Currently, aio-nr is incremented in steps of 'num_possible_cpus() * 8'
for io_setup(nr_events, ..) with 'nr_events < num_possible_cpus() * 4':
ioctx_alloc()
...
nr_events = max(nr_events, num_possible_cpus() * 4);
nr_events *= 2;
...
ctx->max_reqs = nr_events;
...
aio_nr += ctx->max_reqs;
....
This limits the number of aio contexts actually available to much less
than aio-max-nr, and is increasingly worse with greater number of CPUs.
For example, with 64 CPUs, only 256 aio contexts are actually available
(with aio-max-nr = 65536) because the increment is 512 in that scenario.
Note: 65536 [max aio contexts] / (64*4*2) [increment per aio context]
is 128, but make it 256 (double) as counting against 'aio-max-nr * 2':
ioctx_alloc()
...
if (aio_nr + nr_events > (aio_max_nr * 2UL) ||
...
goto err_ctx;
...
This patch uses the original value of nr_events (from userspace) to
increment aio-nr and count against aio-max-nr, which resolves those.
Signed-off-by: Mauricio Faria de Oliveira <mauricfo@linux.vnet.ibm.com>
Reported-by: Lekshmi C. Pillai <lekshmi.cpillai@in.ibm.com>
Tested-by: Lekshmi C. Pillai <lekshmi.cpillai@in.ibm.com>
Tested-by: Paul Nguyen <nguyenp@us.ibm.com>
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Signed-off-by: Benjamin LaHaise <bcrl@kvack.org>
Pull x86 platform updates from Ingo Molnar:
"The main changes include various Hyper-V optimizations such as faster
hypercalls and faster/better TLB flushes - and there's also some
Intel-MID cleanups"
* 'x86-platform-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
tracing/hyper-v: Trace hyperv_mmu_flush_tlb_others()
x86/hyper-v: Support extended CPU ranges for TLB flush hypercalls
x86/platform/intel-mid: Make several arrays static, to make code smaller
MAINTAINERS: Add missed file for Hyper-V
x86/hyper-v: Use hypercall for remote TLB flush
hyper-v: Globalize vp_index
x86/hyper-v: Implement rep hypercalls
hyper-v: Use fast hypercall for HVCALL_SIGNAL_EVENT
x86/hyper-v: Introduce fast hypercall implementation
x86/hyper-v: Make hv_do_hypercall() inline
x86/hyper-v: Include hyperv/ only when CONFIG_HYPERV is set
x86/platform/intel-mid: Make 'bt_sfi_data' const
x86/platform/intel-mid: Make IRQ allocation a bit more flexible
x86/platform/intel-mid: Group timers callbacks together
KVM/ARM Changes for v4.14
Two minor cleanups and improvements, a fix for decoding external abort
types from guests, and added support for migrating the active priority
of interrupts when running a GICv2 guest on a GICv3 host.
Since commit 18290650b1 ("NFS: Move buffered I/O locking into
nfs_file_write()") nfs_file_write() has not flushed the correct byte
range during synchronous writes. generic_write_sync() expects that
iocb->ki_pos points to the right edge of the range rather than the
left edge.
To replicate the problem, open a file with O_DSYNC, have the client
write at increasing offsets, and then print the successful offsets.
Block port 2049 partway through that sequence, and observe that the
client application indicates successful writes in advance of what the
server received.
Fixes: 18290650b1 ("NFS: Move buffered I/O locking into nfs_file_write()")
Signed-off-by: Jacob Strauss <jsstraus@amazon.com>
Signed-off-by: Tarang Gupta <tarangg@amazon.com>
Tested-by: Tarang Gupta <tarangg@amazon.com>
Cc: stable@vger.kernel.org # v4.8+
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
KVM: s390: Fixes and features for 4.14
- merge of topic branch tlb-flushing from the s390 tree to get the
no-dat base features
- merge of kvm/master to avoid conflicts with additional sthyi fixes
- wire up the no-dat enhancements in KVM
- multiple epoch facility (z14 feature)
- Configuration z/Architecture Mode
- more sthyi fixes
- gdb server range checking fix
- small code cleanups
Apparently the PCIe capability is at address 0x40 in config space of X-Gene
v1 Root Ports. Add a definition of that and use the generic PCI_EXP_RTCTL
offset into the capability. No functional change intended.
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
When platform_get_irq() fails we should propagate the real error value
instead of always returning -EINVAL.
Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Duc Dang <dhdang@apm.com>
In commit 87d8a9f352 ("rtlwifi: btcoex: call bind to setup btcoex"),
the code turns on a call to exhalbtc_bind_bt_coex_withadapter(). This
routine contains a bug that causes incorrect antenna selection for those
HP laptops with only one antenna and an incorrectly programmed EFUSE.
These boxes are the ones that need the ant_sel module parameter.
Fixes: 87d8a9f352 ("rtlwifi: btcoex: call bind to setup btcoex")
Signed-off-by: Larry Finger <Larry.Finger@lwfinger.net>
Cc: Ping-Ke Shih <pkshih@realtek.com>
Cc: Yan-Hsuan Chuang <yhchuang@realtek.com>
Cc: Birming Chiu <birming@realtek.com>
Cc: Shaofu <shaofu@realtek.com>
Cc: Steven Ting <steventing@realtek.com>
Cc: Stable <stable@vger.kernel.org> # 4.13+
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
Recently produced GPD win devices have a new BIOS, research into the
changes in this BIOS has found a ChangeLog which also lists 2 previously
unknown BIOS dates.
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
[b.zolnierkie: ported over fbcon changes]
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Cpusets vs. suspend-resume is _completely_ broken. And it got noticed
because it now resulted in non-cpuset usage breaking too.
