x86: Check stack overflow in detail

Currently, only kernel stack is checked for the overflow, which
is not sufficient for systems that need a high reliability. To
enhance it, it is required to check the IRQ and exception
stacks, as well.

This patch checks all the stack types and will cause messages of
stacks in detail when free stack space drops below a certain
limit except user stack.

Signed-off-by: Mitsuo Hayasaka <mitsuo.hayasaka.hu@hitachi.com>
Cc: yrl.pp-manager.tt@hitachi.com
Cc: Randy Dunlap <rdunlap@xenotime.net>
Link: http://lkml.kernel.org/r/20111129060829.11076.51733.stgit@ltc219.sdl.hitachi.co.jp
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>

diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index bf56e1793272d70fdbf4be7b3911f87410e03f9b..4caec1261f12aea792d912922280396b10400c64 100644 (file)
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -63,8 +63,11 @@ config DEBUG_STACKOVERFLOW
        bool "Check for stack overflows"
        depends on DEBUG_KERNEL
        ---help---
-         This option will cause messages to be printed if free stack space
-         drops below a certain limit.
+         Say Y here if you want to check the overflows of kernel, IRQ
+         and exception stacks. This option will cause messages of the
+         stacks in detail when free stack space drops below a certain
+         limit.
+         If in doubt, say "N".
 
 config X86_PTDUMP
        bool "Export kernel pagetable layout to userspace via debugfs"

diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 69bca468c47a8ffc22ea5811cb3bdf63caf0f44b..928a7e909619c6966965ef2c0eedfb96b4b98c51 100644 (file)
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -36,18 +36,35 @@ EXPORT_PER_CPU_SYMBOL(irq_regs);
 static inline void stack_overflow_check(struct pt_regs *regs)
 {
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
+       struct orig_ist *oist;
+       u64 irq_stack_top, irq_stack_bottom;
+       u64 estack_top, estack_bottom;
        u64 curbase = (u64)task_stack_page(current);
 
        if (user_mode_vm(regs))
                return;
 
-       WARN_ONCE(regs->sp >= curbase &&
-                 regs->sp <= curbase + THREAD_SIZE &&
-                 regs->sp <  curbase + sizeof(struct thread_info) +
-                                       sizeof(struct pt_regs) + 128,
+       if (regs->sp >= curbase &&
+           regs->sp <= curbase + THREAD_SIZE &&
+           regs->sp >= curbase + sizeof(struct thread_info) +
+                                 sizeof(struct pt_regs) + 128)
+               return;
+
+       irq_stack_top = (u64)__get_cpu_var(irq_stack_union.irq_stack);
+       irq_stack_bottom = (u64)__get_cpu_var(irq_stack_ptr);
+       if (regs->sp >= irq_stack_top && regs->sp <= irq_stack_bottom)
+               return;
+
+       oist = &__get_cpu_var(orig_ist);
+       estack_top = (u64)oist->ist[0] - EXCEPTION_STKSZ;
+       estack_bottom = (u64)oist->ist[N_EXCEPTION_STACKS - 1];
+       if (regs->sp >= estack_top && regs->sp <= estack_bottom)
+               return;
 
-                 "do_IRQ: %s near stack overflow (cur:%Lx,sp:%lx)\n",
-                       current->comm, curbase, regs->sp);
+       WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx)\n",
+               current->comm, curbase, regs->sp,
+               irq_stack_top, irq_stack_bottom,
+               estack_top, estack_bottom);
 #endif
 }