diff options
author | Stephen Rothwell <sfr@canb.auug.org.au> | 2022-12-02 14:38:54 +1100 |
---|---|---|
committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2022-12-02 14:38:54 +1100 |
commit | c44c7c2acd597ad856856451bc01a3ee20bd8ca5 (patch) | |
tree | d80060447b377c64be6fb58b988d1abef34bca0e | |
parent | 2942033c43e9f27201db72b23d5149ed78afdb32 (diff) | |
parent | 124483111b85e345ef4c4d3e5e389c77949e747b (diff) | |
download | linux-c44c7c2acd597ad856856451bc01a3ee20bd8ca5.tar.gz linux-c44c7c2acd597ad856856451bc01a3ee20bd8ca5.tar.xz |
Merge branch 'mm-everything' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
# Conflicts:
# mm/migrate.c
83 files changed, 2014 insertions, 948 deletions
@@ -228,6 +228,7 @@ Juha Yrjola <at solidboot.com> Juha Yrjola <juha.yrjola@nokia.com> Juha Yrjola <juha.yrjola@solidboot.com> Julien Thierry <julien.thierry.kdev@gmail.com> <julien.thierry@arm.com> +Iskren Chernev <me@iskren.info> <iskren.chernev@gmail.com> Kalle Valo <kvalo@kernel.org> <kvalo@codeaurora.org> Kalyan Thota <quic_kalyant@quicinc.com> <kalyan_t@codeaurora.org> Kay Sievers <kay.sievers@vrfy.org> @@ -287,6 +288,7 @@ Matthew Wilcox <willy@infradead.org> <willy@linux.intel.com> Matthew Wilcox <willy@infradead.org> <willy@parisc-linux.org> Matthias Fuchs <socketcan@esd.eu> <matthias.fuchs@esd.eu> Matthieu CASTET <castet.matthieu@free.fr> +Matti Vaittinen <mazziesaccount@gmail.com> <matti.vaittinen@fi.rohmeurope.com> Matt Ranostay <matt.ranostay@konsulko.com> <matt@ranostay.consulting> Matt Ranostay <mranostay@gmail.com> Matthew Ranostay <mranostay@embeddedalley.com> Matt Ranostay <mranostay@gmail.com> <matt.ranostay@intel.com> diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 6f0ff8b70d16..12915f379c22 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1137,53 +1137,28 @@ static void free_empty_tables(unsigned long addr, unsigned long end, } #endif +void __meminit vmemmap_set_pmd(pmd_t *pmdp, void *p, int node, + unsigned long addr, unsigned long next) +{ + pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL)); +} + +int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node, + unsigned long addr, unsigned long next) +{ + vmemmap_verify((pte_t *)pmdp, node, addr, next); + return 1; +} + int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap) { - unsigned long addr = start; - unsigned long next; - pgd_t *pgdp; - p4d_t *p4dp; - pud_t *pudp; - pmd_t *pmdp; - WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END)); if (!IS_ENABLED(CONFIG_ARM64_4K_PAGES)) return vmemmap_populate_basepages(start, end, node, altmap); - - do { - next = pmd_addr_end(addr, end); - - pgdp = vmemmap_pgd_populate(addr, node); - if (!pgdp) - return -ENOMEM; - - p4dp = vmemmap_p4d_populate(pgdp, addr, node); - if (!p4dp) - return -ENOMEM; - - pudp = vmemmap_pud_populate(p4dp, addr, node); - if (!pudp) - return -ENOMEM; - - pmdp = pmd_offset(pudp, addr); - if (pmd_none(READ_ONCE(*pmdp))) { - void *p = NULL; - - p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap); - if (!p) { - if (vmemmap_populate_basepages(addr, next, node, altmap)) - return -ENOMEM; - continue; - } - - pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL)); - } else - vmemmap_verify((pte_t *)pmdp, node, addr, next); - } while (addr = next, addr != end); - - return 0; + else + return vmemmap_populate_hugepages(start, end, node, altmap); } #ifdef CONFIG_MEMORY_HOTPLUG diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index ca26529a5a07..9cc8b84f7eb0 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -53,6 +53,7 @@ config LOONGARCH select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT + select ARCH_WANT_HUGETLB_PAGE_OPTIMIZE_VMEMMAP select ARCH_WANT_LD_ORPHAN_WARN select ARCH_WANTS_NO_INSTR select BUILDTIME_TABLE_SORT @@ -501,6 +502,7 @@ config ARCH_FLATMEM_ENABLE config ARCH_SPARSEMEM_ENABLE def_bool y + select SPARSEMEM_VMEMMAP_ENABLE help Say Y to support efficient handling of sparse physical memory, for architectures which are either NUMA (Non-Uniform Memory Access) diff --git a/arch/loongarch/include/asm/pgalloc.h b/arch/loongarch/include/asm/pgalloc.h index 4bfeb3c9c9ac..af1d1e4a6965 100644 --- a/arch/loongarch/include/asm/pgalloc.h +++ b/arch/loongarch/include/asm/pgalloc.h @@ -42,15 +42,6 @@ static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) extern void pagetable_init(void); -/* - * Initialize a new pmd table with invalid pointers. - */ -extern void pmd_init(unsigned long page, unsigned long pagetable); - -/* - * Initialize a new pgd / pmd table with invalid pointers. - */ -extern void pgd_init(unsigned long page); extern pgd_t *pgd_alloc(struct mm_struct *mm); #define __pte_free_tlb(tlb, pte, address) \ @@ -76,7 +67,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) } pmd = (pmd_t *)page_address(pg); - pmd_init((unsigned long)pmd, (unsigned long)invalid_pte_table); + pmd_init(pmd); return pmd; } @@ -92,7 +83,7 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) pud = (pud_t *) __get_free_page(GFP_KERNEL); if (pud) - pud_init((unsigned long)pud, (unsigned long)invalid_pmd_table); + pud_init(pud); return pud; } diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h index 754ee51e1ba8..7a34e900d8c1 100644 --- a/arch/loongarch/include/asm/pgtable.h +++ b/arch/loongarch/include/asm/pgtable.h @@ -11,6 +11,7 @@ #include <linux/compiler.h> #include <asm/addrspace.h> +#include <asm/page.h> #include <asm/pgtable-bits.h> #if CONFIG_PGTABLE_LEVELS == 2 @@ -59,6 +60,7 @@ #include <linux/mm_types.h> #include <linux/mmzone.h> #include <asm/fixmap.h> +#include <asm/sparsemem.h> struct mm_struct; struct vm_area_struct; @@ -86,7 +88,10 @@ extern unsigned long zero_page_mask; #define VMALLOC_START MODULES_END #define VMALLOC_END \ (vm_map_base + \ - min(PTRS_PER_PGD * PTRS_PER_PUD * PTRS_PER_PMD * PTRS_PER_PTE * PAGE_SIZE, (1UL << cpu_vabits)) - PMD_SIZE) + min(PTRS_PER_PGD * PTRS_PER_PUD * PTRS_PER_PMD * PTRS_PER_PTE * PAGE_SIZE, (1UL << cpu_vabits)) - PMD_SIZE - VMEMMAP_SIZE) + +#define vmemmap ((struct page *)((VMALLOC_END + PMD_SIZE) & PMD_MASK)) +#define VMEMMAP_END ((unsigned long)vmemmap + VMEMMAP_SIZE - 1) #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %016lx.\n", __FILE__, __LINE__, pte_val(e)) @@ -237,11 +242,11 @@ extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pm #define pfn_pmd(pfn, prot) __pmd(((pfn) << _PFN_SHIFT) | pgprot_val(prot)) /* - * Initialize a new pgd / pmd table with invalid pointers. + * Initialize a new pgd / pud / pmd table with invalid pointers. */ -extern void pgd_init(unsigned long page); -extern void pud_init(unsigned long page, unsigned long pagetable); -extern void pmd_init(unsigned long page, unsigned long pagetable); +extern void pgd_init(void *addr); +extern void pud_init(void *addr); +extern void pmd_init(void *addr); /* * Non-present pages: high 40 bits are offset, next 8 bits type, diff --git a/arch/loongarch/include/asm/sparsemem.h b/arch/loongarch/include/asm/sparsemem.h index 3d18cdf1b069..8d4af6aff8a8 100644 --- a/arch/loongarch/include/asm/sparsemem.h +++ b/arch/loongarch/include/asm/sparsemem.h @@ -11,8 +11,16 @@ #define SECTION_SIZE_BITS 29 /* 2^29 = Largest Huge Page Size */ #define MAX_PHYSMEM_BITS 48 +#ifdef CONFIG_SPARSEMEM_VMEMMAP +#define VMEMMAP_SIZE (sizeof(struct page) * (1UL << (cpu_pabits + 1 - PAGE_SHIFT))) +#endif + #endif /* CONFIG_SPARSEMEM */ +#ifndef VMEMMAP_SIZE +#define VMEMMAP_SIZE 0 /* 1, For FLATMEM; 2, For SPARSEMEM without VMEMMAP. */ +#endif + #ifdef CONFIG_MEMORY_HOTPLUG int memory_add_physaddr_to_nid(u64 addr); #define memory_add_physaddr_to_nid memory_add_physaddr_to_nid diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c index a13f92593cfd..eb5d3a4c8a7a 100644 --- a/arch/loongarch/kernel/numa.c +++ b/arch/loongarch/kernel/numa.c @@ -78,7 +78,7 @@ void __init pcpu_populate_pte(unsigned long addr) new = memblock_alloc(PAGE_SIZE, PAGE_SIZE); pgd_populate(&init_mm, pgd, new); #ifndef __PAGETABLE_PUD_FOLDED - pud_init((unsigned long)new, (unsigned long)invalid_pmd_table); + pud_init(new); #endif } @@ -89,7 +89,7 @@ void __init pcpu_populate_pte(unsigned long addr) new = memblock_alloc(PAGE_SIZE, PAGE_SIZE); pud_populate(&init_mm, pud, new); #ifndef __PAGETABLE_PMD_FOLDED - pmd_init((unsigned long)new, (unsigned long)invalid_pte_table); + pmd_init(new); #endif } diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c index 080061793c85..e018aed34586 100644 --- a/arch/loongarch/mm/init.c +++ b/arch/loongarch/mm/init.c @@ -22,7 +22,7 @@ #include <linux/pfn.h> #include <linux/hardirq.h> #include <linux/gfp.h> -#include <linux/initrd.h> +#include <linux/hugetlb.h> #include <linux/mmzone.h> #include <asm/asm-offsets.h> @@ -152,6 +152,45 @@ EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif #endif +#ifdef CONFIG_SPARSEMEM_VMEMMAP +void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node, + unsigned long addr, unsigned long next) +{ + pmd_t entry; + + entry = pfn_pmd(virt_to_pfn(p), PAGE_KERNEL); + pmd_val(entry) |= _PAGE_HUGE | _PAGE_HGLOBAL; + set_pmd_at(&init_mm, addr, pmd, entry); +} + +int __meminit vmemmap_check_pmd(pmd_t *pmd, int node, + unsigned long addr, unsigned long next) +{ + int huge = pmd_val(*pmd) & _PAGE_HUGE; + + if (huge) + vmemmap_verify((pte_t *)pmd, node, addr, next); + + return huge; +} + +int __meminit vmemmap_populate(unsigned long start, unsigned long end, + int node, struct vmem_altmap *altmap) +{ +#if CONFIG_PGTABLE_LEVELS == 2 + return vmemmap_populate_basepages(start, end, node, NULL); +#else + return vmemmap_populate_hugepages(start, end, node, NULL); +#endif +} + +#ifdef CONFIG_MEMORY_HOTPLUG +void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap) +{ +} +#endif +#endif + static pte_t *fixmap_pte(unsigned long addr) { pgd_t *pgd; @@ -168,7 +207,7 @@ static pte_t *fixmap_pte(unsigned long addr) new = memblock_alloc_low(PAGE_SIZE, PAGE_SIZE); pgd_populate(&init_mm, pgd, new); #ifndef __PAGETABLE_PUD_FOLDED - pud_init((unsigned long)new, (unsigned long)invalid_pmd_table); + pud_init(new); #endif } @@ -179,7 +218,7 @@ static pte_t *fixmap_pte(unsigned long addr) new = memblock_alloc_low(PAGE_SIZE, PAGE_SIZE); pud_populate(&init_mm, pud, new); #ifndef __PAGETABLE_PMD_FOLDED - pmd_init((unsigned long)new, (unsigned long)invalid_pte_table); + pmd_init(new); #endif } diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c index ee179ccd3e3f..36a6dc0148ae 100644 --- a/arch/loongarch/mm/pgtable.c +++ b/arch/loongarch/mm/pgtable.c @@ -16,7 +16,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) ret = (pgd_t *) __get_free_page(GFP_KERNEL); if (ret) { init = pgd_offset(&init_mm, 0UL); - pgd_init((unsigned long)ret); + pgd_init(ret); memcpy(ret + USER_PTRS_PER_PGD, init + USER_PTRS_PER_PGD, (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t)); } @@ -25,7 +25,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(pgd_alloc); -void pgd_init(unsigned long page) +void pgd_init(void *addr) { unsigned long *p, *end; unsigned long entry; @@ -38,7 +38,7 @@ void pgd_init(unsigned long page) entry = (unsigned long)invalid_pte_table; #endif - p = (unsigned long *) page; + p = (unsigned long *)addr; end = p + PTRS_PER_PGD; do { @@ -56,11 +56,12 @@ void pgd_init(unsigned long page) EXPORT_SYMBOL_GPL(pgd_init); #ifndef __PAGETABLE_PMD_FOLDED -void pmd_init(unsigned long addr, unsigned long pagetable) +void pmd_init(void *addr) { unsigned long *p, *end; + unsigned long pagetable = (unsigned long)invalid_pte_table; - p = (unsigned long *) addr; + p = (unsigned long *)addr; end = p + PTRS_PER_PMD; do { @@ -79,9 +80,10 @@ EXPORT_SYMBOL_GPL(pmd_init); #endif #ifndef __PAGETABLE_PUD_FOLDED -void pud_init(unsigned long addr, unsigned long pagetable) +void pud_init(void *addr) { unsigned long *p, *end; + unsigned long pagetable = (unsigned long)invalid_pmd_table; p = (unsigned long *)addr; end = p + PTRS_PER_PUD; @@ -98,6 +100,7 @@ void pud_init(unsigned long addr, unsigned long pagetable) p[-1] = pagetable; } while (p != end); } +EXPORT_SYMBOL_GPL(pud_init); #endif pmd_t mk_pmd(struct page *page, pgprot_t prot) @@ -119,12 +122,12 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, void __init pagetable_init(void) { /* Initialize the entire pgd. */ - pgd_init((unsigned long)swapper_pg_dir); - pgd_init((unsigned long)invalid_pg_dir); + pgd_init(swapper_pg_dir); + pgd_init(invalid_pg_dir); #ifndef __PAGETABLE_PUD_FOLDED - pud_init((unsigned long)invalid_pud_table, (unsigned long)invalid_pmd_table); + pud_init(invalid_pud_table); #endif #ifndef __PAGETABLE_PMD_FOLDED - pmd_init((unsigned long)invalid_pmd_table, (unsigned long)invalid_pte_table); + pmd_init(invalid_pmd_table); #endif } diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h index 796035784c73..f72e737dda21 100644 --- a/arch/mips/include/asm/pgalloc.h +++ b/arch/mips/include/asm/pgalloc.h @@ -33,7 +33,7 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, /* * Initialize a new pmd table with invalid pointers. */ -extern void pmd_init(unsigned long page, unsigned long pagetable); +extern void pmd_init(void *addr); #ifndef __PAGETABLE_PMD_FOLDED @@ -44,9 +44,9 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) #endif /* - * Initialize a new pgd / pmd table with invalid pointers. + * Initialize a new pgd table with invalid pointers. */ -extern void pgd_init(unsigned long page); +extern void pgd_init(void *addr); extern pgd_t *pgd_alloc(struct mm_struct *mm); static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) @@ -77,7 +77,7 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) } pmd = (pmd_t *)page_address(pg); - pmd_init((unsigned long)pmd, (unsigned long)invalid_pte_table); + pmd_init(pmd); return pmd; } @@ -93,7 +93,7 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) pud = (pud_t *) __get_free_pages(GFP_KERNEL, PUD_TABLE_ORDER); if (pud) - pud_init((unsigned long)pud, (unsigned long)invalid_pmd_table); + pud_init(pud); return pud; } diff --git a/arch/mips/include/asm/pgtable-64.h b/arch/mips/include/asm/pgtable-64.h index 436c29d698fa..c6310192b654 100644 --- a/arch/mips/include/asm/pgtable-64.h +++ b/arch/mips/include/asm/pgtable-64.h @@ -313,11 +313,11 @@ static inline pmd_t *pud_pgtable(pud_t pud) #endif /* - * Initialize a new pgd / pmd table with invalid pointers. + * Initialize a new pgd / pud / pmd table with invalid pointers. */ -extern void pgd_init(unsigned long page); -extern void pud_init(unsigned long page, unsigned long pagetable); -extern void pmd_init(unsigned long page, unsigned long pagetable); +extern void pgd_init(void *addr); +extern void pud_init(void *addr); +extern void pmd_init(void *addr); /* * Non-present pages: high 40 bits are offset, next 8 bits type, diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index 74cd64a24d05..e8c08988ed37 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -122,8 +122,7 @@ static pte_t *kvm_mips_walk_pgd(pgd_t *pgd, struct kvm_mmu_memory_cache *cache, if (!cache) return NULL; new_pmd = kvm_mmu_memory_cache_alloc(cache); - pmd_init((unsigned long)new_pmd, - (unsigned long)invalid_pte_table); + pmd_init(new_pmd); pud_populate(NULL, pud, new_pmd); } pmd = pmd_offset(pud, addr); diff --git a/arch/mips/mm/pgtable-32.c b/arch/mips/mm/pgtable-32.c index 61891af25019..f57fb69472f8 100644 --- a/arch/mips/mm/pgtable-32.c +++ b/arch/mips/mm/pgtable-32.c @@ -13,9 +13,9 @@ #include <asm/pgalloc.h> #include <asm/tlbflush.h> -void pgd_init(unsigned long page) +void pgd_init(void *addr) { - unsigned long *p = (unsigned long *) page; + unsigned long *p = (unsigned long *)addr; int i; for (i = 0; i < USER_PTRS_PER_PGD; i+=8) { @@ -61,9 +61,8 @@ void __init pagetable_init(void) #endif /* Initialize the entire pgd. */ - pgd_init((unsigned long)swapper_pg_dir); - pgd_init((unsigned long)swapper_pg_dir - + sizeof(pgd_t) * USER_PTRS_PER_PGD); + pgd_init(swapper_pg_dir); + pgd_init(&swapper_pg_dir[USER_PTRS_PER_PGD]); pgd_base = swapper_pg_dir; diff --git a/arch/mips/mm/pgtable-64.c b/arch/mips/mm/pgtable-64.c index 7536f7804c44..b4386a0e2ef8 100644 --- a/arch/mips/mm/pgtable-64.c +++ b/arch/mips/mm/pgtable-64.c @@ -13,7 +13,7 @@ #include <asm/pgalloc.h> #include <asm/tlbflush.h> -void pgd_init(unsigned long page) +void pgd_init(void *addr) { unsigned long *p, *end; unsigned long entry; @@ -26,7 +26,7 @@ void pgd_init(unsigned long page) entry = (unsigned long)invalid_pte_table; #endif - p = (unsigned long *) page; + p = (unsigned long *) addr; end = p + PTRS_PER_PGD; do { @@ -43,11 +43,12 @@ void pgd_init(unsigned long page) } #ifndef __PAGETABLE_PMD_FOLDED -void pmd_init(unsigned long addr, unsigned long pagetable) +void pmd_init(void *addr) { unsigned long *p, *end; + unsigned long pagetable = (unsigned long)invalid_pte_table; - p = (unsigned long *) addr; + p = (unsigned long *)addr; end = p + PTRS_PER_PMD; do { @@ -66,9 +67,10 @@ EXPORT_SYMBOL_GPL(pmd_init); #endif #ifndef __PAGETABLE_PUD_FOLDED -void pud_init(unsigned long addr, unsigned long pagetable) +void pud_init(void *addr) { unsigned long *p, *end; + unsigned long pagetable = (unsigned long)invalid_pmd_table; p = (unsigned long *)addr; end = p + PTRS_PER_PUD; @@ -108,12 +110,12 @@ void __init pagetable_init(void) pgd_t *pgd_base; /* Initialize the entire pgd. */ - pgd_init((unsigned long)swapper_pg_dir); + pgd_init(swapper_pg_dir); #ifndef __PAGETABLE_PUD_FOLDED - pud_init((unsigned long)invalid_pud_table, (unsigned long)invalid_pmd_table); + pud_init(invalid_pud_table); #endif #ifndef __PAGETABLE_PMD_FOLDED - pmd_init((unsigned long)invalid_pmd_table, (unsigned long)invalid_pte_table); + pmd_init(invalid_pmd_table); #endif pgd_base = swapper_pg_dir; /* diff --git a/arch/mips/mm/pgtable.c b/arch/mips/mm/pgtable.c index 3b7590660a04..b13314be5d0e 100644 --- a/arch/mips/mm/pgtable.c +++ b/arch/mips/mm/pgtable.c @@ -15,7 +15,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) ret = (pgd_t *) __get_free_pages(GFP_KERNEL, PGD_TABLE_ORDER); if (ret) { init = pgd_offset(&init_mm, 0UL); - pgd_init((unsigned long)ret); + pgd_init(ret); memcpy(ret + USER_PTRS_PER_PGD, init + USER_PTRS_PER_PGD, (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t)); } diff --git a/arch/nios2/include/asm/pgalloc.h b/arch/nios2/include/asm/pgalloc.h index 3c4ae74d5798..ecd1657bb2ce 100644 --- a/arch/nios2/include/asm/pgalloc.h +++ b/arch/nios2/include/asm/pgalloc.h @@ -26,11 +26,6 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, set_pmd(pmd, __pmd((unsigned long)page_address(pte))); } -/* - * Initialize a new pmd table with invalid pointers. - */ -extern void pmd_init(unsigned long page, unsigned long pagetable); - extern pgd_t *pgd_alloc(struct mm_struct *mm); #define __pte_free_tlb(tlb, pte, addr) \ diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index e8db4edd7cc9..a190aae8ceaf 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1492,72 +1492,44 @@ static long __meminitdata addr_start, addr_end; static void __meminitdata *p_start, *p_end; static int __meminitdata node_start; -static int __meminit vmemmap_populate_hugepages(unsigned long start, - unsigned long end, int node, struct vmem_altmap *altmap) +void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node, + unsigned long addr, unsigned long next) { - unsigned long addr; - unsigned long next; - pgd_t *pgd; - p4d_t *p4d; - pud_t *pud; - pmd_t *pmd; - - for (addr = start; addr < end; addr = next) { - next = pmd_addr_end(addr, end); - - pgd = vmemmap_pgd_populate(addr, node); - if (!pgd) - return -ENOMEM; - - p4d = vmemmap_p4d_populate(pgd, addr, node); - if (!p4d) - return -ENOMEM; - - pud = vmemmap_pud_populate(p4d, addr, node); - if (!pud) - return -ENOMEM; - - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) { - void *p; - - p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap); - if (p) { - pte_t entry; - - entry = pfn_pte(__pa(p) >> PAGE_SHIFT, - PAGE_KERNEL_LARGE); - set_pmd(pmd, __pmd(pte_val(entry))); + pte_t entry; + + entry = pfn_pte(__pa(p) >> PAGE_SHIFT, + PAGE_KERNEL_LARGE); + set_pmd(pmd, __pmd(pte_val(entry))); + + /* check to see if we have contiguous blocks */ + if (p_end != p || node_start != node) { + if (p_start) + pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n", + addr_start, addr_end-1, p_start, p_end-1, node_start); + addr_start = addr; + node_start = node; + p_start = p; + } - /* check to see if we have contiguous blocks */ - if (p_end != p || node_start != node) { - if (p_start) - pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n", - addr_start, addr_end-1, p_start, p_end-1, node_start); - addr_start = addr; - node_start = node; - p_start = p; - } + addr_end = addr + PMD_SIZE; + p_end = p + PMD_SIZE; - addr_end = addr + PMD_SIZE; - p_end = p + PMD_SIZE; + if (!IS_ALIGNED(addr, PMD_SIZE) || + !IS_ALIGNED(next, PMD_SIZE)) + vmemmap_use_new_sub_pmd(addr, next); +} - if (!IS_ALIGNED(addr, PMD_SIZE) || - !IS_ALIGNED(next, PMD_SIZE)) - vmemmap_use_new_sub_pmd(addr, next); +int __meminit vmemmap_check_pmd(pmd_t *pmd, int node, + unsigned long addr, unsigned long next) +{ + int large = pmd_large(*pmd); - continue; - } else if (altmap) - return -ENOMEM; /* no fallback */ - } else if (pmd_large(*pmd)) { - vmemmap_verify((pte_t *)pmd, node, addr, next); - vmemmap_use_sub_pmd(addr, next); - continue; - } - if (vmemmap_populate_basepages(addr, next, node, NULL)) - return -ENOMEM; + if (pmd_large(*pmd)) { + vmemmap_verify((pte_t *)pmd, node, addr, next); + vmemmap_use_sub_pmd(addr, next); } - return 0; + + return large; } int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c index 3cc83997a1f8..fecf523f36d8 100644 --- a/drivers/rapidio/devices/rio_mport_cdev.c +++ b/drivers/rapidio/devices/rio_mport_cdev.c @@ -1904,10 +1904,6 @@ static int mport_cdev_open(struct inode *inode, struct file *filp) priv->md = chdev; - mutex_lock(&chdev->file_mutex); - list_add_tail(&priv->list, &chdev->file_list); - mutex_unlock(&chdev->file_mutex); - INIT_LIST_HEAD(&priv->db_filters); INIT_LIST_HEAD(&priv->pw_filters); spin_lock_init(&priv->fifo_lock); @@ -1926,6 +1922,9 @@ static int mport_cdev_open(struct inode *inode, struct file *filp) spin_lock_init(&priv->req_lock); mutex_init(&priv->dma_lock); #endif + mutex_lock(&chdev->file_mutex); + list_add_tail(&priv->list, &chdev->file_list); + mutex_unlock(&chdev->file_mutex); filp->private_data = priv; goto out; @@ -334,35 +334,41 @@ static unsigned long dax_end_pfn(void *entry) for (pfn = dax_to_pfn(entry); \ pfn < dax_end_pfn(entry); pfn++) -static inline bool dax_mapping_is_cow(struct address_space *mapping) +static inline bool dax_mapping_is_shared(struct page *page) { - return (unsigned long)mapping == PAGE_MAPPING_DAX_COW; + return (unsigned long)page->mapping == PAGE_MAPPING_DAX_SHARED; } /* - * Set the page->mapping with FS_DAX_MAPPING_COW flag, increase the refcount. + * Set the page->mapping with PAGE_MAPPING_DAX_SHARED flag, increase the + * refcount. */ -static inline void dax_mapping_set_cow(struct page *page) +static inline void dax_mapping_set_shared(struct page *page) { - if ((uintptr_t)page->mapping != PAGE_MAPPING_DAX_COW) { + if ((uintptr_t)page->mapping != PAGE_MAPPING_DAX_SHARED) { /* * Reset the index if the page was already mapped * regularly before. */ if (page->mapping) - page->index = 1; - page->mapping = (void *)PAGE_MAPPING_DAX_COW; + page->share = 1; + page->mapping = (void *)PAGE_MAPPING_DAX_SHARED; } - page->index++; + page->share++; +} + +static