From 15d8791cae75dca27bfda8ecfe87dca9379d6bb0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 16 Feb 2012 09:15:04 -0800 Subject: [PATCH] i387: fix x86-64 preemption-unsafe user stack save/restore Commit 5b1cbac37798 ("i387: make irq_fpu_usable() tests more robust") added a sanity check to the #NM handler to verify that we never cause the "Device Not Available" exception in kernel mode. However, that check actually pinpointed a (fundamental) race where we do cause that exception as part of the signal stack FPU state save/restore code. Because we use the floating point instructions themselves to save and restore state directly from user mode, we cannot do that atomically with testing the TS_USEDFPU bit: the user mode access itself may cause a page fault, which causes a task switch, which saves and restores the FP/MMX state from the kernel buffers. This kind of "recursive" FP state save is fine per se, but it means that when the signal stack save/restore gets restarted, it will now take the '#NM' exception we originally tried to avoid. With preemption this can happen even without the page fault - but because of the user access, we cannot just disable preemption around the save/restore instruction. There are various ways to solve this, including using the "enable/disable_page_fault()" helpers to not allow page faults at all during the sequence, and fall back to copying things by hand without the use of the native FP state save/restore instructions. However, the simplest thing to do is to just allow the #NM from kernel space, but fix the race in setting and clearing CR0.TS that this all exposed: the TS bit changes and the TS_USEDFPU bit absolutely have to be atomic wrt scheduling, so while the actual state save/restore can be interrupted and restarted, the act of actually clearing/setting CR0.TS and the TS_USEDFPU bit together must not. Instead of just adding random "preempt_disable/enable()" calls to what is already excessively ugly code, this introduces some helper functions that mostly mirror the "kernel_fpu_begin/end()" functionality, just for the user state instead. Those helper functions should probably eventually replace the other ad-hoc CR0.TS and TS_USEDFPU tests too, but I'll need to think about it some more: the task switching functionality in particular needs to expose the difference between the 'prev' and 'next' threads, while the new helper functions intentionally were written to only work with 'current'. Signed-off-by: Linus Torvalds --- arch/x86/include/asm/i387.h | 42 +++++++++++++++++++++++++++++++++++++ arch/x86/kernel/traps.c | 1 - arch/x86/kernel/xsave.c | 10 +++------ 3 files changed, 45 insertions(+), 8 deletions(-) diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index 727c1dd84899..f704be239883 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -399,6 +399,48 @@ static inline void irq_ts_restore(int TS_state) stts(); } +/* + * The question "does this thread have fpu access?" + * is slightly racy, since preemption could come in + * and revoke it immediately after the test. + * + * However, even in that very unlikely scenario, + * we can just assume we have FPU access - typically + * to save the FP state - we'll just take a #NM + * fault and get the FPU access back. + * + * The actual user_fpu_begin/end() functions + * need to be preemption-safe, though. + * + * NOTE! user_fpu_end() must be used only after you + * have saved the FP state, and user_fpu_begin() must + * be used only immediately before restoring it. + * These functions do not do any save/restore on + * their own. + */ +static inline int user_has_fpu(void) +{ + return current_thread_info()->status & TS_USEDFPU; +} + +static inline void user_fpu_end(void) +{ + preempt_disable(); + current_thread_info()->status &= ~TS_USEDFPU; + stts(); + preempt_enable(); +} + +static inline void user_fpu_begin(void) +{ + preempt_disable(); + if (!user_has_fpu()) { + clts(); + current_thread_info()->status |= TS_USEDFPU; + } + preempt_enable(); +} + /* * These disable preemption on their own and are safe */ diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 8ba27dbc107a..982433b5da30 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -631,7 +631,6 @@ EXPORT_SYMBOL_GPL(math_state_restore); dotraplinkage void __kprobes do_device_not_available(struct pt_regs *regs, long error_code) { - WARN_ON_ONCE(!user_mode_vm(regs)); #ifdef CONFIG_MATH_EMULATION if (read_cr0() & X86_CR0_EM) { struct math_emu_info info = { }; diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c index a3911343976b..86f1f09a738a 100644 --- a/arch/x86/kernel/xsave.c +++ b/arch/x86/kernel/xsave.c @@ -168,7 +168,7 @@ int save_i387_xstate(void __user *buf) if (!used_math()) return 0; - if (task_thread_info(tsk)->status & TS_USEDFPU) { + if (user_has_fpu()) { if (use_xsave()) err = xsave_user(buf); else @@ -176,8 +176,7 @@ int save_i387_xstate(void __user *buf) if (err) return err; - task_thread_info(tsk)->status &= ~TS_USEDFPU; - stts(); + user_fpu_end(); } else { sanitize_i387_state(tsk); if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave, @@ -292,10 +291,7 @@ int restore_i387_xstate(void __user *buf) return err; } - if (!(task_thread_info(current)->status & TS_USEDFPU)) { - clts(); - task_thread_info(current)->status |= TS_USEDFPU; - } + user_fpu_begin(); if (use_xsave()) err = restore_user_xstate(buf); else -- GitLab