linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: David Gibson <dwg@au1.ibm.com>
To: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: benh@kernel.crashing.org, paulus@samba.org, linux-mm@kvack.org,
	linuxppc-dev@lists.ozlabs.org
Subject: Re: [PATCH -V5 24/25] powerpc: Optimize hugepage invalidate
Date: Fri, 12 Apr 2013 14:21:04 +1000	[thread overview]
Message-ID: <20130412042104.GH5065@truffula.fritz.box> (raw)
In-Reply-To: <1365055083-31956-25-git-send-email-aneesh.kumar@linux.vnet.ibm.com>

[-- Attachment #1: Type: text/plain, Size: 11529 bytes --]

On Thu, Apr 04, 2013 at 11:28:02AM +0530, Aneesh Kumar K.V wrote:
> From: "Aneesh Kumar K.V" <aneesh.kumar@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@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?

> +	}
> +	/*
> +	 * 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.

> +	unsigned long shift, hidx, vpn = 0, vsid, hash, slot;
> +
> +	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]
> +		 */
> +		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;
> +
> +		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,
>  					   int psize, int ssize)
>  {
> @@ -354,13 +472,6 @@ static void pSeries_lpar_hpte_removebolted(unsigned long ea,
>  	pSeries_lpar_hpte_invalidate(slot, vpn, psize, 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
>   * lock.
> @@ -446,6 +557,7 @@ void __init hpte_init_lpar(void)
>  	ppc_md.hpte_removebolted = pSeries_lpar_hpte_removebolted;
>  	ppc_md.flush_hash_range	= pSeries_lpar_flush_hash_range;
>  	ppc_md.hpte_clear_all   = pSeries_lpar_hptab_clear;
> +	ppc_md.hugepage_invalidate = pSeries_lpar_hugepage_invalidate;
>  }
>  
>  #ifdef CONFIG_PPC_SMLPAR

-- 
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

[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 198 bytes --]

  reply	other threads:[~2013-04-12  4:21 UTC|newest]

