Commit 1a527286 authored by Aneesh Kumar K.V's avatar Aneesh Kumar K.V Committed by Benjamin Herrenschmidt

powerpc: Optimize hugepage invalidate

Hugepage invalidate involves invalidating multiple hpte entries.
Optimize the operation using H_BULK_REMOVE on lpar platforms.
On native, reduce the number of tlb flush.
Signed-off-by: default avatarAneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: default avatarBenjamin Herrenschmidt <benh@kernel.crashing.org>
parent 437d4964
...@@ -57,6 +57,9 @@ struct machdep_calls { ...@@ -57,6 +57,9 @@ struct machdep_calls {
void (*hpte_removebolted)(unsigned long ea, void (*hpte_removebolted)(unsigned long ea,
int psize, int ssize); int psize, int ssize);
void (*flush_hash_range)(unsigned long number, int local); void (*flush_hash_range)(unsigned long number, int local);
void (*hugepage_invalidate)(struct mm_struct *mm,
unsigned char *hpte_slot_array,
unsigned long addr, int psize);
/* special for kexec, to be called in real mode, linear mapping is /* special for kexec, to be called in real mode, linear mapping is
* destroyed as well */ * destroyed as well */
......
...@@ -407,6 +407,78 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn, ...@@ -407,6 +407,78 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
local_irq_restore(flags); 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 = 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) static inline int __hpte_actual_psize(unsigned int lp, int psize)
{ {
int i, shift; int i, shift;
...@@ -640,4 +712,5 @@ void __init hpte_init_native(void) ...@@ -640,4 +712,5 @@ void __init hpte_init_native(void)
ppc_md.hpte_remove = native_hpte_remove; ppc_md.hpte_remove = native_hpte_remove;
ppc_md.hpte_clear_all = native_hpte_clear; ppc_md.hpte_clear_all = native_hpte_clear;
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;
} }
...@@ -708,6 +708,7 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr, ...@@ -708,6 +708,7 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
{ {
int ssize, i; int ssize, i;
unsigned long s_addr; unsigned long s_addr;
int max_hpte_count;
unsigned int psize, valid; unsigned int psize, valid;
unsigned char *hpte_slot_array; unsigned char *hpte_slot_array;
unsigned long hidx, vpn, vsid, hash, shift, slot; unsigned long hidx, vpn, vsid, hash, shift, slot;
...@@ -727,9 +728,16 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr, ...@@ -727,9 +728,16 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
/* get the base page size */ /* get the base page size */
psize = get_slice_psize(mm, s_addr); psize = get_slice_psize(mm, s_addr);
shift = mmu_psize_defs[psize].shift;
for (i = 0; i < (HPAGE_PMD_SIZE >> shift); i++) { if (ppc_md.hugepage_invalidate)
return ppc_md.hugepage_invalidate(mm, hpte_slot_array,
s_addr, psize);
/*
* No bluk hpte removal support, invalidate each entry
*/
shift = mmu_psize_defs[psize].shift;
max_hpte_count = HPAGE_PMD_SIZE >> shift;
for (i = 0; i < max_hpte_count; i++) {
/* /*
* 8 bits per each hpte entries * 8 bits per each hpte entries
* 000| [ secondary group (one bit) | hidx (3 bits) | valid bit] * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit]
......
...@@ -45,6 +45,13 @@ ...@@ -45,6 +45,13 @@
#include "plpar_wrappers.h" #include "plpar_wrappers.h"
#include "pseries.h" #include "pseries.h"
/* Flag bits for H_BULK_REMOVE */
#define HBR_REQUEST 0x4000000000000000UL
#define HBR_RESPONSE 0x8000000000000000UL
#define HBR_END 0xc000000000000000UL
#define HBR_AVPN 0x0200000000000000UL
#define HBR_ANDCOND 0x0100000000000000UL
/* in hvCall.S */ /* in hvCall.S */
EXPORT_SYMBOL(plpar_hcall); EXPORT_SYMBOL(plpar_hcall);
...@@ -347,6 +354,113 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn, ...@@ -347,6 +354,113 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
BUG_ON(lpar_rc != H_SUCCESS); BUG_ON(lpar_rc != H_SUCCESS);
} }
/*
* Limit iterations holding pSeries_lpar_tlbie_lock to 3. We also need
* to make sure that we avoid bouncing the hypervisor tlbie lock.
