Commit 24844fd3 authored by Jonathan Corbet's avatar Jonathan Corbet

Merge branch 'mm-rst' into docs-next

Mike Rapoport says:

  These patches convert files in Documentation/vm to ReST format, add an
  initial index and link it to the top level documentation.

  There are no contents changes in the documentation, except few spelling
  fixes. The relatively large diffstat stems from the indentation and
  paragraph wrapping changes.

  I've tried to keep the formatting as consistent as possible, but I could
  miss some places that needed markup and add some markup where it was not
  necessary.

[jc: significant conflicts in vm/hmm.rst]
parents 32fb7ef6 82381918
......@@ -90,4 +90,4 @@ Date: December 2009
Contact: Lee Schermerhorn <lee.schermerhorn@hp.com>
Description:
The node's huge page size control/query attributes.
See Documentation/vm/hugetlbpage.txt
\ No newline at end of file
See Documentation/vm/hugetlbpage.rst
\ No newline at end of file
......@@ -12,4 +12,4 @@ Description:
free_hugepages
surplus_hugepages
resv_hugepages
See Documentation/vm/hugetlbpage.txt for details.
See Documentation/vm/hugetlbpage.rst for details.
......@@ -40,7 +40,7 @@ Description: Kernel Samepage Merging daemon sysfs interface
sleep_millisecs: how many milliseconds ksm should sleep between
scans.
See Documentation/vm/ksm.txt for more information.
See Documentation/vm/ksm.rst for more information.
What: /sys/kernel/mm/ksm/merge_across_nodes
Date: January 2013
......
......@@ -37,7 +37,7 @@ Description:
The alloc_calls file is read-only and lists the kernel code
locations from which allocations for this cache were performed.
The alloc_calls file only contains information if debugging is
enabled for that cache (see Documentation/vm/slub.txt).
enabled for that cache (see Documentation/vm/slub.rst).
What: /sys/kernel/slab/cache/alloc_fastpath
Date: February 2008
......@@ -219,7 +219,7 @@ Contact: Pekka Enberg <penberg@cs.helsinki.fi>,
Description:
The free_calls file is read-only and lists the locations of
object frees if slab debugging is enabled (see
Documentation/vm/slub.txt).
Documentation/vm/slub.rst).
What: /sys/kernel/slab/cache/free_fastpath
Date: February 2008
......
......@@ -3915,7 +3915,7 @@
cache (risks via metadata attacks are mostly
unchanged). Debug options disable merging on their
own.
For more information see Documentation/vm/slub.txt.
For more information see Documentation/vm/slub.rst.
slab_max_order= [MM, SLAB]
Determines the maximum allowed order for slabs.
......@@ -3929,7 +3929,7 @@
slub_debug can create guard zones around objects and
may poison objects when not in use. Also tracks the
last alloc / free. For more information see
Documentation/vm/slub.txt.
Documentation/vm/slub.rst.
slub_memcg_sysfs= [MM, SLUB]
Determines whether to enable sysfs directories for
......@@ -3943,7 +3943,7 @@
Determines the maximum allowed order for slabs.
A high setting may cause OOMs due to memory
fragmentation. For more information see
Documentation/vm/slub.txt.
Documentation/vm/slub.rst.
slub_min_objects= [MM, SLUB]
The minimum number of objects per slab. SLUB will
......@@ -3952,12 +3952,12 @@
the number of objects indicated. The higher the number
of objects the smaller the overhead of tracking slabs
and the less frequently locks need to be acquired.
For more information see Documentation/vm/slub.txt.
For more information see Documentation/vm/slub.rst.
slub_min_order= [MM, SLUB]
Determines the minimum page order for slabs. Must be
lower than slub_max_order.
For more information see Documentation/vm/slub.txt.
For more information see Documentation/vm/slub.rst.
slub_nomerge [MM, SLUB]
Same with slab_nomerge. This is supported for legacy.
......@@ -4313,7 +4313,7 @@
Format: [always|madvise|never]
Can be used to control the default behavior of the system
with respect to transparent hugepages.
See Documentation/vm/transhuge.txt for more details.
See Documentation/vm/transhuge.rst for more details.
tsc= Disable clocksource stability checks for TSC.
Format: <string>
......
......@@ -120,7 +120,7 @@ A typical out of bounds access report looks like this::
The header of the report discribe what kind of bug happened and what kind of
access caused it. It's followed by the description of the accessed slub object
(see 'SLUB Debug output' section in Documentation/vm/slub.txt for details) and
(see 'SLUB Debug output' section in Documentation/vm/slub.rst for details) and
the description of the accessed memory page.
In the last section the report shows memory state around the accessed address.
......
......@@ -515,7 +515,7 @@ guarantees:
The /proc/PID/clear_refs is used to reset the PG_Referenced and ACCESSED/YOUNG
bits on both physical and virtual pages associated with a process, and the
soft-dirty bit on pte (see Documentation/vm/soft-dirty.txt for details).
soft-dirty bit on pte (see Documentation/vm/soft-dirty.rst for details).
To clear the bits for all the pages associated with the process
> echo 1 > /proc/PID/clear_refs
......@@ -536,7 +536,7 @@ Any other value written to /proc/PID/clear_refs will have no effect.
The /proc/pid/pagemap gives the PFN, which can be used to find the pageflags
using /proc/kpageflags and number of times a page is mapped using
/proc/kpagecount. For detailed explanation, see Documentation/vm/pagemap.txt.
/proc/kpagecount. For detailed explanation, see Documentation/vm/pagemap.rst.
The /proc/pid/numa_maps is an extension based on maps, showing the memory
locality and binding policy, as well as the memory usage (in pages) of
......
......@@ -105,7 +105,7 @@ policy for the file will revert to "default" policy.
NUMA memory allocation policies have optional flags that can be used in
conjunction with their modes. These optional flags can be specified
when tmpfs is mounted by appending them to the mode before the NodeList.
See Documentation/vm/numa_memory_policy.txt for a list of all available
See Documentation/vm/numa_memory_policy.rst for a list of all available
memory allocation policy mode flags and their effect on memory policy.
=static is equivalent to MPOL_F_STATIC_NODES
......
......@@ -89,6 +89,7 @@ needed).
sound/index
crypto/index
filesystems/index
vm/index
Architecture-specific documentation
-----------------------------------
......
......@@ -515,7 +515,7 @@ nr_hugepages
Change the minimum size of the hugepage pool.
See Documentation/vm/hugetlbpage.txt
See Documentation/vm/hugetlbpage.rst
==============================================================
......@@ -524,7 +524,7 @@ nr_overcommit_hugepages
Change the maximum size of the hugepage pool. The maximum is
nr_hugepages + nr_overcommit_hugepages.
See Documentation/vm/hugetlbpage.txt
See Documentation/vm/hugetlbpage.rst
==============================================================
......@@ -667,7 +667,7 @@ and don't use much of it.
The default value is 0.
See Documentation/vm/overcommit-accounting and
See Documentation/vm/overcommit-accounting.rst and
mm/mmap.c::__vm_enough_memory() for more information.
==============================================================
......
00-INDEX
- this file.
active_mm.txt
active_mm.rst
- An explanation from Linus about tsk->active_mm vs tsk->mm.
balance
balance.rst
- various information on memory balancing.
cleancache.txt
cleancache.rst
- Intro to cleancache and page-granularity victim cache.
frontswap.txt
frontswap.rst
- Outline frontswap, part of the transcendent memory frontend.
highmem.txt
highmem.rst
- Outline of highmem and common issues.
hmm.txt
hmm.rst
- Documentation of heterogeneous memory management
hugetlbpage.txt
hugetlbpage.rst
- a brief summary of hugetlbpage support in the Linux kernel.
hugetlbfs_reserv.txt
hugetlbfs_reserv.rst
- A brief overview of hugetlbfs reservation design/implementation.
hwpoison.txt
hwpoison.rst
- explains what hwpoison is
idle_page_tracking.txt
idle_page_tracking.rst
- description of the idle page tracking feature.
ksm.txt
ksm.rst
- how to use the Kernel Samepage Merging feature.
mmu_notifier.txt
mmu_notifier.rst
- a note about clearing pte/pmd and mmu notifications
numa
numa.rst
- information about NUMA specific code in the Linux vm.
numa_memory_policy.txt
numa_memory_policy.rst
- documentation of concepts and APIs of the 2.6 memory policy support.
overcommit-accounting
overcommit-accounting.rst
- description of the Linux kernels overcommit handling modes.
page_frags
page_frags.rst
- description of page fragments allocator
page_migration
page_migration.rst
- description of page migration in NUMA systems.
pagemap.txt
pagemap.rst
- pagemap, from the userspace perspective
page_owner.txt
page_owner.rst
- tracking about who allocated each page
remap_file_pages.txt
remap_file_pages.rst
- a note about remap_file_pages() system call
slub.txt
slub.rst
- a short users guide for SLUB.
soft-dirty.txt
soft-dirty.rst
- short explanation for soft-dirty PTEs
split_page_table_lock
split_page_table_lock.rst
- Separate per-table lock to improve scalability of the old page_table_lock.
swap_numa.txt
swap_numa.rst
- automatic binding of swap device to numa node
transhuge.txt
transhuge.rst
- Transparent Hugepage Support, alternative way of using hugepages.
unevictable-lru.txt
unevictable-lru.rst
- Unevictable LRU infrastructure
userfaultfd.txt
userfaultfd.rst
- description of userfaultfd system call
z3fold.txt
- outline of z3fold allocator for storing compressed pages
zsmalloc.txt
zsmalloc.rst
- outline of zsmalloc allocator for storing compressed pages
zswap.txt
zswap.rst
- Intro to compressed cache for swap pages
.. _active_mm:
=========
Active MM
=========
::
List: linux-kernel
Subject: Re: active_mm
From: Linus Torvalds <torvalds () transmeta ! com>
Date: 1999-07-30 21:36:24
Cc'd to linux-kernel, because I don't write explanations all that often,
and when I do I feel better about more people reading them.
On Fri, 30 Jul 1999, David Mosberger wrote:
>
> Is there a brief description someplace on how "mm" vs. "active_mm" in
> the task_struct are supposed to be used? (My apologies if this was
> discussed on the mailing lists---I just returned from vacation and
> wasn't able to follow linux-kernel for a while).
Basically, the new setup is:
- we have "real address spaces" and "anonymous address spaces". The
difference is that an anonymous address space doesn't care about the
user-level page tables at all, so when we do a context switch into an
anonymous address space we just leave the previous address space
active.
