[PATCH v4 05/26] mm/arm64: Use general page fault accounting

From: Peter Xu <peterx@redhat.com>
To: linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc: Andrew Morton <akpm@linux-foundation.org>,
	peterx@redhat.com, John Hubbard <jhubbard@nvidia.com>,
	Michael Ellerman <mpe@ellerman.id.au>,
	Gerald Schaefer <gerald.schaefer@de.ibm.com>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Will Deacon <will@kernel.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	linux-arm-kernel@lists.infradead.org
Subject: [PATCH v4 05/26] mm/arm64: Use general page fault accounting
Date: Tue, 30 Jun 2020 16:45:14 -0400	[thread overview]
Message-ID: <20200630204514.38711-1-peterx@redhat.com> (raw)

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 pass pt_regs pointer into __do_page_fault().

CC: Catalin Marinas <catalin.marinas@arm.com>
CC: Will Deacon <will@kernel.org>
CC: linux-arm-kernel@lists.infradead.org
Signed-off-by: Peter Xu <peterx@redhat.com>
---
 arch/arm64/mm/fault.c | 29 ++++++-----------------------
 1 file changed, 6 insertions(+), 23 deletions(-)

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index be29f4076fe3..f07333e86c2f 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -404,7 +404,8 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re
 #define VM_FAULT_BADACCESS	0x020000
 
 static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr,
-			   unsigned int mm_flags, unsigned long vm_flags)
+				  unsigned int mm_flags, unsigned long vm_flags,
+				  struct pt_regs *regs)
 {
 	struct vm_area_struct *vma = find_vma(mm, addr);
 
@@ -428,7 +429,7 @@ static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr,
 	 */
 	if (!(vma->vm_flags & vm_flags))
 		return VM_FAULT_BADACCESS;
-	return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags, NULL);
+	return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags, regs);
 }
 
 static bool is_el0_instruction_abort(unsigned int esr)
@@ -450,7 +451,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 {
 	const struct fault_info *inf;
 	struct mm_struct *mm = current->mm;
-	vm_fault_t fault, major = 0;
+	vm_fault_t fault;
 	unsigned long vm_flags = VM_ACCESS_FLAGS;
 	unsigned int mm_flags = FAULT_FLAG_DEFAULT;
 
@@ -516,8 +517,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 #endif
 	}
 
-	fault = __do_page_fault(mm, addr, mm_flags, vm_flags);
-	major |= fault & VM_FAULT_MAJOR;
+	fault = __do_page_fault(mm, addr, mm_flags, vm_flags, regs);
 
 	/* Quick path to respond to signals */
 	if (fault_signal_pending(fault, regs)) {
@@ -538,25 +538,8 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	 * Handle the "normal" (no error) case first.
 	 */
 	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP |
-			      VM_FAULT_BADACCESS)))) {
-		/*
-		 * Major/minor page fault accounting is only done
-		 * once. If we go through a retry, it is extremely
-		 * likely that the page will be found in page cache at
-		 * that point.
-		 */
-		if (major) {
-			current->maj_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs,
-				      addr);
-		} else {
-			current->min_flt++;
-			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs,
-				      addr);
-		}
-
+			      VM_FAULT_BADACCESS))))
 		return 0;
-	}
 
 	/*
 	 * If we are in kernel mode at this point, we have no context to
-- 
2.26.2

