summaryrefslogtreecommitdiff
path: root/arch/powerpc
diff options
context:
space:
mode:
authorNicholas Piggin <npiggin@gmail.com>2018-06-15 04:38:37 +0300
committerMichael Ellerman <mpe@ellerman.id.au>2018-06-19 14:28:21 +0300
commit02390f66bd2362df114a0a0770d80ec33061f6d1 (patch)
treeb9de0f001ff1e469303719a29ec156b06e3f3e23 /arch/powerpc
parent69a8405999aa1c489de4b8d349468f0c2b83f093 (diff)
downloadlinux-02390f66bd2362df114a0a0770d80ec33061f6d1.tar.xz
powerpc/64s/radix: Fix MADV_[FREE|DONTNEED] TLB flush miss problem with THP
The patch 99baac21e4 ("mm: fix MADV_[FREE|DONTNEED] TLB flush miss problem") added a force flush mode to the mmu_gather flush, which unconditionally flushes the entire address range being invalidated (even if actual ptes only covered a smaller range), to solve a problem with concurrent threads invalidating the same PTEs causing them to miss TLBs that need flushing. This does not work with powerpc that invalidates mmu_gather batches according to page size. Have powerpc flush all possible page sizes in the range if it encounters this concurrency condition. Patch 4647706ebe ("mm: always flush VMA ranges affected by zap_page_range") does add a TLB flush for all page sizes on powerpc for the zap_page_range case, but that is to be removed and replaced with the mmu_gather flush to avoid redundant flushing. It is also thought to not cover other obscure race conditions: https://lkml.kernel.org/r/BD3A0EBE-ECF4-41D4-87FA-C755EA9AB6BD@gmail.com Hash does not have a problem because it invalidates TLBs inside the page table locks. Reported-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Diffstat (limited to 'arch/powerpc')
-rw-r--r--arch/powerpc/mm/tlb-radix.c96
1 files changed, 75 insertions, 21 deletions
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 67a6e86d3e7e..a734e486664d 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -689,22 +689,17 @@ EXPORT_SYMBOL(radix__flush_tlb_kernel_range);
static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
static unsigned long tlb_local_single_page_flush_ceiling __read_mostly = POWER9_TLB_SETS_RADIX * 2;
-void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
- unsigned long end)
+static inline void __radix__flush_tlb_range(struct mm_struct *mm,
+ unsigned long start, unsigned long end,
+ bool flush_all_sizes)
{
- struct mm_struct *mm = vma->vm_mm;
unsigned long pid;
unsigned int page_shift = mmu_psize_defs[mmu_virtual_psize].shift;
unsigned long page_size = 1UL << page_shift;
unsigned long nr_pages = (end - start) >> page_shift;
bool local, full;
-#ifdef CONFIG_HUGETLB_PAGE
- if (is_vm_hugetlb_page(vma))
- return radix__flush_hugetlb_tlb_range(vma, start, end);
-#endif
-
pid = mm->context.id;
if (unlikely(pid == MMU_NO_CONTEXT))
return;
@@ -738,37 +733,64 @@ is_local:
_tlbie_pid(pid, RIC_FLUSH_TLB);
}
} else {
- bool hflush = false;
+ bool hflush = flush_all_sizes;
+ bool gflush = flush_all_sizes;
unsigned long hstart, hend;
+ unsigned long gstart, gend;
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- hstart = (start + HPAGE_PMD_SIZE - 1) >> HPAGE_PMD_SHIFT;
- hend = end >> HPAGE_PMD_SHIFT;
- if (hstart < hend) {
- hstart <<= HPAGE_PMD_SHIFT;
- hend <<= HPAGE_PMD_SHIFT;
+ if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
hflush = true;
+
+ if (hflush) {
+ hstart = (start + PMD_SIZE - 1) & PMD_MASK;
