summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorWill Deacon <will@kernel.org>2021-01-27 23:53:44 +0000
committerPeter Zijlstra <peterz@infradead.org>2021-01-29 20:02:29 +0100
commitd8b450530b90f8845ab962af18b8a10ed77fc889 (patch)
tree5399ddb38a5f0a743c07866a32bec5ce46175b61
parentae8eba8b5d723a4ca543024b6e51f4d0f4fb6b6b (diff)
tlb: mmu_gather: Introduce tlb_gather_mmu_fullmm()
Passing the range '0, -1' to tlb_gather_mmu() sets the 'fullmm' flag, which indicates that the mm_struct being operated on is going away. In this case, some architectures (such as arm64) can elide TLB invalidation by ensuring that the TLB tag (ASID) associated with this mm is not immediately reclaimed. Although this behaviour is documented in asm-generic/tlb.h, it's subtle and easily missed. Introduce tlb_gather_mmu_fullmm() to make it clearer that this is for the entire mm and WARN() if tlb_gather_mmu() is called with the 'fullmm' address range. Signed-off-by: Will Deacon <will@kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Yu Zhao <yuzhao@google.com> Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Linus Torvalds <torvalds@linux-foundation.org> Link: https://lkml.kernel.org/r/20210127235347.1402-4-will@kernel.org
-rw-r--r--include/asm-generic/tlb.h6
-rw-r--r--include/linux/mm_types.h1
-rw-r--r--mm/mmap.c2
-rw-r--r--mm/mmu_gather.c16
4 files changed, 20 insertions, 5 deletions
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 6661ee1cff47..2c68a545ffa7 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -46,7 +46,9 @@
*
* The mmu_gather API consists of:
*
- * - tlb_gather_mmu() / tlb_finish_mmu(); start and finish a mmu_gather
+ * - tlb_gather_mmu() / tlb_gather_mmu_fullmm() / tlb_finish_mmu()
+ *
+ * start and finish a mmu_gather
*
* Finish in particular will issue a (final) TLB invalidate and free
* all (remaining) queued pages.
@@ -91,7 +93,7 @@
*
* - mmu_gather::fullmm
*
- * A flag set by tlb_gather_mmu() to indicate we're going to free
+ * A flag set by tlb_gather_mmu_fullmm() to indicate we're going to free
* the entire mm; this allows a number of optimizations.
*
* - We can ignore tlb_{start,end}_vma(); because we don't
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 1fe6a51298a6..e49868bc12a7 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -590,6 +590,7 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
struct mmu_gather;
extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
unsigned long start, unsigned long end);
+extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm);
extern void tlb_finish_mmu(struct mmu_gather *tlb);
static inline void init_tlb_flush_pending(struct mm_struct *mm)
diff --git a/mm/mmap.c b/mm/mmap.c
index 7a9f493a4b83..4eac7c63edbe 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -3214,7 +3214,7 @@ void exit_mmap(struct mm_struct *mm)
lru_add_drain();
flush_cache_mm(mm);
- tlb_gather_mmu(&tlb, mm, 0, -1);
+ tlb_gather_mmu_fullmm(&tlb, mm);
/* update_hiwater_rss(mm) here? but nobody should be looking */
/* Use -1 here to ensure all VMAs in the mm are unmapped */
unmap_vmas(&tlb, vma, 0, -1);
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index b0be5a7aa08f..5f5e45d9eb50 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -261,8 +261,8 @@ void tlb_flush_mmu(struct mmu_gather *tlb)
* respectively when @mm is without users and we're going to destroy
* the full address space (exit/execve).
*/
-void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
- unsigned long start, unsigned long end)
+static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+ unsigned long start, unsigned long end)
{
tlb->mm = mm;
@@ -287,6 +287,18 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
inc_tlb_flush_pending(tlb->mm);
}
+void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+ unsigned long start, unsigned long end)
+{
+ WARN_ON(!(start | (end + 1))); /* Use _fullmm() instead */
+ __tlb_gather_mmu(tlb, mm, start, end);
+}
+
+void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm)
+{
+ __tlb_gather_mmu(tlb, mm, 0, -1);
+}
+
/**
* tlb_finish_mmu - finish an mmu_gather structure
* @tlb: the mmu_gather structure to finish