diff options
Diffstat (limited to 'mm/vmalloc.c')
| -rw-r--r-- | mm/vmalloc.c | 4177 |
1 files changed, 3009 insertions, 1168 deletions
diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 3091c2ca60df..ecbac900c35f 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1,12 +1,11 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * linux/mm/vmalloc.c - * * Copyright (C) 1993 Linus Torvalds * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 * SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian <tigran@veritas.com>, May 2000 * Major rework to support vmap/vunmap, Christoph Hellwig, SGI, August 2002 * Numa awareness, Christoph Lameter, SGI, June 2005 + * Improving global KVA allocator, Uladzislau Rezki, Sony, May 2019 */ #include <linux/vmalloc.h> @@ -25,26 +24,61 @@ #include <linux/list.h> #include <linux/notifier.h> #include <linux/rbtree.h> -#include <linux/radix-tree.h> +#include <linux/xarray.h> +#include <linux/io.h> #include <linux/rcupdate.h> #include <linux/pfn.h> #include <linux/kmemleak.h> #include <linux/atomic.h> #include <linux/compiler.h> +#include <linux/memcontrol.h> #include <linux/llist.h> +#include <linux/uio.h> #include <linux/bitops.h> #include <linux/rbtree_augmented.h> #include <linux/overflow.h> - -#include <linux/uaccess.h> +#include <linux/pgtable.h> +#include <linux/hugetlb.h> +#include <linux/sched/mm.h> #include <asm/tlbflush.h> #include <asm/shmparam.h> +#include <linux/page_owner.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/vmalloc.h> #include "internal.h" +#include "pgalloc-track.h" + +#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +static unsigned int __ro_after_init ioremap_max_page_shift = BITS_PER_LONG - 1; + +static int __init set_nohugeiomap(char *str) +{ + ioremap_max_page_shift = PAGE_SHIFT; + return 0; +} +early_param("nohugeiomap", set_nohugeiomap); +#else /* CONFIG_HAVE_ARCH_HUGE_VMAP */ +static const unsigned int ioremap_max_page_shift = PAGE_SHIFT; +#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ + +#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC +static bool __ro_after_init vmap_allow_huge = true; + +static int __init set_nohugevmalloc(char *str) +{ + vmap_allow_huge = false; + return 0; +} +early_param("nohugevmalloc", set_nohugevmalloc); +#else /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */ +static const bool vmap_allow_huge = false; +#endif /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */ bool is_vmalloc_addr(const void *x) { - unsigned long addr = (unsigned long)x; + unsigned long addr = (unsigned long)kasan_reset_tag(x); return addr >= VMALLOC_START && addr < VMALLOC_END; } @@ -56,29 +90,302 @@ struct vfree_deferred { }; static DEFINE_PER_CPU(struct vfree_deferred, vfree_deferred); -static void __vunmap(const void *, int); +/*** Page table manipulation functions ***/ +static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int max_page_shift, pgtbl_mod_mask *mask) +{ + pte_t *pte; + u64 pfn; + struct page *page; + unsigned long size = PAGE_SIZE; -static void free_work(struct work_struct *w) + if (WARN_ON_ONCE(!PAGE_ALIGNED(end - addr))) + return -EINVAL; + + pfn = phys_addr >> PAGE_SHIFT; + pte = pte_alloc_kernel_track(pmd, addr, mask); + if (!pte) + return -ENOMEM; + + arch_enter_lazy_mmu_mode(); + + do { + if (unlikely(!pte_none(ptep_get(pte)))) { + if (pfn_valid(pfn)) { + page = pfn_to_page(pfn); + dump_page(page, "remapping already mapped page"); + } + BUG(); + } + +#ifdef CONFIG_HUGETLB_PAGE + size = arch_vmap_pte_range_map_size(addr, end, pfn, max_page_shift); + if (size != PAGE_SIZE) { + pte_t entry = pfn_pte(pfn, prot); + + entry = arch_make_huge_pte(entry, ilog2(size), 0); + set_huge_pte_at(&init_mm, addr, pte, entry, size); + pfn += PFN_DOWN(size); + continue; + } +#endif + set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot)); + pfn++; + } while (pte += PFN_DOWN(size), addr += size, addr != end); + + arch_leave_lazy_mmu_mode(); + *mask |= PGTBL_PTE_MODIFIED; + return 0; +} + +static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int max_page_shift) { - struct vfree_deferred *p = container_of(w, struct vfree_deferred, wq); - struct llist_node *t, *llnode; + if (max_page_shift < PMD_SHIFT) + return 0; - llist_for_each_safe(llnode, t, llist_del_all(&p->list)) - __vunmap((void *)llnode, 1); + if (!arch_vmap_pmd_supported(prot)) + return 0; + + if ((end - addr) != PMD_SIZE) + return 0; + + if (!IS_ALIGNED(addr, PMD_SIZE)) + return 0; + + if (!IS_ALIGNED(phys_addr, PMD_SIZE)) + return 0; + + if (pmd_present(*pmd) && !pmd_free_pte_page(pmd, addr)) + return 0; + + return pmd_set_huge(pmd, phys_addr, prot); } -/*** Page table manipulation functions ***/ +static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int max_page_shift, pgtbl_mod_mask *mask) +{ + pmd_t *pmd; + unsigned long next; + int err = 0; + + pmd = pmd_alloc_track(&init_mm, pud, addr, mask); + if (!pmd) + return -ENOMEM; + do { + next = pmd_addr_end(addr, end); + + if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot, + max_page_shift)) { + *mask |= PGTBL_PMD_MODIFIED; + continue; + } + + err = vmap_pte_range(pmd, addr, next, phys_addr, prot, max_page_shift, mask); + if (err) + break; + } while (pmd++, phys_addr += (next - addr), addr = next, addr != end); + return err; +} + +static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int max_page_shift) +{ + if (max_page_shift < PUD_SHIFT) + return 0; + + if (!arch_vmap_pud_supported(prot)) + return 0; + + if ((end - addr) != PUD_SIZE) + return 0; + + if (!IS_ALIGNED(addr, PUD_SIZE)) + return 0; + + if (!IS_ALIGNED(phys_addr, PUD_SIZE)) + return 0; + + if (pud_present(*pud) && !pud_free_pmd_page(pud, addr)) + return 0; + + return pud_set_huge(pud, phys_addr, prot); +} + +static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int