CONFIG_DEBUG_PAGEALLOC, hence this option will not help
tracking down these problems.
+ debug_pagealloc=
+ [KNL] When CONFIG_DEBUG_PAGEALLOC is set, this
+ parameter enables the feature at boot time. In
+ default, it is disabled. We can avoid allocating huge
+ chunk of memory for debug pagealloc if we don't enable
+ it at boot time and the system will work mostly same
+ with the kernel built without CONFIG_DEBUG_PAGEALLOC.
+ on: enable the feature
+
debugpat [X86] Enable PAT debugging
decnet.addr= [HW,NET]
Format: {"off" | "on" | "skip[mbr]"}
efi= [EFI]
- Format: { "old_map" }
+ Format: { "old_map", "nochunk", "noruntime" }
old_map [X86-64]: switch to the old ioremap-based EFI
runtime services mapping. 32-bit still uses this one by
default.
+ nochunk: disable reading files in "chunks" in the EFI
+ boot stub, as chunking can cause problems with some
+ firmware implementations.
+ noruntime : disable EFI runtime services support
efi_no_storage_paranoia [EFI; X86]
Using this parameter you can use more than 50% of
multiple times interleaved with hugepages= to reserve
huge pages of different sizes. Valid pages sizes on
x86-64 are 2M (when the CPU supports "pse") and 1G
- (when the CPU supports the "pdpe1gb" cpuinfo flag)
- Note that 1GB pages can only be allocated at boot time
- using hugepages= and not freed afterwards.
+ (when the CPU supports the "pdpe1gb" cpuinfo flag).
hvc_iucv= [S390] Number of z/VM IUCV hypervisor console (HVC)
terminal devices. Valid values: 0..8
i8042.noloop [HW] Disable the AUX Loopback command while probing
for the AUX port
i8042.nomux [HW] Don't check presence of an active multiplexing
- controller. Default: true.
+ controller
i8042.nopnp [HW] Don't use ACPIPnP / PnPBIOS to discover KBD/AUX
controllers
i8042.notimeout [HW] Ignore timeout condition signalled by controller
.cdrom .chs .ignore_cable are additional options
See Documentation/ide/ide.txt.
+ ide-generic.probe-mask= [HW] (E)IDE subsystem
+ Format: <int>
+ Probe mask for legacy ISA IDE ports. Depending on
+ platform up to 6 ports are supported, enabled by
+ setting corresponding bits in the mask to 1. The
+ default value is 0x0, which has a special meaning.
+ On systems that have PCI, it triggers scanning the
+ PCI bus for the first and the second port, which
+ are then probed. On systems without PCI the value
+ of 0x0 enables probing the two first ports as if it
+ was 0x3.
+
ide-pci-generic.all-generic-ide [HW] (E)IDE subsystem
Claim all unknown PCI IDE storage controllers.
Formats: { "ima" | "ima-ng" }
Default: "ima-ng"
+ ima_template_fmt=
+ [IMA] Define a custom template format.
+ Format: { "field1|...|fieldN" }
+
ima.ahash_minsize= [IMA] Minimum file size for asynchronous hash usage
Format: <min_file_size>
Set the minimal file size for using asynchronous hash.
disable
Do not enable intel_pstate as the default
scaling driver for the supported processors
+ no_hwp
+ Do not enable hardware P state control (HWP)
+ if available.
intremap= [X86-64, Intel-IOMMU]
on enable Interrupt Remapping (default)
kmemleak= [KNL] Boot-time kmemleak enable/disable
Valid arguments: on, off
Default: on
+ Built with CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y,
+ the default is off.
kmemcheck= [X86] Boot-time kmemcheck enable/disable/one-shot mode
Valid arguments: 0, 1, 2
nodsp [SH] Disable hardware DSP at boot time.
- noefi [X86] Disable EFI runtime services support.
