From: "Liam R. Howlett" <Liam.Howlett@Oracle.com>
To: maple-tree@lists.infradead.org, linux-mm@kvack.org,
linux-kernel@vger.kernel.org
Cc: Andrew Morton <akpm@google.com>, Song Liu <songliubraving@fb.com>,
Davidlohr Bueso <dave@stgolabs.net>,
"Paul E . McKenney" <paulmck@kernel.org>,
Matthew Wilcox <willy@infradead.org>,
Jerome Glisse <jglisse@redhat.com>,
David Rientjes <rientjes@google.com>,
Axel Rasmussen <axelrasmussen@google.com>,
Suren Baghdasaryan <surenb@google.com>,
Vlastimil Babka <vbabka@suse.cz>
Subject: [PATCH 19/28] mm: Remove vmacache
Date: Thu, 10 Dec 2020 12:03:53 -0500 [thread overview]
Message-ID: <20201210170402.3468568-20-Liam.Howlett@Oracle.com> (raw)
In-Reply-To: <20201210170402.3468568-1-Liam.Howlett@Oracle.com>
The maple tree is able to find a VMA quick enough to no longer need the
vma cache. Remove the vmacache to reduce work in keeping it up to date
and code complexity.
Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
---
fs/exec.c | 3 -
fs/proc/task_mmu.c | 1 -
include/linux/mm_types.h | 1 -
include/linux/mm_types_task.h | 5 --
include/linux/sched.h | 1 -
include/linux/vmacache.h | 28 --------
kernel/debug/debug_core.c | 12 ----
kernel/fork.c | 5 --
mm/Makefile | 2 +-
mm/debug.c | 4 +-
mm/mmap.c | 20 ------
mm/vmacache.c | 117 ----------------------------------
12 files changed, 3 insertions(+), 196 deletions(-)
delete mode 100644 include/linux/vmacache.h
delete mode 100644 mm/vmacache.c
diff --git a/fs/exec.c b/fs/exec.c
index 547a2390baf54..aa466921d6a97 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -28,7 +28,6 @@
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/mm.h>
-#include <linux/vmacache.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/swap.h>
@@ -1019,8 +1018,6 @@ static int exec_mmap(struct mm_struct *mm)
activate_mm(active_mm, mm);
if (IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM))
local_irq_enable();
- tsk->mm->vmacache_seqnum = 0;
- vmacache_flush(tsk);
task_unlock(tsk);
if (old_mm) {
mmap_read_unlock(old_mm);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 217aa2705d5df..5161d8ea2d729 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1,6 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/pagewalk.h>
-#include <linux/vmacache.h>
#include <linux/hugetlb.h>
#include <linux/huge_mm.h>
#include <linux/mount.h>
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index fa3cf29f01f21..5a85b76bb9b9a 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -380,7 +380,6 @@ struct mm_struct {
struct {
struct vm_area_struct *mmap; /* list of VMAs */
struct maple_tree mm_mt;
- u64 vmacache_seqnum; /* per-thread vmacache */
#ifdef CONFIG_MMU
unsigned long (*get_unmapped_area) (struct file *filp,
unsigned long addr, unsigned long len,
diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h
index c1bc6731125cb..33c9fa4d4f66a 100644
--- a/include/linux/mm_types_task.h
+++ b/include/linux/mm_types_task.h
@@ -31,11 +31,6 @@
#define VMACACHE_SIZE (1U << VMACACHE_BITS)
#define VMACACHE_MASK (VMACACHE_SIZE - 1)
-struct vmacache {
- u64 seqnum;
- struct vm_area_struct *vmas[VMACACHE_SIZE];
-};
-
/*
* When updating this, please also update struct resident_page_types[] in
* kernel/fork.c
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 063cd120b4593..6e4cb78e5d1ab 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -750,7 +750,6 @@ struct task_struct {
struct mm_struct *active_mm;
/* Per-thread vma caching: */
- struct vmacache vmacache;
#ifdef SPLIT_RSS_COUNTING
struct task_rss_stat rss_stat;
diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h
deleted file mode 100644
index 6fce268a4588e..0000000000000
--- a/include/linux/vmacache.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __LINUX_VMACACHE_H
-#define __LINUX_VMACACHE_H
-
-#include <linux/sched.h>
-#include <linux/mm.h>
-
-static inline void vmacache_flush(struct task_struct *tsk)
-{
- memset(tsk->vmacache.vmas, 0, sizeof(tsk->vmacache.vmas));
-}
-
-extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma);
-extern struct vm_area_struct *vmacache_find(struct mm_struct *mm,
- unsigned long addr);
-
-#ifndef CONFIG_MMU
-extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm,
- unsigned long start,
- unsigned long end);
-#endif
-
-static inline void vmacache_invalidate(struct mm_struct *mm)
-{
- mm->vmacache_seqnum++;
-}
-
-#endif /* __LINUX_VMACACHE_H */
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index 1e75a8923a8d1..f6e7156088ea7 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -53,7 +53,6 @@
#include <linux/pid.h>