max_page_shift, pgtbl_mod_mask *mask) +{ + pud_t *pud; + unsigned long next; + int err = 0; + + pud = pud_alloc_track(&init_mm, p4d, addr, mask); + if (!pud) + return -ENOMEM; + do { + next = pud_addr_end(addr, end); + + if (vmap_try_huge_pud(pud, addr, next, phys_addr, prot, + max_page_shift)) { + *mask |= PGTBL_PUD_MODIFIED; + continue; + } + + err = vmap_pmd_range(pud, addr, next, phys_addr, prot, max_page_shift, mask); + if (err) + break; + } while (pud++, phys_addr += (next - addr), addr = next, addr != end); + return err; +} + +static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int max_page_shift) +{ + if (max_page_shift < P4D_SHIFT) + return 0; + + if (!arch_vmap_p4d_supported(prot)) + return 0; + + if ((end - addr) != P4D_SIZE) + return 0; + + if (!IS_ALIGNED(addr, P4D_SIZE)) + return 0; + + if (!IS_ALIGNED(phys_addr, P4D_SIZE)) + return 0; + + if (p4d_present(*p4d) && !p4d_free_pud_page(p4d, addr)) + return 0; + + return p4d_set_huge(p4d, phys_addr, prot); +} + +static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int max_page_shift, pgtbl_mod_mask *mask) +{ + p4d_t *p4d; + unsigned long next; + int err = 0; + + p4d = p4d_alloc_track(&init_mm, pgd, addr, mask); + if (!p4d) + return -ENOMEM; + do { + next = p4d_addr_end(addr, end); + + if (vmap_try_huge_p4d(p4d, addr, next, phys_addr, prot, + max_page_shift)) { + *mask |= PGTBL_P4D_MODIFIED; + continue; + } + + err = vmap_pud_range(p4d, addr, next, phys_addr, prot, max_page_shift, mask); + if (err) + break; + } while (p4d++, phys_addr += (next - addr), addr = next, addr != end); + return err; +} + +static int vmap_range_noflush(unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int max_page_shift) +{ + pgd_t *pgd; + unsigned long start; + unsigned long next; + int err; + pgtbl_mod_mask mask = 0; + + might_sleep(); + BUG_ON(addr >= end); + + start = addr; + pgd = pgd_offset_k(addr); + do { + next = pgd_addr_end(addr, end); + err = vmap_p4d_range(pgd, addr, next, phys_addr, prot, + max_page_shift, &mask); + if (err) + break; + } while (pgd++, phys_addr += (next - addr), addr = next, addr != end); + + if (mask & ARCH_PAGE_TABLE_SYNC_MASK) + arch_sync_kernel_mappings(start, end); + + return err; +} + +int vmap_page_range(unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot) +{ + int err; + + err = vmap_range_noflush(addr, end, phys_addr, pgprot_nx(prot), + ioremap_max_page_shift); + flush_cache_vmap(addr, end); + if (!err) + err = kmsan_ioremap_page_range(addr, end, phys_addr, prot, + ioremap_max_page_shift); + return err; +} + +int ioremap_page_range(unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot) +{ + struct vm_struct *area; + + area = find_vm_area((void *)addr); + if (!area || !(area->flags & VM_IOREMAP)) { + WARN_ONCE(1, "vm_area at addr %lx is not marked as VM_IOREMAP\n", addr); + return -EINVAL; + } + if (addr != (unsigned long)area->addr || + (void *)end != area->addr + get_vm_area_size(area)) { + WARN_ONCE(1, "ioremap request [%lx,%lx) doesn't match vm_area [%lx, %lx)\n", + addr, end, (long)area->addr, + (long)area->addr + get_vm_area_size(area)); + return -ERANGE; + } + return vmap_page_range(addr, end, phys_addr, prot); +} static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pgtbl_mod_mask *mask) { pte_t *pte; + pte_t ptent; + unsigned long size = PAGE_SIZE; pte = pte_offset_kernel(pmd, addr); + arch_enter_lazy_mmu_mode(); + do { - pte_t ptent = ptep_get_and_clear(&init_mm, addr, pte); +#ifdef CONFIG_HUGETLB_PAGE + size = arch_vmap_pte_range_unmap_size(addr, pte); + if (size != PAGE_SIZE) { + if (WARN_ON(!IS_ALIGNED(addr, size))) { + addr = ALIGN_DOWN(addr, size); + pte = PTR_ALIGN_DOWN(pte, sizeof(*pte) * (size >> PAGE_SHIFT)); + } + ptent = huge_ptep_get_and_clear(&init_mm, addr, pte, size); + if (WARN_ON(end - addr < size)) + size = end - addr; + } else +#endif + ptent = ptep_get_and_clear(&init_mm, addr, pte); WARN_ON(!pte_none(ptent) && !pte_present(ptent)); - } while (pte++, addr += PAGE_SIZE, addr != end); + } while (pte += (size >> PAGE_SHIFT), addr += size, addr != end); + + arch_leave_lazy_mmu_mode(); *mask |= PGTBL_PTE_MODIFIED; } @@ -97,11 +404,15 @@ static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, if (cleared || pmd_bad(*pmd)) *mask |= PGTBL_PMD_MODIFIED; - if (cleared) + if (cleared) { + WARN_ON(next - addr < PMD_SIZE); continue; + } if (pmd_none_or_clear_bad(pmd)) continue; vunmap_pte_range(pmd, addr, next, mask); + + cond_resched(); } while (pmd++, addr = next, addr != end); } @@ -120,8 +431,10 @@ static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, if (cleared || pud_bad(*pud)) *mask |= PGTBL_PUD_MODIFIED; - if (cleared) + if (cleared) { + WARN_ON(next - addr < PUD_SIZE); continue; + } if (pud_none_or_clear_bad(pud)) continue; vunmap_pmd_range(pud, addr, next, mask); @@ -133,47 +446,41 @@ static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, { p4d_t *p4d; unsigned long next; - int cleared; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); - cleared = p4d_clear_huge(p4d); - if (cleared || p4d_bad(*p4d)) + p4d_clear_huge(p4d); + if (p4d_bad(*p4d)) *mask |= PGTBL_P4D_MODIFIED; - if (cleared) - continue; if (p4d_none_or_clear_bad(p4d)) continue; vunmap_pud_range(p4d, addr, next, mask); } while (p4d++, addr = next, addr != end); } -/** - * unmap_kernel_range_noflush - unmap kernel VM area - * @start: start of the VM area to unmap - * @size: size of the VM area to unmap +/* + * vunmap_range_noflush is similar to vunmap_range, but does not + * flush caches or TLBs. * - * Unmap PFN_UP(@size) pages at @addr. The VM area @addr and @size specify - * should have been allocated using get_vm_area() and its friends. + * The caller is responsible for calling flush_cache_vmap() before calling + * this function, and flush_tlb_kernel_range after it has returned + * successfully (and before the addresses are expected to cause a page fault + * or be re-mapped for something else, if TLB flushes are being delayed or + * coalesced). * - * NOTE: - * This function does NOT do any cache flushing. The caller is responsible - * for calling flush_cache_vunmap() on to-be-mapped areas before calling this - * function and flush_tlb_kernel_range() after. + * This is an internal function only. Do not use outside mm/. */ -void unmap_kernel_range_noflush(unsigned long start, unsigned long size) +void __vunmap_range_noflush(unsigned long start, unsigned long end) { - unsigned long end = start + size; unsigned long next; pgd_t *pgd; unsigned long addr = start; pgtbl_mod_mask mask = 0; BUG_ON(addr >= end); - start = addr; pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); @@ -188,10 +495,33 @@ void unmap_kernel_range_noflush(unsigned long start, unsigned long size) arch_sync_kernel_mappings(start, end); } -static int vmap_pte_range(pmd_t *pmd, unsigned long addr, +void vunmap_range_noflush(unsigned long start, unsigned long end) +{ + kmsan_vunmap_range_noflush(start, end); + __vunmap_range_noflush(start, end); +} + +/** + * vunmap_range - unmap kernel virtual addresses + * @addr: start of the VM area to unmap + * @end: end of the VM area to unmap (non-inclusive) + * + * Clears any present PTEs in the virtual address range, flushes TLBs and + * caches. Any subsequent access to the address before it has been re-mapped + * is a kernel bug. + */ +void vunmap_range(unsigned long addr, unsigned long end) +{ + flush_cache_vunmap(addr, end); + vunmap_range_noflush(addr, end); + flush_tlb_kernel_range(addr, end); +} + +static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { + int err = 0; pte_t *pte; /* @@ -202,21 +532,36 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, pte = pte_alloc_kernel_track(pmd, addr, mask); if (!pte) return -ENOMEM; + + arch_enter_lazy_mmu_mode(); + do { struct page *page = pages[*nr]; - if (WARN_ON(!pte_none(*pte))) - return -EBUSY; - if (WARN_ON(!page)) - return -ENOMEM; + if (WARN_ON(!pte_none(ptep_get(pte)))) { + err = -EBUSY; + break; + } + if (WARN_ON(!page)) { + err = -ENOMEM; + break; + } + if (WARN_ON(!pfn_valid(page_to_pfn(page)))) { + err = -EINVAL; + break; + } + set_pte_at(&init_mm, addr, pte, mk_pte(page, prot)); (*nr)++; } while (pte++, addr += PAGE_SIZE, addr != end); + + arch_leave_lazy_mmu_mode(); *mask |= PGTBL_PTE_MODIFIED; - return 0; + + return err; } -static int vmap_pmd_range(pud_t *pud, unsigned long addr, +static int vmap_pages_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { @@ -228,13 +573,13 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr, return -ENOMEM; do { next = pmd_addr_end(addr, end); - if (vmap_pte_range(pmd, addr, next, prot, pages, nr, mask)) + if (vmap_pages_pte_range(pmd, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (pmd++, addr = next, addr != end); return 0; } -static int vmap_pud_range(p4d_t *p4d, unsigned long addr, +static int vmap_pages_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { @@ -246,13 +591,13 @@ static int vmap_pud_range(p4d_t *p4d, unsigned long addr, return -ENOMEM; do { next = pud_addr_end(addr, end); - if (vmap_pmd_range(pud, addr, next, prot, pages, nr, mask)) + if (vmap_pages_pmd_range(pud, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (pud++, addr = next, addr != end); return 0; } -static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, +static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, int *nr, pgtbl_mod_mask *mask) { @@ -264,37 +609,18 @@ static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, return -ENOMEM; do { next = p4d_addr_end(addr, end); - if (vmap_pud_range(p4d, addr, next, prot, pages, nr, mask)) + if (vmap_pages_pud_range(p4d, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (p4d++, addr = next, addr != end); return 0; } -/** - * map_kernel_range_noflush - map kernel VM area with the specified pages - * @addr: start of the VM area to map - * @size: size of the VM area to map - * @prot: page protection flags to use - * @pages: pages to map - * - * Map PFN_UP(@size) pages at @addr. The VM area @addr and @size specify should - * have been allocated using get_vm_area() and its friends. - * - * NOTE: - * This function does NOT do any cache flushing. The caller is responsible for - * calling flush_cache_vmap() on to-be-mapped areas before calling this - * function. - * - * RETURNS: - * 0 on success, -errno on failure. - */ -int map_kernel_range_noflush(unsigned long addr, unsigned long size, - pgprot_t prot, struct page **pages) +static int vmap_small_pages_range_noflush(unsigned long addr, unsigned long end, + pgprot_t prot, struct page **pages) { unsigned long start = addr; - unsigned long end = addr + size; - unsigned long next; pgd_t *pgd; + unsigned long next; int err = 0; int nr = 0; pgtbl_mod_mask mask = 0; @@ -305,25 +631,143 @@ int map_kernel_range_noflush(unsigned long addr, unsigned long size, next = pgd_addr_end(addr, end); if (pgd_bad(*pgd)) mask |= PGTBL_PGD_MODIFIED; - err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr, &mask); + err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr, &mask); if (err) - return err; + break; } while (pgd++, addr = next, addr != end); if (mask & ARCH_PAGE_TABLE_SYNC_MASK) arch_sync_kernel_mappings(start, end); + return err; +} + +/* + * vmap_pages_range_noflush is similar to vmap_pages_range, but does not + * flush caches. + * + * The caller is responsible for calling flush_cache_vmap() after this + * function returns successfully and before the addresses are accessed. + * + * This is an internal function only. Do not use outside mm/. + */ +int __vmap_pages_range_noflush(unsigned long addr, unsigned long end, + pgprot_t prot, struct page **pages, unsigned