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

Pull x86 fixes from Peter Anvin:
 "Quite a varied little collection of fixes.  Most of them are
  relatively small or isolated; the biggest one is Mel Gorman's fixes
  for TLB range flushing.

  A couple of AMD-related fixes (including not crashing when given an
  invalid microcode image) and fix a crash when compiled with gcov"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86, microcode, AMD: Unify valid container checks
  x86, hweight: Fix BUG when booting with CONFIG_GCOV_PROFILE_ALL=y
  x86/efi: Allow mapping BGRT on x86-32
  x86: Fix the initialization of physnode_map
  x86, cpu hotplug: Fix stack frame warning in check_irq_vectors_for_cpu_disable()
  x86/intel/mid: Fix X86_INTEL_MID dependencies
  arch/x86/mm/srat: Skip NUMA_NO_NODE while parsing SLIT
  mm, x86: Revisit tlb_flushall_shift tuning for page flushes except on IvyBridge
  x86: mm: change tlb_flushall_shift for IvyBridge
  x86/mm: Eliminate redundant page table walk during TLB range flushing
  x86/mm: Clean up inconsistencies when flushing TLB ranges
  mm, x86: Account for TLB flushes only when debugging
  x86/AMD/NB: Fix amd_set_subcaches() parameter type
  x86/quirks: Add workaround for AMD F16h Erratum792
  x86, doc, kconfig: Fix dud URL for Microcode data

3 files changed, 28 insertions, 42 deletions

diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 0342d27ca798..47b6436e41c2 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -52,6 +52,8 @@ void memory_present(int nid, unsigned long start, unsigned long end)
                         nid, start, end);
         printk(KERN_DEBUG "  Setting physnode_map array to node %d for pfns:\n", nid);
         printk(KERN_DEBUG "  ");
+        start = round_down(start, PAGES_PER_SECTION);
+        end = round_up(end, PAGES_PER_SECTION);
         for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) {
                 physnode_map[pfn / PAGES_PER_SECTION] = nid;
                 printk(KERN_CONT "%lx ", pfn);
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 1a25187e151e..1953e9c9391a 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -42,15 +42,25 @@ static __init inline int srat_disabled(void)
         return acpi_numa < 0;
 }
 
-/* Callback for SLIT parsing */
+/*
+ * Callback for SLIT parsing.  pxm_to_node() returns NUMA_NO_NODE for
+ * I/O localities since SRAT does not list them.  I/O localities are
+ * not supported at this point.
+ */
 void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
 {
         int i, j;
 
-        for (i = 0; i < slit->locality_count; i++)
-                for (j = 0; j < slit->locality_count; j++)
+        for (i = 0; i < slit->locality_count; i++) {
+                if (pxm_to_node(i) == NUMA_NO_NODE)
+                        continue;
+                for (j = 0; j < slit->locality_count; j++) {
+                        if (pxm_to_node(j) == NUMA_NO_NODE)
+                                continue;
                         numa_set_distance(pxm_to_node(i), pxm_to_node(j),
                                 slit->entry[slit->locality_count * i + j]);
+                }
+        }
 }
 
 /* Callback for Proximity Domain -> x2APIC mapping */
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index ae699b3bbac8..dd8dda167a24 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -103,7 +103,7 @@ static void flush_tlb_func(void *info)
         if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
                 return;
 
-        count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+        count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
         if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
                 if (f->flush_end == TLB_FLUSH_ALL)
                         local_flush_tlb();
@@ -131,7 +131,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
         info.flush_start = start;
         info.flush_end = end;
 
-        count_vm_event(NR_TLB_REMOTE_FLUSH);
+        count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
         if (is_uv_system()) {
                 unsigned int cpu;
 
@@ -151,44 +151,19 @@ void flush_tlb_current_task(void)
 
         preempt_disable();
 
-        count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+        count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
         local_flush_tlb();
         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();
 }
 
-/*
- * 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)
-{
-        pgd_t *pgd;
-        pud_t *pud;
-        pmd_t *pmd;
-        unsigned long addr = ALIGN(start, HPAGE_SIZE);
-        for (; addr < end; addr += HPAGE_SIZE) {
-                pgd = pgd_offset(mm, addr);
-                if (likely(!pgd_none(*pgd))) {
-                        pud = pud_offset(pgd, addr);
-                        if (likely(!pud_none(*pud))) {
-                                pmd = pmd_offset(pud, addr);
-                                if (likely(!pmd_none(*pmd)))
-                                        if (pmd_large(*pmd))
-                                                return addr;
-                        }
-                }
-        }
-        return 0;
-}
-
 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;
+        unsigned long nr_base_pages;
 
         preempt_disable();
         if (current->active_mm != mm)
@@ -210,21 +185,20 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
                 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;
+        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 ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) {
-                count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+        if (nr_base_pages > act_entries) {
+                count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
                 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) {
-                        count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
+                        count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
                         __flush_tlb_single(addr);
                 }
 
@@ -262,7 +236,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
 
 static void do_flush_tlb_all(void *info)
 {
-        count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+        count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
         __flush_tlb_all();
         if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
                 leave_mm(smp_processor_id());
@@ -270,7 +244,7 @@ static void do_flush_tlb_all(void *info)
 
 void flush_tlb_all(void)
 {
-        count_vm_event(NR_TLB_REMOTE_FLUSH);
+        count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
         on_each_cpu(do_flush_tlb_all, NULL, 1);
 }