#include <linux/smp.h>
#include <linux/mm.h>
-#include <linux/vmacache.h>
#include <linux/rcupdate.h>
#include <linux/irq.h>
@@ -286,17 +285,6 @@ static void kgdb_flush_swbreak_addr(unsigned long addr)
if (!CACHE_FLUSH_IS_SAFE)
return;
- if (current->mm) {
- int i;
-
- for (i = 0; i < VMACACHE_SIZE; i++) {
- if (!current->vmacache.vmas[i])
- continue;
- flush_cache_range(current->vmacache.vmas[i],
- addr, addr + BREAK_INSTR_SIZE);
- }
- }
-
/* Force flush instruction cache if it was outside the mm */
flush_icache_range(addr, addr + BREAK_INSTR_SIZE);
}
diff --git a/kernel/fork.c b/kernel/fork.c
index 5e4de4b860439..52ff974dac511 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -42,7 +42,6 @@
#include <linux/mmu_notifier.h>
#include <linux/fs.h>
#include <linux/mm.h>
-#include <linux/vmacache.h>
#include <linux/nsproxy.h>
#include <linux/capability.h>
#include <linux/cpu.h>
@@ -1011,7 +1010,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
{
mm->mmap = NULL;
mt_init_flags(&mm->mm_mt, MAPLE_ALLOC_RANGE);
- mm->vmacache_seqnum = 0;
atomic_set(&mm->mm_users, 1);
atomic_set(&mm->mm_count, 1);
mmap_init_lock(mm);
@@ -1408,9 +1406,6 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
if (!oldmm)
return 0;
- /* initialize the new vmacache entries */
- vmacache_flush(tsk);
-
if (clone_flags & CLONE_VM) {
mmget(oldmm);
mm = oldmm;
diff --git a/mm/Makefile b/mm/Makefile
index d73aed0fc99c1..ca05b84ac738b 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -50,7 +50,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \
readahead.o swap.o truncate.o vmscan.o shmem.o \
util.o mmzone.o vmstat.o backing-dev.o \
mm_init.o percpu.o slab_common.o \
- compaction.o vmacache.o \
+ compaction.o \
interval_tree.o list_lru.o workingset.o \
debug.o gup.o $(mmu-y)
diff --git a/mm/debug.c b/mm/debug.c
index ccca576b28990..d8ed9d7383267 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -214,7 +214,7 @@ EXPORT_SYMBOL(dump_vma);
void dump_mm(const struct mm_struct *mm)
{
- pr_emerg("mm %px mmap %px seqnum %llu task_size %lu\n"
+ pr_emerg("mm %px mmap %px task_size %lu\n"
#ifdef CONFIG_MMU
"get_unmapped_area %px\n"
#endif
@@ -242,7 +242,7 @@ void dump_mm(const struct mm_struct *mm)
"tlb_flush_pending %d\n"
"def_flags: %#lx(%pGv)\n",
- mm, mm->mmap, (long long) mm->vmacache_seqnum, mm->task_size,
+ mm, mm->mmap, mm->task_size,
#ifdef CONFIG_MMU
mm->get_unmapped_area,
#endif
diff --git a/mm/mmap.c b/mm/mmap.c
index d7a7d01f696c1..c3ac4d6f970d3 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -13,7 +13,6 @@
#include <linux/slab.h>
#include <linux/backing-dev.h>
#include <linux/mm.h>
-#include <linux/vmacache.h>
#include <linux/shm.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
@@ -693,9 +692,6 @@ inline int vma_expand(struct ma_state *mas, struct vm_area_struct *vma,
/* Remove from mm linked list - also updates highest_vm_end */
__vma_unlink_list(mm, next);
- /* Kill the cache */
- vmacache_invalidate(mm);
-
if (file)
__remove_shared_vm_struct(next, file, mapping);
@@ -909,8 +905,6 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
if (remove_next) {
__vma_unlink_list(mm, next);
- /* Kill the cache */
- vmacache_invalidate(mm);
if (file)
__remove_shared_vm_struct(next, file, mapping);
} else if (insert) {
@@ -2197,19 +2191,9 @@ struct vm_area_struct *find_vma_intersection(struct mm_struct *mm,
{
struct vm_area_struct *vma;
MA_STATE(mas, &mm->mm_mt, start_addr, start_addr);
-
- /* Check the cache first. */
- vma = vmacache_find(mm, start_addr);
- if (likely(vma))
- return vma;
-
rcu_read_lock();
vma = mas_find(&mas, end_addr - 1);
rcu_read_unlock();
-
- if (vma)
- vmacache_update(start_addr, vma);
-
return vma;
}
EXPORT_SYMBOL(find_vma_intersection);
@@ -2604,9 +2588,6 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
mm->highest_vm_end = prev ? vm_end_gap(prev) : 0;
tail_vma->vm_next = NULL;
- /* Kill the cache */
- vmacache_invalidate(mm);
-
/*
* Do not downgrade mmap_lock if we are next to VM_GROWSDOWN or
* VM_GROWSUP VMA. Such VMAs can change their size under
@@ -3003,7 +2984,6 @@ static int do_brk_munmap(struct ma_state *mas, struct vm_area_struct *vma,
if (vma_mas_remove(&unmap, mas))
goto mas_store_fail;
- vmacache_invalidate(vma->vm_mm);
if (vma->anon_vma) {
anon_vma_interval_tree_post_update_vma(vma);
anon_vma_unlock_write(vma->anon_vma);
diff --git a/mm/vmacache.c b/mm/vmacache.c
deleted file mode 100644
index 01a6e6688ec1f..0000000000000
--- a/mm/vmacache.c
+++ /dev/null
@@ -1,117 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2014 Davidlohr Bueso.
- */
-#include <linux/sched/signal.h>
-#include <linux/sched/task.h>
-#include <linux/mm.h>
-#include <linux/vmacache.h>
-
-/*
- * Hash based on the pmd of addr if configured with MMU, which provides a good
- * hit rate for workloads with spatial locality. Otherwise, use pages.
- */
-#ifdef CONFIG_MMU
-#define VMACACHE_SHIFT PMD_SHIFT
-#else
-#define VMACACHE_SHIFT PAGE_SHIFT
-#endif
-#define VMACACHE_HASH(addr) ((addr >> VMACACHE_SHIFT) & VMACACHE_MASK)
-
-/*
- * This task may be accessing a foreign mm via (for example)
- * get_user_pages()->find_vma(). The vmacache is task-local and this
- * task's vmacache pertains to a different mm (ie, its own). There is
- * nothing we can do here.
- *
- * Also handle the case where a kernel thread has adopted this mm via
- * kthread_use_mm(). That kernel thread's vmacache is not applicable to this mm.
- */
-static inline bool vmacache_valid_mm(struct mm_struct *mm)
-{
- return current->mm == mm && !(current->flags & PF_KTHREAD);
-}
-
-void vmacache_update(unsigned long addr, struct vm_area_struct *newvma)
-{
- if (vmacache_valid_mm(newvma->vm_mm))
- current->vmacache.vmas[VMACACHE_HASH(addr)] = newvma;
-}
-
-static bool vmacache_valid(struct mm_struct *mm)
-{
- struct task_struct *curr;
-
- if (!vmacache_valid_mm(mm))
- return false;
-
- curr = current;
- if (mm->vmacache_seqnum != curr->vmacache.seqnum) {
- /*
- * First attempt will always be invalid, initialize
- * the new cache for this task here.
- */
- curr->vmacache.seqnum = mm->vmacache_seqnum;
- vmacache_flush(curr);
- return false;
- }
- return true;
-}
-
-struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr)
-{
- int idx = VMACACHE_HASH(addr);
- int i;
-
- count_vm_vmacache_event(VMACACHE_FIND_CALLS);
-
- if (!vmacache_valid(mm))
- return NULL;
-
- for (i = 0; i < VMACACHE_SIZE; i++) {
- struct vm_area_struct *vma = current->vmacache.vmas[idx];
-
- if (vma) {
-#ifdef CONFIG_DEBUG_VM_VMACACHE
- if (WARN_ON_ONCE(vma->vm_mm != mm))
- break;
-#endif
- if (vma->vm_start <= addr && vma->vm_end > addr) {
- count_vm_vmacache_event(VMACACHE_FIND_HITS);
- return vma;
- }
- }
- if (++idx == VMACACHE_SIZE)
- idx = 0;
- }
-
- return NULL;
-}
-
-#ifndef CONFIG_MMU
-struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm,
- unsigned long start,
- unsigned long end)
-{
- int idx = VMACACHE_HASH(start);
- int i;
-
- count_vm_vmacache_event(VMACACHE_FIND_CALLS);
-
- if (!vmacache_valid(mm))
- return NULL;
-
- for (i = 0; i < VMACACHE_SIZE; i++) {
- struct vm_area_struct *vma = current->vmacache.vmas[idx];
-
- if (vma && vma->vm_start == start && vma->vm_end == end) {
- count_vm_vmacache_event(VMACACHE_FIND_HITS);
- return vma;
- }
- if (++idx == VMACACHE_SIZE)
- idx = 0;
- }
-
- return NULL;
-}
-#endif
--
2.28.0
next prev parent reply other threads:[~2020-12-10 17:07 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-10 17:03 [PATCH 00/28] RFC mm: Introducing the Maple Tree Liam R. Howlett
2020-12-10 17:03 ` [PATCH 01/28] radix tree test suite: Enhancements for " Liam R. Howlett
2020-12-10 17:03 ` [PATCH 02/28] radix tree test suite: Add support for fallthrough attribute Liam R. Howlett
