
- return 0;
+ ret = afs_data_complete(call, skb, last);
+ if (ret < 0)
+ return ret;
/* no unmarshalling required */
call->state = AFS_CALL_REPLYING;
_enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
- if (skb->len > 0)
- return -EBADMSG;
- if (!last)
- return 0;
+ ret = afs_data_complete(call, skb, last);
+ if (ret < 0)
+ return ret;
switch (call->unmarshall) {
case 0:
break;
}
- if (!last)
- return 0;
+ ret = afs_data_complete(call, skb, last);
+ if (ret < 0)
+ return ret;
call->state = AFS_CALL_REPLYING;
static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *call,
struct sk_buff *skb, bool last)
{
+ int ret;
+
_enter(",{%u},%d", skb->len, last);
- if (skb->len > 0)
- return -EBADMSG;
- if (!last)
- return 0;
+ ret = afs_data_complete(call, skb, last);
+ if (ret < 0)
+ return ret;
/* no unmarshalling required */
call->state = AFS_CALL_REPLYING;
{
struct afs_vnode *vnode = call->reply;
const __be32 *bp;
+ int ret;
_enter(",,%u", last);
- afs_transfer_reply(call, skb);
- if (!last)
- return 0;
-
- if (call->reply_size != call->reply_max)
- return -EBADMSG;
+ ret = afs_transfer_reply(call, skb, last);
+ if (ret < 0)
+ return ret;
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
case 1:
_debug("extract data length (MSW)");
ret = afs_extract_data(call, skb, last, &call->tmp, 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ if (ret < 0)
+ return ret;
call->count = ntohl(call->tmp);
_debug("DATA length MSW: %u", call->count);
case 2:
_debug("extract data length");
ret = afs_extract_data(call, skb, last, &call->tmp, 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ if (ret < 0)
+ return ret;
call->count = ntohl(call->tmp);
_debug("DATA length: %u", call->count);
ret = afs_extract_data(call, skb, last, buffer,
call->count);
kunmap_atomic(buffer);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ if (ret < 0)
+ return ret;
}
call->offset = 0;
case 4:
ret = afs_extract_data(call, skb, last, call->buffer,
(21 + 3 + 6) * 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ if (ret < 0)
+ return ret;
bp = call->buffer;
xdr_decode_AFSFetchStatus(&bp, &vnode->status, vnode, NULL);
call->unmarshall++;
case 5:
- _debug("trailer");
- if (skb->len != 0)
- return -EBADMSG;
+ ret = afs_data_complete(call, skb, last);
+ if (ret < 0)
+ return ret;
break;
}
- if (!last)
- return 0;
-
if (call->count < PAGE_SIZE) {
_debug("clear");
page = call->reply3;
{
_enter(",{%u},%d", skb->len, last);
- if (skb->len > 0)
- return -EBADMSG; /* shouldn't be any reply data */
- return 0;
+ /* shouldn't be any reply data */
+ return afs_data_complete(call, skb, last);
}
/*
{
struct afs_vnode *vnode = call->reply;
const __be32 *bp;
+ int ret;
_enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
- afs_transfer_reply(call, skb);
- if (!last)
- return 0;
-
- if (call->reply_size != call->reply_max)
- return -EBADMSG;
+ ret = afs_transfer_reply(call, skb, last);
+ if (ret < 0)
+ return ret;
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
{
struct afs_vnode *vnode = call->reply;
const __be32 *bp;
+ int ret;
_enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
- afs_transfer_reply(call, skb);
- if (!last)
- return 0;
-
- if (call->reply_size != call->reply_max)
- return -EBADMSG;
+ ret = afs_transfer_reply(call, skb, last);
+ if (ret < 0)
+ return ret;
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
{
struct afs_vnode *dvnode = call->reply, *vnode = call->reply2;
const __be32 *bp;
+ int ret;
_enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
- afs_transfer_reply(call, skb);
- if (!last)
- return 0;
-
- if (call->reply_size != call->reply_max)
- return -EBADMSG;
+ ret = afs_transfer_reply(call, skb, last);
+ if (ret < 0)
+ return ret;
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
{
struct afs_vnode *vnode = call->reply;
const __be32 *bp;
+ int ret;
_enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
- afs_transfer_reply(call, skb);
- if (!last)
- return 0;
-
- if (call->reply_size != call->reply_max)
- return -EBADMSG;
+ ret = afs_transfer_reply(call, skb, last);
+ if (ret < 0)
+ return ret;
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
{
struct afs_vnode *orig_dvnode = call->reply, *new_dvnode = call->reply2;
const __be32 *bp;
+ int ret;
_enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
- afs_transfer_reply(call, skb);
- if (!last)
- return 0;
-
- if (call->reply_size != call->reply_max)
- return -EBADMSG;
+ ret = afs_transfer_reply(call, skb, last);
+ if (ret < 0)
+ return ret;
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
{
struct afs_vnode *vnode = call->reply;
const __be32 *bp;
+ int ret;
_enter(",,%u", last);
- afs_transfer_reply(call, skb);
- if (!last) {
- _leave(" = 0 [more]");
- return 0;
- }
-
- if (call->reply_size != call->reply_max) {
- _leave(" = -EBADMSG [%u != %u]",
- call->reply_size, call->reply_max);
- return -EBADMSG;
- }
+ ret = afs_transfer_reply(call, skb, last);
+ if (ret < 0)
+ return ret;
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
afs_dataversion_t *store_version;
struct afs_vnode *vnode = call->reply;
const __be32 *bp;
+ int ret;
_enter(",,%u", last);
- afs_transfer_reply(call, skb);
- if (!last) {
- _leave(" = 0 [more]");
- return 0;
- }
-
- if (call->reply_size != call->reply_max) {
- _leave(" = -EBADMSG [%u != %u]",
- call->reply_size, call->reply_max);
- return -EBADMSG;
- }
+ ret = afs_transfer_reply(call, skb, last);
+ if (ret < 0)
+ return ret;
/* unmarshall the reply once we've received all of it */
store_version = NULL;
_debug("extract status");
ret = afs_extract_data(call, skb, last, call->buffer,
12 * 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ if (ret < 0)
+ return ret;
bp = call->buffer;
xdr_decode_AFSFetchVolumeStatus(&bp, call->reply2);
/* extract the volume name length */
case 2:
ret = afs_extract_data(call, skb, last, &call->tmp, 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ if (ret < 0)
+ return ret;
call->count = ntohl(call->tmp);
_debug("volname length: %u", call->count);
if (call->count > 0) {
ret = afs_extract_data(call, skb, last, call->reply3,
call->count);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ if (ret < 0)
+ return ret;
}
p = call->reply3;
case 4:
ret = afs_extract_data(call, skb, last, call->buffer,
call->count);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ if (ret < 0)
+ return ret;
call->offset = 0;
call->unmarshall++;
/* extract the offline message length */
case 5:
ret = afs_extract_data(call, skb, last, &call->tmp, 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ if (ret < 0)
+ return ret;
call->count = ntohl(call->tmp);
_debug("offline msg length: %u", call->count);
if (call->count > 0) {
ret = afs_extract_data(call, skb, last, call->reply3,
call->count);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ if (ret < 0)
+ return ret;
}
p = call->reply3;
case 7:
ret = afs_extract_data(call, skb, last, call->buffer,
call->count);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ if (ret < 0)
+ return ret;
call->offset = 0;
call->unmarshall++;
/* extract the message of the day length */
case 8:
ret = afs_extract_data(call, skb, last, &call->tmp, 4);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ if (ret < 0)
+ return ret;
call->count = ntohl(call->tmp);
_debug("motd length: %u", call->count);
if (call->count > 0) {
ret = afs_extract_data(call, skb, last, call->reply3,
call->count);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ if (ret < 0)
+ return ret;
}
p = call->reply3;
case 10:
ret = afs_extract_data(call, skb, last, call->buffer,
call->count);
- switch (ret) {
- case 0: break;
- case -EAGAIN: return 0;
- default: return ret;
- }
+ if (ret < 0)
+ return ret;
call->offset = 0;
call->unmarshall++;
no_motd_padding:
case 11:
- _debug("trailer %d", skb->len);
- if (skb->len != 0)
- return -EBADMSG;
+ ret = afs_data_complete(call, skb, last);
+ if (ret < 0)
+ return ret;
break;
}
- if (!last)
- return 0;
-
_leave(" = 0 [done]");
return 0;
}
struct sk_buff *skb, bool last)
{
const __be32 *bp;
+ int ret;
_enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
- afs_transfer_reply(call, skb);
- if (!last)
- return 0;
-
- if (call->reply_size != call->reply_max)
- return -EBADMSG;
+ ret = afs_transfer_reply(call, skb, last);
+ if (ret < 0)
+ return ret;
/* unmarshall the reply once we've received all of it */
bp = call->buffer;
*/
extern int afs_open_socket(void);
extern void afs_close_socket(void);
+extern void afs_data_consumed(struct afs_call *, struct sk_buff *);
extern int afs_make_call(struct in_addr *, struct afs_call *, gfp_t,
const struct afs_wait_mode *);
extern struct afs_call *afs_alloc_flat_call(const struct afs_call_type *,
size_t, size_t);
extern void afs_flat_call_destructor(struct afs_call *);
-extern void afs_transfer_reply(struct afs_call *, struct sk_buff *);
+extern int afs_transfer_reply(struct afs_call *, struct sk_buff *, bool);
extern void afs_send_empty_reply(struct afs_call *);
extern void afs_send_simple_reply(struct afs_call *, const void *, size_t);
extern int afs_extract_data(struct afs_call *, struct sk_buff *, bool, void *,
size_t);
+static inline int afs_data_complete(struct afs_call *call, struct sk_buff *skb,
+ bool last)
+{
+ if (skb->len > 0)
+ return -EBADMSG;
+ afs_data_consumed(call, skb);
+ if (!last)
+ return -EAGAIN;
+ return 0;
+}
+
/*
* security.c
*/
}
/*
- * note that the data in a socket buffer is now delivered and that the buffer
- * should be freed
+ * Note that the data in a socket buffer is now consumed.
*/
-static void afs_data_delivered(struct sk_buff *skb)
+void afs_data_consumed(struct afs_call *call, struct sk_buff *skb)
{
if (!skb) {
_debug("DLVR NULL [%d]", atomic_read(&afs_outstanding_skbs));
} else {
_debug("DLVR %p{%u} [%d]",
skb, skb->mark, atomic_read(&afs_outstanding_skbs));
- if (atomic_dec_return(&afs_outstanding_skbs) == -1)
- BUG();
- rxrpc_kernel_data_delivered(skb);
+ rxrpc_kernel_data_consumed(call->rxcall, skb);
}
}
last = rxrpc_kernel_is_data_last(skb);
ret = call->type->deliver(call, skb, last);
switch (ret) {
+ case -EAGAIN:
+ if (last) {
+ _debug("short data");
+ goto unmarshal_error;
+ }
+ break;
case 0:
- if (last &&
- call->state == AFS_CALL_AWAIT_REPLY)
+ ASSERT(last);
+ if (call->state == AFS_CALL_AWAIT_REPLY)
call->state = AFS_CALL_COMPLETE;
break;
case -ENOTCONN:
abort_code = RX_INVALID_OPERATION;
goto do_abort;
default:
+ unmarshal_error:
abort_code = RXGEN_CC_UNMARSHAL;
if (call->state != AFS_CALL_AWAIT_REPLY)
abort_code = RXGEN_SS_UNMARSHAL;
call->state = AFS_CALL_ERROR;
break;
}
- afs_data_delivered(skb);
- skb = NULL;
- continue;
+ break;
case RXRPC_SKB_MARK_FINAL_ACK:
_debug("Rcv ACK");
call->state = AFS_CALL_COMPLETE;
}
/*
- * empty a socket buffer into a flat reply buffer
+ * Empty a socket buffer into a flat reply buffer.
*/
-void afs_transfer_reply(struct afs_call *call, struct sk_buff *skb)
+int afs_transfer_reply(struct afs_call *call, struct sk_buff *skb, bool last)
{
size_t len = skb->len;
- if (skb_copy_bits(skb, 0, call->buffer + call->reply_size, len) < 0)
- BUG();
- call->reply_size += len;
+ if (len > call->reply_max - call->reply_size) {
+ _leave(" = -EBADMSG [%zu > %u]",
+ len, call->reply_max - call->reply_size);
+ return -EBADMSG;
+ }
+
+ if (len > 0) {
+ if (skb_copy_bits(skb, 0, call->buffer + call->reply_size,
+ len) < 0)
+ BUG();
+ call->reply_size += len;
+ }
+
+ afs_data_consumed(call, skb);
+ if (!last)
+ return -EAGAIN;
+
+ if (call->reply_size != call->reply_max) {
+ _leave(" = -EBADMSG [%u != %u]",
+ call->reply_size, call->reply_max);
+ return -EBADMSG;
+ }
+ return 0;
}
/*
}
/*
- * grab the operation ID from an incoming cache manager call
+ * Grab the operation ID from an incoming cache manager call. The socket
+ * buffer is discarded on error or if we don't yet have sufficient data.
*/
static int afs_deliver_cm_op_id(struct afs_call *call, struct sk_buff *skb,
bool last)
call->offset += len;
if (call->offset < 4) {
- if (last) {
- _leave(" = -EBADMSG [op ID short]");
- return -EBADMSG;
- }
- _leave(" = 0 [incomplete]");
- return 0;
+ afs_data_consumed(call, skb);
+ _leave(" = -EAGAIN");
+ return -EAGAIN;
}
call->state = AFS_CALL_AWAIT_REQUEST;
}
/*
- * extract a piece of data from the received data socket buffers
+ * Extract a piece of data from the received data socket buffers.
*/
int afs_extract_data(struct afs_call *call, struct sk_buff *skb,
bool last, void *buf, size_t count)
call->offset += len;
if (call->offset < count) {
- if (last) {
- _leave(" = -EBADMSG [%d < %zu]", call->offset, count);
- return -EBADMSG;
- }
+ afs_data_consumed(call, skb);
_leave(" = -EAGAIN");
return -EAGAIN;
}
struct afs_cache_vlocation *entry;
__be32 *bp;
u32 tmp;
- int loop;
+ int loop, ret;
_enter(",,%u", last);
- afs_transfer_reply(call, skb);
- if (!last)
- return 0;
-
- if (call->reply_size != call->reply_max)
- return -EBADMSG;
+ ret = afs_transfer_reply(call, skb, last);
+ if (ret < 0)
+ return ret;
/* unmarshall the reply once we've received all of it */
entry = call->reply;
static const struct dentry_operations ops = {
.d_dname = simple_dname,
};
- return mount_pseudo(fs_type, "aio:", NULL, &ops, AIO_RING_MAGIC);
+ struct dentry *root = mount_pseudo(fs_type, "aio:", NULL, &ops,
+ AIO_RING_MAGIC);
+
+ if (!IS_ERR(root))
+ root->d_sb->s_iflags |= SB_I_NOEXEC;
+ return root;
}
/* aio_setup
}
return NULL;
}
+
/*
* Find an eligible tree to time-out
* A tree is eligible if :-
struct dentry *root = sb->s_root;
struct dentry *dentry;
struct dentry *expired;
+ struct dentry *found;
struct autofs_info *ino;
if (!root)
dentry = NULL;
while ((dentry = get_next_positive_subdir(dentry, root))) {
+ int flags = how;
+
spin_lock(&sbi->fs_lock);
ino = autofs4_dentry_ino(dentry);
- if (ino->flags & AUTOFS_INF_WANT_EXPIRE)
- expired = NULL;
- else
- expired = should_expire(dentry, mnt, timeout, how);
- if (!expired) {
+ if (ino->flags & AUTOFS_INF_WANT_EXPIRE) {
spin_unlock(&sbi->fs_lock);
continue;
}
+ spin_unlock(&sbi->fs_lock);
+
+ expired = should_expire(dentry, mnt, timeout, flags);
+ if (!expired)
+ continue;
+
+ spin_lock(&sbi->fs_lock);
ino = autofs4_dentry_ino(expired);
ino->flags |= AUTOFS_INF_WANT_EXPIRE;
spin_unlock(&sbi->fs_lock);
synchronize_rcu();
- spin_lock(&sbi->fs_lock);
- if (should_expire(expired, mnt, timeout, how)) {
- if (expired != dentry)
- dput(dentry);
- goto found;
- }
+ /* Make sure a reference is not taken on found if
+ * things have changed.
+ */
+ flags &= ~AUTOFS_EXP_LEAVES;
+ found = should_expire(expired, mnt, timeout, how);
+ if (!found || found != expired)
+ /* Something has changed, continue */
+ goto next;
+
+ if (expired != dentry)
+ dput(dentry);
+
+ spin_lock(&sbi->fs_lock);
+ goto found;
+next:
+ spin_lock(&sbi->fs_lock);
ino->flags &= ~AUTOFS_INF_WANT_EXPIRE;
+ spin_unlock(&sbi->fs_lock);
if (expired != dentry)
dput(expired);
- spin_unlock(&sbi->fs_lock);
}
return NULL;
struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
struct autofs_info *ino = autofs4_dentry_ino(dentry);
int status;
+ int state;
/* Block on any pending expire */
if (!(ino->flags & AUTOFS_INF_WANT_EXPIRE))
if (rcu_walk)
return -ECHILD;
+retry:
spin_lock(&sbi->fs_lock);
- if (ino->flags & AUTOFS_INF_EXPIRING) {
+ state = ino->flags & (AUTOFS_INF_WANT_EXPIRE | AUTOFS_INF_EXPIRING);
+ if (state == AUTOFS_INF_WANT_EXPIRE) {
+ spin_unlock(&sbi->fs_lock);
+ /*
+ * Possibly being selected for expire, wait until
+ * it's selected or not.
+ */
+ schedule_timeout_uninterruptible(HZ/10);
+ goto retry;
+ }
+ if (state & AUTOFS_INF_EXPIRING) {
spin_unlock(&sbi->fs_lock);
pr_debug("waiting for expire %p name=%pd\n", dentry, dentry);
current->flags |= PF_RANDOMIZE;
setup_new_exec(bprm);
+ install_exec_creds(bprm);
/* Do this so that we can load the interpreter, if need be. We will
change some of these later */
goto out;
#endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */
- install_exec_creds(bprm);
retval = create_elf_tables(bprm, &loc->elf_ex,
load_addr, interp_load_addr);
if (retval < 0)
* thaw_bdev drops it.
*/
sb = get_super(bdev);
- drop_super(sb);
+ if (sb)
+ drop_super(sb);
mutex_unlock(&bdev->bd_fsfreeze_mutex);
return sb;
}
{
struct dentry *dent;
dent = mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, BDEVFS_MAGIC);
- if (dent)
+ if (!IS_ERR(dent))
dent->d_sb->s_iflags |= SB_I_CGROUPWB;
return dent;
}
list_del(&ref2->list);
kmem_cache_free(btrfs_prelim_ref_cache, ref2);
+ cond_resched();
}
}
struct list_head ro_bgs;
struct list_head priority_tickets;
struct list_head tickets;
+ u64 tickets_id;
struct rw_semaphore groups_sem;
/* for block groups in our same type */
struct btrfs_workqueue *qgroup_rescan_workers;
struct completion qgroup_rescan_completion;
struct btrfs_work qgroup_rescan_work;
+ bool qgroup_rescan_running; /* protected by qgroup_rescan_lock */
/* filesystem state */
unsigned long fs_state;
struct list_head pinned_chunks;
int creating_free_space_tree;
+ /* Used to record internally whether fs has been frozen */
+ int fs_frozen;
};
struct btrfs_subvolume_writers {
struct btrfs_root *root,
u64 root_objectid, u64 owner, u64 offset,
struct btrfs_key *ins);
-int btrfs_reserve_extent(struct btrfs_root *root, u64 num_bytes,
+int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, u64 num_bytes,
u64 min_alloc_size, u64 empty_size, u64 hint_byte,
struct btrfs_key *ins, int is_data, int delalloc);
int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
struct btrfs_delayed_ref_head *existing;
struct btrfs_delayed_ref_head *head_ref = NULL;
struct btrfs_delayed_ref_root *delayed_refs;
- struct btrfs_qgroup_extent_record *qexisting;
int count_mod = 1;
int must_insert_reserved = 0;
qrecord->num_bytes = num_bytes;
qrecord->old_roots = NULL;
- qexisting = btrfs_qgroup_insert_dirty_extent(fs_info,
- delayed_refs,
- qrecord);
- if (qexisting)
+ if(btrfs_qgroup_insert_dirty_extent_nolock(fs_info,
+ delayed_refs, qrecord))
kfree(qrecord);
}
return 0;
}
-int btrfs_add_delayed_qgroup_reserve(struct btrfs_fs_info *fs_info,
- struct btrfs_trans_handle *trans,
- u64 ref_root, u64 bytenr, u64 num_bytes)
-{
- struct btrfs_delayed_ref_root *delayed_refs;
- struct btrfs_delayed_ref_head *ref_head;
- int ret = 0;
-
- if (!fs_info->quota_enabled || !is_fstree(ref_root))
- return 0;
-
- delayed_refs = &trans->transaction->delayed_refs;
-
- spin_lock(&delayed_refs->lock);
- ref_head = find_ref_head(&delayed_refs->href_root, bytenr, 0);
- if (!ref_head) {
- ret = -ENOENT;
- goto out;
- }
- WARN_ON(ref_head->qgroup_reserved || ref_head->qgroup_ref_root);
- ref_head->qgroup_ref_root = ref_root;
- ref_head->qgroup_reserved = num_bytes;
-out:
- spin_unlock(&delayed_refs->lock);
- return ret;
-}
-
int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
struct btrfs_trans_handle *trans,
u64 bytenr, u64 num_bytes,
u64 parent, u64 ref_root,
u64 owner, u64 offset, u64 reserved, int action,
struct btrfs_delayed_extent_op *extent_op);
-int btrfs_add_delayed_qgroup_reserve(struct btrfs_fs_info *fs_info,
- struct btrfs_trans_handle *trans,
- u64 ref_root, u64 bytenr, u64 num_bytes);
int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
struct btrfs_trans_handle *trans,
u64 bytenr, u64 num_bytes,
u32 nritems = btrfs_header_nritems(leaf);
int slot;
- if (nritems == 0)
+ if (nritems == 0) {
+ struct btrfs_root *check_root;
+
+ key.objectid = btrfs_header_owner(leaf);
+ key.type = BTRFS_ROOT_ITEM_KEY;
+ key.offset = (u64)-1;
+
+ check_root = btrfs_get_fs_root(root->fs_info, &key, false);
+ /*
+ * The only reason we also check NULL here is that during
+ * open_ctree() some roots has not yet been set up.
+ */
+ if (!IS_ERR_OR_NULL(check_root)) {
+ /* if leaf is the root, then it's fine */
+ if (leaf->start !=
+ btrfs_root_bytenr(&check_root->root_item)) {
+ CORRUPT("non-root leaf's nritems is 0",
+ leaf, root, 0);
+ return -EIO;
+ }
+ }
return 0;
+ }
/* Check the 0 item */
if (btrfs_item_offset_nr(leaf, 0) + btrfs_item_size_nr(leaf, 0) !=
return 0;
}
+static int check_node(struct btrfs_root *root, struct extent_buffer *node)
+{
+ unsigned long nr = btrfs_header_nritems(node);
+
+ if (nr == 0 || nr > BTRFS_NODEPTRS_PER_BLOCK(root)) {
+ btrfs_crit(root->fs_info,
+ "corrupt node: block %llu root %llu nritems %lu",
+ node->start, root->objectid, nr);
+ return -EIO;
+ }
+ return 0;
+}
+
static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
u64 phy_offset, struct page *page,
u64 start, u64 end, int mirror)
ret = -EIO;
}
+ if (found_level > 0 && check_node(root, eb))
+ ret = -EIO;
+
if (!ret)
set_extent_buffer_uptodate(eb);
err:
return ret;
}
-static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
- u64 root_id)
+struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
+ u64 root_id)
{
struct btrfs_root *root;
fs_info->quota_enabled = 0;
fs_info->pending_quota_state = 0;
fs_info->qgroup_ulist = NULL;
+ fs_info->qgroup_rescan_running = false;
mutex_init(&fs_info->qgroup_rescan_lock);
}
atomic_set(&fs_info->qgroup_op_seq, 0);
atomic_set(&fs_info->reada_works_cnt, 0);
atomic64_set(&fs_info->tree_mod_seq, 0);
+ fs_info->fs_frozen = 0;
fs_info->sb = sb;
fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE;
fs_info->metadata_ratio = 0;
if (btrfs_root_refs(&root->root_item) == 0)
synchronize_srcu(&fs_info->subvol_srcu);
- if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
+ if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
btrfs_free_log(NULL, root);
+ if (root->reloc_root) {
+ free_extent_buffer(root->reloc_root->node);
+ free_extent_buffer(root->reloc_root->commit_root);
+ btrfs_put_fs_root(root->reloc_root);
+ root->reloc_root = NULL;
+ }
+ }
if (root->free_ino_pinned)
__btrfs_remove_free_space_cache(root->free_ino_pinned);
smp_mb();
/* wait for the qgroup rescan worker to stop */
- btrfs_qgroup_wait_for_completion(fs_info);
+ btrfs_qgroup_wait_for_completion(fs_info, false);
/* wait for the uuid_scan task to finish */
down(&fs_info->uuid_tree_rescan_sem);
struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root,
struct btrfs_key *location);
int btrfs_init_fs_root(struct btrfs_root *root);
+struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
+ u64 root_id);
int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
struct btrfs_root *root);
void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info);
CHUNK_ALLOC_FORCE = 2,
};
-/*
- * Control how reservations are dealt with.
- *
- * RESERVE_FREE - freeing a reservation.
- * RESERVE_ALLOC - allocating space and we need to update bytes_may_use for
- * ENOSPC accounting
- * RESERVE_ALLOC_NO_ACCOUNT - allocating space and we should not update
- * bytes_may_use as the ENOSPC accounting is done elsewhere
- */
-enum {
- RESERVE_FREE = 0,
- RESERVE_ALLOC = 1,
- RESERVE_ALLOC_NO_ACCOUNT = 2,
-};
-
static int update_block_group(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 bytenr,
u64 num_bytes, int alloc);
struct btrfs_key *key);
static void dump_space_info(struct btrfs_space_info *info, u64 bytes,
int dump_block_groups);
-static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
- u64 num_bytes, int reserve,
- int delalloc);
+static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache,
+ u64 ram_bytes, u64 num_bytes, int delalloc);
+static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache,
+ u64 num_bytes, int delalloc);
static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv,
u64 num_bytes);
int btrfs_pin_extent(struct btrfs_root *root,
dcs = BTRFS_DC_SETUP;
else if (ret == -ENOSPC)
set_bit(BTRFS_TRANS_CACHE_ENOSPC, &trans->transaction->flags);
- btrfs_free_reserved_data_space(inode, 0, num_pages);
out_put:
iput(inode);
if (ret < 0)
return ret;
- /*
- * Use new btrfs_qgroup_reserve_data to reserve precious data space
- *
- * TODO: Find a good method to avoid reserve data space for NOCOW
- * range, but don't impact performance on quota disable case.
- */
+ /* Use new btrfs_qgroup_reserve_data to reserve precious data space. */
ret = btrfs_qgroup_reserve_data(inode, start, len);
+ if (ret)
+ btrfs_free_reserved_data_space_noquota(inode, start, len);
return ret;
}
}
}
+/*
+ * If force is CHUNK_ALLOC_FORCE:
+ * - return 1 if it successfully allocates a chunk,
+ * - return errors including -ENOSPC otherwise.
+ * If force is NOT CHUNK_ALLOC_FORCE:
+ * - return 0 if it doesn't need to allocate a new chunk,
+ * - return 1 if it successfully allocates a chunk,
+ * - return errors including -ENOSPC otherwise.
+ */
static int do_chunk_alloc(struct btrfs_trans_handle *trans,
struct btrfs_root *extent_root, u64 flags, int force)
{
btrfs_get_alloc_profile(root, 0),
CHUNK_ALLOC_NO_FORCE);
btrfs_end_transaction(trans, root);
- if (ret == -ENOSPC)
+ if (ret > 0 || ret == -ENOSPC)
ret = 0;
break;
case COMMIT_TRANS:
u64 expected;
u64 to_reclaim = 0;
- to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M);
- if (can_overcommit(root, space_info, to_reclaim,
- BTRFS_RESERVE_FLUSH_ALL))
- return 0;
-
list_for_each_entry(ticket, &space_info->tickets, list)
to_reclaim += ticket->bytes;
list_for_each_entry(ticket, &space_info->priority_tickets, list)
if (to_reclaim)
return to_reclaim;
+ to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M);
+ if (can_overcommit(root, space_info, to_reclaim,
+ BTRFS_RESERVE_FLUSH_ALL))
+ return 0;
+
used = space_info->bytes_used + space_info->bytes_reserved +
space_info->bytes_pinned + space_info->bytes_readonly +
space_info->bytes_may_use;
*/
static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
{
- struct reserve_ticket *last_ticket = NULL;
struct btrfs_fs_info *fs_info;
struct btrfs_space_info *space_info;
u64 to_reclaim;
int flush_state;
int commit_cycles = 0;
+ u64 last_tickets_id;
fs_info = container_of(work, struct btrfs_fs_info, async_reclaim_work);
space_info = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA);
spin_unlock(&space_info->lock);
return;
}
- last_ticket = list_first_entry(&space_info->tickets,
- struct reserve_ticket, list);
+ last_tickets_id = space_info->tickets_id;
spin_unlock(&space_info->lock);
flush_state = FLUSH_DELAYED_ITEMS_NR;
space_info);
ticket = list_first_entry(&space_info->tickets,
struct reserve_ticket, list);
- if (last_ticket == ticket) {
+ if (last_tickets_id == space_info->tickets_id) {
flush_state++;
} else {
- last_ticket = ticket;
+ last_tickets_id = space_info->tickets_id;
flush_state = FLUSH_DELAYED_ITEMS_NR;
if (commit_cycles)
commit_cycles--;
list_del_init(&ticket->list);
num_bytes -= ticket->bytes;
ticket->bytes = 0;
+ space_info->tickets_id++;
wake_up(&ticket->wait);
} else {
ticket->bytes -= num_bytes;
num_bytes -= ticket->bytes;
space_info->bytes_may_use += ticket->bytes;
ticket->bytes = 0;
+ space_info->tickets_id++;
wake_up(&ticket->wait);
} else {
trace_btrfs_space_reservation(fs_info, "space_info",
}
/**
- * btrfs_update_reserved_bytes - update the block_group and space info counters
+ * btrfs_add_reserved_bytes - update the block_group and space info counters
* @cache: The cache we are manipulating
+ * @ram_bytes: The number of bytes of file content, and will be same to
+ * @num_bytes except for the compress path.
* @num_bytes: The number of bytes in question
- * @reserve: One of the reservation enums
* @delalloc: The blocks are allocated for the delalloc write
*
- * This is called by the allocator when it reserves space, or by somebody who is
- * freeing space that was never actually used on disk. For example if you
- * reserve some space for a new leaf in transaction A and before transaction A
- * commits you free that leaf, you call this with reserve set to 0 in order to
- * clear the reservation.
- *
- * Metadata reservations should be called with RESERVE_ALLOC so we do the proper
+ * This is called by the allocator when it reserves space. Metadata
+ * reservations should be called with RESERVE_ALLOC so we do the proper
* ENOSPC accounting. For data we handle the reservation through clearing the
* delalloc bits in the io_tree. We have to do this since we could end up
* allocating less disk space for the amount of data we have reserved in the
* make the reservation and return -EAGAIN, otherwise this function always
* succeeds.
*/
-static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
- u64 num_bytes, int reserve, int delalloc)
+static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache,
+ u64 ram_bytes, u64 num_bytes, int delalloc)
{
struct btrfs_space_info *space_info = cache->space_info;
int ret = 0;
spin_lock(&space_info->lock);
spin_lock(&cache->lock);
- if (reserve != RESERVE_FREE) {
- if (cache->ro) {
- ret = -EAGAIN;
- } else {
- cache->reserved += num_bytes;
- space_info->bytes_reserved += num_bytes;
- if (reserve == RESERVE_ALLOC) {
- trace_btrfs_space_reservation(cache->fs_info,
- "space_info", space_info->flags,
- num_bytes, 0);
- space_info->bytes_may_use -= num_bytes;
- }
-
- if (delalloc)
- cache->delalloc_bytes += num_bytes;
- }
+ if (cache->ro) {
+ ret = -EAGAIN;
} else {
- if (cache->ro)
- space_info->bytes_readonly += num_bytes;
- cache->reserved -= num_bytes;
- space_info->bytes_reserved -= num_bytes;
+ cache->reserved += num_bytes;
+ space_info->bytes_reserved += num_bytes;
+ trace_btrfs_space_reservation(cache->fs_info,
+ "space_info", space_info->flags,
+ ram_bytes, 0);
+ space_info->bytes_may_use -= ram_bytes;
if (delalloc)
- cache->delalloc_bytes -= num_bytes;
+ cache->delalloc_bytes += num_bytes;
}
spin_unlock(&cache->lock);
spin_unlock(&space_info->lock);
return ret;
}
+/**
+ * btrfs_free_reserved_bytes - update the block_group and space info counters
+ * @cache: The cache we are manipulating
+ * @num_bytes: The number of bytes in question
+ * @delalloc: The blocks are allocated for the delalloc write
+ *
+ * This is called by somebody who is freeing space that was never actually used
+ * on disk. For example if you reserve some space for a new leaf in transaction
+ * A and before transaction A commits you free that leaf, you call this with
+ * reserve set to 0 in order to clear the reservation.
+ */
+
+static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache,
+ u64 num_bytes, int delalloc)
+{
+ struct btrfs_space_info *space_info = cache->space_info;
+ int ret = 0;
+
+ spin_lock(&space_info->lock);
+ spin_lock(&cache->lock);
+ if (cache->ro)
+ space_info->bytes_readonly += num_bytes;
+ cache->reserved -= num_bytes;
+ space_info->bytes_reserved -= num_bytes;
+
+ if (delalloc)
+ cache->delalloc_bytes -= num_bytes;
+ spin_unlock(&cache->lock);
+ spin_unlock(&space_info->lock);
+ return ret;
+}
void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags));
btrfs_add_free_space(cache, buf->start, buf->len);
- btrfs_update_reserved_bytes(cache, buf->len, RESERVE_FREE, 0);
+ btrfs_free_reserved_bytes(cache, buf->len, 0);
btrfs_put_block_group(cache);
trace_btrfs_reserved_extent_free(root, buf->start, buf->len);
pin = 0;
* the free space extent currently.
*/
static noinline int find_free_extent(struct btrfs_root *orig_root,
- u64 num_bytes, u64 empty_size,
- u64 hint_byte, struct btrfs_key *ins,
- u64 flags, int delalloc)
+ u64 ram_bytes, u64 num_bytes, u64 empty_size,
+ u64 hint_byte, struct btrfs_key *ins,
+ u64 flags, int delalloc)
{
int ret = 0;
struct btrfs_root *root = orig_root->fs_info->extent_root;
struct btrfs_space_info *space_info;
int loop = 0;
int index = __get_raid_index(flags);
- int alloc_type = (flags & BTRFS_BLOCK_GROUP_DATA) ?
- RESERVE_ALLOC_NO_ACCOUNT : RESERVE_ALLOC;
bool failed_cluster_refill = false;
bool failed_alloc = false;
bool use_cluster = true;
search_start - offset);
BUG_ON(offset > search_start);
- ret = btrfs_update_reserved_bytes(block_group, num_bytes,
- alloc_type, delalloc);
+ ret = btrfs_add_reserved_bytes(block_group, ram_bytes,
+ num_bytes, delalloc);
if (ret == -EAGAIN) {
btrfs_add_free_space(block_group, offset, num_bytes);
goto loop;
up_read(&info->groups_sem);
}
-int btrfs_reserve_extent(struct btrfs_root *root,
+int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes,
u64 num_bytes, u64 min_alloc_size,
u64 empty_size, u64 hint_byte,
struct btrfs_key *ins, int is_data, int delalloc)
flags = btrfs_get_alloc_profile(root, is_data);
again:
WARN_ON(num_bytes < root->sectorsize);
- ret = find_free_extent(root, num_bytes, empty_size, hint_byte, ins,
- flags, delalloc);
+ ret = find_free_extent(root, ram_bytes, num_bytes, empty_size,
+ hint_byte, ins, flags, delalloc);
if (!ret && !is_data) {
btrfs_dec_block_group_reservations(root->fs_info,
ins->objectid);
num_bytes = min(num_bytes >> 1, ins->offset);
num_bytes = round_down(num_bytes, root->sectorsize);
num_bytes = max(num_bytes, min_alloc_size);
+ ram_bytes = num_bytes;
if (num_bytes == min_alloc_size)
final_tried = true;
goto again;
if (btrfs_test_opt(root->fs_info, DISCARD))
ret = btrfs_discard_extent(root, start, len, NULL);
btrfs_add_free_space(cache, start, len);
- btrfs_update_reserved_bytes(cache, len, RESERVE_FREE, delalloc);
+ btrfs_free_reserved_bytes(cache, len, delalloc);
trace_btrfs_reserved_extent_free(root, start, len);
}
{
int ret;
struct btrfs_block_group_cache *block_group;
+ struct btrfs_space_info *space_info;
/*
* Mixed block groups will exclude before processing the log so we only
if (!block_group)
return -EINVAL;
- ret = btrfs_update_reserved_bytes(block_group, ins->offset,
- RESERVE_ALLOC_NO_ACCOUNT, 0);
- BUG_ON(ret); /* logic error */
+ space_info = block_group->space_info;
+ spin_lock(&space_info->lock);
+ spin_lock(&block_group->lock);
+ space_info->bytes_reserved += ins->offset;
+ block_group->reserved += ins->offset;
+ spin_unlock(&block_group->lock);
+ spin_unlock(&space_info->lock);
+
ret = alloc_reserved_file_extent(trans, root, 0, root_objectid,
0, owner, offset, ins, 1);
btrfs_put_block_group(block_group);
if (IS_ERR(block_rsv))
return ERR_CAST(block_rsv);
- ret = btrfs_reserve_extent(root, blocksize, blocksize,
+ ret = btrfs_reserve_extent(root, blocksize, blocksize, blocksize,
empty_size, hint, &ins, 0, 0);
if (ret)
goto out_unuse;
wc->reada_slot = slot;
}
-/*
- * These may not be seen by the usual inc/dec ref code so we have to
- * add them here.
- */
-static int record_one_subtree_extent(struct btrfs_trans_handle *trans,
- struct btrfs_root *root, u64 bytenr,
- u64 num_bytes)
-{
- struct btrfs_qgroup_extent_record *qrecord;
- struct btrfs_delayed_ref_root *delayed_refs;
-
- qrecord = kmalloc(sizeof(*qrecord), GFP_NOFS);
- if (!qrecord)
- return -ENOMEM;
-
- qrecord->bytenr = bytenr;
- qrecord->num_bytes = num_bytes;
- qrecord->old_roots = NULL;
-
- delayed_refs = &trans->transaction->delayed_refs;
- spin_lock(&delayed_refs->lock);
- if (btrfs_qgroup_insert_dirty_extent(trans->fs_info,
- delayed_refs, qrecord))
- kfree(qrecord);
- spin_unlock(&delayed_refs->lock);
-
- return 0;
-}
-
static int account_leaf_items(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct extent_buffer *eb)
num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi);
- ret = record_one_subtree_extent(trans, root, bytenr, num_bytes);
+ ret = btrfs_qgroup_insert_dirty_extent(trans, root->fs_info,
+ bytenr, num_bytes, GFP_NOFS);
if (ret)
return ret;
}
btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
path->locks[level] = BTRFS_READ_LOCK_BLOCKING;
- ret = record_one_subtree_extent(trans, root, child_bytenr,
- root->nodesize);
+ ret = btrfs_qgroup_insert_dirty_extent(trans,
+ root->fs_info, child_bytenr,
+ root->nodesize, GFP_NOFS);
if (ret)
goto out;
}
} else {
ret = 0;
}
+ free_extent_map(em);
goto out;
}
path->slots[0]++;
block_group->iref = 0;
block_group->inode = NULL;
spin_unlock(&block_group->lock);
+ ASSERT(block_group->io_ctl.inode == NULL);
iput(inode);
last = block_group->key.objectid + block_group->key.offset;
btrfs_put_block_group(block_group);
free_excluded_extents(info->extent_root, block_group);
btrfs_remove_free_space_cache(block_group);
+ ASSERT(list_empty(&block_group->dirty_list));
+ ASSERT(list_empty(&block_group->io_list));
+ ASSERT(list_empty(&block_group->bg_list));
+ ASSERT(atomic_read(&block_group->count) == 1);
btrfs_put_block_group(block_group);
spin_lock(&info->block_group_cache_lock);
#define EXTENT_DAMAGED (1U << 14)
#define EXTENT_NORESERVE (1U << 15)
#define EXTENT_QGROUP_RESERVED (1U << 16)
+#define EXTENT_CLEAR_DATA_RESV (1U << 17)
#define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK)
#define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC)
*/
clear_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
&BTRFS_I(inode)->runtime_flags);
+ /*
+ * An ordered extent might have started before and completed
+ * already with io errors, in which case the inode was not
+ * updated and we end up here. So check the inode's mapping
+ * flags for any errors that might have happened while doing
+ * writeback of file data.
+ */
+ ret = btrfs_inode_check_errors(inode);
inode_unlock(inode);
goto out;
}
}
trans->sync = true;
- btrfs_init_log_ctx(&ctx);
+ btrfs_init_log_ctx(&ctx, inode);
ret = btrfs_log_dentry_safe(trans, root, dentry, start, end, &ctx);
if (ret < 0) {
alloc_start = round_down(offset, blocksize);
alloc_end = round_up(offset + len, blocksize);
+ cur_offset = alloc_start;
/* Make sure we aren't being give some crap mode */
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
/* First, check if we exceed the qgroup limit */
INIT_LIST_HEAD(&reserve_list);
- cur_offset = alloc_start;
while (1) {
em = btrfs_get_extent(inode, NULL, 0, cur_offset,
alloc_end - cur_offset, 0);
last_byte - cur_offset);
if (ret < 0)
break;
+ } else {
+ /*
+ * Do not need to reserve unwritten extent for this
+ * range, free reserved data space first, otherwise
+ * it'll result in false ENOSPC error.
+ */
+ btrfs_free_reserved_data_space(inode, cur_offset,
+ last_byte - cur_offset);
}
free_extent_map(em);
cur_offset = last_byte;
range->start,
range->len, 1 << inode->i_blkbits,
offset + len, &alloc_hint);
+ else
+ btrfs_free_reserved_data_space(inode, range->start,
+ range->len);
list_del(&range->list);
kfree(range);
}
unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end,
&cached_state, GFP_KERNEL);
out:
- /*
- * As we waited the extent range, the data_rsv_map must be empty
- * in the range, as written data range will be released from it.
- * And for prealloacted extent, it will also be released when
- * its metadata is written.
- * So this is completely used as cleanup.
- */
- btrfs_qgroup_free_data(inode, alloc_start, alloc_end - alloc_start);
inode_unlock(inode);
/* Let go of our reservation. */
- btrfs_free_reserved_data_space(inode, alloc_start,
- alloc_end - alloc_start);
+ if (ret != 0)
+ btrfs_free_reserved_data_space(inode, alloc_start,
+ alloc_end - cur_offset);
return ret;
}
ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc,
prealloc, prealloc, &alloc_hint);
if (ret) {
- btrfs_delalloc_release_space(inode, 0, prealloc);
+ btrfs_delalloc_release_metadata(inode, prealloc);
goto out_put;
}
- btrfs_free_reserved_data_space(inode, 0, prealloc);
ret = btrfs_write_out_ino_cache(root, trans, path, inode);
out_put:
PAGE_SET_WRITEBACK |
page_error_op |
PAGE_END_WRITEBACK);
+ btrfs_free_reserved_data_space_noquota(inode, start,
+ end - start + 1);
goto free_pages_out;
}
}
lock_extent(io_tree, async_extent->start,
async_extent->start + async_extent->ram_size - 1);
- ret = btrfs_reserve_extent(root,
+ ret = btrfs_reserve_extent(root, async_extent->ram_size,
async_extent->compressed_size,
async_extent->compressed_size,
0, alloc_hint, &ins, 1, 1);
EXTENT_DEFRAG, PAGE_UNLOCK |
PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK |
PAGE_END_WRITEBACK);
-
+ btrfs_free_reserved_data_space_noquota(inode, start,
+ end - start + 1);
*nr_written = *nr_written +
(end - start + PAGE_SIZE) / PAGE_SIZE;
*page_started = 1;
unsigned long op;
cur_alloc_size = disk_num_bytes;
- ret = btrfs_reserve_extent(root, cur_alloc_size,
+ ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size,
root->sectorsize, 0, alloc_hint,
&ins, 1, 1);
if (ret < 0)
extent_clear_unlock_delalloc(inode, cur_offset,
cur_offset + num_bytes - 1,
locked_page, EXTENT_LOCKED |
- EXTENT_DELALLOC, PAGE_UNLOCK |
- PAGE_SET_PRIVATE2);
+ EXTENT_DELALLOC |
+ EXTENT_CLEAR_DATA_RESV,
+ PAGE_UNLOCK | PAGE_SET_PRIVATE2);
+
if (!nolock && nocow)
btrfs_end_write_no_snapshoting(root);
cur_offset = extent_end;
return;
if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
- && do_list && !(state->state & EXTENT_NORESERVE))
+ && do_list && !(state->state & EXTENT_NORESERVE)
+ && (*bits & (EXTENT_DO_ACCOUNTING |
+ EXTENT_CLEAR_DATA_RESV)))
btrfs_free_reserved_data_space_noquota(inode,
state->start, len);
found_key.offset = 0;
inode = btrfs_iget(root->fs_info->sb, &found_key, root, NULL);
ret = PTR_ERR_OR_ZERO(inode);
- if (ret && ret != -ESTALE)
+ if (ret && ret != -ENOENT)
goto out;
- if (ret == -ESTALE && root == root->fs_info->tree_root) {
+ if (ret == -ENOENT && root == root->fs_info->tree_root) {
struct btrfs_root *dead_root;
struct btrfs_fs_info *fs_info = root->fs_info;
int is_dead_root = 0;
* Inode is already gone but the orphan item is still there,
* kill the orphan item.
*/
- if (ret == -ESTALE) {
+ if (ret == -ENOENT) {
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
/*
* read an inode from the btree into the in-memory inode
*/
-static void btrfs_read_locked_inode(struct inode *inode)
+static int btrfs_read_locked_inode(struct inode *inode)
{
struct btrfs_path *path;
struct extent_buffer *leaf;
filled = true;
path = btrfs_alloc_path();
- if (!path)
+ if (!path) {
+ ret = -ENOMEM;
goto make_bad;
+ }
memcpy(&location, &BTRFS_I(inode)->location, sizeof(location));
ret = btrfs_lookup_inode(NULL, root, path, &location, 0);
- if (ret)
+ if (ret) {
+ if (ret > 0)
+ ret = -ENOENT;
goto make_bad;
+ }
leaf = path->nodes[0];
}
btrfs_update_iflags(inode);
- return;
+ return 0;
make_bad:
btrfs_free_path(path);
make_bad_inode(inode);
+ return ret;
}
/*
int err = 0;
struct btrfs_root *root = BTRFS_I(dir)->root;
struct btrfs_trans_handle *trans;
+ u64 last_unlink_trans;
if (inode->i_size > BTRFS_EMPTY_DIR_SIZE)
return -ENOTEMPTY;
if (err)
goto out;
+ last_unlink_trans = BTRFS_I(inode)->last_unlink_trans;
+
/* now the directory is empty */
err = btrfs_unlink_inode(trans, root, dir, d_inode(dentry),
dentry->d_name.name, dentry->d_name.len);
- if (!err)
+ if (!err) {
btrfs_i_size_write(inode, 0);
+ /*
+ * Propagate the last_unlink_trans value of the deleted dir to
+ * its parent directory. This is to prevent an unrecoverable
+ * log tree in the case we do something like this:
+ * 1) create dir foo
+ * 2) create snapshot under dir foo
+ * 3) delete the snapshot
+ * 4) rmdir foo
+ * 5) mkdir foo
+ * 6) fsync foo or some file inside foo
+ */
+ if (last_unlink_trans >= trans->transid)
+ BTRFS_I(dir)->last_unlink_trans = last_unlink_trans;
+ }
out:
btrfs_end_transaction(trans, root);
btrfs_btree_balance_dirty(root);
return ERR_PTR(-ENOMEM);
if (inode->i_state & I_NEW) {
- btrfs_read_locked_inode(inode);
+ int ret;
+
+ ret = btrfs_read_locked_inode(inode);
if (!is_bad_inode(inode)) {
inode_tree_add(inode);
unlock_new_inode(inode);
} else {
unlock_new_inode(inode);
iput(inode);
- inode = ERR_PTR(-ESTALE);
+ ASSERT(ret < 0);
+ inode = ERR_PTR(ret < 0 ? ret : -ESTALE);
}
}
int ret;
alloc_hint = get_extent_allocation_hint(inode, start, len);
- ret = btrfs_reserve_extent(root, len, root->sectorsize, 0,
+ ret = btrfs_reserve_extent(root, len, len, root->sectorsize, 0,
alloc_hint, &ins, 1, 1);
if (ret)
return ERR_PTR(ret);
ret = PTR_ERR(em2);
goto unlock_err;
}
+ /*
+ * For inode marked NODATACOW or extent marked PREALLOC,
+ * use the existing or preallocated extent, so does not
+ * need to adjust btrfs_space_info's bytes_may_use.
+ */
+ btrfs_free_reserved_data_space_noquota(inode,
+ start, len);
goto unlock;
}
}
i_size_write(inode, start + len);
adjust_dio_outstanding_extents(inode, dio_data, len);
- btrfs_free_reserved_data_space(inode, start, len);
WARN_ON(dio_data->reserve < len);
dio_data->reserve -= len;
dio_data->unsubmitted_oe_range_end = start + len;
u64 last_alloc = (u64)-1;
int ret = 0;
bool own_trans = true;
+ u64 end = start + num_bytes - 1;
if (trans)
own_trans = false;
* sized chunks.
*/
cur_bytes = min(cur_bytes, last_alloc);
- ret = btrfs_reserve_extent(root, cur_bytes, min_size, 0,
- *alloc_hint, &ins, 1, 0);
+ ret = btrfs_reserve_extent(root, cur_bytes, cur_bytes,
+ min_size, 0, *alloc_hint, &ins, 1, 0);
if (ret) {
if (own_trans)
btrfs_end_transaction(trans, root);
if (own_trans)
btrfs_end_transaction(trans, root);
}
+ if (cur_offset < end)
+ btrfs_free_reserved_data_space(inode, cur_offset,
+ end - cur_offset + 1);
return ret;
}
int namelen;
int ret = 0;
+ if (!S_ISDIR(file_inode(file)->i_mode))
+ return -ENOTDIR;
+
ret = mnt_want_write_file(file);
if (ret)
goto out;
struct btrfs_ioctl_vol_args *vol_args;
int ret;
+ if (!S_ISDIR(file_inode(file)->i_mode))
+ return -ENOTDIR;
+
vol_args = memdup_user(arg, sizeof(*vol_args));
if (IS_ERR(vol_args))
return PTR_ERR(vol_args);
bool readonly = false;
struct btrfs_qgroup_inherit *inherit = NULL;
+ if (!S_ISDIR(file_inode(file)->i_mode))
+ return -ENOTDIR;
+
vol_args = memdup_user(arg, sizeof(*vol_args));
if (IS_ERR(vol_args))
return PTR_ERR(vol_args);
int ret;
int err = 0;
+ if (!S_ISDIR(dir->i_mode))
+ return -ENOTDIR;
+
vol_args = memdup_user(arg, sizeof(*vol_args));
if (IS_ERR(vol_args))
return PTR_ERR(vol_args);
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- return btrfs_qgroup_wait_for_completion(root->fs_info);
+ return btrfs_qgroup_wait_for_completion(root->fs_info, true);
}
static long _btrfs_ioctl_set_received_subvol(struct file *file,
goto out;
fs_info->quota_enabled = 0;
fs_info->pending_quota_state = 0;
- btrfs_qgroup_wait_for_completion(fs_info);
+ btrfs_qgroup_wait_for_completion(fs_info, false);
spin_lock(&fs_info->qgroup_lock);
quota_root = fs_info->quota_root;
fs_info->quota_root = NULL;
return ret;
}
-struct btrfs_qgroup_extent_record *
-btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info,
- struct btrfs_delayed_ref_root *delayed_refs,
- struct btrfs_qgroup_extent_record *record)
+int btrfs_qgroup_insert_dirty_extent_nolock(struct btrfs_fs_info *fs_info,
+ struct btrfs_delayed_ref_root *delayed_refs,
+ struct btrfs_qgroup_extent_record *record)
{
struct rb_node **p = &delayed_refs->dirty_extent_root.rb_node;
struct rb_node *parent_node = NULL;
else if (bytenr > entry->bytenr)
p = &(*p)->rb_right;
else
- return entry;
+ return 1;
}
rb_link_node(&record->node, parent_node, p);
rb_insert_color(&record->node, &delayed_refs->dirty_extent_root);
- return NULL;
+ return 0;
+}
+
+int btrfs_qgroup_insert_dirty_extent(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes,
+ gfp_t gfp_flag)
+{
+ struct btrfs_qgroup_extent_record *record;
+ struct btrfs_delayed_ref_root *delayed_refs;
+ int ret;
+
+ if (!fs_info->quota_enabled || bytenr == 0 || num_bytes == 0)
+ return 0;
+ if (WARN_ON(trans == NULL))
+ return -EINVAL;
+ record = kmalloc(sizeof(*record), gfp_flag);
+ if (!record)
+ return -ENOMEM;
+
+ delayed_refs = &trans->transaction->delayed_refs;
+ record->bytenr = bytenr;
+ record->num_bytes = num_bytes;
+ record->old_roots = NULL;
+
+ spin_lock(&delayed_refs->lock);
+ ret = btrfs_qgroup_insert_dirty_extent_nolock(fs_info, delayed_refs,
+ record);
+ spin_unlock(&delayed_refs->lock);
+ if (ret > 0)
+ kfree(record);
+ return 0;
}
#define UPDATE_NEW 0
int err = -ENOMEM;
int ret = 0;
+ mutex_lock(&fs_info->qgroup_rescan_lock);
+ fs_info->qgroup_rescan_running = true;
+ mutex_unlock(&fs_info->qgroup_rescan_lock);
+
path = btrfs_alloc_path();
if (!path)
goto out;
}
done:
+ mutex_lock(&fs_info->qgroup_rescan_lock);
+ fs_info->qgroup_rescan_running = false;
+ mutex_unlock(&fs_info->qgroup_rescan_lock);
complete_all(&fs_info->qgroup_rescan_completion);
}
return 0;
}
-int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info)
+int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
+ bool interruptible)
{
int running;
int ret = 0;
mutex_lock(&fs_info->qgroup_rescan_lock);
spin_lock(&fs_info->qgroup_lock);
- running = fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN;
+ running = fs_info->qgroup_rescan_running;
spin_unlock(&fs_info->qgroup_lock);
mutex_unlock(&fs_info->qgroup_rescan_lock);
- if (running)
+ if (!running)
+ return 0;
+
+ if (interruptible)
ret = wait_for_completion_interruptible(
&fs_info->qgroup_rescan_completion);
+ else
+ wait_for_completion(&fs_info->qgroup_rescan_completion);
return ret;
}
struct btrfs_fs_info *fs_info);
int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info);
void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info);
-int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info);
+int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
+ bool interruptible);
int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 src, u64 dst);
int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans,
struct btrfs_delayed_extent_op;
int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info);
-struct btrfs_qgroup_extent_record *
-btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info,
- struct btrfs_delayed_ref_root *delayed_refs,
- struct btrfs_qgroup_extent_record *record);
+/*
+ * Insert one dirty extent record into @delayed_refs, informing qgroup to
+ * account that extent at commit trans time.
+ *
+ * No lock version, caller must acquire delayed ref lock and allocate memory.
+ *
+ * Return 0 for success insert
+ * Return >0 for existing record, caller can free @record safely.
+ * Error is not possible
+ */
+int btrfs_qgroup_insert_dirty_extent_nolock(
+ struct btrfs_fs_info *fs_info,
+ struct btrfs_delayed_ref_root *delayed_refs,
+ struct btrfs_qgroup_extent_record *record);
+
+/*
+ * Insert one dirty extent record into @delayed_refs, informing qgroup to
+ * account that extent at commit trans time.
+ *
+ * Better encapsulated version.
+ *
+ * Return 0 if the operation is done.
+ * Return <0 for error, like memory allocation failure or invalid parameter
+ * (NULL trans)
+ */
+int btrfs_qgroup_insert_dirty_extent(struct btrfs_trans_handle *trans,
+ struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes,
+ gfp_t gfp_flag);
+
int
btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
#include "async-thread.h"
#include "free-space-cache.h"
#include "inode-map.h"
+#include "qgroup.h"
/*
* backref_node, mapping_node and tree_block start with this
u64 num_bytes;
int nr = 0;
int ret = 0;
+ u64 prealloc_start = cluster->start - offset;
+ u64 prealloc_end = cluster->end - offset;
+ u64 cur_offset;
BUG_ON(cluster->start != cluster->boundary[0]);
inode_lock(inode);
- ret = btrfs_check_data_free_space(inode, cluster->start,
- cluster->end + 1 - cluster->start);
+ ret = btrfs_check_data_free_space(inode, prealloc_start,
+ prealloc_end + 1 - prealloc_start);
if (ret)
goto out;
+ cur_offset = prealloc_start;
while (nr < cluster->nr) {
start = cluster->boundary[nr] - offset;
if (nr + 1 < cluster->nr)
lock_extent(&BTRFS_I(inode)->io_tree, start, end);
num_bytes = end + 1 - start;
+ if (cur_offset < start)
+ btrfs_free_reserved_data_space(inode, cur_offset,
+ start - cur_offset);
ret = btrfs_prealloc_file_range(inode, 0, start,
num_bytes, num_bytes,
end + 1, &alloc_hint);
+ cur_offset = end + 1;
unlock_extent(&BTRFS_I(inode)->io_tree, start, end);
if (ret)
break;
nr++;
}
- btrfs_free_reserved_data_space(inode, cluster->start,
- cluster->end + 1 - cluster->start);
+ if (cur_offset < prealloc_end)
+ btrfs_free_reserved_data_space(inode, cur_offset,
+ prealloc_end + 1 - cur_offset);
out:
inode_unlock(inode);
return ret;
return 0;
}
+/*
+ * Qgroup fixer for data chunk relocation.
+ * The data relocation is done in the following steps
+ * 1) Copy data extents into data reloc tree
+ * 2) Create tree reloc tree(special snapshot) for related subvolumes
+ * 3) Modify file extents in tree reloc tree
+ * 4) Merge tree reloc tree with original fs tree, by swapping tree blocks
+ *
+ * The problem is, data and tree reloc tree are not accounted to qgroup,
+ * and 4) will only info qgroup to track tree blocks change, not file extents
+ * in the tree blocks.
+ *
+ * The good news is, related data extents are all in data reloc tree, so we
+ * only need to info qgroup to track all file extents in data reloc tree
+ * before commit trans.
+ */
+static int qgroup_fix_relocated_data_extents(struct btrfs_trans_handle *trans,
+ struct reloc_control *rc)
+{
+ struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
+ struct inode *inode = rc->data_inode;
+ struct btrfs_root *data_reloc_root = BTRFS_I(inode)->root;
+ struct btrfs_path *path;
+ struct btrfs_key key;
+ int ret = 0;
+
+ if (!fs_info->quota_enabled)
+ return 0;
+
+ /*
+ * Only for stage where we update data pointers the qgroup fix is
+ * valid.
+ * For MOVING_DATA stage, we will miss the timing of swapping tree
+ * blocks, and won't fix it.
+ */
+ if (!(rc->stage == UPDATE_DATA_PTRS && rc->extents_found))
+ return 0;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+ key.objectid = btrfs_ino(inode);
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ key.offset = 0;
+
+ ret = btrfs_search_slot(NULL, data_reloc_root, &key, path, 0, 0);
+ if (ret < 0)
+ goto out;
+
+ lock_extent(&BTRFS_I(inode)->io_tree, 0, (u64)-1);
+ while (1) {
+ struct btrfs_file_extent_item *fi;
+
+ btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+ if (key.objectid > btrfs_ino(inode))
+ break;
+ if (key.type != BTRFS_EXTENT_DATA_KEY)
+ goto next;
+ fi = btrfs_item_ptr(path->nodes[0], path->slots[0],
+ struct btrfs_file_extent_item);
+ if (btrfs_file_extent_type(path->nodes[0], fi) !=
+ BTRFS_FILE_EXTENT_REG)
+ goto next;
+ ret = btrfs_qgroup_insert_dirty_extent(trans, fs_info,
+ btrfs_file_extent_disk_bytenr(path->nodes[0], fi),
+ btrfs_file_extent_disk_num_bytes(path->nodes[0], fi),
+ GFP_NOFS);
+ if (ret < 0)
+ break;
+next:
+ ret = btrfs_next_item(data_reloc_root, path);
+ if (ret < 0)
+ break;
+ if (ret > 0) {
+ ret = 0;
+ break;
+ }
+ }
+ unlock_extent(&BTRFS_I(inode)->io_tree, 0 , (u64)-1);
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
{
struct rb_root blocks = RB_ROOT;
/* get rid of pinned extents */
trans = btrfs_join_transaction(rc->extent_root);
- if (IS_ERR(trans))
+ if (IS_ERR(trans)) {
err = PTR_ERR(trans);
- else
- btrfs_commit_transaction(trans, rc->extent_root);
+ goto out_free;
+ }
+ ret = qgroup_fix_relocated_data_extents(trans, rc);
+ if (ret < 0) {
+ btrfs_abort_transaction(trans, ret);
+ if (!err)
+ err = ret;
+ goto out_free;
+ }
+ btrfs_commit_transaction(trans, rc->extent_root);
out_free:
btrfs_free_block_rsv(rc->extent_root, rc->block_rsv);
btrfs_free_path(path);
unset_reloc_control(rc);
trans = btrfs_join_transaction(rc->extent_root);
- if (IS_ERR(trans))
+ if (IS_ERR(trans)) {
err = PTR_ERR(trans);
- else
- err = btrfs_commit_transaction(trans, rc->extent_root);
+ goto out_free;
+ }
+ err = qgroup_fix_relocated_data_extents(trans, rc);
+ if (err < 0) {
+ btrfs_abort_transaction(trans, err);
+ goto out_free;
+ }
+ err = btrfs_commit_transaction(trans, rc->extent_root);
out_free:
kfree(rc);
out:
root_key.objectid = key.offset;
key.offset++;
+ /*
+ * The root might have been inserted already, as before we look
+ * for orphan roots, log replay might have happened, which
+ * triggers a transaction commit and qgroup accounting, which
+ * in turn reads and inserts fs roots while doing backref
+ * walking.
+ */
+ root = btrfs_lookup_fs_root(tree_root->fs_info,
+ root_key.objectid);
+ if (root) {
+ WARN_ON(!test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED,
+ &root->state));
+ if (btrfs_root_refs(&root->root_item) == 0)
+ btrfs_add_dead_root(root);
+ continue;
+ }
+
root = btrfs_read_fs_root(tree_root, &root_key);
err = PTR_ERR_OR_ZERO(root);
if (err && err != -ENOENT) {
set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state);
err = btrfs_insert_fs_root(root->fs_info, root);
- /*
- * The root might have been inserted already, as before we look
- * for orphan roots, log replay might have happened, which
- * triggers a transaction commit and qgroup accounting, which
- * in turn reads and inserts fs roots while doing backref
- * walking.
- */
- if (err == -EEXIST)
- err = 0;
if (err) {
+ BUG_ON(err == -EEXIST);
btrfs_free_fs_root(root);
break;
}
u64 parent_ino;
u64 ino;
u64 gen;
- bool is_orphan;
struct list_head update_refs;
};
char name[];
};
+static void inconsistent_snapshot_error(struct send_ctx *sctx,
+ enum btrfs_compare_tree_result result,
+ const char *what)
+{
+ const char *result_string;
+
+ switch (result) {
+ case BTRFS_COMPARE_TREE_NEW:
+ result_string = "new";
+ break;
+ case BTRFS_COMPARE_TREE_DELETED:
+ result_string = "deleted";
+ break;
+ case BTRFS_COMPARE_TREE_CHANGED:
+ result_string = "updated";
+ break;
+ case BTRFS_COMPARE_TREE_SAME:
+ ASSERT(0);
+ result_string = "unchanged";
+ break;
+ default:
+ ASSERT(0);
+ result_string = "unexpected";
+ }
+
+ btrfs_err(sctx->send_root->fs_info,
+ "Send: inconsistent snapshot, found %s %s for inode %llu without updated inode item, send root is %llu, parent root is %llu",
+ result_string, what, sctx->cmp_key->objectid,
+ sctx->send_root->root_key.objectid,
+ (sctx->parent_root ?
+ sctx->parent_root->root_key.objectid : 0));
+}
+
static int is_waiting_for_move(struct send_ctx *sctx, u64 ino);
static struct waiting_dir_move *
* was already unlinked/moved, so we can safely assume that we will not
* overwrite anything at this point in time.
*/
- if (other_inode > sctx->send_progress) {
+ if (other_inode > sctx->send_progress ||
+ is_waiting_for_move(sctx, other_inode)) {
ret = get_inode_info(sctx->parent_root, other_inode, NULL,
who_gen, NULL, NULL, NULL, NULL);
if (ret < 0)
key.type = BTRFS_INODE_ITEM_KEY;
key.offset = 0;
ret = btrfs_search_slot(NULL, sctx->send_root, &key, path, 0, 0);
+ if (ret > 0)
+ ret = -ENOENT;
if (ret < 0)
goto out;
}
if (loc.objectid > send_progress) {
+ struct orphan_dir_info *odi;
+
+ odi = get_orphan_dir_info(sctx, dir);
+ free_orphan_dir_info(sctx, odi);
ret = 0;
goto out;
}
pm->parent_ino = parent_ino;
pm->ino = ino;
pm->gen = ino_gen;
- pm->is_orphan = is_orphan;
INIT_LIST_HEAD(&pm->list);
INIT_LIST_HEAD(&pm->update_refs);
RB_CLEAR_NODE(&pm->node);
return NULL;
}
+static int path_loop(struct send_ctx *sctx, struct fs_path *name,
+ u64 ino, u64 gen, u64 *ancestor_ino)
+{
+ int ret = 0;
+ u64 parent_inode = 0;
+ u64 parent_gen = 0;
+ u64 start_ino = ino;
+
+ *ancestor_ino = 0;
+ while (ino != BTRFS_FIRST_FREE_OBJECTID) {
+ fs_path_reset(name);
+
+ if (is_waiting_for_rm(sctx, ino))
+ break;
+ if (is_waiting_for_move(sctx, ino)) {
+ if (*ancestor_ino == 0)
+ *ancestor_ino = ino;
+ ret = get_first_ref(sctx->parent_root, ino,
+ &parent_inode, &parent_gen, name);
+ } else {
+ ret = __get_cur_name_and_parent(sctx, ino, gen,
+ &parent_inode,
+ &parent_gen, name);
+ if (ret > 0) {
+ ret = 0;
+ break;
+ }
+ }
+ if (ret < 0)
+ break;
+ if (parent_inode == start_ino) {
+ ret = 1;
+ if (*ancestor_ino == 0)
+ *ancestor_ino = ino;
+ break;
+ }
+ ino = parent_inode;
+ gen = parent_gen;
+ }
+ return ret;
+}
+
static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
{
struct fs_path *from_path = NULL;
u64 parent_ino, parent_gen;
struct waiting_dir_move *dm = NULL;
u64 rmdir_ino = 0;
+ u64 ancestor;
+ bool is_orphan;
int ret;
name = fs_path_alloc();
dm = get_waiting_dir_move(sctx, pm->ino);
ASSERT(dm);
rmdir_ino = dm->rmdir_ino;
+ is_orphan = dm->orphanized;
free_waiting_dir_move(sctx, dm);
- if (pm->is_orphan) {
+ if (is_orphan) {
ret = gen_unique_name(sctx, pm->ino,
pm->gen, from_path);
} else {
goto out;
sctx->send_progress = sctx->cur_ino + 1;
+ ret = path_loop(sctx, name, pm->ino, pm->gen, &ancestor);
+ if (ret < 0)
+ goto out;
+ if (ret) {
+ LIST_HEAD(deleted_refs);
+ ASSERT(ancestor > BTRFS_FIRST_FREE_OBJECTID);
+ ret = add_pending_dir_move(sctx, pm->ino, pm->gen, ancestor,
+ &pm->update_refs, &deleted_refs,
+ is_orphan);
+ if (ret < 0)
+ goto out;
+ if (rmdir_ino) {
+ dm = get_waiting_dir_move(sctx, pm->ino);
+ ASSERT(dm);
+ dm->rmdir_ino = rmdir_ino;
+ }
+ goto out;
+ }
fs_path_reset(name);
to_path = name;
name = NULL;
/* already deleted */
goto finish;
}
- ret = can_rmdir(sctx, rmdir_ino, odi->gen, sctx->cur_ino + 1);
+ ret = can_rmdir(sctx, rmdir_ino, odi->gen, sctx->cur_ino);
if (ret < 0)
goto out;
if (!ret)
* and old parent(s).
*/
list_for_each_entry(cur, &pm->update_refs, list) {
- if (cur->dir == rmdir_ino)
+ /*
+ * The parent inode might have been deleted in the send snapshot
+ */
+ ret = get_inode_info(sctx->send_root, cur->dir, NULL,
+ NULL, NULL, NULL, NULL, NULL);
+ if (ret == -ENOENT) {
+ ret = 0;
continue;
+ }
+ if (ret < 0)
+ goto out;
+
ret = send_utimes(sctx, cur->dir, cur->dir_gen);
if (ret < 0)
goto out;
u64 left_gen;
u64 right_gen;
int ret = 0;
+ struct waiting_dir_move *wdm;
if (RB_EMPTY_ROOT(&sctx->waiting_dir_moves))
return 0;
goto out;
}
- if (is_waiting_for_move(sctx, di_key.objectid)) {
+ wdm = get_waiting_dir_move(sctx, di_key.objectid);
+ if (wdm && !wdm->orphanized) {
ret = add_pending_dir_move(sctx,
sctx->cur_ino,
sctx->cur_inode_gen,
ret = is_ancestor(sctx->parent_root,
sctx->cur_ino, sctx->cur_inode_gen,
ino, path_before);
- break;
+ if (ret)
+ break;
}
fs_path_reset(path_before);
goto out;
if (ret) {
struct name_cache_entry *nce;
+ struct waiting_dir_move *wdm;
ret = orphanize_inode(sctx, ow_inode, ow_gen,
cur->full_path);
if (ret < 0)
goto out;
+
+ /*
+ * If ow_inode has its rename operation delayed
+ * make sure that its orphanized name is used in
+ * the source path when performing its rename
+ * operation.
+ */
+ if (is_waiting_for_move(sctx, ow_inode)) {
+ wdm = get_waiting_dir_move(sctx,
+ ow_inode);
+ ASSERT(wdm);
+ wdm->orphanized = true;
+ }
+
/*
* Make sure we clear our orphanized inode's
* name from the name cache. This is because the
name_cache_delete(sctx, nce);
kfree(nce);
}
+
+ /*
+ * ow_inode might currently be an ancestor of
+ * cur_ino, therefore compute valid_path (the
+ * current path of cur_ino) again because it
+ * might contain the pre-orphanization name of
+ * ow_inode, which is no longer valid.
+ */
+ fs_path_reset(valid_path);
+ ret = get_cur_path(sctx, sctx->cur_ino,
+ sctx->cur_inode_gen, valid_path);
+ if (ret < 0)
+ goto out;
} else {
ret = send_unlink(sctx, cur->full_path);
if (ret < 0)
}
btrfs_release_path(path);
+ /*
+ * We don't actually care about pending_move as we are simply
+ * re-creating this inode and will be rename'ing it into place once we
+ * rename the parent directory.
+ */
ret = process_recorded_refs(sctx, &pending_move);
- /* Only applicable to an incremental send. */
- ASSERT(pending_move == 0);
-
out:
btrfs_free_path(path);
return ret;
{
int ret = 0;
- BUG_ON(sctx->cur_ino != sctx->cmp_key->objectid);
+ if (sctx->cur_ino != sctx->cmp_key->objectid) {
+ inconsistent_snapshot_error(sctx, result, "reference");
+ return -EIO;
+ }
if (!sctx->cur_inode_new_gen &&
sctx->cur_ino != BTRFS_FIRST_FREE_OBJECTID) {
{
int ret = 0;
- BUG_ON(sctx->cur_ino != sctx->cmp_key->objectid);
+ if (sctx->cur_ino != sctx->cmp_key->objectid) {
+ inconsistent_snapshot_error(sctx, result, "xattr");
+ return -EIO;
+ }
if (!sctx->cur_inode_new_gen && !sctx->cur_inode_deleted) {
if (result == BTRFS_COMPARE_TREE_NEW)
{
int ret = 0;
- BUG_ON(sctx->cur_ino != sctx->cmp_key->objectid);
+ if (sctx->cur_ino != sctx->cmp_key->objectid) {
+ inconsistent_snapshot_error(sctx, result, "extent");
+ return -EIO;
+ }
if (!sctx->cur_inode_new_gen && !sctx->cur_inode_deleted) {
if (result != BTRFS_COMPARE_TREE_DELETED)
struct btrfs_trans_handle *trans;
struct btrfs_root *root = btrfs_sb(sb)->tree_root;
+ root->fs_info->fs_frozen = 1;
+ /*
+ * We don't need a barrier here, we'll wait for any transaction that
+ * could be in progress on other threads (and do delayed iputs that
+ * we want to avoid on a frozen filesystem), or do the commit
+ * ourselves.
+ */
trans = btrfs_attach_transaction_barrier(root);
if (IS_ERR(trans)) {
/* no transaction, don't bother */
return btrfs_commit_transaction(trans, root);
}
+static int btrfs_unfreeze(struct super_block *sb)
+{
+ struct btrfs_root *root = btrfs_sb(sb)->tree_root;
+
+ root->fs_info->fs_frozen = 0;
+ return 0;
+}
+
static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
{
struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb);
.statfs = btrfs_statfs,
.remount_fs = btrfs_remount,
.freeze_fs = btrfs_freeze,
+ .unfreeze_fs = btrfs_unfreeze,
};
static const struct file_operations btrfs_ctl_fops = {
kmem_cache_free(btrfs_trans_handle_cachep, trans);
+ /*
+ * If fs has been frozen, we can not handle delayed iputs, otherwise
+ * it'll result in deadlock about SB_FREEZE_FS.
+ */
if (current != root->fs_info->transaction_kthread &&
- current != root->fs_info->cleaner_kthread)
+ current != root->fs_info->cleaner_kthread &&
+ !root->fs_info->fs_frozen)
btrfs_run_delayed_iputs(root);
return ret;
#include "backref.h"
#include "hash.h"
#include "compression.h"
+#include "qgroup.h"
/* magic values for the inode_only field in btrfs_log_inode:
*
ins.type = BTRFS_EXTENT_ITEM_KEY;
offset = key->offset - btrfs_file_extent_offset(eb, item);
+ /*
+ * Manually record dirty extent, as here we did a shallow
+ * file extent item copy and skip normal backref update,
+ * but modifying extent tree all by ourselves.
+ * So need to manually record dirty extent for qgroup,
+ * as the owner of the file extent changed from log tree
+ * (doesn't affect qgroup) to fs/file tree(affects qgroup)
+ */
+ ret = btrfs_qgroup_insert_dirty_extent(trans, root->fs_info,
+ btrfs_file_extent_disk_bytenr(eb, item),
+ btrfs_file_extent_disk_num_bytes(eb, item),
+ GFP_NOFS);
+ if (ret < 0)
+ goto out;
+
if (ins.objectid > 0) {
u64 csum_start;
u64 csum_end;
*/
mutex_unlock(&root->log_mutex);
- btrfs_init_log_ctx(&root_log_ctx);
+ btrfs_init_log_ctx(&root_log_ctx, NULL);
mutex_lock(&log_root_tree->log_mutex);
atomic_inc(&log_root_tree->log_batch);
if (log_root_tree->log_transid_committed >= root_log_ctx.log_transid) {
blk_finish_plug(&plug);
+ list_del_init(&root_log_ctx.list);
mutex_unlock(&log_root_tree->log_mutex);
ret = root_log_ctx.log_ret;
goto out;
static int btrfs_check_ref_name_override(struct extent_buffer *eb,
const int slot,
const struct btrfs_key *key,
- struct inode *inode)
+ struct inode *inode,
+ u64 *other_ino)
{
int ret;
struct btrfs_path *search_path;
search_path, parent,
name, this_name_len, 0);
if (di && !IS_ERR(di)) {
- ret = 1;
+ struct btrfs_key di_key;
+
+ btrfs_dir_item_key_to_cpu(search_path->nodes[0],
+ di, &di_key);
+ if (di_key.type == BTRFS_INODE_ITEM_KEY) {
+ ret = 1;
+ *other_ino = di_key.objectid;
+ } else {
+ ret = -EAGAIN;
+ }
goto out;
} else if (IS_ERR(di)) {
ret = PTR_ERR(di);
if ((min_key.type == BTRFS_INODE_REF_KEY ||
min_key.type == BTRFS_INODE_EXTREF_KEY) &&
BTRFS_I(inode)->generation == trans->transid) {
+ u64 other_ino = 0;
+
ret = btrfs_check_ref_name_override(path->nodes[0],
path->slots[0],
- &min_key, inode);
+ &min_key, inode,
+ &other_ino);
if (ret < 0) {
err = ret;
goto out_unlock;
- } else if (ret > 0) {
- err = 1;
- btrfs_set_log_full_commit(root->fs_info, trans);
- goto out_unlock;
+ } else if (ret > 0 && ctx &&
+ other_ino != btrfs_ino(ctx->inode)) {
+ struct btrfs_key inode_key;
+ struct inode *other_inode;
+
+ if (ins_nr > 0) {
+ ins_nr++;
+ } else {
+ ins_nr = 1;
+ ins_start_slot = path->slots[0];
+ }
+ ret = copy_items(trans, inode, dst_path, path,
+ &last_extent, ins_start_slot,
+ ins_nr, inode_only,
+ logged_isize);
+ if (ret < 0) {
+ err = ret;
+ goto out_unlock;
+ }
+ ins_nr = 0;
+ btrfs_release_path(path);
+ inode_key.objectid = other_ino;
+ inode_key.type = BTRFS_INODE_ITEM_KEY;
+ inode_key.offset = 0;
+ other_inode = btrfs_iget(root->fs_info->sb,
+ &inode_key, root,
+ NULL);
+ /*
+ * If the other inode that had a conflicting dir
+ * entry was deleted in the current transaction,
+ * we don't need to do more work nor fallback to
+ * a transaction commit.
