From: Linus Torvalds Date: Wed, 12 Oct 2016 00:34:10 +0000 (-0700) Subject: Merge branch 'akpm' (patches from Andrew) X-Git-Tag: v4.9-rc1~42 X-Git-Url: http://git.cascardo.info/?p=cascardo%2Flinux.git;a=commitdiff_plain;h=a379f71a30dddbd2e7393624e455ce53c87965d1;hp=de34f4da7f62ff59ac6e1ef320b0fcfa3296fce3 Merge branch 'akpm' (patches from Andrew) Merge more updates from Andrew Morton: - a few block updates that fell in my lap - lib/ updates - checkpatch - autofs - ipc - a ton of misc other things * emailed patches from Andrew Morton : (100 commits) mm: split gfp_mask and mapping flags into separate fields fs: use mapping_set_error instead of opencoded set_bit treewide: remove redundant #include hung_task: allow hung_task_panic when hung_task_warnings is 0 kthread: add kerneldoc for kthread_create() kthread: better support freezable kthread workers kthread: allow to modify delayed kthread work kthread: allow to cancel kthread work kthread: initial support for delayed kthread work kthread: detect when a kthread work is used by more workers kthread: add kthread_destroy_worker() kthread: add kthread_create_worker*() kthread: allow to call __kthread_create_on_node() with va_list args kthread/smpboot: do not park in kthread_create_on_cpu() kthread: kthread worker API cleanup kthread: rename probe_kthread_data() to kthread_probe_data() scripts/tags.sh: enable code completion in VIM mm: kmemleak: avoid using __va() on addresses that don't have a lowmem mapping kdump, vmcoreinfo: report memory sections virtual addresses ipc/sem.c: add cond_resched in exit_sme ... --- diff --git a/Documentation/DMA-attributes.txt b/Documentation/DMA-attributes.txt index 2d455a5cf671..98bf7ac29aad 100644 --- a/Documentation/DMA-attributes.txt +++ b/Documentation/DMA-attributes.txt @@ -126,3 +126,20 @@ means that we won't try quite as hard to get them. NOTE: At the moment DMA_ATTR_ALLOC_SINGLE_PAGES is only implemented on ARM, though ARM64 patches will likely be posted soon. + +DMA_ATTR_NO_WARN +---------------- + +This tells the DMA-mapping subsystem to suppress allocation failure reports +(similarly to __GFP_NOWARN). + +On some architectures allocation failures are reported with error messages +to the system logs. Although this can help to identify and debug problems, +drivers which handle failures (eg, retry later) have no problems with them, +and can actually flood the system logs with error messages that aren't any +problem at all, depending on the implementation of the retry mechanism. + +So, this provides a way for drivers to avoid those error messages on calls +where allocation failures are not a problem, and shouldn't bother the logs. + +NOTE: At the moment DMA_ATTR_NO_WARN is only implemented on PowerPC. diff --git a/Documentation/RCU/lockdep-splat.txt b/Documentation/RCU/lockdep-splat.txt index bf9061142827..238e9f61352f 100644 --- a/Documentation/RCU/lockdep-splat.txt +++ b/Documentation/RCU/lockdep-splat.txt @@ -57,7 +57,7 @@ Call Trace: [] kernel_thread_helper+0x4/0x10 [] ? finish_task_switch+0x80/0x110 [] ? retint_restore_args+0xe/0xe - [] ? __init_kthread_worker+0x70/0x70 + [] ? __kthread_init_worker+0x70/0x70 [] ? gs_change+0xb/0xb Line 2776 of block/cfq-iosched.c in v3.0-rc5 is as follows: diff --git a/Documentation/dev-tools/kmemleak.rst b/Documentation/dev-tools/kmemleak.rst index 1788722d5495..b2391b829169 100644 --- a/Documentation/dev-tools/kmemleak.rst +++ b/Documentation/dev-tools/kmemleak.rst @@ -162,6 +162,15 @@ See the include/linux/kmemleak.h header for the functions prototype. - ``kmemleak_alloc_recursive`` - as kmemleak_alloc but checks the recursiveness - ``kmemleak_free_recursive`` - as kmemleak_free but checks the recursiveness +The following functions take a physical address as the object pointer +and only perform the corresponding action if the address has a lowmem +mapping: + +- ``kmemleak_alloc_phys`` +- ``kmemleak_free_part_phys`` +- ``kmemleak_not_leak_phys`` +- ``kmemleak_ignore_phys`` + Dealing with false positives/negatives -------------------------------------- diff --git a/Documentation/filesystems/autofs4-mount-control.txt b/Documentation/filesystems/autofs4-mount-control.txt index aff22113a986..50a3e01a36f8 100644 --- a/Documentation/filesystems/autofs4-mount-control.txt +++ b/Documentation/filesystems/autofs4-mount-control.txt @@ -179,8 +179,19 @@ struct autofs_dev_ioctl { * including this struct */ __s32 ioctlfd; /* automount command fd */ - __u32 arg1; /* Command parameters */ - __u32 arg2; + union { + struct args_protover protover; + struct args_protosubver protosubver; + struct args_openmount openmount; + struct args_ready ready; + struct args_fail fail; + struct args_setpipefd setpipefd; + struct args_timeout timeout; + struct args_requester requester; + struct args_expire expire; + struct args_askumount askumount; + struct args_ismountpoint ismountpoint; + }; char path[0]; }; @@ -192,8 +203,8 @@ optionally be used to check a specific mount corresponding to a given mount point file descriptor, and when requesting the uid and gid of the last successful mount on a directory within the autofs file system. -The fields arg1 and arg2 are used to communicate parameters and results of -calls made as described below. +The union is used to communicate parameters and results of calls made +as described below. The path field is used to pass a path where it is needed and the size field is used account for the increased structure length when translating the @@ -245,9 +256,9 @@ AUTOFS_DEV_IOCTL_PROTOVER_CMD and AUTOFS_DEV_IOCTL_PROTOSUBVER_CMD Get the major and minor version of the autofs4 protocol version understood by loaded module. This call requires an initialized struct autofs_dev_ioctl with the ioctlfd field set to a valid autofs mount point descriptor -and sets the requested version number in structure field arg1. These -commands return 0 on success or one of the negative error codes if -validation fails. +and sets the requested version number in version field of struct args_protover +or sub_version field of struct args_protosubver. These commands return +0 on success or one of the negative error codes if validation fails. AUTOFS_DEV_IOCTL_OPENMOUNT and AUTOFS_DEV_IOCTL_CLOSEMOUNT @@ -256,9 +267,9 @@ AUTOFS_DEV_IOCTL_OPENMOUNT and AUTOFS_DEV_IOCTL_CLOSEMOUNT Obtain and release a file descriptor for an autofs managed mount point path. The open call requires an initialized struct autofs_dev_ioctl with the path field set and the size field adjusted appropriately as well -as the arg1 field set to the device number of the autofs mount. The -device number can be obtained from the mount options shown in -/proc/mounts. The close call requires an initialized struct +as the devid field of struct args_openmount set to the device number of +the autofs mount. The device number can be obtained from the mount options +shown in /proc/mounts. The close call requires an initialized struct autofs_dev_ioct with the ioctlfd field set to the descriptor obtained from the open call. The release of the file descriptor can also be done with close(2) so any open descriptors will also be closed at process exit. @@ -272,10 +283,10 @@ AUTOFS_DEV_IOCTL_READY_CMD and AUTOFS_DEV_IOCTL_FAIL_CMD Return mount and expire result status from user space to the kernel. Both of these calls require an initialized struct autofs_dev_ioctl with the ioctlfd field set to the descriptor obtained from the open -call and the arg1 field set to the wait queue token number, received -by user space in the foregoing mount or expire request. The arg2 field -is set to the status to be returned. For the ready call this is always -0 and for the fail call it is set to the errno of the operation. +call and the token field of struct args_ready or struct args_fail set +to the wait queue token number, received by user space in the foregoing +mount or expire request. The status field of struct args_fail is set to +the errno of the operation. It is set to 0 on success. AUTOFS_DEV_IOCTL_SETPIPEFD_CMD @@ -290,9 +301,10 @@ mount be catatonic (see next call). The call requires an initialized struct autofs_dev_ioctl with the ioctlfd field set to the descriptor obtained from the open call and -the arg1 field set to descriptor of the pipe. On success the call -also sets the process group id used to identify the controlling process -(eg. the owning automount(8) daemon) to the process group of the caller. +the pipefd field of struct args_setpipefd set to descriptor of the pipe. +On success the call also sets the process group id used to identify the +controlling process (eg. the owning automount(8) daemon) to the process +group of the caller. AUTOFS_DEV_IOCTL_CATATONIC_CMD @@ -323,9 +335,8 @@ mount on the given path dentry. The call requires an initialized struct autofs_dev_ioctl with the path field set to the mount point in question and the size field adjusted -appropriately as well as the arg1 field set to the device number of the -containing autofs mount. Upon return the struct field arg1 contains the -uid and arg2 the gid. +appropriately. Upon return the uid field of struct args_requester contains +the uid and gid field the gid. When reconstructing an autofs mount tree with active mounts we need to re-connect to mounts that may have used the original process uid and @@ -343,8 +354,9 @@ this ioctl is called until no further expire candidates are found. The call requires an initialized struct autofs_dev_ioctl with the ioctlfd field set to the descriptor obtained from the open call. In addition an immediate expire, independent of the mount timeout, can be -requested by setting the arg1 field to 1. If no expire candidates can -be found the ioctl returns -1 with errno set to EAGAIN. +requested by setting the how field of struct args_expire to 1. If no +expire candidates can be found the ioctl returns -1 with errno set to +EAGAIN. This call causes the kernel module to check the mount corresponding to the given ioctlfd for mounts that can be expired, issues an expire @@ -357,7 +369,8 @@ Checks if an autofs mount point is in use. The call requires an initialized struct autofs_dev_ioctl with the ioctlfd field set to the descriptor obtained from the open call and -it returns the result in the arg1 field, 1 for busy and 0 otherwise. +it returns the result in the may_umount field of struct args_askumount, +1 for busy and 0 otherwise. AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD @@ -369,12 +382,12 @@ The call requires an initialized struct autofs_dev_ioctl. There are two possible variations. Both use the path field set to the path of the mount point to check and the size field adjusted appropriately. One uses the ioctlfd field to identify a specific mount point to check while the other -variation uses the path and optionally arg1 set to an autofs mount type. -The call returns 1 if this is a mount point and sets arg1 to the device -number of the mount and field arg2 to the relevant super block magic -number (described below) or 0 if it isn't a mountpoint. In both cases -the the device number (as returned by new_encode_dev()) is returned -in field arg1. +variation uses the path and optionally in.type field of struct args_ismountpoint +set to an autofs mount type. The call returns 1 if this is a mount point +and sets out.devid field to the device number of the mount and out.magic +field to the relevant super block magic number (described below) or 0 if +it isn't a mountpoint. In both cases the the device number (as returned +by new_encode_dev()) is returned in out.devid field. If supplied with a file descriptor we're looking for a specific mount, not necessarily at the top of the mounted stack. In this case the path diff --git a/Documentation/filesystems/autofs4.txt b/Documentation/filesystems/autofs4.txt index 39d02e19fb62..8fac3fe7b8c9 100644 --- a/Documentation/filesystems/autofs4.txt +++ b/Documentation/filesystems/autofs4.txt @@ -203,9 +203,9 @@ initiated or is being considered, otherwise it returns 0. Mountpoint expiry ----------------- -The VFS has a mechansim for automatically expiring unused mounts, +The VFS has a mechanism for automatically expiring unused mounts, much as it can expire any unused dentry information from the dcache. -This is guided by the MNT_SHRINKABLE flag. This only applies to +This is guided by the MNT_SHRINKABLE flag. This only applies to mounts that were created by `d_automount()` returning a filesystem to be mounted. As autofs doesn't return such a filesystem but leaves the mounting to the automount daemon, it must involve the automount daemon @@ -298,7 +298,7 @@ remove directories and symlinks using normal filesystem operations. autofs knows whether a process requesting some operation is the daemon or not based on its process-group id number (see getpgid(1)). -When an autofs filesystem it mounted the pgid of the mounting +When an autofs filesystem is mounted the pgid of the mounting processes is recorded unless the "pgrp=" option is given, in which case that number is recorded instead. Any request arriving from a process in that process group is considered to come from the daemon. @@ -450,7 +450,7 @@ Commands are: numbers for existing filesystems can be found in `/proc/self/mountinfo`. - **AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD**: same as `close(ioctlfd)`. -- **AUTOFS_DEV_IOCTL_SETPIPEFD_CMD**: if the filesystem is in +- **AUTOFS_DEV_IOCTL_SETPIPEFD_CMD**: if the filesystem is in catatonic mode, this can provide the write end of a new pipe in `arg1` to re-establish communication with a daemon. The process group of the calling process is used to identify the diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 705fb915cbf7..a1489e14f8ee 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -33,6 +33,37 @@ can also be entered as Double-quotes can be used to protect spaces in values, e.g.: param="spaces in here" +cpu lists: +---------- + +Some kernel parameters take a list of CPUs as a value, e.g. isolcpus, +nohz_full, irqaffinity, rcu_nocbs. The format of this list is: + + ,..., + +or + + - + (must be a positive range in ascending order) + +or a mixture + +,...,- + +Note that for the special case of a range one can split the range into equal +sized groups and for each group use some amount from the beginning of that +group: + + -cpu number>:/ + +For example one can add to the command line following parameter: + + isolcpus=1,2,10-20,100-2000:2/25 + +where the final item represents CPUs 100,101,125,126,150,151,... + + + This document may not be entirely up to date and comprehensive. The command "modinfo -p ${modulename}" shows a current list of all parameters of a loadable module. Loadable modules, after being loaded into the running kernel, also @@ -1789,13 +1820,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. See Documentation/filesystems/nfs/nfsroot.txt. irqaffinity= [SMP] Set the default irq affinity mask - Format: - ,..., - or - - - (must be a positive range in ascending order) - or a mixture - ,...,- + The argument is a cpu list, as described above. irqfixup [HW] When an interrupt is not handled search all handlers @@ -1812,13 +1837,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Format: ,,, isolcpus= [KNL,SMP] Isolate CPUs from the general scheduler. - Format: - ,..., - or - - - (must be a positive range in ascending order) - or a mixture - ,...,- + The argument is a cpu list, as described above. This option can be used to specify one or more CPUs to isolate from the general SMP balancing and scheduling @@ -2680,6 +2699,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Default: on nohz_full= [KNL,BOOT] + The argument is a cpu list, as described above. In kernels built with CONFIG_NO_HZ_FULL=y, set the specified list of CPUs whose tick will be stopped whenever possible. The boot CPU will be forced outside @@ -3285,6 +3305,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted. See Documentation/blockdev/ramdisk.txt. rcu_nocbs= [KNL] + The argument is a cpu list, as described above. + In kernels built with CONFIG_RCU_NOCB_CPU=y, set the specified list of CPUs to be no-callback CPUs. Invocation of these CPUs' RCU callbacks will diff --git a/arch/arm/include/asm/trusted_foundations.h b/arch/arm/include/asm/trusted_foundations.h index 624e1d436c6c..00748350cf72 100644 --- a/arch/arm/include/asm/trusted_foundations.h +++ b/arch/arm/include/asm/trusted_foundations.h @@ -26,7 +26,6 @@ #ifndef __ASM_ARM_TRUSTED_FOUNDATIONS_H #define __ASM_ARM_TRUSTED_FOUNDATIONS_H -#include #include #include #include diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 612eb530f33f..91d2d5b01414 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -318,8 +318,7 @@ unsigned long get_wchan(struct task_struct *p) unsigned long arch_randomize_brk(struct mm_struct *mm) { - unsigned long range_end = mm->brk + 0x02000000; - return randomize_range(mm->brk, range_end, 0) ? : mm->brk; + return randomize_page(mm->brk, 0x02000000); } #ifdef CONFIG_MMU diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index 55101bd86b98..39feb85a6931 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -7,7 +7,6 @@ #ifndef __ASSEMBLY__ #include -#include #include #include #include diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index a4f5f766af08..27b2f1387df4 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -372,12 +372,8 @@ unsigned long arch_align_stack(unsigned long sp) unsigned long arch_randomize_brk(struct mm_struct *mm) { - unsigned long range_end = mm->brk; - if (is_compat_task()) - range_end += 0x02000000; + return randomize_page(mm->brk, 0x02000000); else - range_end += 0x40000000; - - return randomize_range(mm->brk, range_end, 0) ? : mm->brk; + return randomize_page(mm->brk, 0x40000000); } diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c index cb16fcc5f8f0..5537f95b28c9 100644 --- a/arch/mips/cavium-octeon/setup.c +++ b/arch/mips/cavium-octeon/setup.c @@ -267,6 +267,17 @@ static void octeon_crash_shutdown(struct pt_regs *regs) default_machine_crash_shutdown(regs); } +#ifdef CONFIG_SMP +void octeon_crash_smp_send_stop(void) +{ + int cpu; + + /* disable watchdogs */ + for_each_online_cpu(cpu) + cvmx_write_csr(CVMX_CIU_WDOGX(cpu_logical_map(cpu)), 0); +} +#endif + #endif /* CONFIG_KEXEC */ #ifdef CONFIG_CAVIUM_RESERVE32 @@ -911,6 +922,9 @@ void __init prom_init(void) _machine_kexec_shutdown = octeon_shutdown; _machine_crash_shutdown = octeon_crash_shutdown; _machine_kexec_prepare = octeon_kexec_prepare; +#ifdef CONFIG_SMP + _crash_smp_send_stop = octeon_crash_smp_send_stop; +#endif #endif octeon_user_io_init(); diff --git a/arch/mips/include/asm/kexec.h b/arch/mips/include/asm/kexec.h index ee25ebbf2a28..493a3cc7c39a 100644 --- a/arch/mips/include/asm/kexec.h +++ b/arch/mips/include/asm/kexec.h @@ -45,6 +45,7 @@ extern const unsigned char kexec_smp_wait[]; extern unsigned long secondary_kexec_args[4]; extern void (*relocated_kexec_smp_wait) (void *); extern atomic_t kexec_ready_to_reboot; +extern void (*_crash_smp_send_stop)(void); #endif #endif diff --git a/arch/mips/include/asm/mach-loongson64/loongson.h b/arch/mips/include/asm/mach-loongson64/loongson.h index d1ff774ac4b6..c68c0cc879c6 100644 --- a/arch/mips/include/asm/mach-loongson64/loongson.h +++ b/arch/mips/include/asm/mach-loongson64/loongson.h @@ -14,7 +14,6 @@ #include #include #include -#include #include /* loongson internal northbridge initialization */ diff --git a/arch/mips/kernel/crash.c b/arch/mips/kernel/crash.c index 610f0f3bdb34..1723b1762297 100644 --- a/arch/mips/kernel/crash.c +++ b/arch/mips/kernel/crash.c @@ -47,9 +47,14 @@ static void crash_shutdown_secondary(void *passed_regs) static void crash_kexec_prepare_cpus(void) { + static int cpus_stopped; unsigned int msecs; + unsigned int ncpus; - unsigned int ncpus = num_online_cpus() - 1;/* Excluding the panic cpu */ + if (cpus_stopped) + return; + + ncpus = num_online_cpus() - 1;/* Excluding the panic cpu */ dump_send_ipi(crash_shutdown_secondary); smp_wmb(); @@ -64,6 +69,17 @@ static void crash_kexec_prepare_cpus(void) cpu_relax(); mdelay(1); } + + cpus_stopped = 1; +} + +/* Override the weak function in kernel/panic.c */ +void crash_smp_send_stop(void) +{ + if (_crash_smp_send_stop) + _crash_smp_send_stop(); + + crash_kexec_prepare_cpus(); } #else /* !defined(CONFIG_SMP) */ diff --git a/arch/mips/kernel/machine_kexec.c b/arch/mips/kernel/machine_kexec.c index 50980bf3983e..59725204105c 100644 --- a/arch/mips/kernel/machine_kexec.c +++ b/arch/mips/kernel/machine_kexec.c @@ -25,6 +25,7 @@ void (*_machine_crash_shutdown)(struct pt_regs *regs) = NULL; #ifdef CONFIG_SMP void (*relocated_kexec_smp_wait) (void *); atomic_t kexec_ready_to_reboot = ATOMIC_INIT(0); +void (*_crash_smp_send_stop)(void) = NULL; #endif int diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index 36775d20b0e7..f8b7bf836437 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -35,7 +35,6 @@ */ #include #include -#include #include #include diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c index 39e7b472f0d8..49a2e2226fee 100644 --- a/arch/mips/net/bpf_jit.c +++ b/arch/mips/net/bpf_jit.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 37d6e741be82..5f202a566ec5 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -479,7 +479,8 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl, /* Handle failure */ if (unlikely(entry == DMA_ERROR_CODE)) { - if (printk_ratelimit()) + if (!(attrs & DMA_ATTR_NO_WARN) && + printk_ratelimit()) dev_info(dev, "iommu_alloc failed, tbl %p " "vaddr %lx npages %lu\n", tbl, vaddr, npages); @@ -776,7 +777,8 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl, mask >> tbl->it_page_shift, align, attrs); if (dma_handle == DMA_ERROR_CODE) { - if (printk_ratelimit()) { + if (!(attrs & DMA_ATTR_NO_WARN) && + printk_ratelimit()) { dev_info(dev, "iommu_alloc failed, tbl %p " "vaddr %p npages %d\n", tbl, vaddr, npages); diff --git a/arch/tile/mm/mmap.c b/arch/tile/mm/mmap.c index 851a94e6ae58..ef61c597898b 100644 --- a/arch/tile/mm/mmap.c +++ b/arch/tile/mm/mmap.c @@ -88,6 +88,5 @@ void arch_pick_mmap_layout(struct mm_struct *mm) unsigned long arch_randomize_brk(struct mm_struct *mm) { - unsigned long range_end = mm->brk + 0x02000000; - return randomize_range(mm->brk, range_end, 0) ? : mm->brk; + return randomize_page(mm->brk, 0x02000000); } diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c index 00299c927852..d7c6b676b3a5 100644 --- a/arch/unicore32/kernel/process.c +++ b/arch/unicore32/kernel/process.c @@ -295,8 +295,7 @@ unsigned long get_wchan(struct task_struct *p) unsigned long arch_randomize_brk(struct mm_struct *mm) { - unsigned long range_end = mm->brk + 0x02000000; - return randomize_range(mm->brk, range_end, 0) ? : mm->brk; + return randomize_page(mm->brk, 0x02000000); } /* diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index d2434c1cad05..282630e4c6ea 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -210,6 +210,7 @@ struct kexec_entry64_regs { typedef void crash_vmclear_fn(void); extern crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss; +extern void kdump_nmi_shootdown_cpus(void); #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 19980b36f394..026ea82ecc60 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -47,6 +47,7 @@ struct smp_ops { void (*smp_cpus_done)(unsigned max_cpus); void (*stop_other_cpus)(int wait); + void (*crash_stop_other_cpus)(void); void (*smp_send_reschedule)(int cpu); int (*cpu_up)(unsigned cpu, struct task_struct *tidle); diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 9616cf76940c..650830e39e3a 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -133,15 +133,31 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) disable_local_APIC(); } -static void kdump_nmi_shootdown_cpus(void) +void kdump_nmi_shootdown_cpus(void) { nmi_shootdown_cpus(kdump_nmi_callback); disable_local_APIC(); } +/* Override the weak function in kernel/panic.c */ +void crash_smp_send_stop(void) +{ + static int cpus_stopped; + + if (cpus_stopped) + return; + + if (smp_ops.crash_stop_other_cpus) + smp_ops.crash_stop_other_cpus(); + else + smp_send_stop(); + + cpus_stopped = 1; +} + #else -static void kdump_nmi_shootdown_cpus(void) +void crash_smp_send_stop(void) { /* There are no cpus to shootdown */ } @@ -160,7 +176,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs) /* The kernel is broken so disable interrupts */ local_irq_disable(); - kdump_nmi_shootdown_cpus(); + crash_smp_send_stop(); /* * VMCLEAR VMCSs loaded on this cpu if needed. diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 5a294e48b185..8c1f218926d7 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -337,6 +337,9 @@ void arch_crash_save_vmcoreinfo(void) #endif vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); + VMCOREINFO_PAGE_OFFSET(PAGE_OFFSET); + VMCOREINFO_VMALLOC_START(VMALLOC_START); + VMCOREINFO_VMEMMAP_START(VMEMMAP_START); } /* arch-dependent functionality related to kexec file-based syscall */ diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 28cea7802ecb..0888a879120f 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -509,8 +509,7 @@ unsigned long arch_align_stack(unsigned long sp) unsigned long arch_randomize_brk(struct mm_struct *mm) { - unsigned long range_end = mm->brk + 0x02000000; - return randomize_range(mm->brk, range_end, 0) ? : mm->brk; + return randomize_page(mm->brk, 0x02000000); } /* diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 658777cf3851..68f8cc222f25 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -32,6 +32,8 @@ #include #include #include +#include + /* * Some notes on x86 processor bugs affecting SMP operation: * @@ -342,6 +344,9 @@ struct smp_ops smp_ops = { .smp_cpus_done = native_smp_cpus_done, .stop_other_cpus = native_stop_other_cpus, +#if defined(CONFIG_KEXEC_CORE) + .crash_stop_other_cpus = kdump_nmi_shootdown_cpus, +#endif .smp_send_reschedule = native_smp_send_reschedule, .cpu_up = native_cpu_up, diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 10e0272d789a..a55ed63b9f91 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -101,7 +101,6 @@ static void find_start_end(unsigned long flags, unsigned long *begin, unsigned long *end) { if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT)) { - unsigned long new_begin; /* This is usually used needed to map code in small model, so it needs to be in the first 31bit. Limit it to that. This means we need to move the @@ -112,9 +111,7 @@ static void find_start_end(unsigned long flags, unsigned long *begin, *begin = 0x40000000; *end = 0x80000000; if (current->flags & PF_RANDOMIZE) { - new_begin = randomize_range(*begin, *begin + 0x02000000, 0); - if (new_begin) - *begin = new_begin; + *begin = randomize_page(*begin, 0x02000000); } } else { *begin = current->mm->mmap_legacy_base; diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 5fb6c620180e..16a7134eedac 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -212,7 +212,7 @@ static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian) */ smp_mb(); if (atomic_dec_if_positive(&ps->pending) > 0) - queue_kthread_work(&pit->worker, &pit->expired); + kthread_queue_work(&pit->worker, &pit->expired); } void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu) @@ -233,7 +233,7 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu) static void destroy_pit_timer(struct kvm_pit *pit) { hrtimer_cancel(&pit->pit_state.timer); - flush_kthread_work(&pit->expired); + kthread_flush_work(&pit->expired); } static void pit_do_work(struct kthread_work *work) @@ -272,7 +272,7 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data) if (atomic_read(&ps->reinject)) atomic_inc(&ps->pending); - queue_kthread_work(&pt->worker, &pt->expired); + kthread_queue_work(&pt->worker, &pt->expired); if (ps->is_periodic) { hrtimer_add_expires_ns(&ps->timer, ps->period); @@ -324,7 +324,7 @@ static void create_pit_timer(struct kvm_pit *pit, u32 val, int is_period) /* TODO The new value only affected after the retriggered */ hrtimer_cancel(&ps->timer); - flush_kthread_work(&pit->expired); + kthread_flush_work(&pit->expired); ps->period = interval; ps->is_periodic = is_period; @@ -667,13 +667,13 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) pid_nr = pid_vnr(pid); put_pid(pid); - init_kthread_worker(&pit->worker); + kthread_init_worker(&pit->worker); pit->worker_task = kthread_run(kthread_worker_fn, &pit->worker, "kvm-pit/%d", pid_nr); if (IS_ERR(pit->worker_task)) goto fail_kthread; - init_kthread_work(&pit->expired, pit_do_work); + kthread_init_work(&pit->expired, pit_do_work); pit->kvm = kvm; @@ -730,7 +730,7 @@ void kvm_free_pit(struct kvm *kvm) kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->speaker_dev); kvm_pit_set_reinject(pit, false); hrtimer_cancel(&pit->pit_state.timer); - flush_kthread_work(&pit->expired); + kthread_flush_work(&pit->expired); kthread_stop(pit->worker_task); kvm_free_irq_source_id(kvm, pit->irq_source_id); kfree(pit); diff --git a/block/blk-lib.c b/block/blk-lib.c index 083e56f72308..46fe9248410d 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -31,6 +31,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, unsigned int granularity; enum req_op op; int alignment; + sector_t bs_mask; if (!q) return -ENXIO; @@ -50,6 +51,10 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, op = REQ_OP_DISCARD; } + bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1; + if ((sector | nr_sects) & bs_mask) + return -EINVAL; + /* Zero-sector (unknown) and one-sector granularities are the same. */ granularity = max(q->limits.discard_granularity >> 9, 1U); alignment = (bdev_discard_alignment(bdev) >> 9) % granularity; @@ -150,10 +155,15 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, unsigned int max_write_same_sectors; struct bio *bio = NULL; int ret = 0; + sector_t bs_mask; if (!q) return -ENXIO; + bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1; + if ((sector | nr_sects) & bs_mask) + return -EINVAL; + /* Ensure that max_write_same_sectors doesn't overflow bi_size */ max_write_same_sectors = UINT_MAX >> 9; @@ -202,6 +212,11 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, int ret; struct bio *bio = NULL; unsigned int sz; + sector_t bs_mask; + + bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1; + if ((sector | nr_sects) & bs_mask) + return -EINVAL; while (nr_sects != 0) { bio = next_bio(bio, min(nr_sects, (sector_t)BIO_MAX_PAGES), diff --git a/block/ioctl.c b/block/ioctl.c index ed2397f8de9d..755119c3c1b9 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -225,7 +225,8 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode, unsigned long arg) { uint64_t range[2]; - uint64_t start, len; + struct address_space *mapping; + uint64_t start, end, len; if (!(mode & FMODE_WRITE)) return -EBADF; @@ -235,18 +236,23 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode, start = range[0]; len = range[1]; + end = start + len - 1; if (start & 511) return -EINVAL; if (len & 511) return -EINVAL; - start >>= 9; - len >>= 9; - - if (start + len > (i_size_read(bdev->bd_inode) >> 9)) + if (end >= (uint64_t)i_size_read(bdev->bd_inode)) + return -EINVAL; + if (end < start) return -EINVAL; - return blkdev_issue_zeroout(bdev, start, len, GFP_KERNEL, false); + /* Invalidate the page cache, including dirty pages */ + mapping = bdev->bd_inode->i_mapping; + truncate_inode_pages_range(mapping, start, end); + + return blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL, + false); } static int put_ushort(unsigned long arg, unsigned short val) diff --git a/crypto/crypto_engine.c b/crypto/crypto_engine.c index bfb92ace2c91..6989ba0046df 100644 --- a/crypto/crypto_engine.c +++ b/crypto/crypto_engine.c @@ -47,7 +47,7 @@ static void crypto_pump_requests(struct crypto_engine *engine, /* If another context is idling then defer */ if (engine->idling) { - queue_kthread_work(&engine->kworker, &engine->pump_requests); + kthread_queue_work(&engine->kworker, &engine->pump_requests); goto out; } @@ -58,7 +58,7 @@ static void crypto_pump_requests(struct crypto_engine *engine, /* Only do teardown in the thread */ if (!in_kthread) { - queue_kthread_work(&engine->kworker, + kthread_queue_work(&engine->kworker, &engine->pump_requests); goto out; } @@ -189,7 +189,7 @@ int crypto_transfer_cipher_request(struct crypto_engine *engine, ret = ablkcipher_enqueue_request(&engine->queue, req); if (!engine->busy && need_pump) - queue_kthread_work(&engine->kworker, &engine->pump_requests); + kthread_queue_work(&engine->kworker, &engine->pump_requests); spin_unlock_irqrestore(&engine->queue_lock, flags); return ret; @@ -231,7 +231,7 @@ int crypto_transfer_hash_request(struct crypto_engine *engine, ret = ahash_enqueue_request(&engine->queue, req); if (!engine->busy && need_pump) - queue_kthread_work(&engine->kworker, &engine->pump_requests); + kthread_queue_work(&engine->kworker, &engine->pump_requests); spin_unlock_irqrestore(&engine->queue_lock, flags); return ret; @@ -284,7 +284,7 @@ void crypto_finalize_cipher_request(struct crypto_engine *engine, req->base.complete(&req->base, err); - queue_kthread_work(&engine->kworker, &engine->pump_requests); + kthread_queue_work(&engine->kworker, &engine->pump_requests); } EXPORT_SYMBOL_GPL(crypto_finalize_cipher_request); @@ -321,7 +321,7 @@ void crypto_finalize_hash_request(struct crypto_engine *engine, req->base.complete(&req->base, err); - queue_kthread_work(&engine->kworker, &engine->pump_requests); + kthread_queue_work(&engine->kworker, &engine->pump_requests); } EXPORT_SYMBOL_GPL(crypto_finalize_hash_request); @@ -345,7 +345,7 @@ int crypto_engine_start(struct crypto_engine *engine) engine->running = true; spin_unlock_irqrestore(&engine->queue_lock, flags); - queue_kthread_work(&engine->kworker, &engine->pump_requests); + kthread_queue_work(&engine->kworker, &engine->pump_requests); return 0; } @@ -422,7 +422,7 @@ struct crypto_engine *crypto_engine_alloc_init(struct device *dev, bool rt) crypto_init_queue(&engine->queue, CRYPTO_ENGINE_MAX_QLEN); spin_lock_init(&engine->queue_lock); - init_kthread_worker(&engine->kworker); + kthread_init_worker(&engine->kworker); engine->kworker_task = kthread_run(kthread_worker_fn, &engine->kworker, "%s", engine->name); @@ -430,7 +430,7 @@ struct crypto_engine *crypto_engine_alloc_init(struct device *dev, bool rt) dev_err(dev, "failed to create crypto request pump task\n"); return NULL; } - init_kthread_work(&engine->pump_requests, crypto_pump_work); + kthread_init_work(&engine->pump_requests, crypto_pump_work); if (engine->rt) { dev_info(dev, "will run requests pump with realtime priority\n"); @@ -455,7 +455,7 @@ int crypto_engine_exit(struct crypto_engine *engine) if (ret) return ret; - flush_kthread_worker(&engine->kworker); + kthread_flush_worker(&engine->kworker); kthread_stop(engine->kworker_task); return 0; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index cbdb3b162718..fa1b7a90ba11 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -840,13 +840,13 @@ static void loop_config_discard(struct loop_device *lo) static void loop_unprepare_queue(struct loop_device *lo) { - flush_kthread_worker(&lo->worker); + kthread_flush_worker(&lo->worker); kthread_stop(lo->worker_task); } static int loop_prepare_queue(struct loop_device *lo) { - init_kthread_worker(&lo->worker); + kthread_init_worker(&lo->worker); lo->worker_task = kthread_run(kthread_worker_fn, &lo->worker, "loop%d", lo->lo_number); if (IS_ERR(lo->worker_task)) @@ -1658,7 +1658,7 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx, break; } - queue_kthread_work(&lo->worker, &cmd->work); + kthread_queue_work(&lo->worker, &cmd->work); return BLK_MQ_RQ_QUEUE_OK; } @@ -1696,7 +1696,7 @@ static int loop_init_request(void *data, struct request *rq, struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); cmd->rq = rq; - init_kthread_work(&cmd->work, loop_queue_work); + kthread_init_work(&cmd->work, loop_queue_work); return 0; } diff --git a/drivers/char/random.c b/drivers/char/random.c index 3efb3bf0ab83..d131e152c8ce 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -2100,23 +2100,37 @@ unsigned long get_random_long(void) } EXPORT_SYMBOL(get_random_long); -/* - * randomize_range() returns a start address such that +/** + * randomize_page - Generate a random, page aligned address + * @start: The smallest acceptable address the caller will take. + * @range: The size of the area, starting at @start, within which the + * random address must fall. + * + * If @start + @range would overflow, @range is capped. * - * [...... .....] - * start end + * NOTE: Historical use of randomize_range, which this replaces, presumed that + * @start was already page aligned. We now align it regardless. * - * a with size "len" starting at the return value is inside in the - * area defined by [start, end], but is otherwise randomized. + * Return: A page aligned address within [start, start + range). On error, + * @start is returned. */ unsigned long -randomize_range(unsigned long start, unsigned long end, unsigned long len) +randomize_page(unsigned long start, unsigned long range) { - unsigned long range = end - len - start; + if (!PAGE_ALIGNED(start)) { + range -= PAGE_ALIGN(start) - start; + start = PAGE_ALIGN(start); + } - if (end <= start + len) - return 0; - return PAGE_ALIGN(get_random_int() % range + start); + if (start > ULONG_MAX - range) + range = ULONG_MAX - start; + + range >>= PAGE_SHIFT; + + if (range == 0) + return start; + + return start + (get_random_long() % range << PAGE_SHIFT); } /* Interface for in-kernel drivers of true hardware RNGs. diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 8114744bf30c..d433b1db1fdd 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -38,7 +38,6 @@ #include #include #include -#include #include "../tty/hvc/hvc_console.h" #define is_rproc_enabled IS_ENABLED(CONFIG_REMOTEPROC) diff --git a/drivers/infiniband/sw/rdmavt/cq.c b/drivers/infiniband/sw/rdmavt/cq.c index f2f229efbe64..6d9904a4a0ab 100644 --- a/drivers/infiniband/sw/rdmavt/cq.c +++ b/drivers/infiniband/sw/rdmavt/cq.c @@ -129,7 +129,7 @@ void rvt_cq_enter(struct rvt_cq *cq, struct ib_wc *entry, bool solicited) if (likely(worker)) { cq->notify = RVT_CQ_NONE; cq->triggered++; - queue_kthread_work(worker, &cq->comptask); + kthread_queue_work(worker, &cq->comptask); } } @@ -265,7 +265,7 @@ struct ib_cq *rvt_create_cq(struct ib_device *ibdev, cq->ibcq.cqe = entries; cq->notify = RVT_CQ_NONE; spin_lock_init(&cq->lock); - init_kthread_work(&cq->comptask, send_complete); + kthread_init_work(&cq->comptask, send_complete); cq->queue = wc; ret = &cq->ibcq; @@ -295,7 +295,7 @@ int rvt_destroy_cq(struct ib_cq *ibcq) struct rvt_cq *cq = ibcq_to_rvtcq(ibcq); struct rvt_dev_info *rdi = cq->rdi; - flush_kthread_work(&cq->comptask); + kthread_flush_work(&cq->comptask); spin_lock(&rdi->n_cqs_lock); rdi->n_cqs_allocated--; spin_unlock(&rdi->n_cqs_lock); @@ -514,7 +514,7 @@ int rvt_driver_cq_init(struct rvt_dev_info *rdi) rdi->worker = kzalloc(sizeof(*rdi->worker), GFP_KERNEL); if (!rdi->worker) return -ENOMEM; - init_kthread_worker(rdi->worker); + kthread_init_worker(rdi->worker); task = kthread_create_on_node( kthread_worker_fn, rdi->worker, @@ -547,7 +547,7 @@ void rvt_cq_exit(struct rvt_dev_info *rdi) /* blocks future queuing from send_complete() */ rdi->worker = NULL; smp_wmb(); /* See rdi_cq_enter */ - flush_kthread_worker(worker); + kthread_flush_worker(worker); kthread_stop(worker->task); kfree(worker); } diff --git a/drivers/input/rmi4/rmi_bus.c b/drivers/input/rmi4/rmi_bus.c index 09c769c6e91f..ef8c747c35e7 100644 --- a/drivers/input/rmi4/rmi_bus.c +++ b/drivers/input/rmi4/rmi_bus.c @@ -9,7 +9,6 @@ #include #include -#include #include #include #include diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c index c83bce89028b..4a88312fbd25 100644 --- a/drivers/input/rmi4/rmi_driver.c +++ b/drivers/input/rmi4/rmi_driver.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/input/rmi4/rmi_f01.c b/drivers/input/rmi4/rmi_f01.c index fac81fc9bcf6..b5d2dfc23bad 100644 --- a/drivers/input/rmi4/rmi_f01.c +++ b/drivers/input/rmi4/rmi_f01.c @@ -8,7 +8,6 @@ */ #include -#include #include #include #include diff --git a/drivers/input/rmi4/rmi_f11.c b/drivers/input/rmi4/rmi_f11.c index 20c7134b3d3b..f798f427a46f 100644 --- a/drivers/input/rmi4/rmi_f11.c +++ b/drivers/input/rmi4/rmi_f11.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/irqchip/irq-bcm6345-l1.c b/drivers/irqchip/irq-bcm6345-l1.c index b844c89a9506..daa4ae89e466 100644 --- a/drivers/irqchip/irq-bcm6345-l1.c +++ b/drivers/irqchip/irq-bcm6345-l1.c @@ -52,7 +52,6 @@ #include #include -#include #include #include #include diff --git a/drivers/irqchip/irq-bcm7038-l1.c b/drivers/irqchip/irq-bcm7038-l1.c index 0fea985ef1dc..353c54986211 100644 --- a/drivers/irqchip/irq-bcm7038-l1.c +++ b/drivers/irqchip/irq-bcm7038-l1.c @@ -12,7 +12,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include -#include #include #include #include diff --git a/drivers/irqchip/irq-bcm7120-l2.c b/drivers/irqchip/irq-bcm7120-l2.c index 0ec92631e23c..64c2692070ef 100644 --- a/drivers/irqchip/irq-bcm7120-l2.c +++ b/drivers/irqchip/irq-bcm7120-l2.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/irqchip/irq-brcmstb-l2.c b/drivers/irqchip/irq-brcmstb-l2.c index 1d4a5b46d9ae..bddf169c4b37 100644 --- a/drivers/irqchip/irq-brcmstb-l2.c +++ b/drivers/irqchip/irq-brcmstb-l2.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 5eacce1ef88b..dc75bea0d541 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -581,7 +581,7 @@ static void init_tio(struct dm_rq_target_io *tio, struct request *rq, if (!md->init_tio_pdu) memset(&tio->info, 0, sizeof(tio->info)); if (md->kworker_task) - init_kthread_work(&tio->work, map_tio_request); + kthread_init_work(&tio->work, map_tio_request); } static struct dm_rq_target_io *dm_old_prep_tio(struct request *rq, @@ -831,7 +831,7 @@ static void dm_old_request_fn(struct request_queue *q) tio = tio_from_request(rq); /* Establish tio->ti before queuing work (map_tio_request) */ tio->ti = ti; - queue_kthread_work(&md->kworker, &tio->work); + kthread_queue_work(&md->kworker, &tio->work); BUG_ON(!irqs_disabled()); } } @@ -853,7 +853,7 @@ int dm_old_init_request_queue(struct mapped_device *md) blk_queue_prep_rq(md->queue, dm_old_prep_fn); /* Initialize the request-based DM worker thread */ - init_kthread_worker(&md->kworker); + kthread_init_worker(&md->kworker); md->kworker_task = kthread_run(kthread_worker_fn, &md->kworker, "kdmwork-%s", dm_device_name(md)); if (IS_ERR(md->kworker_task)) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index be35258324c1..147af9536d0c 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1891,7 +1891,7 @@ static void __dm_destroy(struct mapped_device *md, bool wait) spin_unlock_irq(q->queue_lock); if (dm_request_based(md) && md->kworker_task) - flush_kthread_worker(&md->kworker); + kthread_flush_worker(&md->kworker); /* * Take suspend_lock so that presuspend and postsuspend methods @@ -2147,7 +2147,7 @@ static int __dm_suspend(struct mapped_device *md, struct dm_table *map, if (dm_request_based(md)) { dm_stop_queue(md->queue); if (md->kworker_task) - flush_kthread_worker(&md->kworker); + kthread_flush_worker(&md->kworker); } flush_workqueue(md->wq); diff --git a/drivers/media/dvb-frontends/af9013.h b/drivers/media/dvb-frontends/af9013.h index 1dcc936e1661..dcdd163ace85 100644 --- a/drivers/media/dvb-frontends/af9013.h +++ b/drivers/media/dvb-frontends/af9013.h @@ -25,7 +25,6 @@ #ifndef AF9013_H #define AF9013_H -#include #include /* AF9013/5 GPIOs (mostly guessed) diff --git a/drivers/media/dvb-frontends/af9033.h b/drivers/media/dvb-frontends/af9033.h index 6ad22b69a636..5b83e4f96297 100644 --- a/drivers/media/dvb-frontends/af9033.h +++ b/drivers/media/dvb-frontends/af9033.h @@ -22,8 +22,6 @@ #ifndef AF9033_H #define AF9033_H -#include - /* * I2C address (TODO: are these in 8-bit format?) * 0x38, 0x3a, 0x3c, 0x3e diff --git a/drivers/media/dvb-frontends/ascot2e.h b/drivers/media/dvb-frontends/ascot2e.h index 6da4ae6d6cc3..dc61bf7d1b09 100644 --- a/drivers/media/dvb-frontends/ascot2e.h +++ b/drivers/media/dvb-frontends/ascot2e.h @@ -22,7 +22,6 @@ #ifndef __DVB_ASCOT2E_H__ #define __DVB_ASCOT2E_H__ -#include #include #include diff --git a/drivers/media/dvb-frontends/atbm8830.h b/drivers/media/dvb-frontends/atbm8830.h index 5446d13fdfe8..bb862387080f 100644 --- a/drivers/media/dvb-frontends/atbm8830.h +++ b/drivers/media/dvb-frontends/atbm8830.h @@ -22,7 +22,6 @@ #ifndef __ATBM8830_H__ #define __ATBM8830_H__ -#include #include #include diff --git a/drivers/media/dvb-frontends/au8522.h b/drivers/media/dvb-frontends/au8522.h index 78bf3f73e58d..21c51a4c519a 100644 --- a/drivers/media/dvb-frontends/au8522.h +++ b/drivers/media/dvb-frontends/au8522.h @@ -22,7 +22,6 @@ #ifndef __AU8522_H__ #define __AU8522_H__ -#include #include enum au8522_if_freq { diff --git a/drivers/media/dvb-frontends/cx22702.h b/drivers/media/dvb-frontends/cx22702.h index 68b69a7660d2..a1956a9ba406 100644 --- a/drivers/media/dvb-frontends/cx22702.h +++ b/drivers/media/dvb-frontends/cx22702.h @@ -28,7 +28,6 @@ #ifndef CX22702_H #define CX22702_H -#include #include struct cx22702_config { diff --git a/drivers/media/dvb-frontends/cx24113.h b/drivers/media/dvb-frontends/cx24113.h index 962919b9b6e6..194c703611b4 100644 --- a/drivers/media/dvb-frontends/cx24113.h +++ b/drivers/media/dvb-frontends/cx24113.h @@ -22,8 +22,6 @@ #ifndef CX24113_H #define CX24113_H -#include - struct dvb_frontend; struct cx24113_config { diff --git a/drivers/media/dvb-frontends/cx24116.h b/drivers/media/dvb-frontends/cx24116.h index f6dbabc1d62b..9ff8df8d44b8 100644 --- a/drivers/media/dvb-frontends/cx24116.h +++ b/drivers/media/dvb-frontends/cx24116.h @@ -21,7 +21,6 @@ #ifndef CX24116_H #define CX24116_H -#include #include struct cx24116_config { diff --git a/drivers/media/dvb-frontends/cx24117.h b/drivers/media/dvb-frontends/cx24117.h index 1648ab432168..445f13faf63a 100644 --- a/drivers/media/dvb-frontends/cx24117.h +++ b/drivers/media/dvb-frontends/cx24117.h @@ -22,7 +22,6 @@ #ifndef CX24117_H #define CX24117_H -#include #include struct cx24117_config { diff --git a/drivers/media/dvb-frontends/cx24120.h b/drivers/media/dvb-frontends/cx24120.h index f0970423e16f..de4ca9aa0923 100644 --- a/drivers/media/dvb-frontends/cx24120.h +++ b/drivers/media/dvb-frontends/cx24120.h @@ -20,7 +20,6 @@ #ifndef CX24120_H #define CX24120_H -#include #include #include diff --git a/drivers/media/dvb-frontends/cx24123.h b/drivers/media/dvb-frontends/cx24123.h index 975f3c926fe8..aac23444aa9a 100644 --- a/drivers/media/dvb-frontends/cx24123.h +++ b/drivers/media/dvb-frontends/cx24123.h @@ -21,7 +21,6 @@ #ifndef CX24123_H #define CX24123_H -#include #include struct cx24123_config { diff --git a/drivers/media/dvb-frontends/cxd2820r.h b/drivers/media/dvb-frontends/cxd2820r.h index d77afe0b8a9e..f3ff8f6eb3bb 100644 --- a/drivers/media/dvb-frontends/cxd2820r.h +++ b/drivers/media/dvb-frontends/cxd2820r.h @@ -22,7 +22,6 @@ #ifndef CXD2820R_H #define CXD2820R_H -#include #include #define CXD2820R_GPIO_D (0 << 0) /* disable */ diff --git a/drivers/media/dvb-frontends/cxd2841er.h b/drivers/media/dvb-frontends/cxd2841er.h index 62ad5f07390b..7f1acfb8f4f5 100644 --- a/drivers/media/dvb-frontends/cxd2841er.h +++ b/drivers/media/dvb-frontends/cxd2841er.h @@ -22,7 +22,6 @@ #ifndef CXD2841ER_H #define CXD2841ER_H -#include #include enum cxd2841er_xtal { diff --git a/drivers/media/dvb-frontends/dib3000mc.h b/drivers/media/dvb-frontends/dib3000mc.h index b37e69e6a58c..67a6d50865fb 100644 --- a/drivers/media/dvb-frontends/dib3000mc.h +++ b/drivers/media/dvb-frontends/dib3000mc.h @@ -13,8 +13,6 @@ #ifndef DIB3000MC_H #define DIB3000MC_H -#include - #include "dibx000_common.h" struct dib3000mc_config { diff --git a/drivers/media/dvb-frontends/dib7000m.h b/drivers/media/dvb-frontends/dib7000m.h index 6468c278cc4d..8f84dfa9bb58 100644 --- a/drivers/media/dvb-frontends/dib7000m.h +++ b/drivers/media/dvb-frontends/dib7000m.h @@ -1,8 +1,6 @@ #ifndef DIB7000M_H #define DIB7000M_H -#include - #include "dibx000_common.h" struct dib7000m_config { diff --git a/drivers/media/dvb-frontends/dib7000p.h b/drivers/media/dvb-frontends/dib7000p.h index baa278928cf3..205fbbff632b 100644 --- a/drivers/media/dvb-frontends/dib7000p.h +++ b/drivers/media/dvb-frontends/dib7000p.h @@ -1,8 +1,6 @@ #ifndef DIB7000P_H #define DIB7000P_H -#include - #include "dibx000_common.h" struct dib7000p_config { diff --git a/drivers/media/dvb-frontends/drxd.h b/drivers/media/dvb-frontends/drxd.h index a47c22d6667e..f0507cdbb503 100644 --- a/drivers/media/dvb-frontends/drxd.h +++ b/drivers/media/dvb-frontends/drxd.h @@ -24,7 +24,6 @@ #ifndef _DRXD_H_ #define _DRXD_H_ -#include #include #include diff --git a/drivers/media/dvb-frontends/drxk.h b/drivers/media/dvb-frontends/drxk.h index 8f0b9eec528f..a629897eb905 100644 --- a/drivers/media/dvb-frontends/drxk.h +++ b/drivers/media/dvb-frontends/drxk.h @@ -1,7 +1,6 @@ #ifndef _DRXK_H_ #define _DRXK_H_ -#include #include #include diff --git a/drivers/media/dvb-frontends/ds3000.h b/drivers/media/dvb-frontends/ds3000.h index 153169da9017..82e8c2531f26 100644 --- a/drivers/media/dvb-frontends/ds3000.h +++ b/drivers/media/dvb-frontends/ds3000.h @@ -22,7 +22,6 @@ #ifndef DS3000_H #define DS3000_H -#include #include struct ds3000_config { diff --git a/drivers/media/dvb-frontends/dvb_dummy_fe.h b/drivers/media/dvb-frontends/dvb_dummy_fe.h index 15e4ceab869a..50f1af512b62 100644 --- a/drivers/media/dvb-frontends/dvb_dummy_fe.h +++ b/drivers/media/dvb-frontends/dvb_dummy_fe.h @@ -22,7 +22,6 @@ #ifndef DVB_DUMMY_FE_H #define DVB_DUMMY_FE_H -#include #include #include "dvb_frontend.h" diff --git a/drivers/media/dvb-frontends/ec100.h b/drivers/media/dvb-frontends/ec100.h index 9544bab5cd1d..e894bdcf35a3 100644 --- a/drivers/media/dvb-frontends/ec100.h +++ b/drivers/media/dvb-frontends/ec100.h @@ -22,7 +22,6 @@ #ifndef EC100_H #define EC100_H -#include #include struct ec100_config { diff --git a/drivers/media/dvb-frontends/hd29l2.h b/drivers/media/dvb-frontends/hd29l2.h index 48e9ab74c883..a14d6f36dbf6 100644 --- a/drivers/media/dvb-frontends/hd29l2.h +++ b/drivers/media/dvb-frontends/hd29l2.h @@ -23,7 +23,6 @@ #ifndef HD29L2_H #define HD29L2_H -#include #include struct hd29l2_config { diff --git a/drivers/media/dvb-frontends/helene.h b/drivers/media/dvb-frontends/helene.h index e1b9224cfc55..333615491d9e 100644 --- a/drivers/media/dvb-frontends/helene.h +++ b/drivers/media/dvb-frontends/helene.h @@ -21,7 +21,6 @@ #ifndef __DVB_HELENE_H__ #define __DVB_HELENE_H__ -#include #include #include diff --git a/drivers/media/dvb-frontends/horus3a.h b/drivers/media/dvb-frontends/horus3a.h index c1e2d1834b78..672a556df71a 100644 --- a/drivers/media/dvb-frontends/horus3a.h +++ b/drivers/media/dvb-frontends/horus3a.h @@ -22,7 +22,6 @@ #ifndef __DVB_HORUS3A_H__ #define __DVB_HORUS3A_H__ -#include #include #include diff --git a/drivers/media/dvb-frontends/ix2505v.h b/drivers/media/dvb-frontends/ix2505v.h index af107a2dd357..5eab39744b23 100644 --- a/drivers/media/dvb-frontends/ix2505v.h +++ b/drivers/media/dvb-frontends/ix2505v.h @@ -20,7 +20,6 @@ #ifndef DVB_IX2505V_H #define DVB_IX2505V_H -#include #include #include "dvb_frontend.h" diff --git a/drivers/media/dvb-frontends/lg2160.h b/drivers/media/dvb-frontends/lg2160.h index d20bd909de39..8c74ddc6b88a 100644 --- a/drivers/media/dvb-frontends/lg2160.h +++ b/drivers/media/dvb-frontends/lg2160.h @@ -22,7 +22,6 @@ #ifndef _LG2160_H_ #define _LG2160_H_ -#include #include #include "dvb_frontend.h" diff --git a/drivers/media/dvb-frontends/lgdt3305.h b/drivers/media/dvb-frontends/lgdt3305.h index f91a1b49ce2f..e7dceb60e572 100644 --- a/drivers/media/dvb-frontends/lgdt3305.h +++ b/drivers/media/dvb-frontends/lgdt3305.h @@ -22,7 +22,6 @@ #ifndef _LGDT3305_H_ #define _LGDT3305_H_ -#include #include #include "dvb_frontend.h" diff --git a/drivers/media/dvb-frontends/lgs8gl5.h b/drivers/media/dvb-frontends/lgs8gl5.h index a5b3faf121f0..f36a7fd0b102 100644 --- a/drivers/media/dvb-frontends/lgs8gl5.h +++ b/drivers/media/dvb-frontends/lgs8gl5.h @@ -23,7 +23,6 @@ #ifndef LGS8GL5_H #define LGS8GL5_H -#include #include struct lgs8gl5_config { diff --git a/drivers/media/dvb-frontends/lgs8gxx.h b/drivers/media/dvb-frontends/lgs8gxx.h index 368c9928ef7f..7519c0210399 100644 --- a/drivers/media/dvb-frontends/lgs8gxx.h +++ b/drivers/media/dvb-frontends/lgs8gxx.h @@ -26,7 +26,6 @@ #ifndef __LGS8GXX_H__ #define __LGS8GXX_H__ -#include #include #include diff --git a/drivers/media/dvb-frontends/lnbh24.h b/drivers/media/dvb-frontends/lnbh24.h index a088b8ec1e53..24431dfdce1f 100644 --- a/drivers/media/dvb-frontends/lnbh24.h +++ b/drivers/media/dvb-frontends/lnbh24.h @@ -23,8 +23,6 @@ #ifndef _LNBH24_H #define _LNBH24_H -#include - /* system register bits */ #define LNBH24_OLF 0x01 #define LNBH24_OTF 0x02 