From 7d24f0b8a53261709938ffabe3e00f88f6498df9 Mon Sep 17 00:00:00 2001 From: David Gibson Date: Mon, 7 Nov 2005 00:57:52 -0800 Subject: [PATCH] [PATCH] ppc64: Fix bug in SLB miss handler for hugepages This patch, however, should be applied on top of the 64k-page-size patch to fix some problems with hugepage (some pre-existing, another introduced by this patch). The patch fixes a bug in the SLB miss handler for hugepages on ppc64 introduced by the dynamic hugepage patch (commit id c594adad5653491813959277fb87a2fef54c4e05) due to a misunderstanding of the srd instruction's behaviour (mea culpa). The problem arises when a 64-bit process maps some hugepages in the low 4GB of the address space (unusual). In this case, as well as the 256M segment in question being marked for hugepages, other segments at 32G intervals will be incorrectly marked for hugepages. In the process, this patch tweaks the semantics of the hugepage bitmaps to be more sensible. Previously, an address below 4G was marked for hugepages if the appropriate segment bit in the "low areas" bitmask was set *or* if the low bit in the "high areas" bitmap was set (which would mark all addresses below 1TB for hugepage). With this patch, any given address is governed by a single bitmap. Addresses below 4GB are marked for hugepage if and only if their bit is set in the "low areas" bitmap (256M granularity). Addresses between 4GB and 1TB are marked for hugepage iff the low bit in the "high areas" bitmap is set. Higher addresses are marked for hugepage iff their bit in the "high areas" bitmap is set (1TB granularity). To avoid conflicts, this patch must be applied on top of BenH's pending patch for 64k base page size [0]. As such, this patch also addresses a hugepage problem introduced by that patch. That patch allows hugepages of 1MB in size on hardware which supports it, however, that won't work when using 4k pages (4 level pagetable), because in that case hugepage PTEs are stored at the PMD level, and each PMD entry maps 2MB. This patch simply disallows hugepages in that case (we can do something cleverer to re-enable them some other day). Built, booted, and a handful of hugepage related tests passed on POWER5 LPAR (both ARCH=powerpc and ARCH=ppc64). [0] http://gate.crashing.org/~benh/ppc64-64k-pages.diff Signed-off-by: David Gibson Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/mm/hash_utils_64.c | 6 ++++-- arch/powerpc/mm/hugetlbpage.c | 6 ++++++ arch/powerpc/mm/slb_low.S | 13 +++++++++---- include/asm-ppc64/pgtable-4k.h | 3 +++ include/asm-ppc64/pgtable-64k.h | 3 +++ 5 files changed, 25 insertions(+), 6 deletions(-) diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index b2f3dbca695..f15dfb92dec 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -329,12 +329,14 @@ static void __init htab_init_page_sizes(void) */ if (mmu_psize_defs[MMU_PAGE_16M].shift) mmu_huge_psize = MMU_PAGE_16M; + /* With 4k/4level pagetables, we can't (for now) cope with a + * huge page size < PMD_SIZE */ else if (mmu_psize_defs[MMU_PAGE_1M].shift) mmu_huge_psize = MMU_PAGE_1M; /* Calculate HPAGE_SHIFT and sanity check it */ - if (mmu_psize_defs[mmu_huge_psize].shift > 16 && - mmu_psize_defs[mmu_huge_psize].shift < 28) + if (mmu_psize_defs[mmu_huge_psize].shift > MIN_HUGEPTE_SHIFT && + mmu_psize_defs[mmu_huge_psize].shift < SID_SHIFT) HPAGE_SHIFT = mmu_psize_defs[mmu_huge_psize].shift; else HPAGE_SHIFT = 0; /* No huge pages dude ! */ diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 0073a04047e..426c269e552 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -212,6 +212,12 @@ static int prepare_high_area_for_htlb(struct mm_struct *mm, unsigned long area) BUG_ON(area >= NUM_HIGH_AREAS); + /* Hack, so that each addresses is controlled by exactly one + * of the high or low area bitmaps, the first high area starts + * at 4GB, not 0 */ + if (start == 0) + start = 0x100000000UL; + /* Check no VMAs are in the region */ vma = find_vma(mm, start); if (vma && (vma->vm_start < end)) diff --git a/arch/powerpc/mm/slb_low.S b/arch/powerpc/mm/slb_low.S index 3e18241b6f3..950ffc5848c 100644 --- a/arch/powerpc/mm/slb_low.S +++ b/arch/powerpc/mm/slb_low.S @@ -80,12 +80,17 @@ _GLOBAL(slb_miss_kernel_load_virtual) BEGIN_FTR_SECTION b 1f END_FTR_SECTION_IFCLR(CPU_FTR_16M_PAGE) + cmpldi r10,16 + + lhz r9,PACALOWHTLBAREAS(r13) + mr r11,r10 + blt 5f + lhz r9,PACAHIGHHTLBAREAS(r13) srdi r11,r10,(HTLB_AREA_SHIFT-SID_SHIFT) - srd r9,r9,r11 - lhz r11,PACALOWHTLBAREAS(r13) - srd r11,r11,r10 - or. r9,r9,r11 + +5: srd r9,r9,r11 + andi. r9,r9,1 beq 1f _GLOBAL(slb_miss_user_load_huge) li r11,0 diff --git a/include/asm-ppc64/pgtable-4k.h b/include/asm-ppc64/pgtable-4k.h index c883a274855..e9590c06ad9 100644 --- a/include/asm-ppc64/pgtable-4k.h +++ b/include/asm-ppc64/pgtable-4k.h @@ -23,6 +23,9 @@ #define PMD_SIZE (1UL << PMD_SHIFT) #define PMD_MASK (~(PMD_SIZE-1)) +/* With 4k base page size, hugepage PTEs go at the PMD level */ +#define MIN_HUGEPTE_SHIFT PMD_SHIFT + /* PUD_SHIFT determines what a third-level page table entry can map */ #define PUD_SHIFT (PMD_SHIFT + PMD_INDEX_SIZE) #define PUD_SIZE (1UL << PUD_SHIFT) diff --git a/include/asm-ppc64/pgtable-64k.h b/include/asm-ppc64/pgtable-64k.h index c5f437c86b3..154f1840ece 100644 --- a/include/asm-ppc64/pgtable-64k.h +++ b/include/asm-ppc64/pgtable-64k.h @@ -14,6 +14,9 @@ #define PTRS_PER_PMD (1 << PMD_INDEX_SIZE) #define PTRS_PER_PGD (1 << PGD_INDEX_SIZE) +/* With 4k base page size, hugepage PTEs go at the PMD level */ +#define MIN_HUGEPTE_SHIFT PAGE_SHIFT + /* PMD_SHIFT determines what a second-level page table entry can map */ #define PMD_SHIFT (PAGE_SHIFT + PTE_INDEX_SIZE) #define PMD_SIZE (1UL << PMD_SHIFT) -- 2.41.1