Vlastimil Babka
cc252eae85
mm, slab: combine kmalloc_caches and kmalloc_dma_caches ...
Patch series "kmalloc-reclaimable caches", v4.
As discussed at LSF/MM [1] here's a patchset that introduces
kmalloc-reclaimable caches (more details in the second patch) and uses
them for dcache external names. That allows us to repurpose the
NR_INDIRECTLY_RECLAIMABLE_BYTES counter later in the series.
With patch 3/6, dcache external names are allocated from kmalloc-rcl-*
caches, eliminating the need for manual accounting. More importantly, it
also ensures the reclaimable kmalloc allocations are grouped in pages
separate from the regular kmalloc allocations. The need for proper
accounting of dcache external names has shown it's easy for misbehaving
process to allocate lots of them, causing premature OOMs. Without the
added grouping, it's likely that a similar workload can interleave the
dcache external names allocations with regular kmalloc allocations (note:
I haven't searched myself for an example of such regular kmalloc
allocation, but I would be very surprised if there wasn't some). A
pathological case would be e.g. one 64byte regular allocations with 63
external dcache names in a page (64x64=4096), which means the page is not
freed even after reclaiming after all dcache names, and the process can
thus "steal" the whole page with single 64byte allocation.
If other kmalloc users similar to dcache external names become identified,
they can also benefit from the new functionality simply by adding
__GFP_RECLAIMABLE to the kmalloc calls.
Side benefits of the patchset (that could be also merged separately)
include removed branch for detecting __GFP_DMA kmalloc(), and shortening
kmalloc cache names in /proc/slabinfo output. The latter is potentially
an ABI break in case there are tools parsing the names and expecting the
values to be in bytes.
This is how /proc/slabinfo looks like after booting in virtme:
...
kmalloc-rcl-4M 0 0 4194304 1 1024 : tunables 1 1 0 : slabdata 0 0 0
...
kmalloc-rcl-96 7 32 128 32 1 : tunables 120 60 8 : slabdata 1 1 0
kmalloc-rcl-64 25 128 64 64 1 : tunables 120 60 8 : slabdata 2 2 0
kmalloc-rcl-32 0 0 32 124 1 : tunables 120 60 8 : slabdata 0 0 0
kmalloc-4M 0 0 4194304 1 1024 : tunables 1 1 0 : slabdata 0 0 0
kmalloc-2M 0 0 2097152 1 512 : tunables 1 1 0 : slabdata 0 0 0
kmalloc-1M 0 0 1048576 1 256 : tunables 1 1 0 : slabdata 0 0 0
...
/proc/vmstat with renamed nr_indirectly_reclaimable_bytes counter:
...
nr_slab_reclaimable 2817
nr_slab_unreclaimable 1781
...
nr_kernel_misc_reclaimable 0
...
/proc/meminfo with new KReclaimable counter:
...
Shmem: 564 kB
KReclaimable: 11260 kB
Slab: 18368 kB
SReclaimable: 11260 kB
SUnreclaim: 7108 kB
KernelStack: 1248 kB
...
This patch (of 6):
The kmalloc caches currently mainain separate (optional) array
kmalloc_dma_caches for __GFP_DMA allocations. There are tests for
__GFP_DMA in the allocation hotpaths. We can avoid the branches by
combining kmalloc_caches and kmalloc_dma_caches into a single
two-dimensional array where the outer dimension is cache "type". This
will also allow to add kmalloc-reclaimable caches as a third type.