On suspend cpuset_cpu_inactive() doesn't call into
cpuset_update_active_cpus() because it doesn't want to move tasks about,
there is no need, all tasks are frozen and won't run again until after
we've resumed everything.
But this means that when we finally do call into
cpuset_update_active_cpus() after resuming the last frozen cpu in
cpuset_cpu_active(), the top_cpuset will not have any difference with
the cpu_active_mask and this it will not in fact do _anything_.
So the cpuset configuration will not be restored. This was largely
hidden because we would unconditionally create identity domains and
mobile users would not in fact use cpusets much. And servers what do use
cpusets tend to not suspend-resume much.
An addition problem is that we'd not in fact wait for the cpuset work to
finish before resuming the tasks, allowing spurious migrations outside
of the specified domains.
Fix the rebuild by introducing cpuset_force_rebuild() and fix the
ordering with cpuset_wait_for_hotplug().
Reported-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <stable@vger.kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: deb7aa308e ("cpuset: reorganize CPU / memory hotplug handling")
Link: http://lkml.kernel.org/r/20170907091338.orwxrqkbfkki3c24@hirez.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
BUG_ON() is the worst choice for a trivial sanity check.
Either it should be removed or replaced with a softer one like
WARN_ON() if still really needed.
Signed-off-by: Takashi Iwai <tiwai@suse.de>
The debug functions uses wrongly the %pF instead of the %pS printk format
specifier for printing symbols for the address returned by
_builtin_return_address(0). Fix it for the ia64, ppc64 and parisc64
architectures.
Signed-off-by: Helge Deller <deller@gmx.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
* Add a jump target so that a bit of exception handling can be better
reused at the end of this function.
This issue was detected by using the Coccinelle software.
* The script "checkpatch.pl" pointed information out like the following.
ERROR: do not use assignment in if condition
Thus fix a few source code places.
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
* Add a jump target so that a bit of exception handling can be better
reused at the end of this function.
This issue was detected by using the Coccinelle software.
* The script "checkpatch.pl" pointed information out like the following.
ERROR: do not use assignment in if condition
Thus fix a few source code places.
[ This also fixed a potential use-after-free at error path of
snd_opl3_hwdep_new(), too -- tiwai ]
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Add a jump target so that a bit of exception handling can be better reused
at the end of this function.
This issue was detected by using the Coccinelle software.
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Add a jump target so that a bit of exception handling can be better reused
at the end of this function.
This issue was detected by using the Coccinelle software.
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Add a jump target so that a bit of exception handling can be better reused
at the end of this function.
This issue was detected by using the Coccinelle software.
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Add a jump target so that a bit of exception handling can be better reused
at the end of this function.
This issue was detected by using the Coccinelle software.
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Add a jump target so that a bit of common code can be better reused
at the end of this function.
This issue was detected by using the Coccinelle software.
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Add jump targets so that a bit of exception handling can be better reused
at the end of these functions.
This issue was detected by using the Coccinelle software.
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
for_each_active_irq() iterates the sparse irq allocation bitmap. The caller
must hold sparse_irq_lock. Several code pathes expect that an active bit in
the sparse bitmap also has a valid interrupt descriptor.
Unfortunately that's not true. The (de)allocation is a two step process,
which holds the sparse_irq_lock only across the queue/remove from the radix
tree and the set/clear in the allocation bitmap.
If a iteration locks sparse_irq_lock between the two steps, then it might
see an active bit but the corresponding irq descriptor is NULL. If that is
dereferenced unconditionally, then the kernel oopses. Of course, all
iterator sites could be audited and fixed, but....
There is no reason why the sparse_irq_lock needs to be dropped between the
two steps, in fact the code becomes simpler when the mutex is held across
both and the semantics become more straight forward, so future problems of
missing NULL pointer checks in the iteration are avoided and all existing
sites are fixed in one go.
Expand the lock held sections so both operations are covered and the bitmap
and the radixtree are in sync.
Fixes: a05a900a51 ("genirq: Make sparse_lock a mutex")
Reported-and-tested-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Pull libata updates from Tejun Heo:
"Except for the ahci fix that fixes a boot issue, nothing major in this
pull request. Some new platform controller support and device specific
changes"
* 'for-4.14' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata:
libata: zpodd: make arrays cdb static, reduces object code size
ahci: don't use MSI for devices with the silly Intel NVMe remapping scheme
dt-bindings: ata: add DT bindings for MediaTek SATA controller
ata: mediatek: add support for MediaTek SATA controller
pata_octeon_cf: use of_property_read_{bool|u32}()
cs5536: add support for IDE controller variant
ata: sata_gemini: Introduce explicit IDE pin control
ata: sata_gemini: Retire custom pin control
ata: ahci_platform: Add shutdown handler
ata: sata_gemini: explicitly request exclusive reset control
ata: Drop unnecessary static
ata: Convert to using %pOF instead of full_name
Pull cgroup updates from Tejun Heo:
"Several notable changes this cycle:
- Thread mode was merged. This will be used for cgroup2 support for
CPU and possibly other controllers. Unfortunately, CPU controller
cgroup2 support didn't make this pull request but most contentions
have been resolved and the support is likely to be merged before
the next merge window.
- cgroup.stat now shows the number of descendant cgroups.
