From 51d4052b01ca555e0d1d5fe297b309beb6c64aa0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:14 +0200 Subject: watchdog/sysctl: Get rid of the #ifdeffery The sysctl of the nmi_watchdog file prevents writes by setting: min = max = 0 if none of the users is enabled. That involves ifdeffery and is competely non obvious. If none of the facilities is enabeld, then the file can simply be made read only. Move the ifdeffery into the header and use a constant for file permissions. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194147.706073616@linutronix.de Signed-off-by: Ingo Molnar --- kernel/sysctl.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6648fbbb8157..539cb4e97bb8 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -891,14 +891,10 @@ static struct ctl_table kern_table[] = { .procname = "nmi_watchdog", .data = &nmi_watchdog_enabled, .maxlen = sizeof (int), - .mode = 0644, + .mode = NMI_WATCHDOG_SYSCTL_PERM, .proc_handler = proc_nmi_watchdog, .extra1 = &zero, -#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) .extra2 = &one, -#else - .extra2 = &zero, -#endif }, { .procname = "watchdog_cpumask", -- cgit v1.3-8-gc7d7 From 7feeb9cd4f5b34476ffb9e6d58d58c5416375b19 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 12 Sep 2017 21:37:15 +0200 Subject: watchdog/sysctl: Clean up sysctl variable name space Reflect that these variables are user interface related and remove the whitespace damage in the sysctl table while at it. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194147.783210221@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/nmi.h | 16 ++++++++-------- kernel/sysctl.c | 16 ++++++++-------- kernel/watchdog.c | 41 ++++++++++++++++++++--------------------- 3 files changed, 36 insertions(+), 37 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 5774b443dba1..4a8d1037364e 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -17,8 +17,8 @@ void lockup_detector_cleanup(void); bool is_hardlockup(void); extern int watchdog_user_enabled; -extern int nmi_watchdog_enabled; -extern int soft_watchdog_enabled; +extern int nmi_watchdog_user_enabled; +extern int soft_watchdog_user_enabled; extern int watchdog_thresh; extern unsigned long watchdog_enabled; @@ -62,12 +62,12 @@ static inline void reset_hung_task_detector(void) { } * 'watchdog_enabled' variable. Each lockup detector has its dedicated bit - * bit 0 for the hard lockup detector and bit 1 for the soft lockup detector. * - * 'watchdog_user_enabled', 'nmi_watchdog_enabled' and 'soft_watchdog_enabled' - * are variables that are only used as an 'interface' between the parameters - * in /proc/sys/kernel and the internal state bits in 'watchdog_enabled'. The - * 'watchdog_thresh' variable is handled differently because its value is not - * boolean, and the lockup detectors are 'suspended' while 'watchdog_thresh' - * is equal zero. + * 'watchdog_user_enabled', 'nmi_watchdog_user_enabled' and + * 'soft_watchdog_user_enabled' are variables that are only used as an + * 'interface' between the parameters in /proc/sys/kernel and the internal + * state bits in 'watchdog_enabled'. The 'watchdog_thresh' variable is + * handled differently because its value is not boolean, and the lockup + * detectors are 'suspended' while 'watchdog_thresh' is equal zero. */ #define NMI_WATCHDOG_ENABLED_BIT 0 #define SOFT_WATCHDOG_ENABLED_BIT 1 diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 539cb4e97bb8..4c08ed4a379e 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -871,9 +871,9 @@ static struct ctl_table kern_table[] = { #if defined(CONFIG_LOCKUP_DETECTOR) { .procname = "watchdog", - .data = &watchdog_user_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, .proc_handler = proc_watchdog, .extra1 = &zero, .extra2 = &one, @@ -889,8 +889,8 @@ static struct ctl_table kern_table[] = { }, { .procname = "nmi_watchdog", - .data = &nmi_watchdog_enabled, - .maxlen = sizeof (int), + .data = &nmi_watchdog_user_enabled, + .maxlen = sizeof(int), .mode = NMI_WATCHDOG_SYSCTL_PERM, .proc_handler = proc_nmi_watchdog, .extra1 = &zero, @@ -906,9 +906,9 @@ static struct ctl_table kern_table[] = { #ifdef CONFIG_SOFTLOCKUP_DETECTOR { .procname = "soft_watchdog", - .data = &soft_watchdog_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &soft_watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, .proc_handler = proc_soft_watchdog, .extra1 = &zero, .extra2 = &one, diff --git a/kernel/watchdog.c b/kernel/watchdog.c index ca8747221e87..baae9fc95031 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -31,8 +31,6 @@ static DEFINE_MUTEX(watchdog_mutex); -int __read_mostly nmi_watchdog_enabled; - #if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG) unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED | NMI_WATCHDOG_ENABLED; @@ -40,6 +38,17 @@ unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED | unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED; #endif +int __read_mostly nmi_watchdog_user_enabled; +int __read_mostly soft_watchdog_user_enabled; +int __read_mostly watchdog_user_enabled; +int __read_mostly watchdog_thresh = 10; + +struct cpumask watchdog_allowed_mask __read_mostly; +static bool softlockup_threads_initialized __read_mostly; + +struct cpumask watchdog_cpumask __read_mostly; +unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); + #ifdef CONFIG_HARDLOCKUP_DETECTOR /* * Should we panic when a soft-lockup or hard-lockup occurs: @@ -85,12 +94,6 @@ __setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); # endif /* CONFIG_SMP */ #endif /* CONFIG_HARDLOCKUP_DETECTOR */ -int __read_mostly watchdog_user_enabled; -int __read_mostly watchdog_thresh = 10; - -struct cpumask watchdog_cpumask __read_mostly; -unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); - /* * These functions can be overridden if an architecture implements its * own hardlockup detector. @@ -113,7 +116,7 @@ void __weak watchdog_nmi_disable(unsigned int cpu) * watchdog_nmi_reconfigure can be implemented to be notified after any * watchdog configuration change. The arch hardlockup watchdog should * respond to the following variables: - * - nmi_watchdog_enabled + * - watchdog_enabled * - watchdog_thresh * - watchdog_cpumask * - sysctl_hardlockup_all_cpu_backtrace @@ -126,10 +129,6 @@ void __weak watchdog_nmi_reconfigure(void) { } /* Global variables, exported for sysctl */ unsigned int __read_mostly softlockup_panic = CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; -int __read_mostly soft_watchdog_enabled; - -struct cpumask watchdog_allowed_mask __read_mostly; -static bool softlockup_threads_initialized __read_mostly; static u64 __read_mostly sample_period; @@ -606,14 +605,14 @@ static void proc_watchdog_update(void) /* * common function for watchdog, nmi_watchdog and soft_watchdog parameter * - * caller | table->data points to | 'which' contains the flag(s) - * -------------------|-----------------------|----------------------------- - * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED or'ed - * | | with SOFT_WATCHDOG_ENABLED - * -------------------|-----------------------|----------------------------- - * proc_nmi_watchdog | nmi_watchdog_enabled | NMI_WATCHDOG_ENABLED - * -------------------|-----------------------|----------------------------- - * proc_soft_watchdog | soft_watchdog_enabled | SOFT_WATCHDOG_ENABLED + * caller | table->data points to | 'which' + * -------------------|----------------------------|-------------------------- + * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED | + * | | SOFT_WATCHDOG_ENABLED + * -------------------|----------------------------|-------------------------- + * proc_nmi_watchdog | nmi_watchdog_user_enabled | NMI_WATCHDOG_ENABLED + * -------------------|----------------------------|-------------------------- + * proc_soft_watchdog | soft_watchdog_user_enabled | SOFT_WATCHDOG_ENABLED */ static int proc_watchdog_common(int which, struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) -- cgit v1.3-8-gc7d7 From 5ccba44ba118a5000cccc50076b0344632459779 Mon Sep 17 00:00:00 2001 From: Ethan Zhao Date: Mon, 4 Sep 2017 13:59:34 +0800 Subject: sched/sysctl: Check user input value of sysctl_sched_time_avg System will hang if user set sysctl_sched_time_avg to 0: [root@XXX ~]# sysctl kernel.sched_time_avg_ms=0 Stack traceback for pid 0 0xffff883f6406c600 0 0 1 3 R 0xffff883f6406cf50 *swapper/3 ffff883f7ccc3ae8 0000000000000018 ffffffff810c4dd0 0000000000000000 0000000000017800 ffff883f7ccc3d78 0000000000000003 ffff883f7ccc3bf8 ffffffff810c4fc9 ffff883f7ccc3c08 00000000810c5043 ffff883f7ccc3c08 Call Trace: [] ? update_group_capacity+0x110/0x200 [] ? update_sd_lb_stats+0x109/0x600 [] ? find_busiest_group+0x47/0x530 [] ? load_balance+0x194/0x900 [] ? update_rq_clock.part.83+0x1a/0xe0 [] ? rebalance_domains+0x152/0x290 [] ? run_rebalance_domains+0xdc/0x1d0 [] ? __do_softirq+0xfb/0x320 [] ? irq_exit+0x125/0x130 [] ? scheduler_ipi+0x97/0x160 [] ? smp_reschedule_interrupt+0x29/0x30 [] ? reschedule_interrupt+0x6e/0x80 [] ? cpuidle_enter_state+0xcc/0x230 [] ? cpuidle_enter_state+0x9c/0x230 [] ? cpuidle_enter+0x17/0x20 [] ? cpu_startup_entry+0x38c/0x420 [] ? start_secondary+0x173/0x1e0 Because divide-by-zero error happens in function: update_group_capacity() update_cpu_capacity() scale_rt_capacity() { ... total = sched_avg_period() + delta; used = div_u64(avg, total); ... } To fix this issue, check user input value of sysctl_sched_time_avg, keep it unchanged when hitting invalid input, and set the minimum limit of sysctl_sched_time_avg to 1 ms. Reported-by: James Puthukattukaran Signed-off-by: Ethan Zhao Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: efault@gmx.de Cc: ethan.kernel@gmail.com Cc: keescook@chromium.org Cc: mcgrof@kernel.org Cc: Link: http://lkml.kernel.org/r/1504504774-18253-1-git-send-email-ethan.zhao@oracle.com Signed-off-by: Ingo Molnar --- kernel/sysctl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6648fbbb8157..423554ad3610 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -367,7 +367,8 @@ static struct ctl_table kern_table[] = { .data = &sysctl_sched_time_avg, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, #ifdef CONFIG_SCHEDSTATS { -- cgit v1.3-8-gc7d7 From 3181c38e4df257852a0c0a53552fd5c869402886 Mon Sep 17 00:00:00 2001 From: "Luis R. Rodriguez" Date: Tue, 3 Oct 2017 16:16:07 -0700 Subject: kernel/sysctl.c: remove duplicate UINT_MAX check on do_proc_douintvec_conv() do_proc_douintvec_conv() has two UINT_MAX checks, we can remove one. This has no functional changes other than fixing a compiler warning: kernel/sysctl.c:2190]: (warning) Identical condition '*lvalp>UINT_MAX', second condition is always false Fixes: 4f2fec00afa60 ("sysctl: simplify unsigned int support") Link: http://lkml.kernel.org/r/20170919072918.12066-1-mcgrof@kernel.org Signed-off-by: Luis R. Rodriguez Reported-by: David Binderman Acked-by: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 423554ad3610..4da9e622471f 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2186,8 +2186,6 @@ static int do_proc_douintvec_conv(unsigned long *lvalp, int write, void *data) { if (write) { - if (*lvalp > UINT_MAX) - return -EINVAL; if (*lvalp > UINT_MAX) return -EINVAL; *valp = *lvalp; -- cgit v1.3-8-gc7d7 From b35bd0d9f8a8ea17aae40893e18274d191a2d2c5 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 30 Sep 2017 23:39:05 -0600 Subject: sysctl: remove /proc/sys/vm/nr_pdflush_threads This tunable has been obsolete since 2.6.32, and writes to the file have been failing and complaining in dmesg since then: nr_pdflush_threads exported in /proc is scheduled for removal That was 8 years ago. Remove the file ABI obsolete notice, and the sysfs file. Reviewed-by: Jan Kara Signed-off-by: Jens Axboe --- Documentation/ABI/obsolete/proc-sys-vm-nr_pdflush_threads | 5 ----- kernel/sysctl.c | 5 ----- 2 files changed, 10 deletions(-) delete mode 100644 Documentation/ABI/obsolete/proc-sys-vm-nr_pdflush_threads (limited to 'kernel/sysctl.c') diff --git a/Documentation/ABI/obsolete/proc-sys-vm-nr_pdflush_threads b/Documentation/ABI/obsolete/proc-sys-vm-nr_pdflush_threads deleted file mode 100644 index b0b0eeb20fe3..000000000000 --- a/Documentation/ABI/obsolete/proc-sys-vm-nr_pdflush_threads +++ /dev/null @@ -1,5 +0,0 @@ -What: /proc/sys/vm/nr_pdflush_threads -Date: June 2012 -Contact: Wanpeng Li -Description: Since pdflush is replaced by per-BDI flusher, the interface of old pdflush - exported in /proc/sys/vm/ should be removed. diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6648fbbb8157..a5dd8d82c253 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1344,11 +1344,6 @@ static struct ctl_table vm_table[] = { .proc_handler = dirtytime_interval_handler, .extra1 = &zero, }, - { - .procname = "nr_pdflush_threads", - .mode = 0444 /* read-only */, - .proc_handler = pdflush_proc_obsolete, - }, { .procname = "swappiness", .data = &vm_swappiness, -- cgit v1.3-8-gc7d7 From 4675ff05de2d76d167336b368bd07f3fef6ed5a6 Mon Sep 17 00:00:00 2001 From: "Levin, Alexander (Sasha Levin)" Date: Wed, 15 Nov 2017 17:36:02 -0800 Subject: kmemcheck: rip it out Fix up makefiles, remove references, and git rm kmemcheck. Link: http://lkml.kernel.org/r/20171007030159.22241-4-alexander.levin@verizon.com Signed-off-by: Sasha Levin Cc: Steven Rostedt Cc: Vegard Nossum Cc: Pekka Enberg Cc: Michal Hocko Cc: Eric W. Biederman Cc: Alexander Potapenko Cc: Tim Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/kernel-parameters.txt | 7 - Documentation/dev-tools/index.rst | 1 - Documentation/dev-tools/kmemcheck.rst | 733 ------------------------ MAINTAINERS | 10 - arch/x86/Kconfig | 3 +- arch/x86/include/asm/kmemcheck.h | 42 -- arch/x86/include/asm/string_32.h | 9 - arch/x86/include/asm/string_64.h | 8 - arch/x86/kernel/cpu/intel.c | 15 - arch/x86/mm/Makefile | 2 - arch/x86/mm/init.c | 5 +- arch/x86/mm/kmemcheck/Makefile | 1 - arch/x86/mm/kmemcheck/error.c | 227 -------- arch/x86/mm/kmemcheck/error.h | 15 - arch/x86/mm/kmemcheck/kmemcheck.c | 658 --------------------- arch/x86/mm/kmemcheck/opcode.c | 106 ---- arch/x86/mm/kmemcheck/opcode.h | 9 - arch/x86/mm/kmemcheck/pte.c | 22 - arch/x86/mm/kmemcheck/pte.h | 10 - arch/x86/mm/kmemcheck/selftest.c | 70 --- arch/x86/mm/kmemcheck/selftest.h | 6 - arch/x86/mm/kmemcheck/shadow.c | 173 ------ arch/x86/mm/kmemcheck/shadow.h | 18 - include/linux/interrupt.h | 15 - include/linux/kmemcheck.h | 171 ------ kernel/softirq.c | 10 - kernel/sysctl.c | 10 - lib/Kconfig.debug | 6 +- lib/Kconfig.kmemcheck | 94 --- mm/Kconfig.debug | 1 - mm/Makefile | 2 - mm/kmemcheck.c | 125 ---- mm/slub.c | 5 +- scripts/kernel-doc | 2 - tools/include/linux/kmemcheck.h | 8 - 35 files changed, 7 insertions(+), 2592 deletions(-) delete mode 100644 Documentation/dev-tools/kmemcheck.rst delete mode 100644 arch/x86/mm/kmemcheck/Makefile delete mode 100644 arch/x86/mm/kmemcheck/kmemcheck.c delete mode 100644 arch/x86/mm/kmemcheck/shadow.c delete mode 