aboutsummaryrefslogtreecommitdiff
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.c461
1 files changed, 304 insertions, 157 deletions
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 784a400e078..cf1d325eae8 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -14,10 +14,10 @@
#include <linux/spinlock.h>
#include <linux/bitops.h>
+#include <linux/of.h>
#include <linux/threads.h>
#include <linux/smp.h>
-#include <asm/abs_addr.h>
#include <asm/machdep.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
@@ -35,59 +35,109 @@
#define DBG_LOW(fmt...)
#endif
+#ifdef __BIG_ENDIAN__
#define HPTE_LOCK_BIT 3
+#else
+#define HPTE_LOCK_BIT (56+3)
+#endif
-static DEFINE_RAW_SPINLOCK(native_tlbie_lock);
+DEFINE_RAW_SPINLOCK(native_tlbie_lock);
-static inline void __tlbie(unsigned long va, int psize, int ssize)
+static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
{
+ unsigned long va;
unsigned int penc;
+ unsigned long sllp;
- /* clear top 16 bits, non SLS segment */
+ /*
+ * We need 14 to 65 bits of va for a tlibe of 4K page
+ * With vpn we ignore the lower VPN_SHIFT bits already.
+ * And top two bits are already ignored because we can
+ * only accomadate 76 bits in a 64 bit vpn with a VPN_SHIFT
+ * of 12.
+ */
+ va = vpn << VPN_SHIFT;
+ /*
+ * clear top 16 bits of 64bit va, non SLS segment
+ * Older versions of the architecture (2.02 and earler) require the
+ * masking of the top 16 bits.
+ */
va &= ~(0xffffULL << 48);
switch (psize) {
case MMU_PAGE_4K:
- va &= ~0xffful;
+ /* clear out bits after (52) [0....52.....63] */
+ va &= ~((1ul << (64 - 52)) - 1);
va |= ssize << 8;
- asm volatile(ASM_MMU_FTR_IFCLR("tlbie %0,0", PPC_TLBIE(%1,%0),
- %2)
- : : "r" (va), "r"(0), "i" (MMU_FTR_TLBIE_206)
+ 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");
break;
default:
- penc = mmu_psize_defs[psize].penc;
- va &= ~((1ul << mmu_psize_defs[psize].shift) - 1);
+ /* We need 14 to 14 + i bits of va */
+ penc = mmu_psize_defs[psize].penc[apsize];
+ va &= ~((1ul << mmu_psize_defs[apsize].shift) - 1);
va |= penc << 12;
va |= ssize << 8;
+ /*
+ * AVAL bits:
+ * We don't need all the bits, but rest of the bits
+ * must be ignored by the processor.
+ * vpn cover upto 65 bits of va. (0...65) and we need
+ * 58..64 bits of va.
+ */
+ va |= (vpn & 0xfe); /* AVAL */
va |= 1; /* L */
- asm volatile(ASM_MMU_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0),
- %2)
- : : "r" (va), "r"(0), "i" (MMU_FTR_TLBIE_206)
+ asm volatile(ASM_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0), %2)
+ : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
: "memory");
break;
}
}
-static inline void __tlbiel(unsigned long va, int psize, int ssize)
+static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
{
+ unsigned long va;
unsigned int penc;
+ unsigned long sllp;
- /* clear top 16 bits, non SLS segment */
+ /* VPN_SHIFT can be atmost 12 */
+ va = vpn << VPN_SHIFT;
+ /*
+ * clear top 16 bits of 64 bit va, non SLS segment
+ * Older versions of the architecture (2.02 and earler) require the
+ * masking of the top 16 bits.
+ */
va &= ~(0xffffULL << 48);
switch (psize) {
case MMU_PAGE_4K:
- va &= ~0xffful;
+ /* clear out bits after(52) [0....52.....63] */
+ va &= ~((1ul << (64 - 52)) - 1);
va |= ssize << 8;
+ 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;
default:
- penc = mmu_psize_defs[psize].penc;
- va &= ~((1ul << mmu_psize_defs[psize].shift) - 1);
+ /* We need 14 to 14 + i bits of va */
+ penc = mmu_psize_defs[psize].penc[apsize];
+ va &= ~((1ul << mmu_psize_defs[apsize].shift) - 1);
va |= penc << 12;
va |= ssize << 8;
+ /*
+ * AVAL bits:
+ * We don't need all the bits, but rest of the bits
+ * must be ignored by the processor.
+ * vpn cover upto 65 bits of va. (0...65) and we need
+ * 58..64 bits of va.