Thread overview: 73+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-04-04  5:57 [PATCH -V5 00/25] THP support for PPC64 Aneesh Kumar K.V
2013-04-04  5:57 ` [PATCH -V5 01/25] powerpc: Use signed formatting when printing error Aneesh Kumar K.V
2013-04-04  5:57 ` [PATCH -V5 02/25] powerpc: Save DAR and DSISR in pt_regs on MCE Aneesh Kumar K.V
2013-04-04  5:57 ` [PATCH -V5 03/25] powerpc: Don't hard code the size of pte page Aneesh Kumar K.V
2013-04-04  5:57 ` [PATCH -V5 04/25] powerpc: Reduce the PTE_INDEX_SIZE Aneesh Kumar K.V
2013-04-11  7:10   ` David Gibson
2013-04-04  5:57 ` [PATCH -V5 05/25] powerpc: Move the pte free routines from common header Aneesh Kumar K.V
2013-04-04  5:57 ` [PATCH -V5 06/25] powerpc: Reduce PTE table memory wastage Aneesh Kumar K.V
2013-04-10  4:46   ` David Gibson
2013-04-10  6:29     ` Aneesh Kumar K.V
2013-04-10  7:04       ` David Gibson
2013-04-10  7:53         ` Aneesh Kumar K.V
2013-04-10 17:47           ` Aneesh Kumar K.V
2013-04-11  1:20             ` David Gibson
2013-04-11  1:12           ` David Gibson
2013-04-10  7:14   ` Michael Ellerman
2013-04-10  7:54     ` Aneesh Kumar K.V
2013-04-10  8:52       ` Aneesh Kumar K.V
2013-04-04  5:57 ` [PATCH -V5 07/25] powerpc: Use encode avpn where we need only avpn values Aneesh Kumar K.V
2013-04-04  5:57 ` [PATCH -V5 08/25] powerpc: Decode the pte-lp-encoding bits correctly Aneesh Kumar K.V
2013-04-10  7:19   ` David Gibson
2013-04-10  8:11     ` Aneesh Kumar K.V
2013-04-10 17:49       ` Aneesh Kumar K.V
2013-04-11  1:28       ` David Gibson
2013-04-04  5:57 ` [PATCH -V5 09/25] powerpc: Fix hpte_decode to use the correct decoding for page sizes Aneesh Kumar K.V
2013-04-11  3:20   ` David Gibson
2013-04-04  5:57 ` [PATCH -V5 10/25] powerpc: print both base and actual page size on hash failure Aneesh Kumar K.V
2013-04-11  3:21   ` David Gibson
2013-04-04  5:57 ` [PATCH -V5 11/25] powerpc: Print page size info during boot Aneesh Kumar K.V
2013-04-04  5:57 ` [PATCH -V5 12/25] powerpc: Return all the valid pte ecndoing in KVM_PPC_GET_SMMU_INFO ioctl Aneesh Kumar K.V
2013-04-11  3:24   ` David Gibson
2013-04-11  5:11     ` Aneesh Kumar K.V
2013-04-11  5:57       ` David Gibson
2013-04-04  5:57 ` [PATCH -V5 13/25] powerpc: Update tlbie/tlbiel as per ISA doc Aneesh Kumar K.V
2013-04-11  3:30   ` David Gibson
2013-04-11  5:20     ` Aneesh Kumar K.V
2013-04-11  6:16       ` David Gibson
2013-04-11  6:36         ` Aneesh Kumar K.V
2013-04-04  5:57 ` [PATCH -V5 14/25] mm/THP: HPAGE_SHIFT is not a #define on some arch Aneesh Kumar K.V
2013-04-11  3:36   ` David Gibson
2013-04-04  5:57 ` [PATCH -V5 15/25] mm/THP: Add pmd args to pgtable deposit and withdraw APIs Aneesh Kumar K.V
2013-04-11  3:40   ` David Gibson
2013-04-04  5:57 ` [PATCH -V5 16/25] mm/THP: withdraw the pgtable after pmdp related operations Aneesh Kumar K.V
2013-04-04  5:57 ` [PATCH -V5 17/25] powerpc/THP: Implement transparent hugepages for ppc64 Aneesh Kumar K.V
2013-04-11  5:38   ` David Gibson
2013-04-11  7:40     ` Aneesh Kumar K.V
2013-04-12  0:51       ` David Gibson
2013-04-12  5:06         ` Aneesh Kumar K.V
2013-04-12  5:39           ` David Gibson
2013-04-04  5:57 ` [PATCH -V5 18/25] powerpc/THP: Double the PMD table size for THP Aneesh Kumar K.V
2013-04-11  6:18   ` David Gibson
2013-04-04  5:57 ` [PATCH -V5 19/25] powerpc/THP: Differentiate THP PMD entries from HUGETLB PMD entries Aneesh Kumar K.V
2013-04-10  7:21   ` Michael Ellerman
2013-04-10 18:26     ` Aneesh Kumar K.V
2013-04-12  1:28   ` David Gibson
2013-04-04  5:57 ` [PATCH -V5 20/25] powerpc/THP: Add code to handle HPTE faults for large pages Aneesh Kumar K.V
2013-04-12  4:01   ` David Gibson
2013-04-04  5:57 ` [PATCH -V5 21/25] powerpc: Handle hugepage in perf callchain Aneesh Kumar K.V
2013-04-12  1:34   ` David Gibson
2013-04-12  5:05     ` Aneesh Kumar K.V
2013-04-04  5:58 ` [PATCH -V5 22/25] powerpc/THP: get_user_pages_fast changes Aneesh Kumar K.V
2013-04-12  1:41   ` David Gibson
2013-04-04  5:58 ` [PATCH -V5 23/25] powerpc/THP: Enable THP on PPC64 Aneesh Kumar K.V
2013-04-04  5:58 ` [PATCH -V5 24/25] powerpc: Optimize hugepage invalidate Aneesh Kumar K.V
2013-04-12  4:21   ` David Gibson [this message]
2013-04-14 10:02     ` Aneesh Kumar K.V
2013-04-15  1:18       ` David Gibson
2013-04-04  5:58 ` [PATCH -V5 25/25] powerpc: Handle hugepages in kvm Aneesh Kumar K.V
2013-04-04  6:00 ` [PATCH -V5 00/25] THP support for PPC64 Simon Jeons
2013-04-04  6:10   ` Aneesh Kumar K.V
2013-04-04  6:14 ` Simon Jeons
2013-04-04  8:38   ` Aneesh Kumar K.V
2013-04-19  1:55 ` Simon Jeons

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20130412042104.GH5065@truffula.fritz.box \
    --to=dwg@au1.ibm.com \
    --cc=aneesh.kumar@linux.vnet.ibm.com \
    --cc=benh@kernel.crashing.org \
    --cc=linux-mm@kvack.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=paulus@samba.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).