- cpuset now can enable the easier-to-configure v2 behavior on v1
hierarchy"
* 'for-4.14' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (21 commits)
cpuset: Allow v2 behavior in v1 cgroup
cgroup: Add mount flag to enable cpuset to use v2 behavior in v1 cgroup
cgroup: remove unneeded checks
cgroup: misc changes
cgroup: short-circuit cset_cgroup_from_root() on the default hierarchy
cgroup: re-use the parent pointer in cgroup_destroy_locked()
cgroup: add cgroup.stat interface with basic hierarchy stats
cgroup: implement hierarchy limits
cgroup: keep track of number of descent cgroups
cgroup: add comment to cgroup_enable_threaded()
cgroup: remove unnecessary empty check when enabling threaded mode
cgroup: update debug controller to print out thread mode information
cgroup: implement cgroup v2 thread support
cgroup: implement CSS_TASK_ITER_THREADED
cgroup: introduce cgroup->dom_cgrp and threaded css_set handling
cgroup: add @flags to css_task_iter_start() and implement CSS_TASK_ITER_PROCS
cgroup: reorganize cgroup.procs / task write path
cgroup: replace css_set walking populated test with testing cgrp->nr_populated_csets
cgroup: distinguish local and children populated states
cgroup: remove now unused list_head @pending in cgroup_apply_cftypes()
...
Pull workqueue updates from Tejun Heo:
"Nothing major. I introduced a flag collsion bug during v4.13 cycle
which is fixed in this pull request. Fortunately, the flag is for
debugging / verification and the bug isn't critical"
* 'for-4.14' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:
workqueue: Fix flag collision
workqueue: Use TASK_IDLE
workqueue: fix path to documentation
workqueue: doc change for ST behavior on NUMA systems
Pull percpu updates from Tejun Heo:
"A lot of changes for percpu this time around. percpu inherited the
same area allocator from the original pre-virtual-address-mapped
implementation. This was from the time when percpu allocator wasn't
used all that much and the implementation was focused on simplicity,
with the unfortunate computational complexity of O(number of areas
allocated from the chunk) per alloc / free.
With the increase in percpu usage, we're hitting cases where the lack
of scalability is hurting. The most prominent one right now is bpf
perpcu map creation / destruction which may allocate and free a lot of
entries consecutively and it's likely that the problem will become
more prominent in the future.
To address the issue, Dennis replaced the area allocator with hinted
bitmap allocator which is more consistent. While the new allocator
does perform a bit worse in some cases, it outperforms the old
allocator way more than an order of magnitude in other more common
scenarios while staying mostly flat in CPU overhead and completely
flat in memory consumption"
* 'for-4.14' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (27 commits)
percpu: update header to contain bitmap allocator explanation.
percpu: update pcpu_find_block_fit to use an iterator
percpu: use metadata blocks to update the chunk contig hint
percpu: update free path to take advantage of contig hints
percpu: update alloc path to only scan if contig hints are broken
percpu: keep track of the best offset for contig hints
percpu: skip chunks if the alloc does not fit in the contig hint
percpu: add first_bit to keep track of the first free in the bitmap
percpu: introduce bitmap metadata blocks
percpu: replace area map allocator with bitmap
percpu: generalize bitmap (un)populated iterators
percpu: increase minimum percpu allocation size and align first regions
percpu: introduce nr_empty_pop_pages to help empty page accounting
percpu: change the number of pages marked in the first_chunk pop bitmap
percpu: combine percpu address checks
percpu: modify base_addr to be region specific
percpu: setup_first_chunk rename schunk/dchunk to chunk
percpu: end chunk area maps page aligned for the populated bitmap
percpu: unify allocation of schunk and dchunk
percpu: setup_first_chunk remove dyn_size and consolidate logic
...
Now there is no lock protecting nlk ngroups/groups' accessing in
netlink bind and getname. It's safe from nlk groups' setting in
netlink_release, but not from netlink_realloc_groups called by
netlink_setsockopt.
netlink_lock_table is needed in both netlink bind and getname when
accessing nlk groups.
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
ChunYu found a netlink use-after-free issue by syzkaller:
[28448.842981] BUG: KASAN: use-after-free in __nla_put+0x37/0x40 at addr ffff8807185e2378
[28448.969918] Call Trace:
[...]
[28449.117207] __nla_put+0x37/0x40
[28449.132027] nla_put+0xf5/0x130
[28449.146261] sk_diag_fill.isra.4.constprop.5+0x5a0/0x750 [netlink_diag]
[28449.176608] __netlink_diag_dump+0x25a/0x700 [netlink_diag]
[28449.202215] netlink_diag_dump+0x176/0x240 [netlink_diag]
[28449.226834] netlink_dump+0x488/0xbb0
[28449.298014] __netlink_dump_start+0x4e8/0x760
[28449.317924] netlink_diag_handler_dump+0x261/0x340 [netlink_diag]
[28449.413414] sock_diag_rcv_msg+0x207/0x390
[28449.432409] netlink_rcv_skb+0x149/0x380
[28449.467647] sock_diag_rcv+0x2d/0x40
[28449.484362] netlink_unicast+0x562/0x7b0
[28449.564790] netlink_sendmsg+0xaa8/0xe60
[28449.661510] sock_sendmsg+0xcf/0x110
[28449.865631] __sys_sendmsg+0xf3/0x240
[28450.000964] SyS_sendmsg+0x32/0x50
[28450.016969] do_syscall_64+0x25c/0x6c0
[28450.154439] entry_SYSCALL64_slow_path+0x25/0x25
It was caused by no protection between nlk groups' free in netlink_release
and nlk groups' accessing in sk_diag_dump_groups. The similar issue also
exists in netlink_seq_show().
This patch is to defer nlk groups' free in deferred_put_nlk_sk.
Reported-by: ChunYu Wang <chunwang@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The commit 520ac30f45 ("net_sched: drop packets after root qdisc lock
is released) made a big change of tc for performance. There are two points
left in sch_prio and sch_qfq which are not changed with that commit. Now
enhance them now with __qdisc_drop.
Signed-off-by: Gao Feng <gfree.wind@vip.163.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The generic PHY 'phys' property sometime appears in the same node with
the Ethernet PHY 'phy' or 'phy-handle' properties. Add a warning in
phy-bindings.txt to reduce confusion.