diff --git a/drivers/media/dvb-frontends/lnbh25.h b/drivers/media/dvb-frontends/lnbh25.h index 1f329ef05acc..f13fd0308b3e 100644 --- a/drivers/media/dvb-frontends/lnbh25.h +++ b/drivers/media/dvb-frontends/lnbh25.h @@ -22,7 +22,6 @@ #define LNBH25_H #include -#include #include /* 22 kHz tone enabled. Tone output controlled by DSQIN pin */ diff --git a/drivers/media/dvb-frontends/lnbp21.h b/drivers/media/dvb-frontends/lnbp21.h index cd9101f6e579..4bb6439068ec 100644 --- a/drivers/media/dvb-frontends/lnbp21.h +++ b/drivers/media/dvb-frontends/lnbp21.h @@ -27,8 +27,6 @@ #ifndef _LNBP21_H #define _LNBP21_H -#include - /* system register bits */ /* [RO] 0=OK; 1=over current limit flag */ #define LNBP21_OLF 0x01 diff --git a/drivers/media/dvb-frontends/lnbp22.h b/drivers/media/dvb-frontends/lnbp22.h index 5d01d92814c2..0cb72126c498 100644 --- a/drivers/media/dvb-frontends/lnbp22.h +++ b/drivers/media/dvb-frontends/lnbp22.h @@ -28,8 +28,6 @@ #ifndef _LNBP22_H #define _LNBP22_H -#include - /* Enable */ #define LNBP22_EN 0x10 /* Voltage selection */ diff --git a/drivers/media/dvb-frontends/m88rs2000.h b/drivers/media/dvb-frontends/m88rs2000.h index de7430178e9e..1a313b0f5875 100644 --- a/drivers/media/dvb-frontends/m88rs2000.h +++ b/drivers/media/dvb-frontends/m88rs2000.h @@ -20,7 +20,6 @@ #ifndef M88RS2000_H #define M88RS2000_H -#include #include #include "dvb_frontend.h" diff --git a/drivers/media/dvb-frontends/mb86a20s.h b/drivers/media/dvb-frontends/mb86a20s.h index a113282d6956..dfb02db2126c 100644 --- a/drivers/media/dvb-frontends/mb86a20s.h +++ b/drivers/media/dvb-frontends/mb86a20s.h @@ -16,7 +16,6 @@ #ifndef MB86A20S_H #define MB86A20S_H -#include #include /** diff --git a/drivers/media/dvb-frontends/s5h1409.h b/drivers/media/dvb-frontends/s5h1409.h index f58b9ca5557a..b38557c451b9 100644 --- a/drivers/media/dvb-frontends/s5h1409.h +++ b/drivers/media/dvb-frontends/s5h1409.h @@ -22,7 +22,6 @@ #ifndef __S5H1409_H__ #define __S5H1409_H__ -#include #include struct s5h1409_config { diff --git a/drivers/media/dvb-frontends/s5h1411.h b/drivers/media/dvb-frontends/s5h1411.h index f3a87f7ec360..791bab0e16e9 100644 --- a/drivers/media/dvb-frontends/s5h1411.h +++ b/drivers/media/dvb-frontends/s5h1411.h @@ -22,7 +22,6 @@ #ifndef __S5H1411_H__ #define __S5H1411_H__ -#include #include #define S5H1411_I2C_TOP_ADDR (0x32 >> 1) diff --git a/drivers/media/dvb-frontends/s5h1432.h b/drivers/media/dvb-frontends/s5h1432.h index f490c5ee5801..b81c9bd4e422 100644 --- a/drivers/media/dvb-frontends/s5h1432.h +++ b/drivers/media/dvb-frontends/s5h1432.h @@ -22,7 +22,6 @@ #ifndef __S5H1432_H__ #define __S5H1432_H__ -#include #include #define S5H1432_I2C_TOP_ADDR (0x02 >> 1) diff --git a/drivers/media/dvb-frontends/s921.h b/drivers/media/dvb-frontends/s921.h index f5b722d8081b..a47ed894d4ae 100644 --- a/drivers/media/dvb-frontends/s921.h +++ b/drivers/media/dvb-frontends/s921.h @@ -17,7 +17,6 @@ #ifndef S921_H #define S921_H -#include #include struct s921_config { diff --git a/drivers/media/dvb-frontends/si21xx.h b/drivers/media/dvb-frontends/si21xx.h index ef5f351ca68e..b1be62f1983a 100644 --- a/drivers/media/dvb-frontends/si21xx.h +++ b/drivers/media/dvb-frontends/si21xx.h @@ -1,7 +1,6 @@ #ifndef SI21XX_H #define SI21XX_H -#include #include #include "dvb_frontend.h" diff --git a/drivers/media/dvb-frontends/sp2.h b/drivers/media/dvb-frontends/sp2.h index 6cceea022d49..3901cd74b3f7 100644 --- a/drivers/media/dvb-frontends/sp2.h +++ b/drivers/media/dvb-frontends/sp2.h @@ -17,7 +17,6 @@ #ifndef SP2_H #define SP2_H -#include #include "dvb_ca_en50221.h" /* diff --git a/drivers/media/dvb-frontends/stb6000.h b/drivers/media/dvb-frontends/stb6000.h index da581b652cb9..78e75dfc317f 100644 --- a/drivers/media/dvb-frontends/stb6000.h +++ b/drivers/media/dvb-frontends/stb6000.h @@ -23,7 +23,6 @@ #ifndef __DVB_STB6000_H__ #define __DVB_STB6000_H__ -#include #include #include "dvb_frontend.h" diff --git a/drivers/media/dvb-frontends/stv0288.h b/drivers/media/dvb-frontends/stv0288.h index b58603c00c80..803acb917282 100644 --- a/drivers/media/dvb-frontends/stv0288.h +++ b/drivers/media/dvb-frontends/stv0288.h @@ -27,7 +27,6 @@ #ifndef STV0288_H #define STV0288_H -#include #include #include "dvb_frontend.h" diff --git a/drivers/media/dvb-frontends/stv0367.h b/drivers/media/dvb-frontends/stv0367.h index 92b3e85fb818..b88166a9716f 100644 --- a/drivers/media/dvb-frontends/stv0367.h +++ b/drivers/media/dvb-frontends/stv0367.h @@ -26,7 +26,6 @@ #ifndef STV0367_H #define STV0367_H -#include #include #include "dvb_frontend.h" diff --git a/drivers/media/dvb-frontends/stv0900.h b/drivers/media/dvb-frontends/stv0900.h index c90bf00ea9ce..9ca2da90c7d7 100644 --- a/drivers/media/dvb-frontends/stv0900.h +++ b/drivers/media/dvb-frontends/stv0900.h @@ -26,7 +26,6 @@ #ifndef STV0900_H #define STV0900_H -#include #include #include "dvb_frontend.h" diff --git a/drivers/media/dvb-frontends/stv6110.h b/drivers/media/dvb-frontends/stv6110.h index f3c8a5c6b77d..4604f793d954 100644 --- a/drivers/media/dvb-frontends/stv6110.h +++ b/drivers/media/dvb-frontends/stv6110.h @@ -25,7 +25,6 @@ #ifndef __DVB_STV6110_H__ #define __DVB_STV6110_H__ -#include #include #include "dvb_frontend.h" diff --git a/drivers/media/dvb-frontends/tda10048.h b/drivers/media/dvb-frontends/tda10048.h index bc77a7311de1..a2cebb0cceba 100644 --- a/drivers/media/dvb-frontends/tda10048.h +++ b/drivers/media/dvb-frontends/tda10048.h @@ -22,7 +22,6 @@ #ifndef TDA10048_H #define TDA10048_H -#include #include #include diff --git a/drivers/media/dvb-frontends/tda18271c2dd.h b/drivers/media/dvb-frontends/tda18271c2dd.h index 7ebd8eaff4eb..e6ccf240f54c 100644 --- a/drivers/media/dvb-frontends/tda18271c2dd.h +++ b/drivers/media/dvb-frontends/tda18271c2dd.h @@ -1,8 +1,6 @@ #ifndef _TDA18271C2DD_H_ #define _TDA18271C2DD_H_ -#include - #if IS_REACHABLE(CONFIG_DVB_TDA18271C2DD) struct dvb_frontend *tda18271c2dd_attach(struct dvb_frontend *fe, struct i2c_adapter *i2c, u8 adr); diff --git a/drivers/media/dvb-frontends/ts2020.h b/drivers/media/dvb-frontends/ts2020.h index 9220e5cf0d21..facc54f0a6af 100644 --- a/drivers/media/dvb-frontends/ts2020.h +++ b/drivers/media/dvb-frontends/ts2020.h @@ -22,7 +22,6 @@ #ifndef TS2020_H #define TS2020_H -#include #include struct ts2020_config { diff --git a/drivers/media/dvb-frontends/zl10036.h b/drivers/media/dvb-frontends/zl10036.h index 670e76a654ee..c568d8d59de3 100644 --- a/drivers/media/dvb-frontends/zl10036.h +++ b/drivers/media/dvb-frontends/zl10036.h @@ -21,7 +21,6 @@ #ifndef DVB_ZL10036_H #define DVB_ZL10036_H -#include #include #include "dvb_frontend.h" diff --git a/drivers/media/dvb-frontends/zl10039.h b/drivers/media/dvb-frontends/zl10039.h index 070929444e71..66e708569375 100644 --- a/drivers/media/dvb-frontends/zl10039.h +++ b/drivers/media/dvb-frontends/zl10039.h @@ -22,8 +22,6 @@ #ifndef ZL10039_H #define ZL10039_H -#include - #if IS_REACHABLE(CONFIG_DVB_ZL10039) struct dvb_frontend *zl10039_attach(struct dvb_frontend *fe, u8 i2c_addr, diff --git a/drivers/media/pci/cx23885/altera-ci.h b/drivers/media/pci/cx23885/altera-ci.h index 6c511723fd1b..57a40c84b46e 100644 --- a/drivers/media/pci/cx23885/altera-ci.h +++ b/drivers/media/pci/cx23885/altera-ci.h @@ -20,8 +20,6 @@ #ifndef __ALTERA_CI_H #define __ALTERA_CI_H -#include - #define ALT_DATA 0x000000ff #define ALT_TDI 0x00008000 #define ALT_TDO 0x00004000 diff --git a/drivers/media/pci/ivtv/ivtv-driver.c b/drivers/media/pci/ivtv/ivtv-driver.c index 374033a5bdaf..ee48c3e09de4 100644 --- a/drivers/media/pci/ivtv/ivtv-driver.c +++ b/drivers/media/pci/ivtv/ivtv-driver.c @@ -750,7 +750,7 @@ static int ivtv_init_struct1(struct ivtv *itv) spin_lock_init(&itv->lock); spin_lock_init(&itv->dma_reg_lock); - init_kthread_worker(&itv->irq_worker); + kthread_init_worker(&itv->irq_worker); itv->irq_worker_task = kthread_run(kthread_worker_fn, &itv->irq_worker, "%s", itv->v4l2_dev.name); if (IS_ERR(itv->irq_worker_task)) { @@ -760,7 +760,7 @@ static int ivtv_init_struct1(struct ivtv *itv) /* must use the FIFO scheduler as it is realtime sensitive */ sched_setscheduler(itv->irq_worker_task, SCHED_FIFO, ¶m); - init_kthread_work(&itv->irq_work, ivtv_irq_work_handler); + kthread_init_work(&itv->irq_work, ivtv_irq_work_handler); /* Initial settings */ itv->cxhdl.port = CX2341X_PORT_MEMORY; @@ -1441,7 +1441,7 @@ static void ivtv_remove(struct pci_dev *pdev) del_timer_sync(&itv->dma_timer); /* Kill irq worker */ - flush_kthread_worker(&itv->irq_worker); + kthread_flush_worker(&itv->irq_worker); kthread_stop(itv->irq_worker_task); ivtv_streams_cleanup(itv); diff --git a/drivers/media/pci/ivtv/ivtv-irq.c b/drivers/media/pci/ivtv/ivtv-irq.c index 36ca2d67c812..6efe1f71262c 100644 --- a/drivers/media/pci/ivtv/ivtv-irq.c +++ b/drivers/media/pci/ivtv/ivtv-irq.c @@ -1062,7 +1062,7 @@ irqreturn_t ivtv_irq_handler(int irq, void *dev_id) } if (test_and_clear_bit(IVTV_F_I_HAVE_WORK, &itv->i_flags)) { - queue_kthread_work(&itv->irq_worker, &itv->irq_work); + kthread_queue_work(&itv->irq_worker, &itv->irq_work); } spin_unlock(&itv->dma_reg_lock); diff --git a/drivers/media/tuners/fc0011.h b/drivers/media/tuners/fc0011.h index 81bb568d6943..438cf897acd1 100644 --- a/drivers/media/tuners/fc0011.h +++ b/drivers/media/tuners/fc0011.h @@ -1,7 +1,6 @@ #ifndef LINUX_FC0011_H_ #define LINUX_FC0011_H_ -#include #include "dvb_frontend.h" diff --git a/drivers/media/tuners/fc0012.h b/drivers/media/tuners/fc0012.h index 9ad32859bab0..4a23e418daf0 100644 --- a/drivers/media/tuners/fc0012.h +++ b/drivers/media/tuners/fc0012.h @@ -21,7 +21,6 @@ #ifndef _FC0012_H_ #define _FC0012_H_ -#include #include "dvb_frontend.h" #include "fc001x-common.h" diff --git a/drivers/media/tuners/fc0013.h b/drivers/media/tuners/fc0013.h index e130bd7a3230..8c34105c9383 100644 --- a/drivers/media/tuners/fc0013.h +++ b/drivers/media/tuners/fc0013.h @@ -22,7 +22,6 @@ #ifndef _FC0013_H_ #define _FC0013_H_ -#include #include "dvb_frontend.h" #include "fc001x-common.h" diff --git a/drivers/media/tuners/max2165.h b/drivers/media/tuners/max2165.h index 5054f01a78fb..aadd9fea59e4 100644 --- a/drivers/media/tuners/max2165.h +++ b/drivers/media/tuners/max2165.h @@ -22,8 +22,6 @@ #ifndef __MAX2165_H__ #define __MAX2165_H__ -#include - struct dvb_frontend; struct i2c_adapter; diff --git a/drivers/media/tuners/mc44s803.h b/drivers/media/tuners/mc44s803.h index b3e614be657d..6b40df339284 100644 --- a/drivers/media/tuners/mc44s803.h +++ b/drivers/media/tuners/mc44s803.h @@ -22,8 +22,6 @@ #ifndef MC44S803_H #define MC44S803_H -#include - struct dvb_frontend; struct i2c_adapter; diff --git a/drivers/media/tuners/mxl5005s.h b/drivers/media/tuners/mxl5005s.h index 5764b12c5c7c..d842734f2dcd 100644 --- a/drivers/media/tuners/mxl5005s.h +++ b/drivers/media/tuners/mxl5005s.h @@ -23,8 +23,6 @@ #ifndef __MXL5005S_H #define __MXL5005S_H -#include - #include #include "dvb_frontend.h" diff --git a/drivers/media/tuners/r820t.h b/drivers/media/tuners/r820t.h index b1e5661af1c7..fdcab91405de 100644 --- a/drivers/media/tuners/r820t.h +++ b/drivers/media/tuners/r820t.h @@ -21,7 +21,6 @@ #ifndef R820T_H #define R820T_H -#include #include "dvb_frontend.h" enum r820t_chip { diff --git a/drivers/media/tuners/si2157.h b/drivers/media/tuners/si2157.h index 5f1a60bf7ced..76807f5b3cf8 100644 --- a/drivers/media/tuners/si2157.h +++ b/drivers/media/tuners/si2157.h @@ -17,7 +17,6 @@ #ifndef SI2157_H #define SI2157_H -#include #include #include "dvb_frontend.h" diff --git a/drivers/media/tuners/tda18212.h b/drivers/media/tuners/tda18212.h index e58c9096d79c..6391dafd0c9d 100644 --- a/drivers/media/tuners/tda18212.h +++ b/drivers/media/tuners/tda18212.h @@ -21,7 +21,6 @@ #ifndef TDA18212_H #define TDA18212_H -#include #include "dvb_frontend.h" struct tda18212_config { diff --git a/drivers/media/tuners/tda18218.h b/drivers/media/tuners/tda18218.h index 1eacb4f84e93..076b5f2e888d 100644 --- a/drivers/media/tuners/tda18218.h +++ b/drivers/media/tuners/tda18218.h @@ -21,7 +21,6 @@ #ifndef TDA18218_H #define TDA18218_H -#include #include "dvb_frontend.h" struct tda18218_config { diff --git a/drivers/media/tuners/xc5000.h b/drivers/media/tuners/xc5000.h index 00ba29e21fb9..336bd49eb09b 100644 --- a/drivers/media/tuners/xc5000.h +++ b/drivers/media/tuners/xc5000.h @@ -22,7 +22,6 @@ #ifndef __XC5000_H__ #define __XC5000_H__ -#include #include struct dvb_frontend; diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.h b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.h index 7065aca81252..e6eae9d88e9f 100644 --- a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.h +++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.h @@ -21,7 +21,6 @@ #ifndef __MXL111SF_DEMOD_H__ #define __MXL111SF_DEMOD_H__ -#include #include "dvb_frontend.h" #include "mxl111sf.h" diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h index 509b55071218..e96d9a444ed1 100644 --- a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h +++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.h @@ -21,7 +21,6 @@ #ifndef __MXL111SF_TUNER_H__ #define __MXL111SF_TUNER_H__ -#include #include "dvb_frontend.h" #include "mxl111sf.h" diff --git a/drivers/media/usb/dvb-usb/dibusb-common.c b/drivers/media/usb/dvb-usb/dibusb-common.c index 4b08c2a47ae2..18ed3bfbb5e2 100644 --- a/drivers/media/usb/dvb-usb/dibusb-common.c +++ b/drivers/media/usb/dvb-usb/dibusb-common.c @@ -9,7 +9,6 @@ * see Documentation/dvb/README.dvb-usb for more information */ -#include #include "dibusb.h" /* Max transfer size done by I2C transfer functions */ diff --git a/drivers/media/usb/hdpvr/hdpvr-video.c b/drivers/media/usb/hdpvr/hdpvr-video.c index 6d43d75493ea..474c11e1d495 100644 --- a/drivers/media/usb/hdpvr/hdpvr-video.c +++ b/drivers/media/usb/hdpvr/hdpvr-video.c @@ -10,7 +10,6 @@ */ #include -#include #include #include #include diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 4f270482cfd0..d46e4adf6d2b 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -39,7 +39,6 @@ #include #include #include -#include #include #include diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index c1f34f04e338..fccdd49bb964 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -30,7 +30,6 @@ #include #include #include -#include #include "mtdcore.h" diff --git a/drivers/net/dsa/b53/b53_mmap.c b/drivers/net/dsa/b53/b53_mmap.c index cc9e6bd83e0e..76fb8552c9d9 100644 --- a/drivers/net/dsa/b53/b53_mmap.c +++ b/drivers/net/dsa/b53/b53_mmap.c @@ -17,7 +17,6 @@ */ #include -#include #include #include #include diff --git a/drivers/net/ethernet/microchip/encx24j600.c b/drivers/net/ethernet/microchip/encx24j600.c index 42e34076d2de..b14f0305aa31 100644 --- a/drivers/net/ethernet/microchip/encx24j600.c +++ b/drivers/net/ethernet/microchip/encx24j600.c @@ -821,7 +821,7 @@ static void encx24j600_set_multicast_list(struct net_device *dev) } if (oldfilter != priv->rxfilter) - queue_kthread_work(&priv->kworker, &priv->setrx_work); + kthread_queue_work(&priv->kworker, &priv->setrx_work); } static void encx24j600_hw_tx(struct encx24j600_priv *priv) @@ -879,7 +879,7 @@ static netdev_tx_t encx24j600_tx(struct sk_buff *skb, struct net_device *dev) /* Remember the skb for deferred processing */ priv->tx_skb = skb; - queue_kthread_work(&priv->kworker, &priv->tx_work); + kthread_queue_work(&priv->kworker, &priv->tx_work); return NETDEV_TX_OK; } @@ -1037,9 +1037,9 @@ static int encx24j600_spi_probe(struct spi_device *spi) goto out_free; } - init_kthread_worker(&priv->kworker); - init_kthread_work(&priv->tx_work, encx24j600_tx_proc); - init_kthread_work(&priv->setrx_work, encx24j600_setrx_proc); + kthread_init_worker(&priv->kworker); + kthread_init_work(&priv->tx_work, encx24j600_tx_proc); + kthread_init_work(&priv->setrx_work, encx24j600_setrx_proc); priv->kworker_task = kthread_run(kthread_worker_fn, &priv->kworker, "encx24j600"); diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c index e15bf84fc6b2..0ac449acaf5b 100644 --- a/drivers/net/ethernet/sun/ldmvsw.c +++ b/drivers/net/ethernet/sun/ldmvsw.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c index 37ab46cdbec4..d2349a1bc6ba 100644 --- a/drivers/net/ethernet/wiznet/w5100.c +++ b/drivers/net/ethernet/wiznet/w5100.c @@ -9,7 +9,6 @@ #include #include -#include #include #include #include diff --git a/drivers/net/ethernet/wiznet/w5300.c b/drivers/net/ethernet/wiznet/w5300.c index 0b37ce9f28f1..ca31a57dbc86 100644 --- a/drivers/net/ethernet/wiznet/w5300.c +++ b/drivers/net/ethernet/wiznet/w5300.c @@ -10,7 +10,6 @@ #include #include -#include #include #include #include diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 68ef1875e8a8..0fc99f0f2571 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -515,7 +515,8 @@ static int nvme_map_data(struct nvme_dev *dev, struct request *req, goto out; ret = BLK_MQ_RQ_QUEUE_BUSY; - if (!dma_map_sg(dev->dev, iod->sg, iod->nents, dma_dir)) + if (!dma_map_sg_attrs(dev->dev, iod->sg, iod->nents, dma_dir, + DMA_ATTR_NO_WARN)) goto out; if (!nvme_setup_prps(dev, req, size)) diff --git a/drivers/pps/Kconfig b/drivers/pps/Kconfig index 7512e98e9311..564a51abeece 100644 --- a/drivers/pps/Kconfig +++ b/drivers/pps/Kconfig @@ -31,7 +31,7 @@ config PPS_DEBUG config NTP_PPS bool "PPS kernel consumer support" - depends on !NO_HZ + depends on !NO_HZ_COMMON help This option adds support for direct in-kernel time synchronization using an external PPS signal. diff --git a/drivers/rapidio/rio_cm.c b/drivers/rapidio/rio_cm.c index cebc296463ad..bad0e0ea4f30 100644 --- a/drivers/rapidio/rio_cm.c +++ b/drivers/rapidio/rio_cm.c @@ -1841,24 +1841,19 @@ static int cm_chan_msg_send(void __user *arg) { struct rio_cm_msg msg; void *buf; - int ret = 0; + int ret; if (copy_from_user(&msg, arg, sizeof(msg))) return -EFAULT; if (msg.size > RIO_MAX_MSG_SIZE) return -EINVAL; - buf = kmalloc(msg.size, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - if (copy_from_user(buf, (void __user *)(uintptr_t)msg.msg, msg.size)) { - ret = -EFAULT; - goto out; - } + buf = memdup_user((void __user *)(uintptr_t)msg.msg, msg.size); + if (IS_ERR(buf)) + return PTR_ERR(buf); ret = riocm_ch_send(msg.ch_num, buf, msg.size); -out: + kfree(buf); return ret; } diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 8146ccd35a1a..5787b723b593 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1112,7 +1112,7 @@ static void __spi_pump_messages(struct spi_master *master, bool in_kthread) /* If another context is idling the device then defer */ if (master->idling) { - queue_kthread_work(&master->kworker, &master->pump_messages); + kthread_queue_work(&master->kworker, &master->pump_messages); spin_unlock_irqrestore(&master->queue_lock, flags); return; } @@ -1126,7 +1126,7 @@ static void __spi_pump_messages(struct spi_master *master, bool in_kthread) /* Only do teardown in the thread */ if (!in_kthread) { - queue_kthread_work(&master->kworker, + kthread_queue_work(&master->kworker, &master->pump_messages); spin_unlock_irqrestore(&master->queue_lock, flags); return; @@ -1250,7 +1250,7 @@ static int spi_init_queue(struct spi_master *master) master->running = false; master->busy = false; - init_kthread_worker(&master->kworker); + kthread_init_worker(&master->kworker); master->kworker_task = kthread_run(kthread_worker_fn, &master->kworker, "%s", dev_name(&master->dev)); @@ -1258,7 +1258,7 @@ static int spi_init_queue(struct spi_master *master) dev_err(&master->dev, "failed to create message pump task\n"); return PTR_ERR(master->kworker_task); } - init_kthread_work(&master->pump_messages, spi_pump_messages); + kthread_init_work(&master->pump_messages, spi_pump_messages); /* * Master config will indicate if this controller should run the @@ -1331,7 +1331,7 @@ void spi_finalize_current_message(struct spi_master *master) spin_lock_irqsave(&master->queue_lock, flags); master->cur_msg = NULL; master->cur_msg_prepared = false; - queue_kthread_work(&master->kworker, &master->pump_messages); + kthread_queue_work(&master->kworker, &master->pump_messages); spin_unlock_irqrestore(&master->queue_lock, flags); trace_spi_message_done(mesg); @@ -1357,7 +1357,7 @@ static int spi_start_queue(struct spi_master *master) master->cur_msg = NULL; spin_unlock_irqrestore(&master->queue_lock, flags); - queue_kthread_work(&master->kworker, &master->pump_messages); + kthread_queue_work(&master->kworker, &master->pump_messages); return 0; } @@ -1404,7 +1404,7 @@ static int spi_destroy_queue(struct spi_master *master) ret = spi_stop_queue(master); /* - * flush_kthread_worker will block until all work is done. + * kthread_flush_worker will block until all work is done. * If the reason that stop_queue timed out is that the work will never * finish, then it does no good to call flush/stop thread, so * return anyway. @@ -1414,7 +1414,7 @@ static int spi_destroy_queue(struct spi_master *master) return ret; } - flush_kthread_worker(&master->kworker); + kthread_flush_worker(&master->kworker); kthread_stop(master->kworker_task); return 0; @@ -1438,7 +1438,7 @@ static int __spi_queued_transfer(struct spi_device *spi, list_add_tail(&msg->queue, &master->queue); if (!master->busy && need_pump) - queue_kthread_work(&master->kworker, &master->pump_messages); + kthread_queue_work(&master->kworker, &master->pump_messages); spin_unlock_irqrestore(&master->queue_lock, flags); return 0; diff --git a/drivers/staging/lustre/lustre/llite/vvp_page.c b/drivers/staging/lustre/lustre/llite/vvp_page.c index 5d79efc1aafe..046e84d7a158 100644 --- a/drivers/staging/lustre/lustre/llite/vvp_page.c +++ b/drivers/staging/lustre/lustre/llite/vvp_page.c @@ -241,10 +241,7 @@ static void vvp_vmpage_error(struct inode *inode, struct page *vmpage, int ioret obj->vob_discard_page_warned = 0; } else { SetPageError(vmpage); - if (ioret == -ENOSPC) - set_bit(AS_ENOSPC, &inode->i_mapping->flags); - else - set_bit(AS_EIO, &inode->i_mapping->flags); + mapping_set_error(inode->i_mapping, ioret); if ((ioret == -ESHUTDOWN || ioret == -EINTR) && obj->vob_discard_page_warned == 0) { diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index a9d94f7cf683..2675792a8f59 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -708,7 +708,7 @@ static irqreturn_t sc16is7xx_irq(int irq, void *dev_id) { struct sc16is7xx_port *s = (struct sc16is7xx_port *)dev_id; - queue_kthread_work(&s->kworker, &s->irq_work); + kthread_queue_work(&s->kworker, &s->irq_work); return IRQ_HANDLED; } @@ -784,7 +784,7 @@ static void sc16is7xx_ier_clear(struct uart_port *port, u8 bit) one->config.flags |= SC16IS7XX_RECONF_IER; one->config.ier_clear |= bit; - queue_kthread_work(&s->kworker, &one->reg_work); + kthread_queue_work(&s->kworker, &one->reg_work); } static void sc16is7xx_stop_tx(struct uart_port *port) @@ -802,7 +802,7 @@ static void sc16is7xx_start_tx(struct uart_port *port) struct sc16is7xx_port *s = dev_get_drvdata(port->dev); struct sc16is7xx_one *one = to_sc16is7xx_one(port, port); - queue_kthread_work(&s->kworker, &one->tx_work); + kthread_queue_work(&s->kworker, &one->tx_work); } static unsigned int sc16is7xx_tx_empty(struct uart_port *port) @@ -828,7 +828,7 @@ static void sc16is7xx_set_mctrl(struct uart_port *port, unsigned int mctrl) struct sc16is7xx_one *one = to_sc16is7xx_one(port, port); one->config.flags |= SC16IS7XX_RECONF_MD; - queue_kthread_work(&s->kworker, &one->reg_work); + kthread_queue_work(&s->kworker, &one->reg_work); } static void sc16is7xx_break_ctl(struct uart_port *port, int break_state) @@ -957,7 +957,7 @@ static int sc16is7xx_config_rs485(struct uart_port *port, port->rs485 = *rs485; one->config.flags |= SC16IS7XX_RECONF_RS485; - queue_kthread_work(&s->kworker, &one->reg_work); + kthread_queue_work(&s->kworker, &one->reg_work); return 0; } @@ -1030,7 +1030,7 @@ static void sc16is7xx_shutdown(struct uart_port *port) sc16is7xx_power(port, 0); - flush_kthread_worker(&s->kworker); + kthread_flush_worker(&s->kworker); } static const char *sc16is7xx_type(struct uart_port *port) @@ -1176,8 +1176,8 @@ static int sc16is7xx_probe(struct device *dev, s->devtype = devtype; dev_set_drvdata(dev, s); - init_kthread_worker(&s->kworker); - init_kthread_work(&s->irq_work, sc16is7xx_ist); + kthread_init_worker(&s->kworker); + kthread_init_work(&s->irq_work, sc16is7xx_ist); s->kworker_task = kthread_run(kthread_worker_fn, &s->kworker, "sc16is7xx"); if (IS_ERR(s->kworker_task)) { @@ -1234,8 +1234,8 @@ static int sc16is7xx_probe(struct device *dev, SC16IS7XX_EFCR_RXDISABLE_BIT | SC16IS7XX_EFCR_TXDISABLE_BIT); /* Initialize kthread work structs */ - init_kthread_work(&s->p[i].tx_work, sc16is7xx_tx_proc); - init_kthread_work(&s->p[i].reg_work, sc16is7xx_reg_proc); + kthread_init_work(&s->p[i].tx_work, sc16is7xx_tx_proc); + kthread_init_work(&s->p[i].reg_work, sc16is7xx_reg_proc); /* Register port */ uart_add_one_port(&sc16is7xx_uart, &s->p[i].port); @@ -1301,7 +1301,7 @@ static int sc16is7xx_remove(struct device *dev) sc16is7xx_power(&s->p[i].port, 0); } - flush_kthread_worker(&s->kworker); + kthread_flush_worker(&s->kworker); kthread_stop(s->kworker_task); if (!IS_ERR(s->clk)) diff --git a/drivers/usb/early/ehci-dbgp.c b/drivers/usb/early/ehci-dbgp.c index 12731e67d2c7..ea73afb026d8 100644 --- a/drivers/usb/early/ehci-dbgp.c +++ b/drivers/usb/early/ehci-dbgp.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/usb/gadget/udc/bcm63xx_udc.c b/drivers/usb/gadget/udc/bcm63xx_udc.c index f5fccb3e4152..f78503203f42 100644 --- a/drivers/usb/gadget/udc/bcm63xx_udc.c +++ b/drivers/usb/gadget/udc/bcm63xx_udc.