+ */
+ va |= (vpn & 0xfe);
va |= 1; /* L */
asm volatile(".long 0x7c000224 | (%0 << 11) | (1 << 21)"
: : "r"(va) : "memory");
@@ -96,10 +146,11 @@ static inline void __tlbiel(unsigned long va, int psize, int ssize)
}
-static inline void tlbie(unsigned long va, int psize, int ssize, int local)
+static inline void tlbie(unsigned long vpn, int psize, int apsize,
+ int ssize, int local)
{
- unsigned int use_local = local && cpu_has_feature(CPU_FTR_TLBIEL);
- int lock_tlbie = !cpu_has_feature(CPU_FTR_LOCKLESS_TLBIE);
+ unsigned int use_local = local && mmu_has_feature(MMU_FTR_TLBIEL);
+ int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
if (use_local)
use_local = mmu_psize_defs[psize].tlbiel;
@@ -107,10 +158,10 @@ static inline void tlbie(unsigned long va, int psize, int ssize, int local)
raw_spin_lock(&native_tlbie_lock);
asm volatile("ptesync": : :"memory");
if (use_local) {
- __tlbiel(va, psize, ssize);
+ __tlbiel(vpn, psize, apsize, ssize);
asm volatile("ptesync": : :"memory");
} else {
- __tlbie(va, psize, ssize);
+ __tlbie(vpn, psize, apsize, ssize);
asm volatile("eieio; tlbsync; ptesync": : :"memory");
}
if (lock_tlbie && !use_local)
@@ -119,7 +170,7 @@ static inline void tlbie(unsigned long va, int psize, int ssize, int local)
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))
@@ -131,30 +182,30 @@ 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);
}
-static long native_hpte_insert(unsigned long hpte_group, unsigned long va,
+static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
unsigned long pa, unsigned long rflags,
- unsigned long vflags, int psize, int ssize)
+ unsigned long vflags, int psize, int apsize, int ssize)
{
struct hash_pte *hptep = htab_address + hpte_group;
unsigned long hpte_v, hpte_r;
int i;
if (!(vflags & HPTE_V_BOLTED)) {
- DBG_LOW(" insert(group=%lx, va=%016lx, pa=%016lx,"
+ DBG_LOW(" insert(group=%lx, vpn=%016lx, pa=%016lx,"
" rflags=%lx, vflags=%lx, psize=%d)\n",
- hpte_group, va, pa, rflags, vflags, psize);
+ hpte_group, vpn, pa, rflags, vflags, psize);
}
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);
}
@@ -165,22 +216,22 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long va,
if (i == HPTES_PER_GROUP)
return -1;
- hpte_v = hpte_encode_v(va, psize, ssize) | vflags | HPTE_V_VALID;
- hpte_r = hpte_encode_r(pa, psize) | rflags;
+ hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
+ hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;
if (!(vflags & HPTE_V_BOLTED)) {
DBG_LOW(" i=%x hpte_v=%016lx, hpte_r=%016lx\n",
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");
@@ -201,12 +252,12 @@ 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;
@@ -227,41 +278,46 @@ static long native_hpte_remove(unsigned long hpte_group)
}
static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
- unsigned long va, 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;
- want_v = hpte_encode_v(va, psize, ssize);
+ want_v = hpte_encode_avpn(vpn, bpsize, ssize);
- DBG_LOW(" update(va=%016lx, avpnv=%016lx, hash=%016lx, newpp=%x)",
- va, want_v & HPTE_V_AVPN, slot, newpp);
+ 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;
-
- /* Even if we miss, we need to invalidate the TLB */
+ 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
+ * 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".
+ */
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)));
}
native_unlock_hpte(hptep);
/* Ensure it is out of the tlb too. */
- tlbie(va, psize, ssize, local);
+ tlbie(vpn, bpsize, apsize, ssize, local);
return ret;
}
-static long native_hpte_find(unsigned long va, int psize, int ssize)
+static long native_hpte_find(unsigned long vpn, int psize, int ssize)
{
struct hash_pte *hptep;
unsigned long hash;
@@ -269,14 +325,14 @@ static long native_hpte_find(unsigned long va, int psize, int ssize)
long slot;
unsigned long want_v, hpte_v;
- hash = hpt_hash(va, mmu_psize_defs[psize].shift, ssize);
- want_v = hpte_encode_v(va, psize, ssize);
+ hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, ssize);
+ want_v = hpte_encode_avpn(vpn, psize, ssize);
/* Bolted mappings are only ever in the primary group */
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 */
@@ -297,28 +353,32 @@ static long native_hpte_find(unsigned long va, int psize, int ssize)
static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
int psize, int ssize)
{
- unsigned long vsid, va;
+ unsigned long vpn;
+ unsigned long vsid;
long slot;
struct hash_pte *hptep;
vsid = get_kernel_vsid(ea, ssize);
- va = hpt_va(ea, vsid, ssize);
+ vpn = hpt_vpn(ea, vsid, ssize);
- slot = native_hpte_find(va, psize, ssize);
+ slot = native_hpte_find(vpn, psize, ssize);
if (slot == -1)
panic("could not find page to bolt\n");
hptep = htab_address + slot;
/* 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(va, 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 va,
- int psize, int ssize, int local)
+static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
+ int bpsize, int apsize, int ssize, int local)
{
struct hash_pte *hptep = htab_address + slot;
unsigned long hpte_v;
@@ -327,13 +387,19 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long va,
local_irq_save(flags);
- DBG_LOW(" invalidate(va=%016lx, hash: %x)\n", va, slot);
+ DBG_LOW(" invalidate(vpn=%016lx, hash: %lx)\n", vpn, slot);
- want_v = hpte_encode_v(va, 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);
- /* Even if we miss, we need to invalidate the TLB */
+ /*
+ * 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
+ * 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".
