[PATCH -V5 24/25] powerpc: Optimize hugepage invalidate
David Gibson
dwg at au1.ibm.com
Mon Apr 15 11:18:51 EST 2013
On Sun, Apr 14, 2013 at 03:32:12PM +0530, Aneesh Kumar K.V wrote:
> David Gibson <dwg at au1.ibm.com> writes:
>
> > On Thu, Apr 04, 2013 at 11:28:02AM +0530, Aneesh Kumar K.V wrote:
> >> From: "Aneesh Kumar K.V" <aneesh.kumar at linux.vnet.ibm.com>
> >>
> >> 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: Aneesh Kumar K.V <aneesh.kumar at linux.vnet.ibm.com>
> >> ---
> >> arch/powerpc/include/asm/machdep.h | 3 +
> >> arch/powerpc/mm/hash_native_64.c | 78 ++++++++++++++++++++
> >> arch/powerpc/mm/pgtable.c | 13 +++-
> >> arch/powerpc/platforms/pseries/lpar.c | 126 +++++++++++++++++++++++++++++++--
> >> 4 files changed, 210 insertions(+), 10 deletions(-)
> >>
> >> diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
> >> index 6cee6e0..3bc7816 100644
> >> --- a/arch/powerpc/include/asm/machdep.h
> >> +++ b/arch/powerpc/include/asm/machdep.h
> >> @@ -56,6 +56,9 @@ struct machdep_calls {
> >> void (*hpte_removebolted)(unsigned long ea,
> >> int psize, int ssize);
> >> 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
> >> * destroyed as well */
> >> diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
> >> index ac84fa6..59f29bf 100644
> >> --- a/arch/powerpc/mm/hash_native_64.c
> >> +++ b/arch/powerpc/mm/hash_native_64.c
> >> @@ -450,6 +450,83 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
> >> 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 = HUGE_PAGE_SIZE/(1ul << shift);
> >> +
> >> + local_irq_save(flags);
> >> + for (i = 0; i < max_hpte_count; i++) {
> >> + /*
> >> + * 8 bits per each hpte entries
> >> + * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit]
> >> + */
> >> + valid = hpte_slot_array[i] & 0x1;
> >> + if (!valid)
> >> + continue;
> >> + hidx = hpte_slot_array[i] >> 1;
> >> +
> >> + /* 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;
> >
> > Shouldn't you be clearing the entry from the slot_array once it is
> > invalidated in the hash table?
>
> We don't need to do that. We should be fine even if hptes get
> invalidated under us. Also inorder to update slot_array i will have to
> mark the corresponding hpte busy, so that we can ensure nobody is
> looking at the slot array.
Hm, ok.
> >> + }
> >> + /*
> >> + * 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 void hpte_decode(struct hash_pte *hpte, unsigned long slot,
> >> int *psize, int *apsize, int *ssize, unsigned long *vpn)
> >> {
> >> @@ -678,4 +755,5 @@ 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;
> >> }
> >> diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
> >> index fbff062..386cab8 100644
> >> --- a/arch/powerpc/mm/pgtable.c
> >> +++ b/arch/powerpc/mm/pgtable.c
> >> @@ -433,6 +433,7 @@ void hpte_need_hugepage_flush(struct mm_struct *mm, unsigned long addr,
> >> {
> >> int ssize, i;
> >> unsigned long s_addr;
> >> + int max_hpte_count;
> >> unsigned int psize, valid;
> >> unsigned char *hpte_slot_array;
> >> unsigned long hidx, vpn, vsid, hash, shift, slot;
> >> @@ -446,12 +447,18 @@ void hpte_need_hugepage_flush(struct mm_struct *mm, unsigned long addr,
> >> * second half of the PMD
> >> */
> >> hpte_slot_array = *(char **)(pmdp + PTRS_PER_PMD);
> >> -
> >> /* get the base page size */
> >> psize = get_slice_psize(mm, s_addr);
> >> - shift = mmu_psize_defs[psize].shift;
> >>
> >> - for (i = 0; i < HUGE_PAGE_SIZE/(1ul << 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 = HUGE_PAGE_SIZE/(1ul << shift);
> >> + for (i = 0; i < max_hpte_count; i++) {
> >> /*
> >> * 8 bits per each hpte entries
> >> * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit]
> >> diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
> >> index 3daced3..5fcc621 100644
> >> --- a/arch/powerpc/platforms/pseries/lpar.c
> >> +++ b/arch/powerpc/platforms/pseries/lpar.c
> >> @@ -45,6 +45,13 @@
> >> #include "plpar_wrappers.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 */
> >> EXPORT_SYMBOL(plpar_hcall);
> >> @@ -339,6 +346,117 @@ static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
> >> 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[9];
> >> + 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,
> >> + 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];
> >
> > These are really too big to be allocating on the stack. You'd be
> > better off going direct from the char slot array to the data structure
> > for H_BULK_REMOVE, rather than introducing this intermediate
> > structure.
>
> The reason i wanted to do that was to make sure i don't lock/unlock
> pSeries_lpar_tlbie_lock that frequently, ie, for ever H_BULK_REMOVE.
> The total size taken by both the array is only 192 bytes. Is that big
> enough to create trouble ?
Oh, sorry, I missed the batch invalidate. I think 192 bytes is
borderline - Paul or Ben might know better.
--
David Gibson | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
| _way_ _around_!
http://www.ozlabs.org/~dgibson
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 198 bytes
Desc: Digital signature
URL: <http://lists.ozlabs.org/pipermail/linuxppc-dev/attachments/20130415/f4560995/attachment.sig>
More information about the Linuxppc-dev
mailing list