*/
#define PPC64_HUGE_HPTE_BATCH 12
static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
unsigned long *vpn, int count,
int psize, int ssize)
{
unsigned long param[8];
int i = 0, pix = 0, rc;
unsigned long flags = 0;
int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
if (lock_tlbie)
spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags);
for (i = 0; i < count; i++) {
if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
pSeries_lpar_hpte_invalidate(slot[i], vpn[i], psize, 0,
ssize, 0);
} else {
param[pix] = HBR_REQUEST | HBR_AVPN | slot[i];
param[pix+1] = hpte_encode_avpn(vpn[i], psize, ssize);
pix += 2;
if (pix == 8) {
rc = plpar_hcall9(H_BULK_REMOVE, param,
param[0], param[1], param[2],
param[3], param[4], param[5],
param[6], param[7]);
BUG_ON(rc != H_SUCCESS);
pix = 0;
}
}
}
if (pix) {
param[pix] = HBR_END;
rc = plpar_hcall9(H_BULK_REMOVE, param, param[0], param[1],
param[2], param[3], param[4], param[5],
param[6], param[7]);
BUG_ON(rc != H_SUCCESS);
}
if (lock_tlbie)
spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags);
}
static void pSeries_lpar_hugepage_invalidate(struct mm_struct *mm,
unsigned char *hpte_slot_array,
unsigned long addr, int psize)
{
int ssize = 0, i, index = 0;
unsigned long s_addr = addr;
unsigned int max_hpte_count, valid;
unsigned long vpn_array[PPC64_HUGE_HPTE_BATCH];
unsigned long slot_array[PPC64_HUGE_HPTE_BATCH];
unsigned long shift, hidx, vpn = 0, vsid, hash, slot;
shift = mmu_psize_defs[psize].shift;
max_hpte_count = 1U << (PMD_SHIFT - shift);
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;
slot_array[index] = slot;
vpn_array[index] = vpn;
if (index == PPC64_HUGE_HPTE_BATCH - 1) {
/*
* Now do a bluk invalidate
*/
__pSeries_lpar_hugepage_invalidate(slot_array,
vpn_array,
PPC64_HUGE_HPTE_BATCH,
psize, ssize);
index = 0;
} else
index++;
}
if (index)
__pSeries_lpar_hugepage_invalidate(slot_array, vpn_array,
index, psize, ssize);
}
static void pSeries_lpar_hpte_removebolted(unsigned long ea, static void pSeries_lpar_hpte_removebolted(unsigned long ea,
int psize, int ssize) int psize, int ssize)
{ {
...@@ -364,13 +478,6 @@ static void pSeries_lpar_hpte_removebolted(unsigned long ea, ...@@ -364,13 +478,6 @@ static void pSeries_lpar_hpte_removebolted(unsigned long ea,
pSeries_lpar_hpte_invalidate(slot, vpn, psize, 0, ssize, 0); pSeries_lpar_hpte_invalidate(slot, vpn, psize, 0, ssize, 0);
} }
/* Flag bits for H_BULK_REMOVE */
#define HBR_REQUEST 0x4000000000000000UL
#define HBR_RESPONSE 0x8000000000000000UL
#define HBR_END 0xc000000000000000UL
#define HBR_AVPN 0x0200000000000000UL
#define HBR_ANDCOND 0x0100000000000000UL
/* /*
* Take a spinlock around flushes to avoid bouncing the hypervisor tlbie * Take a spinlock around flushes to avoid bouncing the hypervisor tlbie
* lock. * lock.
...@@ -459,6 +566,7 @@ void __init hpte_init_lpar(void) ...@@ -459,6 +566,7 @@ void __init hpte_init_lpar(void)
ppc_md.hpte_removebolted = pSeries_lpar_hpte_removebolted; ppc_md.hpte_removebolted = pSeries_lpar_hpte_removebolted;
ppc_md.flush_hash_range = pSeries_lpar_flush_hash_range; ppc_md.flush_hash_range = pSeries_lpar_flush_hash_range;
ppc_md.hpte_clear_all = pSeries_lpar_hptab_clear; ppc_md.hpte_clear_all = pSeries_lpar_hptab_clear;
ppc_md.hugepage_invalidate = pSeries_lpar_hugepage_invalidate;
} }
#ifdef CONFIG_PPC_SMLPAR #ifdef CONFIG_PPC_SMLPAR
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment