From d7822b1e24f2df5df98c76f0e94a5416349ff759 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Sat, 2 Jun 2018 08:43:54 -0400 Subject: rseq: Introduce restartable sequences system call Expose a new system call allowing each thread to register one userspace memory area to be used as an ABI between kernel and user-space for two purposes: user-space restartable sequences and quick access to read the current CPU number value from user-space. * Restartable sequences (per-cpu atomics) Restartables sequences allow user-space to perform update operations on per-cpu data without requiring heavy-weight atomic operations. The restartable critical sections (percpu atomics) work has been started by Paul Turner and Andrew Hunter. It lets the kernel handle restart of critical sections. [1] [2] The re-implementation proposed here brings a few simplifications to the ABI which facilitates porting to other architectures and speeds up the user-space fast path. Here are benchmarks of various rseq use-cases. Test hardware: arm32: ARMv7 Processor rev 4 (v7l) "Cubietruck", 2-core x86-64: Intel E5-2630 v3@2.40GHz, 16-core, hyperthreading The following benchmarks were all performed on a single thread. * Per-CPU statistic counter increment getcpu+atomic (ns/op) rseq (ns/op) speedup arm32: 344.0 31.4 11.0 x86-64: 15.3 2.0 7.7 * LTTng-UST: write event 32-bit header, 32-bit payload into tracer per-cpu buffer getcpu+atomic (ns/op) rseq (ns/op) speedup arm32: 2502.0 2250.0 1.1 x86-64: 117.4 98.0 1.2 * liburcu percpu: lock-unlock pair, dereference, read/compare word getcpu+atomic (ns/op) rseq (ns/op) speedup arm32: 751.0 128.5 5.8 x86-64: 53.4 28.6 1.9 * jemalloc memory allocator adapted to use rseq Using rseq with per-cpu memory pools in jemalloc at Facebook (based on rseq 2016 implementation): The production workload response-time has 1-2% gain avg. latency, and the P99 overall latency drops by 2-3%. * Reading the current CPU number Speeding up reading the current CPU number on which the caller thread is running is done by keeping the current CPU number up do date within the cpu_id field of the memory area registered by the thread. This is done by making scheduler preemption set the TIF_NOTIFY_RESUME flag on the current thread. Upon return to user-space, a notify-resume handler updates the current CPU value within the registered user-space memory area. User-space can then read the current CPU number directly from memory. Keeping the current cpu id in a memory area shared between kernel and user-space is an improvement over current mechanisms available to read the current CPU number, which has the following benefits over alternative approaches: - 35x speedup on ARM vs system call through glibc - 20x speedup on x86 compared to calling glibc, which calls vdso executing a "lsl" instruction, - 14x speedup on x86 compared to inlined "lsl" instruction, - Unlike vdso approaches, this cpu_id value can be read from an inline assembly, which makes it a useful building block for restartable sequences. - The approach of reading the cpu id through memory mapping shared between kernel and user-space is portable (e.g. ARM), which is not the case for the lsl-based x86 vdso. On x86, yet another possible approach would be to use the gs segment selector to point to user-space per-cpu data. This approach performs similarly to the cpu id cache, but it has two disadvantages: it is not portable, and it is incompatible with existing applications already using the gs segment selector for other purposes. Benchmarking various approaches for reading the current CPU number: ARMv7 Processor rev 4 (v7l) Machine model: Cubietruck - Baseline (empty loop): 8.4 ns - Read CPU from rseq cpu_id: 16.7 ns - Read CPU from rseq cpu_id (lazy register): 19.8 ns - glibc 2.19-0ubuntu6.6 getcpu: 301.8 ns - getcpu system call: 234.9 ns x86-64 Intel(R) Xeon(R) CPU E5-2630 v3 @ 2.40GHz: - Baseline (empty loop): 0.8 ns - Read CPU from rseq cpu_id: 0.8 ns - Read CPU from rseq cpu_id (lazy register): 0.8 ns - Read using gs segment selector: 0.8 ns - "lsl" inline assembly: 13.0 ns - glibc 2.19-0ubuntu6 getcpu: 16.6 ns - getcpu system call: 53.9 ns - Speed (benchmark taken on v8 of patchset) Running 10 runs of hackbench -l 100000 seems to indicate, contrary to expectations, that enabling CONFIG_RSEQ slightly accelerates the scheduler: Configuration: 2 sockets * 8-core Intel(R) Xeon(R) CPU E5-2630 v3 @ 2.40GHz (directly on hardware, hyperthreading disabled in BIOS, energy saving disabled in BIOS, turboboost disabled in BIOS, cpuidle.off=1 kernel parameter), with a Linux v4.6 defconfig+localyesconfig, restartable sequences series applied. * CONFIG_RSEQ=n avg.: 41.37 s std.dev.: 0.36 s * CONFIG_RSEQ=y avg.: 40.46 s std.dev.: 0.33 s - Size On x86-64, between CONFIG_RSEQ=n/y, the text size increase of vmlinux is 567 bytes, and the data size increase of vmlinux is 5696 bytes. [1] https://lwn.net/Articles/650333/ [2] http://www.linuxplumbersconf.org/2013/ocw/system/presentations/1695/original/LPC%20-%20PerCpu%20Atomics.pdf Signed-off-by: Mathieu Desnoyers Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Cc: Joel Fernandes Cc: Catalin Marinas Cc: Dave Watson Cc: Will Deacon Cc: Andi Kleen Cc: "H . Peter Anvin" Cc: Chris Lameter Cc: Russell King Cc: Andrew Hunter Cc: Michael Kerrisk Cc: "Paul E . McKenney" Cc: Paul Turner Cc: Boqun Feng Cc: Josh Triplett Cc: Steven Rostedt Cc: Ben Maurer Cc: Alexander Viro Cc: linux-api@vger.kernel.org Cc: Andy Lutomirski Cc: Andrew Morton Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20151027235635.16059.11630.stgit@pjt-glaptop.roam.corp.google.com Link: http://lkml.kernel.org/r/20150624222609.6116.86035.stgit@kitami.mtv.corp.google.com Link: https://lkml.kernel.org/r/20180602124408.8430-3-mathieu.desnoyers@efficios.com --- kernel/fork.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index a5d21c42acfc..70992bfeba81 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1899,6 +1899,8 @@ static __latent_entropy struct task_struct *copy_process( */ copy_seccomp(p); + rseq_fork(p, clone_flags); + /* * Process group and session signals need to be delivered to just the * parent before the fork or both the parent and the child after the -- cgit v1.2.3 From 050e9baa9dc9fbd9ce2b27f0056990fc9e0a08a0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 14 Jun 2018 12:21:18 +0900 Subject: Kbuild: rename CC_STACKPROTECTOR[_STRONG] config variables The changes to automatically test for working stack protector compiler support in the Kconfig files removed the special STACKPROTECTOR_AUTO option that picked the strongest stack protector that the compiler supported. That was all a nice cleanup - it makes no sense to have the AUTO case now that the Kconfig phase can just determine the compiler support directly. HOWEVER. It also meant that doing "make oldconfig" would now _disable_ the strong stackprotector if you had AUTO enabled, because in a legacy config file, the sane stack protector configuration would look like CONFIG_HAVE_CC_STACKPROTECTOR=y # CONFIG_CC_STACKPROTECTOR_NONE is not set # CONFIG_CC_STACKPROTECTOR_REGULAR is not set # CONFIG_CC_STACKPROTECTOR_STRONG is not set CONFIG_CC_STACKPROTECTOR_AUTO=y and when you ran this through "make oldconfig" with the Kbuild changes, it would ask you about the regular CONFIG_CC_STACKPROTECTOR (that had been renamed from CONFIG_CC_STACKPROTECTOR_REGULAR to just CONFIG_CC_STACKPROTECTOR), but it would think that the STRONG version used to be disabled (because it was really enabled by AUTO), and would disable it in the new config, resulting in: CONFIG_HAVE_CC_STACKPROTECTOR=y CONFIG_CC_HAS_STACKPROTECTOR_NONE=y CONFIG_CC_STACKPROTECTOR=y # CONFIG_CC_STACKPROTECTOR_STRONG is not set CONFIG_CC_HAS_SANE_STACKPROTECTOR=y That's dangerously subtle - people could suddenly find themselves with the weaker stack protector setup without even realizing. The solution here is to just rename not just the old RECULAR stack protector option, but also the strong one. This does that by just removing the CC_ prefix entirely for the user choices, because it really is not about the compiler support (the compiler support now instead automatially impacts _visibility_ of the options to users). This results in "make oldconfig" actually asking the user for their choice, so that we don't have any silent subtle security model changes. The end result would generally look like this: CONFIG_HAVE_CC_STACKPROTECTOR=y CONFIG_CC_HAS_STACKPROTECTOR_NONE=y CONFIG_STACKPROTECTOR=y CONFIG_STACKPROTECTOR_STRONG=y CONFIG_CC_HAS_SANE_STACKPROTECTOR=y where the "CC_" versions really are about internal compiler infrastructure, not the user selections. Acked-by: Masahiro Yamada Signed-off-by: Linus Torvalds --- kernel/fork.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 08c6e5e217a0..92870be50bba 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -811,7 +811,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) clear_tsk_need_resched(tsk); set_task_stack_end_magic(tsk); -#ifdef CONFIG_CC_STACKPROTECTOR +#ifdef CONFIG_STACKPROTECTOR tsk->stack_canary = get_random_canary(); #endif -- cgit v1.2.3 From 655c79bb40a0870adcd0871057d01de11625882b Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Thu, 14 Jun 2018 15:26:34 -0700 Subject: mm: check for SIGKILL inside dup_mmap() loop As a theoretical problem, dup_mmap() of an mm_struct with 60000+ vmas can loop while potentially allocating memory, with mm->mmap_sem held for write by current thread. This is bad if current thread was selected as an OOM victim, for current thread will continue allocations using memory reserves while OOM reaper is unable to reclaim memory. As an actually observable problem, it is not difficult to make OOM reaper unable to reclaim memory if the OOM victim is blocked at i_mmap_lock_write() in this loop. Unfortunately, since nobody can explain whether it is safe to use killable wait there, let's check for SIGKILL before trying to allocate memory. Even without an OOM event, there is no point with continuing the loop from the beginning if current thread is killed. I tested with debug printk(). This patch should be safe because we already fail if security_vm_enough_memory_mm() or kmem_cache_alloc(GFP_KERNEL) fails and exit_mmap() handles it. ***** Aborting dup_mmap() due to SIGKILL ***** ***** Aborting dup_mmap() due to SIGKILL ***** ***** Aborting dup_mmap() due to SIGKILL ***** ***** Aborting dup_mmap() due to SIGKILL ***** ***** Aborting exit_mmap() due to NULL mmap ***** [akpm@linux-foundation.org: add comment] Link: http://lkml.kernel.org/r/201804071938.CDE04681.SOFVQJFtMHOOLF@I-love.SAKURA.ne.jp Signed-off-by: Tetsuo Handa Cc: Alexander Viro Cc: Rik van Riel Cc: Michal Hocko Cc: Kirill A. Shutemov Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 92870be50bba..9440d61b925c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -440,6 +440,14 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, continue; } charge = 0; + /* + * Don't duplicate many vmas if we've been oom-killed (for + * example) + */ + if (fatal_signal_pending(current)) { + retval = -EINTR; + goto out; + } if (mpnt->vm_flags & VM_ACCOUNT) { unsigned long len = vma_pages(mpnt); -- cgit v1.2.3