100644 lib/Kconfig.kmemcheck (limited to 'kernel/sysctl.c') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index b74e13312fdc..00bb04972612 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1864,13 +1864,6 @@ 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 - kmemcheck=0 (disabled) - kmemcheck=1 (enabled) - kmemcheck=2 (one-shot mode) - Default: 2 (one-shot mode) - kvm.ignore_msrs=[KVM] Ignore guest accesses to unhandled MSRs. Default is 0 (don't ignore, but inject #GP) diff --git a/Documentation/dev-tools/index.rst b/Documentation/dev-tools/index.rst index a81787cd47d7..e313925fb0fa 100644 --- a/Documentation/dev-tools/index.rst +++ b/Documentation/dev-tools/index.rst @@ -21,7 +21,6 @@ whole; patches welcome! kasan ubsan kmemleak - kmemcheck gdb-kernel-debugging kgdb kselftest diff --git a/Documentation/dev-tools/kmemcheck.rst b/Documentation/dev-tools/kmemcheck.rst deleted file mode 100644 index 7f3d1985de74..000000000000 --- a/Documentation/dev-tools/kmemcheck.rst +++ /dev/null @@ -1,733 +0,0 @@ -Getting started with kmemcheck -============================== - -Vegard Nossum - - -Introduction ------------- - -kmemcheck is a debugging feature for the Linux Kernel. More specifically, it -is a dynamic checker that detects and warns about some uses of uninitialized -memory. - -Userspace programmers might be familiar with Valgrind's memcheck. The main -difference between memcheck and kmemcheck is that memcheck works for userspace -programs only, and kmemcheck works for the kernel only. The implementations -are of course vastly different. Because of this, kmemcheck is not as accurate -as memcheck, but it turns out to be good enough in practice to discover real -programmer errors that the compiler is not able to find through static -analysis. - -Enabling kmemcheck on a kernel will probably slow it down to the extent that -the machine will not be usable for normal workloads such as e.g. an -interactive desktop. kmemcheck will also cause the kernel to use about twice -as much memory as normal. For this reason, kmemcheck is strictly a debugging -feature. - - -Downloading ------------ - -As of version 2.6.31-rc1, kmemcheck is included in the mainline kernel. - - -Configuring and compiling -------------------------- - -kmemcheck only works for the x86 (both 32- and 64-bit) platform. A number of -configuration variables must have specific settings in order for the kmemcheck -menu to even appear in "menuconfig". These are: - -- ``CONFIG_CC_OPTIMIZE_FOR_SIZE=n`` - This option is located under "General setup" / "Optimize for size". - - Without this, gcc will use certain optimizations that usually lead to - false positive warnings from kmemcheck. An example of this is a 16-bit - field in a struct, where gcc may load 32 bits, then discard the upper - 16 bits. kmemcheck sees only the 32-bit load, and may trigger a - warning for the upper 16 bits (if they're uninitialized). - -- ``CONFIG_SLAB=y`` or ``CONFIG_SLUB=y`` - This option is located under "General setup" / "Choose SLAB - allocator". - -- ``CONFIG_FUNCTION_TRACER=n`` - This option is located under "Kernel hacking" / "Tracers" / "Kernel - Function Tracer" - - When function tracing is compiled in, gcc emits a call to another - function at the beginning of every function. This means that when the - page fault handler is called, the ftrace framework will be called - before kmemcheck has had a chance to handle the fault. If ftrace then - modifies memory that was tracked by kmemcheck, the result is an - endless recursive page fault. - -- ``CONFIG_DEBUG_PAGEALLOC=n`` - This option is located under "Kernel hacking" / "Memory Debugging" - / "Debug page memory allocations". - -In addition, I highly recommend turning on ``CONFIG_DEBUG_INFO=y``. This is also -located under "Kernel hacking". With this, you will be able to get line number -information from the kmemcheck warnings, which is extremely valuable in -debugging a problem. This option is not mandatory, however, because it slows -down the compilation process and produces a much bigger kernel image. - -Now the kmemcheck menu should be visible (under "Kernel hacking" / "Memory -Debugging" / "kmemcheck: trap use of uninitialized memory"). Here follows -a description of the kmemcheck configuration variables: - -- ``CONFIG_KMEMCHECK`` - This must be enabled in order to use kmemcheck at all... - -- ``CONFIG_KMEMCHECK_``[``DISABLED`` | ``ENABLED`` | ``ONESHOT``]``_BY_DEFAULT`` - This option controls the status of kmemcheck at boot-time. "Enabled" - will enable kmemcheck right from the start, "disabled" will boot the - kernel as normal (but with the kmemcheck code compiled in, so it can - be enabled at run-time after the kernel has booted), and "one-shot" is - a special mode which will turn kmemcheck off automatically after - detecting the first use of uninitialized memory. - - If you are using kmemcheck to actively debug a problem, then you - probably want to choose "enabled" here. - - The one-shot mode is mostly useful in automated test setups because it - can prevent floods of warnings and increase the chances of the machine - surviving in case something is really wrong. In other cases, the one- - shot mode could actually be counter-productive because it would turn - itself off at the very first error -- in the case of a false positive - too -- and this would come in the way of debugging the specific - problem you were interested in. - - If you would like to use your kernel as normal, but with a chance to - enable kmemcheck in case of some problem, it might be a good idea to - choose "disabled" here. When kmemcheck is disabled, most of the run- - time overhead is not incurred, and the kernel will be almost as fast - as normal. - -- ``CONFIG_KMEMCHECK_QUEUE_SIZE`` - Select the maximum number of error reports to store in an internal - (fixed-size) buffer. Since errors can occur virtually anywhere and in - any context, we need a temporary storage area which is guaranteed not - to generate any other page faults when accessed. The queue will be - emptied as soon as a tasklet may be scheduled. If the queue is full, - new error reports will be lost. - - The default value of 64 is probably fine. If some code produces more - than 64 errors within an irqs-off section, then the code is likely to - produce many, many more, too, and these additional reports seldom give - any more information (the first report is usually the most valuable - anyway). - - This number might have to be adjusted if you are not using serial - console or similar to capture the kernel log. If you are using the - "dmesg" command to save the log, then getting a lot of kmemcheck - warnings might overflow the kernel log itself, and the earlier reports - will get lost in that way instead. Try setting this to 10 or so on - such a setup. - -- ``CONFIG_KMEMCHECK_SHADOW_COPY_SHIFT`` - Select the number of shadow bytes to save along with each entry of the - error-report queue. These bytes indicate what parts of an allocation - are initialized, uninitialized, etc. and will be displayed when an - error is detected to help the debugging of a particular problem. - - The number entered here is actually the logarithm of the number of - bytes that will be saved. So if you pick for example 5 here, kmemcheck - will save 2^5 = 32 bytes. - - The default value should be fine for debugging most problems. It also - fits nicely within 80 columns. - -- ``CONFIG_KMEMCHECK_PARTIAL_OK`` - This option (when enabled) works around certain GCC optimizations that - produce 32-bit reads from 16-bit variables where the upper 16 bits are - thrown away afterwards. - - The default value (enabled) is recommended. This may of course hide - some real errors, but disabling it would probably produce a lot of - false positives. - -- ``CONFIG_KMEMCHECK_BITOPS_OK`` - This option silences warnings that would be generated for bit-field - accesses where not all the bits are initialized at the same time. This - may also hide some real bugs. - - This option is probably obsolete, or it should be replaced with - the kmemcheck-/bitfield-annotations for the code in question. The - default value is therefore fine. - -Now compile the kernel as usual. - - -How to use ----------- - -Booting -~~~~~~~ - -First some information about the command-line options. There is only one -option specific to kmemcheck, and this is called "kmemcheck". It can be used -to override the default mode as chosen by the ``CONFIG_KMEMCHECK_*_BY_DEFAULT`` -option. Its possible settings are: - -- ``kmemcheck=0`` (disabled) -- ``kmemcheck=1`` (enabled) -- ``kmemcheck=2`` (one-shot mode) - -If SLUB debugging has been enabled in the kernel, it may take precedence over -kmemcheck in such a way that the slab caches which are under SLUB debugging -will not be tracked by kmemcheck. In order to ensure that this doesn't happen -(even though it shouldn't by default), use SLUB's boot option ``slub_debug``, -like this: ``slub_debug=-`` - -In fact, this option may also be used for fine-grained control over SLUB vs. -kmemcheck. For example, if the command line includes -``kmemcheck=1 slub_debug=,dentry``, then SLUB debugging will be used only -for the "dentry" slab cache, and with kmemcheck tracking all the other -caches. This is advanced usage, however, and is not generally recommended. - - -Run-time enable/disable -~~~~~~~~~~~~~~~~~~~~~~~ - -When the kernel has booted, it is possible to enable or disable kmemcheck at -run-time. WARNING: This feature is still experimental and may cause false -positive warnings to appear. Therefore, try not to use this. If you find that -it doesn't work properly (e.g. you see an unreasonable amount of warnings), I -will be happy to take bug reports. - -Use the file ``/proc/sys/kernel/kmemcheck`` for this purpose, e.g.:: - - $ echo 0 > /proc/sys/kernel/kmemcheck # disables kmemcheck - -The numbers are the same as for the ``kmemcheck=`` command-line option. - - -Debugging -~~~~~~~~~ - -A typical report will look something like this:: - - WARNING: kmemcheck: Caught 32-bit read from uninitialized memory (ffff88003e4a2024) - 80000000000000000000000000000000000000000088ffff0000000000000000 - i i i i u u u u i i i i i i i i u u u u u u u u u u u u u u u u - ^ - - Pid: 1856, comm: ntpdate Not tainted 2.6.29-rc5 #264 945P-A - RIP: 0010:[] [] __dequeue_signal+0xc8/0x190 - RSP: 0018:ffff88003cdf7d98 EFLAGS: 00210002 - RAX: 0000000000000030 RBX: ffff88003d4ea968 RCX: 0000000000000009 - RDX: ffff88003e5d6018 RSI: ffff88003e5d6024 RDI: ffff88003cdf7e84 - RBP: ffff88003cdf7db8 R08: ffff88003e5d6000 R09: 0000000000000000 - R10: 0000000000000080 R11: 0000000000000000 R12: 000000000000000e - R13: ffff88003cdf7e78 R14: ffff88003d530710 R15: ffff88003d5a98c8 - FS: 0000000000000000(0000) GS:ffff880001982000(0063) knlGS:00000 - CS: 0010 DS: 002b ES: 002b CR0: 0000000080050033 - CR2: ffff88003f806ea0 CR3: 000000003c036000 CR4: 00000000000006a0 - DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 - DR3: 0000000000000000 DR6: 00000000ffff4ff0 DR7: 0000000000000400 - [] dequeue_signal+0x8e/0x170 - [] get_signal_to_deliver+0x98/0x390 - [] do_notify_resume+0xad/0x7d0 - [] int_signal+0x12/0x17 - [] 0xffffffffffffffff - -The single most valuable information in this report is the RIP (or EIP on 32- -bit) value. This will help us pinpoint exactly which instruction that caused -the warning. - -If your kernel was compiled with ``CONFIG_DEBUG_INFO=y``, then all we have to do -is give this address to the addr2line program, like this:: - - $ addr2line -e vmlinux -i ffffffff8104ede8 - arch/x86/include/asm/string_64.h:12 - include/asm-generic/siginfo.h:287 - kernel/signal.c:380 - kernel/signal.c:410 - -The "``-e vmlinux``" tells addr2line which file to look in. **IMPORTANT:** -This must be the vmlinux of the kernel that produced the warning in the -first place! If not, the line number information will almost certainly be -wrong. - -The "``-i``" tells addr2line to also print the line numbers of inlined -functions. In this case, the flag was very important, because otherwise, -it would only have printed the first line, which is just a call to -``memcpy()``, which could be called from a thousand places in the kernel, and -is therefore not very useful. These inlined functions would not show up in -the stack trace above, simply because the kernel doesn't load the extra -debugging information. This technique can of course be used with ordinary -kernel oopses as well. - -In this case, it's the caller of ``memcpy()`` that is interesting, and it can be -found in ``include/asm-generic/siginfo.h``, line 287:: - - 281 static inline void copy_siginfo(struct siginfo *to, struct siginfo *from) - 282 { - 283 if (from->si_code < 0) - 284 memcpy(to, from, sizeof(*to)); - 285 else - 286 /* _sigchld is currently the largest know union member */ - 287 memcpy(to, from, __ARCH_SI_PREAMBLE_SIZE + sizeof(from->_sifields._sigchld)); - 288 } - -Since this was a read (kmemcheck usually warns about reads only, though it can -warn about writes to unallocated or freed memory as well), it was probably the -"from" argument which contained some uninitialized bytes. Following the chain -of calls, we move upwards to see where "from" was allocated or initialized, -``kernel/signal.c``, line 380:: - - 359 static void collect_signal(int sig, struct sigpending *list, siginfo_t *info) - 360 { - ... - 367 list_for_each_entry(q, &list->list, list) { - 368 if (q->info.si_signo == sig) { - 369 if (first) - 370 goto still_pending; - 371 first = q; - ... - 377 if (first) { - 378 still_pending: - 379 list_del_init(&first->list); - 380 copy_siginfo(info, &first->info); - 381 __sigqueue_free(first); - ... - 392 } - 393 } - -Here, it is ``&first->info`` that is being passed on to ``copy_siginfo()``. The -variable ``first`` was found on a list -- passed in as the second argument to -``collect_signal()``. We continue our journey through the stack, to figure out -where the item on "list" was allocated or initialized. We move to line 410:: - - 395 static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, - 396 siginfo_t *info) - 397 { - ... - 410 collect_signal(sig, pending, info); - ... - 414 } - -Now we need to follow the ``pending`` pointer, since that is being passed on to -``collect_signal()`` as ``list``. At this point, we've run out of lines from the -"addr2line" output. Not to worry, we just paste the next addresses from the -kmemcheck stack dump, i.e.:: - - [] dequeue_signal+0x8e/0x170 - [] get_signal_to_deliver+0x98/0x390 - [] do_notify_resume+0xad/0x7d0 - [] int_signal+0x12/0x17 - - $ addr2line -e vmlinux -i ffffffff8104f04e ffffffff81050bd8 \ - ffffffff8100b87d ffffffff8100c7b5 - kernel/signal.c:446 - kernel/signal.c:1806 - arch/x86/kernel/signal.c:805 - arch/x86/kernel/signal.c:871 - arch/x86/kernel/entry_64.S:694 - -Remember that since these addresses were found on the stack and not as the -RIP