From 2373ac080fa336e04af2000506ad701a515ce527 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 14 Feb 2019 10:30:52 +0100 Subject: [PATCH] sched/x86: Save [ER]FLAGS on context switch commit 6690e86be83ac75832e461c141055b5d601c0a6d upstream. Effectively reverts commit: 2c7577a75837 ("sched/x86_64: Don't save flags on context switch") Specifically because SMAP uses FLAGS.AC which invalidates the claim that the kernel has clean flags. In particular; while preemption from interrupt return is fine (the IRET frame on the exception stack contains FLAGS) it breaks any code that does synchonous scheduling, including preempt_enable(). This has become a significant issue ever since commit: 5b24a7a2aa20 ("Add 'unsafe' user access functions for batched accesses") provided for means of having 'normal' C code between STAC / CLAC, exposing the FLAGS.AC state. So far this hasn't led to trouble, however fix it before it comes apart. Reported-by: Julien Thierry Signed-off-by: Peter Zijlstra (Intel) Acked-by: Andy Lutomirski Cc: Borislav Petkov Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: stable@kernel.org Fixes: 5b24a7a2aa20 ("Add 'unsafe' user access functions for batched accesses") Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- arch/x86/entry/entry_32.S | 2 ++ arch/x86/entry/entry_64.S | 2 ++ arch/x86/include/asm/switch_to.h | 1 + arch/x86/kernel/process_32.c | 7 +++++++ arch/x86/kernel/process_64.c | 8 ++++++++ 5 files changed, 20 insertions(+) diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 60c4c342316c..49adabd94f88 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -234,6 +234,7 @@ ENTRY(__switch_to_asm) pushl %ebx pushl %edi pushl %esi + pushfl /* switch stack */ movl %esp, TASK_threadsp(%eax) @@ -256,6 +257,7 @@ ENTRY(__switch_to_asm) #endif /* restore callee-saved registers */ + popfl popl %esi popl %edi popl %ebx diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 164cd7529f0b..09896f1c114f 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -342,6 +342,7 @@ ENTRY(__switch_to_asm) pushq %r13 pushq %r14 pushq %r15 + pushfq /* switch stack */ movq %rsp, TASK_threadsp(%rdi) @@ -364,6 +365,7 @@ ENTRY(__switch_to_asm) #endif /* restore callee-saved registers */ + popfq popq %r15 popq %r14 popq %r13 diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 12ef2b49d11b..6a7e83092811 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -41,6 +41,7 @@ asmlinkage void ret_from_fork(void); * order of the fields must match the code in __switch_to_asm(). */ struct inactive_task_frame { + unsigned long flags; #ifdef CONFIG_X86_64 unsigned long r15; unsigned long r14; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index c2df91eab573..df6bb5f8ab2a 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -132,6 +132,13 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, struct task_struct *tsk; int err; + /* + * For a new task use the RESET flags value since there is no before. + * All the status flags are zero; DF and all the system flags must also + * be 0, specifically IF must be 0 because we context switch to the new + * task with interrupts disabled. + */ + frame->flags = X86_EFLAGS_FIXED; frame->bp = 0; frame->ret_addr = (unsigned long) ret_from_fork; p->thread.sp = (unsigned long) fork_frame; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index ec63d6be5e02..d1dfd1397b46 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -278,6 +278,14 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, childregs = task_pt_regs(p); fork_frame = container_of(childregs, struct fork_frame, regs); frame = &fork_frame->frame; + + /* + * For a new task use the RESET flags value since there is no before. + * All the status flags are zero; DF and all the system flags must also + * be 0, specifically IF must be 0 because we context switch to the new + * task with interrupts disabled. + */ + frame->flags = X86_EFLAGS_FIXED; frame->bp = 0; frame->ret_addr = (unsigned long) ret_from_fork; p->thread.sp = (unsigned long) fork_frame; -- 2.20.1