Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: will.deacon@arm.com, aneesh.kumar@linux.vnet.ibm.com,
	akpm@linux-foundation.org, npiggin@gmail.com
Cc: linux-arch@vger.kernel.org, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org, peterz@infradead.org,
	linux@armlinux.org.uk, heiko.carstens@de.ibm.com,
	riel@surriel.com
Subject: [PATCH v6 08/18] arm/tlb: Convert to generic mmu_gather
Date: Tue, 19 Feb 2019 11:31:56 +0100
Message-ID: <20190219103233.324160077@infradead.org> (raw)
In-Reply-To: <20190219103148.192029670@infradead.org>

Generic mmu_gather provides everything that ARM needs:

 - range tracking
 - RCU table free
 - VM_EXEC tracking
 - VIPT cache flushing

The one notable curiosity is the 'funny' range tracking for classical
ARM in __pte_free_tlb().

Cc: Nick Piggin <npiggin@gmail.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Russell King <linux@armlinux.org.uk>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/arm/include/asm/tlb.h |  254 ++-------------------------------------------
 1 file changed, 13 insertions(+), 241 deletions(-)

--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -33,270 +33,42 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 
-#define MMU_GATHER_BUNDLE	8
-
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 static inline void __tlb_remove_table(void *_table)
 {
 	free_page_and_swap_cache((struct page *)_table);
 }
 
-struct mmu_table_batch {
-	struct rcu_head		rcu;
-	unsigned int		nr;
-	void			*tables[0];
-};
-
-#define MAX_TABLE_BATCH		\
-	((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
-
-extern void tlb_table_flush(struct mmu_gather *tlb);
-extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
-
-#define tlb_remove_entry(tlb, entry)	tlb_remove_table(tlb, entry)
-#else
-#define tlb_remove_entry(tlb, entry)	tlb_remove_page(tlb, entry)
-#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
-
-/*
- * TLB handling.  This allows us to remove pages from the page
- * tables, and efficiently handle the TLB issues.
- */
-struct mmu_gather {
-	struct mm_struct	*mm;
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	struct mmu_table_batch	*batch;
-	unsigned int		need_flush;
-#endif
-	unsigned int		fullmm;
-	struct vm_area_struct	*vma;
-	unsigned long		start, end;
-	unsigned long		range_start;
-	unsigned long		range_end;
-	unsigned int		nr;
-	unsigned int		max;
-	struct page		**pages;
-	struct page		*local[MMU_GATHER_BUNDLE];
-};
-
-DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
-
-/*
- * This is unnecessarily complex.  There's three ways the TLB shootdown
- * code is used:
- *  1. Unmapping a range of vmas.  See zap_page_range(), unmap_region().
- *     tlb->fullmm = 0, and tlb_start_vma/tlb_end_vma will be called.
- *     tlb->vma will be non-NULL.
- *  2. Unmapping all vmas.  See exit_mmap().
- *     tlb->fullmm = 1, and tlb_start_vma/tlb_end_vma will be called.
- *     tlb->vma will be non-NULL.  Additionally, page tables will be freed.
- *  3. Unmapping argument pages.  See shift_arg_pages().
- *     tlb->fullmm = 0, but tlb_start_vma/tlb_end_vma will not be called.
- *     tlb->vma will be NULL.
- */
-static inline void tlb_flush(struct mmu_gather *tlb)
-{
-	if (tlb->fullmm || !tlb->vma)
-		flush_tlb_mm(tlb->mm);
-	else if (tlb->range_end > 0) {
-		flush_tlb_range(tlb->vma, tlb->range_start, tlb->range_end);
-		tlb->range_start = TASK_SIZE;
-		tlb->range_end = 0;
-	}
-}
-
-static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr)
-{
-	if (!tlb->fullmm) {
-		if (addr < tlb->range_start)
-			tlb->range_start = addr;
-		if (addr + PAGE_SIZE > tlb->range_end)
-			tlb->range_end = addr + PAGE_SIZE;
-	}
-}
-
-static inline void __tlb_alloc_page(struct mmu_gather *tlb)
-{
-	unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
-
-	if (addr) {
-		tlb->pages = (void *)addr;
-		tlb->max = PAGE_SIZE / sizeof(struct page *);
-	}
-}
-
-static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
-	tlb_flush(tlb);
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	tlb_table_flush(tlb);
-#endif
-}
-
-static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-	free_pages_and_swap_cache(tlb->pages, tlb->nr);
-	tlb->nr = 0;
-	if (tlb->pages == tlb->local)
-		__tlb_alloc_page(tlb);
-}
-
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-	tlb_flush_mmu_tlbonly(tlb);
-	tlb_flush_mmu_free(tlb);
-}
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-			unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-	tlb->fullmm = !(start | (end+1));
-	tlb->start = start;
-	tlb->end = end;
-	tlb->vma = NULL;
-	tlb->max = ARRAY_SIZE(tlb->local);
-	tlb->pages = tlb->local;
-	tlb->nr = 0;
-	__tlb_alloc_page(tlb);
+#include <asm-generic/tlb.h>
 
