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 <julien.thierry@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@kernel.org
Fixes: 5b24a7a2aa20 ("Add 'unsafe' user access functions for batched accesses")
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index fbbf1ba..b5c2b10 100644 (file)
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -648,6 +648,7 @@ ENTRY(__switch_to_asm)
        pushl   %ebx
        pushl   %edi
        pushl   %esi
+       pushfl
 
        /* switch stack */
        movl    %esp, TASK_threadsp(%eax)
@@ -670,6 +671,7 @@ 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 617df50..585bbc5 100644 (file)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -352,6 +352,7 @@ ENTRY(__switch_to_asm)
        pushq   %r13
        pushq   %r14
        pushq   %r15
+       pushfq
 
        /* switch stack */
        movq    %rsp, TASK_threadsp(%rdi)
@@ -374,6 +375,7 @@ 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 7cf1a27..157149d 100644 (file)
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -40,6 +40,7 @@ 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 d3e593e..020efe0 100644 (file)
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -130,6 +130,13 @@ 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 a0854f2..59f71d0 100644 (file)
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -300,6 +300,14 @@ 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;