--- /dev/null
+From 9d05041679904b12c12421cbcf9cb5f4860a8d7b Mon Sep 17 00:00:00 2001
+From: Andy Lutomirski <luto@kernel.org>
+Date: Wed, 15 Jul 2015 10:29:33 -0700
+Subject: x86/nmi: Enable nested do_nmi() handling for 64-bit kernels
+
+From: Andy Lutomirski <luto@kernel.org>
+
+commit 9d05041679904b12c12421cbcf9cb5f4860a8d7b upstream.
+
+32-bit kernels handle nested NMIs in C. Enable the exact same
+handling on 64-bit kernels as well. This isn't currently
+necessary, but it will become necessary once the asm code starts
+allowing limited nesting.
+
+Signed-off-by: Andy Lutomirski <luto@kernel.org>
+Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
+Cc: Borislav Petkov <bp@suse.de>
+Cc: Linus Torvalds <torvalds@linux-foundation.org>
+Cc: Peter Zijlstra <peterz@infradead.org>
+Cc: Thomas Gleixner <tglx@linutronix.de>
+Cc: stable@vger.kernel.org
+Signed-off-by: Ingo Molnar <mingo@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+
+---
+ arch/x86/kernel/nmi.c | 125 +++++++++++++++++++++-----------------------------
+ 1 file changed, 53 insertions(+), 72 deletions(-)
+
+--- a/arch/x86/kernel/nmi.c
++++ b/arch/x86/kernel/nmi.c
+@@ -392,15 +392,15 @@ static __kprobes void default_do_nmi(str
+ }
+
+ /*
+- * NMIs can hit breakpoints which will cause it to lose its
+- * NMI context with the CPU when the breakpoint does an iret.
+- */
+-#ifdef CONFIG_X86_32
+-/*
+- * For i386, NMIs use the same stack as the kernel, and we can
+- * add a workaround to the iret problem in C (preventing nested
+- * NMIs if an NMI takes a trap). Simply have 3 states the NMI
+- * can be in:
++ * NMIs can hit breakpoints which will cause it to lose its NMI context
++ * with the CPU when the breakpoint or page fault does an IRET.
++ *
++ * As a result, NMIs can nest if NMIs get unmasked due an IRET during
++ * NMI processing. On x86_64, the asm glue protects us from nested NMIs
++ * if the outer NMI came from kernel mode, but we can still nest if the
++ * outer NMI came from user mode.
++ *
++ * To handle these nested NMIs, we have three states:
+ *
+ * 1) not running
+ * 2) executing
+@@ -414,15 +414,14 @@ static __kprobes void default_do_nmi(str
+ * (Note, the latch is binary, thus multiple NMIs triggering,
+ * when one is running, are ignored. Only one NMI is restarted.)
+ *
+- * If an NMI hits a breakpoint that executes an iret, another
+- * NMI can preempt it. We do not want to allow this new NMI
+- * to run, but we want to execute it when the first one finishes.
+- * We set the state to "latched", and the exit of the first NMI will
+- * perform a dec_return, if the result is zero (NOT_RUNNING), then
+- * it will simply exit the NMI handler. If not, the dec_return
+- * would have set the state to NMI_EXECUTING (what we want it to
+- * be when we are running). In this case, we simply jump back
+- * to rerun the NMI handler again, and restart the 'latched' NMI.
++ * If an NMI executes an iret, another NMI can preempt it. We do not
++ * want to allow this new NMI to run, but we want to execute it when the
++ * first one finishes. We set the state to "latched", and the exit of
++ * the first NMI will perform a dec_return, if the result is zero
++ * (NOT_RUNNING), then it will simply exit the NMI handler. If not, the
++ * dec_return would have set the state to NMI_EXECUTING (what we want it
++ * to be when we are running). In this case, we simply jump back to
++ * rerun the NMI handler again, and restart the 'latched' NMI.