The obvious use for a "anonymous address space" is any thread that
doesn't need any user mappings - all kernel threads basically fall into
this category, but even "real" threads can temporarily say that for
some amount of time they are not going to be interested in user space,
and that the scheduler might as well try to avoid wasting time on
switching the VM state around. Currently only the old-style bdflush
sync does that.
- "tsk->mm" points to the "real address space". For an anonymous process,
tsk->mm will be NULL, for the logical reason that an anonymous process
really doesn't _have_ a real address space at all.
- however, we obviously need to keep track of which address space we
"stole" for such an anonymous user. For that, we have "tsk->active_mm",
which shows what the currently active address space is.
The rule is that for a process with a real address space (ie tsk->mm is
non-NULL) the active_mm obviously always has to be the same as the real
one.
For a anonymous process, tsk->mm == NULL, and tsk->active_mm is the
"borrowed" mm while the anonymous process is running. When the
anonymous process gets scheduled away, the borrowed address space is
returned and cleared.
To support all that, the "struct mm_struct" now has two counters: a
"mm_users" counter that is how many "real address space users" there are,
and a "mm_count" counter that is the number of "lazy" users (ie anonymous
users) plus one if there are any real users.
Usually there is at least one real user, but it could be that the real
user exited on another CPU while a lazy user was still active, so you do
actually get cases where you have a address space that is _only_ used by
lazy users. That is often a short-lived state, because once that thread
gets scheduled away in favour of a real thread, the "zombie" mm gets
released because "mm_users" becomes zero.
Also, a new rule is that _nobody_ ever has "init_mm" as a real MM any
more. "init_mm" should be considered just a "lazy context when no other
context is available", and in fact it is mainly used just at bootup when
no real VM has yet been created. So code that used to check
if (current->mm == &init_mm)
should generally just do
if (!current->mm)
instead (which makes more sense anyway - the test is basically one of "do
we have a user context", and is generally done by the page fault handler
and things like that).
Anyway, I put a pre-patch-2.3.13-1 on ftp.kernel.org just a moment ago,
because it slightly changes the interfaces to accommodate the alpha (who
would have thought it, but the alpha actually ends up having one of the
ugliest context switch codes - unlike the other architectures where the MM
and register state is separate, the alpha PALcode joins the two, and you
need to switch both together).
(From http://marc.info/?l=linux-kernel&m=93337278602211&w=2)
List: linux-kernel
Subject: Re: active_mm
From: Linus Torvalds <torvalds () transmeta ! com>
Date: 1999-07-30 21:36:24
Cc'd to linux-kernel, because I don't write explanations all that often,
and when I do I feel better about more people reading them.
On Fri, 30 Jul 1999, David Mosberger wrote:
>
> Is there a brief description someplace on how "mm" vs. "active_mm" in
> the task_struct are supposed to be used? (My apologies if this was
> discussed on the mailing lists---I just returned from vacation and
> wasn't able to follow linux-kernel for a while).
Basically, the new setup is:
- we have "real address spaces" and "anonymous address spaces". The
difference is that an anonymous address space doesn't care about the
user-level page tables at all, so when we do a context switch into an
anonymous address space we just leave the previous address space
active.
The obvious use for a "anonymous address space" is any thread that
doesn't need any user mappings - all kernel threads basically fall into
this category, but even "real" threads can temporarily say that for
some amount of time they are not going to be interested in user space,
and that the scheduler might as well try to avoid wasting time on
switching the VM state around. Currently only the old-style bdflush
sync does that.
- "tsk->mm" points to the "real address space". For an anonymous process,
tsk->mm will be NULL, for the logical reason that an anonymous process
really doesn't _have_ a real address space at all.
- however, we obviously need to keep track of which address space we
"stole" for such an anonymous user. For that, we have "tsk->active_mm",
which shows what the currently active address space is.
The rule is that for a process with a real address space (ie tsk->mm is
non-NULL) the active_mm obviously always has to be the same as the real
one.
For a anonymous process, tsk->mm == NULL, and tsk->active_mm is the
"borrowed" mm while the anonymous process is running. When the
anonymous process gets scheduled away, the borrowed address space is
returned and cleared.
To support all that, the "struct mm_struct" now has two counters: a
"mm_users" counter that is how many "real address space users" there are,
and a "mm_count" counter that is the number of "lazy" users (ie anonymous
users) plus one if there are any real users.
Usually there is at least one real user, but it could be that the real
user exited on another CPU while a lazy user was still active, so you do
actually get cases where you have a address space that is _only_ used by
lazy users. That is often a short-lived state, because once that thread
gets scheduled away in favour of a real thread, the "zombie" mm gets
released because "mm_users" becomes zero.
Also, a new rule is that _nobody_ ever has "init_mm" as a real MM any
more. "init_mm" should be considered just a "lazy context when no other
context is available", and in fact it is mainly used just at bootup when
no real VM has yet been created. So code that used to check
if (current->mm == &init_mm)
should generally just do
if (!current->mm)
instead (which makes more sense anyway - the test is basically one of "do
we have a user context", and is generally done by the page fault handler
and things like that).
Anyway, I put a pre-patch-2.3.13-1 on ftp.kernel.org just a moment ago,
because it slightly changes the interfaces to accommodate the alpha (who
would have thought it, but the alpha actually ends up having one of the
ugliest context switch codes - unlike the other architectures where the MM
and register state is separate, the alpha PALcode joins the two, and you
need to switch both together).
(From http://marc.info/?l=linux-kernel&m=93337278602211&w=2)
.. _balance:
================
Memory Balancing
================
Started Jan 2000 by Kanoj Sarcar <kanoj@sgi.com>
Memory balancing is needed for !__GFP_ATOMIC and !__GFP_KSWAPD_RECLAIM as
......@@ -89,7 +95,8 @@ pages is below watermark[WMARK_LOW]; in which case zone_wake_kswapd is also set.
(Good) Ideas that I have heard:
1. Dynamic experience should influence balancing: number of failed requests
for a zone can be tracked and fed into the balancing scheme (jalvo@mbay.net)
for a zone can be tracked and fed into the balancing scheme (jalvo@mbay.net)
2. Implement a replace_with_highmem()-like replace_with_regular() to preserve
dma pages. (lkd@tantalophile.demon.co.uk)
dma pages. (lkd@tantalophile.demon.co.uk)
MOTIVATION
.. _cleancache:
==========
Cleancache
==========
Motivation
==========
Cleancache is a new optional feature provided by the VFS layer that
potentially dramatically increases page cache effectiveness for
......@@ -21,9 +28,10 @@ Transcendent memory "drivers" for cleancache are currently implemented
in Xen (using hypervisor memory) and zcache (using in-kernel compressed
memory) and other implementations are in development.
FAQs are included below.
:ref:`FAQs <faq>` are included below.
IMPLEMENTATION OVERVIEW
Implementation Overview
=======================
A cleancache "backend" that provides transcendent memory registers itself
to the kernel's cleancache "frontend" by calling cleancache_register_ops,
......@@ -80,22 +88,33 @@ different Linux threads are simultaneously putting and invalidating a page
with the same handle, the results are indeterminate. Callers must
lock the page to ensure serial behavior.
CLEANCACHE PERFORMANCE METRICS
Cleancache Performance Metrics
==============================
If properly configured, monitoring of cleancache is done via debugfs in
the /sys/kernel/debug/cleancache directory. The effectiveness of cleancache
the `/sys/kernel/debug/cleancache` directory. The effectiveness of cleancache
can be measured (across all filesystems) with:
succ_gets - number of gets that were successful
failed_gets - number of gets that failed
puts - number of puts attempted (all "succeed")
invalidates - number of invalidates attempted
``succ_gets``
number of gets that were successful
``failed_gets``
number of gets that failed
``puts``
number of puts attempted (all "succeed")
``invalidates``
number of invalidates attempted
A backend implementation may provide additional metrics.
.. _faq:
FAQ
===
1) Where's the value? (Andrew Morton)
* Where's the value? (Andrew Morton)
Cleancache provides a significant performance benefit to many workloads
in many environments with negligible overhead by improving the
......@@ -137,7 +156,7 @@ device that stores pages of data in a compressed state. And
the proposed "RAMster" driver shares RAM across multiple physical
systems.
2) Why does cleancache have its sticky fingers so deep inside the
* Why does cleancache have its sticky fingers so deep inside the
filesystems and VFS? (Andrew Morton and Christoph Hellwig)
The core hooks for cleancache in VFS are in most cases a single line
......@@ -168,9 +187,9 @@ filesystems in the future.
The total impact of the hooks to existing fs and mm files is only
about 40 lines added (not counting comments and blank lines).
3) Why not make cleancache asynchronous and batched so it can
more easily interface with real devices with DMA instead
of copying each individual page? (Minchan Kim)
* Why not make cleancache asynchronous and batched so it can more
easily interface with real devices with DMA instead of copying each
individual page? (Minchan Kim)
The one-page-at-a-time copy semantics simplifies the implementation
on both the frontend and backend and also allows the backend to
......@@ -182,7 +201,7 @@ are avoided. While the interface seems odd for a "real device"
or for real kernel-addressable RAM, it makes perfect sense for
transcendent memory.
4) Why is non-shared cleancache "exclusive"? And where is the
* Why is non-shared cleancache "exclusive"? And where is the
page "invalidated" after a "get"? (Minchan Kim)
The main reason is to free up space in transcendent memory and
......@@ -193,7 +212,7 @@ be easily extended to add a "get_no_invalidate" call.
The invalidate is done by the cleancache backend implementation.
5) What's the performance impact?
* What's the performance impact?
Performance analysis has been presented at OLS'09 and LCA'10.
Briefly, performance gains can be significant on most workloads,
......@@ -206,7 +225,7 @@ single-core systems with slow memory-copy speeds, cleancache
has little value, but in newer multicore machines, especially
consolidated/virtualized machines, it has great value.
6) How do I add cleancache support for filesystem X? (Boaz Harrash)
* How do I add cleancache support for filesystem X? (Boaz Harrash)
Filesystems that are well-behaved and conform to certain
restrictions can utilize cleancache simply by making a call to
......@@ -217,26 +236,26 @@ not enable the optional cleancache.
Some points for a filesystem to consider:
- The FS should be block-device-based (e.g. a ram-based FS such
- The FS should be block-device-based (e.g. a ram-based FS such
as tmpfs should not enable cleancache)
- To ensure coherency/correctness, the FS must ensure that all
- To ensure coherency/correctness, the FS must ensure that all
file removal or truncation operations either go through VFS or
add hooks to do the equivalent cleancache "invalidate" operations
- To ensure coherency/correctness, either inode numbers must
- To ensure coherency/correctness, either inode numbers must
be unique across the lifetime of the on-disk file OR the
FS must provide an "encode_fh" function.
- The FS must call the VFS superblock alloc and deactivate routines
- The FS must call the VFS superblock alloc and deactivate routines
or add hooks to do the equivalent cleancache calls done there.
- To maximize performance, all pages fetched from the FS should
- To maximize performance, all pages fetched from the FS should
go through the do_mpag_readpage routine or the FS should add
hooks to do the equivalent (cf. btrfs)
- Currently, the FS blocksize must be the same as PAGESIZE. This
- Currently, the FS blocksize must be the same as PAGESIZE. This
is not an architectural restriction, but no backends currently
support anything different.
- A clustered FS should invoke the "shared_init_fs" cleancache
- A clustered FS should invoke the "shared_init_fs" cleancache
hook to get best performance for some backends.
7) Why not use the KVA of the inode as the key? (Christoph Hellwig)
* Why not use the KVA of the inode as the key? (Christoph Hellwig)
If cleancache would use the inode virtual address instead of
inode/filehandle, the pool id could be eliminated. But, this
......@@ -251,7 +270,7 @@ of cleancache would be lost because the cache of pages in cleanache
is potentially much larger than the kernel pagecache and is most
useful if the pages survive inode cache removal.
8) Why is a global variable required?
* Why is a global variable required?
The cleancache_enabled flag is checked in all of the frequently-used
cleancache hooks. The alternative is a function call to check a static
......@@ -262,13 +281,13 @@ global variable allows cleancache to be enabled by default at compile
time, but have insignificant performance impact when cleancache remains
disabled at runtime.
9) Does cleanache work with KVM?
* Does cleanache work with KVM?
The memory model of KVM is sufficiently different that a cleancache
backend may have less value for KVM. This remains to be tested,
especially in an overcommitted system.
10) Does cleancache work in userspace? It sounds useful for
* Does cleancache work in userspace? It sounds useful for
memory hungry caches like web browsers. (Jamie Lokier)
No plans yet, though we agree it sounds useful, at least for
......
# -*- coding: utf-8; mode: python -*-
project = "Linux Memory Management Documentation"
tags.add("subproject")
latex_documents = [
('index', 'memory-management.tex', project,
'The kernel development community', 'manual'),
]
.. _frontswap:
=========
Frontswap
=========
Frontswap provides a "transcendent memory" interface for swap pages.
In some environments, dramatic performance savings may be obtained because
swapped pages are saved in RAM (or a RAM-like device) instead of a swap disk.
(Note, frontswap -- and cleancache (merged at 3.0) -- are the "frontends"
(Note, frontswap -- and :ref:`cleancache` (merged at 3.0) -- are the "frontends"
and the only necessary changes to the core kernel for transcendent memory;
all other supporting code -- the "backends" -- is implemented as drivers.
See the LWN.net article "Transcendent memory in a nutshell" for a detailed
overview of frontswap and related kernel parts:
https://lwn.net/Articles/454795/ )
See the LWN.net article `Transcendent memory in a nutshell`_
for a detailed overview of frontswap and related kernel parts)
.. _Transcendent memory in a nutshell: https://lwn.net/Articles/454795/
Frontswap is so named because it can be thought of as the opposite of
a "backing" store for a swap device. The storage is assumed to be
......@@ -50,19 +57,27 @@ or the store fails AND the page is invalidated. This ensures stale data may
never be obtained from frontswap.
If properly configured, monitoring of frontswap is done via debugfs in
the /sys/kernel/debug/frontswap directory. The effectiveness of
the `/sys/kernel/debug/frontswap` directory. The effectiveness of
frontswap can be measured (across all swap devices) with:
failed_stores - how many store attempts have failed
loads - how many loads were attempted (all should succeed)
succ_stores - how many store attempts have succeeded
invalidates - how many invalidates were attempted
``failed_stores``
how many store attempts have failed
``loads``
how many loads were attempted (all should succeed)
``succ_stores``
how many store attempts have succeeded
``invalidates``
how many invalidates were attempted
A backend implementation may provide additional metrics.
FAQ
===
1) Where's the value?
* Where's the value?
When a workload starts swapping, performance falls through the floor.
Frontswap significantly increases performance in many such workloads by
......@@ -117,7 +132,7 @@ A KVM implementation is underway and has been RFC'ed to lkml. And,
using frontswap, investigation is also underway on the use of NVM as
a memory extension technology.
2) Sure there may be performance advantages in some situations, but
* Sure there may be performance advantages in some situations, but
what's the space/time overhead of frontswap?
If CONFIG_FRONTSWAP is disabled, every frontswap hook compiles into
......@@ -148,7 +163,7 @@ pressure that can potentially outweigh the other advantages. A
backend, such as zcache, must implement policies to carefully (but
dynamically) manage memory limits to ensure this doesn't happen.
3) OK, how about a quick overview of what this frontswap patch does
* OK, how about a quick overview of what this frontswap patch does
in terms that a kernel hacker can grok?
Let's assume that a frontswap "backend" has registered during
......@@ -188,7 +203,7 @@ and (potentially) a swap device write are replaced by a "frontswap backend
store" and (possibly) a "frontswap backend loads", which are presumably much
faster.
4) Can't frontswap be configured as a "special" swap device that is
* Can't frontswap be configured as a "special" swap device that is
just higher priority than any real swap device (e.g. like zswap,
or maybe swap-over-nbd/NFS)?
......@@ -240,7 +255,7 @@ installation, frontswap is useless. Swapless portable devices
can still use frontswap but a backend for such devices must configure
some kind of "ghost" swap device and ensure that it is never used.
5) Why this weird definition about "duplicate stores"? If a page
* Why this weird definition about "duplicate stores"? If a page
has been previously successfully stored, can't it always be
successfully overwritten?
......@@ -254,7 +269,7 @@ the old data and ensure that it is no longer accessible. Since the
swap subsystem then writes the new data to the read swap device,
this is the correct course of action to ensure coherency.
6) What is frontswap_shrink for?
* What is frontswap_shrink for?
When the (non-frontswap) swap subsystem swaps out a page to a real
swap device, that page is only taking up low-value pre-allocated disk
......@@ -267,7 +282,7 @@ to "repatriate" pages sent to a remote machine back to the local machine;
this is driven using the frontswap_shrink mechanism when memory pressure
subsides.
7) Why does the frontswap patch create the new include file swapfile.h?
* Why does the frontswap patch create the new include file swapfile.h?
The frontswap code depends on some swap-subsystem-internal data
structures that have, over the years, moved back and forth between
......
.. _highmem:
====================
HIGH MEMORY HANDLING
====================
====================
High Memory Handling
====================
By: Peter Zijlstra <a.p.zijlstra@chello.nl>
Contents:
(*) What is high memory?
(*) Temporary virtual mappings.
(*) Using kmap_atomic.
(*) Cost of temporary mappings.
(*) i386 PAE.
.. contents:: :local:
====================
WHAT IS HIGH MEMORY?
What Is High Memory?
====================
High memory (highmem) is used when the size of physical memory approaches or
......@@ -38,7 +27,7 @@ kernel entry/exit. This means the available virtual memory space (4GiB on
i386) has to be divided between user and kernel space.
The traditional split for architectures using this approach is 3:1, 3GiB for
userspace and the top 1GiB for kernel space:
userspace and the top 1GiB for kernel space::
+--------+ 0xffffffff
| Kernel |
......@@ -58,22 +47,21 @@ and user maps. Some hardware (like some ARMs), however, have limited virtual
space when they use mm context tags.
==========================
TEMPORARY VIRTUAL MAPPINGS
Temporary Virtual Mappings
==========================
The kernel contains several ways of creating temporary mappings:
(*) vmap(). This can be used to make a long duration mapping of multiple
* vmap(). This can be used to make a long duration mapping of multiple
physical pages into a contiguous virtual space. It needs global
synchronization to unmap.
(*) kmap(). This permits a short duration mapping of a single page. It needs
* kmap(). This permits a short duration mapping of a single page. It needs
global synchronization, but is amortized somewhat. It is also prone to
deadlocks when using in a nested fashion, and so it is not recommended for
new code.
(*) kmap_atomic(). This permits a very short duration mapping of a single
* kmap_atomic(). This permits a very short duration mapping of a single
page. Since the mapping is restricted to the CPU that issued it, it
performs well, but the issuing task is therefore required to stay on that
CPU until it has finished, lest some other task displace its mappings.
......@@ -84,14 +72,13 @@ The kernel contains several ways of creating temporary mappings:
It may be assumed that k[un]map_atomic() won't fail.
=================
USING KMAP_ATOMIC
Using kmap_atomic
=================
When and where to use kmap_atomic() is straightforward. It is used when code
wants to access the contents of a page that might be allocated from high memory
(see __GFP_HIGHMEM), for example a page in the pagecache. The API has two
functions, and they can be used in a manner similar to the following:
functions, and they can be used in a manner similar to the following::
/* Find the page of interest. */
struct page *page = find_get_page(mapping, offset);
......@@ -109,7 +96,7 @@ Note that the kunmap_atomic() call takes the result of the kmap_atomic() call
not the argument.
If you need to map two pages because you want to copy from one page to
another you need to keep the kmap_atomic calls strictly nested, like:
another you need to keep the kmap_atomic calls strictly nested, like::
vaddr1 = kmap_atomic(page1);
vaddr2 = kmap_atomic(page2);
......@@ -120,8 +107,7 @@ another you need to keep the kmap_atomic calls strictly nested, like:
kunmap_atomic(vaddr1);
==========================
COST OF TEMPORARY MAPPINGS
Cost of Temporary Mappings
==========================
The cost of creating temporary mappings can be quite high. The arch has to
......@@ -136,22 +122,21 @@ If CONFIG_MMU is not set, then there can be no temporary mappings and no
highmem. In such a case, the arithmetic approach will also be used.
========
i386 PAE
========
The i386 arch, under some circumstances, will permit you to stick up to 64GiB
of RAM into your 32-bit machine. This has a number of consequences:
(*) Linux needs a page-frame structure for each page in the system and the
* Linux needs a page-frame structure for each page in the system and the
pageframes need to live in the permanent mapping, which means:
(*) you can have 896M/sizeof(struct page) page-frames at most; with struct
* you can have 896M/sizeof(struct page) page-frames at most; with struct
page being 32-bytes that would end up being something in the order of 112G
worth of pages; the kernel, however, needs to store more than just
page-frames in that memory...
(*) PAE makes your page tables larger - which slows the system down as more
* PAE makes your page tables larger - which slows the system down as more
data has to be accessed to traverse in TLB fills and the like. One
advantage is that PAE has more PTE bits and can provide advanced features
like NX and PAT.
......