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index 35af36253440..d793f548dfe2 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -9,7 +9,6 @@ */ #include -#include #include #include #include diff --git a/fs/afs/write.c b/fs/afs/write.c index 14d506efd1aa..f865c3f05bea 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -398,8 +398,7 @@ no_more: switch (ret) { case -EDQUOT: case -ENOSPC: - set_bit(AS_ENOSPC, - &wb->vnode->vfs_inode.i_mapping->flags); + mapping_set_error(wb->vnode->vfs_inode.i_mapping, -ENOSPC); break; case -EROFS: case -EIO: @@ -409,7 +408,7 @@ no_more: case -ENOMEDIUM: case -ENXIO: afs_kill_pages(wb->vnode, true, first, last); - set_bit(AS_EIO, &wb->vnode->vfs_inode.i_mapping->flags); + mapping_set_error(wb->vnode->vfs_inode.i_mapping, -EIO); break; case -EACCES: case -EPERM: diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h index a439548de785..a1fba4285277 100644 --- a/fs/autofs4/autofs_i.h +++ b/fs/autofs4/autofs_i.h @@ -20,7 +20,8 @@ #define AUTOFS_IOC_COUNT 32 #define AUTOFS_DEV_IOCTL_IOC_FIRST (AUTOFS_DEV_IOCTL_VERSION) -#define AUTOFS_DEV_IOCTL_IOC_COUNT (AUTOFS_IOC_COUNT - 11) +#define AUTOFS_DEV_IOCTL_IOC_COUNT \ + (AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD - AUTOFS_DEV_IOCTL_VERSION_CMD) #include #include @@ -33,8 +34,6 @@ #include #include -/* #define DEBUG */ - #ifdef pr_fmt #undef pr_fmt #endif @@ -111,8 +110,6 @@ struct autofs_sb_info { int max_proto; unsigned long exp_timeout; unsigned int type; - int reghost_enabled; - int needs_reghost; struct super_block *sb; struct mutex wq_mutex; struct mutex pipe_mutex; @@ -271,4 +268,4 @@ static inline void autofs4_del_expiring(struct dentry *dentry) } } -extern void autofs4_kill_sb(struct super_block *); +void autofs4_kill_sb(struct super_block *); diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index c7fcc7438843..fc09eb77ddf3 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -75,7 +75,7 @@ static int check_dev_ioctl_version(int cmd, struct autofs_dev_ioctl *param) if ((param->ver_major != AUTOFS_DEV_IOCTL_VERSION_MAJOR) || (param->ver_minor > AUTOFS_DEV_IOCTL_VERSION_MINOR)) { pr_warn("ioctl control interface version mismatch: " - "kernel(%u.%u), user(%u.%u), cmd(%d)\n", + "kernel(%u.%u), user(%u.%u), cmd(0x%08x)\n", AUTOFS_DEV_IOCTL_VERSION_MAJOR, AUTOFS_DEV_IOCTL_VERSION_MINOR, param->ver_major, param->ver_minor, cmd); @@ -172,6 +172,17 @@ static struct autofs_sb_info *autofs_dev_ioctl_sbi(struct file *f) return sbi; } +/* Return autofs dev ioctl version */ +static int autofs_dev_ioctl_version(struct file *fp, + struct autofs_sb_info *sbi, + struct autofs_dev_ioctl *param) +{ + /* This should have already been set. */ + param->ver_major = AUTOFS_DEV_IOCTL_VERSION_MAJOR; + param->ver_minor = AUTOFS_DEV_IOCTL_VERSION_MINOR; + return 0; +} + /* Return autofs module protocol version */ static int autofs_dev_ioctl_protover(struct file *fp, struct autofs_sb_info *sbi, @@ -586,41 +597,25 @@ out: static ioctl_fn lookup_dev_ioctl(unsigned int cmd) { - static struct { - int cmd; - ioctl_fn fn; - } _ioctls[] = { - {cmd_idx(AUTOFS_DEV_IOCTL_VERSION_CMD), NULL}, - {cmd_idx(AUTOFS_DEV_IOCTL_PROTOVER_CMD), - autofs_dev_ioctl_protover}, - {cmd_idx(AUTOFS_DEV_IOCTL_PROTOSUBVER_CMD), - autofs_dev_ioctl_protosubver}, - {cmd_idx(AUTOFS_DEV_IOCTL_OPENMOUNT_CMD), - autofs_dev_ioctl_openmount}, - {cmd_idx(AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD), - autofs_dev_ioctl_closemount}, - {cmd_idx(AUTOFS_DEV_IOCTL_READY_CMD), - autofs_dev_ioctl_ready}, - {cmd_idx(AUTOFS_DEV_IOCTL_FAIL_CMD), - autofs_dev_ioctl_fail}, - {cmd_idx(AUTOFS_DEV_IOCTL_SETPIPEFD_CMD), - autofs_dev_ioctl_setpipefd}, - {cmd_idx(AUTOFS_DEV_IOCTL_CATATONIC_CMD), - autofs_dev_ioctl_catatonic}, - {cmd_idx(AUTOFS_DEV_IOCTL_TIMEOUT_CMD), - autofs_dev_ioctl_timeout}, - {cmd_idx(AUTOFS_DEV_IOCTL_REQUESTER_CMD), - autofs_dev_ioctl_requester}, - {cmd_idx(AUTOFS_DEV_IOCTL_EXPIRE_CMD), - autofs_dev_ioctl_expire}, - {cmd_idx(AUTOFS_DEV_IOCTL_ASKUMOUNT_CMD), - autofs_dev_ioctl_askumount}, - {cmd_idx(AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD), - autofs_dev_ioctl_ismountpoint} + static ioctl_fn _ioctls[] = { + autofs_dev_ioctl_version, + autofs_dev_ioctl_protover, + autofs_dev_ioctl_protosubver, + autofs_dev_ioctl_openmount, + autofs_dev_ioctl_closemount, + autofs_dev_ioctl_ready, + autofs_dev_ioctl_fail, + autofs_dev_ioctl_setpipefd, + autofs_dev_ioctl_catatonic, + autofs_dev_ioctl_timeout, + autofs_dev_ioctl_requester, + autofs_dev_ioctl_expire, + autofs_dev_ioctl_askumount, + autofs_dev_ioctl_ismountpoint, }; unsigned int idx = cmd_idx(cmd); - return (idx >= ARRAY_SIZE(_ioctls)) ? NULL : _ioctls[idx].fn; + return (idx >= ARRAY_SIZE(_ioctls)) ? NULL : _ioctls[idx]; } /* ioctl dispatcher */ @@ -642,7 +637,7 @@ static int _autofs_dev_ioctl(unsigned int command, cmd = _IOC_NR(command); if (_IOC_TYPE(command) != _IOC_TYPE(AUTOFS_DEV_IOCTL_IOC_FIRST) || - cmd - cmd_first >= AUTOFS_DEV_IOCTL_IOC_COUNT) { + cmd - cmd_first > AUTOFS_DEV_IOCTL_IOC_COUNT) { return -ENOTTY; } @@ -655,14 +650,11 @@ static int _autofs_dev_ioctl(unsigned int command, if (err) goto out; - /* The validate routine above always sets the version */ - if (cmd == AUTOFS_DEV_IOCTL_VERSION_CMD) - goto done; - fn = lookup_dev_ioctl(cmd); if (!fn) { pr_warn("unknown command 0x%08x\n", command); - return -ENOTTY; + err = -ENOTTY; + goto out; } fp = NULL; @@ -671,9 +663,11 @@ static int _autofs_dev_ioctl(unsigned int command, /* * For obvious reasons the openmount can't have a file * descriptor yet. We don't take a reference to the - * file during close to allow for immediate release. + * file during close to allow for immediate release, + * and the same for retrieving ioctl version. */ - if (cmd != AUTOFS_DEV_IOCTL_OPENMOUNT_CMD && + if (cmd != AUTOFS_DEV_IOCTL_VERSION_CMD && + cmd != AUTOFS_DEV_IOCTL_OPENMOUNT_CMD && cmd != AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD) { fp = fget(param->ioctlfd); if (!fp) { @@ -706,7 +700,6 @@ cont: if (fp) fput(fp); -done: if (err >= 0 && copy_to_user(user, param, AUTOFS_DEV_IOCTL_SIZE)) err = -EFAULT; out: diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c index ca9cbd6362e0..438b5bf675b6 100644 --- a/fs/autofs4/inode.c +++ b/fs/autofs4/inode.c @@ -274,6 +274,23 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) goto fail_dput; } + /* Test versions first */ + if (sbi->max_proto < AUTOFS_MIN_PROTO_VERSION || + sbi->min_proto > AUTOFS_MAX_PROTO_VERSION) { + pr_err("kernel does not match daemon version " + "daemon (%d, %d) kernel (%d, %d)\n", + sbi->min_proto, sbi->max_proto, + AUTOFS_MIN_PROTO_VERSION, AUTOFS_MAX_PROTO_VERSION); + goto fail_dput; + } + + /* Establish highest kernel protocol version */ + if (sbi->max_proto > AUTOFS_MAX_PROTO_VERSION) + sbi->version = AUTOFS_MAX_PROTO_VERSION; + else + sbi->version = sbi->max_proto; + sbi->sub_version = AUTOFS_PROTO_SUBVERSION; + if (pgrp_set) { sbi->oz_pgrp = find_get_pid(pgrp); if (!sbi->oz_pgrp) { @@ -291,29 +308,12 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) root_inode->i_fop = &autofs4_root_operations; root_inode->i_op = &autofs4_dir_inode_operations; - /* Couldn't this be tested earlier? */ - if (sbi->max_proto < AUTOFS_MIN_PROTO_VERSION || - sbi->min_proto > AUTOFS_MAX_PROTO_VERSION) { - pr_err("kernel does not match daemon version " - "daemon (%d, %d) kernel (%d, %d)\n", - sbi->min_proto, sbi->max_proto, - AUTOFS_MIN_PROTO_VERSION, AUTOFS_MAX_PROTO_VERSION); - goto fail_dput; - } - - /* Establish highest kernel protocol version */ - if (sbi->max_proto > AUTOFS_MAX_PROTO_VERSION) - sbi->version = AUTOFS_MAX_PROTO_VERSION; - else - sbi->version = sbi->max_proto; - sbi->sub_version = AUTOFS_PROTO_SUBVERSION; - pr_debug("pipe fd = %d, pgrp = %u\n", pipefd, pid_nr(sbi->oz_pgrp)); pipe = fget(pipefd); if (!pipe) { pr_err("could not open pipe file descriptor\n"); - goto fail_dput; + goto fail_put_pid; } ret = autofs_prepare_pipe(pipe); if (ret < 0) @@ -334,14 +334,14 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) fail_fput: pr_err("pipe file descriptor does not contain proper ops\n"); fput(pipe); - /* fall through */ +fail_put_pid: + put_pid(sbi->oz_pgrp); fail_dput: dput(root); goto fail_free; fail_ino: - kfree(ino); + autofs4_free_ino(ino); fail_free: - put_pid(sbi->oz_pgrp); kfree(sbi); s->s_fs_info = NULL; return ret; @@ -368,7 +368,8 @@ struct inode *autofs4_get_inode(struct super_block *sb, umode_t mode) inode->i_fop = &autofs4_dir_operations; } else if (S_ISLNK(mode)) { inode->i_op = &autofs4_symlink_inode_operations; - } + } else + WARN_ON(1); return inode; } diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index 623510e84c96..a11f73174877 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -577,8 +577,6 @@ static int autofs4_dir_symlink(struct inode *dir, inode = autofs4_get_inode(dir->i_sb, S_IFLNK | 0555); if (!inode) { kfree(cp); - if (!dentry->d_fsdata) - kfree(ino); return -ENOMEM; } inode->i_private = cp; @@ -842,7 +840,7 @@ static inline int autofs4_ask_umount(struct vfsmount *mnt, int __user *p) if (may_umount(mnt)) status = 1; - pr_debug("returning %d\n", status); + pr_debug("may umount %d\n", status); status = put_user(status, p); diff --git a/fs/block_dev.c b/fs/block_dev.c index 376e4e426324..05b553368bb4 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include "internal.h" @@ -1775,6 +1776,81 @@ static const struct address_space_operations def_blk_aops = { .is_dirty_writeback = buffer_check_dirty_writeback, }; +#define BLKDEV_FALLOC_FL_SUPPORTED \ + (FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | \ + FALLOC_FL_ZERO_RANGE | FALLOC_FL_NO_HIDE_STALE) + +static long blkdev_fallocate(struct file *file, int mode, loff_t start, + loff_t len) +{ + struct block_device *bdev = I_BDEV(bdev_file_inode(file)); + struct request_queue *q = bdev_get_queue(bdev); + struct address_space *mapping; + loff_t end = start + len - 1; + loff_t isize; + int error; + + /* Fail if we don't recognize the flags. */ + if (mode & ~BLKDEV_FALLOC_FL_SUPPORTED) + return -EOPNOTSUPP; + + /* Don't go off the end of the device. */ + isize = i_size_read(bdev->bd_inode); + if (start >= isize) + return -EINVAL; + if (end >= isize) { + if (mode & FALLOC_FL_KEEP_SIZE) { + len = isize - start; + end = start + len - 1; + } else + return -EINVAL; + } + + /* + * Don't allow IO that isn't aligned to logical block size. + */ + if ((start | len) & (bdev_logical_block_size(bdev) - 1)) + return -EINVAL; + + /* Invalidate the page cache, including dirty pages. */ + mapping = bdev->bd_inode->i_mapping; + truncate_inode_pages_range(mapping, start, end); + + switch (mode) { + case FALLOC_FL_ZERO_RANGE: + case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE: + error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, + GFP_KERNEL, false); + break; + case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE: + /* Only punch if the device can do zeroing discard. */ + if (!blk_queue_discard(q) || !q->limits.discard_zeroes_data) + return -EOPNOTSUPP; + error = blkdev_issue_discard(bdev, start >> 9, len >> 9, + GFP_KERNEL, 0); + break; + case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE: + if (!blk_queue_discard(q)) + return -EOPNOTSUPP; + error = blkdev_issue_discard(bdev, start >> 9, len >> 9, + GFP_KERNEL, 0); + break; + default: + return -EOPNOTSUPP; + } + if (error) + return error; + + /* + * Invalidate again; if someone wandered in and dirtied a page, + * the caller will be given -EBUSY. The third argument is + * inclusive, so the rounding here is safe. + */ + return invalidate_inode_pages2_range(mapping, + start >> PAGE_SHIFT, + end >> PAGE_SHIFT); +} + const struct file_operations def_blk_fops = { .open = blkdev_open, .release = blkdev_close, @@ -1789,6 +1865,7 @@ const struct file_operations def_blk_fops = { #endif .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, + .fallocate = blkdev_fallocate, }; int ioctl_by_bdev(struct block_device *bdev, unsigned cmd, unsigned long arg) diff --git a/fs/buffer.c b/fs/buffer.c index 7dad8713fac8..b205a629001d 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -351,7 +351,7 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate) set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost async page write"); - set_bit(AS_EIO, &page->mapping->flags); + mapping_set_error(page->mapping, -EIO); set_buffer_write_io_error(bh); clear_buffer_uptodate(bh); SetPageError(page); @@ -3249,7 +3249,7 @@ drop_buffers(struct page *page, struct buffer_head **buffers_to_free) bh = head; do { if (buffer_write_io_error(bh) && page->mapping) - set_bit(AS_EIO, &page->mapping->flags); + mapping_set_error(page->mapping, -EIO); if (buffer_busy(bh)) goto failed; bh = bh->b_this_page; diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index d42ff527ab21..d8072bc074a4 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -778,7 +778,7 @@ try_again: fail: EXOFS_DBGMSG("Error: writepage_strip(0x%lx, 0x%lx)=>%d\n", inode->i_ino, page->index, ret); - set_bit(AS_EIO, &page->mapping->flags); + mapping_set_error(page->mapping, -EIO); unlock_page(page); return ret; } diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index b4cbee936cf8..0094923e5ebf 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -88,7 +88,7 @@ static void ext4_finish_bio(struct bio *bio) if (bio->bi_error) { SetPageError(page); - set_bit(AS_EIO, &page->mapping->flags); + mapping_set_error(page->mapping, -EIO); } bh = head = page_buffers(page); /* diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 0d0177c9149c..9ae194fd2fdb 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -75,7 +75,7 @@ static void f2fs_write_end_io(struct bio *bio) fscrypt_pullback_bio_page(&page, true); if (unlikely(bio->bi_error)) { - set_bit(AS_EIO, &page->mapping->flags); + mapping_set_error(page->mapping, -EIO); f2fs_stop_checkpoint(sbi, true); } end_page_writeback(page); diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 5bb565f9989c..31f8ca046639 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -269,8 +269,7 @@ static int journal_finish_inode_data_buffers(journal_t *journal, * filemap_fdatawait_range(), set it again so * that user process can get -EIO from fsync(). */ - set_bit(AS_EIO, - &jinode->i_vfs_inode->i_mapping->flags); + mapping_set_error(jinode->i_vfs_inode->i_mapping, -EIO); if (!ret) ret = err; diff --git a/fs/lockd/procfs.h b/fs/lockd/procfs.h index 2257a1311027..184a15edd18d 100644 --- a/fs/lockd/procfs.h +++ b/fs/lockd/procfs.h @@ -6,8 +6,6 @@ #ifndef _LOCKD_PROCFS_H #define _LOCKD_PROCFS_H -#include - #if IS_ENABLED(CONFIG_PROC_FS) int lockd_create_procfs(void); void lockd_remove_procfs(void); diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 6ea06f8a7d29..3f828a187049 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -3188,6 +3188,9 @@ int dlm_migrate_request_handler(struct o2net_msg *msg, u32 len, void *data, migrate->new_master, migrate->master); + if (ret < 0) + kmem_cache_free(dlm_mle_cache, mle); + spin_unlock(&dlm->master_lock); unlock: spin_unlock(&dlm->spinlock); diff --git a/fs/open.c b/fs/open.c index 8aeb08bb278b..a7719cfb7257 100644 --- a/fs/open.c +++ b/fs/open.c @@ -300,7 +300,8 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) * Let individual file system decide if it supports preallocation * for directories or not. */ - if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) + if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode) && + !S_ISBLK(inode->i_mode)) return -ENODEV; /* Check for wrap through zero too */ diff --git a/fs/pipe.c b/fs/pipe.c index 1f559f0608e1..8e0d9f26dfad 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -601,54 +601,63 @@ pipe_fasync(int fd, struct file *filp, int on) return retval; } -static void account_pipe_buffers(struct pipe_inode_info *pipe, +static unsigned long account_pipe_buffers(struct user_struct *user, unsigned long old, unsigned long new) { - atomic_long_add(new - old, &pipe->user->pipe_bufs); + return atomic_long_add_return(new - old, &user->pipe_bufs); } -static bool too_many_pipe_buffers_soft(struct user_struct *user) +static bool too_many_pipe_buffers_soft(unsigned long user_bufs) { - return pipe_user_pages_soft && - atomic_long_read(&user->pipe_bufs) >= pipe_user_pages_soft; + return pipe_user_pages_soft && user_bufs >= pipe_user_pages_soft; } -static bool too_many_pipe_buffers_hard(struct user_struct *user) +static bool too_many_pipe_buffers_hard(unsigned long user_bufs) { - return pipe_user_pages_hard && - atomic_long_read(&user->pipe_bufs) >= pipe_user_pages_hard; + return pipe_user_pages_hard && user_bufs >= pipe_user_pages_hard; } struct pipe_inode_info *alloc_pipe_info(void) { struct pipe_inode_info *pipe; + unsigned long pipe_bufs = PIPE_DEF_BUFFERS; + struct user_struct *user = get_current_user(); + unsigned long user_bufs; pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL_ACCOUNT); - if (pipe) { - unsigned long pipe_bufs = PIPE_DEF_BUFFERS; - struct user_struct *user = get_current_user(); - - if (!too_many_pipe_buffers_hard(user)) { - if (too_many_pipe_buffers_soft(user)) - pipe_bufs = 1; - pipe->bufs = kcalloc(pipe_bufs, - sizeof(struct pipe_buffer), - GFP_KERNEL_ACCOUNT); - } + if (pipe == NULL) + goto out_free_uid; - if (pipe->bufs) { - init_waitqueue_head(&pipe->wait); - pipe->r_counter = pipe->w_counter = 1; - pipe->buffers = pipe_bufs; - pipe->user = user; - account_pipe_buffers(pipe, 0, pipe_bufs); - mutex_init(&pipe->mutex); - return pipe; - } - free_uid(user); - kfree(pipe); + if (pipe_bufs * PAGE_SIZE > pipe_max_size && !capable(CAP_SYS_RESOURCE)) + pipe_bufs = pipe_max_size >> PAGE_SHIFT; + + user_bufs = account_pipe_buffers(user, 0, pipe_bufs); + + if (too_many_pipe_buffers_soft(user_bufs)) { + user_bufs = account_pipe_buffers(user, pipe_bufs, 1); + pipe_bufs = 1; + } + + if (too_many_pipe_buffers_hard(user_bufs)) + goto out_revert_acct; + + pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer), + GFP_KERNEL_ACCOUNT); + + if (pipe->bufs) { + init_waitqueue_head(&pipe->wait); + pipe->r_counter = pipe->w_counter = 1; + pipe->buffers = pipe_bufs; + pipe->user = user; + mutex_init(&pipe->mutex); + return pipe; } +out_revert_acct: + (void) account_pipe_buffers(user, pipe_bufs, 0); + kfree(pipe); +out_free_uid: + free_uid(user); return NULL; } @@ -656,7 +665,7 @@ void free_pipe_info(struct pipe_inode_info *pipe) { int i; - account_pipe_buffers(pipe, pipe->buffers, 0); + (void) account_pipe_buffers(pipe->user, pipe->buffers, 0); free_uid(pipe->user); for (i = 0; i < pipe->buffers; i++) { struct pipe_buffer *buf = pipe->bufs + i; @@ -1007,13 +1016,55 @@ const struct file_operations pipefifo_fops = { .fasync = pipe_fasync, }; +/* + * Currently we rely on the pipe array holding a power-of-2 number + * of pages. + */ +static inline unsigned int round_pipe_size(unsigned int size) +{ + unsigned long nr_pages; + + nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; + return roundup_pow_of_two(nr_pages) << PAGE_SHIFT; +} + /* * Allocate a new array of pipe buffers and copy the info over. Returns the * pipe size if successful, or return -ERROR on error. */ -static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages) +static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) { struct pipe_buffer *bufs; + unsigned int size, nr_pages; + unsigned long user_bufs; + long ret = 0; + + size = round_pipe_size(arg); + nr_pages = size >> PAGE_SHIFT; + + if (!nr_pages) + return -EINVAL; + + /* + * If trying to increase the pipe capacity, check that an + * unprivileged user is not trying to exceed various limits + * (soft limit check here, hard limit check just below). + * Decreasing the pipe capacity is always permitted, even + * if the user is currently over a limit. + */ + if (nr_pages > pipe->buffers && + size > pipe_max_size && !capable(CAP_SYS_RESOURCE)) + return -EPERM; + + user_bufs = account_pipe_buffers(pipe->user, pipe->buffers, nr_pages); + + if (nr_pages > pipe->buffers && + (too_many_pipe_buffers_hard(user_bufs) || + too_many_pipe_buffers_soft(user_bufs)) && + !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) { + ret = -EPERM; + goto out_revert_acct; + } /* * We can shrink the pipe, if arg >= pipe->nrbufs. Since we don't @@ -1021,13 +1072,17 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages) * again like we would do for growing. If the pipe currently * contains more buffers than arg, then return busy. */ - if (nr_pages < pipe->nrbufs) - return -EBUSY; + if (nr_pages < pipe->nrbufs) { + ret = -EBUSY; + goto out_revert_acct; + } bufs = kcalloc(nr_pages, sizeof(*bufs), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); - if (unlikely(!bufs)) - return -ENOMEM; + if (unlikely(!bufs)) { + ret = -ENOMEM; + goto out_revert_acct; + } /* * The pipe array wraps around, so just start the new one at zero @@ -1050,24 +1105,15 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages) memcpy(bufs + head, pipe->bufs, tail * sizeof(struct pipe_buffer)); } - account_pipe_buffers(pipe, pipe->buffers, nr_pages); pipe->curbuf = 0; kfree(pipe->bufs); pipe->bufs = bufs; pipe->buffers = nr_pages; return nr_pages * PAGE_SIZE; -} - -/* - * Currently we rely on the pipe array holding a power-of-2 number - * of pages. - */ -static inline unsigned int round_pipe_size(unsigned int size) -{ - unsigned long nr_pages; - nr_pages = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; - return roundup_pow_of_two(nr_pages) << PAGE_SHIFT; +out_revert_acct: + (void) account_pipe_buffers(pipe->user, nr_pages, pipe->buffers); + return ret; } /* @@ -1109,28 +1155,9 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg) __pipe_lock(pipe); switch (cmd) { - case F_SETPIPE_SZ: { - unsigned int size, nr_pages; - - size = round_pipe_size(arg); - nr_pages = size >> PAGE_SHIFT; - - ret = -EINVAL; - if (!nr_pages) - goto out; - - if (!capable(CAP_SYS_RESOURCE) && size > pipe_max_size) { - ret = -EPERM; - goto out; - } else if ((too_many_pipe_buffers_hard(pipe->user) || - too_many_pipe_buffers_soft(pipe->user)) && - !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) { - ret = -EPERM; - goto out; - } - ret = pipe_set_size(pipe, nr_pages); + case F_SETPIPE_SZ: + ret = pipe_set_size(pipe, arg); break; - } case F_GETPIPE_SZ: ret = pipe->buffers * PAGE_SIZE; break; @@ -1139,7 +1166,6 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg) break; } -out: __pipe_unlock(pipe); return ret; } diff --git a/fs/select.c b/fs/select.c index 8ed9da50896a..3d4f85defeab 100644 --- a/fs/select.c +++ b/fs/select.c @@ -29,6 +29,7 @@ #include #include #include +#include #include @@ -554,7 +555,7 @@ int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set_bits fds; void *bits; int ret, max_fds; - unsigned int size; + size_t size, alloc_size; struct fdtable *fdt; /* Allocate small arguments on the stack to save memory and be faster */ long stack_fds[SELECT_STACK_ALLOC/sizeof(long)]; @@ -581,7 +582,14 @@ int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, if (size > sizeof(stack_fds) / 6) { /* Not enough space in on-stack array; must use kmalloc */ ret = -ENOMEM; - bits = kmalloc(6 * size, GFP_KERNEL); + if (size > (SIZE_MAX / 6)) + goto out_nofds; + + alloc_size = 6 * size; + bits = kmalloc(alloc_size, GFP_KERNEL|__GFP_NOWARN); + if (!bits && alloc_size > PAGE_SIZE) + bits = vmalloc(alloc_size); + if (!bits) goto out_nofds; } @@ -618,7 +626,7 @@ int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, out: if (bits != stack_fds) - kfree(bits); + kvfree(bits); out_nofds: return ret; } diff --git a/include/linux/auto_dev-ioctl.h b/include/linux/auto_dev-ioctl.h index 7caaf298f539..28c15050ebe6 100644 --- a/include/linux/auto_dev-ioctl.h +++ b/include/linux/auto_dev-ioctl.h @@ -10,214 +10,5 @@ #ifndef _LINUX_AUTO_DEV_IOCTL_H #define _LINUX_AUTO_DEV_IOCTL_H -#include -#include - -#define AUTOFS_DEVICE_NAME "autofs" - -#define AUTOFS_DEV_IOCTL_VERSION_MAJOR 1 -#define AUTOFS_DEV_IOCTL_VERSION_MINOR 0 - -#define AUTOFS_DEVID_LEN 16 - -#define AUTOFS_DEV_IOCTL_SIZE sizeof(struct autofs_dev_ioctl) - -/* - * An ioctl interface for autofs mount point control. - */ - -struct args_protover { - __u32 version; -}; - -struct args_protosubver { - __u32 sub_version; -}; - -struct args_openmount { - __u32 devid; -}; - -struct args_ready { - __u32 token; -}; - -struct args_fail { - __u32 token; - __s32 status; -}; - -struct args_setpipefd { - __s32 pipefd; -}; - -struct args_timeout { - __u64 timeout; -}; - -struct args_requester { - __u32 uid; - __u32 gid; -}; - -struct args_expire { - __u32 how; -}; - -struct args_askumount { - __u32 may_umount; -}; - -struct args_ismountpoint { - union { - struct args_in { - __u32 type; - } in; - struct args_out { - __u32 devid; - __u32 magic; - } out; - }; -}; - -/* - * All the ioctls use this structure. - * When sending a path size must account for the total length - * of the chunk of memory otherwise is is the size of the - * structure. - */ - -struct autofs_dev_ioctl { - __u32 ver_major; - __u32 ver_minor; - __u32 size; /* total size of data passed in - * including this struct */ - __s32 ioctlfd; /* automount command fd */ - - /* Command parameters */ - - union { - struct args_protover protover; - struct args_protosubver protosubver; - struct args_openmount openmount; - struct args_ready ready; - struct args_fail fail; - struct args_setpipefd setpipefd; - struct args_timeout timeout; - struct args_requester requester; - struct args_expire expire; - struct args_askumount askumount; - struct args_ismountpoint ismountpoint; - }; - - char path[0]; -}; - -static inline void init_autofs_dev_ioctl(struct autofs_dev_ioctl *in) -{ - memset(in, 0, sizeof(struct autofs_dev_ioctl)); - in->ver_major = AUTOFS_DEV_IOCTL_VERSION_MAJOR; - in->ver_minor = AUTOFS_DEV_IOCTL_VERSION_MINOR; - in->size = sizeof(struct autofs_dev_ioctl); - in->ioctlfd = -1; -} - -/* - * If you change this make sure you make the corresponding change - * to autofs-dev-ioctl.c:lookup_ioctl() - */ -enum { - /* Get various version info */ - AUTOFS_DEV_IOCTL_VERSION_CMD = 0x71, - AUTOFS_DEV_IOCTL_PROTOVER_CMD, - AUTOFS_DEV_IOCTL_PROTOSUBVER_CMD, - - /* Open mount ioctl fd */ - AUTOFS_DEV_IOCTL_OPENMOUNT_CMD, - - /* Close mount ioctl fd */ - AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD, - - /* Mount/expire status returns */ - AUTOFS_DEV_IOCTL_READY_CMD, - AUTOFS_DEV_IOCTL_FAIL_CMD, - - /* Activate/deactivate autofs mount */ - AUTOFS_DEV_IOCTL_SETPIPEFD_CMD, - AUTOFS_DEV_IOCTL_CATATONIC_CMD, - - /* Expiry timeout */ - AUTOFS_DEV_IOCTL_TIMEOUT_CMD, - - /* Get mount last requesting uid and gid */ - AUTOFS_DEV_IOCTL_REQUESTER_CMD, - - /* Check for eligible expire candidates */ - AUTOFS_DEV_IOCTL_EXPIRE_CMD, - - /* Request busy status */ - AUTOFS_DEV_IOCTL_ASKUMOUNT_CMD, - - /* Check if path is a mountpoint */ - AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD, -}; - -#define AUTOFS_IOCTL 0x93 - -#define AUTOFS_DEV_IOCTL_VERSION \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_VERSION_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_PROTOVER \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_PROTOVER_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_PROTOSUBVER \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_PROTOSUBVER_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_OPENMOUNT \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_OPENMOUNT_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_CLOSEMOUNT \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_READY \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_READY_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_FAIL \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_FAIL_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_SETPIPEFD \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_SETPIPEFD_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_CATATONIC \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_CATATONIC_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_TIMEOUT \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_TIMEOUT_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_REQUESTER \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_REQUESTER_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_EXPIRE \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_EXPIRE_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_ASKUMOUNT \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_ASKUMOUNT_CMD, struct autofs_dev_ioctl) - -#define AUTOFS_DEV_IOCTL_ISMOUNTPOINT \ - _IOWR(AUTOFS_IOCTL, \ - AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD, struct autofs_dev_ioctl) - +#include #endif /* _LINUX_AUTO_DEV_IOCTL_H */ diff --git a/include/linux/auto_fs.h b/include/linux/auto_fs.h index b4066bb89083..b8f814c95cf5 100644 --- a/include/linux/auto_fs.h +++ b/include/linux/auto_fs.h @@ -10,7 +10,6 @@ #define _LINUX_AUTO_FS_H #include -#include #include #include #endif /* _LINUX_AUTO_FS_H */ diff --git a/include/linux/ctype.h b/include/linux/ctype.h index 653589e3e30e..f13e4ff6835a 100644 --- a/include/linux/ctype.h +++ b/include/linux/ctype.h @@ -22,7 +22,10 @@ extern const unsigned char _ctype[]; #define isalnum(c) ((__ismask(c)&(_U|_L|_D)) != 0) #define isalpha(c) ((__ismask(c)&(_U|_L)) != 0) #define iscntrl(c) ((__ismask(c)&(_C)) != 0) -#define isdigit(c) ((__ismask(c)&(_D)) != 0) +static inline int isdigit(int c) +{ + return '0' <= c && c <= '9'; +} #define isgraph(c) ((__ismask(c)&(_P|_U|_L|_D)) != 0) #define islower(c) ((__ismask(c)&(_L)) != 0) #define isprint(c) ((__ismask(c)&(_P|_U|_L|_D|_SP)) != 0) diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 0f90eb5e3c6b..08528afdf58b 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -56,6 +56,11 @@ * that gives better TLB efficiency. */ #define DMA_ATTR_ALLOC_SINGLE_PAGES (1UL << 7) +/* + * DMA_ATTR_NO_WARN: This tells the DMA-mapping subsystem to suppress + * allocation failure reports (similarly to __GFP_NOWARN). + */ +#define DMA_ATTR_NO_WARN (1UL << 8) /* * A dma_addr_t can hold any valid DMA or bus address for the platform. diff --git a/include/linux/export.h b/include/linux/export.h index c565f87f005e..d7df4922da1d 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -78,7 +78,6 @@ extern struct module __this_module; #elif defined(CONFIG_TRIM_UNUSED_KSYMS) -#include #include #define __EXPORT_SYMBOL(sym, sec) \ diff --git a/include/linux/fs.h b/include/linux/fs.h index c145219286a8..bc65d5918140 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -440,8 +440,9 @@ struct address_space { unsigned long nrexceptional; pgoff_t writeback_index;/* writeback starts here */ const struct address_space_operations *a_ops; /* methods */ - unsigned long flags; /* error bits/gfp mask */ + unsigned long flags; /* error bits */ spinlock_t private_lock; /* for use by the address_space */ + gfp_t gfp_mask; /* implicit gfp mask for allocations */ struct list_head private_list; /* ditto */ void *private_data; /* ditto */ } __attribute__((aligned(sizeof(long)))); diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 1f0be7213e6d..24e2cc56beb1 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -8,7 +8,6 @@ #include #include #include -#include struct gpio_desc; struct of_phandle_args; diff --git a/include/linux/kexec.h b/include/linux/kexec.h index d7437777baaa..406c33dcae13 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -259,6 +259,12 @@ phys_addr_t paddr_vmcoreinfo_note(void); vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name) #define VMCOREINFO_CONFIG(name) \ vmcoreinfo_append_str("CONFIG_%s=y\n", #name) +#define VMCOREINFO_PAGE_OFFSET(value) \ + vmcoreinfo_append_str("PAGE_OFFSET=%lx\n", (unsigned long)value) +#define VMCOREINFO_VMALLOC_START(value) \ + vmcoreinfo_append_str("VMALLOC_START=%lx\n", (unsigned long)value) +#define VMCOREINFO_VMEMMAP_START(value) \ + vmcoreinfo_append_str("VMEMMAP_START=%lx\n", (unsigned long)value) extern struct kimage *kexec_image; extern struct kimage *kexec_crash_image; diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h index 4894c6888bc6..1c2a32829620 100644 --- a/include/linux/kmemleak.h +++ b/include/linux/kmemleak.h @@ -38,6 +38,11 @@ extern void kmemleak_not_leak(const void *ptr) __ref; extern void kmemleak_ignore(const void *ptr) __ref; extern void kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp) __ref; extern void kmemleak_no_scan(const void *ptr) __ref; +extern void kmemleak_alloc_phys(phys_addr_t phys, size_t size, int min_count, + gfp_t gfp) __ref; +extern void kmemleak_free_part_phys(phys_addr_t phys, size_t size) __ref; +extern void kmemleak_not_leak_phys(phys_addr_t phys) __ref; +extern void kmemleak_ignore_phys(phys_addr_t phys) __ref; static inline void kmemleak_alloc_recursive(const void *ptr, size_t size, int min_count, unsigned long flags, @@ -106,6 +111,19 @@ static inline void kmemleak_erase(void **ptr) static inline void kmemleak_no_scan(const void *ptr) { } +static inline void kmemleak_alloc_phys(phys_addr_t phys, size_t size, + int min_count, gfp_t gfp) +{ +} +static inline void kmemleak_free_part_phys(phys_addr_t phys, size_t size) +{ +} +static inline void kmemleak_not_leak_phys(phys_addr_t phys) +{ +} +static inline void kmemleak_ignore_phys(phys_addr_t phys) +{ +} #endif /* CONFIG_DEBUG_KMEMLEAK */ diff --git a/include/linux/kthread.h b/include/linux/kthread.h index e691b6a23f72..a6e82a69c363 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -10,6 +10,17 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), int node, const char namefmt[], ...); +/** + * kthread_create - create a kthread on the current node + * @threadfn: the function to run in the thread + * @data: data pointer for @threadfn() + * @namefmt: printf-style format string for the thread name + * @...: arguments for @namefmt. + * + * This macro will create a kthread on the current node, leaving it in + * the stopped state. This is just a helper for kthread_create_on_node(); + * see the documentation there for more details. + */ #define kthread_create(threadfn, data, namefmt, arg...) \ kthread_create_on_node(threadfn, data, NUMA_NO_NODE, namefmt, ##arg) @@ -44,7 +55,7 @@ bool kthread_should_stop(void); bool kthread_should_park(void); bool kthread_freezable_should_stop(bool *was_frozen); void *kthread_data(struct task_struct *k); -void *probe_kthread_data(struct task_struct *k); +void *kthread_probe_data(struct task_struct *k); int kthread_park(struct task_struct *k); void kthread_unpark(struct task_struct *k); void kthread_parkme(void); @@ -57,16 +68,23 @@ extern int tsk_fork_get_node(struct task_struct *tsk); * Simple work processor based on kthread. * * This provides easier way to make use of kthreads. A kthread_work - * can be queued and flushed using queue/flush_kthread_work() + * can be queued and flushed using queue/kthread_flush_work() * respectively. Queued kthread_works are processed by a kthread * running kthread_worker_fn(). */ struct kthread_work; typedef void (*kthread_work_func_t)(struct kthread_work *work); +void kthread_delayed_work_timer_fn(unsigned long __data); + +enum { + KTW_FREEZABLE = 1 << 0, /* freeze during suspend */ +}; struct kthread_worker { + unsigned int flags; spinlock_t lock; struct list_head work_list; + struct list_head delayed_work_list; struct task_struct *task; struct kthread_work *current_work; }; @@ -75,11 +93,19 @@ struct kthread_work { struct list_head node; kthread_work_func_t func; struct kthread_worker *worker; + /* Number of canceling calls that are running at the moment. */ + int canceling; +}; + +struct kthread_delayed_work { + struct kthread_work work; + struct timer_list timer; }; #define KTHREAD_WORKER_INIT(worker) { \ .lock = __SPIN_LOCK_UNLOCKED((worker).lock), \ .work_list = LIST_HEAD_INIT((worker).work_list), \ + .delayed_work_list = LIST_HEAD_INIT((worker).delayed_work_list),\ } #define KTHREAD_WORK_INIT(work, fn) { \ @@ -87,46 +113,88 @@ struct kthread_work { .func = (fn), \ } +#define KTHREAD_DELAYED_WORK_INIT(dwork, fn) { \ + .work = KTHREAD_WORK_INIT((dwork).work, (fn)), \ + .timer = __TIMER_INITIALIZER(kthread_delayed_work_timer_fn, \ + 0, (unsigned long)&(dwork), \ + TIMER_IRQSAFE), \ + } + #define DEFINE_KTHREAD_WORKER(worker) \ struct kthread_worker worker = KTHREAD_WORKER_INIT(worker) #define DEFINE_KTHREAD_WORK(work, fn) \ struct kthread_work work = KTHREAD_WORK_INIT(work, fn) +#define DEFINE_KTHREAD_DELAYED_WORK(dwork, fn) \ + struct kthread_delayed_work dwork = \ + KTHREAD_DELAYED_WORK_INIT(dwork, fn) + /* * kthread_worker.lock needs its own lockdep class key when defined on * stack with lockdep enabled. Use the following macros in such cases. */ #ifdef CONFIG_LOCKDEP # define KTHREAD_WORKER_INIT_ONSTACK(worker) \ - ({ init_kthread_worker(&worker); worker; }) + ({ kthread_init_worker(&worker); worker; }) # define DEFINE_KTHREAD_WORKER_ONSTACK(worker) \ struct kthread_worker worker = KTHREAD_WORKER_INIT_ONSTACK(worker) #else # define DEFINE_KTHREAD_WORKER_ONSTACK(worker) DEFINE_KTHREAD_WORKER(worker) #endif -extern void __init_kthread_worker(struct kthread_worker *worker, +extern void __kthread_init_worker(struct kthread_worker *worker, const char *name, struct lock_class_key *key); -#define init_kthread_worker(worker) \ +#define kthread_init_worker(worker) \ do { \ static struct lock_class_key __key; \ - __init_kthread_worker((worker), "("#worker")->lock", &__key); \ + __kthread_init_worker((worker), "("#worker")->lock", &__key); \ } while (0) -#define init_kthread_work(work, fn) \ +#define kthread_init_work(work, fn) \ do { \ memset((work), 0, sizeof(struct kthread_work)); \ INIT_LIST_HEAD(&(work)->node); \ (work)->func = (fn); \ } while (0) +#define kthread_init_delayed_work(dwork, fn) \ + do { \ + kthread_init_work(&(dwork)->work, (fn)); \ + __setup_timer(&(dwork)->timer, \ + kthread_delayed_work_timer_fn, \ + (unsigned long)(dwork), \ + TIMER_IRQSAFE); \ + } while (0) + int kthread_worker_fn(void *worker_ptr); -bool queue_kthread_work(struct kthread_worker *worker, +__printf(2, 3) +struct kthread_worker * +kthread_create_worker(unsigned int flags, const char namefmt[], ...); + +struct kthread_worker * +kthread_create_worker_on_cpu(int cpu, unsigned int flags, + const char namefmt[], ...); + +bool kthread_queue_work(struct kthread_worker *worker, struct kthread_work *work); -void flush_kthread_work(struct kthread_work *work); -void flush_kthread_worker(struct kthread_worker *worker); + +bool kthread_queue_delayed_work(struct kthread_worker *worker, + struct kthread_delayed_work *dwork, + unsigned long delay); + +bool kthread_mod_delayed_work(struct kthread_worker *worker, + struct kthread_delayed_work *dwork, + unsigned long delay); + +void kthread_flush_work(struct kthread_work *work); +void kthread_flush_worker(struct kthread_worker *worker); + +bool kthread_cancel_work_sync(struct kthread_work *work); +bool kthread_cancel_delayed_work_sync(struct kthread_delayed_work *work); + +void kthread_destroy_worker(struct kthread_worker *worker); #endif /* _LINUX_KTHREAD_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 747f401cc312..dd15d39e1985 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -16,17 +16,16 @@ #include /* - * Bits in mapping->flags. The lower __GFP_BITS_SHIFT bits are the page - * allocation mode flags. + * Bits in mapping->flags. */ enum mapping_flags { - AS_EIO = __GFP_BITS_SHIFT + 0, /* IO error on async write */ - AS_ENOSPC = __GFP_BITS_SHIFT + 1, /* ENOSPC on async write */ - AS_MM_ALL_LOCKS = __GFP_BITS_SHIFT + 2, /* under mm_take_all_locks() */ - AS_UNEVICTABLE = __GFP_BITS_SHIFT + 3, /* e.g., ramdisk, SHM_LOCK */ - AS_EXITING = __GFP_BITS_SHIFT + 4, /* final truncate in progress */ + AS_EIO = 0, /* IO error on async write */ + AS_ENOSPC = 1, /* ENOSPC on async write */ + AS_MM_ALL_LOCKS = 2, /* under mm_take_all_locks() */ + AS_UNEVICTABLE = 3, /* e.g., ramdisk, SHM_LOCK */ + AS_EXITING = 4, /* final truncate in progress */ /* writeback related tags are not used */ - AS_NO_WRITEBACK_TAGS = __GFP_BITS_SHIFT + 5, + AS_NO_WRITEBACK_TAGS = 5, }; static inline void mapping_set_error(struct address_space *mapping, int error) @@ -78,7 +77,7 @@ static inline int mapping_use_writeback_tags(struct address_space *mapping) static inline gfp_t mapping_gfp_mask(struct address_space * mapping) { - return (__force gfp_t)mapping->flags & __GFP_BITS_MASK; + return mapping->gfp_mask; } /* Restricts the given gfp_mask to what the mapping allows. */ @@ -94,8 +93,7 @@ static inline gfp_t mapping_gfp_constraint(struct address_space *mapping, */ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) { - m->flags = (m->flags & ~(__force unsigned long)__GFP_BITS_MASK) | - (__force unsigned long)mask; + m->gfp_mask = mask; } void release_pages(struct page **pages, int nr, bool cold); diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 52b97db93830..af3581b8a451 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -461,6 +461,14 @@ static inline struct radix_tree_node *entry_to_node(void *ptr) * * This function updates @iter->index in the case of a successful lookup. * For tagged lookup it also eats @iter->tags. + * + * There are several cases where 'slot' can be passed in as NULL to this + * function. These cases result from the use of radix_tree_iter_next() or + * radix_tree_iter_retry(). In these cases we don't end up dereferencing + * 'slot' because either: + * a) we are doing tagged iteration and iter->tags has been set to 0, or + * b) we are doing non-tagged iteration, and iter->index and iter->next_index + * have been set up so that radix_tree_chunk_size() returns 1 or 0. */ static __always_inline void ** radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, unsigned flags) diff --git a/include/linux/random.h b/include/linux/random.h index 3d6e9815cd85..f7bb7a355cf7 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -34,7 +34,7 @@ extern const struct file_operations random_fops, urandom_fops; unsigned int get_random_int(void); unsigned long get_random_long(void); -unsigned long randomize_range(unsigned long start, unsigned long end, unsigned long len); +unsigned long randomize_page(unsigned long start, unsigned long range); u32 prandom_u32(void); void prandom_bytes(void *buf, size_t nbytes); diff --git a/include/linux/relay.h b/include/linux/relay.h index ecbb34a382b8..68c1448e56bb 100644 --- a/include/linux/relay.h +++ b/include/linux/relay.h @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -38,7 +39,7 @@ struct rchan_buf size_t subbufs_consumed; /* count of sub-buffers consumed */ struct rchan *chan; /* associated channel */ wait_queue_head_t read_wait; /* reader wait queue */ - struct timer_list timer; /* reader wake-up timer */ + struct irq_work wakeup_work; /* reader wakeup */ struct dentry *dentry; /* channel file dentry */ struct kref kref; /* channel buffer refcount */ struct page **page_array; /* array of current buffer pages */ diff --git a/include/linux/sem.h b/include/linux/sem.h index 976ce3a19f1b..d0efd6e6c20a 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -21,6 +21,7 @@ struct sem_array { struct list_head list_id; /* undo requests on this array */ int sem_nsems; /* no. of semaphores in array */ int complex_count; /* pending complex operations */ + bool complex_mode; /* no parallel simple ops */ }; #ifdef CONFIG_SYSVIPC diff --git a/include/uapi/linux/auto_dev-ioctl.h b/include/uapi/linux/auto_dev-ioctl.h new file mode 100644 index 000000000000..021ed331dd71 --- /dev/null +++ b/include/uapi/linux/auto_dev-ioctl.h @@ -0,0 +1,221 @@ +/* + * Copyright 2008 Red Hat, Inc. All rights reserved. + * Copyright 2008 Ian Kent + * + * This file is part of the Linux kernel and is made available under + * the terms of the GNU General Public License, version 2, or at your + * option, any later version, incorporated herein by reference. + */ + +#ifndef _UAPI_LINUX_AUTO_DEV_IOCTL_H +#define _UAPI_LINUX_AUTO_DEV_IOCTL_H + +#include +#include + +#define AUTOFS_DEVICE_NAME "autofs" + +#define AUTOFS_DEV_IOCTL_VERSION_MAJOR 1 +#define AUTOFS_DEV_IOCTL_VERSION_MINOR 0 + +#define AUTOFS_DEV_IOCTL_SIZE sizeof(struct autofs_dev_ioctl) + +/* + * An ioctl interface for autofs mount point control. + */ + +struct args_protover { + __u32 version; +}; + +struct args_protosubver { + __u32 sub_version; +}; + +struct args_openmount { + __u32 devid; +}; + +struct args_ready { + __u32 token; +}; + +struct args_fail { + __u32 token; + __s32 status; +}; + +struct args_setpipefd { + __s32 pipefd; +}; + +struct args_timeout { + __u64 timeout; +}; + +struct args_requester { + __u32 uid; + __u32 gid; +}; + +struct args_expire { + __u32 how; +}; + +struct args_askumount { + __u32 may_umount; +}; + +struct args_ismountpoint { + union { + struct args_in { + __u32 type; + } in; + struct args_out { + __u32 devid; + __u32 magic; + } out; + }; +}; + +/* + * All the ioctls use this structure. + * When sending a path size must account for the total length + * of the chunk of memory otherwise is is the size of the + * structure. + */ + +struct autofs_dev_ioctl { + __u32 ver_major; + __u32 ver_minor; + __u32 size; /* total size of data passed in + * including this struct */ + __s32 ioctlfd; /* automount command fd */ + + /* Command parameters */ + + union { + struct args_protover protover; + struct args_protosubver protosubver; + struct args_openmount openmount; + struct args_ready ready; + struct args_fail fail; + struct args_setpipefd setpipefd; + struct args_timeout timeout; + struct args_requester requester; + struct args_expire expire; + struct args_askumount askumount; + struct args_ismountpoint ismountpoint; + }; + + char path[0]; +}; + +static inline void init_autofs_dev_ioctl(struct autofs_dev_ioctl *in) +{ + memset(in, 0, sizeof(struct autofs_dev_ioctl)); + in->ver_major = AUTOFS_DEV_IOCTL_VERSION_MAJOR; + in->ver_minor = AUTOFS_DEV_IOCTL_VERSION_MINOR; + in->size = sizeof(struct autofs_dev_ioctl); + in->ioctlfd = -1; +} + +/* + * If you change this make sure you make the corresponding change + * to autofs-dev-ioctl.c:lookup_ioctl() + */ +enum { + /* Get various version info */ + AUTOFS_DEV_IOCTL_VERSION_CMD = 0x71, + AUTOFS_DEV_IOCTL_PROTOVER_CMD, + AUTOFS_DEV_IOCTL_PROTOSUBVER_CMD, + + /* Open mount ioctl fd */ + AUTOFS_DEV_IOCTL_OPENMOUNT_CMD, + + /* Close mount ioctl fd */ + AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD, + + /* Mount/expire status returns */ + AUTOFS_DEV_IOCTL_READY_CMD, + AUTOFS_DEV_IOCTL_FAIL_CMD, + + /* Activate/deactivate autofs mount */ + AUTOFS_DEV_IOCTL_SETPIPEFD_CMD, + AUTOFS_DEV_IOCTL_CATATONIC_CMD, + + /* Expiry timeout */ + AUTOFS_DEV_IOCTL_TIMEOUT_CMD, + + /* Get mount last requesting uid and gid */ + AUTOFS_DEV_IOCTL_REQUESTER_CMD, + + /* Check for eligible expire candidates */ + AUTOFS_DEV_IOCTL_EXPIRE_CMD, + + /* Request busy status */ + AUTOFS_DEV_IOCTL_ASKUMOUNT_CMD, + + /* Check if path is a mountpoint */ + AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD, +}; + +#define AUTOFS_IOCTL 0x93 + +#define AUTOFS_DEV_IOCTL_VERSION \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_VERSION_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_PROTOVER \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_PROTOVER_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_PROTOSUBVER \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_PROTOSUBVER_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_OPENMOUNT \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_OPENMOUNT_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_CLOSEMOUNT \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_CLOSEMOUNT_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_READY \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_READY_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_FAIL \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_FAIL_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_SETPIPEFD \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_SETPIPEFD_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_CATATONIC \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_CATATONIC_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_TIMEOUT \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_TIMEOUT_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_REQUESTER \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_REQUESTER_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_EXPIRE \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_EXPIRE_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_ASKUMOUNT \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_ASKUMOUNT_CMD, struct autofs_dev_ioctl) + +#define AUTOFS_DEV_IOCTL_ISMOUNTPOINT \ + _IOWR(AUTOFS_IOCTL, \ + AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD, struct autofs_dev_ioctl) + +#endif /* _UAPI_LINUX_AUTO_DEV_IOCTL_H */ diff --git a/include/uapi/linux/auto_fs.h b/include/uapi/linux/auto_fs.h index 9175a1b4dc69..1bfc3ed8b284 100644 --- a/include/uapi/linux/auto_fs.h +++ b/include/uapi/linux/auto_fs.h @@ -12,6 +12,7 @@ #define _UAPI_LINUX_AUTO_FS_H #include +#include #ifndef __KERNEL__ #include #endif /* __KERNEL__ */ diff --git a/init/Kconfig b/init/Kconfig index d7fc22639665..34407f15e6d3 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1288,6 +1288,7 @@ config SYSFS_DEPRECATED_V2 config RELAY bool "Kernel->user space relay support (formerly relayfs)" + select IRQ_WORK help This option enables support for relay interface support in certain file systems (such as debugfs). diff --git a/ipc/msg.c b/ipc/msg.c index c6521c205cb4..e12307d0c920 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -51,19 +51,14 @@ struct msg_receiver { long r_msgtype; long r_maxsize; - /* - * Mark r_msg volatile so that the compiler - * does not try to get smart and optimize - * it. We rely on this for the lockless - * receive algorithm. - */ - struct msg_msg *volatile r_msg; + struct msg_msg *r_msg; }; /* one msg_sender for each sleeping sender */ struct msg_sender { struct list_head list; struct task_struct *tsk; + size_t msgsz; }; #define SEARCH_ANY 1 @@ -159,45 +154,72 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params) return msq->q_perm.id; } -static inline void ss_add(struct msg_queue *msq, struct msg_sender *mss) +static inline bool msg_fits_inqueue(struct msg_queue *msq, size_t msgsz) +{ + return msgsz + msq->q_cbytes <= msq->q_qbytes && + 1 + msq->q_qnum <= msq->q_qbytes; +} + +static inline void ss_add(struct msg_queue *msq, + struct msg_sender *mss, size_t msgsz) { mss->tsk = current; + mss->msgsz = msgsz; __set_current_state(TASK_INTERRUPTIBLE); list_add_tail(&mss->list, &msq->q_senders); } static inline void ss_del(struct msg_sender *mss) { - if (mss->list.next != NULL) + if (mss->list.next) list_del(&mss->list); } -static void ss_wakeup(struct list_head *h, int kill) +static void ss_wakeup(struct msg_queue *msq, + struct wake_q_head *wake_q, bool kill) { struct msg_sender *mss, *t; + struct task_struct *stop_tsk = NULL; + struct list_head *h = &msq->q_senders; list_for_each_entry_safe(mss, t, h, list) { if (kill) mss->list.next = NULL; - wake_up_process(mss->tsk); + + /* + * Stop at the first task we don't wakeup, + * we've already iterated the original + * sender queue. + */ + else if (stop_tsk == mss->tsk) + break; + /* + * We are not in an EIDRM scenario here, therefore + * verify that we really need to wakeup the task. + * To maintain current semantics and wakeup order, + * move the sender to the tail on behalf of the + * blocked task. + */ + else if (!msg_fits_inqueue(msq, mss->msgsz)) { + if (!stop_tsk) + stop_tsk = mss->tsk; + + list_move_tail(&mss->list, &msq->q_senders); + continue; + } + + wake_q_add(wake_q, mss->tsk); } } -static void expunge_all(struct msg_queue *msq, int res) +static void expunge_all(struct msg_queue *msq, int res, + struct wake_q_head *wake_q) { struct msg_receiver *msr, *t; list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) { - msr->r_msg = NULL; /* initialize expunge ordering */ - wake_up_process(msr->r_tsk); - /* - * Ensure that the wakeup is visible before setting r_msg as - * the receiving end depends on it: either spinning on a nil, - * or dealing with -EAGAIN cases. See lockless receive part 1 - * and 2 in do_msgrcv(). - */ - smp_wmb(); /* barrier (B) */ - msr->r_msg = ERR_PTR(res); + wake_q_add(wake_q, msr->r_tsk); + WRITE_ONCE(msr->r_msg, ERR_PTR(res)); } } @@ -213,11 +235,13 @@ static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) { struct msg_msg *msg, *t; struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm); + WAKE_Q(wake_q); - expunge_all(msq, -EIDRM); - ss_wakeup(&msq->q_senders, 1); + expunge_all(msq, -EIDRM, &wake_q); + ss_wakeup(msq, &wake_q, true); msg_rmid(ns, msq); ipc_unlock_object(&msq->q_perm); + wake_up_q(&wake_q); rcu_read_unlock(); list_for_each_entry_safe(msg, t, &msq->q_messages, m_list) { @@ -372,6 +396,9 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd, freeque(ns, ipcp); goto out_up; case IPC_SET: + { + WAKE_Q(wake_q); + if (msqid64.msg_qbytes > ns->msg_ctlmnb && !capable(CAP_SYS_RESOURCE)) { err = -EPERM; @@ -386,15 +413,21 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd, msq->q_qbytes = msqid64.msg_qbytes; msq->q_ctime = get_seconds(); - /* sleeping receivers might be excluded by + /* + * Sleeping receivers might be excluded by * stricter permissions. */ - expunge_all(msq, -EAGAIN); - /* sleeping senders might be able to send + expunge_all(msq, -EAGAIN, &wake_q); + /* + * Sleeping senders might be able to send * due to a larger queue size. */ - ss_wakeup(&msq->q_senders, 0); - break; + ss_wakeup(msq, &wake_q, false); + ipc_unlock_object(&msq->q_perm); + wake_up_q(&wake_q); + + goto out_unlock1; + } default: err = -EINVAL; goto out_unlock1; @@ -566,7 +599,8 @@ static int testmsg(struct msg_msg *msg, long type, int mode) return 0; } -static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg) +static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg, + struct