linux-stable/mm
Joerg Roedel 6c1051ffc7 x86/mm: split vmalloc_sync_all()
commit 763802b53a upstream.

Commit 3f8fd02b1b ("mm/vmalloc: Sync unmappings in
__purge_vmap_area_lazy()") introduced a call to vmalloc_sync_all() in
the vunmap() code-path.  While this change was necessary to maintain
correctness on x86-32-pae kernels, it also adds additional cycles for
architectures that don't need it.

Specifically on x86-64 with CONFIG_VMAP_STACK=y some people reported
severe performance regressions in micro-benchmarks because it now also
calls the x86-64 implementation of vmalloc_sync_all() on vunmap().  But
the vmalloc_sync_all() implementation on x86-64 is only needed for newly
created mappings.

To avoid the unnecessary work on x86-64 and to gain the performance
back, split up vmalloc_sync_all() into two functions:

	* vmalloc_sync_mappings(), and
	* vmalloc_sync_unmappings()

Most call-sites to vmalloc_sync_all() only care about new mappings being
synchronized.  The only exception is the new call-site added in the
above mentioned commit.

Shile Zhang directed us to a report of an 80% regression in reaim
throughput.

Fixes: 3f8fd02b1b ("mm/vmalloc: Sync unmappings in __purge_vmap_area_lazy()")
Reported-by: kernel test robot <oliver.sang@intel.com>
Reported-by: Shile Zhang <shile.zhang@linux.alibaba.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Borislav Petkov <bp@suse.de>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>	[GHES]
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/20191009124418.8286-1-joro@8bytes.org
Link: https://lists.01.org/hyperkitty/list/lkp@lists.01.org/thread/4D3JPPHBNOSPFK2KEPC6KGKS6J25AIDB/
Link: http://lkml.kernel.org/r/20191113095530.228959-1-shile.zhang@linux.alibaba.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-03-25 08:06:13 +01:00
..
kasan
backing-dev.c writeback: synchronize sync(2) against cgroup writeback membership switches 2019-03-05 17:58:50 +01:00
balloon_compaction.c
bootmem.c
cleancache.c
cma.c mm/cma.c: fail if fixed declaration can't be honored 2019-08-06 19:06:51 +02:00
cma.h
cma_debug.c mm/cma_debug.c: fix the break condition in cma_maxchunk_get() 2019-06-15 11:54:01 +02:00
compaction.c mm/compaction.c: clear total_{migrate,free}_scanned before scanning a new zone 2019-10-05 13:10:13 +02:00
debug.c mm: get rid of vmacache_flush_all() entirely 2018-09-13 15:18:04 -10:00
debug_page_ref.c
dmapool.c
early_ioremap.c
fadvise.c
failslab.c
filemap.c mm/filemap.c: don't initiate writeback if mapping has no dirty pages 2019-11-12 19:21:20 +01:00
frame_vector.c
frontswap.c
gup.c mm/gup.c: remove some BUG_ONs from get_gate_page() 2019-07-31 07:27:08 +02:00
gup_benchmark.c mm/gup_benchmark.c: prevent integer overflow in ioctl 2019-12-01 09:17:07 +01:00
highmem.c
hmm.c mm/memory_hotplug: shrink zones when offlining memory 2020-01-29 16:43:27 +01:00
huge_memory.c mm: fix possible PMD dirty bit lost in set_pmd_migration_entry() 2020-03-11 14:15:00 +01:00
hugetlb.c hugetlbfs: don't access uninitialized memmaps in pfn_range_valid_gigantic() 2019-10-29 09:19:59 +01:00
hugetlb_cgroup.c mm: hugetlb: switch to css_tryget() in hugetlb_cgroup_charge_cgroup() 2019-11-20 18:45:20 +01:00
hwpoison-inject.c
init-mm.c
internal.h vmscan: return NODE_RECLAIM_NOSCAN in node_reclaim() when CONFIG_NUMA is n 2019-12-05 09:20:57 +01:00
interval_tree.c
Kconfig mm/hmm: select mmu notifier when selecting HMM 2019-06-15 11:54:00 +02:00
Kconfig.debug
khugepaged.c coredump: fix race condition between collapse_huge_page() and core dumping 2019-06-22 08:15:21 +02:00
kmemleak-test.c
kmemleak.c Revert "kmemleak: allow to coexist with fault injection" 2019-08-25 10:47:58 +02:00
ksm.c mm/ksm.c: don't WARN if page is still mapped in remove_stable_node() 2019-12-01 09:16:11 +01:00
list_lru.c mm/list_lru.c: fix memory leak in __memcg_init_list_lru_node 2019-06-19 08:17:59 +02:00
maccess.c
madvise.c mm: madvise(MADV_DODUMP): allow hugetlbfs pages 2018-10-05 16:32:05 -07:00
Makefile
memblock.c mm/page_alloc.c: deduplicate __memblock_free_early() and memblock_free() 2019-12-05 09:20:58 +01:00
memcontrol.c memcg: fix NULL pointer dereference in __mem_cgroup_usage_unregister_event 2020-03-25 08:06:12 +01:00
memfd.c memfd: Use radix_tree_deref_slot_protected to avoid the warning. 2019-11-20 18:47:53 +01:00
memory-failure.c mm/memory-failure: poison read receives SIGKILL instead of SIGBUS if mmaped more than once 2019-10-29 09:19:59 +01:00
memory.c mm, thp, proc: report THP eligibility for each vma 2019-12-17 20:35:45 +01:00
memory_hotplug.c mm/memory_hotplug: fix remove_memory() lockdep splat 2020-02-11 04:33:56 -08:00
mempolicy.c mm/mempolicy.c: fix out of bounds write in mpol_parse_str() 2020-02-05 14:43:36 +00:00
mempool.c
memtest.c
migrate.c mm: move_pages: report the number of non-attempted pages 2020-02-11 04:33:56 -08:00
mincore.c mm/mincore.c: make mincore() more conservative 2019-05-22 07:37:40 +02:00
mlock.c mm/mlock.c: change count_mm_mlocked_page_nr return type 2019-07-10 09:53:40 +02:00
mm_init.c
mmap.c arm64: Revert support for execute-only user mappings 2020-01-09 10:19:03 +01:00
mmu_context.c
mmu_notifier.c mm/mmu_notifier: use hlist_add_head_rcu() 2019-07-31 07:27:08 +02:00
mmzone.c
mprotect.c mm, numa: fix bad pmd by atomically check for pmd_trans_huge when marking page tables prot_numa 2020-03-11 14:15:00 +01:00
mremap.c mremap: properly flush TLB before releasing the page 2018-10-18 11:30:52 +02:00
msync.c
nobootmem.c
nommu.c x86/mm: split vmalloc_sync_all() 2020-03-25 08:06:13 +01:00
oom_kill.c memcg, oom: don't require __GFP_FS when invoking memcg OOM killer 2019-10-05 13:10:07 +02:00
page-writeback.c mm/page-writeback.c: avoid potential division by zero in wb_min_max_ratio() 2020-01-23 08:21:31 +01:00
page_alloc.c mm/page_alloc.c: fix uninitialized memmaps on a partially populated last section 2020-02-11 04:34:18 -08:00
page_counter.c
page_ext.c mm/page_ext.c: fix an imbalance with kmemleak 2019-04-05 22:32:58 +02:00
page_idle.c mm/page_idle.c: fix oops because end_pfn is larger than max_pfn 2019-07-03 13:14:45 +02:00
page_io.c mm/page_io.c: do not free shared swap slots 2019-12-01 09:17:35 +01:00
page_isolation.c
page_owner.c mm/page_owner: don't access uninitialized memmaps when reading /proc/pagetypeinfo 2019-10-29 09:19:58 +01:00
page_poison.c page_poison: play nicely with KASAN 2019-04-05 22:32:59 +02:00
page_vma_mapped.c mm/rmap: map_pte() was not handling private ZONE_DEVICE page properly 2018-11-13 11:08:46 -08:00
pagewalk.c
percpu-internal.h
percpu-km.c percpu: convert spin_lock_irq to spin_lock_irqsave. 2019-02-12 19:47:12 +01:00
percpu-stats.c
percpu-vm.c
percpu.c percpu: do not search past bitmap when allocating an area 2019-06-15 11:54:11 +02:00
pgtable-generic.c
process_vm_access.c
quicklist.c
readahead.c
rmap.c mm/hmm: fix bad subpage pointer in try_to_unmap_one 2019-08-25 10:47:43 +02:00
rodata_test.c
shmem.c mm/shmem.c: thp, shmem: fix conflict of above-47bit hint address and PMD alignment 2020-01-23 08:21:30 +01:00
slab.c mm/slab.c: fix an infinite loop in leaks_show() 2019-06-15 11:54:01 +02:00
slab.h mm: add support for kmem caches in DMA32 zone 2019-04-03 06:26:28 +02:00
slab_common.c mm: memcg/slab: call flush_memcg_workqueue() only if memcg workqueue is valid 2020-01-23 08:21:30 +01:00
slob.c
slub.c mm, slub: prevent kmalloc_node crashes and memory leaks 2020-03-25 08:06:13 +01:00
sparse-vmemmap.c
sparse.c mm/memory_hotplug: remove "zone" parameter from sparse_remove_one_section 2020-01-29 16:43:26 +01:00
swap.c mm/swap: fix release_pages() when releasing devmap pages 2019-07-31 07:27:03 +02:00
swap_cgroup.c
swap_slots.c
swap_state.c
swapfile.c mm, swap: bounds check swap_info array accesses to avoid NULL derefs 2019-04-05 22:32:58 +02:00
truncate.c mm: cleancache: fix corruption on missed inode invalidation 2018-12-05 19:32:13 +01:00
usercopy.c usercopy: Avoid HIGHMEM pfn warning 2019-10-11 18:20:58 +02:00
userfaultfd.c hugetlb: use same fault hash key for shared and private mappings 2019-05-22 07:37:40 +02:00
util.c mm: page_mapped: don't assume compound page is huge or THP 2019-01-16 22:04:36 +01:00
vmacache.c mm: get rid of vmacache_flush_all() entirely 2018-09-13 15:18:04 -10:00
vmalloc.c x86/mm: split vmalloc_sync_all() 2020-03-25 08:06:13 +01:00
vmpressure.c mm/vmpressure.c: fix a signedness bug in vmpressure_register_event() 2019-10-17 13:45:19 -07:00
vmscan.c mm/vmscan.c: don't round up scan size for online memory cgroup 2020-02-28 16:38:50 +01:00
vmstat.c mm/vmstat.c: fix NUMA statistics updates 2019-12-13 08:51:27 +01:00
workingset.c
z3fold.c z3fold: fix possible reclaim races 2018-12-01 09:37:33 +01:00
zbud.c
zpool.c
zsmalloc.c mm/zsmalloc.c: fix the migrated zspage statistics. 2020-01-09 10:19:00 +01:00
zswap.c