summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
authorAlex Shi <alex.shi@intel.com>2012-06-28 09:02:19 +0800
committerH. Peter Anvin <hpa@zytor.com>2012-06-27 19:29:10 -0700
commitc4211f42d3e66875298a5e26a75109878c80f15b (patch)
tree5f4db23b52be8eb74f95c35621373df790eacdd2 /arch/x86
parentd8dfe60d6dcad5989c4558b753b98d657e2813c0 (diff)
downloadop-kernel-dev-c4211f42d3e66875298a5e26a75109878c80f15b.zip
op-kernel-dev-c4211f42d3e66875298a5e26a75109878c80f15b.tar.gz
x86/tlb: add tlb_flushall_shift for specific CPU
Testing show different CPU type(micro architectures and NUMA mode) has different balance points between the TLB flush all and multiple invlpg. And there also has cases the tlb flush change has no any help. This patch give a interface to let x86 vendor developers have a chance to set different shift for different CPU type. like some machine in my hands, balance points is 16 entries on Romely-EP; while it is at 8 entries on Bloomfield NHM-EP; and is 256 on IVB mobile CPU. but on model 15 core2 Xeon using invlpg has nothing help. For untested machine, do a conservative optimization, same as NHM CPU. Signed-off-by: Alex Shi <alex.shi@intel.com> Link: http://lkml.kernel.org/r/1340845344-27557-5-git-send-email-alex.shi@intel.com Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/include/asm/processor.h2
-rw-r--r--arch/x86/kernel/cpu/common.c14
-rw-r--r--arch/x86/kernel/cpu/intel.c34
-rw-r--r--arch/x86/mm/tlb.c7
4 files changed, 51 insertions, 6 deletions
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 39b2bd4..d048cad 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -72,6 +72,8 @@ extern u16 __read_mostly tlb_lli_4m[NR_INFO];
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 s8 __read_mostly tlb_flushall_shift;
+
/*
* CPU type and hardware bug flags. Kept separately for each CPU.
* Members of this structure are referenced in head.S, so think twice
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b2016df..7595552 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -459,16 +459,26 @@ u16 __read_mostly tlb_lld_4k[NR_INFO];
u16 __read_mostly tlb_lld_2m[NR_INFO];
u16 __read_mostly tlb_lld_4m[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 __cpuinit 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\n",
+ "Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \
+ "tlb_flushall_shift is 0x%x\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_2m[ENTRIES], tlb_lld_4m[ENTRIES],
+ tlb_flushall_shift);
}
void __cpuinit detect_ht(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index ed0d512..0a4ce29 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -610,6 +610,39 @@ static void __cpuinit intel_tlb_lookup(const unsigned char desc)
}
}
+static void __cpuinit intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c)
+{
+ if (!cpu_has_invlpg) {
+ tlb_flushall_shift = -1;
+ return;
+ }
+ 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 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 */
+ tlb_flushall_shift = 6;
+ break;
+ case 0x62a: /* SandyBridge */
+ case 0x62d: /* SandyBridge, "Romely-EP" */
+ tlb_flushall_shift = 5;
+ break;
+ case 0x63a: /* Ivybridge */
+ tlb_flushall_shift = 1;
+ break;
+ default:
+ tlb_flushall_shift = 6;
+ }
+}
+
static void __cpuinit intel_detect_tlb(struct cpuinfo_x86 *c)
{
int i, j, n;
@@ -630,6 +663,7 @@ static void __cpuinit 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 __cpuinitconst intel_cpu_dev = {
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 184a02a..2939f2f 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -316,8 +316,6 @@ void flush_tlb_mm(struct mm_struct *mm)
preempt_enable();
}
-#define FLUSHALL_BAR 16
-
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline unsigned long has_large_page(struct mm_struct *mm,
unsigned long start, unsigned long end)
@@ -352,7 +350,7 @@ void flush_tlb_range(struct vm_area_struct *vma,
{
struct mm_struct *mm;
- if (!cpu_has_invlpg || vma->vm_flags & VM_HUGETLB) {
+ if (vma->vm_flags & VM_HUGETLB || tlb_flushall_shift == -1) {
flush_all:
flush_tlb_mm(vma->vm_mm);
return;
@@ -373,7 +371,8 @@ flush_all:
act_entries = tlb_entries > mm->total_vm ?
mm->total_vm : tlb_entries;
- if ((end - start)/PAGE_SIZE > act_entries/FLUSHALL_BAR)
+ if ((end - start) >> PAGE_SHIFT >
+ act_entries >> tlb_flushall_shift)
local_flush_tlb();
else {
if (has_large_page(mm, start, end)) {
OpenPOWER on IntegriCloud