+ */
+ if (IS_ERR(other_inode) &&
+ PTR_ERR(other_inode) == -ENOENT) {
+ goto next_key;
+ } else if (IS_ERR(other_inode)) {
+ err = PTR_ERR(other_inode);
+ goto out_unlock;
+ }
+ /*
+ * We are safe logging the other inode without
+ * acquiring its i_mutex as long as we log with
+ * the LOG_INODE_EXISTS mode. We're safe against
+ * concurrent renames of the other inode as well
+ * because during a rename we pin the log and
+ * update the log with the new name before we
+ * unpin it.
+ */
+ err = btrfs_log_inode(trans, root, other_inode,
+ LOG_INODE_EXISTS,
+ 0, LLONG_MAX, ctx);
+ iput(other_inode);
+ if (err)
+ goto out_unlock;
+ else
+ goto next_key;
}
}
ins_nr = 0;
}
btrfs_release_path(path);
-
+next_key:
if (min_key.offset < (u64)-1) {
min_key.offset++;
} else if (min_key.type < max_key.type) {
if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
break;
- if (IS_ROOT(parent))
+ if (IS_ROOT(parent)) {
+ inode = d_inode(parent);
+ if (btrfs_must_commit_transaction(trans, inode))
+ ret = 1;
break;
+ }
parent = dget_parent(parent);
dput(old_parent);
int log_transid;
int io_err;
bool log_new_dentries;
+ struct inode *inode;
struct list_head list;
};
-static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx)
+static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx,
+ struct inode *inode)
{
ctx->log_ret = 0;
ctx->log_transid = 0;
ctx->io_err = 0;
ctx->log_new_dentries = false;
+ ctx->inode = inode;
INIT_LIST_HEAD(&ctx->list);
}
struct btrfs_device *device;
device = container_of(work, struct btrfs_device, rcu_work);
-
- if (device->bdev)
- blkdev_put(device->bdev, device->mode);
-
rcu_string_free(device->name);
kfree(device);
}
schedule_work(&device->rcu_work);
}
+static void btrfs_close_bdev(struct btrfs_device *device)
+{
+ if (device->bdev && device->writeable) {
+ sync_blockdev(device->bdev);
+ invalidate_bdev(device->bdev);
+ }
+
+ if (device->bdev)
+ blkdev_put(device->bdev, device->mode);
+}
+
static void btrfs_close_one_device(struct btrfs_device *device)
{
struct btrfs_fs_devices *fs_devices = device->fs_devices;
if (device->missing)
fs_devices->missing_devices--;
- if (device->bdev && device->writeable) {
- sync_blockdev(device->bdev);
- invalidate_bdev(device->bdev);
- }
+ btrfs_close_bdev(device);
new_device = btrfs_alloc_device(NULL, &device->devid,
device->uuid);
btrfs_sysfs_rm_device_link(root->fs_info->fs_devices, device);
}
+ btrfs_close_bdev(device);
+
call_rcu(&device->rcu, free_device);
num_devices = btrfs_super_num_devices(root->fs_info->super_copy) - 1;
/* zero out the old super if it is writable */
btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str);
}
+
+ btrfs_close_bdev(srcdev);
+
call_rcu(&srcdev->rcu, free_device);
/*
* the device_list_mutex lock.
*/
btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str);
+
+ btrfs_close_bdev(tgtdev);
call_rcu(&tgtdev->rcu, free_device);
}
{
struct inode *inode = &ci->vfs_inode;
struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc;
- struct ceph_mds_session *session = *psession;
+ struct ceph_mds_session *session = NULL;
int mds;
+
dout("ceph_flush_snaps %p\n", inode);
+ if (psession)
+ session = *psession;
retry:
spin_lock(&ci->i_ceph_lock);
if (!(ci->i_ceph_flags & CEPH_I_FLUSH_SNAPS)) {
if (is_hash_order(new_pos)) {
/* no need to reset last_name for a forward seek when
* dentries are sotred in hash order */
- } else if (fi->frag |= fpos_frag(new_pos)) {
+ } else if (fi->frag != fpos_frag(new_pos)) {
return true;
}
rinfo = fi->last_readdir ? &fi->last_readdir->r_reply_info : NULL;
} else {
path = NULL;
pathlen = 0;
+ pathbase = 0;
}
spin_lock(&ci->i_ceph_lock);
char *s, *p;
char sep;
+ if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
+ return dget(sb->s_root);
+
full_path = cifs_build_path_to_root(vol, cifs_sb,
cifs_sb_master_tcon(cifs_sb));
if (full_path == NULL)
cifs_sb->mountdata = kstrndup(data, PAGE_SIZE, GFP_KERNEL);
if (cifs_sb->mountdata == NULL) {
root = ERR_PTR(-ENOMEM);
- goto out_cifs_sb;
+ goto out_free;
}
- if (volume_info->prepath) {
- cifs_sb->prepath = kstrdup(volume_info->prepath, GFP_KERNEL);
- if (cifs_sb->prepath == NULL) {
- root = ERR_PTR(-ENOMEM);
- goto out_cifs_sb;
- }
+ rc = cifs_setup_cifs_sb(volume_info, cifs_sb);
+ if (rc) {
+ root = ERR_PTR(rc);
+ goto out_free;
}
- cifs_setup_cifs_sb(volume_info, cifs_sb);
-
rc = cifs_mount(cifs_sb, volume_info);
if (rc) {
if (!(flags & MS_SILENT))
cifs_dbg(VFS, "cifs_mount failed w/return code = %d\n",
rc);
root = ERR_PTR(rc);
- goto out_mountdata;
+ goto out_free;
}
mnt_data.vol = volume_info;
sb->s_flags |= MS_ACTIVE;
}
- if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH)
- root = dget(sb->s_root);
- else
- root = cifs_get_root(volume_info, sb);
-
+ root = cifs_get_root(volume_info, sb);
if (IS_ERR(root))
goto out_super;
cifs_cleanup_volume_info(volume_info);
return root;
-out_mountdata:
+out_free:
+ kfree(cifs_sb->prepath);
kfree(cifs_sb->mountdata);
-out_cifs_sb:
kfree(cifs_sb);
out_nls:
unload_nls(volume_info->local_nls);
unsigned int to_read);
extern int cifs_read_page_from_socket(struct TCP_Server_Info *server,
struct page *page, unsigned int to_read);
-extern void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
+extern int cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
struct cifs_sb_info *cifs_sb);
extern int cifs_match_super(struct super_block *, void *);
extern void cifs_cleanup_volume_info(struct smb_vol *pvolume_info);
return 1;
}
+static int
+match_prepath(struct super_block *sb, struct cifs_mnt_data *mnt_data)
+{
+ struct cifs_sb_info *old = CIFS_SB(sb);
+ struct cifs_sb_info *new = mnt_data->cifs_sb;
+
+ if (old->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) {
+ if (!(new->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH))
+ return 0;
+ /* The prepath should be null terminated strings */
+ if (strcmp(new->prepath, old->prepath))
+ return 0;
+
+ return 1;
+ }
+ return 0;
+}
+
int
cifs_match_super(struct super_block *sb, void *data)
{
if (!match_server(tcp_srv, volume_info) ||
!match_session(ses, volume_info) ||
- !match_tcon(tcon, volume_info->UNC)) {
+ !match_tcon(tcon, volume_info->UNC) ||
+ !match_prepath(sb, mnt_data)) {
rc = 0;
goto out;
}
}
}
-void cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
+int cifs_setup_cifs_sb(struct smb_vol *pvolume_info,
struct cifs_sb_info *cifs_sb)
{
INIT_DELAYED_WORK(&cifs_sb->prune_tlinks, cifs_prune_tlinks);
if ((pvolume_info->cifs_acl) && (pvolume_info->dynperm))
cifs_dbg(VFS, "mount option dynperm ignored if cifsacl mount option supported\n");
+
+ if (pvolume_info->prepath) {
+ cifs_sb->prepath = kstrdup(pvolume_info->prepath, GFP_KERNEL);
+ if (cifs_sb->prepath == NULL)
+ return -ENOMEM;
+ }
+
+ return 0;
}
static void
if (bin_attr->cb_max_size &&
*ppos + count > bin_attr->cb_max_size) {
len = -EFBIG;
+ goto out;
}
tbuf = vmalloc(*ppos + count);
#include <linux/random.h>
#include <linux/string.h>
#include <linux/fscrypto.h>
+#include <linux/mount.h>
static int inode_has_encryption_context(struct inode *inode)
{
return inode->i_sb->s_cop->set_context(inode, &ctx, sizeof(ctx), NULL);
}
-int fscrypt_process_policy(struct inode *inode,
+int fscrypt_process_policy(struct file *filp,
const struct fscrypt_policy *policy)
{
+ struct inode *inode = file_inode(filp);
+ int ret;
+
+ if (!inode_owner_or_capable(inode))
+ return -EACCES;
+
if (policy->version != 0)
return -EINVAL;
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
if (!inode_has_encryption_context(inode)) {
- if (!inode->i_sb->s_cop->empty_dir)
- return -EOPNOTSUPP;
- if (!inode->i_sb->s_cop->empty_dir(inode))
- return -ENOTEMPTY;
- return create_encryption_context_from_policy(inode, policy);
+ if (!S_ISDIR(inode->i_mode))
+ ret = -EINVAL;
+ else if (!inode->i_sb->s_cop->empty_dir)
+ ret = -EOPNOTSUPP;
+ else if (!inode->i_sb->s_cop->empty_dir(inode))
+ ret = -ENOTEMPTY;
+ else
+ ret = create_encryption_context_from_policy(inode,
+ policy);
+ } else if (!is_encryption_context_consistent_with_policy(inode,
+ policy)) {
+ printk(KERN_WARNING
+ "%s: Policy inconsistent with encryption context\n",
+ __func__);
+ ret = -EINVAL;
}
- if (is_encryption_context_consistent_with_policy(inode, policy))
- return 0;
-
- printk(KERN_WARNING "%s: Policy inconsistent with encryption context\n",
- __func__);
- return -EINVAL;
+ mnt_drop_write_file(filp);
+ return ret;
}
EXPORT_SYMBOL(fscrypt_process_policy);
*/
void *devpts_get_priv(struct dentry *dentry)
{
- WARN_ON_ONCE(dentry->d_sb->s_magic != DEVPTS_SUPER_MAGIC);
+ if (dentry->d_sb->s_magic != DEVPTS_SUPER_MAGIC)
+ return NULL;
return dentry->d_fsdata;
}
static const struct file_operations format3_fops;
static const struct file_operations format4_fops;
-static int table_open(struct inode *inode, struct file *file)
+static int table_open1(struct inode *inode, struct file *file)
{
struct seq_file *seq;
- int ret = -1;
+ int ret;
- if (file->f_op == &format1_fops)
- ret = seq_open(file, &format1_seq_ops);
- else if (file->f_op == &format2_fops)
- ret = seq_open(file, &format2_seq_ops);
- else if (file->f_op == &format3_fops)
- ret = seq_open(file, &format3_seq_ops);
- else if (file->f_op == &format4_fops)
- ret = seq_open(file, &format4_seq_ops);
+ ret = seq_open(file, &format1_seq_ops);
+ if (ret)
+ return ret;
+
+ seq = file->private_data;
+ seq->private = inode->i_private; /* the dlm_ls */
+ return 0;
+}
+
+static int table_open2(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq;
+ int ret;
+
+ ret = seq_open(file, &format2_seq_ops);
+ if (ret)
+ return ret;
+
+ seq = file->private_data;
+ seq->private = inode->i_private; /* the dlm_ls */
+ return 0;
+}
+
+static int table_open3(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq;
+ int ret;
+
+ ret = seq_open(file, &format3_seq_ops);
+ if (ret)
+ return ret;
+
+ seq = file->private_data;
+ seq->private = inode->i_private; /* the dlm_ls */
+ return 0;
+}
+
+static int table_open4(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq;
+ int ret;
+ ret = seq_open(file, &format4_seq_ops);
if (ret)
return ret;
static const struct file_operations format1_fops = {
.owner = THIS_MODULE,
- .open = table_open,
+ .open = table_open1,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release
static const struct file_operations format2_fops = {
.owner = THIS_MODULE,
- .open = table_open,
+ .open = table_open2,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release
static const struct file_operations format3_fops = {
.owner = THIS_MODULE,
- .open = table_open,
+ .open = table_open3,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release
static const struct file_operations format4_fops = {
.owner = THIS_MODULE,
- .open = table_open,
+ .open = table_open4,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release
sbi->s_want_extra_isize,
iloc, handle);
if (ret) {
- ext4_set_inode_state(inode,
- EXT4_STATE_NO_EXPAND);
if (mnt_count !=
le16_to_cpu(sbi->s_es->s_mnt_count)) {
ext4_warning(inode->i_sb,
(struct fscrypt_policy __user *)arg,
sizeof(policy)))
return -EFAULT;
- return fscrypt_process_policy(inode, &policy);
+ return fscrypt_process_policy(filp, &policy);
#else
return -EOPNOTSUPP;
#endif
/* Called at mount-time, super-block is locked */
static int ext4_check_descriptors(struct super_block *sb,
+ ext4_fsblk_t sb_block,
ext4_group_t *first_not_zeroed)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
grp = i;
block_bitmap = ext4_block_bitmap(sb, gdp);
+ if (block_bitmap == sb_block) {
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+ "Block bitmap for group %u overlaps "
+ "superblock", i);
+ }
if (block_bitmap < first_block || block_bitmap > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Block bitmap for group %u not in group "
return 0;
}
inode_bitmap = ext4_inode_bitmap(sb, gdp);
+ if (inode_bitmap == sb_block) {
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+ "Inode bitmap for group %u overlaps "
+ "superblock", i);
+ }
if (inode_bitmap < first_block || inode_bitmap > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
"Inode bitmap for group %u not in group "
return 0;
}
inode_table = ext4_inode_table(sb, gdp);
+ if (inode_table == sb_block) {
+ ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+ "Inode table for group %u overlaps "
+ "superblock", i);
+ }
if (inode_table < first_block ||
inode_table + sbi->s_itb_per_group - 1 > last_block) {
ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
goto failed_mount2;
}
}
- if (!ext4_check_descriptors(sb, &first_not_zeroed)) {
+ if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) {
ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
ret = -EFSCORRUPTED;
goto failed_mount2;
size_t min_offs, free;
int total_ino;
void *base, *start, *end;
- int extra_isize = 0, error = 0, tried_min_extra_isize = 0;
+ int error = 0, tried_min_extra_isize = 0;
int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize);
+ int isize_diff; /* How much do we need to grow i_extra_isize */
down_write(&EXT4_I(inode)->xattr_sem);
+ /*
+ * Set EXT4_STATE_NO_EXPAND to avoid recursion when marking inode dirty
+ */
+ ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
retry:
- if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) {
- up_write(&EXT4_I(inode)->xattr_sem);
- return 0;
- }
+ isize_diff = new_extra_isize - EXT4_I(inode)->i_extra_isize;
+ if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
+ goto out;
header = IHDR(inode, raw_inode);
entry = IFIRST(header);
goto cleanup;
free = ext4_xattr_free_space(last, &min_offs, base, &total_ino);
- if (free >= new_extra_isize) {
+ if (free >= isize_diff) {
entry = IFIRST(header);
ext4_xattr_shift_entries(entry, EXT4_I(inode)->i_extra_isize
- new_extra_isize, (void *)raw_inode +
(void *)header, total_ino,
inode->i_sb->s_blocksize);
EXT4_I(inode)->i_extra_isize = new_extra_isize;
- error = 0;
- goto cleanup;
+ goto out;
}
/*
end = bh->b_data + bh->b_size;
min_offs = end - base;
free = ext4_xattr_free_space(first, &min_offs, base, NULL);
- if (free < new_extra_isize) {
+ if (free < isize_diff) {
if (!tried_min_extra_isize && s_min_extra_isize) {
tried_min_extra_isize++;
new_extra_isize = s_min_extra_isize;
free = inode->i_sb->s_blocksize;
}
- while (new_extra_isize > 0) {
+ while (isize_diff > 0) {
size_t offs, size, entry_size;
struct ext4_xattr_entry *small_entry = NULL;
struct ext4_xattr_info i = {
EXT4_XATTR_SIZE(le32_to_cpu(last->e_value_size)) +
EXT4_XATTR_LEN(last->e_name_len);
if (total_size <= free && total_size < min_total_size) {
- if (total_size < new_extra_isize) {
+ if (total_size < isize_diff) {
small_entry = last;
} else {
entry = last;
error = ext4_xattr_ibody_set(handle, inode, &i, is);
if (error)
goto cleanup;
+ total_ino -= entry_size;
entry = IFIRST(header);
- if (entry_size + EXT4_XATTR_SIZE(size) >= new_extra_isize)
- shift_bytes = new_extra_isize;
+ if (entry_size + EXT4_XATTR_SIZE(size) >= isize_diff)
+ shift_bytes = isize_diff;
else
- shift_bytes = entry_size + size;
+ shift_bytes = entry_size + EXT4_XATTR_SIZE(size);
/* Adjust the offsets and shift the remaining entries ahead */
- ext4_xattr_shift_entries(entry, EXT4_I(inode)->i_extra_isize -
- shift_bytes, (void *)raw_inode +
- EXT4_GOOD_OLD_INODE_SIZE + extra_isize + shift_bytes,
- (void *)header, total_ino - entry_size,
- inode->i_sb->s_blocksize);
+ ext4_xattr_shift_entries(entry, -shift_bytes,
+ (void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE +
+ EXT4_I(inode)->i_extra_isize + shift_bytes,
+ (void *)header, total_ino, inode->i_sb->s_blocksize);
- extra_isize += shift_bytes;
- new_extra_isize -= shift_bytes;
- EXT4_I(inode)->i_extra_isize = extra_isize;
+ isize_diff -= shift_bytes;
+ EXT4_I(inode)->i_extra_isize += shift_bytes;
+ header = IHDR(inode, raw_inode);
i.name = b_entry_name;
i.value = buffer;
kfree(bs);
}
brelse(bh);
+out:
+ ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
up_write(&EXT4_I(inode)->xattr_sem);
return 0;
kfree(is);
kfree(bs);
brelse(bh);
+ /*
+ * We deliberately leave EXT4_STATE_NO_EXPAND set here since inode
+ * size expansion failed.
+ */
up_write(&EXT4_I(inode)->xattr_sem);
return error;
}
#define EXT4_XATTR_INDEX_SYSTEM 7
#define EXT4_XATTR_INDEX_RICHACL 8
#define EXT4_XATTR_INDEX_ENCRYPTION 9
+#define EXT4_XATTR_INDEX_HURD 10 /* Reserved for Hurd */
struct ext4_xattr_header {
__le32 h_magic; /* magic number for identification */
trace_f2fs_write_end(inode, pos, len, copied);
set_page_dirty(page);
- f2fs_put_page(page, 1);
if (pos + copied > i_size_read(inode))
f2fs_i_size_write(inode, pos + copied);
+ f2fs_put_page(page, 1);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
return copied;
}
/* NAT cache management */
struct radix_tree_root nat_root;/* root of the nat entry cache */
struct radix_tree_root nat_set_root;/* root of the nat set cache */
- struct percpu_rw_semaphore nat_tree_lock; /* protect nat_tree_lock */
+ struct rw_semaphore nat_tree_lock; /* protect nat_tree_lock */
struct list_head nat_entries; /* cached nat entry list (clean) */
unsigned int nat_cnt; /* the # of cached nat entries */
unsigned int dirty_nat_cnt; /* total num of nat entries in set */
struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */
struct inode *meta_inode; /* cache meta blocks */
struct mutex cp_mutex; /* checkpoint procedure lock */
- struct percpu_rw_semaphore cp_rwsem; /* blocking FS operations */
+ struct rw_semaphore cp_rwsem; /* blocking FS operations */
struct rw_semaphore node_write; /* locking node writes */
wait_queue_head_t cp_wait;
unsigned long last_time[MAX_TIME]; /* to store time in jiffies */
static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
{
- percpu_down_read(&sbi->cp_rwsem);
+ down_read(&sbi->cp_rwsem);
}
static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
{
- percpu_up_read(&sbi->cp_rwsem);
+ up_read(&sbi->cp_rwsem);
}
static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
{
- percpu_down_write(&sbi->cp_rwsem);
+ down_write(&sbi->cp_rwsem);
}
static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
{
- percpu_up_write(&sbi->cp_rwsem);
+ up_write(&sbi->cp_rwsem);
}
static inline int __get_cp_reason(struct f2fs_sb_info *sbi)
{
struct fscrypt_policy policy;
struct inode *inode = file_inode(filp);
- int ret;
if (copy_from_user(&policy, (struct fscrypt_policy __user *)arg,
sizeof(policy)))
return -EFAULT;
- ret = mnt_want_write_file(filp);
- if (ret)
- return ret;
-
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
- ret = fscrypt_process_policy(inode, &policy);
- mnt_drop_write_file(filp);
- return ret;
+ return fscrypt_process_policy(filp, &policy);
}
static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg)
if (unlikely(f2fs_readonly(src->i_sb)))
return -EROFS;
- if (S_ISDIR(src->i_mode) || S_ISDIR(dst->i_mode))
- return -EISDIR;
+ if (!S_ISREG(src->i_mode) || !S_ISREG(dst->i_mode))
+ return -EINVAL;
if (f2fs_encrypted_inode(src) || f2fs_encrypted_inode(dst))
return -EOPNOTSUPP;
inode_lock(src);
- if (src != dst)
- inode_lock(dst);
+ if (src != dst) {
+ if (!inode_trylock(dst)) {
+ ret = -EBUSY;
+ goto out;
+ }
+ }
ret = -EINVAL;
if (pos_in + len > src->i_size || pos_in + len < pos_in)
out_unlock:
if (src != dst)
inode_unlock(dst);
+out:
inode_unlock(src);
return ret;
}
struct nat_entry *e;
bool need = false;
- percpu_down_read(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (e) {
if (!get_nat_flag(e, IS_CHECKPOINTED) &&
!get_nat_flag(e, HAS_FSYNCED_INODE))
need = true;
}
- percpu_up_read(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
return need;
}
struct nat_entry *e;
bool is_cp = true;
- percpu_down_read(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (e && !get_nat_flag(e, IS_CHECKPOINTED))
is_cp = false;
- percpu_up_read(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
return is_cp;
}
struct nat_entry *e;
bool need_update = true;
- percpu_down_read(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, ino);
if (e && get_nat_flag(e, HAS_LAST_FSYNC) &&
(get_nat_flag(e, IS_CHECKPOINTED) ||
get_nat_flag(e, HAS_FSYNCED_INODE)))
need_update = false;
- percpu_up_read(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
return need_update;
}
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct nat_entry *e;
- percpu_down_write(&nm_i->nat_tree_lock);
+ down_write(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, ni->nid);
if (!e) {
e = grab_nat_entry(nm_i, ni->nid);
set_nat_flag(e, HAS_FSYNCED_INODE, true);
set_nat_flag(e, HAS_LAST_FSYNC, fsync_done);
}
- percpu_up_write(&nm_i->nat_tree_lock);
+ up_write(&nm_i->nat_tree_lock);
}
int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
struct f2fs_nm_info *nm_i = NM_I(sbi);
int nr = nr_shrink;
- percpu_down_write(&nm_i->nat_tree_lock);
+ if (!down_write_trylock(&nm_i->nat_tree_lock))
+ return 0;
while (nr_shrink && !list_empty(&nm_i->nat_entries)) {
struct nat_entry *ne;
__del_from_nat_cache(nm_i, ne);
nr_shrink--;
}
- percpu_up_write(&nm_i->nat_tree_lock);
+ up_write(&nm_i->nat_tree_lock);
return nr - nr_shrink;
}
ni->nid = nid;
/* Check nat cache */
- percpu_down_read(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
e = __lookup_nat_cache(nm_i, nid);
if (e) {
ni->ino = nat_get_ino(e);
ni->blk_addr = nat_get_blkaddr(e);
ni->version = nat_get_version(e);
- percpu_up_read(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
return;
}
node_info_from_raw_nat(ni, &ne);
f2fs_put_page(page, 1);
cache:
- percpu_up_read(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
/* cache nat entry */
- percpu_down_write(&nm_i->nat_tree_lock);
+ down_write(&nm_i->nat_tree_lock);
cache_nat_entry(sbi, nid, &ne);
- percpu_up_write(&nm_i->nat_tree_lock);
+ up_write(&nm_i->nat_tree_lock);
}
/*
ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES,
META_NAT, true);
- percpu_down_read(&nm_i->nat_tree_lock);
+ down_read(&nm_i->nat_tree_lock);
while (1) {
struct page *page = get_current_nat_page(sbi, nid);
remove_free_nid(nm_i, nid);
}
up_read(&curseg->journal_rwsem);
- percpu_up_read(&nm_i->nat_tree_lock);
+ up_read(&nm_i->nat_tree_lock);
ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid),
nm_i->ra_nid_pages, META_NAT, false);
if (!nm_i->dirty_nat_cnt)
return;
- percpu_down_write(&nm_i->nat_tree_lock);
+ down_write(&nm_i->nat_tree_lock);
/*
* if there are no enough space in journal to store dirty nat
list_for_each_entry_safe(set, tmp, &sets, set_list)
__flush_nat_entry_set(sbi, set);
- percpu_up_write(&nm_i->nat_tree_lock);
+ up_write(&nm_i->nat_tree_lock);
f2fs_bug_on(sbi, nm_i->dirty_nat_cnt);
}
mutex_init(&nm_i->build_lock);
spin_lock_init(&nm_i->free_nid_list_lock);
- if (percpu_init_rwsem(&nm_i->nat_tree_lock))
- return -ENOMEM;
+ init_rwsem(&nm_i->nat_tree_lock);
nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid);
nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP);
spin_unlock(&nm_i->free_nid_list_lock);
/* destroy nat cache */
- percpu_down_write(&nm_i->nat_tree_lock);
+ down_write(&nm_i->nat_tree_lock);
while ((found = __gang_lookup_nat_cache(nm_i,
nid, NATVEC_SIZE, natvec))) {
unsigned idx;
kmem_cache_free(nat_entry_set_slab, setvec[idx]);
}
}
- percpu_up_write(&nm_i->nat_tree_lock);
+ up_write(&nm_i->nat_tree_lock);
- percpu_free_rwsem(&nm_i->nat_tree_lock);
kfree(nm_i->nat_bitmap);
sbi->nm_info = NULL;
kfree(nm_i);
percpu_counter_destroy(&sbi->nr_pages[i]);
percpu_counter_destroy(&sbi->alloc_valid_block_count);
percpu_counter_destroy(&sbi->total_valid_inode_count);
-
- percpu_free_rwsem(&sbi->cp_rwsem);
}
static void f2fs_put_super(struct super_block *sb)
{
int i, err;
- if (percpu_init_rwsem(&sbi->cp_rwsem))
- return -ENOMEM;
-
for (i = 0; i < NR_COUNT_TYPE; i++) {
err = percpu_counter_init(&sbi->nr_pages[i], 0, GFP_KERNEL);
if (err)
sbi->write_io[i].bio = NULL;
}
+ init_rwsem(&sbi->cp_rwsem);
init_waitqueue_head(&sbi->cp_wait);
init_sb_info(sbi);
{
struct backing_dev_info *bdi;
+ /*
+ * If we are expecting writeback progress we must submit plugged IO.
+ */
+ if (blk_needs_flush_plug(current))
+ blk_schedule_flush_plug(current);
+
if (!nr_pages)
nr_pages = get_nr_dirty_pages();
req->out.args[0].size = count;
}
-static void fuse_release_user_pages(struct fuse_req *req, int write)
+static void fuse_release_user_pages(struct fuse_req *req, bool should_dirty)
{
unsigned i;
for (i = 0; i < req->num_pages; i++) {
struct page *page = req->pages[i];
- if (write)
+ if (should_dirty)
set_page_dirty_lock(page);
put_page(page);
}
loff_t *ppos, int flags)
{
int write = flags & FUSE_DIO_WRITE;
+ bool should_dirty = !write && iter_is_iovec(iter);
int cuse = flags & FUSE_DIO_CUSE;
struct file *file = io->file;
struct inode *inode = file->f_mapping->host;
nres = fuse_send_read(req, io, pos, nbytes, owner);
if (!io->async)
- fuse_release_user_pages(req, !write);
+ fuse_release_user_pages(req, should_dirty);
if (req->out.h.error) {
err = req->out.h.error;
break;
return thaw_super(sb);
}
-static long ioctl_file_dedupe_range(struct file *file, void __user *arg)
+static int ioctl_file_dedupe_range(struct file *file, void __user *arg)
{
struct file_dedupe_range __user *argp = arg;
struct file_dedupe_range *same = NULL;
}
size = offsetof(struct file_dedupe_range __user, info[count]);
+ if (size > PAGE_SIZE) {
+ ret = -ENOMEM;
+ goto out;
+ }
same = memdup_user(argp, size);
if (IS_ERR(same)) {
* Now the data has been copied, commit the range we've copied. This
* should not fail unless the filesystem has had a fatal error.
*/
- ret = ops->iomap_end(inode, pos, length, written > 0 ? written : 0,
- flags, &iomap);
+ if (ops->iomap_end) {
+ ret = ops->iomap_end(inode, pos, length,
+ written > 0 ? written : 0,
+ flags, &iomap);
+ }
return written ? written : ret;
}
if (mapping_writably_mapped(inode->i_mapping))
flush_dcache_page(page);
- pagefault_disable();
copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
- pagefault_enable();
flush_dcache_page(page);
- mark_page_accessed(page);
status = iomap_write_end(inode, pos, bytes, copied, page);
if (unlikely(status < 0))
break;
}
+ if (iomap->flags & IOMAP_F_MERGED)
+ flags |= FIEMAP_EXTENT_MERGED;
+
return fiemap_fill_next_extent(fi, iomap->offset,
iomap->blkno != IOMAP_NULL_BLOCK ? iomap->blkno << 9: 0,
- iomap->length, flags | FIEMAP_EXTENT_MERGED);
+ iomap->length, flags);
}
if (ret)
return ret;
- ret = filemap_write_and_wait(inode->i_mapping);
- if (ret)
- return ret;
+ if (fi->fi_flags & FIEMAP_FLAG_SYNC) {
+ ret = filemap_write_and_wait(inode->i_mapping);
+ if (ret)
+ return ret;
+ }
while (len > 0) {
ret = iomap_apply(inode, start, len, 0, ops, &ctx,
iomap_fiemap_actor);
+ /* inode with no (attribute) mapping will give ENOENT */
+ if (ret == -ENOENT)
+ break;
if (ret < 0)
return ret;
if (ret == 0)
mutex_lock(&kernfs_mutex);
list_for_each_entry(info, &kernfs_root(kn)->supers, node) {
+ struct kernfs_node *parent;
struct inode *inode;
- struct dentry *dentry;
+ /*
+ * We want fsnotify_modify() on @kn but as the
+ * modifications aren't originating from userland don't
+ * have the matching @file available. Look up the inodes
+ * and generate the events manually.
+ */
inode = ilookup(info->sb, kn->ino);
if (!inode)
continue;
- dentry = d_find_any_alias(inode);
- if (dentry) {
- fsnotify_parent(NULL, dentry, FS_MODIFY);
- fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE,
- NULL, 0);
- dput(dentry);
+ parent = kernfs_get_parent(kn);
+ if (parent) {
+ struct inode *p_inode;
+
+ p_inode = ilookup(info->sb, parent->ino);
+ if (p_inode) {
+ fsnotify(p_inode, FS_MODIFY | FS_EVENT_ON_CHILD,
+ inode, FSNOTIFY_EVENT_INODE, kn->name, 0);
+ iput(p_inode);
+ }
+
+ kernfs_put(parent);
}
+ fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE,
+ kn->name, 0);
iput(inode);
}
PAGE_SIZE - 1) & (loff_t)PAGE_MASK;
ext_tree_mark_written(bl, start >> SECTOR_SHIFT,
- (end - start) >> SECTOR_SHIFT);
+ (end - start) >> SECTOR_SHIFT, end);
}
pnfs_ld_write_done(hdr);
struct rb_root bl_ext_ro;
spinlock_t bl_ext_lock; /* Protects list manipulation */
bool bl_scsi_layout;
+ u64 bl_lwb;
};
static inline struct pnfs_block_layout *
int ext_tree_remove(struct pnfs_block_layout *bl, bool rw, sector_t start,
sector_t end);
int ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start,
- sector_t len);
+ sector_t len, u64 lwb);
bool ext_tree_lookup(struct pnfs_block_layout *bl, sector_t isect,
struct pnfs_block_extent *ret, bool rw);
int ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg);
int
ext_tree_mark_written(struct pnfs_block_layout *bl, sector_t start,
- sector_t len)
+ sector_t len, u64 lwb)
{
struct rb_root *root = &bl->bl_ext_rw;
sector_t end = start + len;
}
}
out:
+ if (bl->bl_lwb < lwb)
+ bl->bl_lwb = lwb;
spin_unlock(&bl->bl_ext_lock);
__ext_put_deviceids(&tmp);
}
static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
- size_t buffer_size, size_t *count)
+ size_t buffer_size, size_t *count, __u64 *lastbyte)
{
struct pnfs_block_extent *be;
int ret = 0;
p = encode_block_extent(be, p);
be->be_tag = EXTENT_COMMITTING;
}
+ *lastbyte = bl->bl_lwb - 1;
+ bl->bl_lwb = 0;
spin_unlock(&bl->bl_ext_lock);
return ret;
arg->layoutupdate_pages = &arg->layoutupdate_page;
retry:
- ret = ext_tree_encode_commit(bl, start_p + 1, buffer_size, &count);
+ ret = ext_tree_encode_commit(bl, start_p + 1, buffer_size, &count, &arg->lastbytewritten);
if (unlikely(ret)) {
ext_tree_free_commitdata(arg, buffer_size);
err_socks:
svc_rpcb_cleanup(serv, net);
err_bind:
+ nn->cb_users[minorversion]--;
dprintk("NFS: Couldn't create callback socket: err = %d; "
"net = %p\n", ret, net);
return ret;
((u32 *)&rclist->rcl_sessionid.data)[3],
ref->rc_sequenceid, ref->rc_slotid);
- spin_lock(&tbl->slot_tbl_lock);
- status = (test_bit(ref->rc_slotid, tbl->used_slots) &&
- tbl->slots[ref->rc_slotid].seq_nr ==
- ref->rc_sequenceid);
- spin_unlock(&tbl->slot_tbl_lock);
+ status = nfs4_slot_wait_on_seqid(tbl, ref->rc_slotid,
+ ref->rc_sequenceid, HZ >> 1) < 0;
if (status)
goto out;
}
goto out;
tbl = &clp->cl_session->bc_slot_table;
- slot = tbl->slots + args->csa_slotid;
/* Set up res before grabbing the spinlock */
memcpy(&res->csr_sessionid, &args->csa_sessionid,
* Initialise the timeout values for a connection
*/
void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
- unsigned int timeo, unsigned int retrans)
+ int timeo, int retrans)
{
to->to_initval = timeo * HZ / 10;
to->to_retries = retrans;
switch (proto) {
case XPRT_TRANSPORT_TCP:
case XPRT_TRANSPORT_RDMA:
- if (to->to_retries == 0)
+ if (retrans == NFS_UNSPEC_RETRANS)
to->to_retries = NFS_DEF_TCP_RETRANS;
- if (to->to_initval == 0)
+ if (timeo == NFS_UNSPEC_TIMEO || to->to_retries == 0)
to->to_initval = NFS_DEF_TCP_TIMEO * HZ / 10;
if (to->to_initval > NFS_MAX_TCP_TIMEOUT)
to->to_initval = NFS_MAX_TCP_TIMEOUT;
to->to_exponential = 0;
break;
case XPRT_TRANSPORT_UDP:
- if (to->to_retries == 0)
+ if (retrans == NFS_UNSPEC_RETRANS)
to->to_retries = NFS_DEF_UDP_RETRANS;
- if (!to->to_initval)
+ if (timeo == NFS_UNSPEC_TIMEO || to->to_initval == 0)
to->to_initval = NFS_DEF_UDP_TIMEO * HZ / 10;
if (to->to_initval > NFS_MAX_UDP_TIMEOUT)
to->to_initval = NFS_MAX_UDP_TIMEOUT;
if (result <= 0)
goto out;
- written = generic_write_sync(iocb, result);
+ result = generic_write_sync(iocb, result);
+ if (result < 0)
+ goto out;
+ written = result;
iocb->ki_pos += written;
/* Return error values */
if (ffl) {
INIT_LIST_HEAD(&ffl->error_list);
INIT_LIST_HEAD(&ffl->mirrors);
+ ffl->last_report_time = ktime_get();
return &ffl->generic_hdr;
} else
return NULL;
{
static const ktime_t notime = {0};
s64 report_interval = FF_LAYOUTSTATS_REPORT_INTERVAL;
+ struct nfs4_flexfile_layout *ffl = FF_LAYOUT_FROM_HDR(mirror->layout);
nfs4_ff_start_busy_timer(&layoutstat->busy_timer, now);
if (ktime_equal(mirror->start_time, notime))
mirror->start_time = now;
- if (ktime_equal(mirror->last_report_time, notime))
- mirror->last_report_time = now;
if (mirror->report_interval != 0)
report_interval = (s64)mirror->report_interval * 1000LL;
else if (layoutstats_timer != 0)
report_interval = (s64)layoutstats_timer * 1000LL;
- if (ktime_to_ms(ktime_sub(now, mirror->last_report_time)) >=
+ if (ktime_to_ms(ktime_sub(now, ffl->last_report_time)) >=
report_interval) {
- mirror->last_report_time = now;
+ ffl->last_report_time = now;
return true;
}
{
struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
struct nfs4_pnfs_ds *ds;
+ bool fail_return = false;
int idx;
/* mirrors are sorted by efficiency */
for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) {
- ds = nfs4_ff_layout_prepare_ds(lseg, idx, false);
+ if (idx+1 == fls->mirror_array_cnt)
+ fail_return = true;
+ ds = nfs4_ff_layout_prepare_ds(lseg, idx, fail_return);
if (ds) {
*best_idx = idx;
return ds;
struct nfs4_pnfs_ds *ds;
int ds_idx;
+retry:
/* Use full layout for now */
if (!pgio->pg_lseg)
ff_layout_pg_get_read(pgio, req, false);
ds = ff_layout_choose_best_ds_for_read(pgio->pg_lseg, 0, &ds_idx);
if (!ds) {
- if (ff_layout_no_fallback_to_mds(pgio->pg_lseg))
- goto out_pnfs;
- else
+ if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
goto out_mds;
+ pnfs_put_lseg(pgio->pg_lseg);
+ pgio->pg_lseg = NULL;
+ /* Sleep for 1 second before retrying */
+ ssleep(1);
+ goto retry;
}
mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx);
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = NULL;
nfs_pageio_reset_read_mds(pgio);
- return;
-
-out_pnfs:
- pnfs_set_lo_fail(pgio->pg_lseg);
- pnfs_put_lseg(pgio->pg_lseg);
- pgio->pg_lseg = NULL;
}
static void
int i;
int status;
+retry:
if (!pgio->pg_lseg) {
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
req->wb_context,
for (i = 0; i < pgio->pg_mirror_count; i++) {
ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, i, true);
if (!ds) {
- if (ff_layout_no_fallback_to_mds(pgio->pg_lseg))
- goto out_pnfs;
- else
+ if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
goto out_mds;
+ pnfs_put_lseg(pgio->pg_lseg);
+ pgio->pg_lseg = NULL;
+ /* Sleep for 1 second before retrying */
+ ssleep(1);
+ goto retry;
}
pgm = &pgio->pg_mirrors[i];
mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = NULL;
nfs_pageio_reset_write_mds(pgio);
- return;
-
-out_pnfs:
- pnfs_set_lo_fail(pgio->pg_lseg);
- pnfs_put_lseg(pgio->pg_lseg);
- pgio->pg_lseg = NULL;
}
static unsigned int
struct nfs4_ff_layoutstat read_stat;
struct nfs4_ff_layoutstat write_stat;
ktime_t start_time;
- ktime_t last_report_time;
u32 report_interval;
};
struct pnfs_ds_commit_info commit_info;
struct list_head mirrors;
struct list_head error_list; /* nfs4_ff_layout_ds_err */
+ ktime_t last_report_time; /* Layoutstat report times */
};
static inline struct nfs4_flexfile_layout *
#define NFSDBG_FACILITY NFSDBG_PNFS_LD
-static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO;
-static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS;
+static unsigned int dataserver_timeo = NFS_DEF_TCP_RETRANS;
+static unsigned int dataserver_retrans;
void nfs4_ff_layout_put_deviceid(struct nfs4_ff_layout_ds *mirror_ds)
{
devid = &mirror->mirror_ds->id_node;
if (ff_layout_test_devid_unavailable(devid))
- goto out;
+ goto out_fail;
ds = mirror->mirror_ds->ds;
/* matching smp_wmb() in _nfs4_pnfs_v3/4_ds_connect */
mirror->mirror_ds->ds_versions[0].rsize = max_payload;
if (mirror->mirror_ds->ds_versions[0].wsize > max_payload)
mirror->mirror_ds->ds_versions[0].wsize = max_payload;
- } else {
- ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),
- mirror, lseg->pls_range.offset,
- lseg->pls_range.length, NFS4ERR_NXIO,
- OP_ILLEGAL, GFP_NOIO);
- if (fail_return || !ff_layout_has_available_ds(lseg))
- pnfs_error_mark_layout_for_return(ino, lseg);
- ds = NULL;
+ goto out;
}
+ ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),
+ mirror, lseg->pls_range.offset,
+ lseg->pls_range.length, NFS4ERR_NXIO,
+ OP_ILLEGAL, GFP_NOIO);
+out_fail:
+ if (fail_return || !ff_layout_has_available_ds(lseg))
+ pnfs_error_mark_layout_for_return(ino, lseg);
+ ds = NULL;
out:
return ds;
}
*/
#define NFS_UNSPEC_PORT (-1)
+#define NFS_UNSPEC_RETRANS (UINT_MAX)
+#define NFS_UNSPEC_TIMEO (UINT_MAX)
+
/*
* Maximum number of pages that readdir can use for creating
* a vmapped array of pages.
int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *, struct nfs_fattr *);
void nfs_server_insert_lists(struct nfs_server *);
void nfs_server_remove_lists(struct nfs_server *);
-void nfs_init_timeout_values(struct rpc_timeout *, int, unsigned int, unsigned int);
+void nfs_init_timeout_values(struct rpc_timeout *to, int proto, int timeo, int retrans);
int nfs_init_server_rpcclient(struct nfs_server *, const struct rpc_timeout *t,
rpc_authflavor_t);
struct nfs_server *nfs_alloc_server(void);
nfs42_layoutstat_prepare(struct rpc_task *task, void *calldata)
{
struct nfs42_layoutstat_data *data = calldata;
- struct nfs_server *server = NFS_SERVER(data->args.inode);
+ struct inode *inode = data->inode;
+ struct nfs_server *server = NFS_SERVER(inode);
+ struct pnfs_layout_hdr *lo;
+ spin_lock(&inode->i_lock);
+ lo = NFS_I(inode)->layout;
+ if (!pnfs_layout_is_valid(lo)) {
+ spin_unlock(&inode->i_lock);
+ rpc_exit(task, 0);
+ return;
+ }
+ nfs4_stateid_copy(&data->args.stateid, &lo->plh_stateid);
+ spin_unlock(&inode->i_lock);
nfs41_setup_sequence(nfs4_get_session(server), &data->args.seq_args,
&data->res.seq_res, task);
+
}
static void
case 0:
break;
case -NFS4ERR_EXPIRED:
+ case -NFS4ERR_ADMIN_REVOKED:
+ case -NFS4ERR_DELEG_REVOKED:
case -NFS4ERR_STALE_STATEID:
- case -NFS4ERR_OLD_STATEID:
case -NFS4ERR_BAD_STATEID:
spin_lock(&inode->i_lock);
lo = NFS_I(inode)->layout;
- if (lo && nfs4_stateid_match(&data->args.stateid,
+ if (pnfs_layout_is_valid(lo) &&
+ nfs4_stateid_match(&data->args.stateid,
&lo->plh_stateid)) {
LIST_HEAD(head);
} else
spin_unlock(&inode->i_lock);
break;
+ case -NFS4ERR_OLD_STATEID:
+ spin_lock(&inode->i_lock);
+ lo = NFS_I(inode)->layout;
+ if (pnfs_layout_is_valid(lo) &&
+ nfs4_stateid_match_other(&data->args.stateid,
+ &lo->plh_stateid)) {
+ /* Do we need to delay before resending? */
+ if (!nfs4_stateid_is_newer(&lo->plh_stateid,
+ &data->args.stateid))
+ rpc_delay(task, HZ);
+ rpc_restart_call_prepare(task);
+ }
+ spin_unlock(&inode->i_lock);
+ break;
case -ENOTSUPP:
case -EOPNOTSUPP:
NFS_SERVER(inode)->caps &= ~NFS_CAP_LAYOUTSTATS;
- default:
- break;
}
dprintk("%s server returns %d\n", __func__, task->tk_status);
extern void nfs4_renewd_prepare_shutdown(struct nfs_server *);
extern void nfs4_kill_renewd(struct nfs_client *);
extern void nfs4_renew_state(struct work_struct *);
+extern void nfs4_set_lease_period(struct nfs_client *clp,
+ unsigned long lease,
+ unsigned long lastrenewed);
+
/* nfs4state.c */
struct rpc_cred *nfs4_get_clid_cred(struct nfs_client *clp);
goto error;
}
+ if (server->nfs_client == clp) {
+ error = -ELOOP;
+ goto error;
+ }
+
/*
* Query for the lease time on clientid setup or renewal
*
}
EXPORT_SYMBOL_GPL(nfs40_setup_sequence);
-static int nfs40_sequence_done(struct rpc_task *task,
- struct nfs4_sequence_res *res)
+static void nfs40_sequence_free_slot(struct nfs4_sequence_res *res)
{
struct nfs4_slot *slot = res->sr_slot;
struct nfs4_slot_table *tbl;
- if (slot == NULL)
- goto out;
-
tbl = slot->table;
spin_lock(&tbl->slot_tbl_lock);
if (!nfs41_wake_and_assign_slot(tbl, slot))
spin_unlock(&tbl->slot_tbl_lock);
res->sr_slot = NULL;
-out:
+}
+
+static int nfs40_sequence_done(struct rpc_task *task,
+ struct nfs4_sequence_res *res)
+{
+ if (res->sr_slot != NULL)
+ nfs40_sequence_free_slot(res);
return 1;
}
tbl = slot->table;
session = tbl->session;
+ /* Bump the slot sequence number */
+ if (slot->seq_done)
+ slot->seq_nr++;
+ slot->seq_done = 0;
+
spin_lock(&tbl->slot_tbl_lock);
/* Be nice to the server: try to ensure that the last transmitted
* value for highest_user_slotid <= target_highest_slotid
res->sr_slot = NULL;
if (send_new_highest_used_slotid)
nfs41_notify_server(session->clp);
+ if (waitqueue_active(&tbl->slot_waitq))
+ wake_up_all(&tbl->slot_waitq);
}
-int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
+static int nfs41_sequence_process(struct rpc_task *task,
+ struct nfs4_sequence_res *res)
{
struct nfs4_session *session;
struct nfs4_slot *slot = res->sr_slot;
switch (res->sr_status) {
case 0:
/* Update the slot's sequence and clientid lease timer */
- ++slot->seq_nr;
+ slot->seq_done = 1;
clp = session->clp;
do_renew_lease(clp, res->sr_timestamp);
/* Check sequence flags */
goto retry_nowait;
default:
/* Just update the slot sequence no. */
- ++slot->seq_nr;
+ slot->seq_done = 1;
}
out:
/* The session may be reset by one of the error handlers. */
dprintk("%s: Error %d free the slot \n", __func__, res->sr_status);
- nfs41_sequence_free_slot(res);
out_noaction:
return ret;
retry_nowait:
if (rpc_restart_call_prepare(task)) {
+ nfs41_sequence_free_slot(res);
task->tk_status = 0;
ret = 0;
}
rpc_delay(task, NFS4_POLL_RETRY_MAX);
return 0;
}
+
+int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
+{
+ if (!nfs41_sequence_process(task, res))
+ return 0;
+ if (res->sr_slot != NULL)
+ nfs41_sequence_free_slot(res);
+ return 1;
+
+}
EXPORT_SYMBOL_GPL(nfs41_sequence_done);
+static int nfs4_sequence_process(struct rpc_task *task, struct nfs4_sequence_res *res)
+{
+ if (res->sr_slot == NULL)
+ return 1;
+ if (res->sr_slot->table->session != NULL)
+ return nfs41_sequence_process(task, res);
+ return nfs40_sequence_done(task, res);
+}
+
+static void nfs4_sequence_free_slot(struct nfs4_sequence_res *res)
+{
+ if (res->sr_slot != NULL) {
+ if (res->sr_slot->table->session != NULL)
+ nfs41_sequence_free_slot(res);
+ else
+ nfs40_sequence_free_slot(res);
+ }
+}
+
int nfs4_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
{
if (res->sr_slot == NULL)
args, res, task);
}
+static int nfs4_sequence_process(struct rpc_task *task, struct nfs4_sequence_res *res)
+{
+ return nfs40_sequence_done(task, res);
+}
+
+static void nfs4_sequence_free_slot(struct nfs4_sequence_res *res)
+{
+ if (res->sr_slot != NULL)
+ nfs40_sequence_free_slot(res);
+}
+
int nfs4_sequence_done(struct rpc_task *task,
struct nfs4_sequence_res *res)
{
struct super_block *sb = p->dentry->d_sb;
nfs_free_seqid(p->o_arg.seqid);
+ nfs4_sequence_free_slot(&p->o_res.seq_res);
if (p->state != NULL)
nfs4_put_open_state(p->state);
nfs4_put_state_owner(p->owner);
static struct nfs4_state *
nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data)
{
+ struct nfs4_state *ret;
+
if (data->o_arg.claim == NFS4_OPEN_CLAIM_PREVIOUS)
- return _nfs4_opendata_reclaim_to_nfs4_state(data);
- return _nfs4_opendata_to_nfs4_state(data);
+ ret =_nfs4_opendata_reclaim_to_nfs4_state(data);
+ else
+ ret = _nfs4_opendata_to_nfs4_state(data);
+ nfs4_sequence_free_slot(&data->o_res.seq_res);
+ return ret;
}
static struct nfs_open_context *nfs4_state_find_open_context(struct nfs4_state *state)
data->rpc_status = task->tk_status;
- if (!nfs4_sequence_done(task, &data->o_res.seq_res))
+ if (!nfs4_sequence_process(task, &data->o_res.seq_res))
return;
if (task->tk_status == 0) {
err = _nfs4_do_fsinfo(server, fhandle, fsinfo);
trace_nfs4_fsinfo(server, fhandle, fsinfo->fattr, err);
if (err == 0) {
- struct nfs_client *clp = server->nfs_client;
-
- spin_lock(&clp->cl_lock);
- clp->cl_lease_time = fsinfo->lease_time * HZ;
- clp->cl_last_renewal = now;
- spin_unlock(&clp->cl_lock);
+ nfs4_set_lease_period(server->nfs_client,
+ fsinfo->lease_time * HZ,
+ now);
break;
}
err = nfs4_handle_exception(server, err, &exception);
status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
trace_nfs4_create_session(clp, status);
+ switch (status) {
+ case -NFS4ERR_STALE_CLIENTID:
+ case -NFS4ERR_DELAY:
+ case -ETIMEDOUT:
+ case -EACCES:
+ case -EAGAIN:
+ goto out;
+ };
+
+ clp->cl_seqid++;
if (!status) {
/* Verify the session's negotiated channel_attrs values */
status = nfs4_verify_channel_attrs(&args, &res);
/* Increment the clientid slot sequence id */
- if (clp->cl_seqid == res.seqid)
- clp->cl_seqid++;
if (status)
goto out;
nfs4_update_session(session, &res);
struct nfs4_layoutget *lgp = calldata;
dprintk("--> %s\n", __func__);
- nfs41_sequence_done(task, &lgp->res.seq_res);
+ nfs41_sequence_process(task, &lgp->res.seq_res);
dprintk("<-- %s\n", __func__);
}
/* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */
if (status == 0 && lgp->res.layoutp->len)
lseg = pnfs_layout_process(lgp);
+ nfs4_sequence_free_slot(&lgp->res.seq_res);
rpc_put_task(task);
dprintk("<-- %s status=%d\n", __func__, status);
if (status)
dprintk("--> %s\n", __func__);
- if (!nfs41_sequence_done(task, &lrp->res.seq_res))
+ if (!nfs41_sequence_process(task, &lrp->res.seq_res))
return;
server = NFS_SERVER(lrp->args.inode);
case -NFS4ERR_DELAY:
if (nfs4_async_handle_error(task, server, NULL, NULL) != -EAGAIN)
break;
+ nfs4_sequence_free_slot(&lrp->res.seq_res);
rpc_restart_call_prepare(task);
return;
}
dprintk("--> %s\n", __func__);
spin_lock(&lo->plh_inode->i_lock);
- pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range,
- be32_to_cpu(lrp->args.stateid.seqid));
- if (lrp->res.lrs_present && pnfs_layout_is_valid(lo))
+ if (lrp->res.lrs_present) {
+ pnfs_mark_matching_lsegs_invalid(lo, &freeme,
+ &lrp->args.range,
+ be32_to_cpu(lrp->args.stateid.seqid));
pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
+ } else
+ pnfs_mark_layout_stateid_invalid(lo, &freeme);
pnfs_clear_layoutreturn_waitbit(lo);
spin_unlock(&lo->plh_inode->i_lock);
+ nfs4_sequence_free_slot(&lrp->res.seq_res);
pnfs_free_lseg_list(&freeme);
pnfs_put_layout_hdr(lrp->args.layout);
nfs_iput_and_deactive(lrp->inode);
cancel_delayed_work_sync(&clp->cl_renewd);
}
+/**
+ * nfs4_set_lease_period - Sets the lease period on a nfs_client
+ *
+ * @clp: pointer to nfs_client
+ * @lease: new value for lease period
+ * @lastrenewed: time at which lease was last renewed
+ */
+void nfs4_set_lease_period(struct nfs_client *clp,
+ unsigned long lease,
+ unsigned long lastrenewed)
+{
+ spin_lock(&clp->cl_lock);
+ clp->cl_lease_time = lease;
+ clp->cl_last_renewal = lastrenewed;
+ spin_unlock(&clp->cl_lock);
+
+ /* Cap maximum reconnect timeout at 1/2 lease period */
+ rpc_cap_max_reconnect_timeout(clp->cl_rpcclient, lease >> 1);
+}
+
/*
* Local variables:
* c-basic-offset: 8
tbl->highest_used_slotid = NFS4_NO_SLOT;
spin_lock_init(&tbl->slot_tbl_lock);
rpc_init_priority_wait_queue(&tbl->slot_tbl_waitq, queue);
+ init_waitqueue_head(&tbl->slot_waitq);
init_completion(&tbl->complete);
}
return ERR_PTR(-E2BIG);
}
+static int nfs4_slot_get_seqid(struct nfs4_slot_table *tbl, u32 slotid,
+ u32 *seq_nr)
+ __must_hold(&tbl->slot_tbl_lock)
+{
+ struct nfs4_slot *slot;
+
+ slot = nfs4_lookup_slot(tbl, slotid);
+ if (IS_ERR(slot))
+ return PTR_ERR(slot);
+ *seq_nr = slot->seq_nr;
+ return 0;
+}
+
+/*
+ * nfs4_slot_seqid_in_use - test if a slot sequence id is still in use
+ *
+ * Given a slot table, slot id and sequence number, determine if the
+ * RPC call in question is still in flight. This function is mainly
+ * intended for use by the callback channel.
+ */
+static bool nfs4_slot_seqid_in_use(struct nfs4_slot_table *tbl,
+ u32 slotid, u32 seq_nr)
+{
+ u32 cur_seq;
+ bool ret = false;
+
+ spin_lock(&tbl->slot_tbl_lock);
+ if (nfs4_slot_get_seqid(tbl, slotid, &cur_seq) == 0 &&
+ cur_seq == seq_nr && test_bit(slotid, tbl->used_slots))
+ ret = true;
+ spin_unlock(&tbl->slot_tbl_lock);
+ return ret;
+}
+
+/*
+ * nfs4_slot_wait_on_seqid - wait until a slot sequence id is complete
+ *
+ * Given a slot table, slot id and sequence number, wait until the
+ * corresponding RPC call completes. This function is mainly
+ * intended for use by the callback channel.
+ */
+int nfs4_slot_wait_on_seqid(struct nfs4_slot_table *tbl,
+ u32 slotid, u32 seq_nr,
+ unsigned long timeout)
+{
+ if (wait_event_timeout(tbl->slot_waitq,
+ !nfs4_slot_seqid_in_use(tbl, slotid, seq_nr),
+ timeout) == 0)
+ return -ETIMEDOUT;
+ return 0;
+}
+
/*
* nfs4_alloc_slot - efficiently look for a free slot
*
unsigned long generation;
u32 slot_nr;
u32 seq_nr;
- unsigned int interrupted : 1;
+ unsigned int interrupted : 1,
+ seq_done : 1;
};
/* Sessions */
unsigned long used_slots[SLOT_TABLE_SZ]; /* used/unused bitmap */
spinlock_t slot_tbl_lock;
struct rpc_wait_queue slot_tbl_waitq; /* allocators may wait here */
+ wait_queue_head_t slot_waitq; /* Completion wait on slot */
u32 max_slots; /* # slots in table */
u32 max_slotid; /* Max allowed slotid value */
u32 highest_used_slotid; /* sent to server on each SEQ.
extern void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl);
extern struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl);
extern struct nfs4_slot *nfs4_lookup_slot(struct nfs4_slot_table *tbl, u32 slotid);
+extern int nfs4_slot_wait_on_seqid(struct nfs4_slot_table *tbl,
+ u32 slotid, u32 seq_nr,
+ unsigned long timeout);
extern bool nfs4_try_to_lock_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot);
extern void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot);
extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl);
{
int status;
struct nfs_fsinfo fsinfo;
+ unsigned long now;
if (!test_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state)) {
nfs4_schedule_state_renewal(clp);
return 0;
}
+ now = jiffies;
status = nfs4_proc_get_lease_time(clp, &fsinfo);
if (status == 0) {
- /* Update lease time and schedule renewal */
- spin_lock(&clp->cl_lock);
- clp->cl_lease_time = fsinfo.lease_time * HZ;
- clp->cl_last_renewal = jiffies;
- spin_unlock(&clp->cl_lock);
-
+ nfs4_set_lease_period(clp, fsinfo.lease_time * HZ, now);
nfs4_schedule_state_renewal(clp);
}
/* Matched by pnfs_get_layout_hdr in pnfs_layout_insert_lseg */
atomic_dec(&lo->plh_refcount);
if (list_empty(&lo->plh_segs)) {
- set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
+ if (atomic_read(&lo->plh_outstanding) == 0)
+ set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
clear_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
}
rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq);
pnfs_destroy_layouts_byclid(clp, false);
}
+static void
+pnfs_clear_layoutreturn_info(struct pnfs_layout_hdr *lo)
+{
+ lo->plh_return_iomode = 0;
+ lo->plh_return_seq = 0;
+ clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
+}
+
/* update lo->plh_stateid with new if is more recent */
void
pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
bool update_barrier)
{
u32 oldseq, newseq, new_barrier = 0;
- bool invalid = !pnfs_layout_is_valid(lo);
oldseq = be32_to_cpu(lo->plh_stateid.seqid);
newseq = be32_to_cpu(new->seqid);
- if (invalid || pnfs_seqid_is_newer(newseq, oldseq)) {
+
+ if (!pnfs_layout_is_valid(lo)) {
+ nfs4_stateid_copy(&lo->plh_stateid, new);
+ lo->plh_barrier = newseq;
+ pnfs_clear_layoutreturn_info(lo);
+ clear_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
+ return;
+ }
+ if (pnfs_seqid_is_newer(newseq, oldseq)) {
nfs4_stateid_copy(&lo->plh_stateid, new);
/*
* Because of wraparound, we want to keep the barrier
new_barrier = be32_to_cpu(new->seqid);
else if (new_barrier == 0)
return;
- if (invalid || pnfs_seqid_is_newer(new_barrier, lo->plh_barrier))
+ if (pnfs_seqid_is_newer(new_barrier, lo->plh_barrier))
lo->plh_barrier = new_barrier;
}
rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
}
-static void
-pnfs_clear_layoutreturn_info(struct pnfs_layout_hdr *lo)
-{
- lo->plh_return_iomode = 0;
- lo->plh_return_seq = 0;
- clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
-}
-
static bool
pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo,
nfs4_stateid *stateid,
enum pnfs_iomode *iomode)
{
+ /* Serialise LAYOUTGET/LAYOUTRETURN */
+ if (atomic_read(&lo->plh_outstanding) != 0)
+ return false;
if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
return false;
pnfs_get_layout_hdr(lo);
}
lookup_again:
+ nfs4_client_recover_expired_lease(clp);
first = false;
spin_lock(&ino->i_lock);
lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
*/
pnfs_mark_layout_stateid_invalid(lo, &free_me);
- nfs4_stateid_copy(&lo->plh_stateid, &res->stateid);
- lo->plh_barrier = be32_to_cpu(res->stateid.seqid);
+ pnfs_set_layout_stateid(lo, &res->stateid, true);
}
pnfs_get_lseg(lseg);
pnfs_layout_insert_lseg(lo, lseg, &free_me);
- if (!pnfs_layout_is_valid(lo)) {
- pnfs_clear_layoutreturn_info(lo);
- clear_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
- }
if (res->return_on_close)
data->args.fh = NFS_FH(inode);
data->args.inode = inode;
- nfs4_stateid_copy(&data->args.stateid, &hdr->plh_stateid);
status = ld->prepare_layoutstats(&data->args);
if (status)
goto out_free;
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (data) {
+ data->timeo = NFS_UNSPEC_TIMEO;
+ data->retrans = NFS_UNSPEC_RETRANS;
data->acregmin = NFS_DEF_ACREGMIN;
data->acregmax = NFS_DEF_ACREGMAX;
data->acdirmin = NFS_DEF_ACDIRMIN;
return rc;
}
+static int nfs_get_option_ul_bound(substring_t args[], unsigned long *option,
+ unsigned long l_bound, unsigned long u_bound)
+{
+ int ret;
+
+ ret = nfs_get_option_ul(args, option);
+ if (ret != 0)
+ return ret;
+ if (*option < l_bound || *option > u_bound)
+ return -ERANGE;
+ return 0;
+}
+
/*
* Error-check and convert a string of mount options from user space into
* a data structure. The whole mount string is processed; bad options are
mnt->bsize = option;
break;
case Opt_timeo:
- if (nfs_get_option_ul(args, &option) || option == 0)
+ if (nfs_get_option_ul_bound(args, &option, 1, INT_MAX))
goto out_invalid_value;
mnt->timeo = option;
break;
case Opt_retrans:
- if (nfs_get_option_ul(args, &option) || option == 0)
+ if (nfs_get_option_ul_bound(args, &option, 0, INT_MAX))
goto out_invalid_value;
mnt->retrans = option;
break;
return nfs_ok;
}
+static __be32
+nfsd4_free_lock_stateid(stateid_t *stateid, struct nfs4_stid *s)
+{
+ struct nfs4_ol_stateid *stp = openlockstateid(s);
+ __be32 ret;
+
+ mutex_lock(&stp->st_mutex);
+
+ ret = check_stateid_generation(stateid, &s->sc_stateid, 1);
+ if (ret)
+ goto out;
+
+ ret = nfserr_locks_held;
+ if (check_for_locks(stp->st_stid.sc_file,
+ lockowner(stp->st_stateowner)))
+ goto out;
+
+ release_lock_stateid(stp);
+ ret = nfs_ok;
+
+out:
+ mutex_unlock(&stp->st_mutex);
+ nfs4_put_stid(s);
+ return ret;
+}
+
__be32
nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_free_stateid *free_stateid)
stateid_t *stateid = &free_stateid->fr_stateid;
struct nfs4_stid *s;
struct nfs4_delegation *dp;
- struct nfs4_ol_stateid *stp;
struct nfs4_client *cl = cstate->session->se_client;
__be32 ret = nfserr_bad_stateid;
ret = nfserr_locks_held;
break;
case NFS4_LOCK_STID:
- ret = check_stateid_generation(stateid, &s->sc_stateid, 1);
- if (ret)
- break;
- stp = openlockstateid(s);
- ret = nfserr_locks_held;
- if (check_for_locks(stp->st_stid.sc_file,
- lockowner(stp->st_stateowner)))
- break;
- WARN_ON(!unhash_lock_stateid(stp));
+ atomic_inc(&s->sc_count);
spin_unlock(&cl->cl_lock);
- nfs4_put_stid(s);
- ret = nfs_ok;
+ ret = nfsd4_free_lock_stateid(stateid, s);
goto out;
case NFS4_REVOKED_DELEG_STID:
dp = delegstateid(s);
lookup_or_create_lock_state(struct nfsd4_compound_state *cstate,
struct nfs4_ol_stateid *ost,
struct nfsd4_lock *lock,
- struct nfs4_ol_stateid **lst, bool *new)
+ struct nfs4_ol_stateid **plst, bool *new)
{
__be32 status;
struct nfs4_file *fi = ost->st_stid.sc_file;
struct nfs4_client *cl = oo->oo_owner.so_client;
struct inode *inode = d_inode(cstate->current_fh.fh_dentry);
struct nfs4_lockowner *lo;
+ struct nfs4_ol_stateid *lst;
unsigned int strhashval;
+ bool hashed;
lo = find_lockowner_str(cl, &lock->lk_new_owner);
if (!lo) {
goto out;
}
- *lst = find_or_create_lock_stateid(lo, fi, inode, ost, new);
- if (*lst == NULL) {
+retry:
+ lst = find_or_create_lock_stateid(lo, fi, inode, ost, new);
+ if (lst == NULL) {
status = nfserr_jukebox;
goto out;
}
+
+ mutex_lock(&lst->st_mutex);
+
+ /* See if it's still hashed to avoid race with FREE_STATEID */
+ spin_lock(&cl->cl_lock);
+ hashed = !list_empty(&lst->st_perfile);
+ spin_unlock(&cl->cl_lock);
+
+ if (!hashed) {
+ mutex_unlock(&lst->st_mutex);
+ nfs4_put_stid(&lst->st_stid);
+ goto retry;
+ }
status = nfs_ok;
+ *plst = lst;
out:
nfs4_put_stateowner(&lo->lo_owner);
return status;
goto out;
status = lookup_or_create_lock_state(cstate, open_stp, lock,
&lock_stp, &new);
- if (status == nfs_ok)
- mutex_lock(&lock_stp->st_mutex);
} else {
status = nfs4_preprocess_seqid_op(cstate,
lock->lk_old_lock_seqid,
if (IS_ERR(dchild))
return nfserrno(host_err);
err = fh_compose(resfhp, fhp->fh_export, dchild, fhp);
- if (err) {
- dput(dchild);
+ /*
+ * We unconditionally drop our ref to dchild as fh_compose will have
+ * already grabbed its own ref for it.
+ */
+ dput(dchild);
+ if (err)
return err;
- }
return nfsd_create_locked(rqstp, fhp, fname, flen, iap, type,
rdev, resfhp);
}
pr_debug("%s: group=%p event=%p\n", __func__, group, event);
- wait_event(group->fanotify_data.access_waitq, event->response ||
- atomic_read(&group->fanotify_data.bypass_perm));
-
- if (!event->response) { /* bypass_perm set */
- /*
- * Event was canceled because group is being destroyed. Remove
- * it from group's event list because we are responsible for
- * freeing the permission event.
- */
- fsnotify_remove_event(group, &event->fae.fse);
- return 0;
- }
+ wait_event(group->fanotify_data.access_waitq, event->response);
/* userspace responded, convert to something usable */
switch (event->response) {
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
struct fanotify_perm_event_info *event, *next;
+ struct fsnotify_event *fsn_event;
/*
- * There may be still new events arriving in the notification queue
- * but since userspace cannot use fanotify fd anymore, no event can
- * enter or leave access_list by now.
+ * Stop new events from arriving in the notification queue. since
+ * userspace cannot use fanotify fd anymore, no event can enter or
+ * leave access_list by now either.
*/
- spin_lock(&group->fanotify_data.access_lock);
-
- atomic_inc(&group->fanotify_data.bypass_perm);
+ fsnotify_group_stop_queueing(group);
+ /*
+ * Process all permission events on access_list and notification queue
+ * and simulate reply from userspace.
+ */
+ spin_lock(&group->fanotify_data.access_lock);
list_for_each_entry_safe(event, next, &group->fanotify_data.access_list,
fae.fse.list) {
pr_debug("%s: found group=%p event=%p\n", __func__, group,
spin_unlock(&group->fanotify_data.access_lock);
/*
- * Since bypass_perm is set, newly queued events will not wait for
- * access response. Wake up the already sleeping ones now.
- * synchronize_srcu() in fsnotify_destroy_group() will wait for all
- * processes sleeping in fanotify_handle_event() waiting for access
- * response and thus also for all permission events to be freed.
+ * Destroy all non-permission events. For permission events just
+ * dequeue them and set the response. They will be freed once the
+ * response is consumed and fanotify_get_response() returns.
*/
+ mutex_lock(&group->notification_mutex);
+ while (!fsnotify_notify_queue_is_empty(group)) {
+ fsn_event = fsnotify_remove_first_event(group);
+ if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS))
+ fsnotify_destroy_event(group, fsn_event);
+ else
+ FANOTIFY_PE(fsn_event)->response = FAN_ALLOW;
+ }
+ mutex_unlock(&group->notification_mutex);
+
+ /* Response for all permission events it set, wakeup waiters */
wake_up(&group->fanotify_data.access_waitq);
#endif
spin_lock_init(&group->fanotify_data.access_lock);
init_waitqueue_head(&group->fanotify_data.access_waitq);
INIT_LIST_HEAD(&group->fanotify_data.access_list);
- atomic_set(&group->fanotify_data.bypass_perm, 0);
#endif
switch (flags & FAN_ALL_CLASS_BITS) {
case FAN_CLASS_NOTIF:
kfree(group);
}
+/*
+ * Stop queueing new events for this group. Once this function returns
+ * fsnotify_add_event() will not add any new events to the group's queue.
+ */
+void fsnotify_group_stop_queueing(struct fsnotify_group *group)
+{
+ mutex_lock(&group->notification_mutex);
+ group->shutdown = true;
+ mutex_unlock(&group->notification_mutex);
+}
+
/*
* Trying to get rid of a group. Remove all marks, flush all events and release
* the group reference.
*/
void fsnotify_destroy_group(struct fsnotify_group *group)
{
+ /*
+ * Stop queueing new events. The code below is careful enough to not
+ * require this but fanotify needs to stop queuing events even before
+ * fsnotify_destroy_group() is called and this makes the other callers
+ * of fsnotify_destroy_group() to see the same behavior.
+ */
+ fsnotify_group_stop_queueing(group);
+
/* clear all inode marks for this group, attach them to destroy_list */
fsnotify_detach_group_marks(group);
* Add an event to the group notification queue. The group can later pull this
* event off the queue to deal with. The function returns 0 if the event was
* added to the queue, 1 if the event was merged with some other queued event,
- * 2 if the queue of events has overflown.
+ * 2 if the event was not queued - either the queue of events has overflown
+ * or the group is shutting down.
*/
int fsnotify_add_event(struct fsnotify_group *group,
struct fsnotify_event *event,
mutex_lock(&group->notification_mutex);
+ if (group->shutdown) {
+ mutex_unlock(&group->notification_mutex);
+ return 2;
+ }
+
if (group->q_len >= group->max_events) {
ret = 2;
/* Queue overflow event only if it isn't already queued */
return ret;
}
-/*
- * Remove @event from group's notification queue. It is the responsibility of
- * the caller to destroy the event.
- */
-void fsnotify_remove_event(struct fsnotify_group *group,
- struct fsnotify_event *event)
-{
- mutex_lock(&group->notification_mutex);
- if (!list_empty(&event->list)) {
- list_del_init(&event->list);
- group->q_len--;
- }
- mutex_unlock(&group->notification_mutex);
-}
-
/*
* Remove and return the first event from the notification list. It is the
* responsibility of the caller to destroy the obtained event
}
static int ocfs2_replay_truncate_records(struct ocfs2_super *osb,
- handle_t *handle,
struct inode *data_alloc_inode,
struct buffer_head *data_alloc_bh)
{
struct ocfs2_truncate_log *tl;
struct inode *tl_inode = osb->osb_tl_inode;
struct buffer_head *tl_bh = osb->osb_tl_bh;
+ handle_t *handle;
di = (struct ocfs2_dinode *) tl_bh->b_data;
tl = &di->id2.i_dealloc;
i = le16_to_cpu(tl->tl_used) - 1;
while (i >= 0) {
+ handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
+ if (IS_ERR(handle)) {
+ status = PTR_ERR(handle);
+ mlog_errno(status);
+ goto bail;
+ }
+
/* Caller has given us at least enough credits to
* update the truncate log dinode */
status = ocfs2_journal_access_di(handle, INODE_CACHE(tl_inode), tl_bh,
}
}
- status = ocfs2_extend_trans(handle,
- OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
- if (status < 0) {
- mlog_errno(status);
- goto bail;
- }
+ ocfs2_commit_trans(osb, handle);
i--;
}
{
int status;
unsigned int num_to_flush;
- handle_t *handle;
struct inode *tl_inode = osb->osb_tl_inode;
struct inode *data_alloc_inode = NULL;
struct buffer_head *tl_bh = osb->osb_tl_bh;
goto out_mutex;
}
- handle = ocfs2_start_trans(osb, OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC);
- if (IS_ERR(handle)) {
- status = PTR_ERR(handle);
- mlog_errno(status);
- goto out_unlock;
- }
-
- status = ocfs2_replay_truncate_records(osb, handle, data_alloc_inode,
+ status = ocfs2_replay_truncate_records(osb, data_alloc_inode,
data_alloc_bh);
if (status < 0)
mlog_errno(status);
- ocfs2_commit_trans(osb, handle);
-
-out_unlock:
brelse(data_alloc_bh);
ocfs2_inode_unlock(data_alloc_inode, 1);
goto out_mutex;
}
- handle = ocfs2_start_trans(osb, OCFS2_SUBALLOC_FREE);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- mlog_errno(ret);
- goto out_unlock;
- }
-
while (head) {
if (head->free_bg)
bg_blkno = head->free_bg;
else
bg_blkno = ocfs2_which_suballoc_group(head->free_blk,
head->free_bit);
+ handle = ocfs2_start_trans(osb, OCFS2_SUBALLOC_FREE);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ mlog_errno(ret);
+ goto out_unlock;
+ }
+
trace_ocfs2_free_cached_blocks(
(unsigned long long)head->free_blk, head->free_bit);
ret = ocfs2_free_suballoc_bits(handle, inode, di_bh,
head->free_bit, bg_blkno, 1);
- if (ret) {
+ if (ret)
mlog_errno(ret);
- goto out_journal;
- }
- ret = ocfs2_extend_trans(handle, OCFS2_SUBALLOC_FREE);
- if (ret) {
- mlog_errno(ret);
- goto out_journal;
- }
+ ocfs2_commit_trans(osb, handle);
tmp = head;
head = head->free_next;
kfree(tmp);
}
-out_journal:
- ocfs2_commit_trans(osb, handle);
-
out_unlock:
ocfs2_inode_unlock(inode, 1);
brelse(di_bh);
* version here in tcp_internal.h should not need to be bumped for
* filesystem locking changes.
*
- * New in version 12
- * - Negotiate hb timeout when storage is down.
- *
* New in version 11
* - Negotiation of filesystem locking in the dlm join.
*
* - full 64 bit i_size in the metadata lock lvbs
* - introduction of "rw" lock and pushing meta/data locking down
*/
-#define O2NET_PROTOCOL_VERSION 12ULL
+#define O2NET_PROTOCOL_VERSION 11ULL
struct o2net_handshake {
__be64 protocol_version;
__be64 connector_id;
struct dlm_lock *lock, int flags, int type)
{
enum dlm_status status;
- u8 old_owner = res->owner;
mlog(0, "type=%d, convert_type=%d, busy=%d\n", lock->ml.type,
lock->ml.convert_type, res->state & DLM_LOCK_RES_IN_PROGRESS);
spin_lock(&res->spinlock);
res->state &= ~DLM_LOCK_RES_IN_PROGRESS;
- lock->convert_pending = 0;
/* if it failed, move it back to granted queue.
* if master returns DLM_NORMAL and then down before sending ast,
* it may have already been moved to granted queue, reset to
if (status != DLM_NOTQUEUED)
dlm_error(status);
dlm_revert_pending_convert(res, lock);
- } else if ((res->state & DLM_LOCK_RES_RECOVERING) ||
- (old_owner != res->owner)) {
- mlog(0, "res %.*s is in recovering or has been recovered.\n",
- res->lockname.len, res->lockname.name);
+ } else if (!lock->convert_pending) {
+ mlog(0, "%s: res %.*s, owner died and lock has been moved back "
+ "to granted list, retry convert.\n",
+ dlm->name, res->lockname.len, res->lockname.name);
status = DLM_RECOVERING;
}
+
+ lock->convert_pending = 0;
bail:
spin_unlock(&res->spinlock);
u64 start, u64 len)
{
int ret = 0;
- u64 tmpend, end = start + len;
+ u64 tmpend = 0;
+ u64 end = start + len;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
unsigned int csize = osb->s_clustersize;
handle_t *handle;
}
/*
- * We want to get the byte offset of the end of the 1st cluster.
+ * If start is on a cluster boundary and end is somewhere in another
+ * cluster, we have not COWed the cluster starting at start, unless
+ * end is also within the same cluster. So, in this case, we skip this
+ * first call to ocfs2_zero_range_for_truncate() truncate and move on
+ * to the next one.
*/
- tmpend = (u64)osb->s_clustersize + (start & ~(osb->s_clustersize - 1));
- if (tmpend > end)
- tmpend = end;
+ if ((start & (csize - 1)) != 0) {
+ /*
+ * We want to get the byte offset of the end of the 1st
+ * cluster.
+ */
+ tmpend = (u64)osb->s_clustersize +
+ (start & ~(osb->s_clustersize - 1));
+ if (tmpend > end)
+ tmpend = end;
- trace_ocfs2_zero_partial_clusters_range1((unsigned long long)start,
- (unsigned long long)tmpend);
+ trace_ocfs2_zero_partial_clusters_range1(
+ (unsigned long long)start,
+ (unsigned long long)tmpend);
- ret = ocfs2_zero_range_for_truncate(inode, handle, start, tmpend);
- if (ret)
- mlog_errno(ret);
+ ret = ocfs2_zero_range_for_truncate(inode, handle, start,
+ tmpend);
+ if (ret)
+ mlog_errno(ret);
+ }
if (tmpend < end) {
/*
inode_unlock((*ac)->ac_inode);
ret = ocfs2_try_to_free_truncate_log(osb, bits_wanted);
- if (ret == 1)
+ if (ret == 1) {
+ iput((*ac)->ac_inode);
+ (*ac)->ac_inode = NULL;
goto retry;
+ }
if (ret < 0)
mlog_errno(ret);
inode_lock((*ac)->ac_inode);
- ocfs2_inode_lock((*ac)->ac_inode, NULL, 1);
+ ret = ocfs2_inode_lock((*ac)->ac_inode, NULL, 1);
+ if (ret < 0) {
+ mlog_errno(ret);
+ inode_unlock((*ac)->ac_inode);
+ iput((*ac)->ac_inode);
+ (*ac)->ac_inode = NULL;
+ goto bail;
+ }
}
if (status < 0) {
if (status != -ENOSPC)
}
for (name = buf; name < (buf + list_size); name += strlen(name) + 1) {
+ if (ovl_is_private_xattr(name))
+ continue;
retry:
size = vfs_getxattr(old, name, value, value_size);
if (size == -ERANGE)
#include <linux/xattr.h>
#include <linux/security.h>
#include <linux/cred.h>
+#include <linux/posix_acl.h>
+#include <linux/posix_acl_xattr.h>
#include "overlayfs.h"
void ovl_cleanup(struct inode *wdir, struct dentry *wdentry)
struct dentry *newdentry;
int err;
+ if (!hardlink && !IS_POSIXACL(udir))
+ stat->mode &= ~current_umask();
+
inode_lock_nested(udir, I_MUTEX_PARENT);
newdentry = lookup_one_len(dentry->d_name.name, upperdir,
dentry->d_name.len);
return ret;
}
+static int ovl_set_upper_acl(struct dentry *upperdentry, const char *name,
+ const struct posix_acl *acl)
+{
+ void *buffer;
+ size_t size;
+ int err;
+
+ if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !acl)
+ return 0;
+
+ size = posix_acl_to_xattr(NULL, acl, NULL, 0);
+ buffer = kmalloc(size, GFP_KERNEL);
+ if (!buffer)
+ return -ENOMEM;
+
+ size = posix_acl_to_xattr(&init_user_ns, acl, buffer, size);
+ err = size;
+ if (err < 0)
+ goto out_free;
+
+ err = vfs_setxattr(upperdentry, name, buffer, size, XATTR_CREATE);
+out_free:
+ kfree(buffer);
+ return err;
+}
+
static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
struct kstat *stat, const char *link,
struct dentry *hardlink)
struct dentry *upper;
struct dentry *newdentry;
int err;
+ struct posix_acl *acl, *default_acl;
if (WARN_ON(!workdir))
return -EROFS;
+ if (!hardlink) {
+ err = posix_acl_create(dentry->d_parent->d_inode,
+ &stat->mode, &default_acl, &acl);
+ if (err)
+ return err;
+ }
+
err = ovl_lock_rename_workdir(workdir, upperdir);
if (err)
goto out;
if (err)
goto out_cleanup;
}
+ if (!hardlink) {
+ err = ovl_set_upper_acl(newdentry, XATTR_NAME_POSIX_ACL_ACCESS,
+ acl);
+ if (err)
+ goto out_cleanup;
+
+ err = ovl_set_upper_acl(newdentry, XATTR_NAME_POSIX_ACL_DEFAULT,
+ default_acl);
+ if (err)
+ goto out_cleanup;
+ }
if (!hardlink && S_ISDIR(stat->mode)) {
err = ovl_set_opaque(newdentry);
out_unlock:
unlock_rename(workdir, upperdir);
out:
+ if (!hardlink) {
+ posix_acl_release(acl);
+ posix_acl_release(default_acl);
+ }
return err;
out_cleanup:
.permission = ovl_permission,
.getattr = ovl_dir_getattr,
.setxattr = generic_setxattr,
- .getxattr = ovl_getxattr,
+ .getxattr = generic_getxattr,
.listxattr = ovl_listxattr,
- .removexattr = ovl_removexattr,
+ .removexattr = generic_removexattr,
.get_acl = ovl_get_acl,
.update_time = ovl_update_time,
};
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/xattr.h>
+#include <linux/posix_acl.h>
#include "overlayfs.h"
static int ovl_copy_up_truncate(struct dentry *dentry)
return err;
}
-static bool ovl_is_private_xattr(const char *name)
+bool ovl_is_private_xattr(const char *name)
{
-#define OVL_XATTR_PRE_NAME OVL_XATTR_PREFIX "."
- return strncmp(name, OVL_XATTR_PRE_NAME,
- sizeof(OVL_XATTR_PRE_NAME) - 1) == 0;
+ return strncmp(name, OVL_XATTR_PREFIX,
+ sizeof(OVL_XATTR_PREFIX) - 1) == 0;
}
-int ovl_setxattr(struct dentry *dentry, struct inode *inode,
- const char *name, const void *value,
- size_t size, int flags)
+int ovl_xattr_set(struct dentry *dentry, const char *name, const void *value,
+ size_t size, int flags)
{
int err;
- struct dentry *upperdentry;
+ struct path realpath;
+ enum ovl_path_type type = ovl_path_real(dentry, &realpath);
const struct cred *old_cred;
err = ovl_want_write(dentry);
if (err)
goto out;
+ if (!value && !OVL_TYPE_UPPER(type)) {
+ err = vfs_getxattr(realpath.dentry, name, NULL, 0);
+ if (err < 0)
+ goto out_drop_write;
+ }
+
err = ovl_copy_up(dentry);
if (err)
goto out_drop_write;
- upperdentry = ovl_dentry_upper(dentry);
+ if (!OVL_TYPE_UPPER(type))
+ ovl_path_upper(dentry, &realpath);
+
old_cred = ovl_override_creds(dentry->d_sb);
- err = vfs_setxattr(upperdentry, name, value, size, flags);
+ if (value)
+ err = vfs_setxattr(realpath.dentry, name, value, size, flags);
+ else {
+ WARN_ON(flags != XATTR_REPLACE);
+ err = vfs_removexattr(realpath.dentry, name);
+ }
revert_creds(old_cred);
out_drop_write:
return err;
}
-ssize_t ovl_getxattr(struct dentry *dentry, struct inode *inode,
- const char *name, void *value, size_t size)
+int ovl_xattr_get(struct dentry *dentry, const char *name,
+ void *value, size_t size)
{
struct dentry *realdentry = ovl_dentry_real(dentry);
ssize_t res;
const struct cred *old_cred;
- if (ovl_is_private_xattr(name))
- return -ENODATA;
-
old_cred = ovl_override_creds(dentry->d_sb);
res = vfs_getxattr(realdentry, name, value, size);
revert_creds(old_cred);
{
struct dentry *realdentry = ovl_dentry_real(dentry);
ssize_t res;
- int off;
+ size_t len;
+ char *s;
const struct cred *old_cred;
old_cred = ovl_override_creds(dentry->d_sb);
return res;
/* filter out private xattrs */
- for (off = 0; off < res;) {
- char *s = list + off;
- size_t slen = strlen(s) + 1;
+ for (s = list, len = res; len;) {
+ size_t slen = strnlen(s, len) + 1;
- BUG_ON(off + slen > res);
+ /* underlying fs providing us with an broken xattr list? */
+ if (WARN_ON(slen > len))
+ return -EIO;
+ len -= slen;
if (ovl_is_private_xattr(s)) {
res -= slen;
- memmove(s, s + slen, res - off);
+ memmove(s, s + slen, len);
} else {
- off += slen;
+ s += slen;
}
}
return res;
}
-int ovl_removexattr(struct dentry *dentry, const char *name)
-{
- int err;
- struct path realpath;
- enum ovl_path_type type = ovl_path_real(dentry, &realpath);
- const struct cred *old_cred;
-
- err = ovl_want_write(dentry);
- if (err)
- goto out;
-
- err = -ENODATA;
- if (ovl_is_private_xattr(name))
- goto out_drop_write;
-
- if (!OVL_TYPE_UPPER(type)) {
- err = vfs_getxattr(realpath.dentry, name, NULL, 0);
- if (err < 0)
- goto out_drop_write;
-
- err = ovl_copy_up(dentry);
- if (err)
- goto out_drop_write;
-
- ovl_path_upper(dentry, &realpath);
- }
-
- old_cred = ovl_override_creds(dentry->d_sb);
- err = vfs_removexattr(realpath.dentry, name);
- revert_creds(old_cred);
-out_drop_write:
- ovl_drop_write(dentry);
-out:
- return err;
-}
-
struct posix_acl *ovl_get_acl(struct inode *inode, int type)
{
struct inode *realinode = ovl_inode_real(inode, NULL);
const struct cred *old_cred;
struct posix_acl *acl;
- if (!IS_POSIXACL(realinode))
+ if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode))
return NULL;
if (!realinode->i_op->get_acl)
return NULL;
old_cred = ovl_override_creds(inode->i_sb);
- acl = realinode->i_op->get_acl(realinode, type);
+ acl = get_acl(realinode, type);
revert_creds(old_cred);
return acl;
.permission = ovl_permission,
.getattr = ovl_getattr,
.setxattr = generic_setxattr,
- .getxattr = ovl_getxattr,
+ .getxattr = generic_getxattr,
.listxattr = ovl_listxattr,
- .removexattr = ovl_removexattr,
+ .removexattr = generic_removexattr,
.get_acl = ovl_get_acl,
.update_time = ovl_update_time,
};
.readlink = ovl_readlink,
.getattr = ovl_getattr,
.setxattr = generic_setxattr,
- .getxattr = ovl_getxattr,
+ .getxattr = generic_getxattr,
.listxattr = ovl_listxattr,
- .removexattr = ovl_removexattr,
+ .removexattr = generic_removexattr,
.update_time = ovl_update_time,
};
inode->i_ino = get_next_ino();
inode->i_mode = mode;
inode->i_flags |= S_NOCMTIME;
+#ifdef CONFIG_FS_POSIX_ACL
+ inode->i_acl = inode->i_default_acl = ACL_DONT_CACHE;
+#endif
mode &= S_IFMT;
switch (mode) {
(OVL_TYPE_MERGE(type) || !OVL_TYPE_UPPER(type))
-#define OVL_XATTR_PREFIX XATTR_TRUSTED_PREFIX "overlay"
-#define OVL_XATTR_OPAQUE OVL_XATTR_PREFIX ".opaque"
+#define OVL_XATTR_PREFIX XATTR_TRUSTED_PREFIX "overlay."
+#define OVL_XATTR_OPAQUE OVL_XATTR_PREFIX "opaque"
#define OVL_ISUPPER_MASK 1UL
void ovl_cleanup_whiteouts(struct dentry *upper, struct list_head *list);
void ovl_cache_free(struct list_head *list);
int ovl_check_d_type_supported(struct path *realpath);
+void ovl_workdir_cleanup(struct inode *dir, struct vfsmount *mnt,
+ struct dentry *dentry, int level);
/* inode.c */
int ovl_setattr(struct dentry *dentry, struct iattr *attr);
int ovl_permission(struct inode *inode, int mask);
-int ovl_setxattr(struct dentry *dentry, struct inode *inode,
- const char *name, const void *value,
- size_t size, int flags);
-ssize_t ovl_getxattr(struct dentry *dentry, struct inode *inode,
- const char *name, void *value, size_t size);
+int ovl_xattr_set(struct dentry *dentry, const char *name, const void *value,
+ size_t size, int flags);
+int ovl_xattr_get(struct dentry *dentry, const char *name,
+ void *value, size_t size);
ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size);
-int ovl_removexattr(struct dentry *dentry, const char *name);
struct posix_acl *ovl_get_acl(struct inode *inode, int type);
int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags);
int ovl_update_time(struct inode *inode, struct timespec *ts, int flags);
+bool ovl_is_private_xattr(const char *name);
struct inode *ovl_new_inode(struct super_block *sb, umode_t mode);
struct inode *ovl_get_inode(struct super_block *sb, struct inode *realinode);
err = rdd->err;
} while (!err && rdd->count);
- if (!err && rdd->first_maybe_whiteout)
+ if (!err && rdd->first_maybe_whiteout && rdd->dentry)
err = ovl_check_whiteouts(realpath->dentry, rdd);
fput(realfile);
return rdd.d_type_supported;
}
+
+static void ovl_workdir_cleanup_recurse(struct path *path, int level)
+{
+ int err;
+ struct inode *dir = path->dentry->d_inode;
+ LIST_HEAD(list);
+ struct ovl_cache_entry *p;
+ struct ovl_readdir_data rdd = {
+ .ctx.actor = ovl_fill_merge,
+ .dentry = NULL,
+ .list = &list,
+ .root = RB_ROOT,
+ .is_lowest = false,
+ };
+
+ err = ovl_dir_read(path, &rdd);
+ if (err)
+ goto out;
+
+ inode_lock_nested(dir, I_MUTEX_PARENT);
+ list_for_each_entry(p, &list, l_node) {
+ struct dentry *dentry;
+
+ if (p->name[0] == '.') {
+ if (p->len == 1)
+ continue;
+ if (p->len == 2 && p->name[1] == '.')
+ continue;
+ }
+ dentry = lookup_one_len(p->name, path->dentry, p->len);
+ if (IS_ERR(dentry))
+ continue;
+ if (dentry->d_inode)
+ ovl_workdir_cleanup(dir, path->mnt, dentry, level);
+ dput(dentry);
+ }
+ inode_unlock(dir);
+out:
+ ovl_cache_free(&list);
+}
+
+void ovl_workdir_cleanup(struct inode *dir, struct vfsmount *mnt,
+ struct dentry *dentry, int level)
+{
+ int err;
+
+ if (!d_is_dir(dentry) || level > 1) {
+ ovl_cleanup(dir, dentry);
+ return;
+ }
+
+ err = ovl_do_rmdir(dir, dentry);
+ if (err) {
+ struct path path = { .mnt = mnt, .dentry = dentry };
+
+ inode_unlock(dir);
+ ovl_workdir_cleanup_recurse(&path, level + 1);
+ inode_lock_nested(dir, I_MUTEX_PARENT);
+ ovl_cleanup(dir, dentry);
+ }
+}
struct kstat stat = {
.mode = S_IFDIR | 0,
};
+ struct iattr attr = {
+ .ia_valid = ATTR_MODE,
+ .ia_mode = stat.mode,
+ };
if (work->d_inode) {
err = -EEXIST;
goto out_dput;
retried = true;
- ovl_cleanup(dir, work);
+ ovl_workdir_cleanup(dir, mnt, work, 0);
dput(work);
goto retry;
}
err = ovl_create_real(dir, work, &stat, NULL, NULL, true);
if (err)
goto out_dput;
+
+ err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_DEFAULT);
+ if (err && err != -ENODATA && err != -EOPNOTSUPP)
+ goto out_dput;
+
+ err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_ACCESS);
+ if (err && err != -ENODATA && err != -EOPNOTSUPP)
+ goto out_dput;
+
+ /* Clear any inherited mode bits */
+ inode_lock(work->d_inode);
+ err = notify_change(work, &attr, NULL);
+ inode_unlock(work->d_inode);
+ if (err)
+ goto out_dput;
}
out_unlock:
inode_unlock(dir);
return ctr;
}
-static int ovl_posix_acl_xattr_set(const struct xattr_handler *handler,
- struct dentry *dentry, struct inode *inode,
- const char *name, const void *value,
- size_t size, int flags)
+static int __maybe_unused
+ovl_posix_acl_xattr_get(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, void *buffer, size_t size)
+{
+ return ovl_xattr_get(dentry, handler->name, buffer, size);
+}
+
+static int __maybe_unused
+ovl_posix_acl_xattr_set(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
{
struct dentry *workdir = ovl_workdir(dentry);
struct inode *realinode = ovl_inode_real(inode, NULL);
posix_acl_release(acl);
- return ovl_setxattr(dentry, inode, handler->name, value, size, flags);
+ err = ovl_xattr_set(dentry, handler->name, value, size, flags);
+ if (!err)
+ ovl_copyattr(ovl_inode_real(inode, NULL), inode);
+
+ return err;
out_acl_release:
posix_acl_release(acl);
return err;
}
-static int ovl_other_xattr_set(const struct xattr_handler *handler,
- struct dentry *dentry, struct inode *inode,
- const char *name, const void *value,
- size_t size, int flags)
+static int ovl_own_xattr_get(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, void *buffer, size_t size)
{
- return ovl_setxattr(dentry, inode, name, value, size, flags);
+ return -EPERM;
}
static int ovl_own_xattr_set(const struct xattr_handler *handler,
return -EPERM;
}
-static const struct xattr_handler ovl_posix_acl_access_xattr_handler = {
+static int ovl_other_xattr_get(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, void *buffer, size_t size)
+{
+ return ovl_xattr_get(dentry, name, buffer, size);
+}
+
+static int ovl_other_xattr_set(const struct xattr_handler *handler,
+ struct dentry *dentry, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
+{
+ return ovl_xattr_set(dentry, name, value, size, flags);
+}
+
+static const struct xattr_handler __maybe_unused
+ovl_posix_acl_access_xattr_handler = {
.name = XATTR_NAME_POSIX_ACL_ACCESS,
.flags = ACL_TYPE_ACCESS,
+ .get = ovl_posix_acl_xattr_get,
.set = ovl_posix_acl_xattr_set,
};
-static const struct xattr_handler ovl_posix_acl_default_xattr_handler = {
+static const struct xattr_handler __maybe_unused
+ovl_posix_acl_default_xattr_handler = {
.name = XATTR_NAME_POSIX_ACL_DEFAULT,
.flags = ACL_TYPE_DEFAULT,
+ .get = ovl_posix_acl_xattr_get,
.set = ovl_posix_acl_xattr_set,
};
static const struct xattr_handler ovl_own_xattr_handler = {
.prefix = OVL_XATTR_PREFIX,
+ .get = ovl_own_xattr_get,
.set = ovl_own_xattr_set,
};
static const struct xattr_handler ovl_other_xattr_handler = {
.prefix = "", /* catch all */
+ .get = ovl_other_xattr_get,
.set = ovl_other_xattr_set,
};
static const struct xattr_handler *ovl_xattr_handlers[] = {
+#ifdef CONFIG_FS_POSIX_ACL
&ovl_posix_acl_access_xattr_handler,
&ovl_posix_acl_default_xattr_handler,
+#endif
&ovl_own_xattr_handler,
&ovl_other_xattr_handler,
NULL
};
-static const struct xattr_handler *ovl_xattr_noacl_handlers[] = {
- &ovl_own_xattr_handler,
- &ovl_other_xattr_handler,
- NULL,
-};
-
static int ovl_fill_super(struct super_block *sb, void *data, int silent)
{
struct path upperpath = { NULL, NULL };
err = -EINVAL;
stacklen = ovl_split_lowerdirs(lowertmp);
if (stacklen > OVL_MAX_STACK) {
- pr_err("overlayfs: too many lower directries, limit is %d\n",
+ pr_err("overlayfs: too many lower directories, limit is %d\n",
OVL_MAX_STACK);
goto out_free_lowertmp;
} else if (!ufs->config.upperdir && stacklen == 1) {
sb->s_magic = OVERLAYFS_SUPER_MAGIC;
sb->s_op = &ovl_super_operations;
- if (IS_ENABLED(CONFIG_FS_POSIX_ACL))
- sb->s_xattr = ovl_xattr_handlers;
- else
- sb->s_xattr = ovl_xattr_noacl_handlers;
+ sb->s_xattr = ovl_xattr_handlers;
sb->s_root = root_dentry;
sb->s_fs_info = ufs;
sb->s_flags |= MS_POSIXACL;
struct page *page = buf->page;
if (page_count(page) == 1) {
- if (memcg_kmem_enabled()) {
+ if (memcg_kmem_enabled())
memcg_kmem_uncharge(page, 0);
- __ClearPageKmemcg(page);
- }
__SetPageLocked(page);
return 0;
}
static int proc_exe_link(struct dentry *dentry, struct path *exe_path)
{
struct task_struct *task;
- struct mm_struct *mm;
struct file *exe_file;
task = get_proc_task(d_inode(dentry));
if (!task)
return -ENOENT;
- mm = get_task_mm(task);
+ exe_file = get_task_exe_file(task);
put_task_struct(task);
- if (!mm)
- return -ENOENT;
- exe_file = get_mm_exe_file(mm);
- mmput(mm);
if (exe_file) {
*exe_path = exe_file->f_path;
path_get(&exe_file->f_path);
static ssize_t
read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
{
+ char *buf = file->private_data;
ssize_t acc = 0;
size_t size, tsz;
size_t elf_buflen;
if (clear_user(buffer, tsz))
return -EFAULT;
} else if (is_vmalloc_or_module_addr((void *)start)) {
- char * elf_buf;
-
- elf_buf = kzalloc(tsz, GFP_KERNEL);
- if (!elf_buf)
- return -ENOMEM;
- vread(elf_buf, (char *)start, tsz);
+ vread(buf, (char *)start, tsz);
/* we have to zero-fill user buffer even if no read */
- if (copy_to_user(buffer, elf_buf, tsz)) {
- kfree(elf_buf);
+ if (copy_to_user(buffer, buf, tsz))
return -EFAULT;
- }
- kfree(elf_buf);
} else {
if (kern_addr_valid(start)) {
unsigned long n;
- n = copy_to_user(buffer, (char *)start, tsz);
+ /*
+ * Using bounce buffer to bypass the
+ * hardened user copy kernel text checks.
+ */
+ memcpy(buf, (char *) start, tsz);
+ n = copy_to_user(buffer, buf, tsz);
/*
* We cannot distinguish between fault on source
* and fault on destination. When this happens
{
if (!capable(CAP_SYS_RAWIO))
return -EPERM;
+
+ filp->private_data = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!filp->private_data)
+ return -ENOMEM;
+
if (kcore_need_update)
kcore_update_ram();
if (i_size_read(inode) != proc_root_kcore->size) {
return 0;
}
+static int release_kcore(struct inode *inode, struct file *file)
+{
+ kfree(file->private_data);
+ return 0;
+}
static const struct file_operations proc_kcore_operations = {
.read = read_kcore,
.open = open_kcore,
+ .release = release_kcore,
.llseek = default_llseek,
};
cached = 0;
for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
- pages[lru] = global_page_state(NR_LRU_BASE + lru);
+ pages[lru] = global_node_page_state(NR_LRU_BASE + lru);
available = si_mem_available();
mss->anonymous_thp += HPAGE_PMD_SIZE;
else if (PageSwapBacked(page))
mss->shmem_thp += HPAGE_PMD_SIZE;
+ else if (is_zone_device_page(page))
+ /* pass */;
else
VM_BUG_ON_PAGE(1, page);
smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd));
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/ramfs.h>
+#include <linux/sched.h>
#include "internal.h"
+static unsigned long ramfs_mmu_get_unmapped_area(struct file *file,
+ unsigned long addr, unsigned long len, unsigned long pgoff,
+ unsigned long flags)
+{
+ return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
+}
+
const struct file_operations ramfs_file_operations = {
.read_iter = generic_file_read_iter,
.write_iter = generic_file_write_iter,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
.llseek = generic_file_llseek,
+ .get_unmapped_area = ramfs_mmu_get_unmapped_area,
};
const struct inode_operations ramfs_file_inode_operations = {
size -= n;
buf += n;
copied += n;
- if (!m->count)
+ if (!m->count) {
+ m->from = 0;
m->index++;
+ }
if (!size)
goto Done;
}
* If buf != of->prealloc_buf, we don't know how
* large it is, so cannot safely pass it to ->show
*/
- if (pos || WARN_ON_ONCE(buf != of->prealloc_buf))
+ if (WARN_ON_ONCE(buf != of->prealloc_buf))
return 0;
len = ops->show(kobj, of->kn->priv, buf);
+ if (pos) {
+ if (len <= pos)
+ return 0;
+ len -= pos;
+ memmove(buf, buf + pos, len);
+ }
return min(count, len);
}
p = c->gap_lebs;
do {
- ubifs_assert(p < c->gap_lebs + sizeof(int) * c->lst.idx_lebs);
+ ubifs_assert(p < c->gap_lebs + c->lst.idx_lebs);
written = layout_leb_in_gaps(c, p);
if (written < 0) {
err = written;
dbg_gen("xattr '%s', ino %lu ('%pd'), buf size %zd", name,
inode->i_ino, dentry, size);
- return __ubifs_getxattr(inode, name, buffer, size);
+ name = xattr_full_name(handler, name);
+ return __ubifs_getxattr(inode, name, buffer, size);
}
static int ubifs_xattr_set(const struct xattr_handler *handler,
dbg_gen("xattr '%s', host ino %lu ('%pd'), size %zd",
name, inode->i_ino, dentry, size);
+ name = xattr_full_name(handler, name);
+
if (value)
return __ubifs_setxattr(inode, name, value, size, flags);
else
xfs_extlen_t *flenp, /* result length */
int *stat) /* status: 0-freelist, 1-normal/none */
{
+ struct xfs_owner_info oinfo;
int error;
xfs_agblock_t fbno;
xfs_extlen_t flen;
error0);
args->wasfromfl = 1;
trace_xfs_alloc_small_freelist(args);
+
+ /*
+ * If we're feeding an AGFL block to something that
+ * doesn't live in the free space, we need to clear
+ * out the OWN_AG rmap.
+ */
+ xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_AG);
+ error = xfs_rmap_free(args->tp, args->agbp, args->agno,
+ fbno, 1, &oinfo);
+ if (error)
+ goto error0;
+
*stat = 0;
return 0;
}
offsetof(xfs_agf_t, agf_longest),
offsetof(xfs_agf_t, agf_btreeblks),
offsetof(xfs_agf_t, agf_uuid),
+ offsetof(xfs_agf_t, agf_rmap_blocks),
+ /* needed so that we don't log the whole rest of the structure: */
+ offsetof(xfs_agf_t, agf_spare64),
sizeof(xfs_agf_t)
};
XFS_BTREE_STATS_INC(cur, lookup);
+ /* No such thing as a zero-level tree. */
+ if (cur->bc_nlevels == 0)
+ return -EFSCORRUPTED;
+
block = NULL;
keyno = 0;
if (error)
goto out;
+ /* Nothing? See if there's anything to the right. */
+ if (!stat) {
+ error = xfs_btree_increment(cur, 0, &stat);
+ if (error)
+ goto out;
+ }
+
while (stat) {
/* Find the record. */
error = xfs_btree_get_rec(cur, &recp, &stat);
if (error || !stat)
break;
- cur->bc_ops->init_high_key_from_rec(&rec_key, recp);
/* Skip if high_key(rec) < low_key. */
if (firstrec) {
+ cur->bc_ops->init_high_key_from_rec(&rec_key, recp);
firstrec = false;
diff = cur->bc_ops->diff_two_keys(cur, low_key,
&rec_key);
}
/* Stop if high_key < low_key(rec). */
+ cur->bc_ops->init_key_from_rec(&rec_key, recp);
diff = cur->bc_ops->diff_two_keys(cur, &rec_key, high_key);
if (diff > 0)
break;
/* Abort intent items. */
list_for_each_entry(dfp, &dop->dop_pending, dfp_list) {
trace_xfs_defer_pending_abort(tp->t_mountp, dfp);
- if (dfp->dfp_committed)
+ if (!dfp->dfp_done)
dfp->dfp_type->abort_intent(dfp->dfp_intent);
}
struct xfs_defer_pending *dfp;
struct list_head *li;
struct list_head *n;
- void *done_item = NULL;
void *state;
int error = 0;
void (*cleanup_fn)(struct xfs_trans *, void *, int);
if (error)
goto out;
- /* Mark all pending intents as committed. */
- list_for_each_entry_reverse(dfp, &dop->dop_pending, dfp_list) {
- if (dfp->dfp_committed)
- break;
- trace_xfs_defer_pending_commit((*tp)->t_mountp, dfp);
- dfp->dfp_committed = true;
- }
-
/* Log an intent-done item for the first pending item. */
dfp = list_first_entry(&dop->dop_pending,
struct xfs_defer_pending, dfp_list);
trace_xfs_defer_pending_finish((*tp)->t_mountp, dfp);
- done_item = dfp->dfp_type->create_done(*tp, dfp->dfp_intent,
+ dfp->dfp_done = dfp->dfp_type->create_done(*tp, dfp->dfp_intent,
dfp->dfp_count);
cleanup_fn = dfp->dfp_type->finish_cleanup;
list_del(li);
dfp->dfp_count--;
error = dfp->dfp_type->finish_item(*tp, dop, li,
- done_item, &state);
+ dfp->dfp_done, &state);
if (error) {
/*
* Clean up after ourselves and jump out.
dfp = kmem_alloc(sizeof(struct xfs_defer_pending),
KM_SLEEP | KM_NOFS);
dfp->dfp_type = defer_op_types[type];
- dfp->dfp_committed = false;
dfp->dfp_intent = NULL;
+ dfp->dfp_done = NULL;
dfp->dfp_count = 0;
INIT_LIST_HEAD(&dfp->dfp_work);
list_add_tail(&dfp->dfp_list, &dop->dop_intake);
struct xfs_defer_pending {
const struct xfs_defer_op_type *dfp_type; /* function pointers */
struct list_head dfp_list; /* pending items */
- bool dfp_committed; /* committed trans? */
void *dfp_intent; /* log intent item */
+ void *dfp_done; /* log done item */
struct list_head dfp_work; /* work items */
unsigned int dfp_count; /* # extent items */
};
__be32 agf_btreeblks; /* # of blocks held in AGF btrees */
uuid_t agf_uuid; /* uuid of filesystem */
+ __be32 agf_rmap_blocks; /* rmapbt blocks used */
+ __be32 agf_padding; /* padding */
+
/*
* reserve some contiguous space for future logged fields before we add
* the unlogged fields. This makes the range logging via flags and
* structure offsets much simpler.
*/
- __be64 agf_spare64[16];
+ __be64 agf_spare64[15];
/* unlogged fields, written during buffer writeback. */
__be64 agf_lsn; /* last write sequence */
#define XFS_AGF_LONGEST 0x00000400
#define XFS_AGF_BTREEBLKS 0x00000800
#define XFS_AGF_UUID 0x00001000
-#define XFS_AGF_NUM_BITS 13
+#define XFS_AGF_RMAP_BLOCKS 0x00002000
+#define XFS_AGF_SPARE64 0x00004000
+#define XFS_AGF_NUM_BITS 15
#define XFS_AGF_ALL_BITS ((1 << XFS_AGF_NUM_BITS) - 1)
#define XFS_AGF_FLAGS \
{ XFS_AGF_FREEBLKS, "FREEBLKS" }, \
{ XFS_AGF_LONGEST, "LONGEST" }, \
{ XFS_AGF_BTREEBLKS, "BTREEBLKS" }, \
- { XFS_AGF_UUID, "UUID" }
+ { XFS_AGF_UUID, "UUID" }, \
+ { XFS_AGF_RMAP_BLOCKS, "RMAP_BLOCKS" }, \
+ { XFS_AGF_SPARE64, "SPARE64" }
/* disk block (xfs_daddr_t) in the AG */
#define XFS_AGF_DADDR(mp) ((xfs_daddr_t)(1 << (mp)->m_sectbb_log))
union xfs_btree_ptr *new,
int *stat)
{
+ struct xfs_buf *agbp = cur->bc_private.a.agbp;
+ struct xfs_agf *agf = XFS_BUF_TO_AGF(agbp);
int error;
xfs_agblock_t bno;
xfs_trans_agbtree_delta(cur->bc_tp, 1);
new->s = cpu_to_be32(bno);
+ be32_add_cpu(&agf->agf_rmap_blocks, 1);
+ xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS);
XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
*stat = 1;
bno = xfs_daddr_to_agbno(cur->bc_mp, XFS_BUF_ADDR(bp));
trace_xfs_rmapbt_free_block(cur->bc_mp, cur->bc_private.a.agno,
bno, 1);
+ be32_add_cpu(&agf->agf_rmap_blocks, -1);
+ xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS);
error = xfs_alloc_put_freelist(cur->bc_tp, agbp, NULL, bno, 1);
if (error)
return error;
* Only check the in progress field for the primary superblock as
* mkfs.xfs doesn't clear it from secondary superblocks.
*/
- return xfs_mount_validate_sb(mp, &sb, bp->b_bn == XFS_SB_DADDR,
+ return xfs_mount_validate_sb(mp, &sb,
+ bp->b_maps[0].bm_bn == XFS_SB_DADDR,
check_version);
}
if (!(bp->b_flags & _XBF_IN_FLIGHT))
return;
- ASSERT(bp->b_flags & XBF_ASYNC);
bp->b_flags &= ~_XBF_IN_FLIGHT;
percpu_counter_dec(&bp->b_target->bt_io_count);
}
*/
while (percpu_counter_sum(&btp->bt_io_count))
delay(100);
- drain_workqueue(btp->bt_mount->m_buf_workqueue);
+ flush_workqueue(btp->bt_mount->m_buf_workqueue);
/* loop until there is nothing left on the lru list. */
while (list_lru_count(&btp->bt_lru)) {
* page is inserted into the pagecache when we have to serve a write
* fault on a hole. It should never be dirtied and can simply be
* dropped from the pagecache once we get real data for the page.
+ *
+ * XXX: This is racy against mmap, and there's nothing we can do about
+ * it. dax_do_io() should really do this invalidation internally as
+ * it will know if we've allocated over a holei for this specific IO and
+ * if so it needs to update the mapping tree and invalidate existing
+ * PTEs over the newly allocated range. Remove this invalidation when
+ * dax_do_io() is fixed up.
*/
if (mapping->nrpages) {
- ret = invalidate_inode_pages2(mapping);
+ loff_t end = iocb->ki_pos + iov_iter_count(from) - 1;
+
+ ret = invalidate_inode_pages2_range(mapping,
+ iocb->ki_pos >> PAGE_SHIFT,
+ end >> PAGE_SHIFT);
WARN_ON_ONCE(ret);
}
agf->agf_roots[XFS_BTNUM_RMAPi] =
cpu_to_be32(XFS_RMAP_BLOCK(mp));
agf->agf_levels[XFS_BTNUM_RMAPi] = cpu_to_be32(1);
+ agf->agf_rmap_blocks = cpu_to_be32(1);
}
agf->agf_flfirst = cpu_to_be32(1);
* is in the delayed allocation extent on which we sit
* but before our buffer starts.
*/
-
nimaps = 0;
while (nimaps == 0) {
nres = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
-
- error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, nres,
+ /*
+ * We have already reserved space for the extent and any
+ * indirect blocks when creating the delalloc extent,
+ * there is no need to reserve space in this transaction
+ * again.
+ */
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0,
0, XFS_TRANS_RESERVE, &tp);
if (error)
return error;
return error;
trace_xfs_iomap_alloc(ip, offset, length, 0, &imap);
- xfs_bmbt_to_iomap(ip, iomap, &imap);
- } else if (nimaps) {
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- trace_xfs_iomap_found(ip, offset, length, 0, &imap);
- xfs_bmbt_to_iomap(ip, iomap, &imap);
} else {
+ ASSERT(nimaps);
+
xfs_iunlock(ip, XFS_ILOCK_EXCL);
- trace_xfs_iomap_not_found(ip, offset, length, 0, &imap);
- iomap->blkno = IOMAP_NULL_BLOCK;
- iomap->type = IOMAP_HOLE;
- iomap->offset = offset;
- iomap->length = length;
+ trace_xfs_iomap_found(ip, offset, length, 0, &imap);
}
+ xfs_bmbt_to_iomap(ip, iomap, &imap);
return 0;
}
.iomap_begin = xfs_file_iomap_begin,
.iomap_end = xfs_file_iomap_end,
};
+
+static int
+xfs_xattr_iomap_begin(
+ struct inode *inode,
+ loff_t offset,
+ loff_t length,
+ unsigned flags,
+ struct iomap *iomap)
+{
+ struct xfs_inode *ip = XFS_I(inode);
+ struct xfs_mount *mp = ip->i_mount;
+ xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset);
+ xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + length);
+ struct xfs_bmbt_irec imap;
+ int nimaps = 1, error = 0;
+ unsigned lockmode;
+
+ if (XFS_FORCED_SHUTDOWN(mp))
+ return -EIO;
+
+ lockmode = xfs_ilock_data_map_shared(ip);
+
+ /* if there are no attribute fork or extents, return ENOENT */
+ if (XFS_IFORK_Q(ip) || !ip->i_d.di_anextents) {
+ error = -ENOENT;
+ goto out_unlock;
+ }
+
+ ASSERT(ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL);
+ error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
+ &nimaps, XFS_BMAPI_ENTIRE | XFS_BMAPI_ATTRFORK);
+out_unlock:
+ xfs_iunlock(ip, lockmode);
+
+ if (!error) {
+ ASSERT(nimaps);
+ xfs_bmbt_to_iomap(ip, iomap, &imap);
+ }
+
+ return error;
+}
+
+struct iomap_ops xfs_xattr_iomap_ops = {
+ .iomap_begin = xfs_xattr_iomap_begin,
+};
struct xfs_bmbt_irec *);
extern struct iomap_ops xfs_iomap_ops;
+extern struct iomap_ops xfs_xattr_iomap_ops;
#endif /* __XFS_IOMAP_H__*/
int error;
xfs_ilock(XFS_I(inode), XFS_IOLOCK_SHARED);
- error = iomap_fiemap(inode, fieinfo, start, length, &xfs_iomap_ops);
+ if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
+ fieinfo->fi_flags &= ~FIEMAP_FLAG_XATTR;
+ error = iomap_fiemap(inode, fieinfo, start, length,
+ &xfs_xattr_iomap_ops);
+ } else {
+ error = iomap_fiemap(inode, fieinfo, start, length,
+ &xfs_iomap_ops);
+ }
xfs_iunlock(XFS_I(inode), XFS_IOLOCK_SHARED);
return error;
}
}
- if (xfs_sb_version_hasrmapbt(&mp->m_sb))
+ if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
+ if (mp->m_sb.sb_rblocks) {
+ xfs_alert(mp,
+ "EXPERIMENTAL reverse mapping btree not compatible with realtime device!");
+ error = -EINVAL;
+ goto out_filestream_unmount;
+ }
xfs_alert(mp,
"EXPERIMENTAL reverse mapping btree feature enabled. Use at your own risk!");
+ }
error = xfs_mountfs(mp);
if (error)
DEFINE_IOMAP_EVENT(xfs_get_blocks_map_direct);
DEFINE_IOMAP_EVENT(xfs_iomap_alloc);
DEFINE_IOMAP_EVENT(xfs_iomap_found);
-DEFINE_IOMAP_EVENT(xfs_iomap_not_found);
DECLARE_EVENT_CLASS(xfs_simple_io_class,
TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count),
__entry->dev = mp ? mp->m_super->s_dev : 0;
__entry->type = dfp->dfp_type->type;
__entry->intent = dfp->dfp_intent;
- __entry->committed = dfp->dfp_committed;
+ __entry->committed = dfp->dfp_done != NULL;
__entry->nr = dfp->dfp_count;
),
TP_printk("dev %d:%d optype %d intent %p committed %d nr %d\n",
#include <asm-generic/qrwlock_types.h>
/*
- * Writer states & reader shift and bias
+ * Writer states & reader shift and bias.
+ *
+ * | +0 | +1 | +2 | +3 |
+ * ----+----+----+----+----+
+ * LE | 78 | 56 | 34 | 12 | 0x12345678
+ * ----+----+----+----+----+
+ * | wr | rd |
+ * +----+----+----+----+
+ *
+ * ----+----+----+----+----+
+ * BE | 12 | 34 | 56 | 78 | 0x12345678
+ * ----+----+----+----+----+
+ * | rd | wr |
+ * +----+----+----+----+
*/
#define _QW_WAITING 1 /* A writer is waiting */
#define _QW_LOCKED 0xff /* A writer holds the lock */
(void)atomic_sub_return_release(_QR_BIAS, &lock->cnts);
}
+/**
+ * __qrwlock_write_byte - retrieve the write byte address of a queue rwlock
+ * @lock : Pointer to queue rwlock structure
+ * Return: the write byte address of a queue rwlock
+ */
+static inline u8 *__qrwlock_write_byte(struct qrwlock *lock)
+{
+ return (u8 *)lock + 3 * IS_BUILTIN(CONFIG_CPU_BIG_ENDIAN);
+}
+
/**
* queued_write_unlock - release write lock of a queue rwlock
* @lock : Pointer to queue rwlock structure
*/
static inline void queued_write_unlock(struct qrwlock *lock)
{
- smp_store_release((u8 *)&lock->cnts, 0);
+ smp_store_release(__qrwlock_write_byte(lock), 0);
}
/*
/* Returns 0 if exception not found and fixup otherwise. */
extern unsigned long search_exception_table(unsigned long);
+
/*
* architectures with an MMU should override these two
*/
might_fault(); \
access_ok(VERIFY_READ, __p, sizeof(*ptr)) ? \
__get_user((x), (__typeof__(*(ptr)) *)__p) : \
- -EFAULT; \
+ ((x) = (__typeof__(*(ptr)))0,-EFAULT); \
})
#ifndef __get_user_fn
static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
{
- size = __copy_from_user(x, ptr, size);
- return size ? -EFAULT : size;
+ size_t n = __copy_from_user(x, ptr, size);
+ if (unlikely(n)) {
+ memset(x + (size - n), 0, n);
+ return -EFAULT;
+ }
+ return 0;
}
#define __get_user_fn(sz, u, k) __get_user_fn(sz, u, k)
static inline long copy_from_user(void *to,
const void __user * from, unsigned long n)
{
+ unsigned long res = n;
might_fault();
- if (access_ok(VERIFY_READ, from, n))
- return __copy_from_user(to, from, n);
- else
- return n;
+ if (likely(access_ok(VERIFY_READ, from, n)))
+ res = __copy_from_user(to, from, n);
+ if (unlikely(res))
+ memset(to + (n - res), 0, res);
+ return res;
}
static inline long copy_to_user(void __user *to,
*
* @bo: A pointer to a struct ttm_buffer_object.
* @evict: 1: This is an eviction. Don't try to pipeline.
+ * @interruptible: Sleep interruptible if waiting.
* @no_wait_gpu: Return immediately if the GPU is busy.
* @new_mem: struct ttm_mem_reg indicating where to move.
*
*/
extern int ttm_bo_move_ttm(struct ttm_buffer_object *bo,
- bool evict, bool no_wait_gpu,
+ bool evict, bool interruptible, bool no_wait_gpu,
struct ttm_mem_reg *new_mem);
/**
return NULL;
}
-#define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, validate, data, fn) \
+#define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, valid, data, fn) \
static const void * __acpi_table_##name[] \
__attribute__((unused)) \
= { (void *) table_id, \
{
if (bio &&
bio->bi_iter.bi_size &&
- bio_op(bio) != REQ_OP_DISCARD)
+ bio_op(bio) != REQ_OP_DISCARD &&
+ bio_op(bio) != REQ_OP_SECURE_ERASE)
return true;
return false;
static inline bool bio_no_advance_iter(struct bio *bio)
{
- return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_WRITE_SAME;
+ return bio_op(bio) == REQ_OP_DISCARD ||
+ bio_op(bio) == REQ_OP_SECURE_ERASE ||
+ bio_op(bio) == REQ_OP_WRITE_SAME;
}
static inline bool bio_is_rw(struct bio *bio)
if (bio_op(bio) == REQ_OP_DISCARD)
return 1;
+ if (bio_op(bio) == REQ_OP_SECURE_ERASE)
+ return 1;
+
if (bio_op(bio) == REQ_OP_WRITE_SAME)
return 1;
static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
int op)
{
- if (unlikely(op == REQ_OP_DISCARD))
+ if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE))
return min(q->limits.max_discard_sectors, UINT_MAX >> 9);
if (unlikely(op == REQ_OP_WRITE_SAME))
if (unlikely(rq->cmd_type != REQ_TYPE_FS))
return q->limits.max_hw_sectors;
- if (!q->limits.chunk_sectors || (req_op(rq) == REQ_OP_DISCARD))
+ if (!q->limits.chunk_sectors ||
+ req_op(rq) == REQ_OP_DISCARD ||
+ req_op(rq) == REQ_OP_SECURE_ERASE)
return blk_queue_get_max_sectors(q, req_op(rq));
return min(blk_max_size_offset(q, offset),
"Attempted to advance past end of bvec iter\n");
while (bytes) {
- unsigned len = min(bytes, bvec_iter_len(bv, *iter));
+ unsigned iter_len = bvec_iter_len(bv, *iter);
+ unsigned len = min(bytes, iter_len);
bytes -= len;
iter->bi_size -= len;
/* One Touch Record Feature */
-static inline void cec_msg_record_off(struct cec_msg *msg)
+static inline void cec_msg_record_off(struct cec_msg *msg, bool reply)
{
msg->len = 2;
msg->msg[1] = CEC_MSG_RECORD_OFF;
+ msg->reply = reply ? CEC_MSG_RECORD_STATUS : 0;
}
struct cec_op_arib_data {
if (digital->service_id_method == CEC_OP_SERVICE_ID_METHOD_BY_CHANNEL) {
*msg++ = (digital->channel.channel_number_fmt << 2) |
(digital->channel.major >> 8);
- *msg++ = digital->channel.major && 0xff;
+ *msg++ = digital->channel.major & 0xff;
*msg++ = digital->channel.minor >> 8;
*msg++ = digital->channel.minor & 0xff;
*msg++ = 0;
}
static inline void cec_msg_record_on(struct cec_msg *msg,
+ bool reply,
const struct cec_op_record_src *rec_src)
{
switch (rec_src->type) {
rec_src->ext_phys_addr.phys_addr);
break;
}
+ msg->reply = reply ? CEC_MSG_RECORD_STATUS : 0;
}
static inline void cec_ops_record_on(const struct cec_msg *msg,
msg->reply = reply ? CEC_MSG_DEVICE_VENDOR_ID : 0;
}
+static inline void cec_msg_vendor_command(struct cec_msg *msg,
+ __u8 size, const __u8 *vendor_cmd)
+{
+ if (size > 14)
+ size = 14;
+ msg->len = 2 + size;
+ msg->msg[1] = CEC_MSG_VENDOR_COMMAND;
+ memcpy(msg->msg + 2, vendor_cmd, size);
+}
+
+static inline void cec_ops_vendor_command(const struct cec_msg *msg,
+ __u8 *size,
+ const __u8 **vendor_cmd)
+{
+ *size = msg->len - 2;
+
+ if (*size > 14)
+ *size = 14;
+ *vendor_cmd = msg->msg + 2;
+}
+
+static inline void cec_msg_vendor_command_with_id(struct cec_msg *msg,
+ __u32 vendor_id, __u8 size,
+ const __u8 *vendor_cmd)
+{
+ if (size > 11)
+ size = 11;
+ msg->len = 5 + size;
+ msg->msg[1] = CEC_MSG_VENDOR_COMMAND_WITH_ID;
+ msg->msg[2] = vendor_id >> 16;
+ msg->msg[3] = (vendor_id >> 8) & 0xff;
+ msg->msg[4] = vendor_id & 0xff;
+ memcpy(msg->msg + 5, vendor_cmd, size);
+}
+
+static inline void cec_ops_vendor_command_with_id(const struct cec_msg *msg,
+ __u32 *vendor_id, __u8 *size,
+ const __u8 **vendor_cmd)
+{
+ *size = msg->len - 5;
+
+ if (*size > 11)
+ *size = 11;
+ *vendor_id = (msg->msg[2] << 16) | (msg->msg[3] << 8) | msg->msg[4];
+ *vendor_cmd = msg->msg + 5;
+}
+
+static inline void cec_msg_vendor_remote_button_down(struct cec_msg *msg,
+ __u8 size,
+ const __u8 *rc_code)
+{
+ if (size > 14)
+ size = 14;
+ msg->len = 2 + size;
+ msg->msg[1] = CEC_MSG_VENDOR_REMOTE_BUTTON_DOWN;
+ memcpy(msg->msg + 2, rc_code, size);
+}
+
+static inline void cec_ops_vendor_remote_button_down(const struct cec_msg *msg,
+ __u8 *size,
+ const __u8 **rc_code)
+{
+ *size = msg->len - 2;
+
+ if (*size > 14)
+ *size = 14;
+ *rc_code = msg->msg + 2;
+}
+
static inline void cec_msg_vendor_remote_button_up(struct cec_msg *msg)
{
msg->len = 2;
msg->len += 4;
msg->msg[3] = (ui_cmd->channel_identifier.channel_number_fmt << 2) |
(ui_cmd->channel_identifier.major >> 8);
- msg->msg[4] = ui_cmd->channel_identifier.major && 0xff;
+ msg->msg[4] = ui_cmd->channel_identifier.major & 0xff;
msg->msg[5] = ui_cmd->channel_identifier.minor >> 8;
msg->msg[6] = ui_cmd->channel_identifier.minor & 0xff;
break;
* @num_log_addrs: how many logical addresses should be claimed. Set by the
* caller.
* @vendor_id: the vendor ID of the device. Set by the caller.
- * @flags: set to 0.
+ * @flags: flags.
* @osd_name: the OSD name of the device. Set by the caller.
* @primary_device_type: the primary device type for each logical address.
* Set by the caller.
__u8 features[CEC_MAX_LOG_ADDRS][12];
};
+/* Allow a fallback to unregistered */
+#define CEC_LOG_ADDRS_FL_ALLOW_UNREG_FALLBACK (1 << 0)
+
/* Events */
/* Event that occurs when the adapter state changes */
#define __compiler_offsetof(a, b) \
__builtin_offsetof(a, b)
-#if GCC_VERSION >= 40100 && GCC_VERSION < 40600
+#if GCC_VERSION >= 40100
# define __compiletime_object_size(obj) __builtin_object_size(obj, 0)
#endif
*/
#define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0)
-#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP
+/*
+ * sparse (__CHECKER__) pretends to be gcc, but can't do constant
+ * folding in __builtin_bswap*() (yet), so don't set these for it.
+ */
+#if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) && !defined(__CHECKER__)
#if GCC_VERSION >= 40400
#define __HAVE_BUILTIN_BSWAP32__
#define __HAVE_BUILTIN_BSWAP64__
#if GCC_VERSION >= 40800
#define __HAVE_BUILTIN_BSWAP16__
#endif
-#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */
+#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP && !__CHECKER__ */
#if GCC_VERSION >= 50000
#define KASAN_ABI_VERSION 4
* object's lifetime is managed by something other than RCU. That
* "something other" might be reference counting or simple immortality.
*
- * The seemingly unused void * variable is to validate @p is indeed a pointer
- * type. All pointer types silently cast to void *.
+ * The seemingly unused variable ___typecheck_p validates that @p is
+ * indeed a pointer type by using a pointer to typeof(*p) as the type.
+ * Taking a pointer to typeof(*p) again is needed in case p is void *.
*/
#define lockless_dereference(p) \
({ \
typeof(p) _________p1 = READ_ONCE(p); \
- __maybe_unused const void * const _________p2 = _________p1; \
+ typeof(*(p)) *___typecheck_p __maybe_unused; \
smp_read_barrier_depends(); /* Dependency order vs. p above. */ \
(_________p1); \
})
#ifndef __CPUHOTPLUG_H
#define __CPUHOTPLUG_H
+#include <linux/types.h>
+
enum cpuhp_state {
CPUHP_OFFLINE,
CPUHP_CREATE_THREADS,
u32 imagesize;
} efi_capsule_header_t;
+struct efi_boot_memmap {
+ efi_memory_desc_t **map;
+ unsigned long *map_size;
+ unsigned long *desc_size;
+ u32 *desc_ver;
+ unsigned long *key_ptr;
+ unsigned long *buff_size;
+};
+
/*
* EFI capsule flags
*/
/* Iterate through an efi_memory_map */
#define for_each_efi_memory_desc_in_map(m, md) \
for ((md) = (m)->map; \
- ((void *)(md) + (m)->desc_size) <= (m)->map_end; \
+ (md) && ((void *)(md) + (m)->desc_size) <= (m)->map_end; \
(md) = (void *)(md) + (m)->desc_size)
/**
efi_loaded_image_t *image, int *cmd_line_len);
efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg,
- efi_memory_desc_t **map,
- unsigned long *map_size,
- unsigned long *desc_size,
- u32 *desc_ver,
- unsigned long *key_ptr);
+ struct efi_boot_memmap *map);
efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg,
unsigned long size, unsigned long align,
arch_efi_call_virt_teardown(); \
})
+typedef efi_status_t (*efi_exit_boot_map_processing)(
+ efi_system_table_t *sys_table_arg,
+ struct efi_boot_memmap *map,
+ void *priv);
+
+efi_status_t efi_exit_boot_services(efi_system_table_t *sys_table,
+ void *handle,
+ struct efi_boot_memmap *map,
+ void *priv,
+ efi_exit_boot_map_processing priv_func);
#endif /* _LINUX_EFI_H */
* @timestamp: Timestamp when the fence was signaled.
* @status: Optional, only valid if < 0, must be set before calling
* fence_signal, indicates that the fence has completed with an error.
- * @child_list: list of children fences
- * @active_list: list of active fences
*
* the flags member must be manipulated and read using the appropriate
* atomic ops (bit_*), so taking the spinlock will not be needed most
struct posix_acl;
#define ACL_NOT_CACHED ((void *)(-1))
+#define ACL_DONT_CACHE ((void *)(-3))
static inline struct posix_acl *
uncached_acl_sentinel(struct task_struct *task)
extern int fscrypt_zeroout_range(struct inode *, pgoff_t, sector_t,
unsigned int);
/* policy.c */
-extern int fscrypt_process_policy(struct inode *,
- const struct fscrypt_policy *);
+extern int fscrypt_process_policy(struct file *, const struct fscrypt_policy *);
extern int fscrypt_get_policy(struct inode *, struct fscrypt_policy *);
extern int fscrypt_has_permitted_context(struct inode *, struct inode *);
extern int fscrypt_inherit_context(struct inode *, struct inode *,
}
/* policy.c */
-static inline int fscrypt_notsupp_process_policy(struct inode *i,
+static inline int fscrypt_notsupp_process_policy(struct file *f,
const struct fscrypt_policy *p)
{
return -EOPNOTSUPP;
#define FS_PRIO_1 1 /* fanotify content based access control */
#define FS_PRIO_2 2 /* fanotify pre-content access */
unsigned int priority;
+ bool shutdown; /* group is being shut down, don't queue more events */
/* stores all fastpath marks assoc with this group so they can be cleaned on unregister */
struct mutex mark_mutex; /* protect marks_list */
spinlock_t access_lock;
struct list_head access_list;
wait_queue_head_t access_waitq;
- atomic_t bypass_perm;
#endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */
int f_flags;
unsigned int max_marks;
extern void fsnotify_get_group(struct fsnotify_group *group);
/* drop reference on a group from fsnotify_alloc_group */
extern void fsnotify_put_group(struct fsnotify_group *group);
+/* group destruction begins, stop queuing new events */
+extern void fsnotify_group_stop_queueing(struct fsnotify_group *group);
/* destroy group */
extern void fsnotify_destroy_group(struct fsnotify_group *group);
/* fasync handler function */
struct fsnotify_event *event,
int (*merge)(struct list_head *,
struct fsnotify_event *));
-/* Remove passed event from groups notification queue */
-extern void fsnotify_remove_event(struct fsnotify_group *group, struct fsnotify_event *event);
/* true if the group notification queue is empty */
extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group);
/* return, but do not dequeue the first event on the notification queue */
struct tegra_mipi_device *tegra_mipi_request(struct device *device);
void tegra_mipi_free(struct tegra_mipi_device *device);
+int tegra_mipi_enable(struct tegra_mipi_device *device);
+int tegra_mipi_disable(struct tegra_mipi_device *device);
int tegra_mipi_calibrate(struct tegra_mipi_device *device);
#endif
const char *name,
struct config_item_type *type)
{
-#ifdef CONFIG_CONFIGFS_FS
+#if IS_ENABLED(CONFIG_CONFIGFS_FS)
config_group_init_type_name(&t->group, name, type);
#endif
}
#define IOMAP_MAPPED 0x03 /* blocks allocated @blkno */
#define IOMAP_UNWRITTEN 0x04 /* blocks allocated @blkno in unwritten state */
+/*
+ * Flags for iomap mappings:
+ */
+#define IOMAP_F_MERGED 0x01 /* contains multiple blocks/extents */
+
/*
* Magic value for blkno:
*/
sector_t blkno; /* 1st sector of mapping, 512b units */
loff_t offset; /* file offset of mapping, bytes */
u64 length; /* length of mapping, bytes */
- int type; /* type of mapping */
+ u16 type; /* type of mapping */
+ u16 flags; /* flags for mapping */
struct block_device *bdev; /* block device for I/O */
};
static inline void irq_gc_unlock(struct irq_chip_generic *gc) { }
#endif
+/*
+ * The irqsave variants are for usage in non interrupt code. Do not use
+ * them in irq_chip callbacks. Use irq_gc_lock() instead.
+ */
+#define irq_gc_lock_irqsave(gc, flags) \
+ raw_spin_lock_irqsave(&(gc)->lock, flags)
+
+#define irq_gc_unlock_irqrestore(gc, flags) \
+ raw_spin_unlock_irqrestore(&(gc)->lock, flags)
+
static inline void irq_reg_writel(struct irq_chip_generic *gc,
u32 val, int reg_offset)
{
*/
#define E_ITS_MOVI_UNMAPPED_INTERRUPT 0x010107
#define E_ITS_MOVI_UNMAPPED_COLLECTION 0x010109
+#define E_ITS_INT_UNMAPPED_INTERRUPT 0x010307
#define E_ITS_CLEAR_UNMAPPED_INTERRUPT 0x010507
#define E_ITS_MAPD_DEVICE_OOR 0x010801
#define E_ITS_MAPC_PROCNUM_OOR 0x010902
/* create, destroy, and name are mandatory */
struct kvm_device_ops {
const char *name;
+
+ /*
+ * create is called holding kvm->lock and any operations not suitable
+ * to do while holding the lock should be deferred to init (see
+ * below).
+ */
int (*create)(struct kvm_device *dev, u32 type);
+ /*
+ * init is called after create if create is successful and is called
+ * outside of holding kvm->lock.
+ */
+ void (*init)(struct kvm_device *dev);
+
/*
* Destroy is responsible for freeing dev.
*
}
extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long);
+extern void mpol_put_task_policy(struct task_struct *);
#else
return -1; /* no node preference */
}
+static inline void mpol_put_task_policy(struct task_struct *task)
+{
+}
#endif /* CONFIG_NUMA */
#endif
--- /dev/null
+/*
+ * TI DaVinci DA8xx CHIPCFGx registers for syscon consumers.
+ *
+ * Copyright (C) 2016 David Lechner <david@lechnology.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __LINUX_MFD_DA8XX_CFGCHIP_H
+#define __LINUX_MFD_DA8XX_CFGCHIP_H
+
+#include <linux/bitops.h>
+
+/* register offset (32-bit registers) */
+#define CFGCHIP(n) ((n) * 4)
+
+/* CFGCHIP0 (PLL0/EDMA3_0) register bits */
+#define CFGCHIP0_PLL_MASTER_LOCK BIT(4)
+#define CFGCHIP0_EDMA30TC1DBS(n) ((n) << 2)
+#define CFGCHIP0_EDMA30TC1DBS_MASK CFGCHIP0_EDMA30TC1DBS(0x3)
+#define CFGCHIP0_EDMA30TC1DBS_16 CFGCHIP0_EDMA30TC1DBS(0x0)
+#define CFGCHIP0_EDMA30TC1DBS_32 CFGCHIP0_EDMA30TC1DBS(0x1)
+#define CFGCHIP0_EDMA30TC1DBS_64 CFGCHIP0_EDMA30TC1DBS(0x2)
+#define CFGCHIP0_EDMA30TC0DBS(n) ((n) << 0)
+#define CFGCHIP0_EDMA30TC0DBS_MASK CFGCHIP0_EDMA30TC0DBS(0x3)
+#define CFGCHIP0_EDMA30TC0DBS_16 CFGCHIP0_EDMA30TC0DBS(0x0)
+#define CFGCHIP0_EDMA30TC0DBS_32 CFGCHIP0_EDMA30TC0DBS(0x1)
+#define CFGCHIP0_EDMA30TC0DBS_64 CFGCHIP0_EDMA30TC0DBS(0x2)
+
+/* CFGCHIP1 (eCAP/HPI/EDMA3_1/eHRPWM TBCLK/McASP0 AMUTEIN) register bits */
+#define CFGCHIP1_CAP2SRC(n) ((n) << 27)
+#define CFGCHIP1_CAP2SRC_MASK CFGCHIP1_CAP2SRC(0x1f)
+#define CFGCHIP1_CAP2SRC_ECAP_PIN CFGCHIP1_CAP2SRC(0x0)
+#define CFGCHIP1_CAP2SRC_MCASP0_TX CFGCHIP1_CAP2SRC(0x1)
+#define CFGCHIP1_CAP2SRC_MCASP0_RX CFGCHIP1_CAP2SRC(0x2)
+#define CFGCHIP1_CAP2SRC_EMAC_C0_RX_THRESHOLD CFGCHIP1_CAP2SRC(0x7)
+#define CFGCHIP1_CAP2SRC_EMAC_C0_RX CFGCHIP1_CAP2SRC(0x8)
+#define CFGCHIP1_CAP2SRC_EMAC_C0_TX CFGCHIP1_CAP2SRC(0x9)
+#define CFGCHIP1_CAP2SRC_EMAC_C0_MISC CFGCHIP1_CAP2SRC(0xa)
+#define CFGCHIP1_CAP2SRC_EMAC_C1_RX_THRESHOLD CFGCHIP1_CAP2SRC(0xb)
+#define CFGCHIP1_CAP2SRC_EMAC_C1_RX CFGCHIP1_CAP2SRC(0xc)
+#define CFGCHIP1_CAP2SRC_EMAC_C1_TX CFGCHIP1_CAP2SRC(0xd)
+#define CFGCHIP1_CAP2SRC_EMAC_C1_MISC CFGCHIP1_CAP2SRC(0xe)
+#define CFGCHIP1_CAP2SRC_EMAC_C2_RX_THRESHOLD CFGCHIP1_CAP2SRC(0xf)
+#define CFGCHIP1_CAP2SRC_EMAC_C2_RX CFGCHIP1_CAP2SRC(0x10)
+#define CFGCHIP1_CAP2SRC_EMAC_C2_TX CFGCHIP1_CAP2SRC(0x11)
+#define CFGCHIP1_CAP2SRC_EMAC_C2_MISC CFGCHIP1_CAP2SRC(0x12)
+#define CFGCHIP1_CAP1SRC(n) ((n) << 22)
+#define CFGCHIP1_CAP1SRC_MASK CFGCHIP1_CAP1SRC(0x1f)
+#define CFGCHIP1_CAP1SRC_ECAP_PIN CFGCHIP1_CAP1SRC(0x0)
+#define CFGCHIP1_CAP1SRC_MCASP0_TX CFGCHIP1_CAP1SRC(0x1)
+#define CFGCHIP1_CAP1SRC_MCASP0_RX CFGCHIP1_CAP1SRC(0x2)
+#define CFGCHIP1_CAP1SRC_EMAC_C0_RX_THRESHOLD CFGCHIP1_CAP1SRC(0x7)
+#define CFGCHIP1_CAP1SRC_EMAC_C0_RX CFGCHIP1_CAP1SRC(0x8)
+#define CFGCHIP1_CAP1SRC_EMAC_C0_TX CFGCHIP1_CAP1SRC(0x9)
+#define CFGCHIP1_CAP1SRC_EMAC_C0_MISC CFGCHIP1_CAP1SRC(0xa)
+#define CFGCHIP1_CAP1SRC_EMAC_C1_RX_THRESHOLD CFGCHIP1_CAP1SRC(0xb)
+#define CFGCHIP1_CAP1SRC_EMAC_C1_RX CFGCHIP1_CAP1SRC(0xc)
+#define CFGCHIP1_CAP1SRC_EMAC_C1_TX CFGCHIP1_CAP1SRC(0xd)
+#define CFGCHIP1_CAP1SRC_EMAC_C1_MISC CFGCHIP1_CAP1SRC(0xe)
+#define CFGCHIP1_CAP1SRC_EMAC_C2_RX_THRESHOLD CFGCHIP1_CAP1SRC(0xf)
+#define CFGCHIP1_CAP1SRC_EMAC_C2_RX CFGCHIP1_CAP1SRC(0x10)
+#define CFGCHIP1_CAP1SRC_EMAC_C2_TX CFGCHIP1_CAP1SRC(0x11)
+#define CFGCHIP1_CAP1SRC_EMAC_C2_MISC CFGCHIP1_CAP1SRC(0x12)
+#define CFGCHIP1_CAP0SRC(n) ((n) << 17)
+#define CFGCHIP1_CAP0SRC_MASK CFGCHIP1_CAP0SRC(0x1f)
+#define CFGCHIP1_CAP0SRC_ECAP_PIN CFGCHIP1_CAP0SRC(0x0)
+#define CFGCHIP1_CAP0SRC_MCASP0_TX CFGCHIP1_CAP0SRC(0x1)
+#define CFGCHIP1_CAP0SRC_MCASP0_RX CFGCHIP1_CAP0SRC(0x2)
+#define CFGCHIP1_CAP0SRC_EMAC_C0_RX_THRESHOLD CFGCHIP1_CAP0SRC(0x7)
+#define CFGCHIP1_CAP0SRC_EMAC_C0_RX CFGCHIP1_CAP0SRC(0x8)
+#define CFGCHIP1_CAP0SRC_EMAC_C0_TX CFGCHIP1_CAP0SRC(0x9)
+#define CFGCHIP1_CAP0SRC_EMAC_C0_MISC CFGCHIP1_CAP0SRC(0xa)
+#define CFGCHIP1_CAP0SRC_EMAC_C1_RX_THRESHOLD CFGCHIP1_CAP0SRC(0xb)
+#define CFGCHIP1_CAP0SRC_EMAC_C1_RX CFGCHIP1_CAP0SRC(0xc)
+#define CFGCHIP1_CAP0SRC_EMAC_C1_TX CFGCHIP1_CAP0SRC(0xd)
+#define CFGCHIP1_CAP0SRC_EMAC_C1_MISC CFGCHIP1_CAP0SRC(0xe)
+#define CFGCHIP1_CAP0SRC_EMAC_C2_RX_THRESHOLD CFGCHIP1_CAP0SRC(0xf)
+#define CFGCHIP1_CAP0SRC_EMAC_C2_RX CFGCHIP1_CAP0SRC(0x10)
+#define CFGCHIP1_CAP0SRC_EMAC_C2_TX CFGCHIP1_CAP0SRC(0x11)
+#define CFGCHIP1_CAP0SRC_EMAC_C2_MISC CFGCHIP1_CAP0SRC(0x12)
+#define CFGCHIP1_HPIBYTEAD BIT(16)
+#define CFGCHIP1_HPIENA BIT(15)
+#define CFGCHIP0_EDMA31TC0DBS(n) ((n) << 13)
+#define CFGCHIP0_EDMA31TC0DBS_MASK CFGCHIP0_EDMA31TC0DBS(0x3)
+#define CFGCHIP0_EDMA31TC0DBS_16 CFGCHIP0_EDMA31TC0DBS(0x0)
+#define CFGCHIP0_EDMA31TC0DBS_32 CFGCHIP0_EDMA31TC0DBS(0x1)
+#define CFGCHIP0_EDMA31TC0DBS_64 CFGCHIP0_EDMA31TC0DBS(0x2)
+#define CFGCHIP1_TBCLKSYNC BIT(12)
+#define CFGCHIP1_AMUTESEL0(n) ((n) << 0)
+#define CFGCHIP1_AMUTESEL0_MASK CFGCHIP1_AMUTESEL0(0xf)
+#define CFGCHIP1_AMUTESEL0_LOW CFGCHIP1_AMUTESEL0(0x0)
+#define CFGCHIP1_AMUTESEL0_BANK_0 CFGCHIP1_AMUTESEL0(0x1)
+#define CFGCHIP1_AMUTESEL0_BANK_1 CFGCHIP1_AMUTESEL0(0x2)
+#define CFGCHIP1_AMUTESEL0_BANK_2 CFGCHIP1_AMUTESEL0(0x3)
+#define CFGCHIP1_AMUTESEL0_BANK_3 CFGCHIP1_AMUTESEL0(0x4)
+#define CFGCHIP1_AMUTESEL0_BANK_4 CFGCHIP1_AMUTESEL0(0x5)
+#define CFGCHIP1_AMUTESEL0_BANK_5 CFGCHIP1_AMUTESEL0(0x6)
+#define CFGCHIP1_AMUTESEL0_BANK_6 CFGCHIP1_AMUTESEL0(0x7)
+#define CFGCHIP1_AMUTESEL0_BANK_7 CFGCHIP1_AMUTESEL0(0x8)
+
+/* CFGCHIP2 (USB PHY) register bits */
+#define CFGCHIP2_PHYCLKGD BIT(17)
+#define CFGCHIP2_VBUSSENSE BIT(16)
+#define CFGCHIP2_RESET BIT(15)
+#define CFGCHIP2_OTGMODE(n) ((n) << 13)
+#define CFGCHIP2_OTGMODE_MASK CFGCHIP2_OTGMODE(0x3)
+#define CFGCHIP2_OTGMODE_NO_OVERRIDE CFGCHIP2_OTGMODE(0x0)
+#define CFGCHIP2_OTGMODE_FORCE_HOST CFGCHIP2_OTGMODE(0x1)
+#define CFGCHIP2_OTGMODE_FORCE_DEVICE CFGCHIP2_OTGMODE(0x2)
+#define CFGCHIP2_OTGMODE_FORCE_HOST_VBUS_LOW CFGCHIP2_OTGMODE(0x3)
+#define CFGCHIP2_USB1PHYCLKMUX BIT(12)
+#define CFGCHIP2_USB2PHYCLKMUX BIT(11)
+#define CFGCHIP2_PHYPWRDN BIT(10)
+#define CFGCHIP2_OTGPWRDN BIT(9)
+#define CFGCHIP2_DATPOL BIT(8)
+#define CFGCHIP2_USB1SUSPENDM BIT(7)
+#define CFGCHIP2_PHY_PLLON BIT(6)
+#define CFGCHIP2_SESENDEN BIT(5)
+#define CFGCHIP2_VBDTCTEN BIT(4)
+#define CFGCHIP2_REFFREQ(n) ((n) << 0)
+#define CFGCHIP2_REFFREQ_MASK CFGCHIP2_REFFREQ(0xf)
+#define CFGCHIP2_REFFREQ_12MHZ CFGCHIP2_REFFREQ(0x1)
+#define CFGCHIP2_REFFREQ_24MHZ CFGCHIP2_REFFREQ(0x2)
+#define CFGCHIP2_REFFREQ_48MHZ CFGCHIP2_REFFREQ(0x3)
+#define CFGCHIP2_REFFREQ_19_2MHZ CFGCHIP2_REFFREQ(0x4)
+#define CFGCHIP2_REFFREQ_38_4MHZ CFGCHIP2_REFFREQ(0x5)
+#define CFGCHIP2_REFFREQ_13MHZ CFGCHIP2_REFFREQ(0x6)
+#define CFGCHIP2_REFFREQ_26MHZ CFGCHIP2_REFFREQ(0x7)
+#define CFGCHIP2_REFFREQ_20MHZ CFGCHIP2_REFFREQ(0x8)
+#define CFGCHIP2_REFFREQ_40MHZ CFGCHIP2_REFFREQ(0x9)
+
+/* CFGCHIP3 (EMAC/uPP/PLL1/ASYNC3/PRU/DIV4.5/EMIFA) register bits */
+#define CFGCHIP3_RMII_SEL BIT(8)
+#define CFGCHIP3_UPP_TX_CLKSRC BIT(6)
+#define CFGCHIP3_PLL1_MASTER_LOCK BIT(5)
+#define CFGCHIP3_ASYNC3_CLKSRC BIT(4)
+#define CFGCHIP3_PRUEVTSEL BIT(3)
+#define CFGCHIP3_DIV45PENA BIT(2)
+#define CFGCHIP3_EMA_CLKSRC BIT(1)
+
+/* CFGCHIP4 (McASP0 AMUNTEIN) register bits */
+#define CFGCHIP4_AMUTECLR0 BIT(0)
+
+#endif /* __LINUX_MFD_DA8XX_CFGCHIP_H */
/*
* time in us for processing a single channel, calculated as follows:
*
- * num cycles = open delay + (sample delay + conv time) * averaging
+ * max num cycles = open delay + (sample delay + conv time) * averaging
*
- * num cycles: 152 + (1 + 13) * 16 = 376
+ * max num cycles: 262143 + (255 + 13) * 16 = 266431
*
* clock frequency: 26MHz / 8 = 3.25MHz
* clock period: 1 / 3.25MHz = 308ns
*
- * processing time: 376 * 308ns = 116us
+ * max processing time: 266431 * 308ns = 83ms(approx)
*/
-#define IDLE_TIMEOUT 116 /* microsec */
+#define IDLE_TIMEOUT 83 /* milliseconds */
#define TSCADC_CELLS 2
};
struct mlx5_ifc_ptys_reg_bits {
- u8 an_disable_cap[0x1];
+ u8 reserved_at_0[0x1];
u8 an_disable_admin[0x1];
- u8 reserved_at_2[0x6];
+ u8 an_disable_cap[0x1];
+ u8 reserved_at_3[0x5];
u8 local_port[0x8];
u8 reserved_at_10[0xd];
u8 proto_mask[0x3];
extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
extern struct file *get_mm_exe_file(struct mm_struct *mm);
+extern struct file *get_task_exe_file(struct task_struct *task);
extern bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long npages);
extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages);
#ifdef CONFIG_CMA
# define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA)
+# define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA)
#else
# define is_migrate_cma(migratetype) false
+# define is_migrate_cma_page(_page) false
#endif
#define for_each_migratetype_order(order, type) \
*/
#define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones)
-static inline int populated_zone(struct zone *zone)
+/*
+ * Returns true if a zone has pages managed by the buddy allocator.
+ * All the reclaim decisions have to use this function rather than
+ * populated_zone(). If the whole zone is reserved then we can easily
+ * end up with populated_zone() && !managed_zone().
