linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Suren Baghdasaryan <surenb@google.com>
To: akpm@linux-foundation.org
Cc: willy@infradead.org, liam.howlett@oracle.com,
	lorenzo.stoakes@oracle.com,  mhocko@suse.com, vbabka@suse.cz,
	hannes@cmpxchg.org, mjguzik@gmail.com,  oliver.sang@intel.com,
	mgorman@techsingularity.net, david@redhat.com,
	 peterx@redhat.com, oleg@redhat.com, dave@stgolabs.net,
	paulmck@kernel.org,  brauner@kernel.org, dhowells@redhat.com,
	hdanton@sina.com, hughd@google.com,  minchan@google.com,
	jannh@google.com, shakeel.butt@linux.dev,
	 souravpanda@google.com, pasha.tatashin@soleen.com,
	linux-mm@kvack.org,  linux-kernel@vger.kernel.org,
	kernel-team@android.com, surenb@google.com
Subject: [PATCH 4/4] mm: move lesser used vma_area_struct members into the last cacheline
Date: Mon, 11 Nov 2024 12:55:06 -0800	[thread overview]
Message-ID: <20241111205506.3404479-5-surenb@google.com> (raw)
In-Reply-To: <20241111205506.3404479-1-surenb@google.com>

Move several vma_area_struct members which are rarely or never used
during page fault handling into the last cacheline to better pack
vm_area_struct. As a result vm_area_struct will fit into 3 cachelines
as opposed to 4 cachelines before this change. New vm_area_struct layout:

struct vm_area_struct {
	union {
		struct {
			long unsigned int vm_start;      /*     0     8 */
			long unsigned int vm_end;        /*     8     8 */
		};                                       /*     0    16 */
		struct callback_head vm_rcu ;            /*     0    16 */
	} __attribute__((__aligned__(8)));               /*     0    16 */
	struct mm_struct *         vm_mm;                /*    16     8 */
	pgprot_t                   vm_page_prot;         /*    24     8 */
	union {
		const vm_flags_t   vm_flags;             /*    32     8 */
		vm_flags_t         __vm_flags;           /*    32     8 */
	};                                               /*    32     8 */
	bool                       detached;             /*    40     1 */

	/* XXX 3 bytes hole, try to pack */

	unsigned int               vm_lock_seq;          /*    44     4 */
	struct list_head           anon_vma_chain;       /*    48    16 */
	/* --- cacheline 1 boundary (64 bytes) --- */
	struct anon_vma *          anon_vma;             /*    64     8 */
	const struct vm_operations_struct  * vm_ops;     /*    72     8 */
	long unsigned int          vm_pgoff;             /*    80     8 */
	struct file *              vm_file;              /*    88     8 */
	void *                     vm_private_data;      /*    96     8 */
	atomic_long_t              swap_readahead_info;  /*   104     8 */
	struct mempolicy *         vm_policy;            /*   112     8 */

	/* XXX 8 bytes hole, try to pack */

	/* --- cacheline 2 boundary (128 bytes) --- */
	struct vma_lock       vm_lock (__aligned__(64)); /*   128     4 */

	/* XXX 4 bytes hole, try to pack */

	struct {
		struct rb_node     rb (__aligned__(8));  /*   136    24 */
		long unsigned int  rb_subtree_last;      /*   160     8 */
	} __attribute__((__aligned__(8))) shared;        /*   136    32 */
	struct vm_userfaultfd_ctx  vm_userfaultfd_ctx;   /*   168     0 */

	/* size: 192, cachelines: 3, members: 17 */
	/* sum members: 153, holes: 3, sum holes: 15 */
	/* padding: 24 */
	/* forced alignments: 3, forced holes: 2, sum forced holes: 12 */
} __attribute__((__aligned__(64)));


Memory consumption per 1000 VMAs becomes 48 pages:

    slabinfo after vm_area_struct changes:
     <name>           ... <objsize> <objperslab> <pagesperslab> : ...
     vm_area_struct   ...    192   42    2 : ...


Signed-off-by: Suren Baghdasaryan <surenb@google.com>
---
 include/linux/mm_types.h | 37 ++++++++++++++++++-------------------
 1 file changed, 18 insertions(+), 19 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 789bccc05520..c3755b680911 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -733,16 +733,6 @@ struct vm_area_struct {
 	unsigned int vm_lock_seq;
 #endif
 
-	/*
-	 * For areas with an address space and backing store,
-	 * linkage into the address_space->i_mmap interval tree.
-	 *
-	 */
-	struct {
-		struct rb_node rb;
-		unsigned long rb_subtree_last;
-	} shared;
-
 	/*
 	 * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma
 	 * list, after a COW of one of the file pages.	A MAP_SHARED vma
@@ -762,14 +752,6 @@ struct vm_area_struct {
 	struct file * vm_file;		/* File we map to (can be NULL). */
 	void * vm_private_data;		/* was vm_pte (shared mem) */
 
