diff mbox series

[v3,7/9] mm: pgtable: try to reclaim empty PTE page in madvise(MADV_DONTNEED)

Message ID 9e6f0cff7ae29cd8bd1812d3a0e3513de3f42f42.1731566457.git.zhengqi.arch@bytedance.com (mailing list archive)
State New
Headers show
Series synchronously scan and reclaim empty user PTE pages | expand

Commit Message

Qi Zheng Nov. 14, 2024, 6:59 a.m. UTC 
Now in order to pursue high performance, applications mostly use some
high-performance user-mode memory allocators, such as jemalloc or
tcmalloc. These memory allocators use madvise(MADV_DONTNEED or MADV_FREE)
to release physical memory, but neither MADV_DONTNEED nor MADV_FREE will
release page table memory, which may cause huge page table memory usage.

The following are a memory usage snapshot of one process which actually
happened on our server:

        VIRT:  55t
        RES:   590g
        VmPTE: 110g

In this case, most of the page table entries are empty. For such a PTE
page where all entries are empty, we can actually free it back to the
system for others to use.

As a first step, this commit aims to synchronously free the empty PTE
pages in madvise(MADV_DONTNEED) case. We will detect and free empty PTE
pages in zap_pte_range(), and will add zap_details.reclaim_pt to exclude
cases other than madvise(MADV_DONTNEED).

Once an empty PTE is detected, we first try to hold the pmd lock within
the pte lock. If successful, we clear the pmd entry directly (fast path).
Otherwise, we wait until the pte lock is released, then re-hold the pmd
and pte locks and loop PTRS_PER_PTE times to check pte_none() to re-detect
whether the PTE page is empty and free it (slow path).

For other cases such as madvise(MADV_FREE), consider scanning and freeing
empty PTE pages asynchronously in the future.

The following code snippet can show the effect of optimization:

        mmap 50G
        while (1) {
                for (; i < 1024 * 25; i++) {
                        touch 2M memory
                        madvise MADV_DONTNEED 2M
                }
        }

As we can see, the memory usage of VmPTE is reduced:

                        before                          after
VIRT                   50.0 GB                        50.0 GB
RES                     3.1 MB                         3.1 MB
VmPTE                102640 KB                         240 KB

Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
---
 include/linux/mm.h |  1 +
 mm/Kconfig         | 15 ++++++++++
 mm/Makefile        |  1 +
 mm/internal.h      | 19 +++++++++++++
 mm/madvise.c       |  7 ++++-
 mm/memory.c        | 45 ++++++++++++++++++++++++++++-
 mm/pt_reclaim.c    | 71 ++++++++++++++++++++++++++++++++++++++++++++++
 7 files changed, 157 insertions(+), 2 deletions(-)
 create mode 100644 mm/pt_reclaim.c
diff mbox series

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index ca59d165f1f2e..1fcd4172d2c03 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2319,6 +2319,7 @@  extern void pagefault_out_of_memory(void);
 struct zap_details {
 	struct folio *single_folio;	/* Locked folio to be unmapped */
 	bool even_cows;			/* Zap COWed private pages too? */
+	bool reclaim_pt;		/* Need reclaim page tables? */
 	zap_flags_t zap_flags;		/* Extra flags for zapping */
 };
 
diff --git a/mm/Kconfig b/mm/Kconfig
index 84000b0168086..7949ab121070f 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1301,6 +1301,21 @@  config ARCH_HAS_USER_SHADOW_STACK
 	  The architecture has hardware support for userspace shadow call
           stacks (eg, x86 CET, arm64 GCS or RISC-V Zicfiss).
 
