Merge master.kernel.org:/pub/scm/linux/kernel/git/jejb/scsi-misc-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 b75b872ec154f8e004fc04a29375eb97f7f468bb..2e7c3c8ffe035d0981b29fd052da25cb86e21d41 100644 (file)
--- a/arch/x86_64/mm/fault.c
+++ b/arch/x86_64/mm/fault.c
@@ -33,7 +33,13 @@
 #include <asm/proto.h>
 #include <asm/kdebug.h>
 #include <asm-generic/sections.h>
-#include <asm/kdebug.h>
+
+/* Page fault error code bits */
+#define PF_PROT        (1<<0)          /* or no page found */
+#define PF_WRITE       (1<<1)
+#define PF_USER        (1<<2)
+#define PF_RSVD        (1<<3)
+#define PF_INSTR       (1<<4)
 
 void bust_spinlocks(int yes)
 {
@@ -68,7 +74,7 @@ static noinline int is_prefetch(struct pt_regs *regs, unsigned long addr,
        unsigned char *max_instr;
 
        /* If it was a exec fault ignore */
-       if (error_code & (1<<4))
+       if (error_code & PF_INSTR)
                return 0;
        
        instr = (unsigned char *)convert_rip_to_linear(current, regs);
@@ -150,8 +156,8 @@ void dump_pagetable(unsigned long address)
 
        pgd = __va((unsigned long)pgd & PHYSICAL_PAGE_MASK); 
        pgd += pgd_index(address);
-       printk("PGD %lx ", pgd_val(*pgd));
        if (bad_address(pgd)) goto bad;
+       printk("PGD %lx ", pgd_val(*pgd));
        if (!pgd_present(*pgd)) goto ret; 
 
        pud = __pud_offset_k((pud_t *)pgd_page(*pgd), address);
@@ -222,17 +228,22 @@ static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs,
                                 unsigned long error_code)
 {
        unsigned long flags = oops_begin();
+       struct task_struct *tsk;
 
        printk(KERN_ALERT "%s: Corrupted page table at address %lx\n",
               current->comm, address);
        dump_pagetable(address);
+       tsk = current;
+       tsk->thread.cr2 = address;
+       tsk->thread.trap_no = 14;
+       tsk->thread.error_code = error_code;
        __die("Bad pagetable", regs, error_code);
        oops_end(flags);
        do_exit(SIGKILL);
 }
 
 /*
- * Handle a fault on the vmalloc or module mapping area
+ * Handle a fault on the vmalloc area
  *
  * This assumes no large pages in there.
  */
@@ -278,7 +289,6 @@ static int vmalloc_fault(unsigned long address)
           that. */
        if (!pte_present(*pte) || pte_pfn(*pte) != pte_pfn(*pte_ref))
                BUG();
-       __flush_tlb_all();
        return 0;
 }
 
@@ -289,12 +299,6 @@ int exception_trace = 1;
  * This routine handles page faults.  It determines the address,
  * and the problem, and then passes it off to one of the appropriate
  * routines.
- *
- * error_code:
- *     bit 0 == 0 means no page found, 1 means protection fault
- *     bit 1 == 0 means read, 1 means write
- *     bit 2 == 0 means kernel, 1 means user-mode
- *      bit 3 == 1 means fault was an instruction fetch
  */
 asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
                                        unsigned long error_code)
@@ -308,18 +312,6 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
        unsigned long flags;
        siginfo_t info;
 
-#ifdef CONFIG_CHECKING
-       { 
-               unsigned long gs; 
-               struct x8664_pda *pda = cpu_pda + stack_smp_processor_id(); 
-               rdmsrl(MSR_GS_BASE, gs); 
-               if (gs != (unsigned long)pda) { 
-                       wrmsrl(MSR_GS_BASE, pda); 
-                       printk("page_fault: wrong gs %lx expected %p\n", gs, pda);
-               }
-       }
-#endif
-
        /* get the address */
        __asm__("movq %%cr2,%0":"=r" (address));
        if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
@@ -349,12 +341,16 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
         *
         * This verifies that the fault happens in kernel space
         * (error_code & 4) == 0, and that the fault was not a
-        * protection error (error_code & 1) == 0.
+        * protection error (error_code & 9) == 0.
         */
        if (unlikely(address >= TASK_SIZE64)) {
-               if (!(error_code & 5) &&
-                     ((address >= VMALLOC_START && address < VMALLOC_END) ||
-                      (address >= MODULES_VADDR && address < MODULES_END))) {
+               /*
+                * Don't check for the module range here: its PML4
+                * is always initialized because it's shared with the main
+                * kernel text. Only vmalloc may need PML4 syncups.
+                */
+               if (!(error_code & (PF_RSVD|PF_USER|PF_PROT)) &&
+                     ((address >= VMALLOC_START && address < VMALLOC_END))) {
                        if (vmalloc_fault(address) < 0)
                                goto bad_area_nosemaphore;
                        return;
@@ -366,7 +362,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
                goto bad_area_nosemaphore;
        }
 
-       if (unlikely(error_code & (1 << 3)))
+       if (unlikely(error_code & PF_RSVD))
                pgtable_bad(address, regs, error_code);
 
        /*
@@ -393,7 +389,7 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
         * thus avoiding the deadlock.
         */
        if (!down_read_trylock(&mm->mmap_sem)) {
-               if ((error_code & 4) == 0 &&
+               if ((error_code & PF_USER) == 0 &&
                    !search_exception_tables(regs->rip))
                        goto bad_area_nosemaphore;
                down_read(&mm->mmap_sem);
@@ -420,17 +416,17 @@ asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
 good_area:
        info.si_code = SEGV_ACCERR;
        write = 0;
-       switch (error_code & 3) {
+       switch (error_code & (PF_PROT|PF_WRITE)) {
                default:        /* 3: write, present */
                        /* fall through */
-               case 2:         /* write, not present */
+               case PF_WRITE:          /* write, not present */
                        if (!(vma->vm_flags & VM_WRITE))
                                goto bad_area;
                        write++;
                        break;
-               case 1:         /* read, present */
+               case PF_PROT:           /* read, present */
                        goto bad_area;
-               case 0:         /* read, not present */
+               case 0:                 /* read, not present */
                        if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
                                goto bad_area;
        }
@@ -465,7 +461,7 @@ bad_area:
 
 bad_area_nosemaphore:
        /* User mode accesses just cause a SIGSEGV */
-       if (error_code & 4) {
+       if (error_code & PF_USER) {
                if (is_prefetch(regs, address, error_code))
                        return;
 
@@ -533,6 +529,9 @@ no_context:
        printk_address(regs->rip);
        printk("\n");
        dump_pagetable(address);
+       tsk->thread.cr2 = address;
+       tsk->thread.trap_no = 14;
+       tsk->thread.error_code = error_code;
        __die("Oops", regs, error_code);
        /* Executive summary in case the body of the oops scrolled away */
        printk(KERN_EMERG "CR2: %016lx\n", address);
@@ -558,7 +557,7 @@ do_sigbus:
        up_read(&mm->mmap_sem);
 
        /* Kernel mode? Handle exceptions or die */
-       if (!(error_code & 4))
+       if (!(error_code & PF_USER))
                goto no_context;
 
        tsk->thread.cr2 = address;
@@ -571,3 +570,10 @@ do_sigbus:
        force_sig_info(SIGBUS, &info, tsk);
        return;
 }
+
+static int __init enable_pagefaulttrace(char *str)
+{
+       page_fault_trace = 1;
+       return 0;
+}
+__setup("pagefaulttrace", enable_pagefaulttrace);