-#ifdef CONFIG_ANON_VMA_NAME
-	/*
-	 * For private and shared anonymous mappings, a pointer to a null
-	 * terminated string containing the name given to the vma, or NULL if
-	 * unnamed. Serialized by mmap_lock. Use anon_vma_name to access.
-	 */
-	struct anon_vma_name *anon_name;
-#endif
 #ifdef CONFIG_SWAP
 	atomic_long_t swap_readahead_info;
 #endif
@@ -782,11 +764,28 @@ struct vm_area_struct {
 #ifdef CONFIG_NUMA_BALANCING
 	struct vma_numab_state *numab_state;	/* NUMA Balancing state */
 #endif
-	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
 #ifdef CONFIG_PER_VMA_LOCK
 	/* Unstable RCU readers are allowed to read this. */
 	struct vma_lock vm_lock ____cacheline_aligned_in_smp;
 #endif
+	/*
+	 * For areas with an address space and backing store,
+	 * linkage into the address_space->i_mmap interval tree.
+	 *
+	 */
+	struct {
+		struct rb_node rb;
+		unsigned long rb_subtree_last;
+	} shared;
+#ifdef CONFIG_ANON_VMA_NAME
+	/*
+	 * For private and shared anonymous mappings, a pointer to a null
+	 * terminated string containing the name given to the vma, or NULL if
+	 * unnamed. Serialized by mmap_lock. Use anon_vma_name to access.
+	 */
+	struct anon_vma_name *anon_name;
+#endif
+	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
 } __randomize_layout;
 
 #ifdef CONFIG_NUMA
-- 
2.47.0.277.g8800431eea-goog



  parent reply	other threads:[~2024-11-11 20:55 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-11-11 20:55 [PATCH 0/4] move per-vma lock into vm_area_struct Suren Baghdasaryan
2024-11-11 20:55 ` [PATCH 1/4] mm: introduce vma_start_read_locked{_nested} helpers Suren Baghdasaryan
2024-11-11 20:55 ` [PATCH 2/4] mm: move per-vma lock into vm_area_struct Suren Baghdasaryan
2024-11-12  9:36   ` kernel test robot
2024-11-12  9:47   ` kernel test robot
2024-11-12 10:18   ` kernel test robot
2024-11-12 15:57   ` Vlastimil Babka
2024-11-12 16:08     ` Suren Baghdasaryan
2024-11-12 16:58       ` Suren Baghdasaryan
2024-11-11 20:55 ` [PATCH 3/4] mm: replace rw_semaphore with atomic_t in vma_lock Suren Baghdasaryan
2024-11-12  0:06   ` Andrew Morton
2024-11-12  0:52     ` Suren Baghdasaryan
2024-11-12  0:35   ` Davidlohr Bueso
2024-11-12  0:59     ` Suren Baghdasaryan
2024-11-12  4:58   ` Matthew Wilcox
2024-11-12 15:18     ` Suren Baghdasaryan
2024-12-10 22:38       ` Peter Zijlstra
2024-12-10 23:37         ` Suren Baghdasaryan
2024-12-11  8:25           ` Peter Zijlstra
2024-12-11 15:20             ` Suren Baghdasaryan
2024-12-12  3:01               ` Suren Baghdasaryan
2024-12-12  9:16                 ` Peter Zijlstra
2024-12-12 14:17                   ` Suren Baghdasaryan
2024-12-12 14:19                     ` Suren Baghdasaryan
2024-12-13  4:48                       ` Suren Baghdasaryan
2024-12-13  9:57                         ` Peter Zijlstra
2024-12-13 17:45                           ` Suren Baghdasaryan
2024-12-13 18:19                             ` Matthew Wilcox
2024-12-13 18:35                             ` Peter Zijlstra
2024-12-13 18:37                               ` Suren Baghdasaryan
2024-12-16 19:32                                 ` Suren Baghdasaryan
2024-12-13  9:22                     ` Peter Zijlstra
2024-12-13 17:41                       ` Suren Baghdasaryan
2024-11-11 20:55 ` Suren Baghdasaryan [this message]
2024-11-12 10:07   ` [PATCH 4/4] mm: move lesser used vma_area_struct members into the last cacheline Vlastimil Babka
2024-11-12 15:45     ` Suren Baghdasaryan
2024-11-11 21:41 ` [PATCH 0/4] move per-vma lock into vm_area_struct Suren Baghdasaryan
2024-11-12  2:48   ` Liam R. Howlett
2024-11-12  3:27     ` Suren Baghdasaryan
2024-11-11 22:18 ` Davidlohr Bueso
2024-11-11 23:19   ` Suren Baghdasaryan
2024-11-12  0:03     ` Davidlohr Bueso
2024-11-12  0:43       ` Suren Baghdasaryan
2024-11-12  0:11     ` Andrew Morton
2024-11-12  0:48       ` Suren Baghdasaryan
2024-11-12  2:35 ` Liam R. Howlett
2024-11-12  3:23   ` Suren Baghdasaryan
2024-11-12  9:39 ` Lorenzo Stoakes
2024-11-12 15:38   ` Suren Baghdasaryan

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=20241111205506.3404479-5-surenb@google.com \
    --to=surenb@google.com \
    --cc=akpm@linux-foundation.org \
    --cc=brauner@kernel.org \
    --cc=dave@stgolabs.net \
    --cc=david@redhat.com \
    --cc=dhowells@redhat.com \
    --cc=hannes@cmpxchg.org \
    --cc=hdanton@sina.com \
    --cc=hughd@google.com \
    --cc=jannh@google.com \
    --cc=kernel-team@android.com \
    --cc=liam.howlett@oracle.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lorenzo.stoakes@oracle.com \
    --cc=mgorman@techsingularity.net \
    --cc=mhocko@suse.com \
    --cc=minchan@google.com \
    --cc=mjguzik@gmail.com \
    --cc=oleg@redhat.com \
    --cc=oliver.sang@intel.com \
    --cc=pasha.tatashin@soleen.com \
    --cc=paulmck@kernel.org \
    --cc=peterx@redhat.com \
    --cc=shakeel.butt@linux.dev \
    --cc=souravpanda@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