summaryrefslogtreecommitdiff
path: root/arch/powerpc/mm/hash_native_64.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/mm/hash_native_64.c')
-rw-r--r--arch/powerpc/mm/hash_native_64.c251
1 files changed, 153 insertions, 98 deletions
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 4c122c3..3ea26c2 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -35,7 +35,11 @@
#define DBG_LOW(fmt...)
#endif
+#ifdef __BIG_ENDIAN__
#define HPTE_LOCK_BIT 3
+#else
+#define HPTE_LOCK_BIT (56+3)
+#endif
DEFINE_RAW_SPINLOCK(native_tlbie_lock);
@@ -43,6 +47,7 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
{
unsigned long va;
unsigned int penc;
+ unsigned long sllp;
/*
* We need 14 to 65 bits of va for a tlibe of 4K page
@@ -64,7 +69,9 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
/* clear out bits after (52) [0....52.....63] */
va &= ~((1ul << (64 - 52)) - 1);
va |= ssize << 8;
- va |= mmu_psize_defs[apsize].sllp << 6;
+ sllp = ((mmu_psize_defs[apsize].sllp & SLB_VSID_L) >> 6) |
+ ((mmu_psize_defs[apsize].sllp & SLB_VSID_LP) >> 4);
+ va |= sllp << 5;
asm volatile(ASM_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0), %2)
: : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
: "memory");
@@ -98,6 +105,7 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
{
unsigned long va;
unsigned int penc;
+ unsigned long sllp;
/* VPN_SHIFT can be atmost 12 */
va = vpn << VPN_SHIFT;
@@ -113,7 +121,9 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
/* clear out bits after(52) [0....52.....63] */
va &= ~((1ul << (64 - 52)) - 1);
va |= ssize << 8;
- va |= mmu_psize_defs[apsize].sllp << 6;
+ sllp = ((mmu_psize_defs[apsize].sllp & SLB_VSID_L) >> 6) |
+ ((mmu_psize_defs[apsize].sllp & SLB_VSID_LP) >> 4);
+ va |= sllp << 5;
asm volatile(".long 0x7c000224 | (%0 << 11) | (0 << 21)"
: : "r"(va) : "memory");
break;
@@ -166,7 +176,7 @@ static inline void tlbie(unsigned long vpn, int psize, int apsize,
static inline void native_lock_hpte(struct hash_pte *hptep)
{
- unsigned long *word = &hptep->v;
+ unsigned long *word = (unsigned long *)&hptep->v;
while (1) {
if (!test_and_set_bit_lock(HPTE_LOCK_BIT, word))
@@ -178,7 +188,7 @@ static inline void native_lock_hpte(struct hash_pte *hptep)
static inline void native_unlock_hpte(struct hash_pte *hptep)
{
- unsigned long *word = &hptep->v;
+ unsigned long *word = (unsigned long *)&hptep->v;
clear_bit_unlock(HPTE_LOCK_BIT, word);
}
@@ -198,10 +208,10 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
}
for (i = 0; i < HPTES_PER_GROUP; i++) {
- if (! (hptep->v & HPTE_V_VALID)) {
+ if (! (be64_to_cpu(hptep->v) & HPTE_V_VALID)) {
/* retry with lock held */
native_lock_hpte(hptep);
- if (! (hptep->v & HPTE_V_VALID))
+ if (! (be64_to_cpu(hptep->v) & HPTE_V_VALID))
break;
native_unlock_hpte(hptep);
}
@@ -220,14 +230,14 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
i, hpte_v, hpte_r);
}
- hptep->r = hpte_r;
+ hptep->r = cpu_to_be64(hpte_r);
/* Guarantee the second dword is visible before the valid bit */
eieio();
/*
* Now set the first dword including the valid bit
* NOTE: this also unlocks the hpte
*/
- hptep->v = hpte_v;
+ hptep->v = cpu_to_be64(hpte_v);
__asm__ __volatile__ ("ptesync" : : : "memory");
@@ -248,12 +258,12 @@ static long native_hpte_remove(unsigned long hpte_group)
for (i = 0; i < HPTES_PER_GROUP; i++) {
hptep = htab_address + hpte_group + slot_offset;
- hpte_v = hptep->v;
+ hpte_v = be64_to_cpu(hptep->v);
if ((hpte_v & HPTE_V_VALID) && !(hpte_v & HPTE_V_BOLTED)) {
/* retry with lock held */
native_lock_hpte(hptep);
- hpte_v = hptep->v;
+ hpte_v = be64_to_cpu(hptep->v);
if ((hpte_v & HPTE_V_VALID)
&& !(hpte_v & HPTE_V_BOLTED))
break;
@@ -273,69 +283,22 @@ static long native_hpte_remove(unsigned long hpte_group)
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);
native_lock_hpte(hptep);
- hpte_v = hptep->v;
- actual_psize = hpte_actual_psize(hptep, psize);
+ hpte_v = be64_to_cpu(hptep->v);
/*
* 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
@@ -343,25 +306,19 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
* (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 {
DBG_LOW(" -> hit\n");
/* Update the HPTE */
- hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) |
- (newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_C));
+ hptep->r = cpu_to_be64((be64_to_cpu(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;
}
@@ -381,7 +338,7 @@ static long native_hpte_find(unsigned long vpn, int psize, int ssize)
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