Signed-off-by: Baruch Siach <baruch@tkos.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
Merge updates from Andrew Morton:
- various misc bits
- DAX updates
- OCFS2
- most of MM
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (119 commits)
mm,fork: introduce MADV_WIPEONFORK
x86,mpx: make mpx depend on x86-64 to free up VMA flag
mm: add /proc/pid/smaps_rollup
mm: hugetlb: clear target sub-page last when clearing huge page
mm: oom: let oom_reap_task and exit_mmap run concurrently
swap: choose swap device according to numa node
mm: replace TIF_MEMDIE checks by tsk_is_oom_victim
mm, oom: do not rely on TIF_MEMDIE for memory reserves access
z3fold: use per-cpu unbuddied lists
mm, swap: don't use VMA based swap readahead if HDD is used as swap
mm, swap: add sysfs interface for VMA based swap readahead
mm, swap: VMA based swap readahead
mm, swap: fix swap readahead marking
mm, swap: add swap readahead hit statistics
mm/vmalloc.c: don't reinvent the wheel but use existing llist API
mm/vmstat.c: fix wrong comment
selftests/memfd: add memfd_create hugetlbfs selftest
mm/shmem: add hugetlbfs support to memfd_create()
mm, devm_memremap_pages: use multi-order radix for ZONE_DEVICE lookups
mm/vmalloc.c: halve the number of comparisons performed in pcpu_get_vm_areas()
...
While debugging a problem, I thought that using
cr4_set_bits_and_update_boot() to restore CR4.PCIDE would be
helpful. It turns out to be counterproductive.
Add a comment documenting how this works.
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When Linux brings a CPU down and back up, it switches to init_mm and then
loads swapper_pg_dir into CR3. With PCID enabled, this has the side effect
of masking off the ASID bits in CR3.
This can result in some confusion in the TLB handling code. If we
bring a CPU down and back up with any ASID other than 0, we end up
with the wrong ASID active on the CPU after resume. This could
cause our internal state to become corrupt, although major
corruption is unlikely because init_mm doesn't have any user pages.
More obviously, if CONFIG_DEBUG_VM=y, we'll trip over an assertion
in the next context switch. The result of *that* is a failure to
resume from suspend with probability 1 - 1/6^(cpus-1).
Fix it by reinitializing cpu_tlbstate on resume and CPU bringup.
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Reported-by: Jiri Kosina <jikos@kernel.org>
Fixes: 10af6235e0 ("x86/mm: Implement PCID based optimization: try to preserve old TLB entries using PCID")
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Currently trace_clock timestamps are applied to both regular and max
buffers only for global trace. For instance trace, trace_clock
timestamps are applied only to regular buffer. But, regular and max
buffers can be swapped, for example, following a snapshot. So, for
instance trace, bad timestamps can be seen following a snapshot.
Let's apply trace_clock timestamps to instance max buffer as well.
Link: http://lkml.kernel.org/r/ebdb168d0be042dcdf51f81e696b17fabe3609c1.1504642143.git.tom.zanussi@linux.intel.com
Cc: stable@vger.kernel.org
Fixes: 277ba0446 ("tracing: Add interface to allow multiple trace buffers")
Signed-off-by: Baohong Liu <baohong.liu@intel.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Introduce MADV_WIPEONFORK semantics, which result in a VMA being empty
in the child process after fork. This differs from MADV_DONTFORK in one
important way.
If a child process accesses memory that was MADV_WIPEONFORK, it will get
zeroes. The address ranges are still valid, they are just empty.
If a child process accesses memory that was MADV_DONTFORK, it will get a
segmentation fault, since those address ranges are no longer valid in
the child after fork.
Since MADV_DONTFORK also seems to be used to allow very large programs
to fork in systems with strict memory overcommit restrictions, changing
the semantics of MADV_DONTFORK might break existing programs.
MADV_WIPEONFORK only works on private, anonymous VMAs.
The use case is libraries that store or cache information, and want to
know that they need to regenerate it in the child process after fork.
Examples of this would be:
- systemd/pulseaudio API checks (fail after fork) (replacing a getpid
check, which is too slow without a PID cache)
- PKCS#11 API reinitialization check (mandated by specification)
- glibc's upcoming PRNG (reseed after fork)
- OpenSSL PRNG (reseed after fork)
The security benefits of a forking server having a re-inialized PRNG in
every child process are pretty obvious. However, due to libraries
having all kinds of internal state, and programs getting compiled with
many different versions of each library, it is unreasonable to expect
calling programs to re-initialize everything manually after fork.
A further complication is the proliferation of clone flags, programs
bypassing glibc's functions to call clone directly, and programs calling
unshare, causing the glibc pthread_atfork hook to not get called.
It would be better to have the kernel take care of this automatically.
The patch also adds MADV_KEEPONFORK, to undo the effects of a prior
MADV_WIPEONFORK.
This is similar to the OpenBSD minherit syscall with MAP_INHERIT_ZERO:
https://man.openbsd.org/minherit.2
[akpm@linux-foundation.org: numerically order arch/parisc/include/uapi/asm/mman.h #defines]
Link: http://lkml.kernel.org/r/20170811212829.29186-3-riel@redhat.com
Signed-off-by: Rik van Riel <riel@redhat.com>
Reported-by: Florian Weimer <fweimer@redhat.com>
Reported-by: Colm MacCártaigh <colm@allcosts.net>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Helge Deller <deller@gmx.de>
Cc: Kees Cook <keescook@chromium.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Drewry <wad@chromium.org>
Cc: <linux-api@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Patch series "mm,fork,security: introduce MADV_WIPEONFORK", v4.
