Building on 32 bits with pmd_leaf() not returning always false leads
to the following error:
CC arch/powerpc/mm/pgtable.o
arch/powerpc/mm/pgtable.c: In function '__find_linux_pte':
arch/powerpc/mm/pgtable.c:506:1: error: function may return address of local variable [-Werror=return-local-addr]
506 | }
| ^
arch/powerpc/mm/pgtable.c:394:15: note: declared here
394 | pud_t pud, *pudp;
| ^~~
arch/powerpc/mm/pgtable.c:394:15: note: declared here
This is due to pmd_offset() being a no-op in that case.
So rework it for powerpc/32 so that pXd_offset() are used on real
pointers and not on on-stack copies.
Behind fixing the problem, it also has the advantage of simplifying
__find_linux_pte() including the removal of stack frame:
After this patch:
00000018 <__find_linux_pte>:
18: 2c 06 00 00 cmpwi r6,0
1c: 41 82 00 0c beq 28 <__find_linux_pte+0x10>
20: 39 20 00 00 li r9,0
24: 91 26 00 00 stw r9,0(r6)
28: 2f 85 00 00 cmpwi cr7,r5,0
2c: 41 9e 00 0c beq cr7,38 <__find_linux_pte+0x20>
30: 39 20 00 00 li r9,0
34: 99 25 00 00 stb r9,0(r5)
38: 54 89 65 3a rlwinm r9,r4,12,20,29
3c: 7c 63 48 2e lwzx r3,r3,r9
40: 2f 83 00 00 cmpwi cr7,r3,0
44: 41 9e 00 30 beq cr7,74 <__find_linux_pte+0x5c>
48: 54 69 07 3a rlwinm r9,r3,0,28,29
4c: 2f 89 00 0c cmpwi cr7,r9,12
50: 54 63 00 26 clrrwi r3,r3,12
54: 54 84 b5 36 rlwinm r4,r4,22,20,27
58: 3c 63 c0 00 addis r3,r3,-16384
5c: 7c 63 22 14 add r3,r3,r4
60: 4c be 00 20 bnelr+ cr7
64: 4d 82 00 20 beqlr
68: 39 20 00 17 li r9,23
6c: 91 26 00 00 stw r9,0(r6)
70: 4e 80 00 20 blr
74: 38 60 00 00 li r3,0
78: 4e 80 00 20 blr
Before this patch:
00000018 <__find_linux_pte>:
18: 2c 06 00 00 cmpwi r6,0
1c: 94 21 ff e0 stwu r1,-32(r1)
20: 41 82 00 0c beq 2c <__find_linux_pte+0x14>
24: 39 20 00 00 li r9,0
28: 91 26 00 00 stw r9,0(r6)
2c: 2f 85 00 00 cmpwi cr7,r5,0
30: 41 9e 00 0c beq cr7,3c <__find_linux_pte+0x24>
34: 39 20 00 00 li r9,0
38: 99 25 00 00 stb r9,0(r5)
3c: 54 89 65 3a rlwinm r9,r4,12,20,29
40: 7c 63 48 2e lwzx r3,r3,r9
44: 54 69 07 3a rlwinm r9,r3,0,28,29
48: 2f 89 00 0c cmpwi cr7,r9,12
4c: 90 61 00 0c stw r3,12(r1)
50: 41 9e 00 4c beq cr7,9c <__find_linux_pte+0x84>
54: 80 61 00 0c lwz r3,12(r1)
58: 54 69 07 3a rlwinm r9,r3,0,28,29
5c: 2f 89 00 0c cmpwi cr7,r9,12
60: 90 61 00 08 stw r3,8(r1)
64: 41 9e 00 38 beq cr7,9c <__find_linux_pte+0x84>
68: 80 61 00 08 lwz r3,8(r1)
6c: 2f 83 00 00 cmpwi cr7,r3,0
70: 41 9e 00 54 beq cr7,c4 <__find_linux_pte+0xac>
74: 54 69 07 3a rlwinm r9,r3,0,28,29
78: 2f 89 00 0c cmpwi cr7,r9,12
7c: 54 69 00 26 clrrwi r9,r3,12
80: 54 8a b5 36 rlwinm r10,r4,22,20,27
84: 3c 69 c0 00 addis r3,r9,-16384
88: 7c 63 52 14 add r3,r3,r10
8c: 54 84 93 be srwi r4,r4,14
90: 41 9e 00 14 beq cr7,a4 <__find_linux_pte+0x8c>
94: 38 21 00 20 addi r1,r1,32
98: 4e 80 00 20 blr
9c: 54 69 00 26 clrrwi r9,r3,12
a0: 54 84 93 be srwi r4,r4,14
a4: 3c 69 c0 00 addis r3,r9,-16384
a8: 54 84 25 36 rlwinm r4,r4,4,20,27
ac: 7c 63 22 14 add r3,r3,r4
b0: 41 a2 ff e4 beq 94 <__find_linux_pte+0x7c>
b4: 39 20 00 17 li r9,23
b8: 91 26 00 00 stw r9,0(r6)
bc: 38 21 00 20 addi r1,r1,32
c0: 4e 80 00 20 blr
c4: 38 60 00 00 li r3,0
c8: 38 21 00 20 addi r1,r1,32
cc: 4e 80 00 20 blr
Signed-off-by: Christophe Leroy <christophe.leroy@xxxxxxxxxx>
Reviewed-by: Oscar Salvador <osalvador@xxxxxxx>
---
v3: Removed p4dp and pudp locals for PPC32 and add a comment.
v4: Properly set pdshift on PPC32 case
v5: Enhanced commit message
---
arch/powerpc/mm/pgtable.c | 11 ++++++++++-
1 file changed, 10 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 9e7ba9c3851f..bce8a8619589 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -382,8 +382,10 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
bool *is_thp, unsigned *hpage_shift)
{
pgd_t *pgdp;
+#ifdef CONFIG_PPC64
p4d_t p4d, *p4dp;
pud_t pud, *pudp;
+#endif
pmd_t pmd, *pmdp;
pte_t *ret_pte;
hugepd_t *hpdp = NULL;
@@ -401,8 +403,12 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
* page fault or a page unmap. The return pte_t * is still not
* stable. So should be checked there for above conditions.
* Top level is an exception because it is folded into p4d.
+ *
+ * On PPC32, P4D/PUD/PMD are folded into PGD so go straight to
+ * PMD level.
*/
pgdp = pgdir + pgd_index(ea);
+#ifdef CONFIG_PPC64
p4dp = p4d_offset(pgdp, ea);
p4d = READ_ONCE(*p4dp);
pdshift = P4D_SHIFT;
@@ -442,8 +448,11 @@ pte_t *__find_linux_pte(pgd_t *pgdir, unsigned long ea,
goto out_huge;
}
- pdshift = PMD_SHIFT;
pmdp = pmd_offset(&pud, ea);
+#else
+ pmdp = pmd_offset(pud_offset(p4d_offset(pgdp, ea), ea), ea);
+#endif
+ pdshift = PMD_SHIFT;
pmd = READ_ONCE(*pmdp);
/*
--
2.44.0