wake_q_head *wake_q) { struct msg_receiver *msr, *t; @@ -577,27 +611,14 @@ static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg) list_del(&msr->r_list); if (msr->r_maxsize < msg->m_ts) { - /* initialize pipelined send ordering */ - msr->r_msg = NULL; - wake_up_process(msr->r_tsk); - /* barrier (B) see barrier comment below */ - smp_wmb(); - msr->r_msg = ERR_PTR(-E2BIG); + wake_q_add(wake_q, msr->r_tsk); + WRITE_ONCE(msr->r_msg, ERR_PTR(-E2BIG)); } else { - msr->r_msg = NULL; msq->q_lrpid = task_pid_vnr(msr->r_tsk); msq->q_rtime = get_seconds(); - wake_up_process(msr->r_tsk); - /* - * Ensure that the wakeup is visible before - * setting r_msg, as the receiving can otherwise - * exit - once r_msg is set, the receiver can - * continue. See lockless receive part 1 and 2 - * in do_msgrcv(). Barrier (B). - */ - smp_wmb(); - msr->r_msg = msg; + wake_q_add(wake_q, msr->r_tsk); + WRITE_ONCE(msr->r_msg, msg); return 1; } } @@ -613,6 +634,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext, struct msg_msg *msg; int err; struct ipc_namespace *ns; + WAKE_Q(wake_q); ns = current->nsproxy->ipc_ns; @@ -654,10 +676,8 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext, if (err) goto out_unlock0; - if (msgsz + msq->q_cbytes <= msq->q_qbytes && - 1 + msq->q_qnum <= msq->q_qbytes) { + if (msg_fits_inqueue(msq, msgsz)) break; - } /* queue full, wait: */ if (msgflg & IPC_NOWAIT) { @@ -666,7 +686,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext, } /* enqueue the sender and prepare to block */ - ss_add(msq, &s); + ss_add(msq, &s, msgsz); if (!ipc_rcu_getref(msq)) { err = -EIDRM; @@ -686,7 +706,6 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext, err = -EIDRM; goto out_unlock0; } - ss_del(&s); if (signal_pending(current)) { @@ -695,10 +714,11 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext, } } + msq->q_lspid = task_tgid_vnr(current); msq->q_stime = get_seconds(); - if (!pipelined_send(msq, msg)) { + if (!pipelined_send(msq, msg, &wake_q)) { /* no one is waiting for this message, enqueue it */ list_add_tail(&msg->m_list, &msq->q_messages); msq->q_cbytes += msgsz; @@ -712,6 +732,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext, out_unlock0: ipc_unlock_object(&msq->q_perm); + wake_up_q(&wake_q); out_unlock1: rcu_read_unlock(); if (msg != NULL) @@ -829,6 +850,7 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgfl struct msg_queue *msq; struct ipc_namespace *ns; struct msg_msg *msg, *copy = NULL; + WAKE_Q(wake_q); ns = current->nsproxy->ipc_ns; @@ -893,7 +915,7 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgfl msq->q_cbytes -= msg->m_ts; atomic_sub(msg->m_ts, &ns->msg_bytes); atomic_dec(&ns->msg_hdrs); - ss_wakeup(&msq->q_senders, 0); + ss_wakeup(msq, &wake_q, false); goto out_unlock0; } @@ -919,71 +941,38 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgfl rcu_read_unlock(); schedule(); - /* Lockless receive, part 1: - * Disable preemption. We don't hold a reference to the queue - * and getting a reference would defeat the idea of a lockless - * operation, thus the code relies on rcu to guarantee the - * existence of msq: + /* + * Lockless receive, part 1: + * We don't hold a reference to the queue and getting a + * reference would defeat the idea of a lockless operation, + * thus the code relies on rcu to guarantee the existence of + * msq: * Prior to destruction, expunge_all(-EIRDM) changes r_msg. * Thus if r_msg is -EAGAIN, then the queue not yet destroyed. - * rcu_read_lock() prevents preemption between reading r_msg - * and acquiring the q_perm.lock in ipc_lock_object(). */ rcu_read_lock(); - /* Lockless receive, part 2: - * Wait until pipelined_send or expunge_all are outside of - * wake_up_process(). There is a race with exit(), see - * ipc/mqueue.c for the details. The correct serialization - * ensures that a receiver cannot continue without the wakeup - * being visibible _before_ setting r_msg: - * - * CPU 0 CPU 1 - * - * smp_rmb(); (A) <-- pair -. - * r_msg> | msr->r_msg = NULL; - * | wake_up_process(); - * `------> smp_wmb(); (B) - * msr->r_msg = msg; + /* + * Lockless receive, part 2: + * The work in pipelined_send() and expunge_all(): + * - Set pointer to message + * - Queue the receiver task for later wakeup + * - Wake up the process after the lock is dropped. * - * Where (A) orders the message value read and where (B) orders - * the write to the r_msg -- done in both pipelined_send and - * expunge_all. - */ - for (;;) { - /* - * Pairs with writer barrier in pipelined_send - * or expunge_all. - */ - smp_rmb(); /* barrier (A) */ - msg = (struct msg_msg *)msr_d.r_msg; - if (msg) - break; - - /* - * The cpu_relax() call is a compiler barrier - * which forces everything in this loop to be - * re-loaded. - */ - cpu_relax(); - } - - /* Lockless receive, part 3: - * If there is a message or an error then accept it without - * locking. + * Should the process wake up before this wakeup (due to a + * signal) it will either see the message and continue ... */ + msg = READ_ONCE(msr_d.r_msg); if (msg != ERR_PTR(-EAGAIN)) goto out_unlock1; - /* Lockless receive, part 3: - * Acquire the queue spinlock. - */ + /* + * ... or see -EAGAIN, acquire the lock to check the message + * again. + */ ipc_lock_object(&msq->q_perm); - /* Lockless receive, part 4: - * Repeat test after acquiring the spinlock. - */ - msg = (struct msg_msg *)msr_d.r_msg; + msg = msr_d.r_msg; if (msg != ERR_PTR(-EAGAIN)) goto out_unlock0; @@ -998,6 +987,7 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgfl out_unlock0: ipc_unlock_object(&msq->q_perm); + wake_up_q(&wake_q); out_unlock1: rcu_read_unlock(); if (IS_ERR(msg)) { diff --git a/ipc/sem.c b/ipc/sem.c index 7c9d4f7683c0..10b94bc59d4a 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -162,14 +162,21 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it); /* * Locking: + * a) global sem_lock() for read/write * sem_undo.id_next, * sem_array.complex_count, - * sem_array.pending{_alter,_cont}, - * sem_array.sem_undo: global sem_lock() for read/write - * sem_undo.proc_next: only "current" is allowed to read/write that field. + * sem_array.complex_mode + * sem_array.pending{_alter,_const}, + * sem_array.sem_undo * + * b) global or semaphore sem_lock() for read/write: * sem_array.sem_base[i].pending_{const,alter}: - * global or semaphore sem_lock() for read/write + * sem_array.complex_mode (for read) + * + * c) special: + * sem_undo_list.list_proc: + * * undo_list->lock for write + * * rcu for read */ #define sc_semmsl sem_ctls[0] @@ -260,30 +267,61 @@ static void sem_rcu_free(struct rcu_head *head) } /* - * Wait until all currently ongoing simple ops have completed. + * Enter the mode suitable for non-simple operations: * Caller must own sem_perm.lock. - * New simple ops cannot start, because simple ops first check - * that sem_perm.lock is free. - * that a) sem_perm.lock is free and b) complex_count is 0. */ -static void sem_wait_array(struct sem_array *sma) +static void complexmode_enter(struct sem_array *sma) { int i; struct sem *sem; - if (sma->complex_count) { - /* The thread that increased sma->complex_count waited on - * all sem->lock locks. Thus we don't need to wait again. - */ + if (sma->complex_mode) { + /* We are already in complex_mode. Nothing to do */ return; } + /* We need a full barrier after seting complex_mode: + * The write to complex_mode must be visible + * before we read the first sem->lock spinlock state. + */ + smp_store_mb(sma->complex_mode, true); + for (i = 0; i < sma->sem_nsems; i++) { sem = sma->sem_base + i; spin_unlock_wait(&sem->lock); } + /* + * spin_unlock_wait() is not a memory barriers, it is only a + * control barrier. The code must pair with spin_unlock(&sem->lock), + * thus just the control barrier is insufficient. + * + * smp_rmb() is sufficient, as writes cannot pass the control barrier. + */ + smp_rmb(); } +/* + * Try to leave the mode that disallows simple operations: + * Caller must own sem_perm.lock. + */ +static void complexmode_tryleave(struct sem_array *sma) +{ + if (sma->complex_count) { + /* Complex ops are sleeping. + * We must stay in complex mode + */ + return; + } + /* + * Immediately after setting complex_mode to false, + * a simple op can start. Thus: all memory writes + * performed by the current operation must be visible + * before we set complex_mode to false. + */ + smp_store_release(&sma->complex_mode, false); +} + +#define SEM_GLOBAL_LOCK (-1) /* * If the request contains only one semaphore operation, and there are * no complex transactions pending, lock only the semaphore involved. @@ -300,56 +338,42 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops, /* Complex operation - acquire a full lock */ ipc_lock_object(&sma->sem_perm); - /* And wait until all simple ops that are processed - * right now have dropped their locks. - */ - sem_wait_array(sma); - return -1; + /* Prevent parallel simple ops */ + complexmode_enter(sma); + return SEM_GLOBAL_LOCK; } /* * Only one semaphore affected - try to optimize locking. - * The rules are: - * - optimized locking is possible if no complex operation - * is either enqueued or processed right now. - * - The test for enqueued complex ops is simple: - * sma->complex_count != 0 - * - Testing for complex ops that are processed right now is - * a bit more difficult. Complex ops acquire the full lock - * and first wait that the running simple ops have completed. - * (see above) - * Thus: If we own a simple lock and the global lock is free - * and complex_count is now 0, then it will stay 0 and - * thus just locking sem->lock is sufficient. + * Optimized locking is possible if no complex operation + * is either enqueued or processed right now. + * + * Both facts are tracked by complex_mode. */ sem = sma->sem_base + sops->sem_num; - if (sma->complex_count == 0) { + /* + * Initial check for complex_mode. Just an optimization, + * no locking, no memory barrier. + */ + if (!sma->complex_mode) { /* * It appears that no complex operation is around. * Acquire the per-semaphore lock. */ spin_lock(&sem->lock); - /* Then check that the global lock is free */ - if (!spin_is_locked(&sma->sem_perm.lock)) { - /* - * We need a memory barrier with acquire semantics, - * otherwise we can race with another thread that does: - * complex_count++; - * spin_unlock(sem_perm.lock); - */ - smp_acquire__after_ctrl_dep(); + /* + * See 51d7d5205d33 + * ("powerpc: Add smp_mb() to arch_spin_is_locked()"): + * A full barrier is required: the write of sem->lock + * must be visible before the read is executed + */ + smp_mb(); - /* - * Now repeat the test of complex_count: - * It can't change anymore until we drop sem->lock. - * Thus: if is now 0, then it will stay 0. - */ - if (sma->complex_count == 0) { - /* fast path successful! */ - return sops->sem_num; - } + if (!smp_load_acquire(&sma->complex_mode)) { + /* fast path successful! */ + return sops->sem_num; } spin_unlock(&sem->lock); } @@ -369,15 +393,16 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops, /* Not a false alarm, thus complete the sequence for a * full lock. */ - sem_wait_array(sma); - return -1; + complexmode_enter(sma); + return SEM_GLOBAL_LOCK; } } static inline void sem_unlock(struct sem_array *sma, int locknum) { - if (locknum == -1) { + if (locknum == SEM_GLOBAL_LOCK) { unmerge_queues(sma); + complexmode_tryleave(sma); ipc_unlock_object(&sma->sem_perm); } else { struct sem *sem = sma->sem_base + locknum; @@ -529,6 +554,7 @@ static int newary(struct ipc_namespace *ns, struct ipc_params *params) } sma->complex_count = 0; + sma->complex_mode = true; /* dropped by sem_unlock below */ INIT_LIST_HEAD(&sma->pending_alter); INIT_LIST_HEAD(&sma->pending_const); INIT_LIST_HEAD(&sma->list_id); @@ -2079,6 +2105,8 @@ void exit_sem(struct task_struct *tsk) struct list_head tasks; int semid, i; + cond_resched(); + rcu_read_lock(); un = list_entry_rcu(ulp->list_proc.next, struct sem_undo, list_proc); @@ -2184,10 +2212,10 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it) /* * The proc interface isn't aware of sem_lock(), it calls * ipc_lock_object() directly (in sysvipc_find_ipc). - * In order to stay compatible with sem_lock(), we must wait until - * all simple semop() calls have left their critical regions. + * In order to stay compatible with sem_lock(), we must + * enter / leave complex_mode. */ - sem_wait_array(sma); + complexmode_enter(sma); sem_otime = get_semotime(sma); @@ -2204,6 +2232,8 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it) sem_otime, sma->sem_ctime); + complexmode_tryleave(sma); + return 0; } #endif diff --git a/kernel/configs/android-base.config b/kernel/configs/android-base.config index 9f748ed7bea8..1a8f34f63601 100644 --- a/kernel/configs/android-base.config +++ b/kernel/configs/android-base.config @@ -11,7 +11,6 @@ CONFIG_ANDROID_LOW_MEMORY_KILLER=y CONFIG_ARMV8_DEPRECATED=y CONFIG_ASHMEM=y CONFIG_AUDIT=y -CONFIG_BLK_DEV_DM=y CONFIG_BLK_DEV_INITRD=y CONFIG_CGROUPS=y CONFIG_CGROUP_CPUACCT=y @@ -19,9 +18,7 @@ CONFIG_CGROUP_DEBUG=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_SCHED=y CONFIG_CP15_BARRIER_EMULATION=y -CONFIG_DM_CRYPT=y -CONFIG_DM_VERITY=y -CONFIG_DM_VERITY_FEC=y +CONFIG_DEFAULT_SECURITY_SELINUX=y CONFIG_EMBEDDED=y CONFIG_FB=y CONFIG_HIGH_RES_TIMERS=y @@ -41,7 +38,6 @@ CONFIG_IPV6=y CONFIG_IPV6_MIP6=y CONFIG_IPV6_MULTIPLE_TABLES=y CONFIG_IPV6_OPTIMISTIC_DAD=y -CONFIG_IPV6_PRIVACY=y CONFIG_IPV6_ROUTER_PREF=y CONFIG_IPV6_ROUTE_INFO=y CONFIG_IP_ADVANCED_ROUTER=y @@ -135,6 +131,7 @@ CONFIG_PREEMPT=y CONFIG_QUOTA=y CONFIG_RTC_CLASS=y CONFIG_RT_GROUP_SCHED=y +CONFIG_SECCOMP=y CONFIG_SECURITY=y CONFIG_SECURITY_NETWORK=y CONFIG_SECURITY_SELINUX=y diff --git a/kernel/configs/android-recommended.config b/kernel/configs/android-recommended.config index e3b953e966d2..297756be369c 100644 --- a/kernel/configs/android-recommended.config +++ b/kernel/configs/android-recommended.config @@ -6,12 +6,16 @@ # CONFIG_PM_WAKELOCKS_GC is not set # CONFIG_VT is not set CONFIG_BACKLIGHT_LCD_SUPPORT=y +CONFIG_BLK_DEV_DM=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=8192 CONFIG_COMPACTION=y CONFIG_DEBUG_RODATA=y +CONFIG_DM_CRYPT=y CONFIG_DM_UEVENT=y +CONFIG_DM_VERITY=y +CONFIG_DM_VERITY_FEC=y CONFIG_DRAGONRISE_FF=y CONFIG_ENABLE_DEFAULT_TRACERS=y CONFIG_EXT4_FS=y diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 432c3d71d195..2b59c82cc3e1 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -98,26 +98,26 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) trace_sched_process_hang(t); - if (!sysctl_hung_task_warnings) + if (!sysctl_hung_task_warnings && !sysctl_hung_task_panic) return; - if (sysctl_hung_task_warnings > 0) - sysctl_hung_task_warnings--; - /* * Ok, the task did not get scheduled for more than 2 minutes, * complain: */ - pr_err("INFO: task %s:%d blocked for more than %ld seconds.\n", - t->comm, t->pid, timeout); - pr_err(" %s %s %.*s\n", - print_tainted(), init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); - pr_err("\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\"" - " disables this message.\n"); - sched_show_task(t); - debug_show_all_locks(); + if (sysctl_hung_task_warnings) { + sysctl_hung_task_warnings--; + pr_err("INFO: task %s:%d blocked for more than %ld seconds.\n", + t->comm, t->pid, timeout); + pr_err(" %s %s %.*s\n", + print_tainted(), init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); + pr_err("\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\"" + " disables this message.\n"); + sched_show_task(t); + debug_show_all_locks(); + } touch_nmi_watchdog(); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index d10ab6b9b5e0..d63095472ea9 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -49,7 +49,7 @@ #include #include -#include +#include #include #include #include diff --git a/kernel/kthread.c b/kernel/kthread.c index 4ab4c3766a80..be2cc1f9dd57 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -138,7 +138,7 @@ void *kthread_data(struct task_struct *task) } /** - * probe_kthread_data - speculative version of kthread_data() + * kthread_probe_data - speculative version of kthread_data() * @task: possible kthread task in question * * @task could be a kthread task. Return the data value specified when it @@ -146,7 +146,7 @@ void *kthread_data(struct task_struct *task) * inaccessible for any reason, %NULL is returned. This function requires * that @task itself is safe to dereference. */ -void *probe_kthread_data(struct task_struct *task) +void *kthread_probe_data(struct task_struct *task) { struct kthread *kthread = to_kthread(task); void *data = NULL; @@ -244,33 +244,10 @@ static void create_kthread(struct kthread_create_info *create) } } -/** - * kthread_create_on_node - create a kthread. - * @threadfn: the function to run until signal_pending(current). - * @data: data ptr for @threadfn. - * @node: task and thread structures for the thread are allocated on this node - * @namefmt: printf-style name for the thread. - * - * Description: This helper function creates and names a kernel - * thread. The thread will be stopped: use wake_up_process() to start - * it. See also kthread_run(). The new thread has SCHED_NORMAL policy and - * is affine to all CPUs. - * - * If thread is going to be bound on a particular cpu, give its node - * in @node, to get NUMA affinity for kthread stack, or else give NUMA_NO_NODE. - * When woken, the thread will run @threadfn() with @data as its - * argument. @threadfn() can either call do_exit() directly if it is a - * standalone thread for which no one will call kthread_stop(), or - * return when 'kthread_should_stop()' is true (which means - * kthread_stop() has been called). The return value should be zero - * or a negative error number; it will be passed to kthread_stop(). - * - * Returns a task_struct or ERR_PTR(-ENOMEM) or ERR_PTR(-EINTR). - */ -struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), - void *data, int node, - const char namefmt[], - ...) +static struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), + void *data, int node, + const char namefmt[], + va_list args) { DECLARE_COMPLETION_ONSTACK(done); struct task_struct *task; @@ -311,11 +288,8 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), task = create->result; if (!IS_ERR(task)) { static const struct sched_param param = { .sched_priority = 0 }; - va_list args; - va_start(args, namefmt); vsnprintf(task->comm, sizeof(task->comm), namefmt, args); - va_end(args); /* * root may have changed our (kthreadd's) priority or CPU mask. * The kernel thread should not inherit these properties. @@ -326,6 +300,44 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), kfree(create); return task; } + +/** + * kthread_create_on_node - create a kthread. + * @threadfn: the function to run until signal_pending(current). + * @data: data ptr for @threadfn. + * @node: task and thread structures for the thread are allocated on this node + * @namefmt: printf-style name for the thread. + * + * Description: This helper function creates and names a kernel + * thread. The thread will be stopped: use wake_up_process() to start + * it. See also kthread_run(). The new thread has SCHED_NORMAL policy and + * is affine to all CPUs. + * + * If thread is going to be bound on a particular cpu, give its node + * in @node, to get NUMA affinity for kthread stack, or else give NUMA_NO_NODE. + * When woken, the thread will run @threadfn() with @data as its + * argument. @threadfn() can either call do_exit() directly if it is a + * standalone thread for which no one will call kthread_stop(), or + * return when 'kthread_should_stop()' is true (which means + * kthread_stop() has been called). The return value should be zero + * or a negative error number; it will be passed to kthread_stop(). + * + * Returns a task_struct or ERR_PTR(-ENOMEM) or ERR_PTR(-EINTR). + */ +struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), + void *data, int node, + const char namefmt[], + ...) +{ + struct task_struct *task; + va_list args; + + va_start(args, namefmt); + task = __kthread_create_on_node(threadfn, data, node, namefmt, args); + va_end(args); + + return task; +} EXPORT_SYMBOL(kthread_create_on_node); static void __kthread_bind_mask(struct task_struct *p, const struct cpumask *mask, long state) @@ -390,10 +402,10 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), cpu); if (IS_ERR(p)) return p; + kthread_bind(p, cpu); + /* CPU hotplug need to bind once again when unparking the thread. */ set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags); to_kthread(p)->cpu = cpu; - /* Park the thread to get it out of TASK_UNINTERRUPTIBLE state */ - kthread_park(p); return p; } @@ -407,6 +419,10 @@ static void __kthread_unpark(struct task_struct *k, struct kthread *kthread) * which might be about to be cleared. */ if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) { + /* + * Newly created kthread was parked when the CPU was offline. + * The binding was lost and we need to set it again. + */ if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags)) __kthread_bind(k, kthread->cpu, TASK_PARKED); wake_up_state(k, TASK_PARKED); @@ -540,39 +556,48 @@ int kthreadd(void *unused) return 0; } -void __init_kthread_worker(struct kthread_worker *worker, +void __kthread_init_worker(struct kthread_worker *worker, const char *name, struct lock_class_key *key) { + memset(worker, 0, sizeof(struct kthread_worker)); spin_lock_init(&worker->lock); lockdep_set_class_and_name(&worker->lock, key, name); INIT_LIST_HEAD(&worker->work_list); - worker->task = NULL; + INIT_LIST_HEAD(&worker->delayed_work_list); } -EXPORT_SYMBOL_GPL(__init_kthread_worker); +EXPORT_SYMBOL_GPL(__kthread_init_worker); /** * kthread_worker_fn - kthread function to process kthread_worker * @worker_ptr: pointer to initialized kthread_worker * - * This function can be used as @threadfn to kthread_create() or - * kthread_run() with @worker_ptr argument pointing to an initialized - * kthread_worker. The started kthread will process work_list until - * the it is stopped with kthread_stop(). A kthread can also call - * this function directly after extra initialization. + * This function implements the main cycle of kthread worker. It processes + * work_list until it is stopped with kthread_stop(). It sleeps when the queue + * is empty. + * + * The works are not allowed to keep any locks, disable preemption or interrupts + * when they finish. There is defined a safe point for freezing when one work + * finishes and before a new one is started. * - * Different kthreads can be used for the same kthread_worker as long - * as there's only one kthread attached to it at any given time. A - * kthread_worker without an attached kthread simply collects queued - * kthread_works. + * Also the works must not be handled by more than one worker at the same time, + * see also kthread_queue_work(). */ int kthread_worker_fn(void *worker_ptr) { struct kthread_worker *worker = worker_ptr; struct kthread_work *work; - WARN_ON(worker->task); + /* + * FIXME: Update the check and remove the assignment when all kthread + * worker users are created using kthread_create_worker*() functions. + */ + WARN_ON(worker->task && worker->task != current); worker->task = current; + + if (worker->flags & KTW_FREEZABLE) + set_freezable(); + repeat: set_current_state(TASK_INTERRUPTIBLE); /* mb paired w/ kthread_stop */ @@ -605,12 +630,131 @@ repeat: } EXPORT_SYMBOL_GPL(kthread_worker_fn); -/* insert @work before @pos in @worker */ -static void insert_kthread_work(struct kthread_worker *worker, - struct kthread_work *work, - struct list_head *pos) +static struct kthread_worker * +__kthread_create_worker(int cpu, unsigned int flags, + const char namefmt[], va_list args) +{ + struct kthread_worker *worker; + struct task_struct *task; + + worker = kzalloc(sizeof(*worker), GFP_KERNEL); + if (!worker) + return ERR_PTR(-ENOMEM); + + kthread_init_worker(worker); + + if (cpu >= 0) { + char name[TASK_COMM_LEN]; + + /* + * kthread_create_worker_on_cpu() allows to pass a generic + * namefmt in compare with kthread_create_on_cpu. We need + * to format it here. + */ + vsnprintf(name, sizeof(name), namefmt, args); + task = kthread_create_on_cpu(kthread_worker_fn, worker, + cpu, name); + } else { + task = __kthread_create_on_node(kthread_worker_fn, worker, + -1, namefmt, args); + } + + if (IS_ERR(task)) + goto fail_task; + + worker->flags = flags; + worker->task = task; + wake_up_process(task); + return worker; + +fail_task: + kfree(worker); + return ERR_CAST(task); +} + +/** + * kthread_create_worker - create a kthread worker + * @flags: flags modifying the default behavior of the worker + * @namefmt: printf-style name for the kthread worker (task). + * + * Returns a pointer to the allocated worker on success, ERR_PTR(-ENOMEM) + * when the needed structures could not get allocated, and ERR_PTR(-EINTR) + * when the worker was SIGKILLed. + */ +struct kthread_worker * +kthread_create_worker(unsigned int flags, const char namefmt[], ...) +{ + struct kthread_worker *worker; + va_list args; + + va_start(args, namefmt); + worker = __kthread_create_worker(-1, flags, namefmt, args); + va_end(args); + + return worker; +} +EXPORT_SYMBOL(kthread_create_worker); + +/** + * kthread_create_worker_on_cpu - create a kthread worker and bind it + * it to a given CPU and the associated NUMA node. + * @cpu: CPU number + * @flags: flags modifying the default behavior of the worker + * @namefmt: printf-style name for the kthread worker (task). + * + * Use a valid CPU number if you want to bind the kthread worker + * to the given CPU and the associated NUMA node. + * + * A good practice is to add the cpu number also into the worker name. + * For example, use kthread_create_worker_on_cpu(cpu, "helper/%d", cpu). + * + * Returns a pointer to the allocated worker on success, ERR_PTR(-ENOMEM) + * when the needed structures could not get allocated, and ERR_PTR(-EINTR) + * when the worker was SIGKILLed. + */ +struct kthread_worker * +kthread_create_worker_on_cpu(int cpu, unsigned int flags, + const char namefmt[], ...) +{ + struct kthread_worker *worker; + va_list args; + + va_start(args, namefmt); + worker = __kthread_create_worker(cpu, flags, namefmt, args); + va_end(args); + + return worker; +} +EXPORT_SYMBOL(kthread_create_worker_on_cpu); + +/* + * Returns true when the work could not be queued at the moment. + * It happens when it