2020-12-10 17:03 ` [PATCH 03/28] radix tree test suite: Add support for kmem_cache_free_bulk Liam R. Howlett
2020-12-10 17:03 ` [PATCH 04/28] radix tree test suite: Add keme_cache_alloc_bulk() support Liam R. Howlett
2020-12-10 17:03 ` [PATCH 05/28] Maple Tree: Add new data structure Liam R. Howlett
2020-12-10 17:03 ` [PATCH 06/28] mm: Start tracking VMAs with maple tree Liam R. Howlett
2020-12-11 19:30 ` kernel test robot
2020-12-10 17:03 ` [PATCH 07/28] mm/mmap: Introduce unlock_range() for code cleanup Liam R. Howlett
2020-12-10 17:03 ` [PATCH 08/28] mm/mmap: Change find_vma() to use the maple tree Liam R. Howlett
2020-12-10 17:03 ` [PATCH 09/28] mm/mmap: Change find_vma_prev() to use " Liam R. Howlett
2020-12-10 17:03 ` [PATCH 10/28] mm/mmap: Change unmapped_area and unmapped_area_topdown " Liam R. Howlett
2020-12-10 17:03 ` [PATCH 11/28] kernel/fork: Convert dup_mmap " Liam R. Howlett
2020-12-10 17:03 ` [PATCH 12/28] mm: Remove rb tree Liam R. Howlett
2020-12-10 17:03 ` [PATCH 13/28] mm/gup: Expose mm_populate_vma() for use when the vma is known Liam R. Howlett
2020-12-10 21:03 ` kernel test robot
2020-12-10 17:03 ` [PATCH 14/28] mm/mmap: Change do_brk_flags() to expand existing VMA and add do_brk_munmap() Liam R. Howlett
2020-12-10 17:03 ` [PATCH 15/28] mm/mmap: Change vm_brk_flags() to use mm_populate_vma() Liam R. Howlett
2020-12-10 17:03 ` [PATCH 16/28] mm: Move find_vma_intersection to mmap.c and change implementation to maple tree Liam R. Howlett
2020-12-10 17:03 ` [PATCH 17/28] mm/mmap: Change mmap_region to use maple tree state Liam R. Howlett
2020-12-10 17:03 ` [PATCH 18/28] mm/mmap: Drop munmap_vma_range() Liam R. Howlett
2020-12-10 17:03 ` Liam R. Howlett [this message]
2020-12-10 17:03 ` [PATCH 20/28] mm/mmap: Change __do_munmap() to avoid unnecessary lookups Liam R. Howlett
2020-12-10 17:03 ` [PATCH 21/28] mm/mmap: Change __do_munmap() to use a ma_state Liam R. Howlett
2020-12-10 17:03 ` [PATCH 22/28] mm/mmap: Move mmap_region() below do_munmap() Liam R. Howlett
2020-12-10 17:03 ` [PATCH 23/28] mm/mmap: Add do_mas_munmap() and wraper for __do_munmap() Liam R. Howlett
2020-12-10 17:03 ` [PATCH 24/28] mmap: Use find_vma_intersection in do_mmap() for overlap Liam R. Howlett
2020-12-10 17:03 ` [PATCH 25/28] mmap: Remove __do_munmap() in favour of do_mas_munmap() Liam R. Howlett
2020-12-10 17:04 ` [PATCH 26/28] mm/mmap: Change do_brk_munmap() to use do_mas_align_munmap() Liam R. Howlett
2020-12-10 17:04 ` [PATCH 27/28] mmap: Update count_vma_pages_range() to only use one ma_state Liam R. Howlett
2020-12-10 17:04 ` [PATCH 28/28] mmap: make remove_vma_list() inline Liam R. Howlett
Reply instructions:
You may reply publicly 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=20201210170402.3468568-20-Liam.Howlett@Oracle.com \
--to=liam.howlett@oracle.com \
--cc=akpm@google.com \
--cc=axelrasmussen@google.com \
--cc=dave@stgolabs.net \
--cc=jglisse@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=maple-tree@lists.infradead.org \
--cc=paulmck@kernel.org \
--cc=rientjes@google.com \
--cc=songliubraving@fb.com \
--cc=surenb@google.com \
--cc=vbabka@suse.cz \
--cc=willy@infradead.org \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).