diff options
author | Dave Hansen <dave.hansen@linux.intel.com> | 2014-07-31 08:40:55 -0700 |
---|---|---|
committer | H. Peter Anvin <hpa@linux.intel.com> | 2014-07-31 08:48:50 -0700 |
commit | e9f4e0a9fe2723078b7a1a1169828dd46a7b2f9e (patch) | |
tree | c16300d2f05f2fce6b7b70b2c6fed1ac58486129 /arch/x86/kernel | |
parent | 4995ab9cf512e9a6cc07dfd6b1d4e2fc48ce7fef (diff) | |
download | linux-e9f4e0a9fe2723078b7a1a1169828dd46a7b2f9e.tar.bz2 |
x86/mm: Rip out complicated, out-of-date, buggy TLB flushing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>
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r-- | arch/x86/kernel/cpu/amd.c | 7 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/common.c | 13 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/intel.c | 26 |
3 files changed, 2 insertions, 44 deletions
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index ce8b8ff0e0ef..a1a53d094987 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -741,11 +741,6 @@ static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size) } #endif -static void cpu_set_tlb_flushall_shift(struct cpuinfo_x86 *c) -{ - tlb_flushall_shift = 6; -} - static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c) { u32 ebx, eax, ecx, edx; @@ -793,8 +788,6 @@ static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c) tlb_lli_2m[ENTRIES] = eax & mask; tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1; - - cpu_set_tlb_flushall_shift(c); } static const struct cpu_dev amd_cpu_dev = { diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 2cbbf88d8f2c..2c1782085121 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -480,26 +480,17 @@ u16 __read_mostly tlb_lld_2m[NR_INFO]; u16 __read_mostly tlb_lld_4m[NR_INFO]; u16 __read_mostly tlb_lld_1g[NR_INFO]; -/* - * tlb_flushall_shift shows the balance point in replacing cr3 write - * with multiple 'invlpg'. It will do this replacement when - * flush_tlb_lines <= active_lines/2^tlb_flushall_shift. - * If tlb_flushall_shift is -1, means the replacement will be disabled. - */ -s8 __read_mostly tlb_flushall_shift = -1; - void cpu_detect_tlb(struct cpuinfo_x86 *c) { if (this_cpu->c_detect_tlb) this_cpu->c_detect_tlb(c); printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" - "Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d, 1GB %d\n" - "tlb_flushall_shift: %d\n", + "Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d, 1GB %d\n", tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES], tlb_lli_4m[ENTRIES], tlb_lld_4k[ENTRIES], tlb_lld_2m[ENTRIES], tlb_lld_4m[ENTRIES], - tlb_lld_1g[ENTRIES], tlb_flushall_shift); + tlb_lld_1g[ENTRIES]); } void detect_ht(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index a80029035bf2..cd61755de49b 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -634,31 +634,6 @@ static void intel_tlb_lookup(const unsigned char desc) } } -static void intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c) -{ - switch ((c->x86 << 8) + c->x86_model) { - case 0x60f: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */ - case 0x616: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */ - case 0x617: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */ - case 0x61d: /* six-core 45 nm xeon "Dunnington" */ - tlb_flushall_shift = -1; - break; - case 0x63a: /* Ivybridge */ - tlb_flushall_shift = 2; - break; - case 0x61a: /* 45 nm nehalem, "Bloomfield" */ - case 0x61e: /* 45 nm nehalem, "Lynnfield" */ - case 0x625: /* 32 nm nehalem, "Clarkdale" */ - case 0x62c: /* 32 nm nehalem, "Gulftown" */ - case 0x62e: /* 45 nm nehalem-ex, "Beckton" */ - case 0x62f: /* 32 nm Xeon E7 */ - case 0x62a: /* SandyBridge */ - case 0x62d: /* SandyBridge, "Romely-EP" */ - default: - tlb_flushall_shift = 6; - } -} - static void intel_detect_tlb(struct cpuinfo_x86 *c) { int i, j, n; @@ -683,7 +658,6 @@ static void intel_detect_tlb(struct cpuinfo_x86 *c) for (j = 1 ; j < 16 ; j++) intel_tlb_lookup(desc[j]); } - intel_tlb_flushall_shift_set(c); } static const struct cpu_dev intel_cpu_dev = { |