Linux-2.6.12-rc2
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!
diff --git a/arch/ppc64/mm/fault.c b/arch/ppc64/mm/fault.c
new file mode 100644
index 0000000..20b0f37
--- /dev/null
+++ b/arch/ppc64/mm/fault.c
@@ -0,0 +1,312 @@
+/*
+ * arch/ppc/mm/fault.c
+ *
+ * PowerPC version
+ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ * Derived from "arch/i386/mm/fault.c"
+ * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
+ *
+ * Modified by Cort Dougan and Paul Mackerras.
+ *
+ * Modified for PPC64 by Dave Engebretsen (engebret@ibm.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/config.h>
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/smp_lock.h>
+#include <linux/module.h>
+
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/mmu.h>
+#include <asm/mmu_context.h>
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/kdebug.h>
+
+/*
+ * Check whether the instruction at regs->nip is a store using
+ * an update addressing form which will update r1.
+ */
+static int store_updates_sp(struct pt_regs *regs)
+{
+ unsigned int inst;
+
+ if (get_user(inst, (unsigned int __user *)regs->nip))
+ return 0;
+ /* check for 1 in the rA field */
+ if (((inst >> 16) & 0x1f) != 1)
+ return 0;
+ /* check major opcode */
+ switch (inst >> 26) {
+ case 37: /* stwu */
+ case 39: /* stbu */
+ case 45: /* sthu */
+ case 53: /* stfsu */
+ case 55: /* stfdu */
+ return 1;
+ case 62: /* std or stdu */
+ return (inst & 3) == 1;
+ case 31:
+ /* check minor opcode */
+ switch ((inst >> 1) & 0x3ff) {
+ case 181: /* stdux */
+ case 183: /* stwux */
+ case 247: /* stbux */
+ case 439: /* sthux */
+ case 695: /* stfsux */
+ case 759: /* stfdux */
+ return 1;
+ }
+ }
+ return 0;
+}
+
+/*
+ * The error_code parameter is
+ * - DSISR for a non-SLB data access fault,
+ * - SRR1 & 0x08000000 for a non-SLB instruction access fault
+ * - 0 any SLB fault.
+ * The return value is 0 if the fault was handled, or the signal
+ * number if this is a kernel fault that can't be handled here.
+ */
+int do_page_fault(struct pt_regs *regs, unsigned long address,
+ unsigned long error_code)
+{
+ struct vm_area_struct * vma;
+ struct mm_struct *mm = current->mm;
+ siginfo_t info;
+ unsigned long code = SEGV_MAPERR;
+ unsigned long is_write = error_code & DSISR_ISSTORE;
+ unsigned long trap = TRAP(regs);
+ unsigned long is_exec = trap == 0x400;
+
+ BUG_ON((trap == 0x380) || (trap == 0x480));
+
+ if (notify_die(DIE_PAGE_FAULT, "page_fault", regs, error_code,
+ 11, SIGSEGV) == NOTIFY_STOP)
+ return 0;
+
+ if (trap == 0x300) {
+ if (debugger_fault_handler(regs))
+ return 0;
+ }
+
+ /* On a kernel SLB miss we can only check for a valid exception entry */
+ if (!user_mode(regs) && (address >= TASK_SIZE))
+ return SIGSEGV;
+
+ if (error_code & DSISR_DABRMATCH) {
+ if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code,
+ 11, SIGSEGV) == NOTIFY_STOP)
+ return 0;
+ if (debugger_dabr_match(regs))
+ return 0;
+ }
+
+ if (in_atomic() || mm == NULL) {
+ if (!user_mode(regs))
+ return SIGSEGV;
+ /* in_atomic() in user mode is really bad,
+ as is current->mm == NULL. */
+ printk(KERN_EMERG "Page fault in user mode with"
+ "in_atomic() = %d mm = %p\n", in_atomic(), mm);
+ printk(KERN_EMERG "NIP = %lx MSR = %lx\n",
+ regs->nip, regs->msr);
+ die("Weird page fault", regs, SIGSEGV);
+ }
+
+ /* 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
+ * 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
+ * exceptions table.
+ *
+ * As the vast majority of faults will be valid we will only perform
+ * the source reference check when there is a possibilty of a deadlock.
+ * Attempt to lock the address space, if we cannot we then validate the
+ * source. If this is invalid we can skip the address space check,
+ * thus avoiding the deadlock.
+ */
+ if (!down_read_trylock(&mm->mmap_sem)) {
+ if (!user_mode(regs) && !search_exception_tables(regs->nip))
+ goto bad_area_nosemaphore;
+
+ down_read(&mm->mmap_sem);
+ }
+
+ vma = find_vma(mm, address);
+ if (!vma)
+ goto bad_area;
+
+ if (vma->vm_start <= address) {
+ goto good_area;
+ }
+ if (!(vma->vm_flags & VM_GROWSDOWN))
+ goto bad_area;
+
+ /*
+ * N.B. The POWER/Open ABI allows programs to access up to
+ * 288 bytes below the stack pointer.