+ noefi Disable EFI runtime services support.
noexec [IA-64]
OSS [HW,OSS]
See Documentation/sound/oss/oss-parameters.txt
+ page_owner= [KNL] Boot-time page_owner enabling option.
+ Storage of the information about who allocated
+ each page is disabled in default. With this switch,
+ we can turn it on.
+ on: enable the feature
+
panic= [KNL] Kernel behaviour on panic: delay <timeout>
timeout > 0: seconds before rebooting
timeout = 0: wait forever
timeout < 0: reboot immediately
Format: <timeout>
+ panic_on_warn panic() instead of WARN(). Useful to cause kdump
+ on a WARN().
+
crash_kexec_post_notifiers
Run kdump after running panic-notifiers and dumping
kmsg. This only for the users who doubt kdump always
quiescent states. Units are jiffies, minimum
value is one, and maximum value is HZ.
+ rcutree.kthread_prio= [KNL,BOOT]
+ Set the SCHED_FIFO priority of the RCU
+ per-CPU kthreads (rcuc/N). This value is also
+ used for the priority of the RCU boost threads
+ (rcub/N). Valid values are 1-99 and the default
+ is 1 (the least-favored priority).
+
rcutree.rcu_nocb_leader_stride= [KNL]
Set the number of NOCB kthread groups, which
defaults to the square root of the number of
messages. Disable with a value less than or equal
to zero.
+ rcupdate.rcu_self_test= [KNL]
+ Run the RCU early boot self tests
+
+ rcupdate.rcu_self_test_bh= [KNL]
+ Run the RCU bh early boot self tests
+
+ rcupdate.rcu_self_test_sched= [KNL]
+ Run the RCU sched early boot self tests
+
rdinit= [KNL]
Format: <full_path>
Run specified binary instead of /init from the ramdisk,
neutralize any effect of /proc/sys/kernel/sysrq.
Useful for debugging.
+ tcpmhash_entries= [KNL,NET]
+ Set the number of tcp_metrics_hash slots.
+ Default value is 8192 or 16384 depending on total
+ ram pages. This is used to specify the TCP metrics
+ cache size. See Documentation/networking/ip-sysctl.txt
+ "tcp_no_metrics_save" section for more details.
+
tdfx= [HW,DRM]
test_suspend= [SUSPEND][,N]
e.g. base its process migration decisions on it.
Default is on.
+ topology_updates= [KNL, PPC, NUMA]
+ Format: {off}
+ Specify if the kernel should ignore (off)
+ topology updates sent by the hypervisor to this
+ LPAR.
+
tp720= [HW,PS2]
tpm_suspend_pcr=[HW,TPM]
See also Documentation/trace/ftrace.txt "trace options"
section.
+ tp_printk[FTRACE]
+ Have the tracepoints sent to printk as well as the
+ tracing ring buffer. This is useful for early boot up
+ where the system hangs or reboots and does not give the
+ option for reading the tracing buffer or performing a
+ ftrace_dump_on_oops.
+
+ To turn off having tracepoints sent to printk,
+ echo 0 > /proc/sys/kernel/tracepoint_printk
+ Note, echoing 1 into this file without the
+ tracepoint_printk kernel cmdline option has no effect.
+
+ ** CAUTION **
+
+ Having tracepoints sent to printk() and activating high
+ frequency tracepoints such as irq or sched, can cause
+ the system to live lock.
+
traceoff_on_warning
[FTRACE] enable this option to disable tracing when a
warning is hit. This turns off "tracing_on". Tracing can
usb-storage.delay_use=
[UMS] The delay in seconds before a new device is
- scanned for Logical Units (default 5).
