aboutsummaryrefslogtreecommitdiff
path: root/arch/arm/mm/fault.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm/mm/fault.c')
-rw-r--r--arch/arm/mm/fault.c248
1 files changed, 115 insertions, 133 deletions
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 1e21e125fe3..eb8830a4c5e 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -20,25 +20,14 @@
#include <linux/highmem.h>
#include <linux/perf_event.h>
-#include <asm/system.h>
+#include <asm/exception.h>
#include <asm/pgtable.h>
+#include <asm/system_misc.h>
+#include <asm/system_info.h>
#include <asm/tlbflush.h>
#include "fault.h"
-/*
- * Fault status register encodings. We steal bit 31 for our own purposes.
- */
-#define FSR_LNX_PF (1 << 31)
-#define FSR_WRITE (1 << 11)
-#define FSR_FS4 (1 << 10)
-#define FSR_FS3_0 (15)
-
-static inline int fsr_fs(unsigned int fsr)
-{
- return (fsr & FSR_FS3_0) | (fsr & FSR_FS4) >> 6;
-}
-
#ifdef CONFIG_MMU
#ifdef CONFIG_KPROBES
@@ -76,9 +65,11 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
printk(KERN_ALERT "pgd = %p\n", mm->pgd);
pgd = pgd_offset(mm, addr);
- printk(KERN_ALERT "[%08lx] *pgd=%08lx", addr, pgd_val(*pgd));
+ printk(KERN_ALERT "[%08lx] *pgd=%08llx",
+ addr, (long long)pgd_val(*pgd));
do {
+ pud_t *pud;
pmd_t *pmd;
pte_t *pte;
@@ -90,9 +81,21 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
break;
}
- pmd = pmd_offset(pgd, addr);
+ pud = pud_offset(pgd, addr);
+ if (PTRS_PER_PUD != 1)
+ printk(", *pud=%08llx", (long long)pud_val(*pud));
+
+ if (pud_none(*pud))
+ break;
+
+ if (pud_bad(*pud)) {
+ printk("(bad)");
+ break;
+ }
+
+ pmd = pmd_offset(pud, addr);
if (PTRS_PER_PMD != 1)
- printk(", *pmd=%08lx", pmd_val(*pmd));
+ printk(", *pmd=%08llx", (long long)pmd_val(*pmd));
if (pmd_none(*pmd))
break;
@@ -107,8 +110,11 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
break;
pte = pte_offset_map(pmd, addr);
- printk(", *pte=%08lx", pte_val(*pte));
- printk(", *ppte=%08lx", pte_val(pte[-PTRS_PER_PTE]));
+ printk(", *pte=%08llx", (long long)pte_val(*pte));
+#ifndef CONFIG_ARM_LPAE
+ printk(", *ppte=%08llx",
+ (long long)pte_val(pte[PTE_HWTABLE_PTRS]));
+#endif
pte_unmap(pte);
} while(0);
@@ -159,7 +165,8 @@ __do_user_fault(struct task_struct *tsk, unsigned long addr,
struct siginfo si;
#ifdef CONFIG_DEBUG_USER
- if (user_debug & UDBG_SEGV) {
+ if (((user_debug & UDBG_SEGV) && (sig == SIGSEGV)) ||
+ ((user_debug & UDBG_BUS) && (sig == SIGBUS))) {
printk(KERN_DEBUG "%s: unhandled page fault (%d) at 0x%08lx, code 0x%03x\n",
tsk->comm, sig, addr, fsr);
show_pte(tsk->mm, addr);
@@ -215,7 +222,7 @@ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma)
static int __kprobes
__do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
- struct task_struct *tsk)
+ unsigned int flags, struct task_struct *tsk)
{
struct vm_area_struct *vma;
int fault;
@@ -237,21 +244,12 @@ good_area:
goto out;
}
- /*
- * If for any reason at all we couldn't handle the fault, make
- * sure we exit gracefully rather than endlessly redo the fault.