.. hmm:
=====================================
Heterogeneous Memory Management (HMM)
=====================================
Provide infrastructure and helpers to integrate non-conventional memory (device
memory like GPU on board memory) into regular kernel path, with the cornerstone
......@@ -6,10 +10,10 @@ of this being specialized struct page for such memory (see sections 5 to 7 of
this document).
HMM also provides optional helpers for SVM (Share Virtual Memory), i.e.,
allowing a device to transparently access program address coherently with the
CPU meaning that any valid pointer on the CPU is also a valid pointer for the
device. This is becoming mandatory to simplify the use of advanced hetero-
geneous computing where GPU, DSP, or FPGA are used to perform various
allowing a device to transparently access program address coherently with
the CPU meaning that any valid pointer on the CPU is also a valid pointer
for the device. This is becoming mandatory to simplify the use of advanced
heterogeneous computing where GPU, DSP, or FPGA are used to perform various
computations on behalf of a process.
This document is divided as follows: in the first section I expose the problems
......@@ -21,19 +25,10 @@ fifth section deals with how device memory is represented inside the kernel.
Finally, the last section presents a new migration helper that allows lever-
aging the device DMA engine.
.. contents:: :local:
1) Problems of using a device specific memory allocator:
2) I/O bus, device memory characteristics
3) Shared address space and migration
4) Address space mirroring implementation and API
5) Represent and manage device memory from core kernel point of view
6) Migration to and from device memory
7) Memory cgroup (memcg) and rss accounting
-------------------------------------------------------------------------------
1) Problems of using a device specific memory allocator:
Problems of using a device specific memory allocator
====================================================
Devices with a large amount of on board memory (several gigabytes) like GPUs
have historically managed their memory through dedicated driver specific APIs.
......@@ -77,9 +72,8 @@ are only do-able with a shared address space. It is also more reasonable to use
a shared address space for all other patterns.
-------------------------------------------------------------------------------
2) I/O bus, device memory characteristics
I/O bus, device memory characteristics
======================================
I/O buses cripple shared address spaces due to a few limitations. Most I/O
buses only allow basic memory access from device to main memory; even cache
......@@ -109,9 +103,8 @@ access any memory but we must also permit any memory to be migrated to device
memory while device is using it (blocking CPU access while it happens).
-------------------------------------------------------------------------------
3) Shared address space and migration
Shared address space and migration
==================================
HMM intends to provide two main features. First one is to share the address
space by duplicating the CPU page table in the device page table so the same
......@@ -148,23 +141,23 @@ ages device memory by migrating the part of the data set that is actively being
used by the device.
-------------------------------------------------------------------------------
4) Address space mirroring implementation and API
Address space mirroring implementation and API
==============================================
Address space mirroring's main objective is to allow duplication of a range of
CPU page table into a device page table; HMM helps keep both synchronized. A
device driver that wants to mirror a process address space must start with the
registration of an hmm_mirror struct:
registration of an hmm_mirror struct::
int hmm_mirror_register(struct hmm_mirror *mirror,
struct mm_struct *mm);
int hmm_mirror_register_locked(struct hmm_mirror *mirror,
struct mm_struct *mm);
The locked variant is to be used when the driver is already holding mmap_sem
of the mm in write mode. The mirror struct has a set of callbacks that are used
to propagate CPU page tables:
to propagate CPU page tables::
struct hmm_mirror_ops {
/* sync_cpu_device_pagetables() - synchronize page tables
......@@ -193,9 +186,9 @@ The device driver must perform the update action to the range (mark range
read only, or fully unmap, ...). The device must be done with the update before
the driver callback returns.
When the device driver wants to populate a range of virtual addresses, it can
use either:
use either::
int hmm_vma_get_pfns(struct vm_area_struct *vma,
struct hmm_range *range,
unsigned long start,
......@@ -221,7 +214,7 @@ provides a set of flags to help the driver identify special CPU page table
entries.
Locking with the update() callback is the most important aspect the driver must
respect in order to keep things properly synchronized. The usage pattern is:
respect in order to keep things properly synchronized. The usage pattern is::
int driver_populate_range(...)
{
......@@ -262,9 +255,8 @@ report commands as executed is serialized (there is no point in doing this
concurrently).
-------------------------------------------------------------------------------
5) Represent and manage device memory from core kernel point of view
Represent and manage device memory from core kernel point of view
=================================================================
Several different designs were tried to support device memory. First one used
a device specific data structure to keep information about migrated memory and
......@@ -280,14 +272,14 @@ unaware of the difference. We only need to make sure that no one ever tries to
map those pages from the CPU side.
HMM provides a set of helpers to register and hotplug device memory as a new
region needing a struct page. This is offered through a very simple API:
region needing a struct page. This is offered through a very simple API::
struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
struct device *device,
unsigned long size);
void hmm_devmem_remove(struct hmm_devmem *devmem);
The hmm_devmem_ops is where most of the important things are:
The hmm_devmem_ops is where most of the important things are::
struct hmm_devmem_ops {
void (*free)(struct hmm_devmem *devmem, struct page *page);
......@@ -306,13 +298,12 @@ which it cannot do. This second callback must trigger a migration back to
system memory.
-------------------------------------------------------------------------------
6) Migration to and from device memory
Migration to and from device memory
===================================
Because the CPU cannot access device memory, migration must use the device DMA
engine to perform copy from and to device memory. For this we need a new
migration helper:
migration helper::
int migrate_vma(const struct migrate_vma_ops *ops,
struct vm_area_struct *vma,
......@@ -331,7 +322,7 @@ migration might be for a range of addresses the device is actively accessing.
The migrate_vma_ops struct defines two callbacks. First one (alloc_and_copy())
controls destination memory allocation and copy operation. Second one is there
to allow the device driver to perform cleanup operations after migration.
to allow the device driver to perform cleanup operations after migration::
struct migrate_vma_ops {
void (*alloc_and_copy)(struct vm_area_struct *vma,
......@@ -365,9 +356,8 @@ bandwidth but this is considered as a rare event and a price that we are
willing to pay to keep all the code simpler.
-------------------------------------------------------------------------------
7) Memory cgroup (memcg) and rss accounting
Memory cgroup (memcg) and rss accounting
========================================
For now device memory is accounted as any regular page in rss counters (either
anonymous if device page is used for anonymous, file if device page is used for
......
.. hwpoison:
========
hwpoison
========
What is hwpoison?
=================
Upcoming Intel CPUs have support for recovering from some memory errors
(``MCA recovery''). This requires the OS to declare a page "poisoned",
(``MCA recovery``). This requires the OS to declare a page "poisoned",
kill the processes associated with it and avoid using it in the future.
This patchkit implements the necessary infrastructure in the VM.
......@@ -46,9 +53,10 @@ address. This in theory allows other applications to handle
memory failures too. The expection is that near all applications
won't do that, but some very specialized ones might.
---
Failure recovery modes
======================
There are two (actually three) modi memory failure recovery can be in:
There are two (actually three) modes memory failure recovery can be in:
vm.memory_failure_recovery sysctl set to zero:
All memory failures cause a panic. Do not attempt recovery.
......@@ -67,9 +75,8 @@ late kill
This is best for memory error unaware applications and default
Note some pages are always handled as late kill.
---
User control:
User control
============
vm.memory_failure_recovery
See sysctl.txt
......@@ -79,11 +86,19 @@ vm.memory_failure_early_kill
PR_MCE_KILL
Set early/late kill mode/revert to system default
arg1: PR_MCE_KILL_CLEAR: Revert to system default
arg1: PR_MCE_KILL_SET: arg2 defines thread specific mode
PR_MCE_KILL_EARLY: Early kill
PR_MCE_KILL_LATE: Late kill
PR_MCE_KILL_DEFAULT: Use system global default
arg1: PR_MCE_KILL_CLEAR:
Revert to system default
arg1: PR_MCE_KILL_SET:
arg2 defines thread specific mode
PR_MCE_KILL_EARLY:
Early kill
PR_MCE_KILL_LATE:
Late kill
PR_MCE_KILL_DEFAULT
Use system global default
Note that if you want to have a dedicated thread which handles
the SIGBUS(BUS_MCEERR_AO) on behalf of the process, you should
call prctl(PR_MCE_KILL_EARLY) on the designated thread. Otherwise,
......@@ -92,48 +107,38 @@ PR_MCE_KILL
PR_MCE_KILL_GET
return current mode
Testing
=======
---
Testing:
madvise(MADV_HWPOISON, ....)
(as root)
Poison a page in the process for testing
* madvise(MADV_HWPOISON, ....) (as root) - Poison a page in the
process for testing
hwpoison-inject module through debugfs
* hwpoison-inject module through debugfs ``/sys/kernel/debug/hwpoison/``
/sys/kernel/debug/hwpoison/
corrupt-pfn
Inject hwpoison fault at PFN echoed into this file. This does
some early filtering to avoid corrupted unintended pages in test suites.
corrupt-pfn
unpoison-pfn
Software-unpoison page at PFN echoed into this file. This way
a page can be reused again. This only works for Linux
injected failures, not for real memory failures.
Inject hwpoison fault at PFN echoed into this file. This does
some early filtering to avoid corrupted unintended pages in test suites.
Note these injection interfaces are not stable and might change between
kernel versions
unpoison-pfn
corrupt-filter-dev-major, corrupt-filter-dev-minor
Only handle memory failures to pages associated with the file
system defined by block device major/minor. -1U is the
wildcard value. This should be only used for testing with
artificial injection.
Software-unpoison page at PFN echoed into this file. This
way a page can be reused again.
This only works for Linux injected failures, not for real
memory failures.
corrupt-filter-memcg
Limit injection to pages owned by memgroup. Specified by inode
number of the memcg.
Note these injection interfaces are not stable and might change between
kernel versions
Example::
corrupt-filter-dev-major
corrupt-filter-dev-minor
Only handle memory failures to pages associated with the file system defined
by block device major/minor. -1U is the wildcard value.
This should be only used for testing with artificial injection.
corrupt-filter-memcg
Limit injection to pages owned by memgroup. Specified by inode number
of the memcg.
Example:
mkdir /sys/fs/cgroup/mem/hwpoison
usemem -m 100 -s 1000 &
......@@ -145,24 +150,21 @@ Example:
page-types -p `pidof init` --hwpoison # shall do nothing
page-types -p `pidof usemem` --hwpoison # poison its pages
corrupt-filter-flags-mask
corrupt-filter-flags-value
When specified, only poison pages if ((page_flags & mask) == value).