+ scanned for Logical Units (default 1).
usb-storage.quirks=
[UMS] A list of quirks entries to supplement or
#include <linux/mempolicy.h>
#include <linux/key.h>
#include <linux/buffer_head.h>
-#include <linux/page_cgroup.h>
+#include <linux/page_ext.h>
#include <linux/debug_locks.h>
#include <linux/debugobjects.h>
#include <linux/lockdep.h>
#include <linux/context_tracking.h>
#include <linux/random.h>
#include <linux/list.h>
+#include <linux/integrity.h>
#include <asm/io.h>
#include <asm/bugs.h>
static void __init mm_init(void)
{
/*
- * page_cgroup requires contiguous pages,
+ * page_ext requires contiguous pages,
* bigger than MAX_ORDER unless SPARSEMEM.
*/
- page_cgroup_init_flatmem();
+ page_ext_init_flatmem();
mem_init();
kmem_cache_init();
percpu_init_late();
static_command_line, __start___param,
__stop___param - __start___param,
-1, -1, &unknown_bootoption);
- if (after_dashes)
+ if (!IS_ERR_OR_NULL(after_dashes))
parse_args("Setting init args", after_dashes, NULL, 0, -1, -1,
set_init_arg);
local_irq_disable();
idr_init_cache();
rcu_init();
+
+ /* trace_printk() and trace points may be used after this */
+ trace_init();
+
context_tracking_init();
radix_tree_init();
/* init some links before init_ISA_irqs() */
initrd_start = 0;
}
#endif
- page_cgroup_init();
+ page_ext_init();
debug_objects_mem_init();
kmemleak_init();
setup_per_cpu_pageset();
ret = run_init_process(execute_command);
if (!ret)
return 0;
+#ifndef CONFIG_INIT_FALLBACK
+ panic("Requested init %s failed (error %d).",
+ execute_command, ret);
+#else
pr_err("Failed to execute %s (error %d). Attempting defaults...\n",
- execute_command, ret);
+ execute_command, ret);
+#endif
}
if (!try_to_run_init_process("/sbin/init") ||
!try_to_run_init_process("/etc/init") ||
* Ok, we have completed the initial bootup, and
* we're essentially up and running. Get rid of the
* initmem segments and start the user-mode stuff..
+ *
+ * rootfs is available now, try loading the public keys
+ * and default modules
*/
- /* rootfs is available now, try loading default modules */
+ integrity_load_keys();
load_default_modules();
}
.data = &sysctl_numa_balancing_scan_size,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
},
{
.procname = "numa_balancing",
.mode = 0644,
.proc_handler = proc_dointvec,
},
+ {
+ .procname = "tracepoint_printk",
+ .data = &tracepoint_printk,
+ .maxlen = sizeof(tracepoint_printk),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
#endif
#ifdef CONFIG_KEXEC
{
.proc_handler = proc_dointvec,
},
#endif
+ {
+ .procname = "panic_on_warn",
+ .data = &panic_on_warn,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
{ }
};
*/
bool __read_mostly tracing_selftest_disabled;
+ /* Pipe tracepoints to printk */
+ struct trace_iterator *tracepoint_print_iter;
+ int tracepoint_printk;
+
/* For tracers that don't implement custom flags */
static struct tracer_opt dummy_tracer_opt[] = {
{ }
}
__setup("trace_clock=", set_trace_boot_clock);
+ static int __init set_tracepoint_printk(char *str)
+ {
+ if ((strcmp(str, "=0") != 0 && strcmp(str, "=off") != 0))
+ tracepoint_printk = 1;