+config ARCH_SUPPORTS_PT_RECLAIM
+	def_bool n
+
+config PT_RECLAIM
+	bool "reclaim empty user page table pages"
+	default y
+	depends on ARCH_SUPPORTS_PT_RECLAIM && MMU && SMP
+	select MMU_GATHER_RCU_TABLE_FREE
+	help
+	  Try to reclaim empty user page table pages in paths other than munmap
+	  and exit_mmap path.
+
+	  Note: now only empty user PTE page table pages will be reclaimed.
+
+
 source "mm/damon/Kconfig"
 
 endmenu
diff --git a/mm/Makefile b/mm/Makefile
index dba52bb0da8ab..850386a67b3e0 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -146,3 +146,4 @@  obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o
 obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o
 obj-$(CONFIG_EXECMEM) += execmem.o
 obj-$(CONFIG_TMPFS_QUOTA) += shmem_quota.o
+obj-$(CONFIG_PT_RECLAIM) += pt_reclaim.o
diff --git a/mm/internal.h b/mm/internal.h
index 5a7302baeed7c..5b2aef61073f1 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1530,4 +1530,23 @@  int walk_page_range_mm(struct mm_struct *mm, unsigned long start,
 		unsigned long end, const struct mm_walk_ops *ops,
 		void *private);
 
+/* pt_reclaim.c */
+bool try_get_and_clear_pmd(struct mm_struct *mm, pmd_t *pmd, pmd_t *pmdval);
+void free_pte(struct mm_struct *mm, unsigned long addr, struct mmu_gather *tlb,
+	      pmd_t pmdval);
+void try_to_free_pte(struct mm_struct *mm, pmd_t *pmd, unsigned long addr,
+		     struct mmu_gather *tlb);
+
+#ifdef CONFIG_PT_RECLAIM
+bool reclaim_pt_is_enabled(unsigned long start, unsigned long end,
+			   struct zap_details *details);
+#else
+static inline bool reclaim_pt_is_enabled(unsigned long start, unsigned long end,
+					 struct zap_details *details)
+{
+	return false;
+}
+#endif /* CONFIG_PT_RECLAIM */
+
+
 #endif	/* __MM_INTERNAL_H */
diff --git a/mm/madvise.c b/mm/madvise.c
index 0ceae57da7dad..49f3a75046f63 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -851,7 +851,12 @@  static int madvise_free_single_vma(struct vm_area_struct *vma,
 static long madvise_dontneed_single_vma(struct vm_area_struct *vma,
 					unsigned long start, unsigned long end)
 {
-	zap_page_range_single(vma, start, end - start, NULL);
+	struct zap_details details = {
+		.reclaim_pt = true,
+		.even_cows = true,
+	};
+
+	zap_page_range_single(vma, start, end - start, &details);
 	return 0;
 }
 
diff --git a/mm/memory.c b/mm/memory.c
index 8b3348ff374ff..fe93b0648c430 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1436,7 +1436,7 @@  copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 static inline bool should_zap_cows(struct zap_details *details)
 {
 	/* By default, zap all pages */
-	if (!details)
+	if (!details || details->reclaim_pt)
 		return true;
 
 	/* Or, we zap COWed pages only if the caller wants to */
@@ -1698,6 +1698,30 @@  static inline int do_zap_pte_range(struct mmu_gather *tlb,
 					 details, rss);
 }
 
+static inline int count_pte_none(pte_t *pte, int nr)
+{
+	int none_nr = 0;
+
+	/*
+	 * If PTE_MARKER_UFFD_WP is enabled, the uffd-wp PTEs may be
+	 * re-installed, so we need to check pte_none() one by one.
+	 * Otherwise, checking a single PTE in a batch is sufficient.
+	 */
+#ifdef CONFIG_PTE_MARKER_UFFD_WP
+	for (;;) {
+		if (pte_none(ptep_get(pte)))
+			none_nr++;
+		if (--nr == 0)
+			break;
+		pte++;
+	}
+#else
+	if (pte_none(ptep_get(pte)))
+		none_nr = nr;
+#endif
+	return none_nr;
+}
+
 static unsigned long zap_pte_range(struct mmu_gather *tlb,
 				struct vm_area_struct *vma, pmd_t *pmd,
 				unsigned long addr, unsigned long end,
@@ -1709,6 +1733,11 @@  static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	spinlock_t *ptl;
 	pte_t *start_pte;
 	pte_t *pte;
+	pmd_t pmdval;
+	unsigned long start = addr;
+	bool can_reclaim_pt = reclaim_pt_is_enabled(start, end, details);
+	bool direct_reclaim = false;
+	int none_nr = 0;
 	int nr;
 
 retry:
@@ -1726,6 +1755,8 @@  static unsigned long zap_pte_range(struct mmu_gather *tlb,
 
 		nr = skip_none_ptes(pte, addr, end);
 		if (nr) {
+			if (can_reclaim_pt)
+				none_nr += nr;
 			addr += PAGE_SIZE * nr;
 			if (addr == end)
 				break;
@@ -1734,12 +1765,17 @@  static unsigned long zap_pte_range(struct mmu_gather *tlb,
 
 		nr = do_zap_pte_range(tlb, vma, pte, addr, end, details,
 				      rss, &force_flush, &force_break);
+		if (can_reclaim_pt)
+			none_nr += count_pte_none(pte, nr);
 		if (unlikely(force_break)) {
 			addr += nr * PAGE_SIZE;
 			break;
 		}
 	} while (pte += nr, addr += PAGE_SIZE * nr, addr != end);
 
+	if (can_reclaim_pt && addr == end && (none_nr == PTRS_PER_PTE))
+		direct_reclaim = try_get_and_clear_pmd(mm, pmd, &pmdval);
+
 	add_mm_rss_vec(mm, rss);
 	arch_leave_lazy_mmu_mode();
 
@@ -1766,6 +1802,13 @@  static unsigned long zap_pte_range(struct mmu_gather *tlb,
 		goto retry;
 	}
 
+	if (can_reclaim_pt) {
+		if (direct_reclaim)
+			free_pte(mm, start, tlb, pmdval);
+		else
+			try_to_free_pte(mm, pmd, start, tlb);
+	}
+
 	return addr;
 }
 
diff --git a/mm/pt_reclaim.c b/mm/pt_reclaim.c
new file mode 100644
index 0000000000000..6540a3115dde8
--- /dev/null
+++ b/mm/pt_reclaim.c
@@ -0,0 +1,71 @@ 
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/hugetlb.h>
+#include <asm-generic/tlb.h>
+#include <asm/pgalloc.h>
+
+#include "internal.h"
+
+bool reclaim_pt_is_enabled(unsigned long start, unsigned long end,
+			   struct zap_details *details)
+{
+	return details && details->reclaim_pt && (end - start >= PMD_SIZE);
+}
+
+bool try_get_and_clear_pmd(struct mm_struct *mm, pmd_t *pmd, pmd_t *pmdval)
+{
+	spinlock_t *pml = pmd_lockptr(mm, pmd);
+
+	if (!spin_trylock(pml))
+		return false;
+
+	*pmdval = pmdp_get_lockless(pmd);
+	pmd_clear(pmd);
+	spin_unlock(pml);
+
+	return true;
+}
+
+void free_pte(struct mm_struct *mm, unsigned long addr, struct mmu_gather *tlb,
+	      pmd_t pmdval)
+{
+	pte_free_tlb(tlb, pmd_pgtable(pmdval), addr);
+	mm_dec_nr_ptes(mm);
+}
+
+void try_to_free_pte(struct mm_struct *mm, pmd_t *pmd, unsigned long addr,
+		     struct mmu_gather *tlb)
+{
+	pmd_t pmdval;
+	spinlock_t *pml, *ptl;
+	pte_t *start_pte, *pte;
+	int i;
+
+	pml = pmd_lock(mm, pmd);
+	start_pte = pte_offset_map_rw_nolock(mm, pmd, addr, &pmdval, &ptl);
+	if (!start_pte)
+		goto out_ptl;
+	if (ptl != pml)
+		spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
+
+	/* Check if it is empty PTE page */
+	for (i = 0, pte = start_pte; i < PTRS_PER_PTE; i++, pte++) {
+		if (!pte_none(ptep_get(pte)))
+			goto out_ptl;
+	}
+	pte_unmap(start_pte);
+
+	pmd_clear(pmd);
+
+	if (ptl != pml)
+		spin_unlock(ptl);
+	spin_unlock(pml);
+
+	free_pte(mm, addr, tlb, pmdval);
+
+	return;
+out_ptl:
+	if (start_pte)
+		pte_unmap_unlock(start_pte, ptl);
+	if (ptl != pml)
+		spin_unlock(pml);
+}