summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPeter Zijlstra <peterz@infradead.org>2018-09-04 10:43:14 +0200
committerIngo Molnar <mingo@kernel.org>2019-04-03 10:32:39 +0200
commitdea2434c23c102b3e7d320849ec1cfeb432edb60 (patch)
tree46af47eb623e1c3fdc68e877dd8f0afb2f8c4f2b
parent5e7a8ca319268a70a6c7c3c1fde5bea38e1e5539 (diff)
asm-generic/tlb: Provide a comment
Write a comment explaining some of this.. 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--include/asm-generic/tlb.h119
1 files changed, 116 insertions, 3 deletions
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 6be86c1c5c58..f1594ba8b2de 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -22,6 +22,118 @@
#ifdef CONFIG_MMU
+/*
+ * Generic MMU-gather implementation.
+ *
+ * The mmu_gather data structure is used by the mm code to implement the
+ * correct and efficient ordering of freeing pages and TLB invalidations.
+ *
+ * This correct ordering is:
+ *
+ * 1) unhook page
+ * 2) TLB invalidate page
+ * 3) free page
+ *
+ * That is, we must never free a page before we have ensured there are no live
+ * translations left to it. Otherwise it might be possible to observe (or
+ * worse, change) the page content after it has been reused.
+ *
+ * The mmu_gather API consists of:
+ *
+ * - tlb_gather_mmu() / tlb_finish_mmu(); start and finish a mmu_gather
+ *
+ * Finish in particular will issue a (final) TLB invalidate and free
+ * all (remaining) queued pages.
+ *
+ * - tlb_start_vma() / tlb_end_vma(); marks the start / end of a VMA
+ *
+ * Defaults to flushing at tlb_end_vma() to reset the range; helps when
+ * there's large holes between the VMAs.
+ *
+ * - tlb_remove_page() / __tlb_remove_page()
+ * - tlb_remove_page_size() / __tlb_remove_page_size()
+ *
+ * __tlb_remove_page_size() is the basic primitive that queues a page for
+ * freeing. __tlb_remove_page() assumes PAGE_SIZE. Both will return a
+ * boolean indicating if the queue is (now) full and a call to
+ * tlb_flush_mmu() is required.
+ *
+ * tlb_remove_page() and tlb_remove_page_size() imply the call to
+ * tlb_flush_mmu() when required and has no return value.
+ *
+ * - tlb_remove_check_page_size_change()
+ *
+ * call before __tlb_remove_page*() to set the current page-size; implies a
+ * possible tlb_flush_mmu() call.
+ *
+ * - tlb_flush_mmu() / tlb_flush_mmu_tlbonly() / tlb_flush_mmu_free()
+ *
+ * tlb_flush_mmu_tlbonly() - does the TLB invalidate (and resets
+ * related state, like the range)
+ *
+ * tlb_flush_mmu_free() - frees the queued pages; make absolutely
+ * sure no additional tlb_remove_page()
+ * calls happen between _tlbonly() and this.
+ *
+ * tlb_flush_mmu() - the above two calls.
+ *
+ * - mmu_gather::fullmm
+ *
+ * A flag set by tlb_gather_mmu() 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
+ * care about ranges. Everything will be shot down.
+ *
+ * - (RISC) architectures that use ASIDs can cycle to a new ASID
+ * and delay the invalidation until ASID space runs out.
+ *
+ * - mmu_gather::need_flush_all
+ *
+ * A flag that can be set by the arch code if it wants to force
+ * 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().
+ *
+ * tlb_flush() may, in addition to the above mentioned mmu_gather fields, make
+ * use of:
+ *
+ * - mmu_gather::start / mmu_gather::end
+ *
+ * which provides the range that needs to be flushed to cover the pages to
+ * be freed.
+ *
+ * - mmu_gather::freed_tables
+ *
+ * set when we freed page table pages
+ *
+ * - tlb_get_unmap_shift() / tlb_get_unmap_size()
+ *
+ * returns the smallest TLB entry size unmapped in this range
+ *
+ * Additionally there are a few opt-in features:
+ *
+ * HAVE_RCU_TABLE_FREE
+ *
+ * This provides tlb_remove_table(), to be used instead of tlb_remove_page()
+ * for page directores (__p*_free_tlb()). This provides separate freeing of
+ * the page-table pages themselves in a semi-RCU fashion (see comment below).
+ * Useful if your architecture doesn't use IPIs for remote TLB invalidates
+ * and therefore doesn't naturally serialize with software page-table walkers.
+ *
+ * When used, an architecture is expected to provide __tlb_remove_table()
+ * which does the actual freeing of these pages.
+ *
+ * HAVE_RCU_TABLE_INVALIDATE
+ *
+ * This makes HAVE_RCU_TABLE_FREE call tlb_flush_mmu_tlbonly() before freeing
+ * the page-table pages. Required if you use HAVE_RCU_TABLE_FREE and your
+ * architecture uses the Linux page-tables natively.
+ *
+ */
+#define HAVE_GENERIC_MMU_GATHER
+
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
/*
* Semi RCU freeing of the page directories.
@@ -89,14 +201,17 @@ struct mmu_gather_batch {
*/
#define MAX_GATHER_BATCH_COUNT (10000UL/MAX_GATHER_BATCH)
-/* struct mmu_gather is an opaque type used by the mm code for passing around
+/*
+ * struct mmu_gather is an opaque type used by the mm code for passing around
* any data needed by arch specific code for tlb_remove_page.
*/
struct mmu_gather {
struct mm_struct *mm;
+
#ifdef CONFIG_HAVE_RCU_TABLE_FREE
struct mmu_table_batch *batch;
#endif
+
unsigned long start;
unsigned long end;
/*
@@ -131,8 +246,6 @@ struct mmu_gather {
int page_size;
};
-#define HAVE_GENERIC_MMU_GATHER
-
void arch_tlb_gather_mmu(struct mmu_gather *tlb,
struct mm_struct *mm, unsigned long start, unsigned long end);
void tlb_flush_mmu(struct mmu_gather *tlb);