summaryrefslogtreecommitdiff
path: root/arch/powerpc/mm/hash64_64k.c
diff options
context:
space:
mode:
authorRam Pai <linuxram@us.ibm.com>2017-11-06 00:50:47 -0800
committerMichael Ellerman <mpe@ellerman.id.au>2017-12-20 18:57:20 +1100
commit9d2edb18486febea930ea028dd128544cc28f3fe (patch)
treef2564ecf3a0d39d3198be637edf9257b4668dca3 /arch/powerpc/mm/hash64_64k.c
parent318995b4f5fa814b9f9aa434ca845b9a2cb0ae02 (diff)
powerpc: Free up four 64K PTE bits in 4K backed HPTE pages
Rearrange 64K PTE bits to free up bits 3, 4, 5 and 6, in the 4K backed HPTE pages.These bits continue to be used for 64K backed HPTE pages in this patch, but will be freed up in the next patch. The bit numbers are big-endian as defined in the ISA3.0 The patch does the following change to the 4k HTPE backed 64K PTE's format. H_PAGE_BUSY moves from bit 3 to bit 9 (B bit in the figure below) V0 which occupied bit 4 is not used anymore. V1 which occupied bit 5 is not used anymore. V2 which occupied bit 6 is not used anymore. V3 which occupied bit 7 is not used anymore. Before the patch, the 4k backed 64k PTE format was as follows 0 1 2 3 4 5 6 7 8 9 10...........................63 : : : : : : : : : : : : v v v v v v v v v v v v ,-,-,-,-,--,--,--,--,-,-,-,-,-,------------------,-,-,-, |x|x|x|B|V0|V1|V2|V3|x| | |x|x|................|x|x|x|x| <- primary pte '_'_'_'_'__'__'__'__'_'_'_'_'_'________________'_'_'_'_' |S|G|I|X|S |G |I |X |S|G|I|X|..................|S|G|I|X| <- secondary pte '_'_'_'_'__'__'__'__'_'_'_'_'__________________'_'_'_'_' After the patch, the 4k backed 64k PTE format is as follows 0 1 2 3 4 5 6 7 8 9 10...........................63 : : : : : : : : : : : : v v v v v v v v v v v v ,-,-,-,-,--,--,--,--,-,-,-,-,-,------------------,-,-,-, |x|x|x| | | | | |x|B| |x|x|................|.|.|.|.| <- primary pte '_'_'_'_'__'__'__'__'_'_'_'_'_'________________'_'_'_'_' |S|G|I|X|S |G |I |X |S|G|I|X|..................|S|G|I|X| <- secondary pte '_'_'_'_'__'__'__'__'_'_'_'_'__________________'_'_'_'_' the four bits S,G,I,X (one quadruplet per 4k HPTE) that cache the hash-bucket slot value, is initialized to 1,1,1,1 indicating -- an invalid slot. If a HPTE gets cached in a 1111 slot(i.e 7th slot of secondary hash bucket), it is released immediately. In other words, even though 1111 is a valid slot value in the hash bucket, we consider it invalid and release the slot and the HPTE. This gives us the opportunity to determine the validity of S,G,I,X bits based on its contents and not on any of the bits V0,V1,V2 or V3 in the primary PTE When we release a HPTE cached in the 1111 slot we also release a legitimate slot in the primary hash bucket and unmap its corresponding HPTE. This is to ensure that we do get a HPTE cached in a slot of the primary hash bucket, the next time we retry. Though treating 1111 slot as invalid, reduces the number of available slots in the hash bucket and may have an effect on the performance, the probabilty of hitting a 1111 slot is extermely low. Compared to the current scheme, the above scheme reduces the number of false hash table updates significantly and has the added advantage of releasing four valuable PTE bits for other purpose. NOTE:even though bits 3, 4, 5, 6, 7 are not used when the 64K PTE is backed by 4k HPTE, they continue to be used if the PTE gets backed by 64k HPTE. The next patch will decouple that aswell, and truely release the bits. This idea was jointly developed by Paul Mackerras, Aneesh, Michael Ellermen and myself. 4K PTE format remains unchanged currently. The patch does the following code changes a) PTE flags are split between 64k and 4k header files. b) __hash_page_4K() is reimplemented to reflect the above logic. Acked-by: Balbir Singh <bsingharora@gmail.com> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by: Ram Pai <linuxram@us.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Diffstat (limited to 'arch/powerpc/mm/hash64_64k.c')
-rw-r--r--arch/powerpc/mm/hash64_64k.c102
1 files changed, 53 insertions, 49 deletions
diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c
index 1a68cb19b0e3..b79f50c693cf 100644
--- a/arch/powerpc/mm/hash64_64k.c
+++ b/arch/powerpc/mm/hash64_64k.c
@@ -15,34 +15,22 @@
#include <linux/mm.h>
#include <asm/machdep.h>
#include <asm/mmu.h>
+
/*
- * index from 0 - 15
+ * Return true, if the entry has a slot value which
+ * the software considers as invalid.
