fs/proc/page.c: allow inspection of last section and fix end detection

If max_pfn does not fall onto a section boundary, it is possible to
inspect PFNs up to max_pfn, and PFNs above max_pfn, however, max_pfn
itself can't be inspected.  We can have a valid (and online) memmap at and
above max_pfn if max_pfn is not aligned to a section boundary.  The whole
early section has a memmap and is marked online.  Being able to inspect
the state of these PFNs is valuable for debugging, especially because
max_pfn can change on memory hotplug and expose these memmaps.

Also, querying page flags via "./page-types -r -a 0x144001,"
(tools/vm/page-types.c) inside a x86-64 guest with 4160MB under QEMU
results in an (almost) endless loop in user space, because the end is not
detected properly when starting after max_pfn.

Instead, let's allow to inspect all pages in the highest section and
return 0 directly if we try to access pages above that section.

While at it, check the count before adjusting it, to avoid masking user
errors.

Link: http://lkml.kernel.org/r/20191211163201.17179-3-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Bob Picco <bob.picco@oracle.com>
Cc: Daniel Jordan <daniel.m.jordan@oracle.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Pavel Tatashin <pasha.tatashin@oracle.com>
Cc: Steven Sistare <steven.sistare@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/proc/page.c b/fs/proc/page.c
index 7c952ee732e63dffd0ae09f92a6ec3e6c57e5771..7a84f6fcfa681669eff5aea0952bb947f1660778 100644 (file)
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -21,6 +21,21 @@
 #define KPMMASK (KPMSIZE - 1)
 #define KPMBITS (KPMSIZE * BITS_PER_BYTE)
 
+static inline unsigned long get_max_dump_pfn(void)
+{
+#ifdef CONFIG_SPARSEMEM
+       /*
+        * The memmap of early sections is completely populated and marked
+        * online even if max_pfn does not fall on a section boundary -
+        * pfn_to_online_page() will succeed on all pages. Allow inspecting
+        * these memmaps.
+        */
+       return round_up(max_pfn, PAGES_PER_SECTION);
+#else
+       return max_pfn;
+#endif
+}
+
 /* /proc/kpagecount - an array exposing page counts
  *
  * Each entry is a u64 representing the corresponding
@@ -29,6 +44,7 @@
 static ssize_t kpagecount_read(struct file *file, char __user *buf,
                             size_t count, loff_t *ppos)
 {
+       const unsigned long max_dump_pfn = get_max_dump_pfn();
        u64 __user *out = (u64 __user *)buf;
        struct page *ppage;
        unsigned long src = *ppos;
@@ -37,9 +53,11 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf,
        u64 pcount;
 
        pfn = src / KPMSIZE;
-       count = min_t(size_t, count, (max_pfn * KPMSIZE) - src);
        if (src & KPMMASK || count & KPMMASK)
                return -EINVAL;
+       if (src >= max_dump_pfn * KPMSIZE)
+               return 0;
+       count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src);
 
        while (count > 0) {
                /*
@@ -206,6 +224,7 @@ u64 stable_page_flags(struct page *page)
 static ssize_t kpageflags_read(struct file *file, char __user *buf,
                             size_t count, loff_t *ppos)
 {
+       const unsigned long max_dump_pfn = get_max_dump_pfn();
        u64 __user *out = (u64 __user *)buf;
        struct page *ppage;
        unsigned long src = *ppos;
@@ -213,9 +232,11 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf,
        ssize_t ret = 0;
 
        pfn = src / KPMSIZE;
-       count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
        if (src & KPMMASK || count & KPMMASK)
                return -EINVAL;
+       if (src >= max_dump_pfn * KPMSIZE)
+               return 0;
+       count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src);
 
        while (count > 0) {
                /*
@@ -251,6 +272,7 @@ static const struct file_operations proc_kpageflags_operations = {
 static ssize_t kpagecgroup_read(struct file *file, char __user *buf,
                                size_t count, loff_t *ppos)
 {
+       const unsigned long max_dump_pfn = get_max_dump_pfn();
        u64 __user *out = (u64 __user *)buf;
        struct page *ppage;
        unsigned long src = *ppos;
@@ -259,9 +281,11 @@ static ssize_t kpagecgroup_read(struct file *file, char __user *buf,
        u64 ino;
 
        pfn = src / KPMSIZE;
-       count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
        if (src & KPMMASK || count & KPMMASK)
                return -EINVAL;
+       if (src >= max_dump_pfn * KPMSIZE)
+               return 0;
+       count = min_t(unsigned long, count, (max_dump_pfn * KPMSIZE) - src);
 
        while (count > 0) {
                /*