+ */
if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID))
native_unlock_hpte(hptep);
else
@@ -341,73 +407,175 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long va,
hptep->v = 0;
/* Invalidate the TLB */
- tlbie(va, 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);
}
-#define LP_SHIFT 12
-#define LP_BITS 8
-#define LP_MASK(i) ((0xFF >> (i)) << LP_SHIFT)
+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 *ssize, unsigned long *va)
+ int *psize, int *apsize, int *ssize, unsigned long *vpn)
{
- unsigned long hpte_r = hpte->r;
- unsigned long hpte_v = hpte->v;
- unsigned long avpn;
- int i, size, shift, penc;
-
- if (!(hpte_v & HPTE_V_LARGE))
- size = MMU_PAGE_4K;
- else {
- for (i = 0; i < LP_BITS; i++) {
- if ((hpte_r & LP_MASK(i+1)) == LP_MASK(i+1))
- break;
- }
- penc = LP_MASK(i+1) >> LP_SHIFT;
+ unsigned long avpn, pteg, vpi;
+ 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);
+
+ if (!(hpte_v & HPTE_V_LARGE)) {
+ size = MMU_PAGE_4K;
+ a_size = MMU_PAGE_4K;
+ } else {
for (size = 0; size < MMU_PAGE_COUNT; size++) {
- /* 4K pages are not represented by LP */
- if (size == MMU_PAGE_4K)
- continue;
-
/* valid entries have a shift value */
if (!mmu_psize_defs[size].shift)
continue;
- if (penc == mmu_psize_defs[size].penc)
+ a_size = __hpte_actual_psize(lp, size);
+ if (a_size != -1)
break;
}
}
-
/* This works for all page sizes, and for 256M and 1T segments */
+ *ssize = hpte_v >> HPTE_V_SSIZE_SHIFT;
shift = mmu_psize_defs[size].shift;
- avpn = (HPTE_V_AVPN_VAL(hpte_v) & ~mmu_psize_defs[size].avpnm) << 23;
-
- if (shift < 23) {
- unsigned long vpi, vsid, pteg;
- pteg = slot / HPTES_PER_GROUP;
- if (hpte_v & HPTE_V_SECONDARY)
- pteg = ~pteg;
- switch (hpte_v >> HPTE_V_SSIZE_SHIFT) {
- case MMU_SEGSIZE_256M:
- vpi = ((avpn >> 28) ^ pteg) & htab_hash_mask;
- break;
- case MMU_SEGSIZE_1T:
- vsid = avpn >> 40;
+ avpn = (HPTE_V_AVPN_VAL(hpte_v) & ~mmu_psize_defs[size].avpnm);
+ pteg = slot / HPTES_PER_GROUP;
+ if (hpte_v & HPTE_V_SECONDARY)
+ pteg = ~pteg;
+
+ switch (*ssize) {
+ case MMU_SEGSIZE_256M:
+ /* We only have 28 - 23 bits of seg_off in avpn */
+ seg_off = (avpn & 0x1f) << 23;
+ vsid = avpn >> 5;
+ /* We can find more bits from the pteg value */
+ if (shift < 23) {
+ vpi = (vsid ^ pteg) & htab_hash_mask;
+ 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;
+ vsid = avpn >> 17;
+ if (shift < 23) {
vpi = (vsid ^ (vsid << 25) ^ pteg) & htab_hash_mask;
- break;
- default:
- avpn = vpi = size = 0;
+ seg_off |= vpi << shift;
}
- avpn |= (vpi << mmu_psize_defs[size].shift);
+ *vpn = vsid << (SID_SHIFT_1T - VPN_SHIFT) | seg_off >> VPN_SHIFT;
+ break;
+ default:
+ *vpn = size = 0;
}
-
- *va = avpn;
- *psize = size;
- *ssize = hpte_v >> HPTE_V_SSIZE_SHIFT;
+ *psize = size;
+ *apsize = a_size;
}
/*
@@ -420,11 +588,12 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
*/
static void native_hpte_clear(void)
{
+ unsigned long vpn = 0;
unsigned long slot, slots, flags;
struct hash_pte *hptep = htab_address;
- unsigned long hpte_v, va;
+ unsigned long hpte_v;
unsigned long pteg_count;
- int psize, ssize;
+ int psize, apsize, ssize;
pteg_count = htab_hash_mask + 1;
@@ -443,16 +612,16 @@ 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
* already hold the native_tlbie_lock.
