[PATCH v8 6/8] x86/tlb: enable tlb flush range support for generic mmu and x86

[Alex Shi <alex.shi@intel.com>]

Not every tlb_flush execution moment is really need to evacuate all
TLB entries, like in munmap, just few 'invlpg' is better for whole
process performance, since it leaves most of TLB entries for later
accessing.

All of tlb interfaces in mm/memory.c are reused by all architectures
except few of them for generic mmu_gather were protected under
HAVE_GENERIC_MMU_GATHER. So, add flush range start/end under
HAVE_GENERIC_MMU_GATHER for generic mmu implementation.
For x86, just need to re-implement tlb_flush().

This patch also rewrite flush_tlb_range for 2 purposes:
1, split it out to get flush_blt_mm_range function.
2, clean up to reduce line breaking, thanks for Borislav's input.

My macro benchmark 'mummap' http://lkml.org/lkml/2012/5/17/59
show that the random memory access on other CPU has 0~50% speed up
on a 2P * 4cores * HT NHM EP while do 'munmap'.

Thanks for Peter Zijlstra time and time reminder for multiple
architecture code safe!

Signed-off-by: Alex Shi <alex.shi@intel.com>
---
 arch/x86/include/asm/tlb.h      |    9 +++-
 arch/x86/include/asm/tlbflush.h |   17 +++++-
 arch/x86/mm/tlb.c               |  112 ++++++++++++++++-----------------------
 include/asm-generic/tlb.h       |    2 +
 mm/memory.c                     |    9 +++
 5 files changed, 79 insertions(+), 70 deletions(-)

diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 829215f..4fef207 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -4,7 +4,14 @@
 #define tlb_start_vma(tlb, vma) do { } while (0)
 #define tlb_end_vma(tlb, vma) do { } while (0)
 #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
+
+#define tlb_flush(tlb)							\
+{									\
+	if (tlb->fullmm == 0)						\
+		flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end, 0UL);	\
+	else								\
+		flush_tlb_mm_range(tlb->mm, 0UL, TLB_FLUSH_ALL, 0UL);	\
+}
 
 #include <asm-generic/tlb.h>
 
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 33608d9..008043d 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -105,6 +105,13 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 		__flush_tlb();
 }
 
+static inline void flush_tlb_mm_range(struct vm_area_struct *vma,
+	   unsigned long start, unsigned long end, unsigned long vmflag)
+{
+	if (mm == current->active_mm)
+		__flush_tlb();
+}
+
 static inline void native_flush_tlb_others(const struct cpumask *cpumask,
 					   struct mm_struct *mm,
 					   unsigned long start,
@@ -122,12 +129,16 @@ static inline void reset_lazy_tlbstate(void)
 
 #define local_flush_tlb() __flush_tlb()
 
+#define flush_tlb_mm(mm)	flush_tlb_mm_range(mm, 0UL, TLB_FLUSH_ALL, 0UL)
+
+#define flush_tlb_range(vma, start, end)	\
+		flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags)
+
 extern void flush_tlb_all(void);
 extern void flush_tlb_current_task(void);
-extern void flush_tlb_mm(struct mm_struct *);
 extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
-extern void flush_tlb_range(struct vm_area_struct *vma,
-				   unsigned long start, unsigned long end);
+extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
+				unsigned long end, unsigned long vmflag);
 
 #define flush_tlb()	flush_tlb_current_task()
 
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 5911f61..481737d 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -301,23 +301,10 @@ void flush_tlb_current_task(void)
 	preempt_enable();
 }
 
-void flush_tlb_mm(struct mm_struct *mm)
-{
-	preempt_disable();
-
-	if (current->active_mm == mm) {
-		if (current->mm)
-			local_flush_tlb();
-		else
-			leave_mm(smp_processor_id());
-	}
-	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
-
-	preempt_enable();
-}
-
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/*
+ * It can find out the THP large page, or
+ * HUGETLB page in tlb_flush when THP disabled
+ */
 static inline unsigned long has_large_page(struct mm_struct *mm,
 				 unsigned long start, unsigned long end)
 {
@@ -339,68 +326,61 @@ static inline unsigned long has_large_page(struct mm_struct *mm,
 	}
 	return 0;
 }
-#else
-static inline unsigned long has_large_page(struct mm_struct *mm,
-				 unsigned long start, unsigned long end)
-{
-	return 0;
-}
-#endif
-void flush_tlb_range(struct vm_area_struct *vma,
-				   unsigned long start, unsigned long end)
-{
-	struct mm_struct *mm;
 
-	if (vma->vm_flags & VM_HUGETLB || tlb_flushall_shift == -1) {
-flush_all:
-		flush_tlb_mm(vma->vm_mm);
-		return;
-	}
+void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
+				unsigned long end, unsigned long vmflag)
+{
+	unsigned long addr;
+	unsigned act_entries, tlb_entries = 0;
 
 	preempt_disable();
-	mm = vma->vm_mm;
-	if (current->active_mm == mm) {
-		if (current->mm) {
-			unsigned long addr, vmflag = vma->vm_flags;
-			unsigned act_entries, tlb_entries = 0;
+	if (current->active_mm != mm)
+		goto flush_all;
 
-			if (vmflag & VM_EXEC)
-				tlb_entries = tlb_lli_4k[ENTRIES];
-			else
-				tlb_entries = tlb_lld_4k[ENTRIES];
-
-			act_entries = tlb_entries > mm->total_vm ?
-					mm->total_vm : tlb_entries;
+	if (!current->mm) {
+		leave_mm(smp_processor_id());
+		goto flush_all;
+	}
 
-			if ((end - start) >> PAGE_SHIFT >
-					act_entries >> tlb_flushall_shift)
-				local_flush_tlb();
-			else {
-				if (has_large_page(mm, start, end)) {
-					preempt_enable();
-					goto flush_all;
-				}
-				for (addr = start; addr < end;
-						addr += PAGE_SIZE)
-					__flush_tlb_single(addr);
+	if (end == TLB_FLUSH_ALL || tlb_flushall_shift == -1
+					|| vmflag == VM_HUGETLB) {
+		local_flush_tlb();
+		goto flush_all;
+	}
 
-				if (cpumask_any_but(mm_cpumask(mm),
-					smp_processor_id()) < nr_cpu_ids)
-					flush_tlb_others(mm_cpumask(mm), mm,
-								start, end);
-				preempt_enable();
-				return;
-			}
-		} else {
-			leave_mm(smp_processor_id());
+	/* 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 = mm->total_vm > tlb_entries ? tlb_entries : mm->total_vm;
+
+	/* tlb_flushall_shift is on balance point, details in commit log */
+	if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift)
+		local_flush_tlb();
+	else {
+		if (has_large_page(mm, start, end)) {
+			local_flush_tlb();
+			goto flush_all;
 		}
+		/* flush range by one by one 'invlpg' */
+		for (addr = start; addr < end;	addr += PAGE_SIZE)
+			__flush_tlb_single(addr);
+
+		if (cpumask_any_but(mm_cpumask(mm),
+				smp_processor_id()) < nr_cpu_ids)
+			flush_tlb_others(mm_cpumask(mm), mm, start, end);
+		preempt_enable();
+		return;
 	}
+
+flush_all:
 	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
 		flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
 	preempt_enable();
 }
 
-
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
 {
 	struct mm_struct *mm = vma->vm_mm;
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 75e888b..ed6642a 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -86,6 +86,8 @@ struct mmu_gather {
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	struct mmu_table_batch	*batch;
 #endif
+	unsigned long		start;
+	unsigned long		end;
 	unsigned int		need_flush : 1,	/* Did free PTEs */
 				fast_mode  : 1; /* No batching   */
 
diff --git a/mm/memory.c b/mm/memory.c
index 1b7dc66..32c9943 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -206,6 +206,8 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
 	tlb->mm = mm;
 
 	tlb->fullmm     = fullmm;
+	tlb->start	= -1UL;
+	tlb->end	= 0;
 	tlb->need_flush = 0;
 	tlb->fast_mode  = (num_possible_cpus() == 1);
 	tlb->local.next = NULL;
@@ -248,6 +250,8 @@ void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long e
 {
 	struct mmu_gather_batch *batch, *next;
 
+	tlb->start = start;
+	tlb->end   = end;
 	tlb_flush_mmu(tlb);
 
 	/* keep the page table cache within bounds */
@@ -1204,6 +1208,11 @@ again:
 	 */
 	if (force_flush) {
 		force_flush = 0;
+
+#ifdef HAVE_GENERIC_MMU_GATHER
+		tlb->start = addr;
+		tlb->end = end;
+#endif
 		tlb_flush_mmu(tlb);
 		if (addr != end)
 			goto again;
-- 
1.7.5.4