maps4: add /proc/kpageflags interface

This makes a subset of physical page flags available to userspace. Together
with /proc/pid/kpagemap, this allows tracking of a wide variety of VM behaviors.

Exported flags are decoupled from the kernel's internal flags. This
allows us to reorder flag bits, and synthesize any bits that get
redefined in terms of other bits.

[akpm@linux-foundation.org: remove unneeded access_ok()]
[akpm@linux-foundation.org: s/0/NULL/]
Signed-off-by: Matt Mackall <mpm@selenic.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 83 insertions, 1 deletions

diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 19b69f931bef..fd751ea37fce 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -699,7 +699,10 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf,
                 return -EIO;
 
         while (count > 0) {
-                ppage = pfn_to_page(pfn++);
+                ppage = NULL;
+                if (pfn_valid(pfn))
+                        ppage = pfn_to_page(pfn);
+                pfn++;
                 if (!ppage)
                         pcount = 0;
                 else
@@ -724,6 +727,84 @@ static struct file_operations proc_kpagecount_operations = {
         .read = kpagecount_read,
 };
 
+/* /proc/kpageflags - an array exposing page flags
+ *
+ * Each entry is a u64 representing the corresponding
+ * physical page flags.
+ */
+
+/* These macros are used to decouple internal flags from exported ones */
+
+#define KPF_LOCKED     0
+#define KPF_ERROR      1
+#define KPF_REFERENCED 2
+#define KPF_UPTODATE   3
+#define KPF_DIRTY      4
+#define KPF_LRU        5
+#define KPF_ACTIVE     6
+#define KPF_SLAB       7
+#define KPF_WRITEBACK  8
+#define KPF_RECLAIM    9
+#define KPF_BUDDY     10
+
+#define kpf_copy_bit(flags, srcpos, dstpos) (((flags >> srcpos) & 1) << dstpos)
+
+static ssize_t kpageflags_read(struct file *file, char __user *buf,
+                             size_t count, loff_t *ppos)
+{
+        u64 __user *out = (u64 __user *)buf;
+        struct page *ppage;
+        unsigned long src = *ppos;
+        unsigned long pfn;
+        ssize_t ret = 0;
+        u64 kflags, uflags;
+
+        pfn = src / KPMSIZE;
+        count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
+        if (src & KPMMASK || count & KPMMASK)
+                return -EIO;
+
+        while (count > 0) {
+                ppage = NULL;
+                if (pfn_valid(pfn))
+                        ppage = pfn_to_page(pfn);
+                pfn++;
+                if (!ppage)
+                        kflags = 0;
+                else
+                        kflags = ppage->flags;
+
+                uflags = kpf_copy_bit(KPF_LOCKED, PG_locked, kflags) |
+                        kpf_copy_bit(kflags, KPF_ERROR, PG_error) |
+                        kpf_copy_bit(kflags, KPF_REFERENCED, PG_referenced) |
+                        kpf_copy_bit(kflags, KPF_UPTODATE, PG_uptodate) |
+                        kpf_copy_bit(kflags, KPF_DIRTY, PG_dirty) |
+                        kpf_copy_bit(kflags, KPF_LRU, PG_lru) |
+                        kpf_copy_bit(kflags, KPF_ACTIVE, PG_active) |
+                        kpf_copy_bit(kflags, KPF_SLAB, PG_slab) |
+                        kpf_copy_bit(kflags, KPF_WRITEBACK, PG_writeback) |
+                        kpf_copy_bit(kflags, KPF_RECLAIM, PG_reclaim) |
+                        kpf_copy_bit(kflags, KPF_BUDDY, PG_buddy);
+
+                if (put_user(uflags, out++)) {
+                        ret = -EFAULT;
+                        break;
+                }
+
+                count -= KPMSIZE;
+        }
+
+        *ppos += (char __user *)out - buf;
+        if (!ret)
+                ret = (char __user *)out - buf;
+        return ret;
+}
+
+static struct file_operations proc_kpageflags_operations = {
+        .llseek = mem_lseek,
+        .read = kpageflags_read,
+};
+
 struct proc_dir_entry *proc_root_kcore;
 
 void create_seq_entry(char *name, mode_t mode, const struct file_operations *f)
@@ -805,6 +886,7 @@ void __init proc_misc_init(void)
         }
 #endif
         create_seq_entry("kpagecount", S_IRUSR, &proc_kpagecount_operations);
+        create_seq_entry("kpageflags", S_IRUSR, &proc_kpageflags_operations);
 #ifdef CONFIG_PROC_VMCORE
         proc_vmcore = create_proc_entry("vmcore", S_IRUSR, NULL);
         if (proc_vmcore)