Merge branch 'perf/urgent' into perf/core

Merge reason: Pick up updates before queueing up dependent patches.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

4 files changed, 97 insertions, 19 deletions

diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h
index 5aeec1e1735c..16bd48031583 100644
--- a/arch/arm/include/asm/hardware/cache-l2x0.h
+++ b/arch/arm/include/asm/hardware/cache-l2x0.h
@@ -36,6 +36,7 @@
 #define L2X0_RAW_INTR_STAT		0x21C
 #define L2X0_INTR_CLEAR			0x220
 #define L2X0_CACHE_SYNC			0x730
+#define L2X0_DUMMY_REG			0x740
 #define L2X0_INV_LINE_PA		0x770
 #define L2X0_INV_WAY			0x77C
 #define L2X0_CLEAN_LINE_PA		0x7B0
diff --git a/arch/arm/include/asm/hardware/sp810.h b/arch/arm/include/asm/hardware/sp810.h
index 721847dc68ab..e0d1c0cfa548 100644
--- a/arch/arm/include/asm/hardware/sp810.h
+++ b/arch/arm/include/asm/hardware/sp810.h
@@ -58,6 +58,9 @@
 
 static inline void sysctl_soft_reset(void __iomem *base)
 {
+	/* switch to slow mode */
+	writel(0x2, base + SCCTRL);
+
 	/* writing any value to SCSYSSTAT reg will reset system */
 	writel(0, base + SCSYSSTAT);
 }
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index f41a6f57cd12..82dfe5d0c41e 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -18,16 +18,34 @@
 #define __ASMARM_TLB_H
 
 #include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
 
 #ifndef CONFIG_MMU
 
 #include <linux/pagemap.h>
+
+#define tlb_flush(tlb)	((void) tlb)
+
 #include <asm-generic/tlb.h>
 
 #else /* !CONFIG_MMU */
 
+#include <linux/swap.h>
 #include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+
+/*
+ * We need to delay page freeing for SMP as other CPUs can access pages
+ * which have been removed but not yet had their TLB entries invalidated.
+ * Also, as ARMv7 speculative prefetch can drag new entries into the TLB,
+ * we need to apply this same delaying tactic to ensure correct operation.
+ */
+#if defined(CONFIG_SMP) || defined(CONFIG_CPU_32v7)
+#define tlb_fast_mode(tlb)	0
+#define FREE_PTE_NR		500
+#else
+#define tlb_fast_mode(tlb)	1
+#define FREE_PTE_NR		0
+#endif
 
 /*
  * TLB handling.  This allows us to remove pages from the page
@@ -36,12 +54,58 @@
 struct mmu_gather {
 	struct mm_struct	*mm;
 	unsigned int		fullmm;
+	struct vm_area_struct	*vma;
 	unsigned long		range_start;
 	unsigned long		range_end;
+	unsigned int		nr;
+	struct page		*pages[FREE_PTE_NR];
 };
 
 DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
 
+/*
+ * This is unnecessarily complex.  There's three ways the TLB shootdown
+ * code is used:
+ *  1. Unmapping a range of vmas.  See zap_page_range(), unmap_region().
+ *     tlb->fullmm = 0, and tlb_start_vma/tlb_end_vma will be called.
+ *     tlb->vma will be non-NULL.
+ *  2. Unmapping all vmas.  See exit_mmap().
+ *     tlb->fullmm = 1, and tlb_start_vma/tlb_end_vma will be called.
+ *     tlb->vma will be non-NULL.  Additionally, page tables will be freed.
+ *  3. Unmapping argument pages.  See shift_arg_pages().
+ *     tlb->fullmm = 0, but tlb_start_vma/tlb_end_vma will not be called.
+ *     tlb->vma will be NULL.
+ */
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+	if (tlb->fullmm || !tlb->vma)
+		flush_tlb_mm(tlb->mm);
+	else if (tlb->range_end > 0) {
+		flush_tlb_range(tlb->vma, tlb->range_start, tlb->range_end);
+		tlb->range_start = TASK_SIZE;
+		tlb->range_end = 0;
+	}
+}
+
+static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr)
+{
+	if (!tlb->fullmm) {
+		if (addr < tlb->range_start)
+			tlb->range_start = addr;
+		if (addr + PAGE_SIZE > tlb->range_end)
+			tlb->range_end = addr + PAGE_SIZE;
+	}
+}
+
+static inline void tlb_flush_mmu(struct mmu_gather *tlb)
+{
+	tlb_flush(tlb);
+	if (!tlb_fast_mode(tlb)) {
+		free_pages_and_swap_cache(tlb->pages, tlb->nr);
+		tlb->nr = 0;
+	}
+}
+
 static inline struct mmu_gather *
 tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
 {
@@ -49,6 +113,8 @@ tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
 
 	tlb->mm = mm;
 	tlb->fullmm = full_mm_flush;
+	tlb->vma = NULL;
+	tlb->nr = 0;
 
 	return tlb;
 }
@@ -56,8 +122,7 @@ tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
 static inline void
 tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
 {
-	if (tlb->fullmm)
-		flush_tlb_mm(tlb->mm);
+	tlb_flush_mmu(tlb);
 
 	/* keep the page table cache within bounds */
 	check_pgt_cache();
@@ -71,12 +136,7 @@ tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
 static inline void
 tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long addr)
 {
-	if (!tlb->fullmm) {
-		if (addr < tlb->range_start)
-			tlb->range_start = addr;
-		if (addr + PAGE_SIZE > tlb->range_end)
-			tlb->range_end = addr + PAGE_SIZE;
-	}
+	tlb_add_flush(tlb, addr);
 }
 
 /*
@@ -89,6 +149,7 @@ tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
 {
 	if (!tlb->fullmm) {
 		flush_cache_range(vma, vma->vm_start, vma->vm_end);
+		tlb->vma = vma;
 		tlb->range_start = TASK_SIZE;
 		tlb->range_end = 0;
 	}
@@ -97,12 +158,30 @@ tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
 static inline void
 tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
 {
-	if (!tlb->fullmm && tlb->range_end > 0)
-		flush_tlb_range(vma, tlb->range_start, tlb->range_end);
+	if (!tlb->fullmm)
+		tlb_flush(tlb);
+}
+
+static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+	if (tlb_fast_mode(tlb)) {
+		free_page_and_swap_cache(page);
+	} else {
+		tlb->pages[tlb->nr++] = page;
+		if (tlb->nr >= FREE_PTE_NR)
+			tlb_flush_mmu(tlb);
+	}
+}
+
+static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
+	unsigned long addr)
+{
+	pgtable_page_dtor(pte);
+	tlb_add_flush(tlb, addr);
+	tlb_remove_page(tlb, pte);
 }
 
-#define tlb_remove_page(tlb,page)	free_page_and_swap_cache(page)
-#define pte_free_tlb(tlb, ptep, addr)	pte_free((tlb)->mm, ptep)
+#define pte_free_tlb(tlb, ptep, addr)	__pte_free_tlb(tlb, ptep, addr)
 #define pmd_free_tlb(tlb, pmdp, addr)	pmd_free((tlb)->mm, pmdp)
 
 #define tlb_migrate_finish(mm)		do { } while (0)
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index ce7378ea15a2..d2005de383b8 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -10,12 +10,7 @@
 #ifndef _ASMARM_TLBFLUSH_H
 #define _ASMARM_TLBFLUSH_H
 
-
-#ifndef CONFIG_MMU
-
-#define tlb_flush(tlb)	((void) tlb)
-
-#else /* CONFIG_MMU */
+#ifdef CONFIG_MMU
 
 #include <asm/glue.h>