+ */
+static inline bool managed_zone(struct zone *zone)
+{
+ return zone->managed_pages;
+}
+
+/* Returns true if a zone has memory */
+static inline bool populated_zone(struct zone *zone)
{
- return (!!zone->present_pages);
+ return zone->present_pages;
}
extern int movable_zone;
MSI_FLAG_MULTI_PCI_MSI = (1 << 2),
/* Support PCI MSIX interrupts */
MSI_FLAG_PCI_MSIX = (1 << 3),
+ /* Needs early activate, required for PCI */
+ MSI_FLAG_ACTIVATE_EARLY = (1 << 4),
};
int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask,
napi->skb = NULL;
}
+bool netdev_is_rx_handler_busy(struct net_device *dev);
int netdev_rx_handler_register(struct net_device *dev,
rx_handler_func_t *rx_handler,
void *rx_handler_data);
extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly;
void netdev_rss_key_fill(void *buffer, size_t len);
-int dev_get_nest_level(struct net_device *dev,
- bool (*type_check)(const struct net_device *dev));
+int dev_get_nest_level(struct net_device *dev);
int skb_checksum_help(struct sk_buff *skb);
struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
netdev_features_t features, bool tx_path);
struct nf_acct *nfnl_acct_find_get(struct net *net, const char *filter_name);
void nfnl_acct_put(struct nf_acct *acct);
void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct);
-extern int nfnl_acct_overquota(const struct sk_buff *skb,
- struct nf_acct *nfacct);
+int nfnl_acct_overquota(struct net *net, const struct sk_buff *skb,
+ struct nf_acct *nfacct);
#endif /* _NFNL_ACCT_H */
};
struct nvmf_connect_data {
- uuid_le hostid;
+ uuid_be hostid;
__le16 cntlid;
char resv4[238];
char subsysnqn[NVMF_NQN_FIELD_LEN];
*/
static inline int fault_in_multipages_writeable(char __user *uaddr, int size)
{
- int ret = 0;
char __user *end = uaddr + size - 1;
if (unlikely(size == 0))
- return ret;
+ return 0;
+ if (unlikely(uaddr > end))
+ return -EFAULT;
/*
* Writing zeroes into userspace here is OK, because we know that if
* the zero gets there, we'll be overwriting it.
*/
- while (uaddr <= end) {
- ret = __put_user(0, uaddr);
- if (ret != 0)
- return ret;
+ do {
+ if (unlikely(__put_user(0, uaddr) != 0))
+ return -EFAULT;
uaddr += PAGE_SIZE;
- }
+ } while (uaddr <= end);
/* Check whether the range spilled into the next page. */
if (((unsigned long)uaddr & PAGE_MASK) ==
((unsigned long)end & PAGE_MASK))
- ret = __put_user(0, end);
+ return __put_user(0, end);
- return ret;
+ return 0;
}
static inline int fault_in_multipages_readable(const char __user *uaddr,
int size)
{
volatile char c;
- int ret = 0;
const char __user *end = uaddr + size - 1;
if (unlikely(size == 0))
- return ret;
+ return 0;
- while (uaddr <= end) {
- ret = __get_user(c, uaddr);
- if (ret != 0)
- return ret;
+ if (unlikely(uaddr > end))
+ return -EFAULT;
+
+ do {
+ if (unlikely(__get_user(c, uaddr) != 0))
+ return -EFAULT;
uaddr += PAGE_SIZE;
- }
+ } while (uaddr <= end);
/* Check whether the range spilled into the next page. */
if (((unsigned long)uaddr & PAGE_MASK) ==
((unsigned long)end & PAGE_MASK)) {
- ret = __get_user(c, end);
- (void)c;
+ return __get_user(c, end);
}
- return ret;
+ (void)c;
+ return 0;
}
int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
#define to_pci_driver(drv) container_of(drv, struct pci_driver, driver)
-/**
- * DEFINE_PCI_DEVICE_TABLE - macro used to describe a pci device table
- * @_table: device table name
- *
- * This macro is deprecated and should not be used in new code.
- */
-#define DEFINE_PCI_DEVICE_TABLE(_table) \
- const struct pci_device_id _table[]
-
/**
* PCI_DEVICE - macro used to describe a specific pci device
* @vend: the 16 bit PCI Vendor ID
int pci_set_vga_state(struct pci_dev *pdev, bool decode,
unsigned int command_bits, u32 flags);
-#define PCI_IRQ_NOLEGACY (1 << 0) /* don't use legacy interrupts */
-#define PCI_IRQ_NOMSI (1 << 1) /* don't use MSI interrupts */
-#define PCI_IRQ_NOMSIX (1 << 2) /* don't use MSI-X interrupts */
-#define PCI_IRQ_NOAFFINITY (1 << 3) /* don't auto-assign affinity */
+#define PCI_IRQ_LEGACY (1 << 0) /* allow legacy interrupts */
+#define PCI_IRQ_MSI (1 << 1) /* allow MSI interrupts */
+#define PCI_IRQ_MSIX (1 << 2) /* allow MSI-X interrupts */
+#define PCI_IRQ_AFFINITY (1 << 3) /* auto-assign affinity */
+#define PCI_IRQ_ALL_TYPES \
+ (PCI_IRQ_LEGACY | PCI_IRQ_MSI | PCI_IRQ_MSIX)
/* kmem_cache style wrapper around pci_alloc_consistent() */
u64 parent_gen;
u64 generation;
int pin_count;
+#ifdef CONFIG_CGROUP_PERF
int nr_cgroups; /* cgroup evts */
+#endif
void *task_ctx_data; /* pmu specific data */
struct rcu_head rcu_head;
};
unsigned int hrtimer_active;
struct pmu *unique_pmu;
+#ifdef CONFIG_CGROUP_PERF
struct perf_cgroup *cgrp;
+#endif
};
struct perf_output_handle {
* and other debug macros are compiled out unless either DEBUG is defined
* or CONFIG_DYNAMIC_DEBUG is set.
*/
-
-#ifdef CONFIG_PRINTK
-
-asmlinkage __printf(1, 2) __cold void __pr_emerg(const char *fmt, ...);
-asmlinkage __printf(1, 2) __cold void __pr_alert(const char *fmt, ...);
-asmlinkage __printf(1, 2) __cold void __pr_crit(const char *fmt, ...);
-asmlinkage __printf(1, 2) __cold void __pr_err(const char *fmt, ...);
-asmlinkage __printf(1, 2) __cold void __pr_warn(const char *fmt, ...);
-asmlinkage __printf(1, 2) __cold void __pr_notice(const char *fmt, ...);
-asmlinkage __printf(1, 2) __cold void __pr_info(const char *fmt, ...);
-
-#define pr_emerg(fmt, ...) __pr_emerg(pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_alert(fmt, ...) __pr_alert(pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_crit(fmt, ...) __pr_crit(pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_err(fmt, ...) __pr_err(pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_warn(fmt, ...) __pr_warn(pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_notice(fmt, ...) __pr_notice(pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_info(fmt, ...) __pr_info(pr_fmt(fmt), ##__VA_ARGS__)
-
-#else
-
-#define pr_emerg(fmt, ...) printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_alert(fmt, ...) printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_crit(fmt, ...) printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_err(fmt, ...) printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_warn(fmt, ...) printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_notice(fmt, ...) printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__)
-#define pr_info(fmt, ...) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
-
-#endif
-
-#define pr_warning pr_warn
-
+#define pr_emerg(fmt, ...) \
+ printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_alert(fmt, ...) \
+ printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_crit(fmt, ...) \
+ printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_err(fmt, ...) \
+ printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_warning(fmt, ...) \
+ printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_warn pr_warning
+#define pr_notice(fmt, ...) \
+ printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__)
+#define pr_info(fmt, ...) \
+ printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
/*
* Like KERN_CONT, pr_cont() should only be used when continuing
* a line with no newline ('\n') enclosed. Otherwise it defaults
u8 max_tc;
};
+enum qed_dcbx_sf_ieee_type {
+ QED_DCBX_SF_IEEE_ETHTYPE,
+ QED_DCBX_SF_IEEE_TCP_PORT,
+ QED_DCBX_SF_IEEE_UDP_PORT,
+ QED_DCBX_SF_IEEE_TCP_UDP_PORT
+};
+
struct qed_app_entry {
bool ethtype;
+ enum qed_dcbx_sf_ieee_type sf_ieee;
bool enabled;
u8 prio;
u16 proto_id;
sctp_authhdr_t auth_hdr;
} __packed sctp_auth_chunk_t;
-struct sctp_info {
- __u32 sctpi_tag;
- __u32 sctpi_state;
- __u32 sctpi_rwnd;
- __u16 sctpi_unackdata;
- __u16 sctpi_penddata;
- __u16 sctpi_instrms;
- __u16 sctpi_outstrms;
- __u32 sctpi_fragmentation_point;
- __u32 sctpi_inqueue;
- __u32 sctpi_outqueue;
- __u32 sctpi_overall_error;
- __u32 sctpi_max_burst;
- __u32 sctpi_maxseg;
- __u32 sctpi_peer_rwnd;
- __u32 sctpi_peer_tag;
- __u8 sctpi_peer_capable;
- __u8 sctpi_peer_sack;
- __u16 __reserved1;
-
- /* assoc status info */
- __u64 sctpi_isacks;
- __u64 sctpi_osacks;
- __u64 sctpi_opackets;
- __u64 sctpi_ipackets;
- __u64 sctpi_rtxchunks;
- __u64 sctpi_outofseqtsns;
- __u64 sctpi_idupchunks;
- __u64 sctpi_gapcnt;
- __u64 sctpi_ouodchunks;
- __u64 sctpi_iuodchunks;
- __u64 sctpi_oodchunks;
- __u64 sctpi_iodchunks;
- __u64 sctpi_octrlchunks;
- __u64 sctpi_ictrlchunks;
-
- /* primary transport info */
- struct sockaddr_storage sctpi_p_address;
- __s32 sctpi_p_state;
- __u32 sctpi_p_cwnd;
- __u32 sctpi_p_srtt;
- __u32 sctpi_p_rto;
- __u32 sctpi_p_hbinterval;
- __u32 sctpi_p_pathmaxrxt;
- __u32 sctpi_p_sackdelay;
- __u32 sctpi_p_sackfreq;
- __u32 sctpi_p_ssthresh;
- __u32 sctpi_p_partial_bytes_acked;
- __u32 sctpi_p_flight_size;
- __u16 sctpi_p_error;
- __u16 __reserved2;
-
- /* sctp sock info */
- __u32 sctpi_s_autoclose;
- __u32 sctpi_s_adaptation_ind;
- __u32 sctpi_s_pd_point;
- __u8 sctpi_s_nodelay;
- __u8 sctpi_s_disable_fragments;
- __u8 sctpi_s_v4mapped;
- __u8 sctpi_s_frag_interleave;
- __u32 sctpi_s_type;
- __u32 __reserved3;
-};
-
struct sctp_infox {
struct sctp_info *sctpinfo;
struct sctp_association *asoc;
* if no_console_suspend
*/
unsigned char probe;
- struct mctrl_gpios *gpios;
#define UART_PROBE_RSA (1 << 0)
/*
__skb_linearize(skb) : 0;
}
+static __always_inline void
+__skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len,
+ unsigned int off)
+{
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
+ skb->csum = csum_block_sub(skb->csum,
+ csum_partial(start, len, 0), off);
+ else if (skb->ip_summed == CHECKSUM_PARTIAL &&
+ skb_checksum_start_offset(skb) < 0)
+ skb->ip_summed = CHECKSUM_NONE;
+}
+
/**
* skb_postpull_rcsum - update checksum for received skb after pull
* @skb: buffer to update
* update the CHECKSUM_COMPLETE checksum, or set ip_summed to
* CHECKSUM_NONE so that it can be recomputed from scratch.
*/
-
static inline void skb_postpull_rcsum(struct sk_buff *skb,
const void *start, unsigned int len)
{
- if (skb->ip_summed == CHECKSUM_COMPLETE)
- skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0));
- else if (skb->ip_summed == CHECKSUM_PARTIAL &&
- skb_checksum_start_offset(skb) < 0)
- skb->ip_summed = CHECKSUM_NONE;
+ __skb_postpull_rcsum(skb, start, len, 0);
}
-unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len);
+static __always_inline void
+__skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len,
+ unsigned int off)
+{
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
+ skb->csum = csum_block_add(skb->csum,
+ csum_partial(start, len, 0), off);
+}
+/**
+ * skb_postpush_rcsum - update checksum for received skb after push
+ * @skb: buffer to update
+ * @start: start of data after push
+ * @len: length of data pushed
+ *
+ * After doing a push on a received packet, you need to call this to
+ * update the CHECKSUM_COMPLETE checksum.
+ */
static inline void skb_postpush_rcsum(struct sk_buff *skb,
const void *start, unsigned int len)
{
- /* For performing the reverse operation to skb_postpull_rcsum(),
- * we can instead of ...
- *
- * skb->csum = csum_add(skb->csum, csum_partial(start, len, 0));
- *
- * ... just use this equivalent version here to save a few
- * instructions. Feeding csum of 0 in csum_partial() and later
- * on adding skb->csum is equivalent to feed skb->csum in the
- * first place.
- */
- if (skb->ip_summed == CHECKSUM_COMPLETE)
- skb->csum = csum_partial(start, len, skb->csum);
+ __skb_postpush_rcsum(skb, start, len, 0);
}
+unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len);
+
/**
* skb_push_rcsum - push skb and update receive checksum
* @skb: buffer to update
void kzfree(const void *);
size_t ksize(const void *);
+#ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR
+const char *__check_heap_object(const void *ptr, unsigned long n,
+ struct page *page);
+#else
+static inline const char *__check_heap_object(const void *ptr,
+ unsigned long n,
+ struct page *page)
+{
+ return NULL;
+}
+#endif
+
/*
* Some archs want to perform DMA into kmalloc caches and need a guaranteed
* alignment larger than the alignment of a 64-bit integer.
#ifndef __SMC91X_H__
#define __SMC91X_H__
+/*
+ * These bits define which access sizes a platform can support, rather
+ * than the maximal access size. So, if your platform can do 16-bit
+ * and 32-bit accesses to the SMC91x device, but not 8-bit, set both
+ * SMC91X_USE_16BIT and SMC91X_USE_32BIT.
+ *
+ * The SMC91x driver requires at least one of SMC91X_USE_8BIT or
+ * SMC91X_USE_16BIT to be supported - just setting SMC91X_USE_32BIT is
+ * an invalid configuration.
+ */
#define SMC91X_USE_8BIT (1 << 0)
#define SMC91X_USE_16BIT (1 << 1)
#define SMC91X_USE_32BIT (1 << 2)
struct rpc_xprt *,
void *),
void *data);
+void rpc_cap_max_reconnect_timeout(struct rpc_clnt *clnt,
+ unsigned long timeo);
const char *rpc_proc_name(const struct rpc_task *task);
#endif /* __KERNEL__ */
struct work_struct task_cleanup;
struct timer_list timer;
unsigned long last_used,
- idle_timeout;
+ idle_timeout,
+ max_reconnect_timeout;
/*
* Send stuff
void __user *, size_t *, loff_t *);
extern int proc_dointvec(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
+extern int proc_douintvec(struct ctl_table *, int,
+ void __user *, size_t *, loff_t *);
extern int proc_dointvec_minmax(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int proc_dointvec_jiffies(struct ctl_table *, int,
#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED)
+#ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES
+static inline int arch_within_stack_frames(const void * const stack,
+ const void * const stackend,
+ const void *obj, unsigned long len)
+{
+ return 0;
+}
+#endif
+
+#ifdef CONFIG_HARDENED_USERCOPY
+extern void __check_object_size(const void *ptr, unsigned long n,
+ bool to_user);
+
+static __always_inline void check_object_size(const void *ptr, unsigned long n,
+ bool to_user)
+{
+ if (!__builtin_constant_p(n))
+ __check_object_size(ptr, n, to_user);
+}
+#else
+static inline void check_object_size(const void *ptr, unsigned long n,
+ bool to_user)
+{ }
+#endif /* CONFIG_HARDENED_USERCOPY */
+
#endif /* __KERNEL__ */
#endif /* _LINUX_THREAD_INFO_H */
#ifndef user_access_begin
#define user_access_begin() do { } while (0)
#define user_access_end() do { } while (0)
-#define unsafe_get_user(x, ptr) __get_user(x, ptr)
-#define unsafe_put_user(x, ptr) __put_user(x, ptr)
+#define unsafe_get_user(x, ptr, err) do { if (unlikely(__get_user(x, ptr))) goto err; } while (0)
+#define unsafe_put_user(x, ptr, err) do { if (unlikely(__put_user(x, ptr))) goto err; } while (0)
#endif
#endif /* __LINUX_UACCESS_H__ */
struct iov_iter *i, unsigned long offset, size_t bytes);
void iov_iter_advance(struct iov_iter *i, size_t bytes);
int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes);
-int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes);
+#define iov_iter_fault_in_multipages_readable iov_iter_fault_in_readable
size_t iov_iter_single_seg_count(const struct iov_iter *i);
size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
struct iov_iter *i);
int minor;
bool registered;
bool unregistered;
- struct mutex fhs_lock;
struct list_head fhs;
+ struct mutex lock;
};
struct cec_adapter;
int tcf_unregister_action(struct tc_action_ops *a,
struct pernet_operations *ops);
int tcf_action_destroy(struct list_head *actions, int bind);
-int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions,
- struct tcf_result *res);
+int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
+ int nr_actions, struct tcf_result *res);
int tcf_action_init(struct net *net, struct nlattr *nla,
struct nlattr *est, char *n, int ovr,
int bind, struct list_head *);
int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int);
int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int);
-#define tc_no_actions(_exts) \
- (list_empty(&(_exts)->actions))
-
-#define tc_for_each_action(_a, _exts) \
- list_for_each_entry(a, &(_exts)->actions, list)
-
-#define tc_single_action(_exts) \
- (list_is_singular(&(_exts)->actions))
+#endif /* CONFIG_NET_CLS_ACT */
static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes,
u64 packets, u64 lastuse)
{
+#ifdef CONFIG_NET_CLS_ACT
if (!a->ops->stats_update)
return;
a->ops->stats_update(a, bytes, packets, lastuse);
+#endif
}
-#else /* CONFIG_NET_CLS_ACT */
-
-#define tc_no_actions(_exts) true
-#define tc_for_each_action(_a, _exts) while ((void)(_a), 0)
-#define tc_single_action(_exts) false
-#define tcf_action_stats_update(a, bytes, packets, lastuse)
-
-#endif /* CONFIG_NET_CLS_ACT */
#endif
unsigned long,
gfp_t);
int rxrpc_kernel_send_data(struct rxrpc_call *, struct msghdr *, size_t);
+void rxrpc_kernel_data_consumed(struct rxrpc_call *, struct sk_buff *);
void rxrpc_kernel_abort_call(struct rxrpc_call *, u32);
void rxrpc_kernel_end_call(struct rxrpc_call *);
bool rxrpc_kernel_is_data_last(struct sk_buff *);
u32 rxrpc_kernel_get_abort_code(struct sk_buff *);
int rxrpc_kernel_get_error_number(struct sk_buff *);
-void rxrpc_kernel_data_delivered(struct sk_buff *);
void rxrpc_kernel_free_skb(struct sk_buff *);
struct rxrpc_call *rxrpc_kernel_accept_call(struct socket *, unsigned long);
int rxrpc_kernel_reject_call(struct socket *);
struct sock sk;
struct unix_address *addr;
struct path path;
- struct mutex readlock;
+ struct mutex iolock, bindlock;
struct sock *peer;
struct list_head link;
atomic_long_t inflight;
struct cfg80211_tid_stats pertid[IEEE80211_NUM_TIDS + 1];
};
+#if IS_ENABLED(CONFIG_CFG80211)
/**
* cfg80211_get_station - retrieve information about a given station
* @dev: the device where the station is supposed to be connected to
*/
int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr,
struct station_info *sinfo);
+#else
+static inline int cfg80211_get_station(struct net_device *dev,
+ const u8 *mac_addr,
+ struct station_info *sinfo)
+{
+ return -ENOENT;
+}
+#endif
/**
* enum monitor_flags - monitor flags
skb_push(skb, hdr_len);
+ skb_set_inner_protocol(skb, proto);
skb_reset_transport_header(skb);
greh = (struct gre_base_hdr *)skb->data;
greh->flags = gre_tnl_flags_to_gre_flags(flags);
to = from | htonl(INET_ECN_CE << 20);
*(__be32 *)iph = to;
if (skb->ip_summed == CHECKSUM_COMPLETE)
- skb->csum = csum_add(csum_sub(skb->csum, from), to);
+ skb->csum = csum_add(csum_sub(skb->csum, (__force __wsum)from),
+ (__force __wsum)to);
return 1;
}
unsigned char fib_scope;
unsigned char fib_type;
__be32 fib_prefsrc;
+ u32 fib_tb_id;
u32 fib_priority;
u32 *fib_metrics;
#define fib_mtu fib_metrics[RTAX_MTU-1]
/* Exported by fib_semantics.c */
int ip_fib_check_default(__be32 gw, struct net_device *dev);
int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force);
-int fib_sync_down_addr(struct net *net, __be32 local);
+int fib_sync_down_addr(struct net_device *dev, __be32 local);
int fib_sync_up(struct net_device *dev, unsigned int nh_flags);
extern u32 fib_multipath_secret __read_mostly;
int (*join_ibss)(struct ieee80211_hw *hw, struct ieee80211_vif *vif);
void (*leave_ibss)(struct ieee80211_hw *hw, struct ieee80211_vif *vif);
- u32 (*get_expected_throughput)(struct ieee80211_sta *sta);
+ u32 (*get_expected_throughput)(struct ieee80211_hw *hw,
+ struct ieee80211_sta *sta);
int (*get_txpower)(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
int *dbm);
#endif
}
+static inline bool nf_ct_add_synproxy(struct nf_conn *ct,
+ const struct nf_conn *tmpl)
+{
+ if (tmpl && nfct_synproxy(tmpl)) {
+ if (!nfct_seqadj_ext_add(ct))
+ return false;
+
+ if (!nfct_synproxy_ext_add(ct))
+ return false;
+ }
+
+ return true;
+}
+
struct synproxy_stats {
unsigned int syn_received;
unsigned int cookie_invalid;
void nft_meta_set_destroy(const struct nft_ctx *ctx,
const struct nft_expr *expr);
+int nft_meta_set_validate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nft_data **data);
+
#endif
extern const struct nla_policy nft_reject_policy[];
+int nft_reject_validate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nft_data **data);
+
int nft_reject_init(const struct nft_ctx *ctx,
const struct nft_expr *expr,
const struct nlattr * const tb[]);
struct tcf_exts {
#ifdef CONFIG_NET_CLS_ACT
__u32 type; /* for backward compat(TCA_OLD_COMPAT) */
- struct list_head actions;
+ int nr_actions;
+ struct tc_action **actions;
#endif
/* Map to export classifier specific extension TLV types to the
* generic extensions API. Unsupported extensions must be set to 0.
{
#ifdef CONFIG_NET_CLS_ACT
exts->type = 0;
- INIT_LIST_HEAD(&exts->actions);
+ exts->nr_actions = 0;
+ exts->actions = kcalloc(TCA_ACT_MAX_PRIO, sizeof(struct tc_action *),
+ GFP_KERNEL);
+ WARN_ON(!exts->actions); /* TODO: propagate the error to callers */
#endif
exts->action = action;
exts->police = police;
tcf_exts_is_predicative(struct tcf_exts *exts)
{
#ifdef CONFIG_NET_CLS_ACT
- return !list_empty(&exts->actions);
+ return exts->nr_actions;
#else
return 0;
#endif
return tcf_exts_is_predicative(exts);
}
+static inline void tcf_exts_to_list(const struct tcf_exts *exts,
+ struct list_head *actions)
+{
+#ifdef CONFIG_NET_CLS_ACT
+ int i;
+
+ for (i = 0; i < exts->nr_actions; i++) {
+ struct tc_action *a = exts->actions[i];
+
+ list_add(&a->list, actions);
+ }
+#endif
+}
+
/**
* tcf_exts_exec - execute tc filter extensions
* @skb: socket buffer
struct tcf_result *res)
{
#ifdef CONFIG_NET_CLS_ACT
- if (!list_empty(&exts->actions))
- return tcf_action_exec(skb, &exts->actions, res);
+ if (exts->nr_actions)
+ return tcf_action_exec(skb, exts->actions, exts->nr_actions,
+ res);
#endif
return 0;
}
+#ifdef CONFIG_NET_CLS_ACT
+
+#define tc_no_actions(_exts) ((_exts)->nr_actions == 0)
+#define tc_single_action(_exts) ((_exts)->nr_actions == 1)
+
+#else /* CONFIG_NET_CLS_ACT */
+
+#define tc_no_actions(_exts) true
+#define tc_single_action(_exts) false
+
+#endif /* CONFIG_NET_CLS_ACT */
+
int tcf_exts_validate(struct net *net, struct tcf_proto *tp,
struct nlattr **tb, struct nlattr *rate_tlv,
struct tcf_exts *exts, bool ovr);
ADDIP_SERIAL_SIGN_BIT = (1<<31)
};
-static inline int ADDIP_SERIAL_gte(__u16 s, __u16 t)
+static inline int ADDIP_SERIAL_gte(__u32 s, __u32 t)
{
return ((s) == (t)) || (((t) - (s)) & ADDIP_SERIAL_SIGN_BIT);
}
if (!sk_has_account(sk))
return;
sk->sk_forward_alloc += size;
+
+ /* Avoid a possible overflow.
+ * TCP send queues can make this happen, if sk_mem_reclaim()
+ * is not called and more than 2 GBytes are released at once.
+ *
+ * If we reach 2 MBytes, reclaim 1 MBytes right now, there is
+ * no need to hold that much forward allocation anyway.
+ */
+ if (unlikely(sk->sk_forward_alloc >= 1 << 21))
+ __sk_mem_reclaim(sk, 1 << 20);
}
static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
{
if (sk->sk_send_head == skb_unlinked)
sk->sk_send_head = NULL;
+ if (tcp_sk(sk)->highest_sack == skb_unlinked)
+ tcp_sk(sk)->highest_sack = NULL;
}
static inline void tcp_init_send_head(struct sock *sk)
void xfrm4_local_error(struct sk_buff *skb, u32 mtu);
int xfrm6_extract_header(struct sk_buff *skb);
int xfrm6_extract_input(struct xfrm_state *x, struct sk_buff *skb);
-int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi);
+int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi,
+ struct ip6_tnl *t);
int xfrm6_transport_finish(struct sk_buff *skb, int async);
+int xfrm6_rcv_tnl(struct sk_buff *skb, struct ip6_tnl *t);
int xfrm6_rcv(struct sk_buff *skb);
int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
xfrm_address_t *saddr, u8 proto);
size_t len)
{
const void __user *p = udata->inbuf + offset;
- bool ret = false;
+ bool ret;
u8 *buf;
if (len > USHRT_MAX)
return false;
- buf = kmalloc(len, GFP_KERNEL);
- if (!buf)
+ buf = memdup_user(p, len);
+ if (IS_ERR(buf))
return false;
- if (copy_from_user(buf, p, len))
- goto free;
-
ret = !memchr_inv(buf, 0, len);
-
-free:
kfree(buf);
return ret;
}
struct request;
#if !IS_ENABLED(CONFIG_SCSI_SAS_ATTRS)
-static inline int is_sas_attached(struct scsi_device *sdev)
+static inline int scsi_is_sas_rphy(const struct device *sdev)
{
return 0;
}
#else
-extern int is_sas_attached(struct scsi_device *sdev);
+extern int scsi_is_sas_rphy(const struct device *);
#endif
static inline int sas_protocol_ata(enum sas_protocol proto)
extern void sas_rphy_remove(struct sas_rphy *);
extern void sas_rphy_delete(struct sas_rphy *);
extern void sas_rphy_unlink(struct sas_rphy *);
-extern int scsi_is_sas_rphy(const struct device *);
struct sas_port *sas_port_alloc(struct device *, int);
struct sas_port *sas_port_alloc_num(struct device *);
#ifdef CONFIG_NO_HZ_COMMON
#define TICK_DEP_NAMES \
- tick_dep_name(NONE) \
+ tick_dep_mask_name(NONE) \
tick_dep_name(POSIX_TIMER) \
tick_dep_name(PERF_EVENTS) \
tick_dep_name(SCHED) \
tick_dep_name_end(CLOCK_UNSTABLE)
#undef tick_dep_name
+#undef tick_dep_mask_name
#undef tick_dep_name_end
-#define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep);
-#define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep);
+/* The MASK will convert to their bits and they need to be processed too */
+#define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \
+ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep);
+#define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \
+ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep);
+/* NONE only has a mask defined for it */
+#define tick_dep_mask_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep);
TICK_DEP_NAMES
#undef tick_dep_name
+#undef tick_dep_mask_name
#undef tick_dep_name_end
#define tick_dep_name(sdep) { TICK_DEP_MASK_##sdep, #sdep },
+#define tick_dep_mask_name(sdep) { TICK_DEP_MASK_##sdep, #sdep },
#define tick_dep_name_end(sdep) { TICK_DEP_MASK_##sdep, #sdep }
#define show_tick_dep_name(val) \
#include <linux/atmapi.h>
#include <linux/atmioc.h>
+#include <linux/time.h>
#define ZATM_GETPOOL _IOW('a',ATMIOC_SARPRV+1,struct atmif_sioc)
/* get pool statistics */
BPF_FUNC_skb_change_type,
/**
- * bpf_skb_in_cgroup(skb, map, index) - Check cgroup2 membership of skb
+ * bpf_skb_under_cgroup(skb, map, index) - Check cgroup2 membership of skb
* @skb: pointer to skb
* @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
* @index: index of the cgroup in the bpf_map
* == 1 skb succeeded the cgroup2 descendant test
* < 0 error
*/
- BPF_FUNC_skb_in_cgroup,
+ BPF_FUNC_skb_under_cgroup,
/**
* bpf_get_hash_recalc(skb)
#define _UAPI__LINUX_IF_PPPOL2TP_H
#include <linux/types.h>
-
+#include <linux/in.h>
+#include <linux/in6.h>
/* Structure used to connect() the socket to a particular tunnel UDP
* socket over IPv4.
#include <asm/byteorder.h>
#include <linux/socket.h>
+#include <linux/if.h>
#include <linux/if_ether.h>
#include <linux/if_pppol2tp.h>
+#include <linux/in.h>
+#include <linux/in6.h>
/* For user-space programs to pick up these definitions
* which they wouldn't get otherwise without defining __KERNEL__
#define _UAPI_IF_TUNNEL_H_
#include <linux/types.h>
+#include <linux/if.h>
+#include <linux/ip.h>
+#include <linux/in6.h>
#include <asm/byteorder.h>
#ifndef _IPX_H_
#define _IPX_H_
+#include <linux/libc-compat.h> /* for compatibility with glibc netipx/ipx.h */
#include <linux/types.h>
#include <linux/sockios.h>
#include <linux/socket.h>
#define IPX_NODE_LEN 6
#define IPX_MTU 576
+#if __UAPI_DEF_SOCKADDR_IPX
struct sockaddr_ipx {
__kernel_sa_family_t sipx_family;
__be16 sipx_port;
__u8 sipx_type;
unsigned char sipx_zero; /* 16 byte fill */
};
+#endif /* __UAPI_DEF_SOCKADDR_IPX */
/*
* So we can fit the extra info for SIOCSIFADDR into the address nicely
#define IPX_DLTITF 0
#define IPX_CRTITF 1
+#if __UAPI_DEF_IPX_ROUTE_DEFINITION
struct ipx_route_definition {
__be32 ipx_network;
__be32 ipx_router_network;
unsigned char ipx_router_node[IPX_NODE_LEN];
};
+#endif /* __UAPI_DEF_IPX_ROUTE_DEFINITION */
+#if __UAPI_DEF_IPX_INTERFACE_DEFINITION
struct ipx_interface_definition {
__be32 ipx_network;
unsigned char ipx_device[16];
#define IPX_INTERNAL 2
unsigned char ipx_node[IPX_NODE_LEN];
};
-
+#endif /* __UAPI_DEF_IPX_INTERFACE_DEFINITION */
+
+#if __UAPI_DEF_IPX_CONFIG_DATA
struct ipx_config_data {
unsigned char ipxcfg_auto_select_primary;
unsigned char ipxcfg_auto_create_interfaces;
};
+#endif /* __UAPI_DEF_IPX_CONFIG_DATA */
/*
* OLD Route Definition for backward compatibility.
*/
+#if __UAPI_DEF_IPX_ROUTE_DEF
struct ipx_route_def {
__be32 ipx_network;
__be32 ipx_router_network;
#define IPX_RT_BLUEBOOK 2
#define IPX_RT_ROUTED 1
};
+#endif /* __UAPI_DEF_IPX_ROUTE_DEF */
#define SIOCAIPXITFCRT (SIOCPROTOPRIVATE)
#define SIOCAIPXPRISLT (SIOCPROTOPRIVATE + 1)
#endif /* _NETINET_IN_H */
+/* Coordinate with glibc netipx/ipx.h header. */
+#if defined(__NETIPX_IPX_H)
+
+#define __UAPI_DEF_SOCKADDR_IPX 0
+#define __UAPI_DEF_IPX_ROUTE_DEFINITION 0
+#define __UAPI_DEF_IPX_INTERFACE_DEFINITION 0
+#define __UAPI_DEF_IPX_CONFIG_DATA 0
+#define __UAPI_DEF_IPX_ROUTE_DEF 0
+
+#else /* defined(__NETIPX_IPX_H) */
+
+#define __UAPI_DEF_SOCKADDR_IPX 1
+#define __UAPI_DEF_IPX_ROUTE_DEFINITION 1
+#define __UAPI_DEF_IPX_INTERFACE_DEFINITION 1
+#define __UAPI_DEF_IPX_CONFIG_DATA 1
+#define __UAPI_DEF_IPX_ROUTE_DEF 1
+
+#endif /* defined(__NETIPX_IPX_H) */
+
/* Definitions for xattr.h */
#if defined(_SYS_XATTR_H)
#define __UAPI_DEF_XATTR 0
#define __UAPI_DEF_IN6_PKTINFO 1
#define __UAPI_DEF_IP6_MTUINFO 1
+/* Definitions for ipx.h */
+#define __UAPI_DEF_SOCKADDR_IPX 1
+#define __UAPI_DEF_IPX_ROUTE_DEFINITION 1
+#define __UAPI_DEF_IPX_INTERFACE_DEFINITION 1
+#define __UAPI_DEF_IPX_CONFIG_DATA 1
+#define __UAPI_DEF_IPX_ROUTE_DEF 1
+
/* Definitions for xattr.h */
#define __UAPI_DEF_XATTR 1
__NFT_REG_MAX,
NFT_REG32_00 = 8,
- MFT_REG32_01,
+ NFT_REG32_01,
NFT_REG32_02,
NFT_REG32_03,
NFT_REG32_04,
#define OVS_USERSPACE_ATTR_MAX (__OVS_USERSPACE_ATTR_MAX - 1)
struct ovs_action_trunc {
- uint32_t max_len; /* Max packet size in bytes. */
+ __u32 max_len; /* Max packet size in bytes. */
};
/**
* @hash_basis: basis used for computing hash.
*/
struct ovs_action_hash {
- uint32_t hash_alg; /* One of ovs_hash_alg. */
- uint32_t hash_basis;
+ __u32 hash_alg; /* One of ovs_hash_alg. */
+ __u32 hash_basis;
};
/**
__u16 pr_policy;
};
+struct sctp_info {
+ __u32 sctpi_tag;
+ __u32 sctpi_state;
+ __u32 sctpi_rwnd;
+ __u16 sctpi_unackdata;
+ __u16 sctpi_penddata;
+ __u16 sctpi_instrms;
+ __u16 sctpi_outstrms;
+ __u32 sctpi_fragmentation_point;
+ __u32 sctpi_inqueue;
+ __u32 sctpi_outqueue;
+ __u32 sctpi_overall_error;
+ __u32 sctpi_max_burst;
+ __u32 sctpi_maxseg;
+ __u32 sctpi_peer_rwnd;
+ __u32 sctpi_peer_tag;
+ __u8 sctpi_peer_capable;
+ __u8 sctpi_peer_sack;
+ __u16 __reserved1;
+
+ /* assoc status info */
+ __u64 sctpi_isacks;
+ __u64 sctpi_osacks;
+ __u64 sctpi_opackets;
+ __u64 sctpi_ipackets;
+ __u64 sctpi_rtxchunks;
+ __u64 sctpi_outofseqtsns;
+ __u64 sctpi_idupchunks;
+ __u64 sctpi_gapcnt;
+ __u64 sctpi_ouodchunks;
+ __u64 sctpi_iuodchunks;
+ __u64 sctpi_oodchunks;
+ __u64 sctpi_iodchunks;
+ __u64 sctpi_octrlchunks;
+ __u64 sctpi_ictrlchunks;
+
+ /* primary transport info */
+ struct sockaddr_storage sctpi_p_address;
+ __s32 sctpi_p_state;
+ __u32 sctpi_p_cwnd;
+ __u32 sctpi_p_srtt;
+ __u32 sctpi_p_rto;
+ __u32 sctpi_p_hbinterval;
+ __u32 sctpi_p_pathmaxrxt;
+ __u32 sctpi_p_sackdelay;
+ __u32 sctpi_p_sackfreq;
+ __u32 sctpi_p_ssthresh;
+ __u32 sctpi_p_partial_bytes_acked;
+ __u32 sctpi_p_flight_size;
+ __u16 sctpi_p_error;
+ __u16 __reserved2;
+
+ /* sctp sock info */
+ __u32 sctpi_s_autoclose;
+ __u32 sctpi_s_adaptation_ind;
+ __u32 sctpi_s_pd_point;
+ __u8 sctpi_s_nodelay;
+ __u8 sctpi_s_disable_fragments;
+ __u8 sctpi_s_v4mapped;
+ __u8 sctpi_s_frag_interleave;
+ __u32 sctpi_s_type;
+ __u32 __reserved3;
+};
+
#endif /* _UAPI_SCTP_H */
*/
#ifndef _UAPI_LINUX_VIRTIO_VSOCK_H
-#define _UAPI_LINUX_VIRTIO_VOSCK_H
+#define _UAPI_LINUX_VIRTIO_VSOCK_H
#include <linux/types.h>
#include <linux/virtio_ids.h>
*
* Of course the contents will be ABI, but that's up the AFU driver.
*/
- size_t data_size;
- u8 data[];
+ __u32 data_size;
+ __u8 data[];
};
struct cxl_event {
DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu);
-DECLARE_PER_CPU(int, xen_vcpu_id);
-static inline int xen_vcpu_nr(int cpu)
+DECLARE_PER_CPU(uint32_t, xen_vcpu_id);
+static inline uint32_t xen_vcpu_nr(int cpu)
{
return per_cpu(xen_vcpu_id, cpu);
}
config SLAB
bool "SLAB"
+ select HAVE_HARDENED_USERCOPY_ALLOCATOR
help
The regular slab allocator that is established and known to work
well in all environments. It organizes cache hot objects in
config SLUB
bool "SLUB (Unqueued Allocator)"
+ select HAVE_HARDENED_USERCOPY_ALLOCATOR
help
SLUB is a slab allocator that minimizes cache line usage
instead of managing queues of cached objects (SLAB approach).
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
+#include <linux/file.h>
#include <linux/kernel.h>
#include <linux/audit.h>
#include <linux/kthread.h>
unsigned long ino;
dev_t dev;
- rcu_read_lock();
- exe_file = rcu_dereference(tsk->mm->exe_file);
+ exe_file = get_task_exe_file(tsk);
+ if (!exe_file)
+ return 0;
ino = exe_file->f_inode->i_ino;
dev = exe_file->f_inode->i_sb->s_dev;
- rcu_read_unlock();
+ fput(exe_file);
return audit_mark_compare(mark, ino, dev);
}
struct bucket *buckets;
void *elems;
struct pcpu_freelist freelist;
+ void __percpu *extra_elems;
atomic_t count; /* number of elements in this hashtable */
u32 n_buckets; /* number of hash buckets */
u32 elem_size; /* size of each element in bytes */
};
+enum extra_elem_state {
+ HTAB_NOT_AN_EXTRA_ELEM = 0,
+ HTAB_EXTRA_ELEM_FREE,
+ HTAB_EXTRA_ELEM_USED
+};
+
/* each htab element is struct htab_elem + key + value */
struct htab_elem {
union {
struct bpf_htab *htab;
struct pcpu_freelist_node fnode;
};
- struct rcu_head rcu;
+ union {
+ struct rcu_head rcu;
+ enum extra_elem_state state;
+ };
u32 hash;
char key[0] __aligned(8);
};
return err;
}
+static int alloc_extra_elems(struct bpf_htab *htab)
+{
+ void __percpu *pptr;
+ int cpu;
+
+ pptr = __alloc_percpu_gfp(htab->elem_size, 8, GFP_USER | __GFP_NOWARN);
+ if (!pptr)
+ return -ENOMEM;
+
+ for_each_possible_cpu(cpu) {
+ ((struct htab_elem *)per_cpu_ptr(pptr, cpu))->state =
+ HTAB_EXTRA_ELEM_FREE;
+ }
+ htab->extra_elems = pptr;
+ return 0;
+}
+
/* Called from syscall */
static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
{
if (percpu)
cost += (u64) round_up(htab->map.value_size, 8) *
num_possible_cpus() * htab->map.max_entries;
+ else
+ cost += (u64) htab->elem_size * num_possible_cpus();
if (cost >= U32_MAX - PAGE_SIZE)
/* make sure page count doesn't overflow */
raw_spin_lock_init(&htab->buckets[i].lock);
}
+ if (!percpu) {
+ err = alloc_extra_elems(htab);
+ if (err)
+ goto free_buckets;
+ }
+
if (!(attr->map_flags & BPF_F_NO_PREALLOC)) {
err = prealloc_elems_and_freelist(htab);
if (err)
- goto free_buckets;
+ goto free_extra_elems;
}
return &htab->map;
+free_extra_elems:
+ free_percpu(htab->extra_elems);
free_buckets:
kvfree(htab->buckets);
free_htab:
if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH)
free_percpu(htab_elem_get_ptr(l, htab->map.key_size));
kfree(l);
-
}
static void htab_elem_free_rcu(struct rcu_head *head)
static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
{
+ if (l->state == HTAB_EXTRA_ELEM_USED) {
+ l->state = HTAB_EXTRA_ELEM_FREE;
+ return;
+ }
+
if (!(htab->map.map_flags & BPF_F_NO_PREALLOC)) {
pcpu_freelist_push(&htab->freelist, &l->fnode);
} else {
static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
void *value, u32 key_size, u32 hash,
- bool percpu, bool onallcpus)
+ bool percpu, bool onallcpus,
+ bool old_elem_exists)
{
u32 size = htab->map.value_size;
bool prealloc = !(htab->map.map_flags & BPF_F_NO_PREALLOC);
struct htab_elem *l_new;
void __percpu *pptr;
+ int err = 0;
if (prealloc) {
l_new = (struct htab_elem *)pcpu_freelist_pop(&htab->freelist);
if (!l_new)
- return ERR_PTR(-E2BIG);
+ err = -E2BIG;
} else {
if (atomic_inc_return(&htab->count) > htab->map.max_entries) {
atomic_dec(&htab->count);
- return ERR_PTR(-E2BIG);
+ err = -E2BIG;
+ } else {
+ l_new = kmalloc(htab->elem_size,
+ GFP_ATOMIC | __GFP_NOWARN);
+ if (!l_new)
+ return ERR_PTR(-ENOMEM);
}
- l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN);
- if (!l_new)
- return ERR_PTR(-ENOMEM);
+ }
+
+ if (err) {
+ if (!old_elem_exists)
+ return ERR_PTR(err);
+
+ /* if we're updating the existing element and the hash table
+ * is full, use per-cpu extra elems
+ */
+ l_new = this_cpu_ptr(htab->extra_elems);
+ if (l_new->state != HTAB_EXTRA_ELEM_FREE)
+ return ERR_PTR(-E2BIG);
+ l_new->state = HTAB_EXTRA_ELEM_USED;
+ } else {
+ l_new->state = HTAB_NOT_AN_EXTRA_ELEM;
}
memcpy(l_new->key, key, key_size);
if (ret)
goto err;
- l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false);
+ l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false,
+ !!l_old);
if (IS_ERR(l_new)) {
/* all pre-allocated elements are in use or memory exhausted */
ret = PTR_ERR(l_new);
}
} else {
l_new = alloc_htab_elem(htab, key, value, key_size,
- hash, true, onallcpus);
+ hash, true, onallcpus, false);
if (IS_ERR(l_new)) {
ret = PTR_ERR(l_new);
goto err;
htab_free_elems(htab);
pcpu_freelist_destroy(&htab->freelist);
}
+ free_percpu(htab->extra_elems);
kvfree(htab->buckets);
kfree(htab);
}
struct verifier_state_list **explored_states; /* search pruning optimization */
struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */
u32 used_map_cnt; /* number of used maps */
+ u32 id_gen; /* used to generate unique reg IDs */
bool allow_ptr_leaks;
};
goto error;
break;
case BPF_MAP_TYPE_CGROUP_ARRAY:
- if (func_id != BPF_FUNC_skb_in_cgroup)
+ if (func_id != BPF_FUNC_skb_under_cgroup)
goto error;
break;
default:
if (map->map_type != BPF_MAP_TYPE_STACK_TRACE)
goto error;
break;
- case BPF_FUNC_skb_in_cgroup:
+ case BPF_FUNC_skb_under_cgroup:
if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY)
goto error;
break;
/* dst_reg stays as pkt_ptr type and since some positive
* integer value was added to the pointer, increment its 'id'
*/
- dst_reg->id++;
+ dst_reg->id = ++env->id_gen;
/* something was added to pkt_ptr, set range and off to zero */
dst_reg->off = 0;
if (cgroup_sk_alloc_disabled)
return;
+ /* Socket clone path */
+ if (skcd->val) {
+ cgroup_get(sock_cgroup_ptr(skcd));
+ return;
+ }
+
rcu_read_lock();
while (true) {
+# CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE is not set
CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+# CONFIG_KERNEL_GZIP is not set
+# CONFIG_KERNEL_BZIP2 is not set
+# CONFIG_KERNEL_LZMA is not set
CONFIG_KERNEL_XZ=y
+# CONFIG_KERNEL_LZO is not set
+# CONFIG_KERNEL_LZ4 is not set
CONFIG_OPTIMIZE_INLINING=y
+# CONFIG_SLAB is not set
+# CONFIG_SLUB is not set
CONFIG_SLOB=y
mutex_unlock(&cpuset_mutex);
}
+/*
+ * Make sure the new task conform to the current state of its parent,
+ * which could have been changed by cpuset just after it inherits the
+ * state from the parent and before it sits on the cgroup's task list.
+ */
+void cpuset_fork(struct task_struct *task)
+{
+ if (task_css_is_root(task, cpuset_cgrp_id))
+ return;
+
+ set_cpus_allowed_ptr(task, ¤t->cpus_allowed);
+ task->mems_allowed = current->mems_allowed;
+}
+
struct cgroup_subsys cpuset_cgrp_subsys = {
.css_alloc = cpuset_css_alloc,
.css_online = cpuset_css_online,
.attach = cpuset_attach,
.post_attach = cpuset_post_attach,
.bind = cpuset_bind,
+ .fork = cpuset_fork,
.legacy_cftypes = files,
.early_init = true,
};
return ret;
}
-static void event_function_local(struct perf_event *event, event_f func, void *data)
-{
- struct event_function_struct efs = {
- .event = event,
- .func = func,
- .data = data,
- };
-
- int ret = event_function(&efs);
- WARN_ON_ONCE(ret);
-}
-
static void event_function_call(struct perf_event *event, event_f func, void *data)
{
struct perf_event_context *ctx = event->ctx;
raw_spin_unlock_irq(&ctx->lock);
}
+/*
+ * Similar to event_function_call() + event_function(), but hard assumes IRQs
+ * are already disabled and we're on the right CPU.
+ */
+static void event_function_local(struct perf_event *event, event_f func, void *data)
+{
+ struct perf_event_context *ctx = event->ctx;
+ struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+ struct task_struct *task = READ_ONCE(ctx->task);
+ struct perf_event_context *task_ctx = NULL;
+
+ WARN_ON_ONCE(!irqs_disabled());
+
+ if (task) {
+ if (task == TASK_TOMBSTONE)
+ return;
+
+ task_ctx = ctx;
+ }
+
+ perf_ctx_lock(cpuctx, task_ctx);
+
+ task = ctx->task;
+ if (task == TASK_TOMBSTONE)
+ goto unlock;
+
+ if (task) {
+ /*
+ * We must be either inactive or active and the right task,
+ * otherwise we're screwed, since we cannot IPI to somewhere
+ * else.
+ */
+ if (ctx->is_active) {
+ if (WARN_ON_ONCE(task != current))
+ goto unlock;
+
+ if (WARN_ON_ONCE(cpuctx->task_ctx != ctx))
+ goto unlock;
+ }
+ } else {
+ WARN_ON_ONCE(&cpuctx->ctx != ctx);
+ }
+
+ func(event, cpuctx, ctx, data);
+unlock:
+ perf_ctx_unlock(cpuctx, task_ctx);
+}
+
#define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\
PERF_FLAG_FD_OUTPUT |\
PERF_FLAG_PID_CGROUP |\
}
}
}
+
+/*
+ * Update cpuctx->cgrp so that it is set when first cgroup event is added and
+ * cleared when last cgroup event is removed.
+ */
+static inline void
+list_update_cgroup_event(struct perf_event *event,
+ struct perf_event_context *ctx, bool add)
+{
+ struct perf_cpu_context *cpuctx;
+
+ if (!is_cgroup_event(event))
+ return;
+
+ if (add && ctx->nr_cgroups++)
+ return;
+ else if (!add && --ctx->nr_cgroups)
+ return;
+ /*
+ * Because cgroup events are always per-cpu events,
+ * this will always be called from the right CPU.
+ */
+ cpuctx = __get_cpu_context(ctx);
+ cpuctx->cgrp = add ? event->cgrp : NULL;
+}
+
#else /* !CONFIG_CGROUP_PERF */
static inline bool
struct perf_event_context *ctx)
{
}
+
+static inline void
+list_update_cgroup_event(struct perf_event *event,
+ struct perf_event_context *ctx, bool add)
+{
+}
+
#endif
/*
static void
list_add_event(struct perf_event *event, struct perf_event_context *ctx)
{
+
lockdep_assert_held(&ctx->lock);
WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
list_add_tail(&event->group_entry, list);
}
- if (is_cgroup_event(event))
- ctx->nr_cgroups++;
+ list_update_cgroup_event(event, ctx, true);
list_add_rcu(&event->event_entry, &ctx->event_list);
ctx->nr_events++;
static void
list_del_event(struct perf_event *event, struct perf_event_context *ctx)
{
- struct perf_cpu_context *cpuctx;
-
WARN_ON_ONCE(event->ctx != ctx);
lockdep_assert_held(&ctx->lock);
event->attach_state &= ~PERF_ATTACH_CONTEXT;
- if (is_cgroup_event(event)) {
- ctx->nr_cgroups--;
- /*
- * Because cgroup events are always per-cpu events, this will
- * always be called from the right CPU.
- */
- cpuctx = __get_cpu_context(ctx);
- /*
- * If there are no more cgroup events then clear cgrp to avoid
- * stale pointer in update_cgrp_time_from_cpuctx().
- */
- if (!ctx->nr_cgroups)
- cpuctx->cgrp = NULL;
- }
+ list_update_cgroup_event(event, ctx, false);
ctx->nr_events--;
if (event->attr.inherit_stat)
static inline int
event_filter_match(struct perf_event *event)
{
- return (event->cpu == -1 || event->cpu == smp_processor_id())
- && perf_cgroup_match(event) && pmu_filter_match(event);
+ return (event->cpu == -1 || event->cpu == smp_processor_id()) &&
+ perf_cgroup_match(event) && pmu_filter_match(event);
}
static void
* maintained, otherwise bogus information is return
* via read() for time_enabled, time_running:
*/
- if (event->state == PERF_EVENT_STATE_INACTIVE
- && !event_filter_match(event)) {
+ if (event->state == PERF_EVENT_STATE_INACTIVE &&
+ !event_filter_match(event)) {
delta = tstamp - event->tstamp_stopped;
event->tstamp_running += delta;
event->tstamp_stopped = tstamp;
lockdep_assert_held(&ctx->mutex);
- event->ctx = ctx;
if (event->cpu != -1)
event->cpu = cpu;
+ /*
+ * Ensures that if we can observe event->ctx, both the event and ctx
+ * will be 'complete'. See perf_iterate_sb_cpu().
+ */
+ smp_store_release(&event->ctx, ctx);
+
if (!task) {
cpu_function_call(cpu, __perf_install_in_context, event);
return;
return 0;
}
-static int perf_event_restart(struct perf_event *event)
+static int perf_event_stop(struct perf_event *event, int restart)
{
struct stop_event_data sd = {
.event = event,
- .restart = 1,
+ .restart = restart,
};
int ret = 0;
.group = group,
.ret = 0,
};
- smp_call_function_single(event->oncpu,
- __perf_event_read, &data, 1);
+ /*
+ * Purposely ignore the smp_call_function_single() return
+ * value.
+ *
+ * If event->oncpu isn't a valid CPU it means the event got
+ * scheduled out and that will have updated the event count.
+ *
+ * Therefore, either way, we'll have an up-to-date event count
+ * after this.
+ */
+ (void)smp_call_function_single(event->oncpu, __perf_event_read, &data, 1);
ret = data.ret;
} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
struct perf_event_context *ctx = event->ctx;
static bool exclusive_event_match(struct perf_event *e1, struct perf_event *e2)
{
- if ((e1->pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) &&
+ if ((e1->pmu == e2->pmu) &&
(e1->cpu == e2->cpu ||
e1->cpu == -1 ||
e2->cpu == -1))
spin_unlock_irqrestore(&rb->event_lock, flags);
}
+ /*
+ * Avoid racing with perf_mmap_close(AUX): stop the event
+ * before swizzling the event::rb pointer; if it's getting
+ * unmapped, its aux_mmap_count will be 0 and it won't
+ * restart. See the comment in __perf_pmu_output_stop().
+ *
+ * Data will inevitably be lost when set_output is done in
+ * mid-air, but then again, whoever does it like this is
+ * not in for the data anyway.
+ */
+ if (has_aux(event))
+ perf_event_stop(event, 0);
+
rcu_assign_pointer(event->rb, rb);
if (old_rb) {
struct perf_event *event;
list_for_each_entry_rcu(event, &pel->list, sb_list) {
+ /*
+ * Skip events that are not fully formed yet; ensure that
+ * if we observe event->ctx, both event and ctx will be
+ * complete enough. See perf_install_in_context().
+ */
+ if (!smp_load_acquire(&event->ctx))
+ continue;
+
if (event->state < PERF_EVENT_STATE_INACTIVE)
continue;
if (!event_filter_match(event))
raw_spin_unlock_irqrestore(&ifh->lock, flags);
if (restart)
- perf_event_restart(event);
+ perf_event_stop(event, 1);
}
void perf_event_exec(void)
/*
* In case of inheritance, it will be the parent that links to the
- * ring-buffer, but it will be the child that's actually using it:
+ * ring-buffer, but it will be the child that's actually using it.
+ *
+ * We are using event::rb to determine if the event should be stopped,
+ * however this may race with ring_buffer_attach() (through set_output),
+ * which will make us skip the event that actually needs to be stopped.
+ * So ring_buffer_attach() has to stop an aux event before re-assigning
+ * its rb pointer.
*/
if (rcu_dereference(parent->rb) == rb)
ro->err = __perf_event_stop(&sd);
{
struct perf_event *event = info;
struct pmu *pmu = event->pmu;
- struct perf_cpu_context *cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+ struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
struct remote_output ro = {
.rb = event->rb,
};
kfree(buf);
}
-/*
- * Whether this @filter depends on a dynamic object which is not loaded
- * yet or its load addresses are not known.
- */
-static bool perf_addr_filter_needs_mmap(struct perf_addr_filter *filter)
-{
- return filter->filter && filter->inode;
-}
-
/*
* Check whether inode and address range match filter criteria.
*/
raw_spin_unlock_irqrestore(&ifh->lock, flags);
if (restart)
- perf_event_restart(event);
+ perf_event_stop(event, 1);
}
/*
struct perf_event_context *ctx;
int ctxn;
+ /*
+ * Data tracing isn't supported yet and as such there is no need
+ * to keep track of anything that isn't related to executable code:
+ */
+ if (!(vma->vm_flags & VM_EXEC))
+ return;
+
rcu_read_lock();
for_each_task_context_nr(ctxn) {
ctx = rcu_dereference(current->perf_event_ctxp[ctxn]);
list_for_each_entry(filter, &ifh->list, entry) {
event->addr_filters_offs[count] = 0;
- if (perf_addr_filter_needs_mmap(filter))
+ /*
+ * Adjust base offset if the filter is associated to a binary
+ * that needs to be mapped:
+ */
+ if (filter->inode)
event->addr_filters_offs[count] =
perf_addr_filter_apply(filter, mm);
mmput(mm);
restart:
- perf_event_restart(event);
+ perf_event_stop(event, 1);
}
/*
goto fail;
}
- if (token == IF_SRC_FILE) {
- filename = match_strdup(&args[2]);
+ if (token == IF_SRC_FILE || token == IF_SRC_FILEADDR) {
+ int fpos = filter->range ? 2 : 1;
+
+ filename = match_strdup(&args[fpos]);
if (!filename) {
ret = -ENOMEM;
goto fail;
if (!rb)
return NULL;
- if (!rb_has_aux(rb) || !atomic_inc_not_zero(&rb->aux_refcount))
+ if (!rb_has_aux(rb))
goto err;
/*
- * If rb::aux_mmap_count is zero (and rb_has_aux() above went through),
- * the aux buffer is in perf_mmap_close(), about to get freed.
+ * If aux_mmap_count is zero, the aux buffer is in perf_mmap_close(),
+ * about to get freed, so we leave immediately.
+ *
+ * Checking rb::aux_mmap_count and rb::refcount has to be done in
+ * the same order, see perf_mmap_close. Otherwise we end up freeing
+ * aux pages in this path, which is a bug, because in_atomic().
*/
if (!atomic_read(&rb->aux_mmap_count))
- goto err_put;
+ goto err;
+
+ if (!atomic_inc_not_zero(&rb->aux_refcount))
+ goto err;
/*
* Nesting is not supported for AUX area, make sure nested
mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
err = -EAGAIN;
ptep = page_check_address(page, mm, addr, &ptl, 0);
- if (!ptep)
+ if (!ptep) {
+ mem_cgroup_cancel_charge(kpage, memcg, false);
goto unlock;
+ }
get_page(kpage);
page_add_new_anon_rmap(kpage, vma, addr, false);
err = 0;
unlock:
- mem_cgroup_cancel_charge(kpage, memcg, false);
mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
unlock_page(page);
return err;
TASKS_RCU(preempt_enable());
exit_notify(tsk, group_dead);
proc_exit_connector(tsk);
-#ifdef CONFIG_NUMA
- task_lock(tsk);
- mpol_put(tsk->mempolicy);
- tsk->mempolicy = NULL;
- task_unlock(tsk);
-#endif
+ mpol_put_task_policy(tsk);
#ifdef CONFIG_FUTEX
if (unlikely(current->pi_state_cache))
kfree(current->pi_state_cache);
}
EXPORT_SYMBOL(get_mm_exe_file);
+/**
+ * get_task_exe_file - acquire a reference to the task's executable file
+ *
+ * Returns %NULL if task's mm (if any) has no associated executable file or
+ * this is a kernel thread with borrowed mm (see the comment above get_task_mm).
+ * User must release file via fput().
+ */
+struct file *get_task_exe_file(struct task_struct *task)
+{
+ struct file *exe_file = NULL;
+ struct mm_struct *mm;
+
+ task_lock(task);
+ mm = task->mm;
+ if (mm) {
+ if (!(task->flags & PF_KTHREAD))
+ exe_file = get_mm_exe_file(mm);
+ }
+ task_unlock(task);
+ return exe_file;
+}
+EXPORT_SYMBOL(get_task_exe_file);
+
/**
* get_task_mm - acquire a reference to the task's mm
*
deactivate_mm(tsk, mm);
/*
- * If we're exiting normally, clear a user-space tid field if
- * requested. We leave this alone when dying by signal, to leave
- * the value intact in a core dump, and to save the unnecessary
- * trouble, say, a killed vfork parent shouldn't touch this mm.
- * Userland only wants this done for a sys_exit.
+ * Signal userspace if we're not exiting with a core dump
+ * because we want to leave the value intact for debugging
+ * purposes.
*/
if (tsk->clear_child_tid) {
- if (!(tsk->flags & PF_SIGNALED) &&
+ if (!(tsk->signal->flags & SIGNAL_GROUP_COREDUMP) &&
atomic_read(&mm->mm_users) > 1) {
/*
* We don't check the error code - if userspace has
p->real_start_time = ktime_get_boot_ns();
p->io_context = NULL;
p->audit_context = NULL;
- threadgroup_change_begin(current);
cgroup_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_dup(p->mempolicy);
INIT_LIST_HEAD(&p->thread_group);
p->task_works = NULL;
+ threadgroup_change_begin(current);
/*
* Ensure that the cgroup subsystem policies allow the new process to be
* forked. It should be noted the the new process's css_set can be changed
bad_fork_cancel_cgroup:
cgroup_cancel_fork(p);
bad_fork_free_pid:
+ threadgroup_change_end(current);
if (pid != &init_struct_pid)
free_pid(pid);
bad_fork_cleanup_thread:
mpol_put(p->mempolicy);
bad_fork_cleanup_threadgroup_lock:
#endif
- threadgroup_change_end(current);
delayacct_tsk_free(p);
bad_fork_cleanup_count:
atomic_dec(&p->cred->user->processes);
* Futex flags used to encode options to functions and preserve them across
* restarts.
*/
-#define FLAGS_SHARED 0x01
+#ifdef CONFIG_MMU
+# define FLAGS_SHARED 0x01
+#else
+/*
+ * NOMMU does not have per process address space. Let the compiler optimize
+ * code away.
+ */
+# define FLAGS_SHARED 0x00
+#endif
#define FLAGS_CLOCKRT 0x02
#define FLAGS_HAS_TIMEOUT 0x04
if (!key->both.ptr)
return;
+ /*
+ * On MMU less systems futexes are always "private" as there is no per
+ * process address space. We need the smp wmb nevertheless - yes,
+ * arch/blackfin has MMU less SMP ...
+ */
+ if (!IS_ENABLED(CONFIG_MMU)) {
+ smp_mb(); /* explicit smp_mb(); (B) */
+ return;
+ }
+
switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
case FUT_OFF_INODE:
ihold(key->shared.inode); /* implies smp_mb(); (B) */
return;
}
+ if (!IS_ENABLED(CONFIG_MMU))
+ return;
+
switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
case FUT_OFF_INODE:
iput(key->shared.inode);
return NULL;
}
+ get_online_cpus();
if (max_vecs >= num_online_cpus()) {
cpumask_copy(affinity_mask, cpu_online_mask);
*nr_vecs = num_online_cpus();
}
*nr_vecs = vecs;
}
+ put_online_cpus();
return affinity_mask;
}
desc->name = name;
if (handle != handle_bad_irq && is_chained) {
+ unsigned int type = irqd_get_trigger_type(&desc->irq_data);
+
+ /*
+ * We're about to start this interrupt immediately,
+ * hence the need to set the trigger configuration.
+ * But the .set_type callback may have overridden the
+ * flow handler, ignoring that we're dealing with a
+ * chained interrupt. Reset it immediately because we
+ * do know better.
+ */
+ if (type != IRQ_TYPE_NONE) {
+ __irq_set_trigger(desc, type);
+ desc->handle_irq = handle;
+ }
+
irq_settings_set_noprobe(desc);
irq_settings_set_norequest(desc);
irq_settings_set_nothread(desc);
action->dev_id = dev_id;
retval = irq_chip_pm_get(&desc->irq_data);
- if (retval < 0)
+ if (retval < 0) {
+ kfree(action);
return retval;
+ }
chip_bus_lock(desc);
retval = __setup_irq(irq, desc, action);
action->percpu_dev_id = dev_id;
retval = irq_chip_pm_get(&desc->irq_data);
- if (retval < 0)
+ if (retval < 0) {
+ kfree(action);
return retval;
+ }
chip_bus_lock(desc);
retval = __setup_irq(irq, desc, action);
else
dev_dbg(dev, "irq [%d-%d] for MSI\n",
virq, virq + desc->nvec_used - 1);
+ /*
+ * This flag is set by the PCI layer as we need to activate
+ * the MSI entries before the PCI layer enables MSI in the
+ * card. Otherwise the card latches a random msi message.
+ */
+ if (info->flags & MSI_FLAG_ACTIVATE_EARLY) {
+ struct irq_data *irq_data;
+
+ irq_data = irq_domain_get_irq_data(domain, desc->irq);
+ irq_domain_activate_irq(irq_data);
+ }
}
return 0;
return 0;
out:
vfree(pi->sechdrs);
+ pi->sechdrs = NULL;
+
vfree(pi->purgatory_buf);
+ pi->purgatory_buf = NULL;
return ret;
}
goto gotlock;
}
}
- WRITE_ONCE(pn->state, vcpu_halted);
+ WRITE_ONCE(pn->state, vcpu_hashed);
qstat_inc(qstat_pv_wait_head, true);
qstat_inc(qstat_pv_wait_again, waitcnt);
pv_wait(&l->locked, _Q_SLOW_VAL);
*/
if ((counter == qstat_pv_latency_kick) ||
(counter == qstat_pv_latency_wake)) {
- stat = 0;
if (kicks)
stat = DIV_ROUND_CLOSEST_ULL(stat, kicks);
}
align_start = res->start & ~(SECTION_SIZE - 1);
align_size = ALIGN(resource_size(res), SECTION_SIZE);
arch_remove_memory(align_start, align_size);
+ untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
pgmap_radix_release(res);
dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc,
"%s: failed to free all reserved pages\n", __func__);
struct percpu_ref *ref, struct vmem_altmap *altmap)
{
resource_size_t key, align_start, align_size, align_end;
+ pgprot_t pgprot = PAGE_KERNEL;
struct dev_pagemap *pgmap;
struct page_map *page_map;
int error, nid, is_ram;
if (nid < 0)
nid = numa_mem_id();
+ error = track_pfn_remap(NULL, &pgprot, PHYS_PFN(align_start), 0,
+ align_size);
+ if (error)
+ goto err_pfn_remap;
+
error = arch_add_memory(nid, align_start, align_size, true);
if (error)
goto err_add_memory;
return __va(res->start);
err_add_memory:
+ untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
+ err_pfn_remap:
err_radix:
pgmap_radix_release(res);
devres_free(page_map);
save_processor_state();
trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, true);
error = swsusp_arch_suspend();
+ /* Restore control flow magically appears here */
+ restore_processor_state();
trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false);
if (error)
printk(KERN_ERR "PM: Error %d creating hibernation image\n",
error);
- /* Restore control flow magically appears here */
- restore_processor_state();
if (!in_suspend)
events_check_enabled = false;
return;
}
- cancel_delayed_work_sync(&req->work);
+ /*
+ * This function may be called very early during boot, for example,
+ * from of_clk_init(), where irq needs to stay disabled.
+ * cancel_delayed_work_sync() assumes that irq is enabled on
+ * invocation and re-enables it on return. Avoid calling it until
+ * workqueue is initialized.
+ */
+ if (keventd_up())
+ cancel_delayed_work_sync(&req->work);
+
__pm_qos_update_request(req, new_value);
}
EXPORT_SYMBOL_GPL(pm_qos_update_request);
*/
static bool rtree_next_node(struct memory_bitmap *bm)
{
- bm->cur.node = list_entry(bm->cur.node->list.next,
- struct rtree_node, list);
- if (&bm->cur.node->list != &bm->cur.zone->leaves) {
+ if (!list_is_last(&bm->cur.node->list, &bm->cur.zone->leaves)) {
+ bm->cur.node = list_entry(bm->cur.node->list.next,
+ struct rtree_node, list);
bm->cur.node_pfn += BM_BITS_PER_BLOCK;
bm->cur.node_bit = 0;
touch_softlockup_watchdog();
}
/* No more nodes, goto next zone */
- bm->cur.zone = list_entry(bm->cur.zone->list.next,
+ if (!list_is_last(&bm->cur.zone->list, &bm->zones)) {
+ bm->cur.zone = list_entry(bm->cur.zone->list.next,
struct mem_zone_bm_rtree, list);
- if (&bm->cur.zone->list != &bm->zones) {
bm->cur.node = list_entry(bm->cur.zone->leaves.next,
struct rtree_node, list);
bm->cur.node_pfn = 0;
char *_braille_console_setup(char **str, char **brl_options)
{
- if (!memcmp(*str, "brl,", 4)) {
+ if (!strncmp(*str, "brl,", 4)) {
*brl_options = "";
*str += 4;
- } else if (!memcmp(str, "brl=", 4)) {
+ } else if (!strncmp(*str, "brl=", 4)) {
*brl_options = *str + 4;
*str = strchr(*brl_options, ',');
if (!*str)
*/
#include <linux/percpu.h>
-typedef __printf(2, 0) int (*printk_func_t)(int level, const char *fmt,
- va_list args);
+typedef __printf(1, 0) int (*printk_func_t)(const char *fmt, va_list args);
-__printf(2, 0)
-int vprintk_default(int level, const char *fmt, va_list args);
+int __printf(1, 0) vprintk_default(const char *fmt, va_list args);
#ifdef CONFIG_PRINTK_NMI
* via per-CPU variable.
*/
DECLARE_PER_CPU(printk_func_t, printk_func);
-__printf(2, 0)
-static inline int vprintk_func(int level, const char *fmt, va_list args)
+static inline __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
{
- return this_cpu_read(printk_func)(level, fmt, args);
+ return this_cpu_read(printk_func)(fmt, args);
}
extern atomic_t nmi_message_lost;
#else /* CONFIG_PRINTK_NMI */
-__printf(2, 0)
-static inline int vprintk_func(int level, const char *fmt, va_list args)
+static inline __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
{
- return vprintk_default(level, fmt, args);
+ return vprintk_default(fmt, args);
}
static inline int get_nmi_message_lost(void)
* one writer running. But the buffer might get flushed from another
* CPU, so we need to be careful.
*/
-static int vprintk_nmi(int level, const char *fmt, va_list args)
+static int vprintk_nmi(const char *fmt, va_list args)
{
struct nmi_seq_buf *s = this_cpu_ptr(&nmi_print_seq);
int add = 0;
if (!len)
smp_rmb();
- if (level != LOGLEVEL_DEFAULT) {
- add = snprintf(s->buffer + len, sizeof(s->buffer) - len,
- KERN_SOH "%c", '0' + level);
- add += vsnprintf(s->buffer + len + add,
- sizeof(s->buffer) - len - add,
- fmt, args);
- } else {
- add = vsnprintf(s->buffer + len, sizeof(s->buffer) - len,
- fmt, args);
- }
+ add = vsnprintf(s->buffer + len, sizeof(s->buffer) - len, fmt, args);
/*
* Do it once again if the buffer has been flushed in the meantime.
return add;
}
-/*
- * printk one line from the temporary buffer from @start index until
- * and including the @end index.
- */
-static void print_nmi_seq_line(struct nmi_seq_buf *s, int start, int end)
+static void printk_nmi_flush_line(const char *text, int len)
{
- const char *buf = s->buffer + start;
-
/*
* The buffers are flushed in NMI only on panic. The messages must
* go only into the ring buffer at this stage. Consoles will get
* explicitly called later when a crashdump is not generated.
*/
if (in_nmi())
- printk_deferred("%.*s", (end - start) + 1, buf);
+ printk_deferred("%.*s", len, text);
else
- printk("%.*s", (end - start) + 1, buf);
+ printk("%.*s", len, text);
+
+}
+/*
+ * printk one line from the temporary buffer from @start index until
+ * and including the @end index.
+ */
+static void printk_nmi_flush_seq_line(struct nmi_seq_buf *s,
+ int start, int end)
+{
+ const char *buf = s->buffer + start;
+
+ printk_nmi_flush_line(buf, (end - start) + 1);
}
/*
* the buffer an unexpected way. If we printed something then
* @len must only increase.
*/
- if (i && i >= len)
- pr_err("printk_nmi_flush: internal error: i=%d >= len=%zu\n",
- i, len);
+ if (i && i >= len) {
+ const char *msg = "printk_nmi_flush: internal error\n";
+
+ printk_nmi_flush_line(msg, strlen(msg));
+ }
if (!len)
goto out; /* Someone else has already flushed the buffer. */
/* Print line by line. */
for (; i < size; i++) {
if (s->buffer[i] == '\n') {
- print_nmi_seq_line(s, last_i, i);
+ printk_nmi_flush_seq_line(s, last_i, i);
last_i = i + 1;
}
}
/* Check if there was a partial line. */
if (last_i < size) {
- print_nmi_seq_line(s, last_i, size - 1);
- pr_cont("\n");
+ printk_nmi_flush_seq_line(s, last_i, size - 1);
+ printk_nmi_flush_line("\n", strlen("\n"));
}
/*
}
EXPORT_SYMBOL(printk_emit);
-#ifdef CONFIG_PRINTK
-#define define_pr_level(func, loglevel) \
-asmlinkage __visible void func(const char *fmt, ...) \
-{ \
- va_list args; \
- \
- va_start(args, fmt); \
- vprintk_default(loglevel, fmt, args); \
- va_end(args); \
-} \
-EXPORT_SYMBOL(func)
-
-define_pr_level(__pr_emerg, LOGLEVEL_EMERG);
-define_pr_level(__pr_alert, LOGLEVEL_ALERT);
-define_pr_level(__pr_crit, LOGLEVEL_CRIT);
-define_pr_level(__pr_err, LOGLEVEL_ERR);
-define_pr_level(__pr_warn, LOGLEVEL_WARNING);
-define_pr_level(__pr_notice, LOGLEVEL_NOTICE);
-define_pr_level(__pr_info, LOGLEVEL_INFO);
-#endif
-
-int vprintk_default(int level, const char *fmt, va_list args)
+int vprintk_default(const char *fmt, va_list args)
{
int r;
return r;
}
#endif
- r = vprintk_emit(0, level, NULL, 0, fmt, args);
+ r = vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args);
return r;
}
int r;
va_start(args, fmt);
- r = vprintk_func(LOGLEVEL_DEFAULT, fmt, args);
+ r = vprintk_func(fmt, args);
va_end(args);
return r;
#include <linux/context_tracking.h>
#include <linux/compiler.h>
#include <linux/frame.h>
+#include <linux/prefetch.h>
#include <asm/switch_to.h>
#include <asm/tlb.h>
success = 1; /* we're going to change ->state */
cpu = task_cpu(p);
+ /*
+ * Ensure we load p->on_rq _after_ p->state, otherwise it would
+ * be possible to, falsely, observe p->on_rq == 0 and get stuck
+ * in smp_cond_load_acquire() below.
+ *
+ * sched_ttwu_pending() try_to_wake_up()
+ * [S] p->on_rq = 1; [L] P->state
+ * UNLOCK rq->lock -----.
+ * \
+ * +--- RMB
+ * schedule() /
+ * LOCK rq->lock -----'
+ * UNLOCK rq->lock
+ *
+ * [task p]
+ * [S] p->state = UNINTERRUPTIBLE [L] p->on_rq
+ *
+ * Pairs with the UNLOCK+LOCK on rq->lock from the
+ * last wakeup of our task and the schedule that got our task
+ * current.
+ */
+ smp_rmb();
if (p->on_rq && ttwu_remote(p, wake_flags))
goto stat;
EXPORT_PER_CPU_SYMBOL(kstat);
EXPORT_PER_CPU_SYMBOL(kernel_cpustat);
+/*
+ * The function fair_sched_class.update_curr accesses the struct curr
+ * and its field curr->exec_start; when called from task_sched_runtime(),
+ * we observe a high rate of cache misses in practice.
+ * Prefetching this data results in improved performance.
+ */
+static inline void prefetch_curr_exec_start(struct task_struct *p)
+{
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ struct sched_entity *curr = (&p->se)->cfs_rq->curr;
+#else
+ struct sched_entity *curr = (&task_rq(p)->cfs)->curr;
+#endif
+ prefetch(curr);
+ prefetch(&curr->exec_start);
+}
+
/*
* Return accounted runtime for the task.
* In case the task is currently running, return the runtime plus current's
* thread, breaking clock_gettime().
*/
if (task_current(rq, p) && task_on_rq_queued(p)) {
+ prefetch_curr_exec_start(p);
update_rq_clock(rq);
p->sched_class->update_curr(rq);
}
if (old_idx == IDX_INVALID) {
cp->size++;
- cp->elements[cp->size - 1].dl = 0;
+ cp->elements[cp->size - 1].dl = dl;
cp->elements[cp->size - 1].cpu = cpu;
cp->elements[cpu].idx = cp->size - 1;
cpudl_change_key(cp, cp->size - 1, dl);
cpustat[CPUTIME_IDLE] += (__force u64) cputime;
}
+/*
+ * When a guest is interrupted for a longer amount of time, missed clock
+ * ticks are not redelivered later. Due to that, this function may on
+ * occasion account more time than the calling functions think elapsed.
+ */
static __always_inline cputime_t steal_account_process_time(cputime_t maxtime)
{
#ifdef CONFIG_PARAVIRT
* idle, or potentially user or system time. Due to rounding,
* other time can exceed ticks occasionally.
