powerpc/mm: handle hugepage size correctly when invalidating hpte entries
If a hash bucket gets full, we "evict" a more/less random entry from it.
When we do that we don't invalidate the TLB (hpte_remove) because we assume
the old translation is still technically "valid". This implies that when
we are invalidating or updating pte, even if HPTE entry is not valid
we should do a tlb invalidate. With hugepages, we need to pass the correct
actual page size value for tlb invalidation.
This change update the patch 0608d692463598c1d6e826d9dd7283381b4f246c
"powerpc/mm: Always invalidate tlb on hpte invalidate and update" to handle
transparent hugepages correctly.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 4c122c3..6d152bc 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -273,61 +273,15 @@
return i;
}
-static inline int __hpte_actual_psize(unsigned int lp, int psize)
-{
- int i, shift;
- unsigned int mask;
-
- /* start from 1 ignoring MMU_PAGE_4K */
- for (i = 1; i < MMU_PAGE_COUNT; i++) {
-
- /* invalid penc */
- if (mmu_psize_defs[psize].penc[i] == -1)
- continue;
- /*
- * encoding bits per actual page size
- * PTE LP actual page size
- * rrrr rrrz >=8KB
- * rrrr rrzz >=16KB
- * rrrr rzzz >=32KB
- * rrrr zzzz >=64KB
- * .......
- */
- shift = mmu_psize_defs[i].shift - LP_SHIFT;
- if (shift > LP_BITS)
- shift = LP_BITS;
- mask = (1 << shift) - 1;
- if ((lp & mask) == mmu_psize_defs[psize].penc[i])
- return i;
- }
- return -1;
-}
-
-static inline int hpte_actual_psize(struct hash_pte *hptep, int psize)
-{
- /* Look at the 8 bit LP value */
- unsigned int lp = (hptep->r >> LP_SHIFT) & ((1 << LP_BITS) - 1);
-
- if (!(hptep->v & HPTE_V_VALID))
- return -1;
-
- /* First check if it is large page */
- if (!(hptep->v & HPTE_V_LARGE))
- return MMU_PAGE_4K;
-
- return __hpte_actual_psize(lp, psize);
-}
-
static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
- unsigned long vpn, int psize, int ssize,
- int local)
+ unsigned long vpn, int bpsize,
+ int apsize, int ssize, int local)
{
struct hash_pte *hptep = htab_address + slot;
unsigned long hpte_v, want_v;
int ret = 0;
- int actual_psize;
- want_v = hpte_encode_avpn(vpn, psize, ssize);
+ want_v = hpte_encode_avpn(vpn, bpsize, ssize);
DBG_LOW(" update(vpn=%016lx, avpnv=%016lx, group=%lx, newpp=%lx)",
vpn, want_v & HPTE_V_AVPN, slot, newpp);
@@ -335,7 +289,6 @@
native_lock_hpte(hptep);
hpte_v = hptep->v;
- actual_psize = hpte_actual_psize(hptep, psize);
/*
* We need to invalidate the TLB always because hpte_remove doesn't do
* a tlb invalidate. If a hash bucket gets full, we "evict" a more/less
@@ -343,12 +296,7 @@
* (hpte_remove) because we assume the old translation is still
* technically "valid".
*/
- if (actual_psize < 0) {
- actual_psize = psize;
- ret = -1;
- goto err_out;
- }
- if (!HPTE_V_COMPARE(hpte_v, want_v)) {
+ if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID)) {
DBG_LOW(" -> miss\n");
ret = -1;
} else {
@@ -357,11 +305,10 @@
hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) |
(newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_C));
}
-err_out:
native_unlock_hpte(hptep);
/* Ensure it is out of the tlb too. */
- tlbie(vpn, psize, actual_psize, ssize, local);
+ tlbie(vpn, bpsize, apsize, ssize, local);
return ret;
}
@@ -402,7 +349,6 @@
static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
int psize, int ssize)
{
- int actual_psize;
unsigned long vpn;
unsigned long vsid;
long slot;
@@ -415,36 +361,33 @@
if (slot == -1)
panic("could not find page to bolt\n");
hptep = htab_address + slot;
- actual_psize = hpte_actual_psize(hptep, psize);
- if (actual_psize < 0)
- actual_psize = psize;
/* Update the HPTE */
hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) |
(newpp & (HPTE_R_PP | HPTE_R_N));
-
- /* Ensure it is out of the tlb too. */
- tlbie(vpn, psize, actual_psize, ssize, 0);
+ /*
+ * Ensure it is out of the tlb too. Bolted entries base and
+ * actual page size will be same.
+ */
+ tlbie(vpn, psize, psize, ssize, 0);
}
static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
- int psize, int ssize, int local)
+ int bpsize, int apsize, int ssize, int local)
{
struct hash_pte *hptep = htab_address + slot;
unsigned long hpte_v;
unsigned long want_v;
unsigned long flags;
- int actual_psize;
local_irq_save(flags);
DBG_LOW(" invalidate(vpn=%016lx, hash: %lx)\n", vpn, slot);
- want_v = hpte_encode_avpn(vpn, psize, ssize);
+ want_v = hpte_encode_avpn(vpn, bpsize, ssize);
native_lock_hpte(hptep);
hpte_v = hptep->v;
- actual_psize = hpte_actual_psize(hptep, psize);
/*
* We need to invalidate the TLB always because hpte_remove doesn't do
* a tlb invalidate. If a hash bucket gets full, we "evict" a more/less
@@ -452,23 +395,48 @@
* (hpte_remove) because we assume the old translation is still
* technically "valid".
*/
- if (actual_psize < 0) {
- actual_psize = psize;
- native_unlock_hpte(hptep);
- goto err_out;
- }
- if (!HPTE_V_COMPARE(hpte_v, want_v))
+ if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID))
native_unlock_hpte(hptep);
else
/* Invalidate the hpte. NOTE: this also unlocks it */
hptep->v = 0;
-err_out:
/* Invalidate the TLB */
- tlbie(vpn, psize, actual_psize, ssize, local);
+ tlbie(vpn, bpsize, apsize, ssize, local);
+
local_irq_restore(flags);
}
+static inline int __hpte_actual_psize(unsigned int lp, int psize)
+{
+ int i, shift;
+ unsigned int mask;
+
+ /* start from 1 ignoring MMU_PAGE_4K */
+ for (i = 1; i < MMU_PAGE_COUNT; i++) {
+
+ /* invalid penc */
+ if (mmu_psize_defs[psize].penc[i] == -1)
+ continue;
+ /*
+ * encoding bits per actual page size
+ * PTE LP actual page size
+ * rrrr rrrz >=8KB
+ * rrrr rrzz >=16KB
+ * rrrr rzzz >=32KB
+ * rrrr zzzz >=64KB
+ * .......
+ */
+ shift = mmu_psize_defs[i].shift - LP_SHIFT;
+ if (shift > LP_BITS)
+ shift = LP_BITS;
+ mask = (1 << shift) - 1;
+ if ((lp & mask) == mmu_psize_defs[psize].penc[i])
+ return i;
+ }
+ return -1;
+}
+
static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
int *psize, int *apsize, int *ssize, unsigned long *vpn)
{