This allows stress testing of many kinds of pages. The page_flags
are the same as in /proc/kpageflags. The flag bits are defined in
include/linux/kernel-page-flags.h and documented in
Documentation/vm/pagemap.txt
corrupt-filter-flags-mask, corrupt-filter-flags-value
When specified, only poison pages if ((page_flags & mask) ==
value). This allows stress testing of many kinds of
pages. The page_flags are the same as in /proc/kpageflags. The
flag bits are defined in include/linux/kernel-page-flags.h and
documented in Documentation/vm/pagemap.rst
Architecture specific MCE injector
* Architecture specific MCE injector
x86 has mce-inject, mce-test
x86 has mce-inject, mce-test
Some portable hwpoison test programs in mce-test, see blow.
Some portable hwpoison test programs in mce-test, see below.
---
References:
References
==========
http://halobates.de/mce-lc09-2.pdf
Overview presentation from LinuxCon 09
......@@ -174,14 +176,11 @@ git://git.kernel.org/pub/scm/utils/cpu/mce/mce-inject.git
x86 specific injector
---
Limitations:
Limitations
===========
- Not all page types are supported and never will. Most kernel internal
objects cannot be recovered, only LRU pages for now.
objects cannot be recovered, only LRU pages for now.
- Right now hugepage support is missing.
---
Andi Kleen, Oct 2009
MOTIVATION
.. _idle_page_tracking:
==================
Idle Page Tracking
==================
Motivation
==========
The idle page tracking feature allows to track which memory pages are being
accessed by a workload and which are idle. This information can be useful for
......@@ -8,10 +15,14 @@ or deciding where to place the workload within a compute cluster.
It is enabled by CONFIG_IDLE_PAGE_TRACKING=y.
USER API
.. _user_api:
The idle page tracking API is located at /sys/kernel/mm/page_idle. Currently,
it consists of the only read-write file, /sys/kernel/mm/page_idle/bitmap.
User API
========
The idle page tracking API is located at ``/sys/kernel/mm/page_idle``.
Currently, it consists of the only read-write file,
``/sys/kernel/mm/page_idle/bitmap``.
The file implements a bitmap where each bit corresponds to a memory page. The
bitmap is represented by an array of 8-byte integers, and the page at PFN #i is
......@@ -19,8 +30,9 @@ mapped to bit #i%64 of array element #i/64, byte order is native. When a bit is
set, the corresponding page is idle.
A page is considered idle if it has not been accessed since it was marked idle
(for more details on what "accessed" actually means see the IMPLEMENTATION
DETAILS section). To mark a page idle one has to set the bit corresponding to
(for more details on what "accessed" actually means see the :ref:`Implementation
Details <impl_details>` section).
To mark a page idle one has to set the bit corresponding to
the page by writing to the file. A value written to the file is OR-ed with the
current bitmap value.
......@@ -30,9 +42,9 @@ page types (e.g. SLAB pages) an attempt to mark a page idle is silently ignored,
and hence such pages are never reported idle.
For huge pages the idle flag is set only on the head page, so one has to read
/proc/kpageflags in order to correctly count idle huge pages.
``/proc/kpageflags`` in order to correctly count idle huge pages.
Reading from or writing to /sys/kernel/mm/page_idle/bitmap will return
Reading from or writing to ``/sys/kernel/mm/page_idle/bitmap`` will return
-EINVAL if you are not starting the read/write on an 8-byte boundary, or
if the size of the read/write is not a multiple of 8 bytes. Writing to
this file beyond max PFN will return -ENXIO.
......@@ -41,21 +53,25 @@ That said, in order to estimate the amount of pages that are not used by a
workload one should:
1. Mark all the workload's pages as idle by setting corresponding bits in
/sys/kernel/mm/page_idle/bitmap. The pages can be found by reading
/proc/pid/pagemap if the workload is represented by a process, or by
filtering out alien pages using /proc/kpagecgroup in case the workload is
placed in a memory cgroup.
``/sys/kernel/mm/page_idle/bitmap``. The pages can be found by reading
``/proc/pid/pagemap`` if the workload is represented by a process, or by
filtering out alien pages using ``/proc/kpagecgroup`` in case the workload
is placed in a memory cgroup.
2. Wait until the workload accesses its working set.
3. Read /sys/kernel/mm/page_idle/bitmap and count the number of bits set. If
one wants to ignore certain types of pages, e.g. mlocked pages since they
are not reclaimable, he or she can filter them out using /proc/kpageflags.
3. Read ``/sys/kernel/mm/page_idle/bitmap`` and count the number of bits set.
If one wants to ignore certain types of pages, e.g. mlocked pages since they
are not reclaimable, he or she can filter them out using
``/proc/kpageflags``.
See Documentation/vm/pagemap.rst for more information about
``/proc/pid/pagemap``, ``/proc/kpageflags``, and ``/proc/kpagecgroup``.
See Documentation/vm/pagemap.txt for more information about /proc/pid/pagemap,
/proc/kpageflags, and /proc/kpagecgroup.
.. _impl_details:
IMPLEMENTATION DETAILS
Implementation Details
======================
The kernel internally keeps track of accesses to user memory pages in order to
reclaim unreferenced pages first on memory shortage conditions. A page is
......@@ -77,7 +93,8 @@ When a dirty page is written to swap or disk as a result of memory reclaim or
exceeding the dirty memory limit, it is not marked referenced.
The idle memory tracking feature adds a new page flag, the Idle flag. This flag
is set manually, by writing to /sys/kernel/mm/page_idle/bitmap (see the USER API
is set manually, by writing to ``/sys/kernel/mm/page_idle/bitmap`` (see the
:ref:`User API <user_api>`
section), and cleared automatically whenever a page is referenced as defined
above.
......
=====================================
Linux Memory Management Documentation
=====================================
This is a collection of documents about Linux memory management (mm) subsystem.
User guides for MM features
===========================
The following documents provide guides for controlling and tuning
various features of the Linux memory management
.. toctree::
:maxdepth: 1
hugetlbpage
idle_page_tracking
ksm
numa_memory_policy
pagemap
transhuge
soft-dirty
swap_numa
userfaultfd
zswap
Kernel developers MM documentation
==================================
The below documents describe MM internals with different level of
details ranging from notes and mailing list responses to elaborate
descriptions of data structures and algorithms.
.. toctree::
:maxdepth: 1
active_mm
balance
cleancache
frontswap
highmem
hmm
hwpoison
hugetlbfs_reserv
mmu_notifier
numa
overcommit-accounting
page_migration
page_frags
page_owner
remap_file_pages
slub
split_page_table_lock
unevictable-lru
z3fold
zsmalloc
.. _mmu_notifier:
When do you need to notify inside page table lock ?
===================================================
When clearing a pte/pmd we are given a choice to notify the event through
(notify version of *_clear_flush call mmu_notifier_invalidate_range) under
(notify version of \*_clear_flush call mmu_notifier_invalidate_range) under
the page table lock. But that notification is not necessary in all cases.
For secondary TLB (non CPU TLB) like IOMMU TLB or device TLB (when device use
......@@ -18,6 +21,7 @@ a page that might now be used by some completely different task.
Case B is more subtle. For correctness it requires the following sequence to
happen:
- take page table lock
- clear page table entry and notify ([pmd/pte]p_huge_clear_flush_notify())
- set page table entry to point to new page
......@@ -28,58 +32,60 @@ the device.
Consider the following scenario (device use a feature similar to ATS/PASID):
Two address addrA and addrB such that |addrA - addrB| >= PAGE_SIZE we assume
Two address addrA and addrB such that \|addrA - addrB\| >= PAGE_SIZE we assume
they are write protected for COW (other case of B apply too).
[Time N] --------------------------------------------------------------------
CPU-thread-0 {try to write to addrA}
CPU-thread-1 {try to write to addrB}
CPU-thread-2 {}
CPU-thread-3 {}
DEV-thread-0 {read addrA and populate device TLB}
DEV-thread-2 {read addrB and populate device TLB}
[Time N+1] ------------------------------------------------------------------
CPU-thread-0 {COW_step0: {mmu_notifier_invalidate_range_start(addrA)}}
CPU-thread-1 {COW_step0: {mmu_notifier_invalidate_range_start(addrB)}}
CPU-thread-2 {}
CPU-thread-3 {}
DEV-thread-0 {}
DEV-thread-2 {}
[Time N+2] ------------------------------------------------------------------
CPU-thread-0 {COW_step1: {update page table to point to new page for addrA}}
CPU-thread-1 {COW_step1: {update page table to point to new page for addrB}}
CPU-thread-2 {}
CPU-thread-3 {}
DEV-thread-0 {}
DEV-thread-2 {}
[Time N+3] ------------------------------------------------------------------
CPU-thread-0 {preempted}
CPU-thread-1 {preempted}
CPU-thread-2 {write to addrA which is a write to new page}
CPU-thread-3 {}
DEV-thread-0 {}
DEV-thread-2 {}
[Time N+3] ------------------------------------------------------------------
CPU-thread-0 {preempted}
CPU-thread-1 {preempted}
CPU-thread-2 {}
CPU-thread-3 {write to addrB which is a write to new page}
DEV-thread-0 {}
DEV-thread-2 {}
[Time N+4] ------------------------------------------------------------------
CPU-thread-0 {preempted}
CPU-thread-1 {COW_step3: {mmu_notifier_invalidate_range_end(addrB)}}
CPU-thread-2 {}
CPU-thread-3 {}
DEV-thread-0 {}
DEV-thread-2 {}
[Time N+5] ------------------------------------------------------------------
CPU-thread-0 {preempted}
CPU-thread-1 {}
CPU-thread-2 {}
CPU-thread-3 {}
DEV-thread-0 {read addrA from old page}
DEV-thread-2 {read addrB from new page}
::
[Time N] --------------------------------------------------------------------
CPU-thread-0 {try to write to addrA}
CPU-thread-1 {try to write to addrB}
CPU-thread-2 {}
CPU-thread-3 {}
DEV-thread-0 {read addrA and populate device TLB}
DEV-thread-2 {read addrB and populate device TLB}
[Time N+1] ------------------------------------------------------------------
CPU-thread-0 {COW_step0: {mmu_notifier_invalidate_range_start(addrA)}}
CPU-thread-1 {COW_step0: {mmu_notifier_invalidate_range_start(addrB)}}
CPU-thread-2 {}
CPU-thread-3 {}
DEV-thread-0 {}
DEV-thread-2 {}
[Time N+2] ------------------------------------------------------------------
CPU-thread-0 {COW_step1: {update page table to point to new page for addrA}}
CPU-thread-1 {COW_step1: {update page table to point to new page for addrB}}
CPU-thread-2 {}
CPU-thread-3 {}
DEV-thread-0 {}
DEV-thread-2 {}
[Time N+3] ------------------------------------------------------------------
CPU-thread-0 {preempted}
CPU-thread-1 {preempted}
CPU-thread-2 {write to addrA which is a write to new page}
CPU-thread-3 {}
DEV-thread-0 {}
DEV-thread-2 {}
[Time N+3] ------------------------------------------------------------------
CPU-thread-0 {preempted}
CPU-thread-1 {preempted}
CPU-thread-2 {}
CPU-thread-3 {write to addrB which is a write to new page}
DEV-thread-0 {}
DEV-thread-2 {}
[Time N+4] ------------------------------------------------------------------
CPU-thread-0 {preempted}
CPU-thread-1 {COW_step3: {mmu_notifier_invalidate_range_end(addrB)}}
CPU-thread-2 {}
CPU-thread-3 {}
DEV-thread-0 {}
DEV-thread-2 {}
[Time N+5] ------------------------------------------------------------------
CPU-thread-0 {preempted}
CPU-thread-1 {}
CPU-thread-2 {}
CPU-thread-3 {}
DEV-thread-0 {read addrA from old page}
DEV-thread-2 {read addrB from new page}
So here because at time N+2 the clear page table entry was not pair with a
notification to invalidate the secondary TLB, the device see the new value for
......