inline unsigned long dax_mapping_decrease_shared(struct page *page) +{ + return --page->share; } /* - * When it is called in dax_insert_entry(), the cow flag will indicate that + * When it is called in dax_insert_entry(), the shared flag will indicate that * whether this entry is shared by multiple files. If so, set the page->mapping - * FS_DAX_MAPPING_COW, and use page->index as refcount. + * PAGE_MAPPING_DAX_SHARED, and use page->share as refcount. */ static void dax_associate_entry(void *entry, struct address_space *mapping, - struct vm_area_struct *vma, unsigned long address, bool cow) + struct vm_area_struct *vma, unsigned long address, bool shared) { unsigned long size = dax_entry_size(entry), pfn, index; int i = 0; @@ -374,8 +380,8 @@ static void dax_associate_entry(void *entry, struct address_space *mapping, for_each_mapped_pfn(entry, pfn) { struct page *page = pfn_to_page(pfn); - if (cow) { - dax_mapping_set_cow(page); + if (shared) { + dax_mapping_set_shared(page); } else { WARN_ON_ONCE(page->mapping); page->mapping = mapping; @@ -396,9 +402,9 @@ static void dax_disassociate_entry(void *entry, struct address_space *mapping, struct page *page = pfn_to_page(pfn); WARN_ON_ONCE(trunc && page_ref_count(page) > 1); - if (dax_mapping_is_cow(page->mapping)) { - /* keep the CoW flag if this page is still shared */ - if (page->index-- > 0) + if (dax_mapping_is_shared(page)) { + /* keep the shared flag if this page is still shared */ + if (dax_mapping_decrease_shared(page) > 0) continue; } else WARN_ON_ONCE(page->mapping && page->mapping != mapping); @@ -840,12 +846,6 @@ static bool dax_fault_is_synchronous(const struct iomap_iter *iter, (iter->iomap.flags & IOMAP_F_DIRTY); } -static bool dax_fault_is_cow(const struct iomap_iter *iter) -{ - return (iter->flags & IOMAP_WRITE) && - (iter->iomap.flags & IOMAP_F_SHARED); -} - /* * By this point grab_mapping_entry() has ensured that we have a locked entry * of the appropriate size so we don't have to worry about downgrading PMDs to @@ -859,13 +859,14 @@ static void *dax_insert_entry(struct xa_state *xas, struct vm_fault *vmf, { struct address_space *mapping = vmf->vma->vm_file->f_mapping; void *new_entry = dax_make_entry(pfn, flags); - bool dirty = !dax_fault_is_synchronous(iter, vmf->vma); - bool cow = dax_fault_is_cow(iter); + bool write = iter->flags & IOMAP_WRITE; + bool dirty = write && !dax_fault_is_synchronous(iter, vmf->vma); + bool shared = iter->iomap.flags & IOMAP_F_SHARED; if (dirty) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); - if (cow || (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE))) { + if (shared || (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE))) { unsigned long index = xas->xa_index; /* we are replacing a zero page with block mapping */ if (dax_is_pmd_entry(entry)) @@ -877,12 +878,12 @@ static void *dax_insert_entry(struct xa_state *xas, struct vm_fault *vmf, xas_reset(xas); xas_lock_irq(xas); - if (cow || dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) { + if (shared || dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) { void *old; dax_disassociate_entry(entry, mapping, false); dax_associate_entry(new_entry, mapping, vmf->vma, vmf->address, - cow); + shared); /* * Only swap our new entry into the page cache if the current * entry is a zero page or an empty entry. If a normal PTE or @@ -902,7 +903,7 @@ static void *dax_insert_entry(struct xa_state *xas, struct vm_fault *vmf, if (dirty) xas_set_mark(xas, PAGECACHE_TAG_DIRTY); - if (cow) + if (write && shared) xas_set_mark(xas, PAGECACHE_TAG_TOWRITE); xas_unlock_irq(xas); @@ -1086,7 +1087,7 @@ out: } /** - * dax_iomap_cow_copy - Copy the data from source to destination before write + * dax_iomap_copy_around - Copy the data from source to destination before write * @pos: address to do copy from. * @length: size of copy operation. * @align_size: aligned w.r.t align_size (either PMD_SIZE or PAGE_SIZE) @@ -1095,35 +1096,50 @@ out: * * This can be called from two places. Either during DAX write fault (page * aligned), to copy the length size data to daddr. Or, while doing normal DAX - * write operation, dax_iomap_actor() might call this to do the copy of either + * write operation, dax_iomap_iter() might call this to do the copy of either * start or end unaligned address. In the latter case the rest of the copy of - * aligned ranges is taken care by dax_iomap_actor() itself. + * aligned ranges is taken care by dax_iomap_iter() itself. + * If the srcmap contains invalid data, such as HOLE and UNWRITTEN, zero the + * area to make sure no old data remains. */ -static int dax_iomap_cow_copy(loff_t pos, uint64_t length, size_t align_size, +static int dax_iomap_copy_around(loff_t pos, uint64_t length, size_t align_size, const struct iomap *srcmap, void *daddr) { loff_t head_off = pos & (align_size - 1); size_t size = ALIGN(head_off + length, align_size); loff_t end = pos + length; loff_t pg_end = round_up(end, align_size); + /* copy_all is usually in page fault case */ bool copy_all = head_off == 0 && end == pg_end; + /* zero the edges if srcmap is a HOLE or IOMAP_UNWRITTEN */ + bool zero_edge = srcmap->flags & IOMAP_F_SHARED || + srcmap->type == IOMAP_UNWRITTEN; void *saddr = 0; int ret = 0; - ret = dax_iomap_direct_access(srcmap, pos, size, &saddr, NULL); - if (ret) - return ret; + if (!zero_edge) { + ret = dax_iomap_direct_access(srcmap, pos, size, &saddr, NULL); + if (ret) + return ret; + } if (copy_all) { - ret = copy_mc_to_kernel(daddr, saddr, length); - return ret ? -EIO : 0; + if (zero_edge) + memset(daddr, 0, size); + else + ret = copy_mc_to_kernel(daddr, saddr, length); + goto out; } /* Copy the head part of the range */ if (head_off) { - ret = copy_mc_to_kernel(daddr, saddr, head_off); - if (ret) - return -EIO; + if (zero_edge) + memset(daddr, 0, head_off); + else { + ret = copy_mc_to_kernel(daddr, saddr, head_off); + if (ret) + return -EIO; + } } /* Copy the tail part of the range */ @@ -1131,12 +1147,19 @@ static int dax_iomap_cow_copy(loff_t pos, uint64_t length, size_t align_size, loff_t tail_off = head_off + length; loff_t tail_len = pg_end - end; - ret = copy_mc_to_kernel(daddr + tail_off, saddr + tail_off, - tail_len); - if (ret) - return -EIO; + if (zero_edge) + memset(daddr + tail_off, 0, tail_len); + else { + ret = copy_mc_to_kernel(daddr + tail_off, + saddr + tail_off, tail_len); + if (ret) + return -EIO; + } } - return 0; +out: + if (zero_edge) + dax_flush(srcmap->dax_dev, daddr, size); + return ret ? -EIO : 0; } /* @@ -1221,6 +1244,58 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, } #endif /* CONFIG_FS_DAX_PMD */ +static s64 dax_unshare_iter(struct iomap_iter *iter) +{ + struct iomap *iomap = &iter->iomap; + const struct iomap *srcmap = iomap_iter_srcmap(iter); + loff_t pos = iter->pos; + loff_t length = iomap_length(iter); + int id = 0; + s64 ret = 0; + void *daddr = NULL, *saddr = NULL; + + /* don't bother with blocks that are not shared to start with */ + if (!(iomap->flags & IOMAP_F_SHARED)) + return length; + /* don't bother with holes or unwritten extents */ + if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) + return length; + + id = dax_read_lock(); + ret = dax_iomap_direct_access(iomap, pos, length, &daddr, NULL); + if (ret < 0) + goto out_unlock; + + ret = dax_iomap_direct_access(srcmap, pos, length, &saddr, NULL); + if (ret < 0) + goto out_unlock; + + ret = copy_mc_to_kernel(daddr, saddr, length); + if (ret) + ret = -EIO; + +out_unlock: + dax_read_unlock(id); + return ret; +} + +int dax_file_unshare(struct inode *inode, loff_t pos, loff_t len, + const struct iomap_ops *ops) +{ + struct iomap_iter iter = { + .inode = inode, + .pos = pos, + .len = len, + .flags = IOMAP_WRITE | IOMAP_UNSHARE | IOMAP_DAX, + }; + int ret; + + while ((ret = iomap_iter(&iter, ops)) > 0) + iter.processed = dax_unshare_iter(&iter); + return ret; +} +EXPORT_SYMBOL_GPL(dax_file_unshare); + static int dax_memzero(struct iomap_iter *iter, loff_t pos, size_t size) { const struct iomap *iomap = &iter->iomap; @@ -1235,13 +1310,10 @@ static int dax_memzero(struct iomap_iter *iter, loff_t pos, size_t size) if (ret < 0) return ret; memset(kaddr + offset, 0, size); - if (srcmap->addr != iomap->addr) { - ret = dax_iomap_cow_copy(pos, size, PAGE_SIZE, srcmap, - kaddr); - if (ret < 0) - return ret; - dax_flush(iomap->dax_dev, kaddr, PAGE_SIZE); - } else + if (iomap->flags & IOMAP_F_SHARED) + ret = dax_iomap_copy_around(pos, size, PAGE_SIZE, srcmap, + kaddr); + else dax_flush(iomap->dax_dev, kaddr + offset, size); return ret; } @@ -1258,6 +1330,15 @@ static s64 dax_zero_iter(struct iomap_iter *iter, bool *did_zero) if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) return length; + /* + * invalidate the pages whose sharing state is to be changed + * because of CoW. + */ + if (iomap->flags & IOMAP_F_SHARED) + invalidate_inode_pages2_range(iter->inode->i_mapping, + pos >> PAGE_SHIFT, + (pos + length - 1) >> PAGE_SHIFT); + do { unsigned offset = offset_in_page(pos); unsigned size = min_t(u64, PAGE_SIZE - offset, length); @@ -1318,12 +1399,13 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, struct iov_iter *iter) { const struct iomap *iomap = &iomi->iomap; - const struct iomap *srcmap = &iomi->srcmap; + const struct iomap *srcmap = iomap_iter_srcmap(iomi); loff_t length = iomap_length(iomi); loff_t pos = iomi->pos; struct dax_device *dax_dev = iomap->dax_dev; loff_t end = pos + length, done = 0; bool write = iov_iter_rw(iter) == WRITE; + bool cow = write && iomap->flags & IOMAP_F_SHARED; ssize_t ret = 0; size_t xfer; int id; @@ -1350,7 +1432,7 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, * into page tables. We have to tear down these mappings so that data * written by write(2) is visible in mmap. */ - if (iomap->flags & IOMAP_F_NEW) { + if (iomap->flags & IOMAP_F_NEW || cow) { invalidate_inode_pages2_range(iomi->inode->i_mapping, pos >> PAGE_SHIFT, (end - 1) >> PAGE_SHIFT); @@ -1384,10 +1466,9 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, break; } - if (write && - srcmap->type != IOMAP_HOLE && srcmap->addr != iomap->addr) { - ret = dax_iomap_cow_copy(pos, length, PAGE_SIZE, srcmap, - kaddr); + if (cow) { + ret = dax_iomap_copy_around(pos, length, PAGE_SIZE, + srcmap, kaddr); if (ret) break; } @@ -1532,7 +1613,7 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf, struct xa_state *xas, void **entry, bool pmd) { const struct iomap *iomap = &iter->iomap; - const struct iomap *srcmap = &iter->srcmap; + const struct iomap *srcmap = iomap_iter_srcmap(iter); size_t size = pmd ? PMD_SIZE : PAGE_SIZE; loff_t pos = (loff_t)xas->xa_index << PAGE_SHIFT; bool write = iter->flags & IOMAP_WRITE; @@ -1563,9 +1644,8 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf, *entry = dax_insert_entry(xas, vmf, iter, *entry, pfn, entry_flags); - if (write && - srcmap->type != IOMAP_HOLE && srcmap->addr != iomap->addr) { - err = dax_iomap_cow_copy(pos, size, size, srcmap, kaddr); + if (write && iomap->flags & IOMAP_F_SHARED) { + err = dax_iomap_copy_around(pos, size, size, srcmap, kaddr); if (err) return dax_fault_return(err); } @@ -1936,15 +2016,15 @@ int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff, .len = len, .flags = IOMAP_DAX, }; - int ret; + int ret, compared = 0; - while ((ret = iomap_iter(&src_iter, ops)) > 0) { - while ((ret = iomap_iter(&dst_iter, ops)) > 0) { - dst_iter.processed = dax_range_compare_iter(&src_iter, - &dst_iter, len, same); - } - if (ret <= 0) - src_iter.processed = ret; + while ((ret = iomap_iter(&src_iter, ops)) > 0 && + (ret = iomap_iter(&dst_iter, ops)) > 0) { + compared = dax_range_compare_iter(&src_iter, &dst_iter, len, + same); + if (compared < 0) + return ret; + src_iter.processed = dst_iter.processed = compared; } return ret; } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index c77eea4f636b..9f349f834977 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -766,11 +766,11 @@ static int fuse_copy_do(struct fuse_copy_state *cs, void **val, unsigned *size) return ncpy; } -static int fuse_check_page(struct page *page) +static int fuse_check_folio(struct folio *folio) { - if (page_mapcount(page) || - page->mapping != NULL || - (page->flags & PAGE_FLAGS_CHECK_AT_PREP & + if (folio_mapped(folio) || + folio->mapping != NULL || + (folio->flags & PAGE_FLAGS_CHECK_AT_PREP & ~(1 << PG_locked | 1 << PG_referenced | 1 << PG_uptodate | @@ -780,7 +780,7 @@ static int fuse_check_page(struct page *page) 1 << PG_reclaim | 1 << PG_waiters | LRU_GEN_MASK | LRU_REFS_MASK))) { - dump_page(page, "fuse: trying to steal weird page"); + dump_page(&folio->page, "fuse: trying to steal weird page"); return 1; } return 0; @@ -789,11 +789,11 @@ static int fuse_check_page(struct page *page) static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) { int err; - struct page *oldpage = *pagep; - struct page *newpage; + struct folio *oldfolio = page_folio(*pagep); + struct folio *newfolio; struct pipe_buffer *buf = cs->pipebufs; - get_page(oldpage); + folio_get(oldfolio); err = unlock_request(cs->req); if (err) goto out_put_old; @@ -816,35 +816,36 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) if (!pipe_buf_try_steal(cs->pipe, buf)) goto out_fallback; - newpage = buf->page; + newfolio = page_folio(buf->page); - if (!PageUptodate(newpage)) - SetPageUptodate(newpage); + if (!folio_test_uptodate(newfolio)) + folio_mark_uptodate(newfolio); - ClearPageMappedToDisk(newpage); + folio_clear_mappedtodisk(newfolio); - if (fuse_check_page(newpage) != 0) + if (fuse_check_folio(newfolio) != 0) goto out_fallback_unlock; /* * This is a new and locked page, it shouldn't be mapped or * have any special flags on it */ - if (WARN_ON(page_mapped(oldpage))) + if (WARN_ON(folio_mapped(oldfolio))) goto out_fallback_unlock; - if (WARN_ON(page_has_private(oldpage))) + if (WARN_ON(folio_has_private(oldfolio))) goto out_fallback_unlock; - if (WARN_ON(PageDirty(oldpage) || PageWriteback(oldpage))) + if (WARN_ON(folio_test_dirty(oldfolio) || + folio_test_writeback(oldfolio))) goto out_fallback_unlock; - if (WARN_ON(PageMlocked(oldpage))) + if (WARN_ON(folio_test_mlocked(oldfolio))) goto out_fallback_unlock; - replace_page_cache_page(oldpage, newpage); + replace_page_cache_folio(oldfolio, newfolio); - get_page(newpage); + folio_get(newfolio); if (!(buf->flags & PIPE_BUF_FLAG_LRU)) - lru_cache_add(newpage); + folio_add_lru(newfolio); /* * Release while we have extra ref on stolen page. Otherwise @@ -857,28 +858,28 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) if (test_bit(FR_ABORTED, &cs->req->flags)) err = -ENOENT; else - *pagep = newpage; + *pagep = &newfolio->page; spin_unlock(&cs->req->waitq.lock); if (err) { - unlock_page(newpage); - put_page(newpage); + folio_unlock(newfolio); + folio_put(newfolio); goto out_put_old; } - unlock_page(oldpage); + folio_unlock(oldfolio); /* Drop ref for ap->pages[] array */ - put_page(oldpage); + folio_put(oldfolio); cs->len = 0; err = 0; out_put_old: /* Drop ref obtained in this function */ - put_page(oldpage); + folio_put(oldfolio); return err; out_fallback_unlock: - unlock_page(newpage); + folio_unlock(newfolio); out_fallback: cs->pg = buf->page; cs->offset = buf->offset; diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index c4526f16355d..a0746be3c1de 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -458,6 +458,8 @@ int hfs_write_inode(struct inode *inode, struct writeback_control *wbc) /* panic? */ return -EIO; + if (HFS_I(main_inode)->cat_key.CName.len > HFS_NAMELEN) + return -EIO; fd.search_key->cat = HFS_I(main_inode)->cat_key; if (hfs_brec_find(&fd)) /* panic? */ diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 790d2727141a..48f1a8ad2243 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -388,9 +388,7 @@ static bool hugetlb_vma_maps_page(struct vm_area_struct *vma, { pte_t *ptep, pte; - ptep = huge_pte_offset(vma->vm_mm, addr, - huge_page_size(hstate_vma(vma))); - + ptep = hugetlb_walk(vma, addr, huge_page_size(hstate_vma(vma))); if (!ptep) return false; @@ -412,10 +410,12 @@ static bool hugetlb_vma_maps_page(struct vm_area_struct *vma, */ static unsigned long vma_offset_start(struct vm_area_struct *vma, pgoff_t start) { + unsigned long offset = 0; + if (vma->vm_pgoff < start) - return (start - vma->vm_pgoff) << PAGE_SHIFT; - else - return 0; + offset = (start - vma->vm_pgoff) << PAGE_SHIFT; + + return vma->vm_start + offset; } static unsigned long vma_offset_end(struct vm_area_struct *vma, pgoff_t end) @@ -457,7 +457,7 @@ retry: v_start = vma_offset_start(vma, start); v_end = vma_offset_end(vma, end); - if (!hugetlb_vma_maps_page(vma, vma->vm_start + v_start, page)) + if (!hugetlb_vma_maps_page(vma, v_start, page)) continue; if (!hugetlb_vma_trylock_write(vma)) { @@ -473,8 +473,8 @@ retry: break; } - unmap_hugepage_range(vma, vma->vm_start + v_start, v_end, - NULL, ZAP_FLAG_DROP_MARKER); + unmap_hugepage_range(vma, v_start, v_end, NULL, + ZAP_FLAG_DROP_MARKER); hugetlb_vma_unlock_write(vma); } @@ -507,10 +507,9 @@ retry: */ v_start = vma_offset_start(vma, start); v_end = vma_offset_end(vma, end); - if (hugetlb_vma_maps_page(vma, vma->vm_start + v_start, page)) - unmap_hugepage_range(vma, vma->vm_start + v_start, - v_end, NULL, - ZAP_FLAG_DROP_MARKER); + if (hugetlb_vma_maps_page(vma, v_start, page)) + unmap_hugepage_range(vma, v_start, v_end, NULL, + ZAP_FLAG_DROP_MARKER); kref_put(&vma_lock->refs, hugetlb_vma_lock_release); hugetlb_vma_unlock_write(vma); @@ -540,8 +539,7 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end, v_start = vma_offset_start(vma, start); v_end = vma_offset_end(vma, end); - unmap_hugepage_range(vma, vma->vm_start + v_start, v_end, - NULL, zap_flags); + unmap_hugepage_range(vma, v_start, v_end, NULL, zap_flags); /* * Note that vma lock only exists for shared/non-private diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 740b64238312..a503c553bab2 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -560,8 +560,7 @@ static inline unsigned int ocfs2_read_links_count(struct ocfs2_dinode *di) u32 nlink = le16_to_cpu(di->i_links_count); u32 hi = le16_to_cpu(di->i_links_count_hi); - if (di->i_dyn_features & cpu_to_le16(OCFS2_INDEXED_DIR_FL)) - nlink |= (hi << OCFS2_LINKS_HI_SHIFT); + nlink |= (hi << OCFS2_LINKS_HI_SHIFT); return nlink; } diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 98ac37e34e3d..9ea8555a19bc 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -237,14 +237,12 @@ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx, unsigned long flags, unsigned long reason) { - struct mm_struct *mm = ctx->mm; pte_t *ptep, pte; bool ret = true; - mmap_assert_locked(mm); - - ptep = huge_pte_offset(mm, address, vma_mmu_pagesize(vma)); + mmap_assert_locked(ctx->mm); + ptep = hugetlb_walk(vma, address, vma_mmu_pagesize(vma)); if (!ptep) goto out; @@ -376,7 +374,8 @@ static inline unsigned int userfaultfd_get_blocking_state(unsigned int flags) */ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) { - struct mm_struct *mm = vmf->vma->vm_mm; + struct vm_area_struct *vma = vmf->vma; + struct mm_struct *mm = vma->vm_mm; struct userfaultfd_ctx *ctx; struct userfaultfd_wait_queue uwq; vm_fault_t ret = VM_FAULT_SIGBUS; @@ -403,7 +402,7 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) */ mmap_assert_locked(mm); - ctx = vmf->vma->vm_userfaultfd_ctx.ctx; + ctx = vma->vm_userfaultfd_ctx.ctx; if (!ctx) goto out; @@ -493,6 +492,13 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) blocking_state = userfaultfd_get_blocking_state(vmf->flags); + /* + * This stablizes pgtable for hugetlb on e.g. pmd unsharing. Need + * to be before setting current state. + */ + if (is_vm_hugetlb_page(vma)) + hugetlb_vma_lock_read(vma); + spin_lock_irq(&ctx->fault_pending_wqh.lock); /* * After the __add_wait_queue the uwq is visible to userland @@ -507,13 +513,15 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason) set_current_state(blocking_state); spin_unlock_irq(&ctx->fault_pending_wqh.lock); - if (!is_vm_hugetlb_page(vmf->vma)) + if (!is_vm_hugetlb_page(vma)) must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags, reason); else - must_wait = userfaultfd_huge_must_wait(ctx, vmf->vma, + must_wait = userfaultfd_huge_must_wait(ctx, vma, vmf->address, vmf->flags, reason); + if (is_vm_hugetlb_page(vma)) + hugetlb_vma_unlock_read(vma); mmap_read_unlock(mm); if (likely(must_wait && !READ_ONCE(ctx->released))) { diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 1f783e979629..13f1b2add390 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1138,10 +1138,6 @@ xfs_ioctl_setattr_xflags( if ((fa->fsx_xflags & FS_XFLAG_REALTIME) && xfs_is_reflink_inode(ip)) ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK; - /* Don't allow us to set DAX mode for a reflinked file for now. */ - if ((fa->fsx_xflags & FS_XFLAG_DAX) && xfs_is_reflink_inode(ip)) - return -EINVAL; - /* diflags2 only valid for v3 inodes. */ i_flags2 = xfs_flags2diflags2(ip, fa->fsx_xflags); if (i_flags2 && !xfs_has_v3inodes(mp)) diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 68436370927d..8ac27bbda882 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1253,7 +1253,7 @@ xfs_read_iomap_begin( return error; error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap, &nimaps, 0); - if (!error && (flags & IOMAP_REPORT)) + if (!error && ((flags & IOMAP_REPORT) || IS_DAX(inode))) error = xfs_reflink_trim_around_shared(ip, &imap, &shared); seq = xfs_iomap_inode_sequence(ip, shared ? IOMAP_F_SHARED : 0); xfs_iunlock(ip, lockmode); @@ -1415,7 +1415,7 @@ xfs_zero_range( if (IS_DAX(inode)) return dax_zero_range(inode, pos, len, did_zero, - &xfs_direct_write_iomap_ops); + &xfs_dax_write_iomap_ops); return iomap_zero_range(inode, pos, len, did_zero, &xfs_buffered_write_iomap_ops); } @@ -1430,7 +1430,7 @@ xfs_truncate_page( if (IS_DAX(inode)) return dax_truncate_page(inode, pos, did_zero, - &xfs_direct_write_iomap_ops); + &xfs_dax_write_iomap_ops); return iomap_truncate_page(inode, pos, did_zero, &xfs_buffered_write_iomap_ops); } diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 712238305bc3..515318dfbc38 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -1187,10 +1187,6 @@ xfs_inode_supports_dax( if (!S_ISREG(VFS_I(ip)->i_mode)) return false; - /* Only supported on non-reflinked files. */ - if (xfs_is_reflink_inode(ip)) - return false; - /* Block size must match page size */ if (mp->m_sb.sb_blocksize != PAGE_SIZE) return false; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 93bdd25680bc..fe46bce8cae6 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1693,8 +1693,12 @@ xfs_reflink_unshare( inode_dio_wait(inode); - error = iomap_file_unshare(inode, offset, len, - &xfs_buffered_write_iomap_ops); + if (IS_DAX(inode)) + error = dax_file_unshare(inode, offset, len, + &xfs_dax_write_iomap_ops); + else + error = iomap_file_unshare(inode, offset, len, + &xfs_buffered_write_iomap_ops); if (error) goto out; diff --git a/include/linux/dax.h b/include/linux/dax.h index ba985333e26b..2b5ecb591059 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -205,6 +205,8 @@ static inline void dax_unlock_mapping_entry(struct address_space *mapping, } #endif +int dax_file_unshare(struct inode *inode, loff_t pos, loff_t len, + const struct iomap_ops *ops); int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, const struct iomap_ops *ops); int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index 786824f58d3d..36a486505b08 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -62,7 +62,7 @@ static inline struct eventfd_ctx *eventfd_ctx_fdget(int fd) return ERR_PTR(-ENOSYS); } -static inline int eventfd_signal(struct eventfd_ctx *ctx, int n) +static inline int eventfd_signal(struct eventfd_ctx *ctx, __u64 n) { return -ENOSYS; } diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 551834cd5299..1c20cbbf3d22 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -2,6 +2,7 @@ #ifndef _LINUX_HUGETLB_H #define _LINUX_HUGETLB_H +#include <linux/mm.h> #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/fs.h> @@ -192,6 +193,43 @@ extern struct list_head huge_boot_pages; pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz); +/* + * huge_pte_offset(): Walk the hugetlb pgtable until the last level PTE. + * Returns the pte_t* if found, or NULL if the address is not mapped. + * + * IMPORTANT: we should normally not directly call this function, instead + * this is only a common interface to implement arch-specific walker. + * Please consider using the hugetlb_walk() helper to make sure of the + * correct locking is satisfied. + * + * Since this function will walk all the pgtable pages (including not only + * high-level pgtable page, but also PUD entry that can be unshared + * concurrently for VM_SHARED), the caller of this function should be + * responsible of its thread safety. One can follow this rule: + * + * (1) For private mappings: pmd unsharing is not possible, so it'll + * always be safe if we're with the mmap sem for either read or write. + * This is normally always the case, IOW we don't need to do anything + * special. + * + * (2) For shared mappings: pmd unsharing is possible (so the PUD-ranged + * pgtable page can go away from under us! It can be done by a pmd + * unshare with a follow up munmap() on the other process), then we + * need either: + * + * (2.1) hugetlb vma lock read or write held, to make sure pmd unshare + * won't happen upon the range (it also makes sure the pte_t we + * read is the right and stable one), or, + * + * (2.2) hugetlb mapping i_mmap_rwsem lock held read or write, to make + * sure even if unshare happened the racy unmap() will wait until + * i_mmap_rwsem is released. + * + * Option (2.1) is the safest, which guarantees pte stability from pmd + * sharing pov, until the vma lock released. Option (2.2) doesn't protect + * a concurrent pmd unshare, but it makes sure the pgtable page is safe to + * access. + */ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); unsigned long hugetlb_mask_last_page(struct hstate *h); @@ -1197,4 +1235,37 @@ bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr); #define flush_hugetlb_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #endif +static inline bool +__vma_shareable_flags_pmd(struct vm_area_struct *vma) +{ + return vma->vm_flags & (VM_MAYSHARE | VM_SHARED) && + vma->vm_private_data; +} + +/* + * Safe version of huge_pte_offset() to check the locks. See comments + * above huge_pte_offset(). + */ +static inline pte_t * +hugetlb_walk(struct vm_area_struct *vma, unsigned long addr, unsigned long sz) +{ +#if defined(CONFIG_HUGETLB_PAGE) && \ + defined(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) && defined(CONFIG_LOCKDEP) + struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; + + /* + * If pmd sharing possible, locking needed to safely walk the + * hugetlb pgtables. More information can be found at the comment + * above huge_pte_offset() in the same file. + * + * NOTE: lockdep_is_held() is only defined with CONFIG_LOCKDEP. + */ + if (__vma_shareable_flags_pmd(vma)) + WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) && + !lockdep_is_held( + &vma->vm_file->f_mapping->i_mmap_rwsem)); +#endif + return huge_pte_offset(vma->vm_mm, addr, sz); +} + #endif /* _LINUX_HUGETLB_H */ diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 66a774d2710e..09d4f17c8d3b 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -213,7 +213,7 @@ io_mapping_free(struct io_mapping *iomap) kfree(iomap); } -#endif /* _LINUX_IO_MAPPING_H */ - int io_mapping_map_user(struct io_mapping *iomap, struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, unsigned long size); + +#endif /* _LINUX_IO_MAPPING_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 9651c39d1287..517225fce10f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -986,6 +986,13 @@ static inline void set_compound_page_dtor(struct page *page, page[1].compound_dtor = compound_dtor; } +static inline void folio_set_compound_dtor(struct folio *folio, + enum compound_dtor_id compound_dtor) +{ + VM_BUG_ON_FOLIO(compound_dtor >= NR_COMPOUND_DTORS, folio); + folio->_folio_dtor = compound_dtor; +} + void destroy_large_folio(struct folio *folio); static inline int head_compound_pincount(struct page *head) @@ -1001,6 +1008,15 @@ static inline void set_compound_order(struct page *page, unsigned int order) #endif } +static inline void folio_set_compound_order(struct folio *folio, + unsigned int order) +{ + folio->_folio_order = order; +#ifdef CONFIG_64BIT + folio->_folio_nr_pages = order ? 1U << order : 0; +#endif +} + /* Returns the number of pages in this potentially compound page. */ static inline unsigned long compound_nr(struct page *page) { @@ -3046,7 +3062,6 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * and return without waiting upon it */ #define FOLL_NOFAULT 0x80 /* do not fault in pages */ #define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ -#define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ #define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ #define FOLL_ANON 0x8000 /* don't do file mappings */ @@ -3352,6 +3367,8 @@ void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap, struct dev_pagemap *pgmap); +void pmd_init(void *addr); +void pud_init(void *addr); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); @@ -3363,8 +3380,14 @@ struct vmem_altmap; void *vmemmap_alloc_block_buf(unsigned long size, int node, struct vmem_altmap *altmap); void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); +void vmemmap_set_pmd(pmd_t *pmd, void *p, int node, + unsigned long addr, unsigned long next); +int vmemmap_check_pmd(pmd_t *pmd, int node, + unsigned long addr, unsigned long next); int vmemmap_populate_basepages(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); +int vmemmap_populate_hugepages(unsigned long start, unsigned long end, + int node, struct vmem_altmap *altmap); int vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); void vmemmap_populate_print_last(void); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 018b1c098173..3b8475007734 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -104,7 +104,10 @@ struct page { }; /* See page-flags.h for PAGE_MAPPING_FLAGS */ struct address_space *mapping; - pgoff_t index; /* Our offset within mapping. */ + union { + pgoff_t index; /* Our offset within mapping. */ + unsigned long share; /* share count for fsdax */ + }; /** * @private: Mapping-private opaque data. * Usually used for buffer_heads if PagePrivate. @@ -929,7 +932,6 @@ typedef __bitwise unsigned int vm_fault_t; * @VM_FAULT_OOM: Out Of Memory * @VM_FAULT_SIGBUS: Bad access * @VM_FAULT_MAJOR: Page read from storage - * @VM_FAULT_WRITE: Special case for get_user_pages * @VM_FAULT_HWPOISON: Hit poisoned small page * @VM_FAULT_HWPOISON_LARGE: Hit poisoned large page. Index encoded * in upper bits @@ -950,7 +952,6 @@ enum vm_fault_reason { VM_FAULT_OOM = (__force vm_fault_t)0x000001, VM_FAULT_SIGBUS = (__force vm_fault_t)0x000002, VM_FAULT_MAJOR = (__force vm_fault_t)0x000004, - VM_FAULT_WRITE = (__force vm_fault_t)0x000008, VM_FAULT_HWPOISON = (__force vm_fault_t)0x000010, VM_FAULT_HWPOISON_LARGE = (__force vm_fault_t)0x000020, VM_FAULT_SIGSEGV = (__force vm_fault_t)0x000040, @@ -976,7 +977,6 @@ enum vm_fault_reason { { VM_FAULT_OOM, "OOM" }, \ { VM_FAULT_SIGBUS, "SIGBUS" }, \ { VM_FAULT_MAJOR, "MAJOR" }, \ - { VM_FAULT_WRITE, "WRITE" }, \ { VM_FAULT_HWPOISON, "HWPOISON" }, \ { VM_FAULT_HWPOISON_LARGE, "HWPOISON_LARGE" }, \ { VM_FAULT_SIGSEGV, "SIGSEGV" }, \ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index f235ec442b61..480626efd786 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -639,7 +639,7 @@ PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) * Different with flags above, this flag is used only for fsdax mode. It * indicates that this page->mapping is now under reflink case. */ -#define PAGE_MAPPING_DAX_COW 0x1 +#define PAGE_MAPPING_DAX_SHARED 0x1 static __always_inline bool folio_mapping_flags(struct folio *folio) { diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 2ec0ca1f3d38..29e1f9e76eb6 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1102,7 +1102,7 @@ int filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp); void filemap_remove_folio(struct folio *folio); void __filemap_remove_folio(struct folio *folio, void *shadow); -void replace_page_cache_page(struct page *old, struct page *new); +void replace_page_cache_folio(struct folio *old, struct folio *new); void delete_from_page_cache_batch(struct address_space *mapping, struct folio_batch *fbatch); bool filemap_release_folio(struct folio *folio, gfp_t gfp); diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h index f3fafb731ffd..959f52e5867d 100644 --- a/include/linux/pagewalk.h +++ b/include/linux/pagewalk.h @@ -27,6 +27,8 @@ struct mm_walk; * "do page table walk over the current vma", returning * a negative value means "abort current page table walk * right now" and returning 1 means "skip the current vma" + * Note that this callback is not called when the caller + * passes in a single VMA as for walk_page_vma(). * @pre_vma: if set, called before starting walk on a non-null vma. * @post_vma: if set, called after a walk on a non-null vma, provided * that @pre_vma and the vma walk succeeded. @@ -99,6 +101,9 @@ int walk_page_range_novma(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, pgd_t *pgd, void *private); +int walk_page_range_vma(struct vm_area_struct *vma, unsigned long start, + unsigned long end, const struct mm_walk_ops *ops, + void *private); int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, void *private); int walk_page_mapping(struct address_space *mapping, pgoff_t first_index, diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 576093de8b1c..1159b25b0542 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -456,9 +456,7 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long address, pte_t *ptep, int full) { - pte_t pte; - pte = ptep_get_and_clear(mm, address, ptep); - return pte; + return ptep_get_and_clear(mm, address, ptep); } #endif diff --git a/include/linux/rmap.h b/include/linux/rmap.h index bd3504d11b15..a50d18bb86aa 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -13,6 +13,7 @@ #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/memremap.h> +#include <linux/hugetlb.h> /* * The anon_vma heads a list of private "related" vmas, to scan if @@ -408,6 +409,9 @@ static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw) pte_unmap(pvmw->pte); if (pvmw->ptl) spin_unlock(pvmw->ptl); + /* This needs to be after unlock of the spinlock */ + if (is_vm_hugetlb_page(pvmw->vma)) + hugetlb_vma_unlock_read(pvmw->vma); } bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw); diff --git a/include/linux/swap.h b/include/linux/swap.h index b61e2007d156..0ceed49516ad 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -381,7 +381,6 @@ void lru_note_cost(struct lruvec *lruvec, bool file, void lru_note_cost_refault(struct folio *); void folio_add_lru(struct folio *); void folio_add_lru_vma(struct folio *, struct vm_area_struct *); -void lru_cache_add(struct page *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 27ade4f22abb..09b22b169a71 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -335,7 +335,8 @@ extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address); #ifdef CONFIG_HUGETLB_PAGE -extern void __migration_entry_wait_huge(pte_t *ptep, spinlock_t *ptl); +extern void __migration_entry_wait_huge(struct vm_area_struct *vma, + pte_t *ptep, spinlock_t *ptl); extern void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte); #endif /* CONFIG_HUGETLB_PAGE */ #else /* CONFIG_MIGRATION */ @@ -364,7 +365,8 @@ static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } #ifdef CONFIG_HUGETLB_PAGE -static inline void __migration_entry_wait_huge(pte_t *ptep, spinlock_t *ptl) { } +static inline void __migration_entry_wait_huge(struct vm_area_struct *vma, + pte_t *ptep, spinlock_t *ptl) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte) { } #endif /* CONFIG_HUGETLB_PAGE */ static inline int is_writable_migration_entry(swp_entry_t entry) diff --git a/include/trace/events/huge_memory.h b/include/trace/events/huge_memory.h index 760455dfa860..35d759d3b010 100644 --- a/include/trace/events/huge_memory.h +++ b/include/trace/events/huge_memory.h @@ -203,5 +203,43 @@ TRACE_EVENT(mm_khugepaged_scan_file, __print_symbolic(__entry->result, SCAN_STATUS)) ); +TRACE_EVENT(mm_khugepaged_collapse_file, + TP_PROTO(struct mm_struct *mm, struct page *hpage, pgoff_t index, + bool is_shmem, unsigned long addr, struct file *file, + int nr, int result), + TP_ARGS(mm, hpage, index, is_shmem, addr, file, nr, result), + TP_STRUCT__entry( + __field(struct mm_struct *, mm) + __field(unsigned long, hpfn) + __field(pgoff_t, index) + __field(bool, is_shmem) + __field(unsigned long, addr) + __string(filename, file->f_path.dentry->d_iname) + __field(int, nr) + __field(int, result) + ), + + TP_fast_assign( + __entry->mm = mm; + __entry->hpfn = hpage ? page_to_pfn(hpage) : -1; + __entry->index = index; + __entry->is_shmem = is_shmem; + __entry->addr = addr; + __assign_str(filename, file->f_path.dentry->d_iname); + __entry->nr = nr; + __entry->result = result; + ), + + TP_printk("mm=%p, hpage_pfn=0x%lx, index=%ld, is_shmem=%d, addr=%ld, filename=%s, nr=%d, result=%s", + __entry->mm, + __entry->hpfn, + __entry->index, + __entry->is_shmem, + __entry->addr, + __get_str(filename), + __entry->nr, + __print_symbolic(__entry->result, SCAN_STATUS)) +); + #endif /* __HUGE_MEMORY_H */ #include <trace/define_trace.h> diff --git a/kernel/kcsan/Makefile b/kernel/kcsan/Makefile index 4f35d1bced6a..8cf70f068d92 100644 --- a/kernel/kcsan/Makefile +++ b/kernel/kcsan/Makefile @@ -17,4 +17,5 @@ KCSAN_INSTRUMENT_BARRIERS_selftest.o := y obj-$(CONFIG_KCSAN_SELFTEST) += selftest.o CFLAGS_kcsan_test.o := $(CFLAGS_KCSAN) -g -fno-omit-frame-pointer +CFLAGS_kcsan_test.o += $(DISABLE_STRUCTLEAK_PLUGIN) obj-$(CONFIG_KCSAN_KUNIT_TEST) += kcsan_test.o diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index ea925731fa40..0db4093d17b8 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -7,7 +7,6 @@ obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o # Avoid recursion lockdep -> sanitizer -> ... -> lockdep. KCSAN_SANITIZE_lockdep.o := n -KMSAN_SANITIZE_lockdep.o := n ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE) diff --git a/kernel/relay.c b/kernel/relay.c index d7edc934c56d..ef12532168d9 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -148,13 +148,13 @@ static struct rchan_buf *relay_create_buf(struct rchan *chan) { struct rchan_buf *buf; - if (chan->n_subbufs > KMALLOC_MAX_SIZE / sizeof(size_t *)) + if (chan->n_subbufs > KMALLOC_MAX_SIZE / sizeof(size_t)) return NULL; buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL); if (!buf) return NULL; - buf->padding = kmalloc_array(chan->n_subbufs, sizeof(size_t *), + buf->padding = kmalloc_array(chan->n_subbufs, sizeof(size_t), GFP_KERNEL); if (!buf->padding) goto free_buf; @@ -507,7 +507,7 @@ struct rchan *relay_open(const char *base_filename, chan->private_data = private_data; if (base_filename) { chan->has_base_filename = 1; - strlcpy(chan->base_filename, base_filename, NAME_MAX); + strscpy(chan->base_filename, base_filename, NAME_MAX); } chan->cb = cb; kref_init(&chan->kref); @@ -578,7 +578,7 @@ int relay_late_setup_files(struct rchan *chan, if (!chan || !base_filename) return -EINVAL; - strlcpy(chan->base_filename, base_filename, NAME_MAX); + strscpy(chan->base_filename, base_filename, NAME_MAX); mutex_lock(&relay_channels_mutex); /* Is chan already set up? */ diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 3fe1491d2bf9..fe3947b80069 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -6062,7 +6062,7 @@ void *mas_find_rev(struct ma_state *mas, unsigned long min) if (mas->index < min) return NULL; - /* Retries on dead nodes handled by mas_next_entry */ + /* Retries on dead nodes handled by mas_prev_entry */ return mas_prev_entry(mas, min); } EXPORT_SYMBOL_GPL(mas_find_rev); diff --git a/mm/fadvise.c b/mm/fadvise.c index c76ee665355a..bf04fec87f35 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -72,7 +72,7 @@ int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice) */ endbyte = (u64)offset + (u64)len; if (!len || endbyte < len) - endbyte = -1; + endbyte = LLONG_MAX; else endbyte--; /* inclusive */ diff --git a/mm/filemap.c b/mm/filemap.c index 65eee6ec1066..c4d4ace9cc70 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -506,9 +506,6 @@ static void __filemap_fdatawait_range(struct address_space *mapping, struct pagevec pvec; int nr_pages; - if (end_byte < start_byte) - return; - pagevec_init(&pvec); while (index <= end) { unsigned i; @@ -670,6 +667,9 @@ int filemap_write_and_wait_range(struct address_space *mapping, { int err = 0, err2; + if (lend < lstart) + return 0; + if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); @@ -770,6 +770,9 @@ int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend) int err = 0, err2; struct address_space *mapping = file->f_mapping; + if (lend < lstart) + return 0; + if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); @@ -785,56 +788,54 @@ int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend) EXPORT_SYMBOL(file_write_and_wait_range); /** - * replace_page_cache_page - replace a pagecache page with a new one - * @old: page to be replaced - * @new: page to replace with - * - * This function replaces a page in the pagecache with a new one. On - * success it acquires the pagecache reference for the new page and - * drops it for the old page. Both the old and new pages must be - * locked. This function does not add the new page to the LRU, the + * replace_page_cache_folio - replace a pagecache folio with a new one + * @old: folio to be replaced + * @new: folio to replace with + * + * This function replaces a folio in the pagecache with a new one. On + * success it acquires the pagecache reference for the new folio and + * drops it for the old folio. Both the old and new folios must be + * locked. This function does not add the new folio to the LRU, the * caller must do that. * * The remove + add is atomic. This function cannot fail. */ -void replace_page_cache_page(struct page *old, struct page *new) +void replace_page_cache_folio(struct folio *old, struct folio *new) { - struct folio *fold = page_folio(old); - struct folio *fnew = page_folio(new); struct address_space *mapping = old->mapping; void (*free_folio)(struct folio *) = mapping->a_ops->free_folio; pgoff_t offset = old->index; XA_STATE(xas, &mapping->i_pages, offset); - VM_BUG_ON_PAGE(!PageLocked(old), old); - VM_BUG_ON_PAGE(!PageLocked(new), new); - VM_BUG_ON_PAGE(new->mapping, new); + VM_BUG_ON_FOLIO(!folio_test_locked(old), old); + VM_BUG_ON_FOLIO(!folio_test_locked(new), new); + VM_BUG_ON_FOLIO(new->mapping, new); - get_page(new); + folio_get(new); new->mapping = mapping; new->index = offset; - mem_cgroup_migrate(fold, fnew); + mem_cgroup_migrate(old, new); xas_lock_irq(&xas); xas_store(&xas, new); old->mapping = NULL; /* hugetlb pages do not participate in page cache accounting. */ - if (!PageHuge(old)) - __dec_lruvec_page_state(old, NR_FILE_PAGES); - if (!PageHuge(new)) - __inc_lruvec_page_state(new, NR_FILE_PAGES); - if (PageSwapBacked(old)) - __dec_lruvec_page_state(old, NR_SHMEM); - if (PageSwapBacked(new)) - __inc_lruvec_page_state(new, NR_SHMEM); + if (!folio_test_hugetlb(old)) + __lruvec_stat_sub_folio(old, NR_FILE_PAGES); + if (!folio_test_hugetlb(new)) + __lruvec_stat_add_folio(new, NR_FILE_PAGES); + if (folio_test_swapbacked(old)) + __lruvec_stat_sub_folio(old, NR_SHMEM); + if (folio_test_swapbacked(new)) + __lruvec_stat_add_folio(new, NR_SHMEM); xas_unlock_irq(&xas); if (free_folio) - free_folio(fold); - folio_put(fold); + free_folio(old); + folio_put(old); } -EXPORT_SYMBOL_GPL(replace_page_cache_page); +EXPORT_SYMBOL_GPL(replace_page_cache_folio); noinline int __filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp) diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 86933fa8f3e1..69ed25790c68 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -76,12 +76,6 @@ bool redirty_page_for_writepage(struct writeback_control *wbc, } EXPORT_SYMBOL(redirty_page_for_writepage); -void lru_cache_add(struct page *page) -{ - folio_add_lru(page_folio(page)); -} -EXPORT_SYMBOL(lru_cache_add); - void lru_cache_add_inactive_or_unevictable(struct page *page, struct vm_area_struct *vma) { @@ -545,30 +545,13 @@ static struct page *follow_page_pte(struct vm_area_struct *vma, if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) return ERR_PTR(-EINVAL); -retry: if (unlikely(pmd_bad(*pmd))) return no_page_table(vma, flags); ptep = pte_offset_map_lock(mm, pmd, address, &ptl); pte = *ptep; - if (!pte_present(pte)) { - swp_entry_t entry; - /* - * KSM's break_ksm() relies upon recognizing a ksm page - * even while it is being migrated, so for that case we - * need migration_entry_wait(). - */ - if (likely(!(flags & FOLL_MIGRATION))) - goto no_page; - if (pte_none(pte)) - goto no_page; - entry = pte_to_swp_entry(pte); - if (!is_migration_entry(entry)) - goto no_page; - pte_unmap_unlock(ptep, ptl); - migration_entry_wait(mm, pmd, address); - goto retry; - } + if (!pte_present(pte)) + goto no_page; if (pte_protnone(pte) && !gup_can_follow_protnone(flags)) goto no_page; @@ -678,28 +661,8 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma, pmdval = READ_ONCE(*pmd); if (pmd_none(pmdval)) return no_page_table(vma, flags); -retry: - if (!pmd_present(pmdval)) { - /* - * Should never reach here, if thp migration is not supported; - * Otherwise, it must be a thp migration entry. - */ - VM_BUG_ON(!thp_migration_supported() || - !is_pmd_migration_entry(pmdval)); - - if (likely(!(flags & FOLL_MIGRATION))) - return no_page_table(vma, flags); - - pmd_migration_entry_wait(mm, pmd); - pmdval = READ_ONCE(*pmd); - /* - * MADV_DONTNEED may convert the pmd to null because - * mmap_lock is held in read mode - */ - if (pmd_none(pmdval)) - return no_page_table(vma, flags); - goto retry; - } + if (!pmd_present(pmdval)) + return no_page_table(vma, flags); if (pmd_devmap(pmdval)) { ptl = pmd_lock(mm, pmd); page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap); @@ -713,18 +676,10 @@ retry: if (pmd_protnone(pmdval) && !gup_can_follow_protnone(flags)) return no_page_table(vma, flags); -retry_locked: ptl = pmd_lock(mm, pmd); - if (unlikely(pmd_none(*pmd))) { - spin_unlock(ptl); - return no_page_table(vma, flags); - } if (unlikely(!pmd_present(*pmd))) { spin_unlock(ptl); - if (likely(!