- */
- fault = handle_mm_fault(mm, vma, addr & PAGE_MASK, (fsr & FSR_WRITE) ? FAULT_FLAG_WRITE : 0);
- if (unlikely(fault & VM_FAULT_ERROR))
- return fault;
- if (fault & VM_FAULT_MAJOR)
- tsk->maj_flt++;
- else
- tsk->min_flt++;
- return fault;
+ return handle_mm_fault(mm, vma, addr & PAGE_MASK, flags);
check_stack:
- if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
+ /* Don't allow expansion below FIRST_USER_ADDRESS */
+ if (vma->vm_flags & VM_GROWSDOWN &&
+ addr >= FIRST_USER_ADDRESS && !expand_stack(vma, addr))
goto good_area;
out:
return fault;
@@ -263,6 +261,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
struct task_struct *tsk;
struct mm_struct *mm;
int fault, sig, code;
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
if (notify_page_fault(regs, fsr))
return 0;
@@ -270,6 +269,10 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
tsk = current;
mm = tsk->mm;
+ /* Enable interrupts if they were enabled in the parent context. */
+ if (interrupts_enabled(regs))
+ local_irq_enable();
+
/*
* If we're in an interrupt or have no user
* context, we must not take the fault..
@@ -277,6 +280,11 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
if (in_atomic() || !mm)
goto no_context;
+ if (user_mode(regs))
+ flags |= FAULT_FLAG_USER;
+ if (fsr & FSR_WRITE)
+ flags |= FAULT_FLAG_WRITE;
+
/*
* As per x86, we may deadlock here. However, since the kernel only
* validly references user space from well defined areas of the code,
@@ -285,6 +293,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
if (!down_read_trylock(&mm->mmap_sem)) {
if (!user_mode(regs) && !search_exception_tables(regs->ARM_pc))
goto no_context;
+retry:
down_read(&mm->mmap_sem);
} else {
/*
@@ -300,14 +309,42 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
#endif
}
- fault = __do_page_fault(mm, addr, fsr, tsk);
- up_read(&mm->mmap_sem);
+ fault = __do_page_fault(mm, addr, fsr, flags, tsk);
- perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, addr);
- if (fault & VM_FAULT_MAJOR)
- perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0, regs, addr);
- else if (fault & VM_FAULT_MINOR)
- perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0, regs, addr);
+ /* If we need to retry but a fatal signal is pending, handle the
+ * signal first. We do not need to release the mmap_sem because
+ * it would already be released in __lock_page_or_retry in
+ * mm/filemap.c. */
+ if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+ return 0;
+
+ /*
+ * Major/minor page fault accounting is only done on the
+ * initial attempt. If we go through a retry, it is extremely
+ * likely that the page will be found in page cache at that point.
+ */
+
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
+ if (!(fault & VM_FAULT_ERROR) && flags & FAULT_FLAG_ALLOW_RETRY) {
+ if (fault & VM_FAULT_MAJOR) {
+ tsk->maj_flt++;
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
+ regs, addr);
+ } else {
+ tsk->min_flt++;
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
+ regs, addr);
+ }
+ if (fault & VM_FAULT_RETRY) {
+ /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
+ * of starvation. */
+ flags &= ~FAULT_FLAG_ALLOW_RETRY;
+ flags |= FAULT_FLAG_TRIED;
+ goto retry;
+ }
+ }
+
+ up_read(&mm->mmap_sem);
/*
* Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR
@@ -315,6 +352,13 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))
return 0;
+ /*
+ * If we are in kernel mode at this point, we
+ * have no context to handle this fault with.
+ */
+ if (!user_mode(regs))
+ goto no_context;
+
if (fault & VM_FAULT_OOM) {
/*
* We ran out of memory, call the OOM killer, and return to
@@ -325,13 +369,6 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
return 0;
}
- /*
- * If we are in kernel mode at this point, we
- * have no context to handle this fault with.
- */
- if (!user_mode(regs))
- goto no_context;
-
if (fault & VM_FAULT_SIGBUS) {
/*
* We had some memory, but were unable to
@@ -388,6 +425,7 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
{
unsigned int index;
pgd_t *pgd, *pgd_k;
+ pud_t *pud, *pud_k;
pmd_t *pmd, *pmd_k;
if (addr < TASK_SIZE)
@@ -398,21 +436,31 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
index = pgd_index(addr);
- /*
- * FIXME: CP15 C1 is write only on ARMv3 architectures.