+ * The kernel signal delivery code writes up to about 1.5kB
+ * below the stack pointer (r1) before decrementing it.
+ * The exec code can write slightly over 640kB to the stack
+ * before setting the user r1. Thus we allow the stack to
+ * expand to 1MB without further checks.
+ */
+ if (address + 0x100000 < vma->vm_end) {
+ /* get user regs even if this fault is in kernel mode */
+ struct pt_regs *uregs = current->thread.regs;
+ if (uregs == NULL)
+ goto bad_area;
+
+ /*
+ * A user-mode access to an address a long way below
+ * the stack pointer is only valid if the instruction
+ * is one which would update the stack pointer to the
+ * address accessed if the instruction completed,
+ * i.e. either stwu rs,n(r1) or stwux rs,r1,rb
+ * (or the byte, halfword, float or double forms).
+ *
+ * If we don't check this then any write to the area
+ * between the last mapped region and the stack will
+ * expand the stack rather than segfaulting.
+ */
+ if (address + 2048 < uregs->gpr[1]
+ && (!user_mode(regs) || !store_updates_sp(regs)))
+ goto bad_area;
+ }
+
+ if (expand_stack(vma, address))
+ goto bad_area;
+
+good_area:
+ code = SEGV_ACCERR;
+
+ if (is_exec) {
+ /* protection fault */
+ if (error_code & DSISR_PROTFAULT)
+ goto bad_area;
+ if (!(vma->vm_flags & VM_EXEC))
+ goto bad_area;
+ /* a write */
+ } else if (is_write) {
+ if (!(vma->vm_flags & VM_WRITE))
+ goto bad_area;
+ /* a read */
+ } else {
+ if (!(vma->vm_flags & VM_READ))
+ goto bad_area;
+ }
+
+ survive:
+ /*
+ * If for any reason at all we couldn't handle the fault,
+ * make sure we exit gracefully rather than endlessly redo
+ * the fault.
+ */
+ switch (handle_mm_fault(mm, vma, address, is_write)) {
+
+ case VM_FAULT_MINOR:
+ current->min_flt++;
+ break;
+ case VM_FAULT_MAJOR:
+ current->maj_flt++;
+ break;
+ case VM_FAULT_SIGBUS:
+ goto do_sigbus;
+ case VM_FAULT_OOM:
+ goto out_of_memory;
+ default:
+ BUG();
+ }
+
+ up_read(&mm->mmap_sem);
+ return 0;
+
+bad_area:
+ up_read(&mm->mmap_sem);
+
+bad_area_nosemaphore:
+ /* User mode accesses cause a SIGSEGV */
+ if (user_mode(regs)) {
+ info.si_signo = SIGSEGV;
+ info.si_errno = 0;
+ info.si_code = code;
+ info.si_addr = (void __user *) address;
+ force_sig_info(SIGSEGV, &info, current);
+ return 0;
+ }
+
+ if (trap == 0x400 && (error_code & DSISR_PROTFAULT)
+ && printk_ratelimit())
+ printk(KERN_CRIT "kernel tried to execute NX-protected"
+ " page (%lx) - exploit attempt? (uid: %d)\n",
+ address, current->uid);
+
+ return SIGSEGV;
+
+/*
+ * We ran out of memory, or some other thing happened to us that made
+ * us unable to handle the page fault gracefully.
+ */
+out_of_memory:
+ up_read(&mm->mmap_sem);
+ if (current->pid == 1) {
+ yield();
+ down_read(&mm->mmap_sem);
+ goto survive;
+ }
+ printk("VM: killing process %s\n", current->comm);
+ if (user_mode(regs))
+ do_exit(SIGKILL);
+ return SIGKILL;
+
+do_sigbus:
+ up_read(&mm->mmap_sem);
+ if (user_mode(regs)) {
+ info.si_signo = SIGBUS;
+ info.si_errno = 0;
+ info.si_code = BUS_ADRERR;
+ info.si_addr = (void __user *)address;
+ force_sig_info(SIGBUS, &info, current);
+ return 0;
+ }
+ return SIGBUS;
+}
+
+/*
+ * bad_page_fault is called when we have a bad access from the kernel.
+ * It is called from do_page_fault above and from some of the procedures
+ * in traps.c.
+ */
+void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
+{
+ const struct exception_table_entry *entry;
+
+ /* Are we prepared to handle this fault? */
+ if ((entry = search_exception_tables(regs->nip)) != NULL) {
+ regs->nip = entry->fixup;
+ return;
+ }
+
+ /* kernel has accessed a bad area */
+ die("Kernel access of bad area", regs, sig);
+}