is already pending in a worker list + * or when it is being cancelled. + */ +static inline bool queuing_blocked(struct kthread_worker *worker, + struct kthread_work *work) +{ + lockdep_assert_held(&worker->lock); + + return !list_empty(&work->node) || work->canceling; +} + +static void kthread_insert_work_sanity_check(struct kthread_worker *worker, + struct kthread_work *work) { lockdep_assert_held(&worker->lock); + WARN_ON_ONCE(!list_empty(&work->node)); + /* Do not use a work with >1 worker, see kthread_queue_work() */ + WARN_ON_ONCE(work->worker && work->worker != worker); +} + +/* insert @work before @pos in @worker */ +static void kthread_insert_work(struct kthread_worker *worker, + struct kthread_work *work, + struct list_head *pos) +{ + kthread_insert_work_sanity_check(worker, work); list_add_tail(&work->node, pos); work->worker = worker; @@ -619,29 +763,133 @@ static void insert_kthread_work(struct kthread_worker *worker, } /** - * queue_kthread_work - queue a kthread_work + * kthread_queue_work - queue a kthread_work * @worker: target kthread_worker * @work: kthread_work to queue * * Queue @work to work processor @task for async execution. @task * must have been created with kthread_worker_create(). Returns %true * if @work was successfully queued, %false if it was already pending. + * + * Reinitialize the work if it needs to be used by another worker. + * For example, when the worker was stopped and started again. */ -bool queue_kthread_work(struct kthread_worker *worker, +bool kthread_queue_work(struct kthread_worker *worker, struct kthread_work *work) { bool ret = false; unsigned long flags; spin_lock_irqsave(&worker->lock, flags); - if (list_empty(&work->node)) { - insert_kthread_work(worker, work, &worker->work_list); + if (!queuing_blocked(worker, work)) { + kthread_insert_work(worker, work, &worker->work_list); + ret = true; + } + spin_unlock_irqrestore(&worker->lock, flags); + return ret; +} +EXPORT_SYMBOL_GPL(kthread_queue_work); + +/** + * kthread_delayed_work_timer_fn - callback that queues the associated kthread + * delayed work when the timer expires. + * @__data: pointer to the data associated with the timer + * + * The format of the function is defined by struct timer_list. + * It should have been called from irqsafe timer with irq already off. + */ +void kthread_delayed_work_timer_fn(unsigned long __data) +{ + struct kthread_delayed_work *dwork = + (struct kthread_delayed_work *)__data; + struct kthread_work *work = &dwork->work; + struct kthread_worker *worker = work->worker; + + /* + * This might happen when a pending work is reinitialized. + * It means that it is used a wrong way. + */ + if (WARN_ON_ONCE(!worker)) + return; + + spin_lock(&worker->lock); + /* Work must not be used with >1 worker, see kthread_queue_work(). */ + WARN_ON_ONCE(work->worker != worker); + + /* Move the work from worker->delayed_work_list. */ + WARN_ON_ONCE(list_empty(&work->node)); + list_del_init(&work->node); + kthread_insert_work(worker, work, &worker->work_list); + + spin_unlock(&worker->lock); +} +EXPORT_SYMBOL(kthread_delayed_work_timer_fn); + +void __kthread_queue_delayed_work(struct kthread_worker *worker, + struct kthread_delayed_work *dwork, + unsigned long delay) +{ + struct timer_list *timer = &dwork->timer; + struct kthread_work *work = &dwork->work; + + WARN_ON_ONCE(timer->function != kthread_delayed_work_timer_fn || + timer->data != (unsigned long)dwork); + + /* + * If @delay is 0, queue @dwork->work immediately. This is for + * both optimization and correctness. The earliest @timer can + * expire is on the closest next tick and delayed_work users depend + * on that there's no such delay when @delay is 0. + */ + if (!delay) { + kthread_insert_work(worker, work, &worker->work_list); + return; + } + + /* Be paranoid and try to detect possible races already now. */ + kthread_insert_work_sanity_check(worker, work); + + list_add(&work->node, &worker->delayed_work_list); + work->worker = worker; + timer_stats_timer_set_start_info(&dwork->timer); + timer->expires = jiffies + delay; + add_timer(timer); +} + +/** + * kthread_queue_delayed_work - queue the associated kthread work + * after a delay. + * @worker: target kthread_worker + * @dwork: kthread_delayed_work to queue + * @delay: number of jiffies to wait before queuing + * + * If the work has not been pending it starts a timer that will queue + * the work after the given @delay. If @delay is zero, it queues the + * work immediately. + * + * Return: %false if the @work has already been pending. It means that + * either the timer was running or the work was queued. It returns %true + * otherwise. + */ +bool kthread_queue_delayed_work(struct kthread_worker *worker, + struct kthread_delayed_work *dwork, + unsigned long delay) +{ + struct kthread_work *work = &dwork->work; + unsigned long flags; + bool ret = false; + + spin_lock_irqsave(&worker->lock, flags); + + if (!queuing_blocked(worker, work)) { + __kthread_queue_delayed_work(worker, dwork, delay); ret = true; } + spin_unlock_irqrestore(&worker->lock, flags); return ret; } -EXPORT_SYMBOL_GPL(queue_kthread_work); +EXPORT_SYMBOL_GPL(kthread_queue_delayed_work); struct kthread_flush_work { struct kthread_work work; @@ -656,12 +904,12 @@ static void kthread_flush_work_fn(struct kthread_work *work) } /** - * flush_kthread_work - flush a kthread_work + * kthread_flush_work - flush a kthread_work * @work: work to flush * * If @work is queued or executing, wait for it to finish execution. */ -void flush_kthread_work(struct kthread_work *work) +void kthread_flush_work(struct kthread_work *work) { struct kthread_flush_work fwork = { KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn), @@ -670,21 +918,19 @@ void flush_kthread_work(struct kthread_work *work) struct kthread_worker *worker; bool noop = false; -retry: worker = work->worker; if (!worker) return; spin_lock_irq(&worker->lock); - if (work->worker != worker) { - spin_unlock_irq(&worker->lock); - goto retry; - } + /* Work must not be used with >1 worker, see kthread_queue_work(). */ + WARN_ON_ONCE(work->worker != worker); if (!list_empty(&work->node)) - insert_kthread_work(worker, &fwork.work, work->node.next); + kthread_insert_work(worker, &fwork.work, work->node.next); else if (worker->current_work == work) - insert_kthread_work(worker, &fwork.work, worker->work_list.next); + kthread_insert_work(worker, &fwork.work, + worker->work_list.next); else noop = true; @@ -693,23 +939,214 @@ retry: if (!noop) wait_for_completion(&fwork.done); } -EXPORT_SYMBOL_GPL(flush_kthread_work); +EXPORT_SYMBOL_GPL(kthread_flush_work); + +/* + * This function removes the work from the worker queue. Also it makes sure + * that it won't get queued later via the delayed work's timer. + * + * The work might still be in use when this function finishes. See the + * current_work proceed by the worker. + * + * Return: %true if @work was pending and successfully canceled, + * %false if @work was not pending + */ +static bool __kthread_cancel_work(struct kthread_work *work, bool is_dwork, + unsigned long *flags) +{ + /* Try to cancel the timer if exists. */ + if (is_dwork) { + struct kthread_delayed_work *dwork = + container_of(work, struct kthread_delayed_work, work); + struct kthread_worker *worker = work->worker; + + /* + * del_timer_sync() must be called to make sure that the timer + * callback is not running. The lock must be temporary released + * to avoid a deadlock with the callback. In the meantime, + * any queuing is blocked by setting the canceling counter. + */ + work->canceling++; + spin_unlock_irqrestore(&worker->lock, *flags); + del_timer_sync(&dwork->timer); + spin_lock_irqsave(&worker->lock, *flags); + work->canceling--; + } + + /* + * Try to remove the work from a worker list. It might either + * be from worker->work_list or from worker->delayed_work_list. + */ + if (!list_empty(&work->node)) { + list_del_init(&work->node); + return true; + } + + return false; +} + +/** + * kthread_mod_delayed_work - modify delay of or queue a kthread delayed work + * @worker: kthread worker to use + * @dwork: kthread delayed work to queue + * @delay: number of jiffies to wait before queuing + * + * If @dwork is idle, equivalent to kthread_queue_delayed_work(). Otherwise, + * modify @dwork's timer so that it expires after @delay. If @delay is zero, + * @work is guaranteed to be queued immediately. + * + * Return: %true if @dwork was pending and its timer was modified, + * %false otherwise. + * + * A special case is when the work is being canceled in parallel. + * It might be caused either by the real kthread_cancel_delayed_work_sync() + * or yet another kthread_mod_delayed_work() call. We let the other command + * win and return %false here. The caller is supposed to synchronize these + * operations a reasonable way. + * + * This function is safe to call from any context including IRQ handler. + * See __kthread_cancel_work() and kthread_delayed_work_timer_fn() + * for details. + */ +bool kthread_mod_delayed_work(struct kthread_worker *worker, + struct kthread_delayed_work *dwork, + unsigned long delay) +{ + struct kthread_work *work = &dwork->work; + unsigned long flags; + int ret = false; + + spin_lock_irqsave(&worker->lock, flags); + + /* Do not bother with canceling when never queued. */ + if (!work->worker) + goto fast_queue; + + /* Work must not be used with >1 worker, see kthread_queue_work() */ + WARN_ON_ONCE(work->worker != worker); + + /* Do not fight with another command that is canceling this work. */ + if (work->canceling) + goto out; + + ret = __kthread_cancel_work(work, true, &flags); +fast_queue: + __kthread_queue_delayed_work(worker, dwork, delay); +out: + spin_unlock_irqrestore(&worker->lock, flags); + return ret; +} +EXPORT_SYMBOL_GPL(kthread_mod_delayed_work); + +static bool __kthread_cancel_work_sync(struct kthread_work *work, bool is_dwork) +{ + struct kthread_worker *worker = work->worker; + unsigned long flags; + int ret = false; + + if (!worker) + goto out; + + spin_lock_irqsave(&worker->lock, flags); + /* Work must not be used with >1 worker, see kthread_queue_work(). */ + WARN_ON_ONCE(work->worker != worker); + + ret = __kthread_cancel_work(work, is_dwork, &flags); + + if (worker->current_work != work) + goto out_fast; + + /* + * The work is in progress and we need to wait with the lock released. + * In the meantime, block any queuing by setting the canceling counter. + */ + work->canceling++; + spin_unlock_irqrestore(&worker->lock, flags); + kthread_flush_work(work); + spin_lock_irqsave(&worker->lock, flags); + work->canceling--; + +out_fast: + spin_unlock_irqrestore(&worker->lock, flags); +out: + return ret; +} + +/** + * kthread_cancel_work_sync - cancel a kthread work and wait for it to finish + * @work: the kthread work to cancel + * + * Cancel @work and wait for its execution to finish. This function + * can be used even if the work re-queues itself. On return from this + * function, @work is guaranteed to be not pending or executing on any CPU. + * + * kthread_cancel_work_sync(&delayed_work->work) must not be used for + * delayed_work's. Use kthread_cancel_delayed_work_sync() instead. + * + * The caller must ensure that the worker on which @work was last + * queued can't be destroyed before this function returns. + * + * Return: %true if @work was pending, %false otherwise. + */ +bool kthread_cancel_work_sync(struct kthread_work *work) +{ + return __kthread_cancel_work_sync(work, false); +} +EXPORT_SYMBOL_GPL(kthread_cancel_work_sync); + +/** + * kthread_cancel_delayed_work_sync - cancel a kthread delayed work and + * wait for it to finish. + * @dwork: the kthread delayed work to cancel + * + * This is kthread_cancel_work_sync() for delayed works. + * + * Return: %true if @dwork was pending, %false otherwise. + */ +bool kthread_cancel_delayed_work_sync(struct kthread_delayed_work *dwork) +{ + return __kthread_cancel_work_sync(&dwork->work, true); +} +EXPORT_SYMBOL_GPL(kthread_cancel_delayed_work_sync); /** - * flush_kthread_worker - flush all current works on a kthread_worker + * kthread_flush_worker - flush all current works on a kthread_worker * @worker: worker to flush * * Wait until all currently executing or pending works on @worker are * finished. */ -void flush_kthread_worker(struct kthread_worker *worker) +void kthread_flush_worker(struct kthread_worker *worker) { struct kthread_flush_work fwork = { KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn), COMPLETION_INITIALIZER_ONSTACK(fwork.done), }; - queue_kthread_work(worker, &fwork.work); + kthread_queue_work(worker, &fwork.work); wait_for_completion(&fwork.done); } -EXPORT_SYMBOL_GPL(flush_kthread_worker); +EXPORT_SYMBOL_GPL(kthread_flush_worker); + +/** + * kthread_destroy_worker - destroy a kthread worker + * @worker: worker to be destroyed + * + * Flush and destroy @worker. The simple flush is enough because the kthread + * worker API is used only in trivial scenarios. There are no multi-step state + * machines needed. + */ +void kthread_destroy_worker(struct kthread_worker *worker) +{ + struct task_struct *task; + + task = worker->task; + if (WARN_ON(!task)) + return; + + kthread_flush_worker(worker); + kthread_stop(task); + WARN_ON(!list_empty(&worker->work_list)); + kfree(worker); +} +EXPORT_SYMBOL(kthread_destroy_worker); diff --git a/kernel/panic.c b/kernel/panic.c index ca8cea1ef673..e6480e20379e 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -71,6 +71,32 @@ void __weak nmi_panic_self_stop(struct pt_regs *regs) panic_smp_self_stop(); } +/* + * Stop other CPUs in panic. Architecture dependent code may override this + * with more suitable version. For example, if the architecture supports + * crash dump, it should save registers of each stopped CPU and disable + * per-CPU features such as virtualization extensions. + */ +void __weak crash_smp_send_stop(void) +{ + static int cpus_stopped; + + /* + * This function can be called twice in panic path, but obviously + * we execute this only once. + */ + if (cpus_stopped) + return; + + /* + * Note smp_send_stop is the usual smp shutdown function, which + * unfortunately means it may not be hardened to work in a panic + * situation. + */ + smp_send_stop(); + cpus_stopped = 1; +} + atomic_t panic_cpu = ATOMIC_INIT(PANIC_CPU_INVALID); /* @@ -164,14 +190,21 @@ void panic(const char *fmt, ...) if (!_crash_kexec_post_notifiers) { printk_nmi_flush_on_panic(); __crash_kexec(NULL); - } - /* - * Note smp_send_stop is the usual smp shutdown function, which - * unfortunately means it may not be hardened to work in a panic - * situation. - */ - smp_send_stop(); + /* + * Note smp_send_stop is the usual smp shutdown function, which + * unfortunately means it may not be hardened to work in a + * panic situation. + */ + smp_send_stop(); + } else { + /* + * If we want to do crash dump after notifier calls and + * kmsg_dump, we will need architecture dependent extra + * works in addition to stopping other CPUs. + */ + crash_smp_send_stop(); + } /* * Run any panic handlers, including those that might need to diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 1d3b7665d0be..2a99027312a6 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -73,6 +73,8 @@ void __ptrace_unlink(struct task_struct *child) { BUG_ON(!child->ptrace); + clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); + child->parent = child->real_parent; list_del_init(&child->ptrace_entry); @@ -489,7 +491,6 @@ static int ptrace_detach(struct task_struct *child, unsigned int data) /* Architecture-specific hardware disable .. */ ptrace_disable(child); - clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); write_lock_irq(&tasklist_lock); /* diff --git a/kernel/relay.c b/kernel/relay.c index 9988f5cc2d46..da79a109dbeb 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -328,13 +328,15 @@ static struct rchan_callbacks default_channel_callbacks = { /** * wakeup_readers - wake up readers waiting on a channel - * @data: contains the channel buffer + * @work: contains the channel buffer * - * This is the timer function used to defer reader waking. + * This is the function used to defer reader waking */ -static void wakeup_readers(unsigned long data) +static void wakeup_readers(struct irq_work *work) { - struct rchan_buf *buf = (struct rchan_buf *)data; + struct rchan_buf *buf; + + buf = container_of(work, struct rchan_buf, wakeup_work); wake_up_interruptible(&buf->read_wait); } @@ -352,9 +354,10 @@ static void __relay_reset(struct rchan_buf *buf, unsigned int init) if (init) { init_waitqueue_head(&buf->read_wait); kref_init(&buf->kref); - setup_timer(&buf->timer, wakeup_readers, (unsigned long)buf); - } else - del_timer_sync(&buf->timer); + init_irq_work(&buf->wakeup_work, wakeup_readers); + } else { + irq_work_sync(&buf->wakeup_work); + } buf->subbufs_produced = 0; buf->subbufs_consumed = 0; @@ -487,7 +490,7 @@ free_buf: static void relay_close_buf(struct rchan_buf *buf) { buf->finalized = 1; - del_timer_sync(&buf->timer); + irq_work_sync(&buf->wakeup_work); buf->chan->cb->remove_buf_file(buf->dentry); kref_put(&buf->kref, relay_remove_buf); } @@ -754,14 +757,15 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length) buf->early_bytes += buf->chan->subbuf_size - buf->padding[old_subbuf]; smp_mb(); - if (waitqueue_active(&buf->read_wait)) + if (waitqueue_active(&buf->read_wait)) { /* * Calling wake_up_interruptible() from here * will deadlock if we happen to be logging * from the scheduler (trying to re-grab * rq->lock), so defer it. */ - mod_timer(&buf->timer, jiffies + 1); + irq_work_queue(&buf->wakeup_work); + } } old = buf->data; diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 13bc43d1fb22..4a5c6e73ecd4 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -186,6 +186,11 @@ __smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu) kfree(td); return PTR_ERR(tsk); } + /* + * Park the thread so that it could start right on the CPU + * when it is available. + */ + kthread_park(tsk); get_task_struct(tsk); *per_cpu_ptr(ht->store, cpu) = tsk; if (ht->create) { diff --git a/kernel/workqueue.c b/kernel/workqueue.c index bd81f0390277..479d840db286 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -4261,7 +4261,7 @@ void print_worker_info(const char *log_lvl, struct task_struct *task) * This function is called without any synchronization and @task * could be in any state. Be careful with dereferences. */ - worker = probe_kthread_data(task); + worker = kthread_probe_data(task); /* * Carefully copy the associated workqueue's workfn and name. Keep diff --git a/lib/Makefile b/lib/Makefile index f3ca8c0ab634..50144a3aeebd 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -180,6 +180,7 @@ obj-$(CONFIG_IRQ_POLL) += irq_poll.o obj-$(CONFIG_STACKDEPOT) += stackdepot.o KASAN_SANITIZE_stackdepot.o := n +KCOV_INSTRUMENT_stackdepot.o := n libfdt_files = fdt.o fdt_ro.o fdt_wip.o fdt_rw.o fdt_sw.o fdt_strerror.o \ fdt_empty_tree.o diff --git a/lib/bitmap.c b/lib/bitmap.c index eca88087fa8a..0b66f0e5eb6b 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -496,6 +496,11 @@ EXPORT_SYMBOL(bitmap_print_to_pagebuf); * ranges. Consecutively set bits are shown as two hyphen-separated * decimal numbers, the smallest and largest bit numbers set in * the range. + * Optionally each range can be postfixed to denote that only parts of it + * should be set. The range will divided to groups of specific size. + * From each group will be used only defined amount of bits. + * Syntax: range:used_size/group_size + * Example: 0-1023:2/256 ==> 0,1,256,257,512,513,768,769 * * Returns 0 on success, -errno on invalid input strings. * Error values: @@ -507,16 +512,20 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen, int is_user, unsigned long *maskp, int nmaskbits) { - unsigned a, b; + unsigned int a, b, old_a, old_b; + unsigned int group_size, used_size; int c, old_c, totaldigits, ndigits; const char __user __force *ubuf = (const char __user __force *)buf; - int at_start, in_range; + int at_start, in_range, in_partial_range; totaldigits = c = 0; + old_a = old_b = 0; + group_size = used_size = 0; bitmap_zero(maskp, nmaskbits); do { at_start = 1; in_range = 0; + in_partial_range = 0; a = b = 0; ndigits = totaldigits; @@ -547,6 +556,24 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen, if ((totaldigits != ndigits) && isspace(old_c)) return -EINVAL; + if (c == '/') { + used_size = a; + at_start = 1; + in_range = 0; + a = b = 0; + continue; + } + + if (c == ':') { + old_a = a; + old_b = b; + at_start = 1; + in_range = 0; + in_partial_range = 1; + a = b = 0; + continue; + } + if (c == '-') { if (at_start || in_range) return -EINVAL; @@ -567,15 +594,30 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen, } if (ndigits == totaldigits) continue; + if (in_partial_range) { + group_size = a; + a = old_a; + b = old_b; + old_a = old_b = 0; + } /* if no digit is after '-', it's wrong*/ if (at_start && in_range) return -EINVAL; - if (!(a <= b)) + if (!(a <= b) || !(used_size <= group_size)) return -EINVAL; if (b >= nmaskbits) return -ERANGE; while (a <= b) { - set_bit(a, maskp); + if (in_partial_range) { + static int pos_in_group = 1; + + if (pos_in_group <= used_size) + set_bit(a, maskp); + + if (a == b || ++pos_in_group > group_size) + pos_in_group = 1; + } else + set_bit(a, maskp); a++; } } while (buflen && c == ','); diff --git a/lib/kstrtox.c b/lib/kstrtox.c index d8a5cf66c316..b8e2080c1a47 100644 --- a/lib/kstrtox.c +++ b/lib/kstrtox.c @@ -48,11 +48,9 @@ unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long { unsigned long long res; unsigned int rv; - int overflow; res = 0; rv = 0; - overflow = 0; while (*s) { unsigned int val; @@ -71,15 +69,13 @@ unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long */ if (unlikely(res & (~0ull << 60))) { if (res > div_u64(ULLONG_MAX - val, base)) - overflow = 1; + rv |= KSTRTOX_OVERFLOW; } res = res * base + val; rv++; s++; } *p = res; - if (overflow) - rv |= KSTRTOX_OVERFLOW; return rv; } diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c index 9c5fe8110413..7e35fc450c5b 100644 --- a/lib/strncpy_from_user.c +++ b/lib/strncpy_from_user.c @@ -1,6 +1,7 @@ #include #include #include +#include #include #include #include @@ -111,6 +112,7 @@ long strncpy_from_user(char *dst, const char __user *src, long count) long retval; kasan_check_write(dst, count); + check_object_size(dst, count, false); user_access_begin(); retval = do_strncpy_from_user(dst, src, count, max); user_access_end(); diff --git a/mm/bootmem.c b/mm/bootmem.c index a869f84f44d3..e8a55a3c9feb 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -155,7 +155,7 @@ void __init free_bootmem_late(unsigned long physaddr, unsigned long size) { unsigned long cursor, end; - kmemleak_free_part(__va(physaddr), size); + kmemleak_free_part_phys(physaddr, size); cursor = PFN_UP(physaddr); end = PFN_DOWN(physaddr + size); @@ -399,7 +399,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, { unsigned long start, end; - kmemleak_free_part(__va(physaddr), size); + kmemleak_free_part_phys(physaddr, size); start = PFN_UP(physaddr); end = PFN_DOWN(physaddr + size); @@ -420,7 +420,7 @@ void __init free_bootmem(unsigned long physaddr, unsigned long size) { unsigned long start, end; - kmemleak_free_part(__va(physaddr), size); + kmemleak_free_part_phys(physaddr, size); start = PFN_UP(physaddr); end = PFN_DOWN(physaddr + size); diff --git a/mm/cma.c b/mm/cma.c index bd0e1412475e..384c2cb51b56 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -336,7 +336,7 @@ int __init cma_declare_contiguous(phys_addr_t base, * kmemleak scans/reads tracked objects for pointers to other * objects but this address isn't mapped and accessible */ - kmemleak_ignore(phys_to_virt(addr)); + kmemleak_ignore_phys(addr); base = addr; } diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 086292f7c59d..a5e453cf05c4 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -90,6 +90,8 @@ #include #include #include +#include +#include #include #include #include @@ -1121,6 +1123,51 @@ void __ref kmemleak_no_scan(const void *ptr) } EXPORT_SYMBOL(kmemleak_no_scan); +/** + * kmemleak_alloc_phys - similar to kmemleak_alloc but taking a physical + * address argument + */ +void __ref kmemleak_alloc_phys(phys_addr_t phys, size_t size, int min_count, + gfp_t gfp) +{ + if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + kmemleak_alloc(__va(phys), size, min_count, gfp); +} +EXPORT_SYMBOL(kmemleak_alloc_phys); + +/** + * kmemleak_free_part_phys - similar to kmemleak_free_part but taking a + * physical address argument + */ +void __ref kmemleak_free_part_phys(phys_addr_t phys, size_t size) +{ + if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + kmemleak_free_part(__va(phys), size); +} +EXPORT_SYMBOL(kmemleak_free_part_phys); + +/** + * kmemleak_not_leak_phys - similar to kmemleak_not_leak but taking a physical + * address argument + */ +void __ref kmemleak_not_leak_phys(phys_addr_t phys) +{ + if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + kmemleak_not_leak(__va(phys)); +} +EXPORT_SYMBOL(kmemleak_not_leak_phys); + +/** + * kmemleak_ignore_phys - similar to kmemleak_ignore but taking a physical + * address argument + */ +void __ref kmemleak_ignore_phys(phys_addr_t phys) +{ + if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + kmemleak_ignore(__va(phys)); +} +EXPORT_SYMBOL(kmemleak_ignore_phys); + /* * Update an object's checksum and return true if it was modified. */ diff --git a/mm/memblock.c b/mm/memblock.c index c8dfa430342b..7608bc305936 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -723,7 +723,7 @@ int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size) (unsigned long long)base + size - 1, (void *)_RET_IP_); - kmemleak_free_part(__va(base), size); + kmemleak_free_part_phys(base, size); return memblock_remove_range(&memblock.reserved, base, size); } @@ -1152,7 +1152,7 @@ static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, * The min_count is set to 0 so that memblock allocations are * never reported as leaks. */ - kmemleak_alloc(__va(found), size, 0, 0); + kmemleak_alloc_phys(found, size, 0, 0); return found; } return 0; @@ -1399,7 +1399,7 @@ void __init __memblock_free_early(phys_addr_t base, phys_addr_t size) memblock_dbg("%s: [%#016llx-%#016llx] %pF\n", __func__, (u64)base, (u64)base + size - 1, (void *)_RET_IP_); - kmemleak_free_part(__va(base), size); + kmemleak_free_part_phys(base, size); memblock_remove_range(&memblock.reserved, base, size); } @@ -1419,7 +1419,7 @@ void __init __memblock_free_late(phys_addr_t base, phys_addr_t size) memblock_dbg("%s: [%#016llx-%#016llx] %pF\n", __func__, (u64)base, (u64)base + size - 1, (void *)_RET_IP_); - kmemleak_free_part(__va(base), size); + kmemleak_free_part_phys(base, size); cursor = PFN_UP(base); end = PFN_DOWN(base + size); diff --git a/mm/nobootmem.c b/mm/nobootmem.c index ba609b684d7a..487dad610731 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -84,7 +84,7 @@ void __init free_bootmem_late(unsigned long addr, unsigned long size) { unsigned long cursor, end; - kmemleak_free_part(__va(addr), size); + kmemleak_free_part_phys(addr, size); cursor = PFN_UP(addr); end = PFN_DOWN(addr + size); diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index c68ff3dcb926..e49121ee55f6 100644 --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -20,8 +20,6 @@ #include "main.h" -#include - struct net_device; #define BATADV_DEBUGFS_SUBDIR "batman_adv" diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 206a6b346a8d..a8368d1c4348 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -54,6 +54,7 @@ my $min_conf_desc_length = 4; my $spelling_file = "$D/spelling.txt"; my $codespell = 0; my $codespellfile = "/usr/share/codespell/dictionary.txt"; +my $conststructsfile = "$D/const_structs.checkpatch"; my $color = 1; my $allow_c99_comments = 1; @@ -523,7 +524,11 @@ our @mode_permission_funcs = ( ["module_param_array_named", 5], ["debugfs_create_(?:file|u8|u16|u32|u64|x8|x16|x32|x64|size_t|atomic_t|bool|blob|regset32|u32_array)", 2], ["proc_create(?:_data|)", 2], - ["(?:CLASS|DEVICE|SENSOR)_ATTR", 2], + ["(?:CLASS|DEVICE|SENSOR|SENSOR_DEVICE|IIO_DEVICE)_ATTR", 2], + ["IIO_DEV_ATTR_[A-Z_]+", 1], + ["SENSOR_(?:DEVICE_|)ATTR_2", 2], + ["SENSOR_TEMPLATE(?:_2|)", 3], + ["__ATTR", 2], ); #Create a search pattern for all these functions to speed up a loop below @@ -541,6 +546,32 @@ our $mode_perms_world_writable = qr{ 0[0-7][0-7][2367] }x; +our %mode_permission_string_types = ( + "S_IRWXU" => 0700, + "S_IRUSR" => 0400, + "S_IWUSR" => 0200, + "S_IXUSR" => 0100, + "S_IRWXG" => 0070, + "S_IRGRP" => 0040, + "S_IWGRP" => 0020, + "S_IXGRP" => 0010, + "S_IRWXO" => 0007, + "S_IROTH" => 0004, + "S_IWOTH" => 0002, + "S_IXOTH" => 0001, + "S_IRWXUGO" => 0777, + "S_IRUGO" => 0444, + "S_IWUGO" => 0222, + "S_IXUGO" => 0111, +); + +#Create a search pattern for all these strings to speed up a loop below +our $mode_perms_string_search = ""; +foreach my $entry (keys %mode_permission_string_types) { + $mode_perms_string_search .