- */
pgd = cpu_get_pgd() + index;
pgd_k = init_mm.pgd + index;
if (pgd_none(*pgd_k))
goto bad_area;
-
if (!pgd_present(*pgd))
set_pgd(pgd, *pgd_k);
- pmd_k = pmd_offset(pgd_k, addr);
- pmd = pmd_offset(pgd, addr);
+ pud = pud_offset(pgd, addr);
+ pud_k = pud_offset(pgd_k, addr);
+
+ if (pud_none(*pud_k))
+ goto bad_area;
+ if (!pud_present(*pud))
+ set_pud(pud, *pud_k);
+
+ pmd = pmd_offset(pud, addr);
+ pmd_k = pmd_offset(pud_k, addr);
+#ifdef CONFIG_ARM_LPAE
+ /*
+ * Only one hardware entry per PMD with LPAE.
+ */
+ index = 0;
+#else
/*
* On ARM one Linux PGD entry contains two hardware entries (see page
* tables layout in pgtable.h). We normally guarantee that we always
@@ -422,6 +470,7 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
* for the first of pair.
*/
index = (addr >> SECTION_SHIFT) & 1;
+#endif
if (pmd_none(pmd_k[index]))
goto bad_area;
@@ -445,12 +494,14 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
* Some section permission faults need to be handled gracefully.
* They can happen due to a __{get,put}_user during an oops.
*/
+#ifndef CONFIG_ARM_LPAE
static int
do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
do_bad_area(addr, fsr, regs);
return 0;
}
+#endif /* CONFIG_ARM_LPAE */
/*
* This abort handler always returns "fault".
@@ -461,55 +512,20 @@ do_bad(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
return 1;
}
-static struct fsr_info {
+struct fsr_info {
int (*fn)(unsigned long addr, unsigned int fsr, struct pt_regs *regs);
int sig;
int code;
const char *name;
-} fsr_info[] = {
- /*
- * The following are the standard ARMv3 and ARMv4 aborts. ARMv5
- * defines these to be "precise" aborts.
- */
- { do_bad, SIGSEGV, 0, "vector exception" },
- { do_bad, SIGBUS, BUS_ADRALN, "alignment exception" },
- { do_bad, SIGKILL, 0, "terminal exception" },
- { do_bad, SIGBUS, BUS_ADRALN, "alignment exception" },
- { do_bad, SIGBUS, 0, "external abort on linefetch" },
- { do_translation_fault, SIGSEGV, SEGV_MAPERR, "section translation fault" },
- { do_bad, SIGBUS, 0, "external abort on linefetch" },
- { do_page_fault, SIGSEGV, SEGV_MAPERR, "page translation fault" },
- { do_bad, SIGBUS, 0, "external abort on non-linefetch" },
- { do_bad, SIGSEGV, SEGV_ACCERR, "section domain fault" },
- { do_bad, SIGBUS, 0, "external abort on non-linefetch" },
- { do_bad, SIGSEGV, SEGV_ACCERR, "page domain fault" },
- { do_bad, SIGBUS, 0, "external abort on translation" },
- { do_sect_fault, SIGSEGV, SEGV_ACCERR, "section permission fault" },
- { do_bad, SIGBUS, 0, "external abort on translation" },
- { do_page_fault, SIGSEGV, SEGV_ACCERR, "page permission fault" },
- /*
- * The following are "imprecise" aborts, which are signalled by bit
- * 10 of the FSR, and may not be recoverable. These are only
- * supported if the CPU abort handler supports bit 10.
