[PATCH v5 04/25] mm/arm: Use general page fault accounting

From: Peter Xu <peterx@redhat.com>
To: linux-kernel@vger.kernel.org, linux-mm@kvack.org
Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	peterx@redhat.com, Andrew Morton <akpm@linux-foundation.org>,
	Will Deacon <will@kernel.org>,
	Andrea Arcangeli <aarcange@redhat.com>,
	David Rientjes <rientjes@google.com>,
	John Hubbard <jhubbard@nvidia.com>,
	Michael Ellerman <mpe@ellerman.id.au>,
	Russell King <linux@armlinux.org.uk>,
	linux-arm-kernel@lists.infradead.org
Subject: [PATCH v5 04/25] mm/arm: Use general page fault accounting
Date: Tue,  7 Jul 2020 18:50:00 -0400	[thread overview]
Message-ID: <20200707225021.200906-5-peterx@redhat.com> (raw)
In-Reply-To: <20200707225021.200906-1-peterx@redhat.com>

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@armlinux.org.uk>
CC: Will Deacon <will@kernel.org>
CC: linux-arm-kernel@lists.infradead.org
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 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 01a8e0f8fef7..efa402025031 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -202,7 +202,8 @@ 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;
@@ -224,7 +225,7 @@ __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 */
@@ -266,6 +267,8 @@ 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,
@@ -290,7 +293,7 @@ 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_lock because
@@ -302,23 +305,7 @@ 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