If a child process accesses memory that was MADV_WIPEONFORK, it will get
zeroes. The address ranges are still valid, they are just empty.
If a child process accesses memory that was MADV_DONTFORK, it will get a
segmentation fault, since those address ranges are no longer valid in
the child after fork.
Since MADV_DONTFORK also seems to be used to allow very large programs
to fork in systems with strict memory overcommit restrictions, changing
the semantics of MADV_DONTFORK might break existing programs.
The use case is libraries that store or cache information, and want to
know that they need to regenerate it in the child process after fork.
Examples of this would be:
- systemd/pulseaudio API checks (fail after fork) (replacing a getpid
check, which is too slow without a PID cache)
- PKCS#11 API reinitialization check (mandated by specification)
- glibc's upcoming PRNG (reseed after fork)
- OpenSSL PRNG (reseed after fork)
The security benefits of a forking server having a re-inialized PRNG in
every child process are pretty obvious. However, due to libraries
having all kinds of internal state, and programs getting compiled with
many different versions of each library, it is unreasonable to expect
calling programs to re-initialize everything manually after fork.
A further complication is the proliferation of clone flags, programs
bypassing glibc's functions to call clone directly, and programs calling
unshare, causing the glibc pthread_atfork hook to not get called.
It would be better to have the kernel take care of this automatically.
The patchset also adds MADV_KEEPONFORK, to undo the effects of a prior
MADV_WIPEONFORK.
This is similar to the OpenBSD minherit syscall with MAP_INHERIT_ZERO:
https://man.openbsd.org/minherit.2
This patch (of 2):
MPX only seems to be available on 64 bit CPUs, starting with Skylake and
Goldmont. Move VM_MPX into the 64 bit only portion of vma->vm_flags, in
order to free up a VMA flag.
Link: http://lkml.kernel.org/r/20170811212829.29186-2-riel@redhat.com
Signed-off-by: Rik van Riel <riel@redhat.com>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Will Drewry <wad@chromium.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Colm MacCártaigh <colm@allcosts.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
/proc/pid/smaps_rollup is a new proc file that improves the performance
of user programs that determine aggregate memory statistics (e.g., total
PSS) of a process.
Android regularly "samples" the memory usage of various processes in
order to balance its memory pool sizes. This sampling process involves
opening /proc/pid/smaps and summing certain fields. For very large
processes, sampling memory use this way can take several hundred
milliseconds, due mostly to the overhead of the seq_printf calls in
task_mmu.c.
smaps_rollup improves the situation. It contains most of the fields of
/proc/pid/smaps, but instead of a set of fields for each VMA,
smaps_rollup instead contains one synthetic smaps-format entry
representing the whole process. In the single smaps_rollup synthetic
entry, each field is the summation of the corresponding field in all of
the real-smaps VMAs. Using a common format for smaps_rollup and smaps
allows userspace parsers to repurpose parsers meant for use with
non-rollup smaps for smaps_rollup, and it allows userspace to switch
between smaps_rollup and smaps at runtime (say, based on the
availability of smaps_rollup in a given kernel) with minimal fuss.
By using smaps_rollup instead of smaps, a caller can avoid the
significant overhead of formatting, reading, and parsing each of a large
process's potentially very numerous memory mappings. For sampling
system_server's PSS in Android, we measured a 12x speedup, representing
a savings of several hundred milliseconds.
One alternative to a new per-process proc file would have been including
PSS information in /proc/pid/status. We considered this option but
thought that PSS would be too expensive (by a few orders of magnitude)
to collect relative to what's already emitted as part of
/proc/pid/status, and slowing every user of /proc/pid/status for the
sake of readers that happen to want PSS feels wrong.
The code itself works by reusing the existing VMA-walking framework we
use for regular smaps generation and keeping the mem_size_stats
structure around between VMA walks instead of using a fresh one for each
VMA. In this way, summation happens automatically. We let seq_file
walk over the VMAs just as it does for regular smaps and just emit
nothing to the seq_file until we hit the last VMA.
Benchmarks:
using smaps:
iterations:1000 pid:1163 pss:220023808
0m29.46s real 0m08.28s user 0m20.98s system
using smaps_rollup:
iterations:1000 pid:1163 pss:220702720
0m04.39s real 0m00.03s user 0m04.31s system
We're using the PSS samples we collect asynchronously for
system-management tasks like fine-tuning oom_adj_score, memory use
tracking for debugging, application-level memory-use attribution, and
deciding whether we want to kill large processes during system idle
maintenance windows. Android has been using PSS for these purposes for
a long time; as the average process VMA count has increased and and
devices become more efficiency-conscious, PSS-collection inefficiency
has started to matter more. IMHO, it'd be a lot safer to optimize the
existing PSS-collection model, which has been fine-tuned over the years,
instead of changing the memory tracking approach entirely to work around
smaps-generation inefficiency.
Tim said:
: There are two main reasons why Android gathers PSS information:
:
: 1. Android devices can show the user the amount of memory used per
: application via the settings app. This is a less important use case.
:
: 2. We log PSS to help identify leaks in applications. We have found
: an enormous number of bugs (in the Android platform, in Google's own
: apps, and in third-party applications) using this data.
:
: To do this, system_server (the main process in Android userspace) will
: sample the PSS of a process three seconds after it changes state (for
: example, app is launched and becomes the foreground application) and about
: every ten minutes after that. The net result is that PSS collection is
: regularly running on at least one process in the system (usually a few
: times a minute while the screen is on, less when screen is off due to
: suspend). PSS of a process is an incredibly useful stat to track, and we
: aren't going to get rid of it. We've looked at some very hacky approaches
: using RSS ("take the RSS of the target process, subtract the RSS of the
: zygote process that is the parent of all Android apps") to reduce the
: accounting time, but it regularly overestimated the memory used by 20+
: percent. Accordingly, I don't think that there's a good alternative to
: using PSS.