.. _numa:
Started Nov 1999 by Kanoj Sarcar <kanoj@sgi.com>
=============
What is NUMA?
=============
This question can be answered from a couple of perspectives: the
hardware view and the Linux software view.
......@@ -106,7 +110,7 @@ to improve NUMA locality using various CPU affinity command line interfaces,
such as taskset(1) and numactl(1), and program interfaces such as
sched_setaffinity(2). Further, one can modify the kernel's default local
allocation behavior using Linux NUMA memory policy.
[see Documentation/vm/numa_memory_policy.txt.]
[see Documentation/vm/numa_memory_policy.rst.]
System administrators can restrict the CPUs and nodes' memories that a non-
privileged user can specify in the scheduling or NUMA commands and functions
......
The Linux kernel supports the following overcommit handling modes
0 - Heuristic overcommit handling. Obvious overcommits of
address space are refused. Used for a typical system. It
ensures a seriously wild allocation fails while allowing
overcommit to reduce swap usage. root is allowed to
allocate slightly more memory in this mode. This is the
default.
1 - Always overcommit. Appropriate for some scientific
applications. Classic example is code using sparse arrays
and just relying on the virtual memory consisting almost
entirely of zero pages.
2 - Don't overcommit. The total address space commit
for the system is not permitted to exceed swap + a
configurable amount (default is 50%) of physical RAM.
Depending on the amount you use, in most situations
this means a process will not be killed while accessing
pages but will receive errors on memory allocation as
appropriate.
Useful for applications that want to guarantee their
memory allocations will be available in the future
without having to initialize every page.
The overcommit policy is set via the sysctl `vm.overcommit_memory'.
The overcommit amount can be set via `vm.overcommit_ratio' (percentage)
or `vm.overcommit_kbytes' (absolute value).
The current overcommit limit and amount committed are viewable in
/proc/meminfo as CommitLimit and Committed_AS respectively.
Gotchas
-------
The C language stack growth does an implicit mremap. If you want absolute
guarantees and run close to the edge you MUST mmap your stack for the
largest size you think you will need. For typical stack usage this does
not matter much but it's a corner case if you really really care
In mode 2 the MAP_NORESERVE flag is ignored.
How It Works
------------
The overcommit is based on the following rules
For a file backed map
SHARED or READ-only - 0 cost (the file is the map not swap)
PRIVATE WRITABLE - size of mapping per instance
For an anonymous or /dev/zero map
SHARED - size of mapping
PRIVATE READ-only - 0 cost (but of little use)
PRIVATE WRITABLE - size of mapping per instance
Additional accounting
Pages made writable copies by mmap
shmfs memory drawn from the same pool
Status
------
o We account mmap memory mappings
o We account mprotect changes in commit
o We account mremap changes in size
o We account brk
o We account munmap
o We report the commit status in /proc
o Account and check on fork
o Review stack handling/building on exec
o SHMfs accounting
o Implement actual limit enforcement
To Do
-----
o Account ptrace pages (this is hard)
.. _overcommit_accounting:
=====================
Overcommit Accounting
=====================
The Linux kernel supports the following overcommit handling modes
0
Heuristic overcommit handling. Obvious overcommits of address
space are refused. Used for a typical system. It ensures a
seriously wild allocation fails while allowing overcommit to
reduce swap usage. root is allowed to allocate slightly more
memory in this mode. This is the default.
1
Always overcommit. Appropriate for some scientific
applications. Classic example is code using sparse arrays and
just relying on the virtual memory consisting almost entirely
of zero pages.
2
Don't overcommit. The total address space commit for the
system is not permitted to exceed swap + a configurable amount
(default is 50%) of physical RAM. Depending on the amount you
use, in most situations this means a process will not be
killed while accessing pages but will receive errors on memory
allocation as appropriate.
Useful for applications that want to guarantee their memory
allocations will be available in the future without having to
initialize every page.
The overcommit policy is set via the sysctl ``vm.overcommit_memory``.
The overcommit amount can be set via ``vm.overcommit_ratio`` (percentage)
or ``vm.overcommit_kbytes`` (absolute value).
The current overcommit limit and amount committed are viewable in
``/proc/meminfo`` as CommitLimit and Committed_AS respectively.
Gotchas
=======
The C language stack growth does an implicit mremap. If you want absolute
guarantees and run close to the edge you MUST mmap your stack for the
largest size you think you will need. For typical stack usage this does
not matter much but it's a corner case if you really really care
In mode 2 the MAP_NORESERVE flag is ignored.
How It Works
============
The overcommit is based on the following rules
For a file backed map
| SHARED or READ-only - 0 cost (the file is the map not swap)
| PRIVATE WRITABLE - size of mapping per instance
For an anonymous or ``/dev/zero`` map
| SHARED - size of mapping
| PRIVATE READ-only - 0 cost (but of little use)
| PRIVATE WRITABLE - size of mapping per instance
Additional accounting
| Pages made writable copies by mmap
| shmfs memory drawn from the same pool
Status
======
* We account mmap memory mappings
* We account mprotect changes in commit
* We account mremap changes in size
* We account brk
* We account munmap
* We report the commit status in /proc
* Account and check on fork
* Review stack handling/building on exec
* SHMfs accounting
* Implement actual limit enforcement
To Do
=====
* Account ptrace pages (this is hard)
.. _page_frags:
==============
Page fragments
--------------
==============
A page fragment is an arbitrary-length arbitrary-offset area of memory
which resides within a 0 or higher order compound page. Multiple
......
.. _page_owner:
==================================================
page owner: Tracking about who allocated each page
-----------------------------------------------------------
==================================================
* Introduction
Introduction
============
page owner is for the tracking about who allocated each page.
It can be used to debug memory leak or to find a memory hogger.
......@@ -34,11 +38,13 @@ not affect to allocation performance, especially if the static keys jump
label patching functionality is available. Following is the kernel's code
size change due to this facility.
- Without page owner
- Without page owner::
text data bss dec hex filename
40662 1493 644 42799 a72f mm/page_alloc.o
- With page owner
- With page owner::
text data bss dec hex filename
40892 1493 644 43029 a815 mm/page_alloc.o
1427 24 8 1459 5b3 mm/page_ext.o
......@@ -62,21 +68,23 @@ are catched and marked, although they are mostly allocated from struct
page extension feature. Anyway, after that, no page is left in
un-tracking state.
* Usage
Usage
=====
1) Build user-space helper::
1) Build user-space helper
cd tools/vm
make page_owner_sort
2) Enable page owner
Add "page_owner=on" to boot cmdline.
2) Enable page owner: add "page_owner=on" to boot cmdline.
3) Do the job what you want to debug
4) Analyze information from page owner
4) Analyze information from page owner::
cat /sys/kernel/debug/page_owner > page_owner_full.txt
grep -v ^PFN page_owner_full.txt > page_owner.txt
./page_owner_sort page_owner.txt sorted_page_owner.txt
See the result about who allocated each page
in the sorted_page_owner.txt.
in the ``sorted_page_owner.txt``.
pagemap, from the userspace perspective
---------------------------------------
.. _pagemap:
======================================
pagemap from the Userspace Perspective
======================================
pagemap is a new (as of 2.6.25) set of interfaces in the kernel that allow
userspace programs to examine the page tables and related information by
reading files in /proc.
reading files in ``/proc``.
There are four components to pagemap:
* /proc/pid/pagemap. This file lets a userspace process find out which
* ``/proc/pid/pagemap``. This file lets a userspace process find out which
physical frame each virtual page is mapped to. It contains one 64-bit
value for each virtual page, containing the following data (from
fs/proc/task_mmu.c, above pagemap_read):
......@@ -15,7 +18,7 @@ There are four components to pagemap:
* Bits 0-54 page frame number (PFN) if present
* Bits 0-4 swap type if swapped
* Bits 5-54 swap offset if swapped
* Bit 55 pte is soft-dirty (see Documentation/vm/soft-dirty.txt)
* Bit 55 pte is soft-dirty (see Documentation/vm/soft-dirty.rst)
* Bit 56 page exclusively mapped (since 4.2)
* Bits 57-60 zero
* Bit 61 page is file-page or shared-anon (since 3.5)
......@@ -37,13 +40,13 @@ There are four components to pagemap:
determine which areas of memory are actually mapped and llseek to
skip over unmapped regions.
* /proc/kpagecount. This file contains a 64-bit count of the number of
* ``/proc/kpagecount``. This file contains a 64-bit count of the number of
times each page is mapped, indexed by PFN.
* /proc/kpageflags. This file contains a 64-bit set of flags for each
* ``/proc/kpageflags``. This file contains a 64-bit set of flags for each
page, indexed by PFN.
The flags are (from fs/proc/page.c, above kpageflags_read):
The flags are (from ``fs/proc/page.c``, above kpageflags_read):
0. LOCKED
1. ERROR
......@@ -72,98 +75,108 @@ There are four components to pagemap:
24. ZERO_PAGE
25. IDLE
* /proc/kpagecgroup. This file contains a 64-bit inode number of the
* ``/proc/kpagecgroup``. This file contains a 64-bit inode number of the
memory cgroup each page is charged to, indexed by PFN. Only available when
CONFIG_MEMCG is set.
Short descriptions to the page flags:
=====================================
0. LOCKED
0 - LOCKED
page is being locked for exclusive access, eg. by undergoing read/write IO
7. SLAB
7 - SLAB
page is managed by the SLAB/SLOB/SLUB/SLQB kernel memory allocator
When compound page is used, SLUB/SLQB will only set this flag on the head
page; SLOB will not flag it at all.
10. BUDDY
10 - BUDDY
a free memory block managed by the buddy system allocator
The buddy system organizes free memory in blocks of various orders.
