lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Mon,  5 Oct 2020 15:40:06 +0000
From:   Kalesh Singh <kaleshsingh@...gle.com>
To:     unlisted-recipients:; (no To-header on input)
Cc:     surenb@...gle.com, minchan@...gle.com, joelaf@...gle.com,
        lokeshgidra@...gle.com, kaleshsingh@...gle.com,
        kernel-team@...roid.com, kernel test robot <lkp@...el.com>,
        Catalin Marinas <catalin.marinas@....com>,
        Will Deacon <will@...nel.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
        x86@...nel.org, "H. Peter Anvin" <hpa@...or.com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Shuah Khan <shuah@...nel.org>,
        "Aneesh Kumar K.V" <aneesh.kumar@...ux.ibm.com>,
        Kees Cook <keescook@...omium.org>,
        Peter Zijlstra <peterz@...radead.org>,
        Sami Tolvanen <samitolvanen@...gle.com>,
        Masahiro Yamada <masahiroy@...nel.org>,
        Arnd Bergmann <arnd@...db.de>,
        Krzysztof Kozlowski <krzk@...nel.org>,
        Frederic Weisbecker <frederic@...nel.org>,
        Hassan Naveed <hnaveed@...ecomp.com>,
        Christian Brauner <christian.brauner@...ntu.com>,
        Stephen Boyd <sboyd@...nel.org>,
        Mark Rutland <mark.rutland@....com>,
        Mike Rapoport <rppt@...nel.org>, Gavin Shan <gshan@...hat.com>,
        Mark Brown <broonie@...nel.org>,
        Chris von Recklinghausen <crecklin@...hat.com>,
        Jia He <justin.he@....com>, Zhenyu Ye <yezhenyu2@...wei.com>,
        John Hubbard <jhubbard@...dia.com>,
        Sandipan Das <sandipan@...ux.ibm.com>,
        Ralph Campbell <rcampbell@...dia.com>,
        "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
        Dave Hansen <dave.hansen@...el.com>,
        Masami Hiramatsu <mhiramat@...nel.org>,
        Brian Geffon <bgeffon@...gle.com>,
        Ram Pai <linuxram@...ibm.com>,
        SeongJae Park <sjpark@...zon.de>, linux-kernel@...r.kernel.org,
        linux-arm-kernel@...ts.infradead.org, linux-mm@...ck.org,
        linux-kselftest@...r.kernel.org
Subject: [PATCH v3 3/5] mm: Speedup mremap on 1GB or larger regions

Android needs to move large memory regions for garbage collection.
The GC requires moving physical pages of multi-gigabyte heap
using mremap. During this move, the application threads have to
be paused for correctness. It is critical to keep this pause as
short as possible to avoid jitters during user interaction.

Optimize mremap for >= 1GB-sized regions by moving at the PUD/PGD
level if the source and destination addresses are PUD-aligned.
For CONFIG_PGTABLE_LEVELS == 3, moving at the PUD level in effect moves
PGD entries, since the PUD entry is “folded back” onto the PGD entry.
Add HAVE_MOVE_PUD so that architectures where moving at the PUD level
isn't supported/tested can turn this off by not selecting the config.

Fix build test error from v1 of this series reported by
kernel test robot in [1].

[1] https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org/thread/CKPGL4FH4NG7TGH2CVYX2UX76L25BTA3/

Signed-off-by: Kalesh Singh <kaleshsingh@...gle.com>
Reported-by: kernel test robot <lkp@...el.com>
---
Changes in v2:
  - Update commit message with description of Android GC's use case.
  - Move set_pud_at() to a separate patch.
  - Use switch() instead of ifs in move_pgt_entry()
  - Fix build test error reported by kernel test robot on x86_64 in [1].
    Guard move_huge_pmd() with IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE),
    since this section doesn't get optimized out in the kernel test
    robot's build test when HAVE_MOVE_PUD is enabled.
  - Keep WARN_ON_ONCE(1) instead of BUILD_BUG() for the aforementioned
    reason.