- */
- { do_bad, SIGBUS, 0, "unknown 16" },
- { do_bad, SIGBUS, 0, "unknown 17" },
- { do_bad, SIGBUS, 0, "unknown 18" },
- { do_bad, SIGBUS, 0, "unknown 19" },
- { do_bad, SIGBUS, 0, "lock abort" }, /* xscale */
- { do_bad, SIGBUS, 0, "unknown 21" },
- { do_bad, SIGBUS, BUS_OBJERR, "imprecise external abort" }, /* xscale */
- { do_bad, SIGBUS, 0, "unknown 23" },
- { do_bad, SIGBUS, 0, "dcache parity error" }, /* xscale */
- { do_bad, SIGBUS, 0, "unknown 25" },
- { do_bad, SIGBUS, 0, "unknown 26" },
- { do_bad, SIGBUS, 0, "unknown 27" },
- { do_bad, SIGBUS, 0, "unknown 28" },
- { do_bad, SIGBUS, 0, "unknown 29" },
- { do_bad, SIGBUS, 0, "unknown 30" },
- { do_bad, SIGBUS, 0, "unknown 31" }
};
+/* FSR definition */
+#ifdef CONFIG_ARM_LPAE
+#include "fsr-3level.c"
+#else
+#include "fsr-2level.c"
+#endif
+
void __init
hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *),
int sig, int code, const char *name)
@@ -545,42 +561,6 @@ do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
arm_notify_die("", regs, &info, fsr, 0);
}
-
-static struct fsr_info ifsr_info[] = {
- { do_bad, SIGBUS, 0, "unknown 0" },
- { do_bad, SIGBUS, 0, "unknown 1" },
- { do_bad, SIGBUS, 0, "debug event" },
- { do_bad, SIGSEGV, SEGV_ACCERR, "section access flag fault" },
- { do_bad, SIGBUS, 0, "unknown 4" },
- { do_translation_fault, SIGSEGV, SEGV_MAPERR, "section translation fault" },
- { do_bad, SIGSEGV, SEGV_ACCERR, "page access flag fault" },
- { do_page_fault, SIGSEGV, SEGV_MAPERR, "page translation fault" },
- { do_bad, SIGBUS, 0, "external abort on non-linefetch" },
- { do_bad, SIGSEGV, SEGV_ACCERR, "section domain fault" },
- { do_bad, SIGBUS, 0, "unknown 10" },
- { do_bad, SIGSEGV, SEGV_ACCERR, "page domain fault" },
- { do_bad, SIGBUS, 0, "external abort on translation" },
- { do_sect_fault, SIGSEGV, SEGV_ACCERR, "section permission fault" },
- { do_bad, SIGBUS, 0, "external abort on translation" },
- { do_page_fault, SIGSEGV, SEGV_ACCERR, "page permission fault" },
- { do_bad, SIGBUS, 0, "unknown 16" },
- { do_bad, SIGBUS, 0, "unknown 17" },
- { do_bad, SIGBUS, 0, "unknown 18" },
- { do_bad, SIGBUS, 0, "unknown 19" },
- { do_bad, SIGBUS, 0, "unknown 20" },
- { do_bad, SIGBUS, 0, "unknown 21" },
- { do_bad, SIGBUS, 0, "unknown 22" },
- { do_bad, SIGBUS, 0, "unknown 23" },
- { do_bad, SIGBUS, 0, "unknown 24" },
- { do_bad, SIGBUS, 0, "unknown 25" },
- { do_bad, SIGBUS, 0, "unknown 26" },
- { do_bad, SIGBUS, 0, "unknown 27" },
- { do_bad, SIGBUS, 0, "unknown 28" },
- { do_bad, SIGBUS, 0, "unknown 29" },
- { do_bad, SIGBUS, 0, "unknown 30" },
- { do_bad, SIGBUS, 0, "unknown 31" },
-};
-
void __init
hook_ifault_code(int nr, int (*fn)(unsigned long, unsigned int, struct pt_regs *),
int sig, int code, const char *name)
@@ -613,6 +593,7 @@ do_PrefetchAbort(unsigned long addr, unsigned int ifsr, struct pt_regs *regs)
arm_notify_die("", regs, &info, ifsr, 0);
}
+#ifndef CONFIG_ARM_LPAE
static int __init exceptions_init(void)
{
if (cpu_architecture() >= CPU_ARCH_ARMv6) {
@@ -635,3 +616,4 @@ static int __init exceptions_init(void)
}
arch_initcall(exceptions_init);
+#endif
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-05 07:50:26 +0000