An order N block has 2^N physically contiguous pages, with the BUDDY flag
set for and _only_ for the first page.
15. COMPOUND_HEAD
16. COMPOUND_TAIL
15 - COMPOUND_HEAD
A compound page with order N consists of 2^N physically contiguous pages.
A compound page with order 2 takes the form of "HTTT", where H donates its
head page and T donates its tail page(s). The major consumers of compound
pages are hugeTLB pages (Documentation/vm/hugetlbpage.txt), the SLUB etc.
pages are hugeTLB pages (Documentation/vm/hugetlbpage.rst), the SLUB etc.
memory allocators and various device drivers. However in this interface,
only huge/giga pages are made visible to end users.
17. HUGE
16 - COMPOUND_TAIL
A compound page tail (see description above).
17 - HUGE
this is an integral part of a HugeTLB page
19. HWPOISON
19 - HWPOISON
hardware detected memory corruption on this page: don't touch the data!
20. NOPAGE
20 - NOPAGE
no page frame exists at the requested address
21. KSM
21 - KSM
identical memory pages dynamically shared between one or more processes
22. THP
22 - THP
contiguous pages which construct transparent hugepages
23. BALLOON
23 - BALLOON
balloon compaction page
24. ZERO_PAGE
24 - ZERO_PAGE
zero page for pfn_zero or huge_zero page
25. IDLE
25 - IDLE
page has not been accessed since it was marked idle (see
Documentation/vm/idle_page_tracking.txt). Note that this flag may be
Documentation/vm/idle_page_tracking.rst). Note that this flag may be
stale in case the page was accessed via a PTE. To make sure the flag
is up-to-date one has to read /sys/kernel/mm/page_idle/bitmap first.
is up-to-date one has to read ``/sys/kernel/mm/page_idle/bitmap`` first.
IO related page flags
---------------------
[IO related page flags]
1. ERROR IO error occurred
3. UPTODATE page has up-to-date data
1 - ERROR
IO error occurred
3 - UPTODATE
page has up-to-date data
ie. for file backed page: (in-memory data revision >= on-disk one)
4. DIRTY page has been written to, hence contains new data
4 - DIRTY
page has been written to, hence contains new data
ie. for file backed page: (in-memory data revision > on-disk one)
8. WRITEBACK page is being synced to disk
[LRU related page flags]
5. LRU page is in one of the LRU lists
6. ACTIVE page is in the active LRU list
18. UNEVICTABLE page is in the unevictable (non-)LRU list
It is somehow pinned and not a candidate for LRU page reclaims,
eg. ramfs pages, shmctl(SHM_LOCK) and mlock() memory segments
2. REFERENCED page has been referenced since last LRU list enqueue/requeue
9. RECLAIM page will be reclaimed soon after its pageout IO completed
11. MMAP a memory mapped page
12. ANON a memory mapped page that is not part of a file
13. SWAPCACHE page is mapped to swap space, ie. has an associated swap entry
14. SWAPBACKED page is backed by swap/RAM
8 - WRITEBACK
page is being synced to disk
LRU related page flags
----------------------
5 - LRU
page is in one of the LRU lists
6 - ACTIVE
page is in the active LRU list
18 - UNEVICTABLE
page is in the unevictable (non-)LRU list It is somehow pinned and
not a candidate for LRU page reclaims, eg. ramfs pages,
shmctl(SHM_LOCK) and mlock() memory segments
2 - REFERENCED
page has been referenced since last LRU list enqueue/requeue
9 - RECLAIM
page will be reclaimed soon after its pageout IO completed
11 - MMAP
a memory mapped page
12 - ANON
a memory mapped page that is not part of a file
13 - SWAPCACHE
page is mapped to swap space, ie. has an associated swap entry
14 - SWAPBACKED
page is backed by swap/RAM
The page-types tool in the tools/vm directory can be used to query the
above flags.
Using pagemap to do something useful:
Using pagemap to do something useful
====================================
The general procedure for using pagemap to find out about a process' memory
usage goes like this:
1. Read /proc/pid/maps to determine which parts of the memory space are
1. Read ``/proc/pid/maps`` to determine which parts of the memory space are
mapped to what.
2. Select the maps you are interested in -- all of them, or a particular
library, or the stack or the heap, etc.
3. Open /proc/pid/pagemap and seek to the pages you would like to examine.
3. Open ``/proc/pid/pagemap`` and seek to the pages you would like to examine.
4. Read a u64 for each page from pagemap.
5. Open /proc/kpagecount and/or /proc/kpageflags. For each PFN you just
read, seek to that entry in the file, and read the data you want.
5. Open ``/proc/kpagecount`` and/or ``/proc/kpageflags``. For each PFN you
just read, seek to that entry in the file, and read the data you want.
For example, to find the "unique set size" (USS), which is the amount of
memory that a process is using that is not shared with any other process,
......@@ -171,7 +184,8 @@ you can go through every map in the process, find the PFNs, look those up
in kpagecount, and tally up the number of pages that are only referenced
once.
Other notes:
Other notes
===========
Reading from any of the files will return -EINVAL if you are not starting
the read on an 8-byte boundary (e.g., if you sought an odd number of bytes
......
.. _remap_file_pages:
==============================
remap_file_pages() system call
==============================
The remap_file_pages() system call is used to create a nonlinear mapping,
that is, a mapping in which the pages of the file are mapped into a
nonsequential order in memory. The advantage of using remap_file_pages()
......
SOFT-DIRTY PTEs
.. _soft_dirty:
The soft-dirty is a bit on a PTE which helps to track which pages a task
===============
Soft-Dirty PTEs
===============
The soft-dirty is a bit on a PTE which helps to track which pages a task
writes to. In order to do this tracking one should
1. Clear soft-dirty bits from the task's PTEs.
This is done by writing "4" into the /proc/PID/clear_refs file of the
This is done by writing "4" into the ``/proc/PID/clear_refs`` file of the
task in question.
2. Wait some time.
3. Read soft-dirty bits from the PTEs.
This is done by reading from the /proc/PID/pagemap. The bit 55 of the
This is done by reading from the ``/proc/PID/pagemap``. The bit 55 of the
64-bit qword is the soft-dirty one. If set, the respective PTE was
written to since step 1.
Internally, to do this tracking, the writable bit is cleared from PTEs
Internally, to do this tracking, the writable bit is cleared from PTEs
when the soft-dirty bit is cleared. So, after this, when the task tries to
modify a page at some virtual address the #PF occurs and the kernel sets
the soft-dirty bit on the respective PTE.
Note, that although all the task's address space is marked as r/o after the
Note, that although all the task's address space is marked as r/o after the
soft-dirty bits clear, the #PF-s that occur after that are processed fast.
This is so, since the pages are still mapped to physical memory, and thus all
the kernel does is finds this fact out and puts both writable and soft-dirty
bits on the PTE.
While in most cases tracking memory changes by #PF-s is more than enough
While in most cases tracking memory changes by #PF-s is more than enough
there is still a scenario when we can lose soft dirty bits -- a task
unmaps a previously mapped memory region and then maps a new one at exactly
the same place. When unmap is called, the kernel internally clears PTE values
......@@ -36,7 +40,7 @@ including soft dirty bits. To notify user space application about such
memory region renewal the kernel always marks new memory regions (and
expanded regions) as soft dirty.
This feature is actively used by the checkpoint-restore project. You
This feature is actively used by the checkpoint-restore project. You
can find more details about it on http://criu.org
......
.. _split_page_table_lock:
=====================
Split page table lock
=====================
......@@ -11,6 +14,7 @@ access to the table. At the moment we use split lock for PTE and PMD
tables. Access to higher level tables protected by mm->page_table_lock.
There are helpers to lock/unlock a table and other accessor functions:
- pte_offset_map_lock()
maps pte and takes PTE table lock, returns pointer to the taken
lock;
......@@ -34,12 +38,13 @@ Split page table lock for PMD tables is enabled, if it's enabled for PTE
tables and the architecture supports it (see below).
Hugetlb and split page table lock
---------------------------------
=================================
Hugetlb can support several page sizes. We use split lock only for PMD
level, but not for PUD.
Hugetlb-specific helpers:
- huge_pte_lock()
takes pmd split lock for PMD_SIZE page, mm->page_table_lock
otherwise;
......@@ -47,7 +52,7 @@ Hugetlb-specific helpers:
returns pointer to table lock;
Support of split page table lock by an architecture
---------------------------------------------------
===================================================
There's no need in special enabling of PTE split page table lock:
everything required is done by pgtable_page_ctor() and pgtable_page_dtor(),
......@@ -73,7 +78,7 @@ NOTE: pgtable_page_ctor() and pgtable_pmd_page_ctor() can fail -- it must
be handled properly.
page->ptl
---------
=========
page->ptl is used to access split page table lock, where 'page' is struct
page of page containing the table. It shares storage with page->private
......@@ -81,6 +86,7 @@ page of page containing the table. It shares storage with page->private
To avoid increasing size of struct page and have best performance, we use a
trick:
- if spinlock_t fits into long, we use page->ptr as spinlock, so we
can avoid indirect access and save a cache line.
- if size of spinlock_t is bigger then size of long, we use page->ptl as
......
.. _swap_numa:
===========================================
Automatically bind swap device to numa node
-------------------------------------------
===========================================
If the system has more than one swap device and swap device has the node
information, we can make use of this information to decide which swap
......@@ -7,15 +10,16 @@ device to use in get_swap_pages() to get better performance.
How to use this feature
-----------------------
=======================
Swap device has priority and that decides the order of it to be used. To make
use of automatically binding, there is no need to manipulate priority settings
for swap devices. e.g. on a 2 node machine, assume 2 swap devices swapA and
swapB, with swapA attached to node 0 and swapB attached to node 1, are going
to be swapped on. Simply swapping them on by doing:
# swapon /dev/swapA
# swapon /dev/swapB
to be swapped on. Simply swapping them on by doing::
# swapon /dev/swapA
# swapon /dev/swapB
Then node 0 will use the two swap devices in the order of swapA then swapB and
node 1 will use the two swap devices in the order of swapB then swapA. Note
......@@ -24,32 +28,39 @@ that the order of them being swapped on doesn't matter.
A more complex example on a 4 node machine. Assume 6 swap devices are going to
be swapped on: swapA and swapB are attached to node 0, swapC is attached to
node 1, swapD and swapE are attached to node 2 and swapF is attached to node3.
