The patch titled
Subject: powerpc/64s: use contiguous PMD/PUD instead of HUGEPD
has been added to the -mm mm-unstable branch. Its filename is
powerpc-64s-use-contiguous-pmd-pud-instead-of-hugepd.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/powerpc-64s-use-contiguous-pmd-pud-instead-of-hugepd.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Christophe Leroy <christophe.leroy@xxxxxxxxxx>
Subject: powerpc/64s: use contiguous PMD/PUD instead of HUGEPD
Date: Tue, 2 Jul 2024 15:51:33 +0200
On book3s/64, the only user of hugepd is hash in 4k mode.
All other setups (hash-64, radix-4, radix-64) use leaf PMD/PUD.
Rework hash-4k to use contiguous PMD and PUD instead.
In that setup there are only two huge page sizes: 16M and 16G.
16M sits at PMD level and 16G at PUD level.
pte_update doesn't know page size, lets use the same trick as
hpte_need_flush() to get page size from segment properties. That's not
the most efficient way but let's do that until callers of pte_update()
provide page size instead of just a huge flag.
Link: https://lkml.kernel.org/r/7448f60a9b3efd396595f4f735d1e0babc5ae379.1719928057.git.christophe.leroy@xxxxxxxxxx
Signed-off-by: Christophe Leroy <christophe.leroy@xxxxxxxxxx>
Acked-by: Michael Ellerman <mpe@xxxxxxxxxxxxxx> (powerpc)
Cc: Jason Gunthorpe <jgg@xxxxxxxxxx>
Cc: Nicholas Piggin <npiggin@xxxxxxxxx>
Cc: Oscar Salvador <osalvador@xxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
arch/powerpc/include/asm/book3s/64/hash-4k.h | 15 ----
arch/powerpc/include/asm/book3s/64/hash.h | 40 +++++++++--
arch/powerpc/include/asm/book3s/64/hugetlb.h | 38 ----------
arch/powerpc/include/asm/book3s/64/pgtable-4k.h | 47 -------------
arch/powerpc/include/asm/book3s/64/pgtable-64k.h | 20 -----
arch/powerpc/include/asm/book3s/64/pgtable.h | 22 +++++-
arch/powerpc/include/asm/hugetlb.h | 4 +
arch/powerpc/include/asm/nohash/hugetlb-e500.h | 4 -
arch/powerpc/include/asm/page.h | 8 --
arch/powerpc/mm/book3s64/hash_utils.c | 11 +--
arch/powerpc/mm/book3s64/hugetlbpage.c | 10 ++
arch/powerpc/mm/book3s64/pgtable.c | 12 ---
arch/powerpc/mm/hugetlbpage.c | 26 -------
arch/powerpc/mm/pgtable.c | 2
arch/powerpc/platforms/Kconfig.cputype | 1
15 files changed, 74 insertions(+), 186 deletions(-)
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h~powerpc-64s-use-contiguous-pmd-pud-instead-of-hugepd
+++ a/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -74,21 +74,6 @@
#define remap_4k_pfn(vma, addr, pfn, prot) \
remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE, (prot))
-#ifdef CONFIG_HUGETLB_PAGE
-static inline int hash__hugepd_ok(hugepd_t hpd)
-{
- unsigned long hpdval = hpd_val(hpd);
- /*
- * if it is not a pte and have hugepd shift mask
- * set, then it is a hugepd directory pointer
- */
- if (!(hpdval & _PAGE_PTE) && (hpdval & _PAGE_PRESENT) &&
- ((hpdval & HUGEPD_SHIFT_MASK) != 0))
- return true;
- return false;
-}
-#endif
-
/*
* 4K PTE format is different from 64K PTE format. Saving the hash_slot is just
* a matter of returning the PTE bits that need to be modified. On 64K PTE,
--- a/arch/powerpc/include/asm/book3s/64/hash.h~powerpc-64s-use-contiguous-pmd-pud-instead-of-hugepd
+++ a/arch/powerpc/include/asm/book3s/64/hash.h
@@ -4,6 +4,7 @@
#ifdef __KERNEL__
#include <asm/asm-const.h>
+#include <asm/book3s/64/slice.h>
/*
* Common bits between 4K and 64K pages in a linux-style PTE.
