/proc/kpageflags: do not use uninitialized struct pages

A kernel panic was observed during reading /proc/kpageflags for first few
pfns allocated by pmem namespace:

BUG: unable to handle page fault for address: fffffffffffffffe
[  114.495280] #PF: supervisor read access in kernel mode
[  114.495738] #PF: error_code(0x0000) - not-present page
[  114.496203] PGD 17120e067 P4D 17120e067 PUD 171210067 PMD 0
[  114.496713] Oops: 0000 [#1] SMP PTI
[  114.497037] CPU: 9 PID: 1202 Comm: page-types Not tainted 5.3.0-rc1 #1
[  114.497621] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.0-0-g63451fca13-prebuilt.qemu-project.org 04/01/2014
[  114.498706] RIP: 0010:stable_page_flags+0x27/0x3f0
[  114.499142] Code: 82 66 90 66 66 66 66 90 48 85 ff 0f 84 d1 03 00 00 41 54 55 48 89 fd 53 48 8b 57 08 48 8b 1f 48 8d 42 ff 83 e2 01 48 0f 44 c7 <48> 8b 00 f6 c4 02 0f 84 57 03 00 00 45 31 e4 48 8b 55 08 48 89 ef
[  114.500788] RSP: 0018:ffffa5e601a0fe60 EFLAGS: 00010202
[  114.501373] RAX: fffffffffffffffe RBX: ffffffffffffffff RCX: 0000000000000000
[  114.502009] RDX: 0000000000000001 RSI: 00007ffca13a7310 RDI: ffffd07489000000
[  114.502637] RBP: ffffd07489000000 R08: 0000000000000001 R09: 0000000000000000
[  114.503270] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000240000
[  114.503896] R13: 0000000000080000 R14: 00007ffca13a7310 R15: ffffa5e601a0ff08
[  114.504530] FS:  00007f0266c7f540(0000) GS:ffff962dbbac0000(0000) knlGS:0000000000000000
[  114.505245] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  114.505754] CR2: fffffffffffffffe CR3: 000000023a204000 CR4: 00000000000006e0
[  114.506401] Call Trace:
[  114.506660]  kpageflags_read+0xb1/0x130
[  114.507051]  proc_reg_read+0x39/0x60
[  114.507387]  vfs_read+0x8a/0x140
[  114.507686]  ksys_pread64+0x61/0xa0
[  114.508021]  do_syscall_64+0x5f/0x1a0
[  114.508372]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[  114.508844] RIP: 0033:0x7f0266ba426b

The reason for the panic is that stable_page_flags() which parses the page
flags uses uninitialized struct pages reserved by the ZONE_DEVICE driver.

Earlier approach to fix this was discussed here:
https://marc.info/?l=linux-mm&m=152964770000672&w=2

This is another approach.  To avoid using the uninitialized struct page,
immediately return with KPF_RESERVED at the beginning of
stable_page_flags() if the page is reserved by ZONE_DEVICE driver.

Dan said:

: The nvdimm implementation uses vmem_altmap to arrange for the 'struct
: page' array to be allocated from a reservation of a pmem namespace.  A
: namespace in this mode contains an info-block that consumes the first
: 8K of the namespace capacity, capacity designated for page mapping,
: capacity for padding the start of data to optionally 4K, 2MB, or 1GB
: (on x86), and then the namespace data itself.  The implementation
: specifies a section aligned (now sub-section aligned) address to
: arch_add_memory() to establish the linear mapping to map the metadata,
: and then vmem_altmap indicates to memmap_init_zone() which pfns
: represent data.  The implementation only specifies enough 'struct page'
: capacity for pfn_to_page() to operate on the data space, not the
: namespace metadata space.
:
: The proposal to validate ZONE_DEVICE pfns against the altmap seems the
: right approach to me.

Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Toshiki Fukasawa <[email protected]>
Cc: Alexey Dobriyan <[email protected]>
Cc: Christoph Hellwig <[email protected]>
Cc: Dan Williams <[email protected]>
Cc: Junichi Nomura <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Naoya Horiguchi <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Stephen Rothwell <[email protected]>

fs/proc/page.c

@@ -117,6 +117,9 @@ u64 stable_page_flags(struct page *page)
 	if (!page)
 		return BIT_ULL(KPF_NOPAGE);
 
+	if (pfn_zone_device_reserved(page_to_pfn(page)))
+		return BIT_ULL(KPF_RESERVED);
+
 	k = page->flags;
 	u = 0;
 

include/linux/memremap.h

@@ -130,6 +130,7 @@ static inline unsigned long pgmap_vmemmap_nr(struct dev_pagemap *pgmap)
 }
 
 #ifdef CONFIG_ZONE_DEVICE
+bool pfn_zone_device_reserved(unsigned long pfn);
 void *memremap_pages(struct dev_pagemap *pgmap, int nid);
 void memunmap_pages(struct dev_pagemap *pgmap);
 void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap);
@@ -142,6 +143,11 @@ unsigned long vmem_altmap_offset(struct vmem_altmap *altmap);
 void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns);
 unsigned long memremap_compat_align(void);
 #else
+static inline bool pfn_zone_device_reserved(unsigned long pfn)
+{
+	return false;
+}
+
 static inline void *devm_memremap_pages(struct device *dev,
 		struct dev_pagemap *pgmap)
 {

mm/memremap.c

@@ -115,6 +115,26 @@ static unsigned long pfn_len(struct dev_pagemap *pgmap, unsigned long range_id)
 		pfn_first(pgmap, range_id)) >> pgmap->vmemmap_shift;
 }
 
+/*
+ * This returns true if the page is reserved by ZONE_DEVICE driver.
+ */
+bool pfn_zone_device_reserved(unsigned long pfn)
+{
+	struct dev_pagemap *pgmap;
+	struct vmem_altmap *altmap;
+	bool ret = false;
+
+	pgmap = get_dev_pagemap(pfn, NULL);
+	if (!pgmap)
+		return ret;
+	altmap = pgmap_altmap(pgmap);
+	if (altmap && pfn < (altmap->base_pfn + altmap->reserve))
+		ret = true;
+	put_dev_pagemap(pgmap);
+
+	return ret;
+}
+
 #define for_each_device_pfn(pfn, map, i) \
 	for (pfn = pfn_first(map, i); pfn < pfn_end(map, i); \
 	     pfn = pfn_next(map, pfn))