= '|' if ($mode_perms_string_search ne ""); + $mode_perms_string_search .= $entry; +} + our $allowed_asm_includes = qr{(?x: irq| memory| @@ -598,6 +629,29 @@ if ($codespell) { $misspellings = join("|", sort keys %spelling_fix) if keys %spelling_fix; +my $const_structs = ""; +if (open(my $conststructs, '<', $conststructsfile)) { + while (<$conststructs>) { + my $line = $_; + + $line =~ s/\s*\n?$//g; + $line =~ s/^\s*//g; + + next if ($line =~ m/^\s*#/); + next if ($line =~ m/^\s*$/); + if ($line =~ /\s/) { + print("$conststructsfile: '$line' invalid - ignored\n"); + next; + } + + $const_structs .= '|' if ($const_structs ne ""); + $const_structs .= $line; + } + close($conststructsfile); +} else { + warn "No structs that should be const will be found - file '$conststructsfile': $!\n"; +} + sub build_types { my $mods = "(?x: \n" . join("|\n ", (@modifierList, @modifierListFile)) . "\n)"; my $all = "(?x: \n" . join("|\n ", (@typeList, @typeListFile)) . "\n)"; @@ -704,6 +758,16 @@ sub seed_camelcase_file { } } +sub is_maintained_obsolete { + my ($filename) = @_; + + return 0 if (!(-e "$root/scripts/get_maintainer.pl")); + + my $status = `perl $root/scripts/get_maintainer.pl --status --nom --nol --nogit --nogit-fallback -f $filename 2>&1`; + + return $status =~ /obsolete/i; +} + my $camelcase_seeded = 0; sub seed_camelcase_includes { return if ($camelcase_seeded); @@ -2289,6 +2353,10 @@ sub process { } if ($found_file) { + if (is_maintained_obsolete($realfile)) { + WARN("OBSOLETE", + "$realfile is marked as 'obsolete' in the MAINTAINERS hierarchy. No unnecessary modifications please.\n"); + } if ($realfile =~ m@^(?:drivers/net/|net/|drivers/staging/)@) { $check = 1; } else { @@ -2939,6 +3007,30 @@ sub process { "Block comments use a trailing */ on a separate line\n" . $herecurr); } +# Block comment * alignment + if ($prevline =~ /$;[ \t]*$/ && #ends in comment + $line =~ /^\+[ \t]*$;/ && #leading comment + $rawline =~ /^\+[ \t]*\*/ && #leading * + (($prevrawline =~ /^\+.*?\/\*/ && #leading /* + $prevrawline !~ /\*\/[ \t]*$/) || #no trailing */ + $prevrawline =~ /^\+[ \t]*\*/)) { #leading * + my $oldindent; + $prevrawline =~ m@^\+([ \t]*/?)\*@; + if (defined($1)) { + $oldindent = expand_tabs($1); + } else { + $prevrawline =~ m@^\+(.*/?)\*@; + $oldindent = expand_tabs($1); + } + $rawline =~ m@^\+([ \t]*)\*@; + my $newindent = $1; + $newindent = expand_tabs($newindent); + if (length($oldindent) ne length($newindent)) { + WARN("BLOCK_COMMENT_STYLE", + "Block comments should align the * on each line\n" . $hereprev); + } + } + # check for missing blank lines after struct/union declarations # with exceptions for various attributes and macros if ($prevline =~ /^[\+ ]};?\s*$/ && @@ -4665,7 +4757,17 @@ sub process { $has_flow_statement = 1 if ($ctx =~ /\b(goto|return)\b/); $has_arg_concat = 1 if ($ctx =~ /\#\#/ && $ctx !~ /\#\#\s*(?:__VA_ARGS__|args)\b/); - $dstat =~ s/^.\s*\#\s*define\s+$Ident(?:\([^\)]*\))?\s*//; + $dstat =~ s/^.\s*\#\s*define\s+$Ident(\([^\)]*\))?\s*//; + my $define_args = $1; + my $define_stmt = $dstat; + my @def_args = (); + + if (defined $define_args && $define_args ne "") { + $define_args = substr($define_args, 1, length($define_args) - 2); + $define_args =~ s/\s*//g; + @def_args = split(",", $define_args); + } + $dstat =~ s/$;//g; $dstat =~ s/\\\n.//g; $dstat =~ s/^\s*//s; @@ -4701,6 +4803,15 @@ sub process { ^\[ }x; #print "REST<$rest> dstat<$dstat> ctx<$ctx>\n"; + + $ctx =~ s/\n*$//; + my $herectx = $here . "\n"; + my $stmt_cnt = statement_rawlines($ctx); + + for (my $n = 0; $n < $stmt_cnt; $n++) { + $herectx .= raw_line($linenr, $n) . "\n"; + } + if ($dstat ne '' && $dstat !~ /^(?:$Ident|-?$Constant),$/ && # 10, // foo(), $dstat !~ /^(?:$Ident|-?$Constant);$/ && # foo(); @@ -4716,13 +4827,6 @@ sub process { $dstat !~ /^\(\{/ && # ({... $ctx !~ /^.\s*#\s*define\s+TRACE_(?:SYSTEM|INCLUDE_FILE|INCLUDE_PATH)\b/) { - $ctx =~ s/\n*$//; - my $herectx = $here . "\n"; - my $cnt = statement_rawlines($ctx); - - for (my $n = 0; $n < $cnt; $n++) { - $herectx .= raw_line($linenr, $n) . "\n"; - } if ($dstat =~ /;/) { ERROR("MULTISTATEMENT_MACRO_USE_DO_WHILE", @@ -4731,6 +4835,46 @@ sub process { ERROR("COMPLEX_MACRO", "Macros with complex values should be enclosed in parentheses\n" . "$herectx"); } + + } + + # Make $define_stmt single line, comment-free, etc + my @stmt_array = split('\n', $define_stmt); + my $first = 1; + $define_stmt = ""; + foreach my $l (@stmt_array) { + $l =~ s/\\$//; + if ($first) { + $define_stmt = $l; + $first = 0; + } elsif ($l =~ /^[\+ ]/) { + $define_stmt .= substr($l, 1); + } + } + $define_stmt =~ s/$;//g; + $define_stmt =~ s/\s+/ /g; + $define_stmt = trim($define_stmt); + +# check if any macro arguments are reused (ignore '...' and 'type') + foreach my $arg (@def_args) { + next if ($arg =~ /\.\.\./); + next if ($arg =~ /^type$/i); + my $tmp = $define_stmt; + $tmp =~ s/\b(typeof|__typeof__|__builtin\w+|typecheck\s*\(\s*$Type\s*,|\#+)\s*\(*\s*$arg\s*\)*\b//g; + $tmp =~ s/\#+\s*$arg\b//g; + $tmp =~ s/\b$arg\s*\#\#//g; + my $use_cnt = $tmp =~ s/\b$arg\b//g; + if ($use_cnt > 1) { + CHK("MACRO_ARG_REUSE", + "Macro argument reuse '$arg' - possible side-effects?\n" . "$herectx"); + } +# check if any macro arguments may have other precedence issues + if ($define_stmt =~ m/($Operators)?\s*\b$arg\b\s*($Operators)?/m && + ((defined($1) && $1 ne ',') || + (defined($2) && $2 ne ','))) { + CHK("MACRO_ARG_PRECEDENCE", + "Macro argument '$arg' may be better as '($arg)' to avoid precedence issues\n" . "$herectx"); + } } # check for macros with flow control, but without ## concatenation @@ -5495,46 +5639,46 @@ sub process { } # Check for memcpy(foo, bar, ETH_ALEN) that could be ether_addr_copy(foo, bar) - if ($^V && $^V ge 5.10.0 && - defined $stat && - $stat =~ /^\+(?:.*?)\bmemcpy\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*ETH_ALEN\s*\)/) { - if (WARN("PREFER_ETHER_ADDR_COPY", - "Prefer ether_addr_copy() over memcpy() if the Ethernet addresses are __aligned(2)\n" . "$here\n$stat\n") && - $fix) { - $fixed[$fixlinenr] =~ s/\bmemcpy\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*ETH_ALEN\s*\)/ether_addr_copy($2, $7)/; - } - } +# if ($^V && $^V ge 5.10.0 && +# defined $stat && +# $stat =~ /^\+(?:.*?)\bmemcpy\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*ETH_ALEN\s*\)/) { +# if (WARN("PREFER_ETHER_ADDR_COPY", +# "Prefer ether_addr_copy() over memcpy() if the Ethernet addresses are __aligned(2)\n" . "$here\n$stat\n") && +# $fix) { +# $fixed[$fixlinenr] =~ s/\bmemcpy\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*ETH_ALEN\s*\)/ether_addr_copy($2, $7)/; +# } +# } # Check for memcmp(foo, bar, ETH_ALEN) that could be ether_addr_equal*(foo, bar) - if ($^V && $^V ge 5.10.0 && - defined $stat && - $stat =~ /^\+(?:.*?)\bmemcmp\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*ETH_ALEN\s*\)/) { - WARN("PREFER_ETHER_ADDR_EQUAL", - "Prefer ether_addr_equal() or ether_addr_equal_unaligned() over memcmp()\n" . "$here\n$stat\n") - } +# if ($^V && $^V ge 5.10.0 && +# defined $stat && +# $stat =~ /^\+(?:.*?)\bmemcmp\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*ETH_ALEN\s*\)/) { +# WARN("PREFER_ETHER_ADDR_EQUAL", +# "Prefer ether_addr_equal() or ether_addr_equal_unaligned() over memcmp()\n" . "$here\n$stat\n") +# } # check for memset(foo, 0x0, ETH_ALEN) that could be eth_zero_addr # check for memset(foo, 0xFF, ETH_ALEN) that could be eth_broadcast_addr - if ($^V && $^V ge 5.10.0 && - defined $stat && - $stat =~ /^\+(?:.*?)\bmemset\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*ETH_ALEN\s*\)/) { - - my $ms_val = $7; - - if ($ms_val =~ /^(?:0x|)0+$/i) { - if (WARN("PREFER_ETH_ZERO_ADDR", - "Prefer eth_zero_addr over memset()\n" . "$here\n$stat\n") && - $fix) { - $fixed[$fixlinenr] =~ s/\bmemset\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*,\s*ETH_ALEN\s*\)/eth_zero_addr($2)/; - } - } elsif ($ms_val =~ /^(?:0xff|255)$/i) { - if (WARN("PREFER_ETH_BROADCAST_ADDR", - "Prefer eth_broadcast_addr() over memset()\n" . "$here\n$stat\n") && - $fix) { - $fixed[$fixlinenr] =~ s/\bmemset\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*,\s*ETH_ALEN\s*\)/eth_broadcast_addr($2)/; - } - } - } +# if ($^V && $^V ge 5.10.0 && +# defined $stat && +# $stat =~ /^\+(?:.*?)\bmemset\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*\,\s*ETH_ALEN\s*\)/) { +# +# my $ms_val = $7; +# +# if ($ms_val =~ /^(?:0x|)0+$/i) { +# if (WARN("PREFER_ETH_ZERO_ADDR", +# "Prefer eth_zero_addr over memset()\n" . "$here\n$stat\n") && +# $fix) { +# $fixed[$fixlinenr] =~ s/\bmemset\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*,\s*ETH_ALEN\s*\)/eth_zero_addr($2)/; +# } +# } elsif ($ms_val =~ /^(?:0xff|255)$/i) { +# if (WARN("PREFER_ETH_BROADCAST_ADDR", +# "Prefer eth_broadcast_addr() over memset()\n" . "$here\n$stat\n") && +# $fix) { +# $fixed[$fixlinenr] =~ s/\bmemset\s*\(\s*$FuncArg\s*,\s*$FuncArg\s*,\s*ETH_ALEN\s*\)/eth_broadcast_addr($2)/; +# } +# } +# } # typecasts on min/max could be min_t/max_t if ($^V && $^V ge 5.10.0 && @@ -5654,6 +5798,19 @@ sub process { "externs should be avoided in .c files\n" . $herecurr); } + if ($realfile =~ /\.[ch]$/ && defined $stat && + $stat =~ /^.\s*(?:extern\s+)?$Type\s*$Ident\s*\(\s*([^{]+)\s*\)\s*;/s && + $1 ne "void") { + my $args = trim($1); + while ($args =~ m/\s*($Type\s*(?:$Ident|\(\s*\*\s*$Ident?\s*\)\s*$balanced_parens)?)/g) { + my $arg = trim($1); + if ($arg =~ /^$Type$/ && $arg !~ /enum\s+$Ident$/) { + WARN("FUNCTION_ARGUMENTS", + "function definition argument '$arg' should also have an identifier name\n" . $herecurr); + } + } + } + # checks for new __setup's if ($rawline =~ /\b__setup\("([^"]*)"/) { my $name = $1; @@ -5853,46 +6010,6 @@ sub process { } # check for various structs that are normally const (ops, kgdb, device_tree) - my $const_structs = qr{ - acpi_dock_ops| - address_space_operations| - backlight_ops| - block_device_operations| - dentry_operations| - dev_pm_ops| - dma_map_ops| - extent_io_ops| - file_lock_operations| - file_operations| - hv_ops| - ide_dma_ops| - intel_dvo_dev_ops| - item_operations| - iwl_ops| - kgdb_arch| - kgdb_io| - kset_uevent_ops| - lock_manager_operations| - microcode_ops| - mtrr_ops| - neigh_ops| - nlmsvc_binding| - of_device_id| - pci_raw_ops| - pipe_buf_operations| - platform_hibernation_ops| - platform_suspend_ops| - proto_ops| - rpc_pipe_ops| - seq_operations| - snd_ac97_build_ops| - soc_pcmcia_socket_ops| - stacktrace_ops| - sysfs_ops| - tty_operations| - uart_ops| - usb_mon_operations| - wd_ops}x; if ($line !~ /\bconst\b/ && $line =~ /\bstruct\s+($const_structs)\b/) { WARN("CONST_STRUCT", @@ -5979,34 +6096,69 @@ sub process { # Mode permission misuses where it seems decimal should be octal # This uses a shortcut match to avoid unnecessary uses of a slow foreach loop if ($^V && $^V ge 5.10.0 && + defined $stat && $line =~ /$mode_perms_search/) { foreach my $entry (@mode_permission_funcs) { my $func = $entry->[0]; my $arg_pos = $entry->[1]; + my $lc = $stat =~ tr@\n@@; + $lc = $lc + $linenr; + my $stat_real = raw_line($linenr, 0); + for (my $count = $linenr + 1; $count <= $lc; $count++) { + $stat_real = $stat_real . "\n" . raw_line($count, 0); + } + my $skip_args = ""; if ($arg_pos > 1) { $arg_pos--; $skip_args = "(?:\\s*$FuncArg\\s*,\\s*){$arg_pos,$arg_pos}"; } - my $test = "\\b$func\\s*\\(${skip_args}([\\d]+)\\s*[,\\)]"; - if ($line =~ /$test/) { + my $test = "\\b$func\\s*\\(${skip_args}($FuncArg(?:\\|\\s*$FuncArg)*)\\s*[,\\)]"; + if ($stat =~ /$test/) { my $val = $1; $val = $6 if ($skip_args ne ""); - - if ($val !~ /^0$/ && - (($val =~ /^$Int$/ && $val !~ /^$Octal$/) || - length($val) ne 4)) { + if (($val =~ /^$Int$/ && $val !~ /^$Octal$/) || + ($val =~ /^$Octal$/ && length($val) ne 4)) { ERROR("NON_OCTAL_PERMISSIONS", - "Use 4 digit octal (0777) not decimal permissions\n" . $herecurr); - } elsif ($val =~ /^$Octal$/ && (oct($val) & 02)) { + "Use 4 digit octal (0777) not decimal permissions\n" . "$here\n" . $stat_real); + } + if ($val =~ /^$Octal$/ && (oct($val) & 02)) { ERROR("EXPORTED_WORLD_WRITABLE", - "Exporting writable files is usually an error. Consider more restrictive permissions.\n" . $herecurr); + "Exporting writable files is usually an error. Consider more restrictive permissions.\n" . "$here\n" . $stat_real); } } } } +# check for uses of S_ that could be octal for readability + if ($line =~ /\b$mode_perms_string_search\b/) { + my $val = ""; + my $oval = ""; + my $to = 0; + my $curpos = 0; + my $lastpos = 0; + while ($line =~ /\b(($mode_perms_string_search)\b(?:\s*\|\s*)?\s*)/g) { + $curpos = pos($line); + my $match = $2; + my $omatch = $1; + last if ($lastpos > 0 && ($curpos - length($omatch) != $lastpos)); + $lastpos = $curpos; + $to |= $mode_permission_string_types{$match}; + $val .= '\s*\|\s*' if ($val ne ""); + $val .= $match; + $oval .= $omatch; + } + $oval =~ s/^\s*\|\s*//; + $oval =~ s/\s*\|\s*$//; + my $octal = sprintf("%04o", $to); + if (WARN("SYMBOLIC_PERMS", + "Symbolic permissions '$oval' are not preferred. Consider using octal permissions '$octal'.\n" . $herecurr) && + $fix) { + $fixed[$fixlinenr] =~ s/$val/$octal/; + } + } + # validate content of MODULE_LICENSE against list from include/linux/module.h if ($line =~ /\bMODULE_LICENSE\s*\(\s*($String)\s*\)/) { my $extracted_string = get_quoted_string($line, $rawline); diff --git a/scripts/const_structs.checkpatch b/scripts/const_structs.checkpatch new file mode 100644 index 000000000000..ac5f1267151d --- /dev/null +++ b/scripts/const_structs.checkpatch @@ -0,0 +1,64 @@ +acpi_dock_ops +address_space_operations +backlight_ops +block_device_operations +clk_ops +comedi_lrange +component_ops +dentry_operations +dev_pm_ops +dma_map_ops +driver_info +drm_connector_funcs +drm_encoder_funcs +drm_encoder_helper_funcs +ethtool_ops +extent_io_ops +file_lock_operations +file_operations +hv_ops +ide_dma_ops +ide_port_ops +inode_operations +intel_dvo_dev_ops +irq_domain_ops +item_operations +iwl_cfg +iwl_ops +kgdb_arch +kgdb_io +kset_uevent_ops +lock_manager_operations +machine_desc +microcode_ops +mlxsw_reg_info +mtrr_ops +neigh_ops +net_device_ops +nlmsvc_binding +nvkm_device_chip +of_device_id +pci_raw_ops +pipe_buf_operations +platform_hibernation_ops +platform_suspend_ops +proto_ops +regmap_access_table +rpc_pipe_ops +rtc_class_ops +sd_desc +seq_operations +sirfsoc_padmux +snd_ac97_build_ops +snd_soc_component_driver +soc_pcmcia_socket_ops +stacktrace_ops +sysfs_ops +tty_operations +uart_ops +usb_mon_operations +v4l2_ctrl_ops +v4l2_ioctl_ops +vm_operations_struct +wacom_features +wd_ops diff --git a/scripts/tags.sh b/scripts/tags.sh index b3775a9604ea..a2ff3388e5ea 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -263,7 +263,8 @@ exuberant() -I EXPORT_SYMBOL,EXPORT_SYMBOL_GPL,ACPI_EXPORT_SYMBOL \ -I DEFINE_TRACE,EXPORT_TRACEPOINT_SYMBOL,EXPORT_TRACEPOINT_SYMBOL_GPL \ -I static,const \ - --extra=+f --c-kinds=+px --langmap=c:+.h "${regex[@]}" + --extra=+fq --c-kinds=+px --fields=+iaS --langmap=c:+.h \ + "${regex[@]}" setup_regex exuberant kconfig all_kconfigs | xargs $1 -a \ diff --git a/sound/soc/intel/baytrail/sst-baytrail-ipc.c b/sound/soc/intel/baytrail/sst-baytrail-ipc.c index c8455b47388b..7ab14ce65a73 100644 --- a/sound/soc/intel/baytrail/sst-baytrail-ipc.c +++ b/sound/soc/intel/baytrail/sst-baytrail-ipc.c @@ -338,7 +338,7 @@ static irqreturn_t sst_byt_irq_thread(int irq, void *context) spin_unlock_irqrestore(&sst->spinlock, flags); /* continue to send any remaining messages... */ - queue_kthread_work(&ipc->kworker, &ipc->kwork); + kthread_queue_work(&ipc->kworker, &ipc->kwork); return IRQ_HANDLED; } diff --git a/sound/soc/intel/common/sst-acpi.h b/sound/soc/intel/common/sst-acpi.h index 5d2949324d0e..012742299dd5 100644 --- a/sound/soc/intel/common/sst-acpi.h +++ b/sound/soc/intel/common/sst-acpi.h @@ -12,7 +12,6 @@ * */ -#include #include #include diff --git a/sound/soc/intel/common/sst-ipc.c b/sound/soc/intel/common/sst-ipc.c index a12c7bb08d3b..6c672ac79cce 100644 --- a/sound/soc/intel/common/sst-ipc.c +++ b/sound/soc/intel/common/sst-ipc.c @@ -111,7 +111,7 @@ static int ipc_tx_message(struct sst_generic_ipc *ipc, u64 header, list_add_tail(&msg->list, &ipc->tx_list); spin_unlock_irqrestore(&ipc->dsp->spinlock, flags); - queue_kthread_work(&ipc->kworker, &ipc->kwork); + kthread_queue_work(&ipc->kworker, &ipc->kwork); if (wait) return tx_wait_done(ipc, msg, rx_data); @@ -281,7 +281,7 @@ int sst_ipc_init(struct sst_generic_ipc *ipc) return -ENOMEM; /* start the IPC message thread */ - init_kthread_worker(&ipc->kworker); + kthread_init_worker(&ipc->kworker); ipc->tx_thread = kthread_run(kthread_worker_fn, &ipc->kworker, "%s", dev_name(ipc->dev)); @@ -292,7 +292,7 @@ int sst_ipc_init(struct sst_generic_ipc *ipc) return ret; } - init_kthread_work(&ipc->kwork, ipc_tx_msgs); + kthread_init_work(&ipc->kwork, ipc_tx_msgs); return 0; } EXPORT_SYMBOL_GPL(sst_ipc_init); diff --git a/sound/soc/intel/haswell/sst-haswell-ipc.c b/sound/soc/intel/haswell/sst-haswell-ipc.c index 91565229d074..e432a31fd9f2 100644 --- a/sound/soc/intel/haswell/sst-haswell-ipc.c +++ b/sound/soc/intel/haswell/sst-haswell-ipc.c @@ -818,7 +818,7 @@ static irqreturn_t hsw_irq_thread(int irq, void *context) spin_unlock_irqrestore(&sst->spinlock, flags); /* continue to send any remaining messages... */ - queue_kthread_work(&ipc->kworker, &ipc->kwork); + kthread_queue_work(&ipc->kworker, &ipc->kwork); return IRQ_HANDLED; } diff --git a/sound/soc/intel/skylake/skl-sst-ipc.c b/sound/soc/intel/skylake/skl-sst-ipc.c index 0bd01e62622c..797cf4053235 100644 --- a/sound/soc/intel/skylake/skl-sst-ipc.c +++ b/sound/soc/intel/skylake/skl-sst-ipc.c @@ -464,7 +464,7 @@ irqreturn_t skl_dsp_irq_thread_handler(int irq, void *context) skl_ipc_int_enable(dsp); /* continue to send any remaining messages... */ - queue_kthread_work(&ipc->kworker, &ipc->kwork); + kthread_queue_work(&ipc->kworker, &ipc->kwork); return IRQ_HANDLED; } diff --git a/tools/testing/nvdimm/config_check.c b/tools/testing/nvdimm/config_check.c index 878daf3429e8..7dc5a0af9b54 100644 --- a/tools/testing/nvdimm/config_check.c +++ b/tools/testing/nvdimm/config_check.c @@ -1,4 +1,3 @@ -#include #include void check(void) diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index 9d0919ed52a4..f2e07f2fd4b4 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -3,7 +3,8 @@ 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 \ - regression1.o regression2.o regression3.o multiorder.o + regression1.o regression2.o regression3.o multiorder.o \ + iteration_check.o targets: $(TARGETS) diff --git a/tools/testing/radix-tree/iteration_check.c b/tools/testing/radix-tree/iteration_check.c new file mode 100644 index 000000000000..9adb8e7415a6 --- /dev/null +++ b/tools/testing/radix-tree/iteration_check.c @@ -0,0 +1,180 @@ +/* + * iteration_check.c: test races having to do with radix tree iteration + * Copyright (c) 2016 Intel Corporation + * Author: Ross Zwisler + * + * 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 +#include +#include "test.h" + +#define NUM_THREADS 4 +#define TAG 0 +static pthread_mutex_t tree_lock = PTHREAD_MUTEX_INITIALIZER; +static pthread_t threads[NUM_THREADS]; +RADIX_TREE(tree, GFP_KERNEL); +bool test_complete; + +/* relentlessly fill the tree with tagged entries */ +static void *add_entries_fn(void *arg) +{ + int pgoff; + + while (!test_complete) { + for (pgoff = 0; pgoff < 100; pgoff++) { + pthread_mutex_lock(&tree_lock); + if (item_insert(&tree, pgoff) == 0) + item_tag_set(&tree, pgoff, TAG); + pthread_mutex_unlock(&tree_lock); + } + } + + return NULL; +} + +/* + * Iterate over the tagged entries, doing a radix_tree_iter_retry() as we find + * things that have been removed and randomly resetting our iteration to the + * next chunk with radix_tree_iter_next(). Both radix_tree_iter_retry() and + * radix_tree_iter_next() cause radix_tree_next_slot() to be called with a + * NULL 'slot' variable. + */ +static void *tagged_iteration_fn(void *arg) +{ + struct radix_tree_iter iter; + void **slot; + + while (!test_complete) { + rcu_read_lock(); + radix_tree_for_each_tagged(slot, &tree, &iter, 0, TAG) { + void *entry; + int i; + + /* busy wait to let removals happen */ + for (i = 0; i < 1000000; i++) + ; + + entry = radix_tree_deref_slot(slot); + if (unlikely(!entry)) + continue; + + if (radix_tree_deref_retry(entry)) { + slot = radix_tree_iter_retry(&iter); + continue; + } + + if (rand() % 50 == 0) + slot = radix_tree_iter_next(&iter); + } + rcu_read_unlock(); + } + + return NULL; +} + +/* + * Iterate over the entries, doing a radix_tree_iter_retry() as we find things + * that have been removed and randomly resetting our iteration to the next + * chunk with radix_tree_iter_next(). Both radix_tree_iter_retry() and + * radix_tree_iter_next() cause radix_tree_next_slot() to be called with a + * NULL 'slot' variable. + */ +static void *untagged_iteration_fn(void *arg) +{ + struct radix_tree_iter iter; + void **slot; + + while (!test_complete) { + rcu_read_lock(); + radix_tree_for_each_slot(slot, &tree, &iter, 0) { + void *entry; + int i; + + /* busy wait to let removals happen */ + for (i = 0; i < 1000000; i++) + ; + + entry = radix_tree_deref_slot(slot); + if (unlikely(!entry)) + continue; + + if (radix_tree_deref_retry(entry)) { + slot = radix_tree_iter_retry(&iter); + continue; + } + + if (rand() % 50 == 0) + slot = radix_tree_iter_next(&iter); + } + rcu_read_unlock(); + } + + return NULL; +} + +/* + * Randomly remove entries to help induce radix_tree_iter_retry() calls in the + * two iteration functions. + */ +static void *remove_entries_fn(void *arg) +{ + while (!test_complete) { + int pgoff; + + pgoff = rand() % 100; + + pthread_mutex_lock(&tree_lock); + item_delete(&tree, pgoff); + pthread_mutex_unlock(&tree_lock); + } + + return NULL; +} + +/* This is a unit test for a bug found by the syzkaller tester */ +void iteration_test(void) +{ + int i; + + printf("Running iteration tests for 10 seconds\n"); + + srand(time(0)); + test_complete = false; + + if (pthread_create(&threads[0], NULL, tagged_iteration_fn, NULL)) { + perror("pthread_create"); + exit(1); + } + if (pthread_create(&threads[1], NULL, untagged_iteration_fn, NULL)) { + perror("pthread_create"); + exit(1); + } + if (pthread_create(&threads[2], NULL, add_entries_fn, NULL)) { + perror("pthread_create"); + exit(1); + } + if (pthread_create(&threads[3], NULL, remove_entries_fn, NULL)) { + perror("pthread_create"); + exit(1); + } + + sleep(10); + test_complete = true; + + for (i = 0; i < NUM_THREADS; i++) { + if (pthread_join(threads[i], NULL)) { + perror("pthread_join"); + exit(1); + } + } + + item_kill_tree(&tree); +} diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c index b7619ff3b552..daa9010693e8 100644 --- a/tools/testing/radix-tree/main.c +++ b/tools/testing/radix-tree/main.c @@ -332,6 +332,7 @@ int main(int argc, char **argv) regression1_test(); regression2_test(); regression3_test(); + iteration_test(); single_thread_tests(long_run); sleep(1); diff --git a/tools/testing/radix-tree/regression1.c b/tools/testing/radix-tree/regression1.c index 2d03a63bb79c..0d6813a61b37 100644 --- a/tools/testing/radix-tree/regression1.c +++ b/tools/testing/radix-tree/regression1.c @@ -43,7 +43,7 @@ #include "regression.h" static RADIX_TREE(mt_tree, GFP_KERNEL); -static pthread_mutex_t mt_lock; +static pthread_mutex_t mt_lock = PTHREAD_MUTEX_INITIALIZER; struct page { pthread_mutex_t lock; diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h index e85131369723..217fb2403f09 100644 --- a/tools/testing/radix-tree/test.h +++ b/tools/testing/radix-tree/test.h @@ -27,6 +27,7 @@ void item_kill_tree(struct radix_tree_root *root); void tag_check(void); void multiorder_checks(void); +void iteration_test(void); struct item * item_tag_set(struct radix_tree_root *root, unsigned long index, int tag);