[tip:x86/fpu] x86/fpu: Handle #NM without FPU emulation as an error

[tip-bot for Andy Lutomirski]

Commit-ID:  bef8b6da95229f780a0a7f63e23124058bfad6d3
Gitweb: http://git.kernel.org/tip/bef8b6da95229f780a0a7f63e23124058bfad6d3
Author: Andy Lutomirski 
AuthorDate: Mon, 31 Oct 2016 15:18:47 -0700
Committer:  Ingo Molnar 
CommitDate: Tue, 1 Nov 2016 07:47:54 +0100

x86/fpu: Handle #NM without FPU emulation as an error

Don't use CR0.TS.  Make it an error rather than making nonsensical
changes to the FPU state.

(The cond_local_irq_enable() appears to have been pointless, too.)

Signed-off-by: Andy Lutomirski 
Cc: Borislav Petkov 
Cc: Brian Gerst 
Cc: Dave Hansen 
Cc: Denys Vlasenko 
Cc: Fenghua Yu 
Cc: H. Peter Anvin 
Cc: Josh Poimboeuf 
Cc: Linus Torvalds 
Cc: Oleg Nesterov 
Cc: Paolo Bonzini 
Cc: Peter Zijlstra 
Cc: Quentin Casasnovas 
Cc: Rik van Riel 
Cc: Rusty Russell 
Cc: Thomas Gleixner 
Cc: kvm list 
Link: 
http://lkml.kernel.org/r/f1ee6bf73ed1025fccaab321ba43d0594245f927.1477951965.git.l...@kernel.org
Signed-off-by: Ingo Molnar 
---
 arch/x86/kernel/traps.c | 20 
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index bd4e3d4..bf0c6d0 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -853,6 +853,8 @@ do_spurious_interrupt_bug(struct pt_regs *regs, long 
error_code)
 dotraplinkage void
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
+   unsigned long cr0;
+
RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 
 #ifdef CONFIG_MATH_EMULATION
@@ -866,10 +868,20 @@ do_device_not_available(struct pt_regs *regs, long 
error_code)
return;
}
 #endif
-   fpu__restore(>thread.fpu); /* interrupts still off */
-#ifdef CONFIG_X86_32
-   cond_local_irq_enable(regs);
-#endif
+
+   /* This should not happen. */
+   cr0 = read_cr0();
+   if (WARN(cr0 & X86_CR0_TS, "CR0.TS was set")) {
+   /* Try to fix it up and carry on. */
+   write_cr0(cr0 & ~X86_CR0_TS);
+   } else {
+   /*
+* Something terrible happened, and we're better off trying
+* to kill the task than getting stuck in a never-ending
+* loop of #NM faults.
+*/
+   die("unexpected #NM exception", regs, error_code);
+   }
 }
 NOKPROBE_SYMBOL(do_device_not_available);
 

[tip:x86/fpu] x86/fpu: Handle #NM without FPU emulation as an error

[tip-bot for Andy Lutomirski]

Commit-ID:  bef8b6da95229f780a0a7f63e23124058bfad6d3
Gitweb: http://git.kernel.org/tip/bef8b6da95229f780a0a7f63e23124058bfad6d3
Author: Andy Lutomirski 
AuthorDate: Mon, 31 Oct 2016 15:18:47 -0700
Committer:  Ingo Molnar 
CommitDate: Tue, 1 Nov 2016 07:47:54 +0100

x86/fpu: Handle #NM without FPU emulation as an error

Don't use CR0.TS.  Make it an error rather than making nonsensical
changes to the FPU state.

(The cond_local_irq_enable() appears to have been pointless, too.)

Signed-off-by: Andy Lutomirski 
Cc: Borislav Petkov 
Cc: Brian Gerst 
Cc: Dave Hansen 
Cc: Denys Vlasenko 
Cc: Fenghua Yu 
Cc: H. Peter Anvin 
Cc: Josh Poimboeuf 
Cc: Linus Torvalds 
Cc: Oleg Nesterov 
Cc: Paolo Bonzini 
Cc: Peter Zijlstra 
Cc: Quentin Casasnovas 
Cc: Rik van Riel 
Cc: Rusty Russell 
Cc: Thomas Gleixner 
Cc: kvm list 
Link: 
http://lkml.kernel.org/r/f1ee6bf73ed1025fccaab321ba43d0594245f927.1477951965.git.l...@kernel.org
Signed-off-by: Ingo Molnar 
---
 arch/x86/kernel/traps.c | 20 
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index bd4e3d4..bf0c6d0 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -853,6 +853,8 @@ do_spurious_interrupt_bug(struct pt_regs *regs, long 
error_code)
 dotraplinkage void
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
+   unsigned long cr0;
+
RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
 
 #ifdef CONFIG_MATH_EMULATION
@@ -866,10 +868,20 @@ do_device_not_available(struct pt_regs *regs, long 
error_code)
return;
}
 #endif
-   fpu__restore(>thread.fpu); /* interrupts still off */
-#ifdef CONFIG_X86_32
-   cond_local_irq_enable(regs);
-#endif
+
+   /* This should not happen. */
+   cr0 = read_cr0();
+   if (WARN(cr0 & X86_CR0_TS, "CR0.TS was set")) {
+   /* Try to fix it up and carry on. */
+   write_cr0(cr0 & ~X86_CR0_TS);
+   } else {
+   /*
+* Something terrible happened, and we're better off trying
+* to kill the task than getting stuck in a never-ending
+* loop of #NM faults.
+*/
+   die("unexpected #NM exception", regs, error_code);
+   }
 }
 NOKPROBE_SYMBOL(do_device_not_available);