(flags & FOLL_MIGRATION))) - return no_page_table(vma, flags); - pmd_migration_entry_wait(mm, pmd); - goto retry_locked; + return no_page_table(vma, flags); } if (unlikely(!pmd_trans_huge(*pmd))) { spin_unlock(ptl); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 7651420e2d8f..abe6cfd92ffa 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1381,7 +1381,7 @@ reuse: if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry, 1)) update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); spin_unlock(vmf->ptl); - return VM_FAULT_WRITE; + return 0; } unlock_fallback: diff --git a/mm/hugetlb.c b/mm/hugetlb.c index be0b2953de42..084efa3cf5e8 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -54,13 +54,13 @@ struct hstate hstates[HUGE_MAX_HSTATE]; #ifdef CONFIG_CMA static struct cma *hugetlb_cma[MAX_NUMNODES]; static unsigned long hugetlb_cma_size_in_node[MAX_NUMNODES] __initdata; -static bool hugetlb_cma_page(struct page *page, unsigned int order) +static bool hugetlb_cma_folio(struct folio *folio, unsigned int order) { - return cma_pages_valid(hugetlb_cma[page_to_nid(page)], page, + return cma_pages_valid(hugetlb_cma[folio_nid(folio)], &folio->page, 1 << order); } #else -static bool hugetlb_cma_page(struct page *page, unsigned int order) +static bool hugetlb_cma_folio(struct folio *folio, unsigned int order) { return false; } @@ -1127,17 +1127,17 @@ static bool vma_has_reserves(struct vm_area_struct *vma, long chg) return false; } -static void enqueue_huge_page(struct hstate *h, struct page *page) +static void enqueue_hugetlb_folio(struct hstate *h, struct folio *folio) { - int nid = page_to_nid(page); + int nid = folio_nid(folio); lockdep_assert_held(&hugetlb_lock); - VM_BUG_ON_PAGE(page_count(page), page); + VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); - list_move(&page->lru, &h->hugepage_freelists[nid]); + list_move(&folio->lru, &h->hugepage_freelists[nid]); h->free_huge_pages++; h->free_huge_pages_node[nid]++; - SetHPageFreed(page); + folio_set_hugetlb_freed(folio); } static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid) @@ -1325,77 +1325,76 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) nr_nodes--) /* used to demote non-gigantic_huge pages as well */ -static void __destroy_compound_gigantic_page(struct page *page, +static void __destroy_compound_gigantic_folio(struct folio *folio, unsigned int order, bool demote) { int i; int nr_pages = 1 << order; struct page *p; - atomic_set(compound_mapcount_ptr(page), 0); - atomic_set(subpages_mapcount_ptr(page), 0); - atomic_set(compound_pincount_ptr(page), 0); + atomic_set(folio_mapcount_ptr(folio), 0); + atomic_set(folio_subpages_mapcount_ptr(folio), 0); + atomic_set(folio_pincount_ptr(folio), 0); for (i = 1; i < nr_pages; i++) { - p = nth_page(page, i); + p = folio_page(folio, i); p->mapping = NULL; clear_compound_head(p); if (!demote) set_page_refcounted(p); } - set_compound_order(page, 0); -#ifdef CONFIG_64BIT - page[1].compound_nr = 0; -#endif - __ClearPageHead(page); + folio_set_compound_order(folio, 0); + __folio_clear_head(folio); } -static void destroy_compound_hugetlb_page_for_demote(struct page *page, +static void destroy_compound_hugetlb_folio_for_demote(struct folio *folio, unsigned int order) { - __destroy_compound_gigantic_page(page, order, true); + __destroy_compound_gigantic_folio(folio, order, true); } #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE -static void destroy_compound_gigantic_page(struct page *page, +static void destroy_compound_gigantic_folio(struct folio *folio, unsigned int order) { - __destroy_compound_gigantic_page(page, order, false); + __destroy_compound_gigantic_folio(folio, order, false); } -static void free_gigantic_page(struct page *page, unsigned int order) +static void free_gigantic_folio(struct folio *folio, unsigned int order) { /* * If the page isn't allocated using the cma allocator, * cma_release() returns false. */ #ifdef CONFIG_CMA - if (cma_release(hugetlb_cma[page_to_nid(page)], page, 1 << order)) + int nid = folio_nid(folio); + + if (cma_release(hugetlb_cma[nid], &folio->page, 1 << order)) return; #endif - free_contig_range(page_to_pfn(page), 1 << order); + free_contig_range(folio_pfn(folio), 1 << order); } #ifdef CONFIG_CONTIG_ALLOC -static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, +static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { + struct page *page; unsigned long nr_pages = pages_per_huge_page(h); if (nid == NUMA_NO_NODE) nid = numa_mem_id(); #ifdef CONFIG_CMA { - struct page *page; int node; if (hugetlb_cma[nid]) { page = cma_alloc(hugetlb_cma[nid], nr_pages, huge_page_order(h), true); if (page) - return page; + return page_folio(page); } if (!(gfp_mask & __GFP_THISNODE)) { @@ -1406,17 +1405,18 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, page = cma_alloc(hugetlb_cma[node], nr_pages, huge_page_order(h), true); if (page) - return page; + return page_folio(page); } } } #endif - return alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask); + page = alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask); + return page ? page_folio(page) : NULL; } #else /* !CONFIG_CONTIG_ALLOC */ -static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, +static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { return NULL; @@ -1424,30 +1424,30 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, #endif /* CONFIG_CONTIG_ALLOC */ #else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */ -static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, +static struct folio *alloc_gigantic_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { return NULL; } -static inline void free_gigantic_page(struct page *page, unsigned int order) { } -static inline void destroy_compound_gigantic_page(struct page *page, +static inline void free_gigantic_folio(struct folio *folio, + unsigned int order) { } +static inline void destroy_compound_gigantic_folio(struct folio *folio, unsigned int order) { } #endif /* - * Remove hugetlb page from lists, and update dtor so that page appears + * Remove hugetlb folio from lists, and update dtor so that the folio appears * as just a compound page. * - * A reference is held on the page, except in the case of demote. + * A reference is held on the folio, except in the case of demote. * * Must be called with hugetlb lock held. */ -static void __remove_hugetlb_page(struct hstate *h, struct page *page, +static void __remove_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus, bool demote) { - int nid = page_to_nid(page); - struct folio *folio = page_folio(page); + int nid = folio_nid(folio); VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio(folio), folio); VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio_rsvd(folio), folio); @@ -1456,9 +1456,9 @@ static void __remove_hugetlb_page(struct hstate *h, struct page *page, if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; - list_del(&page->lru); + list_del(&folio->lru); - if (HPageFreed(page)) { + if (folio_test_hugetlb_freed(folio)) { h->free_huge_pages--; h->free_huge_pages_node[nid]--; } @@ -1477,50 +1477,50 @@ static void __remove_hugetlb_page(struct hstate *h, struct page *page, * * For gigantic pages set the destructor to the null dtor. This * destructor will never be called. Before freeing the gigantic - * page destroy_compound_gigantic_page will turn the compound page - * into a simple group of pages. After this the destructor does not + * page destroy_compound_gigantic_folio will turn the folio into a + * simple group of pages. After this the destructor does not * apply. * * This handles the case where more than one ref is held when and - * after update_and_free_page is called. + * after update_and_free_hugetlb_folio is called. * * In the case of demote we do not ref count the page as it will soon * be turned into a page of smaller size. */ if (!demote) - set_page_refcounted(page); + folio_ref_unfreeze(folio, 1); if (hstate_is_gigantic(h)) - set_compound_page_dtor(page, NULL_COMPOUND_DTOR); + folio_set_compound_dtor(folio, NULL_COMPOUND_DTOR); else - set_compound_page_dtor(page, COMPOUND_PAGE_DTOR); + folio_set_compound_dtor(folio, COMPOUND_PAGE_DTOR); h->nr_huge_pages--; h->nr_huge_pages_node[nid]--; } -static void remove_hugetlb_page(struct hstate *h, struct page *page, +static void remove_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus) { - __remove_hugetlb_page(h, page, adjust_surplus, false); + __remove_hugetlb_folio(h, folio, adjust_surplus, false); } -static void remove_hugetlb_page_for_demote(struct hstate *h, struct page *page, +static void remove_hugetlb_folio_for_demote(struct hstate *h, struct folio *folio, bool adjust_surplus) { - __remove_hugetlb_page(h, page, adjust_surplus, true); + __remove_hugetlb_folio(h, folio, adjust_surplus, true); } -static void add_hugetlb_page(struct hstate *h, struct page *page, +static void add_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus) { int zeroed; - int nid = page_to_nid(page); + int nid = folio_nid(folio); - VM_BUG_ON_PAGE(!HPageVmemmapOptimized(page), page); + VM_BUG_ON_FOLIO(!folio_test_hugetlb_vmemmap_optimized(folio), folio); lockdep_assert_held(&hugetlb_lock); - INIT_LIST_HEAD(&page->lru); + INIT_LIST_HEAD(&folio->lru); h->nr_huge_pages++; h->nr_huge_pages_node[nid]++; @@ -1529,21 +1529,21 @@ static void add_hugetlb_page(struct hstate *h, struct page *page, h->surplus_huge_pages_node[nid]++; } - set_compound_page_dtor(page, HUGETLB_PAGE_DTOR); - set_page_private(page, 0); + folio_set_compound_dtor(folio, HUGETLB_PAGE_DTOR); + folio_change_private(folio, NULL); /* - * We have to set HPageVmemmapOptimized again as above - * set_page_private(page, 0) cleared it. + * We have to set hugetlb_vmemmap_optimized again as above + * folio_change_private(folio, NULL) cleared it. */ - SetHPageVmemmapOptimized(page); + folio_set_hugetlb_vmemmap_optimized(folio); /* - * This page is about to be managed by the hugetlb allocator and + * This folio is about to be managed by the hugetlb allocator and * should have no users. Drop our reference, and check for others * just in case. */ - zeroed = put_page_testzero(page); - if (!zeroed) + zeroed = folio_put_testzero(folio); + if (unlikely(!zeroed)) /* * It is VERY unlikely soneone else has taken a ref on * the page. In this case, we simply return as the @@ -1552,13 +1552,14 @@ static void add_hugetlb_page(struct hstate *h, struct page *page, */ return; - arch_clear_hugepage_flags(page); - enqueue_huge_page(h, page); + arch_clear_hugepage_flags(&folio->page); + enqueue_hugetlb_folio(h, folio); } static void __update_and_free_page(struct hstate *h, struct page *page) { int i; + struct folio *folio = page_folio(page); struct page *subpage; if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) @@ -1568,7 +1569,7 @@ static void __update_and_free_page(struct hstate *h, struct page *page) * If we don't know which subpages are hwpoisoned, we can't free * the hugepage, so it's leaked intentionally. */ - if (HPageRawHwpUnreliable(page)) + if (folio_test_hugetlb_raw_hwp_unreliable(folio)) return; if (hugetlb_vmemmap_restore(h, page)) { @@ -1578,7 +1579,7 @@ static void __update_and_free_page(struct hstate *h, struct page *page) * page and put the page back on the hugetlb free list and treat * as a surplus page. */ - add_hugetlb_page(h, page, true); + add_hugetlb_folio(h, folio, true); spin_unlock_irq(&hugetlb_lock); return; } @@ -1587,11 +1588,11 @@ static void __update_and_free_page(struct hstate *h, struct page *page) * Move PageHWPoison flag from head page to the raw error pages, * which makes any healthy subpages reusable. */ - if (unlikely(PageHWPoison(page))) - hugetlb_clear_page_hwpoison(page); + if (unlikely(folio_test_hwpoison(folio))) + hugetlb_clear_page_hwpoison(&folio->page); for (i = 0; i < pages_per_huge_page(h); i++) { - subpage = nth_page(page, i); + subpage = folio_page(folio, i); subpage->flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced | 1 << PG_dirty | 1 << PG_active | 1 << PG_private | @@ -1600,19 +1601,19 @@ static void __update_and_free_page(struct hstate *h, struct page *page) /* * Non-gigantic pages demoted from CMA allocated gigantic pages - * need to be given back to CMA in free_gigantic_page. + * need to be given back to CMA in free_gigantic_folio. */ if (hstate_is_gigantic(h) || - hugetlb_cma_page(page, huge_page_order(h))) { - destroy_compound_gigantic_page(page, huge_page_order(h)); - free_gigantic_page(page, huge_page_order(h)); + hugetlb_cma_folio(folio, huge_page_order(h))) { + destroy_compound_gigantic_folio(folio, huge_page_order(h)); + free_gigantic_folio(folio, huge_page_order(h)); } else { __free_pages(page, huge_page_order(h)); } } /* - * As update_and_free_page() can be called under any context, so we cannot + * As update_and_free_hugetlb_folio() can be called under any context, so we cannot * use GFP_KERNEL to allocate vmemmap pages. However, we can defer the * actual freeing in a workqueue to prevent from using GFP_ATOMIC to allocate * the vmemmap pages. @@ -1641,8 +1642,9 @@ static void free_hpage_workfn(struct work_struct *work) /* * The VM_BUG_ON_PAGE(!PageHuge(page), page) in page_hstate() * is going to trigger because a previous call to - * remove_hugetlb_page() will set_compound_page_dtor(page, - * NULL_COMPOUND_DTOR), so do not use page_hstate() directly. + * remove_hugetlb_folio() will call folio_set_compound_dtor + * (folio, NULL_COMPOUND_DTOR), so do not use page_hstate() + * directly. */ h = size_to_hstate(page_size(page)); @@ -1659,11 +1661,11 @@ static inline void flush_free_hpage_work(struct hstate *h) flush_work(&free_hpage_work); } -static void update_and_free_page(struct hstate *h, struct page *page, +static void update_and_free_hugetlb_folio(struct hstate *h, struct folio *folio, bool atomic) { - if (!HPageVmemmapOptimized(page) || !atomic) { - __update_and_free_page(h, page); + if (!folio_test_hugetlb_vmemmap_optimized(folio) || !atomic) { + __update_and_free_page(h, &folio->page); return; } @@ -1674,16 +1676,18 @@ static void update_and_free_page(struct hstate *h, struct page *page, * empty. Otherwise, schedule_work() had been called but the workfn * hasn't retrieved the list yet. */ - if (llist_add((struct llist_node *)&page->mapping, &hpage_freelist)) + if (llist_add((struct llist_node *)&folio->mapping, &hpage_freelist)) schedule_work(&free_hpage_work); } static void update_and_free_pages_bulk(struct hstate *h, struct list_head *list) { struct page *page, *t_page; + struct folio *folio; list_for_each_entry_safe(page, t_page, list, lru) { - update_and_free_page(h, page, false); + folio = page_folio(page); + update_and_free_hugetlb_folio(h, folio, false); cond_resched(); } } @@ -1751,17 +1755,17 @@ void free_huge_page(struct page *page) h->resv_huge_pages++; if (folio_test_hugetlb_temporary(folio)) { - remove_hugetlb_page(h, page, false); + remove_hugetlb_folio(h, folio, false); spin_unlock_irqrestore(&hugetlb_lock, flags); - update_and_free_page(h, page, true); + update_and_free_hugetlb_folio(h, folio, true); } else if (h->surplus_huge_pages_node[nid]) { /* remove the page from active list */ - remove_hugetlb_page(h, page, true); + remove_hugetlb_folio(h, folio, true); spin_unlock_irqrestore(&hugetlb_lock, flags); - update_and_free_page(h, page, true); + update_and_free_hugetlb_folio(h, folio, true); } else { arch_clear_hugepage_flags(page); - enqueue_huge_page(h, page); + enqueue_hugetlb_folio(h, folio); spin_unlock_irqrestore(&hugetlb_lock, flags); } } @@ -1780,35 +1784,33 @@ static void __prep_new_hugetlb_folio(struct hstate *h, struct folio *folio) { hugetlb_vmemmap_optimize(h, &folio->page); INIT_LIST_HEAD(&folio->lru); - folio->_folio_dtor = HUGETLB_PAGE_DTOR; + folio_set_compound_dtor(folio, HUGETLB_PAGE_DTOR); hugetlb_set_folio_subpool(folio, NULL); set_hugetlb_cgroup(folio, NULL); set_hugetlb_cgroup_rsvd(folio, NULL); } -static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) +static void prep_new_hugetlb_folio(struct hstate *h, struct folio *folio, int nid) { - struct folio *folio = page_folio(page); - __prep_new_hugetlb_folio(h, folio); spin_lock_irq(&hugetlb_lock); __prep_account_new_huge_page(h, nid); spin_unlock_irq(&hugetlb_lock); } -static bool __prep_compound_gigantic_page(struct page *page, unsigned int order, - bool demote) +static bool __prep_compound_gigantic_folio(struct folio *folio, + unsigned int order, bool demote) { int i, j; int nr_pages = 1 << order; struct page *p; - /* we rely on prep_new_huge_page to set the destructor */ - set_compound_order(page, order); - __ClearPageReserved(page); - __SetPageHead(page); + /* we rely on prep_new_hugetlb_folio to set the destructor */ + folio_set_compound_order(folio, order); + __folio_clear_reserved(folio); + __folio_set_head(folio); for (i = 0; i < nr_pages; i++) { - p = nth_page(page, i); + p = folio_page(folio, i); /* * For gigantic hugepages allocated through bootmem at @@ -1850,43 +1852,41 @@ static bool __prep_compound_gigantic_page(struct page *page, unsigned int order, VM_BUG_ON_PAGE(page_count(p), p); } if (i != 0) - set_compound_head(p, page); + set_compound_head(p, &folio->page); } - atomic_set(compound_mapcount_ptr(page), -1); - atomic_set(subpages_mapcount_ptr(page), 0); - atomic_set(compound_pincount_ptr(page), 0); + atomic_set(folio_mapcount_ptr(folio), -1); + atomic_set(folio_subpages_mapcount_ptr(folio), 0); + atomic_set(folio_pincount_ptr(folio), 0); return true; out_error: /* undo page modifications made above */ for (j = 0; j < i; j++) { - p = nth_page(page, j); + p = folio_page(folio, j); if (j != 0) clear_compound_head(p); set_page_refcounted(p); } /* need to clear PG_reserved on remaining tail pages */ for (; j < nr_pages; j++) { - p = nth_page(page, j); + p = folio_page(folio, j); __ClearPageReserved(p); } - set_compound_order(page, 0); -#ifdef CONFIG_64BIT - page[1].compound_nr = 0; -#endif - __ClearPageHead(page); + folio_set_compound_order(folio, 0); + __folio_clear_head(folio); return false; } -static bool prep_compound_gigantic_page(struct page *page, unsigned int order) +static bool prep_compound_gigantic_folio(struct folio *folio, + unsigned int order) { - return __prep_compound_gigantic_page(page, order, false); + return __prep_compound_gigantic_folio(folio, order, false); } -static bool prep_compound_gigantic_page_for_demote(struct page *page, +static bool prep_compound_gigantic_folio_for_demote(struct folio *folio, unsigned int order) { - return __prep_compound_gigantic_page(page, order, true); + return __prep_compound_gigantic_folio(folio, order, true); } /* @@ -1951,7 +1951,7 @@ pgoff_t hugetlb_basepage_index(struct page *page) return (index << compound_order(page_head)) + compound_idx; } -static struct page *alloc_buddy_huge_page(struct hstate *h, +static struct folio *alloc_buddy_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { @@ -1989,11 +1989,6 @@ retry: page = NULL; } - if (page) - __count_vm_event(HTLB_BUDDY_PGALLOC); - else - __count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); - /* * If we did not specify __GFP_RETRY_MAYFAIL, but still got a page this * indicates an overall state change. Clear bit so that we resume @@ -2010,7 +2005,13 @@ retry: if (node_alloc_noretry && !page && alloc_try_hard) node_set(nid, *node_alloc_noretry); - return page; + if (!page) { + __count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); + return NULL; + } + + __count_vm_event(HTLB_BUDDY_PGALLOC); + return page_folio(page); } /* @@ -2020,29 +2021,28 @@ retry: * Note that returned page is 'frozen': ref count of head page and all tail * pages is zero. */ -static struct page *alloc_fresh_huge_page(struct hstate *h, +static struct folio *alloc_fresh_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { - struct page *page; + struct folio *folio; bool retry = false; retry: if (hstate_is_gigantic(h)) - page = alloc_gigantic_page(h, gfp_mask, nid, nmask); + folio = alloc_gigantic_folio(h, gfp_mask, nid, nmask); else - page = alloc_buddy_huge_page(h, gfp_mask, + folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, nmask, node_alloc_noretry); - if (!page) + if (!folio) return NULL; - if (hstate_is_gigantic(h)) { - if (!prep_compound_gigantic_page(page, huge_page_order(h))) { + if (!prep_compound_gigantic_folio(folio, huge_page_order(h))) { /* * Rare failure to convert pages to compound page. * Free pages and try again - ONCE! */ - free_gigantic_page(page, huge_page_order(h)); + free_gigantic_folio(folio, huge_page_order(h)); if (!retry) { retry = true; goto retry; @@ -2050,9 +2050,9 @@ retry: return NULL; } } - prep_new_huge_page(h, page, page_to_nid(page)); + prep_new_hugetlb_folio(h, folio, folio_nid(folio)); - return page; + return folio; } /* @@ -2062,23 +2062,20 @@ retry: static int alloc_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, nodemask_t *node_alloc_noretry) { - struct page *page; + struct folio *folio; int nr_nodes, node; gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) { - page = alloc_fresh_huge_page(h, gfp_mask, node, nodes_allowed, - node_alloc_noretry); - if (page) - break; + folio = alloc_fresh_hugetlb_folio(h, gfp_mask, node, + nodes_allowed, node_alloc_noretry); + if (folio) { + free_huge_page(&folio->page); /* free it into the hugepage allocator */ + return 1; + } } - if (!page) - return 0; - - free_huge_page(page); /* free it into the hugepage allocator */ - - return 1; + return 0; } /* @@ -2094,6 +2091,7 @@ static struct page *remove_pool_huge_page(struct hstate *h, { int nr_nodes, node; struct page *page = NULL; + struct folio *folio; lockdep_assert_held(&hugetlb_lock); for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { @@ -2105,7 +2103,8 @@ static struct page *remove_pool_huge_page(struct hstate *h, !list_empty(&h->hugepage_freelists[node])) { page = list_entry(h->hugepage_freelists[node].next, struct page, lru); - remove_hugetlb_page(h, page, acct_surplus); + folio = page_folio(page); + remove_hugetlb_folio(h, folio, acct_surplus); break; } } @@ -2130,21 +2129,21 @@ static struct page *remove_pool_huge_page(struct hstate *h, int dissolve_free_huge_page(struct page *page) { int rc = -EBUSY; + struct folio *folio = page_folio(page); retry: /* Not to disrupt normal path by vainly holding hugetlb_lock */ - if (!PageHuge(page)) + if (!folio_test_hugetlb(folio)) return 0; spin_lock_irq(&hugetlb_lock); - if (!PageHuge(page)) { + if (!folio_test_hugetlb(folio)) { rc = 0; goto out; } - if (!page_count(page)) { - struct page *head = compound_head(page); - struct hstate *h = page_hstate(head); + if (!folio_ref_count(folio)) { + struct hstate *h = folio_hstate(folio); if (!available_huge_pages(h)) goto out; @@ -2152,7 +2151,7 @@ retry: * We should make sure that the page is already on the free list * when it is dissolved. */ - if (unlikely(!HPageFreed(head))) { + if (unlikely(!folio_test_hugetlb_freed(folio))) { spin_unlock_irq(&hugetlb_lock); cond_resched(); @@ -2167,24 +2166,24 @@ retry: goto retry; } - remove_hugetlb_page(h, head, false); + remove_hugetlb_folio(h, folio, false); h->max_huge_pages--; spin_unlock_irq(&hugetlb_lock); /* - * Normally update_and_free_page will allocate required vmemmmap - * before freeing the page. update_and_free_page will fail to + * Normally update_and_free_hugtlb_folio will allocate required vmemmmap + * before freeing the page. update_and_free_hugtlb_folio will fail to * free the page if it can not allocate required vmemmap. We * need to adjust max_huge_pages if