:
: We started looking into PSS collection performance after we noticed random
: frequency spikes while a phone's screen was off; occasionally, one of the
: CPU clusters would ramp to a high frequency because there was 200-300ms of
: constant CPU work from a single thread in the main Android userspace
: process. The work causing the spike (which is reasonable governor
: behavior given the amount of CPU time needed) was always PSS collection.
: As a result, Android is burning more power than we should be on PSS
: collection.
:
: The other issue (and why I'm less sure about improving smaps as a
: long-term solution) is that the number of VMAs per process has increased
: significantly from release to release. After trying to figure out why we
: were seeing these 200-300ms PSS collection times on Android O but had not
: noticed it in previous versions, we found that the number of VMAs in the
: main system process increased by 50% from Android N to Android O (from
: ~1800 to ~2700) and varying increases in every userspace process. Android
: M to N also had an increase in the number of VMAs, although not as much.
: I'm not sure why this is increasing so much over time, but thinking about
: ASLR and ways to make ASLR better, I expect that this will continue to
: increase going forward. I would not be surprised if we hit 5000 VMAs on
: the main Android process (system_server) by 2020.
:
: If we assume that the number of VMAs is going to increase over time, then
: doing anything we can do to reduce the overhead of each VMA during PSS
: collection seems like the right way to go, and that means outputting an
: aggregate statistic (to avoid whatever overhead there is per line in
: writing smaps and in reading each line from userspace).
Link: http://lkml.kernel.org/r/20170812022148.178293-1-dancol@google.com
Signed-off-by: Daniel Colascione <dancol@google.com>
Cc: Tim Murray <timmurray@google.com>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Sonny Rao <sonnyrao@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Huge page helps to reduce TLB miss rate, but it has higher cache
footprint, sometimes this may cause some issue. For example, when
clearing huge page on x86_64 platform, the cache footprint is 2M. But
on a Xeon E5 v3 2699 CPU, there are 18 cores, 36 threads, and only 45M
LLC (last level cache). That is, in average, there are 2.5M LLC for
each core and 1.25M LLC for each thread.
If the cache pressure is heavy when clearing the huge page, and we clear
the huge page from the begin to the end, it is possible that the begin
of huge page is evicted from the cache after we finishing clearing the
end of the huge page. And it is possible for the application to access
the begin of the huge page after clearing the huge page.
To help the above situation, in this patch, when we clear a huge page,
the order to clear sub-pages is changed. In quite some situation, we
can get the address that the application will access after we clear the
huge page, for example, in a page fault handler. Instead of clearing
the huge page from begin to end, we will clear the sub-pages farthest
from the the sub-page to access firstly, and clear the sub-page to
access last. This will make the sub-page to access most cache-hot and
sub-pages around it more cache-hot too. If we cannot know the address
the application will access, the begin of the huge page is assumed to be
the the address the application will access.
With this patch, the throughput increases ~28.3% in vm-scalability
anon-w-seq test case with 72 processes on a 2 socket Xeon E5 v3 2699
system (36 cores, 72 threads). The test case creates 72 processes, each
process mmap a big anonymous memory area and writes to it from the begin
to the end. For each process, other processes could be seen as other
workload which generates heavy cache pressure. At the same time, the
cache miss rate reduced from ~33.4% to ~31.7%, the IPC (instruction per
cycle) increased from 0.56 to 0.74, and the time spent in user space is
reduced ~7.9%
Christopher Lameter suggests to clear bytes inside a sub-page from end
to begin too. But tests show no visible performance difference in the
tests. May because the size of page is small compared with the cache
size.
Thanks Andi Kleen to propose to use address to access to determine the
order of sub-pages to clear.
The hugetlbfs access address could be improved, will do that in another
patch.
[ying.huang@intel.com: improve readability of clear_huge_page()]
Link: http://lkml.kernel.org/r/20170830051842.1397-1-ying.huang@intel.com
Link: http://lkml.kernel.org/r/20170815014618.15842-1-ying.huang@intel.com
Suggested-by: Andi Kleen <andi.kleen@intel.com>
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Acked-by: Jan Kara <jack@suse.cz>
Reviewed-by: Michal Hocko <mhocko@suse.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Nadia Yvette Chambers <nyc@holomorphy.com>
Cc: Matthew Wilcox <mawilcox@microsoft.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Shaohua Li <shli@fb.com>
Cc: Christopher Lameter <cl@linux.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This is purely required because exit_aio() may block and exit_mmap() may
never start, if the oom_reap_task cannot start running on a mm with
mm_users == 0.
At the same time if the OOM reaper doesn't wait at all for the memory of
the current OOM candidate to be freed by exit_mmap->unmap_vmas, it would
generate a spurious OOM kill.
If it wasn't because of the exit_aio or similar blocking functions in
the last mmput, it would be enough to change the oom_reap_task() in the
case it finds mm_users == 0, to wait for a timeout or to wait for
__mmput to set MMF_OOM_SKIP itself, but it's not just exit_mmap the
problem here so the concurrency of exit_mmap and oom_reap_task is
apparently warranted.
It's a non standard runtime, exit_mmap() runs without mmap_sem, and
oom_reap_task runs with the mmap_sem for reading as usual (kind of
MADV_DONTNEED).
The race between the two is solved with a combination of
tsk_is_oom_victim() (serialized by task_lock) and MMF_OOM_SKIP
(serialized by a dummy down_write/up_write cycle on the same lines of
the ksm_exit method).
If the oom_reap_task() may be running concurrently during exit_mmap,
exit_mmap will wait it to finish in down_write (before taking down mm
structures that would make the oom_reap_task fail with use after free).