@@ -161,14 +162,10 @@ extern void hpte_need_flush(struct mm_st
pte_t *ptep, unsigned long pte, int huge);
unsigned long htab_convert_pte_flags(unsigned long pteflags, unsigned long flags);
/* Atomic PTE updates */
-static inline unsigned long hash__pte_update(struct mm_struct *mm,
- unsigned long addr,
- pte_t *ptep, unsigned long clr,
- unsigned long set,
- int huge)
+static inline unsigned long hash__pte_update_one(pte_t *ptep, unsigned long clr,
+ unsigned long set)
{
__be64 old_be, tmp_be;
- unsigned long old;
__asm__ __volatile__(
"1: ldarx %0,0,%3 # pte_update\n\
@@ -182,11 +179,40 @@ static inline unsigned long hash__pte_up
: "r" (ptep), "r" (cpu_to_be64(clr)), "m" (*ptep),
"r" (cpu_to_be64(H_PAGE_BUSY)), "r" (cpu_to_be64(set))
: "cc" );
+
+ return be64_to_cpu(old_be);
+}
+
+static inline unsigned long hash__pte_update(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep, unsigned long clr,
+ unsigned long set,
+ int huge)
+{
+ unsigned long old;
+
+ old = hash__pte_update_one(ptep, clr, set);
+
+ if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && huge) {
+ unsigned int psize = get_slice_psize(mm, addr);
+ int nb, i;
+
+ if (psize == MMU_PAGE_16M)
+ nb = SZ_16M / PMD_SIZE;
+ else if (psize == MMU_PAGE_16G)
+ nb = SZ_16G / PUD_SIZE;
+ else
+ nb = 1;
+
+ WARN_ON_ONCE(nb == 1); /* Should never happen */
+
+ for (i = 1; i < nb; i++)
+ hash__pte_update_one(ptep + i, clr, set);
+ }
/* huge pages use the old page table lock */
if (!huge)
assert_pte_locked(mm, addr);
- old = be64_to_cpu(old_be);
if (old & H_PAGE_HASHPTE)
hpte_need_flush(mm, addr, ptep, old, huge);
--- a/arch/powerpc/include/asm/book3s/64/hugetlb.h~powerpc-64s-use-contiguous-pmd-pud-instead-of-hugepd
+++ a/arch/powerpc/include/asm/book3s/64/hugetlb.h
@@ -49,9 +49,6 @@ static inline bool gigantic_page_runtime
return true;
}
-/* hugepd entry valid bit */
-#define HUGEPD_VAL_BITS (0x8000000000000000UL)
-
#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep);
@@ -60,29 +57,7 @@ extern pte_t huge_ptep_modify_prot_start
extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t old_pte, pte_t new_pte);
-/*
- * This should work for other subarchs too. But right now we use the
- * new format only for 64bit book3s
- */
-static inline pte_t *hugepd_page(hugepd_t hpd)
-{
- BUG_ON(!hugepd_ok(hpd));
- /*
- * We have only four bits to encode, MMU page size
- */
- BUILD_BUG_ON((MMU_PAGE_COUNT - 1) > 0xf);
- return __va(hpd_val(hpd) & HUGEPD_ADDR_MASK);
-}
-
-static inline unsigned int hugepd_mmu_psize(hugepd_t hpd)
-{
- return (hpd_val(hpd) & HUGEPD_SHIFT_MASK) >> 2;
-}
-static inline unsigned int hugepd_shift(hugepd_t hpd)
-{
- return mmu_psize_to_shift(hugepd_mmu_psize(hpd));
-}
static inline void flush_hugetlb_page(struct vm_area_struct *vma,
unsigned long vmaddr)
{
@@ -90,19 +65,6 @@ static inline void flush_hugetlb_page(st
return radix__flush_hugetlb_page(vma, vmaddr);
}
-static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
- unsigned int pdshift)
-{
- unsigned long idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(hpd);
-
- return hugepd_page(hpd) + idx;
-}
-
-static inline void hugepd_populate(hugepd_t *hpdp, pte_t *new, unsigned int pshift)
-{
- *hpdp = __hugepd(__pa(new) | HUGEPD_VAL_BITS | (shift_to_mmu_psize(pshift) << 2));
-}
-
void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
static inline int check_and_get_huge_psize(int shift)
--- a/arch/powerpc/include/asm/book3s/64/pgtable-4k.h
+++ /dev/null
@@ -1,47 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_4K_H
-#define _ASM_POWERPC_BOOK3S_64_PGTABLE_4K_H
-/*
- * hash 4k can't share hugetlb and also doesn't support THP
- */
-#ifndef __ASSEMBLY__
-#ifdef CONFIG_HUGETLB_PAGE
-/*
- * With radix , we have hugepage ptes in the pud and pmd entries. We don't
- * need to setup hugepage directory for them. Our pte and page directory format
- * enable us to have this enabled.
- */
-static inline int hugepd_ok(hugepd_t hpd)
-{
- if (radix_enabled())
- return 0;
- return hash__hugepd_ok(hpd);
-}
-#define is_hugepd(hpd) (hugepd_ok(hpd))
-
-/*
- * 16M and 16G huge page directory tables are allocated from slab cache
- *
- */
-#define H_16M_CACHE_INDEX (PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE - 24)
-#define H_16G_CACHE_INDEX \
- (PAGE_SHIFT + H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE + H_PUD_INDEX_SIZE - 34)
-
-static inline int get_hugepd_cache_index(int index)
-{
- switch (index) {
- case H_16M_CACHE_INDEX:
- return HTLB_16M_INDEX;
- case H_16G_CACHE_INDEX:
- return HTLB_16G_INDEX;
- default:
- BUG();
- }
- /* should not reach */
-}
-
-#endif /* CONFIG_HUGETLB_PAGE */
-
-#endif /* __ASSEMBLY__ */
-
-#endif /*_ASM_POWERPC_BOOK3S_64_PGTABLE_4K_H */
--- a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h~powerpc-64s-use-contiguous-pmd-pud-instead-of-hugepd
+++ a/arch/powerpc/include/asm/book3s/64/pgtable-64k.h
@@ -5,26 +5,6 @@
#ifndef __ASSEMBLY__
#ifdef CONFIG_HUGETLB_PAGE
-/*
- * With 64k page size, we have hugepage ptes in the pgd and pmd entries. We don't
- * need to setup hugepage directory for them. Our pte and page directory format
- * enable us to have this enabled.
- */
-static inline int hugepd_ok(hugepd_t hpd)
-{
- return 0;
-}
-
-#define is_hugepd(pdep) 0
-
-/*
- * This should never get called
- */
-static __always_inline int get_hugepd_cache_index(int index)
-{
- BUILD_BUG();
-}
-
#endif /* CONFIG_HUGETLB_PAGE */
static inline int remap_4k_pfn(struct vm_area_struct *vma, unsigned long addr,
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h~powerpc-64s-use-contiguous-pmd-pud-instead-of-hugepd
+++ a/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -274,6 +274,24 @@ static inline bool pud_leaf(pud_t pud)
{
return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PTE));
}
+
+#define pmd_leaf_size pmd_leaf_size
+static inline unsigned long pmd_leaf_size(pmd_t pmd)
+{
+ if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !radix_enabled())
+ return SZ_16M;
+ else
+ return PMD_SIZE;
+}
+
+#define pud_leaf_size pud_leaf_size
+static inline unsigned long pud_leaf_size(pud_t pud)
+{
+ if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !radix_enabled())
+ return SZ_16G;
+ else
+ return PUD_SIZE;
+}
#endif /* __ASSEMBLY__ */
#include <asm/book3s/64/hash.h>
@@ -285,11 +303,9 @@ static inline bool pud_leaf(pud_t pud)
#define MAX_PHYSMEM_BITS R_MAX_PHYSMEM_BITS
#endif
-
+/* hash 4k can't share hugetlb and also doesn't support THP */
#ifdef CONFIG_PPC_64K_PAGES
#include <asm/book3s/64/pgtable-64k.h>
-#else
-#include <asm/book3s/64/pgtable-4k.h>
#endif
#include <asm/barrier.h>
--- a/arch/powerpc/include/asm/hugetlb.h~powerpc-64s-use-contiguous-pmd-pud-instead-of-hugepd
+++ a/arch/powerpc/include/asm/hugetlb.h
@@ -37,6 +37,10 @@ void hugetlb_free_pgd_range(struct mmu_g
unsigned long ceiling);
#endif
+#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+ pte_t pte, unsigned long sz);
+
#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
--- a/arch/powerpc/include/asm/nohash/hugetlb-e500.h~powerpc-64s-use-contiguous-pmd-pud-instead-of-hugepd
+++ a/arch/powerpc/include/asm/nohash/hugetlb-e500.h
@@ -2,10 +2,6 @@
#ifndef _ASM_POWERPC_NOHASH_HUGETLB_E500_H
#define _ASM_POWERPC_NOHASH_HUGETLB_E500_H
-#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
- pte_t pte, unsigned long sz);
-
void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
static inline int check_and_get_huge_psize(int shift)
--- a/arch/powerpc/include/asm/page.h~powerpc-64s-use-contiguous-pmd-pud-instead-of-hugepd
+++ a/arch/powerpc/include/asm/page.h
@@ -269,14 +269,6 @@ static inline const void *pfn_to_kaddr(u
#define is_kernel_addr(x) ((x) >= TASK_SIZE)
#endif
-#ifdef CONFIG_PPC_BOOK3S_64
-/*
- * Book3S 64 stores real addresses in the hugepd entries to
- * avoid overlaps with _PAGE_PRESENT and _PAGE_PTE.
- */
-#define HUGEPD_ADDR_MASK (0x0ffffffffffffffful & ~HUGEPD_SHIFT_MASK)
-#endif /* CONFIG_PPC_BOOK3S_64 */
-
/*
* Some number of bits at the level of the page table that points to
* a hugepte are used to encode the size. This masks those bits.
--- a/arch/powerpc/mm/book3s64/hash_utils.c~powerpc-64s-use-contiguous-pmd-pud-instead-of-hugepd
+++ a/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1233,10 +1233,6 @@ void __init hash__early_init_mmu(void)
__pmd_table_size = H_PMD_TABLE_SIZE;
__pud_table_size = H_PUD_TABLE_SIZE;
__pgd_table_size = H_PGD_TABLE_SIZE;
- /*
- * 4k use hugepd format, so for hash set then to
- * zero
- */
__pmd_val_bits = HASH_PMD_VAL_BITS;
__pud_val_bits = HASH_PUD_VAL_BITS;
__pgd_val_bits = HASH_PGD_VAL_BITS;
@@ -1546,6 +1542,13 @@ int hash_page_mm(struct mm_struct *mm, u
goto bail;
}
+ if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !radix_enabled()) {
+ if (hugeshift == PMD_SHIFT && psize == MMU_PAGE_16M)
+ hugeshift = mmu_psize_defs[MMU_PAGE_16M].shift;
+ if (hugeshift == PUD_SHIFT && psize == MMU_PAGE_16G)
+ hugeshift = mmu_psize_defs[MMU_PAGE_16G].shift;
+ }
+
/*
* Add _PAGE_PRESENT to the required access perm. If there are parallel
* updates to the pte that can possibly clear _PAGE_PTE, catch that too.
--- a/arch/powerpc/mm/book3s64/hugetlbpage.c~powerpc-64s-use-contiguous-pmd-pud-instead-of-hugepd
+++ a/arch/powerpc/mm/book3s64/hugetlbpage.c
@@ -53,6 +53,16 @@ int __hash_page_huge(unsigned long ea, u
/* If PTE permissions don't match, take page fault */
if (unlikely(!check_pte_access(access, old_pte)))
return 1;
+ /*
+ * If hash-4k, hugepages use seeral contiguous PxD entries
+ * so bail out and let mm make the page young or dirty
+ */
+ if (IS_ENABLED(CONFIG_PPC_4K_PAGES)) {
+ if (!(old_pte & _PAGE_ACCESSED))
+ return 1;
+ if ((access & _PAGE_WRITE) && !(old_pte & _PAGE_DIRTY))
+ return 1;
+ }
/*
* Try to lock the PTE, add ACCESSED and DIRTY if it was
--- a/arch/powerpc/mm/book3s64/pgtable.c~powerpc-64s-use-contiguous-pmd-pud-instead-of-hugepd
+++ a/arch/powerpc/mm/book3s64/pgtable.c
@@ -461,18 +461,6 @@ static inline void pgtable_free(void *ta
case PUD_INDEX:
__pud_free(table);
break;
-#if defined(CONFIG_PPC_4K_PAGES) && defined(CONFIG_HUGETLB_PAGE)
- /* 16M hugepd directory at pud level */
- case HTLB_16M_INDEX:
- BUILD_BUG_ON(H_16M_CACHE_INDEX <= 0);
- kmem_cache_free(PGT_CACHE(H_16M_CACHE_INDEX), table);
- break;
- /* 16G hugepd directory at the pgd level */
- case HTLB_16G_INDEX:
- BUILD_BUG_ON(H_16G_CACHE_INDEX <= 0);
- kmem_cache_free(PGT_CACHE(H_16G_CACHE_INDEX), table);
- break;
-#endif
/* We don't free pgd table via RCU callback */
default:
BUG();
--- a/arch/powerpc/mm/hugetlbpage.c~powerpc-64s-use-contiguous-pmd-pud-instead-of-hugepd
