[3.13.y.z extended stable] Patch "powerpc/thp: Invalidate old 64K based hash page mapping before insert of 4k pte" has been added to staging queue

Kamal Mostafa kamal at canonical.com
Mon Sep 15 22:08:07 UTC 2014


This is a note to let you know that I have just added a patch titled

    powerpc/thp: Invalidate old 64K based hash page mapping before insert of 4k pte

to the linux-3.13.y-queue branch of the 3.13.y.z extended stable tree 
which can be found at:

 http://kernel.ubuntu.com/git?p=ubuntu/linux.git;a=shortlog;h=refs/heads/linux-3.13.y-queue

This patch is scheduled to be released in version 3.13.11.7.

If you, or anyone else, feels it should not be added to this tree, please 
reply to this email.

For more information about the 3.13.y.z tree, see
https://wiki.ubuntu.com/Kernel/Dev/ExtendedStable

Thanks.
-Kamal

------

>From 1c3b4c9086a70f3bbea57b320c7c8b5a928dcec4 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar at linux.vnet.ibm.com>
Date: Wed, 13 Aug 2014 12:31:59 +0530
Subject: powerpc/thp: Invalidate old 64K based hash page mapping before insert
 of 4k pte

commit 629149fae478f0ac6bf705a535708b192e9c6b59 upstream.

If we changed base page size of the segment, either via sub_page_protect
or via remap_4k_pfn, we do a demote_segment which doesn't flush the hash
table entries. We do a lazy hash page table flush for all mapped pages
in the demoted segment. This happens when we handle hash page fault
for these pages.

We use _PAGE_COMBO bit along with _PAGE_HASHPTE to indicate whether a
pte is backed by 4K hash pte. If we find _PAGE_COMBO not set on the pte,
that implies that we could possibly have older 64K hash pte entries in
the hash page table and we need to invalidate those entries.

Handle this correctly for 16M pages

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar at linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh at kernel.crashing.org>
[ kamal: backport to 3.13-stable: context ]
Signed-off-by: Kamal Mostafa <kamal at canonical.com>
---
 arch/powerpc/mm/hugepage-hash64.c | 79 ++++++++++++++++++++++++++++++++++-----
 1 file changed, 70 insertions(+), 9 deletions(-)

diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c
index f50c4df..e0da847 100644
--- a/arch/powerpc/mm/hugepage-hash64.c
+++ b/arch/powerpc/mm/hugepage-hash64.c
@@ -18,6 +18,57 @@
 #include <linux/mm.h>
 #include <asm/machdep.h>

+static void invalidate_old_hpte(unsigned long vsid, unsigned long addr,
+				pmd_t *pmdp, unsigned int psize, int ssize)
+{
+	int i, max_hpte_count, valid;
+	unsigned long s_addr;
+	unsigned char *hpte_slot_array;
+	unsigned long hidx, shift, vpn, hash, slot;
+
+	s_addr = addr & HPAGE_PMD_MASK;
+	hpte_slot_array = get_hpte_slot_array(pmdp);
+	/*
+	 * IF we try to do a HUGE PTE update after a withdraw is done.
+	 * we will find the below NULL. This happens when we do
+	 * split_huge_page_pmd
+	 */
+	if (!hpte_slot_array)
+		return;
+
+	if (ppc_md.hugepage_invalidate)
+		return ppc_md.hugepage_invalidate(vsid, s_addr, hpte_slot_array,
+						  psize, ssize);
+	/*
+	 * 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
+		 * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit]
+		 */
+		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));
+		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;
+		ppc_md.hpte_invalidate(slot, vpn, psize,
+				       MMU_PAGE_16M, ssize, 0);
+	}
+}
+
+
 int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 		    pmd_t *pmdp, unsigned long trap, int local, int ssize,
 		    unsigned int psize)
@@ -85,6 +136,15 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 	vpn = hpt_vpn(ea, vsid, ssize);
 	hash = hpt_hash(vpn, shift, ssize);
 	hpte_slot_array = get_hpte_slot_array(pmdp);
+	if (psize == MMU_PAGE_4K) {
+		/*
+		 * invalidate the old hpte entry if we have that mapped via 64K
+		 * base page size. This is because demote_segment won't flush
+		 * hash page table entries.
+		 */
+		if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO))
+			invalidate_old_hpte(vsid, ea, pmdp, MMU_PAGE_64K, ssize);
+	}

 	valid = hpte_valid(hpte_slot_array, index);
 	if (valid) {
@@ -107,11 +167,8 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 			 * safely update this here.
 			 */
 			valid = 0;
-			new_pmd &= ~_PAGE_HPTEFLAGS;
 			hpte_slot_array[index] = 0;
-		} else
-			/* clear the busy bits and set the hash pte bits */
-			new_pmd = (new_pmd & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE;
+		}
 	}

 	if (!valid) {
@@ -119,15 +176,13 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,

 		/* insert new entry */
 		pa = pmd_pfn(__pmd(old_pmd)) << PAGE_SHIFT;
-repeat:
-		hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;
-
-		/* clear the busy bits and set the hash pte bits */
-		new_pmd = (new_pmd & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE;
+		new_pmd |= _PAGE_HASHPTE;

 		/* Add in WIMG bits */
 		rflags |= (new_pmd & (_PAGE_WRITETHRU | _PAGE_NO_CACHE |
 				      _PAGE_COHERENT | _PAGE_GUARDED));
+repeat:
+		hpte_group = ((hash & htab_hash_mask) * HPTES_PER_GROUP) & ~0x7UL;

 		/* Insert into the hash table, primary slot */
 		slot = ppc_md.hpte_insert(hpte_group, vpn, pa, rflags, 0,
@@ -168,6 +223,12 @@ repeat:
 		mark_hpte_slot_valid(hpte_slot_array, index, slot);
 	}
 	/*
+	 * Mark the pte with _PAGE_COMBO, if we are trying to hash it with
+	 * base page size 4k.
+	 */
+	if (psize == MMU_PAGE_4K)
+		new_pmd |= _PAGE_COMBO;
+	/*
 	 * The hpte valid is stored in the pgtable whose address is in the
 	 * second half of the PMD. Order this against clearing of the busy bit in
 	 * huge pmd.
--
1.9.1





More information about the kernel-team mailing list