If exit_mmap comes first, oom_reap_task() will skip the mm if
MMF_OOM_SKIP is already set and in turn all memory is already freed and
furthermore the mm data structures may already have been taken down by
free_pgtables.
[aarcange@redhat.com: incremental one liner]
Link: http://lkml.kernel.org/r/20170726164319.GC29716@redhat.com
[rientjes@google.com: remove unused mmput_async]
Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1708141733130.50317@chino.kir.corp.google.com
[aarcange@redhat.com: microoptimization]
Link: http://lkml.kernel.org/r/20170817171240.GB5066@redhat.com
Link: http://lkml.kernel.org/r/20170726162912.GA29716@redhat.com
Fixes: 26db62f179 ("oom: keep mm of the killed task available")
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Reported-by: David Rientjes <rientjes@google.com>
Tested-by: David Rientjes <rientjes@google.com>
Reviewed-by: Michal Hocko <mhocko@suse.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
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
device to use in get_swap_pages() to get better performance.
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
priority, they are used round robin. This patch changes the previous
single global swap_avail_list into a per-numa-node list, i.e. for each
numa node, it sees its own priority based list of available swap
devices. Swap device's priority can be promoted on its matching node's
swap_avail_list.
The current swap device's priority is set as: user can set a >=0 value,
or the system will pick one starting from -1 then downwards. The
priority value in the swap_avail_list is the negated value of the swap
device's due to plist being sorted from low to high. The new policy
doesn't change the semantics for priority >=0 cases, the previous
starting from -1 then downwards now becomes starting from -2 then
downwards and -1 is reserved as the promoted value.
Take 4-node EX machine as an example, suppose 4 swap devices are
available, each sit on a different node:
swapA on node 0
swapB on node 1
swapC on node 2
swapD on node 3
After they are all swapped on in the sequence of ABCD.
Current behaviour:
their priorities will be:
swapA: -1
swapB: -2
swapC: -3
swapD: -4
And their position in the global swap_avail_list will be:
swapA -> swapB -> swapC -> swapD
prio:1 prio:2 prio:3 prio:4
New behaviour:
their priorities will be(note that -1 is skipped):
swapA: -2
swapB: -3
swapC: -4
swapD: -5
And their positions in the 4 swap_avail_lists[nid] will be:
swap_avail_lists[0]: /* node 0's available swap device list */
swapA -> swapB -> swapC -> swapD
prio:1 prio:3 prio:4 prio:5
swap_avali_lists[1]: /* node 1's available swap device list */
swapB -> swapA -> swapC -> swapD
prio:1 prio:2 prio:4 prio:5
swap_avail_lists[2]: /* node 2's available swap device list */
swapC -> swapA -> swapB -> swapD
prio:1 prio:2 prio:3 prio:5
swap_avail_lists[3]: /* node 3's available swap device list */
swapD -> swapA -> swapB -> swapC
prio:1 prio:2 prio:3 prio:4
To see the effect of the patch, a test that starts N process, each mmap
a region of anonymous memory and then continually write to it at random
position to trigger both swap in and out is used.
On a 2 node Skylake EP machine with 64GiB memory, two 170GB SSD drives
are used as swap devices with each attached to a different node, the
result is:
runtime=30m/processes=32/total test size=128G/each process mmap region=4G
kernel throughput
vanilla 13306
auto-binding 15169 +14%
runtime=30m/processes=64/total test size=128G/each process mmap region=2G
kernel throughput
vanilla 11885
auto-binding 14879 +25%
[aaron.lu@intel.com: v2]
Link: http://lkml.kernel.org/r/20170814053130.GD2369@aaronlu.sh.intel.com
Link: http://lkml.kernel.org/r/20170816024439.GA10925@aaronlu.sh.intel.com
[akpm@linux-foundation.org: use kmalloc_array()]
Link: http://lkml.kernel.org/r/20170814053130.GD2369@aaronlu.sh.intel.com
Link: http://lkml.kernel.org/r/20170816024439.GA10925@aaronlu.sh.intel.com
Signed-off-by: Aaron Lu <aaron.lu@intel.com>
Cc: "Chen, Tim C" <tim.c.chen@intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
For ages we have been relying on TIF_MEMDIE thread flag to mark OOM
victims and then, among other things, to give these threads full access
to memory reserves. There are few shortcomings of this implementation,
though.
First of all and the most serious one is that the full access to memory
reserves is quite dangerous because we leave no safety room for the
system to operate and potentially do last emergency steps to move on.
Secondly this flag is per task_struct while the OOM killer operates on
mm_struct granularity so all processes sharing the given mm are killed.
Giving the full access to all these task_structs could lead to a quick
memory reserves depletion. We have tried to reduce this risk by giving
TIF_MEMDIE only to the main thread and the currently allocating task but
that doesn't really solve this problem while it surely opens up a room
for corner cases - e.g. GFP_NO{FS,IO} requests might loop inside the
allocator without access to memory reserves because a particular thread
was not the group leader.
Now that we have the oom reaper and that all oom victims are reapable
after 1b51e65eab ("oom, oom_reaper: allow to reap mm shared by the
kthreads") we can be more conservative and grant only partial access to
memory reserves because there are reasonable chances of the parallel
memory freeing. We still want some access to reserves because we do not
want other consumers to eat up the victim's freed memory. oom victims
will still contend with __GFP_HIGH users but those shouldn't be so
aggressive to starve oom victims completely.
Introduce ALLOC_OOM flag and give all tsk_is_oom_victim tasks access to
the half of the reserves. This makes the access to reserves independent
on which task has passed through mark_oom_victim. Also drop any usage
of TIF_MEMDIE from the page allocator proper and replace it by
tsk_is_oom_victim as well which will make page_alloc.c completely
TIF_MEMDIE free finally.