+ return 1;
+ }
+ __setup("tp_printk", set_tracepoint_printk);
unsigned long long ns2usecs(cycle_t nsec)
{
return ret;
}
+/* TODO add a seq_buf_to_buffer() */
static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
{
int len;
- if (s->len <= s->readpos)
+ if (trace_seq_used(s) <= s->seq.readpos)
return -EBUSY;
- len = s->len - s->readpos;
+ len = trace_seq_used(s) - s->seq.readpos;
if (cnt > len)
cnt = len;
- memcpy(buf, s->buffer + s->readpos, cnt);
+ memcpy(buf, s->buffer + s->seq.readpos, cnt);
- s->readpos += cnt;
+ s->seq.readpos += cnt;
return cnt;
}
}
#endif /* CONFIG_TRACER_MAX_TRACE */
-static int wait_on_pipe(struct trace_iterator *iter)
+static int wait_on_pipe(struct trace_iterator *iter, bool full)
{
/* Iterators are static, they should be filled or empty */
if (trace_buffer_iter(iter, iter->cpu_file))
return 0;
- return ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file);
+ return ring_buffer_wait(iter->trace_buffer->buffer, iter->cpu_file,
+ full);
}
#ifdef CONFIG_FTRACE_STARTUP_TEST
pr_warning("** trace_printk() being used. Allocating extra memory. **\n");
pr_warning("** **\n");
pr_warning("** This means that this is a DEBUG kernel and it is **\n");
- pr_warning("** unsafe for produciton use. **\n");
+ pr_warning("** unsafe for production use. **\n");
pr_warning("** **\n");
pr_warning("** If you see this message and you are not debugging **\n");
pr_warning("** the kernel, report this immediately to your vendor! **\n");
goto out;
}
+ trace_seq_init(&iter->seq);
+
/*
* We make a copy of the current tracer to avoid concurrent
* changes on it while we are reading.
mutex_unlock(&iter->mutex);
- ret = wait_on_pipe(iter);
+ ret = wait_on_pipe(iter, false);
mutex_lock(&iter->mutex);
if (ret)
return ret;
-
- if (signal_pending(current))
- return -EINTR;
}
return 1;
trace_access_lock(iter->cpu_file);
while (trace_find_next_entry_inc(iter) != NULL) {
enum print_line_t ret;
- int len = iter->seq.len;
+ int save_len = iter->seq.seq.len;
ret = print_trace_line(iter);
if (ret == TRACE_TYPE_PARTIAL_LINE) {
/* don't print partial lines */
- iter->seq.len = len;
+ iter->seq.seq.len = save_len;
break;
}
if (ret != TRACE_TYPE_NO_CONSUME)
trace_consume(iter);
- if (iter->seq.len >= cnt)
+ if (trace_seq_used(&iter->seq) >= cnt)
break;
/*
/* Now copy what we have to the user */
sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
- if (iter->seq.readpos >= iter->seq.len)
+ if (iter->seq.seq.readpos >= trace_seq_used(&iter->seq))
trace_seq_init(&iter->seq);
/*
tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter)
{
size_t count;
+ int save_len;
int ret;
/* Seq buffer is page-sized, exactly what we need. */
for (;;) {
- count = iter->seq.len;
+ save_len = iter->seq.seq.len;
ret = print_trace_line(iter);
- count = iter->seq.len - count;
- if (rem < count) {
- rem = 0;
- iter->seq.len -= count;
+
+ if (trace_seq_has_overflowed(&iter->seq)) {
+ iter->seq.seq.len = save_len;
break;
}
+
+ /*
+ * This should not be hit, because it should only
+ * be set if the iter->seq overflowed. But check it
+ * anyway to be safe.
