Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm changes from Ingo Molnar:
 "This tree includes a micro-optimization that avoids cr3 switches
  during idling; it fixes corner cases and there's also small cleanups"

Fix up trivial context conflict with the percpu_xx -> this_cpu_xx
changes.

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86-64: Fix accounting in kernel_physical_mapping_init()
  x86/tlb: Clean up and unify TLB_FLUSH_ALL definition
  x86: Drop obsolete ARCH_BOOTMEM support
  x86, tlb: Switch cr3 in leave_mm() only when needed
  x86/mm: Fix the size calculation of mapping tables

3 files changed, 30 insertions, 22 deletions

diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 4f0cec7e4ffb..319b6f2fb8b9 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -29,8 +29,14 @@ int direct_gbpages
 #endif
 ;
 
-static void __init find_early_table_space(unsigned long end, int use_pse,
-                                          int use_gbpages)
+struct map_range {
+        unsigned long start;
+        unsigned long end;
+        unsigned page_size_mask;
+};
+
+static void __init find_early_table_space(struct map_range *mr, unsigned long end,
+                                          int use_pse, int use_gbpages)
 {
         unsigned long puds, pmds, ptes, tables, start = 0, good_end = end;
         phys_addr_t base;
@@ -55,6 +61,9 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
 #ifdef CONFIG_X86_32
                 extra += PMD_SIZE;
 #endif
+                /* The first 2/4M doesn't use large pages. */
+                extra += mr->end - mr->start;
+
                 ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
         } else
                 ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
@@ -84,12 +93,6 @@ void __init native_pagetable_reserve(u64 start, u64 end)
         memblock_reserve(start, end - start);
 }
 
-struct map_range {
-        unsigned long start;
-        unsigned long end;
-        unsigned page_size_mask;
-};
-
 #ifdef CONFIG_X86_32
 #define NR_RANGE_MR 3
 #else /* CONFIG_X86_64 */
@@ -261,7 +264,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
          * nodes are discovered.
          */
         if (!after_bootmem)
-                find_early_table_space(end, use_pse, use_gbpages);
+                find_early_table_space(&mr[0], end, use_pse, use_gbpages);
 
         for (i = 0; i < nr_range; i++)
                 ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index fc18be0f6f29..2b6b4a3c8beb 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -407,12 +407,12 @@ static unsigned long __meminit
 phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
               unsigned long page_size_mask, pgprot_t prot)
 {
-        unsigned long pages = 0;
+        unsigned long pages = 0, next;
         unsigned long last_map_addr = end;
 
         int i = pmd_index(address);
 
-        for (; i < PTRS_PER_PMD; i++, address += PMD_SIZE) {
+        for (; i < PTRS_PER_PMD; i++, address = next) {
                 unsigned long pte_phys;
                 pmd_t *pmd = pmd_page + pmd_index(address);
                 pte_t *pte;
@@ -426,6 +426,8 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
                         break;
                 }
 
+                next = (address & PMD_MASK) + PMD_SIZE;
+
                 if (pmd_val(*pmd)) {
                         if (!pmd_large(*pmd)) {
                                 spin_lock(&init_mm.page_table_lock);
@@ -449,7 +451,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
                          * attributes.
                          */
                         if (page_size_mask & (1 << PG_LEVEL_2M)) {
-                                pages++;
+                                last_map_addr = next;
                                 continue;
                         }
                         new_prot = pte_pgprot(pte_clrhuge(*(pte_t *)pmd));
@@ -462,7 +464,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
                                 pfn_pte(address >> PAGE_SHIFT,
                                         __pgprot(pgprot_val(prot) | _PAGE_PSE)));
                         spin_unlock(&init_mm.page_table_lock);
-                        last_map_addr = (address & PMD_MASK) + PMD_SIZE;
+                        last_map_addr = next;
                         continue;
                 }
 
@@ -482,11 +484,11 @@ static unsigned long __meminit
 phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
                          unsigned long page_size_mask)
 {
-        unsigned long pages = 0;
+        unsigned long pages = 0, next;
         unsigned long last_map_addr = end;
         int i = pud_index(addr);
 
-        for (; i < PTRS_PER_PUD; i++, addr = (addr & PUD_MASK) + PUD_SIZE) {
+        for (; i < PTRS_PER_PUD; i++, addr = next) {
                 unsigned long pmd_phys;
                 pud_t *pud = pud_page + pud_index(addr);
                 pmd_t *pmd;
@@ -495,8 +497,9 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
                 if (addr >= end)
                         break;
 
-                if (!after_bootmem &&
-                                !e820_any_mapped(addr, addr+PUD_SIZE, 0)) {
+                next = (addr & PUD_MASK) + PUD_SIZE;
+
+                if (!after_bootmem && !e820_any_mapped(addr, next, 0)) {
                         set_pud(pud, __pud(0));
                         continue;
                 }
@@ -523,7 +526,7 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
                          * attributes.
                          */
                         if (page_size_mask & (1 << PG_LEVEL_1G)) {
-                                pages++;
+                                last_map_addr = next;
                                 continue;
                         }
                         prot = pte_pgprot(pte_clrhuge(*(pte_t *)pud));
@@ -535,7 +538,7 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
                         set_pte((pte_t *)pud,
                                 pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
                         spin_unlock(&init_mm.page_table_lock);
-                        last_map_addr = (addr & PUD_MASK) + PUD_SIZE;
+                        last_map_addr = next;
                         continue;
                 }
 
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 3804471db104..5e57e113b72c 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -61,11 +61,13 @@ static DEFINE_PER_CPU_READ_MOSTLY(int, tlb_vector_offset);
  */
 void leave_mm(int cpu)
 {
+        struct mm_struct *active_mm = this_cpu_read(cpu_tlbstate.active_mm);
         if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
                 BUG();
-        cpumask_clear_cpu(cpu,
-                          mm_cpumask(this_cpu_read(cpu_tlbstate.active_mm)));
-        load_cr3(swapper_pg_dir);
+        if (cpumask_test_cpu(cpu, mm_cpumask(active_mm))) {
+                cpumask_clear_cpu(cpu, mm_cpumask(active_mm));
+                load_cr3(swapper_pg_dir);
+        }
 }
 EXPORT_SYMBOL_GPL(leave_mm);