summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorPeter Zijlstra <peterz@infradead.org>2018-09-04 13:18:15 +0200
committerIngo Molnar <mingo@kernel.org>2019-04-03 10:32:42 +0200
commit5f307be18b32aeff7bbad540c0d3897ecedbeb56 (patch)
tree1e0d7ff96e913739cecc5a654a41f88ef76e4e3d
parente7fd28a706bfaf9cd65dccf18140187f7ad04839 (diff)
downloadlinux-5f307be18b32aeff7bbad540c0d3897ecedbeb56.tar.bz2
asm-generic/tlb, arch: Provide generic tlb_flush() based on flush_tlb_range()
Provide a generic tlb_flush() implementation that relies on flush_tlb_range(). This is a little awkward because flush_tlb_range() assumes a VMA for range invalidation, but we no longer have one. Audit of all flush_tlb_range() implementations shows only vma->vm_mm and vma->vm_flags are used, and of the latter only VM_EXEC (I-TLB invalidates) and VM_HUGETLB (large TLB invalidate) are used. Therefore, track VM_EXEC and VM_HUGETLB in two more bits, and create a 'fake' VMA. This allows architectures that have a reasonably efficient flush_tlb_range() to not require any additional effort. No change in behavior intended. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Will Deacon <will.deacon@arm.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Nick Piggin <npiggin@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@surriel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Ingo Molnar <mingo@kernel.org>
-rw-r--r--arch/arm64/include/asm/tlb.h1
-rw-r--r--arch/powerpc/include/asm/tlb.h1
-rw-r--r--arch/riscv/include/asm/tlb.h1
-rw-r--r--arch/x86/include/asm/tlb.h1
-rw-r--r--include/asm-generic/tlb.h95
5 files changed, 87 insertions, 12 deletions
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 106fdc951b6e..37603b5616a5 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -27,6 +27,7 @@ static inline void __tlb_remove_table(void *_table)
free_page_and_swap_cache((struct page *)_table);
}
+#define tlb_flush tlb_flush
static void tlb_flush(struct mmu_gather *tlb);
#include <asm-generic/tlb.h>
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index b018e9f9b491..34fba1ce27f7 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -28,6 +28,7 @@
#define tlb_end_vma(tlb, vma) do { } while (0)
#define __tlb_remove_tlb_entry __tlb_remove_tlb_entry
+#define tlb_flush tlb_flush
extern void tlb_flush(struct mmu_gather *tlb);
/* Get the generic bits... */
diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
index 439dc7072e05..1ad8d093c58b 100644
--- a/arch/riscv/include/asm/tlb.h
+++ b/arch/riscv/include/asm/tlb.h
@@ -18,6 +18,7 @@ struct mmu_gather;
static void tlb_flush(struct mmu_gather *tlb);
+#define tlb_flush tlb_flush
#include <asm-generic/tlb.h>
static inline void tlb_flush(struct mmu_gather *tlb)
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 404b8b1d44f5..f23e7aaff4cd 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -6,6 +6,7 @@
#define tlb_end_vma(tlb, vma) do { } while (0)
#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
+#define tlb_flush tlb_flush
static inline void tlb_flush(struct mmu_gather *tlb);
#include <asm-generic/tlb.h>
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index f0aa53db5e60..e6a4c407be6c 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -95,7 +95,7 @@
* flush the entire TLB irrespective of the range. For instance
* x86-PAE needs this when changing top-level entries.
*
- * And requires the architecture to provide and implement tlb_flush().
+ * And allows the architecture to provide and implement tlb_flush():
*
* tlb_flush() may, in addition to the above mentioned mmu_gather fields, make
* use of:
@@ -111,7 +111,10 @@
*
* - tlb_get_unmap_shift() / tlb_get_unmap_size()
*
- * returns the smallest TLB entry size unmapped in this range
+ * returns the smallest TLB entry size unmapped in this range.
+ *
+ * If an architecture does not provide tlb_flush() a default implementation
+ * based on flush_tlb_range() will be used.
*
* Additionally there are a few opt-in features:
*
@@ -245,6 +248,12 @@ struct mmu_gather {
unsigned int cleared_puds : 1;
unsigned int cleared_p4ds : 1;
+ /*
+ * tracks VM_EXEC | VM_HUGETLB in tlb_start_vma
+ */
+ unsigned int vma_exec : 1;
+ unsigned int vma_huge : 1;
+
unsigned int batch_count;
struct mmu_gather_batch *active;
@@ -286,8 +295,59 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
tlb->cleared_pmds = 0;
tlb->cleared_puds = 0;
tlb->cleared_p4ds = 0;
+ /*
+ * Do not reset mmu_gather::vma_* fields here, we do not
+ * call into tlb_start_vma() again to set them if there is an
+ * intermediate flush.
+ */
+}
+
+#ifndef tlb_flush
+
+#if defined(tlb_start_vma) || defined(tlb_end_vma)
+#error Default tlb_flush() relies on default tlb_start_vma() and tlb_end_vma()
+#endif
+
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+ if (tlb->fullmm || tlb->need_flush_all) {
+ flush_tlb_mm(tlb->mm);
+ } else if (tlb->end) {
+ struct vm_area_struct vma = {
+ .vm_mm = tlb->mm,
+ .vm_flags = (tlb->vma_exec ? VM_EXEC : 0) |
+ (tlb->vma_huge ? VM_HUGETLB : 0),
+ };
+
+ flush_tlb_range(&vma, tlb->start, tlb->end);
+ }
+}
+
+static inline void
+tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+ /*
+ * flush_tlb_range() implementations that look at VM_HUGETLB (tile,
+ * mips-4k) flush only large pages.
+ *
+ * flush_tlb_range() implementations that flush I-TLB also flush D-TLB
+ * (tile, xtensa, arm), so it's ok to just add VM_EXEC to an existing
+ * range.
+ *
+ * We rely on tlb_end_vma() to issue a flush, such that when we reset
+ * these values the batch is empty.
+ */
+ tlb->vma_huge = !!(vma->vm_flags & VM_HUGETLB);
+ tlb->vma_exec = !!(vma->vm_flags & VM_EXEC);
}
+#else
+
+static inline void
+tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
+
+#endif
+
static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
{
if (!tlb->end)
@@ -357,19 +417,30 @@ static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb)
* the vmas are adjusted to only cover the region to be torn down.
*/
#ifndef tlb_start_vma
-#define tlb_start_vma(tlb, vma) \
-do { \
- if (!tlb->fullmm) \
- flush_cache_range(vma, vma->vm_start, vma->vm_end); \
-} while (0)
+static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+ if (tlb->fullmm)
+ return;
+
+ tlb_update_vma_flags(tlb, vma);
+ flush_cache_range(vma, vma->vm_start, vma->vm_end);
+}
#endif
#ifndef tlb_end_vma
-#define tlb_end_vma(tlb, vma) \
-do { \
- if (!tlb->fullmm) \
- tlb_flush_mmu_tlbonly(tlb); \
-} while (0)
+static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+ if (tlb->fullmm)
+ return;
+
+ /*
+ * Do a TLB flush and reset the range at VMA boundaries; this avoids
+ * the ranges growing with the unused space between consecutive VMAs,
+ * but also the mmu_gather::vma_* flags from tlb_start_vma() rely on
+ * this.
+ */
+ tlb_flush_mmu_tlbonly(tlb);
+}
#endif
#ifndef __tlb_remove_tlb_entry