[tip:x86/mm] x86/mm: Rip out complicated, out-of-date, buggy TLB flushing

From: tip-bot for Dave Hansen
Date: Thu Jul 31 2014 - 12:14:39 EST


Commit-ID: e9f4e0a9fe2723078b7a1a1169828dd46a7b2f9e
Gitweb: http://git.kernel.org/tip/e9f4e0a9fe2723078b7a1a1169828dd46a7b2f9e
Author: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
AuthorDate: Thu, 31 Jul 2014 08:40:55 -0700
Committer: H. Peter Anvin <hpa@xxxxxxxxxxxxxxx>
CommitDate: Thu, 31 Jul 2014 08:48:50 -0700

x86/mm: Rip out complicated, out-of-date, buggy TLB flushing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@xxxxxxxxx
(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@xxxxxxxxxxxxxxx>
Link: http://lkml.kernel.org/r/20140731154055.ABC88E89@xxxxxxxxxxxxxxxxxx
Acked-by: Rik van Riel <riel@xxxxxxxxxx>
Acked-by: Mel Gorman <mgorman@xxxxxxx>
Signed-off-by: H. Peter Anvin <hpa@xxxxxxxxxxxxxxx>
---
arch/x86/include/asm/processor.h | 1 -
arch/x86/kernel/cpu/amd.c | 7 ----
arch/x86/kernel/cpu/common.c | 13 +-----
arch/x86/kernel/cpu/intel.c | 26 ------------
arch/x86/mm/tlb.c | 87 +++++-----------------------------------
5 files changed, 13 insertions(+), 121 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index a4ea023..43d61da 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -72,7 +72,6 @@ extern u16 __read_mostly tlb_lld_4k[NR_INFO];
extern u16 __read_mostly tlb_lld_2m[NR_INFO];
extern u16 __read_mostly tlb_lld_4m[NR_INFO];
extern u16 __read_mostly tlb_lld_1g[NR_INFO];
-extern s8 __read_mostly tlb_flushall_shift;

/*
* CPU type and hardware bug flags. Kept separately for each CPU.
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index ce8b8ff..a1a53d0 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 2cbbf88..2c17820 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 a800290..cd61755 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 = {
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 378fbef..dff6dde 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -158,13 +158,14 @@ void flush_tlb_current_task(void)
preempt_enable();
}

+/* in units of pages */
+unsigned long tlb_single_page_flush_ceiling = 1;
+
void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
unsigned long end, unsigned long vmflag)
{
- bool need_flush_others_all = true;
+ int need_flush_others_all = 1;
unsigned long addr;
- unsigned act_entries, tlb_entries = 0;
- unsigned long nr_base_pages;

preempt_disable();
if (current->active_mm != mm)
@@ -175,29 +176,16 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
goto out;
}

- if (end == TLB_FLUSH_ALL || tlb_flushall_shift == -1
- || vmflag & VM_HUGETLB) {
+ if (end == TLB_FLUSH_ALL || vmflag & VM_HUGETLB) {
local_flush_tlb();
goto out;
}

- /* In modern CPU, last level tlb used for both data/ins */
- if (vmflag & VM_EXEC)
- tlb_entries = tlb_lli_4k[ENTRIES];
- else
- tlb_entries = tlb_lld_4k[ENTRIES];
-
- /* Assume all of TLB entries was occupied by this task */
- act_entries = tlb_entries >> tlb_flushall_shift;
- act_entries = mm->total_vm > act_entries ? act_entries : mm->total_vm;
- nr_base_pages = (end - start) >> PAGE_SHIFT;
-
- /* tlb_flushall_shift is on balance point, details in commit log */
- if (nr_base_pages > act_entries) {
+ if ((end - start) > tlb_single_page_flush_ceiling * PAGE_SIZE) {
count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
local_flush_tlb();
} else {
- need_flush_others_all = false;
+ need_flush_others_all = 0;
/* flush range by one by one 'invlpg' */
for (addr = start; addr < end; addr += PAGE_SIZE) {
count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
@@ -259,68 +247,15 @@ static void do_kernel_range_flush(void *info)

void flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
- unsigned act_entries;
- struct flush_tlb_info info;
-
- /* In modern CPU, last level tlb used for both data/ins */
- act_entries = tlb_lld_4k[ENTRIES];

/* Balance as user space task's flush, a bit conservative */
- if (end == TLB_FLUSH_ALL || tlb_flushall_shift == -1 ||
- (end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift)
-
+ if (end == TLB_FLUSH_ALL ||
+ (end - start) > tlb_single_page_flush_ceiling * PAGE_SIZE) {
on_each_cpu(do_flush_tlb_all, NULL, 1);
- else {
+ } else {
+ struct flush_tlb_info info;
info.flush_start = start;
info.flush_end = end;
on_each_cpu(do_kernel_range_flush, &info, 1);
}
}
-
-#ifdef CONFIG_DEBUG_TLBFLUSH
-static ssize_t tlbflush_read_file(struct file *file, char __user *user_buf,
- size_t count, loff_t *ppos)
-{
- char buf[32];
- unsigned int len;
-
- len = sprintf(buf, "%hd\n", tlb_flushall_shift);
- return simple_read_from_buffer(user_buf, count, ppos, buf, len);
-}
-
-static ssize_t tlbflush_write_file(struct file *file,
- const char __user *user_buf, size_t count, loff_t *ppos)
-{
- char buf[32];
- ssize_t len;
- s8 shift;
-
- len = min(count, sizeof(buf) - 1);
- if (copy_from_user(buf, user_buf, len))
- return -EFAULT;
-
- buf[len] = '\0';
- if (kstrtos8(buf, 0, &shift))
- return -EINVAL;
-
- if (shift < -1 || shift >= BITS_PER_LONG)
- return -EINVAL;
-
- tlb_flushall_shift = shift;
- return count;
-}
-
-static const struct file_operations fops_tlbflush = {
- .read = tlbflush_read_file,
- .write = tlbflush_write_file,
- .llseek = default_llseek,
-};
-
-static int __init create_tlb_flushall_shift(void)
-{
- debugfs_create_file("tlb_flushall_shift", S_IRUSR | S_IWUSR,
- arch_debugfs_dir, NULL, &fops_tlbflush);
- return 0;
-}
-late_initcall(create_tlb_flushall_shift);
-#endif
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/