Link: http://lkml.kernel.org/r/20180731090649.16028-2-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Christoph Lameter <cl@linux.com>
Acked-by: Roman Gushchin <guro@fb.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Laura Abbott <labbott@redhat.com>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: Vijayanand Jitta <vjitta@codeaurora.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-26 16:26:31 -07:00
mmc: mmci: Drop support for pdata GPIO numbers
2018-10-08 11:40:43 +02:00
virtchnl: Added support to exchange additional speed values
2018-10-03 07:42:29 -07:00
firmware /meson
fpga: add devm_fpga_region_create
2018-10-16 11:13:50 +02:00
This is the bulk of GPIO changes for the v4.20 series:
2018-10-23 08:45:05 +01:00
KVM updates for v4.20
2018-10-25 17:57:35 -07:00
power supply and reset changes for the v4.20 series
2018-10-25 06:28:08 -07:00
First merge window pull request
2018-10-26 07:38:19 -07:00
mmc: core: add helper to see if a host is doing a retune
2018-10-08 11:40:43 +02:00
SPI NOR changes:
2018-10-23 01:09:22 +01:00
netfilter: nft_osf: Add ttl option support
2018-10-16 10:01:48 +02:00
arm64: perf: Reject stand-alone CHAIN events for PMUv3
2018-10-12 15:25:17 +01:00
USB/PHY patches for 4.20-rc1
2018-10-26 08:14:13 -07:00
USB/PHY patches for 4.20-rc1
2018-10-26 08:14:13 -07:00
First merge window pull request
2018-10-26 07:38:19 -07:00
regulator/mfd: Support for the ROHM BD71847
2018-09-28 15:07:30 +01:00
Merge branch 'siginfo-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace
2018-10-24 11:22:39 +01:00
Merge remote-tracking branch 'spi/topic/of' into spi-next
2018-10-21 17:00:17 +01:00
gss_krb5: Remove VLA usage of skcipher
2018-09-28 12:46:07 +08:00
USB/PHY patches for 4.20-rc1
2018-10-26 08:14:13 -07:00
pci-v4.20-changes
2018-10-25 06:50:48 -07:00
ACPI/ADXL: Add address translation interface using an ACPI DSM
2018-10-16 10:03:00 +02:00
signal: Distinguish between kernel_siginfo and siginfo
2018-10-03 16:47:43 +02:00
blkcg: reassociate bios when make_request() is called recursively
2018-10-20 15:39:55 -06:00
blkcg: fix edge case for blk_get_rl() under memory pressure
2018-10-20 15:39:54 -06:00
blk-mq: provide helper for setting up an SQ queue and tag set
2018-10-15 20:05:18 -06:00
block: Move power management code into a new source file
2018-09-26 15:11:28 -06:00
pci-v4.20-changes
2018-10-25 06:50:48 -07:00
bpf: introduce per-cpu cgroup local storage
2018-10-01 16:18:32 +02:00
bpf: add queue and stack maps
2018-10-19 13:24:31 -07:00
bpf: add queue and stack maps
2018-10-19 13:24:31 -07:00
bpf: add verifier callback to get stack usage info for offloaded progs
2018-10-08 10:24:12 +02:00
ext4: convert fault handler to use vm_fault_t type
2018-10-02 22:20:50 -04:00
cgroup: Fix dom_cgrp propagation when enabling threaded mode
2018-10-04 13:28:08 -07:00
Merge branch 'for-4.20' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup
2018-10-25 17:15:46 -07:00
Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
2018-10-25 11:14:36 -07:00
Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
2018-10-25 11:14:36 -07:00
s390 updates for the 4.20 merge window
2018-10-23 11:14:47 +01:00
x86/objtool: Use asm macros to work around GCC inlining bugs
2018-10-04 11:24:58 +02:00
Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6
2018-10-25 16:43:35 -07:00
signal: Distinguish between kernel_siginfo and siginfo
2018-10-03 16:47:43 +02:00
coresight: Add support for CLAIM tag protocol
2018-09-25 20:09:19 +02:00
cpuidle: menu: Fix wakeup statistics updates for polling state
2018-10-04 10:23:37 +02:00
kdump, proc/vmcore: Enable kdumping encrypted memory with SME enabled
