Use the general page fault accounting by passing regs into handle_mm_fault().
It naturally solve the issue of multiple page fault accounting when page fault
retry happened. To do this, we need to pass the pt_regs pointer into
__do_page_fault().
Fix PERF_COUNT_SW_PAGE_FAULTS perf event manually for page fault retries, by
moving it before taking mmap_sem.
CC: Russell King <linux@xxxxxxxxxxxxxxx>
CC: Will Deacon <will@xxxxxxxxxx>
CC: linux-arm-kernel@xxxxxxxxxxxxxxxxxxx
Signed-off-by: Peter Xu <peterx@xxxxxxxxxx>
---
arch/arm/mm/fault.c | 25 ++++++-------------------
1 file changed, 6 insertions(+), 19 deletions(-)
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 0d6be0f4f27c..8530befee012 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -201,7 +201,8 @@ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma)
static vm_fault_t __kprobes
__do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
- unsigned int flags, struct task_struct *tsk)
+ unsigned int flags, struct task_struct *tsk,
+ struct pt_regs *regs)
{
struct vm_area_struct *vma;
vm_fault_t fault;
@@ -223,7 +224,7 @@ __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
goto out;
}
- return handle_mm_fault(vma, addr & PAGE_MASK, flags, NULL);
+ return handle_mm_fault(vma, addr & PAGE_MASK, flags, regs);
check_stack:
/* Don't allow expansion below FIRST_USER_ADDRESS */
@@ -265,6 +266,8 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
if ((fsr & FSR_WRITE) && !(fsr & FSR_CM))
flags |= FAULT_FLAG_WRITE;
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
+
/*
* As per x86, we may deadlock here. However, since the kernel only
* validly references user space from well defined areas of the code,
@@ -289,7 +292,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
#endif
}
- fault = __do_page_fault(mm, addr, fsr, flags, tsk);
+ fault = __do_page_fault(mm, addr, fsr, flags, tsk, regs);
/* 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
@@ -301,23 +304,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
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) {
flags |= FAULT_FLAG_TRIED;
goto retry;
--
2.26.2
