The patch titled
Subject: mm/xtensa: use general page fault accounting
has been removed from the -mm tree. Its filename was
mm-xtensa-use-general-page-fault-accounting.patch
This patch was dropped because it was merged into mainline or a subsystem tree
------------------------------------------------------
From: Peter Xu <peterx@xxxxxxxxxx>
Subject: mm/xtensa: use general page fault accounting
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.
Remove the PERF_COUNT_SW_PAGE_FAULTS_[MAJ|MIN] perf events because it's
now also done in handle_mm_fault().
Move the PERF_COUNT_SW_PAGE_FAULTS event higher before taking mmap_sem for
the fault, then it'll match with the rest of the archs.
Link: http://lkml.kernel.org/r/20200707225021.200906-24-peterx@xxxxxxxxxx
Signed-off-by: Peter Xu <peterx@xxxxxxxxxx>
Acked-by: Max Filippov <jcmvbkbc@xxxxxxxxx>
Cc: Chris Zankel <chris@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
arch/xtensa/mm/fault.c | 15 ++++-----------
1 file changed, 4 insertions(+), 11 deletions(-)
--- a/arch/xtensa/mm/fault.c~mm-xtensa-use-general-page-fault-accounting
+++ a/arch/xtensa/mm/fault.c
@@ -72,6 +72,9 @@ void do_page_fault(struct pt_regs *regs)
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
+
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+
retry:
mmap_read_lock(mm);
vma = find_vma(mm, address);
@@ -107,7 +110,7 @@ good_area:
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(vma, address, flags, NULL);
+ fault = handle_mm_fault(vma, address, flags, regs);
if (fault_signal_pending(fault, regs))
return;
@@ -122,10 +125,6 @@ good_area:
BUG();
}
if (flags & FAULT_FLAG_ALLOW_RETRY) {
- if (fault & VM_FAULT_MAJOR)
- current->maj_flt++;
- else
- current->min_flt++;
if (fault & VM_FAULT_RETRY) {
flags |= FAULT_FLAG_TRIED;
@@ -139,12 +138,6 @@ good_area:
}
mmap_read_unlock(mm);
- perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
- if (flags & VM_FAULT_MAJOR)
- perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
- else
- perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
-
return;
/* Something tried to access memory that isn't in our memory map..
_
Patches currently in -mm which might be from peterx@xxxxxxxxxx are
