[PATCH] /proc/<pid>/numa_maps to show on which nodes pages reside

[linux-2.6] / fs / proc / task_mmu.c

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 28b4a0253a92161fff797dcfae5f79585fafd022..64e84cadfa3c135ce3b26887d095405033b75288 100644 (file)
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -2,6 +2,8 @@
 #include <linux/hugetlb.h>
 #include <linux/mount.h>
 #include <linux/seq_file.h>
+#include <linux/pagemap.h>
+#include <linux/mempolicy.h>
 #include <asm/elf.h>
 #include <asm/uaccess.h>
 #include "internal.h"
@@ -233,3 +235,133 @@ struct seq_operations proc_pid_maps_op = {
        .stop   = m_stop,
        .show   = show_map
 };
+
+#ifdef CONFIG_NUMA
+
+struct numa_maps {
+       unsigned long pages;
+       unsigned long anon;
+       unsigned long mapped;
+       unsigned long mapcount_max;
+       unsigned long node[MAX_NUMNODES];
+};
+
+/*
+ * Calculate numa node maps for a vma
+ */
+static struct numa_maps *get_numa_maps(const struct vm_area_struct *vma)
+{
+       struct page *page;
+       unsigned long vaddr;
+       struct mm_struct *mm = vma->vm_mm;
+       int i;
+       struct numa_maps *md = kmalloc(sizeof(struct numa_maps), GFP_KERNEL);
+
+       if (!md)
+               return NULL;
+       md->pages = 0;
+       md->anon = 0;
+       md->mapped = 0;
+       md->mapcount_max = 0;
+       for_each_node(i)
+               md->node[i] =0;
+
+       spin_lock(&mm->page_table_lock);
+       for (vaddr = vma->vm_start; vaddr < vma->vm_end; vaddr += PAGE_SIZE) {
+               page = follow_page(mm, vaddr, 0);
+               if (page) {
+                       int count = page_mapcount(page);
+
+                       if (count)
+                               md->mapped++;
+                       if (count > md->mapcount_max)
+                               md->mapcount_max = count;
+                       md->pages++;
+                       if (PageAnon(page))
+                               md->anon++;
+                       md->node[page_to_nid(page)]++;
+               }
+       }
+       spin_unlock(&mm->page_table_lock);
+       return md;
+}
+
+static int show_numa_map(struct seq_file *m, void *v)
+{
+       struct task_struct *task = m->private;
+       struct vm_area_struct *vma = v;
+       struct mempolicy *pol;
+       struct numa_maps *md;
+       struct zone **z;
+       int n;
+       int first;
+
+       if (!vma->vm_mm)
+               return 0;
+
+       md = get_numa_maps(vma);
+       if (!md)
+               return 0;
+
+       seq_printf(m, "%08lx", vma->vm_start);
+       pol = get_vma_policy(task, vma, vma->vm_start);
+       /* Print policy */
+       switch (pol->policy) {
+       case MPOL_PREFERRED:
+               seq_printf(m, " prefer=%d", pol->v.preferred_node);
+               break;
+       case MPOL_BIND:
+               seq_printf(m, " bind={");
+               first = 1;
+               for (z = pol->v.zonelist->zones; *z; z++) {
+
+                       if (!first)
+                               seq_putc(m, ',');
+                       else
+                               first = 0;
+                       seq_printf(m, "%d/%s", (*z)->zone_pgdat->node_id,
+                                       (*z)->name);
+               }
+               seq_putc(m, '}');
+               break;
+       case MPOL_INTERLEAVE:
+               seq_printf(m, " interleave={");
+               first = 1;
+               for_each_node(n) {
+                       if (test_bit(n, pol->v.nodes)) {
+                               if (!first)
+                                       seq_putc(m,',');
+                               else
+                                       first = 0;
+                               seq_printf(m, "%d",n);
+                       }
+               }
+               seq_putc(m, '}');
+               break;
+       default:
+               seq_printf(m," default");
+               break;
+       }
+       seq_printf(m, " MaxRef=%lu Pages=%lu Mapped=%lu",
+                       md->mapcount_max, md->pages, md->mapped);
+       if (md->anon)
+               seq_printf(m," Anon=%lu",md->anon);
+
+       for_each_online_node(n) {
+               if (md->node[n])
+                       seq_printf(m, " N%d=%lu", n, md->node[n]);
+       }
+       seq_putc(m, '\n');
+       kfree(md);
+       if (m->count < m->size)  /* vma is copied successfully */
+               m->version = (vma != get_gate_vma(task)) ? vma->vm_start : 0;
+       return 0;
+}
+
+struct seq_operations proc_pid_numa_maps_op = {
+       .start  = m_start,
+       .next   = m_next,
+       .stop   = m_stop,
+       .show   = show_numa_map
+};
+#endif