linux/arch/x86/mm
Dave Hansen e9f4e0a9fe x86/mm: Rip out complicated, out-of-date, buggy TLB flushing
I think the flush_tlb_mm_range() code that tries to tune the
flush sizes based on the CPU needs to get ripped out for
several reasons:

1. It is obviously buggy.  It uses mm->total_vm to judge the
   task's footprint in the TLB.  It should certainly be using
   some measure of RSS, *NOT* ->total_vm since only resident
   memory can populate the TLB.
2. Haswell, and several other CPUs are missing from the
   intel_tlb_flushall_shift_set() function.  Thus, it has been
   demonstrated to bitrot quickly in practice.
3. It is plain wrong in my vm:
	[    0.037444] Last level iTLB entries: 4KB 0, 2MB 0, 4MB 0
	[    0.037444] Last level dTLB entries: 4KB 0, 2MB 0, 4MB 0
	[    0.037444] tlb_flushall_shift: 6
   Which leads to it to never use invlpg.
4. The assumptions about TLB refill costs are wrong:
	http://lkml.kernel.org/r/1337782555-8088-3-git-send-email-alex.shi@intel.com
    (more on this in later patches)
5. I can not reproduce the original data: https://lkml.org/lkml/2012/5/17/59
   I believe the sample times were too short.  Running the
   benchmark in a loop yields times that vary quite a bit.

Note that this leaves us with a static ceiling of 1 page.  This
is a conservative, dumb setting, and will be revised in a later
patch.

This also removes the code which attempts to predict whether we
are flushing data or instructions.  We expect instruction flushes
to be relatively rare and not worth tuning for explicitly.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: http://lkml.kernel.org/r/20140731154055.ABC88E89@viggo.jf.intel.com
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2014-07-31 08:48:50 -07:00
..
kmemcheck arch/x86/mm/kmemcheck/kmemcheck.c: use kstrtoint() instead of sscanf() 2014-04-08 16:48:52 -07:00
amdtopology.c x86/mm/numa: Simplify some bit mangling 2013-04-10 19:06:26 +02:00
dump_pagetables.c x86-64, espfix: Don't leak bits 31:16 of %esp returning to 16-bit stack 2014-04-30 14:14:28 -07:00
extable.c x86, extable: Switch to relative exception table entries 2012-04-20 17:22:34 -07:00
fault.c x86/smep: Be more informative when signalling an SMEP fault 2014-06-11 17:55:30 -07:00
gup.c mm: dump page when hitting a VM_BUG_ON using VM_BUG_ON_PAGE 2014-01-23 16:36:50 -08:00
highmem_32.c mm: accurately calculate zone->managed_pages for highmem zones 2013-07-03 16:07:33 -07:00
hugetlbpage.c hugetlb: restrict hugepage_migration_support() to x86_64 2014-06-04 16:53:51 -07:00
init_32.c memblock: make memblock_set_node() support different memblock_type 2014-01-21 16:19:44 -08:00
init_64.c Merge branch 'x86/vdso' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into next 2014-06-05 08:05:29 -07:00
init.c arch/x86/mm/init.c: fix incorrect function name in alloc_low_pages() 2013-11-13 12:09:11 +09:00
iomap_32.c
ioremap.c Merge branch 'x86/vdso' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into next 2014-06-05 08:05:29 -07:00
kmmio.c x86: Delete non-required instances of include <linux/init.h> 2014-01-06 21:25:18 -08:00
Makefile x86, trace: Add page fault tracepoints 2013-11-08 14:15:49 -08:00
memtest.c x86/mm: memblock: switch to use NUMA_NO_NODE 2014-01-21 16:19:47 -08:00
mm_internal.h x86, mm: Move after_bootmem to mm_internel.h 2012-11-17 11:59:45 -08:00
mmap.c x86 get_unmapped_area: Access mmap_legacy_base through mm_struct member 2013-08-22 10:19:35 -07:00
mmio-mod.c x86: delete __cpuinit usage from all x86 files 2013-07-14 19:36:56 -04:00
numa_32.c x86: Fix the initialization of physnode_map 2014-02-01 22:15:51 -08:00
numa_64.c x86, mm: kill numa_free_all_bootmem() 2012-11-17 11:59:47 -08:00
numa_emulation.c x86: delete __cpuinit usage from all x86 files 2013-07-14 19:36:56 -04:00
numa_internal.h x86-32, mm: Rip out x86_32 NUMA remapping code 2013-01-31 14:12:30 -08:00
numa.c arch/x86/mm/numa.c: use for_each_memblock() 2014-06-04 16:54:05 -07:00
pageattr-test.c x86: define _PAGE_NUMA by reusing software bits on the PMD and PTE levels 2014-06-04 16:53:55 -07:00
pageattr.c Merge branch 'x86-efi-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2014-03-31 12:26:05 -07:00
pat_internal.h
pat_rbtree.c rbtree: move augmented rbtree functionality to rbtree_augmented.h 2012-10-09 16:22:40 +09:00
pat.c x86: Do not try to sync identity map for non-mapped pages 2013-03-07 13:23:28 -08:00
pf_in.c x86: Eliminate various 'set but not used' warnings 2011-05-21 19:10:33 +02:00
pf_in.h
pgtable_32.c x86: use generic early_ioremap 2014-04-07 16:36:15 -07:00
pgtable.c Merge branch 'x86/vdso' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into next 2014-06-05 08:05:29 -07:00
physaddr.c x86, mm: Make DEBUG_VIRTUAL work earlier in boot 2013-01-25 16:33:22 -08:00
physaddr.h
setup_nx.c x86: delete __cpuinit usage from all x86 files 2013-07-14 19:36:56 -04:00
srat.c x86/mm: Avoid duplicated pxm_to_node() calls 2014-02-09 15:32:31 +01:00
testmmiotrace.c
tlb.c x86/mm: Rip out complicated, out-of-date, buggy TLB flushing 2014-07-31 08:48:50 -07:00