Merge branch 'master' of /home/trondmy/kernel/linux-2.6/

[linux-2.6-omap-h63xx.git] / arch / x86_64 / mm / fault.c

diff --git a/arch/x86_64/mm/fault.c b/arch/x86_64/mm/fault.c
index de91e17daf6f21e5f6893e73f862324d00f5bcd2..5afcf6eb00fab9fb0627b177c514be964161639b 100644 (file)
--- a/arch/x86_64/mm/fault.c
+++ b/arch/x86_64/mm/fault.c
@@ -5,7 +5,6 @@
  *  Copyright (C) 2001,2002 Andi Kleen, SuSE Labs.
  */
 
-#include <linux/config.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
@@ -41,6 +40,41 @@
 #define PF_RSVD        (1<<3)
 #define PF_INSTR       (1<<4)
 
+#ifdef CONFIG_KPROBES
+ATOMIC_NOTIFIER_HEAD(notify_page_fault_chain);
+
+/* Hook to register for page fault notifications */
+int register_page_fault_notifier(struct notifier_block *nb)
+{
+       vmalloc_sync_all();
+       return atomic_notifier_chain_register(&notify_page_fault_chain, nb);
+}
+
+int unregister_page_fault_notifier(struct notifier_block *nb)
+{
+       return atomic_notifier_chain_unregister(&notify_page_fault_chain, nb);
+}
+
+static inline int notify_page_fault(enum die_val val, const char *str,
+                       struct pt_regs *regs, long err, int trap, int sig)
+{
+       struct die_args args = {
+               .regs = regs,
+               .str = str,
+               .err = err,
+               .trapnr = trap,
+               .signr = sig
+       };
+       return atomic_notifier_call_chain(&notify_page_fault_chain, val, &args);
+}
+#else
+static inline int notify_page_fault(enum die_val val, const char *str,
+                       struct pt_regs *regs, long err, int trap, int sig)
+{
+       return NOTIFY_DONE;
+}
+#endif
+
 void bust_spinlocks(int yes)
 {
        int loglevel_save = console_loglevel;
@@ -160,7 +194,7 @@ void dump_pagetable(unsigned long address)
        printk("PGD %lx ", pgd_val(*pgd));
        if (!pgd_present(*pgd)) goto ret; 
 
-       pud = __pud_offset_k((pud_t *)pgd_page(*pgd), address);
+       pud = pud_offset(pgd, address);
        if (bad_address(pud)) goto bad;
        printk("PUD %lx ", pud_val(*pud));
        if (!pud_present(*pud)) goto ret;
@@ -314,11 +348,13 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
        unsigned long flags;
        siginfo_t info;
 
+       tsk = current;
+       mm = tsk->mm;
+       prefetchw(&mm->mmap_sem);
+
        /* get the address */
        __asm__("movq %%cr2,%0":"=r" (address));
 
-       tsk = current;
-       mm = tsk->mm;
        info.si_code = SEGV_MAPERR;
 
 
@@ -346,7 +382,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
                        if (vmalloc_fault(address) >= 0)
                                return;
                }
-               if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
+               if (notify_page_fault(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
                                                SIGSEGV) == NOTIFY_STOP)
                        return;
                /*
@@ -356,7 +392,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
                goto bad_area_nosemaphore;
        }
 
-       if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
+       if (notify_page_fault(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
                                        SIGSEGV) == NOTIFY_STOP)
                return;
 
@@ -381,7 +417,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
        /* When running in the kernel we expect faults to occur only to
         * addresses in user space.  All other faults represent errors in the
         * kernel and should generate an OOPS.  Unfortunatly, in the case of an
-        * erroneous fault occuring in a code path which already holds mmap_sem
+        * erroneous fault occurring in a code path which already holds mmap_sem
         * we will deadlock attempting to validate the fault against the
         * address space.  Luckily the kernel only validly references user
         * space from well defined areas of code, which are listed in the
@@ -408,8 +444,10 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
        if (!(vma->vm_flags & VM_GROWSDOWN))
                goto bad_area;
        if (error_code & 4) {
-               // XXX: align red zone size with ABI 
-               if (address + 128 < regs->rsp)
+               /* Allow userspace just enough access below the stack pointer
+                * to let the 'enter' instruction work.
+                */
+               if (address + 65536 + 32 * sizeof(unsigned long) < regs->rsp)
                        goto bad_area;
        }
        if (expand_stack(vma, address))
@@ -621,6 +659,6 @@ void vmalloc_sync_all(void)
 static int __init enable_pagefaulttrace(char *str)
 {
        page_fault_trace = 1;
-       return 0;
+       return 1;
 }
 __setup("pagefaulttrace", enable_pagefaulttrace);