2018-10-06 12:09:26 +02:00
crypto: user - Implement a generic crypto statistics
2018-09-28 12:46:25 +08:00
locking/lockdep: Make global debug_locks* variables read-mostly
2018-10-19 07:53:18 +02:00
PM / devfreq: Make update_devfreq() public
2018-10-02 10:16:41 +09:00
Driver core patches for 4.20-rc1
2018-10-26 08:42:25 -07:00
dma-debug: Check for drivers mapping invalid addresses in dma_map_single()
2018-10-08 09:44:17 +02:00
dma-direct: implement complete bus_dma_mask handling
2018-10-01 07:28:03 -07:00
dma-mapping: translate __GFP_NOFAIL to DMA_ATTR_NO_WARN
2018-10-09 15:08:26 +02:00
dns: Allow the dns resolver to retrieve a server set
2018-10-04 09:40:52 -07:00
EDAC: Raise the maximum number of memory controllers
2018-09-27 07:52:05 +02:00
efi/x86: Handle page faults occurring while running EFI runtime services
2018-09-26 12:14:55 +02:00
block: move call of scheduler's ->completed_request() hook
2018-09-27 17:34:52 -06:00
f2fs: guarantee journalled quota data by checkpoint
2018-10-22 17:54:47 -07:00
bpf: add cg_skb_is_valid_access for BPF_PROG_TYPE_CGROUP_SKB
2018-10-19 13:49:34 -07:00
vfs: swap names of {do,vfs}_clone_file_range()
2018-09-24 10:54:01 +02:00
This is the 4.19-rc6 release
2018-10-01 08:58:57 -06:00
Merge branch 'for-4.20/logitech-highres' into for-linus
2018-10-23 13:35:22 +02:00
mm: remove references to vm_insert_pfn()
2018-10-26 16:25:20 -07:00
mremap: properly flush TLB before releasing the page
2018-10-18 11:30:52 +02:00
mm: migration: fix migration of huge PMD shared pages
2018-10-05 16:32:04 -07:00
hwrng: core - document the quality field
2018-10-05 10:16:56 +08:00
hwmon: (core) Add hwmon_in_enable attribute
2018-10-10 20:37:13 -07:00
vmbus: split ring buffer allocation from open
2018-09-25 20:33:24 +02:00
mac80211: minstrel: Enable STBC and LDPC for VHT Rates
2018-10-11 16:01:00 +02:00
LSM: Convert from initcall to struct lsm_info
2018-10-10 20:40:21 -07:00
genirq: Fix grammar s/an /a /
2018-10-09 07:50:41 +02:00
fs/iomap.c: change return type to vm_fault_t
2018-10-26 16:25:18 -07:00
irqchip/irq-mvebu-sei: Add new driver for Marvell SEI
2018-10-02 12:00:08 +01:00
jump_label: Annotate entries that operate on __init code earlier
2018-09-27 17:56:48 +02:00
leds: core: Introduce LED pattern trigger
2018-10-11 21:55:58 +02:00
lightnvm: pblk: fix mapping issue on failed writes
2018-10-09 08:25:07 -06:00
include/linux/linkage.h: align weak symbols
2018-10-26 16:25:18 -07:00
net: phy: Replace phy driver features u32 with link_mode bitmap
2018-10-01 22:55:36 -07:00
locking/lockdep: Make class->ops a percpu counter and move it under CONFIG_DEBUG_LOCKDEP=y
2018-10-09 09:56:33 +02:00
Merge branch 'next-general' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security
2018-10-24 11:49:35 +01:00
mm: don't miss the last page because of round-off error
2018-10-26 16:25:19 -07:00
mm: rework memcg kernel stack accounting
2018-10-26 16:25:19 -07:00
PCI/P2PDMA: Add PCI p2pmem DMA mappings to adjust the bus offset
2018-10-17 12:18:16 -05:00
net: phy: micrel: add Microchip KSZ9131 initial driver
2018-10-19 17:02:23 -07:00
net: phy: Add limkmode equivalents to some of the MII ethtool helpers
2018-10-01 22:55:36 -07:00
mm: remove vm_insert_pfn()
2018-10-26 16:25:20 -07:00
Revert "mm, mmu_notifier: annotate mmu notifiers with blockable invalidate callbacks"
2018-10-26 16:25:19 -07:00
mm, sched/numa: Remove remaining traces of NUMA rate-limiting
2018-10-09 08:30:51 +02:00
Merge branch 'next-general' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security
2018-10-24 11:49:35 +01:00
net: Plumb support for filtering ipv4 and ipv6 multicast route dumps
2018-10-16 00:13:39 -07:00