value, they actually point to the _next_ instruction (they are return -addresses). This becomes obvious when we look at the code for line 446:: - - 422 int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) - 423 { - ... - 431 signr = __dequeue_signal(&tsk->signal->shared_pending, - 432 mask, info); - 433 /* - 434 * itimer signal ? - 435 * - 436 * itimers are process shared and we restart periodic - 437 * itimers in the signal delivery path to prevent DoS - 438 * attacks in the high resolution timer case. This is - 439 * compliant with the old way of self restarting - 440 * itimers, as the SIGALRM is a legacy signal and only - 441 * queued once. Changing the restart behaviour to - 442 * restart the timer in the signal dequeue path is - 443 * reducing the timer noise on heavy loaded !highres - 444 * systems too. - 445 */ - 446 if (unlikely(signr == SIGALRM)) { - ... - 489 } - -So instead of looking at 446, we should be looking at 431, which is the line -that executes just before 446. Here we see that what we are looking for is -``&tsk->signal->shared_pending``. - -Our next task is now to figure out which function that puts items on this -``shared_pending`` list. A crude, but efficient tool, is ``git grep``:: - - $ git grep -n 'shared_pending' kernel/ - ... - kernel/signal.c:828: pending = group ? &t->signal->shared_pending : &t->pending; - kernel/signal.c:1339: pending = group ? &t->signal->shared_pending : &t->pending; - ... - -There were more results, but none of them were related to list operations, -and these were the only assignments. We inspect the line numbers more closely -and find that this is indeed where items are being added to the list:: - - 816 static int send_signal(int sig, struct siginfo *info, struct task_struct *t, - 817 int group) - 818 { - ... - 828 pending = group ? &t->signal->shared_pending : &t->pending; - ... - 851 q = __sigqueue_alloc(t, GFP_ATOMIC, (sig < SIGRTMIN && - 852 (is_si_special(info) || - 853 info->si_code >= 0))); - 854 if (q) { - 855 list_add_tail(&q->list, &pending->list); - ... - 890 } - -and:: - - 1309 int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group) - 1310 { - .... - 1339 pending = group ? &t->signal->shared_pending : &t->pending; - 1340 list_add_tail(&q->list, &pending->list); - .... - 1347 } - -In the first case, the list element we are looking for, ``q``, is being -returned from the function ``__sigqueue_alloc()``, which looks like an -allocation function. Let's take a look at it:: - - 187 static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags, - 188 int override_rlimit) - 189 { - 190 struct sigqueue *q = NULL; - 191 struct user_struct *user; - 192 - 193 /* - 194 * We won't get problems with the target's UID changing under us - 195 * because changing it requires RCU be used, and if t != current, the - 196 * caller must be holding the RCU readlock (by way of a spinlock) and - 197 * we use RCU protection here - 198 */ - 199 user = get_uid(__task_cred(t)->user); - 200 atomic_inc(&user->sigpending); - 201 if (override_rlimit || - 202 atomic_read(&user->sigpending) <= - 203 t->signal->rlim[RLIMIT_SIGPENDING].rlim_cur) - 204 q = kmem_cache_alloc(sigqueue_cachep, flags); - 205 if (unlikely(q == NULL)) { - 206 atomic_dec(&user->sigpending); - 207 free_uid(user); - 208 } else { - 209 INIT_LIST_HEAD(&q->list); - 210 q->flags = 0; - 211 q->user = user; - 212 } - 213 - 214 return q; - 215 } - -We see that this function initializes ``q->list``, ``q->flags``, and -``q->user``. It seems that now is the time to look at the definition of -``struct sigqueue``, e.g.:: - - 14 struct sigqueue { - 15 struct list_head list; - 16 int flags; - 17 siginfo_t info; - 18 struct user_struct *user; - 19 }; - -And, you might remember, it was a ``memcpy()`` on ``&first->info`` that -caused the warning, so this makes perfect sense. It also seems reasonable -to assume that it is the caller of ``__sigqueue_alloc()`` that has the -responsibility of filling out (initializing) this member. - -But just which fields of the struct were uninitialized? Let's look at -kmemcheck's report again:: - - WARNING: kmemcheck: Caught 32-bit read from uninitialized memory (ffff88003e4a2024) - 80000000000000000000000000000000000000000088ffff0000000000000000 - i i i i u u u u i i i i i i i i u u u u u u u u u u u u u u u u - ^ - -These first two lines are the memory dump of the memory object itself, and -the shadow bytemap, respectively. The memory object itself is in this case -``&first->info``. Just beware that the start of this dump is NOT the start -of the object itself! The position of the caret (^) corresponds with the -address of the read (ffff88003e4a2024). - -The shadow bytemap dump legend is as follows: - -- i: initialized -- u: uninitialized -- a: unallocated (memory has been allocated by the slab layer, but has not - yet been handed off to anybody) -- f: freed (memory has been allocated by the slab layer, but has been freed - by the previous owner) - -In order to figure out where (relative to the start of the object) the -uninitialized memory was located, we have to look at the disassembly. For -that, we'll need the RIP address again:: - - RIP: 0010:[] [] __dequeue_signal+0xc8/0x190 - - $ objdump -d --no-show-raw-insn vmlinux | grep -C 8 ffffffff8104ede8: - ffffffff8104edc8: mov %r8,0x8(%r8) - ffffffff8104edcc: test %r10d,%r10d - ffffffff8104edcf: js ffffffff8104ee88 <__dequeue_signal+0x168> - ffffffff8104edd5: mov %rax,%rdx - ffffffff8104edd8: mov $0xc,%ecx - ffffffff8104eddd: mov %r13,%rdi - ffffffff8104ede0: mov $0x30,%eax - ffffffff8104ede5: mov %rdx,%rsi - ffffffff8104ede8: rep movsl %ds:(%rsi),%es:(%rdi) - ffffffff8104edea: test $0x2,%al - ffffffff8104edec: je ffffffff8104edf0 <__dequeue_signal+0xd0> - ffffffff8104edee: movsw %ds:(%rsi),%es:(%rdi) - ffffffff8104edf0: test $0x1,%al - ffffffff8104edf2: je ffffffff8104edf5 <__dequeue_signal+0xd5> - ffffffff8104edf4: movsb %ds:(%rsi),%es:(%rdi) - ffffffff8104edf5: mov %r8,%rdi - ffffffff8104edf8: callq ffffffff8104de60 <__sigqueue_free> - -As expected, it's the "``rep movsl``" instruction from the ``memcpy()`` -that causes the warning. We know about ``REP MOVSL`` that it uses the register -``RCX`` to count the number of remaining iterations. By taking a look at the -register dump again (from the kmemcheck report), we can figure out how many -bytes were left to copy:: - - RAX: 0000000000000030 RBX: ffff88003d4ea968 RCX: 0000000000000009 - -By looking at the disassembly, we also see that ``%ecx`` is being loaded -with the value ``$0xc`` just before (ffffffff8104edd8), so we are very -lucky. Keep in mind that this is the number of iterations, not bytes. And -since this is a "long" operation, we need to multiply by 4 to get the -number of bytes. So this means that the uninitialized value was encountered -at 4 * (0xc - 0x9) = 12 bytes from the start of the object. - -We can now try to figure out which field of the "``struct siginfo``" that -was not initialized. This is the beginning of the struct:: - - 40 typedef struct siginfo { - 41 int si_signo; - 42 int si_errno; - 43 int si_code; - 44 - 45 union { - .. - 92 } _sifields; - 93 } siginfo_t; - -On 64-bit, the int is 4 bytes long, so it must the union member that has -not been initialized. We can verify this using gdb:: - - $ gdb vmlinux - ... - (gdb) p &((struct siginfo *) 0)->_sifields - $1 = (union {...} *) 0x10 - -Actually, it seems that the union member is located at offset 0x10 -- which -means that gcc has inserted 4 bytes of padding between the members ``si_code`` -and ``_sifields``. We can now get a fuller picture of the memory dump:: - - _----------------------------=> si_code - / _--------------------=> (padding) - | / _------------=> _sifields(._kill._pid) - | | / _----=> _sifields(._kill._uid) - | | | / - -------|-------|-------|-------| - 80000000000000000000000000000000000000000088ffff0000000000000000 - i i i i u u u u i i i i i i i i u u u u u u u u u u u u u u u u - -This allows us to realize another important fact: ``si_code`` contains the -value 0x80. Remember that x86 is little endian, so the first 4 bytes -"80000000" are really the number 0x00000080. With a bit of research, we -find that this is actually the constant ``SI_KERNEL`` defined in -``include/asm-generic/siginfo.h``:: - - 144 #define SI_KERNEL 0x80 /* sent by the kernel from somewhere */ - -This macro is used in exactly one place in the x86 kernel: In ``send_signal()`` -in ``kernel/signal.c``:: - - 816 static int send_signal(int sig, struct siginfo *info, struct task_struct *t, - 817 int group) - 818 { - ... - 828 pending = group ? &t->signal->shared_pending : &t->pending; - ... - 851 q = __sigqueue_alloc(t, GFP_ATOMIC, (sig < SIGRTMIN && - 852 (is_si_special(info) || - 853 info->si_code >= 0))); - 854 if (q) { - 855 list_add_tail(&q->list, &pending->list); - 856 switch ((unsigned long) info) { - ... - 865 case (unsigned long) SEND_SIG_PRIV: - 866 q->info.si_signo = sig; - 867 q->info.si_errno = 0; - 868 q->info.si_code = SI_KERNEL; - 869 q->info.si_pid = 0; - 870 q->info.si_uid = 0; - 871 break; - ... - 890 } - -Not only does this match with the ``.si_code`` member, it also matches the place -we found earlier when looking for where siginfo_t objects are enqueued on the -``shared_pending`` list. - -So to sum up: It seems that it is the padding introduced by the compiler -between two struct fields that is uninitialized, and this gets reported when -we do a ``memcpy()`` on the struct. This means that we have identified a false -positive warning. - -Normally, kmemcheck will not report uninitialized accesses in ``memcpy()`` calls -when both the source and destination addresses are tracked. (Instead, we copy -the shadow bytemap as well). In this case, the destination address clearly -was not tracked. We can dig a little deeper into the stack trace from above:: - - arch/x86/kernel/signal.c:805 - arch/x86/kernel/signal.c:871 - arch/x86/kernel/entry_64.S:694 - -And we clearly see that the destination siginfo object is located on the -stack:: - - 782 static void do_signal(struct pt_regs *regs) - 783 { - 784 struct k_sigaction ka; - 785 siginfo_t info; - ... - 804 signr = get_signal_to_deliver(&info, &ka, regs, NULL); - ... - 854 } - -And this ``&info`` is what eventually gets passed to ``copy_siginfo()`` as the -destination argument. - -Now, even though we didn't find an actual error here, the example is still a -good one, because it shows how one would go about to find out what the report -was all about. - - -Annotating false positives -~~~~~~~~~~~~~~~~~~~~~~~~~~ - -There are a few different ways to make annotations in the source code that -will keep kmemcheck from checking and reporting certain allocations. Here -they are: - -- ``__GFP_NOTRACK_FALSE_POSITIVE`` - This flag can be passed to ``kmalloc()`` or ``kmem_cache_alloc()`` - (therefore also to other functions that end up calling one of - these) to indicate that the allocation should not be tracked - because it would lead to a false positive report. This is a "big - hammer" way of silencing kmemcheck; after all, even if the false - positive pertains to particular field in a struct, for example, we - will now lose the ability to find (real) errors in other parts of - the same struct. - - Example:: - - /* No warnings will ever trigger on accessing any part of x */ - x = kmalloc(sizeof *x, GFP_KERNEL | __GFP_NOTRACK_FALSE_POSITIVE); - -- ``kmemcheck_bitfield_begin(name)``/``kmemcheck_bitfield_end(name)`` and - ``kmemcheck_annotate_bitfield(ptr, name)`` - The first two of these three macros can be used inside struct - definitions to signal, respectively, the beginning and end of a - bitfield. Additionally, this will assign the bitfield a name, which - is given as an argument to the macros. - - Having used these markers, one can later use - kmemcheck_annotate_bitfield() at the point of allocation, to indicate - which parts of the allocation is part of a bitfield. - - Example:: - - struct foo { - int x; - - kmemcheck_bitfield_begin(flags); - int flag_a:1; - int flag_b:1; - kmemcheck_bitfield_end(flags); - - int y; - }; - - struct foo *x = kmalloc(sizeof *x); - - /* No warnings will trigger on accessing the bitfield of x */ - kmemcheck_annotate_bitfield(x, flags); - - Note that ``kmemcheck_annotate_bitfield()`` can be used even before the - return value of ``kmalloc()`` is checked -- in other words, passing NULL - as the first argument is legal (and will do nothing). - - -Reporting errors ----------------- - -As we have seen, kmemcheck will produce false positive reports. Therefore, it -is not very wise to blindly post kmemcheck warnings to mailing lists and -maintainers. Instead, I encourage maintainers and developers to find errors -in their own code. If you get a warning, you can try to work around it, try -to figure out if it's a real error or not, or simply ignore it. Most -developers know their own code and will quickly and efficiently determine the -root cause of a kmemcheck report. This is therefore also the most efficient -way to work with kmemcheck. - -That said, we (the kmemcheck maintainers) will always be on the lookout for -false positives that we can annotate and silence. So whatever you find, -please drop us a note privately! Kernel configs and steps to reproduce (if -available) are of course a great help too. - -Happy hacking! - - -Technical description ---------------------- - -kmemcheck works by marking memory pages non-present. This means that whenever -somebody attempts to access the page, a page fault is generated. The page -fault handler notices that the page was in fact only hidden, and so it calls -on the kmemcheck code to make further investigations. - -When the investigations are completed, kmemcheck "shows" the page by marking -it present (as it would be under normal circumstances). This way, the -interrupted code can continue as usual. - -But after the instruction has been executed, we should hide the page again, so -that we can catch the next access too! Now kmemcheck makes use of a debugging -feature of the processor, namely single-stepping. When the processor has -finished the one instruction that generated the memory access, a debug -exception is raised. From here, we simply hide the page again and continue -execution, this time with the single-stepping feature turned off. - -kmemcheck requires some assistance from the memory allocator in order to work. -The memory allocator needs to - - 1. Tell kmemcheck about newly allocated pages and pages that are about to - be freed. This allows kmemcheck to set up and tear down the shadow memory - for the pages in question. The shadow memory stores the status of each - byte in the allocation proper, e.g. whether it is initialized or - uninitialized. - - 2. Tell kmemcheck which parts of memory should be marked uninitialized. - There are actually a few more states, such as "not yet allocated" and - "recently