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	tlb->batch = NULL;
+#ifndef CONFIG_HAVE_RCU_TABLE_FREE
+#define tlb_remove_table(tlb, entry) tlb_remove_page(tlb, entry)
 #endif
-}
-
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
-			unsigned long start, unsigned long end, bool force)
-{
-	if (force) {
-		tlb->range_start = start;
-		tlb->range_end = end;
-	}
-
-	tlb_flush_mmu(tlb);
 
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-
-	if (tlb->pages != tlb->local)
-		free_pages((unsigned long)tlb->pages, 0);
-}
-
-/*
- * Memorize the range for the TLB flush.
- */
 static inline void
-tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long addr)
-{
-	tlb_add_flush(tlb, addr);
-}
-
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
-	tlb_remove_tlb_entry(tlb, ptep, address)
-/*
- * In the case of tlb vma handling, we can optimise these away in the
- * case where we're doing a full MM flush.  When we're doing a munmap,
- * the vmas are adjusted to only cover the region to be torn down.
- */
-static inline void
-tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm) {
-		flush_cache_range(vma, vma->vm_start, vma->vm_end);
-		tlb->vma = vma;
-		tlb->range_start = TASK_SIZE;
-		tlb->range_end = 0;
-	}
-}
-
-static inline void
-tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm)
-		tlb_flush(tlb);
-}
-
-static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	tlb->pages[tlb->nr++] = page;
-	VM_WARN_ON(tlb->nr > tlb->max);
-	if (tlb->nr == tlb->max)
-		return true;
-	return false;
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	if (__tlb_remove_page(tlb, page))
-		tlb_flush_mmu(tlb);
-}
-
-static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
-					  struct page *page, int page_size)
-{
-	return __tlb_remove_page(tlb, page);
-}
-
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
-					struct page *page, int page_size)
-{
-	return tlb_remove_page(tlb, page);
-}
-
-static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
-	unsigned long addr)
+__pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr)
 {
 	pgtable_page_dtor(pte);
 
-#ifdef CONFIG_ARM_LPAE
-	tlb_add_flush(tlb, addr);
-#else
+#ifndef CONFIG_ARM_LPAE
 	/*
 	 * With the classic ARM MMU, a pte page has two corresponding pmd
 	 * entries, each covering 1MB.
 	 */
-	addr &= PMD_MASK;
-	tlb_add_flush(tlb, addr + SZ_1M - PAGE_SIZE);
-	tlb_add_flush(tlb, addr + SZ_1M);
+	addr = (addr & PMD_MASK) + SZ_1M;
+	__tlb_adjust_range(tlb, addr - PAGE_SIZE, 2 * PAGE_SIZE);
 #endif
 
-	tlb_remove_entry(tlb, pte);
-}
-
-static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
-				  unsigned long addr)
-{
-#ifdef CONFIG_ARM_LPAE
-	tlb_add_flush(tlb, addr);
-	tlb_remove_entry(tlb, virt_to_page(pmdp));
-#endif
+	tlb_remove_table(tlb, pte);
 }
 
 static inline void
-tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
+__pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
 {
-	tlb_add_flush(tlb, addr);
-}
-
-#define pte_free_tlb(tlb, ptep, addr)	__pte_free_tlb(tlb, ptep, addr)
-#define pmd_free_tlb(tlb, pmdp, addr)	__pmd_free_tlb(tlb, pmdp, addr)
-#define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)
-
-#define tlb_migrate_finish(mm)		do { } while (0)
-
-static inline void tlb_change_page_size(struct mmu_gather *tlb,
-						     unsigned int page_size)
-{
-}
-
-static inline void tlb_flush_remove_tables(struct mm_struct *mm)
-{
-}
+#ifdef CONFIG_ARM_LPAE
+	struct page *page = virt_to_page(pmdp);
 
-static inline void tlb_flush_remove_tables_local(void *arg)
-{
+	tlb_remove_table(tlb, page);
+#endif
 }
 