genirq/msi: Allow creation of a tree-based irqdomain for platform-msi
2018-10-02 11:16:38 +01:00
UAPI: ndctl: Remove use of PAGE_SIZE
2018-10-17 13:56:58 -07:00
FDDI: defza: Support capturing outgoing SMT traffic
2018-10-15 21:46:06 -07:00
netfilter: avoid erronous array bounds warning
2018-09-28 14:47:40 +02:00
netlink: Add answer_flags to netlink_callback
2018-10-16 00:13:12 -07:00
netpoll: allow cleanup to be synchronous
2018-10-19 17:01:43 -07:00
nvme: call nvme_complete_rq when nvmf_check_ready fails for mpath I/O
2018-10-01 14:16:13 -07:00
nvmem: use EOPNOTSUPP instead of ENOSYS
2018-09-28 15:14:55 +02:00
nvmem: use EOPNOTSUPP instead of ENOSYS
2018-09-28 15:14:55 +02:00
PCI: Remove pci_set_dma_max_seg_size()
2018-10-10 15:47:00 -05:00
PCI/P2PDMA: Introduce configfs/sysfs enable attribute helpers
2018-10-17 12:18:17 -05:00
pci-v4.20-changes
2018-10-25 06:50:48 -07:00
pci-v4.20-changes
2018-10-25 06:50:48 -07:00
percpu-refcount: Introduce percpu_ref_resurrect()
2018-09-26 15:11:29 -06:00
include/linux/pfn_t.h: force '~' to be parsed as an unary operator
2018-10-26 16:25:18 -07:00
net: phy: improve handling delayed work
2018-10-01 23:14:10 -07:00
PM / Domains: Document flags for genpd
2018-10-18 12:25:10 +02:00
signal: Distinguish between kernel_siginfo and siginfo
2018-10-03 16:47:43 +02:00
pstore/ram: Clarify resource reservation labels
2018-10-22 07:11:58 -07:00
Merge branch 'siginfo-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace
2018-10-24 11:22:39 +01:00
spi: pxa2xx: Add devicetree support
2018-10-11 15:28:04 +01:00
firmware: qcom: scm: Add WLAN VMID for Qualcomm SCM interface
2018-10-13 20:31:37 +03:00
Merge remote-tracking branches 'regmap/topic/noinc' and 'regmap/topic/single-rw' into regmap-next
2018-10-21 12:07:26 +01:00
net: sched: extend Qdisc with rcu
2018-09-25 20:17:35 -07:00
Merge branch 'siginfo-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace
2018-10-24 11:22:39 +01:00
signal: Distinguish between kernel_siginfo and siginfo
2018-10-03 16:47:43 +02:00
Revert "serial: sh-sci: Remove SCIx_RZ_SCIFA_REGTYPE"
2018-10-02 14:38:02 -07:00
signal: Guard against negative signal numbers in copy_siginfo_from_user32
2018-10-10 20:34:14 -05:00
signal: Use a smaller struct siginfo in the kernel
2018-10-03 16:50:39 +02:00
net: skbuff.h: Mark expected switch fall-throughs
2018-10-17 22:31:30 -07:00
bpf: sk_msg program helper bpf_msg_push_data
2018-10-20 21:37:11 +02:00
mm, slab: combine kmalloc_caches and kmalloc_dma_caches
2018-10-26 16:26:31 -07:00
smp,cpumask: introduce on_each_cpu_cond_mask
2018-10-09 16:51:11 +02:00
init: add arch_call_rest_init to allow stack switching
2018-10-09 11:20:55 +02:00
lib: Add memcat_p(): paste 2 pointer arrays together
2018-10-11 12:12:55 +02:00
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input
2018-10-12 12:35:02 +02:00
tcp: do not change tcp_wstamp_ns in tcp_mstamp_refresh
2018-10-15 22:56:41 -07:00
thunderbolt: Convert rest of the driver files to use SPDX identifier
2018-10-02 15:52:08 -07:00
Merge branch 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
2018-10-25 11:14:36 -07:00
tracepoint: Fix tracepoint array element size mismatch
2018-10-17 15:35:29 -04:00
tracepoint: Fix tracepoint array element size mismatch
2018-10-17 15:35:29 -04:00
change semantics of ldisc ->compat_ioctl()
2018-10-13 00:50:53 -04:00
uio: introduce UIO_MEM_IOVA
2018-09-25 20:33:24 +02:00
umh: Add command line to user mode helpers
2018-10-22 19:37:36 -07:00
net/packet: fix packet drop as of virtio gso
2018-10-04 22:23:15 -07:00
scsi: sched/wait: Add wait_event_lock_irq_timeout for TASK_UNINTERRUPTIBLE usage
2018-10-16 00:11:13 -04:00
