From 5fa10196bdb5f190f595ebd048490ee52dddea0f Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Fri, 7 Mar 2014 15:05:20 -0800 Subject: x86: Ignore NMIs that come in during early boot Don Zickus reports: A customer generated an external NMI using their iLO to test kdump worked. Unfortunately, the machine hung. Disabling the nmi_watchdog made things work. I speculated the external NMI fired, caused the machine to panic (as expected) and the perf NMI from the watchdog came in and was latched. My guess was this somehow caused the hang. ---- It appears that the latched NMI stays latched until the early page table generation on 64 bits, which causes exceptions to happen which end in IRET, which re-enable NMI. Therefore, ignore NMIs that come in during early execution, until we have proper exception handling. Reported-and-tested-by: Don Zickus Link: http://lkml.kernel.org/r/1394221143-29713-1-git-send-email-dzickus@redhat.com Signed-off-by: H. Peter Anvin Cc: # v3.5+, older with some backport effort --- arch/x86/kernel/head_64.S | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'arch/x86/kernel/head_64.S') diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index e1aabdb314c8..33f36c78594e 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -343,6 +343,9 @@ early_idt_handlers: ENTRY(early_idt_handler) cld + cmpl $X86_TRAP_NMI,(%rsp) + je is_nmi # Ignore NMI + cmpl $2,early_recursion_flag(%rip) jz 1f incl early_recursion_flag(%rip) @@ -405,8 +408,9 @@ ENTRY(early_idt_handler) popq %rdx popq %rcx popq %rax - addq $16,%rsp # drop vector number and error code decl early_recursion_flag(%rip) +is_nmi: + addq $16,%rsp # drop vector number and error code INTERRUPT_RETURN ENDPROC(early_idt_handler) -- cgit v1.2.3 From b01d4e68933ec23e43b1046fa35d593cefcf37d1 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 7 Mar 2014 18:58:40 -0800 Subject: x86: fix compile error due to X86_TRAP_NMI use in asm files It's an enum, not a #define, you can't use it in asm files. Introduced in commit 5fa10196bdb5 ("x86: Ignore NMIs that come in during early boot"), and sadly I didn't compile-test things like I should have before pushing out. My weak excuse is that the x86 tree generally doesn't introduce stupid things like this (and the ARM pull afterwards doesn't cause me to do a compile-test either, since I don't cross-compile). Cc: Don Zickus Cc: H. Peter Anvin Signed-off-by: Linus Torvalds --- arch/x86/kernel/head_32.S | 2 +- arch/x86/kernel/head_64.S | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel/head_64.S') diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index d2a21590794a..f36bd42d6f0c 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -545,7 +545,7 @@ ENDPROC(early_idt_handlers) ENTRY(early_idt_handler) cld - cmpl $X86_TRAP_NMI,(%esp) + cmpl $2,(%esp) # X86_TRAP_NMI je is_nmi # Ignore NMI cmpl $2,%ss:early_recursion_flag diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 33f36c78594e..a468c0a65c42 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -343,7 +343,7 @@ early_idt_handlers: ENTRY(early_idt_handler) cld - cmpl $X86_TRAP_NMI,(%rsp) + cmpl $2,(%rsp) # X86_TRAP_NMI je is_nmi # Ignore NMI cmpl $2,early_recursion_flag(%rip) -- cgit v1.2.3