*/
if (hpte_v & HPTE_V_VALID) {
- hpte_decode(hptep, slot, &psize, &ssize, &va);
+ hpte_decode(hptep, slot, &psize, &apsize, &ssize, &vpn);
hptep->v = 0;
- __tlbie(va, psize, ssize);
+ __tlbie(vpn, psize, apsize, ssize);
}
}
@@ -467,7 +636,8 @@ static void native_hpte_clear(void)
*/
static void native_flush_hash_range(unsigned long number, int local)
{
- unsigned long va, hash, index, hidx, shift, slot;
+ unsigned long vpn;
+ unsigned long hash, index, hidx, shift, slot;
struct hash_pte *hptep;
unsigned long hpte_v;
unsigned long want_v;
@@ -481,20 +651,20 @@ static void native_flush_hash_range(unsigned long number, int local)
local_irq_save(flags);
for (i = 0; i < number; i++) {
- va = batch->vaddr[i];
+ vpn = batch->vpn[i];
pte = batch->pte[i];
- pte_iterate_hashed_subpages(pte, psize, va, index, shift) {
- hash = hpt_hash(va, shift, ssize);
+ pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) {
+ hash = hpt_hash(vpn, shift, ssize);
hidx = __rpte_to_hidx(pte, index);
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_v(va, psize, ssize);
+ 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);
@@ -503,33 +673,33 @@ static void native_flush_hash_range(unsigned long number, int local)
} pte_iterate_hashed_end();
}
- if (cpu_has_feature(CPU_FTR_TLBIEL) &&
+ if (mmu_has_feature(MMU_FTR_TLBIEL) &&
mmu_psize_defs[psize].tlbiel && local) {
asm volatile("ptesync":::"memory");
for (i = 0; i < number; i++) {
- va = batch->vaddr[i];
+ vpn = batch->vpn[i];
pte = batch->pte[i];
- pte_iterate_hashed_subpages(pte, psize, va, index,
- shift) {
- __tlbiel(va, psize, ssize);
+ pte_iterate_hashed_subpages(pte, psize,
+ vpn, index, shift) {
+ __tlbiel(vpn, psize, psize, ssize);
} pte_iterate_hashed_end();
}
asm volatile("ptesync":::"memory");
} else {
- int lock_tlbie = !cpu_has_feature(CPU_FTR_LOCKLESS_TLBIE);
+ int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
if (lock_tlbie)
raw_spin_lock(&native_tlbie_lock);
asm volatile("ptesync":::"memory");
for (i = 0; i < number; i++) {
- va = batch->vaddr[i];
+ vpn = batch->vpn[i];
pte = batch->pte[i];
- pte_iterate_hashed_subpages(pte, psize, va, index,
- shift) {
- __tlbie(va, psize, ssize);
+ pte_iterate_hashed_subpages(pte, psize,
+ vpn, index, shift) {
+ __tlbie(vpn, psize, psize, ssize);
} pte_iterate_hashed_end();
}
asm volatile("eieio; tlbsync; ptesync":::"memory");
@@ -541,29 +711,6 @@ static void native_flush_hash_range(unsigned long number, int local)
local_irq_restore(flags);
}
-#ifdef CONFIG_PPC_PSERIES
-/* Disable TLB batching on nighthawk */
-static inline int tlb_batching_enabled(void)
-{
- struct device_node *root = of_find_node_by_path("/");
- int enabled = 1;
-
- if (root) {
- const char *model = of_get_property(root, "model", NULL);
- if (model && !strcmp(model, "IBM,9076-N81"))
- enabled = 0;
- of_node_put(root);
- }
-
- return enabled;
-}
-#else
-static inline int tlb_batching_enabled(void)
-{
- return 1;
-}
-#endif
-
void __init hpte_init_native(void)
{
ppc_md.hpte_invalidate = native_hpte_invalidate;
@@ -572,6 +719,6 @@ void __init hpte_init_native(void)
ppc_md.hpte_insert = native_hpte_insert;
ppc_md.hpte_remove = native_hpte_remove;
ppc_md.hpte_clear_all = native_hpte_clear;
- if (tlb_batching_enabled())
- ppc_md.flush_hash_range = native_flush_hash_range;
+ ppc_md.flush_hash_range = native_flush_hash_range;
+ ppc_md.hugepage_invalidate = native_hugepage_invalidate;
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-05 18:29:50 +0000