+ *
+ * No trap (breakpoint or page fault) should be hit before nmi_restart,
+ * thus there is no race between the first check of state for NOT_RUNNING
+@@ -445,49 +444,36 @@ enum nmi_states {
+ static DEFINE_PER_CPU(enum nmi_states, nmi_state);
+ static DEFINE_PER_CPU(unsigned long, nmi_cr2);
+
+-#define nmi_nesting_preprocess(regs) \
+- do { \
+- if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) { \
+- this_cpu_write(nmi_state, NMI_LATCHED); \
+- return; \
+- } \
+- this_cpu_write(nmi_state, NMI_EXECUTING); \
+- this_cpu_write(nmi_cr2, read_cr2()); \
+- } while (0); \
+- nmi_restart:
+-
+-#define nmi_nesting_postprocess() \
+- do { \
+- if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) \
+- write_cr2(this_cpu_read(nmi_cr2)); \
+- if (this_cpu_dec_return(nmi_state)) \
+- goto nmi_restart; \
+- } while (0)
+-#else /* x86_64 */
++#ifdef CONFIG_X86_64
+ /*
+- * In x86_64 things are a bit more difficult. This has the same problem
+- * where an NMI hitting a breakpoint that calls iret will remove the
+- * NMI context, allowing a nested NMI to enter. What makes this more
+- * difficult is that both NMIs and breakpoints have their own stack.
+- * When a new NMI or breakpoint is executed, the stack is set to a fixed
+- * point. If an NMI is nested, it will have its stack set at that same
+- * fixed address that the first NMI had, and will start corrupting the
+- * stack. This is handled in entry_64.S, but the same problem exists with
+- * the breakpoint stack.
+- *
+- * If a breakpoint is being processed, and the debug stack is being used,
+- * if an NMI comes in and also hits a breakpoint, the stack pointer
+- * will be set to the same fixed address as the breakpoint that was
+- * interrupted, causing that stack to be corrupted. To handle this case,
+- * check if the stack that was interrupted is the debug stack, and if
+- * so, change the IDT so that new breakpoints will use the current stack
+- * and not switch to the fixed address. On return of the NMI, switch back
+- * to the original IDT.
++ * In x86_64, we need to handle breakpoint -> NMI -> breakpoint. Without
++ * some care, the inner breakpoint will clobber the outer breakpoint's
++ * stack.
++ *
++ * If a breakpoint is being processed, and the debug stack is being
++ * used, if an NMI comes in and also hits a breakpoint, the stack
++ * pointer will be set to the same fixed address as the breakpoint that
++ * was interrupted, causing that stack to be corrupted. To handle this
++ * case, check if the stack that was interrupted is the debug stack, and
++ * if so, change the IDT so that new breakpoints will use the current
++ * stack and not switch to the fixed address. On return of the NMI,
++ * switch back to the original IDT.
+ */
+ static DEFINE_PER_CPU(int, update_debug_stack);
++#endif
+
+-static inline void nmi_nesting_preprocess(struct pt_regs *regs)
++dotraplinkage notrace void
++do_nmi(struct pt_regs *regs, long error_code)
+ {
++ if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) {
++ this_cpu_write(nmi_state, NMI_LATCHED);
++ return;
++ }
++ this_cpu_write(nmi_state, NMI_EXECUTING);
++ this_cpu_write(nmi_cr2, read_cr2());
++nmi_restart:
++
++#ifdef CONFIG_X86_64
+ /*
+ * If we interrupted a breakpoint, it is possible that
+ * the nmi handler will have breakpoints too. We need to
+@@ -498,22 +484,8 @@ static inline void nmi_nesting_preproces
+ debug_stack_set_zero();
+ this_cpu_write(update_debug_stack, 1);
+ }
+-}
+-
+-static inline void nmi_nesting_postprocess(void)
+-{
+- if (unlikely(this_cpu_read(update_debug_stack))) {
+- debug_stack_reset();
+- this_cpu_write(update_debug_stack, 0);
+- }
+-}
+ #endif
+
+-dotraplinkage notrace __kprobes void
+-do_nmi(struct pt_regs *regs, long error_code)
+-{
+- nmi_nesting_preprocess(regs);
+-
+ nmi_enter();
+
+ inc_irq_stat(__nmi_count);
+@@ -523,8 +495,17 @@ do_nmi(struct pt_regs *regs, long error_
+
+ nmi_exit();
+
+- /* On i386, may loop back to preprocess */
+- nmi_nesting_postprocess();
++#ifdef CONFIG_X86_64
++ if (unlikely(this_cpu_read(update_debug_stack))) {
++ debug_stack_reset();
++ this_cpu_write(update_debug_stack, 0);
++ }
++#endif
++
++ if (unlikely(this_cpu_read(nmi_cr2) != read_cr2()))
++ write_cr2(this_cpu_read(nmi_cr2));
++ if (this_cpu_dec_return(nmi_state))
++ goto nmi_restart;
+ }
+
+ void stop_nmi(void)
projects / thirdparty / kernel / stable-queue.git / commitdiff
