H_PAGE_THP_HUGE is used to differentiate between a THP hugepage and
hugetlb hugepage entries. The difference is WRT how we handle hash
fault on these address. THP address enables MPSS in segments. We want
to manage devmap hugepage entries similar to THP pt entries. Hence use
H_PAGE_THP_HUGE for devmap huge PTE entries.
With current code while handling hash PTE fault, we do set is_thp =
true when finding devmap PTE huge PTE entries.
Current code also does the below sequence we setting up huge devmap
entries.
entry = pmd_mkhuge(pfn_t_pmd(pfn, prot));
if (pfn_t_devmap(pfn))
entry = pmd_mkdevmap(entry);
In that case we would find both H_PAGE_THP_HUGE and PAGE_DEVMAP set
for huge devmap PTE entries. This results in false positive error like
below.
kernel BUG at /home/kvaneesh/src/linux/mm/memory.c:4321!
Oops: Exception in kernel mode, sig: 5 [#1]
LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
Modules linked in:
CPU: 56 PID: 67996 Comm: t_mmap_dio Not tainted 5.6.0-rc4-59640-g371c804dedbc #128
....
NIP [
c00000000044c9e4] __follow_pte_pmd+0x264/0x900
LR [
c0000000005d45f8] dax_writeback_one+0x1a8/0x740
Call Trace:
str_spec.74809+0x22ffb4/0x2d116c (unreliable)
dax_writeback_one+0x1a8/0x740
dax_writeback_mapping_range+0x26c/0x700
ext4_dax_writepages+0x150/0x5a0
do_writepages+0x68/0x180
__filemap_fdatawrite_range+0x138/0x180
file_write_and_wait_range+0xa4/0x110
ext4_sync_file+0x370/0x6e0
vfs_fsync_range+0x70/0xf0
sys_msync+0x220/0x2e0
system_call+0x5c/0x68
This is because our pmd_trans_huge check doesn't exclude _PAGE_DEVMAP.
To make this all consistent, update pmd_mkdevmap to set
H_PAGE_THP_HUGE and pmd_trans_huge check now excludes _PAGE_DEVMAP
correctly.
Fixes:
ebd31197931d ("powerpc/mm: Add devmap support for ppc64")
Cc: stable@vger.kernel.org # v4.13+
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200313094842.351830-1-aneesh.kumar@linux.ibm.com
extern int hash__has_transparent_hugepage(void);
#endif
+static inline pmd_t hash__pmd_mkdevmap(pmd_t pmd)
+{
+ BUG();
+ return pmd;
+}
+
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_POWERPC_BOOK3S_64_HASH_4K_H */
*/
static inline int hash__pmd_trans_huge(pmd_t pmd)
{
- return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE)) ==
+ return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE | _PAGE_DEVMAP)) ==
(_PAGE_PTE | H_PAGE_THP_HUGE));
}
unsigned long addr, pmd_t *pmdp);
extern int hash__has_transparent_hugepage(void);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+static inline pmd_t hash__pmd_mkdevmap(pmd_t pmd)
+{
+ return __pmd(pmd_val(pmd) | (_PAGE_PTE | H_PAGE_THP_HUGE | _PAGE_DEVMAP));
+}
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_POWERPC_BOOK3S_64_HASH_64K_H */
static inline pmd_t pmd_mkdevmap(pmd_t pmd)
{
- return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP));
+ if (radix_enabled())
+ return radix__pmd_mkdevmap(pmd);
+ return hash__pmd_mkdevmap(pmd);
}
static inline int pmd_devmap(pmd_t pmd)
}
#endif
+static inline pmd_t radix__pmd_mkdevmap(pmd_t pmd)
+{
+ return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP));
+}
+
extern int __meminit radix__vmemmap_create_mapping(unsigned long start,
unsigned long page_size,
unsigned long phys);