for (i = 0; i < HPTES_PER_GROUP; i++) {
hptep = htab_address + slot;
- hpte_v = hptep->v;
+ hpte_v = be64_to_cpu(hptep->v);
if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID))
/* HPTE matches */
@@ -402,7 +359,6 @@ static long native_hpte_find(unsigned long vpn, int psize, int ssize)
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 +371,34 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
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);
+ hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) &
+ ~(HPTE_R_PP | HPTE_R_N)) |
+ (newpp & (HPTE_R_PP | HPTE_R_N)));
+ /*
+ * 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;
+ hpte_v = be64_to_cpu(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
@@ -452,32 +406,130 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
* (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 void native_hugepage_invalidate(struct mm_struct *mm,
+ unsigned char *hpte_slot_array,
+ unsigned long addr, int psize)
+{
+ int ssize = 0, i;
+ int lock_tlbie;
+ struct hash_pte *hptep;
+ int actual_psize = MMU_PAGE_16M;
+ unsigned int max_hpte_count, valid;
+ unsigned long flags, s_addr = addr;
+ unsigned long hpte_v, want_v, shift;
+ unsigned long hidx, vpn = 0, vsid, hash, slot;
+
+ shift = mmu_psize_defs[psize].shift;
+ max_hpte_count = 1U << (PMD_SHIFT - shift);
+
+ local_irq_save(flags);
+ for (i = 0; i < max_hpte_count; i++) {
+ valid = hpte_valid(hpte_slot_array, i);
+ if (!valid)
+ continue;
+ hidx = hpte_hash_index(hpte_slot_array, i);
+
+ /* get the vpn */
+ addr = s_addr + (i * (1ul << shift));
+ if (!is_kernel_addr(addr)) {
+ ssize = user_segment_size(addr);
+ vsid = get_vsid(mm->context.id, addr, ssize);
+ WARN_ON(vsid == 0);
+ } else {
+ vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
+ ssize = mmu_kernel_ssize;
+ }
+
+ vpn = hpt_vpn(addr, vsid, ssize);
+ hash = hpt_hash(vpn, shift, ssize);
+ if (hidx & _PTEIDX_SECONDARY)
+ hash = ~hash;
+
+ slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+ slot += hidx & _PTEIDX_GROUP_IX;
+
+ hptep = htab_address + slot;
+ want_v = hpte_encode_avpn(vpn, psize, ssize);
+ native_lock_hpte(hptep);
+ hpte_v = be64_to_cpu(hptep->v);
+
+ /* Even if we miss, we need to invalidate the TLB */
+ 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;
+ }
+ /*
+ * Since this is a hugepage, we just need a single tlbie.
+ * use the last vpn.
+ */
+ lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
+ if (lock_tlbie)
+ raw_spin_lock(&native_tlbie_lock);
+
+ asm volatile("ptesync":::"memory");
+ __tlbie(vpn, psize, actual_psize, ssize);
+ asm volatile("eieio; tlbsync; ptesync":::"memory");
+
+ if (lock_tlbie)
+ raw_spin_unlock(&native_tlbie_lock);
+
+ 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)
{
unsigned long avpn, pteg, vpi;
- unsigned long hpte_v = hpte->v;
+ unsigned long hpte_v = be64_to_cpu(hpte->v);
+ unsigned long hpte_r = be64_to_cpu(hpte->r);
unsigned long vsid, seg_off;
int size, a_size, shift;
/* Look at the 8 bit LP value */
- unsigned int lp = (hpte->r >> LP_SHIFT) & ((1 << LP_BITS) - 1);
+ unsigned int lp = (hpte_r >> LP_SHIFT) & ((1 << LP_BITS) - 1);
if (!(hpte_v & HPTE_V_LARGE)) {
size = MMU_PAGE_4K;
@@ -514,6 +566,7 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
seg_off |= vpi << shift;
}
*vpn = vsid << (SID_SHIFT - VPN_SHIFT) | seg_off >> VPN_SHIFT;
+ break;
case MMU_SEGSIZE_1T:
/* We only have 40 - 23 bits of seg_off in avpn */
seg_off = (avpn & 0x1ffff) << 23;
@@ -523,6 +576,7 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
seg_off |= vpi << shift;
}
*vpn = vsid << (SID_SHIFT_1T - VPN_SHIFT) | seg_off >> VPN_SHIFT;
+ break;
default:
*vpn = size = 0;
}
@@ -564,7 +618,7 @@ static void native_hpte_clear(void)
* running, right? and for crash dump, we probably
* don't want to wait for a maybe bad cpu.
*/
- hpte_v = hptep->v;
+ hpte_v = be64_to_cpu(hptep->v);
/*
* Call __tlbie() here rather than tlbie() since we
@@ -616,7 +670,7 @@ static void native_flush_hash_range(unsigned long number, int local)
hptep = htab_address + slot;
want_v = hpte_encode_avpn(vpn, psize, ssize);
native_lock_hpte(hptep);
- hpte_v = hptep->v;
+ hpte_v = be64_to_cpu(hptep->v);
if (!HPTE_V_COMPARE(hpte_v, want_v) ||
!(hpte_v & HPTE_V_VALID))
native_unlock_hpte(hptep);
@@ -672,4 +726,5 @@ void __init hpte_init_native(void)
ppc_md.hpte_remove = native_hpte_remove;
ppc_md.hpte_clear_all = native_hpte_clear;
ppc_md.flush_hash_range = native_flush_hash_range;
+ ppc_md.hugepage_invalidate = native_hugepage_invalidate;
}
generated by cgit v0.10.2 at 2024-07-15 21:49:51 (GMT)