+ */
if (ret == TRACE_TYPE_PARTIAL_LINE) {
- iter->seq.len -= count;
+ iter->seq.seq.len = save_len;
+ break;
+ }
+
+ count = trace_seq_used(&iter->seq) - save_len;
+ if (rem < count) {
+ rem = 0;
+ iter->seq.seq.len = save_len;
break;
}
/* Copy the data into the page, so we can start over. */
ret = trace_seq_to_buffer(&iter->seq,
page_address(spd.pages[i]),
- iter->seq.len);
+ trace_seq_used(&iter->seq));
if (ret < 0) {
__free_page(spd.pages[i]);
break;
}
spd.partial[i].offset = 0;
- spd.partial[i].len = iter->seq.len;
+ spd.partial[i].len = trace_seq_used(&iter->seq);
trace_seq_init(&iter->seq);
}
goto out_unlock;
}
mutex_unlock(&trace_types_lock);
- ret = wait_on_pipe(iter);
+ ret = wait_on_pipe(iter, false);
mutex_lock(&trace_types_lock);
if (ret) {
size = ret;
goto out_unlock;
}
- if (signal_pending(current)) {
- size = -EINTR;
- goto out_unlock;
- }
goto again;
}
size = 0;
};
struct buffer_ref *ref;
int entries, size, i;
- ssize_t ret;
+ ssize_t ret = 0;
mutex_lock(&trace_types_lock);
int r;
ref = kzalloc(sizeof(*ref), GFP_KERNEL);
- if (!ref)
+ if (!ref) {
+ ret = -ENOMEM;
break;
+ }
ref->ref = 1;
ref->buffer = iter->trace_buffer->buffer;
ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file);
if (!ref->page) {
+ ret = -ENOMEM;
kfree(ref);
break;
}
/* did we read anything? */
if (!spd.nr_pages) {
+ if (ret)
+ goto out;
+
if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) {
ret = -EAGAIN;
goto out;
}
mutex_unlock(&trace_types_lock);
- ret = wait_on_pipe(iter);
+ ret = wait_on_pipe(iter, true);
mutex_lock(&trace_types_lock);
if (ret)
goto out;
- if (signal_pending(current)) {
- ret = -EINTR;
- goto out;
- }
+
goto again;
}
cnt = ring_buffer_read_events_cpu(trace_buf->buffer, cpu);
trace_seq_printf(s, "read events: %ld\n", cnt);
- count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
+ count = simple_read_from_buffer(ubuf, count, ppos,
+ s->buffer, trace_seq_used(s));
kfree(s);
int ret;
/* Paranoid: Make sure the parent is the "instances" directory */
- parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias);
+ parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
if (WARN_ON_ONCE(parent != trace_instance_dir))
return -ENOENT;
int ret;
/* Paranoid: Make sure the parent is the "instances" directory */
- parent = hlist_entry(inode->i_dentry.first, struct dentry, d_alias);
+ parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
if (WARN_ON_ONCE(parent != trace_instance_dir))
return -ENOENT;
trace_printk_seq(struct trace_seq *s)
{
/* Probably should print a warning here. */
- if (s->len >= TRACE_MAX_PRINT)
- s->len = TRACE_MAX_PRINT;
+ if (s->seq.len >= TRACE_MAX_PRINT)
+ s->seq.len = TRACE_MAX_PRINT;
+
+ /*
+ * More paranoid code. Although the buffer size is set to
+ * PAGE_SIZE, and TRACE_MAX_PRINT is 1000, this is just
+ * an extra layer of protection.
+ */
+ if (WARN_ON_ONCE(s->seq.len >= s->seq.size))
+ s->seq.len = s->seq.size - 1;
/* should be zero ended, but we are paranoid. */
- s->buffer[s->len] = 0;
+ s->buffer[s->seq.len] = 0;
printk(KERN_TRACE "%s", s->buffer);
return ret;
}
+ void __init trace_init(void)
+ {
+ if (tracepoint_printk) {
+ tracepoint_print_iter =
+ kmalloc(sizeof(*tracepoint_print_iter), GFP_KERNEL);
+ if (WARN_ON(!tracepoint_print_iter))
+ tracepoint_printk = 0;
+ }
+ tracer_alloc_buffers();
+ init_ftrace_syscalls();
+ trace_event_init();
+ }
+
__init static int clear_boot_tracer(void)
{
/*
return 0;
}
- early_initcall(tracer_alloc_buffers);
fs_initcall(tracer_init_debugfs);
late_initcall(clear_boot_tracer);
}
EXPORT_SYMBOL_GPL(ftrace_event_buffer_reserve);
+ static DEFINE_SPINLOCK(tracepoint_iter_lock);
+
+ static void output_printk(struct ftrace_event_buffer *fbuffer)
+ {
+ struct ftrace_event_call *event_call;
+ struct trace_event *event;
+ unsigned long flags;
+ struct trace_iterator *iter = tracepoint_print_iter;
+
+ if (!iter)
+ return;
+
+ event_call = fbuffer->ftrace_file->event_call;
+ if (!event_call || !event_call->event.funcs ||
+ !event_call->event.funcs->trace)
+ return;
+
+ event = &fbuffer->ftrace_file->event_call->event;
+
+ spin_lock_irqsave(&tracepoint_iter_lock, flags);
+ trace_seq_init(&iter->seq);
+ iter->ent = fbuffer->entry;
+ event_call->event.funcs->trace(iter, 0, event);
+ trace_seq_putc(&iter->seq, 0);
+ printk("%s", iter->seq.buffer);
+
+ spin_unlock_irqrestore(&tracepoint_iter_lock, flags);
+ }
+
void ftrace_event_buffer_commit(struct ftrace_event_buffer *fbuffer)
{
+ if (tracepoint_printk)
+ output_printk(fbuffer);
+
event_trigger_unlock_commit(fbuffer->ftrace_file, fbuffer->buffer,
fbuffer->event, fbuffer->entry,
fbuffer->flags, fbuffer->pc);
if (dir) {
spin_lock(&dir->d_lock); /* probably unneeded */
- list_for_each_entry(child, &dir->d_subdirs, d_u.d_child) {
+ list_for_each_entry(child, &dir->d_subdirs, d_child) {
if (child->d_inode) /* probably unneeded */
child->d_inode->i_private = NULL;
}
mutex_unlock(&event_mutex);
if (file)
- r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+ r = simple_read_from_buffer(ubuf, cnt, ppos,
+ s->buffer, trace_seq_used(s));
kfree(s);
trace_seq_init(s);
print_subsystem_event_filter(system, s);
- r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+ r = simple_read_from_buffer(ubuf, cnt, ppos,
+ s->buffer, trace_seq_used(s));
kfree(s);
trace_seq_init(s);
func(s);
- r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
+ r = simple_read_from_buffer(ubuf, cnt, ppos,
+ s->buffer, trace_seq_used(s));
kfree(s);
#endif
return 0;
}
- early_initcall(event_trace_memsetup);
- core_initcall(event_trace_enable);
+
+ void __init trace_event_init(void)
+ {
+ event_trace_memsetup();
+ init_ftrace_syscalls();
+ event_trace_enable();
+ }
+
fs_initcall(event_trace_init);
#ifdef CONFIG_FTRACE_STARTUP_TEST
int size;
syscall_nr = trace_get_syscall_nr(current, regs);
- if (syscall_nr < 0)
+ if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
return;
/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */
int syscall_nr;
syscall_nr = trace_get_syscall_nr(current, regs);
- if (syscall_nr < 0)
+ if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
return;
/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE()) */
return (unsigned long)sys_call_table[nr];
}
- static int __init init_ftrace_syscalls(void)
+ void __init init_ftrace_syscalls(void)
{
struct syscall_metadata *meta;
unsigned long addr;
GFP_KERNEL);
if (!syscalls_metadata) {
WARN_ON(1);
- return -ENOMEM;
+ return;
}
for (i = 0; i < NR_syscalls; i++) {
meta->syscall_nr = i;
syscalls_metadata[i] = meta;
}
-
- return 0;
}
- early_initcall(init_ftrace_syscalls);
#ifdef CONFIG_PERF_EVENTS
int size;
syscall_nr = trace_get_syscall_nr(current, regs);
- if (syscall_nr < 0)
+ if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
return;
if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
return;
int size;
syscall_nr = trace_get_syscall_nr(current, regs);
- if (syscall_nr < 0)
+ if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
return;
if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
return;