the page is not freed. * Attempt to allocate vmemmmap here so that we can take * appropriate action on failure. */ - rc = hugetlb_vmemmap_restore(h, head); + rc = hugetlb_vmemmap_restore(h, &folio->page); if (!rc) { - update_and_free_page(h, head, false); + update_and_free_hugetlb_folio(h, folio, false); } else { spin_lock_irq(&hugetlb_lock); - add_hugetlb_page(h, head, false); + add_hugetlb_folio(h, folio, false); h->max_huge_pages++; spin_unlock_irq(&hugetlb_lock); } @@ -2235,7 +2234,7 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { - struct page *page = NULL; + struct folio *folio = NULL; if (hstate_is_gigantic(h)) return NULL; @@ -2245,8 +2244,8 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask, goto out_unlock; spin_unlock_irq(&hugetlb_lock); - page = alloc_fresh_huge_page(h, gfp_mask, nid, nmask, NULL); - if (!page) + folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, NULL); + if (!folio) return NULL; spin_lock_irq(&hugetlb_lock); @@ -2258,43 +2257,42 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask, * codeflow */ if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) { - SetHPageTemporary(page); + folio_set_hugetlb_temporary(folio); spin_unlock_irq(&hugetlb_lock); - free_huge_page(page); + free_huge_page(&folio->page); return NULL; } h->surplus_huge_pages++; - h->surplus_huge_pages_node[page_to_nid(page)]++; + h->surplus_huge_pages_node[folio_nid(folio)]++; out_unlock: spin_unlock_irq(&hugetlb_lock); - return page; + return &folio->page; } static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { - struct page *page; + struct folio *folio; if (hstate_is_gigantic(h)) return NULL; - page = alloc_fresh_huge_page(h, gfp_mask, nid, nmask, NULL); - if (!page) + folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, NULL); + if (!folio) return NULL; /* fresh huge pages are frozen */ - set_page_refcounted(page); - + folio_ref_unfreeze(folio, 1); /* * We do not account these pages as surplus because they are only * temporary and will be released properly on the last reference */ - SetHPageTemporary(page); + folio_set_hugetlb_temporary(folio); - return page; + return &folio->page; } /* @@ -2436,7 +2434,7 @@ retry: if ((--needed) < 0) break; /* Add the page to the hugetlb allocator */ - enqueue_huge_page(h, page); + enqueue_hugetlb_folio(h, page_folio(page)); } free: spin_unlock_irq(&hugetlb_lock); @@ -2743,19 +2741,18 @@ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, } /* - * alloc_and_dissolve_huge_page - Allocate a new page and dissolve the old one + * alloc_and_dissolve_hugetlb_folio - Allocate a new folio and dissolve + * the old one * @h: struct hstate old page belongs to - * @old_page: Old page to dissolve + * @old_folio: Old folio to dissolve * @list: List to isolate the page in case we need to * Returns 0 on success, otherwise negated error. */ -static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page, - struct list_head *list) +static int alloc_and_dissolve_hugetlb_folio(struct hstate *h, + struct folio *old_folio, struct list_head *list) { gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; - struct folio *old_folio = page_folio(old_page); int nid = folio_nid(old_folio); - struct page *new_page; struct folio *new_folio; int ret = 0; @@ -2766,26 +2763,25 @@ static int alloc_and_dissolve_huge_page(struct hstate *h, struct page *old_page, * the pool. This simplifies and let us do most of the processing * under the lock. */ - new_page = alloc_buddy_huge_page(h, gfp_mask, nid, NULL, NULL); - if (!new_page) + new_folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, NULL, NULL); + if (!new_folio) return -ENOMEM; - new_folio = page_folio(new_page); __prep_new_hugetlb_folio(h, new_folio); retry: spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(old_folio)) { /* - * Freed from under us. Drop new_page too. + * Freed from under us. Drop new_folio too. */ goto free_new; } else if (folio_ref_count(old_folio)) { /* - * Someone has grabbed the page, try to isolate it here. + * Someone has grabbed the folio, try to isolate it here. * Fail with -EBUSY if not possible. */ spin_unlock_irq(&hugetlb_lock); - ret = isolate_hugetlb(old_page, list); + ret = isolate_hugetlb(&old_folio->page, list); spin_lock_irq(&hugetlb_lock); goto free_new; } else if (!folio_test_hugetlb_freed(old_folio)) { @@ -2802,23 +2798,23 @@ retry: * Ok, old_page is still a genuine free hugepage. Remove it from * the freelist and decrease the counters. These will be * incremented again when calling __prep_account_new_huge_page() - * and enqueue_huge_page() for new_page. The counters will remain - * stable since this happens under the lock. + * and enqueue_hugetlb_folio() for new_folio. The counters will + * remain stable since this happens under the lock. */ - remove_hugetlb_page(h, old_page, false); + remove_hugetlb_folio(h, old_folio, false); /* * Ref count on new page is already zero as it was dropped * earlier. It can be directly added to the pool free list. */ __prep_account_new_huge_page(h, nid); - enqueue_huge_page(h, new_page); + enqueue_hugetlb_folio(h, new_folio); /* * Pages have been replaced, we can safely free the old one. */ spin_unlock_irq(&hugetlb_lock); - update_and_free_page(h, old_page, false); + update_and_free_hugetlb_folio(h, old_folio, false); } return ret; @@ -2827,7 +2823,7 @@ free_new: spin_unlock_irq(&hugetlb_lock); /* Page has a zero ref count, but needs a ref to be freed */ folio_ref_unfreeze(new_folio, 1); - update_and_free_page(h, new_page, false); + update_and_free_hugetlb_folio(h, new_folio, false); return ret; } @@ -2863,7 +2859,7 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) if (folio_ref_count(folio) && !isolate_hugetlb(&folio->page, list)) ret = 0; else if (!folio_ref_count(folio)) - ret = alloc_and_dissolve_huge_page(h, &folio->page, list); + ret = alloc_and_dissolve_hugetlb_folio(h, folio, list); return ret; } @@ -2938,7 +2934,6 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, * a reservation exists for the allocation. */ page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, gbl_chg); - if (!page) { spin_unlock_irq(&hugetlb_lock); page = alloc_buddy_huge_page_with_mpol(h, vma, addr); @@ -3049,17 +3044,18 @@ static void __init gather_bootmem_prealloc(void) list_for_each_entry(m, &huge_boot_pages, list) { struct page *page = virt_to_page(m); + struct folio *folio = page_folio(page); struct hstate *h = m->hstate; VM_BUG_ON(!hstate_is_gigantic(h)); - WARN_ON(page_count(page) != 1); - if (prep_compound_gigantic_page(page, huge_page_order(h))) { - WARN_ON(PageReserved(page)); - prep_new_huge_page(h, page, page_to_nid(page)); + WARN_ON(folio_ref_count(folio) != 1); + if (prep_compound_gigantic_folio(folio, huge_page_order(h))) { + WARN_ON(folio_test_reserved(folio)); + prep_new_hugetlb_folio(h, folio, folio_nid(folio)); free_huge_page(page); /* add to the hugepage allocator */ } else { /* VERY unlikely inflated ref count on a tail page */ - free_gigantic_page(page, huge_page_order(h)); + free_gigantic_folio(folio, huge_page_order(h)); } /* @@ -3081,14 +3077,14 @@ static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid) if (!alloc_bootmem_huge_page(h, nid)) break; } else { - struct page *page; + struct folio *folio; gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; - page = alloc_fresh_huge_page(h, gfp_mask, nid, + folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, &node_states[N_MEMORY], NULL); - if (!page) + if (!folio) break; - free_huge_page(page); /* free it into the hugepage allocator */ + free_huge_page(&folio->page); /* free it into the hugepage allocator */ } cond_resched(); } @@ -3233,7 +3229,7 @@ static void try_to_free_low(struct hstate *h, unsigned long count, goto out; if (PageHighMem(page)) continue; - remove_hugetlb_page(h, page, false); + remove_hugetlb_folio(h, page_folio(page), false); list_add(&page->lru, &page_list); } } @@ -3438,12 +3434,13 @@ static int demote_free_huge_page(struct hstate *h, struct page *page) { int i, nid = page_to_nid(page); struct hstate *target_hstate; + struct folio *folio = page_folio(page); struct page *subpage; int rc = 0; target_hstate = size_to_hstate(PAGE_SIZE << h->demote_order); - remove_hugetlb_page_for_demote(h, page, false); + remove_hugetlb_folio_for_demote(h, folio, false); spin_unlock_irq(&hugetlb_lock); rc = hugetlb_vmemmap_restore(h, page); @@ -3451,15 +3448,15 @@ static int demote_free_huge_page(struct hstate *h, struct page *page) /* Allocation of vmemmmap failed, we can not demote page */ spin_lock_irq(&hugetlb_lock); set_page_refcounted(page); - add_hugetlb_page(h, page, false); + add_hugetlb_folio(h, page_folio(page), false); return rc; } /* - * Use destroy_compound_hugetlb_page_for_demote for all huge page + * Use destroy_compound_hugetlb_folio_for_demote for all huge page * sizes as it will not ref count pages. */ - destroy_compound_hugetlb_page_for_demote(page, huge_page_order(h)); + destroy_compound_hugetlb_folio_for_demote(folio, huge_page_order(h)); /* * Taking target hstate mutex synchronizes with set_max_huge_pages. @@ -3473,13 +3470,14 @@ static int demote_free_huge_page(struct hstate *h, struct page *page) for (i = 0; i < pages_per_huge_page(h); i += pages_per_huge_page(target_hstate)) { subpage = nth_page(page, i); + folio = page_folio(subpage); if (hstate_is_gigantic(target_hstate)) - prep_compound_gigantic_page_for_demote(subpage, + prep_compound_gigantic_folio_for_demote(folio, target_hstate->order); else prep_compound_page(subpage, target_hstate->order); set_page_private(subpage, 0); - prep_new_huge_page(target_hstate, subpage, nid); + prep_new_hugetlb_folio(target_hstate, folio, nid); free_huge_page(subpage); } mutex_unlock(&target_hstate->resize_lock); @@ -4816,7 +4814,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, } else { /* * For shared mappings the vma lock must be held before - * calling huge_pte_offset in the src vma. Otherwise, the + * calling hugetlb_walk() in the src vma. Otherwise, the * returned ptep could go away if part of a shared pmd and * another thread calls huge_pmd_unshare. */ @@ -4826,7 +4824,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, last_addr_mask = hugetlb_mask_last_page(h); for (addr = src_vma->vm_start; addr < src_vma->vm_end; addr += sz) { spinlock_t *src_ptl, *dst_ptl; - src_pte = huge_pte_offset(src, addr, sz); + src_pte = hugetlb_walk(src_vma, addr, sz); if (!src_pte) { addr |= last_addr_mask; continue; @@ -5030,7 +5028,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, hugetlb_vma_lock_write(vma); i_mmap_lock_write(mapping); for (; old_addr < old_end; old_addr += sz, new_addr += sz) { - src_pte = huge_pte_offset(mm, old_addr, sz); + src_pte = hugetlb_walk(vma, old_addr, sz); if (!src_pte) { old_addr |= last_addr_mask; new_addr |= last_addr_mask; @@ -5093,7 +5091,7 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct last_addr_mask = hugetlb_mask_last_page(h); address = start; for (; address < end; address += sz) { - ptep = huge_pte_offset(mm, address, sz); + ptep = hugetlb_walk(vma, address, sz); if (!ptep) { address |= last_addr_mask; continue; @@ -5406,7 +5404,7 @@ retry_avoidcopy: mutex_lock(&hugetlb_fault_mutex_table[hash]); hugetlb_vma_lock_read(vma); spin_lock(ptl); - ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); + ptep = hugetlb_walk(vma, haddr, huge_page_size(h)); if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) goto retry_avoidcopy; @@ -5444,7 +5442,7 @@ retry_avoidcopy: * before the page tables are altered */ spin_lock(ptl); - ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); + ptep = hugetlb_walk(vma, haddr, huge_page_size(h)); if (likely(ptep && pte_same(huge_ptep_get(ptep), pte))) { /* Break COW or unshare */ huge_ptep_clear_flush(vma, haddr, ptep); @@ -5826,22 +5824,6 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, int need_wait_lock = 0; unsigned long haddr = address & huge_page_mask(h); - ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); - if (ptep) { - /* - * Since we hold no locks, ptep could be stale. That is - * OK as we are only making decisions based on content and - * not actually modifying content here. - */ - entry = huge_ptep_get(ptep); - if (unlikely(is_hugetlb_entry_migration(entry))) { - migration_entry_wait_huge(vma, ptep); - return 0; - } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) - return VM_FAULT_HWPOISON_LARGE | - VM_FAULT_SET_HINDEX(hstate_index(h)); - } - /* * Serialize hugepage allocation and instantiation, so that we don't * get spurious allocation failures if two CPUs race to instantiate @@ -5857,7 +5839,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, * until finished with ptep. This prevents huge_pmd_unshare from * being called elsewhere and making the ptep no longer valid. * - * ptep could have already be assigned via huge_pte_offset. That + * ptep could have already be assigned via hugetlb_walk(). That * is OK, as huge_pte_alloc will return the same value unless * something has changed. */ @@ -5888,8 +5870,22 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, * fault, and is_hugetlb_entry_(migration|hwpoisoned) check will * properly handle it. */ - if (!pte_present(entry)) + if (!pte_present(entry)) { + if (unlikely(is_hugetlb_entry_migration(entry))) { + /* + * Release fault lock first because the vma lock is + * needed to guard the huge_pte_lockptr() later in + * migration_entry_wait_huge(). The vma lock will + * be released there. + */ + mutex_unlock(&hugetlb_fault_mutex_table[hash]); + migration_entry_wait_huge(vma, ptep); + return 0; + } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) + ret = VM_FAULT_HWPOISON_LARGE | + VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_mutex; + } /* * If we are going to COW/unshare the mapping later, we examine the @@ -6234,10 +6230,10 @@ struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, if (WARN_ON_ONCE(flags & FOLL_PIN)) return NULL; -retry: - pte = huge_pte_offset(mm, haddr, huge_page_size(h)); + hugetlb_vma_lock_read(vma); + pte = hugetlb_walk(vma, haddr, huge_page_size(h)); if (!pte) - return NULL; + goto out_unlock; ptl = huge_pte_lock(h, mm, pte); entry = huge_ptep_get(pte); @@ -6257,19 +6253,11 @@ retry: page = NULL; goto out; } - } else { - if (is_hugetlb_entry_migration(entry)) { - spin_unlock(ptl); - __migration_entry_wait_huge(pte, ptl); - goto retry; - } - /* - * hwpoisoned entry is treated as no_page_table in - * follow_page_mask(). - */ } out: spin_unlock(ptl); +out_unlock: + hugetlb_vma_unlock_read(vma); return page; } @@ -6300,6 +6288,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, break; } + hugetlb_vma_lock_read(vma); /* * Some archs (sparc64, sh*) have multiple pte_ts to * each hugepage. We have to make sure we get the @@ -6307,8 +6296,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, * * Note that page table lock is not held when pte is null. */ - pte = huge_pte_offset(mm, vaddr & huge_page_mask(h), - huge_page_size(h)); + pte = hugetlb_walk(vma, vaddr & huge_page_mask(h), + huge_page_size(h)); if (pte) ptl = huge_pte_lock(h, mm, pte); absent = !pte || huge_pte_none(huge_ptep_get(pte)); @@ -6324,6 +6313,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, !hugetlbfs_pagecache_present(h, vma, vaddr)) { if (pte) spin_unlock(ptl); + hugetlb_vma_unlock_read(vma); remainder = 0; break; } @@ -6345,6 +6335,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, if (pte) spin_unlock(ptl); + hugetlb_vma_unlock_read(vma); + if (flags & FOLL_WRITE) fault_flags |= FAULT_FLAG_WRITE; else if (unshare) @@ -6407,6 +6399,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, remainder -= pages_per_huge_page(h); i += pages_per_huge_page(h); spin_unlock(ptl); + hugetlb_vma_unlock_read(vma); continue; } @@ -6436,6 +6429,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, if (WARN_ON_ONCE(!try_grab_folio(pages[i], refs, flags))) { spin_unlock(ptl); + hugetlb_vma_unlock_read(vma); remainder = 0; err = -ENOMEM; break; @@ -6447,6 +6441,7 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, i += refs; spin_unlock(ptl); + hugetlb_vma_unlock_read(vma); } *nr_pages = remainder; /* @@ -6493,7 +6488,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, last_addr_mask = hugetlb_mask_last_page(h); for (; address < end; address += psize) { spinlock_t *ptl; - ptep = huge_pte_offset(mm, address, psize); + ptep = hugetlb_walk(vma, address, psize); if (!ptep) { address |= last_addr_mask; continue; @@ -6871,12 +6866,6 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, *end = ALIGN(*end, PUD_SIZE); } -static bool __vma_shareable_flags_pmd(struct vm_area_struct *vma) -{ - return vma->vm_flags & (VM_MAYSHARE | VM_SHARED) && - vma->vm_private_data; -} - void hugetlb_vma_lock_read(struct vm_area_struct *vma) { if (__vma_shareable_flags_pmd(vma)) { @@ -7042,8 +7031,8 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, saddr = page_table_shareable(svma, vma, addr, idx); if (saddr) { - spte = huge_pte_offset(svma->vm_mm, saddr, - vma_mmu_pagesize(svma)); + spte = hugetlb_walk(svma, saddr, + vma_mmu_pagesize(svma)); if (spte) { get_page(virt_to_page(spte)); break; @@ -7348,7 +7337,6 @@ void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int re int old_nid = folio_nid(old_folio); int new_nid = folio_nid(new_folio); - folio_set_hugetlb_temporary(old_folio); folio_clear_hugetlb_temporary(new_folio); @@ -7402,7 +7390,7 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) hugetlb_vma_lock_write(vma); i_mmap_lock_write(vma->vm_file->f_mapping); for (address = start; address < end; address += PUD_SIZE) { - ptep = huge_pte_offset(mm, address, sz); + ptep = hugetlb_walk(vma, address, sz); if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index a84491bc4867..ea8cf1310b1e 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -541,6 +541,18 @@ static inline bool kasan_arch_is_ready(void) { return true; } #error kasan_arch_is_ready only works in KASAN generic outline mode! #endif +#if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) + +void kasan_kunit_test_suite_start(void); +void kasan_kunit_test_suite_end(void); + +#else /* CONFIG_KASAN_KUNIT_TEST */ + +static inline void kasan_kunit_test_suite_start(void) { } +static inline void kasan_kunit_test_suite_end(void) { } + +#endif /* CONFIG_KASAN_KUNIT_TEST */ + #if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) || IS_ENABLED(CONFIG_KASAN_MODULE_TEST) bool kasan_save_enable_multi_shot(void); diff --git a/mm/kasan/kasan_test.c b/mm/kasan/kasan_test.c index b8ff39324ed7..74cd80c12b25 100644 --- a/mm/kasan/kasan_test.c +++ b/mm/kasan/kasan_test.c @@ -76,6 +76,9 @@ static int kasan_suite_init(struct kunit_suite *suite) return -1; } + /* Stop failing KUnit tests on KASAN reports. */ + kasan_kunit_test_suite_start(); + /* * Temporarily enable multi-shot mode. Otherwise, KASAN would only * report the first detected bug and panic the kernel if panic_on_warn @@ -94,6 +97,7 @@ static int kasan_suite_init(struct kunit_suite *suite) static void kasan_suite_exit(struct kunit_suite *suite) { + kasan_kunit_test_suite_end(); kasan_restore_multi_shot(multishot); for_each_kernel_tracepoint(unregister_tracepoints, NULL); tracepoint_synchronize_unregister(); diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 6522619a9762..1d02757e90a3 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -9,6 +9,7 @@ * Andrey Konovalov <andreyknvl@gmail.com> */ +#include <kunit/test.h> #include <linux/bitops.h> #include <linux/ftrace.h> #include <linux/init.h> @@ -112,10 +113,62 @@ EXPORT_SYMBOL_GPL(kasan_restore_multi_shot); #endif +#if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST) + +/* + * Whether the KASAN KUnit test suite is currently being executed. + * Updated in kasan_test.c. + */ +bool kasan_kunit_executing; + +void kasan_kunit_test_suite_start(void) +{ + WRITE_ONCE(kasan_kunit_executing, true); +} +EXPORT_SYMBOL_GPL(kasan_kunit_test_suite_start); + +void kasan_kunit_test_suite_end(void) +{ + WRITE_ONCE(kasan_kunit_executing, false); +} +EXPORT_SYMBOL_GPL(kasan_kunit_test_suite_end); + +static bool kasan_kunit_test_suite_executing(void) +{ + return READ_ONCE(kasan_kunit_executing); +} + +#else /* CONFIG_KASAN_KUNIT_TEST */ + +static inline bool kasan_kunit_test_suite_executing(void) { return false; } + +#endif /* CONFIG_KASAN_KUNIT_TEST */ + +#if IS_ENABLED(CONFIG_KUNIT) + +static void fail_non_kasan_kunit_test(void) +{ + struct kunit *test; + + if (kasan_kunit_test_suite_executing()) + return; + + test = current->kunit_test; + if (test) + kunit_set_failure(test); +} + +#else /* CONFIG_KUNIT */ + +static inline void fail_non_kasan_kunit_test(void) { } + +#endif /* CONFIG_KUNIT */ + static DEFINE_SPINLOCK(report_lock); static void start_report(unsigned long *flags, bool sync) { + fail_non_kasan_kunit_test(); /* Respect the /proc/sys/kernel/traceoff_on_warning interface. */ disable_trace_on_warning(); /* Do not allow LOCKDEP mangling KASAN reports. */ diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 6fc4d80d991a..5cb401aa2b9d 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1744,12 +1744,12 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, { struct address_space *mapping = file->f_mapping; struct page *hpage; - pgoff_t index, end = start + HPAGE_PMD_NR; + pgoff_t index = 0, end = start + HPAGE_PMD_NR; LIST_HEAD(pagelist); XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER); int nr_none = 0, result = SCAN_SUCCEED; bool is_shmem = shmem_file(file); - int nr; + int nr = 0; VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem); VM_BUG_ON(start & (HPAGE_PMD_NR - 1)); @@ -2013,6 +2013,7 @@ xa_unlocked: if (result == SCAN_SUCCEED) { struct page *page, *tmp; + struct folio *folio; /* * Replacing old pages with new one has succeeded, now we @@ -2040,11 +2041,13 @@ xa_unlocked: index++; } - SetPageUptodate(hpage); - page_ref_add(hpage, HPAGE_PMD_NR - 1); + folio = page_folio(hpage); + folio_mark_uptodate(folio); + folio_ref_add(folio, HPAGE_PMD_NR - 1); + if (is_shmem) - set_page_dirty(hpage); - lru_cache_add(hpage); + folio_mark_dirty(folio); + folio_add_lru(folio); /* * Remove pte page tables, so we can re-fault the page as huge. @@ -2102,7 +2105,8 @@ out: mem_cgroup_uncharge(page_folio(hpage)); put_page(hpage); } - /* TODO: tracepoints */ + + trace_mm_khugepaged_collapse_file(mm, hpage, index, is_shmem, addr, file, nr, result); return result; } diff --git a/mm/kmsan/instrumentation.c b/mm/kmsan/instrumentation.c index 271f135f97a1..770fe02904f3 100644 --- a/mm/kmsan/instrumentation.c +++ b/mm/kmsan/instrumentation.c @@ -81,12 +81,16 @@ DECLARE_METADATA_PTR_GETTER(8); * Handle a memory store performed by inline assembly. KMSAN conservatively * attempts to unpoison the outputs of asm() directives to prevent false * positives caused by missed stores. + * + * __msan_instrument_asm_store() may be called for inline assembly code when + * entering or leaving IRQ. We omit the check for kmsan_in_runtime() to ensure + * the memory written to in these cases is also marked as initialized. */ void __msan_instrument_asm_store(void *addr, uintptr_t size) { unsigned long ua_flags; - if (!kmsan_enabled || kmsan_in_runtime()) + if (!kmsan_enabled) return; ua_flags = user_access_save(); @@ -103,10 +107,8 @@ void __msan_instrument_asm_store(void *addr, uintptr_t size) user_access_restore(ua_flags); return; } - kmsan_enter_runtime(); /* Unpoisoning the memory on best effort. */ kmsan_internal_unpoison_memory(addr, size, /*checked*/ false); - kmsan_leave_runtime(); user_access_restore(ua_flags); } EXPORT_SYMBOL(__msan_instrument_asm_store); @@ -39,6 +39,7 @@ #include <linux/freezer.h> #include <linux/oom.h> #include <linux/numa.h> +#include <linux/pagewalk.h> #include <asm/tlbflush.h> #include "internal.h" @@ -419,47 +420,74 @@ static inline bool ksm_test_exit(struct mm_struct *mm) return atomic_read(&mm->mm_users) == 0; } +static int break_ksm_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long next, + struct mm_walk *walk) +{ + struct page *page = NULL; + spinlock_t *ptl; + pte_t *pte; + int ret; + + if (pmd_leaf(*pmd) || !pmd_present(*pmd)) + return 0; + + pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + if (pte_present(*pte)) { + page = vm_normal_page(walk->vma, addr, *pte); + } else if (!pte_none(*pte)) { + swp_entry_t entry = pte_to_swp_entry(*pte); + + /* + * As KSM pages remain KSM pages until freed, no need to wait + * here for migration to end. + */ + if (is_migration_entry(entry)) + page = pfn_swap_entry_to_page(entry); + } + ret = page && PageKsm(page); + pte_unmap_unlock(pte, ptl); + return ret; +} + +static const struct mm_walk_ops break_ksm_ops = { + .pmd_entry = break_ksm_pmd_entry, +}; + /* - * We use break_ksm to break COW on a ksm page: it's a stripped down - * - * if (get_user_pages(addr, 1, FOLL_WRITE, &page, NULL) == 1) - * put_page(page); + * We use break_ksm to break COW on a ksm page by triggering unsharing, + * such that the ksm page will get replaced by an exclusive anonymous page. * - * but taking great care only to touch a ksm page, in a VM_MERGEABLE vma, + * We take great care only to touch a ksm page, in a VM_MERGEABLE vma, * in case the application has unmapped and remapped mm,addr meanwhile. * Could a ksm page appear anywhere else? Actually yes, in a VM_PFNMAP * mmap of /dev/mem, where we would not want to touch it. * - * FAULT_FLAG/FOLL_REMOTE are because we do this outside the context + * FAULT_FLAG_REMOTE/FOLL_REMOTE are because we do this outside the context * of the process that owns 'vma'. We also do not want to enforce * protection keys here anyway. */ static int break_ksm(struct vm_area_struct *vma, unsigned long addr) { - struct page *page; vm_fault_t ret = 0; do { + int ksm_page; + cond_resched(); - page = follow_page(vma, addr, - FOLL_GET | FOLL_MIGRATION | FOLL_REMOTE); - if (IS_ERR_OR_NULL(page)) - break; - if (PageKsm(page)) - ret = handle_mm_fault(vma, addr, - FAULT_FLAG_WRITE | FAULT_FLAG_REMOTE, - NULL); - else - ret = VM_FAULT_WRITE; - put_page(page); - } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM))); + ksm_page = walk_page_range_vma(vma, addr, addr + 1, + &break_ksm_ops, NULL); + if (WARN_ON_ONCE(ksm_page < 0)) + return ksm_page; + if (!ksm_page) + return 0; + ret = handle_mm_fault(vma, addr, + FAULT_FLAG_UNSHARE | FAULT_FLAG_REMOTE, + NULL); + } while (!(ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM))); /* - * We must loop because handle_mm_fault() may back out if there's - * any difficulty e.g. if pte accessed bit gets updated concurrently. - * - * VM_FAULT_WRITE is what we have been hoping for: it indicates that - * COW has been broken, even if the vma does not permit VM_WRITE; - * but note that a concurrent fault might break PageKsm for us. + * We must loop until we no longer find a KSM page because + * handle_mm_fault() may back out if there's any difficulty e.g. if + * pte accessed bit gets updated concurrently. * * VM_FAULT_SIGBUS could occur if we race with truncation of the * backing file, which also invalidates anonymous pages: that's diff --git a/mm/madvise.c b/mm/madvise.c index 71155fec5df6..90217646c0c0 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -40,6 +40,7 @@ struct madvise_walk_private { struct mmu_gather *tlb; bool pageout; + bool can_pageout_file; }; /* @@ -325,6 +326,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, struct madvise_walk_private *private = walk->private; struct mmu_gather *tlb = private->tlb; bool pageout = private->pageout; + bool pageout_anon_only = pageout && !private->can_pageout_file; struct mm_struct *mm = tlb->mm; struct vm_area_struct *vma = walk->vma; pte_t *orig_pte, *pte, ptent; @@ -361,6 +363,9 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, if (page_mapcount(page) != 1) goto huge_unlock; + if (pageout_anon_only && !PageAnon(page)) + goto huge_unlock; + if (next - addr != HPAGE_PMD_SIZE) { int err; @@ -429,6 +434,8 @@ regular_page: if (PageTransCompound(page)) { if (page_mapcount(page) != 1) break; + if (pageout_anon_only && !PageAnon(page)) + break; get_page(page); if (!trylock_page(page)) { put_page(page); @@ -456,6 +463,9 @@ regular_page: if (!PageLRU(page) || page_mapcount(page) != 1) continue; + if (pageout_anon_only && !PageAnon(page)) + continue; + VM_BUG_ON_PAGE(PageTransCompound(page), page); if (pte_young(ptent)) { @@ -538,11 +548,13 @@ static long madvise_cold(struct vm_area_struct *vma, static void madvise_pageout_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, - unsigned long addr, unsigned long end) + unsigned long addr, unsigned long end, + bool can_pageout_file) { struct madvise_walk_private walk_private = { .pageout = true, .tlb = tlb, + .can_pageout_file = can_pageout_file, }; tlb_start_vma(tlb, vma); @@ -550,10 +562,8 @@ static void madvise_pageout_page_range(struct mmu_gather *tlb, tlb_end_vma(tlb, vma); } -static inline bool can_do_pageout(struct vm_area_struct *vma) +static inline bool can_do_file_pageout(struct vm_area_struct *vma) { - if (vma_is_anonymous(vma)) - return true; if (!vma->vm_file) return false; /* @@ -573,17 +583,23 @@ static long madvise_pageout(struct vm_area_struct *vma, { struct mm_struct *mm = vma->vm_mm; struct mmu_gather tlb; + bool can_pageout_file; *prev = vma; if (!can_madv_lru_vma(vma)) return -EINVAL; - if (!can_do_pageout(vma)) - return 0; + /* + * If the VMA belongs to a private file mapping, there can be private + * dirty pages which can be paged out if even this process is neither + * owner nor write capable of the file. Cache the file access check + * here and use it later during page walk. + */ + can_pageout_file = can_do_file_pageout(vma); lru_add_drain(); tlb_gather_mmu(&tlb, mm); - madvise_pageout_page_range(&tlb, vma, start_addr, end_addr); + madvise_pageout_page_range(&tlb, vma, start_addr, end_addr, can_pageout_file); tlb_finish_mmu(&tlb); return 0; diff --git a/mm/memory.c b/mm/memory.c index 815d2ff05c62..aad226daf41b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3213,7 +3213,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) } delayacct_wpcopy_end(); - return (page_copied && !unshare) ? VM_FAULT_WRITE : 0; + return 0; oom_free_new: put_page(new_page); oom: @@ -3277,14 +3277,14 @@ static vm_fault_t wp_pfn_shared(struct vm_fault *vmf) return finish_mkwrite_fault(vmf); } wp_page_reuse(vmf); - return VM_FAULT_WRITE; + return 0; } static vm_fault_t wp_page_shared(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; - vm_fault_t ret = VM_FAULT_WRITE; + vm_fault_t ret = 0; get_page(vmf->page); @@ -3430,7 +3430,7 @@ reuse: return 0; } wp_page_reuse(vmf); - return VM_FAULT_WRITE; + return 0; } copy: /* @@ -3944,7 +3944,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (vmf->flags & FAULT_FLAG_WRITE) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); vmf->flags &= ~FAULT_FLAG_WRITE; - ret |= VM_FAULT_WRITE; } rmap_flags |= RMAP_EXCLUSIVE; } diff --git a/mm/migrate.c b/mm/migrate.c index e50b3c42e6ad..36be77470cc8 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -223,7 +223,14 @@ static bool remove_migration_pte(struct folio *folio, if (is_writable_migration_entry(entry)) pte = maybe_mkwrite(pte, vma); else - /* NOTE: mk_pte can have write bit set */ + /* + * NOTE: mk_pte() can have write bit set per memory + * type (e.g. shmem), or pte_mkdirty() per archs + * (e.g., sparc64). If this is a read migration + * entry, we need to make sure when we recover the + * pte from migration entry to present entry the + * write bit is cleared. + */ pte = pte_wrprotect(pte); if (pte_swp_uffd_wp(*pvmw.pte)) { @@ -335,24 +342,41 @@ void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, } #ifdef CONFIG_HUGETLB_PAGE -void __migration_entry_wait_huge(pte_t *ptep, spinlock_t *ptl) +void __migration_entry_wait_huge(struct vm_area_struct *vma, + pte_t *ptep, spinlock_t *ptl) { pte_t pte; + /* + * The vma read lock must be taken, which will be released before + * the function returns. It makes sure the pgtable page (along + * with its spin lock) not be freed in parallel. + */ + hugetlb_vma_assert_locked(vma); + spin_lock(ptl); pte = huge_ptep_get(ptep); - if (unlikely(!is_hugetlb_entry_migration(pte))) + if (unlikely(!is_hugetlb_entry_migration(pte))) { spin_unlock(ptl); - else + hugetlb_vma_unlock_read(vma); + } else { + /* + * If migration entry existed, safe to release vma lock + * here because the pgtable page won't be freed without the + * pgtable lock released. See comment right above pgtable + * lock release in migration_entry_wait_on_locked(). + */ + hugetlb_vma_unlock_read(vma); migration_entry_wait_on_locked(pte_to_swp_entry(pte), NULL, ptl); + } } void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte) { spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), vma->vm_mm, pte); - __migration_entry_wait_huge(pte, ptl); + __migration_entry_wait_huge(vma, pte, ptl); } #endif diff --git a/mm/mmap.c b/mm/mmap.c index 872059752f66..3158f37bbfd8 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1779,9 +1779,6 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, */ pgoff = 0; get_area = shmem_get_unmapped_area; - } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { - /* Ensures that larger anonymous mappings are THP aligned. */ - get_area = thp_get_unmapped_area; } addr = get_area(file, addr, len, pgoff, flags); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5ab9dd29ef7e..0745aedebb37 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1702,6 +1702,11 @@ static void __free_pages_ok(struct page *page, unsigned int order, if (!free_pages_prepare(page, order, true, fpi_flags)) return; + /* + * Calling get_pfnblock_migratetype() without spin_lock_irqsave() here + * is used to avoid calling get_pfnblock_migratetype() under the lock. + * This will reduce the lock holding time. + */ migratetype = get_pfnblock_migratetype(page, pfn); spin_lock_irqsave(&zone->lock, flags); diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 93e13fc17d3c..bb782dea4b42 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -169,10 +169,13 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) if (pvmw->pte) return not_found(pvmw); + hugetlb_vma_lock_read(vma); /* when pud is not present, pte will be NULL */ - pvmw->pte = huge_pte_offset(mm, pvmw->address, size); - if (!pvmw->pte) + pvmw->pte = hugetlb_walk(vma, pvmw->address, size); + if (!pvmw->pte) { + hugetlb_vma_unlock_read(vma); return false; + } pvmw->ptl = huge_pte_lock(hstate, mm, pvmw->pte); if (!check_pte(pvmw)) diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 2ff3a5bebceb..cb23f8a15c13 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -302,18 +302,18 @@ static int walk_hugetlb_range(unsigned long addr, unsigned long end, const struct mm_walk_ops *ops = walk->ops; int err = 0; + hugetlb_vma_lock_read(vma); do { next = hugetlb_entry_end(h, addr, end); - pte = huge_pte_offset(walk->mm, addr & hmask, sz); - + pte = hugetlb_walk(vma, addr & hmask, sz); if (pte) err = ops->hugetlb_entry(pte, hmask, addr, next, walk); else if (ops->pte_hole) err = ops->pte_hole(addr, next, -1, walk); - if (err) break; } while (addr = next, addr != end); + hugetlb_vma_unlock_read(vma); return err; } @@ -517,6 +517,26 @@ int walk_page_range_novma(struct mm_struct *mm, unsigned long start, return walk_pgd_range(start, end, &walk); } +int walk_page_range_vma(struct vm_area_struct *vma, unsigned long start, + unsigned long end, const struct mm_walk_ops *ops, + void *private) +{ + struct mm_walk walk = { + .ops = ops, + .mm = vma->vm_mm, + .vma = vma, + .private = private, + }; + + if (start >= end || !walk.mm) + return -EINVAL; + if (start < vma->vm_start || end > vma->vm_end) + return -EINVAL; + + mmap_assert_locked(walk.mm); + return __walk_page_range(start, end, &walk); +} + int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, void *private) { @@ -526,18 +546,11 @@ int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops, .vma = vma, .private = private, }; - int err; if (!walk.mm) return -EINVAL; mmap_assert_locked(walk.mm); - - err = walk_page_test(vma->vm_start, vma->vm_end, &walk); - if (err > 0) - return 0; - if (err < 0) - return err; return __walk_page_range(vma->vm_start, vma->vm_end, &walk); } diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 46ae542118c0..c5398a5960d0 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -196,6 +196,10 @@ pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node) return pmd; } +void __weak __meminit pmd_init(void *addr) +{ +} + pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node) { pud_t *pud = pud_offset(p4d, addr); @@ -203,11 +207,16 @@ pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node) void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node); if (!p) return NULL; + pmd_init(p); pud_populate(&init_mm, pud, p); } return pud; } +void __weak __meminit pud_init(void *addr) +{ +} + p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node) { p4d_t *p4d = p4d_offset(pgd, addr); @@ -215,6 +224,7 @@ p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node) void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node); if (!p) return NULL; + pud_init(p); p4d_populate(&init_mm, p4d, p); } return p4d; @@ -285,6 +295,69 @@ int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end, return vmemmap_populate_range(start, end, node, altmap, NULL); } +void __weak __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node, + unsigned long addr, unsigned long next) +{ +} + +int __weak __meminit vmemmap_check_pmd(pmd_t *pmd, int node, + unsigned long addr, unsigned long next) +{ + return 0; +} + +int __meminit vmemmap_populate_hugepages(unsigned long start, unsigned long end, + int node, struct vmem_altmap *altmap) +{ + unsigned long addr; + unsigned long next; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + for (addr = start; addr < end; addr = next) { + next = pmd_addr_end(addr, end); + + pgd = vmemmap_pgd_populate(addr, node); + if (!pgd) + return -ENOMEM; + + p4d = vmemmap_p4d_populate(pgd, addr, node); + if (!p4d) + return -ENOMEM; + + pud = vmemmap_pud_populate(p4d, addr, node); + if (!pud) + return -ENOMEM; + + pmd = pmd_offset(pud, addr); + if (pmd_none(READ_ONCE(*pmd))) { + void *p; + + p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap); + if (p) { + vmemmap_set_pmd(pmd, p, node, addr, next); + continue; + } else if (altmap) { + /* + * No fallback: In any case we care about, the + * altmap should be reasonably sized and aligned + * such that vmemmap_alloc_block_buf() will always + * succeed. For consistency with the PTE case, + * return an error here as failure could indicate + * a configuration issue with the size of the altmap. + */ + return -ENOMEM; + } + } else if (vmemmap_check_pmd(pmd, node, addr, next)) + continue; + if (vmemmap_populate_basepages(addr, next, node, altmap)) + return -ENOMEM; + } + return 0; +} + /* * For compound pages bigger than section size (e.g. x86 1G compound * pages with 2M subsection size) fill the rest of sections as tail diff --git a/mm/truncate.c b/mm/truncate.c index c7bfd247a651..7b4ea4c4a46b 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -565,7 +565,7 @@ EXPORT_SYMBOL(invalidate_mapping_pages); * refcount. We do this because invalidate_inode_pages2() needs stronger * invalidation guarantees, and cannot afford to leave pages behind because * shrink_page_list() has a temp ref on them, or because they're transiently - * sitting in the lru_cache_add() pagevecs. + * sitting in the folio_add_lru() pagevecs. */ static int invalidate_complete_folio2(struct address_space *mapping, struct folio *folio) diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 3a8ff47943d5..0499907b6f1a 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -66,6 +66,7 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, bool vm_shared = dst_vma->vm_flags & VM_SHARED; bool page_in_cache = page_mapping(page); spinlock_t *ptl; + struct folio *folio; struct inode *inode; pgoff_t offset, max_off; @@ -113,14 +114,15 @@ int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, if (!pte_none_mostly(*dst_pte)) goto out_unlock; + folio = page_folio(page); if (page_in_cache) { /* Usually, cache pages are already added to LRU */ if (newly_allocated) - lru_cache_add(page); + folio_add_lru(folio); page_add_file_rmap(page, dst_vma, false); } else { page_add_new_anon_rmap(page, dst_vma, dst_addr); - lru_cache_add_inactive_or_unevictable(page, dst_vma); + folio_add_lru_vma(folio, dst_vma); } /* diff --git a/mm/workingset.c b/mm/workingset.c index d2d02978588c..1a86645b7b3c 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -492,7 +492,10 @@ void workingset_refault(struct folio *folio, void *shadow) /* Folio was active prior to eviction */ if (workingset) { folio_set_workingset(folio); - /* XXX: Move to lru_cache_add() when it supports new vs putback */ + /* + * XXX: Move to folio_add_lru() when it supports new vs + * putback + */ lru_note_cost_refault(folio); mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file, nr); } diff --git a/mm/z3fold.c b/mm/z3fold.c index cf71da10d04e..a4de0c317ac7 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -68,9 +68,6 @@ * Structures *****************/ struct z3fold_pool; -struct z3fold_ops { - int (*evict)(struct z3fold_pool *pool, unsigned long handle); -}; enum buddy { HEADLESS = 0, @@ -138,8 +135,6 @@ struct z3fold_header { * @stale: list of pages marked for freeing * @pages_nr: number of z3fold pages in the pool. * @c_handle: cache for z3fold_buddy_slots allocation - * @ops: pointer to a structure of user defined operations specified at - * pool creation time. * @zpool: zpool driver * @zpool_ops: zpool operations structure with an evict callback * @compact_wq: workqueue for page layout background optimization @@ -158,7 +153,6 @@ struct z3fold_pool { struct list_head stale; atomic64_t pages_nr; struct kmem_cache *c_handle; - const struct z3fold_ops *ops; struct zpool *zpool; const struct zpool_ops *zpool_ops; struct workqueue_struct *compact_wq; @@ -907,13 +901,11 @@ out_fail: * z3fold_create_pool() - create a new z3fold pool * @name: pool name * @gfp: gfp flags when allocating the z3fold pool structure - * @ops: user-defined operations for the z3fold pool * * Return: pointer to the new z3fold pool or NULL if the metadata allocation * failed. */ -static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp, - const struct z3fold_ops *ops) +static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp) { struct z3fold_pool *pool = NULL; int i, cpu; @@ -949,7 +941,6 @@ static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp, if (!pool->release_wq) goto out_wq; INIT_WORK(&pool->work, free_pages_work); - pool->ops = ops; return pool; out_wq: @@ -1230,10 +1221,6 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) slots.pool = (unsigned long)pool | (1 << HANDLES_NOFREE); spin_lock(&pool->lock); - if (!pool->ops || !pool->ops->evict || retries == 0) { - spin_unlock(&pool->lock); - return -EINVAL; - } for (i = 0; i < retries; i++) { if (list_empty(&pool->lru)) { spin_unlock(&pool->lock); @@ -1319,17 +1306,17 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) } /* Issue the eviction callback(s) */ if (middle_handle) { - ret = pool->ops->evict(pool, middle_handle); + ret = pool->zpool_ops->evict(pool->zpool, middle_handle); if (ret) goto next; } if (first_handle) { - ret = pool->ops->evict(pool, first_handle); + ret = pool->zpool_ops->evict(pool->zpool, first_handle); if (ret) goto next; } if (last_handle) { - ret = pool->ops->evict(pool, last_handle); + ret = pool->zpool_ops->evict(pool->zpool, last_handle); if (ret) goto next; } @@ -1593,26 +1580,13 @@ static const struct movable_operations z3fold_mops = { * zpool ****************/ -static int z3fold_zpool_evict(struct z3fold_pool *pool, unsigned long handle) -{ - if (pool->zpool && pool->zpool_ops && pool->zpool_ops->evict) - return pool->zpool_ops->evict(pool->zpool, handle); - else - return -ENOENT; -} - -static const struct z3fold_ops z3fold_zpool_ops = { - .evict = z3fold_zpool_evict -}; - static void *z3fold_zpool_create(const char *name, gfp_t gfp, const struct zpool_ops *zpool_ops, struct zpool *zpool) { struct z3fold_pool *pool; - pool = z3fold_create_pool(name, gfp, - zpool_ops ? &z3fold_zpool_ops : NULL); + pool = z3fold_create_pool(name, gfp); if (pool) { pool->zpool = zpool; pool->zpool_ops = zpool_ops; diff --git a/mm/zbud.c b/mm/zbud.c index 6348932430b8..3acd26193920 100644 --- a/mm/zbud.c +++ b/mm/zbud.c @@ -74,10 +74,6 @@ struct zbud_pool; -struct zbud_ops { - int (*evict)(struct zbud_pool *pool, unsigned long handle); -}; - /** * struct zbud_pool - stores metadata for each zbud pool * @lock: protects all pool fields and first|last_chunk fields of any @@ -90,8 +86,6 @@ struct zbud_ops { * @lru: list tracking the zbud pages in LRU order by most recently * added buddy. * @pages_nr: number of zbud pages in the pool. - * @ops: pointer to a structure of user defined operations specified at - * pool creation time. * @zpool: zpool driver * @zpool_ops: zpool operations structure with an evict callback * @@ -110,7 +104,6 @@ struct zbud_pool { }; struct list_head lru; u64 pages_nr; - const struct zbud_ops *ops; struct zpool *zpool; const struct zpool_ops *zpool_ops; }; @@ -212,12 +205,11 @@ static int num_free_chunks(struct zbud_header *zhdr) /** * zbud_create_pool() - create a new zbud pool * @gfp: gfp flags when allocating the zbud pool structure - * @ops: user-defined operations for the zbud pool * * Return: pointer to the new zbud pool or NULL if the metadata allocation * failed. */ -static struct zbud_pool *zbud_create_pool(gfp_t gfp, const struct zbud_ops *ops) +static struct zbud_pool *zbud_create_pool(gfp_t gfp) { struct zbud_pool *pool; int i; @@ -231,7 +223,6 @@ static struct zbud_pool *zbud_create_pool(gfp_t gfp, const struct zbud_ops *ops) INIT_LIST_HEAD(&pool->buddied); INIT_LIST_HEAD(&pool->lru); pool->pages_nr = 0; - pool->ops = ops; return pool; } @@ -419,8 +410,7 @@ static int zbud_reclaim_page(struct zbud_pool *pool, unsigned int retries) unsigned long first_handle = 0, last_handle = 0; spin_lock(&pool->lock); - if (!pool->ops || !pool->ops->evict || list_empty(&pool->lru) || - retries == 0) { + if (list_empty(&pool->lru)) { spin_unlock(&pool->lock); return -EINVAL; } @@ -444,12 +434,12 @@ static int zbud_reclaim_page(struct zbud_pool *pool, unsigned int retries) /* Issue the eviction callback(s) */ if (first_handle) { - ret = pool->ops->evict(pool, first_handle); + ret = pool->zpool_ops->evict(pool->zpool, first_handle); if (ret) goto next; } if (last_handle) { - ret = pool->ops->evict(pool, last_handle); + ret = pool->zpool_ops->evict(pool->zpool, last_handle); if (ret) goto next; } @@ -524,25 +514,13 @@ static u64 zbud_get_pool_size(struct zbud_pool *pool) * zpool ****************/ -static int zbud_zpool_evict(struct zbud_pool *pool, unsigned long handle) -{ - if (pool->zpool && pool->zpool_ops && pool->zpool_ops->evict) - return pool->zpool_ops->evict(pool->zpool, handle); - else - return -ENOENT; -} - -static const struct zbud_ops zbud_zpool_ops = { - .evict = zbud_zpool_evict -}; - static void *zbud_zpool_create(const char *name, gfp_t gfp, const struct zpool_ops *zpool_ops, struct zpool *zpool) { struct zbud_pool *pool; - pool = zbud_create_pool(gfp, zpool_ops ? &zbud_zpool_ops : NULL); + pool = zbud_create_pool(gfp); if (pool) { pool->zpool = zpool; pool->zpool_ops = zpool_ops; diff --git a/mm/zpool.c b/mm/zpool.c index f46c0d5e766c..571f5c5031dd 100644 --- a/mm/zpool.c +++ b/mm/zpool.c @@ -21,9 +21,6 @@ struct zpool { struct zpool_driver *driver; void *pool; - const struct zpool_ops *ops; - bool evictable; - bool can_sleep_mapped; }; static LIST_HEAD(drivers_head); @@ -177,9 +174,6 @@ struct zpool *zpool_create_pool(const char *type, const char *name, gfp_t gfp, zpool->driver = driver; zpool->pool = driver->create(name, gfp, ops, zpool); - zpool->ops = ops; - zpool->evictable = driver->shrink && ops && ops->evict; - zpool->can_sleep_mapped = driver->sleep_mapped; if (!zpool->pool) { pr_err("couldn't create %s pool\n", type); @@ -380,7 +374,7 @@ u64 zpool_get_total_size(struct zpool *zpool) */ bool zpool_evictable(struct zpool *zpool) { - return zpool->evictable; + return zpool->driver->shrink; } /** @@ -398,7 +392,7 @@ bool zpool_evictable(struct zpool *zpool) */ bool zpool_can_sleep_mapped(struct zpool *zpool) { - return zpool->can_sleep_mapped; + return zpool->driver->sleep_mapped; } MODULE_LICENSE("GPL"); diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 78feda34ad9a..9445bee6b014 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -33,8 +33,7 @@ /* * lock ordering: * page_lock - * pool->migrate_lock - * class->lock + * pool->lock * zspage->lock */ @@ -192,7 +191,6 @@ static const int fullness_threshold_frac = 4; static size_t huge_class_size; struct size_class { - spinlock_t lock; struct list_head fullness_list[NR_ZS_FULLNESS]; /* * Size of objects stored in this class. Must be multiple @@ -241,14 +239,20 @@ struct zs_pool { /* Compact classes */ struct shrinker shrinker; +#ifdef CONFIG_ZPOOL + /* List tracking the zspages in LRU order by most recently added object */ + struct list_head lru; + struct zpool *zpool; + const struct zpool_ops *zpool_ops; +#endif + #ifdef CONFIG_ZSMALLOC_STAT struct dentry *stat_dentry; #endif #ifdef CONFIG_COMPACTION struct work_struct free_work; #endif - /* protect page/zspage migration */ - rwlock_t migrate_lock; + spinlock_t lock; }; struct zspage { @@ -263,10 +267,17 @@ struct zspage { unsigned int freeobj; struct page *first_page; struct list_head list; /* fullness list */ + +#ifdef CONFIG_ZPOOL + /* links the zspage to the lru list in the pool */ + struct list_head lru; + bool under_reclaim; + /* list of unfreed handles whose objects have been reclaimed */ + unsigned long *deferred_handles; +#endif + struct zs_pool *pool; -#ifdef CONFIG_COMPACTION rwlock_t lock; -#endif }; struct mapping_area { @@ -287,10 +298,11 @@ static bool ZsHugePage(struct zspage *zspage) return zspage->huge; } -#ifdef CONFIG_COMPACTION static void migrate_lock_init(struct zspage *zspage); static void migrate_read_lock(struct zspage *zspage); static void migrate_read_unlock(struct zspage *zspage); + +#ifdef CONFIG_COMPACTION static void migrate_write_lock(struct zspage *zspage); static void migrate_write_lock_nested(struct zspage *zspage); static void migrate_write_unlock(struct zspage *zspage); @@ -298,9 +310,6 @@ static void kick_deferred_free(struct zs_pool *pool); static void init_deferred_free(struct zs_pool *pool); static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage); #else -static void migrate_lock_init(struct zspage *zspage) {} -static void migrate_read_lock(struct zspage *zspage) {} -static void migrate_read_unlock(struct zspage *zspage) {} static void migrate_write_lock(struct zspage *zspage) {} static void migrate_write_lock_nested(struct zspage *zspage) {} static void migrate_write_unlock(struct zspage *zspage) {} @@ -355,7 +364,7 @@ static void cache_free_zspage(struct zs_pool *pool, struct zspage *zspage) kmem_cache_free(pool->zspage_cachep, zspage); } -/* class->lock(which owns the handle) synchronizes races */ +/* pool->lock(which owns the handle) synchronizes races */ static void record_obj(unsigned long handle, unsigned long obj) { *(unsigned long *)handle = obj; @@ -374,7 +383,14 @@ static void *zs_zpool_create(const char *name, gfp_t gfp, * different contexts and its caller must provide a valid * gfp mask. */ - return zs_create_pool(name); + struct zs_pool *pool = zs_create_pool(name); + + if (pool) { + pool->zpool = zpool; + pool->zpool_ops = zpool_ops; + } + + return pool; } static void zs_zpool_destroy(void *pool) @@ -396,6 +412,27 @@ static void zs_zpool_free(void *pool, unsigned long handle) zs_free(pool, handle); } +static int zs_reclaim_page(struct zs_pool *pool, unsigned int retries); + +static int zs_zpool_shrink(void *pool, unsigned int pages, + unsigned int *reclaimed) +{ + unsigned int total = 0; + int ret = -EINVAL; + + while (total < pages) { + ret = zs_reclaim_page(pool, 8); + if (ret < 0) + break; + total++; + } + + if (reclaimed) + *reclaimed = total; + + return ret; +} + static void *zs_zpool_map(void *pool, unsigned long handle, enum zpool_mapmode mm) { @@ -434,6 +471,7 @@ static struct zpool_driver zs_zpool_driver = { .malloc_support_movable = true, .malloc = zs_zpool_malloc, .free = zs_zpool_free, + .shrink = zs_zpool_shrink, .map = zs_zpool_map, .unmap = zs_zpool_unmap, .total_size = zs_zpool_total_size, @@ -452,7 +490,7 @@ static __maybe_unused int is_first_page(struct page *page) return PagePrivate(page); } -/* Protected by class->lock */ +/* Protected by pool->lock */ static inline int get_zspage_inuse(struct zspage *zspage) { return zspage->inuse; @@ -597,13 +635,13 @@ static int zs_stats_size_show(struct seq_file *s, void *v) if (class->index != i) continue; - spin_lock(&class->lock); + spin_lock(&pool->lock); class_almost_full = zs_stat_get(class, CLASS_ALMOST_FULL); class_almost_empty = zs_stat_get(class, CLASS_ALMOST_EMPTY); obj_allocated = zs_stat_get(class, OBJ_ALLOCATED); obj_used = zs_stat_get(class, OBJ_USED); freeable = zs_can_compact(class); - spin_unlock(&class->lock); + spin_unlock(&pool->lock); objs_per_zspage = class->objs_per_zspage; pages_used = obj_allocated / objs_per_zspage * @@ -907,6 +945,25 @@ unlock: return 0; } +#ifdef CONFIG_ZPOOL +/* + * Free all the deferred handles whose objects are freed in zs_free. + */ +static void free_handles(struct zs_pool *pool, struct zspage *zspage) +{ + unsigned long handle = (unsigned long)zspage->deferred_handles; + + while (handle) { + unsigned long nxt_handle = handle_to_obj(handle); + + cache_free_handle(pool, handle); + handle = nxt_handle; + } +} +#else +static inline void free_handles(struct zs_pool *pool, struct zspage *zspage) {} +#endif + static void __free_zspage(struct zs_pool *pool, struct size_class *class, struct zspage *zspage) { @@ -916,11 +973,14 @@ static void __free_zspage(struct zs_pool *pool, struct size_class *class, get_zspage_mapping(zspage, &class_idx, &fg); - assert_spin_locked(&class->lock); + assert_spin_locked(&pool->lock); VM_BUG_ON(get_zspage_inuse(zspage)); VM_BUG_ON(fg != ZS_EMPTY); + /* Free all deferred handles from zs_free */ + free_handles(pool, zspage); + next = page = get_first_page(zspage); do { VM_BUG_ON_PAGE(!PageLocked(page), page); @@ -956,6 +1016,9 @@ static void free_zspage(struct zs_pool *pool, struct size_class *class, } remove_zspage(class, zspage, ZS_EMPTY); +#ifdef CONFIG_ZPOOL + list_del(&zspage->lru); +#endif __free_zspage(pool, class, zspage); } @@ -1001,6 +1064,12 @@ static void init_zspage(struct size_class *class, struct zspage *zspage) off %= PAGE_SIZE; } +#ifdef CONFIG_ZPOOL + INIT_LIST_HEAD(&zspage->lru); + zspage->under_reclaim = false; + zspage->deferred_handles = NULL; +#endif + set_freeobj(zspage, 0); } @@ -1268,19 +1337,44 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle, BUG_ON(in_interrupt()); /* It guarantees it can get zspage from handle safely */ - read_lock(&pool->migrate_lock); + spin_lock(&pool->lock); obj = handle_to_obj(handle); obj_to_location(obj, &page, &obj_idx); zspage = get_zspage(page); +#ifdef CONFIG_ZPOOL + /* + * Move the zspage to front of pool's LRU. + * + * Note that this is swap-specific, so by definition there are no ongoing + * accesses to the memory while the page is swapped out that would make + * it "hot". A new entry is hot, then ages to the tail until it gets either + * written back or swaps back in. + * + * Furthermore, map is also called during writeback. We must not put an + * isolated page on the LRU mid-reclaim. + * + * As a result, only update the LRU when the page is mapped for write + * when it's first instantiated. + * + * This is a deviation from the other backends, which perform this update + * in the allocation function (zbud_alloc, z3fold_alloc). + */ + if (mm == ZS_MM_WO) { + if (!list_empty(&zspage->lru)) + list_del(&zspage->lru); + list_add(&zspage->lru, &pool->lru); + } +#endif + /* - * migration cannot move any zpages in this zspage. Here, class->lock + * migration cannot move any zpages in this zspage. Here, pool->lock * is too heavy since callers would take some time until they calls * zs_unmap_object API so delegate the locking from class to zspage * which is smaller granularity. */ migrate_read_lock(zspage); - read_unlock(&pool->migrate_lock); + spin_unlock(&pool->lock); class = zspage_class(pool, zspage); off = (class->size * obj_idx) & ~PAGE_MASK; @@ -1433,8 +1527,8 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) size += ZS_HANDLE_SIZE; class = pool->size_class[get_size_class_index(size)]; - /* class->lock effectively protects the zpage migration */ - spin_lock(&class->lock); + /* pool->lock effectively protects the zpage migration */ + spin_lock(&pool->lock); zspage = find_get_zspage(class); if (likely(zspage)) { obj = obj_malloc(pool, zspage, handle); @@ -1442,12 +1536,12 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) fix_fullness_group(class, zspage); record_obj(handle, obj); class_stat_inc(class, OBJ_USED, 1); - spin_unlock(&class->lock); + spin_unlock(&pool->lock); return handle; } - spin_unlock(&class->lock); + spin_unlock(&pool->lock); zspage = alloc_zspage(pool, class, gfp); if (!zspage) { @@ -1455,7 +1549,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) return (unsigned long)ERR_PTR(-ENOMEM); } - spin_lock(&class->lock); + spin_lock(&pool->lock); obj = obj_malloc(pool, zspage, handle); newfg = get_fullness_group(class, zspage); insert_zspage(class, zspage, newfg); @@ -1468,7 +1562,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) /* We completely set up zspage so mark them as movable */ SetZsPageMovable(pool, zspage); - spin_unlock(&class->lock); + spin_unlock(&pool->lock); return handle; } @@ -1512,26 +1606,38 @@ void zs_free(struct zs_pool *pool, unsigned long handle) return; /* - * The pool->migrate_lock protects the race with zpage's migration + * The pool->lock protects the race with zpage's migration * so it's safe to get the page from handle. */ - read_lock(&pool->migrate_lock); + spin_lock(&pool->lock); obj = handle_to_obj(handle); obj_to_page(obj, &f_page); zspage = get_zspage(f_page); class = zspage_class(pool, zspage); - spin_lock(&class->lock); - read_unlock(&pool->migrate_lock); obj_free(class->size, obj); class_stat_dec(class, OBJ_USED, 1); + +#ifdef CONFIG_ZPOOL + if (zspage->under_reclaim) { + /* + * Reclaim needs the handles during writeback. It'll free + * them along with the zspage when it's done with them. + * + * Record current deferred handle at the memory location + * whose address is given by handle. + */ + record_obj(handle, (unsigned long)zspage->deferred_handles); + zspage->deferred_handles = (unsigned long *)handle; + spin_unlock(&pool->lock); + return; + } +#endif fullness = fix_fullness_group(class, zspage); - if (fullness != ZS_EMPTY) - goto out; + if (fullness == ZS_EMPTY) + free_zspage(pool, class, zspage); - free_zspage(pool, class, zspage); -out: - spin_unlock(&class->lock); + spin_unlock(&pool->lock); cache_free_handle(pool, handle); } EXPORT_SYMBOL_GPL(zs_free); @@ -1730,7 +1836,7 @@ static enum fullness_group putback_zspage(struct size_class *class, return fullness; } -#ifdef CONFIG_COMPACTION +#if defined(CONFIG_ZPOOL) || defined(CONFIG_COMPACTION) /* * To prevent zspage destroy during migration, zspage freeing should * hold locks of all pages in the zspage. @@ -1772,6 +1878,24 @@ static void lock_zspage(struct zspage *zspage) } migrate_read_unlock(zspage); } +#endif /* defined(CONFIG_ZPOOL) || defined(CONFIG_COMPACTION) */ + +#ifdef CONFIG_ZPOOL +/* + * Unlocks all the pages of the zspage. + * + * pool->lock must be held before this function is called + * to prevent the underlying pages from migrating. + */ +static void unlock_zspage(struct zspage *zspage) +{ + struct page *page = get_first_page(zspage); + + do { + unlock_page(page); + } while ((page = get_next_page(page)) != NULL); +} +#endif /* CONFIG_ZPOOL */ static void migrate_lock_init(struct zspage *zspage) { @@ -1788,6 +1912,7 @@ static void migrate_read_unlock(struct zspage *zspage) __releases(&zspage->lock) read_unlock(&zspage->lock); } +#ifdef CONFIG_COMPACTION static void migrate_write_lock(struct zspage *zspage) { write_lock(&zspage->lock); @@ -1888,16 +2013,12 @@ static int zs_page_migrate(struct page *newpage, struct page *page, pool = zspage->pool; /* - * The pool migrate_lock protects the race between zpage migration + * The pool's lock protects the race between zpage migration * and zs_free. */ - write_lock(&pool->migrate_lock); + spin_lock(&pool->lock); class = zspage_class(pool, zspage); - /* - * the class lock protects zpage alloc/free in the zspage. - */ - spin_lock(&class->lock); /* the migrate_write_lock protects zpage access via zs_map_object */ migrate_write_lock(zspage); @@ -1927,10 +2048,9 @@ static int zs_page_migrate(struct page *newpage, struct page *page, replace_sub_page(class, zspage, newpage, page); /* * Since we complete the data copy and set up new zspage structure, - * it's okay to release migration_lock. + * it's okay to release the pool's lock. */ - write_unlock(&pool->migrate_lock); - spin_unlock(&class->lock); + spin_unlock(&pool->lock); dec_zspage_isolation(zspage); migrate_write_unlock(zspage); @@ -1985,9 +2105,9 @@ static void async_free_zspage(struct work_struct *work) if (class->index != i) continue; - spin_lock(&class->lock); + spin_lock(&pool->lock); list_splice_init(&class->fullness_list[ZS_EMPTY], &free_pages); - spin_unlock(&class->lock); + spin_unlock(&pool->lock); } list_for_each_entry_safe(zspage, tmp, &free_pages, list) { @@ -1997,9 +2117,12 @@ static void async_free_zspage(struct work_struct *work) get_zspage_mapping(zspage, &class_idx, &fullness); VM_BUG_ON(fullness != ZS_EMPTY); class = pool->size_class[class_idx]; - spin_lock(&class->lock); + spin_lock(&pool->lock); +#ifdef CONFIG_ZPOOL + list_del(&zspage->lru); +#endif __free_zspage(pool, class, zspage); - spin_unlock(&class->lock); + spin_unlock(&pool->lock); } }; @@ -2060,10 +2183,11 @@ static unsigned long __zs_compact(struct zs_pool *pool, struct zspage *dst_zspage = NULL; unsigned long pages_freed = 0; - /* protect the race between zpage migration and zs_free */ - write_lock(&pool->migrate_lock); - /* protect zpage allocation/free */ - spin_lock(&class->lock); + /* + * protect the race between zpage migration and zs_free + * as well as zpage allocation/free + */ + spin_lock(&pool->lock); while ((src_zspage = isolate_zspage(class, true))) { /* protect someone accessing the zspage(i.e., zs_map_object) */ migrate_write_lock(src_zspage); @@ -2088,7 +2212,7 @@ static unsigned long __zs_compact(struct zs_pool *pool, putback_zspage(class, dst_zspage); migrate_write_unlock(dst_zspage); dst_zspage = NULL; - if (rwlock_is_contended(&pool->migrate_lock)) + if (spin_is_contended(&pool->lock)) break; } @@ -2105,11 +2229,9 @@ static unsigned long __zs_compact(struct zs_pool *pool, pages_freed += class->pages_per_zspage; } else migrate_write_unlock(src_zspage); - spin_unlock(&class->lock); - write_unlock(&pool->migrate_lock); + spin_unlock(&pool->lock); cond_resched(); - write_lock(&pool->migrate_lock); - spin_lock(&class->lock); + spin_lock(&pool->lock); } if (src_zspage) { @@ -2117,8 +2239,7 @@ static unsigned long __zs_compact(struct zs_pool *pool, migrate_write_unlock(src_zspage); } - spin_unlock(&class->lock); - write_unlock(&pool->migrate_lock); + spin_unlock(&pool->lock); return pages_freed; } @@ -2221,7 +2342,7 @@ struct zs_pool *zs_create_pool(const char *name) return NULL; init_deferred_free(pool); - rwlock_init(&pool->migrate_lock); + spin_lock_init(&pool->lock); pool->name = kstrdup(name, GFP_KERNEL); if (!pool->name) @@ -2292,7 +2413,6 @@ struct zs_pool *zs_create_pool(const char *name) class->index = i; class->pages_per_zspage = pages_per_zspage; class->objs_per_zspage = objs_per_zspage; - spin_lock_init(&class->lock); pool->size_class[i] = class; for (fullness = ZS_EMPTY; fullness < NR_ZS_FULLNESS; fullness++) @@ -2312,6 +2432,10 @@ struct zs_pool *zs_create_pool(const char *name) */ zs_register_shrinker(pool); +#ifdef CONFIG_ZPOOL + INIT_LIST_HEAD(&pool->lru); +#endif + return pool; err: @@ -2353,6 +2477,100 @@ void zs_destroy_pool(struct zs_pool *pool) } EXPORT_SYMBOL_GPL(zs_destroy_pool); +#ifdef CONFIG_ZPOOL +static int zs_reclaim_page(struct zs_pool *pool, unsigned int retries) +{ + int i, obj_idx, ret = 0; + unsigned long handle; + struct zspage *zspage; + struct page *page; + enum fullness_group fullness; + + /* Lock LRU and fullness list */ + spin_lock(&pool->lock); + if (list_empty(&pool->lru)) { + spin_unlock(&pool->lock); + return -EINVAL; + } + + for (i = 0; i < retries; i++) { + struct size_class *class; + + zspage = list_last_entry(&pool->lru, struct zspage, lru); + list_del(&zspage->lru); + + /* zs_free may free objects, but not the zspage and handles */ + zspage->under_reclaim = true; + + class = zspage_class(pool, zspage); + fullness = get_fullness_group(class, zspage); + + /* Lock out object allocations and object compaction */ + remove_zspage(class, zspage, fullness); + + spin_unlock(&pool->lock); + cond_resched(); + + /* Lock backing pages into place */ + lock_zspage(zspage); + + obj_idx = 0; + page = get_first_page(zspage); + while (1) { + handle = find_alloced_obj(class, page, &obj_idx); + if (!handle) { + page = get_next_page(page); + if (!page) + break; + obj_idx = 0; + continue; + } + + /* + * This will write the object and call zs_free. + * + * zs_free will free the object, but the + * under_reclaim flag prevents it from freeing + * the zspage altogether. This is necessary so + * that we can continue working with the + * zspage potentially after the last object + * has been freed. + */ + ret = pool->zpool_ops->evict(pool->zpool, handle); + if (ret) + goto next; + + obj_idx++; + } + +next: + /* For freeing the zspage, or putting it back in the pool and LRU list. */ + spin_lock(&pool->lock); + zspage->under_reclaim = false; + + if (!get_zspage_inuse(zspage)) { + /* + * Fullness went stale as zs_free() won't touch it + * while the page is removed from the pool. Fix it + * up for the check in __free_zspage(). + */ + zspage->fullness = ZS_EMPTY; + + __free_zspage(pool, class, zspage); + spin_unlock(&pool->lock); + return 0; + } + + putback_zspage(class, zspage); + list_add(&zspage->lru, &pool->lru); + unlock_zspage(zspage); + } + + spin_unlock(&pool->lock); + return -EAGAIN; +} +#endif /* CONFIG_ZPOOL */ + static int __init zs_init(void) { int ret; diff --git a/mm/zswap.c b/mm/zswap.c index 3019f0bde194..f6c89049cf70 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -968,6 +968,7 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) swpentry = zhdr->swpentry; /* here */ tree = zswap_trees[swp_type(swpentry)]; offset = swp_offset(swpentry); + zpool_unmap_handle(pool, handle); /* find and ref zswap entry */ spin_lock(&tree->lock); @@ -975,20 +976,12 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) if (!entry) { /* entry was invalidated */ spin_unlock(&tree->lock); - zpool_unmap_handle(pool, handle); kfree(tmp); return 0; } spin_unlock(&tree->lock); BUG_ON(offset != entry->offset); - src = (u8 *)zhdr + sizeof(struct zswap_header); - if (!zpool_can_sleep_mapped(pool)) { - memcpy(tmp, src, entry->length); - src = tmp; - zpool_unmap_handle(pool, handle); - } - /* try to allocate swap cache page */ switch (zswap_get_swap_cache_page(swpentry, &page)) { case ZSWAP_SWAPCACHE_FAIL: /* no memory or invalidate happened */ @@ -1006,6 +999,14 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); dlen = PAGE_SIZE; + zhdr = zpool_map_handle(pool, handle, ZPOOL_MM_RO); + src = (u8 *)zhdr + sizeof(struct zswap_header); + if (!zpool_can_sleep_mapped(pool)) { + memcpy(tmp, src, entry->length); + src = tmp; + zpool_unmap_handle(pool, handle); + } + mutex_lock(acomp_ctx->mutex); sg_init_one(&input, src, entry->length); sg_init_table(&output, 1); @@ -1015,6 +1016,11 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) dlen = acomp_ctx->req->dlen; mutex_unlock(acomp_ctx->mutex); + if (!zpool_can_sleep_mapped(pool)) + kfree(tmp); + else + zpool_unmap_handle(pool, handle); + BUG_ON(ret); BUG_ON(dlen != PAGE_SIZE); @@ -1045,7 +1051,11 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) zswap_entry_put(tree, entry); spin_unlock(&tree->lock); - goto end; + return ret; + +fail: + if (!zpool_can_sleep_mapped(pool)) + kfree(tmp); /* * if we get here due to ZSWAP_SWAPCACHE_EXIST @@ -1054,17 +1064,10 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle) * if we free the entry in the following put * it is also okay to return !0 */ -fail: spin_lock(&tree->lock); zswap_entry_put(tree, entry); spin_unlock(&tree->lock); -end: - if (zpool_can_sleep_mapped(pool)) - zpool_unmap_handle(pool, handle); - else - kfree(tmp); - return ret; } diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index 2e91973fbaa6..81fa7ec2e66a 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: GPL-2.0+ /* - * maple_tree.c: Userspace shim for maple tree test-suite - * Copyright (c) 2018 Liam R. Howlett <Liam.Howlett@Oracle.com> + * maple_tree.c: Userspace testing for maple tree test-suite + * Copyright (c) 2018-2022 Oracle Corporation + * Author: Liam R. Howlett <Liam.Howlett@Oracle.com> * * Any tests that require internal knowledge of the tree or threads and other * difficult to handle in kernel tests. diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile index 838a8e49f77b..b71247ba7196 100644 --- a/tools/testing/selftests/damon/Makefile +++ b/tools/testing/selftests/damon/Makefile @@ -8,7 +8,7 @@ TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh TEST_PROGS += debugfs_empty_targets.sh debugfs_huge_count_read_write.sh TEST_PROGS += debugfs_duplicate_context_creation.sh TEST_PROGS += debugfs_rm_non_contexts.sh -TEST_PROGS += sysfs.sh +TEST_PROGS += sysfs.sh sysfs_update_removed_scheme_dir.sh TEST_PROGS += reclaim.sh lru_sort.sh include ../lib.mk diff --git a/tools/testing/selftests/damon/sysfs_update_removed_scheme_dir.sh