Changes in v3:
  - Move get_old_pud() and alloc_new_pud() out of
    #ifdef CONFIG_HAVE_MOVE_PUD.
  - Have get_old_pmd() and alloc_new_pmd() use get_old_pud() and
    alloc_old_pud().
  - Use switch() in get_extent() instead of ifs.
  - Add BUILD_BUG() to default case of get_extent().
  - Replace #ifdef CONFIG_HAVE_MOVE_PMD/PUD in move_page_tables() with
    IS_ENABLED(CONFIG_HAVE_MOVE_PMD/PUD).
  - Make lines 80 cols or less, where they don’t need to be longer.
  - s/=  /= /g (Fixed double spaces after '=').

 arch/Kconfig |   7 ++
 mm/mremap.c  | 230 ++++++++++++++++++++++++++++++++++++++++++---------
 2 files changed, 197 insertions(+), 40 deletions(-)

diff --git a/arch/Kconfig b/arch/Kconfig
index af14a567b493..5eabaa00bf9b 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -602,6 +602,13 @@ config HAVE_IRQ_TIME_ACCOUNTING
 	  Archs need to ensure they use a high enough resolution clock to
 	  support irq time accounting and then call enable_sched_clock_irqtime().
 
+config HAVE_MOVE_PUD
+	bool
+	help
+	  Architectures that select this are able to move page tables at the
+	  PUD level. If there are only 3 page table levels, the move effectively
+	  happens at the PGD level.
+
 config HAVE_MOVE_PMD
 	bool
 	help
diff --git a/mm/mremap.c b/mm/mremap.c
index 138abbae4f75..078f731277b6 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -30,12 +30,11 @@
 
 #include "internal.h"
 
-static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
+static pud_t *get_old_pud(struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
 	pud_t *pud;
-	pmd_t *pmd;
 
 	pgd = pgd_offset(mm, addr);
 	if (pgd_none_or_clear_bad(pgd))
@@ -49,6 +48,18 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
 	if (pud_none_or_clear_bad(pud))
 		return NULL;
 
+	return pud;
+}
+
+static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
+{
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pud = get_old_pud(mm, addr);
+	if (!pud)
+		return NULL;
+
 	pmd = pmd_offset(pud, addr);
 	if (pmd_none(*pmd))
 		return NULL;
@@ -56,19 +67,27 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
 	return pmd;
 }
 
-static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
+static pud_t *alloc_new_pud(struct mm_struct *mm, struct vm_area_struct *vma,
 			    unsigned long addr)
 {
 	pgd_t *pgd;
 	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
 
 	pgd = pgd_offset(mm, addr);
 	p4d = p4d_alloc(mm, pgd, addr);
 	if (!p4d)
 		return NULL;
-	pud = pud_alloc(mm, p4d, addr);
+
+	return pud_alloc(mm, p4d, addr);
+}
+
+static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
+			    unsigned long addr)
+{
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pud = alloc_new_pud(mm, vma, addr);
 	if (!pud)
 		return NULL;
 
@@ -249,14 +268,148 @@ static bool move_normal_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 
 	return true;
 }
+#else
+static inline bool move_normal_pmd(struct vm_area_struct *vma,
+		unsigned long old_addr, unsigned long new_addr, pmd_t *old_pmd,
+		pmd_t *new_pmd)
+{
+	return false;
+}
 #endif
 
+#ifdef CONFIG_HAVE_MOVE_PUD
+static bool move_normal_pud(struct vm_area_struct *vma, unsigned long old_addr,
+		  unsigned long new_addr, pud_t *old_pud, pud_t *new_pud)
+{
+	spinlock_t *old_ptl, *new_ptl;
+	struct mm_struct *mm = vma->vm_mm;
+	pud_t pud;
+
+	/*
+	 * The destination pud shouldn't be established, free_pgtables()
+	 * should have released it.
+	 */
+	if (WARN_ON_ONCE(!pud_none(*new_pud)))
+		return false;
+
+	/*
+	 * We don't have to worry about the ordering of src and dst
+	 * ptlocks because exclusive mmap_lock prevents deadlock.
+	 */
+	old_ptl = pud_lock(vma->vm_mm, old_pud);
+	new_ptl = pud_lockptr(mm, new_pud);
+	if (new_ptl != old_ptl)
+		spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
+
+	/* Clear the pud */
+	pud = *old_pud;
+	pud_clear(old_pud);
+
+	VM_BUG_ON(!pud_none(*new_pud));
+
+	/* Set the new pud */
+	set_pud_at(mm, new_addr, new_pud, pud);
+	flush_tlb_range(vma, old_addr, old_addr + PUD_SIZE);
+	if (new_ptl != old_ptl)
+		spin_unlock(new_ptl);
+	spin_unlock(old_ptl);
+
+	return true;
+}
+#else
+static inline bool move_normal_pud(struct vm_area_struct *vma,
+		unsigned long old_addr, unsigned long new_addr, pud_t *old_pud,
+		pud_t *new_pud)
+{
+	return false;
+}
+#endif
+
+enum pgt_entry {
+	NORMAL_PMD,
+	HPAGE_PMD,
+	NORMAL_PUD,
+};
+
+/*
+ * Returns an extent of the corresponding size for the pgt_entry specified if
+ * valid. Else returns a smaller extent bounded by the end of the source and
+ * destination pgt_entry.
+ */
+static unsigned long get_extent(enum pgt_entry entry, unsigned long old_addr,
+			unsigned long old_end, unsigned long new_addr)
+{
+	unsigned long next, extent, mask, size;
+
+	switch (entry) {
+	case HPAGE_PMD:
+	case NORMAL_PMD:
+		mask = PMD_MASK;
+		size = PMD_SIZE;
+		break;
+	case NORMAL_PUD:
+		mask = PUD_MASK;
+		size = PUD_SIZE;
+		break;
+	default:
+		BUILD_BUG();
+		break;
+	}
+
+	next = (old_addr + size) & mask;
+	/* even if next overflowed, extent below will be ok */
+	extent = (next > old_end) ? old_end - old_addr : next - old_addr;
+	next = (new_addr + size) & mask;
+	if (extent > next - new_addr)
+		extent = next - new_addr;
+	return extent;
+}
+
+/*
+ * Attempts to speedup the move by moving entry at the level corresponding to
+ * pgt_entry. Returns true if the move was successful, else false.
+ */
+static bool move_pgt_entry(enum pgt_entry entry, struct vm_area_struct *vma,
+			unsigned long old_addr, unsigned long new_addr,
+			void *old_entry, void *new_entry, bool need_rmap_locks)
+{
+	bool moved = false;
+
+	/* See comment in move_ptes() */
+	if (need_rmap_locks)
+		take_rmap_locks(vma);
+
+	switch (entry) {
+	case NORMAL_PMD:
+		moved = move_normal_pmd(vma, old_addr, new_addr, old_entry,
+					new_entry);
+		break;
+	case NORMAL_PUD:
+		moved = move_normal_pud(vma, old_addr, new_addr, old_entry,
+					new_entry);
+		break;
+	case HPAGE_PMD:
+		moved = IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
+			move_huge_pmd(vma, old_addr, new_addr, old_entry,
+				      new_entry);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
+
+	if (need_rmap_locks)
+		drop_rmap_locks(vma);
+
+	return moved;
+}
+
 unsigned long move_page_tables(struct vm_area_struct *vma,
 		unsigned long old_addr, struct vm_area_struct *new_vma,
 		unsigned long new_addr, unsigned long len,
 		bool need_rmap_locks)
 {
-	unsigned long extent, next, old_end;
+	unsigned long extent, old_end;
 	struct mmu_notifier_range range;
 	pmd_t *old_pmd, *new_pmd;
 