+++ a/arch/powerpc/mm/hugetlbpage.c
@@ -592,40 +592,14 @@ static int __init hugetlbpage_init(void)
for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
unsigned shift;
- unsigned pdshift;
if (!mmu_psize_defs[psize].shift)
continue;
shift = mmu_psize_to_shift(psize);
-#ifdef CONFIG_PPC_BOOK3S_64
- if (shift > PGDIR_SHIFT)
- continue;
- else if (shift > PUD_SHIFT)
- pdshift = PGDIR_SHIFT;
- else if (shift > PMD_SHIFT)
- pdshift = PUD_SHIFT;
- else
- pdshift = PMD_SHIFT;
-#else
- if (shift < PUD_SHIFT)
- pdshift = PMD_SHIFT;
- else if (shift < PGDIR_SHIFT)
- pdshift = PUD_SHIFT;
- else
- pdshift = PGDIR_SHIFT;
-#endif
-
if (add_huge_page_size(1ULL << shift) < 0)
continue;
- /*
- * if we have pdshift and shift value same, we don't
- * use pgt cache for hugepd.
- */
- if (pdshift > shift) {
- pgtable_cache_add(pdshift - shift);
- }
configured = true;
}
--- a/arch/powerpc/mm/pgtable.c~powerpc-64s-use-contiguous-pmd-pud-instead-of-hugepd
+++ a/arch/powerpc/mm/pgtable.c
@@ -331,7 +331,7 @@ void set_huge_pte_at(struct mm_struct *m
__set_huge_pte_at(pmdp, ptep, pte_val(pte));
}
}
-#elif defined(CONFIG_PPC_E500)
+#else
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
pte_t pte, unsigned long sz)
{
--- a/arch/powerpc/platforms/Kconfig.cputype~powerpc-64s-use-contiguous-pmd-pud-instead-of-hugepd
+++ a/arch/powerpc/platforms/Kconfig.cputype
@@ -98,7 +98,6 @@ config PPC_BOOK3S_64
select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION
select ARCH_ENABLE_SPLIT_PMD_PTLOCK
select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
- select ARCH_HAS_HUGEPD if HUGETLB_PAGE
select ARCH_SUPPORTS_HUGETLBFS
select ARCH_SUPPORTS_NUMA_BALANCING
select HAVE_MOVE_PMD
_
Patches currently in -mm which might be from christophe.leroy@xxxxxxxxxx are
mm-define-__pte_leaf_size-to-also-take-a-pmd-entry.patch
mm-provide-mm_struct-and-address-to-huge_ptep_get.patch
powerpc-mm-remove-_page_psize.patch
powerpc-mm-fix-__find_linux_pte-on-32-bits-with-pmd-leaf-entries.patch
powerpc-mm-allow-hugepages-without-hugepd.patch
powerpc-8xx-fix-size-given-to-set_huge_pte_at.patch
powerpc-8xx-rework-support-for-8m-pages-using-contiguous-pte-entries.patch
powerpc-8xx-simplify-struct-mmu_psize_def.patch
powerpc-e500-remove-enc-and-ind-fields-from-struct-mmu_psize_def.patch
powerpc-e500-switch-to-64-bits-pgd-on-85xx-32-bits.patch
powerpc-e500-encode-hugepage-size-in-pte-bits.patch
powerpc-e500-dont-pre-check-write-access-on-data-tlb-error.patch
powerpc-e500-free-r10-for-find_pte.patch
powerpc-e500-use-contiguous-pmd-instead-of-hugepd.patch
powerpc-64s-use-contiguous-pmd-pud-instead-of-hugepd.patch
powerpc-mm-remove-hugepd-leftovers.patch
mm-remove-config_arch_has_hugepd.patch