b/tools/testing/selftests/damon/sysfs_update_removed_scheme_dir.sh new file mode 100644 index 000000000000..ade35576e748 --- /dev/null +++ b/tools/testing/selftests/damon/sysfs_update_removed_scheme_dir.sh @@ -0,0 +1,58 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +if [ $EUID -ne 0 ] +then + echo "Run as root" + exit $ksft_skip +fi + +damon_sysfs="/sys/kernel/mm/damon/admin" +if [ ! -d "$damon_sysfs" ] +then + echo "damon sysfs not found" + exit $ksft_skip +fi + +# clear log +dmesg -C + +# start DAMON with a scheme +echo 1 > "$damon_sysfs/kdamonds/nr_kdamonds" +echo 1 > "$damon_sysfs/kdamonds/0/contexts/nr_contexts" +echo "vaddr" > "$damon_sysfs/kdamonds/0/contexts/0/operations" +echo 1 > "$damon_sysfs/kdamonds/0/contexts/0/targets/nr_targets" +echo $$ > "$damon_sysfs/kdamonds/0/contexts/0/targets/0/pid_target" +echo 1 > "$damon_sysfs/kdamonds/0/contexts/0/schemes/nr_schemes" +scheme_dir="$damon_sysfs/kdamonds/0/contexts/0/schemes/0" +echo 4096000 > "$scheme_dir/access_pattern/sz/max" +echo 20 > "$scheme_dir/access_pattern/nr_accesses/max" +echo 1024 > "$scheme_dir/access_pattern/age/max" +echo "on" > "$damon_sysfs/kdamonds/0/state" +sleep 0.3 + +# remove scheme sysfs dir +echo 0 > "$damon_sysfs/kdamonds/0/contexts/0/schemes/nr_schemes" + +# try to update stat of already removed scheme sysfs dir +echo "update_schemes_stats" > "$damon_sysfs/kdamonds/0/state" +if dmesg | grep -q BUG +then + echo "update_schemes_stats triggers a kernel bug" + dmesg + exit 1 +fi + +# try to update tried regions of already removed scheme sysfs dir +echo "update_schemes_tried_regions" > "$damon_sysfs/kdamonds/0/state" +if dmesg | grep -q BUG +then + echo "update_schemes_tried_regions triggers a kernel bug" + dmesg + exit 1 +fi + +echo "off" > "$damon_sysfs/kdamonds/0/state" diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index a4d764efd6e3..89c14e41bd43 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -55,6 +55,7 @@ TEST_GEN_FILES += userfaultfd TEST_GEN_PROGS += soft-dirty TEST_GEN_PROGS += split_huge_page_test TEST_GEN_FILES += ksm_tests +TEST_GEN_PROGS += ksm_functional_tests ifeq ($(MACHINE),x86_64) CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_32bit_program.c -m32) @@ -100,6 +101,7 @@ include ../lib.mk $(OUTPUT)/cow: vm_util.c $(OUTPUT)/khugepaged: vm_util.c +$(OUTPUT)/ksm_functional_tests: vm_util.c $(OUTPUT)/madv_populate: vm_util.c $(OUTPUT)/soft-dirty: vm_util.c $(OUTPUT)/split_huge_page_test: vm_util.c diff --git a/tools/testing/selftests/vm/ksm_functional_tests.c b/tools/testing/selftests/vm/ksm_functional_tests.c new file mode 100644 index 000000000000..96644be68962 --- /dev/null +++ b/tools/testing/selftests/vm/ksm_functional_tests.c @@ -0,0 +1,279 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KSM functional tests + * + * Copyright 2022, Red Hat, Inc. + * + * Author(s): David Hildenbrand <david@redhat.com> + */ +#define _GNU_SOURCE +#include <stdlib.h> +#include <string.h> +#include <stdbool.h> +#include <stdint.h> +#include <unistd.h> +#include <errno.h> +#include <fcntl.h> +#include <sys/mman.h> +#include <sys/syscall.h> +#include <sys/ioctl.h> +#include <linux/userfaultfd.h> + +#include "../kselftest.h" +#include "vm_util.h" + +#define KiB 1024u +#define MiB (1024 * KiB) + +static int ksm_fd; +static int ksm_full_scans_fd; +static int pagemap_fd; +static size_t pagesize; + +static bool range_maps_duplicates(char *addr, unsigned long size) +{ + unsigned long offs_a, offs_b, pfn_a, pfn_b; + + /* + * There is no easy way to check if there are KSM pages mapped into + * this range. We only check that the range does not map the same PFN + * twice by comaring each pair of mapped pages. + */ + for (offs_a = 0; offs_a < size; offs_a += pagesize) { + pfn_a = pagemap_get_pfn(pagemap_fd, addr + offs_a); + /* Page not present or PFN not exposed by the kernel. */ + if (pfn_a == -1ull || !pfn_a) + continue; + + for (offs_b = offs_a + pagesize; offs_b < size; + offs_b += pagesize) { + pfn_b = pagemap_get_pfn(pagemap_fd, addr + offs_b); + if (pfn_b == -1ull || !pfn_b) + continue; + if (pfn_a == pfn_b) + return true; + } + } + return false; +} + +static long ksm_get_full_scans(void) +{ + char buf[10]; + ssize_t ret; + + ret = pread(ksm_full_scans_fd, buf, sizeof(buf) - 1, 0); + if (ret <= 0) + return -errno; + buf[ret] = 0; + + return strtol(buf, NULL, 10); +} + +static int ksm_merge(void) +{ + long start_scans, end_scans; + + /* Wait for two full scans such that any possible merging happened. */ + start_scans = ksm_get_full_scans(); + if (start_scans < 0) + return start_scans; + if (write(ksm_fd, "1", 1) != 1) + return -errno; + do { + end_scans = ksm_get_full_scans(); + if (end_scans < 0) + return end_scans; + } while (end_scans < start_scans + 2); + + return 0; +} + +static char *mmap_and_merge_range(char val, unsigned long size) +{ + char *map; + + map = mmap(NULL, size, PROT_READ|PROT_WRITE, + MAP_PRIVATE|MAP_ANON, -1, 0); + if (map == MAP_FAILED) { + ksft_test_result_fail("mmap() failed\n"); + return MAP_FAILED; + } + + /* Don't use THP. Ignore if THP are not around on a kernel. */ + if (madvise(map, size, MADV_NOHUGEPAGE) && errno != EINVAL) { + ksft_test_result_fail("MADV_NOHUGEPAGE failed\n"); + goto unmap; + } + + /* Make sure each page contains the same values to merge them. */ + memset(map, val, size); + if (madvise(map, size, MADV_MERGEABLE)) { + ksft_test_result_fail("MADV_MERGEABLE failed\n"); + goto unmap; + } + + /* Run KSM to trigger merging and wait. */ + if (ksm_merge()) { + ksft_test_result_fail("Running KSM failed\n"); + goto unmap; + } + return map; +unmap: + munmap(map, size); + return MAP_FAILED; +} + +static void test_unmerge(void) +{ + const unsigned int size = 2 * MiB; + char *map; + + ksft_print_msg("[RUN] %s\n", __func__); + + map = mmap_and_merge_range(0xcf, size); + if (map == MAP_FAILED) + return; + + if (madvise(map, size, MADV_UNMERGEABLE)) { + ksft_test_result_fail("MADV_UNMERGEABLE failed\n"); + goto unmap; + } + + ksft_test_result(!range_maps_duplicates(map, size), + "Pages were unmerged\n"); +unmap: + munmap(map, size); +} + +static void test_unmerge_discarded(void) +{ + const unsigned int size = 2 * MiB; + char *map; + + ksft_print_msg("[RUN] %s\n", __func__); + + map = mmap_and_merge_range(0xcf, size); + if (map == MAP_FAILED) + return; + + /* Discard half of all mapped pages so we have pte_none() entries. */ + if (madvise(map, size / 2, MADV_DONTNEED)) { + ksft_test_result_fail("MADV_DONTNEED failed\n"); + goto unmap; + } + + if (madvise(map, size, MADV_UNMERGEABLE)) { + ksft_test_result_fail("MADV_UNMERGEABLE failed\n"); + goto unmap; + } + + ksft_test_result(!range_maps_duplicates(map, size), + "Pages were unmerged\n"); +unmap: + munmap(map, size); +} + +#ifdef __NR_userfaultfd +static void test_unmerge_uffd_wp(void) +{ + struct uffdio_writeprotect uffd_writeprotect; + struct uffdio_register uffdio_register; + const unsigned int size = 2 * MiB; + struct uffdio_api uffdio_api; + char *map; + int uffd; + + ksft_print_msg("[RUN] %s\n", __func__); + + map = mmap_and_merge_range(0xcf, size); + if (map == MAP_FAILED) + return; + + /* See if UFFD is around. */ + uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK); + if (uffd < 0) { + ksft_test_result_skip("__NR_userfaultfd failed\n"); + goto unmap; + } + + /* See if UFFD-WP is around. */ + uffdio_api.api = UFFD_API; + uffdio_api.features = UFFD_FEATURE_PAGEFAULT_FLAG_WP; + if (ioctl(uffd, UFFDIO_API, &uffdio_api) < 0) { + ksft_test_result_fail("UFFDIO_API failed\n"); + goto close_uffd; + } + if (!(uffdio_api.features & UFFD_FEATURE_PAGEFAULT_FLAG_WP)) { + ksft_test_result_skip("UFFD_FEATURE_PAGEFAULT_FLAG_WP not available\n"); + goto close_uffd; + } + + /* Register UFFD-WP, no need for an actual handler. */ + uffdio_register.range.start = (unsigned long) map; + uffdio_register.range.len = size; + uffdio_register.mode = UFFDIO_REGISTER_MODE_WP; + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) < 0) { + ksft_test_result_fail("UFFDIO_REGISTER_MODE_WP failed\n"); + goto close_uffd; + } + + /* Write-protect the range using UFFD-WP. */ + uffd_writeprotect.range.start = (unsigned long) map; + uffd_writeprotect.range.len = size; + uffd_writeprotect.mode = UFFDIO_WRITEPROTECT_MODE_WP; + if (ioctl(uffd, UFFDIO_WRITEPROTECT, &uffd_writeprotect)) { + ksft_test_result_fail("UFFDIO_WRITEPROTECT failed\n"); + goto close_uffd; + } + + if (madvise(map, size, MADV_UNMERGEABLE)) { + ksft_test_result_fail("MADV_UNMERGEABLE failed\n"); + goto close_uffd; + } + + ksft_test_result(!range_maps_duplicates(map, size), + "Pages were unmerged\n"); +close_uffd: + close(uffd); +unmap: + munmap(map, size); +} +#endif + +int main(int argc, char **argv) +{ + unsigned int tests = 2; + int err; + +#ifdef __NR_userfaultfd + tests++; +#endif + + ksft_print_header(); + ksft_set_plan(tests); + + pagesize = getpagesize(); + + ksm_fd = open("/sys/kernel/mm/ksm/run", O_RDWR); + if (ksm_fd < 0) + ksft_exit_skip("open(\"/sys/kernel/mm/ksm/run\") failed\n"); + ksm_full_scans_fd = open("/sys/kernel/mm/ksm/full_scans", O_RDONLY); + if (ksm_full_scans_fd < 0) + ksft_exit_skip("open(\"/sys/kernel/mm/ksm/full_scans\") failed\n"); + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + if (pagemap_fd < 0) + ksft_exit_skip("open(\"/proc/self/pagemap\") failed\n"); + + test_unmerge(); + test_unmerge_discarded(); +#ifdef __NR_userfaultfd + test_unmerge_uffd_wp(); +#endif + + err = ksft_get_fail_cnt(); + if (err) + ksft_exit_fail_msg("%d out of %d tests failed\n", + err, ksft_test_num()); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/vm/ksm_tests.c b/tools/testing/selftests/vm/ksm_tests.c index 0d85be2350fa..f9eb4d67e0dd 100644 --- a/tools/testing/selftests/vm/ksm_tests.c +++ b/tools/testing/selftests/vm/ksm_tests.c @@ -40,6 +40,7 @@ enum ksm_test_name { CHECK_KSM_NUMA_MERGE, KSM_MERGE_TIME, KSM_MERGE_TIME_HUGE_PAGES, + KSM_UNMERGE_TIME, KSM_COW_TIME }; @@ -108,7 +109,10 @@ static void print_help(void) " -P evaluate merging time and speed.\n" " For this test, the size of duplicated memory area (in MiB)\n" " must be provided using -s option\n" - " -H evaluate merging time and speed of area allocated mostly with huge pages\n" + " -H evaluate merging time and speed of area allocated mostly with huge pages\n" + " For this test, the size of duplicated memory area (in MiB)\n" + " must be provided using -s option\n" + " -D evaluate unmerging time and speed when disabling KSM.\n" " For this test, the size of duplicated memory area (in MiB)\n" " must be provided using -s option\n" " -C evaluate the time required to break COW of merged pages.\n\n"); @@ -188,6 +192,16 @@ static int ksm_merge_pages(void *addr, size_t size, struct timespec start_time, return 0; } +static int ksm_unmerge_pages(void *addr, size_t size, + struct timespec start_time, int timeout) +{ + if (madvise(addr, size, MADV_UNMERGEABLE)) { + perror("madvise"); + return 1; + } + return 0; +} + static bool assert_ksm_pages_count(long dupl_page_count) { unsigned long max_page_sharing, pages_sharing, pages_shared; @@ -560,6 +574,53 @@ err_out: return KSFT_FAIL; } +static int ksm_unmerge_time(int mapping, int prot, int timeout, size_t map_size) +{ + void *map_ptr; + struct timespec start_time, end_time; + unsigned long scan_time_ns; + + map_size *= MB; + + map_ptr = allocate_memory(NULL, prot, mapping, '*', map_size); + if (!map_ptr) + return KSFT_FAIL; + if (clock_gettime(CLOCK_MONOTONIC_RAW, &start_time)) { + perror("clock_gettime"); + goto err_out; + } + if (ksm_merge_pages(map_ptr, map_size, start_time, timeout)) + goto err_out; + + if (clock_gettime(CLOCK_MONOTONIC_RAW, &start_time)) { + perror("clock_gettime"); + goto err_out; + } + if (ksm_unmerge_pages(map_ptr, map_size, start_time, timeout)) + goto err_out; + if (clock_gettime(CLOCK_MONOTONIC_RAW, &end_time)) { + perror("clock_gettime"); + goto err_out; + } + + scan_time_ns = (end_time.tv_sec - start_time.tv_sec) * NSEC_PER_SEC + + (end_time.tv_nsec - start_time.tv_nsec); + + printf("Total size: %lu MiB\n", map_size / MB); + printf("Total time: %ld.%09ld s\n", scan_time_ns / NSEC_PER_SEC, + scan_time_ns % NSEC_PER_SEC); + printf("Average speed: %.3f MiB/s\n", (map_size / MB) / + ((double)scan_time_ns / NSEC_PER_SEC)); + + munmap(map_ptr, map_size); + return KSFT_PASS; + +err_out: + printf("Not OK\n"); + munmap(map_ptr, map_size); + return KSFT_FAIL; +} + static int ksm_cow_time(int mapping, int prot, int timeout, size_t page_size) { void *map_ptr; @@ -644,7 +705,7 @@ int main(int argc, char *argv[]) bool merge_across_nodes = KSM_MERGE_ACROSS_NODES_DEFAULT; long size_MB = 0; - while ((opt = getopt(argc, argv, "ha:p:l:z:m:s:MUZNPCH")) != -1) { + while ((opt = getopt(argc, argv, "ha:p:l:z:m:s:MUZNPCHD")) != -1) { switch (opt) { case 'a': prot = str_to_prot(optarg); @@ -701,6 +762,9 @@ int main(int argc, char *argv[]) case 'H': test_name = KSM_MERGE_TIME_HUGE_PAGES; break; + case 'D': + test_name = KSM_UNMERGE_TIME; + break; case 'C': test_name = KSM_COW_TIME; break; @@ -762,6 +826,14 @@ int main(int argc, char *argv[]) ret = ksm_merge_hugepages_time(MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec, size_MB); break; + case KSM_UNMERGE_TIME: + if (size_MB == 0) { + printf("Option '-s' is required.\n"); + return KSFT_FAIL; + } + ret = ksm_unmerge_time(MAP_PRIVATE | MAP_ANONYMOUS, prot, + ksm_scan_limit_sec, size_MB); + break; case KSM_COW_TIME: ret = ksm_cow_time(MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec, page_size); diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh index 54d7a822c2ce..8984e0bb58c7 100755 --- a/tools/testing/selftests/vm/run_vmtests.sh +++ b/tools/testing/selftests/vm/run_vmtests.sh @@ -1,13 +1,88 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -#please run as root +# Please run as root # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 exitcode=0 -#get huge pagesize and freepages from /proc/meminfo +usage() { + cat <<EOF +usage: ${BASH_SOURCE[0]:-$0} [ -h | -t "<categories>"] + -t: specify specific categories to tests to run + -h: display this message + +The default behavior is to run all tests. + +Alternatively, specific groups tests can be run by passing a string +to the -t argument containing one or more of the following categories +separated by spaces: +- mmap + tests for mmap(2) +- gup_test + tests for gup using gup_test interface +- userfaultfd + tests for userfaultfd(2) +- compaction + a test for the patch "Allow compaction of unevictable pages" +- mlock + tests for mlock(2) +- mremap + tests for mremap(2) +- hugevm + tests for very large virtual address space +- vmalloc + vmalloc smoke tests +- hmm + hmm smoke tests +- madv_populate + test memadvise(2) MADV_POPULATE_{READ,WRITE} options +- memfd_secret + test memfd_secret(2) +- process_mrelease + test process_mrelease(2) +- ksm + ksm tests that do not require >=2 NUMA nodes +- ksm_numa + ksm tests that require >=2 NUMA nodes +- pkey + memory protection key tests +- soft_dirty + test soft dirty page bit semantics +- cow + test copy-on-write semantics +example: ./run_vmtests.sh -t "hmm mmap ksm" +EOF + exit 0 +} + + +while getopts "ht:" OPT; do + case ${OPT} in + "h") usage ;; + "t") VM_SELFTEST_ITEMS=${OPTARG} ;; + esac +done +shift $((OPTIND -1)) + +# default behavior: run all tests +VM_SELFTEST_ITEMS=${VM_SELFTEST_ITEMS:-default} + +test_selected() { + if [ "$VM_SELFTEST_ITEMS" == "default" ]; then + # If no VM_SELFTEST_ITEMS are specified, run all tests + return 0 + fi + # If test selected argument is one of the test items + if [[ " ${VM_SELFTEST_ITEMS[*]} " =~ " ${1} " ]]; then + return 0 + else + return 1 + fi +} + +# get huge pagesize and freepages from /proc/meminfo while read -r name size unit; do if [ "$name" = "HugePages_Free:" ]; then freepgs="$size" @@ -27,7 +102,7 @@ hpgsize_MB=$((hpgsize_KB / 1024)) half_ufd_size_MB=$((((nr_cpus * hpgsize_MB + 127) / 128) * 128)) needmem_KB=$((half_ufd_size_MB * 2 * 1024)) -#set proper nr_hugepages +# set proper nr_hugepages if [ -n "$freepgs" ] && [ -n "$hpgsize_KB" ]; then nr_hugepgs=$(cat /proc/sys/vm/nr_hugepages) needpgs=$((needmem_KB / hpgsize_KB)) @@ -56,136 +131,144 @@ else exit 1 fi -#filter 64bit architectures +# filter 64bit architectures ARCH64STR="arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64" if [ -z "$ARCH" ]; then ARCH=$(uname -m 2>/dev/null | sed -e 's/aarch64.*/arm64/') fi VADDR64=0 -echo "$ARCH64STR" | grep "$ARCH" && VADDR64=1 +echo "$ARCH64STR" | grep "$ARCH" &>/dev/null && VADDR64=1 # Usage: run_test [test binary] [arbitrary test arguments...] run_test() { - local title="running $*" - local sep=$(echo -n "$title" | tr "[:graph:][:space:]" -) - printf "%s\n%s\n%s\n" "$sep" "$title" "$sep" - - "$@" - local ret=$? - if [ $ret -eq 0 ]; then - echo "[PASS]" - elif [ $ret -eq $ksft_skip ]; then - echo "[SKIP]" - exitcode=$ksft_skip - else - echo "[FAIL]" - exitcode=1 - fi + if test_selected ${CATEGORY}; then + local title="running $*" + local sep=$(echo -n "$title" | tr "[:graph:][:space:]" -) + printf "%s\n%s\n%s\n" "$sep" "$title" "$sep" + + "$@" + local ret=$? + if [ $ret -eq 0 ]; then + echo "[PASS]" + elif [ $ret -eq $ksft_skip ]; then + echo "[SKIP]" + exitcode=$ksft_skip + else + echo "[FAIL]" + exitcode=1 + fi + fi # test_selected } -run_test ./hugepage-mmap +CATEGORY="hugetlb" run_test ./hugepage-mmap shmmax=$(cat /proc/sys/kernel/shmmax) shmall=$(cat /proc/sys/kernel/shmall) echo 268435456 > /proc/sys/kernel/shmmax echo 4194304 > /proc/sys/kernel/shmall -run_test ./hugepage-shm +CATEGORY="hugetlb" run_test ./hugepage-shm echo "$shmmax" > /proc/sys/kernel/shmmax echo "$shmall" > /proc/sys/kernel/shmall -run_test ./map_hugetlb -run_test ./hugepage-mremap -run_test ./hugepage-vmemmap -run_test ./hugetlb-madvise +CATEGORY="hugetlb" run_test ./map_hugetlb +CATEGORY="hugetlb" run_test ./hugepage-mremap +CATEGORY="hugetlb" run_test ./hugepage-vmemmap +CATEGORY="hugetlb" run_test ./hugetlb-madvise -echo "NOTE: The above hugetlb tests provide minimal coverage. Use" -echo " https://github.com/libhugetlbfs/libhugetlbfs.git for" -echo " hugetlb regression testing." +if test_selected "hugetlb"; then + echo "NOTE: These hugetlb tests provide minimal coverage. Use" + echo " https://github.com/libhugetlbfs/libhugetlbfs.git for" + echo " hugetlb regression testing." +fi -run_test ./map_fixed_noreplace +CATEGORY="mmap" run_test ./map_fixed_noreplace # get_user_pages_fast() benchmark -run_test ./gup_test -u +CATEGORY="gup_test" run_test ./gup_test -u # pin_user_pages_fast() benchmark -run_test ./gup_test -a +CATEGORY="gup_test" run_test ./gup_test -a # Dump pages 0, 19, and 4096, using pin_user_pages: -run_test ./gup_test -ct -F 0x1 0 19 0x1000 +CATEGORY="gup_test" run_test ./gup_test -ct -F 0x1 0 19 0x1000 uffd_mods=("" ":dev") for mod in "${uffd_mods[@]}"; do - run_test ./userfaultfd anon${mod} 20 16 + CATEGORY="userfaultfd" run_test ./userfaultfd anon${mod} 20 16 # Hugetlb tests require source and destination huge pages. Pass in half # the size ($half_ufd_size_MB), which is used for *each*. - run_test ./userfaultfd hugetlb${mod} "$half_ufd_size_MB" 32 - run_test ./userfaultfd hugetlb_shared${mod} "$half_ufd_size_MB" 32 - run_test ./userfaultfd shmem${mod} 20 16 + CATEGORY="userfaultfd" run_test ./userfaultfd hugetlb${mod} "$half_ufd_size_MB" 32 + CATEGORY="userfaultfd" run_test ./userfaultfd hugetlb_shared${mod} "$half_ufd_size_MB" 32 + CATEGORY="userfaultfd" run_test ./userfaultfd shmem${mod} 20 16 done #cleanup echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages -run_test ./compaction_test +CATEGORY="compaction" run_test ./compaction_test -run_test sudo -u nobody ./on-fault-limit +CATEGORY="mlock" run_test sudo -u nobody ./on-fault-limit -run_test ./map_populate +CATEGORY="mmap" run_test ./map_populate -run_test ./mlock-random-test +CATEGORY="mlock" run_test ./mlock-random-test -run_test ./mlock2-tests +CATEGORY="mlock" run_test ./mlock2-tests -run_test ./mrelease_test +CATEGORY="process_mrelease" run_test ./mrelease_test -run_test ./mremap_test +CATEGORY="mremap" run_test ./mremap_test -run_test ./thuge-gen +CATEGORY="hugetlb" run_test ./thuge-gen if [ $VADDR64 -ne 0 ]; then - run_test ./virtual_address_range + CATEGORY="hugevm" run_test ./virtual_address_range # virtual address 128TB switch test - run_test ./va_128TBswitch.sh + CATEGORY="hugevm" run_test ./va_128TBswitch.sh fi # VADDR64 # vmalloc stability smoke test -run_test ./test_vmalloc.sh smoke +CATEGORY="vmalloc" run_test ./test_vmalloc.sh smoke -run_test ./mremap_dontunmap +CATEGORY="mremap" run_test ./mremap_dontunmap -run_test ./test_hmm.sh smoke +CATEGORY="hmm" run_test ./test_hmm.sh smoke # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests -run_test ./madv_populate +CATEGORY="madv_populate" run_test ./madv_populate -run_test ./memfd_secret +CATEGORY="memfd_secret" run_test ./memfd_secret # KSM MADV_MERGEABLE test with 10 identical pages -run_test ./ksm_tests -M -p 10 +CATEGORY="ksm" run_test ./ksm_tests -M -p 10 # KSM unmerge test -run_test ./ksm_tests -U +CATEGORY="ksm" run_test ./ksm_tests -U # KSM test with 10 zero pages and use_zero_pages = 0 -run_test ./ksm_tests -Z -p 10 -z 0 +CATEGORY="ksm" run_test ./ksm_tests -Z -p 10 -z 0 # KSM test with 10 zero pages and use_zero_pages = 1 -run_test ./ksm_tests -Z -p 10 -z 1 +CATEGORY="ksm" run_test ./ksm_tests -Z -p 10 -z 1 # KSM test with 2 NUMA nodes and merge_across_nodes = 1 -run_test ./ksm_tests -N -m 1 +CATEGORY="ksm_numa" run_test ./ksm_tests -N -m 1 # KSM test with 2 NUMA nodes and merge_across_nodes = 0 -run_test ./ksm_tests -N -m 0 +CATEGORY="ksm_numa" run_test ./ksm_tests -N -m 0 + +CATEGORY="ksm" run_test ./ksm_functional_tests + +run_test ./ksm_functional_tests # protection_keys tests if [ -x ./protection_keys_32 ] then - run_test ./protection_keys_32 + CATEGORY="pkey" run_test ./protection_keys_32 fi if [ -x ./protection_keys_64 ] then - run_test ./protection_keys_64 + CATEGORY="pkey" run_test ./protection_keys_64 fi -run_test ./soft-dirty +CATEGORY="soft_dirty" run_test ./soft-dirty -# COW tests for anonymous memory -run_test ./cow +# COW tests +CATEGORY="cow" run_test ./cow exit $exitcode diff --git a/tools/testing/selftests/vm/vm_util.c b/tools/testing/selftests/vm/vm_util.c index 5bbf7641a0f0..710571902743 100644 --- a/tools/testing/selftests/vm/vm_util.c +++ b/tools/testing/selftests/vm/vm_util.c @@ -43,6 +43,16 @@ bool pagemap_is_populated(int fd, char *start) return entry & 0xc000000000000000ull; } +unsigned long pagemap_get_pfn(int fd, char *start) +{ + uint64_t entry = pagemap_get_entry(fd, start); + + /* If present (63th bit), PFN is at bit 0 -- 54. */ + if (entry & 0x8000000000000000ull) + return entry & 0x007fffffffffffffull; + return -1ull; +} + void clear_softdirty(void) { int ret; diff --git a/tools/testing/selftests/vm/vm_util.h b/tools/testing/selftests/vm/vm_util.h index 80d5a6ad413b..1995ee911ef2 100644 --- a/tools/testing/selftests/vm/vm_util.h +++ b/tools/testing/selftests/vm/vm_util.h @@ -6,6 +6,7 @@ uint64_t pagemap_get_entry(int fd, char *start); bool pagemap_is_softdirty(int fd, char *start); bool pagemap_is_swapped(int fd, char *start); bool pagemap_is_populated(int fd, char *start); +unsigned long pagemap_get_pfn(int fd, char *start); void clear_softdirty(void); bool check_for_pattern(FILE *fp, const char *pattern, char *buf, size_t len); uint64_t read_pmd_pagesize(void); |