@@ -269,53 +422,50 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 
 	for (; old_addr < old_end; old_addr += extent, new_addr += extent) {
 		cond_resched();
-		next = (old_addr + PMD_SIZE) & PMD_MASK;
-		/* even if next overflowed, extent below will be ok */
-		extent = next - old_addr;
-		if (extent > old_end - old_addr)
-			extent = old_end - old_addr;
-		next = (new_addr + PMD_SIZE) & PMD_MASK;
-		if (extent > next - new_addr)
-			extent = next - new_addr;
+		/*
+		 * If extent is PUD-sized try to speed up the move by moving at the
+		 * PUD level if possible.
+		 */
+		extent = get_extent(NORMAL_PUD, old_addr, old_end, new_addr);
+		if (IS_ENABLED(CONFIG_HAVE_MOVE_PUD) && extent == PUD_SIZE) {
+			pud_t *old_pud, *new_pud;
+
+			old_pud = get_old_pud(vma->vm_mm, old_addr);
+			if (!old_pud)
+				continue;
+			new_pud = alloc_new_pud(vma->vm_mm, vma, new_addr);
+			if (!new_pud)
+				break;
+			if (move_pgt_entry(NORMAL_PUD, vma, old_addr, new_addr,
+					   old_pud, new_pud, need_rmap_locks))
+				continue;
+		}
+
+		extent = get_extent(NORMAL_PMD, old_addr, old_end, new_addr);
 		old_pmd = get_old_pmd(vma->vm_mm, old_addr);
 		if (!old_pmd)
 			continue;
 		new_pmd = alloc_new_pmd(vma->vm_mm, vma, new_addr);
 		if (!new_pmd)
 			break;
-		if (is_swap_pmd(*old_pmd) || pmd_trans_huge(*old_pmd) || pmd_devmap(*old_pmd)) {
-			if (extent == HPAGE_PMD_SIZE) {
-				bool moved;
-				/* See comment in move_ptes() */
-				if (need_rmap_locks)
-					take_rmap_locks(vma);
-				moved = move_huge_pmd(vma, old_addr, new_addr,
-						      old_pmd, new_pmd);
-				if (need_rmap_locks)
-					drop_rmap_locks(vma);
-				if (moved)
-					continue;
-			}
+		if (is_swap_pmd(*old_pmd) || pmd_trans_huge(*old_pmd) ||
+		    pmd_devmap(*old_pmd)) {
+			if (extent == HPAGE_PMD_SIZE &&
+			    move_pgt_entry(HPAGE_PMD, vma, old_addr, new_addr,
+					   old_pmd, new_pmd, need_rmap_locks))
+				continue;
 			split_huge_pmd(vma, old_pmd, old_addr);
 			if (pmd_trans_unstable(old_pmd))
 				continue;
-		} else if (extent == PMD_SIZE) {
-#ifdef CONFIG_HAVE_MOVE_PMD
+		} else if (IS_ENABLED(CONFIG_HAVE_MOVE_PMD) &&
+			   extent == PMD_SIZE) {
 			/*
 			 * If the extent is PMD-sized, try to speed the move by
 			 * moving at the PMD level if possible.
 			 */
-			bool moved;
-
-			if (need_rmap_locks)
-				take_rmap_locks(vma);
-			moved = move_normal_pmd(vma, old_addr, new_addr,
-						old_pmd, new_pmd);
-			if (need_rmap_locks)
-				drop_rmap_locks(vma);
-			if (moved)
+			if (move_pgt_entry(NORMAL_PMD, vma, old_addr, new_addr,
+					   old_pmd, new_pmd, need_rmap_locks))
 				continue;
-#endif
 		}
 
 		if (pte_alloc(new_vma->vm_mm, new_pmd))
-- 
2.28.0.806.g8561365e88-goog

Powered by blists - more mailing lists