CONFIG_MMU=n doesn't have oom reaper so let's stick to the original
ALLOC_NO_WATERMARKS approach.
There is a demand to make the oom killer memcg aware which will imply
many tasks killed at once. This change will allow such a usecase
without worrying about complete memory reserves depletion.
Link: http://lkml.kernel.org/r/20170810075019.28998-2-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
It's been noted that z3fold doesn't scale well when it's run in a large
number of threads on many cores, which can be easily reproduced with fio
'randrw' test with --numjobs=32. E.g. the result for 1 cluster (4 cores)
is:
Run status group 0 (all jobs):
READ: io=244785MB, aggrb=496883KB/s, minb=15527KB/s, ...
WRITE: io=246735MB, aggrb=500841KB/s, minb=15651KB/s, ...
While for 8 cores (2 clusters) the result is:
Run status group 0 (all jobs):
READ: io=244785MB, aggrb=265942KB/s, minb=8310KB/s, ...
WRITE: io=246735MB, aggrb=268060KB/s, minb=8376KB/s, ...
The bottleneck here is the pool lock which many threads become waiting
upon. To reduce that spin lock contention, z3fold can operate only on
the lists local to the current CPU whenever possible. Due to the nature
of z3fold unbuddied list handling (it only takes the first entry off the
list on a hot path), if the z3fold pool is big enough and balanced well
enough, limiting search to only local unbuddied list doesn't lead to a
significant compression ratio degrade (2.57x vs 2.65x in our
measurements).
This patch also introduces two worker threads: one for async in-page
object layout optimization and one for releasing freed pages. This is
done to speed up z3fold_free() which is often on a hot path.
The fio results for 8-core case are now the following:
Run status group 0 (all jobs):
READ: io=244785MB, aggrb=1568.3MB/s, minb=50182KB/s, ...
WRITE: io=246735MB, aggrb=1580.8MB/s, minb=50582KB/s, ...
So we're in for almost 6x performance increase.
Link: http://lkml.kernel.org/r/20170806181443.f9b65018f8bde25ef990f9e8@gmail.com
Signed-off-by: Vitaly Wool <vitalywool@gmail.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
VMA based swap readahead will readahead the virtual pages that is
continuous in the virtual address space. While the original swap
readahead will readahead the swap slots that is continuous in the swap
device. Although VMA based swap readahead is more correct for the swap
slots to be readahead, it will trigger more small random readings, which
may cause the performance of HDD (hard disk) to degrade heavily, and may
finally exceed the benefit.
To avoid the issue, in this patch, if the HDD is used as swap, the VMA
based swap readahead will be disabled, and the original swap readahead
will be used instead.
Link: http://lkml.kernel.org/r/20170807054038.1843-6-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Tim Chen <tim.c.chen@intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The swap readahead is an important mechanism to reduce the swap in
latency. Although pure sequential memory access pattern isn't very
popular for anonymous memory, the space locality is still considered
valid.
In the original swap readahead implementation, the consecutive blocks in
swap device are readahead based on the global space locality estimation.
But the consecutive blocks in swap device just reflect the order of page
reclaiming, don't necessarily reflect the access pattern in virtual
memory. And the different tasks in the system may have different access
patterns, which makes the global space locality estimation incorrect.
In this patch, when page fault occurs, the virtual pages near the fault
address will be readahead instead of the swap slots near the fault swap
slot in swap device. This avoid to readahead the unrelated swap slots.
At the same time, the swap readahead is changed to work on per-VMA from
globally. So that the different access patterns of the different VMAs
could be distinguished, and the different readahead policy could be
applied accordingly. The original core readahead detection and scaling
algorithm is reused, because it is an effect algorithm to detect the
space locality.
The test and result is as follow,
Common test condition
=====================
Test Machine: Xeon E5 v3 (2 sockets, 72 threads, 32G RAM) Swap device:
NVMe disk
Micro-benchmark with combined access pattern
============================================
vm-scalability, sequential swap test case, 4 processes to eat 50G
virtual memory space, repeat the sequential memory writing until 300
seconds. The first round writing will trigger swap out, the following
rounds will trigger sequential swap in and out.
At the same time, run vm-scalability random swap test case in
background, 8 processes to eat 30G virtual memory space, repeat the
random memory write until 300 seconds. This will trigger random swap-in
in the background.
This is a combined workload with sequential and random memory accessing
at the same time. The result (for sequential workload) is as follow,
Base Optimized
---- ---------
throughput 345413 KB/s 414029 KB/s (+19.9%)
latency.average 97.14 us 61.06 us (-37.1%)
latency.50th 2 us 1 us
latency.60th 2 us 1 us
latency.70th 98 us 2 us
latency.80th 160 us 2 us
latency.90th 260 us 217 us
latency.95th 346 us 369 us
latency.99th 1.34 ms 1.09 ms
ra_hit% 52.69% 99.98%
The original swap readahead algorithm is confused by the background
random access workload, so readahead hit rate is lower. The VMA-base
readahead algorithm works much better.
Linpack
=======
The test memory size is bigger than RAM to trigger swapping.
Base Optimized
---- ---------
elapsed_time 393.49 s 329.88 s (-16.2%)
ra_hit% 86.21% 98.82%
The score of base and optimized kernel hasn't visible changes. But the
elapsed time reduced and readahead hit rate improved, so the optimized
kernel runs better for startup and tear down stages. And the absolute
value of readahead hit rate is high, shows that the space locality is
still valid in some practical workloads.
Link: http://lkml.kernel.org/r/20170807054038.1843-4-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Tim Chen <tim.c.chen@intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