+ hend = end & PMD_MASK;
+ if (hstart == hend)
+ hflush = false;
+ }
+
+ if (gflush) {
+ gstart = (start + PUD_SIZE - 1) & PUD_MASK;
+ gend = end & PUD_MASK;
+ if (gstart == gend)
+ gflush = false;
}
-#endif
asm volatile("ptesync": : :"memory");
if (local) {
__tlbiel_va_range(start, end, pid, page_size, mmu_virtual_psize);
if (hflush)
__tlbiel_va_range(hstart, hend, pid,
- HPAGE_PMD_SIZE, MMU_PAGE_2M);
+ PMD_SIZE, MMU_PAGE_2M);
+ if (gflush)
+ __tlbiel_va_range(gstart, gend, pid,
+ PUD_SIZE, MMU_PAGE_1G);
asm volatile("ptesync": : :"memory");
} else {
__tlbie_va_range(start, end, pid, page_size, mmu_virtual_psize);
if (hflush)
__tlbie_va_range(hstart, hend, pid,
- HPAGE_PMD_SIZE, MMU_PAGE_2M);
+ PMD_SIZE, MMU_PAGE_2M);
+ if (gflush)
+ __tlbie_va_range(gstart, gend, pid,
+ PUD_SIZE, MMU_PAGE_1G);
fixup_tlbie();
asm volatile("eieio; tlbsync; ptesync": : :"memory");
}
}
preempt_enable();
}
+
+void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end)
+
+{
+#ifdef CONFIG_HUGETLB_PAGE
+ if (is_vm_hugetlb_page(vma))
+ return radix__flush_hugetlb_tlb_range(vma, start, end);
+#endif
+
+ __radix__flush_tlb_range(vma->vm_mm, start, end, false);
+}
EXPORT_SYMBOL(radix__flush_tlb_range);
static int radix_get_mmu_psize(int page_size)
@@ -837,6 +859,8 @@ void radix__tlb_flush(struct mmu_gather *tlb)
int psize = 0;
struct mm_struct *mm = tlb->mm;
int page_size = tlb->page_size;
+ unsigned long start = tlb->start;
+ unsigned long end = tlb->end;
/*
* if page size is not something we understand, do a full mm flush
@@ -847,15 +871,45 @@ void radix__tlb_flush(struct mmu_gather *tlb)
*/
if (tlb->fullmm) {
__flush_all_mm(mm, true);
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)
+ } else if (mm_tlb_flush_nested(mm)) {
+ /*
+ * If there is a concurrent invalidation that is clearing ptes,
+ * then it's possible this invalidation will miss one of those
+ * cleared ptes and miss flushing the TLB. If this invalidate
+ * returns before the other one flushes TLBs, that can result
+ * in it returning while there are still valid TLBs inside the
+ * range to be invalidated.
+ *
+ * See mm/memory.c:tlb_finish_mmu() for more details.
+ *
+ * The solution to this is ensure the entire range is always
+ * flushed here. The problem for powerpc is that the flushes
+ * are page size specific, so this "forced flush" would not
+ * do the right thing if there are a mix of page sizes in
+ * the range to be invalidated. So use __flush_tlb_range
+ * which invalidates all possible page sizes in the range.
+ *
+ * PWC flush probably is not be required because the core code
+ * shouldn't free page tables in this path, but accounting
+ * for the possibility makes us a bit more robust.
+ *
+ * need_flush_all is an uncommon case because page table
+ * teardown should be done with exclusive locks held (but
+ * after locks are dropped another invalidate could come
+ * in), it could be optimized further if necessary.
+ */
+ if (!tlb->need_flush_all)
+ __radix__flush_tlb_range(mm, start, end, true);
+ else
+ radix__flush_all_mm(mm);
+#endif
} else if ( (psize = radix_get_mmu_psize(page_size)) == -1) {
if (!tlb->need_flush_all)
radix__flush_tlb_mm(mm);
else
radix__flush_all_mm(mm);
} else {
- unsigned long start = tlb->start;
- unsigned long end = tlb->end;
-
if (!tlb->need_flush_all)
radix__flush_tlb_range_psize(mm, start, end, psize);
else