mm: add spurious fault fixing support for huge pmd

The page faults may be spurious because of the racy access to the page
table.  For example, a non-populated virtual page is accessed on 2
CPUs simultaneously, thus the page faults are triggered on both CPUs.
However, it's possible that one CPU (say CPU A) cannot find the reason
for the page fault if the other CPU (say CPU B) has changed the page
table before the PTE is checked on CPU A.  Most of the time, the
spurious page faults can be ignored safely.  However, if the page
fault is for the write access, it's possible that a stale read-only
TLB entry exists in the local CPU and needs to be flushed on some
architectures.  This is called the spurious page fault fixing.

In the current kernel, there is spurious fault fixing support for pte,
but not for huge pmd because no architectures need it. But in the
next patch in the series, we will change the write protection fault
handling logic on arm64, so that some stale huge pmd entries may
remain in the TLB. These entries need to be flushed via the huge pmd
spurious fault fixing mechanism.

Signed-off-by: Huang Ying <ying.huang@linux.alibaba.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Zi Yan <ziy@nvidia.com>
Cc: Will Deacon <will@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yang Shi <yang@os.amperecomputing.com>
Cc: Christoph Lameter (Ampere) <cl@gentwo.org>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Yin Fengwei <fengwei_yin@linux.alibaba.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

1 files changed, 46 insertions, 16 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 74b45e258323..6e5a08c4fd2e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -6116,6 +6116,45 @@ split:
 }
 
 /*
+ * The page faults may be spurious because of the racy access to the
+ * page table.  For example, a non-populated virtual page is accessed
+ * on 2 CPUs simultaneously, thus the page faults are triggered on
+ * both CPUs.  However, it's possible that one CPU (say CPU A) cannot
+ * find the reason for the page fault if the other CPU (say CPU B) has
+ * changed the page table before the PTE is checked on CPU A.  Most of
+ * the time, the spurious page faults can be ignored safely.  However,
+ * if the page fault is for the write access, it's possible that a
+ * stale read-only TLB entry exists in the local CPU and needs to be
+ * flushed on some architectures.  This is called the spurious page
+ * fault fixing.
+ *
+ * Note: flush_tlb_fix_spurious_fault() is defined as flush_tlb_page()
+ * by default and used as such on most architectures, while
+ * flush_tlb_fix_spurious_fault_pmd() is defined as NOP by default and
+ * used as such on most architectures.
+ */
+static void fix_spurious_fault(struct vm_fault *vmf,
+			       enum pgtable_level ptlevel)
+{
+	/* Skip spurious TLB flush for retried page fault */
+	if (vmf->flags & FAULT_FLAG_TRIED)
+		return;
+	/*
+	 * This is needed only for protection faults but the arch code
+	 * is not yet telling us if this is a protection fault or not.
+	 * This still avoids useless tlb flushes for .text page faults
+	 * with threads.
+	 */
+	if (vmf->flags & FAULT_FLAG_WRITE) {
+		if (ptlevel == PGTABLE_LEVEL_PTE)
+			flush_tlb_fix_spurious_fault(vmf->vma, vmf->address,
+						     vmf->pte);
+		else
+			flush_tlb_fix_spurious_fault_pmd(vmf->vma, vmf->address,
+							 vmf->pmd);
+	}
+}
+/*
  * These routines also need to handle stuff like marking pages dirty
  * and/or accessed for architectures that don't do it in hardware (most
  * RISC architectures).  The early dirtying is also good on the i386.
@@ -6196,23 +6235,11 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
 	}
 	entry = pte_mkyoung(entry);
 	if (ptep_set_access_flags(vmf->vma, vmf->address, vmf->pte, entry,
-				vmf->flags & FAULT_FLAG_WRITE)) {
+				vmf->flags & FAULT_FLAG_WRITE))
 		update_mmu_cache_range(vmf, vmf->vma, vmf->address,
 				vmf->pte, 1);
-	} else {
-		/* Skip spurious TLB flush for retried page fault */
-		if (vmf->flags & FAULT_FLAG_TRIED)
-			goto unlock;
-		/*
-		 * This is needed only for protection faults but the arch code
-		 * is not yet telling us if this is a protection fault or not.
-		 * This still avoids useless tlb flushes for .text page faults
-		 * with threads.
-		 */
-		if (vmf->flags & FAULT_FLAG_WRITE)
-			flush_tlb_fix_spurious_fault(vmf->vma, vmf->address,
-						     vmf->pte);
-	}
+	else
+		fix_spurious_fault(vmf, PGTABLE_LEVEL_PTE);
 unlock:
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
 	return 0;
@@ -6309,7 +6336,10 @@ retry_pud:
 				if (!(ret & VM_FAULT_FALLBACK))
 					return ret;
 			} else {
-				huge_pmd_set_accessed(&vmf);
+				vmf.ptl = pmd_lock(mm, vmf.pmd);
+				if (!huge_pmd_set_accessed(&vmf))
+					fix_spurious_fault(&vmf, PGTABLE_LEVEL_PMD);
+				spin_unlock(vmf.ptl);
 				return 0;
 			}
 		}