freed". - -If a slab cache is set up using the SLAB_NOTRACK flag, it will never return -memory that can take page faults because of kmemcheck. - -If a slab cache is NOT set up using the SLAB_NOTRACK flag, callers can still -request memory with the __GFP_NOTRACK or __GFP_NOTRACK_FALSE_POSITIVE flags. -This does not prevent the page faults from occurring, however, but marks the -object in question as being initialized so that no warnings will ever be -produced for this object. - -Currently, the SLAB and SLUB allocators are supported by kmemcheck. diff --git a/MAINTAINERS b/MAINTAINERS index 7e9c887ad951..ac814d3dd1c1 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7688,16 +7688,6 @@ F: include/linux/kdb.h F: include/linux/kgdb.h F: kernel/debug/ -KMEMCHECK -M: Vegard Nossum -M: Pekka Enberg -S: Maintained -F: Documentation/dev-tools/kmemcheck.rst -F: arch/x86/include/asm/kmemcheck.h -F: arch/x86/mm/kmemcheck/ -F: include/linux/kmemcheck.h -F: mm/kmemcheck.c - KMEMLEAK M: Catalin Marinas S: Maintained diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index f08977d82ca0..cb678192da4a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -112,7 +112,6 @@ config X86 select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP select HAVE_ARCH_KGDB - select HAVE_ARCH_KMEMCHECK select HAVE_ARCH_MMAP_RND_BITS if MMU select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT select HAVE_ARCH_COMPAT_MMAP_BASES if MMU && COMPAT @@ -1430,7 +1429,7 @@ config ARCH_DMA_ADDR_T_64BIT config X86_DIRECT_GBPAGES def_bool y - depends on X86_64 && !DEBUG_PAGEALLOC && !KMEMCHECK + depends on X86_64 && !DEBUG_PAGEALLOC ---help--- Certain kernel features effectively disable kernel linear 1 GB mappings (even if the CPU otherwise diff --git a/arch/x86/include/asm/kmemcheck.h b/arch/x86/include/asm/kmemcheck.h index 945a0337fbcf..ea32a7d3cf1b 100644 --- a/arch/x86/include/asm/kmemcheck.h +++ b/arch/x86/include/asm/kmemcheck.h @@ -1,43 +1 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef ASM_X86_KMEMCHECK_H -#define ASM_X86_KMEMCHECK_H - -#include -#include - -#ifdef CONFIG_KMEMCHECK -bool kmemcheck_active(struct pt_regs *regs); - -void kmemcheck_show(struct pt_regs *regs); -void kmemcheck_hide(struct pt_regs *regs); - -bool kmemcheck_fault(struct pt_regs *regs, - unsigned long address, unsigned long error_code); -bool kmemcheck_trap(struct pt_regs *regs); -#else -static inline bool kmemcheck_active(struct pt_regs *regs) -{ - return false; -} - -static inline void kmemcheck_show(struct pt_regs *regs) -{ -} - -static inline void kmemcheck_hide(struct pt_regs *regs) -{ -} - -static inline bool kmemcheck_fault(struct pt_regs *regs, - unsigned long address, unsigned long error_code) -{ - return false; -} - -static inline bool kmemcheck_trap(struct pt_regs *regs) -{ - return false; -} -#endif /* CONFIG_KMEMCHECK */ - -#endif diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h index 076502241eae..55d392c6bd29 100644 --- a/arch/x86/include/asm/string_32.h +++ b/arch/x86/include/asm/string_32.h @@ -179,8 +179,6 @@ static inline void *__memcpy3d(void *to, const void *from, size_t len) * No 3D Now! */ -#ifndef CONFIG_KMEMCHECK - #if (__GNUC__ >= 4) #define memcpy(t, f, n) __builtin_memcpy(t, f, n) #else @@ -189,13 +187,6 @@ static inline void *__memcpy3d(void *to, const void *from, size_t len) ? __constant_memcpy((t), (f), (n)) \ : __memcpy((t), (f), (n))) #endif -#else -/* - * kmemcheck becomes very happy if we use the REP instructions unconditionally, - * because it means that we know both memory operands in advance. - */ -#define memcpy(t, f, n) __memcpy((t), (f), (n)) -#endif #endif #endif /* !CONFIG_FORTIFY_SOURCE */ diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index 0b1b4445f4c5..533f74c300c2 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -33,7 +33,6 @@ extern void *memcpy(void *to, const void *from, size_t len); extern void *__memcpy(void *to, const void *from, size_t len); #ifndef CONFIG_FORTIFY_SOURCE -#ifndef CONFIG_KMEMCHECK #if (__GNUC__ == 4 && __GNUC_MINOR__ < 3) || __GNUC__ < 4 #define memcpy(dst, src, len) \ ({ \ @@ -46,13 +45,6 @@ extern void *__memcpy(void *to, const void *from, size_t len); __ret; \ }) #endif -#else -/* - * kmemcheck becomes very happy if we use the REP instructions unconditionally, - * because it means that we know both memory operands in advance. - */ -#define memcpy(dst, src, len) __inline_memcpy((dst), (src), (len)) -#endif #endif /* !CONFIG_FORTIFY_SOURCE */ #define __HAVE_ARCH_MEMSET diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index b720dacac051..b1af22073e28 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -187,21 +187,6 @@ static void early_init_intel(struct cpuinfo_x86 *c) if (c->x86 == 6 && c->x86_model < 15) clear_cpu_cap(c, X86_FEATURE_PAT); -#ifdef CONFIG_KMEMCHECK - /* - * P4s have a "fast strings" feature which causes single- - * stepping REP instructions to only generate a #DB on - * cache-line boundaries. - * - * Ingo Molnar reported a Pentium D (model 6) and a Xeon - * (model 2) with the same problem. - */ - if (c->x86 == 15) - if (msr_clear_bit(MSR_IA32_MISC_ENABLE, - MSR_IA32_MISC_ENABLE_FAST_STRING_BIT) > 0) - pr_info("kmemcheck: Disabling fast string operations\n"); -#endif - /* * If fast string is not enabled in IA32_MISC_ENABLE for any reason, * clear the fast string and enhanced fast string CPU capabilities. diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 7ba7f3d7f477..8e13b8cc6bed 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -29,8 +29,6 @@ obj-$(CONFIG_X86_PTDUMP) += debug_pagetables.o obj-$(CONFIG_HIGHMEM) += highmem_32.o -obj-$(CONFIG_KMEMCHECK) += kmemcheck/ - KASAN_SANITIZE_kasan_init_$(BITS).o := n obj-$(CONFIG_KASAN) += kasan_init_$(BITS).o diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index ef94620ceb8a..6fdf91ef130a 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -163,12 +163,11 @@ static int page_size_mask; static void __init probe_page_size_mask(void) { /* - * For CONFIG_KMEMCHECK or pagealloc debugging, identity mapping will - * use small pages. + * For pagealloc debugging, identity mapping will use small pages. * This will simplify cpa(), which otherwise needs to support splitting * large pages into small in interrupt context, etc. */ - if (boot_cpu_has(X86_FEATURE_PSE) && !debug_pagealloc_enabled() && !IS_ENABLED(CONFIG_KMEMCHECK)) + if (boot_cpu_has(X86_FEATURE_PSE) && !debug_pagealloc_enabled()) page_size_mask |= 1 << PG_LEVEL_2M; else direct_gbpages = 0; diff --git a/arch/x86/mm/kmemcheck/Makefile b/arch/x86/mm/kmemcheck/Makefile deleted file mode 100644 index 520b3bce4095..000000000000 --- a/arch/x86/mm/kmemcheck/Makefile +++ /dev/null @@ -1 +0,0 @@ -obj-y := error.o kmemcheck.o opcode.o pte.o selftest.o shadow.o diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c index 872ec4159a68..cec594032515 100644 --- a/arch/x86/mm/kmemcheck/error.c +++ b/arch/x86/mm/kmemcheck/error.c @@ -1,228 +1 @@ // SPDX-License-Identifier: GPL-2.0 -#include -#include -#include -#include -#include -#include -#include -#include - -#include "error.h" -#include "shadow.h" - -enum kmemcheck_error_type { - KMEMCHECK_ERROR_INVALID_ACCESS, - KMEMCHECK_ERROR_BUG, -}; - -#define SHADOW_COPY_SIZE (1 << CONFIG_KMEMCHECK_SHADOW_COPY_SHIFT) - -struct kmemcheck_error { - enum kmemcheck_error_type type; - - union { - /* KMEMCHECK_ERROR_INVALID_ACCESS */ - struct { - /* Kind of access that caused the error */ - enum kmemcheck_shadow state; - /* Address and size of the erroneous read */ - unsigned long address; - unsigned int size; - }; - }; - - struct pt_regs regs; - struct stack_trace trace; - unsigned long trace_entries[32]; - - /* We compress it to a char. */ - unsigned char shadow_copy[SHADOW_COPY_SIZE]; - unsigned char memory_copy[SHADOW_COPY_SIZE]; -}; - -/* - * Create a ring queue of errors to output. We can't call printk() directly - * from the kmemcheck traps, since this may call the console drivers and - * result in a recursive fault. - */ -static struct kmemcheck_error error_fifo[CONFIG_KMEMCHECK_QUEUE_SIZE]; -static unsigned int error_count; -static unsigned int error_rd; -static unsigned int error_wr; -static unsigned int error_missed_count; - -static struct kmemcheck_error *error_next_wr(void) -{ - struct kmemcheck_error *e; - - if (error_count == ARRAY_SIZE(error_fifo)) { - ++error_missed_count; - return NULL; - } - - e = &error_fifo[error_wr]; - if (++error_wr == ARRAY_SIZE(error_fifo)) - error_wr = 0; - ++error_count; - return e; -} - -static struct kmemcheck_error *error_next_rd(void) -{ - struct kmemcheck_error *e; - - if (error_count == 0) - return NULL; - - e = &error_fifo[error_rd]; - if (++error_rd == ARRAY_SIZE(error_fifo)) - error_rd = 0; - --error_count; - return e; -} - -void kmemcheck_error_recall(void) -{ - static const char *desc[] = { - [KMEMCHECK_SHADOW_UNALLOCATED] = "unallocated", - [KMEMCHECK_SHADOW_UNINITIALIZED] = "uninitialized", - [KMEMCHECK_SHADOW_INITIALIZED] = "initialized", - [KMEMCHECK_SHADOW_FREED] = "freed", - }; - - static const char short_desc[] = { - [KMEMCHECK_SHADOW_UNALLOCATED] = 'a', - [KMEMCHECK_SHADOW_UNINITIALIZED] = 'u', - [KMEMCHECK_SHADOW_INITIALIZED] = 'i', - [KMEMCHECK_SHADOW_FREED] = 'f', - }; - - struct kmemcheck_error *e; - unsigned int i; - - e = error_next_rd(); - if (!e) - return; - - switch (e->type) { - case KMEMCHECK_ERROR_INVALID_ACCESS: - printk(KERN_WARNING "WARNING: kmemcheck: Caught %d-bit read from %s memory (%p)\n", - 8 * e->size, e->state < ARRAY_SIZE(desc) ? - desc[e->state] : "(invalid shadow state)", - (void *) e->address); - - printk(KERN_WARNING); - for (i = 0; i < SHADOW_COPY_SIZE; ++i) - printk(KERN_CONT "%02x", e->memory_copy[i]); - printk(KERN_CONT "\n"); - - printk(KERN_WARNING); - for (i = 0; i < SHADOW_COPY_SIZE; ++i) { - if (e->shadow_copy[i] < ARRAY_SIZE(short_desc)) - printk(KERN_CONT " %c", short_desc[e->shadow_copy[i]]); - else - printk(KERN_CONT " ?"); - } - printk(KERN_CONT "\n"); - printk(KERN_WARNING "%*c\n", 2 + 2 - * (int) (e->address & (SHADOW_COPY_SIZE - 1)), '^'); - break; - case KMEMCHECK_ERROR_BUG: - printk(KERN_EMERG "ERROR: kmemcheck: Fatal error\n"); - break; - } - - __show_regs(&e->regs, 1); - print_stack_trace(&e->trace, 0); -} - -static void do_wakeup(unsigned long data) -{ - while (error_count > 0) - kmemcheck_error_recall(); - - if (error_missed_count > 0) { - printk(KERN_WARNING "kmemcheck: Lost %d error reports because " - "the queue was too small\n", error_missed_count); - error_missed_count = 0; - } -} - -static DECLARE_TASKLET(kmemcheck_tasklet, &do_wakeup, 0); - -/* - * Save the context of an error report. - */ -void kmemcheck_error_save(enum kmemcheck_shadow state, - unsigned long address, unsigned int size, struct pt_regs *regs) -{ - static unsigned long prev_ip; - - struct kmemcheck_error *e; - void *shadow_copy; - void *memory_copy; - - /* Don't report several adjacent errors from the same EIP. */ - if (regs->ip == prev_ip) - return; - prev_ip = regs->ip; - - e = error_next_wr(); - if (!e) - return; - - e->type = KMEMCHECK_ERROR_INVALID_ACCESS; - - e->state = state; - e->address = address; - e->size = size; - - /* Save regs */ - memcpy(&e->regs, regs, sizeof(*regs)); - - /* Save stack trace */ - e->trace.nr_entries = 0; - e->trace.entries = e->trace_entries; - e->trace.max_entries = ARRAY_SIZE(e->trace_entries); - e->trace.skip = 0; - save_stack_trace_regs(regs, &e->trace); - - /* Round address down to nearest 16 bytes */ - shadow_copy = kmemcheck_shadow_lookup(address - & ~(SHADOW_COPY_SIZE - 1)); - BUG_ON(!shadow_copy); - - memcpy(e->shadow_copy, shadow_copy, SHADOW_COPY_SIZE); - - kmemcheck_show_addr(address); - memory_copy = (void *) (address & ~(SHADOW_COPY_SIZE - 1)); - memcpy(e->memory_copy, memory_copy, SHADOW_COPY_SIZE); - kmemcheck_hide_addr(address); - - tasklet_hi_schedule_first(&kmemcheck_tasklet); -} - -/* - * Save the context of a kmemcheck bug. - */ -void kmemcheck_error_save_bug(struct pt_regs *regs) -{ - struct kmemcheck_error *e; - - e = error_next_wr(); - if (!e) - return; - - e->type = KMEMCHECK_ERROR_BUG; - - memcpy(&e->regs, regs, sizeof(*regs)); - - e->trace.nr_entries = 0; - e->trace.entries = e->trace_entries; - e->trace.max_entries = ARRAY_SIZE(e->trace_entries); - e->trace.skip = 1; - save_stack_trace(&e->trace); - - tasklet_hi_schedule_first(&kmemcheck_tasklet); -} diff --git a/arch/x86/mm/kmemcheck/error.h b/arch/x86/mm/kmemcheck/error.h index 39f80d7a874d..ea32a7d3cf1b 100644 --- a/arch/x86/mm/kmemcheck/error.h +++ b/arch/x86/mm/kmemcheck/error.h @@ -1,16 +1 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef ARCH__X86__MM__KMEMCHECK__ERROR_H -#define ARCH__X86__MM__KMEMCHECK__ERROR_H - -#include - -#include "shadow.h" - -void kmemcheck_error_save(enum kmemcheck_shadow state, - unsigned long address, unsigned int size, struct pt_regs *regs); - -void kmemcheck_error_save_bug(struct pt_regs *regs); - -void kmemcheck_error_recall(void); - -#endif diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c deleted file mode 100644 index 4515bae36bbe..000000000000 --- a/arch/x86/mm/kmemcheck/kmemcheck.c +++ /dev/null @@ -1,658 +0,0 @@ -/** - * kmemcheck - a heavyweight memory checker for the linux kernel - * Copyright (C) 2007, 2008 Vegard Nossum - * (With a lot of help from Ingo Molnar and Pekka Enberg.) - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License (version 2) as - * published by the Free Software Foundation. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include - -#include "error.h" -#include "opcode.h" -#include "pte.h" -#include "selftest.h" -#include "shadow.h" - - -#ifdef CONFIG_KMEMCHECK_DISABLED_BY_DEFAULT -# define KMEMCHECK_ENABLED 0 -#endif - -#ifdef CONFIG_KMEMCHECK_ENABLED_BY_DEFAULT -# define KMEMCHECK_ENABLED 1 -#endif - -#ifdef CONFIG_KMEMCHECK_ONESHOT_BY_DEFAULT -# define KMEMCHECK_ENABLED 2 -#endif - -int kmemcheck_enabled = KMEMCHECK_ENABLED; - -int __init kmemcheck_init(void) -{ -#ifdef CONFIG_SMP - /* - * Limit SMP to use a single CPU. We rely on the fact that this code - * runs before SMP is set up. - */ - if (setup_max_cpus > 1) { - printk(KERN_INFO - "kmemcheck: Limiting number of CPUs to 1.