*/
-bool __rpte_sub_valid(real_pte_t rpte, unsigned long index)
+static inline bool hpte_soft_invalid(unsigned long hidx)
{
- unsigned long g_idx;
- unsigned long ptev = pte_val(rpte.pte);
-
- g_idx = (ptev & H_PAGE_COMBO_VALID) >> H_PAGE_F_GIX_SHIFT;
- index = index >> 2;
- if (g_idx & (0x1 << index))
- return true;
- else
- return false;
+ return ((hidx & 0xfUL) == 0xfUL);
}
+
/*
* index from 0 - 15
*/
-static unsigned long mark_subptegroup_valid(unsigned long ptev, unsigned long index)
+bool __rpte_sub_valid(real_pte_t rpte, unsigned long index)
{
- unsigned long g_idx;
-
- if (!(ptev & H_PAGE_COMBO))
- return ptev;
- index = index >> 2;
- g_idx = 0x1 << index;
-
- return ptev | (g_idx << H_PAGE_F_GIX_SHIFT);
+ return !(hpte_soft_invalid(__rpte_to_hidx(rpte, index)));
}
int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
@@ -50,12 +38,11 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
int ssize, int subpg_prot)
{
real_pte_t rpte;
- unsigned long *hidxp;
unsigned long hpte_group;
unsigned int subpg_index;
- unsigned long rflags, pa, hidx;
+ unsigned long rflags, pa;
unsigned long old_pte, new_pte, subpg_pte;
- unsigned long vpn, hash, slot;
+ unsigned long vpn, hash, slot, gslot;
unsigned long shift = mmu_psize_defs[MMU_PAGE_4K].shift;
/*
@@ -126,18 +113,14 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
if (__rpte_sub_valid(rpte, subpg_index)) {
int ret;
- hash = hpt_hash(vpn, shift, ssize);
- hidx = __rpte_to_hidx(rpte, subpg_index);
- if (hidx & _PTEIDX_SECONDARY)
- hash = ~hash;
- slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
- slot += hidx & _PTEIDX_GROUP_IX;
-
- ret = mmu_hash_ops.hpte_updatepp(slot, rflags, vpn,
+ gslot = pte_get_hash_gslot(vpn, shift, ssize, rpte,
+ subpg_index);
+ ret = mmu_hash_ops.hpte_updatepp(gslot, rflags, vpn,
MMU_PAGE_4K, MMU_PAGE_4K,
ssize, flags);
+
/*
- *if we failed because typically the HPTE wasn't really here
+ * If we failed because typically the HPTE wasn't really here
* we try an insertion.
*/
if (ret == -1)
@@ -148,6 +131,14 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
}
htab_insert_hpte:
+
+ /*
+ * Initialize all hidx entries to invalid value, the first time
+ * the PTE is about to allocate a 4K HPTE.
+ */
+ if (!(old_pte & H_PAGE_COMBO))
+ rpte.hidx = INVALID_RPTE_HIDX;
+
/*
* handle H_PAGE_4K_PFN case
*/
@@ -172,15 +163,39 @@ repeat:
* Primary is full, try the secondary
*/
if (unlikely(slot == -1)) {
+ bool soft_invalid;
+
hpte_group = ((~hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
slot = mmu_hash_ops.hpte_insert(hpte_group, vpn, pa,
rflags, HPTE_V_SECONDARY,
MMU_PAGE_4K, MMU_PAGE_4K,
ssize);
- if (slot == -1) {
- if (mftb() & 0x1)
+
+ soft_invalid = hpte_soft_invalid(slot);
+ if (unlikely(soft_invalid)) {
+ /*
+ * We got a valid slot from a hardware point of view.
+ * but we cannot use it, because we use this special
+ * value; as defined by hpte_soft_invalid(), to track
+ * invalid slots. We cannot use it. So invalidate it.
+ */
+ gslot = slot & _PTEIDX_GROUP_IX;
+ mmu_hash_ops.hpte_invalidate(hpte_group + gslot, vpn,
+ MMU_PAGE_4K, MMU_PAGE_4K,
+ ssize, 0);
+ }
+
+ if (unlikely(slot == -1 || soft_invalid)) {
+ /*
+ * For soft invalid slot, let's ensure that we release a
+ * slot from the primary, with the hope that we will
+ * acquire that slot next time we try. This will ensure
+ * that we do not get the same soft-invalid slot.
+ */
+ if (soft_invalid || (mftb() & 0x1))
hpte_group = ((hash & htab_hash_mask) *
HPTES_PER_GROUP) & ~0x7UL;
+
mmu_hash_ops.hpte_remove(hpte_group);
/*
* FIXME!! Should be try the group from which we removed ?
@@ -198,21 +213,10 @@ repeat:
MMU_PAGE_4K, MMU_PAGE_4K, old_pte);
return -1;
}
- /*
- * Insert slot number & secondary bit in PTE second half,
- * clear H_PAGE_BUSY and set appropriate HPTE slot bit
- * Since we have H_PAGE_BUSY set on ptep, we can be sure
- * nobody is undating hidx.
- */
- hidxp = (unsigned long *)(ptep + PTRS_PER_PTE);
- rpte.hidx &= ~(0xfUL << (subpg_index << 2));
- *hidxp = rpte.hidx | (slot << (subpg_index << 2));
- new_pte = mark_subptegroup_valid(new_pte, subpg_index);
- new_pte |= H_PAGE_HASHPTE;
- /*
- * check __real_pte for details on matching smp_rmb()
- */
- smp_wmb();
+
+ new_pte |= pte_set_hidx(ptep, rpte, subpg_index, slot);
+ new_pte |= H_PAGE_HASHPTE;
+
*ptep = __pte(new_pte & ~H_PAGE_BUSY);
return 0;
}