*/
- other = account_other_time(cputime);
+ other = account_other_time(ULONG_MAX);
if (other >= cputime)
return;
cputime -= other;
}
cputime = cputime_one_jiffy;
- steal = steal_account_process_time(cputime);
+ steal = steal_account_process_time(ULONG_MAX);
if (steal >= cputime)
return;
*/
void account_idle_ticks(unsigned long ticks)
{
+ cputime_t cputime, steal;
if (sched_clock_irqtime) {
irqtime_account_idle_ticks(ticks);
return;
}
- account_idle_time(jiffies_to_cputime(ticks));
+ cputime = jiffies_to_cputime(ticks);
+ steal = steal_account_process_time(ULONG_MAX);
+
+ if (steal >= cputime)
+ return;
+
+ cputime -= steal;
+ account_idle_time(cputime);
}
/*
stime = curr->stime;
utime = curr->utime;
- if (utime == 0) {
- stime = rtime;
+ /*
+ * If either stime or both stime and utime are 0, assume all runtime is
+ * userspace. Once a task gets some ticks, the monotonicy code at
+ * 'update' will ensure things converge to the observed ratio.
+ */
+ if (stime == 0) {
+ utime = rtime;
goto update;
}
- if (stime == 0) {
- utime = rtime;
+ if (utime == 0) {
+ stime = rtime;
goto update;
}
stime = scale_stime((__force u64)stime, (__force u64)rtime,
(__force u64)(stime + utime));
+update:
/*
* Make sure stime doesn't go backwards; this preserves monotonicity
* for utime because rtime is monotonic.
stime = rtime - utime;
}
-update:
prev->stime = stime;
prev->utime = utime;
out:
unsigned long now = READ_ONCE(jiffies);
cputime_t delta, other;
+ /*
+ * Unlike tick based timing, vtime based timing never has lost
+ * ticks, and no need for steal time accounting to make up for
+ * lost ticks. Vtime accounts a rounded version of actual
+ * elapsed time. Limit account_other_time to prevent rounding
+ * errors from causing elapsed vtime to go negative.
+ */
delta = jiffies_to_cputime(now - tsk->vtime_snap);
other = account_other_time(delta);
WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE);
*
* XXX figure out if select_task_rq_dl() deals with offline cpus.
*/
- if (unlikely(!rq->online))
+ if (unlikely(!rq->online)) {
+ lockdep_unpin_lock(&rq->lock, rf.cookie);
rq = dl_task_offline_migration(rq, p);
+ rf.cookie = lockdep_pin_lock(&rq->lock);
+ }
/*
* Queueing this task back might have overloaded rq, check if we need
pcfs_rq = tg->parent->cfs_rq[cpu];
cfs_rq->throttle_count = pcfs_rq->throttle_count;
- pcfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu));
+ cfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu));
}
/* conditionally throttle active cfs_rq's from put_prev_entity() */
ptrace_event(PTRACE_EVENT_SECCOMP, data);
/*
* The delivery of a fatal signal during event
- * notification may silently skip tracer notification.
- * Terminating the task now avoids executing a system
- * call that may not be intended.
+ * notification may silently skip tracer notification,
+ * which could leave us with a potentially unmodified
+ * syscall that the tracer would have liked to have
+ * changed. Since the process is about to die, we just
+ * force the syscall to be skipped and let the signal
+ * kill the process and correctly handle any tracer exit
+ * notifications.
*/
if (fatal_signal_pending(current))
- do_exit(SIGSYS);
+ goto skip;
/* Check if the tracer forced the syscall to be skipped. */
this_syscall = syscall_get_nr(current, task_pt_regs(current));
if (this_syscall < 0)
return 0;
}
+static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp,
+ int *valp,
+ int write, void *data)
+{
+ if (write) {
+ if (*negp)
+ return -EINVAL;
+ *valp = *lvalp;
+ } else {
+ unsigned int val = *valp;
+ *lvalp = (unsigned long)val;
+ }
+ return 0;
+}
+
static const char proc_wspace_sep[] = { ' ', '\t', '\n' };
static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
int proc_dointvec(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- return do_proc_dointvec(table,write,buffer,lenp,ppos,
- NULL,NULL);
+ return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL);
+}
+
+/**
+ * proc_douintvec - read a vector of unsigned integers
+ * @table: the sysctl table
+ * @write: %TRUE if this is a write to the sysctl file
+ * @buffer: the user buffer
+ * @lenp: the size of the user buffer
+ * @ppos: file position
+ *
+ * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer
+ * values from/to the user buffer, treated as an ASCII string.
+ *
+ * Returns 0 on success.
+ */
+int proc_douintvec(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ return do_proc_dointvec(table, write, buffer, lenp, ppos,
+ do_proc_douintvec_conv, NULL);
}
/*
return -ENOSYS;
}
+int proc_douintvec(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ return -ENOSYS;
+}
+
int proc_dointvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
* exception granted :-)
*/
EXPORT_SYMBOL(proc_dointvec);
+EXPORT_SYMBOL(proc_douintvec);
EXPORT_SYMBOL(proc_dointvec_jiffies);
EXPORT_SYMBOL(proc_dointvec_minmax);
EXPORT_SYMBOL(proc_dointvec_userhz_jiffies);
ktime_t now, expires;
int cpu = smp_processor_id();
+ now = tick_nohz_start_idle(ts);
+
if (can_stop_idle_tick(cpu, ts)) {
int was_stopped = ts->tick_stopped;
- now = tick_nohz_start_idle(ts);
ts->idle_calls++;
expires = tick_nohz_stop_sched_tick(ts, now, cpu);
do {
seq = raw_read_seqcount_latch(&tkf->seq);
tkr = tkf->base + (seq & 0x01);
- now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr);
+ now = ktime_to_ns(tkr->base);
+
+ now += clocksource_delta(tkr->read(tkr->clock),
+ tkr->cycle_last, tkr->mask);
} while (read_seqcount_retry(&tkf->seq, seq));
return now;
#include "timekeeping_internal.h"
-static unsigned int sleep_time_bin[32] = {0};
+#define NUM_BINS 32
+
+static unsigned int sleep_time_bin[NUM_BINS] = {0};
static int tk_debug_show_sleep_time(struct seq_file *s, void *data)
{
void tk_debug_account_sleep_time(struct timespec64 *t)
{
- sleep_time_bin[fls(t->tv_sec)]++;
+ /* Cap bin index so we don't overflow the array */
+ int bin = min(fls(t->tv_sec), NUM_BINS-1);
+
+ sleep_time_bin[bin]++;
}
struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
u64 expires = KTIME_MAX;
unsigned long nextevt;
+ bool is_max_delta;
/*
* Pretend that there is no timer pending if the cpu is offline.
spin_lock(&base->lock);
nextevt = __next_timer_interrupt(base);
+ is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA);
base->next_expiry = nextevt;
/*
* We have a fresh next event. Check whether we can forward the base:
expires = basem;
base->is_idle = false;
} else {
- expires = basem + (nextevt - basej) * TICK_NSEC;
+ if (!is_max_delta)
+ expires = basem + (nextevt - basej) * TICK_NSEC;
/*
* If we expect to sleep more than a tick, mark the base idle:
*/
what |= MASK_TC_BIT(op_flags, META);
what |= MASK_TC_BIT(op_flags, PREFLUSH);
what |= MASK_TC_BIT(op_flags, FUA);
- if (op == REQ_OP_DISCARD)
+ if (op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)
what |= BLK_TC_ACT(BLK_TC_DISCARD);
if (op == REQ_OP_FLUSH)
what |= BLK_TC_ACT(BLK_TC_FLUSH);
struct trace_iterator *iter = filp->private_data;
ssize_t sret;
- /* return any leftover data */
- sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
- if (sret != -EBUSY)
- return sret;
-
- trace_seq_init(&iter->seq);
-
/*
* Avoid more than one consumer on a single file descriptor
* This is just a matter of traces coherency, the ring buffer itself
* is protected.
*/
mutex_lock(&iter->mutex);
+
+ /* return any leftover data */
+ sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
+ if (sret != -EBUSY)
+ goto out;
+
+ trace_seq_init(&iter->seq);
+
if (iter->trace->read) {
sret = iter->trace->read(iter, filp, ubuf, cnt, ppos);
if (sret)
return -EBUSY;
#endif
- if (splice_grow_spd(pipe, &spd))
- return -ENOMEM;
-
if (*ppos & (PAGE_SIZE - 1))
return -EINVAL;
len &= PAGE_MASK;
}
+ if (splice_grow_spd(pipe, &spd))
+ return -ENOMEM;
+
again:
trace_access_lock(iter->cpu_file);
entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file);
/* did we read anything? */
if (!spd.nr_pages) {
if (ret)
- return ret;
+ goto out;
+ ret = -EAGAIN;
if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK))
- return -EAGAIN;
+ goto out;
ret = wait_on_pipe(iter, true);
if (ret)
- return ret;
+ goto out;
goto again;
}
ret = splice_to_pipe(pipe, &spd);
+out:
splice_shrink_spd(&spd);
return ret;
help
Say Y here to enable the kernel to detect "hung tasks",
which are bugs that cause the task to be stuck in
- uninterruptible "D" state indefinitiley.
+ uninterruptible "D" state indefinitely.
When a hung task is detected, the kernel will print the
current stack trace (which you should report), but the
Enable this option if you want to use the LatencyTOP tool
to find out which userspace is blocking on what kernel operations.
-config ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
- bool
-
-config DEBUG_STRICT_USER_COPY_CHECKS
- bool "Strict user copy size checks"
- depends on ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
- depends on DEBUG_KERNEL && !TRACE_BRANCH_PROFILING
- help
- Enabling this option turns a certain set of sanity checks for user
- copy operations into compile time failures.
-
- The copy_from_user() etc checks are there to help test if there
- are sufficient security checks on the length argument of
- the copy operation, by having gcc prove that the argument is
- within bounds.
-
- If unsure, say N.
-
source kernel/trace/Kconfig
menu "Runtime Testing"
is_single_threaded.o plist.o decompress.o kobject_uevent.o \
earlycpio.o seq_buf.o nmi_backtrace.o nodemask.o
-obj-$(CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS) += usercopy.o
lib-$(CONFIG_MMU) += ioremap.o
lib-$(CONFIG_SMP) += cpumask.o
lib-$(CONFIG_HAS_DMA) += dma-noop.o
return wanted - bytes;
}
-/*
- * Fault in the first iovec of the given iov_iter, to a maximum length
- * of bytes. Returns 0 on success, or non-zero if the memory could not be
- * accessed (ie. because it is an invalid address).
- *
- * writev-intensive code may want this to prefault several iovecs -- that
- * would be possible (callers must not rely on the fact that _only_ the
- * first iovec will be faulted with the current implementation).
- */
-int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
-{
- if (!(i->type & (ITER_BVEC|ITER_KVEC))) {
- char __user *buf = i->iov->iov_base + i->iov_offset;
- bytes = min(bytes, i->iov->iov_len - i->iov_offset);
- return fault_in_pages_readable(buf, bytes);
- }
- return 0;
-}
-EXPORT_SYMBOL(iov_iter_fault_in_readable);
-
/*
* Fault in one or more iovecs of the given iov_iter, to a maximum length of
* bytes. For each iovec, fault in each page that constitutes the iovec.
* Return 0 on success, or non-zero if the memory could not be accessed (i.e.
* because it is an invalid address).
*/
-int iov_iter_fault_in_multipages_readable(struct iov_iter *i, size_t bytes)
+int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes)
{
size_t skip = i->iov_offset;
const struct iovec *iov;
}
return 0;
}
-EXPORT_SYMBOL(iov_iter_fault_in_multipages_readable);
+EXPORT_SYMBOL(iov_iter_fault_in_readable);
void iov_iter_init(struct iov_iter *i, int direction,
const struct iovec *iov, unsigned long nr_segs,
#ifdef CONFIG_RADIX_TREE_MULTIORDER
if (radix_tree_is_internal_node(entry)) {
- unsigned long siboff = get_slot_offset(parent, entry);
- if (siboff < RADIX_TREE_MAP_SIZE) {
- offset = siboff;
- entry = rcu_dereference_raw(parent->slots[offset]);
+ if (is_sibling_entry(parent, entry)) {
+ void **sibentry = (void **) entry_to_node(entry);
+ offset = get_slot_offset(parent, sibentry);
+ entry = rcu_dereference_raw(*sibentry);
}
}
#endif
#define HASH_DEFAULT_SIZE 64UL
#define HASH_MIN_SIZE 4U
-#define BUCKET_LOCKS_PER_CPU 128UL
+#define BUCKET_LOCKS_PER_CPU 32UL
static u32 head_hashfn(struct rhashtable *ht,
const struct bucket_table *tbl,
unsigned int nr_pcpus = num_possible_cpus();
#endif
- nr_pcpus = min_t(unsigned int, nr_pcpus, 32UL);
+ nr_pcpus = min_t(unsigned int, nr_pcpus, 64UL);
size = roundup_pow_of_two(nr_pcpus * ht->p.locks_mul);
/* Never allocate more than 0.5 locks per bucket */
size = min_t(unsigned int, size, tbl->size >> 1);
if (sizeof(spinlock_t) != 0) {
+ tbl->locks = NULL;
#ifdef CONFIG_NUMA
if (size * sizeof(spinlock_t) > PAGE_SIZE &&
gfp == GFP_KERNEL)
tbl->locks = vmalloc(size * sizeof(spinlock_t));
- else
#endif
- tbl->locks = kmalloc_array(size, sizeof(spinlock_t),
- gfp);
+ if (gfp != GFP_KERNEL)
+ gfp |= __GFP_NOWARN | __GFP_NORETRY;
+
+ if (!tbl->locks)
+ tbl->locks = kmalloc_array(size, sizeof(spinlock_t),
+ gfp);
if (!tbl->locks)
return -ENOMEM;
for (i = 0; i < size; i++)
static int rhashtable_shrink(struct rhashtable *ht)
{
struct bucket_table *new_tbl, *old_tbl = rht_dereference(ht->tbl, ht);
- unsigned int size;
+ unsigned int nelems = atomic_read(&ht->nelems);
+ unsigned int size = 0;
int err;
ASSERT_RHT_MUTEX(ht);
- size = roundup_pow_of_two(atomic_read(&ht->nelems) * 3 / 2);
+ if (nelems)
+ size = roundup_pow_of_two(nelems * 3 / 2);
if (size < ht->p.min_size)
size = ht->p.min_size;
unsigned long c, data;
/* Fall back to byte-at-a-time if we get a page fault */
- if (unlikely(unsafe_get_user(c,(unsigned long __user *)(src+res))))
- break;
+ unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time);
+
*(unsigned long *)(dst+res) = c;
if (has_zero(c, &data, &constants)) {
data = prep_zero_mask(c, data, &constants);
while (max) {
char c;
- if (unlikely(unsafe_get_user(c,src+res)))
- return -EFAULT;
+ unsafe_get_user(c,src+res, efault);
dst[res] = c;
if (!c)
return res;
* Nope: we hit the address space limit, and we still had more
* characters the caller would have wanted. That's an EFAULT.
*/
+efault:
return -EFAULT;
}
src -= align;
max += align;
- if (unlikely(unsafe_get_user(c,(unsigned long __user *)src)))
- return 0;
+ unsafe_get_user(c, (unsigned long __user *)src, efault);
c |= aligned_byte_mask(align);
for (;;) {
if (unlikely(max <= sizeof(unsigned long)))
break;
max -= sizeof(unsigned long);
- if (unlikely(unsafe_get_user(c,(unsigned long __user *)(src+res))))
- return 0;
+ unsafe_get_user(c, (unsigned long __user *)(src+res), efault);
}
res -= align;
* Nope: we hit the address space limit, and we still had more
* characters the caller would have wanted. That's 0.
*/
+efault:
return 0;
}
test_hash_init(void)
{
char buf[SIZE+1];
- u32 string_or = 0, hash_or[2][33] = { 0 };
+ u32 string_or = 0, hash_or[2][33] = { { 0, } };
unsigned tests = 0;
unsigned long long h64 = 0;
int i, j;
}
/* Issue notices about skipped tests. */
-#ifndef HAVE_ARCH__HASH_32
- pr_info("__hash_32() has no arch implementation to test.");
-#elif HAVE_ARCH__HASH_32 != 1
+#ifdef HAVE_ARCH__HASH_32
+#if HAVE_ARCH__HASH_32 != 1
pr_info("__hash_32() is arch-specific; not compared to generic.");
#endif
-#ifndef HAVE_ARCH_HASH_32
- pr_info("hash_32() has no arch implementation to test.");
-#elif HAVE_ARCH_HASH_32 != 1
+#else
+ pr_info("__hash_32() has no arch implementation to test.");
+#endif
+#ifdef HAVE_ARCH_HASH_32
+#if HAVE_ARCH_HASH_32 != 1
pr_info("hash_32() is arch-specific; not compared to generic.");
#endif
-#ifndef HAVE_ARCH_HASH_64
- pr_info("hash_64() has no arch implementation to test.");
-#elif HAVE_ARCH_HASH_64 != 1
+#else
+ pr_info("hash_32() has no arch implementation to test.");
+#endif
+#ifdef HAVE_ARCH_HASH_64
+#if HAVE_ARCH_HASH_64 != 1
pr_info("hash_64() is arch-specific; not compared to generic.");
#endif
+#else
+ pr_info("hash_64() has no arch implementation to test.");
+#endif
pr_notice("%u tests passed.", tests);
static int max_size = 0;
module_param(max_size, int, 0);
-MODULE_PARM_DESC(runs, "Maximum table size (default: calculated)");
+MODULE_PARM_DESC(max_size, "Maximum table size (default: calculated)");
static bool shrinking = false;
module_param(shrinking, bool, 0);
+++ /dev/null
-#include <linux/export.h>
-#include <linux/bug.h>
-#include <linux/uaccess.h>
-
-void copy_from_user_overflow(void)
-{
- WARN(1, "Buffer overflow detected!\n");
-}
-EXPORT_SYMBOL(copy_from_user_overflow);
select MIGRATION
depends on MMU
help
- Allows the compaction of memory for the allocation of huge pages.
+ Compaction is the only memory management component to form
+ high order (larger physically contiguous) memory blocks
+ reliably. The page allocator relies on compaction heavily and
+ the lack of the feature can lead to unexpected OOM killer
+ invocations for high order memory requests. You shouldn't
+ disable this option unless there really is a strong reason for
+ it and then we would be really interested to hear about that at
+ linux-mm@kvack.org.
#
# support for page migration
KCOV_INSTRUMENT_mmzone.o := n
KCOV_INSTRUMENT_vmstat.o := n
+# Since __builtin_frame_address does work as used, disable the warning.
+CFLAGS_usercopy.o += $(call cc-disable-warning, frame-address)
+
mmu-y := nommu.o
mmu-$(CONFIG_MMU) := gup.o highmem.o memory.o mincore.o \
mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \
obj-$(CONFIG_IDLE_PAGE_TRACKING) += page_idle.o
obj-$(CONFIG_FRAME_VECTOR) += frame_vector.o
obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o
+obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o
void __dump_page(struct page *page, const char *reason)
{
+ int mapcount = PageSlab(page) ? 0 : page_mapcount(page);
+
pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx",
- page, page_ref_count(page), page_mapcount(page),
- page->mapping, page->index);
+ page, page_ref_count(page), mapcount,
+ page->mapping, page_to_pgoff(page));
if (PageCompound(page))
pr_cont(" compound_mapcount: %d", compound_mapcount(page));
pr_cont("\n");
goto out;
page = pmd_page(*pmd);
- VM_BUG_ON_PAGE(!PageHead(page), page);
+ VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);
if (flags & FOLL_TOUCH)
touch_pmd(vma, addr, pmd);
if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
}
skip_mlock:
page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
- VM_BUG_ON_PAGE(!PageCompound(page), page);
+ VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page);
if (flags & FOLL_GET)
get_page(page);
bool was_writable;
int flags = 0;
- /* A PROT_NONE fault should not end up here */
- BUG_ON(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)));
-
fe->ptl = pmd_lock(vma->vm_mm, fe->pmd);
if (unlikely(!pmd_same(pmd, *fe->pmd)))
goto out_unlock;
struct page *page;
pgtable_t pgtable;
pmd_t _pmd;
- bool young, write, dirty;
+ bool young, write, dirty, soft_dirty;
unsigned long addr;
int i;
write = pmd_write(*pmd);
young = pmd_young(*pmd);
dirty = pmd_dirty(*pmd);
+ soft_dirty = pmd_soft_dirty(*pmd);
pmdp_huge_split_prepare(vma, haddr, pmd);
pgtable = pgtable_trans_huge_withdraw(mm, pmd);
swp_entry_t swp_entry;
swp_entry = make_migration_entry(page + i, write);
entry = swp_entry_to_pte(swp_entry);
+ if (soft_dirty)
+ entry = pte_swp_mksoft_dirty(entry);
} else {
entry = mk_pte(page + i, vma->vm_page_prot);
entry = maybe_mkwrite(entry, vma);
entry = pte_wrprotect(entry);
if (!young)
entry = pte_mkold(entry);
+ if (soft_dirty)
+ entry = pte_mksoft_dirty(entry);
}
if (dirty)
SetPageDirty(page + i);
list_del(&page->lru);
h->free_huge_pages--;
h->free_huge_pages_node[nid]--;
+ h->max_huge_pages--;
update_and_free_page(h, page);
}
spin_unlock(&hugetlb_lock);
new_quarantine_size = (READ_ONCE(totalram_pages) << PAGE_SHIFT) /
QUARANTINE_FRACTION;
percpu_quarantines = QUARANTINE_PERCPU_SIZE * num_online_cpus();
- if (WARN_ONCE(new_quarantine_size < percpu_quarantines,
- "Too little memory, disabling global KASAN quarantine.\n"))
- new_quarantine_size = 0;
- else
- new_quarantine_size -= percpu_quarantines;
+ new_quarantine_size = (new_quarantine_size < percpu_quarantines) ?
+ 0 : new_quarantine_size - percpu_quarantines;
WRITE_ONCE(quarantine_size, new_quarantine_size);
last = global_quarantine.head;
* value (scan code).
*/
-static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address)
+static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
+ struct vm_area_struct **vmap)
{
struct vm_area_struct *vma;
unsigned long hstart, hend;
if (unlikely(khugepaged_test_exit(mm)))
return SCAN_ANY_PROCESS;
- vma = find_vma(mm, address);
+ *vmap = vma = find_vma(mm, address);
if (!vma)
return SCAN_VMA_NULL;
.pmd = pmd,
};
+ /* we only decide to swapin, if there is enough young ptes */
+ if (referenced < HPAGE_PMD_NR/2) {
+ trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
+ return false;
+ }
fe.pte = pte_offset_map(pmd, address);
for (; fe.address < address + HPAGE_PMD_NR*PAGE_SIZE;
fe.pte++, fe.address += PAGE_SIZE) {
if (!is_swap_pte(pteval))
continue;
swapped_in++;
- /* we only decide to swapin, if there is enough young ptes */
- if (referenced < HPAGE_PMD_NR/2) {
- trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
- return false;
- }
ret = do_swap_page(&fe, pteval);
/* do_swap_page returns VM_FAULT_RETRY with released mmap_sem */
if (ret & VM_FAULT_RETRY) {
down_read(&mm->mmap_sem);
- if (hugepage_vma_revalidate(mm, address)) {
+ if (hugepage_vma_revalidate(mm, address, &fe.vma)) {
/* vma is no longer available, don't continue to swapin */
trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
return false;
static void collapse_huge_page(struct mm_struct *mm,
unsigned long address,
struct page **hpage,
- struct vm_area_struct *vma,
int node, int referenced)
{
pmd_t *pmd, _pmd;
spinlock_t *pmd_ptl, *pte_ptl;
int isolated = 0, result = 0;
struct mem_cgroup *memcg;
+ struct vm_area_struct *vma;
unsigned long mmun_start; /* For mmu_notifiers */
unsigned long mmun_end; /* For mmu_notifiers */
gfp_t gfp;
}
down_read(&mm->mmap_sem);
- result = hugepage_vma_revalidate(mm, address);
+ result = hugepage_vma_revalidate(mm, address, &vma);
if (result) {
mem_cgroup_cancel_charge(new_page, memcg, true);
up_read(&mm->mmap_sem);
* handled by the anon_vma lock + PG_lock.
*/
down_write(&mm->mmap_sem);
- result = hugepage_vma_revalidate(mm, address);
+ result = hugepage_vma_revalidate(mm, address, &vma);
if (result)
goto out;
/* check if the pmd is still valid */
if (ret) {
node = khugepaged_find_target_node();
/* collapse_huge_page will return with the mmap_sem released */
- collapse_huge_page(mm, address, hpage, vma, node, referenced);
+ collapse_huge_page(mm, address, hpage, node, referenced);
}
out:
trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced,
static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
{
struct memcg_stock_pcp *stock;
+ unsigned long flags;
bool ret = false;
if (nr_pages > CHARGE_BATCH)
return ret;
- stock = &get_cpu_var(memcg_stock);
+ local_irq_save(flags);
+
+ stock = this_cpu_ptr(&memcg_stock);
if (memcg == stock->cached && stock->nr_pages >= nr_pages) {
stock->nr_pages -= nr_pages;
ret = true;
}
- put_cpu_var(memcg_stock);
+
+ local_irq_restore(flags);
+
return ret;
}
stock->cached = NULL;
}
-/*
- * This must be called under preempt disabled or must be called by
- * a thread which is pinned to local cpu.
- */
static void drain_local_stock(struct work_struct *dummy)
{
- struct memcg_stock_pcp *stock = this_cpu_ptr(&memcg_stock);
+ struct memcg_stock_pcp *stock;
+ unsigned long flags;
+
+ local_irq_save(flags);
+
+ stock = this_cpu_ptr(&memcg_stock);
drain_stock(stock);
clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
+
+ local_irq_restore(flags);
}
/*
*/
static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
{
- struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock);
+ struct memcg_stock_pcp *stock;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ stock = this_cpu_ptr(&memcg_stock);
if (stock->cached != memcg) { /* reset if necessary */
drain_stock(stock);
stock->cached = memcg;
}
stock->nr_pages += nr_pages;
- put_cpu_var(memcg_stock);
+
+ local_irq_restore(flags);
}
/*
return 0;
memcg = get_mem_cgroup_from_mm(current->mm);
- if (!mem_cgroup_is_root(memcg))
+ if (!mem_cgroup_is_root(memcg)) {
ret = memcg_kmem_charge_memcg(page, gfp, order, memcg);
+ if (!ret)
+ __SetPageKmemcg(page);
+ }
css_put(&memcg->css);
return ret;
}
page_counter_uncharge(&memcg->memsw, nr_pages);
page->mem_cgroup = NULL;
+
+ /* slab pages do not have PageKmemcg flag set */
+ if (PageKmemcg(page))
+ __ClearPageKmemcg(page);
+
css_put_many(&memcg->css, nr_pages);
}
#endif /* !CONFIG_SLOB */
static DEFINE_IDR(mem_cgroup_idr);
-static void mem_cgroup_id_get(struct mem_cgroup *memcg)
+static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n)
{
- atomic_inc(&memcg->id.ref);
+ atomic_add(n, &memcg->id.ref);
}
-static void mem_cgroup_id_put(struct mem_cgroup *memcg)
+static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n)
{
- if (atomic_dec_and_test(&memcg->id.ref)) {
+ if (atomic_sub_and_test(n, &memcg->id.ref)) {
idr_remove(&mem_cgroup_idr, memcg->id.id);
memcg->id.id = 0;
}
}
+static inline void mem_cgroup_id_get(struct mem_cgroup *memcg)
+{
+ mem_cgroup_id_get_many(memcg, 1);
+}
+
+static inline void mem_cgroup_id_put(struct mem_cgroup *memcg)
+{
+ mem_cgroup_id_put_many(memcg, 1);
+}
+
/**
* mem_cgroup_from_id - look up a memcg from a memcg id
* @id: the memcg id to look up
if (!mem_cgroup_is_root(mc.from))
page_counter_uncharge(&mc.from->memsw, mc.moved_swap);
+ mem_cgroup_id_put_many(mc.from, mc.moved_swap);
+
/*
* we charged both to->memory and to->memsw, so we
* should uncharge to->memory.
if (!mem_cgroup_is_root(mc.to))
page_counter_uncharge(&mc.to->memory, mc.moved_swap);
- css_put_many(&mc.from->css, mc.moved_swap);
+ mem_cgroup_id_get_many(mc.to, mc.moved_swap);
+ css_put_many(&mc.to->css, mc.moved_swap);
- /* we've already done css_get(mc.to) */
mc.moved_swap = 0;
}
memcg_oom_recover(from);
else
nr_file += nr_pages;
pgpgout++;
- } else
+ } else {
nr_kmem += 1 << compound_order(page);
+ __ClearPageKmemcg(page);
+ }
page->mem_cgroup = NULL;
} while (next != page_list);
subsys_initcall(mem_cgroup_init);
#ifdef CONFIG_MEMCG_SWAP
+static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg)
+{
+ while (!atomic_inc_not_zero(&memcg->id.ref)) {
+ /*
+ * The root cgroup cannot be destroyed, so it's refcount must
+ * always be >= 1.
+ */
+ if (WARN_ON_ONCE(memcg == root_mem_cgroup)) {
+ VM_BUG_ON(1);
+ break;
+ }
+ memcg = parent_mem_cgroup(memcg);
+ if (!memcg)
+ memcg = root_mem_cgroup;
+ }
+ return memcg;
+}
+
/**
* mem_cgroup_swapout - transfer a memsw charge to swap
* @page: page whose memsw charge to transfer
*/
void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
{
- struct mem_cgroup *memcg;
+ struct mem_cgroup *memcg, *swap_memcg;
unsigned short oldid;
VM_BUG_ON_PAGE(PageLRU(page), page);
if (!memcg)
return;
- mem_cgroup_id_get(memcg);
- oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg));
+ /*
+ * In case the memcg owning these pages has been offlined and doesn't
+ * have an ID allocated to it anymore, charge the closest online
+ * ancestor for the swap instead and transfer the memory+swap charge.
+ */
+ swap_memcg = mem_cgroup_id_get_online(memcg);
+ oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg));
VM_BUG_ON_PAGE(oldid, page);
- mem_cgroup_swap_statistics(memcg, true);
+ mem_cgroup_swap_statistics(swap_memcg, true);
page->mem_cgroup = NULL;
if (!mem_cgroup_is_root(memcg))
page_counter_uncharge(&memcg->memory, 1);
+ if (memcg != swap_memcg) {
+ if (!mem_cgroup_is_root(swap_memcg))
+ page_counter_charge(&swap_memcg->memsw, 1);
+ page_counter_uncharge(&memcg->memsw, 1);
+ }
+
/*
* Interrupts should be disabled here because the caller holds the
* mapping->tree_lock lock which is taken with interrupts-off. It is
if (!memcg)
return 0;
+ memcg = mem_cgroup_id_get_online(memcg);
+
if (!mem_cgroup_is_root(memcg) &&
- !page_counter_try_charge(&memcg->swap, 1, &counter))
+ !page_counter_try_charge(&memcg->swap, 1, &counter)) {
+ mem_cgroup_id_put(memcg);
return -ENOMEM;
+ }
- mem_cgroup_id_get(memcg);
oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg));
VM_BUG_ON_PAGE(oldid, page);
mem_cgroup_swap_statistics(memcg, true);
bool was_writable = pte_write(pte);
int flags = 0;
- /* A PROT_NONE fault should not end up here */
- BUG_ON(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)));
-
/*
* The "pte" at this point cannot be used safely without
* validation through pte_unmap_same(). It's of NUMA type but
return VM_FAULT_FALLBACK;
}
+static inline bool vma_is_accessible(struct vm_area_struct *vma)
+{
+ return vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE);
+}
+
/*
* These routines also need to handle stuff like marking pages dirty
* and/or accessed for architectures that don't do it in hardware (most
if (!pte_present(entry))
return do_swap_page(fe, entry);
- if (pte_protnone(entry))
+ if (pte_protnone(entry) && vma_is_accessible(fe->vma))
return do_numa_page(fe, entry);
fe->ptl = pte_lockptr(fe->vma->vm_mm, fe->pmd);
barrier();
if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) {
- if (pmd_protnone(orig_pmd))
+ if (pmd_protnone(orig_pmd) && vma_is_accessible(vma))
return do_huge_pmd_numa_page(&fe, orig_pmd);
if ((fe.flags & FAULT_FLAG_WRITE) &&
/* init node's zones as empty zones, we don't have any present pages.*/
free_area_init_node(nid, zones_size, start_pfn, zholes_size);
+ pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat);
/*
* The node we allocated has no zone fallback lists. For avoiding
static void rollback_node_hotadd(int nid, pg_data_t *pgdat)
{
arch_refresh_nodedata(nid, NULL);
+ free_percpu(pgdat->per_cpu_nodestats);
arch_free_nodedata(pgdat);
return;
}
return alloc_huge_page_node(page_hstate(compound_head(page)),
next_node_in(nid, nmask));
- node_clear(nid, nmask);
+ if (nid != next_node_in(nid, nmask))
+ node_clear(nid, nmask);
+
if (PageHighMem(page)
|| (zone_idx(page_zone(page)) == ZONE_MOVABLE))
gfp_mask |= __GFP_HIGHMEM;
return ret;
}
+/*
+ * Drop the (possibly final) reference to task->mempolicy. It needs to be
+ * dropped after task->mempolicy is set to NULL so that any allocation done as
+ * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed
+ * policy.
+ */
+void mpol_put_task_policy(struct task_struct *task)
+{
+ struct mempolicy *pol;
+
+ task_lock(task);
+ pol = task->mempolicy;
+ task->mempolicy = NULL;
+ task_unlock(task);
+ mpol_put(pol);
+}
+
static void sp_delete(struct shared_policy *sp, struct sp_node *n)
{
pr_debug("deleting %lx-l%lx\n", n->start, n->end);
{
struct mm_struct *mm = task->mm;
struct task_struct *p;
- bool ret;
+ bool ret = true;
/*
* Skip tasks without mm because it might have passed its exit_mm and
}
if (PageMappingFlags(page))
page->mapping = NULL;
- if (memcg_kmem_enabled() && PageKmemcg(page)) {
+ if (memcg_kmem_enabled() && PageKmemcg(page))
memcg_kmem_uncharge(page, order);
- __ClearPageKmemcg(page);
- }
if (check_free)
bad += free_pages_check(page);
if (bad)
return NULL;
}
-static inline bool
-should_compact_retry(struct alloc_context *ac, int order, int alloc_flags,
- enum compact_result compact_result,
- enum compact_priority *compact_priority,
- int compaction_retries)
-{
- int max_retries = MAX_COMPACT_RETRIES;
-
- if (!order)
- return false;
-
- /*
- * compaction considers all the zone as desperately out of memory
- * so it doesn't really make much sense to retry except when the
- * failure could be caused by insufficient priority
- */
- if (compaction_failed(compact_result)) {
- if (*compact_priority > MIN_COMPACT_PRIORITY) {
- (*compact_priority)--;
- return true;
- }
- return false;
- }
-
- /*
- * make sure the compaction wasn't deferred or didn't bail out early
- * due to locks contention before we declare that we should give up.
- * But do not retry if the given zonelist is not suitable for
- * compaction.
- */
- if (compaction_withdrawn(compact_result))
- return compaction_zonelist_suitable(ac, order, alloc_flags);
-
- /*
- * !costly requests are much more important than __GFP_REPEAT
- * costly ones because they are de facto nofail and invoke OOM
- * killer to move on while costly can fail and users are ready
- * to cope with that. 1/4 retries is rather arbitrary but we
- * would need much more detailed feedback from compaction to
- * make a better decision.
- */
- if (order > PAGE_ALLOC_COSTLY_ORDER)
- max_retries /= 4;
- if (compaction_retries <= max_retries)
- return true;
-
- return false;
-}
#else
static inline struct page *
__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
return NULL;
}
+#endif /* CONFIG_COMPACTION */
+
static inline bool
should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_flags,
enum compact_result compact_result,
}
return false;
}
-#endif /* CONFIG_COMPACTION */
/* Perform direct synchronous page reclaim */
static int
}
out:
- if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page) {
- if (unlikely(memcg_kmem_charge(page, gfp_mask, order))) {
- __free_pages(page, order);
- page = NULL;
- } else
- __SetPageKmemcg(page);
+ if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page &&
+ unlikely(memcg_kmem_charge(page, gfp_mask, order) != 0)) {
+ __free_pages(page, order);
+ page = NULL;
}
if (kmemcheck_enabled && page)
int lru;
for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
- pages[lru] = global_page_state(NR_LRU_BASE + lru);
+ pages[lru] = global_node_page_state(NR_LRU_BASE + lru);
for_each_zone(zone)
wmark_low += zone->watermark[WMARK_LOW];
do {
zone_type--;
zone = pgdat->node_zones + zone_type;
- if (populated_zone(zone)) {
+ if (managed_zone(zone)) {
zoneref_set_zone(zone,
&zonelist->_zonerefs[nr_zones++]);
check_highest_zone(zone_type);
for (j = 0; j < nr_nodes; j++) {
node = node_order[j];
z = &NODE_DATA(node)->node_zones[zone_type];
- if (populated_zone(z)) {
+ if (managed_zone(z)) {
zoneref_set_zone(z,
&zonelist->_zonerefs[pos++]);
check_highest_zone(zone_type);
}
#endif
+static void setup_min_unmapped_ratio(void);
+static void setup_min_slab_ratio(void);
#else /* CONFIG_NUMA */
static void set_zonelist_order(void)
zone->managed_pages = is_highmem_idx(j) ? realsize : freesize;
#ifdef CONFIG_NUMA
zone->node = nid;
- pgdat->min_unmapped_pages += (freesize*sysctl_min_unmapped_ratio)
- / 100;
- pgdat->min_slab_pages += (freesize * sysctl_min_slab_ratio) / 100;
#endif
zone->name = zone_names[j];
zone->zone_pgdat = pgdat;
setup_per_zone_wmarks();
refresh_zone_stat_thresholds();
setup_per_zone_lowmem_reserve();
+
+#ifdef CONFIG_NUMA
+ setup_min_unmapped_ratio();
+ setup_min_slab_ratio();
+#endif
+
return 0;
}
core_initcall(init_per_zone_wmark_min)
}
#ifdef CONFIG_NUMA
+static void setup_min_unmapped_ratio(void)
+{
+ pg_data_t *pgdat;
+ struct zone *zone;
+
+ for_each_online_pgdat(pgdat)
+ pgdat->min_unmapped_pages = 0;
+
+ for_each_zone(zone)
+ zone->zone_pgdat->min_unmapped_pages += (zone->managed_pages *
+ sysctl_min_unmapped_ratio) / 100;
+}
+
+
int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
- struct pglist_data *pgdat;
- struct zone *zone;
int rc;
rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (rc)
return rc;
+ setup_min_unmapped_ratio();
+
+ return 0;
+}
+
+static void setup_min_slab_ratio(void)
+{
+ pg_data_t *pgdat;
+ struct zone *zone;
+
for_each_online_pgdat(pgdat)
pgdat->min_slab_pages = 0;
for_each_zone(zone)
- zone->zone_pgdat->min_unmapped_pages += (zone->managed_pages *
- sysctl_min_unmapped_ratio) / 100;
- return 0;
+ zone->zone_pgdat->min_slab_pages += (zone->managed_pages *
+ sysctl_min_slab_ratio) / 100;
}
int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
- struct pglist_data *pgdat;
- struct zone *zone;
int rc;
rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (rc)
return rc;
- for_each_online_pgdat(pgdat)
- pgdat->min_slab_pages = 0;
+ setup_min_slab_ratio();
- for_each_zone(zone)
- zone->zone_pgdat->min_slab_pages += (zone->managed_pages *
- sysctl_min_slab_ratio) / 100;
return 0;
}
#endif
int ret;
struct swap_info_struct *sis = page_swap_info(page);
+ BUG_ON(!PageSwapCache(page));
if (sis->flags & SWP_FILE) {
struct kiocb kiocb;
struct file *swap_file = sis->swap_file;
int ret = 0;
struct swap_info_struct *sis = page_swap_info(page);
+ BUG_ON(!PageSwapCache(page));
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageUptodate(page), page);
if (frontswap_load(page) == 0) {
if (sis->flags & SWP_FILE) {
struct address_space *mapping = sis->swap_file->f_mapping;
+ BUG_ON(!PageSwapCache(page));
return mapping->a_ops->set_page_dirty(page);
} else {
return __set_page_dirty_no_writeback(page);
*/
#include <linux/kernel.h>
+#include <linux/dax.h>
#include <linux/gfp.h>
#include <linux/export.h>
#include <linux/blkdev.h>
if (!mapping || !mapping->a_ops)
return -EINVAL;
+ /*
+ * Readahead doesn't make sense for DAX inodes, but we don't want it
+ * to report a failure either. Instead, we just return success and
+ * don't do any work.
+ */
+ if (dax_mapping(mapping))
+ return 0;
+
return force_page_cache_readahead(mapping, filp, index, nr);
}
VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
__inc_node_page_state(page, NR_SHMEM_PMDMAPPED);
} else {
- if (PageTransCompound(page)) {
- VM_BUG_ON_PAGE(!PageLocked(page), page);
+ if (PageTransCompound(page) && page_mapping(page)) {
+ VM_WARN_ON_ONCE(!PageLocked(page));
+
SetPageDoubleMap(compound_head(page));
if (PageMlocked(page))
clear_page_mlock(compound_head(page));
{
int i, nr = 1;
- VM_BUG_ON_PAGE(compound && !PageTransHuge(page), page);
+ VM_BUG_ON_PAGE(compound && !PageHead(page), page);
lock_page_memcg(page);
/* Hugepages are not counted in NR_FILE_MAPPED for now. */
info->alloced -= pages;
shmem_recalc_inode(inode);
spin_unlock_irqrestore(&info->lock, flags);
-
+ shmem_unacct_blocks(info->flags, pages);
return false;
}
percpu_counter_add(&sbinfo->used_blocks, pages);
if (sbinfo->max_blocks)
percpu_counter_sub(&sbinfo->used_blocks, pages);
+ shmem_unacct_blocks(info->flags, pages);
}
/*
return addr;
sb = shm_mnt->mnt_sb;
}
- if (SHMEM_SB(sb)->huge != SHMEM_HUGE_NEVER)
+ if (SHMEM_SB(sb)->huge == SHMEM_HUGE_NEVER)
return addr;
}
struct kobj_attribute shmem_enabled_attr =
__ATTR(shmem_enabled, 0644, shmem_enabled_show, shmem_enabled_store);
+#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE && CONFIG_SYSFS */
+#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
bool shmem_huge_enabled(struct vm_area_struct *vma)
{
struct inode *inode = file_inode(vma->vm_file);
return false;
}
}
-#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE && CONFIG_SYSFS */
+#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE */
#else /* !CONFIG_SHMEM */
module_init(slab_proc_init);
#endif
+#ifdef CONFIG_HARDENED_USERCOPY
+/*
+ * Rejects objects that are incorrectly sized.
+ *
+ * Returns NULL if check passes, otherwise const char * to name of cache
+ * to indicate an error.
+ */
+const char *__check_heap_object(const void *ptr, unsigned long n,
+ struct page *page)
+{
+ struct kmem_cache *cachep;
+ unsigned int objnr;
+ unsigned long offset;
+
+ /* Find and validate object. */
+ cachep = page->slab_cache;
+ objnr = obj_to_index(cachep, page, (void *)ptr);
+ BUG_ON(objnr >= cachep->num);
+
+ /* Find offset within object. */
+ offset = ptr - index_to_obj(cachep, page, objnr) - obj_offset(cachep);
+
+ /* Allow address range falling entirely within object size. */
+ if (offset <= cachep->object_size && n <= cachep->object_size - offset)
+ return NULL;
+
+ return cachep->name;
+}
+#endif /* CONFIG_HARDENED_USERCOPY */
+
/**
* ksize - get the actual amount of memory allocated for a given object
* @objp: Pointer to the object
*/
static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
{
+ LIST_HEAD(discard);
struct page *page, *h;
BUG_ON(irqs_disabled());
list_for_each_entry_safe(page, h, &n->partial, lru) {
if (!page->inuse) {
remove_partial(n, page);
- discard_slab(s, page);
+ list_add(&page->lru, &discard);
} else {
list_slab_objects(s, page,
"Objects remaining in %s on __kmem_cache_shutdown()");
}
}
spin_unlock_irq(&n->list_lock);
+
+ list_for_each_entry_safe(page, h, &discard, lru)
+ discard_slab(s, page);
}
/*
EXPORT_SYMBOL(__kmalloc_node);
#endif
+#ifdef CONFIG_HARDENED_USERCOPY
+/*
+ * Rejects objects that are incorrectly sized.
+ *
+ * Returns NULL if check passes, otherwise const char * to name of cache
+ * to indicate an error.
+ */
+const char *__check_heap_object(const void *ptr, unsigned long n,
+ struct page *page)
+{
+ struct kmem_cache *s;
+ unsigned long offset;
+ size_t object_size;
+
+ /* Find object and usable object size. */
+ s = page->slab_cache;
+ object_size = slab_ksize(s);
+
+ /* Reject impossible pointers. */
+ if (ptr < page_address(page))
+ return s->name;
+
+ /* Find offset within object. */
+ offset = (ptr - page_address(page)) % s->size;
+
+ /* Adjust for redzone and reject if within the redzone. */
+ if (kmem_cache_debug(s) && s->flags & SLAB_RED_ZONE) {
+ if (offset < s->red_left_pad)
+ return s->name;
+ offset -= s->red_left_pad;
+ }
+
+ /* Allow address range falling entirely within object size. */
+ if (offset <= object_size && n <= object_size - offset)
+ return NULL;
+
+ return s->name;
+}
+#endif /* CONFIG_HARDENED_USERCOPY */
+
static size_t __ksize(const void *object)
{
struct page *page;
struct swap_info_struct *page_swap_info(struct page *page)
{
swp_entry_t swap = { .val = page_private(page) };
- BUG_ON(!PageSwapCache(page));
return swap_info[swp_type(swap)];
}
--- /dev/null
+/*
+ * This implements the various checks for CONFIG_HARDENED_USERCOPY*,
+ * which are designed to protect kernel memory from needless exposure
+ * and overwrite under many unintended conditions. This code is based
+ * on PAX_USERCOPY, which is:
+ *
+ * Copyright (C) 2001-2016 PaX Team, Bradley Spengler, Open Source
+ * Security Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <asm/sections.h>
+
+enum {
+ BAD_STACK = -1,
+ NOT_STACK = 0,
+ GOOD_FRAME,
+ GOOD_STACK,
+};
+
+/*
+ * Checks if a given pointer and length is contained by the current
+ * stack frame (if possible).
+ *
+ * Returns:
+ * NOT_STACK: not at all on the stack
+ * GOOD_FRAME: fully within a valid stack frame
+ * GOOD_STACK: fully on the stack (when can't do frame-checking)
+ * BAD_STACK: error condition (invalid stack position or bad stack frame)
+ */
+static noinline int check_stack_object(const void *obj, unsigned long len)
+{
+ const void * const stack = task_stack_page(current);
+ const void * const stackend = stack + THREAD_SIZE;
+ int ret;
+
+ /* Object is not on the stack at all. */
+ if (obj + len <= stack || stackend <= obj)
+ return NOT_STACK;
+
+ /*
+ * Reject: object partially overlaps the stack (passing the
+ * the check above means at least one end is within the stack,
+ * so if this check fails, the other end is outside the stack).
+ */
+ if (obj < stack || stackend < obj + len)
+ return BAD_STACK;
+
+ /* Check if object is safely within a valid frame. */
+ ret = arch_within_stack_frames(stack, stackend, obj, len);
+ if (ret)
+ return ret;
+
+ return GOOD_STACK;
+}
+
+static void report_usercopy(const void *ptr, unsigned long len,
+ bool to_user, const char *type)
+{
+ pr_emerg("kernel memory %s attempt detected %s %p (%s) (%lu bytes)\n",
+ to_user ? "exposure" : "overwrite",
+ to_user ? "from" : "to", ptr, type ? : "unknown", len);
+ /*
+ * For greater effect, it would be nice to do do_group_exit(),
+ * but BUG() actually hooks all the lock-breaking and per-arch
+ * Oops code, so that is used here instead.
+ */
+ BUG();
+}
+
+/* Returns true if any portion of [ptr,ptr+n) over laps with [low,high). */
+static bool overlaps(const void *ptr, unsigned long n, unsigned long low,
+ unsigned long high)
+{
+ unsigned long check_low = (uintptr_t)ptr;
+ unsigned long check_high = check_low + n;
+
+ /* Does not overlap if entirely above or entirely below. */
+ if (check_low >= high || check_high <= low)
+ return false;
+
+ return true;
+}
+
+/* Is this address range in the kernel text area? */
+static inline const char *check_kernel_text_object(const void *ptr,
+ unsigned long n)
+{
+ unsigned long textlow = (unsigned long)_stext;
+ unsigned long texthigh = (unsigned long)_etext;
+ unsigned long textlow_linear, texthigh_linear;
+
+ if (overlaps(ptr, n, textlow, texthigh))
+ return "<kernel text>";
+
+ /*
+ * Some architectures have virtual memory mappings with a secondary
+ * mapping of the kernel text, i.e. there is more than one virtual
+ * kernel address that points to the kernel image. It is usually
+ * when there is a separate linear physical memory mapping, in that
+ * __pa() is not just the reverse of __va(). This can be detected
+ * and checked:
+ */
+ textlow_linear = (unsigned long)__va(__pa(textlow));
+ /* No different mapping: we're done. */
+ if (textlow_linear == textlow)
+ return NULL;
+
+ /* Check the secondary mapping... */
+ texthigh_linear = (unsigned long)__va(__pa(texthigh));
+ if (overlaps(ptr, n, textlow_linear, texthigh_linear))
+ return "<linear kernel text>";
+
+ return NULL;
+}
+
+static inline const char *check_bogus_address(const void *ptr, unsigned long n)
+{
+ /* Reject if object wraps past end of memory. */
+ if ((unsigned long)ptr + n < (unsigned long)ptr)
+ return "<wrapped address>";
+
+ /* Reject if NULL or ZERO-allocation. */
+ if (ZERO_OR_NULL_PTR(ptr))
+ return "<null>";
+
+ return NULL;
+}
+
+/* Checks for allocs that are marked in some way as spanning multiple pages. */
+static inline const char *check_page_span(const void *ptr, unsigned long n,
+ struct page *page, bool to_user)
+{
+#ifdef CONFIG_HARDENED_USERCOPY_PAGESPAN
+ const void *end = ptr + n - 1;
+ struct page *endpage;
+ bool is_reserved, is_cma;
+
+ /*
+ * Sometimes the kernel data regions are not marked Reserved (see
+ * check below). And sometimes [_sdata,_edata) does not cover
+ * rodata and/or bss, so check each range explicitly.
+ */
+
+ /* Allow reads of kernel rodata region (if not marked as Reserved). */
+ if (ptr >= (const void *)__start_rodata &&
+ end <= (const void *)__end_rodata) {
+ if (!to_user)
+ return "<rodata>";
+ return NULL;
+ }
+
+ /* Allow kernel data region (if not marked as Reserved). */
+ if (ptr >= (const void *)_sdata && end <= (const void *)_edata)
+ return NULL;
+
+ /* Allow kernel bss region (if not marked as Reserved). */
+ if (ptr >= (const void *)__bss_start &&
+ end <= (const void *)__bss_stop)
+ return NULL;
+
+ /* Is the object wholly within one base page? */
+ if (likely(((unsigned long)ptr & (unsigned long)PAGE_MASK) ==
+ ((unsigned long)end & (unsigned long)PAGE_MASK)))
+ return NULL;
+
+ /* Allow if fully inside the same compound (__GFP_COMP) page. */
+ endpage = virt_to_head_page(end);
+ if (likely(endpage == page))
+ return NULL;
+
+ /*
+ * Reject if range is entirely either Reserved (i.e. special or
+ * device memory), or CMA. Otherwise, reject since the object spans
+ * several independently allocated pages.
+ */
+ is_reserved = PageReserved(page);
+ is_cma = is_migrate_cma_page(page);
+ if (!is_reserved && !is_cma)
+ return "<spans multiple pages>";
+
+ for (ptr += PAGE_SIZE; ptr <= end; ptr += PAGE_SIZE) {
+ page = virt_to_head_page(ptr);
+ if (is_reserved && !PageReserved(page))
+ return "<spans Reserved and non-Reserved pages>";
+ if (is_cma && !is_migrate_cma_page(page))
+ return "<spans CMA and non-CMA pages>";
+ }
+#endif
+
+ return NULL;
+}
+
+static inline const char *check_heap_object(const void *ptr, unsigned long n,
+ bool to_user)
+{
+ struct page *page;
+
+ /*
+ * Some architectures (arm64) return true for virt_addr_valid() on
+ * vmalloced addresses. Work around this by checking for vmalloc
+ * first.
+ *
+ * We also need to check for module addresses explicitly since we
+ * may copy static data from modules to userspace
+ */
+ if (is_vmalloc_or_module_addr(ptr))
+ return NULL;
+
+ if (!virt_addr_valid(ptr))
+ return NULL;
+
+ page = virt_to_head_page(ptr);
+
+ /* Check slab allocator for flags and size. */
+ if (PageSlab(page))
+ return __check_heap_object(ptr, n, page);
+
+ /* Verify object does not incorrectly span multiple pages. */
+ return check_page_span(ptr, n, page, to_user);
+}
+
+/*
+ * Validates that the given object is:
+ * - not bogus address
+ * - known-safe heap or stack object
+ * - not in kernel text
+ */
+void __check_object_size(const void *ptr, unsigned long n, bool to_user)
+{
+ const char *err;
+
+ /* Skip all tests if size is zero. */
+ if (!n)
+ return;
+
+ /* Check for invalid addresses. */
+ err = check_bogus_address(ptr, n);
+ if (err)
+ goto report;
+
+ /* Check for bad heap object. */
+ err = check_heap_object(ptr, n, to_user);
+ if (err)
+ goto report;
+
+ /* Check for bad stack object. */
+ switch (check_stack_object(ptr, n)) {
+ case NOT_STACK:
+ /* Object is not touching the current process stack. */
+ break;
+ case GOOD_FRAME:
+ case GOOD_STACK:
+ /*
+ * Object is either in the correct frame (when it
+ * is possible to check) or just generally on the
+ * process stack (when frame checking not available).
+ */
+ return;
+ default:
+ err = "<process stack>";
+ goto report;
+ }
+
+ /* Check for object in kernel to avoid text exposure. */
+ err = check_kernel_text_object(ptr, n);
+ if (!err)
+ return;
+
+report:
+ report_usercopy(ptr, n, to_user, err);
+}
+EXPORT_SYMBOL(__check_object_size);
for (zid = sc->reclaim_idx; zid >= 0; zid--) {
zone = &pgdat->node_zones[zid];
- if (!populated_zone(zone))
+ if (!managed_zone(zone))
continue;
if (zone_page_state_snapshot(zone, NR_ZONE_LRU_BASE +
struct zone *zone = &pgdat->node_zones[zid];
unsigned long inactive_zone, active_zone;
- if (!populated_zone(zone))
+ if (!managed_zone(zone))
continue;
inactive_zone = zone_page_state(zone,
for (z = 0; z < MAX_NR_ZONES; z++) {
struct zone *zone = &pgdat->node_zones[z];
- if (!populated_zone(zone))
+ if (!managed_zone(zone))
continue;
total_high_wmark += high_wmark_pages(zone);
}
}
-#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
-static void init_tlb_ubc(void)
-{
- /*
- * This deliberately does not clear the cpumask as it's expensive
- * and unnecessary. If there happens to be data in there then the
- * first SWAP_CLUSTER_MAX pages will send an unnecessary IPI and
- * then will be cleared.
- */
- current->tlb_ubc.flush_required = false;
-}
-#else
-static inline void init_tlb_ubc(void)
-{
-}
-#endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */
-
/*
* This is a basic per-node page freer. Used by both kswapd and direct reclaim.
*/
scan_adjusted = (global_reclaim(sc) && !current_is_kswapd() &&
sc->priority == DEF_PRIORITY);
- init_tlb_ubc();
-
blk_start_plug(&plug);
while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
nr[LRU_INACTIVE_FILE]) {
/* If compaction would go ahead or the allocation would succeed, stop */
for (z = 0; z <= sc->reclaim_idx; z++) {
struct zone *zone = &pgdat->node_zones[z];
- if (!populated_zone(zone))
+ if (!managed_zone(zone))
continue;
switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) {
for (i = 0; i <= ZONE_NORMAL; i++) {
zone = &pgdat->node_zones[i];
- if (!populated_zone(zone) ||
+ if (!managed_zone(zone) ||
pgdat_reclaimable_pages(pgdat) == 0)
continue;
for (i = 0; i <= classzone_idx; i++) {
struct zone *zone = pgdat->node_zones + i;
- if (!populated_zone(zone))
+ if (!managed_zone(zone))
continue;
if (!zone_balanced(zone, order, classzone_idx))
sc->nr_to_reclaim = 0;
for (z = 0; z <= sc->reclaim_idx; z++) {
zone = pgdat->node_zones + z;
- if (!populated_zone(zone))
+ if (!managed_zone(zone))
continue;
sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX);
if (buffer_heads_over_limit) {
for (i = MAX_NR_ZONES - 1; i >= 0; i--) {
zone = pgdat->node_zones + i;
- if (!populated_zone(zone))
+ if (!managed_zone(zone))
continue;
sc.reclaim_idx = i;
*/
for (i = classzone_idx; i >= 0; i--) {
zone = pgdat->node_zones + i;
- if (!populated_zone(zone))
+ if (!managed_zone(zone))
continue;
if (zone_balanced(zone, sc.order, classzone_idx))
pg_data_t *pgdat;
int z;
- if (!populated_zone(zone))
+ if (!managed_zone(zone))
return;
if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
/* Only wake kswapd if all zones are unbalanced */
for (z = 0; z <= classzone_idx; z++) {
zone = pgdat->node_zones + z;
- if (!populated_zone(zone))
+ if (!managed_zone(zone))
continue;
if (zone_balanced(zone, order, classzone_idx))
if (err < 0)
goto out_uninit_mvrp;
- vlan->nest_level = dev_get_nest_level(real_dev, is_vlan_dev) + 1;
+ vlan->nest_level = dev_get_nest_level(real_dev) + 1;
err = register_netdevice(dev);
if (err < 0)
goto out_uninit_mvrp;
/* wakeup anybody waiting for slots to pin pages */
wake_up(&vp_wq);
}
- kfree(in_pages);
- kfree(out_pages);
+ kvfree(in_pages);
+ kvfree(out_pages);
return err;
}
goto out;
skb_reserve(hard_iface->bat_v.elp_skb, ETH_HLEN + NET_IP_ALIGN);
- elp_buff = skb_push(hard_iface->bat_v.elp_skb, BATADV_ELP_HLEN);
+ elp_buff = skb_put(hard_iface->bat_v.elp_skb, BATADV_ELP_HLEN);
elp_packet = (struct batadv_elp_packet *)elp_buff;
memset(elp_packet, 0, BATADV_ELP_HLEN);
return 0;
}
+/**
+ * batadv_last_bonding_get - Get last_bonding_candidate of orig_node
+ * @orig_node: originator node whose last bonding candidate should be retrieved
+ *
+ * Return: last bonding candidate of router or NULL if not found
+ *
+ * The object is returned with refcounter increased by 1.
+ */
+static struct batadv_orig_ifinfo *
+batadv_last_bonding_get(struct batadv_orig_node *orig_node)
+{
+ struct batadv_orig_ifinfo *last_bonding_candidate;
+
+ spin_lock_bh(&orig_node->neigh_list_lock);
+ last_bonding_candidate = orig_node->last_bonding_candidate;
+
+ if (last_bonding_candidate)
+ kref_get(&last_bonding_candidate->refcount);
+ spin_unlock_bh(&orig_node->neigh_list_lock);
+
+ return last_bonding_candidate;
+}
+
/**
* batadv_last_bonding_replace - Replace last_bonding_candidate of orig_node
* @orig_node: originator node whose bonding candidates should be replaced
* router - obviously there are no other candidates.
*/
rcu_read_lock();
- last_candidate = orig_node->last_bonding_candidate;
+ last_candidate = batadv_last_bonding_get(orig_node);
if (last_candidate)
last_cand_router = rcu_dereference(last_candidate->router);
batadv_orig_ifinfo_put(next_candidate);
}
+ if (last_candidate)
+ batadv_orig_ifinfo_put(last_candidate);
+
return router;
}
skb_free_datagram(sk, skb);
- if (msg->msg_flags & MSG_TRUNC)
+ if (flags & MSG_TRUNC)
copied = skblen;
return err ? : copied;
break;
}
+ kfree_skb(hdev->req_skb);
+ hdev->req_skb = NULL;
hdev->req_status = hdev->req_result = 0;
BT_DBG("%s end: err %d", hdev->name, err);
skb_free_datagram(sk, skb);
- if (msg->msg_flags & MSG_TRUNC)
+ if (flags & MSG_TRUNC)
copied = skblen;
return err ? : copied;
#include <linux/debugfs.h>
#include <linux/crc16.h>
+#include <linux/filter.h>
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci_core.h>
if (chan->sdu)
break;
+ if (!pskb_may_pull(skb, L2CAP_SDULEN_SIZE))
+ break;
+
chan->sdu_len = get_unaligned_le16(skb->data);
skb_pull(skb, L2CAP_SDULEN_SIZE);
goto drop;
}
+ if ((chan->mode == L2CAP_MODE_ERTM ||
+ chan->mode == L2CAP_MODE_STREAMING) && sk_filter(chan->data, skb))
+ goto drop;
+
if (!control->sframe) {
int err;
goto done;
if (pi->rx_busy_skb) {
- if (!sock_queue_rcv_skb(sk, pi->rx_busy_skb))
+ if (!__sock_queue_rcv_skb(sk, pi->rx_busy_skb))
pi->rx_busy_skb = NULL;
else
goto done;
goto done;
}
- err = sock_queue_rcv_skb(sk, skb);
+ if (chan->mode != L2CAP_MODE_ERTM &&
+ chan->mode != L2CAP_MODE_STREAMING) {
+ /* Even if no filter is attached, we could potentially
+ * get errors from security modules, etc.
+ */
+ err = sk_filter(sk, skb);
+ if (err)
+ goto done;
+ }
+
+ err = __sock_queue_rcv_skb(sk, skb);
/* For ERTM, handle one skb that doesn't fit into the recv
* buffer. This is important to do because the data frames
/* If old entry was unassociated with any port, then delete it. */
f = __br_fdb_get(br, br->dev->dev_addr, 0);
- if (f && f->is_local && !f->dst)
+ if (f && f->is_local && !f->dst && !f->added_by_user)
fdb_delete_local(br, NULL, f);
fdb_insert(br, NULL, newaddr, 0);
if (!br_vlan_should_use(v))
continue;
f = __br_fdb_get(br, br->dev->dev_addr, v->vid);
- if (f && f->is_local && !f->dst)
+ if (f && f->is_local && !f->dst && !f->added_by_user)
fdb_delete_local(br, NULL, f);
fdb_insert(br, NULL, newaddr, v->vid);
}
}
/* Update (create or replace) forwarding database entry */
-static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr,
- __u16 state, __u16 flags, __u16 vid)
+static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source,
+ const __u8 *addr, __u16 state, __u16 flags, __u16 vid)
{
- struct net_bridge *br = source->br;
struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)];
struct net_bridge_fdb_entry *fdb;
bool modified = false;
/* If the port cannot learn allow only local and static entries */
- if (!(state & NUD_PERMANENT) && !(state & NUD_NOARP) &&
+ if (source && !(state & NUD_PERMANENT) && !(state & NUD_NOARP) &&
!(source->state == BR_STATE_LEARNING ||
source->state == BR_STATE_FORWARDING))
return -EPERM;
+ if (!source && !(state & NUD_PERMANENT)) {
+ pr_info("bridge: RTM_NEWNEIGH %s without NUD_PERMANENT\n",
+ br->dev->name);
+ return -EINVAL;
+ }
+
fdb = fdb_find(head, addr, vid);
if (fdb == NULL) {
if (!(flags & NLM_F_CREATE))
return 0;
}
-static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p,
- const unsigned char *addr, u16 nlh_flags, u16 vid)
+static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br,
+ struct net_bridge_port *p, const unsigned char *addr,
+ u16 nlh_flags, u16 vid)
{
int err = 0;
if (ndm->ndm_flags & NTF_USE) {
+ if (!p) {
+ pr_info("bridge: RTM_NEWNEIGH %s with NTF_USE is not supported\n",
+ br->dev->name);
+ return -EINVAL;
+ }
local_bh_disable();
rcu_read_lock();
- br_fdb_update(p->br, p, addr, vid, true);
+ br_fdb_update(br, p, addr, vid, true);
rcu_read_unlock();
local_bh_enable();
} else {
- spin_lock_bh(&p->br->hash_lock);
- err = fdb_add_entry(p, addr, ndm->ndm_state,
+ spin_lock_bh(&br->hash_lock);
+ err = fdb_add_entry(br, p, addr, ndm->ndm_state,
nlh_flags, vid);
- spin_unlock_bh(&p->br->hash_lock);
+ spin_unlock_bh(&br->hash_lock);
}
return err;
dev->name);
return -EINVAL;
}
+ br = p->br;
vg = nbp_vlan_group(p);
}
}
/* VID was specified, so use it. */
- if (dev->priv_flags & IFF_EBRIDGE)
- err = br_fdb_insert(br, NULL, addr, vid);
- else
- err = __br_fdb_add(ndm, p, addr, nlh_flags, vid);
+ err = __br_fdb_add(ndm, br, p, addr, nlh_flags, vid);
} else {
- if (dev->priv_flags & IFF_EBRIDGE)
- err = br_fdb_insert(br, NULL, addr, 0);
- else
- err = __br_fdb_add(ndm, p, addr, nlh_flags, 0);
+ err = __br_fdb_add(ndm, br, p, addr, nlh_flags, 0);
if (err || !vg || !vg->num_vlans)
goto out;
list_for_each_entry(v, &vg->vlan_list, vlist) {
if (!br_vlan_should_use(v))
continue;
- if (dev->priv_flags & IFF_EBRIDGE)
- err = br_fdb_insert(br, NULL, addr, v->vid);
- else
- err = __br_fdb_add(ndm, p, addr, nlh_flags,
- v->vid);
+ err = __br_fdb_add(ndm, br, p, addr, nlh_flags, v->vid);
if (err)
goto out;
}
BR_INPUT_SKB_CB(skb)->proxyarp_replied = false;
- if (dev->flags & IFF_NOARP)
+ if ((dev->flags & IFF_NOARP) ||
+ !pskb_may_pull(skb, arp_hdr_len(dev)))
return;
- if (!pskb_may_pull(skb, arp_hdr_len(dev))) {
- dev->stats.tx_dropped++;
- return;
- }
parp = arp_hdr(skb);
if (parp->ar_pro != htons(ETH_P_IP) ||
} else {
err = br_ip6_multicast_add_group(br, port,
&grec->grec_mca, vid);
- if (!err)
+ if (err)
break;
}
}
match = xt_find_match(NFPROTO_BRIDGE, m->u.name, 0);
if (IS_ERR(match) || match->family != NFPROTO_BRIDGE) {
+ if (!IS_ERR(match))
+ module_put(match->me);
request_module("ebt_%s", m->u.name);
match = xt_find_match(NFPROTO_BRIDGE, m->u.name, 0);
}
.init = nft_meta_set_init,
.destroy = nft_meta_set_destroy,
.dump = nft_meta_set_dump,
+ .validate = nft_meta_set_validate,
};
static const struct nft_expr_ops *
put_generic_request(req);
}
-void cancel_generic_request(struct ceph_mon_generic_request *req)
+static void cancel_generic_request(struct ceph_mon_generic_request *req)
{
struct ceph_mon_client *monc = req->monc;
struct ceph_mon_generic_request *lookup_req;
pages = ceph_alloc_page_vector(calc_pages_for(0, data_len),
GFP_NOIO);
- if (!pages) {
+ if (IS_ERR(pages)) {
ceph_msg_put(m);
return NULL;
}
}
EXPORT_SYMBOL(ceph_find_or_create_string);
-static void ceph_free_string(struct rcu_head *head)
-{
- struct ceph_string *cs = container_of(head, struct ceph_string, rcu);
- kfree(cs);
-}
-
void ceph_release_string(struct kref *ref)
{
struct ceph_string *cs = container_of(ref, struct ceph_string, kref);
}
spin_unlock(&string_tree_lock);
- call_rcu(&cs->rcu, ceph_free_string);
+ kfree_rcu(cs, rcu);
}
EXPORT_SYMBOL(ceph_release_string);
return skb;
}
+/**
+ * netdev_is_rx_handler_busy - check if receive handler is registered
+ * @dev: device to check
+ *
+ * Check if a receive handler is already registered for a given device.
+ * Return true if there one.
+ *
+ * The caller must hold the rtnl_mutex.
+ */
+bool netdev_is_rx_handler_busy(struct net_device *dev)
+{
+ ASSERT_RTNL();
+ return dev && rtnl_dereference(dev->rx_handler);
+}
+EXPORT_SYMBOL_GPL(netdev_is_rx_handler_busy);
+
/**
* netdev_rx_handler_register - register receive handler
* @dev: device to register a handler for
EXPORT_SYMBOL(netdev_lower_dev_get_private);
-int dev_get_nest_level(struct net_device *dev,
- bool (*type_check)(const struct net_device *dev))
+int dev_get_nest_level(struct net_device *dev)
{
struct net_device *lower = NULL;
struct list_head *iter;
ASSERT_RTNL();
netdev_for_each_lower_dev(dev, lower, iter) {
- nest = dev_get_nest_level(lower, type_check);
+ nest = dev_get_nest_level(lower);
if (max_nest < nest)
max_nest = nest;
}
- if (type_check(dev))
- max_nest++;
-
- return max_nest;
+ return max_nest + 1;
}
EXPORT_SYMBOL(dev_get_nest_level);
{
int err;
- if (!skb_cloned(skb))
- return 0;
- if (skb_clone_writable(skb, write_len))
- return 0;
- err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
- if (!err)
- bpf_compute_data_end(skb);
+ err = skb_ensure_writable(skb, write_len);
+ bpf_compute_data_end(skb);
+
return err;
}
+static inline void bpf_push_mac_rcsum(struct sk_buff *skb)
+{
+ if (skb_at_tc_ingress(skb))
+ skb_postpush_rcsum(skb, skb_mac_header(skb), skb->mac_len);
+}
+
+static inline void bpf_pull_mac_rcsum(struct sk_buff *skb)
+{
+ if (skb_at_tc_ingress(skb))
+ skb_postpull_rcsum(skb, skb_mac_header(skb), skb->mac_len);
+}
+
static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags)
{
- struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp);
struct sk_buff *skb = (struct sk_buff *) (long) r1;
- int offset = (int) r2;
+ unsigned int offset = (unsigned int) r2;
void *from = (void *) (long) r3;
unsigned int len = (unsigned int) r4;
void *ptr;
if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH)))
return -EINVAL;
-
- /* bpf verifier guarantees that:
- * 'from' pointer points to bpf program stack
- * 'len' bytes of it were initialized
- * 'len' > 0
- * 'skb' is a valid pointer to 'struct sk_buff'
- *
- * so check for invalid 'offset' and too large 'len'
- */
- if (unlikely((u32) offset > 0xffff || len > sizeof(sp->buff)))
+ if (unlikely(offset > 0xffff))
return -EFAULT;
if (unlikely(bpf_try_make_writable(skb, offset + len)))
return -EFAULT;
- ptr = skb_header_pointer(skb, offset, len, sp->buff);
- if (unlikely(!ptr))
- return -EFAULT;
-
+ ptr = skb->data + offset;
if (flags & BPF_F_RECOMPUTE_CSUM)
- skb_postpull_rcsum(skb, ptr, len);
+ __skb_postpull_rcsum(skb, ptr, len, offset);
memcpy(ptr, from, len);
- if (ptr == sp->buff)
- /* skb_store_bits cannot return -EFAULT here */
- skb_store_bits(skb, offset, ptr, len);
-
if (flags & BPF_F_RECOMPUTE_CSUM)
- skb_postpush_rcsum(skb, ptr, len);
+ __skb_postpush_rcsum(skb, ptr, len, offset);
if (flags & BPF_F_INVALIDATE_HASH)
skb_clear_hash(skb);
static u64 bpf_skb_load_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
const struct sk_buff *skb = (const struct sk_buff *)(unsigned long) r1;
- int offset = (int) r2;
+ unsigned int offset = (unsigned int) r2;
void *to = (void *)(unsigned long) r3;
unsigned int len = (unsigned int) r4;
void *ptr;
- if (unlikely((u32) offset > 0xffff))
+ if (unlikely(offset > 0xffff))
goto err_clear;
ptr = skb_header_pointer(skb, offset, len, to);
static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags)
{
struct sk_buff *skb = (struct sk_buff *) (long) r1;
- int offset = (int) r2;
- __sum16 sum, *ptr;
+ unsigned int offset = (unsigned int) r2;
+ __sum16 *ptr;
if (unlikely(flags & ~(BPF_F_HDR_FIELD_MASK)))
return -EINVAL;
- if (unlikely((u32) offset > 0xffff))
+ if (unlikely(offset > 0xffff || offset & 1))
return -EFAULT;
- if (unlikely(bpf_try_make_writable(skb, offset + sizeof(sum))))
- return -EFAULT;
-
- ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
- if (unlikely(!ptr))
+ if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr))))
return -EFAULT;
+ ptr = (__sum16 *)(skb->data + offset);
switch (flags & BPF_F_HDR_FIELD_MASK) {
case 0:
if (unlikely(from != 0))
return -EINVAL;
}
- if (ptr == &sum)
- /* skb_store_bits guaranteed to not return -EFAULT here */
- skb_store_bits(skb, offset, ptr, sizeof(sum));
-
return 0;
}
struct sk_buff *skb = (struct sk_buff *) (long) r1;
bool is_pseudo = flags & BPF_F_PSEUDO_HDR;
bool is_mmzero = flags & BPF_F_MARK_MANGLED_0;
- int offset = (int) r2;
- __sum16 sum, *ptr;
+ unsigned int offset = (unsigned int) r2;
+ __sum16 *ptr;
if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_PSEUDO_HDR |
BPF_F_HDR_FIELD_MASK)))
return -EINVAL;
- if (unlikely((u32) offset > 0xffff))
+ if (unlikely(offset > 0xffff || offset & 1))
return -EFAULT;
- if (unlikely(bpf_try_make_writable(skb, offset + sizeof(sum))))
+ if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr))))
return -EFAULT;
- ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum);
- if (unlikely(!ptr))
- return -EFAULT;
+ ptr = (__sum16 *)(skb->data + offset);
if (is_mmzero && !*ptr)
return 0;
if (is_mmzero && !*ptr)
*ptr = CSUM_MANGLED_0;
- if (ptr == &sum)
- /* skb_store_bits guaranteed to not return -EFAULT here */
- skb_store_bits(skb, offset, ptr, sizeof(sum));
-
return 0;
}
static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)
{
- if (skb_at_tc_ingress(skb))
- skb_postpush_rcsum(skb, skb_mac_header(skb), skb->mac_len);
-
return dev_forward_skb(dev, skb);
}
if (unlikely(!skb))
return -ENOMEM;
+ bpf_push_mac_rcsum(skb);
+
return flags & BPF_F_INGRESS ?
__bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb);
}
return -EINVAL;
}
+ bpf_push_mac_rcsum(skb);
+
return ri->flags & BPF_F_INGRESS ?
__bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb);
}
vlan_proto != htons(ETH_P_8021AD)))
vlan_proto = htons(ETH_P_8021Q);
+ bpf_push_mac_rcsum(skb);
ret = skb_vlan_push(skb, vlan_proto, vlan_tci);
+ bpf_pull_mac_rcsum(skb);
+
bpf_compute_data_end(skb);
return ret;
}
struct sk_buff *skb = (struct sk_buff *) (long) r1;
int ret;
+ bpf_push_mac_rcsum(skb);
ret = skb_vlan_pop(skb);
+ bpf_pull_mac_rcsum(skb);
+
bpf_compute_data_end(skb);
return ret;
}
}
#ifdef CONFIG_SOCK_CGROUP_DATA
-static u64 bpf_skb_in_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+static u64 bpf_skb_under_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
{
struct sk_buff *skb = (struct sk_buff *)(long)r1;
struct bpf_map *map = (struct bpf_map *)(long)r2;
return cgroup_is_descendant(sock_cgroup_ptr(&sk->sk_cgrp_data), cgrp);
}
-static const struct bpf_func_proto bpf_skb_in_cgroup_proto = {
- .func = bpf_skb_in_cgroup,
+static const struct bpf_func_proto bpf_skb_under_cgroup_proto = {
+ .func = bpf_skb_under_cgroup,
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
case BPF_FUNC_get_smp_processor_id:
return &bpf_get_smp_processor_id_proto;
#ifdef CONFIG_SOCK_CGROUP_DATA
- case BPF_FUNC_skb_in_cgroup:
- return &bpf_skb_in_cgroup_proto;
+ case BPF_FUNC_skb_under_cgroup:
+ return &bpf_skb_under_cgroup_proto;
#endif
default:
return sk_filter_func_proto(func_id);
void __skb_get_hash(struct sk_buff *skb)
{
struct flow_keys keys;
+ u32 hash;
__flow_hash_secret_init();
- __skb_set_sw_hash(skb, ___skb_get_hash(skb, &keys, hashrnd),
- flow_keys_have_l4(&keys));
+ hash = ___skb_get_hash(skb, &keys, hashrnd);
+
+ __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys));
}
EXPORT_SYMBOL(__skb_get_hash);
if (!try_module_get(prot->owner))
goto out_free_sec;
sk_tx_queue_clear(sk);
- cgroup_sk_alloc(&sk->sk_cgrp_data);
}
return sk;
sock_net_set(sk, net);
atomic_set(&sk->sk_wmem_alloc, 1);
+ cgroup_sk_alloc(&sk->sk_cgrp_data);
sock_update_classid(&sk->sk_cgrp_data);
sock_update_netprioidx(&sk->sk_cgrp_data);
}
newsk->sk_priority = 0;
newsk->sk_incoming_cpu = raw_smp_processor_id();
atomic64_set(&newsk->sk_cookie, 0);
+
+ cgroup_sk_alloc(&newsk->sk_cgrp_data);
+
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
};
static int __devinet_sysctl_register(struct net *net, char *dev_name,
- struct ipv4_devconf *p)
+ int ifindex, struct ipv4_devconf *p)
{
int i;
struct devinet_sysctl_table *t;
goto free;
p->sysctl = t;
+
+ inet_netconf_notify_devconf(net, NETCONFA_ALL, ifindex, p);
return 0;
free:
if (err)
return err;
err = __devinet_sysctl_register(dev_net(idev->dev), idev->dev->name,
- &idev->cnf);
+ idev->dev->ifindex, &idev->cnf);
if (err)
neigh_sysctl_unregister(idev->arp_parms);
return err;
}
#ifdef CONFIG_SYSCTL
- err = __devinet_sysctl_register(net, "all", all);
+ err = __devinet_sysctl_register(net, "all", NETCONFA_IFINDEX_ALL, all);
if (err < 0)
goto err_reg_all;
- err = __devinet_sysctl_register(net, "default", dflt);
+ err = __devinet_sysctl_register(net, "default",
+ NETCONFA_IFINDEX_DEFAULT, dflt);
if (err < 0)
goto err_reg_dflt;
if (!dev)
return -ENODEV;
cfg->fc_oif = dev->ifindex;
+ cfg->fc_table = l3mdev_fib_table(dev);
if (colon) {
struct in_ifaddr *ifa;
struct in_device *in_dev = __in_dev_get_rtnl(dev);
* First of all, we scan fib_info list searching
* for stray nexthop entries, then ignite fib_flush.
*/
- if (fib_sync_down_addr(dev_net(dev), ifa->ifa_local))
+ if (fib_sync_down_addr(dev, ifa->ifa_local))
fib_flush(dev_net(dev));
}
}
fi->fib_priority = cfg->fc_priority;
fi->fib_prefsrc = cfg->fc_prefsrc;
fi->fib_type = cfg->fc_type;
+ fi->fib_tb_id = cfg->fc_table;
fi->fib_nhs = nhs;
change_nexthops(fi) {
* referring to it.
* - device went down -> we must shutdown all nexthops going via it.
*/
-int fib_sync_down_addr(struct net *net, __be32 local)
+int fib_sync_down_addr(struct net_device *dev, __be32 local)
{
int ret = 0;
unsigned int hash = fib_laddr_hashfn(local);
struct hlist_head *head = &fib_info_laddrhash[hash];
+ struct net *net = dev_net(dev);
+ int tb_id = l3mdev_fib_table(dev);
struct fib_info *fi;
if (!fib_info_laddrhash || local == 0)
return 0;
hlist_for_each_entry(fi, head, fib_lhash) {
- if (!net_eq(fi->fib_net, net))
+ if (!net_eq(fi->fib_net, net) ||
+ fi->fib_tb_id != tb_id)
continue;
if (fi->fib_prefsrc == local) {
fi->fib_flags |= RTNH_F_DEAD;
* index into the parent's child array. That is, they will be used to find
* 'n' among tp's children.
*
- * The bits from (n->pos + n->bits) to (tn->pos - 1) - "S" - are skipped bits
+ * The bits from (n->pos + n->bits) to (tp->pos - 1) - "S" - are skipped bits
* for the node n.
*
* All the bits we have seen so far are significant to the node n. The rest
* The bits from (n->pos) to (n->pos + n->bits - 1) - "C" - are the index into
* n's child array, and will of course be different for each child.
*
- * The rest of the bits, from 0 to (n->pos + n->bits), are completely unknown
+ * The rest of the bits, from 0 to (n->pos -1) - "u" - are completely unknown
* at this point.
*/
static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
loff_t pos)
{
- struct fib_table *tb = iter->main_tb;
struct key_vector *l, **tp = &iter->tnode;
- struct trie *t;
t_key key;
/* use cache location of next-to-find key */
pos -= iter->pos;
key = iter->key;
} else {
- t = (struct trie *)tb->tb_data;
- iter->tnode = t->kv;
iter->pos = 0;
key = 0;
}
return NULL;
iter->main_tb = tb;
+ t = (struct trie *)tb->tb_data;
+ iter->tnode = t->kv;
if (*pos != 0)
return fib_route_get_idx(iter, *pos);
- t = (struct trie *)tb->tb_data;
- iter->tnode = t->kv;
iter->pos = 0;
iter->key = 0;
tunnel->parms.o_flags, proto, tunnel->parms.o_key,
htonl(tunnel->o_seqno));
- skb_set_inner_protocol(skb, proto);
ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol);
}
{
const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
+ struct net_device *dev = skb->dev;
/* if ingress device is enslaved to an L3 master device pass the
* skb to its handler for processing
*/
if (!skb_valid_dst(skb)) {
int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
- iph->tos, skb->dev);
+ iph->tos, dev);
if (unlikely(err)) {
if (err == -EXDEV)
__NET_INC_STATS(net, LINUX_MIB_IPRPFILTER);
__IP_UPD_PO_STATS(net, IPSTATS_MIB_INBCAST, skb->len);
} else if (skb->pkt_type == PACKET_BROADCAST ||
skb->pkt_type == PACKET_MULTICAST) {
- struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
+ struct in_device *in_dev = __in_dev_get_rcu(dev);
/* RFC 1122 3.3.6:
*
skb_dst_set(skb, &rt->dst);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
- if (skb_iif && proto == IPPROTO_UDP) {
- /* Arrived from an ingress interface and got udp encapuslated.
- * The encapsulated network segment length may exceed dst mtu.
+ if (skb_iif && !(df & htons(IP_DF))) {
+ /* Arrived from an ingress interface, got encapsulated, with
+ * fragmentation of encapulating frames allowed.
+ * If skb is gso, the resulting encapsulated network segments
+ * may exceed dst mtu.
* Allow IP Fragmentation of segments.
*/
IPCB(skb)->flags |= IPSKB_FRAG_SEGS;
struct net_device *dev;
struct pcpu_sw_netstats *tstats;
struct xfrm_state *x;
+ struct xfrm_mode *inner_mode;
struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4;
u32 orig_mark = skb->mark;
int ret;
}
x = xfrm_input_state(skb);
- family = x->inner_mode->afinfo->family;
+
+ inner_mode = x->inner_mode;
+
+ if (x->sel.family == AF_UNSPEC) {
+ inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
+ if (inner_mode == NULL) {
+ XFRM_INC_STATS(dev_net(skb->dev),
+ LINUX_MIB_XFRMINSTATEMODEERROR);
+ return -EINVAL;
+ }
+ }
+
+ family = inner_mode->afinfo->family;
skb->mark = be32_to_cpu(tunnel->parms.i_key);
ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
.get_link_net = ip_tunnel_get_link_net,
};
+static bool is_vti_tunnel(const struct net_device *dev)
+{
+ return dev->netdev_ops == &vti_netdev_ops;
+}
+
+static int vti_device_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+
+ if (!is_vti_tunnel(dev))
+ return NOTIFY_DONE;
+
+ switch (event) {
+ case NETDEV_DOWN:
+ if (!net_eq(tunnel->net, dev_net(dev)))
+ xfrm_garbage_collect(tunnel->net);
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block vti_notifier_block __read_mostly = {
+ .notifier_call = vti_device_event,
+};
+
static int __init vti_init(void)
{
const char *msg;
pr_info("IPv4 over IPsec tunneling driver\n");
+ register_netdevice_notifier(&vti_notifier_block);
+
msg = "tunnel device";
err = register_pernet_device(&vti_net_ops);
if (err < 0)
xfrm_proto_esp_failed:
unregister_pernet_device(&vti_net_ops);
pernet_dev_failed:
+ unregister_netdevice_notifier(&vti_notifier_block);
pr_err("vti init: failed to register %s\n", msg);
return err;
}
xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
unregister_pernet_device(&vti_net_ops);
+ unregister_netdevice_notifier(&vti_notifier_block);
}
module_init(vti_init);
struct rta_mfc_stats mfcs;
struct nlattr *mp_attr;
struct rtnexthop *nhp;
+ unsigned long lastuse;
int ct;
/* If cache is unresolved, don't try to parse IIF and OIF */
nla_nest_end(skb, mp_attr);
+ lastuse = READ_ONCE(c->mfc_un.res.lastuse);
+ lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0;
+
mfcs.mfcs_packets = c->mfc_un.res.pkt;
mfcs.mfcs_bytes = c->mfc_un.res.bytes;
mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if;
if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) ||
- nla_put_u64_64bit(skb, RTA_EXPIRES,
- jiffies_to_clock_t(c->mfc_un.res.lastuse),
+ nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse),
RTA_PAD))
return -EMSGSIZE;
__be32 saddr, daddr;
u_int8_t tos;
const struct iphdr *iph;
+ int err;
/* root is playing with raw sockets. */
if (skb->len < sizeof(struct iphdr) ||
tos = iph->tos;
ret = nft_do_chain(&pkt, priv);
- if (ret != NF_DROP && ret != NF_QUEUE) {
+ if (ret != NF_DROP && ret != NF_STOLEN) {
iph = ip_hdr(skb);
if (iph->saddr != saddr ||
iph->daddr != daddr ||
skb->mark != mark ||
- iph->tos != tos)
- if (ip_route_me_harder(state->net, skb, RTN_UNSPEC))
- ret = NF_DROP;
+ iph->tos != tos) {
+ err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+ if (err < 0)
+ ret = NF_DROP_ERR(err);
+ }
}
return ret;
}
.eval = nft_reject_ipv4_eval,
.init = nft_reject_init,
.dump = nft_reject_dump,
+ .validate = nft_reject_validate,
};
static struct nft_expr_type nft_reject_ipv4_type __read_mostly = {
atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ;
u32 old = ACCESS_ONCE(*p_tstamp);
u32 now = (u32)jiffies;
- u32 delta = 0;
+ u32 new, delta = 0;
if (old != now && cmpxchg(p_tstamp, old, now) == old)
delta = prandom_u32_max(now - old);
- return atomic_add_return(segs + delta, p_id) - segs;
+ /* Do not use atomic_add_return() as it makes UBSAN unhappy */
+ do {
+ old = (u32)atomic_read(p_id);
+ new = old + delta + segs;
+ } while (atomic_cmpxchg(p_id, old, new) != old);
+
+ return new - segs;
}
EXPORT_SYMBOL(ip_idents_reserve);
local_bh_enable();
return 0;
}
- sock_gen_put(sk);
return -EOPNOTSUPP;
}
bh_unlock_sock(sk);
local_bh_enable();
release_sock(sk);
- sock_put(sk);
return 0;
}
EXPORT_SYMBOL_GPL(tcp_abort);
{
struct net *net = sock_net(in_skb->sk);
struct sock *sk = inet_diag_find_one_icsk(net, &tcp_hashinfo, req);
+ int err;
if (IS_ERR(sk))
return PTR_ERR(sk);
- return sock_diag_destroy(sk, ECONNABORTED);
+ err = sock_diag_destroy(sk, ECONNABORTED);
+
+ sock_gen_put(sk);
+
+ return err;
}
#endif
tp->segs_in = 0;
tcp_segs_in(tp, skb);
__skb_pull(skb, tcp_hdrlen(skb));
+ sk_forced_mem_schedule(sk, skb->truesize);
skb_set_owner_r(skb, sk);
TCP_SKB_CB(skb)->seq++;
tcp_fastopen_add_skb(child, skb);
tcp_rsk(req)->rcv_nxt = tp->rcv_nxt;
+ tp->rcv_wup = tp->rcv_nxt;
/* tcp_conn_request() is sending the SYNACK,
* and queues the child into listener accept queue.
*/
* so release it.
*/
if (req) {
- tp->total_retrans = req->num_retrans;
+ inet_csk(sk)->icsk_retransmits = 0;
reqsk_fastopen_remove(sk, req, false);
} else {
/* Make sure socket is routed, for correct metrics. */
u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 :
tcp_sk(sk)->snd_nxt;
+ /* RFC 7323 2.3
+ * The window field (SEG.WND) of every outgoing segment, with the
+ * exception of <SYN> segments, MUST be right-shifted by
+ * Rcv.Wind.Shift bits:
+ */
tcp_v4_send_ack(sock_net(sk), skb, seq,
- tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd,
+ tcp_rsk(req)->rcv_nxt,
+ req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
tcp_time_stamp,
req->ts_recent,
0,
* copying overhead: fragmentation, tunneling, mangling etc.
*/
if (atomic_read(&sk->sk_wmem_alloc) >
- min(sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf))
+ min_t(u32, sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2),
+ sk->sk_sndbuf))
return -EAGAIN;
if (skb_still_in_host_queue(sk, skb))
if (tcp_retransmit_skb(sk, skb, segs))
return;
- NET_INC_STATS(sock_net(sk), mib_idx);
+ NET_ADD_STATS(sock_net(sk), mib_idx, tcp_skb_pcount(skb));
if (tcp_in_cwnd_reduction(sk))
tp->prr_out += tcp_skb_pcount(skb);
if (!res) {
__TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS);
__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
+ if (unlikely(tcp_passive_fastopen(sk)))
+ tcp_sk(sk)->total_retrans++;
}
return res;
}
*/
inet_rtx_syn_ack(sk, req);
req->num_timeout++;
+ icsk->icsk_retransmits++;
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX);
}
if (!tcp_is_cwnd_limited(sk))
return;
- if (tp->snd_cwnd <= tp->snd_ssthresh)
+ if (tcp_in_slow_start(tp))
tcp_slow_start(tp, acked);
else if (!yeah->doing_reno_now) {
* @sk: socket
*
* Drops all bad checksum frames, until a valid one is found.
- * Returns the length of found skb, or 0 if none is found.
+ * Returns the length of found skb, or -1 if none is found.
*/
-static unsigned int first_packet_length(struct sock *sk)
+static int first_packet_length(struct sock *sk)
{
struct sk_buff_head list_kill, *rcvq = &sk->sk_receive_queue;
struct sk_buff *skb;
- unsigned int res;
+ int res;
__skb_queue_head_init(&list_kill);
__skb_unlink(skb, rcvq);
__skb_queue_tail(&list_kill, skb);
}
- res = skb ? skb->len : 0;
+ res = skb ? skb->len : -1;
spin_unlock_bh(&rcvq->lock);
if (!skb_queue_empty(&list_kill)) {
case SIOCINQ:
{
- unsigned int amount = first_packet_length(sk);
+ int amount = max_t(int, 0, first_packet_length(sk));
return put_user(amount, (int __user *)arg);
}
/* Check for false positives due to checksum errors */
if ((mask & POLLRDNORM) && !(file->f_flags & O_NONBLOCK) &&
- !(sk->sk_shutdown & RCV_SHUTDOWN) && !first_packet_length(sk))
+ !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1)
mask &= ~(POLLIN | POLLRDNORM);
return mask;
.sysctl_wmem = &sysctl_udp_wmem_min,
.sysctl_rmem = &sysctl_udp_rmem_min,
.obj_size = sizeof(struct udp_sock),
- .slab_flags = SLAB_DESTROY_BY_RCU,
.h.udp_table = &udp_table,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_udp_setsockopt,
.unhash = udp_lib_unhash,
.get_port = udp_v4_get_port,
.obj_size = sizeof(struct udp_sock),
- .slab_flags = SLAB_DESTROY_BY_RCU,
.h.udp_table = &udplite_table,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_udp_setsockopt,
memset(fl4, 0, sizeof(*fl4));
fl4->daddr = daddr->a4;
fl4->flowi4_tos = tos;
- fl4->flowi4_oif = oif;
+ fl4->flowi4_oif = l3mdev_master_ifindex_by_index(net, oif);
if (saddr)
fl4->saddr = saddr->a4;
}
if (p == &net->ipv6.devconf_all->forwarding) {
+ int old_dflt = net->ipv6.devconf_dflt->forwarding;
+
net->ipv6.devconf_dflt->forwarding = newf;
+ if ((!newf) ^ (!old_dflt))
+ inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING,
+ NETCONFA_IFINDEX_DEFAULT,
+ net->ipv6.devconf_dflt);
+
addrconf_forward_change(net, newf);
if ((!newf) ^ (!old))
inet6_netconf_notify_devconf(net, NETCONFA_FORWARDING,
void addrconf_dad_failure(struct inet6_ifaddr *ifp)
{
- struct in6_addr addr;
struct inet6_dev *idev = ifp->idev;
struct net *net = dev_net(ifp->idev->dev);
in6_ifa_put(ifp2);
lock_errdad:
spin_lock_bh(&ifp->lock);
- } else if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) {
- addr.s6_addr32[0] = htonl(0xfe800000);
- addr.s6_addr32[1] = 0;
-
- if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) &&
- ipv6_addr_equal(&ifp->addr, &addr)) {
- /* DAD failed for link-local based on MAC address */
- idev->cnf.disable_ipv6 = 1;
-
- pr_info("%s: IPv6 being disabled!\n",
- ifp->idev->dev->name);
- }
}
errdad:
spin_unlock_bh(&ifp->lock);
addrconf_mod_dad_work(ifp, 0);
+ in6_ifa_put(ifp);
}
/* Join to solicited addr multicast group.
/* combine the user config with event to determine if permanent
* addresses are to be removed from address hash table
*/
- keep_addr = !(how || _keep_addr <= 0);
+ keep_addr = !(how || _keep_addr <= 0 || idev->cnf.disable_ipv6);
/* Step 2: clear hash table */
for (i = 0; i < IN6_ADDR_HSIZE; i++) {
/* re-combine the user config with event to determine if permanent
* addresses are to be removed from the interface list
*/
- keep_addr = (!how && _keep_addr > 0);
+ keep_addr = (!how && _keep_addr > 0 && !idev->cnf.disable_ipv6);
INIT_LIST_HEAD(&del_list);
list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) {
dad_work);
struct inet6_dev *idev = ifp->idev;
struct in6_addr mcaddr;
+ bool disable_ipv6 = false;
enum {
DAD_PROCESS,
} else if (ifp->state == INET6_IFADDR_STATE_ERRDAD) {
action = DAD_ABORT;
ifp->state = INET6_IFADDR_STATE_POSTDAD;
+
+ if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6 &&
+ !(ifp->flags & IFA_F_STABLE_PRIVACY)) {
+ struct in6_addr addr;
+
+ addr.s6_addr32[0] = htonl(0xfe800000);
+ addr.s6_addr32[1] = 0;
+
+ if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) &&
+ ipv6_addr_equal(&ifp->addr, &addr)) {
+ /* DAD failed for link-local based on MAC */
+ idev->cnf.disable_ipv6 = 1;
+
+ pr_info("%s: IPv6 being disabled!\n",
+ ifp->idev->dev->name);
+ disable_ipv6 = true;
+ }
+ }
}
spin_unlock_bh(&ifp->lock);
addrconf_dad_begin(ifp);
goto out;
} else if (action == DAD_ABORT) {
+ in6_ifa_hold(ifp);
addrconf_dad_stop(ifp, 1);
+ if (disable_ipv6)
+ addrconf_ifdown(idev->dev, 0);
goto out;
}
static int __addrconf_sysctl_register(struct net *net, char *dev_name,
struct inet6_dev *idev, struct ipv6_devconf *p)
{
- int i;
+ int i, ifindex;
struct ctl_table *table;
char path[sizeof("net/ipv6/conf/") + IFNAMSIZ];
if (!p->sysctl_header)
goto free;
+ if (!strcmp(dev_name, "all"))
+ ifindex = NETCONFA_IFINDEX_ALL;
+ else if (!strcmp(dev_name, "default"))
+ ifindex = NETCONFA_IFINDEX_DEFAULT;
+ else
+ ifindex = idev->dev->ifindex;
+ inet6_netconf_notify_devconf(net, NETCONFA_ALL, ifindex, p);
return 0;
free:
memcpy(new, hop, start);
ret_val = calipso_genopt((unsigned char *)new, start, buf_len, doi_def,
secattr);
- if (ret_val < 0)
+ if (ret_val < 0) {
+ kfree(new);
return ERR_PTR(ret_val);
+ }
buf_len = start + ret_val;
/* At this point buf_len aligns to 4n, so (buf_len & 4) pads to 8n */
gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags,
protocol, tunnel->parms.o_key, htonl(tunnel->o_seqno));
- skb_set_inner_protocol(skb, protocol);
-
return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu,
NEXTHDR_GRE);
}
encap_limit = t->parms.encap_limit;
memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
+ fl6.flowi6_proto = IPPROTO_IPIP;
dsfield = ipv4_get_dsfield(iph);
encap_limit = t->parms.encap_limit;
memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
+ fl6.flowi6_proto = IPPROTO_IPV6;
dsfield = ipv6_get_dsfield(ipv6h);
if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
goto discard;
}
- XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t;
-
rcu_read_unlock();
- return xfrm6_rcv(skb);
+ return xfrm6_rcv_tnl(skb, t);
}
rcu_read_unlock();
return -EINVAL;
struct net_device *dev;
struct pcpu_sw_netstats *tstats;
struct xfrm_state *x;
+ struct xfrm_mode *inner_mode;
struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6;
u32 orig_mark = skb->mark;
int ret;
}
x = xfrm_input_state(skb);
- family = x->inner_mode->afinfo->family;
+
+ inner_mode = x->inner_mode;
+
+ if (x->sel.family == AF_UNSPEC) {
+ inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
+ if (inner_mode == NULL) {
+ XFRM_INC_STATS(dev_net(skb->dev),
+ LINUX_MIB_XFRMINSTATEMODEERROR);
+ return -EINVAL;
+ }
+ }
+
+ family = inner_mode->afinfo->family;
skb->mark = be32_to_cpu(t->parms.i_key);
ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
struct rta_mfc_stats mfcs;
struct nlattr *mp_attr;
struct rtnexthop *nhp;
+ unsigned long lastuse;
int ct;
/* If cache is unresolved, don't try to parse IIF and OIF */
nla_nest_end(skb, mp_attr);
+ lastuse = READ_ONCE(c->mfc_un.res.lastuse);
+ lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0;
+
mfcs.mfcs_packets = c->mfc_un.res.pkt;
mfcs.mfcs_bytes = c->mfc_un.res.bytes;
mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if;
if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) ||
- nla_put_u64_64bit(skb, RTA_EXPIRES,
- jiffies_to_clock_t(c->mfc_un.res.lastuse),
+ nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse),
RTA_PAD))
return -EMSGSIZE;
struct in6_addr saddr, daddr;
u_int8_t hop_limit;
u32 mark, flowlabel;
+ int err;
/* malformed packet, drop it */
if (nft_set_pktinfo_ipv6(&pkt, skb, state) < 0)
flowlabel = *((u32 *)ipv6_hdr(skb));
ret = nft_do_chain(&pkt, priv);
- if (ret != NF_DROP && ret != NF_QUEUE &&
+ if (ret != NF_DROP && ret != NF_STOLEN &&
(memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) ||
memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) ||
skb->mark != mark ||
ipv6_hdr(skb)->hop_limit != hop_limit ||
- flowlabel != *((u_int32_t *)ipv6_hdr(skb))))
- return ip6_route_me_harder(state->net, skb) == 0 ? ret : NF_DROP;
+ flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) {
+ err = ip6_route_me_harder(state->net, skb);
+ if (err < 0)
+ ret = NF_DROP_ERR(err);
+ }
return ret;
}
.eval = nft_reject_ipv6_eval,
.init = nft_reject_init,
.dump = nft_reject_dump,
+ .validate = nft_reject_validate,
};
static struct nft_expr_type nft_reject_ipv6_type __read_mostly = {
struct icmp6hdr user_icmph;
int addr_type;
struct in6_addr *daddr;
- int iif = 0;
+ int oif = 0;
struct flowi6 fl6;
int err;
struct dst_entry *dst;
if (u->sin6_family != AF_INET6) {
return -EAFNOSUPPORT;
}
- if (sk->sk_bound_dev_if &&
- sk->sk_bound_dev_if != u->sin6_scope_id) {
- return -EINVAL;
- }
daddr = &(u->sin6_addr);
- iif = u->sin6_scope_id;
+ if (__ipv6_addr_needs_scope_id(ipv6_addr_type(daddr)))
+ oif = u->sin6_scope_id;
} else {
if (sk->sk_state != TCP_ESTABLISHED)
return -EDESTADDRREQ;
daddr = &sk->sk_v6_daddr;
}
- if (!iif)
- iif = sk->sk_bound_dev_if;
+ if (!oif)
+ oif = sk->sk_bound_dev_if;
+
+ if (!oif)
+ oif = np->sticky_pktinfo.ipi6_ifindex;
+
+ if (!oif && ipv6_addr_is_multicast(daddr))
+ oif = np->mcast_oif;
+ else if (!oif)
+ oif = np->ucast_oif;
addr_type = ipv6_addr_type(daddr);
- if (__ipv6_addr_needs_scope_id(addr_type) && !iif)
- return -EINVAL;
- if (addr_type & IPV6_ADDR_MAPPED)
+ if ((__ipv6_addr_needs_scope_id(addr_type) && !oif) ||
+ (addr_type & IPV6_ADDR_MAPPED) ||
+ (oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if))
return -EINVAL;
/* TODO: use ip6_datagram_send_ctl to get options from cmsg */
fl6.flowi6_proto = IPPROTO_ICMPV6;
fl6.saddr = np->saddr;
fl6.daddr = *daddr;
+ fl6.flowi6_oif = oif;
fl6.flowi6_mark = sk->sk_mark;
fl6.fl6_icmp_type = user_icmph.icmp6_type;
fl6.fl6_icmp_code = user_icmph.icmp6_code;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
- if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
- fl6.flowi6_oif = np->mcast_oif;
- else if (!fl6.flowi6_oif)
- fl6.flowi6_oif = np->ucast_oif;
-
ipc6.tclass = np->tclass;
fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
rt = (struct rt6_info *) dst;
np = inet6_sk(sk);
- if (!np)
- return -EBADF;
+ if (!np) {
+ err = -EBADF;
+ goto dst_err_out;
+ }
if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
fl6.flowi6_oif = np->mcast_oif;
}
release_sock(sk);
+dst_err_out:
+ dst_release(dst);
+
if (err)
return err;
if (!(gwa_type & IPV6_ADDR_UNICAST))
goto out;
- if (cfg->fc_table)
+ if (cfg->fc_table) {
grt = ip6_nh_lookup_table(net, cfg, gw_addr);
+ if (grt) {
+ if (grt->rt6i_flags & RTF_GATEWAY ||
+ (dev && dev != grt->dst.dev)) {
+ ip6_rt_put(grt);
+ grt = NULL;
+ }
+ }
+ }
+
if (!grt)
grt = rt6_lookup(net, gw_addr, NULL,
cfg->fc_ifindex, 1);
/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
* sk->sk_state == TCP_SYN_RECV -> for Fast Open.
*/
+ /* RFC 7323 2.3
+ * The window field (SEG.WND) of every outgoing segment, with the
+ * exception of <SYN> segments, MUST be right-shifted by
+ * Rcv.Wind.Shift bits:
+ */
tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ?
tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
- tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd,
+ tcp_rsk(req)->rcv_nxt,
+ req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
tcp_time_stamp, req->ts_recent, sk->sk_bound_dev_if,
tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr),
0, 0);
.sysctl_wmem = &sysctl_udp_wmem_min,
.sysctl_rmem = &sysctl_udp_rmem_min,
.obj_size = sizeof(struct udp6_sock),
- .slab_flags = SLAB_DESTROY_BY_RCU,
.h.udp_table = &udp_table,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_udpv6_setsockopt,
.unhash = udp_lib_unhash,
.get_port = udp_v6_get_port,
.obj_size = sizeof(struct udp6_sock),
- .slab_flags = SLAB_DESTROY_BY_RCU,
.h.udp_table = &udplite_table,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_udpv6_setsockopt,
return xfrm6_extract_header(skb);
}
-int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi)
+int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi,
+ struct ip6_tnl *t)
{
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = t;
XFRM_SPI_SKB_CB(skb)->family = AF_INET6;
XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr);
return xfrm_input(skb, nexthdr, spi, 0);
return -1;
}
-int xfrm6_rcv(struct sk_buff *skb)
+int xfrm6_rcv_tnl(struct sk_buff *skb, struct ip6_tnl *t)
{
return xfrm6_rcv_spi(skb, skb_network_header(skb)[IP6CB(skb)->nhoff],
- 0);
+ 0, t);
}
-EXPORT_SYMBOL(xfrm6_rcv);
+EXPORT_SYMBOL(xfrm6_rcv_tnl);
+int xfrm6_rcv(struct sk_buff *skb)
+{
+ return xfrm6_rcv_tnl(skb, NULL);
+}
+EXPORT_SYMBOL(xfrm6_rcv);
int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
xfrm_address_t *saddr, u8 proto)
{
int err;
memset(&fl6, 0, sizeof(fl6));
- fl6.flowi6_oif = oif;
+ fl6.flowi6_oif = l3mdev_master_ifindex_by_index(net, oif);
fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF;
memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr));
if (saddr)
__be32 spi;
spi = xfrm6_tunnel_spi_lookup(net, (const xfrm_address_t *)&iph->saddr);
- return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi);
+ return xfrm6_rcv_spi(skb, IPPROTO_IPV6, spi, NULL);
}
static int xfrm6_tunnel_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
struct sock *sk = sock->sk;
struct irda_sock *new, *self = irda_sk(sk);
struct sock *newsk;
- struct sk_buff *skb;
+ struct sk_buff *skb = NULL;
int err;
err = irda_create(sock_net(sk), newsock, sk->sk_protocol, 0);
err = -EPERM; /* value does not seem to make sense. -arnd */
if (!new->tsap) {
pr_debug("%s(), dup failed!\n", __func__);
- kfree_skb(skb);
goto out;
}
/* Clean up the original one to keep it in listen state */
irttp_listen(self->tsap);
- kfree_skb(skb);
sk->sk_ack_backlog--;
newsock->state = SS_CONNECTED;
irda_connect_response(new);
err = 0;
out:
+ kfree_skb(skb);
release_sock(sk);
return err;
}
self->magic = IAS_MAGIC;
self->mode = mode;
- if (mode == IAS_CLIENT)
- iriap_register_lsap(self, slsap_sel, mode);
+ if (mode == IAS_CLIENT) {
+ if (iriap_register_lsap(self, slsap_sel, mode)) {
+ kfree(self);
+ return NULL;
+ }
+ }
self->confirm = callback;
self->priv = priv;
#include <linux/socket.h>
#include <linux/uaccess.h>
#include <linux/workqueue.h>
+#include <linux/syscalls.h>
#include <net/kcm.h>
#include <net/netns/generic.h>
#include <net/sock.h>
if (copy_to_user((void __user *)arg, &info,
sizeof(info))) {
err = -EFAULT;
- sock_release(newsock);
+ sys_close(info.fd);
}
}
(void)l2tp_tunnel_delete(tunnel);
}
rcu_read_unlock_bh();
+
+ flush_workqueue(l2tp_wq);
+ rcu_barrier();
}
static struct pernet_operations l2tp_net_ops = {
error = -ENOTCONN;
if (sk == NULL)
goto end;
- if (sk->sk_state != PPPOX_CONNECTED)
+ if (!(sk->sk_state & PPPOX_CONNECTED))
goto end;
error = -EBADF;
.timeout = timeout,
.ssn = start_seq_num,
};
-
int i, ret = -EOPNOTSUPP;
u16 status = WLAN_STATUS_REQUEST_DECLINED;
+ if (tid >= IEEE80211_FIRST_TSPEC_TSID) {
+ ht_dbg(sta->sdata,
+ "STA %pM requests BA session on unsupported tid %d\n",
+ sta->sta.addr, tid);
+ goto end_no_lock;
+ }
+
if (!sta->sta.ht_cap.ht_supported) {
ht_dbg(sta->sdata,
"STA %pM erroneously requests BA session on tid %d w/o QoS\n",
ieee80211_hw_check(&local->hw, TX_AMPDU_SETUP_IN_HW))
return -EINVAL;
+ if (WARN_ON(tid >= IEEE80211_FIRST_TSPEC_TSID))
+ return -EINVAL;
+
ht_dbg(sdata, "Open BA session requested for %pM tid %u\n",
pubsta->addr, tid);
/* free all potentially still buffered bcast frames */
local->total_ps_buffered -= skb_queue_len(&sdata->u.ap.ps.bc_buf);
- skb_queue_purge(&sdata->u.ap.ps.bc_buf);
+ ieee80211_purge_tx_queue(&local->hw, &sdata->u.ap.ps.bc_buf);
mutex_lock(&local->mtx);
ieee80211_vif_copy_chanctx_to_vlans(sdata, true);
trace_drv_get_expected_throughput(sta);
if (local->ops->get_expected_throughput)
- ret = local->ops->get_expected_throughput(sta);
+ ret = local->ops->get_expected_throughput(&local->hw, sta);
trace_drv_return_u32(local, ret);
return ret;
netif_carrier_off(sdata->dev);
+ /* flush STAs and mpaths on this iface */
+ sta_info_flush(sdata);
+ mesh_path_flush_by_iface(sdata);
+
/* stop the beacon */
ifmsh->mesh_id_len = 0;
sdata->vif.bss_conf.enable_beacon = false;
clear_bit(SDATA_STATE_OFFCHANNEL_BEACON_STOPPED, &sdata->state);
ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED);
+
+ /* remove beacon */
bcn = rcu_dereference_protected(ifmsh->beacon,
lockdep_is_held(&sdata->wdev.mtx));
RCU_INIT_POINTER(ifmsh->beacon, NULL);
kfree_rcu(bcn, rcu_head);
- /* flush STAs and mpaths on this iface */
- sta_info_flush(sdata);
- mesh_path_flush_by_iface(sdata);
-
/* free all potentially still buffered group-addressed frames */
local->total_ps_buffered -= skb_queue_len(&ifmsh->ps.bc_buf);
skb_queue_purge(&ifmsh->ps.bc_buf);
sta = next_hop_deref_protected(mpath);
if (mpath->flags & MESH_PATH_ACTIVE &&
ether_addr_equal(ta, sta->sta.addr) &&
+ !(mpath->flags & MESH_PATH_FIXED) &&
(!(mpath->flags & MESH_PATH_SN_VALID) ||
SN_GT(target_sn, mpath->sn) || target_sn == 0)) {
mpath->flags &= ~MESH_PATH_ACTIVE;
goto enddiscovery;
spin_lock_bh(&mpath->state_lock);
- if (mpath->flags & MESH_PATH_DELETED) {
+ if (mpath->flags & (MESH_PATH_DELETED | MESH_PATH_FIXED)) {
spin_unlock_bh(&mpath->state_lock);
goto enddiscovery;
}
mpath->metric = 0;
mpath->hop_count = 0;
mpath->exp_time = 0;
- mpath->flags |= MESH_PATH_FIXED;
+ mpath->flags = MESH_PATH_FIXED | MESH_PATH_SN_VALID;
mesh_path_activate(mpath);
spin_unlock_bh(&mpath->state_lock);
mesh_path_tx_pending(mpath);
for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) {
struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]);
- if (!txqi->tin.backlog_packets)
+ if (txqi->tin.backlog_packets)
set_bit(tid, &sta->txq_buffered_tids);
else
clear_bit(tid, &sta->txq_buffered_tids);
sta_info_recalc_tim(sta);
} else {
- unsigned long tids = sta->txq_buffered_tids & driver_release_tids;
int tid;
/*
for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) {
struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]);
- if (!(tids & BIT(tid)) || txqi->tin.backlog_packets)
+ if (!(driver_release_tids & BIT(tid)) ||
+ txqi->tin.backlog_packets)
continue;
sta_info_recalc_tim(sta);
clear_sta_flag(sta, WLAN_STA_SP);
acked = !!(info->flags & IEEE80211_TX_STAT_ACK);
+
+ /* mesh Peer Service Period support */
+ if (ieee80211_vif_is_mesh(&sta->sdata->vif) &&
+ ieee80211_is_data_qos(fc))
+ ieee80211_mpsp_trigger_process(
+ ieee80211_get_qos_ctl(hdr), sta, true, acked);
+
if (!acked && test_sta_flag(sta, WLAN_STA_PS_STA)) {
/*
* The STA is in power save mode, so assume
return;
}
- /* mesh Peer Service Period support */
- if (ieee80211_vif_is_mesh(&sta->sdata->vif) &&
- ieee80211_is_data_qos(fc))
- ieee80211_mpsp_trigger_process(
- ieee80211_get_qos_ctl(hdr),
- sta, true, acked);
-
if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL) &&
(ieee80211_is_data(hdr->frame_control)) &&
(rates_idx != -1))
if (!uc.center_freq1)
return;
- /* proceed to downgrade the chandef until usable or the same */
+ /* proceed to downgrade the chandef until usable or the same as AP BW */
while (uc.width > max_width ||
- !cfg80211_reg_can_beacon_relax(sdata->local->hw.wiphy, &uc,
- sdata->wdev.iftype))
+ (uc.width > sta->tdls_chandef.width &&
+ !cfg80211_reg_can_beacon_relax(sdata->local->hw.wiphy, &uc,
+ sdata->wdev.iftype)))
ieee80211_chandef_downgrade(&uc);
if (!cfg80211_chandef_identical(&uc, &sta->tdls_chandef)) {
skb = skb_dequeue(&ps->bc_buf);
if (skb) {
purged++;
- dev_kfree_skb(skb);
+ ieee80211_free_txskb(&local->hw, skb);
}
total += skb_queue_len(&ps->bc_buf);
}
if (skb_queue_len(&ps->bc_buf) >= AP_MAX_BC_BUFFER) {
ps_dbg(tx->sdata,
"BC TX buffer full - dropping the oldest frame\n");
- dev_kfree_skb(skb_dequeue(&ps->bc_buf));
+ ieee80211_free_txskb(&tx->local->hw, skb_dequeue(&ps->bc_buf));
} else
tx->local->total_ps_buffered++;
return ret;
}
+static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local,
+ struct ieee80211_vif *vif,
+ struct ieee80211_sta *pubsta,
+ struct sk_buff *skb)
+{
+ struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
+ struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+ struct ieee80211_txq *txq = NULL;
+
+ if ((info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM) ||
+ (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE))
+ return NULL;
+
+ if (!ieee80211_is_data(hdr->frame_control))
+ return NULL;
+
+ if (pubsta) {
+ u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
+
+ txq = pubsta->txq[tid];
+ } else if (vif) {
+ txq = vif->txq;
+ }
+
+ if (!txq)
+ return NULL;
+
+ return to_txq_info(txq);
+}
+
static ieee80211_tx_result debug_noinline
ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx)
{
tid = *qc & IEEE80211_QOS_CTL_TID_MASK;
tx->sta->tx_stats.msdu[tid]++;
- if (!tx->sta->sta.txq[0])
+ if (!ieee80211_get_txq(tx->local, info->control.vif, &tx->sta->sta,
+ tx->skb))
hdr->seq_ctrl = ieee80211_tx_next_seq(tx->sta, tid);
return TX_CONTINUE;
return TX_CONTINUE;
}
-static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local,
- struct ieee80211_vif *vif,
- struct ieee80211_sta *pubsta,
- struct sk_buff *skb)
-{
- struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
- struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
- struct ieee80211_txq *txq = NULL;
-
- if ((info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM) ||
- (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE))
- return NULL;
-
- if (!ieee80211_is_data(hdr->frame_control))
- return NULL;
-
- if (pubsta) {
- u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
-
- txq = pubsta->txq[tid];
- } else if (vif) {
- txq = vif->txq;
- }
-
- if (!txq)
- return NULL;
-
- return to_txq_info(txq);
-}
-
static void ieee80211_set_skb_enqueue_time(struct sk_buff *skb)
{
IEEE80211_SKB_CB(skb)->control.enqueue_time = codel_get_time();
spin_unlock_bh(&fq->lock);
if (skb && skb_has_frag_list(skb) &&
- !ieee80211_hw_check(&local->hw, TX_FRAG_LIST))
- skb_linearize(skb);
+ !ieee80211_hw_check(&local->hw, TX_FRAG_LIST)) {
+ if (skb_linearize(skb)) {
+ ieee80211_free_txskb(&local->hw, skb);
+ return NULL;
+ }
+ }
return skb;
}
if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) {
*ieee80211_get_qos_ctl(hdr) = tid;
- if (!sta->sta.txq[0])
+ if (!ieee80211_get_txq(local, &sdata->vif, &sta->sta, skb))
hdr->seq_ctrl = ieee80211_tx_next_seq(sta, tid);
} else {
info->flags |= IEEE80211_TX_CTL_ASSIGN_SEQ;
sdata = IEEE80211_DEV_TO_SUB_IF(skb->dev);
if (!ieee80211_tx_prepare(sdata, &tx, NULL, skb))
break;
- dev_kfree_skb_any(skb);
+ ieee80211_free_txskb(hw, skb);
}
info = IEEE80211_SKB_CB(skb);
if (IS_ERR(ct))
return (struct nf_conntrack_tuple_hash *)ct;
- if (tmpl && nfct_synproxy(tmpl)) {
- nfct_seqadj_ext_add(ct);
- nfct_synproxy_ext_add(ct);
+ if (!nf_ct_add_synproxy(ct, tmpl)) {
+ nf_conntrack_free(ct);
+ return ERR_PTR(-ENOMEM);
}
timeout_ext = tmpl ? nf_ct_timeout_find(tmpl) : NULL;
helper = rcu_dereference(nfct_help(expect->master)->helper);
if (helper) {
seq_printf(s, "%s%s", expect->flags ? " " : "", helper->name);
- if (helper->expect_policy[expect->class].name)
+ if (helper->expect_policy[expect->class].name[0])
seq_printf(s, "/%s",
helper->expect_policy[expect->class].name);
}
"timeout to %u seconds for",
info->timeout);
nf_ct_dump_tuple(&exp->tuple);
- mod_timer(&exp->timeout, jiffies + info->timeout * HZ);
+ mod_timer_pending(&exp->timeout,
+ jiffies + info->timeout * HZ);
}
spin_unlock_bh(&nf_conntrack_expect_lock);
}
if (!cda[CTA_TUPLE_ORIG] || !cda[CTA_TUPLE_REPLY])
return -EINVAL;
+ if (otuple.dst.protonum != rtuple.dst.protonum)
+ return -EINVAL;
ct = ctnetlink_create_conntrack(net, &zone, cda, &otuple,
&rtuple, u3);
return PTR_ERR(exp);
err = nf_ct_expect_related_report(exp, portid, report);
- if (err < 0) {
- nf_ct_expect_put(exp);
- return err;
- }
-
- return 0;
+ nf_ct_expect_put(exp);
+ return err;
}
static void ctnetlink_glue_seqadj(struct sk_buff *skb, struct nf_conn *ct,
return NF_DROP;
}
cseq = simple_strtoul(*dptr + matchoff, NULL, 10);
- if (!cseq) {
+ if (!cseq && *(*dptr + matchoff) != '0') {
nf_ct_helper_log(skb, ct, "cannot get cseq");
return NF_DROP;
}
return NF_DROP;
}
cseq = simple_strtoul(*dptr + matchoff, NULL, 10);
- if (!cseq) {
+ if (!cseq && *(*dptr + matchoff) != '0') {
nf_ct_helper_log(skb, ct, "cannot get cseq");
return NF_DROP;
}
struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash);
const struct nf_conntrack_l3proto *l3proto;
const struct nf_conntrack_l4proto *l4proto;
+ struct net *net = seq_file_net(s);
int ret = 0;
NF_CT_ASSERT(ct);
if (NF_CT_DIRECTION(hash))
goto release;
+ if (!net_eq(nf_ct_net(ct), net))
+ goto release;
+
l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct));
NF_CT_ASSERT(l3proto);
l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
ct->status |= IPS_DST_NAT;
if (nfct_help(ct))
- nfct_seqadj_ext_add(ct);
+ if (!nfct_seqadj_ext_add(ct))
+ return NF_DROP;
}
if (maniptype == NF_NAT_MANIP_SRC) {
if (err < 0)
return err;
- return nf_nat_setup_info(ct, &range, manip);
+ return nf_nat_setup_info(ct, &range, manip) == NF_DROP ? -ENOMEM : 0;
}
#else
static int
if (!iph)
return;
- iph = ip_hdr(skb);
if (iph->ihl < 5 || iph->version != 4)
return;
break;
case NFT_TRACETYPE_POLICY:
if (nla_put_be32(skb, NFTA_TRACE_POLICY,
- info->basechain->policy))
+ htonl(info->basechain->policy)))
goto nla_put_failure;
break;
}
{
int ret = 0;
- /* we want to avoid races with nfnl_acct_find_get. */
- if (atomic_dec_and_test(&cur->refcnt)) {
+ /* We want to avoid races with nfnl_acct_put. So only when the current
+ * refcnt is 1, we decrease it to 0.
+ */
+ if (atomic_cmpxchg(&cur->refcnt, 1, 0) == 1) {
/* We are protected by nfnl mutex. */
list_del_rcu(&cur->head);
kfree_rcu(cur, rcu_head);
} else {
- /* still in use, restore reference counter. */
- atomic_inc(&cur->refcnt);
ret = -EBUSY;
}
return ret;
struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const tb[])
{
- char *acct_name;
- struct nf_acct *cur;
+ struct nf_acct *cur, *tmp;
int ret = -ENOENT;
+ char *acct_name;
if (!tb[NFACCT_NAME]) {
- list_for_each_entry(cur, &net->nfnl_acct_list, head)
+ list_for_each_entry_safe(cur, tmp, &net->nfnl_acct_list, head)
nfnl_acct_try_del(cur);
return 0;
}
EXPORT_SYMBOL_GPL(nfnl_acct_update);
-static void nfnl_overquota_report(struct nf_acct *nfacct)
+static void nfnl_overquota_report(struct net *net, struct nf_acct *nfacct)
{
int ret;
struct sk_buff *skb;
kfree_skb(skb);
return;
}
- netlink_broadcast(init_net.nfnl, skb, 0, NFNLGRP_ACCT_QUOTA,
+ netlink_broadcast(net->nfnl, skb, 0, NFNLGRP_ACCT_QUOTA,
GFP_ATOMIC);
}
-int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct)
+int nfnl_acct_overquota(struct net *net, const struct sk_buff *skb,
+ struct nf_acct *nfacct)
{
u64 now;
u64 *quota;
if (now >= *quota &&
!test_and_set_bit(NFACCT_OVERQUOTA_BIT, &nfacct->flags)) {
- nfnl_overquota_report(nfacct);
+ nfnl_overquota_report(net, nfacct);
}
return ret;
break;
}
- l4proto = nf_ct_l4proto_find_get(l3num, l4num);
-
- /* This protocol is not supportted, skip. */
- if (l4proto->l4proto != l4num) {
- ret = -EOPNOTSUPP;
- goto err_proto_put;
- }
-
if (matching) {
if (nlh->nlmsg_flags & NLM_F_REPLACE) {
/* You cannot replace one timeout policy by another of
* different kind, sorry.
*/
if (matching->l3num != l3num ||
- matching->l4proto->l4proto != l4num) {
- ret = -EINVAL;
- goto err_proto_put;
- }
-
- ret = ctnl_timeout_parse_policy(&matching->data,
- l4proto, net,
- cda[CTA_TIMEOUT_DATA]);
- return ret;
+ matching->l4proto->l4proto != l4num)
+ return -EINVAL;
+
+ return ctnl_timeout_parse_policy(&matching->data,
+ matching->l4proto, net,
+ cda[CTA_TIMEOUT_DATA]);
}
- ret = -EBUSY;
+
+ return -EBUSY;
+ }
+
+ l4proto = nf_ct_l4proto_find_get(l3num, l4num);
+
+ /* This protocol is not supportted, skip. */
+ if (l4proto->l4proto != l4num) {
+ ret = -EOPNOTSUPP;
goto err_proto_put;
}
const struct hlist_nulls_node *nn;
unsigned int last_hsize;
spinlock_t *lock;
- int i;
+ int i, cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
+
+ spin_lock_bh(&pcpu->lock);
+ hlist_nulls_for_each_entry(h, nn, &pcpu->unconfirmed, hnnode)
+ untimeout(h, timeout);
+ spin_unlock_bh(&pcpu->lock);
+ }
local_bh_disable();
restart:
{
int ret = 0;
- /* we want to avoid races with nf_ct_timeout_find_get. */
- if (atomic_dec_and_test(&timeout->refcnt)) {
+ /* We want to avoid races with ctnl_timeout_put. So only when the
+ * current refcnt is 1, we decrease it to 0.
+ */
+ if (atomic_cmpxchg(&timeout->refcnt, 1, 0) == 1) {
/* We are protected by nfnl mutex. */
list_del_rcu(&timeout->head);
nf_ct_l4proto_put(timeout->l4proto);
ctnl_untimeout(net, timeout);
kfree_rcu(timeout, rcu_head);
} else {
- /* still in use, restore reference counter. */
- atomic_inc(&timeout->refcnt);
ret = -EBUSY;
}
return ret;
const struct nlmsghdr *nlh,
const struct nlattr * const cda[])
{
- struct ctnl_timeout *cur;
+ struct ctnl_timeout *cur, *tmp;
int ret = -ENOENT;
char *name;
if (!cda[CTA_TIMEOUT_NAME]) {
- list_for_each_entry(cur, &net->nfct_timeout_list, head)
+ list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list,
+ head)
ctnl_timeout_try_del(net, cur);
return 0;
static void ctnl_timeout_put(struct ctnl_timeout *timeout)
{
- atomic_dec(&timeout->refcnt);
+ if (atomic_dec_and_test(&timeout->refcnt))
+ kfree_rcu(timeout, rcu_head);
+
module_put(THIS_MODULE);
}
#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list, head) {
list_del_rcu(&cur->head);
nf_ct_l4proto_put(cur->l4proto);
- kfree_rcu(cur, rcu_head);
+
+ if (atomic_dec_and_test(&cur->refcnt))
+ kfree_rcu(cur, rcu_head);
}
}
MODULE_ALIAS_NF_LOGGER(AF_INET, 1);
MODULE_ALIAS_NF_LOGGER(AF_INET6, 1);
MODULE_ALIAS_NF_LOGGER(AF_BRIDGE, 1);
+MODULE_ALIAS_NF_LOGGER(3, 1); /* NFPROTO_ARP */
module_init(nfnetlink_log_init);
module_exit(nfnetlink_log_fini);
struct nfnl_queue_net *q = nfnl_queue_pernet(net);
int err;
- queue = instance_lookup(q, queue_num);
- if (!queue)
- queue = verdict_instance_lookup(q, queue_num,
- NETLINK_CB(skb).portid);
+ queue = verdict_instance_lookup(q, queue_num,
+ NETLINK_CB(skb).portid);
if (IS_ERR(queue))
return PTR_ERR(queue);
const struct nlattr * const tb[])
{
struct nft_exthdr *priv = nft_expr_priv(expr);
+ u32 offset, len;
if (tb[NFTA_EXTHDR_DREG] == NULL ||
tb[NFTA_EXTHDR_TYPE] == NULL ||
tb[NFTA_EXTHDR_LEN] == NULL)
return -EINVAL;
+ offset = ntohl(nla_get_be32(tb[NFTA_EXTHDR_OFFSET]));
+ len = ntohl(nla_get_be32(tb[NFTA_EXTHDR_LEN]));
+
+ if (offset > U8_MAX || len > U8_MAX)
+ return -ERANGE;
+
priv->type = nla_get_u8(tb[NFTA_EXTHDR_TYPE]);
- priv->offset = ntohl(nla_get_be32(tb[NFTA_EXTHDR_OFFSET]));
- priv->len = ntohl(nla_get_be32(tb[NFTA_EXTHDR_LEN]));
+ priv->offset = offset;
+ priv->len = len;
priv->dreg = nft_parse_register(tb[NFTA_EXTHDR_DREG]);
return nft_validate_register_store(ctx, priv->dreg, NULL,
}
EXPORT_SYMBOL_GPL(nft_meta_get_init);
-static int nft_meta_set_init_pkttype(const struct nft_ctx *ctx)
+int nft_meta_set_validate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nft_data **data)
{
+ struct nft_meta *priv = nft_expr_priv(expr);
unsigned int hooks;
+ if (priv->key != NFT_META_PKTTYPE)
+ return 0;
+
switch (ctx->afi->family) {
case NFPROTO_BRIDGE:
hooks = 1 << NF_BR_PRE_ROUTING;
return nft_chain_validate_hooks(ctx->chain, hooks);
}
+EXPORT_SYMBOL_GPL(nft_meta_set_validate);
int nft_meta_set_init(const struct nft_ctx *ctx,
const struct nft_expr *expr,
len = sizeof(u8);
break;
case NFT_META_PKTTYPE:
- err = nft_meta_set_init_pkttype(ctx);
- if (err)
- return err;
len = sizeof(u8);
break;
default:
return -EOPNOTSUPP;
}
+ err = nft_meta_set_validate(ctx, expr, NULL);
+ if (err < 0)
+ return err;
+
priv->sreg = nft_parse_register(tb[NFTA_META_SREG]);
err = nft_validate_register_load(priv->sreg, len);
if (err < 0)
.init = nft_meta_set_init,
.destroy = nft_meta_set_destroy,
.dump = nft_meta_set_dump,
+ .validate = nft_meta_set_validate,
};
static const struct nft_expr_ops *
} else if (d > 0)
parent = parent->rb_right;
else {
-found:
if (!nft_set_elem_active(&rbe->ext, genmask)) {
parent = parent->rb_left;
continue;
}
}
- if (set->flags & NFT_SET_INTERVAL && interval != NULL) {
- rbe = interval;
- goto found;
+ if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
+ nft_set_elem_active(&interval->ext, genmask) &&
+ !nft_rbtree_interval_end(interval)) {
+ spin_unlock_bh(&nft_rbtree_lock);
+ *ext = &interval->ext;
+ return true;
}
out:
spin_unlock_bh(&nft_rbtree_lock);
};
EXPORT_SYMBOL_GPL(nft_reject_policy);
+int nft_reject_validate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nft_data **data)
+{
+ return nft_chain_validate_hooks(ctx->chain,
+ (1 << NF_INET_LOCAL_IN) |
+ (1 << NF_INET_FORWARD) |
+ (1 << NF_INET_LOCAL_OUT));
+}
+EXPORT_SYMBOL_GPL(nft_reject_validate);
+
int nft_reject_init(const struct nft_ctx *ctx,
const struct nft_expr *expr,
const struct nlattr * const tb[])
{
struct nft_reject *priv = nft_expr_priv(expr);
+ int err;
+
+ err = nft_reject_validate(ctx, expr, NULL);
+ if (err < 0)
+ return err;
if (tb[NFTA_REJECT_TYPE] == NULL)
return -EINVAL;
const struct nlattr * const tb[])
{
struct nft_reject *priv = nft_expr_priv(expr);
- int icmp_code;
+ int icmp_code, err;
+
+ err = nft_reject_validate(ctx, expr, NULL);
+ if (err < 0)
+ return err;
if (tb[NFTA_REJECT_TYPE] == NULL)
return -EINVAL;
.eval = nft_reject_inet_eval,
.init = nft_reject_inet_init,
.dump = nft_reject_inet_dump,
+ .validate = nft_reject_validate,
};
static struct nft_expr_type nft_reject_inet_type __read_mostly = {
daddr, dport,
in->ifindex);
+ if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
+ sk = NULL;
/* NOTE: we return listeners even if bound to
* 0.0.0.0, those are filtered out in
* xt_socket, since xt_TPROXY needs 0 bound
daddr, ntohs(dport),
in->ifindex);
+ if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
+ sk = NULL;
/* NOTE: we return listeners even if bound to
* 0.0.0.0, those are filtered out in
* xt_socket, since xt_TPROXY needs 0 bound
nfnl_acct_update(skb, info->nfacct);
- overquota = nfnl_acct_overquota(skb, info->nfacct);
+ overquota = nfnl_acct_overquota(par->net, skb, info->nfacct);
return overquota == NFACCT_UNDERQUOTA ? false : true;
}
struct nf_conntrack_l4proto *l4proto;
struct nf_conntrack_tuple tuple;
struct nf_conntrack_tuple_hash *h;
- enum ip_conntrack_info ctinfo;
struct nf_conn *ct;
unsigned int dataoff;
u8 protonum;
ct = nf_ct_tuplehash_to_ctrack(h);
- ctinfo = ovs_ct_get_info(h);
- if (ctinfo == IP_CT_NEW) {
- /* This should not happen. */
- WARN_ONCE(1, "ovs_ct_find_existing: new packet for %p\n", ct);
- }
skb->nfct = &ct->ct_general;
- skb->nfctinfo = ctinfo;
+ skb->nfctinfo = ovs_ct_get_info(h);
return ct;
}
return ERR_CAST(dev);
}
- dev_change_flags(dev, dev->flags | IFF_UP);
+ err = dev_change_flags(dev, dev->flags | IFF_UP);
+ if (err < 0) {
+ rtnl_delete_link(dev);
+ rtnl_unlock();
+ ovs_vport_free(vport);
+ goto error;
+ }
+
rtnl_unlock();
return vport;
error:
struct net *net = ovs_dp_get_net(parms->dp);
struct net_device *dev;
struct vport *vport;
+ int err;
vport = ovs_vport_alloc(0, &ovs_gre_vport_ops, parms);
if (IS_ERR(vport))
return ERR_CAST(dev);
}
- dev_change_flags(dev, dev->flags | IFF_UP);
- rtnl_unlock();
+ err = dev_change_flags(dev, dev->flags | IFF_UP);
+ if (err < 0) {
+ rtnl_delete_link(dev);
+ rtnl_unlock();
+ ovs_vport_free(vport);
+ return ERR_PTR(err);
+ }
+ rtnl_unlock();
return vport;
}
static void internal_set_rx_headroom(struct net_device *dev, int new_hr)
{
- dev->needed_headroom = new_hr;
+ dev->needed_headroom = new_hr < 0 ? 0 : new_hr;
}
static const struct net_device_ops internal_dev_netdev_ops = {
return ERR_CAST(dev);
}
- dev_change_flags(dev, dev->flags | IFF_UP);
+ err = dev_change_flags(dev, dev->flags | IFF_UP);
+ if (err < 0) {
+ rtnl_delete_link(dev);
+ rtnl_unlock();
+ ovs_vport_free(vport);
+ goto error;
+ }
+
rtnl_unlock();
return vport;
error:
spinlock_t lock;
rwlock_t state_lock; /* lock for state transition */
atomic_t usage;
+ atomic_t skb_count; /* Outstanding packets on this call */
atomic_t sequence; /* Tx data packet sequence counter */
u32 local_abort; /* local abort code */
u32 remote_abort; /* remote abort code */
call->state = RXRPC_CALL_SERVER_ACCEPTING;
list_add_tail(&call->accept_link, &rx->acceptq);
rxrpc_get_call(call);
+ atomic_inc(&call->skb_count);
nsp = rxrpc_skb(notification);
nsp->call = call;
ASSERTCMP(sp->call, ==, NULL);
sp->call = call;
rxrpc_get_call(call);
+ atomic_inc(&call->skb_count);
/* insert into the buffer in sequence order */
spin_lock_bh(&call->lock);
skb->mark = RXRPC_SKB_MARK_FINAL_ACK;
sp->call = call;
rxrpc_get_call(call);
+ atomic_inc(&call->skb_count);
spin_lock_bh(&call->lock);
if (rxrpc_queue_rcv_skb(call, skb, true, true) < 0)
BUG();
sp->error = error;
sp->call = call;
rxrpc_get_call(call);
+ atomic_inc(&call->skb_count);
spin_lock_bh(&call->lock);
ret = rxrpc_queue_rcv_skb(call, skb, true, fatal);
return;
}
+ if (!call->conn)
+ goto skip_msg_init;
+
/* there's a good chance we're going to have to send a message, so set
* one up in advance */
msg.msg_name = &call->conn->params.peer->srx.transport;
memset(iov, 0, sizeof(iov));
iov[0].iov_base = &whdr;
iov[0].iov_len = sizeof(whdr);
+skip_msg_init:
/* deal with events of a final nature */
if (test_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events)) {
list_del_init(&call->link);
write_unlock_bh(&rxrpc_call_lock);
+ set_bit(RXRPC_CALL_RELEASED, &call->flags);
call->state = RXRPC_CALL_DEAD;
rxrpc_put_call(call);
_leave(" = %d", ret);
*/
found_user_ID_now_present:
write_unlock(&rx->call_lock);
+ set_bit(RXRPC_CALL_RELEASED, &call->flags);
call->state = RXRPC_CALL_DEAD;
rxrpc_put_call(call);
_leave(" = -EEXIST [%p]", call);
spin_lock_bh(&call->lock);
while ((skb = skb_dequeue(&call->rx_queue)) ||
(skb = skb_dequeue(&call->rx_oos_queue))) {
- sp = rxrpc_skb(skb);
- if (sp->call) {
- ASSERTCMP(sp->call, ==, call);
- rxrpc_put_call(call);
- sp->call = NULL;
- }
- skb->destructor = NULL;
spin_unlock_bh(&call->lock);
+ sp = rxrpc_skb(skb);
_debug("- zap %s %%%u #%u",
rxrpc_pkts[sp->hdr.type],
sp->hdr.serial, sp->hdr.seq);
if (atomic_dec_and_test(&call->usage)) {
_debug("call %d dead", call->debug_id);
+ WARN_ON(atomic_read(&call->skb_count) != 0);
ASSERTCMP(call->state, ==, RXRPC_CALL_DEAD);
rxrpc_queue_work(&call->destroyer);
}
if (test_bit(RXRPC_CALL_TERMINAL_MSG, &call->flags)) {
_debug("already terminated");
ASSERTCMP(call->state, >=, RXRPC_CALL_COMPLETE);
- skb->destructor = NULL;
- sp->call = NULL;
- rxrpc_put_call(call);
rxrpc_free_skb(skb);
return 0;
}
ret = 0;
out:
- /* release the socket buffer */
- if (skb) {
- skb->destructor = NULL;
- sp->call = NULL;
- rxrpc_put_call(call);
- rxrpc_free_skb(skb);
- }
+ rxrpc_free_skb(skb);
_leave(" = %d", ret);
return ret;
struct rxrpc_skb_priv *sp;
bool terminal;
int ret, ackbit, ack;
+ u32 serial;
+ u8 flags;
_enter("{%u,%u},,{%u}", call->rx_data_post, call->rx_first_oos, seq);
sp = rxrpc_skb(skb);
ASSERTCMP(sp->call, ==, NULL);
+ flags = sp->hdr.flags;
+ serial = sp->hdr.serial;
spin_lock(&call->lock);
sp->call = call;
rxrpc_get_call(call);
- terminal = ((sp->hdr.flags & RXRPC_LAST_PACKET) &&
- !(sp->hdr.flags & RXRPC_CLIENT_INITIATED));
+ atomic_inc(&call->skb_count);
+ terminal = ((flags & RXRPC_LAST_PACKET) &&
+ !(flags & RXRPC_CLIENT_INITIATED));
ret = rxrpc_queue_rcv_skb(call, skb, false, terminal);
if (ret < 0) {
if (ret == -ENOMEM || ret == -ENOBUFS) {
}
skb = NULL;
+ sp = NULL;
_debug("post #%u", seq);
ASSERTCMP(call->rx_data_post, ==, seq);
call->rx_data_post++;
- if (sp->hdr.flags & RXRPC_LAST_PACKET)
+ if (flags & RXRPC_LAST_PACKET)
set_bit(RXRPC_CALL_RCVD_LAST, &call->flags);
/* if we've reached an out of sequence packet then we need to drain
spin_unlock(&call->lock);
atomic_inc(&call->ackr_not_idle);
- rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, sp->hdr.serial, false);
+ rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, false);
_leave(" = 0 [posted]");
return 0;
discard_and_ack:
_debug("discard and ACK packet %p", skb);
- __rxrpc_propose_ACK(call, ack, sp->hdr.serial, true);
+ __rxrpc_propose_ACK(call, ack, serial, true);
discard:
spin_unlock(&call->lock);
rxrpc_free_skb(skb);
return 0;
enqueue_and_ack:
- __rxrpc_propose_ACK(call, ack, sp->hdr.serial, true);
+ __rxrpc_propose_ACK(call, ack, serial, true);
enqueue_packet:
_net("defer skb %p", skb);
spin_unlock(&call->lock);
* post connection-level events to the connection
* - this includes challenges, responses and some aborts
*/
-static bool rxrpc_post_packet_to_conn(struct rxrpc_connection *conn,
+static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn,
struct sk_buff *skb)
{
_enter("%p,%p", conn, skb);
skb_queue_tail(&conn->rx_queue, skb);
- return rxrpc_queue_conn(conn);
+ rxrpc_queue_conn(conn);
}
/*
rcu_read_lock();
-retry_find_conn:
conn = rxrpc_find_connection_rcu(local, skb);
if (!conn)
goto cant_route_call;
if (sp->hdr.callNumber == 0) {
/* Connection-level packet */
_debug("CONN %p {%d}", conn, conn->debug_id);
- if (!rxrpc_post_packet_to_conn(conn, skb))
- goto retry_find_conn;
+ rxrpc_post_packet_to_conn(conn, skb);
} else {
/* Call-bound packets are routed by connection channel. */
unsigned int channel = sp->hdr.cid & RXRPC_CHANNELMASK;
if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) {
_debug("reject type %d",sp->hdr.type);
rxrpc_reject_packet(local, skb);
+ } else {
+ rxrpc_free_skb(skb);
}
_leave(" [no call]");
return;
}
/* we transferred the whole data packet */
+ if (!(flags & MSG_PEEK))
+ rxrpc_kernel_data_consumed(call, skb);
+
if (sp->hdr.flags & RXRPC_LAST_PACKET) {
_debug("last");
if (rxrpc_conn_is_client(call->conn)) {
}
-/**
- * rxrpc_kernel_data_delivered - Record delivery of data message
- * @skb: Message holding data
- *
- * Record the delivery of a data message. This permits RxRPC to keep its
- * tracking correct. The socket buffer will be deleted.
- */
-void rxrpc_kernel_data_delivered(struct sk_buff *skb)
-{
- struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- struct rxrpc_call *call = sp->call;
-
- ASSERTCMP(sp->hdr.seq, >=, call->rx_data_recv);
- ASSERTCMP(sp->hdr.seq, <=, call->rx_data_recv + 1);
- call->rx_data_recv = sp->hdr.seq;
-
- ASSERTCMP(sp->hdr.seq, >, call->rx_data_eaten);
- rxrpc_free_skb(skb);
-}
-
-EXPORT_SYMBOL(rxrpc_kernel_data_delivered);
-
/**
* rxrpc_kernel_is_data_last - Determine if data message is last one
* @skb: Message holding data
spin_unlock_bh(&call->lock);
}
+/**
+ * rxrpc_kernel_data_consumed - Record consumption of data message
+ * @call: The call to which the message pertains.
+ * @skb: Message holding data
+ *
+ * Record the consumption of a data message and generate an ACK if appropriate.
+ * The call state is shifted if this was the final packet. The caller must be
+ * in process context with no spinlocks held.
+ *
+ * TODO: Actually generate the ACK here rather than punting this to the
+ * workqueue.
+ */
+void rxrpc_kernel_data_consumed(struct rxrpc_call *call, struct sk_buff *skb)
+{
+ struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+
+ _enter("%d,%p{%u}", call->debug_id, skb, sp->hdr.seq);
+
+ ASSERTCMP(sp->call, ==, call);
+ ASSERTCMP(sp->hdr.type, ==, RXRPC_PACKET_TYPE_DATA);
+
+ /* TODO: Fix the sequence number tracking */
+ ASSERTCMP(sp->hdr.seq, >=, call->rx_data_recv);
+ ASSERTCMP(sp->hdr.seq, <=, call->rx_data_recv + 1);
+ ASSERTCMP(sp->hdr.seq, >, call->rx_data_eaten);
+
+ call->rx_data_recv = sp->hdr.seq;
+ rxrpc_hard_ACK_data(call, sp);
+}
+EXPORT_SYMBOL(rxrpc_kernel_data_consumed);
+
/*
- * destroy a packet that has an RxRPC control buffer
- * - advance the hard-ACK state of the parent call (done here in case something
- * in the kernel bypasses recvmsg() and steals the packet directly off of the
- * socket receive queue)
+ * Destroy a packet that has an RxRPC control buffer
*/
void rxrpc_packet_destructor(struct sk_buff *skb)
{
_enter("%p{%p}", skb, call);
if (call) {
- /* send the final ACK on a client call */
- if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA)
- rxrpc_hard_ACK_data(call, sp);
+ if (atomic_dec_return(&call->skb_count) < 0)
+ BUG();
rxrpc_put_call(call);
sp->call = NULL;
}
if (p->tcfa_bindcnt <= 0 && p->tcfa_refcnt <= 0) {
if (p->ops->cleanup)
p->ops->cleanup(p, bind);
- list_del(&p->list);
tcf_hash_destroy(p->hinfo, p);
ret = ACT_P_DELETED;
}
return res;
}
-int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions,
- struct tcf_result *res)
+int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
+ int nr_actions, struct tcf_result *res)
{
- const struct tc_action *a;
- int ret = -1;
+ int ret = -1, i;
if (skb->tc_verd & TC_NCLS) {
skb->tc_verd = CLR_TC_NCLS(skb->tc_verd);
ret = TC_ACT_OK;
goto exec_done;
}
- list_for_each_entry(a, actions, list) {
+ for (i = 0; i < nr_actions; i++) {
+ const struct tc_action *a = actions[i];
+
repeat:
ret = a->ops->act(skb, a, res);
if (ret == TC_ACT_REPEAT)
return ERR_PTR(err);
}
-static void cleanup_a(struct list_head *actions)
-{
- struct tc_action *a, *tmp;
-
- list_for_each_entry_safe(a, tmp, actions, list) {
- list_del(&a->list);
- kfree(a);
- }
-}
-
static int tca_action_flush(struct net *net, struct nlattr *nla,
struct nlmsghdr *n, u32 portid)
{
return ret;
}
err:
- cleanup_a(&actions);
+ tcf_action_destroy(&actions, 0);
return ret;
}
ret = tcf_action_init(net, nla, NULL, NULL, ovr, 0, &actions);
if (ret)
- goto done;
+ return ret;
- /* dump then free all the actions after update; inserted policy
- * stays intact
- */
- ret = tcf_add_notify(net, n, &actions, portid);
- cleanup_a(&actions);
-done:
- return ret;
+ return tcf_add_notify(net, n, &actions, portid);
}
static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n)
u32 *tlv = (u32 *)(skbdata);
u16 totlen = nla_total_size(dlen); /*alignment + hdr */
char *dptr = (char *)tlv + NLA_HDRLEN;
- u32 htlv = attrtype << 16 | totlen;
+ u32 htlv = attrtype << 16 | dlen;
*tlv = htonl(htlv);
memset(dptr, 0, totlen - NLA_HDRLEN);
int ife_validate_meta_u32(void *val, int len)
{
- if (len == 4)
+ if (len == sizeof(u32))
return 0;
return -EINVAL;
int ife_validate_meta_u16(void *val, int len)
{
- /* length will include padding */
- if (len == NLA_ALIGN(2))
+ /* length will not include padding */
+ if (len == sizeof(u16))
return 0;
return -EINVAL;
u8 *tlvdata = (u8 *)tlv;
u16 mtype = tlv->type;
u16 mlen = tlv->len;
+ u16 alen;
mtype = ntohs(mtype);
mlen = ntohs(mlen);
+ alen = NLA_ALIGN(mlen);
- if (find_decode_metaid(skb, ife, mtype, (mlen - 4),
- (void *)(tlvdata + 4))) {
+ if (find_decode_metaid(skb, ife, mtype, (mlen - NLA_HDRLEN),
+ (void *)(tlvdata + NLA_HDRLEN))) {
/* abuse overlimits to count when we receive metadata
* but dont have an ops for it
*/
ife->tcf_qstats.overlimits++;
}
- tlvdata += mlen;
- ifehdrln -= mlen;
+ tlvdata += alen;
+ ifehdrln -= alen;
tlv = (struct meta_tlvhdr *)tlvdata;
}
const struct tc_action_ops *ops)
{
struct tc_action_net *tn = net_generic(net, police_net_id);
- struct tcf_hashinfo *hinfo = tn->hinfo;
- int err = 0, index = -1, i = 0, s_i = 0, n_i = 0;
- struct nlattr *nest;
-
- spin_lock_bh(&hinfo->lock);
-
- s_i = cb->args[0];
-
- for (i = 0; i < (POL_TAB_MASK + 1); i++) {
- struct hlist_head *head;
- struct tc_action *p;
-
- head = &hinfo->htab[tcf_hash(i, POL_TAB_MASK)];
-
- hlist_for_each_entry_rcu(p, head, tcfa_head) {
- index++;
- if (index < s_i)
- continue;
- nest = nla_nest_start(skb, index);
- if (nest == NULL)
- goto nla_put_failure;
- if (type == RTM_DELACTION)
- err = tcf_action_dump_1(skb, p, 0, 1);
- else
- err = tcf_action_dump_1(skb, p, 0, 0);
- if (err < 0) {
- index--;
- nla_nest_cancel(skb, nest);
- goto done;
- }
- nla_nest_end(skb, nest);
- n_i++;
- }
- }
-done:
- spin_unlock_bh(&hinfo->lock);
- if (n_i)
- cb->args[0] += n_i;
- return n_i;
-nla_put_failure:
- nla_nest_cancel(skb, nest);
- goto done;
+ return tcf_generic_walker(tn, skb, cb, type, ops);
}
static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = {
struct tcf_police *police;
struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL;
struct tc_action_net *tn = net_generic(net, police_net_id);
+ bool exists = false;
int size;
if (nla == NULL)
size = nla_len(tb[TCA_POLICE_TBF]);
if (size != sizeof(*parm) && size != sizeof(struct tc_police_compat))
return -EINVAL;
+
parm = nla_data(tb[TCA_POLICE_TBF]);
+ exists = tcf_hash_check(tn, parm->index, a, bind);
+ if (exists && bind)
+ return 0;
- if (parm->index) {
- if (tcf_hash_check(tn, parm->index, a, bind)) {
- if (ovr)
- goto override;
- /* not replacing */
- return -EEXIST;
- }
- } else {
+ if (!exists) {
ret = tcf_hash_create(tn, parm->index, NULL, a,
&act_police_ops, bind, false);
if (ret)
return ret;
ret = ACT_P_CREATED;
+ } else {
+ tcf_hash_release(*a, bind);
+ if (!ovr)
+ return -EEXIST;
}
-override:
police = to_police(*a);
if (parm->rate.rate) {
err = -ENOMEM;
void tcf_exts_destroy(struct tcf_exts *exts)
{
#ifdef CONFIG_NET_CLS_ACT
- tcf_action_destroy(&exts->actions, TCA_ACT_UNBIND);
- INIT_LIST_HEAD(&exts->actions);
+ LIST_HEAD(actions);
+
+ tcf_exts_to_list(exts, &actions);
+ tcf_action_destroy(&actions, TCA_ACT_UNBIND);
+ kfree(exts->actions);
+ exts->nr_actions = 0;
#endif
}
EXPORT_SYMBOL(tcf_exts_destroy);
{
struct tc_action *act;
- INIT_LIST_HEAD(&exts->actions);
if (exts->police && tb[exts->police]) {
act = tcf_action_init_1(net, tb[exts->police], rate_tlv,
"police", ovr,
return PTR_ERR(act);
act->type = exts->type = TCA_OLD_COMPAT;
- list_add(&act->list, &exts->actions);
+ exts->actions[0] = act;
+ exts->nr_actions = 1;
} else if (exts->action && tb[exts->action]) {
- int err;
+ LIST_HEAD(actions);
+ int err, i = 0;
+
err = tcf_action_init(net, tb[exts->action], rate_tlv,
NULL, ovr,
- TCA_ACT_BIND, &exts->actions);
+ TCA_ACT_BIND, &actions);
if (err)
return err;
+ list_for_each_entry(act, &actions, list)
+ exts->actions[i++] = act;
+ exts->nr_actions = i;
}
}
#else
struct tcf_exts *src)
{
#ifdef CONFIG_NET_CLS_ACT
- LIST_HEAD(tmp);
+ struct tcf_exts old = *dst;
+
tcf_tree_lock(tp);
- list_splice_init(&dst->actions, &tmp);
- list_splice(&src->actions, &dst->actions);
+ dst->nr_actions = src->nr_actions;
+ dst->actions = src->actions;
dst->type = src->type;
tcf_tree_unlock(tp);
- tcf_action_destroy(&tmp, TCA_ACT_UNBIND);
+
+ tcf_exts_destroy(&old);
#endif
}
EXPORT_SYMBOL(tcf_exts_change);
-#define tcf_exts_first_act(ext) \
- list_first_entry_or_null(&(exts)->actions, \
- struct tc_action, list)
+#ifdef CONFIG_NET_CLS_ACT
+static struct tc_action *tcf_exts_first_act(struct tcf_exts *exts)
+{
+ if (exts->nr_actions == 0)
+ return NULL;
+ else
+ return exts->actions[0];
+}
+#endif
int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts)
{
#ifdef CONFIG_NET_CLS_ACT
struct nlattr *nest;
- if (exts->action && !list_empty(&exts->actions)) {
+ if (exts->action && exts->nr_actions) {
/*
* again for backward compatible mode - we want
* to work with both old and new modes of entering
* tc data even if iproute2 was newer - jhs
*/
if (exts->type != TCA_OLD_COMPAT) {
+ LIST_HEAD(actions);
+
nest = nla_nest_start(skb, exts->action);
if (nest == NULL)
goto nla_put_failure;
- if (tcf_action_dump(skb, &exts->actions, 0, 0) < 0)
+
+ tcf_exts_to_list(exts, &actions);
+ if (tcf_action_dump(skb, &actions, 0, 0) < 0)
goto nla_put_failure;
nla_nest_end(skb, nest);
} else if (exts->police) {
struct Qdisc *sch;
if (!try_module_get(ops->owner))
- goto errout;
+ return NULL;
sch = qdisc_alloc(dev_queue, ops);
- if (IS_ERR(sch))
- goto errout;
+ if (IS_ERR(sch)) {
+ module_put(ops->owner);
+ return NULL;
+ }
sch->parent = parentid;
if (!ops->init || ops->init(sch, NULL) == 0)
return sch;
qdisc_destroy(sch);
-errout:
return NULL;
}
EXPORT_SYMBOL(qdisc_create_dflt);
skb_transport_offset(skb))
goto discard_it;
- if (!pskb_may_pull(skb, sizeof(struct sctphdr)))
+ /* If the packet is fragmented and we need to do crc checking,
+ * it's better to just linearize it otherwise crc computing
+ * takes longer.
+ */
+ if ((!(skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) &&
+ skb_linearize(skb)) ||
+ !pskb_may_pull(skb, sizeof(struct sctphdr)))
goto discard_it;
/* Pull up the IP header. */
static inline int sctp_hash_cmp(struct rhashtable_compare_arg *arg,
const void *ptr)
{
+ struct sctp_transport *t = (struct sctp_transport *)ptr;
const struct sctp_hash_cmp_arg *x = arg->key;
- const struct sctp_transport *t = ptr;
- struct sctp_association *asoc = t->asoc;
- const struct net *net = x->net;
+ struct sctp_association *asoc;
+ int err = 1;
if (!sctp_cmp_addr_exact(&t->ipaddr, x->paddr))
- return 1;
- if (!net_eq(sock_net(asoc->base.sk), net))
- return 1;
+ return err;
+ if (!sctp_transport_hold(t))
+ return err;
+
+ asoc = t->asoc;
+ if (!net_eq(sock_net(asoc->base.sk), x->net))
+ goto out;
if (x->ep) {
if (x->ep != asoc->ep)
- return 1;
+ goto out;
} else {
if (x->laddr->v4.sin_port != htons(asoc->base.bind_addr.port))
- return 1;
+ goto out;
if (!sctp_bind_addr_match(&asoc->base.bind_addr,
x->laddr, sctp_sk(asoc->base.sk)))
- return 1;
+ goto out;
}
- return 0;
+ err = 0;
+out:
+ sctp_transport_put(t);
+ return err;
}
static inline u32 sctp_hash_obj(const void *data, u32 len, u32 seed)
if ((skb_shinfo(skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP)
return NULL;
- if (skb_linearize(skb))
- return NULL;
-
ch = (sctp_chunkhdr_t *) skb->data;
/* The code below will attempt to walk the chunk and extract
chunk = list_entry(entry, struct sctp_chunk, list);
- /* Linearize if it's not GSO */
- if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) != SKB_GSO_SCTP &&
- skb_is_nonlinear(chunk->skb)) {
- if (skb_linearize(chunk->skb)) {
- __SCTP_INC_STATS(dev_net(chunk->skb->dev), SCTP_MIB_IN_PKT_DISCARDS);
- sctp_chunk_free(chunk);
- goto next_chunk;
- }
-
- /* Update sctp_hdr as it probably changed */
- chunk->sctp_hdr = sctp_hdr(chunk->skb);
- }
-
if ((skb_shinfo(chunk->skb)->gso_type & SKB_GSO_SCTP) == SKB_GSO_SCTP) {
/* GSO-marked skbs but without frags, handle
* them normally
struct sctp_chunk *chunk,
u16 chunk_len)
{
- size_t psize, pmtu;
+ size_t psize, pmtu, maxsize;
sctp_xmit_t retval = SCTP_XMIT_OK;
psize = packet->size;
goto out;
}
+ /* Similarly, if this chunk was built before a PMTU
+ * reduction, we have to fragment it at IP level now. So
+ * if the packet already contains something, we need to
+ * flush.
+ */
+ maxsize = pmtu - packet->overhead;
+ if (packet->auth)
+ maxsize -= WORD_ROUND(packet->auth->skb->len);
+ if (chunk_len > maxsize)
+ retval = SCTP_XMIT_PMTU_FULL;
+
/* It is also okay to fragment if the chunk we are
* adding is a control chunk, but only if current packet
* is not a GSO one otherwise it causes fragmentation of
return ERR_PTR(err);
}
+ iter->start_fail = 0;
return sctp_transport_get_idx(seq_file_net(seq), &iter->hti, *pos);
}
{
union sctp_addr laddr, paddr;
struct dst_entry *dst;
+ struct timer_list *t3_rtx = &asoc->peer.primary_path->T3_rtx_timer;
laddr = list_entry(asoc->base.bind_addr.address_list.next,
struct sctp_sockaddr_entry, list)->a;
}
r->idiag_state = asoc->state;
- r->idiag_timer = SCTP_EVENT_TIMEOUT_T3_RTX;
- r->idiag_retrans = asoc->rtx_data_chunks;
- r->idiag_expires = jiffies_to_msecs(
- asoc->timeouts[SCTP_EVENT_TIMEOUT_T3_RTX] - jiffies);
+ if (timer_pending(t3_rtx)) {
+ r->idiag_timer = SCTP_EVENT_TIMEOUT_T3_RTX;
+ r->idiag_retrans = asoc->rtx_data_chunks;
+ r->idiag_expires = jiffies_to_msecs(t3_rtx->expires - jiffies);
+ } else {
+ r->idiag_timer = 0;
+ r->idiag_retrans = 0;
+ r->idiag_expires = 0;
+ }
}
static int inet_diag_msg_sctpladdrs_fill(struct sk_buff *skb,
if (cb->args[4] < cb->args[1])
goto next;
- if ((r->idiag_states & ~TCPF_LISTEN) && !list_empty(&ep->asocs))
+ if (!(r->idiag_states & TCPF_LISTEN) && !list_empty(&ep->asocs))
goto next;
if (r->sdiag_family != AF_UNSPEC &&
paddr.v4.sin_family = AF_INET;
} else {
laddr.v6.sin6_port = req->id.idiag_sport;
- memcpy(&laddr.v6.sin6_addr, req->id.idiag_src, 64);
+ memcpy(&laddr.v6.sin6_addr, req->id.idiag_src,
+ sizeof(laddr.v6.sin6_addr));
laddr.v6.sin6_family = AF_INET6;
paddr.v6.sin6_port = req->id.idiag_dport;
- memcpy(&paddr.v6.sin6_addr, req->id.idiag_dst, 64);
+ memcpy(&paddr.v6.sin6_addr, req->id.idiag_dst,
+ sizeof(paddr.v6.sin6_addr));
paddr.v6.sin6_family = AF_INET6;
}
* 3 : to mark if we have dumped the ep info of the current asoc
* 4 : to work as a temporary variable to traversal list
*/
- if (!(idiag_states & ~TCPF_LISTEN))
+ if (!(idiag_states & ~(TCPF_LISTEN | TCPF_CLOSE)))
goto done;
sctp_for_each_transport(sctp_tsp_dump, net, cb->args[2], &commp);
done:
*/
sctp_ulpevent_init(event, 0, skb->len + sizeof(struct sk_buff));
- sctp_ulpevent_receive_data(event, asoc);
-
/* And hold the chunk as we need it for getting the IP headers
* later in recvmsg
*/
sctp_chunk_hold(chunk);
event->chunk = chunk;
+ sctp_ulpevent_receive_data(event, asoc);
+
event->stream = ntohs(chunk->subh.data_hdr->stream);
event->ssn = ntohs(chunk->subh.data_hdr->ssn);
event->ppid = chunk->subh.data_hdr->ppid;
}
static struct gss_upcall_msg *
-__gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid)
+__gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid, const struct gss_auth *auth)
{
struct gss_upcall_msg *pos;
list_for_each_entry(pos, &pipe->in_downcall, list) {
if (!uid_eq(pos->uid, uid))
continue;
+ if (auth && pos->auth->service != auth->service)
+ continue;
atomic_inc(&pos->count);
dprintk("RPC: %s found msg %p\n", __func__, pos);
return pos;
struct gss_upcall_msg *old;
spin_lock(&pipe->lock);
- old = __gss_find_upcall(pipe, gss_msg->uid);
+ old = __gss_find_upcall(pipe, gss_msg->uid, gss_msg->auth);
if (old == NULL) {
atomic_inc(&gss_msg->count);
list_add(&gss_msg->list, &pipe->in_downcall);
err = -ENOENT;
/* Find a matching upcall */
spin_lock(&pipe->lock);
- gss_msg = __gss_find_upcall(pipe, uid);
+ gss_msg = __gss_find_upcall(pipe, uid, NULL);
if (gss_msg == NULL) {
spin_unlock(&pipe->lock);
goto err_put_ctx;
struct rsc *found;
memset(&rsci, 0, sizeof(rsci));
- rsci.handle.data = handle->data;
- rsci.handle.len = handle->len;
+ if (dup_to_netobj(&rsci.handle, handle->data, handle->len))
+ return NULL;
found = rsc_lookup(cd, &rsci);
+ rsc_free(&rsci);
if (!found)
return NULL;
if (cache_check(cd, &found->h, NULL))
struct rpc_xprt_switch *xps;
if (args->bc_xprt && args->bc_xprt->xpt_bc_xps) {
- WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP);
+ WARN_ON_ONCE(!(args->protocol & XPRT_TRANSPORT_BC));
xps = args->bc_xprt->xpt_bc_xps;
xprt_switch_get(xps);
} else {
char servername[48];
if (args->bc_xprt) {
- WARN_ON(args->protocol != XPRT_TRANSPORT_BC_TCP);
+ WARN_ON_ONCE(!(args->protocol & XPRT_TRANSPORT_BC));
xprt = args->bc_xprt->xpt_bc_xprt;
if (xprt) {
xprt_get(xprt);
{
struct rpc_xprt_switch *xps;
struct rpc_xprt *xprt;
+ unsigned long reconnect_timeout;
unsigned char resvport;
int ret = 0;
return -EAGAIN;
}
resvport = xprt->resvport;
+ reconnect_timeout = xprt->max_reconnect_timeout;
rcu_read_unlock();
xprt = xprt_create_transport(xprtargs);
goto out_put_switch;
}
xprt->resvport = resvport;
+ xprt->max_reconnect_timeout = reconnect_timeout;
rpc_xprt_switch_set_roundrobin(xps);
if (setup) {
}
EXPORT_SYMBOL_GPL(rpc_clnt_add_xprt);
+static int
+rpc_xprt_cap_max_reconnect_timeout(struct rpc_clnt *clnt,
+ struct rpc_xprt *xprt,
+ void *data)
+{
+ unsigned long timeout = *((unsigned long *)data);
+
+ if (timeout < xprt->max_reconnect_timeout)
+ xprt->max_reconnect_timeout = timeout;
+ return 0;
+}
+
+void
+rpc_cap_max_reconnect_timeout(struct rpc_clnt *clnt, unsigned long timeo)
+{
+ rpc_clnt_iterate_for_each_xprt(clnt,
+ rpc_xprt_cap_max_reconnect_timeout,
+ &timeo);
+}
+EXPORT_SYMBOL_GPL(rpc_cap_max_reconnect_timeout);
+
#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
static void rpc_show_header(void)
{
spin_unlock_bh(&xprt->transport_lock);
}
+static bool
+xprt_has_timer(const struct rpc_xprt *xprt)
+{
+ return xprt->idle_timeout != 0;
+}
+
+static void
+xprt_schedule_autodisconnect(struct rpc_xprt *xprt)
+ __must_hold(&xprt->transport_lock)
+{
+ if (list_empty(&xprt->recv) && xprt_has_timer(xprt))
+ mod_timer(&xprt->timer, xprt->last_used + xprt->idle_timeout);
+}
+
static void
xprt_init_autodisconnect(unsigned long data)
{
spin_lock(&xprt->transport_lock);
if (!list_empty(&xprt->recv))
goto out_abort;
+ /* Reset xprt->last_used to avoid connect/autodisconnect cycling */
+ xprt->last_used = jiffies;
if (test_and_set_bit(XPRT_LOCKED, &xprt->state))
goto out_abort;
spin_unlock(&xprt->transport_lock);
goto out;
xprt->snd_task =NULL;
xprt->ops->release_xprt(xprt, NULL);
+ xprt_schedule_autodisconnect(xprt);
out:
spin_unlock_bh(&xprt->transport_lock);
wake_up_bit(&xprt->state, XPRT_LOCKED);
spin_unlock_bh(&xprt->transport_lock);
}
-static inline int xprt_has_timer(struct rpc_xprt *xprt)
-{
- return xprt->idle_timeout != 0;
-}
-
/**
* xprt_prepare_transmit - reserve the transport before sending a request
* @task: RPC task about to send a request
if (!list_empty(&req->rq_list))
list_del(&req->rq_list);
xprt->last_used = jiffies;
- if (list_empty(&xprt->recv) && xprt_has_timer(xprt))
- mod_timer(&xprt->timer,
- xprt->last_used + xprt->idle_timeout);
+ xprt_schedule_autodisconnect(xprt);
spin_unlock_bh(&xprt->transport_lock);
if (req->rq_buffer)
xprt->ops->buf_free(req->rq_buffer);
#include <linux/slab.h>
#include <linux/prefetch.h>
#include <linux/sunrpc/addr.h>
+#include <linux/sunrpc/svc_rdma.h>
#include <asm/bitops.h>
#include <linux/module.h> /* try_module_get()/module_put() */
}
INIT_LIST_HEAD(&buf->rb_recv_bufs);
- for (i = 0; i < buf->rb_max_requests; i++) {
+ for (i = 0; i < buf->rb_max_requests + RPCRDMA_MAX_BC_REQUESTS; i++) {
struct rpcrdma_rep *rep;
rep = rpcrdma_create_rep(r_xprt);
rep = rpcrdma_buffer_get_rep_locked(buf);
rpcrdma_destroy_rep(ia, rep);
}
+ buf->rb_send_count = 0;
spin_lock(&buf->rb_reqslock);
while (!list_empty(&buf->rb_allreqs)) {
spin_lock(&buf->rb_reqslock);
}
spin_unlock(&buf->rb_reqslock);
+ buf->rb_recv_count = 0;
rpcrdma_destroy_mrs(buf);
}
spin_unlock(&buf->rb_mwlock);
}
+static struct rpcrdma_rep *
+rpcrdma_buffer_get_rep(struct rpcrdma_buffer *buffers)
+{
+ /* If an RPC previously completed without a reply (say, a
+ * credential problem or a soft timeout occurs) then hold off
+ * on supplying more Receive buffers until the number of new
+ * pending RPCs catches up to the number of posted Receives.
+ */
+ if (unlikely(buffers->rb_send_count < buffers->rb_recv_count))
+ return NULL;
+
+ if (unlikely(list_empty(&buffers->rb_recv_bufs)))
+ return NULL;
+ buffers->rb_recv_count++;
+ return rpcrdma_buffer_get_rep_locked(buffers);
+}
+
/*
* Get a set of request/reply buffers.
+ *
+ * Reply buffer (if available) is attached to send buffer upon return.
*/
struct rpcrdma_req *
rpcrdma_buffer_get(struct rpcrdma_buffer *buffers)
spin_lock(&buffers->rb_lock);
if (list_empty(&buffers->rb_send_bufs))
goto out_reqbuf;
+ buffers->rb_send_count++;
req = rpcrdma_buffer_get_req_locked(buffers);
- if (list_empty(&buffers->rb_recv_bufs))
- goto out_repbuf;
- req->rl_reply = rpcrdma_buffer_get_rep_locked(buffers);
+ req->rl_reply = rpcrdma_buffer_get_rep(buffers);
spin_unlock(&buffers->rb_lock);
return req;
out_reqbuf:
spin_unlock(&buffers->rb_lock);
- pr_warn("rpcrdma: out of request buffers (%p)\n", buffers);
- return NULL;
-out_repbuf:
- list_add(&req->rl_free, &buffers->rb_send_bufs);
- spin_unlock(&buffers->rb_lock);
- pr_warn("rpcrdma: out of reply buffers (%p)\n", buffers);
+ pr_warn("RPC: %s: out of request buffers\n", __func__);
return NULL;
}
req->rl_reply = NULL;
spin_lock(&buffers->rb_lock);
+ buffers->rb_send_count--;
list_add_tail(&req->rl_free, &buffers->rb_send_bufs);
- if (rep)
+ if (rep) {
+ buffers->rb_recv_count--;
list_add_tail(&rep->rr_list, &buffers->rb_recv_bufs);
+ }
spin_unlock(&buffers->rb_lock);
}
struct rpcrdma_buffer *buffers = req->rl_buffer;
spin_lock(&buffers->rb_lock);
- if (!list_empty(&buffers->rb_recv_bufs))
- req->rl_reply = rpcrdma_buffer_get_rep_locked(buffers);
+ req->rl_reply = rpcrdma_buffer_get_rep(buffers);
spin_unlock(&buffers->rb_lock);
}
struct rpcrdma_buffer *buffers = &rep->rr_rxprt->rx_buf;
spin_lock(&buffers->rb_lock);
+ buffers->rb_recv_count--;
list_add_tail(&rep->rr_list, &buffers->rb_recv_bufs);
spin_unlock(&buffers->rb_lock);
}
char *rb_pool;
spinlock_t rb_lock; /* protect buf lists */
+ int rb_send_count, rb_recv_count;
struct list_head rb_send_bufs;
struct list_head rb_recv_bufs;
u32 rb_max_requests;
* increase over time if the server is down or not responding.
*/
#define XS_TCP_INIT_REEST_TO (3U * HZ)
-#define XS_TCP_MAX_REEST_TO (5U * 60 * HZ)
/*
* TCP idle timeout; client drops the transport socket if it is idle
skb = skb_recv_datagram(sk, 0, 1, &err);
if (skb != NULL) {
xs_udp_data_read_skb(&transport->xprt, sk, skb);
- skb_free_datagram(sk, skb);
+ skb_free_datagram_locked(sk, skb);
continue;
}
if (!test_and_clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state))
write_unlock_bh(&sk->sk_callback_lock);
}
xs_udp_do_set_buffer_size(xprt);
+
+ xprt->stat.connect_start = jiffies;
}
static void xs_udp_setup_socket(struct work_struct *work)
unsigned int keepcnt = xprt->timeout->to_retries + 1;
unsigned int opt_on = 1;
unsigned int timeo;
+ unsigned int addr_pref = IPV6_PREFER_SRC_PUBLIC;
/* TCP Keepalive options */
kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT,
(char *)&keepcnt, sizeof(keepcnt));
+ /* Avoid temporary address, they are bad for long-lived
+ * connections such as NFS mounts.
+ * RFC4941, section 3.6 suggests that:
+ * Individual applications, which have specific
+ * knowledge about the normal duration of connections,
+ * MAY override this as appropriate.
+ */
+ kernel_setsockopt(sock, SOL_IPV6, IPV6_ADDR_PREFERENCES,
+ (char *)&addr_pref, sizeof(addr_pref));
+
/* TCP user timeout (see RFC5482) */
timeo = jiffies_to_msecs(xprt->timeout->to_initval) *
(xprt->timeout->to_retries + 1);
/* SYN_SENT! */
if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO)
xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
+ break;
+ case -EADDRNOTAVAIL:
+ /* Source port number is unavailable. Try a new one! */
+ transport->srcport = 0;
}
out:
return ret;
xprt_wake_pending_tasks(xprt, status);
}
+static unsigned long xs_reconnect_delay(const struct rpc_xprt *xprt)
+{
+ unsigned long start, now = jiffies;
+
+ start = xprt->stat.connect_start + xprt->reestablish_timeout;
+ if (time_after(start, now))
+ return start - now;
+ return 0;
+}
+
+static void xs_reconnect_backoff(struct rpc_xprt *xprt)
+{
+ xprt->reestablish_timeout <<= 1;
+ if (xprt->reestablish_timeout > xprt->max_reconnect_timeout)
+ xprt->reestablish_timeout = xprt->max_reconnect_timeout;
+ if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO)
+ xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
+}
+
/**
* xs_connect - connect a socket to a remote endpoint
* @xprt: pointer to transport structure
static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task)
{
struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
+ unsigned long delay = 0;
WARN_ON_ONCE(!xprt_lock_connect(xprt, task, transport));
/* Start by resetting any existing state */
xs_reset_transport(transport);
- queue_delayed_work(xprtiod_workqueue,
- &transport->connect_worker,
- xprt->reestablish_timeout);
- xprt->reestablish_timeout <<= 1;
- if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO)
- xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO;
- if (xprt->reestablish_timeout > XS_TCP_MAX_REEST_TO)
- xprt->reestablish_timeout = XS_TCP_MAX_REEST_TO;
- } else {
+ delay = xs_reconnect_delay(xprt);
+ xs_reconnect_backoff(xprt);
+
+ } else
dprintk("RPC: xs_connect scheduled xprt %p\n", xprt);
- queue_delayed_work(xprtiod_workqueue,
- &transport->connect_worker, 0);
- }
+
+ queue_delayed_work(xprtiod_workqueue,
+ &transport->connect_worker,
+ delay);
}
/**
xprt->ops = &xs_tcp_ops;
xprt->timeout = &xs_tcp_default_timeout;
+ xprt->max_reconnect_timeout = xprt->timeout->to_maxval;
+
INIT_WORK(&transport->recv_worker, xs_tcp_data_receive_workfn);
INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_setup_socket);
u32 bearer_id, u32 *prev_node)
{
struct tipc_monitor *mon = tipc_monitor(net, bearer_id);
- struct tipc_peer *peer = mon->self;
+ struct tipc_peer *peer;
if (!mon)
return -EINVAL;
read_lock_bh(&mon->lock);
+ peer = mon->self;
do {
if (*prev_node) {
if (peer->addr == *prev_node)
/**
* named_prepare_buf - allocate & initialize a publication message
+ *
+ * The buffer returned is of size INT_H_SIZE + payload size
*/
static struct sk_buff *named_prepare_buf(struct net *net, u32 type, u32 size,
u32 dest)
struct publication *publ;
struct sk_buff *skb = NULL;
struct distr_item *item = NULL;
- uint msg_dsz = (tipc_node_get_mtu(net, dnode, 0) / ITEM_SIZE) *
- ITEM_SIZE;
- uint msg_rem = msg_dsz;
+ u32 msg_dsz = ((tipc_node_get_mtu(net, dnode, 0) - INT_H_SIZE) /
+ ITEM_SIZE) * ITEM_SIZE;
+ u32 msg_rem = msg_dsz;
list_for_each_entry(publ, pls, local_list) {
/* Prepare next buffer: */
TIPC_CONN_MSG, SHORT_H_SIZE,
0, dnode, onode, dport, oport,
TIPC_CONN_SHUTDOWN);
- tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
+ if (skb)
+ tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
}
tsk->connected = 0;
sock->state = SS_DISCONNECTING;
tuncfg.encap_destroy = NULL;
setup_udp_tunnel_sock(net, ub->ubsock, &tuncfg);
- if (enable_mcast(ub, remote))
+ err = enable_mcast(ub, remote);
+ if (err)
goto err;
return 0;
err:
+ if (ub->ubsock)
+ udp_tunnel_sock_release(ub->ubsock);
kfree(ub);
return err;
}
{
struct unix_sock *u = unix_sk(sk);
- if (mutex_lock_interruptible(&u->readlock))
+ if (mutex_lock_interruptible(&u->iolock))
return -EINTR;
sk->sk_peek_off = val;
- mutex_unlock(&u->readlock);
+ mutex_unlock(&u->iolock);
return 0;
}
spin_lock_init(&u->lock);
atomic_long_set(&u->inflight, 0);
INIT_LIST_HEAD(&u->link);
- mutex_init(&u->readlock); /* single task reading lock */
+ mutex_init(&u->iolock); /* single task reading lock */
+ mutex_init(&u->bindlock); /* single task binding lock */
init_waitqueue_head(&u->peer_wait);
init_waitqueue_func_entry(&u->peer_wake, unix_dgram_peer_wake_relay);
unix_insert_socket(unix_sockets_unbound(sk), sk);
int err;
unsigned int retries = 0;
- err = mutex_lock_interruptible(&u->readlock);
+ err = mutex_lock_interruptible(&u->bindlock);
if (err)
return err;
spin_unlock(&unix_table_lock);
err = 0;
-out: mutex_unlock(&u->readlock);
+out: mutex_unlock(&u->bindlock);
return err;
}
return NULL;
}
-static int unix_mknod(struct dentry *dentry, const struct path *path, umode_t mode,
- struct path *res)
+static int unix_mknod(const char *sun_path, umode_t mode, struct path *res)
{
- int err;
+ struct dentry *dentry;
+ struct path path;
+ int err = 0;
+ /*
+ * Get the parent directory, calculate the hash for last
+ * component.
+ */
+ dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
+ err = PTR_ERR(dentry);
+ if (IS_ERR(dentry))
+ return err;
- err = security_path_mknod(path, dentry, mode, 0);
+ /*
+ * All right, let's create it.
+ */
+ err = security_path_mknod(&path, dentry, mode, 0);
if (!err) {
- err = vfs_mknod(d_inode(path->dentry), dentry, mode, 0);
+ err = vfs_mknod(d_inode(path.dentry), dentry, mode, 0);
if (!err) {
- res->mnt = mntget(path->mnt);
+ res->mnt = mntget(path.mnt);
res->dentry = dget(dentry);
}
}
-
+ done_path_create(&path, dentry);
return err;
}
struct unix_sock *u = unix_sk(sk);
struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr;
char *sun_path = sunaddr->sun_path;
- int err, name_err;
+ int err;
unsigned int hash;
struct unix_address *addr;
struct hlist_head *list;
- struct path path;
- struct dentry *dentry;
err = -EINVAL;
if (sunaddr->sun_family != AF_UNIX)
goto out;
addr_len = err;
- name_err = 0;
- dentry = NULL;
- if (sun_path[0]) {
- /* Get the parent directory, calculate the hash for last
- * component.
- */
- dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
-
- if (IS_ERR(dentry)) {
- /* delay report until after 'already bound' check */
- name_err = PTR_ERR(dentry);
- dentry = NULL;
- }
- }
-
- err = mutex_lock_interruptible(&u->readlock);
+ err = mutex_lock_interruptible(&u->bindlock);
if (err)
- goto out_path;
+ goto out;
err = -EINVAL;
if (u->addr)
goto out_up;
- if (name_err) {
- err = name_err == -EEXIST ? -EADDRINUSE : name_err;
- goto out_up;
- }
-
err = -ENOMEM;
addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL);
if (!addr)
addr->hash = hash ^ sk->sk_type;
atomic_set(&addr->refcnt, 1);
- if (dentry) {
- struct path u_path;
+ if (sun_path[0]) {
+ struct path path;
umode_t mode = S_IFSOCK |
(SOCK_INODE(sock)->i_mode & ~current_umask());
- err = unix_mknod(dentry, &path, mode, &u_path);
+ err = unix_mknod(sun_path, mode, &path);
if (err) {
if (err == -EEXIST)
err = -EADDRINUSE;
goto out_up;
}
addr->hash = UNIX_HASH_SIZE;
- hash = d_real_inode(dentry)->i_ino & (UNIX_HASH_SIZE - 1);
+ hash = d_real_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1);
spin_lock(&unix_table_lock);
- u->path = u_path;
+ u->path = path;
list = &unix_socket_table[hash];
} else {
spin_lock(&unix_table_lock);
out_unlock:
spin_unlock(&unix_table_lock);
out_up:
- mutex_unlock(&u->readlock);
-out_path:
- if (dentry)
- done_path_create(&path, dentry);
-
+ mutex_unlock(&u->bindlock);
out:
return err;
}
if (false) {
alloc_skb:
unix_state_unlock(other);
- mutex_unlock(&unix_sk(other)->readlock);
+ mutex_unlock(&unix_sk(other)->iolock);
newskb = sock_alloc_send_pskb(sk, 0, 0, flags & MSG_DONTWAIT,
&err, 0);
if (!newskb)
goto err;
}
- /* we must acquire readlock as we modify already present
+ /* we must acquire iolock as we modify already present
* skbs in the sk_receive_queue and mess with skb->len
*/
- err = mutex_lock_interruptible(&unix_sk(other)->readlock);
+ err = mutex_lock_interruptible(&unix_sk(other)->iolock);
if (err) {
err = flags & MSG_DONTWAIT ? -EAGAIN : -ERESTARTSYS;
goto err;
}
unix_state_unlock(other);
- mutex_unlock(&unix_sk(other)->readlock);
+ mutex_unlock(&unix_sk(other)->iolock);
other->sk_data_ready(other);
scm_destroy(&scm);
err_state_unlock:
unix_state_unlock(other);
err_unlock:
- mutex_unlock(&unix_sk(other)->readlock);
+ mutex_unlock(&unix_sk(other)->iolock);
err:
kfree_skb(newskb);
if (send_sigpipe && !(flags & MSG_NOSIGNAL))
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
do {
- mutex_lock(&u->readlock);
+ mutex_lock(&u->iolock);
skip = sk_peek_offset(sk, flags);
skb = __skb_try_recv_datagram(sk, flags, &peeked, &skip, &err,
if (skb)
break;
- mutex_unlock(&u->readlock);
+ mutex_unlock(&u->iolock);
if (err != -EAGAIN)
break;
} while (timeo &&
!__skb_wait_for_more_packets(sk, &err, &timeo, last));
- if (!skb) { /* implies readlock unlocked */
+ if (!skb) { /* implies iolock unlocked */
unix_state_lock(sk);
/* Signal EOF on disconnected non-blocking SEQPACKET socket. */
if (sk->sk_type == SOCK_SEQPACKET && err == -EAGAIN &&
out_free:
skb_free_datagram(sk, skb);
- mutex_unlock(&u->readlock);
+ mutex_unlock(&u->iolock);
out:
return err;
}
/* Lock the socket to prevent queue disordering
* while sleeps in memcpy_tomsg
*/
- mutex_lock(&u->readlock);
+ mutex_lock(&u->iolock);
if (flags & MSG_PEEK)
skip = sk_peek_offset(sk, flags);
break;
}
- mutex_unlock(&u->readlock);
+ mutex_unlock(&u->iolock);
timeo = unix_stream_data_wait(sk, timeo, last,
last_len);
goto out;
}
- mutex_lock(&u->readlock);
+ mutex_lock(&u->iolock);
goto redo;
unlock:
unix_state_unlock(sk);
}
} while (size);
- mutex_unlock(&u->readlock);
+ mutex_unlock(&u->iolock);
if (state->msg)
scm_recv(sock, state->msg, &scm, flags);
else
int ret;
struct unix_sock *u = unix_sk(sk);
- mutex_unlock(&u->readlock);
+ mutex_unlock(&u->iolock);
ret = splice_to_pipe(pipe, spd);
- mutex_lock(&u->readlock);
+ mutex_lock(&u->iolock);
return ret;
}
vq = vsock->vqs[VSOCK_VQ_TX];
- /* Avoid unnecessary interrupts while we're processing the ring */
- virtqueue_disable_cb(vq);
-
for (;;) {
struct virtio_vsock_pkt *pkt;
struct scatterlist hdr, buf, *sgs[2];
spin_lock_bh(&vsock->send_pkt_list_lock);
if (list_empty(&vsock->send_pkt_list)) {
spin_unlock_bh(&vsock->send_pkt_list_lock);
- virtqueue_enable_cb(vq);
break;
}
}
ret = virtqueue_add_sgs(vq, sgs, out_sg, in_sg, pkt, GFP_KERNEL);
+ /* Usually this means that there is no more space available in
+ * the vq
+ */
if (ret < 0) {
spin_lock_bh(&vsock->send_pkt_list_lock);
list_add(&pkt->list, &vsock->send_pkt_list);
spin_unlock_bh(&vsock->send_pkt_list_lock);
-
- if (!virtqueue_enable_cb(vq) && ret == -ENOSPC)
- continue; /* retry now that we have more space */
break;
}
r = cfg80211_get_chans_dfs_available(wiphy,
chandef->center_freq2,
width);
+ break;
default:
WARN_ON(chandef->center_freq2);
break;
{
struct nlattr *tb[NL80211_MESHCONF_ATTR_MAX + 1];
u32 mask = 0;
+ u16 ht_opmode;
#define FILL_IN_MESH_PARAM_IF_SET(tb, cfg, param, min, max, mask, attr, fn) \
do { \
FILL_IN_MESH_PARAM_IF_SET(tb, cfg, rssi_threshold, -255, 0,
mask, NL80211_MESHCONF_RSSI_THRESHOLD,
nl80211_check_s32);
- FILL_IN_MESH_PARAM_IF_SET(tb, cfg, ht_opmode, 0, 16,
- mask, NL80211_MESHCONF_HT_OPMODE,
- nl80211_check_u16);
+ /*
+ * Check HT operation mode based on
+ * IEEE 802.11 2012 8.4.2.59 HT Operation element.
+ */
+ if (tb[NL80211_MESHCONF_HT_OPMODE]) {
+ ht_opmode = nla_get_u16(tb[NL80211_MESHCONF_HT_OPMODE]);
+
+ if (ht_opmode & ~(IEEE80211_HT_OP_MODE_PROTECTION |
+ IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT |
+ IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
+ return -EINVAL;
+
+ if ((ht_opmode & IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT) &&
+ (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
+ return -EINVAL;
+
+ switch (ht_opmode & IEEE80211_HT_OP_MODE_PROTECTION) {
+ case IEEE80211_HT_OP_MODE_PROTECTION_NONE:
+ case IEEE80211_HT_OP_MODE_PROTECTION_20MHZ:
+ if (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)
+ return -EINVAL;
+ break;
+ case IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER:
+ case IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED:
+ if (!(ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
+ return -EINVAL;
+ break;
+ }
+ cfg->ht_opmode = ht_opmode;
+ }
FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPactivePathToRootTimeout,
1, 65535, mask,
NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT,
params.n_counter_offsets_presp = len / sizeof(u16);
if (rdev->wiphy.max_num_csa_counters &&
- (params.n_counter_offsets_beacon >
+ (params.n_counter_offsets_presp >
rdev->wiphy.max_num_csa_counters))
return -EINVAL;
return private(dev, iwr, cmd, info, handler);
}
/* Old driver API : call driver ioctl handler */
- if (dev->netdev_ops->ndo_do_ioctl) {
-#ifdef CONFIG_COMPAT
- if (info->flags & IW_REQUEST_FLAG_COMPAT) {
- int ret = 0;
- struct iwreq iwr_lcl;
- struct compat_iw_point *iwp_compat = (void *) &iwr->u.data;
-
- memcpy(&iwr_lcl, iwr, sizeof(struct iwreq));
- iwr_lcl.u.data.pointer = compat_ptr(iwp_compat->pointer);
- iwr_lcl.u.data.length = iwp_compat->length;
- iwr_lcl.u.data.flags = iwp_compat->flags;
-
- ret = dev->netdev_ops->ndo_do_ioctl(dev, (void *) &iwr_lcl, cmd);
-
- iwp_compat->pointer = ptr_to_compat(iwr_lcl.u.data.pointer);
- iwp_compat->length = iwr_lcl.u.data.length;
- iwp_compat->flags = iwr_lcl.u.data.flags;
-
- return ret;
- } else
-#endif
- return dev->netdev_ops->ndo_do_ioctl(dev, ifr, cmd);
- }
+ if (dev->netdev_ops->ndo_do_ioctl)
+ return dev->netdev_ops->ndo_do_ioctl(dev, ifr, cmd);
return -EOPNOTSUPP;
}
family = XFRM_SPI_SKB_CB(skb)->family;
/* if tunnel is present override skb->mark value with tunnel i_key */
- if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4) {
- switch (family) {
- case AF_INET:
+ switch (family) {
+ case AF_INET:
+ if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4)
mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4->parms.i_key);
- break;
- case AF_INET6:
+ break;
+ case AF_INET6:
+ if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6)
mark = be32_to_cpu(XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6->parms.i_key);
- break;
- }
+ break;
}
/* Allocate new secpath or COW existing one. */
/* re-insert all policies by order of creation */
list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) {
+ if (xfrm_policy_id2dir(policy->index) >= XFRM_POLICY_MAX) {
+ /* skip socket policies */
+ continue;
+ }
newpos = NULL;
chain = policy_hash_bysel(net, &policy->selector,
policy->family,
{
tasklet_hrtimer_cancel(&x->mtimer);
del_timer_sync(&x->rtimer);
+ kfree(x->aead);
kfree(x->aalg);
kfree(x->ealg);
kfree(x->calg);
if (err)
goto error;
- if (attrs[XFRMA_SEC_CTX] &&
- security_xfrm_state_alloc(x, nla_data(attrs[XFRMA_SEC_CTX])))
- goto error;
+ if (attrs[XFRMA_SEC_CTX]) {
+ err = security_xfrm_state_alloc(x,
+ nla_data(attrs[XFRMA_SEC_CTX]));
+ if (err)
+ goto error;
+ }
if ((err = xfrm_alloc_replay_state_esn(&x->replay_esn, &x->preplay_esn,
attrs[XFRMA_REPLAY_ESN_VAL])))
struct sock *sk = cb->skb->sk;
struct net *net = sock_net(sk);
- xfrm_state_walk_done(walk, net);
+ if (cb->args[0])
+ xfrm_state_walk_done(walk, net);
return 0;
}
u8 proto = 0;
int err;
- cb->args[0] = 1;
-
err = nlmsg_parse(cb->nlh, 0, attrs, XFRMA_MAX,
xfrma_policy);
if (err < 0)
proto = nla_get_u8(attrs[XFRMA_PROTO]);
xfrm_state_walk_init(walk, proto, filter);
+ cb->args[0] = 1;
}
(void) xfrm_state_walk(net, walk, dump_one_state, &info);
if (up->hard) {
xfrm_policy_delete(xp, p->dir);
xfrm_audit_policy_delete(xp, 1, true);
- } else {
- // reset the timers here?
- WARN(1, "Don't know what to do with soft policy expire\n");
}
km_policy_expired(xp, p->dir, up->hard, nlh->nlmsg_pid);
err = verify_newpolicy_info(&ua->policy);
if (err)
- goto bad_policy;
+ goto free_state;
/* build an XP */
xp = xfrm_policy_construct(net, &ua->policy, attrs, &err);
return 0;
-bad_policy:
- WARN(1, "BAD policy passed\n");
free_state:
kfree(x);
nomem:
(void *) BPF_FUNC_l3_csum_replace;
static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) =
(void *) BPF_FUNC_l4_csum_replace;
-static int (*bpf_skb_in_cgroup)(void *ctx, void *map, int index) =
- (void *) BPF_FUNC_skb_in_cgroup;
+static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) =
+ (void *) BPF_FUNC_skb_under_cgroup;
#if defined(__x86_64__)
bpf_trace_printk(dont_care_msg, sizeof(dont_care_msg),
eth->h_proto, ip6h->nexthdr);
return TC_ACT_OK;
- } else if (bpf_skb_in_cgroup(skb, &test_cgrp2_array_pin, 0) != 1) {
+ } else if (bpf_skb_under_cgroup(skb, &test_cgrp2_array_pin, 0) != 1) {
bpf_trace_printk(pass_msg, sizeof(pass_msg));
return TC_ACT_OK;
} else {
assert(bpf_update_elem(map_fd, &key, &value, BPF_NOEXIST) == -1 &&
errno == E2BIG);
+ /* update existing element, thought the map is full */
+ key = 1;
+ assert(bpf_update_elem(map_fd, &key, &value, BPF_EXIST) == 0);
+ key = 2;
+ assert(bpf_update_elem(map_fd, &key, &value, BPF_ANY) == 0);
+ key = 1;
+ assert(bpf_update_elem(map_fd, &key, &value, BPF_ANY) == 0);
+
/* check that key = 0 doesn't exist */
+ key = 0;
assert(bpf_delete_elem(map_fd, &key) == -1 && errno == ENOENT);
/* iterate over two elements */
for (i = fn; i < MAP_SIZE; i += TASKS) {
key = value = i;
- if (do_update)
+ if (do_update) {
assert(bpf_update_elem(map_fd, &key, &value, BPF_NOEXIST) == 0);
- else
+ assert(bpf_update_elem(map_fd, &key, &value, BPF_EXIST) == 0);
+ } else {
assert(bpf_delete_elem(map_fd, &key) == 0);
+ }
}
}
as-instr = $(call try-run,\
printf "%b\n" "$(1)" | $(CC) $(KBUILD_AFLAGS) -c -x assembler -o "$$TMP" -,$(2),$(3))
+# Do not attempt to build with gcc plugins during cc-option tests.
+# (And this uses delayed resolution so the flags will be up to date.)
+CC_OPTION_CFLAGS = $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS))
+
# cc-option
# Usage: cflags-y += $(call cc-option,-march=winchip-c6,-march=i586)
cc-option = $(call try-run,\
- $(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
+ $(CC) $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
# cc-option-yn
# Usage: flag := $(call cc-option-yn,-march=winchip-c6)
cc-option-yn = $(call try-run,\
- $(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",y,n)
+ $(CC) $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",y,n)
# cc-option-align
# Prefix align with either -falign or -malign
# cc-disable-warning
# Usage: cflags-y += $(call cc-disable-warning,unused-but-set-variable)
cc-disable-warning = $(call try-run,\
- $(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1)))
+ $(CC) $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1)))
# cc-name
# Expands to either gcc or clang
endif
endif
- GCC_PLUGINS_CFLAGS := $(addprefix -fplugin=$(objtree)/scripts/gcc-plugins/, $(gcc-plugin-y))
+ GCC_PLUGINS_CFLAGS := $(strip $(addprefix -fplugin=$(objtree)/scripts/gcc-plugins/, $(gcc-plugin-y)) $(gcc-plugin-cflags-y))
- export PLUGINCC GCC_PLUGINS_CFLAGS GCC_PLUGIN SANCOV_PLUGIN
+ export PLUGINCC GCC_PLUGINS_CFLAGS GCC_PLUGIN GCC_PLUGIN_SUBDIR SANCOV_PLUGIN
+ ifneq ($(PLUGINCC),)
+ # SANCOV_PLUGIN can be only in CFLAGS_KCOV because avoid duplication.
+ GCC_PLUGINS_CFLAGS := $(filter-out $(SANCOV_PLUGIN), $(GCC_PLUGINS_CFLAGS))
+ endif
+
+ KBUILD_CFLAGS += $(GCC_PLUGINS_CFLAGS)
+ GCC_PLUGIN := $(gcc-plugin-y)
+ GCC_PLUGIN_SUBDIR := $(gcc-plugin-subdir-y)
+endif
+
+# If plugins aren't supported, abort the build before hard-to-read compiler
+# errors start getting spewed by the main build.
+PHONY += gcc-plugins-check
+gcc-plugins-check: FORCE
+ifdef CONFIG_GCC_PLUGINS
ifeq ($(PLUGINCC),)
ifneq ($(GCC_PLUGINS_CFLAGS),)
ifeq ($(call cc-ifversion, -ge, 0405, y), y)
- PLUGINCC := $(shell $(CONFIG_SHELL) -x $(srctree)/scripts/gcc-plugin.sh "$(__PLUGINCC)" "$(HOSTCXX)" "$(CC)")
- $(warning warning: your gcc installation does not support plugins, perhaps the necessary headers are missing?)
+ $(Q)$(srctree)/scripts/gcc-plugin.sh --show-error "$(__PLUGINCC)" "$(HOSTCXX)" "$(CC)" || true
+ @echo "Cannot use CONFIG_GCC_PLUGINS: your gcc installation does not support plugins, perhaps the necessary headers are missing?" >&2 && exit 1
else
- $(warning warning: your gcc version does not support plugins, you should upgrade it to gcc 4.5 at least)
+ @echo "Cannot use CONFIG_GCC_PLUGINS: your gcc version does not support plugins, you should upgrade it to at least gcc 4.5" >&2 && exit 1
endif
endif
- else
- # SANCOV_PLUGIN can be only in CFLAGS_KCOV because avoid duplication.
- GCC_PLUGINS_CFLAGS := $(filter-out $(SANCOV_PLUGIN), $(GCC_PLUGINS_CFLAGS))
endif
+endif
+ @:
- KBUILD_CFLAGS += $(GCC_PLUGINS_CFLAGS)
- GCC_PLUGIN := $(gcc-plugin-y)
-
+# Actually do the build, if requested.
+PHONY += gcc-plugins
+gcc-plugins: scripts_basic gcc-plugins-check
+ifdef CONFIG_GCC_PLUGINS
+ $(Q)$(MAKE) $(build)=scripts/gcc-plugins
endif
+ @:
}
}
-# check for uses of DEFINE_PCI_DEVICE_TABLE
- if ($line =~ /\bDEFINE_PCI_DEVICE_TABLE\s*\(\s*(\w+)\s*\)\s*=/) {
- if (WARN("DEFINE_PCI_DEVICE_TABLE",
- "Prefer struct pci_device_id over deprecated DEFINE_PCI_DEVICE_TABLE\n" . $herecurr) &&
- $fix) {
- $fixed[$fixlinenr] =~ s/\b(?:static\s+|)DEFINE_PCI_DEVICE_TABLE\s*\(\s*(\w+)\s*\)\s*=\s*/static const struct pci_device_id $1\[\] = /;
- }
- }
-
# check for new typedefs, only function parameters and sparse annotations
# make sense.
if ($line =~ /\btypedef\s/ &&
--- /dev/null
+#!/bin/bash
+#
+# Translate stack dump function offsets.
+#
+# addr2line doesn't work with KASLR addresses. This works similarly to
+# addr2line, but instead takes the 'func+0x123' format as input:
+#
+# $ ./scripts/faddr2line ~/k/vmlinux meminfo_proc_show+0x5/0x568
+# meminfo_proc_show+0x5/0x568:
+# meminfo_proc_show at fs/proc/meminfo.c:27
+#
+# If the address is part of an inlined function, the full inline call chain is
+# printed:
+#
+# $ ./scripts/faddr2line ~/k/vmlinux native_write_msr+0x6/0x27
+# native_write_msr+0x6/0x27:
+# arch_static_branch at arch/x86/include/asm/msr.h:121
+# (inlined by) static_key_false at include/linux/jump_label.h:125
+# (inlined by) native_write_msr at arch/x86/include/asm/msr.h:125
+#
+# The function size after the '/' in the input is optional, but recommended.
+# It's used to help disambiguate any duplicate symbol names, which can occur
+# rarely. If the size is omitted for a duplicate symbol then it's possible for
+# multiple code sites to be printed:
+#
+# $ ./scripts/faddr2line ~/k/vmlinux raw_ioctl+0x5
+# raw_ioctl+0x5/0x20:
+# raw_ioctl at drivers/char/raw.c:122
+#
+# raw_ioctl+0x5/0xb1:
+# raw_ioctl at net/ipv4/raw.c:876
+#
+# Multiple addresses can be specified on a single command line:
+#
+# $ ./scripts/faddr2line ~/k/vmlinux type_show+0x10/45 free_reserved_area+0x90
+# type_show+0x10/0x2d:
+# type_show at drivers/video/backlight/backlight.c:213
+#
+# free_reserved_area+0x90/0x123:
+# free_reserved_area at mm/page_alloc.c:6429 (discriminator 2)
+
+
+set -o errexit
+set -o nounset
+
+command -v awk >/dev/null 2>&1 || die "awk isn't installed"
+command -v readelf >/dev/null 2>&1 || die "readelf isn't installed"
+command -v addr2line >/dev/null 2>&1 || die "addr2line isn't installed"
+
+usage() {
+ echo "usage: faddr2line <object file> <func+offset> <func+offset>..." >&2
+ exit 1
+}
+
+warn() {
+ echo "$1" >&2
+}
+
+die() {
+ echo "ERROR: $1" >&2
+ exit 1
+}
+
+# Try to figure out the source directory prefix so we can remove it from the
+# addr2line output. HACK ALERT: This assumes that start_kernel() is in
+# kernel/init.c! This only works for vmlinux. Otherwise it falls back to
+# printing the absolute path.
+find_dir_prefix() {
+ local objfile=$1
+
+ local start_kernel_addr=$(readelf -sW $objfile | awk '$8 == "start_kernel" {printf "0x%s", $2}')
+ [[ -z $start_kernel_addr ]] && return
+
+ local file_line=$(addr2line -e $objfile $start_kernel_addr)
+ [[ -z $file_line ]] && return
+
+ local prefix=${file_line%init/main.c:*}
+ if [[ -z $prefix ]] || [[ $prefix = $file_line ]]; then
+ return
+ fi
+
+ DIR_PREFIX=$prefix
+ return 0
+}
+
+__faddr2line() {
+ local objfile=$1
+ local func_addr=$2
+ local dir_prefix=$3
+ local print_warnings=$4
+
+ local func=${func_addr%+*}
+ local offset=${func_addr#*+}
+ offset=${offset%/*}
+ local size=
+ [[ $func_addr =~ "/" ]] && size=${func_addr#*/}
+
+ if [[ -z $func ]] || [[ -z $offset ]] || [[ $func = $func_addr ]]; then
+ warn "bad func+offset $func_addr"
+ DONE=1
+ return
+ fi
+
+ # Go through each of the object's symbols which match the func name.
+ # In rare cases there might be duplicates.
+ while read symbol; do
+ local fields=($symbol)
+ local sym_base=0x${fields[1]}
+ local sym_size=${fields[2]}
+ local sym_type=${fields[3]}
+
+ # calculate the address
+ local addr=$(($sym_base + $offset))
+ if [[ -z $addr ]] || [[ $addr = 0 ]]; then
+ warn "bad address: $sym_base + $offset"
+ DONE=1
+ return
+ fi
+ local hexaddr=0x$(printf %x $addr)
+
+ # weed out non-function symbols
+ if [[ $sym_type != "FUNC" ]]; then
+ [[ $print_warnings = 1 ]] &&
+ echo "skipping $func address at $hexaddr due to non-function symbol"
+ continue
+ fi
+
+ # if the user provided a size, make sure it matches the symbol's size
+ if [[ -n $size ]] && [[ $size -ne $sym_size ]]; then
+ [[ $print_warnings = 1 ]] &&
+ echo "skipping $func address at $hexaddr due to size mismatch ($size != $sym_size)"
+ continue;
+ fi
+
+ # make sure the provided offset is within the symbol's range
+ if [[ $offset -gt $sym_size ]]; then
+ [[ $print_warnings = 1 ]] &&
+ echo "skipping $func address at $hexaddr due to size mismatch ($offset > $sym_size)"
+ continue
+ fi
+
+ # separate multiple entries with a blank line
+ [[ $FIRST = 0 ]] && echo
+ FIRST=0
+
+ local hexsize=0x$(printf %x $sym_size)
+ echo "$func+$offset/$hexsize:"
+ addr2line -fpie $objfile $hexaddr | sed "s; $dir_prefix\(\./\)*; ;"
+ DONE=1
+
+ done < <(readelf -sW $objfile | awk -v f=$func '$8 == f {print}')
+}
+
+[[ $# -lt 2 ]] && usage
+
+objfile=$1
+[[ ! -f $objfile ]] && die "can't find objfile $objfile"
+shift
+
+DIR_PREFIX=supercalifragilisticexpialidocious
+find_dir_prefix $objfile
+
+FIRST=1
+while [[ $# -gt 0 ]]; do
+ func_addr=$1
+ shift
+
+ # print any matches found
+ DONE=0
+ __faddr2line $objfile $func_addr $DIR_PREFIX 0
+
+ # if no match was found, print warnings
+ if [[ $DONE = 0 ]]; then
+ __faddr2line $objfile $func_addr $DIR_PREFIX 1
+ warn "no match for $func_addr"
+ fi
+done
#!/bin/sh
srctree=$(dirname "$0")
+
+SHOW_ERROR=
+if [ "$1" = "--show-error" ] ; then
+ SHOW_ERROR=1
+ shift || true
+fi
+
gccplugins_dir=$($3 -print-file-name=plugin)
plugincc=$($1 -E -x c++ - -o /dev/null -I"${srctree}"/gcc-plugins -I"${gccplugins_dir}"/include 2>&1 <<EOF
#include "gcc-common.h"
if [ $? -ne 0 ]
then
+ if [ -n "$SHOW_ERROR" ] ; then
+ echo "${plugincc}" >&2
+ fi
exit 1
fi
echo "$2"
exit 0
fi
+
+if [ -n "$SHOW_ERROR" ] ; then
+ echo "${plugincc}" >&2
+fi
exit 1
export HOST_EXTRACXXFLAGS
endif
-export GCCPLUGINS_DIR HOSTLIBS
-
ifneq ($(CFLAGS_KCOV), $(SANCOV_PLUGIN))
GCC_PLUGIN := $(filter-out $(SANCOV_PLUGIN), $(GCC_PLUGIN))
endif
-$(HOSTLIBS)-y := $(GCC_PLUGIN)
+export HOSTLIBS
+
+$(HOSTLIBS)-y := $(foreach p,$(GCC_PLUGIN),$(if $(findstring /,$(p)),,$(p)))
always := $($(HOSTLIBS)-y)
-cyc_complexity_plugin-objs := cyc_complexity_plugin.o
-sancov_plugin-objs := sancov_plugin.o
+$(foreach p,$($(HOSTLIBS)-y:%.so=%),$(eval $(p)-objs := $(p).o))
+
+subdir-y := $(GCC_PLUGIN_SUBDIR)
+subdir- += $(GCC_PLUGIN_SUBDIR)
clean-files += *.so
die "$P: file '${file}' not found\n";
}
}
- if ($from_filename || vcs_file_exists($file)) {
+ if ($from_filename || ($file ne "&STDIN" && vcs_file_exists($file))) {
$file =~ s/^\Q${cur_path}\E//; #strip any absolute path
$file =~ s/^\Q${lk_path}\E//; #or the path to the lk tree
push(@files, $file);
my $cmd = $VCS_cmds{"file_exists_cmd"};
$cmd =~ s/(\$\w+)/$1/eeg; # interpolate $cmd
-
+ $cmd .= " 2>&1";
$exists = &{$VCS_cmds{"execute_cmd"}}($cmd);
+ return 0 if ($? != 0);
+
return $exists;
}
(cd $objtree; find tools/objtool -type f -executable) >> "$objtree/debian/hdrobjfiles"
fi
(cd $objtree; find arch/$SRCARCH/include Module.symvers include scripts -type f) >> "$objtree/debian/hdrobjfiles"
-(cd $objtree; find scripts/gcc-plugins -name \*.so -o -name gcc-common.h) >> "$objtree/debian/hdrobjfiles"
+if grep -q '^CONFIG_GCC_PLUGINS=y' $KCONFIG_CONFIG ; then
+ (cd $objtree; find scripts/gcc-plugins -name \*.so -o -name gcc-common.h) >> "$objtree/debian/hdrobjfiles"
+fi
destdir=$kernel_headers_dir/usr/src/linux-headers-$version
mkdir -p "$destdir"
(cd $srctree; tar -c -f - -T -) < "$objtree/debian/hdrsrcfiles" | (cd $destdir; tar -xf -)
'/\<DEFINE_PER_CPU_SHARED_ALIGNED([^,]*, *\([[:alnum:]_]*\)/\1/v/'
'/\<DECLARE_WAIT_QUEUE_HEAD(\([[:alnum:]_]*\)/\1/v/'
'/\<DECLARE_\(TASKLET\|WORK\|DELAYED_WORK\)(\([[:alnum:]_]*\)/\2/v/'
- '/\<DEFINE_PCI_DEVICE_TABLE(\([[:alnum:]_]*\)/\1/v/'
'/\(^\s\)OFFSET(\([[:alnum:]_]*\)/\2/v/'
'/\(^\s\)DEFINE(\([[:alnum:]_]*\)/\2/v/'
'/\<DEFINE_HASHTABLE(\([[:alnum:]_]*\)/\1/v/'
this low address space will need the permission specific to the
systems running LSM.
+config HAVE_HARDENED_USERCOPY_ALLOCATOR
+ bool
+ help
+ The heap allocator implements __check_heap_object() for
+ validating memory ranges against heap object sizes in
+ support of CONFIG_HARDENED_USERCOPY.
+
+config HAVE_ARCH_HARDENED_USERCOPY
+ bool
+ help
+ The architecture supports CONFIG_HARDENED_USERCOPY by
+ calling check_object_size() just before performing the
+ userspace copies in the low level implementation of
+ copy_to_user() and copy_from_user().
+
+config HARDENED_USERCOPY
+ bool "Harden memory copies between kernel and userspace"
+ depends on HAVE_ARCH_HARDENED_USERCOPY
+ depends on HAVE_HARDENED_USERCOPY_ALLOCATOR
+ select BUG
+ help
+ This option checks for obviously wrong memory regions when
+ copying memory to/from the kernel (via copy_to_user() and
+ copy_from_user() functions) by rejecting memory ranges that
+ are larger than the specified heap object, span multiple
+ separately allocates pages, are not on the process stack,
+ or are part of the kernel text. This kills entire classes
+ of heap overflow exploits and similar kernel memory exposures.
+
+config HARDENED_USERCOPY_PAGESPAN
+ bool "Refuse to copy allocations that span multiple pages"
+ depends on HARDENED_USERCOPY
+ depends on EXPERT
+ help
+ When a multi-page allocation is done without __GFP_COMP,
+ hardened usercopy will reject attempts to copy it. There are,
+ however, several cases of this in the kernel that have not all
+ been removed. This config is intended to be used only while
+ trying to find such users.
+
source security/selinux/Kconfig
source security/smack/Kconfig
source security/tomoyo/Kconfig
#include <linux/rcupdate.h>
#include <linux/scatterlist.h>
#include <linux/ctype.h>
+#include <crypto/aes.h>
#include <crypto/hash.h>
#include <crypto/sha.h>
#include <crypto/skcipher.h>
struct crypto_skcipher *tfm;
struct skcipher_request *req;
unsigned int encrypted_datalen;
+ u8 iv[AES_BLOCK_SIZE];
unsigned int padlen;
char pad[16];
int ret;
sg_init_table(sg_out, 1);
sg_set_buf(sg_out, epayload->encrypted_data, encrypted_datalen);
- skcipher_request_set_crypt(req, sg_in, sg_out, encrypted_datalen,
- epayload->iv);
+ memcpy(iv, epayload->iv, sizeof(iv));
+ skcipher_request_set_crypt(req, sg_in, sg_out, encrypted_datalen, iv);
ret = crypto_skcipher_encrypt(req);
tfm = crypto_skcipher_reqtfm(req);
skcipher_request_free(req);
struct crypto_skcipher *tfm;
struct skcipher_request *req;
unsigned int encrypted_datalen;
+ u8 iv[AES_BLOCK_SIZE];
char pad[16];
int ret;
epayload->decrypted_datalen);
sg_set_buf(&sg_out[1], pad, sizeof pad);
- skcipher_request_set_crypt(req, sg_in, sg_out, encrypted_datalen,
- epayload->iv);
+ memcpy(iv, epayload->iv, sizeof(iv));
+ skcipher_request_set_crypt(req, sg_in, sg_out, encrypted_datalen, iv);
ret = crypto_skcipher_decrypt(req);
tfm = crypto_skcipher_reqtfm(req);
skcipher_request_free(req);
return -EBUSY;
}
list_add_tail(&rmidi->list, &snd_rawmidi_devices);
+ mutex_unlock(®ister_mutex);
err = snd_register_device(SNDRV_DEVICE_TYPE_RAWMIDI,
rmidi->card, rmidi->device,
&snd_rawmidi_f_ops, rmidi, &rmidi->dev);
if (err < 0) {
rmidi_err(rmidi, "unable to register\n");
+ mutex_lock(®ister_mutex);
list_del(&rmidi->list);
mutex_unlock(®ister_mutex);
return err;
if (rmidi->ops && rmidi->ops->dev_register &&
(err = rmidi->ops->dev_register(rmidi)) < 0) {
snd_unregister_device(&rmidi->dev);
+ mutex_lock(®ister_mutex);
list_del(&rmidi->list);
mutex_unlock(®ister_mutex);
return err;
}
}
#endif /* CONFIG_SND_OSSEMUL */
- mutex_unlock(®ister_mutex);
sprintf(name, "midi%d", rmidi->device);
entry = snd_info_create_card_entry(rmidi->card, name, rmidi->card->proc_root);
if (entry) {
#include <sound/initval.h>
#include <linux/kmod.h>
+/* internal flags */
+#define SNDRV_TIMER_IFLG_PAUSED 0x00010000
+
#if IS_ENABLED(CONFIG_SND_HRTIMER)
#define DEFAULT_TIMER_LIMIT 4
#else
get_device(&timer->card->card_dev);
timeri->slave_class = tid->dev_sclass;
timeri->slave_id = slave_id;
- if (list_empty(&timer->open_list_head) && timer->hw.open)
- timer->hw.open(timer);
+
+ if (list_empty(&timer->open_list_head) && timer->hw.open) {
+ int err = timer->hw.open(timer);
+ if (err) {
+ kfree(timeri->owner);
+ kfree(timeri);
+
+ if (timer->card)
+ put_device(&timer->card->card_dev);
+ module_put(timer->module);
+ mutex_unlock(®ister_mutex);
+ return err;
+ }
+ }
+
list_add_tail(&timeri->open_list, &timer->open_list_head);
snd_timer_check_master(timeri);
mutex_unlock(®ister_mutex);
}
}
timeri->flags &= ~(SNDRV_TIMER_IFLG_RUNNING | SNDRV_TIMER_IFLG_START);
+ if (stop)
+ timeri->flags &= ~SNDRV_TIMER_IFLG_PAUSED;
+ else
+ timeri->flags |= SNDRV_TIMER_IFLG_PAUSED;
snd_timer_notify1(timeri, stop ? SNDRV_TIMER_EVENT_STOP :
SNDRV_TIMER_EVENT_CONTINUE);
unlock:
*/
int snd_timer_continue(struct snd_timer_instance *timeri)
{
+ /* timer can continue only after pause */
+ if (!(timeri->flags & SNDRV_TIMER_IFLG_PAUSED))
+ return -EINVAL;
+
if (timeri->flags & SNDRV_TIMER_IFLG_SLAVE)
return snd_timer_start_slave(timeri, false);
else
timer->tmr_subdevice = tid->subdevice;
if (id)
strlcpy(timer->id, id, sizeof(timer->id));
+ timer->sticks = 1;
INIT_LIST_HEAD(&timer->device_list);
INIT_LIST_HEAD(&timer->open_list_head);
INIT_LIST_HEAD(&timer->active_list_head);
tu = file->private_data;
if (!tu->timeri)
return -EBADFD;
+ /* start timer instead of continue if it's not used before */
+ if (!(tu->timeri->flags & SNDRV_TIMER_IFLG_PAUSED))
+ return snd_timer_user_start(file);
tu->timeri->lost = 0;
return (err = snd_timer_continue(tu->timeri)) < 0 ? err : 0;
}
tu->qused--;
spin_unlock_irq(&tu->qlock);
+ mutex_lock(&tu->ioctl_lock);
if (tu->tread) {
if (copy_to_user(buffer, &tu->tqueue[qhead],
sizeof(struct snd_timer_tread)))
sizeof(struct snd_timer_read)))
err = -EFAULT;
}
+ mutex_unlock(&tu->ioctl_lock);
spin_lock_irq(&tu->qlock);
if (err < 0)
u8 *resp_buf;
u8 *pull_ptr;
u8 *push_ptr;
- unsigned int resp_queues;
};
int snd_efw_transaction_cmd(struct fw_unit *unit,
{
unsigned int length, till_end, type;
struct snd_efw_transaction *t;
+ u8 *pull_ptr;
long count = 0;
if (remained < sizeof(type) + sizeof(struct snd_efw_transaction))
buf += sizeof(type);
/* write into buffer as many responses as possible */
- while (efw->resp_queues > 0) {
- t = (struct snd_efw_transaction *)(efw->pull_ptr);
+ spin_lock_irq(&efw->lock);
+
+ /*
+ * When another task reaches here during this task's access to user
+ * space, it picks up current position in buffer and can read the same
+ * series of responses.
+ */
+ pull_ptr = efw->pull_ptr;
+
+ while (efw->push_ptr != pull_ptr) {
+ t = (struct snd_efw_transaction *)(pull_ptr);
length = be32_to_cpu(t->length) * sizeof(__be32);
/* confirm enough space for this response */
/* copy from ring buffer to user buffer */
while (length > 0) {
till_end = snd_efw_resp_buf_size -
- (unsigned int)(efw->pull_ptr - efw->resp_buf);
+ (unsigned int)(pull_ptr - efw->resp_buf);
till_end = min_t(unsigned int, length, till_end);
- if (copy_to_user(buf, efw->pull_ptr, till_end))
+ spin_unlock_irq(&efw->lock);
+
+ if (copy_to_user(buf, pull_ptr, till_end))
return -EFAULT;
- efw->pull_ptr += till_end;
- if (efw->pull_ptr >= efw->resp_buf +
- snd_efw_resp_buf_size)
- efw->pull_ptr -= snd_efw_resp_buf_size;
+ spin_lock_irq(&efw->lock);
+
+ pull_ptr += till_end;
+ if (pull_ptr >= efw->resp_buf + snd_efw_resp_buf_size)
+ pull_ptr -= snd_efw_resp_buf_size;
length -= till_end;
buf += till_end;
count += till_end;
remained -= till_end;
}
-
- efw->resp_queues--;
}
+ /*
+ * All of tasks can read from the buffer nearly simultaneously, but the
+ * last position for each task is different depending on the length of
+ * given buffer. Here, for simplicity, a position of buffer is set by
+ * the latest task. It's better for a listening application to allow one
+ * thread to read from the buffer. Unless, each task can read different
+ * sequence of responses depending on variation of buffer length.
+ */
+ efw->pull_ptr = pull_ptr;
+
+ spin_unlock_irq(&efw->lock);
+
return count;
}
hwdep_read_locked(struct snd_efw *efw, char __user *buf, long count,
loff_t *offset)
{
- union snd_firewire_event event;
+ union snd_firewire_event event = {
+ .lock_status.type = SNDRV_FIREWIRE_EVENT_LOCK_STATUS,
+ };
- memset(&event, 0, sizeof(event));
+ spin_lock_irq(&efw->lock);
- event.lock_status.type = SNDRV_FIREWIRE_EVENT_LOCK_STATUS;
event.lock_status.status = (efw->dev_lock_count > 0);
efw->dev_lock_changed = false;
+ spin_unlock_irq(&efw->lock);
+
count = min_t(long, count, sizeof(event.lock_status));
if (copy_to_user(buf, &event, count))
{
struct snd_efw *efw = hwdep->private_data;
DEFINE_WAIT(wait);
+ bool dev_lock_changed;
+ bool queued;
spin_lock_irq(&efw->lock);
- while ((!efw->dev_lock_changed) && (efw->resp_queues == 0)) {
+ dev_lock_changed = efw->dev_lock_changed;
+ queued = efw->push_ptr != efw->pull_ptr;
+
+ while (!dev_lock_changed && !queued) {
prepare_to_wait(&efw->hwdep_wait, &wait, TASK_INTERRUPTIBLE);
spin_unlock_irq(&efw->lock);
schedule();
if (signal_pending(current))
return -ERESTARTSYS;
spin_lock_irq(&efw->lock);
+ dev_lock_changed = efw->dev_lock_changed;
+ queued = efw->push_ptr != efw->pull_ptr;
}
- if (efw->dev_lock_changed)
+ spin_unlock_irq(&efw->lock);
+
+ if (dev_lock_changed)
count = hwdep_read_locked(efw, buf, count, offset);
- else if (efw->resp_queues > 0)
+ else if (queued)
count = hwdep_read_resp_buf(efw, buf, count, offset);
- spin_unlock_irq(&efw->lock);
-
return count;
}
poll_wait(file, &efw->hwdep_wait, wait);
spin_lock_irq(&efw->lock);
- if (efw->dev_lock_changed || (efw->resp_queues > 0))
+ if (efw->dev_lock_changed || efw->pull_ptr != efw->push_ptr)
events = POLLIN | POLLRDNORM;
else
events = 0;
else
consumed = (unsigned int)(efw->push_ptr - efw->pull_ptr);
- snd_iprintf(buffer, "%d %d/%d\n",
- efw->resp_queues, consumed, snd_efw_resp_buf_size);
+ snd_iprintf(buffer, "%d/%d\n",
+ consumed, snd_efw_resp_buf_size);
}
static void
size_t capacity, till_end;
struct snd_efw_transaction *t;
- spin_lock_irq(&efw->lock);
-
t = (struct snd_efw_transaction *)data;
length = min_t(size_t, be32_to_cpu(t->length) * sizeof(u32), length);
+ spin_lock_irq(&efw->lock);
+
if (efw->push_ptr < efw->pull_ptr)
capacity = (unsigned int)(efw->pull_ptr - efw->push_ptr);
else
}
/* for hwdep */
- efw->resp_queues++;
wake_up(&efw->hwdep_wait);
*rcode = RCODE_COMPLETE;
#include "tascam.h"
-static long hwdep_read_locked(struct snd_tscm *tscm, char __user *buf,
- long count)
-{
- union snd_firewire_event event;
-
- memset(&event, 0, sizeof(event));
-
- event.lock_status.type = SNDRV_FIREWIRE_EVENT_LOCK_STATUS;
- event.lock_status.status = (tscm->dev_lock_count > 0);
- tscm->dev_lock_changed = false;
-
- count = min_t(long, count, sizeof(event.lock_status));
-
- if (copy_to_user(buf, &event, count))
- return -EFAULT;
-
- return count;
-}
-
static long hwdep_read(struct snd_hwdep *hwdep, char __user *buf, long count,
loff_t *offset)
{
struct snd_tscm *tscm = hwdep->private_data;
DEFINE_WAIT(wait);
- union snd_firewire_event event;
+ union snd_firewire_event event = {
+ .lock_status.type = SNDRV_FIREWIRE_EVENT_LOCK_STATUS,
+ };
spin_lock_irq(&tscm->lock);
spin_lock_irq(&tscm->lock);
}
- memset(&event, 0, sizeof(event));
- count = hwdep_read_locked(tscm, buf, count);
+ event.lock_status.status = (tscm->dev_lock_count > 0);
+ tscm->dev_lock_changed = false;
+
spin_unlock_irq(&tscm->lock);
+ count = min_t(long, count, sizeof(event.lock_status));
+
+ if (copy_to_user(buf, &event, count))
+ return -EFAULT;
+
return count;
}
struct snd_card *card = dev_get_drvdata(dev);
struct azx *chip;
struct hda_intel *hda;
+ struct hdac_bus *bus;
if (!card)
return 0;
chip = card->private_data;
hda = container_of(chip, struct hda_intel, chip);
+ bus = azx_bus(chip);
if (chip->disabled || hda->init_failed || !chip->running)
return 0;
- if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL
- && hda->need_i915_power) {
- snd_hdac_display_power(azx_bus(chip), true);
- snd_hdac_i915_set_bclk(azx_bus(chip));
+ if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) {
+ snd_hdac_display_power(bus, true);
+ if (hda->need_i915_power)
+ snd_hdac_i915_set_bclk(bus);
}
+
if (chip->msi)
if (pci_enable_msi(pci) < 0)
chip->msi = 0;
hda_intel_init_chip(chip, true);
+ /* power down again for link-controlled chips */
+ if ((chip->driver_caps & AZX_DCAPS_I915_POWERWELL) &&
+ !hda->need_i915_power)
+ snd_hdac_display_power(bus, false);
+
snd_power_change_state(card, SNDRV_CTL_POWER_D0);
trace_azx_resume(chip);
chip = card->private_data;
hda = container_of(chip, struct hda_intel, chip);
+ bus = azx_bus(chip);
if (chip->disabled || hda->init_failed)
return 0;
return 0;
if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) {
- bus = azx_bus(chip);
- if (hda->need_i915_power) {
- snd_hdac_display_power(bus, true);
+ snd_hdac_display_power(bus, true);
+ if (hda->need_i915_power)
snd_hdac_i915_set_bclk(bus);
- } else {
- /* toggle codec wakeup bit for STATESTS read */
- snd_hdac_set_codec_wakeup(bus, true);
- snd_hdac_set_codec_wakeup(bus, false);
- }
}
/* Read STATESTS before controller reset */
azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) &
~STATESTS_INT_MASK);
+ /* power down again for link-controlled chips */
+ if ((chip->driver_caps & AZX_DCAPS_I915_POWERWELL) &&
+ !hda->need_i915_power)
+ snd_hdac_display_power(bus, false);
+
trace_azx_runtime_resume(chip);
return 0;
}
ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
ALC292_FIXUP_TPT440_DOCK,
ALC292_FIXUP_TPT440,
- ALC283_FIXUP_BXBT2807_MIC,
+ ALC283_FIXUP_HEADSET_MIC,
ALC255_FIXUP_DELL_WMI_MIC_MUTE_LED,
ALC282_FIXUP_ASPIRE_V5_PINS,
ALC280_FIXUP_HP_GPIO4,
ALC221_FIXUP_HP_FRONT_MIC,
ALC292_FIXUP_TPT460,
ALC298_FIXUP_SPK_VOLUME,
+ ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER,
};
static const struct hda_fixup alc269_fixups[] = {
.chained = true,
.chain_id = ALC292_FIXUP_TPT440_DOCK,
},
- [ALC283_FIXUP_BXBT2807_MIC] = {
+ [ALC283_FIXUP_HEADSET_MIC] = {
.type = HDA_FIXUP_PINS,
.v.pins = (const struct hda_pintbl[]) {
{ 0x19, 0x04a110f0 },
.chained = true,
.chain_id = ALC298_FIXUP_DELL1_MIC_NO_PRESENCE,
},
+ [ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x1b, 0x90170151 },
+ { }
+ },
+ .chained = true,
+ .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE
+ },
};
static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1028, 0x06df, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK),
SND_PCI_QUIRK(0x1028, 0x06e0, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK),
SND_PCI_QUIRK(0x1028, 0x0704, "Dell XPS 13 9350", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
+ SND_PCI_QUIRK(0x1028, 0x0706, "Dell Inspiron 7559", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER),
SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE),
SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME),
SND_PCI_QUIRK(0x10cf, 0x1757, "Lifebook E752", ALC269_FIXUP_LIFEBOOK_HP_PIN),
SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
- SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_BXBT2807_MIC),
+ SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE),
SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE),
SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE),
{0x12, 0x90a60170},
{0x14, 0x90170120},
{0x21, 0x02211030}),
+ SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell Inspiron 5468", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+ {0x12, 0x90a60180},
+ {0x14, 0x90170120},
+ {0x21, 0x02211030}),
SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
ALC256_STANDARD_PINS),
SND_HDA_PIN_QUIRK(0x10ec0280, 0x103c, "HP", ALC280_FIXUP_HP_GPIO4,
clk_enable(ssc_p->ssc->clk);
ssc_p->mck_rate = clk_get_rate(ssc_p->ssc->clk);
- /* Reset the SSC to keep it at a clean status */
- ssc_writel(ssc_p->ssc->regs, CR, SSC_BIT(CR_SWRST));
+ /* Reset the SSC unless initialized to keep it in a clean state */
+ if (!ssc_p->initialized)
+ ssc_writel(ssc_p->ssc->regs, CR, SSC_BIT(CR_SWRST));
if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
dir = 0;
struct arizona_fll_cfg {
int n;
- int theta;
- int lambda;
+ unsigned int theta;
+ unsigned int lambda;
int refdiv;
int outdiv;
int fratio;
if (already_enabled) {
/* Facilitate smooth refclk across the transition */
- regmap_update_bits_async(fll->arizona->regmap, fll->base + 0x9,
- ARIZONA_FLL1_GAIN_MASK, 0);
regmap_update_bits(fll->arizona->regmap, fll->base + 1,
ARIZONA_FLL1_FREERUN, ARIZONA_FLL1_FREERUN);
udelay(32);
+ regmap_update_bits_async(fll->arizona->regmap, fll->base + 0x9,
+ ARIZONA_FLL1_GAIN_MASK, 0);
}
/*
fll->ref_src != fll->sync_src) {
arizona_calc_fll(fll, &cfg, fll->ref_freq, false);
+ /* Ref path hardcodes lambda to 65536 when sync is on */
+ if (fll->sync_src >= 0 && cfg.lambda)
+ cfg.theta = (cfg.theta * (1 << 16)) / cfg.lambda;
+
arizona_apply_fll(arizona, fll->base, &cfg, fll->ref_src,
false);
if (fll->sync_src >= 0) {
ARIZONA_FLL1_SYNC_BW);
if (!already_enabled)
- pm_runtime_get(arizona->dev);
+ pm_runtime_get_sync(arizona->dev);
regmap_update_bits_async(arizona->regmap, fll->base + 1,
ARIZONA_FLL1_ENA, ARIZONA_FLL1_ENA);
return -EINVAL;
}
- /* By default only 32 BCLK per WCLK is supported */
- dai_clk_mode |= DA7213_DAI_BCLKS_PER_WCLK_32;
+ /* By default only 64 BCLK per WCLK is supported */
+ dai_clk_mode |= DA7213_DAI_BCLKS_PER_WCLK_64;
snd_soc_write(codec, DA7213_DAI_CLK_MODE, dai_clk_mode);
snd_soc_update_bits(codec, DA7213_DAI_CTRL, DA7213_DAI_FORMAT_MASK,
return ret;
}
+ /* Software reset codec. */
+ regmap_write_bits(da7219->regmap, DA7219_ACCDET_CONFIG_1,
+ DA7219_ACCDET_EN_MASK, 0);
+ regmap_write_bits(da7219->regmap, DA7219_CIF_CTRL,
+ DA7219_CIF_REG_SOFT_RESET_MASK, 0);
+ regmap_write_bits(da7219->regmap, DA7219_SYSTEM_ACTIVE,
+ DA7219_SYSTEM_ACTIVE_MASK, 0);
+
ret = snd_soc_register_codec(&i2c->dev, &soc_codec_dev_da7219,
&da7219_dai, 1);
if (ret < 0) {
static const struct i2c_device_id max98371_i2c_id[] = {
{ "max98371", 0 },
+ { }
};
MODULE_DEVICE_TABLE(i2c, max98371_i2c_id);
0xfa2f, 0xfaea, 0xfba5, 0xfc60, 0xfd1a, 0xfdd4, 0xfe8e, 0xff47
};
-static struct snd_soc_dai *nau8825_get_codec_dai(struct nau8825 *nau8825)
-{
- struct snd_soc_codec *codec = snd_soc_dapm_to_codec(nau8825->dapm);
- struct snd_soc_component *component = &codec->component;
- struct snd_soc_dai *codec_dai, *_dai;
-
- list_for_each_entry_safe(codec_dai, _dai, &component->dai_list, list) {
- if (!strncmp(codec_dai->name, NUVOTON_CODEC_DAI,
- strlen(NUVOTON_CODEC_DAI)))
- return codec_dai;
- }
- return NULL;
-}
-
-static bool nau8825_dai_is_active(struct nau8825 *nau8825)
-{
- struct snd_soc_dai *codec_dai = nau8825_get_codec_dai(nau8825);
-
- if (codec_dai) {
- if (codec_dai->playback_active || codec_dai->capture_active)
- return true;
- }
- return false;
-}
-
/**
* nau8825_sema_acquire - acquire the semaphore of nau88l25
* @nau8825: component to register the codec private data with
* Acquires the semaphore without jiffies. If no more tasks are allowed
* to acquire the semaphore, calling this function will put the task to
* sleep until the semaphore is released.