\n"); - setup_max_cpus = 1; - } -#endif - - if (!kmemcheck_selftest()) { - printk(KERN_INFO "kmemcheck: self-tests failed; disabling\n"); - kmemcheck_enabled = 0; - return -EINVAL; - } - - printk(KERN_INFO "kmemcheck: Initialized\n"); - return 0; -} - -early_initcall(kmemcheck_init); - -/* - * We need to parse the kmemcheck= option before any memory is allocated. - */ -static int __init param_kmemcheck(char *str) -{ - int val; - int ret; - - if (!str) - return -EINVAL; - - ret = kstrtoint(str, 0, &val); - if (ret) - return ret; - kmemcheck_enabled = val; - return 0; -} - -early_param("kmemcheck", param_kmemcheck); - -int kmemcheck_show_addr(unsigned long address) -{ - pte_t *pte; - - pte = kmemcheck_pte_lookup(address); - if (!pte) - return 0; - - set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT)); - __flush_tlb_one(address); - return 1; -} - -int kmemcheck_hide_addr(unsigned long address) -{ - pte_t *pte; - - pte = kmemcheck_pte_lookup(address); - if (!pte) - return 0; - - set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT)); - __flush_tlb_one(address); - return 1; -} - -struct kmemcheck_context { - bool busy; - int balance; - - /* - * There can be at most two memory operands to an instruction, but - * each address can cross a page boundary -- so we may need up to - * four addresses that must be hidden/revealed for each fault. - */ - unsigned long addr[4]; - unsigned long n_addrs; - unsigned long flags; - - /* Data size of the instruction that caused a fault. */ - unsigned int size; -}; - -static DEFINE_PER_CPU(struct kmemcheck_context, kmemcheck_context); - -bool kmemcheck_active(struct pt_regs *regs) -{ - struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); - - return data->balance > 0; -} - -/* Save an address that needs to be shown/hidden */ -static void kmemcheck_save_addr(unsigned long addr) -{ - struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); - - BUG_ON(data->n_addrs >= ARRAY_SIZE(data->addr)); - data->addr[data->n_addrs++] = addr; -} - -static unsigned int kmemcheck_show_all(void) -{ - struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); - unsigned int i; - unsigned int n; - - n = 0; - for (i = 0; i < data->n_addrs; ++i) - n += kmemcheck_show_addr(data->addr[i]); - - return n; -} - -static unsigned int kmemcheck_hide_all(void) -{ - struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); - unsigned int i; - unsigned int n; - - n = 0; - for (i = 0; i < data->n_addrs; ++i) - n += kmemcheck_hide_addr(data->addr[i]); - - return n; -} - -/* - * Called from the #PF handler. - */ -void kmemcheck_show(struct pt_regs *regs) -{ - struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); - - BUG_ON(!irqs_disabled()); - - if (unlikely(data->balance != 0)) { - kmemcheck_show_all(); - kmemcheck_error_save_bug(regs); - data->balance = 0; - return; - } - - /* - * None of the addresses actually belonged to kmemcheck. Note that - * this is not an error. - */ - if (kmemcheck_show_all() == 0) - return; - - ++data->balance; - - /* - * The IF needs to be cleared as well, so that the faulting - * instruction can run "uninterrupted". Otherwise, we might take - * an interrupt and start executing that before we've had a chance - * to hide the page again. - * - * NOTE: In the rare case of multiple faults, we must not override - * the original flags: - */ - if (!(regs->flags & X86_EFLAGS_TF)) - data->flags = regs->flags; - - regs->flags |= X86_EFLAGS_TF; - regs->flags &= ~X86_EFLAGS_IF; -} - -/* - * Called from the #DB handler. - */ -void kmemcheck_hide(struct pt_regs *regs) -{ - struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); - int n; - - BUG_ON(!irqs_disabled()); - - if (unlikely(data->balance != 1)) { - kmemcheck_show_all(); - kmemcheck_error_save_bug(regs); - data->n_addrs = 0; - data->balance = 0; - - if (!(data->flags & X86_EFLAGS_TF)) - regs->flags &= ~X86_EFLAGS_TF; - if (data->flags & X86_EFLAGS_IF) - regs->flags |= X86_EFLAGS_IF; - return; - } - - if (kmemcheck_enabled) - n = kmemcheck_hide_all(); - else - n = kmemcheck_show_all(); - - if (n == 0) - return; - - --data->balance; - - data->n_addrs = 0; - - if (!(data->flags & X86_EFLAGS_TF)) - regs->flags &= ~X86_EFLAGS_TF; - if (data->flags & X86_EFLAGS_IF) - regs->flags |= X86_EFLAGS_IF; -} - -void kmemcheck_show_pages(struct page *p, unsigned int n) -{ - unsigned int i; - - for (i = 0; i < n; ++i) { - unsigned long address; - pte_t *pte; - unsigned int level; - - address = (unsigned long) page_address(&p[i]); - pte = lookup_address(address, &level); - BUG_ON(!pte); - BUG_ON(level != PG_LEVEL_4K); - - set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT)); - set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_HIDDEN)); - __flush_tlb_one(address); - } -} - -bool kmemcheck_page_is_tracked(struct page *p) -{ - /* This will also check the "hidden" flag of the PTE. */ - return kmemcheck_pte_lookup((unsigned long) page_address(p)); -} - -void kmemcheck_hide_pages(struct page *p, unsigned int n) -{ - unsigned int i; - - for (i = 0; i < n; ++i) { - unsigned long address; - pte_t *pte; - unsigned int level; - - address = (unsigned long) page_address(&p[i]); - pte = lookup_address(address, &level); - BUG_ON(!pte); - BUG_ON(level != PG_LEVEL_4K); - - set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_PRESENT)); - set_pte(pte, __pte(pte_val(*pte) | _PAGE_HIDDEN)); - __flush_tlb_one(address); - } -} - -/* Access may NOT cross page boundary */ -static void kmemcheck_read_strict(struct pt_regs *regs, - unsigned long addr, unsigned int size) -{ - void *shadow; - enum kmemcheck_shadow status; - - shadow = kmemcheck_shadow_lookup(addr); - if (!shadow) - return; - - kmemcheck_save_addr(addr); - status = kmemcheck_shadow_test(shadow, size); - if (status == KMEMCHECK_SHADOW_INITIALIZED) - return; - - if (kmemcheck_enabled) - kmemcheck_error_save(status, addr, size, regs); - - if (kmemcheck_enabled == 2) - kmemcheck_enabled = 0; - - /* Don't warn about it again. */ - kmemcheck_shadow_set(shadow, size); -} - -bool kmemcheck_is_obj_initialized(unsigned long addr, size_t size) -{ - enum kmemcheck_shadow status; - void *shadow; - - shadow = kmemcheck_shadow_lookup(addr); - if (!shadow) - return true; - - status = kmemcheck_shadow_test_all(shadow, size); - - return status == KMEMCHECK_SHADOW_INITIALIZED; -} - -/* Access may cross page boundary */ -static void kmemcheck_read(struct pt_regs *regs, - unsigned long addr, unsigned int size) -{ - unsigned long page = addr & PAGE_MASK; - unsigned long next_addr = addr + size - 1; - unsigned long next_page = next_addr & PAGE_MASK; - - if (likely(page == next_page)) { - kmemcheck_read_strict(regs, addr, size); - return; - } - - /* - * What we do is basically to split the access across the - * two pages and handle each part separately. Yes, this means - * that we may now see reads that are 3 + 5 bytes, for - * example (and if both are uninitialized, there will be two - * reports), but it makes the code a lot simpler. - */ - kmemcheck_read_strict(regs, addr, next_page - addr); - kmemcheck_read_strict(regs, next_page, next_addr - next_page); -} - -static void kmemcheck_write_strict(struct pt_regs *regs, - unsigned long addr, unsigned int size) -{ - void *shadow; - - shadow = kmemcheck_shadow_lookup(addr); - if (!shadow) - return; - - kmemcheck_save_addr(addr); - kmemcheck_shadow_set(shadow, size); -} - -static void kmemcheck_write(struct pt_regs *regs, - unsigned long addr, unsigned int size) -{ - unsigned long page = addr & PAGE_MASK; - unsigned long next_addr = addr + size - 1; - unsigned long next_page = next_addr & PAGE_MASK; - - if (likely(page == next_page)) { - kmemcheck_write_strict(regs, addr, size); - return; - } - - /* See comment in kmemcheck_read(). */ - kmemcheck_write_strict(regs, addr, next_page - addr); - kmemcheck_write_strict(regs, next_page, next_addr - next_page); -} - -/* - * Copying is hard. We have two addresses, each of which may be split across - * a page (and each page will have different shadow addresses). - */ -static void kmemcheck_copy(struct pt_regs *regs, - unsigned long src_addr, unsigned long dst_addr, unsigned int size) -{ - uint8_t shadow[8]; - enum kmemcheck_shadow status; - - unsigned long page; - unsigned long next_addr; - unsigned long next_page; - - uint8_t *x; - unsigned int i; - unsigned int n; - - BUG_ON(size > sizeof(shadow)); - - page = src_addr & PAGE_MASK; - next_addr = src_addr + size - 1; - next_page = next_addr & PAGE_MASK; - - if (likely(page == next_page)) { - /* Same page */ - x = kmemcheck_shadow_lookup(src_addr); - if (x) { - kmemcheck_save_addr(src_addr); - for (i = 0; i < size; ++i) - shadow[i] = x[i]; - } else { - for (i = 0; i < size; ++i) - shadow[i] = KMEMCHECK_SHADOW_INITIALIZED; - } - } else { - n = next_page - src_addr; - BUG_ON(n > sizeof(shadow)); - - /* First page */ - x = kmemcheck_shadow_lookup(src_addr); - if (x) { - kmemcheck_save_addr(src_addr); - for (i = 0; i < n; ++i) - shadow[i] = x[i]; - } else { - /* Not tracked */ - for (i = 0; i < n; ++i) - shadow[i] = KMEMCHECK_SHADOW_INITIALIZED; - } - - /* Second page */ - x = kmemcheck_shadow_lookup(next_page); - if (x) { - kmemcheck_save_addr(next_page); - for (i = n; i < size; ++i) - shadow[i] = x[i - n]; - } else { - /* Not tracked */ - for (i = n; i < size; ++i) - shadow[i] = KMEMCHECK_SHADOW_INITIALIZED; - } - } - - page = dst_addr & PAGE_MASK; - next_addr = dst_addr + size - 1; - next_page = next_addr & PAGE_MASK; - - if (likely(page == next_page)) { - /* Same page */ - x = kmemcheck_shadow_lookup(dst_addr); - if (x) { - kmemcheck_save_addr(dst_addr); - for (i = 0; i < size; ++i) { - x[i] = shadow[i]; - shadow[i] = KMEMCHECK_SHADOW_INITIALIZED; - } - } - } else { - n = next_page - dst_addr; - BUG_ON(n > sizeof(shadow)); - - /* First page */ - x = kmemcheck_shadow_lookup(dst_addr); - if (x) { - kmemcheck_save_addr(dst_addr); - for (i = 0; i < n; ++i) { - x[i] = shadow[i]; - shadow[i] = KMEMCHECK_SHADOW_INITIALIZED; - } - } - - /* Second page */ - x = kmemcheck_shadow_lookup(next_page); - if (x) { - kmemcheck_save_addr(next_page); - for (i = n; i < size; ++i) { - x[i - n] = shadow[i]; - shadow[i] = KMEMCHECK_SHADOW_INITIALIZED; - } - } - } - - status = kmemcheck_shadow_test(shadow, size); - if (status == KMEMCHECK_SHADOW_INITIALIZED) - return; - - if (kmemcheck_enabled) - kmemcheck_error_save(status, src_addr, size, regs); - - if (kmemcheck_enabled == 2) - kmemcheck_enabled = 0; -} - -enum kmemcheck_method { - KMEMCHECK_READ, - KMEMCHECK_WRITE, -}; - -static void kmemcheck_access(struct pt_regs *regs, - unsigned long fallback_address, enum kmemcheck_method fallback_method) -{ - const uint8_t *insn; - const uint8_t *insn_primary; - unsigned int size; - - struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context); - - /* Recursive fault -- ouch. */ - if (data->busy) { - kmemcheck_show_addr(fallback_address); - kmemcheck_error_save_bug(regs); - return; - } - - data->busy = true; - - insn = (const uint8_t *) regs->ip; - insn_primary = kmemcheck_opcode_get_primary(insn); - - kmemcheck_opcode_decode(insn, &size); - - switch (insn_primary[0]) { -#ifdef CONFIG_KMEMCHECK_BITOPS_OK - /* AND, OR, XOR */ - /* - * Unfortunately, these instructions have to be excluded from - * our regular checking since they access only some (and not - * all) bits. This clears out "bogus" bitfield-access warnings. - */ - case 0x80: - case 0x81: - case 0x82: - case 0x83: - switch ((insn_primary[1] >> 3) & 7) { - /* OR */ - case 1: - /* AND */ - case 4: - /* XOR */ - case 6: - kmemcheck_write(regs, fallback_address, size); - goto out; - - /* ADD */ - case 0: - /* ADC */ - case 2: - /* SBB */ - case 3: - /* SUB */ - case 5: - /* CMP */ - case 7: - break; - } - break; -#endif - - /* MOVS, MOVSB, MOVSW, MOVSD */ - case 0xa4: - case 0xa5: - /* - * These instructions are special because they take two - * addresses, but we only get one page fault. - */ - kmemcheck_copy(regs, regs->si, regs->di, size); - goto out; - - /* CMPS, CMPSB, CMPSW, CMPSD */ - case 0xa6: - case 0xa7: - kmemcheck_read(regs, regs->si, size); - kmemcheck_read(regs, regs->di, size); - goto out; - } - - /* - * If the opcode isn't special in any way, we use the data from the - * page fault handler to determine the address and type of memory - * access. - */ - switch (fallback_method) { - case KMEMCHECK_READ: - kmemcheck_read(regs, fallback_address, size); - goto out; - case KMEMCHECK_WRITE: - kmemcheck_write(regs, fallback_address, size); - goto out; - } - -out: - data->busy = false; -} - -bool kmemcheck_fault(struct pt_regs *regs, unsigned long address, - unsigned long error_code) -{ - pte_t *pte; - - /* - * XXX: Is it safe to assume that memory accesses from virtual 86 - * mode or non-kernel code segments will _never_ access kernel - * memory (e.g. tracked pages)? For now, we need this to avoid - * invoking kmemcheck for PnP BIOS calls. - */ - if (regs->flags & X86_VM_MASK) - return false; - if (regs->cs != __KERNEL_CS) - return false; - - pte = kmemcheck_pte_lookup(address); - if (!pte) - return false; - - WARN_ON_ONCE(in_nmi()); - - if (error_code & 2) - kmemcheck_access(regs, address, KMEMCHECK_WRITE); - else - kmemcheck_access(regs, address, KMEMCHECK_READ); - - kmemcheck_show(regs); - return true; -} - -bool kmemcheck_trap(struct pt_regs *regs) -{ - if (!kmemcheck_active(regs)) - return false; - - /* We're done. */ - kmemcheck_hide(regs); - return true; -} diff --git a/arch/x86/mm/kmemcheck/opcode.c b/arch/x86/mm/kmemcheck/opcode.c index df8109ddf7fe..cec594032515 100644 --- a/arch/x86/mm/kmemcheck/opcode.c +++ b/arch/x86/mm/kmemcheck/opcode.c @@ -1,107 +1 @@ // SPDX-License-Identifier: GPL-2.0 -#include - -#include "opcode.h" - -static bool opcode_is_prefix(uint8_t b) -{ - return - /* Group 1 */ - b == 0xf0 || b == 0xf2 || b == 0xf3 - /* Group 2 */ - || b == 0x2e || b == 0x36 || b == 0x3e || b == 0x26 - || b == 0x64 || b == 0x65 - /* Group 3 */ - || b == 0x66 - /* Group 4 */ - || b == 0x67; -} - -#ifdef CONFIG_X86_64 -static bool opcode_is_rex_prefix(uint8_t b) -{ - return (b & 0xf0) == 0x40; -} -#else -static bool opcode_is_rex_prefix(uint8_t b) -{ - return false; -} -#endif - -#define REX_W (1 << 3) - -/* - * This is a VERY crude opcode decoder. We only need to find the size of the - * load/store that caused our #PF and this should work for all the opcodes - * that we care about. Moreover, the ones who invented this instruction set - * should be shot. - */ -void kmemcheck_opcode_decode(const uint8_t *op, unsigned int *size) -{ - /* Default operand size */ - int operand_size_override = 4; - - /* prefixes */ - for (; opcode_is_prefix(*op); ++op) { - if (*op == 0x66) - operand_size_override = 2; - } - - /* REX prefix */ - if (opcode_is_rex_prefix(*op)) { - uint8_t rex = *op; - - ++op; - if (rex & REX_W) { - switch (*op) { - case 0x63: - *size = 4; - return; - case 0x0f: - ++op; - - switch (*op) { - case 0xb6: - case 0xbe: - *size = 1; - return; - case 0xb7: - case 0xbf: - *size = 2; - return; - } - - break; - } - - *size = 8; - return; - } - } - - /* escape opcode */ - if (*op == 0x0f) { - ++op; - - /* - * This is move with zero-extend and sign-extend, respectively; - * we don't have to think about 0xb6/0xbe, because this is - * already handled in the conditional below. - */ - if (*op == 0xb7 || *op == 0xbf) - operand_size_override = 2; - } - - *size = (*op & 1) ? operand_size_override : 1; -} - -const uint8_t *kmemcheck_opcode_get_primary(const uint8_t *op) -{ - /* skip prefixes */ - while (opcode_is_prefix(*op)) - ++op; - if (opcode_is_rex_prefix(*op)) - ++op; - return op; -} diff --git a/arch/x86/mm/kmemcheck/opcode.h b/arch/x86/mm/kmemcheck/opcode.h index 51a1ce94c24a..ea32a7d3cf1b 100644 --- a/arch/x86/mm/kmemcheck/opcode.h +++ b/arch/x86/mm/kmemcheck/opcode.h @@ -1,10 +1 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef ARCH__X86__MM__KMEMCHECK__OPCODE_H -#define ARCH__X86__MM__KMEMCHECK__OPCODE_H - -#include - -void kmemcheck_opcode_decode(const uint8_t *op, unsigned int *size); -const uint8_t *kmemcheck_opcode_get_primary(const uint8_t *op); - -#endif diff --git a/arch/x86/mm/kmemcheck/pte.c b/arch/x86/mm/kmemcheck/pte.c index 8a03be90272a..cec594032515 100644 --- a/arch/x86/mm/kmemcheck/pte.c +++ b/arch/x86/mm/kmemcheck/pte.c @@ -1,23 +1 @@ // SPDX-License-Identifier: GPL-2.0 -#include - -#include - -#include "pte.h" - -pte_t *kmemcheck_pte_lookup(unsigned long address) -{ - pte_t *pte; - unsigned int level; - - pte = lookup_address(address, &level); - if (!pte) - return NULL; - if (level != PG_LEVEL_4K) - return NULL; - if (!pte_hidden(*pte)) - return NULL; - - return pte; -} - diff --git a/arch/x86/mm/kmemcheck/pte.h b/arch/x86/mm/kmemcheck/pte.h index b595612382c2..ea32a7d3cf1b 100644 --- a/arch/x86/mm/kmemcheck/pte.h +++ b/arch/x86/mm/kmemcheck/pte.h @@ -1,11 +1 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef ARCH__X86__MM__KMEMCHECK__PTE_H -#define ARCH__X86__MM__KMEMCHECK__PTE_H - -#include - -#include - -pte_t *kmemcheck_pte_lookup(unsigned long address); - -#endif diff --git a/arch/x86/mm/kmemcheck/selftest.c b/arch/x86/mm/kmemcheck/selftest.c index 7ce0be1f99eb..cec594032515 100644 --- a/arch/x86/mm/kmemcheck/selftest.c +++ b/arch/x86/mm/kmemcheck/selftest.c @@ -1,71 +1 @@ // SPDX-License-Identifier: GPL-2.0 -#include -#include - -#include "opcode.h" -#include "selftest.h" - -struct selftest_opcode { - unsigned int expected_size; - const uint8_t *insn; - const char *desc; -}; - -static const struct selftest_opcode selftest_opcodes[] = { - /* REP MOVS */ - {1, "\xf3\xa4", "rep movsb , "}, - {4, "\xf3\xa5", "rep movsl , "}, - - /* MOVZX / MOVZXD */ - {1, "\x66\x0f\xb6\x51\xf8", "movzwq , "}, - {1, "\x0f\xb6\x51\xf8", "movzwq , "}, - - /* MOVSX / MOVSXD */ - {1, "\x66\x0f\xbe\x51\xf8", "movswq , "}, - {1, "\x0f\xbe\x51\xf8", "movswq , "}, - -#ifdef CONFIG_X86_64 - /* MOVZX / MOVZXD */ - {1, "\x49\x0f\xb6\x51\xf8", "movzbq , "}, - {2, "\x49\x0f\xb7\x51\xf8", "movzbq , "}, - - /* MOVSX / MOVSXD */ - {1, "\x49\x0f\xbe\x51\xf8", "movsbq , "}, - {2, "\x49\x0f\xbf\x51\xf8", "movsbq , "}, - {4, "\x49\x63\x51\xf8", "movslq , "}, -#endif -}; - -static bool selftest_opcode_one(const struct selftest_opcode *op) -{ - unsigned size; - - kmemcheck_opcode_decode(op->insn, &size); - - if (size == op->expected_size) - return true; - - printk(KERN_WARNING "kmemcheck: opcode %s: expected size %d, got %d\n", - op->desc, op->expected_size, size); - return false; -} - -static bool selftest_opcodes_all(void) -{ - bool pass = true; - unsigned int i; - - for (i = 0; i < ARRAY_SIZE(selftest_opcodes); ++i) - pass = pass && selftest_opcode_one(&selftest_opcodes[i]); - - return pass; -} - -bool kmemcheck_selftest(void) -{ - bool pass = true; - - pass = pass && selftest_opcodes_all(); - - return pass; -} diff --git a/arch/x86/mm/kmemcheck/selftest.h b/arch/x86/mm/kmemcheck/selftest.h index 8d759aae453d..ea32a7d3cf1b 100644 --- a/arch/x86/mm/kmemcheck/selftest.h +++ b/arch/x86/mm/kmemcheck/selftest.h @@ -1,7 +1 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef ARCH_X86_MM_KMEMCHECK_SELFTEST_H -#define ARCH_X86_MM_KMEMCHECK_SELFTEST_H - -bool kmemcheck_selftest(void); - -#endif diff --git a/arch/x86/mm/kmemcheck/shadow.c b/arch/x86/mm/kmemcheck/shadow.c deleted file mode 100644 index c2638a7d2c10..000000000000 --- a/arch/x86/mm/kmemcheck/shadow.c +++ /dev/null @@ -1,173 +0,0 @@ -#include -#include -#include - -#include -#include - -#include "pte.h" -#include "shadow.h" - -/* - * Return the shadow address for the given address. Returns NULL if the - * address is not tracked. - * - * We need to be extremely careful not to follow any invalid pointers, - * because this function can be called for *any* possible address. - */ -void *kmemcheck_shadow_lookup(unsigned long address) -{ - pte_t *pte; - struct page *page; - - if (!virt_addr_valid(address)) - return NULL; - - pte = kmemcheck_pte_lookup(address); - if (!pte) - return NULL; - - page = virt_to_page(address); - if (!page->shadow) - return NULL; - return page->shadow + (address & (PAGE_SIZE - 1)); -} - -static void mark_shadow(void *address, unsigned int n, - enum kmemcheck_shadow status) -{ - unsigned long addr = (unsigned long) address; - unsigned long last_addr = addr + n - 1; - unsigned long page = addr & PAGE_MASK; - unsigned long last_page = last_addr & PAGE_MASK; - unsigned int first_n; - void *shadow; - - /* If the memory range crosses a page boundary, stop there. */ - if (page == last_page) - first_n = n; - else - first_n = page + PAGE_SIZE - addr; - - shadow = kmemcheck_shadow_lookup(addr); - if (shadow) - memset(shadow, status, first_n); - - addr += first_n; - n -= first_n; - - /* Do full-page memset()s. */ - while (n >= PAGE_SIZE) { - shadow = kmemcheck_shadow_lookup(addr); - if (shadow) - memset(shadow, status, PAGE_SIZE); - - addr += PAGE_SIZE; - n -= PAGE_SIZE; - } - - /* Do the remaining page, if any. */ - if (n > 0) { - shadow = kmemcheck_shadow_lookup(addr); - if (shadow) - memset(shadow, status, n); - } -} - -void kmemcheck_mark_unallocated(void *address, unsigned int n) -{ - mark_shadow(address, n, KMEMCHECK_SHADOW_UNALLOCATED); -} - -void kmemcheck_mark_uninitialized(void *address, unsigned int n) -{ - mark_shadow(address, n, KMEMCHECK_SHADOW_UNINITIALIZED); -} - -/* - * Fill the shadow memory of the given address such that the memory at that - * address is marked as being initialized. - */ -void kmemcheck_mark_initialized(void *address, unsigned int n) -{ - mark_shadow(address, n, KMEMCHECK_SHADOW_INITIALIZED); -} -EXPORT_SYMBOL_GPL(kmemcheck_mark_initialized); - -void kmemcheck_mark_freed(void *address, unsigned int n) -{ - mark_shadow(address, n, KMEMCHECK_SHADOW_FREED); -} - -void kmemcheck_mark_unallocated_pages(struct page *p, unsigned int n) -{ - unsigned int i; - - for (i = 0; i < n; ++i) - kmemcheck_mark_unallocated(page_address(&p[i]), PAGE_SIZE); -} - -void kmemcheck_mark_uninitialized_pages(struct page *p, unsigned int n) -{ - unsigned int i; - - for (i = 0; i < n; ++i) - kmemcheck_mark_uninitialized(page_address(&p[i]), PAGE_SIZE); -} - -void kmemcheck_mark_initialized_pages(struct page *p, unsigned int n) -{ - unsigned int i; - - for (i = 0; i < n; ++i) - kmemcheck_mark_initialized(page_address(&p[i]), PAGE_SIZE); -} - -enum kmemcheck_shadow kmemcheck_shadow_test(void *shadow, unsigned int size) -{ -#ifdef CONFIG_KMEMCHECK_PARTIAL_OK - uint8_t *x; - unsigned int i; - - x = shadow; - - /* - * Make sure _some_ bytes are initialized. Gcc frequently generates - * code to access neighboring bytes. - */ - for (i = 0; i < size; ++i) { - if (x[i] == KMEMCHECK_SHADOW_INITIALIZED) - return x[i]; - } - - return x[0]; -#else - return kmemcheck_shadow_test_all(shadow, size); -#endif -} - -enum kmemcheck_shadow kmemcheck_shadow_test_all(void *shadow, unsigned int size) -{ - uint8_t *x; - unsigned int i; - - x = shadow; - - /* All bytes must be initialized. */ - for (i = 0; i < size; ++i) { - if (x[i] != KMEMCHECK_SHADOW_INITIALIZED) - return x[i]; - } - - return x[0]; -} - -void kmemcheck_shadow_set(void *shadow, unsigned int size) -{ - uint8_t *x; - unsigned int i; - - x = shadow; - for (i = 0; i < size; ++i) - x[i] = KMEMCHECK_SHADOW_INITIALIZED; -} diff --git a/arch/x86/mm/kmemcheck/shadow.h b/arch/x86/mm/kmemcheck/shadow.h index 49768dc18664..ea32a7d3cf1b 100644 --- a/arch/x86/mm/kmemcheck/shadow.h +++ b/arch/x86/mm/kmemcheck/shadow.h @@ -1,19 +1 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef ARCH__X86__MM__KMEMCHECK__SHADOW_H -#define ARCH__X86__MM__KMEMCHECK__SHADOW_H - -enum kmemcheck_shadow { - KMEMCHECK_SHADOW_UNALLOCATED, - KMEMCHECK_SHADOW_UNINITIALIZED, - KMEMCHECK_SHADOW_INITIALIZED, - KMEMCHECK_SHADOW_FREED, -}; - -void *kmemcheck_shadow_lookup(unsigned long address); - -enum kmemcheck_shadow kmemcheck_shadow_test(void *shadow, unsigned int size); -enum kmemcheck_shadow kmemcheck_shadow_test_all(void *shadow, - unsigned int size); -void kmemcheck_shadow_set(void *shadow, unsigned int size); - -#endif diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index baeb872283d9..69c238210325 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -594,21 +594,6 @@ static inline void tasklet_hi_schedule(struct tasklet_struct *t) __tasklet_hi_schedule(t); } -extern void __tasklet_hi_schedule_first(struct tasklet_struct *t); - -/* - * This version avoids touching any other tasklets. Needed for kmemcheck - * in order not to take any page faults while enqueueing this tasklet; - * consider VERY carefully whether you really need this or - * tasklet_hi_schedule()... - */ -static inline void tasklet_hi_schedule_first(struct tasklet_struct *t) -{ - if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) - __tasklet_hi_schedule_first(t); -} - - static inline void tasklet_disable_nosync(struct tasklet_struct *t) { atomic_inc(&t->count); diff --git a/include/linux/kmemcheck.h b/include/linux/kmemcheck.h index 7b1d7bead7d9..ea32a7d3cf1b 100644 --- a/include/linux/kmemcheck.h +++ b/include/linux/kmemcheck.h @@ -1,172 +1 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef LINUX_KMEMCHECK_H -#define LINUX_KMEMCHECK_H - -#include -#include - -#ifdef CONFIG_KMEMCHECK -extern int kmemcheck_enabled; - -/* The slab-related functions. */ -void kmemcheck_alloc_shadow(struct page *page, int order, gfp_t flags, int node); -void kmemcheck_free_shadow(struct page *page, int order); -void kmemcheck_slab_alloc(struct kmem_cache *s, gfp_t gfpflags, void *object, - size_t size); -void kmemcheck_slab_free(struct kmem_cache *s, void *object, size_t size); - -void kmemcheck_pagealloc_alloc(struct page *p, unsigned int order, - gfp_t gfpflags); - -void kmemcheck_show_pages(struct page *p, unsigned int n); -void kmemcheck_hide_pages(struct page *p, unsigned int n); - -bool kmemcheck_page_is_tracked(struct page *p); - -void kmemcheck_mark_unallocated(void *address, unsigned int n); -void kmemcheck_mark_uninitialized(void *address, unsigned int n); -void kmemcheck_mark_initialized(void *address, unsigned int n); -void kmemcheck_mark_freed(void *address, unsigned int n); - -void kmemcheck_mark_unallocated_pages(struct page *p, unsigned int n); -void kmemcheck_mark_uninitialized_pages(struct page *p, unsigned int n); -void kmemcheck_mark_initialized_pages(struct page *p, unsigned int n); - -int kmemcheck_show_addr(unsigned long address); -int kmemcheck_hide_addr(unsigned long address); - -bool kmemcheck_is_obj_initialized(unsigned long addr, size_t size); - -/* - * Bitfield annotations - * - * How to use: If you have a struct using bitfields, for example - * - * struct a { - * int x:8, y:8; - * }; - * - * then this should be rewritten as - * - * struct a { - * kmemcheck_bitfield_begin(flags); - * int x:8, y:8; - * kmemcheck_bitfield_end(flags); - * }; - * - * Now the "flags_begin" and "flags_end" members may be used to refer to the - * beginning and end, respectively, of the bitfield (and things like - * &x.flags_begin is allowed). As soon as the struct is allocated, the bit- - * fields should be annotated: - * - * struct a *a = kmalloc(sizeof(struct a), GFP_KERNEL); - * kmemcheck_annotate_bitfield(a, flags); - */ -#define kmemcheck_bitfield_begin(name) \ - int name##_begin[0]; - -#define kmemcheck_bitfield_end(name) \ - int name##_end[0]; - -#define kmemcheck_annotate_bitfield(ptr, name) \ - do { \ - int _n; \ - \ - if (!ptr) \ - break; \ - \ - _n = (long) &((ptr)->name##_end) \ - - (long) &((ptr)->name##_begin); \ - BUILD_BUG_ON(_n < 0); \ - \ - kmemcheck_mark_initialized(&((ptr)->name##_begin), _n); \ - } while (0) - -#define kmemcheck_annotate_variable(var) \ - do { \ - kmemcheck_mark_initialized(&(var), sizeof(var)); \ - } while (0) \ - -#else -#define kmemcheck_enabled 0 - -static inline void -kmemcheck_alloc_shadow(struct page *page, int order, gfp_t flags, int node) -{ -} - -static inline void -kmemcheck_free_shadow(struct page *page, int order) -{ -} - -static inline void -kmemcheck_slab_alloc(struct kmem_cache *s, gfp_t gfpflags, void *object, - size_t size) -{ -} - -static inline void kmemcheck_slab_free(struct kmem_cache *s, void *object, - size_t size) -{ -} - -static inline void kmemcheck_pagealloc_alloc(struct page *p, - unsigned int order, gfp_t gfpflags) -{ -} - -static inline bool kmemcheck_page_is_tracked(struct page *p) -{ - return false; -} - -static inline void kmemcheck_mark_unallocated(void *address, unsigned int n) -{ -} - -static inline void kmemcheck_mark_uninitialized(void *address, unsigned int n) -{ -} - -static inline void kmemcheck_mark_initialized(void *address, unsigned int n) -{ -} - -static inline void kmemcheck_mark_freed(void *address, unsigned int n) -{ -} - -static inline void kmemcheck_mark_unallocated_pages(struct page *p, - unsigned int n) -{ -} - -static inline void kmemcheck_mark_uninitialized_pages(struct page *p, - unsigned int n) -{ -} - -static inline void kmemcheck_mark_initialized_pages(struct page *p, - unsigned int n) -{ -} - -static inline bool kmemcheck_is_obj_initialized(unsigned long addr, size_t size) -{ - return true; -} - -#define kmemcheck_bitfield_begin(name) -#define kmemcheck_bitfield_end(name) -#define kmemcheck_annotate_bitfield(ptr, name) \ - do { \ - } while (0) - -#define kmemcheck_annotate_variable(var) \ - do { \ - } while (0) - -#endif /* CONFIG_KMEMCHECK */ - -#endif /* LINUX_KMEMCHECK_H */ diff --git a/kernel/softirq.c b/kernel/softirq.c index 662f7b1b7a78..2f5e87f1bae2 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -486,16 +486,6 @@ void __tasklet_hi_schedule(struct tasklet_struct *t) } EXPORT_SYMBOL(__tasklet_hi_schedule); -void __tasklet_hi_schedule_first(struct tasklet_struct *t) -{ - lockdep_assert_irqs_disabled(); - - t->next = __this_cpu_read(tasklet_hi_vec.head); - __this_cpu_write(tasklet_hi_vec.head, t); - __raise_softirq_irqoff(HI_SOFTIRQ); -} -EXPORT_SYMBOL(__tasklet_hi_schedule_first); - static __latent_entropy void tasklet_action(struct softirq_action *a) { struct tasklet_struct *list; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 9576bd582d4a..7638e2f7fff8 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -30,7 +30,6 @@ #include #include #include -#include #include #include #include @@ -1173,15 +1172,6 @@ static struct ctl_table kern_table[] = { .extra1 = &zero, .extra2 = &one_thousand, }, -#endif -#ifdef CONFIG_KMEMCHECK - { - .procname = "kmemcheck", - .data = &kmemcheck_enabled, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, #endif { .procname = "panic_on_warn", diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 07ce7449765a..5402e3954659 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -504,7 +504,7 @@ config DEBUG_OBJECTS_ENABLE_DEFAULT config DEBUG_SLAB bool "Debug slab memory allocations" - depends on DEBUG_KERNEL && SLAB && !KMEMCHECK + depends on DEBUG_KERNEL && SLAB help Say Y here to have the kernel do limited verification on memory allocation as well as poisoning memory on free to catch use of freed @@ -516,7 +516,7 @@ config DEBUG_SLAB_LEAK config SLUB_DEBUG_ON bool "SLUB debugging on by default" - depends on SLUB && SLUB_DEBUG && !KMEMCHECK + depends on SLUB && SLUB_DEBUG default n help Boot with debugging on by default. SLUB boots by default with @@ -730,8 +730,6 @@ config DEBUG_STACKOVERFLOW If in doubt, say "N". -source "lib/Kconfig.kmemcheck" - source "lib/Kconfig.kasan" endmenu # "Memory Debugging" diff --git a/lib/Kconfig.kmemcheck b/lib/Kconfig.kmemcheck deleted file mode 100644 index 846e039a86b4..000000000000 --- a/lib/Kconfig.kmemcheck +++ /dev/null @@ -1,94 +0,0 @@ -config HAVE_ARCH_KMEMCHECK - bool - -if HAVE_ARCH_KMEMCHECK - -menuconfig KMEMCHECK - bool "kmemcheck: trap use of uninitialized memory" - depends on DEBUG_KERNEL - depends on !X86_USE_3DNOW - depends on SLUB || SLAB - depends on !CC_OPTIMIZE_FOR_SIZE - depends on !FUNCTION_TRACER - select FRAME_POINTER - select STACKTRACE - default n - help - This option enables tracing of dynamically allocated kernel memory - to see if memory is used before it has been given an initial value. - Be aware that this requires half of your memory for bookkeeping and - will insert extra code at *every* read and write to tracked memory - thus slow down the kernel code (but user code is unaffected). - - The kernel may be started with kmemcheck=0 or kmemcheck=1 to disable - or enable kmemcheck at boot-time. If the kernel is started with - kmemcheck=0, the large memory and CPU overhead is not incurred. - -choice - prompt "kmemcheck: default mode at boot" - depends on KMEMCHECK - default KMEMCHECK_ONESHOT_BY_DEFAULT - help - This option controls the default behaviour of kmemcheck when the - kernel boots and no kmemcheck= parameter is given. - -config KMEMCHECK_DISABLED_BY_DEFAULT - bool "disabled" - depends on KMEMCHECK - -config KMEMCHECK_ENABLED_BY_DEFAULT - bool "enabled" - depends on KMEMCHECK - -config KMEMCHECK_ONESHOT_BY_DEFAULT - bool "one-shot" - depends on KMEMCHECK - help - In one-shot mode, only the first error detected is reported before - kmemcheck is disabled. - -endchoice - -config KMEMCHECK_QUEUE_SIZE - int "kmemcheck: error queue size" - depends on KMEMCHECK - default 64 - help - Select the maximum number of errors to store in the queue. Since - errors can occur virtually anywhere and in any context, we need a - temporary storage area which is guarantueed not to generate any - other faults. The queue will be emptied as soon as a tasklet may - be scheduled. If the queue is full, new error reports will be - lost. - -config KMEMCHECK_SHADOW_COPY_SHIFT - int "kmemcheck: shadow copy size (5 => 32 bytes, 6 => 64 bytes)" - depends on KMEMCHECK - range 2 8 - default 5 - help - Select the number of shadow bytes to save along with each entry of - the queue. These bytes indicate what parts of an allocation are - initialized, uninitialized, etc. and will be displayed when an - error is detected to help the debugging of a particular problem. - -config KMEMCHECK_PARTIAL_OK - bool "kmemcheck: allow partially uninitialized memory" - depends on KMEMCHECK - default y - help - This option works around certain GCC optimizations that produce - 32-bit reads from 16-bit variables where the upper 16 bits are - thrown away afterwards. This may of course also hide some real - bugs. - -config KMEMCHECK_BITOPS_OK - bool "kmemcheck: allow bit-field manipulation" - depends on KMEMCHECK - default n - help - This option silences warnings that would be generated for bit-field - accesses where not all the bits are initialized at the same time. - This may also hide some real bugs. - -endif diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug index 5b0adf1435de..e5e606ee5f71 100644 --- a/mm/Kconfig.debug +++ b/mm/Kconfig.debug @@ -11,7 +11,6 @@ config DEBUG_PAGEALLOC bool "Debug page memory allocations" depends on DEBUG_KERNEL depends on !HIBERNATION || ARCH_SUPPORTS_DEBUG_PAGEALLOC && !PPC && !SPARC - depends on !KMEMCHECK select PAGE_EXTENSION select PAGE_POISONING if !ARCH_SUPPORTS_DEBUG_PAGEALLOC ---help--- diff --git a/mm/Makefile b/mm/Makefile index 4659b93cba43..e7ebd176fb93 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -17,7 +17,6 @@ KCOV_INSTRUMENT_slub.o := n KCOV_INSTRUMENT_page_alloc.o := n KCOV_INSTRUMENT_debug-pagealloc.o := n KCOV_INSTRUMENT_kmemleak.o := n -KCOV_INSTRUMENT_kmemcheck.o := n KCOV_INSTRUMENT_memcontrol.o := n KCOV_INSTRUMENT_mmzone.o := n KCOV_INSTRUMENT_vmstat.o := n @@ -70,7 +69,6 @@ obj-$(CONFIG_KSM) += ksm.o obj-$(CONFIG_PAGE_POISONING) += page_poison.o obj-$(CONFIG_SLAB) += slab.o obj-$(CONFIG_SLUB) += slub.o -obj-$(CONFIG_KMEMCHECK) += kmemcheck.o obj-$(CONFIG_KASAN) += kasan/ obj-$(CONFIG_FAILSLAB) += failslab.o obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o diff --git a/mm/kmemcheck.c b/mm/kmemcheck.c index b3a4d61d341c..cec594032515 100644 --- a/mm/kmemcheck.c +++ b/mm/kmemcheck.c @@ -1,126 +1 @@ // SPDX-License-Identifier: GPL-2.0 -#include -#include -#include -#include -#include "slab.h" -#include - -void kmemcheck_alloc_shadow(struct page *page, int order, gfp_t flags, int node) -{ - struct page *shadow; - int pages; - int i; - - pages = 1 << order; - - /* - * With kmemcheck enabled, we need to allocate a memory area for the - * shadow bits as well. - */ - shadow = alloc_pages_node(node, flags, order); - if (!shadow) { - if (printk_ratelimit()) - pr_err("kmemcheck: failed to allocate shadow bitmap\n"); - return; - } - - for(i = 0; i < pages; ++i) - page[i].shadow = page_address(&shadow[i]); - - /* - * Mark it as non-present for the MMU so that our accesses to - * this memory will trigger a page fault and let us analyze - * the memory accesses. - */ - kmemcheck_hide_pages(page, pages); -} - -void kmemcheck_free_shadow(struct page *page, int order) -{ - struct page *shadow; - int pages; - int i; - - if (!kmemcheck_page_is_tracked(page)) - return; - - pages = 1 << order; - - kmemcheck_show_pages(page, pages); - - shadow = virt_to_page(page[0].shadow); - - for(i = 0; i < pages; ++i) - page[i].shadow = NULL; - - __free_pages(shadow, order); -} - -void kmemcheck_slab_alloc(struct kmem_cache *s, gfp_t gfpflags, void *object, - size_t size) -{ - if (unlikely(!object)) /* Skip object if allocation failed */ - return; - - /* - * Has already been memset(), which initializes the shadow for us - * as well. - */ - if (gfpflags & __GFP_ZERO) - return; - - /* No need to initialize the shadow of a non-tracked slab. */ - if (s->flags & SLAB_NOTRACK) - return; - - if (!kmemcheck_enabled || gfpflags & __GFP_NOTRACK) { - /* - * Allow notracked objects to be allocated from - * tracked caches. Note however that these objects - * will still get page faults on access, they just - * won't ever be flagged as uninitialized. If page - * faults are not acceptable, the slab cache itself - * should be marked NOTRACK. - */ - kmemcheck_mark_initialized(object, size); - } else if (!s->ctor) { - /* - * New objects should be marked uninitialized before - * they're returned to the called. - */ - kmemcheck_mark_uninitialized(object, size); - } -} - -void kmemcheck_slab_free(struct kmem_cache *s, void *object, size_t size) -{ - /* TODO: RCU freeing is unsupported for now; hide false positives. */ - if (!s->ctor && !(s->flags & SLAB_TYPESAFE_BY_RCU)) - kmemcheck_mark_freed(object, size); -} - -void kmemcheck_pagealloc_alloc(struct page *page, unsigned int order, - gfp_t gfpflags) -{ - int pages; - - if (gfpflags & (__GFP_HIGHMEM | __GFP_NOTRACK)) - return; - - pages = 1 << order; - - /* - * NOTE: We choose to track GFP_ZERO pages too; in fact, they - * can become uninitialized by copying uninitialized memory - * into them. - */ - - /* XXX: Can use zone->node for node? */ - kmemcheck_alloc_shadow(page, order, gfpflags, -1); - - if (gfpflags & __GFP_ZERO) - kmemcheck_mark_initialized_pages(page, pages); - else - kmemcheck_mark_uninitialized_pages(page, pages); -} diff --git a/mm/slub.c b/mm/slub.c index c2c41e178acf..cfd56e5a35fb 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1371,7 +1371,7 @@ static inline void *slab_free_hook(struct kmem_cache *s, void *x) * So in order to make the debug calls that expect irqs to be * disabled we need to disable interrupts temporarily. */ -#if defined(CONFIG_KMEMCHECK) || defined(CONFIG_LOCKDEP) +#ifdef CONFIG_LOCKDEP { unsigned long flags; @@ -1399,8 +1399,7 @@ static inline void slab_free_freelist_hook(struct kmem_cache *s, * Compiler cannot detect this function can be removed if slab_free_hook() * evaluates to nothing. Thus, catch all relevant config debug options here. */ -#if defined(CONFIG_KMEMCHECK) || \ - defined(CONFIG_LOCKDEP) || \ +#if defined(CONFIG_LOCKDEP) || \ defined(CONFIG_DEBUG_KMEMLEAK) || \ defined(CONFIG_DEBUG_OBJECTS_FREE) || \ defined(CONFIG_KASAN) diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 67d051edd615..7bd52b8f63d4 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -2182,8 +2182,6 @@ sub dump_struct($$) { # strip comments: $members =~ s/\/\*.*?\*\///gos; $nested =~ s/\/\*.*?\*\///gos; - # strip kmemcheck_bitfield_{begin,end}.*; - $members =~ s/kmemcheck_bitfield_.*?;//gos; # strip attributes $members =~ s/__attribute__\s*\(\([a-z,_\*\s\(\)]*\)\)//i; $members =~ s/__aligned\s*\([^;]*\)//gos; diff --git a/tools/include/linux/kmemcheck.h b/tools/include/linux/kmemcheck.h index 2bccd2c7b897..ea32a7d3cf1b 100644 --- a/tools/include/linux/kmemcheck.h +++ b/tools/include/linux/kmemcheck.h @@ -1,9 +1 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LIBLOCKDEP_LINUX_KMEMCHECK_H_ -#define _LIBLOCKDEP_LINUX_KMEMCHECK_H_ - -static inline void kmemcheck_mark_initialized(void *address, unsigned int n) -{ -} - -#endif -- cgit v1.3-8-gc7d7 From 4518085e127dff97e74f74a8780d7564e273bec8 Mon Sep 17 00:00:00 2001 From: Kemi Wang Date: Wed, 15 Nov 2017 17:38:22 -0800 Subject: mm, sysctl: make NUMA stats configurable This is the second step which introduces a tunable interface that allow numa stats configurable for optimizing zone_statistics(), as suggested by Dave Hansen and Ying Huang. ========================================================================= When page allocation performance becomes a bottleneck and you can tolerate some possible tool breakage and decreased numa counter precision, you can do: echo 0 > /proc/sys/vm/numa_stat In this case, numa counter update is ignored. We can see about *4.8%*(185->176) drop of cpu cycles per single page allocation and reclaim on Jesper's page_bench01 (single thread) and *8.1%*(343->315) drop of cpu cycles per single page allocation and reclaim on Jesper's page_bench03 (88 threads) running on a 2-Socket Broadwell-based server (88 threads, 126G memory). Benchmark link provided by Jesper D Brouer (increase loop times to 10000000): https://github.com/netoptimizer/prototype-kernel/tree/master/kernel/mm/bench ========================================================================= When page allocation performance is not a bottleneck and you want all tooling to work, you can do: echo 1 > /proc/sys/vm/numa_stat This is system default setting. Many thanks to Michal Hocko, Dave Hansen, Ying Huang and Vlastimil Babka for comments to help improve the original patch. [keescook@chromium.org: make sure mutex is a global static] Link: http://lkml.kernel.org/r/20171107213809.GA4314@beast Link: http://lkml.kernel.org/r/1508290927-8518-1-git-send-email-kemi.wang@intel.com Signed-off-by: Kemi Wang Signed-off-by: Kees Cook Reported-by: Jesper Dangaard Brouer Suggested-by: Dave Hansen Suggested-by: Ying Huang Acked-by: Vlastimil Babka Acked-by: Michal Hocko Cc: "Luis R . Rodriguez" Cc: Kees Cook Cc: Jonathan Corbet Cc: Mel Gorman Cc: Johannes Weiner Cc: Christopher Lameter Cc: Sebastian Andrzej Siewior Cc: Andrey Ryabinin Cc: Tim Chen Cc: Andi Kleen Cc: Aaron Lu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 16 ++++++++++ include/linux/vmstat.h | 10 +++++++ kernel/sysctl.c | 9 ++++++ mm/mempolicy.c | 3 ++ mm/page_alloc.c | 6 ++++ mm/vmstat.c | 71 +++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 115 insertions(+) (limited to 'kernel/sysctl.c') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 3e579740b49f..055c8b3e1018 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -58,6 +58,7 @@ Currently, these files are in /proc/sys/vm: - percpu_pagelist_fraction - stat_interval - stat_refresh +- numa_stat - swappiness - user_reserve_kbytes - vfs_cache_pressure @@ -799,6 +800,21 @@ with no ill effects: errors and warnings on these stats are suppressed.) ============================================================== +numa_stat + +This interface allows runtime configuration of numa statistics. + +When page allocation performance becomes a bottleneck and you can tolerate +some possible tool breakage and decreased numa counter precision, you can +do: + echo 0 > /proc/sys/vm/numa_stat + +When page allocation performance is not a bottleneck and you want all +tooling to work, you can do: + echo 1 > /proc/sys/vm/numa_stat + +============================================================== + swappiness This control is used to define how aggressive the kernel will swap diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 1e0cb72e0598..1779c9817b39 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -7,9 +7,19 @@ #include #include #include +#include extern int sysctl_stat_interval; +#ifdef CONFIG_NUMA +#define ENABLE_NUMA_STAT 1 +#define DISABLE_NUMA_STAT 0 +extern int sysctl_vm_numa_stat; +DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key); +extern int sysctl_vm_numa_stat_handler(struct ctl_table *table, + int write, void __user *buffer, size_t *length, loff_t *ppos); +#endif + #ifdef CONFIG_VM_EVENT_COUNTERS /* * Light weight per cpu counter implementation. diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 7638e2f7fff8..4a13a389e99b 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1356,6 +1356,15 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = &hugetlb_mempolicy_sysctl_handler, }, + { + .procname = "numa_stat", + .data = &sysctl_vm_numa_stat, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = sysctl_vm_numa_stat_handler, + .extra1 = &zero, + .extra2 = &one, + }, #endif { .procname = "hugetlb_shm_group", diff --git a/mm/mempolicy.c b/mm/mempolicy.c index dad166b736ba..4ce44d3ff03d 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1915,6 +1915,9 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, struct page *page; page = __alloc_pages(gfp, order, nid); + /* skip NUMA_INTERLEAVE_HIT counter update if numa stats is disabled */ + if (!static_branch_likely(&vm_numa_stat_key)) + return page; if (page && page_to_nid(page) == nid) { preempt_disable(); __inc_numa_state(page_zone(page), NUMA_INTERLEAVE_HIT); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7ca668e946e5..67f523c4711a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -82,6 +82,8 @@ DEFINE_PER_CPU(int, numa_node); EXPORT_PER_CPU_SYMBOL(numa_node); #endif +DEFINE_STATIC_KEY_TRUE(vm_numa_stat_key); + #ifdef CONFIG_HAVE_MEMORYLESS_NODES /* * N.B., Do NOT reference the '_numa_mem_' per cpu variable directly. @@ -2777,6 +2779,10 @@ static inline void zone_statistics(struct zone *preferred_zone, struct zone *z) #ifdef CONFIG_NUMA enum numa_stat_item local_stat = NUMA_LOCAL; + /* skip numa counters update if numa stats is disabled */ + if (!static_branch_likely(&vm_numa_stat_key)) + return; + if (z->node != numa_node_id()) local_stat = NUMA_OTHER; diff --git a/mm/vmstat.c b/mm/vmstat.c index 7d11554861e4..40b2db6db6b1 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -32,6 +32,77 @@ #define NUMA_STATS_THRESHOLD (U16_MAX - 2) +#ifdef CONFIG_NUMA +int sysctl_vm_numa_stat = ENABLE_NUMA_STAT; + +/* zero numa counters within a zone */ +static void zero_zone_numa_counters(struct zone *zone) +{ + int item, cpu; + + for (item = 0; item < NR_VM_NUMA_STAT_ITEMS; item++) { + atomic_long_set(&zone->vm_numa_stat[item], 0); + for_each_online_cpu(cpu) + per_cpu_ptr(zone->pageset, cpu)->vm_numa_stat_diff[item] + = 0; + } +} + +/* zero numa counters of all the populated zones */ +static void zero_zones_numa_counters(void) +{ + struct zone *zone; + + for_each_populated_zone(zone) + zero_zone_numa_counters(zone); +} + +/* zero global numa counters */ +static void zero_global_numa_counters(void) +{ + int item; + + for (item = 0; item < NR_VM_NUMA_STAT_ITEMS; item++) + atomic_long_set(&vm_numa_stat[item], 0); +} + +static void invalid_numa_statistics(void) +{ + zero_zones_numa_counters(); + zero_global_numa_counters(); +} + +static DEFINE_MUTEX(vm_numa_stat_lock); + +int sysctl_vm_numa_stat_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) +{ + int ret, oldval; + + mutex_lock(&vm_numa_stat_lock); + if (write) + oldval = sysctl_vm_numa_stat; + ret = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (ret || !write) + goto out; + + if (oldval == sysctl_vm_numa_stat) + goto out; + else if (sysctl_vm_numa_stat == ENABLE_NUMA_STAT) { + static_branch_enable(&vm_numa_stat_key); + pr_info("enable numa statistics\n"); + } else { + static_branch_disable(&vm_numa_stat_key); + invalid_numa_statistics(); + pr_info("disable numa statistics, and clear numa counters\n"); + } + +out: + mutex_unlock(&vm_numa_stat_lock); + return ret; +} +#endif + #ifdef CONFIG_VM_EVENT_COUNTERS DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}}; EXPORT_PER_CPU_SYMBOL(vm_event_states); -- cgit v1.3-8-gc7d7 From 98159d977f71c3b3dee898d1c34e56f520b094e7 Mon Sep 17 00:00:00 2001 From: Joe Lawrence Date: Fri, 17 Nov 2017 15:29:17 -0800 Subject: pipe: match pipe_max_size data type with procfs Patch series "A few round_pipe_size() and pipe-max-size fixups", v3. While backporting Michael's "pipe: fix limit handling" patchset to a distro-kernel, Mikulas noticed that current upstream pipe limit handling contains a few problems: 1 - procfs signed wrap: echo'ing a large number into /proc/sys/fs/pipe-max-size and then cat'ing it back out shows a negative value. 2 - round_pipe_size() nr_pages overflow on 32bit: this would subsequently try roundup_pow_of_two(0), which is undefined. 3 - visible non-rounded pipe-max-size value: there is no mutual exclusion or protection between the time pipe_max_size is assigned a raw value from proc_dointvec_minmax() and when it is rounded. 4 - unsigned long -> unsigned int conversion makes for potential odd return errors from do_proc_douintvec_minmax_conv() and do_proc_dopipe_max_size_conv(). This version underwent the same testing as v1: https://marc.info/?l=linux-kernel&m=150643571406022&w=2 This patch (of 4): pipe_max_size is defined as an unsigned int: unsigned int pipe_max_size = 1048576; but its procfs/sysctl representation is an integer: static struct ctl_table fs_table[] = { ... { .procname = "pipe-max-size", .data = &pipe_max_size, .maxlen = sizeof(int), .mode = 0644, .proc_handler = &pipe_proc_fn, .extra1 = &pipe_min_size, }, ... that is signed: int pipe_proc_fn(struct ctl_table *table, int write, void __user *buf, size_t *lenp, loff_t *ppos) { ... ret = proc_dointvec_minmax(table, write, buf, lenp, ppos) This leads to signed results via procfs for large values of pipe_max_size: % echo 2147483647 >/proc/sys/fs/pipe-max-size % cat /proc/sys/fs/pipe-max-size -2147483648 Use unsigned operations on this variable to avoid such negative values. Link: http://lkml.kernel.org/r/1507658689-11669-2-git-send-email-joe.lawrence@redhat.com Signed-off-by: Joe Lawrence Reported-by: Mikulas Patocka Reviewed-by: Mikulas Patocka Cc: Michael Kerrisk Cc: Randy Dunlap Cc: Al Viro Cc: Jens Axboe Cc: Josh Poimboeuf Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/pipe.c | 2 +- kernel/sysctl.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/fs/pipe.c b/fs/pipe.c index 349c9d56d4b3..3909c55ed389 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1125,7 +1125,7 @@ int pipe_proc_fn(struct ctl_table *table, int write, void __user *buf, { int ret; - ret = proc_dointvec_minmax(table, write, buf, lenp, ppos); + ret = proc_douintvec_minmax(table, write, buf, lenp, ppos); if (ret < 0 || !write) return ret; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 4a13a389e99b..2d42183b4c98 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1816,7 +1816,7 @@ static struct ctl_table fs_table[] = { { .procname = "pipe-max-size", .data = &pipe_max_size, - .maxlen = sizeof(int), + .maxlen = sizeof(pipe_max_size), .mode = 0644, .proc_handler = &pipe_proc_fn, .extra1 = &pipe_min_size, -- cgit v1.3-8-gc7d7 From 7a8d181949fb2c16be00f8cdb354794a30e46b39 Mon Sep 17 00:00:00 2001 From: Joe Lawrence Date: Fri, 17 Nov 2017 15:29:24 -0800 Subject: pipe: add proc_dopipe_max_size() to safely assign pipe_max_size pipe_max_size is assigned directly via procfs sysctl: static struct ctl_table fs_table[] = { ... { .procname = "pipe-max-size", .data = &pipe_max_size, .maxlen = sizeof(int), .mode = 0644, .proc_handler = &pipe_proc_fn, .extra1 = &pipe_min_size, }, ... int pipe_proc_fn(struct ctl_table *table, int write, void __user *buf, size_t *lenp, loff_t *ppos) { ... ret = proc_dointvec_minmax(table, write, buf, lenp, ppos) ... and then later rounded in-place a few statements later: ... pipe_max_size = round_pipe_size(pipe_max_size); ... This leaves a window of time between initial assignment and rounding that may be visible to other threads. (For example, one thread sets a non-rounded value to pipe_max_size while another reads its value.) Similar reads of pipe_max_size are potentially racy: pipe.c :: alloc_pipe_info() pipe.c :: pipe_set_size() Add a new proc_dopipe_max_size() that consolidates reading the new value from the user buffer, verifying bounds, and calling round_pipe_size() with a single assignment to pipe_max_size. Link: http://lkml.kernel.org/r/1507658689-11669-4-git-send-email-joe.lawrence@redhat.com Signed-off-by: Joe Lawrence Reported-by: Mikulas Patocka Reviewed-by: Mikulas Patocka Cc: Al Viro Cc: Jens Axboe Cc: Michael Kerrisk Cc: Randy Dunlap Cc: Josh Poimboeuf Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/pipe.c | 18 +++-------------- include/linux/pipe_fs_i.h | 1 + include/linux/sysctl.h | 3 +++ kernel/sysctl.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 56 insertions(+), 15 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/fs/pipe.c b/fs/pipe.c index f0f4ab36c444..6d98566201ef 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1020,7 +1020,7 @@ const struct file_operations pipefifo_fops = { * Currently we rely on the pipe array holding a power-of-2 number * of pages. Returns 0 on error. */ -static inline unsigned int round_pipe_size(unsigned int size) +unsigned int round_pipe_size(unsigned int size) { unsigned long nr_pages; @@ -1125,25 +1125,13 @@ out_revert_acct: } /* - * This should work even if CONFIG_PROC_FS isn't set, as proc_dointvec_minmax + * This should work even if CONFIG_PROC_FS isn't set, as proc_dopipe_max_size * will return an error. */ int pipe_proc_fn(struct ctl_table *table, int write, void __user *buf, size_t *lenp, loff_t *ppos) { - unsigned int rounded_pipe_max_size; - int ret; - - ret = proc_douintvec_minmax(table, write, buf, lenp, ppos); - if (ret < 0 || !write) - return ret; - - rounded_pipe_max_size = round_pipe_size(pipe_max_size); - if (rounded_pipe_max_size == 0) - return -EINVAL; - - pipe_max_size = rounded_pipe_max_size; - return ret; + return proc_dopipe_max_size(table, write, buf, lenp, ppos); } /* diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 6a80cfc63e0c..2dc5e9870fcd 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -191,5 +191,6 @@ long pipe_fcntl(struct file *, unsigned int, unsigned long arg); struct pipe_inode_info *get_pipe_info(struct file *file); int create_pipe_files(struct file **, int); +unsigned int round_pipe_size(unsigned int size); #endif diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index b769ecfcc3bd..992bc9948232 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -51,6 +51,9 @@ extern int proc_dointvec_minmax(struct ctl_table *, int, extern int proc_douintvec_minmax(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +extern int proc_dopipe_max_size(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); extern int proc_dointvec_jiffies(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 2d42183b4c98..138b6484f277 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -66,6 +66,7 @@ #include #include #include +#include #include #include @@ -2620,6 +2621,47 @@ int proc_douintvec_minmax(struct ctl_table *table, int write, do_proc_douintvec_minmax_conv, ¶m); } +struct do_proc_dopipe_max_size_conv_param { + unsigned int *min; +}; + +static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, + unsigned int *valp, + int write, void *data) +{ + struct do_proc_dopipe_max_size_conv_param *param = data; + + if (write) { + unsigned int val = round_pipe_size(*lvalp); + + if (val == 0) + return -EINVAL; + + if (param->min && *param->min > val) + return -ERANGE; + + if (*lvalp > UINT_MAX) + return -EINVAL; + + *valp = val; + } else { + unsigned int val = *valp; + *lvalp = (unsigned long) val; + } + + return 0; +} + +int proc_dopipe_max_size(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct do_proc_dopipe_max_size_conv_param param = { + .min = (unsigned int *) table->extra1, + }; + return do_proc_douintvec(table, write, buffer, lenp, ppos, + do_proc_dopipe_max_size_conv, ¶m); +} + static void validate_coredump_safety(void) { #ifdef CONFIG_COREDUMP @@ -3125,6 +3167,12 @@ int proc_douintvec_minmax(struct ctl_table *table, int write, return -ENOSYS; } +int proc_dopipe_max_size(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} + int proc_dointvec_jiffies(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -3168,6 +3216,7 @@ EXPORT_SYMBOL(proc_douintvec); EXPORT_SYMBOL(proc_dointvec_jiffies); EXPORT_SYMBOL(proc_dointvec_minmax); EXPORT_SYMBOL_GPL(proc_douintvec_minmax); +EXPORT_SYMBOL_GPL(proc_dopipe_max_size); EXPORT_SYMBOL(proc_dointvec_userhz_jiffies); EXPORT_SYMBOL(proc_dointvec_ms_jiffies); EXPORT_SYMBOL(proc_dostring); -- cgit v1.3-8-gc7d7 From fb910c42ccebf853c29296185c45c11164a56098 Mon Sep 17 00:00:00 2001 From: Joe Lawrence Date: Fri, 17 Nov 2017 15:29:28 -0800 Subject: sysctl: check for UINT_MAX before unsigned int min/max Mikulas noticed in the existing do_proc_douintvec_minmax_conv() and do_proc_dopipe_max_size_conv() introduced in this patchset, that they inconsistently handle overflow and min/max range inputs: For example: 0 ... param->min - 1 ---> ERANGE param->min ... param->max ---> the value is accepted param->max + 1 ... 0x100000000L + param->min - 1 ---> ERANGE 0x100000000L + param->min ... 0x100000000L + param->max ---> EINVAL 0x100000000L + param->max + 1, 0x200000000L + param->min - 1 ---> ERANGE 0x200000000L + param->min ... 0x200000000L + param->max ---> EINVAL 0x200000000L + param->max + 1, 0x300000000L + param->min - 1 ---> ERANGE In do_proc_do*() routines which store values into unsigned int variables (4 bytes wide for 64-bit builds), first validate that the input unsigned long value (8 bytes wide for 64-bit builds) will fit inside the smaller unsigned int variable. Then check that the unsigned int value falls inside the specified parameter min, max range. Otherwise the unsigned long -> unsigned int conversion drops leading bits from the input value, leading to the inconsistent pattern Mikulas documented above. Link: http://lkml.kernel.org/r/1507658689-11669-5-git-send-email-joe.lawrence@redhat.com Signed-off-by: Joe Lawrence Reported-by: Mikulas Patocka Reviewed-by: Mikulas Patocka Cc: Al Viro Cc: Jens Axboe Cc: Michael Kerrisk Cc: Randy Dunlap Cc: Josh Poimboeuf Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 138b6484f277..dd25d90896fc 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2576,12 +2576,13 @@ static int do_proc_douintvec_minmax_conv(unsigned long *lvalp, if (write) { unsigned int val = *lvalp; + if (*lvalp > UINT_MAX) + return -EINVAL; + if ((param->min && *param->min > val) || (param->max && *param->max < val)) return -ERANGE; - if (*lvalp > UINT_MAX) - return -EINVAL; *valp = val; } else { unsigned int val = *valp; @@ -2632,17 +2633,18 @@ static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, struct do_proc_dopipe_max_size_conv_param *param = data; if (write) { - unsigned int val = round_pipe_size(*lvalp); + unsigned int val; + if (*lvalp > UINT_MAX) + return -EINVAL; + + val = round_pipe_size(*lvalp); if (val == 0) return -EINVAL; if (param->min && *param->min > val) return -ERANGE; - if (*lvalp > UINT_MAX) - return -EINVAL; - *valp = val; } else { unsigned int val = *valp; -- cgit v1.3-8-gc7d7 From f9eb2fdd04d4e68fbea18970bbf65ace716d25b6 Mon Sep 17 00:00:00 2001 From: "Ola N. Kaldestad" Date: Fri, 17 Nov 2017 15:30:26 -0800 Subject: kernel/sysctl.c: code cleanups Remove unnecessary else block, remove redundant return and call to kfree in if block. Link: http://lkml.kernel.org/r/1510238435-1655-1-git-send-email-mail@okal.no Signed-off-by: Ola N. Kaldestad Acked-by: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sysctl.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'kernel/sysctl.c') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index dd25d90896fc..557d46728577 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -3127,14 +3127,12 @@ int proc_do_large_bitmap(struct ctl_table *table, int write, else bitmap_copy(bitmap, tmp_bitmap, bitmap_len); } - kfree(tmp_bitmap); *lenp -= left; *ppos += *lenp; - return 0; - } else { - kfree(tmp_bitmap); - return err; } + + kfree(tmp_bitmap); + return err; } #else /* CONFIG_PROC_SYSCTL */ -- cgit v1.3-8-gc7d7