 #endif /* CONFIG_MMU */



  parent reply index

Thread overview: 44+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-02-19 10:31 [PATCH v6 00/18] generic mmu_gather patches Peter Zijlstra
2019-02-19 10:31 ` [PATCH v6 01/18] asm-generic/tlb: Provide a comment Peter Zijlstra
2019-02-19 10:31 ` [PATCH v6 02/18] asm-generic/tlb: Provide HAVE_MMU_GATHER_PAGE_SIZE Peter Zijlstra
2019-02-19 10:31 ` [PATCH v6 03/18] asm-generic/tlb: Provide generic VIPT cache flush Peter Zijlstra
2019-02-19 10:31 ` [PATCH v6 04/18] asm-generic/tlb: Provide generic tlb_flush() based on flush_tlb_range() Peter Zijlstra
2019-02-19 10:31 ` [PATCH v6 05/18] asm-generic/tlb: Provide generic tlb_flush() based on flush_tlb_mm() Peter Zijlstra
2019-02-19 12:47   ` Will Deacon
2019-02-19 10:31 ` [PATCH v6 06/18] asm-generic/tlb: Conditionally provide tlb_migrate_finish() Peter Zijlstra
2019-02-19 12:47   ` Will Deacon
2019-02-19 13:41     ` Peter Zijlstra
2019-02-20 14:47       ` Will Deacon
2019-02-20 15:02         ` Matthew Wilcox
2019-02-19 10:31 ` [PATCH v6 07/18] asm-generic/tlb: Invert HAVE_RCU_TABLE_INVALIDATE Peter Zijlstra
2019-02-19 10:31 ` Peter Zijlstra [this message]
2019-02-19 10:31 ` [PATCH v6 09/18] ia64/tlb: Conver to generic mmu_gather Peter Zijlstra
2019-02-19 12:47   ` Will Deacon
2019-02-21  2:52   ` Souptick Joarder
2019-02-19 10:31 ` [PATCH v6 10/18] sh/tlb: Convert SH " Peter Zijlstra
2019-12-03 11:19   ` Geert Uytterhoeven
2019-12-04 10:47     ` Peter Zijlstra
2019-12-04 12:32       ` Geert Uytterhoeven
2019-12-04 13:22         ` Guenter Roeck
2019-12-04 15:17           ` Geert Uytterhoeven
2019-12-04 19:03             ` Guenter Roeck
2019-12-04 13:34         ` Peter Zijlstra
2019-12-04 15:07           ` Geert Uytterhoeven
2019-12-04 16:41             ` Peter Zijlstra
2019-12-05 15:26               ` Geert Uytterhoeven
2019-12-05 19:24       ` Rob Landley
2019-12-05 19:23         ` Rich Felker
2019-12-05 19:30       ` John Paul Adrian Glaubitz
2019-12-05 22:56         ` Guenter Roeck
2019-12-06 13:38           ` John Paul Adrian Glaubitz
2019-12-06 14:03             ` Guenter Roeck
2019-02-19 10:31 ` [PATCH v6 11/18] um/tlb: Convert " Peter Zijlstra
2019-02-19 10:32 ` [PATCH v6 12/18] arch/tlb: Clean up simple architectures Peter Zijlstra
2019-02-19 10:32 ` [PATCH v6 13/18] asm-generic/tlb: Introduce HAVE_MMU_GATHER_NO_GATHER Peter Zijlstra
2019-02-19 12:47   ` Will Deacon
2019-02-19 10:32 ` [PATCH v6 14/18] s390/tlb: convert to generic mmu_gather Peter Zijlstra
2019-02-19 12:47   ` Will Deacon
2019-02-19 10:32 ` [PATCH v6 15/18] asm-generic/tlb: Remove arch_tlb*_mmu() Peter Zijlstra
2019-02-19 10:32 ` [PATCH v6 16/18] asm-generic/tlb: Remove HAVE_GENERIC_MMU_GATHER Peter Zijlstra
2019-02-19 10:32 ` [PATCH v6 17/18] asm-generic/tlb: Remove tlb_flush_mmu_free() Peter Zijlstra
2019-02-19 10:32 ` [PATCH v6 18/18] asm-generic/tlb: Remove tlb_table_flush() Peter Zijlstra

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190219103233.324160077@infradead.org \
    --to=peterz@infradead.org \
    --cc=akpm@linux-foundation.org \
    --cc=aneesh.kumar@linux.vnet.ibm.com \
    --cc=heiko.carstens@de.ibm.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux@armlinux.org.uk \
    --cc=npiggin@gmail.com \
    --cc=riel@surriel.com \
    --cc=will.deacon@arm.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-mm linux-mm/ https://lore.kernel.org/linux-mm \
		linux-mm@kvack.org
	public-inbox-index linux-mm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kvack.linux-mm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git