- * It returns if the semaphore was acquired.
+ * If the semaphore is not released within the specified number of jiffies,
+ * this function returns -ETIME.
+ * If the sleep is interrupted by a signal, this function will return -EINTR.
+ * It returns 0 if the semaphore was acquired successfully.
*/
-static void nau8825_sema_acquire(struct nau8825 *nau8825, long timeout)
+static int nau8825_sema_acquire(struct nau8825 *nau8825, long timeout)
{
int ret;
- if (timeout)
+ if (timeout) {
ret = down_timeout(&nau8825->xtalk_sem, timeout);
- else
+ if (ret < 0)
+ dev_warn(nau8825->dev, "Acquire semaphone timeout\n");
+ } else {
ret = down_interruptible(&nau8825->xtalk_sem);
+ if (ret < 0)
+ dev_warn(nau8825->dev, "Acquire semaphone fail\n");
+ }
- if (ret < 0)
- dev_warn(nau8825->dev, "Acquire semaphone fail\n");
+ return ret;
}
/**
struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec);
unsigned int val_len = 0;
+ nau8825_sema_acquire(nau8825, 2 * HZ);
+
switch (params_width(params)) {
case 16:
val_len |= NAU8825_I2S_DL_16;
regmap_update_bits(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL1,
NAU8825_I2S_DL_MASK, val_len);
+ /* Release the semaphone. */
+ nau8825_sema_release(nau8825);
+
return 0;
}
struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec);
unsigned int ctrl1_val = 0, ctrl2_val = 0;
+ nau8825_sema_acquire(nau8825, 2 * HZ);
+
switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
case SND_SOC_DAIFMT_CBM_CFM:
ctrl2_val |= NAU8825_I2S_MS_MASTER;
regmap_update_bits(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL2,
NAU8825_I2S_MS_MASK, ctrl2_val);
+ /* Release the semaphone. */
+ nau8825_sema_release(nau8825);
+
return 0;
}
* cess and restore changes if process
* is ongoing when ejection.
*/
+ int ret;
nau8825->xtalk_protect = true;
- nau8825_sema_acquire(nau8825, 0);
+ ret = nau8825_sema_acquire(nau8825, 0);
+ if (ret < 0)
+ nau8825->xtalk_protect = false;
}
/* Startup cross talk detection process */
nau8825->xtalk_state = NAU8825_XTALK_PREPARE;
/* Calculate the FLL 10-bit integer input and the FLL 16-bit fractional
* input based on FDCO, FREF and FLL ratio.
*/
- fvco = div_u64(fvco << 16, fref * fll_param->ratio);
+ fvco = div_u64(fvco_max << 16, fref * fll_param->ratio);
fll_param->fll_int = (fvco >> 16) & 0x3FF;
fll_param->fll_frac = fvco & 0xFFFF;
return 0;
static int __maybe_unused nau8825_resume(struct snd_soc_codec *codec)
{
struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec);
+ int ret;
regcache_cache_only(nau8825->regmap, false);
regcache_sync(nau8825->regmap);
- if (nau8825_is_jack_inserted(nau8825->regmap)) {
- /* If the jack is inserted, we need to check whether the play-
- * back is active before suspend. If active, the driver has to
- * raise the protection for cross talk function to avoid the
- * playback recovers before cross talk process finish. Other-
- * wise, the playback will be interfered by cross talk func-
- * tion. It is better to apply hardware related parameters
- * before starting playback or record.
- */
- if (nau8825_dai_is_active(nau8825)) {
- nau8825->xtalk_protect = true;
- nau8825_sema_acquire(nau8825, 0);
- }
- }
+ nau8825->xtalk_protect = true;
+ ret = nau8825_sema_acquire(nau8825, 0);
+ if (ret < 0)
+ nau8825->xtalk_protect = false;
enable_irq(nau8825->irq);
return 0;
8, 8, TLV_DB_SCALE_ITEM(1700, 0, 0)
);
-static const DECLARE_TLV_DB_SCALE(adc_vol_tlv, -17625, 375, 0);
+static const DECLARE_TLV_DB_SCALE(adc_vol_tlv, -1725, 75, 0);
static int rt5514_dsp_voice_wake_up_get(struct snd_kcontrol *kcontrol,
struct snd_ctl_elem_value *ucontrol)
SOC_DOUBLE_TLV("MIC Boost Volume", RT5514_ANA_CTRL_MICBST,
RT5514_SEL_BSTL_SFT, RT5514_SEL_BSTR_SFT, 8, 0, bst_tlv),
SOC_DOUBLE_R_TLV("ADC1 Capture Volume", RT5514_DOWNFILTER0_CTRL1,
- RT5514_DOWNFILTER0_CTRL2, RT5514_AD_GAIN_SFT, 127, 0,
+ RT5514_DOWNFILTER0_CTRL2, RT5514_AD_GAIN_SFT, 63, 0,
adc_vol_tlv),
SOC_DOUBLE_R_TLV("ADC2 Capture Volume", RT5514_DOWNFILTER1_CTRL1,
- RT5514_DOWNFILTER1_CTRL2, RT5514_AD_GAIN_SFT, 127, 0,
+ RT5514_DOWNFILTER1_CTRL2, RT5514_AD_GAIN_SFT, 63, 0,
adc_vol_tlv),
SOC_SINGLE_EXT("DSP Voice Wake Up", SND_SOC_NOPM, 0, 1, 0,
rt5514_dsp_voice_wake_up_get, rt5514_dsp_voice_wake_up_put),
#define RT5514_AD_AD_MIX_BIT 10
#define RT5514_AD_AD_MUTE (0x1 << 7)
#define RT5514_AD_AD_MUTE_BIT 7
-#define RT5514_AD_GAIN_MASK (0x7f << 0)
-#define RT5514_AD_GAIN_SFT 0
+#define RT5514_AD_GAIN_MASK (0x3f << 1)
+#define RT5514_AD_GAIN_SFT 1
/* RT5514_ANA_CTRL_MICBST (0x2220) */
#define RT5514_SEL_BSTL_MASK (0xf << 4)
static int tpa6130a2_power(struct tpa6130a2_data *data, bool enable)
{
- int ret;
+ int ret = 0, ret2;
if (enable) {
ret = regulator_enable(data->supply);
/* Power on */
if (data->power_gpio >= 0)
gpio_set_value(data->power_gpio, 1);
+
+ /* Sync registers */
+ regcache_cache_only(data->regmap, false);
+ ret = regcache_sync(data->regmap);
+ if (ret != 0) {
+ dev_err(data->dev,
+ "Failed to sync registers: %d\n", ret);
+ goto regcache_sync_failed;
+ }
} else {
+ /* Powered off device does not retain registers. While device
+ * is off, any register updates (i.e. volume changes) should
+ * happen in cache only.
+ */
+ regcache_mark_dirty(data->regmap);
+regcache_sync_failed:
+ regcache_cache_only(data->regmap, true);
+
/* Power off */
if (data->power_gpio >= 0)
gpio_set_value(data->power_gpio, 0);
- ret = regulator_disable(data->supply);
- if (ret != 0) {
+ ret2 = regulator_disable(data->supply);
+ if (ret2 != 0) {
dev_err(data->dev,
- "Failed to disable supply: %d\n", ret);
- return ret;
+ "Failed to disable supply: %d\n", ret2);
+ return ret ? ret : ret2;
}
-
- /* device regs does not match the cache state anymore */
- regcache_mark_dirty(data->regmap);
}
return ret;
{
struct snd_soc_component *c = snd_soc_dapm_to_component(w->dapm);
struct tpa6130a2_data *data = snd_soc_component_get_drvdata(c);
- int ret;
- /* before widget power up */
if (SND_SOC_DAPM_EVENT_ON(event)) {
- /* Turn on the chip */
- tpa6130a2_power(data, true);
- /* Sync the registers */
- ret = regcache_sync(data->regmap);
- if (ret < 0) {
- dev_err(c->dev, "Failed to initialize chip\n");
- tpa6130a2_power(data, false);
- return ret;
- }
- /* after widget power down */
+ /* Before widget power up: turn chip on, sync registers */
+ return tpa6130a2_power(data, true);
} else {
- tpa6130a2_power(data, false);
+ /* After widget power down: turn chip off */
+ return tpa6130a2_power(data, false);
}
-
- return 0;
}
/*
if (anc_transitions[i].dest == ANC_OFF)
clk_disable_unprepare(wm2000->mclk);
- return ret;
+ return 0;
}
static int wm2000_anc_set_mode(struct wm2000_priv *wm2000)
-obj-$(CONFIG_SND_SIMPLE_CARD_UTILS) := simple-card-utils.o
-
+snd-soc-simple-card-utils-objs := simple-card-utils.o
snd-soc-simple-card-objs := simple-card.o
-obj-$(CONFIG_SND_SIMPLE_CARD) += snd-soc-simple-card.o
+obj-$(CONFIG_SND_SIMPLE_CARD_UTILS) += snd-soc-simple-card-utils.o
+obj-$(CONFIG_SND_SIMPLE_CARD) += snd-soc-simple-card.o
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
+#include <linux/module.h>
#include <linux/of.h>
#include <sound/simple_card_utils.h>
return 0;
}
EXPORT_SYMBOL_GPL(asoc_simple_card_parse_card_name);
+
+/* Module information */
+MODULE_AUTHOR("Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>");
+MODULE_DESCRIPTION("ALSA SoC Simple Card Utils");
+MODULE_LICENSE("GPL v2");
"Period elapsed rcvd for pipe id 0x%x\n",
pipe_id);
stream = &sst_drv_ctx->streams[str_id];
+ /* If stream is dropped, skip processing this message*/
+ if (stream->status == STREAM_INIT)
+ break;
if (stream->period_elapsed)
stream->period_elapsed(stream->pcm_substream);
if (stream->compr_cb)
if (response) {
ret = sst_wait_timeout(sst, block);
- if (ret < 0) {
+ if (ret < 0)
goto out;
- } else if(block->data) {
- if (!data)
- goto out;
- *data = kzalloc(block->size, GFP_KERNEL);
- if (!(*data)) {
+
+ if (data && block->data) {
+ *data = kmemdup(block->data, block->size, GFP_KERNEL);
+ if (!*data) {
ret = -ENOMEM;
goto out;
- } else
- memcpy(data, (void *) block->data, block->size);
+ }
}
}
out:
uuid_mod = (uuid_le *)mconfig->guid;
+ if (list_empty(&ctx->uuid_list)) {
+ dev_err(ctx->dev, "Module list is empty\n");
+ return -EINVAL;
+ }
+
list_for_each_entry(module, &ctx->uuid_list, list) {
if (uuid_le_cmp(*uuid_mod, module->uuid) == 0) {
mconfig->id.module_id = module->id;
skl->nhlt = skl_nhlt_init(bus->dev);
- if (skl->nhlt == NULL)
+ if (skl->nhlt == NULL) {
+ err = -ENODEV;
goto out_free;
+ }
skl_nhlt_update_topology_bin(skl);
struct abe_twl6040 {
int jack_detection; /* board can detect jack events */
int mclk_freq; /* MCLK frequency speed for twl6040 */
-
- struct platform_device *dmic_codec_dev;
};
+struct platform_device *dmic_codec_dev;
+
static int omap_abe_hw_params(struct snd_pcm_substream *substream,
struct snd_pcm_hw_params *params)
{
if (priv == NULL)
return -ENOMEM;
- priv->dmic_codec_dev = ERR_PTR(-EINVAL);
-
if (snd_soc_of_parse_card_name(card, "ti,model")) {
dev_err(&pdev->dev, "Card name is not provided\n");
return -ENODEV;
num_links = 2;
abe_twl6040_dai_links[1].cpu_of_node = dai_node;
abe_twl6040_dai_links[1].platform_of_node = dai_node;
-
- priv->dmic_codec_dev = platform_device_register_simple(
- "dmic-codec", -1, NULL, 0);
- if (IS_ERR(priv->dmic_codec_dev)) {
- dev_err(&pdev->dev, "Can't instantiate dmic-codec\n");
- return PTR_ERR(priv->dmic_codec_dev);
- }
} else {
num_links = 1;
}
of_property_read_u32(node, "ti,mclk-freq", &priv->mclk_freq);
if (!priv->mclk_freq) {
dev_err(&pdev->dev, "MCLK frequency not provided\n");
- ret = -EINVAL;
- goto err_unregister;
+ return -EINVAL;
}
card->fully_routed = 1;
if (!priv->mclk_freq) {
dev_err(&pdev->dev, "MCLK frequency missing\n");
- ret = -ENODEV;
- goto err_unregister;
+ return -ENODEV;
}
card->dai_link = abe_twl6040_dai_links;
snd_soc_card_set_drvdata(card, priv);
ret = snd_soc_register_card(card);
- if (ret) {
+ if (ret)
dev_err(&pdev->dev, "snd_soc_register_card() failed: %d\n",
ret);
- goto err_unregister;
- }
-
- return 0;
-
-err_unregister:
- if (!IS_ERR(priv->dmic_codec_dev))
- platform_device_unregister(priv->dmic_codec_dev);
return ret;
}
static int omap_abe_remove(struct platform_device *pdev)
{
struct snd_soc_card *card = platform_get_drvdata(pdev);
- struct abe_twl6040 *priv = snd_soc_card_get_drvdata(card);
snd_soc_unregister_card(card);
- if (!IS_ERR(priv->dmic_codec_dev))
- platform_device_unregister(priv->dmic_codec_dev);
-
return 0;
}
.remove = omap_abe_remove,
};
-module_platform_driver(omap_abe_driver);
+static int __init omap_abe_init(void)
+{
+ int ret;
+
+ dmic_codec_dev = platform_device_register_simple("dmic-codec", -1, NULL,
+ 0);
+ if (IS_ERR(dmic_codec_dev)) {
+ pr_err("%s: dmic-codec device registration failed\n", __func__);
+ return PTR_ERR(dmic_codec_dev);
+ }
+
+ ret = platform_driver_register(&omap_abe_driver);
+ if (ret) {
+ pr_err("%s: platform driver registration failed\n", __func__);
+ platform_device_unregister(dmic_codec_dev);
+ }
+
+ return ret;
+}
+module_init(omap_abe_init);
+
+static void __exit omap_abe_exit(void)
+{
+ platform_driver_unregister(&omap_abe_driver);
+ platform_device_unregister(dmic_codec_dev);
+}
+module_exit(omap_abe_exit);
MODULE_AUTHOR("Misael Lopez Cruz <misael.lopez@ti.com>");
MODULE_DESCRIPTION("ALSA SoC for OMAP boards with ABE and twl6040 codec");
#include <linux/err.h>
#include <linux/io.h>
#include <linux/irq.h>
-#include <linux/clk.h>
#include <linux/slab.h>
#include <linux/pm_runtime.h>
#include <linux/of_device.h>
unsigned long phys_base;
void __iomem *io_base;
int irq;
- struct clk *pdmclk;
struct mutex mutex;
struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai);
int ret;
- clk_prepare_enable(mcpdm->pdmclk);
pm_runtime_enable(mcpdm->dev);
/* Disable lines while request is ongoing */
pm_runtime_get_sync(mcpdm->dev);
omap_mcpdm_write(mcpdm, MCPDM_REG_CTRL, 0x00);
- ret = devm_request_irq(mcpdm->dev, mcpdm->irq, omap_mcpdm_irq_handler,
- 0, "McPDM", (void *)mcpdm);
+ ret = request_irq(mcpdm->irq, omap_mcpdm_irq_handler, 0, "McPDM",
+ (void *)mcpdm);
pm_runtime_put_sync(mcpdm->dev);
{
struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai);
+ free_irq(mcpdm->irq, (void *)mcpdm);
pm_runtime_disable(mcpdm->dev);
- clk_disable_unprepare(mcpdm->pdmclk);
return 0;
}
mcpdm->pm_active_count++;
}
- clk_disable_unprepare(mcpdm->pdmclk);
-
return 0;
}
{
struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai);
- clk_prepare_enable(mcpdm->pdmclk);
-
if (mcpdm->pm_active_count) {
while (mcpdm->pm_active_count--)
pm_runtime_get_sync(mcpdm->dev);
mcpdm->dev = &pdev->dev;
- mcpdm->pdmclk = devm_clk_get(&pdev->dev, "pdmclk");
- if (IS_ERR(mcpdm->pdmclk)) {
- if (PTR_ERR(mcpdm->pdmclk) == -EPROBE_DEFER)
- return -EPROBE_DEFER;
- dev_warn(&pdev->dev, "Error getting pdmclk (%ld)!\n",
- PTR_ERR(mcpdm->pdmclk));
- mcpdm->pdmclk = NULL;
- }
-
ret = devm_snd_soc_register_component(&pdev->dev,
&omap_mcpdm_component,
&omap_mcpdm_dai, 1);
static int s3c24xx_uda134x_startup(struct snd_pcm_substream *substream)
{
- int ret = 0;
+ struct snd_soc_pcm_runtime *rtd = substream->private_data;
+ struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
#ifdef ENFORCE_RATES
struct snd_pcm_runtime *runtime = substream->runtime;
#endif
+ int ret = 0;
mutex_lock(&clk_lock);
pr_debug("%s %d\n", __func__, clk_users);
printk(KERN_ERR "%s cannot get xtal\n", __func__);
ret = PTR_ERR(xtal);
} else {
- pclk = clk_get(&s3c24xx_uda134x_snd_device->dev,
- "pclk");
+ pclk = clk_get(cpu_dai->dev, "iis");
if (IS_ERR(pclk)) {
printk(KERN_ERR "%s cannot get pclk\n",
__func__);
ifscr = 0;
fsrate = 0;
if (fin != fout) {
+ u64 n;
+
ifscr = 1;
- fsrate = 0x0400000 / fout * fin;
+ n = (u64)0x0400000 * fin;
+ do_div(n, fout);
+ fsrate = n;
}
/*
dpcm_be_disconnect(fe, stream);
fe->dpcm[stream].runtime = NULL;
- goto fe_err;
+ goto path_err;
}
dpcm_clear_pending_state(fe, stream);
return 0;
+path_err:
+ dpcm_path_put(&list);
fe_err:
if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->shutdown)
fe->dai_link->compr_ops->shutdown(cstream);
if (!rtd->platform) {
dev_err(card->dev, "ASoC: platform %s not registered\n",
dai_link->platform_name);
- return -EPROBE_DEFER;
+ goto _err_defer;
}
soc_add_pcm_runtime(card, rtd);
/* remove auxiliary devices */
soc_remove_aux_devices(card);
+ snd_soc_dapm_free(&card->dapm);
soc_cleanup_card_debugfs(card);
/* remove the card */
if (card->remove)
card->remove(card);
- snd_soc_dapm_free(&card->dapm);
-
snd_card_free(card->snd_card);
return 0;
case snd_soc_dapm_switch:
case snd_soc_dapm_mixer:
case snd_soc_dapm_pga:
+ case snd_soc_dapm_out_drv:
wname_in_long_name = true;
kcname_in_long_name = true;
break;
* @custom_stop_condition: (optional) a function meant to stop the widget graph
* walk based on custom logic.
*
- * Queries DAPM graph as to whether an valid audio stream path exists for
+ * Queries DAPM graph as to whether a valid audio stream path exists for
* the initial stream specified by name. This takes into account
* current mixer and mux kcontrol settings. Creates list of valid widgets.
*
return w->new_power;
}
-/* Generic check to see if a widget should be powered.
- */
+/* Generic check to see if a widget should be powered. */
static int dapm_generic_check_power(struct snd_soc_dapm_widget *w)
{
int in, out;
struct snd_soc_dapm_context *d = data;
int ret;
- /* If we're off and we're not supposed to be go into STANDBY */
+ /* If we're off and we're not supposed to go into STANDBY */
if (d->bias_level == SND_SOC_BIAS_OFF &&
d->target_bias_level != SND_SOC_BIAS_OFF) {
if (d->dev)
* A complete path is a route that has valid endpoints i.e.:-
*
* o DAC to output pin.
- * o Input Pin to ADC.
+ * o Input pin to ADC.
* o Input pin to Output pin (bypass, sidetone)
* o DAC to ADC (loopback).
*/
* soc_dapm_connect_path() - Connects or disconnects a path
* @path: The path to update
* @connect: The new connect state of the path. True if the path is connected,
- * false if it is disconneted.
+ * false if it is disconnected.
* @reason: The reason why the path changed (for debugging only)
*/
static void soc_dapm_connect_path(struct snd_soc_dapm_path *path,
if (w->dapm != dapm)
continue;
- /* only display widgets that burnm power */
+ /* only display widgets that burn power */
switch (w->id) {
case snd_soc_dapm_hp:
case snd_soc_dapm_mic:
switch (w->id) {
case snd_soc_dapm_input:
- /* On a fully routed card a input is never a source */
+ /* On a fully routed card an input is never a source */
if (w->dapm->card->fully_routed)
return;
ep = SND_SOC_DAPM_EP_SOURCE;
}
mutex_unlock(&card->dapm_mutex);
+ if (ret)
+ return ret;
+
if (invert)
ucontrol->value.integer.value[0] = max - val;
else
if (e->shift_l != e->shift_r) {
if (item[1] > e->items)
return -EINVAL;
- val |= snd_soc_enum_item_to_val(e, item[1]) << e->shift_l;
+ val |= snd_soc_enum_item_to_val(e, item[1]) << e->shift_r;
mask |= e->mask << e->shift_r;
}
w->endpoints[dir] = -1;
}
- /* machine layer set ups unconnected pins and insertions */
+ /* machine layer sets up unconnected pins and insertions */
w->connected = 1;
return w;
}
const struct snd_soc_pcm_stream *config = w->params + w->params_select;
struct snd_pcm_substream substream;
struct snd_pcm_hw_params *params = NULL;
+ struct snd_pcm_runtime *runtime = NULL;
u64 fmt;
int ret;
memset(&substream, 0, sizeof(substream));
+ /* Allocate a dummy snd_pcm_runtime for startup() and other ops() */
+ runtime = kzalloc(sizeof(*runtime), GFP_KERNEL);
+ if (!runtime) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ substream.runtime = runtime;
+
switch (event) {
case SND_SOC_DAPM_PRE_PMU:
substream.stream = SNDRV_PCM_STREAM_CAPTURE;
}
out:
+ kfree(runtime);
kfree(params);
return ret;
}
item = snd_soc_enum_val_to_item(e, val);
ucontrol->value.enumerated.item[0] = item;
if (e->shift_l != e->shift_r) {
- val = (reg_val >> e->shift_l) & e->mask;
+ val = (reg_val >> e->shift_r) & e->mask;
item = snd_soc_enum_val_to_item(e, val);
ucontrol->value.enumerated.item[1] = item;
}
err = line6_pcm_acquire(line6pcm, LINE6_STREAM_IMPULSE);
if (err < 0) {
line6pcm->impulse_volume = 0;
- line6_pcm_release(line6pcm, LINE6_STREAM_IMPULSE);
return err;
}
} else {
spin_lock_irqsave(&pstr->lock, flags);
clear_bit(type, &pstr->running);
if (!pstr->running) {
+ spin_unlock_irqrestore(&pstr->lock, flags);
line6_unlink_audio_urbs(line6pcm, pstr);
+ spin_lock_irqsave(&pstr->lock, flags);
if (direction == SNDRV_PCM_STREAM_CAPTURE) {
line6pcm->prev_fbuf = NULL;
line6pcm->prev_fsize = 0;
static ssize_t serial_number_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
- struct usb_interface *interface = to_usb_interface(dev);
- struct usb_line6_pod *pod = usb_get_intfdata(interface);
+ struct snd_card *card = dev_to_snd_card(dev);
+ struct usb_line6_pod *pod = card->private_data;
return sprintf(buf, "%u\n", pod->serial_number);
}
static ssize_t firmware_version_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
- struct usb_interface *interface = to_usb_interface(dev);
- struct usb_line6_pod *pod = usb_get_intfdata(interface);
+ struct snd_card *card = dev_to_snd_card(dev);
+ struct usb_line6_pod *pod = card->private_data;
return sprintf(buf, "%d.%02d\n", pod->firmware_version / 100,
pod->firmware_version % 100);
static ssize_t device_id_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
- struct usb_interface *interface = to_usb_interface(dev);
- struct usb_line6_pod *pod = usb_get_intfdata(interface);
+ struct snd_card *card = dev_to_snd_card(dev);
+ struct usb_line6_pod *pod = card->private_data;
return sprintf(buf, "%d\n", pod->device_id);
}
{
/* devices which do not support reading the sample rate. */
switch (chip->usb_id) {
+ case USB_ID(0x041E, 0x4080): /* Creative Live Cam VF0610 */
case USB_ID(0x045E, 0x075D): /* MS Lifecam Cinema */
case USB_ID(0x045E, 0x076D): /* MS Lifecam HD-5000 */
case USB_ID(0x045E, 0x076E): /* MS Lifecam HD-5001 */
case USB_ID(0x047F, 0xAA05): /* Plantronics DA45 */
case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */
case USB_ID(0x0556, 0x0014): /* Phoenix Audio TMX320VC */
+ case USB_ID(0x05A3, 0x9420): /* ELP HD USB Camera */
case USB_ID(0x074D, 0x3553): /* Outlaw RR2150 (Micronas UAC3553B) */
+ case USB_ID(0x1901, 0x0191): /* GE B850V3 CP2114 audio interface */
case USB_ID(0x1de7, 0x0013): /* Phoenix Audio MT202exe */
case USB_ID(0x1de7, 0x0014): /* Phoenix Audio TMX320 */
case USB_ID(0x1de7, 0x0114): /* Phoenix Audio MT202pcs */
/* Supported VGICv3 address types */
#define KVM_VGIC_V3_ADDR_TYPE_DIST 2
#define KVM_VGIC_V3_ADDR_TYPE_REDIST 3
+#define KVM_VGIC_ITS_ADDR_TYPE 4
#define KVM_VGIC_V3_DIST_SIZE SZ_64K
#define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K)
+#define KVM_VGIC_V3_ITS_SIZE (2 * SZ_64K)
#define KVM_ARM_VCPU_POWER_OFF 0 /* CPU is started in OFF state */
#define KVM_ARM_VCPU_EL1_32BIT 1 /* CPU running a 32bit VM */
__u64 fac_list[256];
};
+#define KVM_S390_VM_CPU_PROCESSOR_FEAT 2
+#define KVM_S390_VM_CPU_MACHINE_FEAT 3
+
+#define KVM_S390_VM_CPU_FEAT_NR_BITS 1024
+#define KVM_S390_VM_CPU_FEAT_ESOP 0
+#define KVM_S390_VM_CPU_FEAT_SIEF2 1
+#define KVM_S390_VM_CPU_FEAT_64BSCAO 2
+#define KVM_S390_VM_CPU_FEAT_SIIF 3
+#define KVM_S390_VM_CPU_FEAT_GPERE 4
+#define KVM_S390_VM_CPU_FEAT_GSLS 5
+#define KVM_S390_VM_CPU_FEAT_IB 6
+#define KVM_S390_VM_CPU_FEAT_CEI 7
+#define KVM_S390_VM_CPU_FEAT_IBS 8
+#define KVM_S390_VM_CPU_FEAT_SKEY 9
+#define KVM_S390_VM_CPU_FEAT_CMMA 10
+#define KVM_S390_VM_CPU_FEAT_PFMFI 11
+#define KVM_S390_VM_CPU_FEAT_SIGPIF 12
+struct kvm_s390_vm_cpu_feat {
+ __u64 feat[16];
+};
+
+#define KVM_S390_VM_CPU_PROCESSOR_SUBFUNC 4
+#define KVM_S390_VM_CPU_MACHINE_SUBFUNC 5
+/* for "test bit" instructions MSB 0 bit ordering, for "query" raw blocks */
+struct kvm_s390_vm_cpu_subfunc {
+ __u8 plo[32]; /* always */
+ __u8 ptff[16]; /* with TOD-clock steering */
+ __u8 kmac[16]; /* with MSA */
+ __u8 kmc[16]; /* with MSA */
+ __u8 km[16]; /* with MSA */
+ __u8 kimd[16]; /* with MSA */
+ __u8 klmd[16]; /* with MSA */
+ __u8 pckmo[16]; /* with MSA3 */
+ __u8 kmctr[16]; /* with MSA4 */
+ __u8 kmf[16]; /* with MSA4 */
+ __u8 kmo[16]; /* with MSA4 */
+ __u8 pcc[16]; /* with MSA4 */
+ __u8 ppno[16]; /* with MSA5 */
+ __u8 reserved[1824];
+};
+
/* kvm attributes for crypto */
#define KVM_S390_VM_CRYPTO_ENABLE_AES_KW 0
#define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW 1
exit_code_ipa0(0xB2, 0x4c, "TAR"), \
exit_code_ipa0(0xB2, 0x50, "CSP"), \
exit_code_ipa0(0xB2, 0x54, "MVPG"), \
+ exit_code_ipa0(0xB2, 0x56, "STHYI"), \
exit_code_ipa0(0xB2, 0x58, "BSG"), \
exit_code_ipa0(0xB2, 0x5a, "BSA"), \
exit_code_ipa0(0xB2, 0x5f, "CHSC"), \
#define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */
#define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */
#define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */
-#define X86_FEATURE_PCOMMIT ( 9*32+22) /* PCOMMIT instruction */
#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */
#define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */
#define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */
#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
-#define X86_BUG_NULL_SEG X86_BUG(9) /* Nulling a selector preserves the base */
-#define X86_BUG_SWAPGS_FENCE X86_BUG(10) /* SWAPGS without input dep on GS */
-
-
#ifdef CONFIG_X86_32
/*
* 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional
*/
#define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
#endif
-
+#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */
+#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */
+#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */
#endif /* _ASM_X86_CPUFEATURES_H */
#define DISABLED_MASK14 0
#define DISABLED_MASK15 0
#define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE)
+#define DISABLED_MASK17 0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
#endif /* _ASM_X86_DISABLED_FEATURES_H */
#define REQUIRED_MASK14 0
#define REQUIRED_MASK15 0
#define REQUIRED_MASK16 0
+#define REQUIRED_MASK17 0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
#endif /* _ASM_X86_REQUIRED_FEATURES_H */
#define EXIT_REASON_PML_FULL 62
#define EXIT_REASON_XSAVES 63
#define EXIT_REASON_XRSTORS 64
-#define EXIT_REASON_PCOMMIT 65
#define VMX_EXIT_REASONS \
{ EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \
{ EXIT_REASON_INVVPID, "INVVPID" }, \
{ EXIT_REASON_INVPCID, "INVPCID" }, \
{ EXIT_REASON_XSAVES, "XSAVES" }, \
- { EXIT_REASON_XRSTORS, "XRSTORS" }, \
- { EXIT_REASON_PCOMMIT, "PCOMMIT" }
+ { EXIT_REASON_XRSTORS, "XRSTORS" }
#define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1
#define VMX_ABORT_LOAD_HOST_MSR_FAIL 4
/*
- * gpio-hammer - example swiss army knife to shake GPIO lines on a system
+ * gpio-event-mon - monitor GPIO line events from userspace
*
* Copyright (C) 2016 Linus Walleij
*
int notrigger = 0;
char *dummy;
- struct iio_channel_info *channels;
+ struct iio_channel_info *channels = NULL;
register_cleanup();
if (notrigger) {
printf("trigger-less mode selected\n");
- } if (trig_num >= 0) {
+ } else if (trig_num >= 0) {
char *trig_dev_name;
ret = asprintf(&trig_dev_name, "%strigger%d", iio_dir, trig_num);
if (ret < 0) {
int strtobool(const char *s, bool *res);
-#ifdef __GLIBC__
+/*
+ * glibc based builds needs the extern while uClibc doesn't.
+ * However uClibc headers also define __GLIBC__ hence the hack below
+ */
+#if defined(__GLIBC__) && !defined(__UCLIBC__)
extern size_t strlcpy(char *dest, const char *src, size_t size);
#endif
BPF_MAP_TYPE_PERCPU_HASH,
BPF_MAP_TYPE_PERCPU_ARRAY,
BPF_MAP_TYPE_STACK_TRACE,
+ BPF_MAP_TYPE_CGROUP_ARRAY,
};
enum bpf_prog_type {
BPF_PROG_TYPE_SCHED_CLS,
BPF_PROG_TYPE_SCHED_ACT,
BPF_PROG_TYPE_TRACEPOINT,
+ BPF_PROG_TYPE_XDP,
};
#define BPF_PSEUDO_MAP_FD 1
*/
BPF_FUNC_skb_get_tunnel_opt,
BPF_FUNC_skb_set_tunnel_opt,
+
+ /**
+ * bpf_skb_change_proto(skb, proto, flags)
+ * Change protocol of the skb. Currently supported is
+ * v4 -> v6, v6 -> v4 transitions. The helper will also
+ * resize the skb. eBPF program is expected to fill the
+ * new headers via skb_store_bytes and lX_csum_replace.
+ * @skb: pointer to skb
+ * @proto: new skb->protocol type
+ * @flags: reserved
+ * Return: 0 on success or negative error
+ */
+ BPF_FUNC_skb_change_proto,
+
+ /**
+ * bpf_skb_change_type(skb, type)
+ * Change packet type of skb.
+ * @skb: pointer to skb
+ * @type: new skb->pkt_type type
+ * Return: 0 on success or negative error
+ */
+ BPF_FUNC_skb_change_type,
+
+ /**
+ * bpf_skb_in_cgroup(skb, map, index) - Check cgroup2 membership of skb
+ * @skb: pointer to skb
+ * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type
+ * @index: index of the cgroup in the bpf_map
+ * Return:
+ * == 0 skb failed the cgroup2 descendant test
+ * == 1 skb succeeded the cgroup2 descendant test
+ * < 0 error
+ */
+ BPF_FUNC_skb_in_cgroup,
+
+ /**
+ * bpf_get_hash_recalc(skb)
+ * Retrieve and possibly recalculate skb->hash.
+ * @skb: pointer to skb
+ * Return: hash
+ */
+ BPF_FUNC_get_hash_recalc,
+
+ /**
+ * u64 bpf_get_current_task(void)
+ * Returns current task_struct
+ * Return: current
+ */
+ BPF_FUNC_get_current_task,
+
+ /**
+ * bpf_probe_write_user(void *dst, void *src, int len)
+ * safely attempt to write to a location
+ * @dst: destination address in userspace
+ * @src: source address on stack
+ * @len: number of bytes to copy
+ * Return: 0 on success or negative error
+ */
+ BPF_FUNC_probe_write_user,
+
__BPF_FUNC_MAX_ID,
};
#define BPF_F_ZERO_CSUM_TX (1ULL << 1)
#define BPF_F_DONT_FRAGMENT (1ULL << 2)
-/* BPF_FUNC_perf_event_output flags. */
+/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */
#define BPF_F_INDEX_MASK 0xffffffffULL
#define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK
+/* BPF_FUNC_perf_event_output for sk_buff input context. */
+#define BPF_F_CTXLEN_MASK (0xfffffULL << 32)
/* user accessible mirror of in-kernel sk_buff.
* new fields can only be added to the end of this structure
__u32 tunnel_label;
};
+/* User return codes for XDP prog type.
+ * A valid XDP program must return one of these defined values. All other
+ * return codes are reserved for future use. Unknown return codes will result
+ * in packet drop.
+ */
+enum xdp_action {
+ XDP_ABORTED = 0,
+ XDP_DROP,
+ XDP_PASS,
+ XDP_TX,
+};
+
+/* user accessible metadata for XDP packet hook
+ * new fields must be added to the end of this structure
+ */
+struct xdp_md {
+ __u32 data;
+ __u32 data_end;
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
}
}
+ /* If we exit via err(), this kills all the threads, restores tty. */
+ atexit(cleanup_devices);
+
/* We always have a console device, and it's always device 1. */
setup_console();
/* Ensure that we terminate if a device-servicing child dies. */
signal(SIGCHLD, kill_launcher);
- /* If we exit via err(), this kills all the threads, restores tty. */
- atexit(cleanup_devices);
-
/* If requested, chroot to a directory */
if (chroot_path) {
if (chroot(chroot_path) != 0)
'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.)
'$vars' and '$params' special arguments are also available for NAME, '$vars' is expanded to the local variables (including function parameters) which can access at given probe point. '$params' is expanded to only the function parameters.
-'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type.
+'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. Currently, basic types (u8/u16/u32/u64/s8/s16/s32/s64), signedness casting (u/s), "string" and bitfield are supported. (see TYPES for detail)
On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid.
+TYPES
+-----
+Basic types (u8/u16/u32/u64/s8/s16/s32/s64) are integer types. Prefix 's' and 'u' means those types are signed and unsigned respectively. Traced arguments are shown in decimal (signed) or hex (unsigned). You can also use 's' or 'u' to specify only signedness and leave its size auto-detected by perf probe.
+String type is a special type, which fetches a "null-terminated" string from kernel space. This means it will fail and store NULL if the string container has been paged out. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type.
+Bitfield is another special type, which takes 3 parameters, bit-width, bit-offset, and container-size (usually 32). The syntax is;
+
+ b<bit-width>@<bit-offset>/<container-size>
+
LINE SYNTAX
-----------
Line range is described by following syntax.
--fields::
Comma separated list of fields to print. Options are:
comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
- srcline, period, iregs, brstack, brstacksym, flags.
- Field list can be prepended with the type, trace, sw or hw,
+ srcline, period, iregs, brstack, brstacksym, flags, bpf-output,
+ callindent. Field list can be prepended with the type, trace, sw or hw,
to indicate to which event type the field list applies.
e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace
#endif
#if defined(_CALL_ELF) && _CALL_ELF == 2
-bool arch__prefers_symtab(void)
-{
- return true;
-}
#ifdef HAVE_LIBELF_SUPPORT
void arch__sym_update(struct symbol *s, GElf_Sym *sym)
tev->point.offset += lep_offset;
}
}
+
+#ifdef HAVE_LIBELF_SUPPORT
+void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
+ int ntevs)
+{
+ struct probe_trace_event *tev;
+ struct map *map;
+ struct symbol *sym = NULL;
+ struct rb_node *tmp;
+ int i = 0;
+
+ map = get_target_map(pev->target, pev->uprobes);
+ if (!map || map__load(map, NULL) < 0)
+ return;
+
+ for (i = 0; i < ntevs; i++) {
+ tev = &pev->tevs[i];
+ map__for_each_symbol(map, sym, tmp) {
+ if (map->unmap_ip(map, sym->start) == tev->point.address)
+ arch__fix_tev_from_maps(pev, tev, map, sym);
+ }
+ }
+}
+#endif /* HAVE_LIBELF_SUPPORT */
+
#endif
struct intel_pt_recording *ptr =
container_of(itr, struct intel_pt_recording, itr);
struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu;
- bool have_timing_info;
+ bool have_timing_info, need_immediate = false;
struct perf_evsel *evsel, *intel_pt_evsel = NULL;
const struct cpu_map *cpus = evlist->cpus;
bool privileged = geteuid() == 0 || perf_event_paranoid() < 0;
ptr->have_sched_switch = 3;
} else {
opts->record_switch_events = true;
+ need_immediate = true;
if (cpu_wide)
ptr->have_sched_switch = 3;
else
tracking_evsel->attr.freq = 0;
tracking_evsel->attr.sample_period = 1;
+ if (need_immediate)
+ tracking_evsel->immediate = true;
+
/* In per-cpu case, always need the time of mmap events etc */
if (!cpu_map__empty(cpus)) {
perf_evsel__set_sample_bit(tracking_evsel, TIME);
if (mem->operation & MEM_OPERATION_LOAD)
perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true;
+ if (mem->operation & MEM_OPERATION_STORE)
+ perf_mem_events[PERF_MEM_EVENTS__STORE].record = true;
+
if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record)
rec_argv[i++] = "-W";
if (!no_callchain) {
bool use_callchain = false;
+ bool not_pipe = false;
evlist__for_each_entry(session->evlist, evsel) {
+ not_pipe = true;
if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
use_callchain = true;
break;
}
}
- if (!use_callchain)
+ if (not_pipe && !use_callchain)
symbol_conf.use_callchain = false;
}
snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path());
scripts_dir = opendir(scripts_path);
- if (!scripts_dir)
- return -1;
+ if (!scripts_dir) {
+ fprintf(stdout,
+ "open(%s) failed.\n"
+ "Check \"PERF_EXEC_PATH\" env to set scripts dir.\n",
+ scripts_path);
+ exit(-1);
+ }
for_each_lang(scripts_path, scripts_dir, lang_dirent) {
snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
"Valid types: hw,sw,trace,raw. "
"Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
"addr,symoff,period,iregs,brstack,brstacksym,flags,"
- "callindent", parse_output_fields),
+ "bpf-output,callindent", parse_output_fields),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]",
return 0;
}
-static void read_counters(bool close_counters)
+static void read_counters(void)
{
struct perf_evsel *counter;
if (perf_stat_process_counter(&stat_config, counter))
pr_warning("failed to process counter %s\n", counter->name);
-
- if (close_counters) {
- perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
- thread_map__nr(evsel_list->threads));
- }
}
}
{
struct timespec ts, rs;
- read_counters(false);
+ read_counters();
clock_gettime(CLOCK_MONOTONIC, &ts);
diff_timespec(&rs, &ts, &ref_time);
perf_evlist__enable(evsel_list);
}
+static void disable_counters(void)
+{
+ /*
+ * If we don't have tracee (attaching to task or cpu), counters may
+ * still be running. To get accurate group ratios, we must stop groups
+ * from counting before reading their constituent counters.
+ */
+ if (!target__none(&target))
+ perf_evlist__disable(evsel_list);
+}
+
static volatile int workload_exec_errno;
/*
}
}
+ disable_counters();
+
t1 = rdclock();
update_stats(&walltime_nsecs_stats, t1 - t0);
- read_counters(true);
+ /*
+ * Closing a group leader splits the group, and as we only disable
+ * group leaders, results in remaining events becoming enabled. To
+ * avoid arbitrary skew, we must read all counters before closing any
+ * group leaders.
+ */
+ read_counters();
+ perf_evlist__close(evsel_list);
return WEXITSTATUS(status);
}
u8 op, result, type = (config >> 0) & 0xff;
const char *err = "unknown-ext-hardware-cache-type";
- if (type > PERF_COUNT_HW_CACHE_MAX)
+ if (type >= PERF_COUNT_HW_CACHE_MAX)
goto out_err;
op = (config >> 8) & 0xff;
err = "unknown-ext-hardware-cache-op";
- if (op > PERF_COUNT_HW_CACHE_OP_MAX)
+ if (op >= PERF_COUNT_HW_CACHE_OP_MAX)
goto out_err;
result = (config >> 16) & 0xff;
err = "unknown-ext-hardware-cache-result";
- if (result > PERF_COUNT_HW_CACHE_RESULT_MAX)
+ if (result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
goto out_err;
err = "invalid-cache";
bool have_calc_cyc_to_tsc;
int exec_mode;
unsigned int insn_bytes;
- uint64_t sign_bit;
- uint64_t sign_bits;
uint64_t period;
enum intel_pt_period_type period_type;
uint64_t tot_insn_cnt;
decoder->data = params->data;
decoder->return_compression = params->return_compression;
- decoder->sign_bit = (uint64_t)1 << 47;
- decoder->sign_bits = ~(((uint64_t)1 << 48) - 1);
-
decoder->period = params->period;
decoder->period_type = params->period_type;
return 0;
}
-static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder,
- const struct intel_pt_pkt *packet,
+static uint64_t intel_pt_calc_ip(const struct intel_pt_pkt *packet,
uint64_t last_ip)
{
uint64_t ip;
switch (packet->count) {
- case 2:
+ case 1:
ip = (last_ip & (uint64_t)0xffffffffffff0000ULL) |
packet->payload;
break;
- case 4:
+ case 2:
ip = (last_ip & (uint64_t)0xffffffff00000000ULL) |
packet->payload;
break;
+ case 3:
+ ip = packet->payload;
+ /* Sign-extend 6-byte ip */
+ if (ip & (uint64_t)0x800000000000ULL)
+ ip |= (uint64_t)0xffff000000000000ULL;
+ break;
+ case 4:
+ ip = (last_ip & (uint64_t)0xffff000000000000ULL) |
+ packet->payload;
+ break;
case 6:
ip = packet->payload;
break;
return 0;
}
- if (ip & decoder->sign_bit)
- return ip | decoder->sign_bits;
-
return ip;
}
static inline void intel_pt_set_last_ip(struct intel_pt_decoder *decoder)
{
- decoder->last_ip = intel_pt_calc_ip(decoder, &decoder->packet,
- decoder->last_ip);
+ decoder->last_ip = intel_pt_calc_ip(&decoder->packet, decoder->last_ip);
}
static inline void intel_pt_set_ip(struct intel_pt_decoder *decoder)
}
}
+static inline bool intel_pt_have_ip(struct intel_pt_decoder *decoder)
+{
+ return decoder->last_ip || decoder->packet.count == 0 ||
+ decoder->packet.count == 3 || decoder->packet.count == 6;
+}
+
/* Walk PSB+ packets to get in sync. */
static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
{
case INTEL_PT_FUP:
decoder->pge = true;
- if (decoder->last_ip || decoder->packet.count == 6 ||
- decoder->packet.count == 0) {
+ if (intel_pt_have_ip(decoder)) {
uint64_t current_ip = decoder->ip;
intel_pt_set_ip(decoder);
case INTEL_PT_TIP_PGE:
case INTEL_PT_TIP:
decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD;
- if (decoder->last_ip || decoder->packet.count == 6 ||
- decoder->packet.count == 0)
+ if (intel_pt_have_ip(decoder))
intel_pt_set_ip(decoder);
if (decoder->ip)
return 0;
case INTEL_PT_FUP:
if (decoder->overflow) {
- if (decoder->last_ip ||
- decoder->packet.count == 6 ||
- decoder->packet.count == 0)
+ if (intel_pt_have_ip(decoder))
intel_pt_set_ip(decoder);
if (decoder->ip)
return 0;
const unsigned char *buf, size_t len,
struct intel_pt_pkt *packet)
{
- switch (byte >> 5) {
+ int ip_len;
+
+ packet->count = byte >> 5;
+
+ switch (packet->count) {
case 0:
- packet->count = 0;
+ ip_len = 0;
break;
case 1:
if (len < 3)
return INTEL_PT_NEED_MORE_BYTES;
- packet->count = 2;
+ ip_len = 2;
packet->payload = le16_to_cpu(*(uint16_t *)(buf + 1));
break;
case 2:
if (len < 5)
return INTEL_PT_NEED_MORE_BYTES;
- packet->count = 4;
+ ip_len = 4;
packet->payload = le32_to_cpu(*(uint32_t *)(buf + 1));
break;
case 3:
- case 6:
+ case 4:
if (len < 7)
return INTEL_PT_NEED_MORE_BYTES;
- packet->count = 6;
+ ip_len = 6;
memcpy_le64(&packet->payload, buf + 1, 6);
break;
+ case 6:
+ if (len < 9)
+ return INTEL_PT_NEED_MORE_BYTES;
+ ip_len = 8;
+ packet->payload = le64_to_cpu(*(uint64_t *)(buf + 1));
+ break;
default:
return INTEL_PT_BAD_PACKET;
}
packet->type = type;
- return packet->count + 1;
+ return ip_len + 1;
}
static int intel_pt_get_mode(const unsigned char *buf, size_t len,
+#include <sys/sysmacros.h>
#include <sys/types.h>
#include <stdio.h>
#include <stdlib.h>
module = "kernel";
for (pos = maps__first(maps); pos; pos = map__next(pos)) {
+ /* short_name is "[module]" */
if (strncmp(pos->dso->short_name + 1, module,
- pos->dso->short_name_len - 2) == 0) {
+ pos->dso->short_name_len - 2) == 0 &&
+ module[pos->dso->short_name_len - 2] == '\0') {
return pos;
}
}
return NULL;
}
-static struct map *get_target_map(const char *target, bool user)
+struct map *get_target_map(const char *target, bool user)
{
/* Init maps of given executable or kernel */
if (user)
if (uprobes)
address = sym->start;
else
- address = map->unmap_ip(map, sym->start);
+ address = map->unmap_ip(map, sym->start) - map->reloc;
break;
}
if (!address) {
return ret;
}
-/* Post processing the probe events */
-static int post_process_probe_trace_events(struct probe_trace_event *tevs,
- int ntevs, const char *module,
- bool uprobe)
+static int
+post_process_kernel_probe_trace_events(struct probe_trace_event *tevs,
+ int ntevs)
{
struct ref_reloc_sym *reloc_sym;
char *tmp;
int i, skipped = 0;
- if (uprobe)
- return add_exec_to_probe_trace_events(tevs, ntevs, module);
-
- /* Note that currently ref_reloc_sym based probe is not for drivers */
- if (module)
- return add_module_to_probe_trace_events(tevs, ntevs, module);
-
reloc_sym = kernel_get_ref_reloc_sym();
if (!reloc_sym) {
pr_warning("Relocated base symbol is not found!\n");
return skipped;
}
+void __weak
+arch__post_process_probe_trace_events(struct perf_probe_event *pev __maybe_unused,
+ int ntevs __maybe_unused)
+{
+}
+
+/* Post processing the probe events */
+static int post_process_probe_trace_events(struct perf_probe_event *pev,
+ struct probe_trace_event *tevs,
+ int ntevs, const char *module,
+ bool uprobe)
+{
+ int ret;
+
+ if (uprobe)
+ ret = add_exec_to_probe_trace_events(tevs, ntevs, module);
+ else if (module)
+ /* Currently ref_reloc_sym based probe is not for drivers */
+ ret = add_module_to_probe_trace_events(tevs, ntevs, module);
+ else
+ ret = post_process_kernel_probe_trace_events(tevs, ntevs);
+
+ if (ret >= 0)
+ arch__post_process_probe_trace_events(pev, ntevs);
+
+ return ret;
+}
+
/* Try to find perf_probe_event with debuginfo */
static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
struct probe_trace_event **tevs)
if (ntevs > 0) { /* Succeeded to find trace events */
pr_debug("Found %d probe_trace_events.\n", ntevs);
- ret = post_process_probe_trace_events(*tevs, ntevs,
+ ret = post_process_probe_trace_events(pev, *tevs, ntevs,
pev->target, pev->uprobes);
if (ret < 0 || ret == ntevs) {
clear_probe_trace_events(*tevs, ntevs);
return err;
}
-bool __weak arch__prefers_symtab(void) { return false; }
-
/* Concatinate two arrays */
static void *memcat(void *a, size_t sz_a, void *b, size_t sz_b)
{
if (ret > 0 || pev->sdt) /* SDT can be found only in the cache */
return ret == 0 ? -ENOENT : ret; /* Found in probe cache */
- if (arch__prefers_symtab() && !perf_probe_event_need_dwarf(pev)) {
- ret = find_probe_trace_events_from_map(pev, tevs);
- if (ret > 0)
- return ret; /* Found in symbol table */
- }
-
/* Convert perf_probe_event with debuginfo */
ret = try_to_find_probe_trace_events(pev, tevs);
if (ret != 0)
int show_available_vars(struct perf_probe_event *pevs, int npevs,
struct strfilter *filter);
int show_available_funcs(const char *module, struct strfilter *filter, bool user);
-bool arch__prefers_symtab(void);
void arch__fix_tev_from_maps(struct perf_probe_event *pev,
struct probe_trace_event *tev, struct map *map,
struct symbol *sym);
int copy_to_probe_trace_arg(struct probe_trace_arg *tvar,
struct perf_probe_arg *pvar);
+struct map *get_target_map(const char *target, bool user);
+
+void arch__post_process_probe_trace_events(struct perf_probe_event *pev,
+ int ntevs);
+
#endif /*_PROBE_EVENT_H */
/* Get raw string list of current kprobe_events or uprobe_events */
struct strlist *probe_file__get_rawlist(int fd)
{
- int ret, idx;
+ int ret, idx, fddup;
FILE *fp;
char buf[MAX_CMDLEN];
char *p;
return NULL;
sl = strlist__new(NULL, NULL);
+ if (sl == NULL)
+ return NULL;
+
+ fddup = dup(fd);
+ if (fddup < 0)
+ goto out_free_sl;
+
+ fp = fdopen(fddup, "r");
+ if (!fp)
+ goto out_close_fddup;
- fp = fdopen(dup(fd), "r");
while (!feof(fp)) {
p = fgets(buf, MAX_CMDLEN, fp);
if (!p)
ret = strlist__add(sl, buf);
if (ret < 0) {
pr_debug("strlist__add failed (%d)\n", ret);
- strlist__delete(sl);
- return NULL;
+ goto out_close_fp;
}
}
fclose(fp);
return sl;
+
+out_close_fp:
+ fclose(fp);
+ goto out_free_sl;
+out_close_fddup:
+ close(fddup);
+out_free_sl:
+ strlist__delete(sl);
+ return NULL;
}
static struct strlist *__probe_file__get_namelist(int fd, bool include_group)
{
struct probe_cache_entry *entry = NULL;
char buf[MAX_CMDLEN], *p;
- int ret = 0;
+ int ret = 0, fddup;
FILE *fp;
- fp = fdopen(dup(pcache->fd), "r");
- if (!fp)
+ fddup = dup(pcache->fd);
+ if (fddup < 0)
+ return -errno;
+ fp = fdopen(fddup, "r");
+ if (!fp) {
+ close(fddup);
return -EINVAL;
+ }
while (!feof(fp)) {
if (!fgets(buf, MAX_CMDLEN, fp))
char sbuf[STRERR_BUFSIZE];
int bsize, boffs, total;
int ret;
+ char sign;
/* TODO: check all types */
- if (cast && strcmp(cast, "string") != 0) {
+ if (cast && strcmp(cast, "string") != 0 &&
+ strcmp(cast, "s") != 0 && strcmp(cast, "u") != 0) {
/* Non string type is OK */
+ /* and respect signedness cast */
tvar->type = strdup(cast);
return (tvar->type == NULL) ? -ENOMEM : 0;
}
return (tvar->type == NULL) ? -ENOMEM : 0;
}
+ if (cast && (strcmp(cast, "u") == 0))
+ sign = 'u';
+ else if (cast && (strcmp(cast, "s") == 0))
+ sign = 's';
+ else
+ sign = die_is_signed_type(&type) ? 's' : 'u';
+
ret = dwarf_bytesize(&type);
if (ret <= 0)
/* No size ... try to use default type */
dwarf_diename(&type), MAX_BASIC_TYPE_BITS);
ret = MAX_BASIC_TYPE_BITS;
}
- ret = snprintf(buf, 16, "%c%d",
- die_is_signed_type(&type) ? 's' : 'u', ret);
+ ret = snprintf(buf, 16, "%c%d", sign, ret);
formatted:
if (ret < 0 || ret >= 16) {
} else {
pevent_event_info(&seq, evsel->tp_format, &rec);
}
- return seq.buffer;
+ /*
+ * Trim the buffer, it starts at 4KB and we're not going to
+ * add anything more to this buffer.
+ */
+ return realloc(seq.buffer, seq.len + 1);
}
static int64_t
sec = syms_ss->symtab;
shdr = syms_ss->symshdr;
- if (elf_section_by_name(elf, &ehdr, &tshdr, ".text", NULL))
+ if (elf_section_by_name(runtime_ss->elf, &runtime_ss->ehdr, &tshdr,
+ ".text", NULL))
dso->text_offset = tshdr.sh_addr - tshdr.sh_offset;
if (runtime_ss->opdsec)
if (__report_module(&al, ip, ui))
return -1;
- e->ip = ip;
+ e->ip = al.addr;
e->map = al.map;
e->sym = al.sym;
thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
MAP__FUNCTION, ip, &al);
- e.ip = ip;
+ e.ip = al.addr;
e.map = al.map;
e.sym = al.sym;
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/platform_device.h>
#include <linux/dma-mapping.h>
+#include <linux/workqueue.h>
#include <linux/libnvdimm.h>
#include <linux/vmalloc.h>
#include <linux/device.h>
if (nfit_test->setup != nfit_test0_setup)
return 0;
+ flush_work(&acpi_desc->work);
nfit_test->setup_hotplug = 1;
nfit_test->setup(nfit_test);
-CFLAGS += -I. -g -Wall -D_LGPL_SOURCE
+CFLAGS += -I. -g -O2 -Wall -D_LGPL_SOURCE
LDFLAGS += -lpthread -lurcu
TARGETS = main
OFILES = main.o radix-tree.o linux.o test.o tag_check.o find_next_bit.o \
unsigned long i;
unsigned long min = index & ~((1UL << order) - 1);
unsigned long max = min + (1UL << order);
+ void **slot;
+ struct item *item2 = item_create(min);
RADIX_TREE(tree, GFP_KERNEL);
printf("Multiorder index %ld, order %d\n", index, order);
item_check_absent(&tree, i);
for (i = max; i < 2*max; i++)
item_check_absent(&tree, i);
+ for (i = min; i < max; i++)
+ assert(radix_tree_insert(&tree, i, item2) == -EEXIST);
+
+ slot = radix_tree_lookup_slot(&tree, index);
+ free(*slot);
+ radix_tree_replace_slot(slot, item2);
for (i = min; i < max; i++) {
- static void *entry = (void *)
- (0xA0 | RADIX_TREE_EXCEPTIONAL_ENTRY);
- assert(radix_tree_insert(&tree, i, entry) == -EEXIST);
+ struct item *item = item_lookup(&tree, i);
+ assert(item != 0);
+ assert(item->index == min);
}
- assert(item_delete(&tree, index) != 0);
+ assert(item_delete(&tree, min) != 0);
for (i = 0; i < 2*max; i++)
item_check_absent(&tree, i);
GIT_VERSION = $(shell git describe --always --long --dirty || echo "unknown")
-CFLAGS := -Wall -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) $(CFLAGS)
+CFLAGS := -std=gnu99 -Wall -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) $(CFLAGS)
export CFLAGS
DMA_NONE = 3,
};
+#define dma_alloc_coherent(d, s, hp, f) ({ \
+ void *__dma_alloc_coherent_p = kmalloc((s), (f)); \
+ *(hp) = (unsigned long)__dma_alloc_coherent_p; \
+ __dma_alloc_coherent_p; \
+})
+
+#define dma_free_coherent(d, s, p, h) kfree(p)
+
+#define dma_map_page(d, p, o, s, dir) (page_to_phys(p) + (o))
+
+#define dma_map_single(d, p, s, dir) (virt_to_phys(p))
+#define dma_mapping_error(...) (0)
+
+#define dma_unmap_single(...) do { } while (0)
+#define dma_unmap_page(...) do { } while (0)
+
#endif
#define PAGE_SIZE getpagesize()
#define PAGE_MASK (~(PAGE_SIZE-1))
+#define PAGE_ALIGN(x) ((x + PAGE_SIZE - 1) & PAGE_MASK)
+typedef unsigned long long phys_addr_t;
typedef unsigned long long dma_addr_t;
typedef size_t __kernel_size_t;
typedef unsigned int __wsum;
return p;
}
+static inline void *alloc_pages_exact(size_t s, gfp_t gfp)
+{
+ return kmalloc(s, gfp);
+}
+
static inline void kfree(void *p)
{
if (p >= __kfree_ignore_start && p < __kfree_ignore_end)
free(p);
}
+static inline void free_pages_exact(void *p, size_t s)
+{
+ kfree(p);
+}
+
static inline void *krealloc(void *p, size_t s, gfp_t gfp)
{
return realloc(p, s);
#define dev_err(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__)
#define dev_warn(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__)
+#define WARN_ON_ONCE(cond) ((cond) && fprintf (stderr, "WARNING\n"))
+
#define min(x, y) ({ \
typeof(x) _min1 = (x); \
typeof(y) _min2 = (y); \
#ifndef LINUX_SLAB_H
+#define GFP_KERNEL 0
+#define GFP_ATOMIC 0
+#define __GFP_NOWARN 0
+#define __GFP_ZERO 0
#endif
#include <linux/scatterlist.h>
#include <linux/kernel.h>
+struct device {
+ void *parent;
+};
+
struct virtio_device {
- void *dev;
+ struct device dev;
u64 features;
};
#define virtio_has_feature(dev, feature) \
(__virtio_test_bit((dev), feature))
+/**
+ * virtio_has_iommu_quirk - determine whether this device has the iommu quirk
+ * @vdev: the device
+ */
+static inline bool virtio_has_iommu_quirk(const struct virtio_device *vdev)
+{
+ /*
+ * Note the reverse polarity of the quirk feature (compared to most
+ * other features), this is for compatibility with legacy systems.
+ */
+ return !virtio_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM);
+}
+
static inline bool virtio_is_little_endian(struct virtio_device *vdev)
{
return virtio_has_feature(vdev, VIRTIO_F_VERSION_1) ||
#define cache_line_size() SMP_CACHE_BYTES
#define ____cacheline_aligned_in_smp __attribute__ ((aligned (SMP_CACHE_BYTES)))
#define unlikely(x) (__builtin_expect(!!(x), 0))
+#define likely(x) (__builtin_expect(!!(x), 1))
#define ALIGN(x, a) (((x) + (a) - 1) / (a) * (a))
typedef pthread_spinlock_t spinlock_t;
static struct timecounter *timecounter;
static struct workqueue_struct *wqueue;
static unsigned int host_vtimer_irq;
+static u32 host_vtimer_irq_flags;
void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
{
static void kvm_timer_init_interrupt(void *info)
{
- enable_percpu_irq(host_vtimer_irq, 0);
+ enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags);
}
int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
}
host_vtimer_irq = info->virtual_irq;
+ host_vtimer_irq_flags = irq_get_trigger_type(host_vtimer_irq);
+ if (host_vtimer_irq_flags != IRQF_TRIGGER_HIGH &&
+ host_vtimer_irq_flags != IRQF_TRIGGER_LOW) {
+ kvm_err("Invalid trigger for IRQ%d, assuming level low\n",
+ host_vtimer_irq);
+ host_vtimer_irq_flags = IRQF_TRIGGER_LOW;
+ }
+
err = request_percpu_irq(host_vtimer_irq, kvm_arch_timer_handler,
"kvm guest timer", kvm_get_running_vcpus());
if (err) {
int i, vcpu_lock_idx = -1, ret;
struct kvm_vcpu *vcpu;
- mutex_lock(&kvm->lock);
-
- if (irqchip_in_kernel(kvm)) {
- ret = -EEXIST;
- goto out;
- }
+ if (irqchip_in_kernel(kvm))
+ return -EEXIST;
/*
* This function is also called by the KVM_CREATE_IRQCHIP handler,
* the proper checks already.
*/
if (type == KVM_DEV_TYPE_ARM_VGIC_V2 &&
- !kvm_vgic_global_state.can_emulate_gicv2) {
- ret = -ENODEV;
- goto out;
- }
+ !kvm_vgic_global_state.can_emulate_gicv2)
+ return -ENODEV;
/*
* Any time a vcpu is run, vcpu_load is called which tries to grab the
vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
mutex_unlock(&vcpu->mutex);
}
-
-out:
- mutex_unlock(&kvm->lock);
return ret;
}
irq = kzalloc(sizeof(struct vgic_irq), GFP_KERNEL);
if (!irq)
- return NULL;
+ return ERR_PTR(-ENOMEM);
INIT_LIST_HEAD(&irq->lpi_list);
INIT_LIST_HEAD(&irq->ap_list);
* Find the target VCPU and the LPI number for a given devid/eventid pair
* and make this IRQ pending, possibly injecting it.
* Must be called with the its_lock mutex held.
+ * Returns 0 on success, a positive error value for any ITS mapping
+ * related errors and negative error values for generic errors.
*/
-static void vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its,
- u32 devid, u32 eventid)
+static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its,
+ u32 devid, u32 eventid)
{
+ struct kvm_vcpu *vcpu;
struct its_itte *itte;
if (!its->enabled)
- return;
+ return -EBUSY;
itte = find_itte(its, devid, eventid);
- /* Triggering an unmapped IRQ gets silently dropped. */
- if (itte && its_is_collection_mapped(itte->collection)) {
- struct kvm_vcpu *vcpu;
-
- vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr);
- if (vcpu && vcpu->arch.vgic_cpu.lpis_enabled) {
- spin_lock(&itte->irq->irq_lock);
- itte->irq->pending = true;
- vgic_queue_irq_unlock(kvm, itte->irq);
- }
- }
+ if (!itte || !its_is_collection_mapped(itte->collection))
+ return E_ITS_INT_UNMAPPED_INTERRUPT;
+
+ vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr);
+ if (!vcpu)
+ return E_ITS_INT_UNMAPPED_INTERRUPT;
+
+ if (!vcpu->arch.vgic_cpu.lpis_enabled)
+ return -EBUSY;
+
+ spin_lock(&itte->irq->irq_lock);
+ itte->irq->pending = true;
+ vgic_queue_irq_unlock(kvm, itte->irq);
+
+ return 0;
+}
+
+static struct vgic_io_device *vgic_get_its_iodev(struct kvm_io_device *dev)
+{
+ struct vgic_io_device *iodev;
+
+ if (dev->ops != &kvm_io_gic_ops)
+ return NULL;
+
+ iodev = container_of(dev, struct vgic_io_device, dev);
+
+ if (iodev->iodev_type != IODEV_ITS)
+ return NULL;
+
+ return iodev;
}
/*
* Queries the KVM IO bus framework to get the ITS pointer from the given
* doorbell address.
* We then call vgic_its_trigger_msi() with the decoded data.
+ * According to the KVM_SIGNAL_MSI API description returns 1 on success.
*/
int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi)
{
u64 address;
struct kvm_io_device *kvm_io_dev;
struct vgic_io_device *iodev;
+ int ret;
if (!vgic_has_its(kvm))
return -ENODEV;
kvm_io_dev = kvm_io_bus_get_dev(kvm, KVM_MMIO_BUS, address);
if (!kvm_io_dev)
- return -ENODEV;
+ return -EINVAL;
- iodev = container_of(kvm_io_dev, struct vgic_io_device, dev);
+ iodev = vgic_get_its_iodev(kvm_io_dev);
+ if (!iodev)
+ return -EINVAL;
mutex_lock(&iodev->its->its_lock);
- vgic_its_trigger_msi(kvm, iodev->its, msi->devid, msi->data);
+ ret = vgic_its_trigger_msi(kvm, iodev->its, msi->devid, msi->data);
mutex_unlock(&iodev->its->its_lock);
- return 0;
+ if (ret < 0)
+ return ret;
+
+ /*
+ * KVM_SIGNAL_MSI demands a return value > 0 for success and 0
+ * if the guest has blocked the MSI. So we map any LPI mapping
+ * related error to that.
+ */
+ if (ret)
+ return 0;
+ else
+ return 1;
}
/* Requires the its_lock to be held. */
list_del(&itte->itte_list);
/* This put matches the get in vgic_add_lpi. */
- vgic_put_irq(kvm, itte->irq);
+ if (itte->irq)
+ vgic_put_irq(kvm, itte->irq);
kfree(itte);
}
struct its_device *device;
struct its_collection *collection, *new_coll = NULL;
int lpi_nr;
+ struct vgic_irq *irq;
device = find_its_device(its, device_id);
if (!device)
lpi_nr >= max_lpis_propbaser(kvm->arch.vgic.propbaser))
return E_ITS_MAPTI_PHYSICALID_OOR;
+ /* If there is an existing mapping, behavior is UNPREDICTABLE. */
+ if (find_itte(its, device_id, event_id))
+ return 0;
+
collection = find_collection(its, coll_id);
if (!collection) {
int ret = vgic_its_alloc_collection(its, &collection, coll_id);
new_coll = collection;
}
- itte = find_itte(its, device_id, event_id);
+ itte = kzalloc(sizeof(struct its_itte), GFP_KERNEL);
if (!itte) {
- itte = kzalloc(sizeof(struct its_itte), GFP_KERNEL);
- if (!itte) {
- if (new_coll)
- vgic_its_free_collection(its, coll_id);
- return -ENOMEM;
- }
-
- itte->event_id = event_id;
- list_add_tail(&itte->itte_list, &device->itt_head);
+ if (new_coll)
+ vgic_its_free_collection(its, coll_id);
+ return -ENOMEM;
}
+ itte->event_id = event_id;
+ list_add_tail(&itte->itte_list, &device->itt_head);
+
itte->collection = collection;
itte->lpi = lpi_nr;
- itte->irq = vgic_add_lpi(kvm, lpi_nr);
+
+ irq = vgic_add_lpi(kvm, lpi_nr);
+ if (IS_ERR(irq)) {
+ if (new_coll)
+ vgic_its_free_collection(its, coll_id);
+ its_free_itte(kvm, itte);
+ return PTR_ERR(irq);
+ }
+ itte->irq = irq;
+
update_affinity_itte(kvm, itte);
/*
u32 msi_data = its_cmd_get_id(its_cmd);
u64 msi_devid = its_cmd_get_deviceid(its_cmd);
- vgic_its_trigger_msi(kvm, its, msi_devid, msi_data);
-
- return 0;
+ return vgic_its_trigger_msi(kvm, its, msi_devid, msi_data);
}
/*
its_sync_lpi_pending_table(vcpu);
}
-static int vgic_its_init_its(struct kvm *kvm, struct vgic_its *its)
+static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its)
{
struct vgic_io_device *iodev = &its->iodev;
int ret;
- if (its->initialized)
- return 0;
+ if (!its->initialized)
+ return -EBUSY;
if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base))
return -ENXIO;
KVM_VGIC_V3_ITS_SIZE, &iodev->dev);
mutex_unlock(&kvm->slots_lock);
- if (!ret)
- its->initialized = true;
-
return ret;
}
if (type != KVM_VGIC_ITS_ADDR_TYPE)
return -ENODEV;
- if (its->initialized)
- return -EBUSY;
-
if (copy_from_user(&addr, uaddr, sizeof(addr)))
return -EFAULT;
case KVM_DEV_ARM_VGIC_GRP_CTRL:
switch (attr->attr) {
case KVM_DEV_ARM_VGIC_CTRL_INIT:
- return vgic_its_init_its(dev->kvm, its);
+ its->initialized = true;
+
+ return 0;
}
break;
}
return kvm_register_device_ops(&kvm_arm_vgic_its_ops,
KVM_DEV_TYPE_ARM_VGIC_ITS);
}
+
+/*
+ * Registers all ITSes with the kvm_io_bus framework.
+ * To follow the existing VGIC initialization sequence, this has to be
+ * done as late as possible, just before the first VCPU runs.
+ */
+int vgic_register_its_iodevs(struct kvm *kvm)
+{
+ struct kvm_device *dev;
+ int ret = 0;
+
+ list_for_each_entry(dev, &kvm->devices, vm_node) {
+ if (dev->ops != &kvm_arm_vgic_its_ops)
+ continue;
+
+ ret = vgic_register_its_iodev(kvm, dev->private);
+ if (ret)
+ return ret;
+ /*
+ * We don't need to care about tearing down previously
+ * registered ITSes, as the kvm_io_bus framework removes
+ * them for us if the VM gets destroyed.
+ */
+ }
+
+ return ret;
+}
{
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
- u64 propbaser = dist->propbaser;
+ u64 old_propbaser, propbaser;
/* Storing a value with LPIs already enabled is undefined */
if (vgic_cpu->lpis_enabled)
return;
- propbaser = update_64bit_reg(propbaser, addr & 4, len, val);
- propbaser = vgic_sanitise_propbaser(propbaser);
-
- dist->propbaser = propbaser;
+ do {
+ old_propbaser = dist->propbaser;
+ propbaser = old_propbaser;
+ propbaser = update_64bit_reg(propbaser, addr & 4, len, val);
+ propbaser = vgic_sanitise_propbaser(propbaser);
+ } while (cmpxchg64(&dist->propbaser, old_propbaser,
+ propbaser) != old_propbaser);
}
static unsigned long vgic_mmio_read_pendbase(struct kvm_vcpu *vcpu,
unsigned long val)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
- u64 pendbaser = vgic_cpu->pendbaser;
+ u64 old_pendbaser, pendbaser;
/* Storing a value with LPIs already enabled is undefined */
if (vgic_cpu->lpis_enabled)
return;
- pendbaser = update_64bit_reg(pendbaser, addr & 4, len, val);
- pendbaser = vgic_sanitise_pendbaser(pendbaser);
-
- vgic_cpu->pendbaser = pendbaser;
+ do {
+ old_pendbaser = vgic_cpu->pendbaser;
+ pendbaser = old_pendbaser;
+ pendbaser = update_64bit_reg(pendbaser, addr & 4, len, val);
+ pendbaser = vgic_sanitise_pendbaser(pendbaser);
+ } while (cmpxchg64(&vgic_cpu->pendbaser, old_pendbaser,
+ pendbaser) != old_pendbaser);
}
/*
goto out;
}
+ if (vgic_has_its(kvm)) {
+ ret = vgic_register_its_iodevs(kvm);
+ if (ret) {
+ kvm_err("Unable to register VGIC ITS MMIO regions\n");
+ goto out;
+ }
+ }
+
dist->ready = true;
out:
void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq)
{
- struct vgic_dist *dist;
+ struct vgic_dist *dist = &kvm->arch.vgic;
if (irq->intid < VGIC_MIN_LPI)
return;
- if (!kref_put(&irq->refcount, vgic_irq_release))
+ spin_lock(&dist->lpi_list_lock);
+ if (!kref_put(&irq->refcount, vgic_irq_release)) {
+ spin_unlock(&dist->lpi_list_lock);
return;
+ };
- dist = &kvm->arch.vgic;
-
- spin_lock(&dist->lpi_list_lock);
list_del(&irq->lpi_list);
dist->lpi_list_count--;
spin_unlock(&dist->lpi_list_lock);
int vgic_v3_probe(const struct gic_kvm_info *info);
int vgic_v3_map_resources(struct kvm *kvm);
int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t dist_base_address);
+int vgic_register_its_iodevs(struct kvm *kvm);
bool vgic_has_its(struct kvm *kvm);
int kvm_vgic_register_its_device(void);
void vgic_enable_lpis(struct kvm_vcpu *vcpu);
return -ENODEV;
}
+static inline int vgic_register_its_iodevs(struct kvm *kvm)
+{
+ return -ENODEV;
+}
+
static inline bool vgic_has_its(struct kvm *kvm)
{
return false;
{
struct kvm_device *dev, *tmp;
+ /*
+ * We do not need to take the kvm->lock here, because nobody else
+ * has a reference to the struct kvm at this point and therefore
+ * cannot access the devices list anyhow.
+ */
list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) {
list_del(&dev->vm_node);
dev->ops->destroy(dev);
dev->ops = ops;
dev->kvm = kvm;
+ mutex_lock(&kvm->lock);
ret = ops->create(dev, cd->type);
if (ret < 0) {
+ mutex_unlock(&kvm->lock);
kfree(dev);
return ret;
}
+ list_add(&dev->vm_node, &kvm->devices);
+ mutex_unlock(&kvm->lock);
+
+ if (ops->init)
+ ops->init(dev);
ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC);
if (ret < 0) {
ops->destroy(dev);
+ mutex_lock(&kvm->lock);
+ list_del(&dev->vm_node);
+ mutex_unlock(&kvm->lock);
return ret;
}
- list_add(&dev->vm_node, &kvm->devices);
kvm_get_kvm(kvm);
cd->fd = ret;
return 0;
projects / cascardo / linux.git / commitdiff