The way to swap them on is the same as above:
# swapon /dev/swapA
# swapon /dev/swapB
# swapon /dev/swapC
# swapon /dev/swapD
# swapon /dev/swapE
# swapon /dev/swapF
Then node 0 will use them in the order of:
swapA/swapB -> swapC -> swapD -> swapE -> swapF
The way to swap them on is the same as above::
# swapon /dev/swapA
# swapon /dev/swapB
# swapon /dev/swapC
# swapon /dev/swapD
# swapon /dev/swapE
# swapon /dev/swapF
Then node 0 will use them in the order of::
swapA/swapB -> swapC -> swapD -> swapE -> swapF
swapA and swapB will be used in a round robin mode before any other swap device.
node 1 will use them in the order of:
swapC -> swapA -> swapB -> swapD -> swapE -> swapF
node 1 will use them in the order of::
swapC -> swapA -> swapB -> swapD -> swapE -> swapF
node 2 will use them in the order of::
swapD/swapE -> swapA -> swapB -> swapC -> swapF
node 2 will use them in the order of:
swapD/swapE -> swapA -> swapB -> swapC -> swapF
Similaly, swapD and swapE will be used in a round robin mode before any
other swap devices.
node 3 will use them in the order of:
swapF -> swapA -> swapB -> swapC -> swapD -> swapE
node 3 will use them in the order of::
swapF -> swapA -> swapB -> swapC -> swapD -> swapE
Implementation details
----------------------
======================
The current code uses a priority based list, swap_avail_list, to decide
which swap device to use and if multiple swap devices share the same
......
= Userfaultfd =
.. _userfaultfd:
== Objective ==
===========
Userfaultfd
===========
Objective
=========
Userfaults allow the implementation of on-demand paging from userland
and more generally they allow userland to take control of various
......@@ -9,7 +14,8 @@ memory page faults, something otherwise only the kernel code could do.
For example userfaults allows a proper and more optimal implementation
of the PROT_NONE+SIGSEGV trick.
== Design ==
Design
======
Userfaults are delivered and resolved through the userfaultfd syscall.
......@@ -41,7 +47,8 @@ different processes without them being aware about what is going on
themselves on the same region the manager is already tracking, which
is a corner case that would currently return -EBUSY).
== API ==
API
===
When first opened the userfaultfd must be enabled invoking the
UFFDIO_API ioctl specifying a uffdio_api.api value set to UFFD_API (or
......@@ -101,7 +108,8 @@ UFFDIO_COPY. They're atomic as in guaranteeing that nothing can see an
half copied page since it'll keep userfaulting until the copy has
finished.
== QEMU/KVM ==
QEMU/KVM
========
QEMU/KVM is using the userfaultfd syscall to implement postcopy live
migration. Postcopy live migration is one form of memory
......@@ -163,7 +171,8 @@ sending the same page twice (in case the userfault is read by the
postcopy thread just before UFFDIO_COPY|ZEROPAGE runs in the migration
thread).
== Non-cooperative userfaultfd ==
Non-cooperative userfaultfd
===========================
When the userfaultfd is monitored by an external manager, the manager
must be able to track changes in the process virtual memory
......@@ -172,27 +181,30 @@ the same read(2) protocol as for the page fault notifications. The
manager has to explicitly enable these events by setting appropriate
bits in uffdio_api.features passed to UFFDIO_API ioctl:
UFFD_FEATURE_EVENT_FORK - enable userfaultfd hooks for fork(). When
this feature is enabled, the userfaultfd context of the parent process
is duplicated into the newly created process. The manager receives
UFFD_EVENT_FORK with file descriptor of the new userfaultfd context in
the uffd_msg.fork.
UFFD_FEATURE_EVENT_REMAP - enable notifications about mremap()
calls. When the non-cooperative process moves a virtual memory area to
a different location, the manager will receive UFFD_EVENT_REMAP. The
uffd_msg.remap will contain the old and new addresses of the area and
its original length.
UFFD_FEATURE_EVENT_REMOVE - enable notifications about
madvise(MADV_REMOVE) and madvise(MADV_DONTNEED) calls. The event
UFFD_EVENT_REMOVE will be generated upon these calls to madvise. The
uffd_msg.remove will contain start and end addresses of the removed
area.
UFFD_FEATURE_EVENT_UNMAP - enable notifications about memory
unmapping. The manager will get UFFD_EVENT_UNMAP with uffd_msg.remove
containing start and end addresses of the unmapped area.
UFFD_FEATURE_EVENT_FORK
enable userfaultfd hooks for fork(). When this feature is
enabled, the userfaultfd context of the parent process is
duplicated into the newly created process. The manager
receives UFFD_EVENT_FORK with file descriptor of the new
userfaultfd context in the uffd_msg.fork.
UFFD_FEATURE_EVENT_REMAP
enable notifications about mremap() calls. When the
non-cooperative process moves a virtual memory area to a
different location, the manager will receive
UFFD_EVENT_REMAP. The uffd_msg.remap will contain the old and
new addresses of the area and its original length.
UFFD_FEATURE_EVENT_REMOVE
enable notifications about madvise(MADV_REMOVE) and
madvise(MADV_DONTNEED) calls. The event UFFD_EVENT_REMOVE will
be generated upon these calls to madvise. The uffd_msg.remove
will contain start and end addresses of the removed area.
UFFD_FEATURE_EVENT_UNMAP
enable notifications about memory unmapping. The manager will
get UFFD_EVENT_UNMAP with uffd_msg.remove containing start and
end addresses of the unmapped area.
Although the UFFD_FEATURE_EVENT_REMOVE and UFFD_FEATURE_EVENT_UNMAP
are pretty similar, they quite differ in the action expected from the
......
.. _z3fold:
======
z3fold
------
======
z3fold is a special purpose allocator for storing compressed pages.
It is designed to store up to three compressed pages per physical page.
......@@ -7,6 +10,7 @@ It is a zbud derivative which allows for higher compression
ratio keeping the simplicity and determinism of its predecessor.
The main differences between z3fold and zbud are:
* unlike zbud, z3fold allows for up to PAGE_SIZE allocations
* z3fold can hold up to 3 compressed pages in its page
* z3fold doesn't export any API itself and is thus intended to be used
......
.. _zsmalloc:
========
zsmalloc
--------
========
This allocator is designed for use with zram. Thus, the allocator is
supposed to work well under low memory conditions. In particular, it
......@@ -31,40 +34,49 @@ be mapped using zs_map_object() to get a usable pointer and subsequently
unmapped using zs_unmap_object().
stat
----
====
With CONFIG_ZSMALLOC_STAT, we could see zsmalloc internal information via
/sys/kernel/debug/zsmalloc/<user name>. Here is a sample of stat output:
``/sys/kernel/debug/zsmalloc/<user name>``. Here is a sample of stat output::
# cat /sys/kernel/debug/zsmalloc/zram0/classes
# cat /sys/kernel/debug/zsmalloc/zram0/classes
class size almost_full almost_empty obj_allocated obj_used pages_used pages_per_zspage
..
..
...
...
9 176 0 1 186 129 8 4
10 192 1 0 2880 2872 135 3
11 208 0 1 819 795 42 2
12 224 0 1 219 159 12 4
..
..
...
...
class
index
size
object size zspage stores
almost_empty
the number of ZS_ALMOST_EMPTY zspages(see below)
almost_full
the number of ZS_ALMOST_FULL zspages(see below)
obj_allocated
the number of objects allocated
obj_used
the number of objects allocated to the user
pages_used
the number of pages allocated for the class
pages_per_zspage
the number of 0-order pages to make a zspage
class: index
size: object size zspage stores
almost_empty: the number of ZS_ALMOST_EMPTY zspages(see below)
almost_full: the number of ZS_ALMOST_FULL zspages(see below)
obj_allocated: the number of objects allocated
obj_used: the number of objects allocated to the user
pages_used: the number of pages allocated for the class
pages_per_zspage: the number of 0-order pages to make a zspage
We assign a zspage to ZS_ALMOST_EMPTY fullness group when n <= N / f, where
We assign a zspage to ZS_ALMOST_EMPTY fullness group when:
n <= N / f, where
n = number of allocated objects
N = total number of objects zspage can store
f = fullness_threshold_frac(ie, 4 at the moment)
* n = number of allocated objects
* N = total number of objects zspage can store
* f = fullness_threshold_frac(ie, 4 at the moment)
Similarly, we assign zspage to:
ZS_ALMOST_FULL when n > N / f
ZS_EMPTY when n == 0
ZS_FULL when n == N
* ZS_ALMOST_FULL when n > N / f
* ZS_EMPTY when n == 0
* ZS_FULL when n == N
......@@ -15621,7 +15621,7 @@ L: linux-mm@kvack.org
S: Maintained
F: mm/zsmalloc.c
F: include/linux/zsmalloc.h
F: Documentation/vm/zsmalloc.txt
F: Documentation/vm/zsmalloc.rst
ZSWAP COMPRESSED SWAP CACHING
M: Seth Jennings <sjenning@redhat.com>
......
......@@ -585,7 +585,7 @@ config ARCH_DISCONTIGMEM_ENABLE
Say Y to support efficient handling of discontiguous physical memory,
for architectures which are either NUMA (Non-Uniform Memory Access)
or have huge holes in the physical address space for other reasons.
See <file:Documentation/vm/numa> for more.
See <file:Documentation/vm/numa.rst> for more.
source "mm/Kconfig"
......
......@@ -397,7 +397,7 @@ config ARCH_DISCONTIGMEM_ENABLE
Say Y to support efficient handling of discontiguous physical memory,
for architectures which are either NUMA (Non-Uniform Memory Access)
or have huge holes in the physical address space for other reasons.
See <file:Documentation/vm/numa> for more.
See <file:Documentation/vm/numa.rst> for more.
config ARCH_FLATMEM_ENABLE
def_bool y
......
......@@ -2556,7 +2556,7 @@ config ARCH_DISCONTIGMEM_ENABLE
Say Y to support efficient handling of discontiguous physical memory,
for architectures which are either NUMA (Non-Uniform Memory Access)
or have huge holes in the physical address space for other reasons.
See <file:Documentation/vm/numa> for more.
See <file:Documentation/vm/numa.rst> for more.
config ARCH_SPARSEMEM_ENABLE
bool
......
......@@ -883,7 +883,7 @@ config PPC_MEM_KEYS
page-based protections, but without requiring modification of the
page tables when an application changes protection domains.
For details, see Documentation/vm/protection-keys.txt
For details, see Documentation/vm/protection-keys.rst
If unsure, say y.
......
......@@ -196,7 +196,7 @@ config HUGETLBFS
help
hugetlbfs is a filesystem backing for HugeTLB pages, based on
ramfs. For architectures that support it, say Y here and read
<file:Documentation/vm/hugetlbpage.txt> for details.
<file:Documentation/vm/hugetlbpage.rst> for details.
If unsure, say N.
......
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment