From patchwork Thu Dec 13 13:58:39 2012 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [154/241] x86, fpu: Avoid FPU lazy restore after suspend Date: Thu, 13 Dec 2012 03:58:39 -0000 From: Herton Ronaldo Krzesinski X-Patchwork-Id: 206001 Message-Id: <1355407206-17100-155-git-send-email-herton.krzesinski@canonical.com> To: linux-kernel@vger.kernel.org, stable@vger.kernel.org, kernel-team@lists.ubuntu.com Cc: Olof Johansson , "H. Peter Anvin" , Vincent Palatin , Duncan Laurie 3.5.7.2 -stable review patch. If anyone has any objections, please let me know. ------------------ From: Vincent Palatin commit 644c154186386bb1fa6446bc5e037b9ed098db46 upstream. When a cpu enters S3 state, the FPU state is lost. After resuming for S3, if we try to lazy restore the FPU for a process running on the same CPU, this will result in a corrupted FPU context. Ensure that "fpu_owner_task" is properly invalided when (re-)initializing a CPU, so nobody will try to lazy restore a state which doesn't exist in the hardware. Tested with a 64-bit kernel on a 4-core Ivybridge CPU with eagerfpu=off, by doing thousands of suspend/resume cycles with 4 processes doing FPU operations running. Without the patch, a process is killed after a few hundreds cycles by a SIGFPE. Cc: Duncan Laurie Cc: Olof Johansson Signed-off-by: Vincent Palatin Link: http://lkml.kernel.org/r/1354306532-1014-1-git-send-email-vpalatin@chromium.org Signed-off-by: H. Peter Anvin Signed-off-by: Herton Ronaldo Krzesinski --- arch/x86/include/asm/fpu-internal.h | 15 +++++++++------ arch/x86/kernel/smpboot.c | 5 +++++ 2 files changed, 14 insertions(+), 6 deletions(-) diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h index 75f4c6d..04cb0f8 100644 --- a/arch/x86/include/asm/fpu-internal.h +++ b/arch/x86/include/asm/fpu-internal.h @@ -334,14 +334,17 @@ static inline void __thread_fpu_begin(struct task_struct *tsk) typedef struct { int preload; } fpu_switch_t; /* - * FIXME! We could do a totally lazy restore, but we need to - * add a per-cpu "this was the task that last touched the FPU - * on this CPU" variable, and the task needs to have a "I last - * touched the FPU on this CPU" and check them. + * Must be run with preemption disabled: this clears the fpu_owner_task, + * on this CPU. * - * We don't do that yet, so "fpu_lazy_restore()" always returns - * false, but some day.. + * This will disable any lazy FPU state restore of the current FPU state, + * but if the current thread owns the FPU, it will still be saved by. */ +static inline void __cpu_disable_lazy_restore(unsigned int cpu) +{ + per_cpu(fpu_owner_task, cpu) = NULL; +} + static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu) { return new == this_cpu_read_stable(fpu_owner_task) && diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 7bd8a08..6977453 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -66,6 +66,8 @@ #include #include #include +#include +#include #include #include #include @@ -826,6 +828,9 @@ int __cpuinit native_cpu_up(unsigned int cpu, struct task_struct *tidle) per_cpu(cpu_state, cpu) = CPU_UP_PREPARE; + /* the FPU context is blank, nobody can own it */ + __cpu_disable_lazy_restore(cpu); + err = do_boot_cpu(apicid, cpu, tidle); if (err) { pr_debug("do_boot_cpu failed %d\n", err);