int page_shift) +{ + unsigned int i, nr = (end - addr) >> PAGE_SHIFT; + + WARN_ON(page_shift < PAGE_SHIFT); + + if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC) || + page_shift == PAGE_SHIFT) + return vmap_small_pages_range_noflush(addr, end, prot, pages); + + for (i = 0; i < nr; i += 1U << (page_shift - PAGE_SHIFT)) { + int err; + + err = vmap_range_noflush(addr, addr + (1UL << page_shift), + page_to_phys(pages[i]), prot, + page_shift); + if (err) + return err; + + addr += 1UL << page_shift; + } + return 0; } -int map_kernel_range(unsigned long start, unsigned long size, pgprot_t prot, - struct page **pages) +int vmap_pages_range_noflush(unsigned long addr, unsigned long end, + pgprot_t prot, struct page **pages, unsigned int page_shift, + gfp_t gfp_mask) { - int ret; + int ret = kmsan_vmap_pages_range_noflush(addr, end, prot, pages, + page_shift, gfp_mask); - ret = map_kernel_range_noflush(start, size, prot, pages); - flush_cache_vmap(start, start + size); - return ret; + if (ret) + return ret; + return __vmap_pages_range_noflush(addr, end, prot, pages, page_shift); +} + +static int __vmap_pages_range(unsigned long addr, unsigned long end, + pgprot_t prot, struct page **pages, unsigned int page_shift, + gfp_t gfp_mask) +{ + int err; + + err = vmap_pages_range_noflush(addr, end, prot, pages, page_shift, gfp_mask); + flush_cache_vmap(addr, end); + return err; +} + +/** + * vmap_pages_range - map pages to a kernel virtual address + * @addr: start of the VM area to map + * @end: end of the VM area to map (non-inclusive) + * @prot: page protection flags to use + * @pages: pages to map (always PAGE_SIZE pages) + * @page_shift: maximum shift that the pages may be mapped with, @pages must + * be aligned and contiguous up to at least this shift. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +int vmap_pages_range(unsigned long addr, unsigned long end, + pgprot_t prot, struct page **pages, unsigned int page_shift) +{ + return __vmap_pages_range(addr, end, prot, pages, page_shift, GFP_KERNEL); +} + +static int check_sparse_vm_area(struct vm_struct *area, unsigned long start, + unsigned long end) +{ + might_sleep(); + if (WARN_ON_ONCE(area->flags & VM_FLUSH_RESET_PERMS)) + return -EINVAL; + if (WARN_ON_ONCE(area->flags & VM_NO_GUARD)) + return -EINVAL; + if (WARN_ON_ONCE(!(area->flags & VM_SPARSE))) + return -EINVAL; + if ((end - start) >> PAGE_SHIFT > totalram_pages()) + return -E2BIG; + if (start < (unsigned long)area->addr || + (void *)end > area->addr + get_vm_area_size(area)) + return -ERANGE; + return 0; +} + +/** + * vm_area_map_pages - map pages inside given sparse vm_area + * @area: vm_area + * @start: start address inside vm_area + * @end: end address inside vm_area + * @pages: pages to map (always PAGE_SIZE pages) + */ +int vm_area_map_pages(struct vm_struct *area, unsigned long start, + unsigned long end, struct page **pages) +{ + int err; + + err = check_sparse_vm_area(area, start, end); + if (err) + return err; + + return vmap_pages_range(start, end, PAGE_KERNEL, pages, PAGE_SHIFT); +} + +/** + * vm_area_unmap_pages - unmap pages inside given sparse vm_area + * @area: vm_area + * @start: start address inside vm_area + * @end: end address inside vm_area + */ +void vm_area_unmap_pages(struct vm_struct *area, unsigned long start, + unsigned long end) +{ + if (check_sparse_vm_area(area, start, end)) + return; + + vunmap_range(start, end); } int is_vmalloc_or_module_addr(const void *x) @@ -333,16 +777,19 @@ int is_vmalloc_or_module_addr(const void *x) * and fall back on vmalloc() if that fails. Others * just put it in the vmalloc space. */ -#if defined(CONFIG_MODULES) && defined(MODULES_VADDR) - unsigned long addr = (unsigned long)x; +#if defined(CONFIG_EXECMEM) && defined(MODULES_VADDR) + unsigned long addr = (unsigned long)kasan_reset_tag(x); if (addr >= MODULES_VADDR && addr < MODULES_END) return 1; #endif return is_vmalloc_addr(x); } +EXPORT_SYMBOL_GPL(is_vmalloc_or_module_addr); /* - * Walk a vmap address to the struct page it maps. + * Walk a vmap address to the struct page it maps. Huge vmap mappings will + * return the tail page that corresponds to the base page address, which + * matches small vmap mappings. */ struct page *vmalloc_to_page(const void *vmalloc_addr) { @@ -362,32 +809,40 @@ struct page *vmalloc_to_page(const void *vmalloc_addr) if (pgd_none(*pgd)) return NULL; + if (WARN_ON_ONCE(pgd_leaf(*pgd))) + return NULL; /* XXX: no allowance for huge pgd */ + if (WARN_ON_ONCE(pgd_bad(*pgd))) + return NULL; + p4d = p4d_offset(pgd, addr); if (p4d_none(*p4d)) return NULL; - pud = pud_offset(p4d, addr); + if (p4d_leaf(*p4d)) + return p4d_page(*p4d) + ((addr & ~P4D_MASK) >> PAGE_SHIFT); + if (WARN_ON_ONCE(p4d_bad(*p4d))) + return NULL; - /* - * Don't dereference bad PUD or PMD (below) entries. This will also - * identify huge mappings, which we may encounter on architectures - * that define CONFIG_HAVE_ARCH_HUGE_VMAP=y. Such regions will be - * identified as vmalloc addresses by is_vmalloc_addr(), but are - * not [unambiguously] associated with a struct page, so there is - * no correct value to return for them. - */ - WARN_ON_ONCE(pud_bad(*pud)); - if (pud_none(*pud) || pud_bad(*pud)) + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) + return NULL; + if (pud_leaf(*pud)) + return pud_page(*pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); + if (WARN_ON_ONCE(pud_bad(*pud))) return NULL; + pmd = pmd_offset(pud, addr); - WARN_ON_ONCE(pmd_bad(*pmd)); - if (pmd_none(*pmd) || pmd_bad(*pmd)) + if (pmd_none(*pmd)) + return NULL; + if (pmd_leaf(*pmd)) + return pmd_page(*pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); + if (WARN_ON_ONCE(pmd_bad(*pmd))) return NULL; - ptep = pte_offset_map(pmd, addr); - pte = *ptep; + ptep = pte_offset_kernel(pmd, addr); + pte = ptep_get(ptep); if (pte_present(pte)) page = pte_page(pte); - pte_unmap(ptep); + return page; } EXPORT_SYMBOL(vmalloc_to_page); @@ -408,12 +863,7 @@ EXPORT_SYMBOL(vmalloc_to_pfn); #define DEBUG_AUGMENT_LOWEST_MATCH_CHECK 0 -static DEFINE_SPINLOCK(vmap_area_lock); static DEFINE_SPINLOCK(free_vmap_area_lock); -/* Export for kexec only */ -LIST_HEAD(vmap_area_list); -static LLIST_HEAD(vmap_purge_list); -static struct rb_root vmap_area_root = RB_ROOT; static bool vmap_initialized __read_mostly; /* @@ -449,6 +899,147 @@ static struct rb_root free_vmap_area_root = RB_ROOT; */ static DEFINE_PER_CPU(struct vmap_area *, ne_fit_preload_node); +/* + * This structure defines a single, solid model where a list and + * rb-tree are part of one entity protected by the lock. Nodes are + * sorted in ascending order, thus for O(1) access to left/right + * neighbors a list is used as well as for sequential traversal. + */ +struct rb_list { + struct rb_root root; + struct list_head head; + spinlock_t lock; +}; + +/* + * A fast size storage contains VAs up to 1M size. A pool consists + * of linked between each other ready to go VAs of certain sizes. + * An index in the pool-array corresponds to number of pages + 1. + */ +#define MAX_VA_SIZE_PAGES 256 + +struct vmap_pool { + struct list_head head; + unsigned long len; +}; + +/* + * An effective vmap-node logic. Users make use of nodes instead + * of a global heap. It allows to balance an access and mitigate + * contention. + */ +static struct vmap_node { + /* Simple size segregated storage. */ + struct vmap_pool pool[MAX_VA_SIZE_PAGES]; + spinlock_t pool_lock; + bool skip_populate; + + /* Bookkeeping data of this node. */ + struct rb_list busy; + struct rb_list lazy; + + /* + * Ready-to-free areas. + */ + struct list_head purge_list; + struct work_struct purge_work; + unsigned long nr_purged; +} single; + +/* + * Initial setup consists of one single node, i.e. a balancing + * is fully disabled. Later on, after vmap is initialized these + * parameters are updated based on a system capacity. + */ +static struct vmap_node *vmap_nodes = &single; +static __read_mostly unsigned int nr_vmap_nodes = 1; +static __read_mostly unsigned int vmap_zone_size = 1; + +/* A simple iterator over all vmap-nodes. */ +#define for_each_vmap_node(vn) \ + for ((vn) = &vmap_nodes[0]; \ + (vn) < &vmap_nodes[nr_vmap_nodes]; (vn)++) + +static inline unsigned int +addr_to_node_id(unsigned long addr) +{ + return (addr / vmap_zone_size) % nr_vmap_nodes; +} + +static inline struct vmap_node * +addr_to_node(unsigned long addr) +{ + return &vmap_nodes[addr_to_node_id(addr)]; +} + +static inline struct vmap_node * +id_to_node(unsigned int id) +{ + return &vmap_nodes[id % nr_vmap_nodes]; +} + +static inline unsigned int +node_to_id(struct vmap_node *node) +{ + /* Pointer arithmetic. */ + unsigned int id = node - vmap_nodes; + + if (likely(id < nr_vmap_nodes)) + return id; + + WARN_ONCE(1, "An address 0x%p is out-of-bounds.\n", node); + return 0; +} + +/* + * We use the value 0 to represent "no node", that is why + * an encoded value will be the node-id incremented by 1. + * It is always greater then 0. A valid node_id which can + * be encoded is [0:nr_vmap_nodes - 1]. If a passed node_id + * is not valid 0 is returned. + */ +static unsigned int +encode_vn_id(unsigned int node_id) +{ + /* Can store U8_MAX [0:254] nodes. */ + if (node_id < nr_vmap_nodes) + return (node_id + 1) << BITS_PER_BYTE; + + /* Warn and no node encoded. */ + WARN_ONCE(1, "Encode wrong node id (%u)\n", node_id); + return 0; +} + +/* + * Returns an encoded node-id, the valid range is within + * [0:nr_vmap_nodes-1] values. Otherwise nr_vmap_nodes is + * returned if extracted data is wrong. + */ +static unsigned int +decode_vn_id(unsigned int val) +{ + unsigned int node_id = (val >> BITS_PER_BYTE) - 1; + + /* Can store U8_MAX [0:254] nodes. */ + if (node_id < nr_vmap_nodes) + return node_id; + + /* If it was _not_ zero, warn. */ + WARN_ONCE(node_id != UINT_MAX, + "Decode wrong node id (%d)\n", node_id); + + return nr_vmap_nodes; +} + +static bool +is_vn_id_valid(unsigned int node_id) +{ + if (node_id < nr_vmap_nodes) + return true; + + return false; +} + static __always_inline unsigned long va_size(struct vmap_area *va) { @@ -464,34 +1055,27 @@ get_subtree_max_size(struct rb_node *node) return va ? va->subtree_max_size : 0; } -/* - * Gets called when remove the node and rotate. - */ -static __always_inline unsigned long -compute_subtree_max_size(struct vmap_area *va) -{ - return max3(va_size(va), - get_subtree_max_size(va->rb_node.rb_left), - get_subtree_max_size(va->rb_node.rb_right)); -} - RB_DECLARE_CALLBACKS_MAX(static, free_vmap_area_rb_augment_cb, struct vmap_area, rb_node, unsigned long, subtree_max_size, va_size) -static void purge_vmap_area_lazy(void); +static void reclaim_and_purge_vmap_areas(void); static BLOCKING_NOTIFIER_HEAD(vmap_notify_list); -static unsigned long lazy_max_pages(void); +static void drain_vmap_area_work(struct work_struct *work); +static DECLARE_WORK(drain_vmap_work, drain_vmap_area_work); -static atomic_long_t nr_vmalloc_pages; +static __cacheline_aligned_in_smp atomic_long_t nr_vmalloc_pages; +static __cacheline_aligned_in_smp atomic_long_t vmap_lazy_nr; unsigned long vmalloc_nr_pages(void) { return atomic_long_read(&nr_vmalloc_pages); } -static struct vmap_area *__find_vmap_area(unsigned long addr) +static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root) { - struct rb_node *n = vmap_area_root.rb_node; + struct rb_node *n = root->rb_node; + + addr = (unsigned long)kasan_reset_tag((void *)addr); while (n) { struct vmap_area *va; @@ -508,9 +1092,86 @@ static struct vmap_area *__find_vmap_area(unsigned long addr) return NULL; } +/* Look up the first VA which satisfies addr < va_end, NULL if none. */ +static struct vmap_area * +__find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root) +{ + struct vmap_area *va = NULL; + struct rb_node *n = root->rb_node; + + addr = (unsigned long)kasan_reset_tag((void *)addr); + + while (n) { + struct vmap_area *tmp; + + tmp = rb_entry(n, struct vmap_area, rb_node); + if (tmp->va_end > addr) { + va = tmp; + if (tmp->va_start <= addr) + break; + + n = n->rb_left; + } else + n = n->rb_right; + } + + return va; +} + +/* + * Returns a node where a first VA, that satisfies addr < va_end, resides. + * If success, a node is locked. A user is responsible to unlock it when a + * VA is no longer needed to be accessed. + * + * Returns NULL if nothing found. + */ +static struct vmap_node * +find_vmap_area_exceed_addr_lock(unsigned long addr, struct vmap_area **va) +{ + unsigned long va_start_lowest; + struct vmap_node *vn; + +repeat: + va_start_lowest = 0; + + for_each_vmap_node(vn) { + spin_lock(&vn->busy.lock); + *va = __find_vmap_area_exceed_addr(addr, &vn->busy.root); + + if (*va) + if (!va_start_lowest || (*va)->va_start < va_start_lowest) + va_start_lowest = (*va)->va_start; + spin_unlock(&vn->busy.lock); + } + + /* + * Check if found VA exists, it might have gone away. In this case we + * repeat the search because a VA has been removed concurrently and we + * need to proceed to the next one, which is a rare case. + */ + if (va_start_lowest) { + vn = addr_to_node(va_start_lowest); + + spin_lock(&vn->busy.lock); + *va = __find_vmap_area(va_start_lowest, &vn->busy.root); + + if (*va) + return vn; + + spin_unlock(&vn->busy.lock); + goto repeat; + } + + return NULL; +} + /* * This function returns back addresses of parent node * and its left or right link for further processing. + * + * Otherwise NULL is returned. In that case all further + * steps regarding inserting of conflicting overlap range + * have to be declined and actually considered as a bug. */ static __always_inline struct rb_node ** find_va_links(struct vmap_area *va, @@ -543,14 +1204,16 @@ find_va_links(struct vmap_area *va, * Trigger the BUG() if there are sides(left/right) * or full overlaps. */ - if (va->va_start < tmp_va->va_end && - va->va_end <= tmp_va->va_start) + if (va->va_end <= tmp_va->va_start) link = &(*link)->rb_left; - else if (va->va_end > tmp_va->va_start && - va->va_start >= tmp_va->va_end) + else if (va->va_start >= tmp_va->va_end) link = &(*link)->rb_right; - else - BUG(); + else { + WARN(1, "vmalloc bug: 0x%lx-0x%lx overlaps with 0x%lx-0x%lx\n", + va->va_start, va->va_end, tmp_va->va_start, tmp_va->va_end); + + return NULL; + } } while (*link); *parent = &tmp_va->rb_node; @@ -576,8 +1239,9 @@ get_va_next_sibling(struct rb_node *parent, struct rb_node **link) } static __always_inline void -link_va(struct vmap_area *va, struct rb_root *root, - struct rb_node *parent, struct rb_node **link, struct list_head *head) +__link_va(struct vmap_area *va, struct rb_root *root, + struct rb_node *parent, struct rb_node **link, + struct list_head *head, bool augment) { /* * VA is still not in the list, but we can @@ -591,12 +1255,12 @@ link_va(struct vmap_area *va, struct rb_root *root, /* Insert to the rb-tree */ rb_link_node(&va->rb_node, parent, link); - if (root == &free_vmap_area_root) { + if (augment) { /* * Some explanation here. Just perform simple insertion * to the tree. We do not set va->subtree_max_size to * its current size before calling rb_insert_augmented(). - * It is because of we populate the tree from the bottom + * It is because we populate the tree from the bottom * to parent levels when the node _is_ in the tree. * * Therefore we set subtree_max_size to zero after insertion, @@ -615,60 +1279,73 @@ link_va(struct vmap_area *va, struct rb_root *root, } static __always_inline void -unlink_va(struct vmap_area *va, struct rb_root *root) +link_va(struct vmap_area *va, struct rb_root *root, + struct rb_node *parent, struct rb_node **link, + struct list_head *head) +{ + __link_va(va, root, parent, link, head, false); +} + +static __always_inline void +link_va_augment(struct vmap_area *va, struct rb_root *root, + struct rb_node *parent, struct rb_node **link, + struct list_head *head) +{ + __link_va(va, root, parent, link, head, true); +} + +static __always_inline void +__unlink_va(struct vmap_area *va, struct rb_root *root, bool augment) { if (WARN_ON(RB_EMPTY_NODE(&va->rb_node))) return; - if (root == &free_vmap_area_root) + if (augment) rb_erase_augmented(&va->rb_node, root, &free_vmap_area_rb_augment_cb); else rb_erase(&va->rb_node, root); - list_del(&va->list); + list_del_init(&va->list); RB_CLEAR_NODE(&va->rb_node); } -#if DEBUG_AUGMENT_PROPAGATE_CHECK -static void -augment_tree_propagate_check(struct rb_node *n) +static __always_inline void +unlink_va(struct vmap_area *va, struct rb_root *root) { - struct vmap_area *va; - struct rb_node *node; - unsigned long size; - bool found = false; - - if (n == NULL) - return; - - va = rb_entry(n, struct vmap_area, rb_node); - size = va->subtree_max_size; - node = n; + __unlink_va(va, root, false); +} - while (node) { - va = rb_entry(node, struct vmap_area, rb_node); +static __always_inline void +unlink_va_augment(struct vmap_area *va, struct rb_root *root) +{ + __unlink_va(va, root, true); +} - if (get_subtree_max_size(node->rb_left) == size) { - node = node->rb_left; - } else { - if (va_size(va) == size) { - found = true; - break; - } +#if DEBUG_AUGMENT_PROPAGATE_CHECK +/* + * Gets called when remove the node and rotate. + */ +static __always_inline unsigned long +compute_subtree_max_size(struct vmap_area *va) +{ + return max3(va_size(va), + get_subtree_max_size(va->rb_node.rb_left), + get_subtree_max_size(va->rb_node.rb_right)); +} - node = node->rb_right; - } - } +static void +augment_tree_propagate_check(void) +{ + struct vmap_area *va; + unsigned long computed_size; - if (!found) { - va = rb_entry(n, struct vmap_area, rb_node); - pr_emerg("tree is corrupted: %lu, %lu\n", - va_size(va), va->subtree_max_size); + list_for_each_entry(va, &free_vmap_area_list, list) { + computed_size = compute_subtree_max_size(va); + if (computed_size != va->subtree_max_size) + pr_emerg("tree is corrupted: %lu, %lu\n", + va_size(va), va->subtree_max_size); } - - augment_tree_propagate_check(n->rb_left); - augment_tree_propagate_check(n->rb_right); } #endif @@ -702,28 +1379,15 @@ augment_tree_propagate_check(struct rb_node *n) static __always_inline void augment_tree_propagate_from(struct vmap_area *va) { - struct rb_node *node = &va->rb_node; - unsigned long new_va_sub_max_size; - - while (node) { - va = rb_entry(node, struct vmap_area, rb_node); - new_va_sub_max_size = compute_subtree_max_size(va); - - /* - * If the newly calculated maximum available size of the - * subtree is equal to the current one, then it means that - * the tree is propagated correctly. So we have to stop at - * this point to save cycles. - */ - if (va->subtree_max_size == new_va_sub_max_size) - break; - - va->subtree_max_size = new_va_sub_max_size; - node = rb_parent(&va->rb_node); - } + /* + * Populate the tree from bottom towards the root until + * the calculated maximum available size of checked node + * is equal to its current one. + */ + free_vmap_area_rb_augment_cb_propagate(&va->rb_node, NULL); #if DEBUG_AUGMENT_PROPAGATE_CHECK - augment_tree_propagate_check(free_vmap_area_root.rb_node); + augment_tree_propagate_check(); #endif } @@ -735,7 +1399,8 @@ insert_vmap_area(struct vmap_area *va, struct rb_node *parent; link = find_va_links(va, root, NULL, &parent); - link_va(va, root, parent, link, head); + if (link) + link_va(va, root, parent, link, head); } static void @@ -751,8 +1416,10 @@ insert_vmap_area_augment(struct vmap_area *va, else link = find_va_links(va, root, NULL, &parent); - link_va(va, root, parent, link, head); - augment_tree_propagate_from(va); + if (link) { + link_va_augment(va, root, parent, link, head); + augment_tree_propagate_from(va); + } } /* @@ -760,10 +1427,15 @@ insert_vmap_area_augment(struct vmap_area *va, * and next free blocks. If coalesce is not done a new * free area is inserted. If VA has been merged, it is * freed. + * + * Please note, it can return NULL in case of overlap + * ranges, followed by WARN() report. Despite it is a + * buggy behaviour, a system can be alive and keep + * ongoing. */ static __always_inline struct vmap_area * -merge_or_add_vmap_area(struct vmap_area *va, - struct rb_root *root, struct list_head *head) +__merge_or_add_vmap_area(struct vmap_area *va, + struct rb_root *root, struct list_head *head, bool augment) { struct vmap_area *sibling; struct list_head *next; @@ -776,6 +1448,8 @@ merge_or_add_vmap_area(struct vmap_area *va, * inserted, unless it is merged with its sibling/siblings. */ link = find_va_links(va, root, NULL, &parent); + if (!link) + return NULL; /* * Get next node of VA to check if merging can be done. @@ -796,9 +1470,6 @@ merge_or_add_vmap_area(struct vmap_area *va, if (sibling->va_start == va->va_end) { sibling->va_start = va->va_start; - /* Check and update the tree if needed. */ - augment_tree_propagate_from(sibling); - /* Free vmap_area object. */ kmem_cache_free(vmap_area_cachep, va); @@ -818,13 +1489,17 @@ merge_or_add_vmap_area(struct vmap_area *va, if (next->prev != head) { sibling = list_entry(next->prev, struct vmap_area, list); if (sibling->va_end == va->va_start) { - sibling->va_end = va->va_end; - - /* Check and update the tree if needed. */ - augment_tree_propagate_from(sibling); - + /* + * If both neighbors are coalesced, it is important + * to unlink the "next" node first, followed by merging + * with "previous" one. Otherwise the tree might not be + * fully populated if a sibling's augmented value is + * "normalized" because of rotation operations. + */ if (merged) - unlink_va(va, root); + __unlink_va(va, root, augment); + + sibling->va_end = va->va_end; /* Free vmap_area object. */ kmem_cache_free(vmap_area_cachep, va); @@ -836,10 +1511,26 @@ merge_or_add_vmap_area(struct vmap_area *va, } insert: - if (!merged) { - link_va(va, root, parent, link, head); + if (!merged) + __link_va(va, root, parent, link, head, augment); + + return va; +} + +static __always_inline struct vmap_area * +merge_or_add_vmap_area(struct vmap_area *va, + struct rb_root *root, struct list_head *head) +{ + return __merge_or_add_vmap_area(va, root, head, false); +} + +static __always_inline struct vmap_area * +merge_or_add_vmap_area_augment(struct vmap_area *va, + struct rb_root *root, struct list_head *head) +{ + va = __merge_or_add_vmap_area(va, root, head, true); + if (va) augment_tree_propagate_from(va); - } return va; } @@ -866,21 +1557,23 @@ is_within_this_va(struct vmap_area *va, unsigned long size, /* * Find the first free block(lowest start address) in the tree, * that will accomplish the request corresponding to passing - * parameters. + * parameters. Please note, with an alignment bigger than PAGE_SIZE, + * a search length is adjusted to account for worst case alignment + * overhead. */ static __always_inline struct vmap_area * -find_vmap_lowest_match(unsigned long size, - unsigned long align, unsigned long vstart) +find_vmap_lowest_match(struct rb_root *root, unsigned long size, + unsigned long align, unsigned long vstart, bool adjust_search_size) { struct vmap_area *va; struct rb_node *node; unsigned long length; /* Start from the root. */ - node = free_vmap_area_root.rb_node; + node = root->rb_node; /* Adjust the search size for alignment overhead. */ - length = size + align - 1; + length = adjust_search_size ? size + align - 1 : size; while (node) { va = rb_entry(node, struct vmap_area, rb_node); @@ -905,7 +1598,8 @@ find_vmap_lowest_match(unsigned long size, /* * OK. We roll back and find the first right sub-tree, * that will satisfy the search criteria. It can happen - * only once due to "vstart" restriction. + * due to "vstart" restriction or an alignment overhead + * that is bigger then PAGE_SIZE. */ while ((node = rb_parent(node))) { va = rb_entry(node, struct vmap_area, rb_node); @@ -914,6 +1608,13 @@ find_vmap_lowest_match(unsigned long size, if (get_subtree_max_size(node->rb_right) >= length && vstart <= va->va_start) { + /* + * Shift the vstart forward. Please note, we update it with + * parent's start address adding "1" because we do not want + * to enter same sub-tree after it has already been checked + * and no suitable free block found there. + */ + vstart = va->va_start + 1; node = node->rb_right; break; } @@ -928,12 +1629,12 @@ find_vmap_lowest_match(unsigned long size, #include <linux/random.h> static struct vmap_area * -find_vmap_lowest_linear_match(unsigned long size, +find_vmap_lowest_linear_match(struct list_head *head, unsigned long size, unsigned long align, unsigned long vstart) { struct vmap_area *va; - list_for_each_entry(va, &free_vmap_area_list, list) { + list_for_each_entry(va, head, list) { if (!is_within_this_va(va, size, align, vstart)) continue; @@ -944,7 +1645,8 @@ find_vmap_lowest_linear_match(unsigned long size, } static void -find_vmap_lowest_match_check(unsigned long size) +find_vmap_lowest_match_check(struct rb_root *root, struct list_head *head, + unsigned long size, unsigned long align) { struct vmap_area *va_1, *va_2; unsigned long vstart; @@ -953,8 +1655,8 @@ find_vmap_lowest_match_check(unsigned long size) get_random_bytes(&rnd, sizeof(rnd)); vstart = VMALLOC_START + rnd; - va_1 = find_vmap_lowest_match(size, 1, vstart); - va_2 = find_vmap_lowest_linear_match(size, 1, vstart); + va_1 = find_vmap_lowest_match(root, size, align, vstart, false); + va_2 = find_vmap_lowest_linear_match(head, size, align, vstart); if (va_1 != va_2) pr_emerg("not lowest: t: 0x%p, l: 0x%p, v: 0x%lx\n", @@ -997,11 +1699,12 @@ classify_va_fit_type(struct vmap_area *va, } static __always_inline int -adjust_va_to_fit_type(struct vmap_area *va, - unsigned long nva_start_addr, unsigned long size, - enum fit_type type) +va_clip(struct rb_root *root, struct list_head *head, + struct vmap_area *va, unsigned long nva_start_addr, + unsigned long size) { struct vmap_area *lva = NULL; + enum fit_type type = classify_va_fit_type(va, nva_start_addr, size); if (type == FL_FIT_TYPE) { /* @@ -1011,7 +1714,7 @@ adjust_va_to_fit_type(struct vmap_area *va, * V NVA V * |---------------| */ - unlink_va(va, &free_vmap_area_root); + unlink_va_augment(va, root); kmem_cache_free(vmap_area_cachep, va); } else if (type == LE_FIT_TYPE) { /* @@ -1068,7 +1771,7 @@ adjust_va_to_fit_type(struct vmap_area *va, */ lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT); if (!lva) - return -1; + return -ENOMEM; } /* @@ -1082,37 +1785,28 @@ adjust_va_to_fit_type(struct vmap_area *va, */ va->va_start = nva_start_addr + size; } else { - return -1; + return -EINVAL; } if (type != FL_FIT_TYPE) { augment_tree_propagate_from(va); if (lva) /* type == NE_FIT_TYPE */ - insert_vmap_area_augment(lva, &va->rb_node, - &free_vmap_area_root, &free_vmap_area_list); + insert_vmap_area_augment(lva, &va->rb_node, root, head); } return 0; } -/* - * Returns a start address of the newly allocated area, if success. - * Otherwise a vend is returned that indicates failure. - */ -static __always_inline unsigned long -__alloc_vmap_area(unsigned long size, unsigned long align, - unsigned long vstart, unsigned long vend) +static unsigned long +va_alloc(struct vmap_area *va, + struct rb_root *root, struct list_head *head, + unsigned long size, unsigned long align, + unsigned long vstart, unsigned long vend) { unsigned long nva_start_addr; - struct vmap_area *va; - enum fit_type type; int ret; - va = find_vmap_lowest_match(size, align, vstart); - if (unlikely(!va)) - return vend; - if (va->va_start > vstart) nva_start_addr = ALIGN(va->va_start, align); else @@ -1120,20 +1814,50 @@ __alloc_vmap_area(unsigned long size, unsigned long align, /* Check the "vend" restriction. */ if (nva_start_addr + size > vend) - return vend; - - /* Classify what we have found. */ - type = classify_va_fit_type(va, nva_start_addr, size); - if (WARN_ON_ONCE(type == NOTHING_FIT)) - return vend; + return -ERANGE; /* Update the free vmap_area. */ - ret = adjust_va_to_fit_type(va, nva_start_addr, size, type); - if (ret) - return vend; + ret = va_clip(root, head, va, nva_start_addr, size); + if (WARN_ON_ONCE(ret)) + return ret; + + return nva_start_addr; +} + +/* + * Returns a start address of the newly allocated area, if success. + * Otherwise an error value is returned that indicates failure. + */ +static __always_inline unsigned long +__alloc_vmap_area(struct rb_root *root, struct list_head *head, + unsigned long size, unsigned long align, + unsigned long vstart, unsigned long vend) +{ + bool adjust_search_size = true; + unsigned long nva_start_addr; + struct vmap_area *va; + + /* + * Do not adjust when: + * a) align <= PAGE_SIZE, because it does not make any sense. + * All blocks(their start addresses) are at least PAGE_SIZE + * aligned anyway; + * b) a short range where a requested size corresponds to exactly + * specified [vstart:vend] interval and an alignment > PAGE_SIZE. + * With adjusted search length an allocation would not succeed. + */ + if (align <= PAGE_SIZE || (align > PAGE_SIZE && (vend - vstart) == size)) + adjust_search_size = false; + + va = find_vmap_lowest_match(root, size, align, vstart, adjust_search_size); + if (unlikely(!va)) + return -ENOENT; + + nva_start_addr = va_alloc(va, root, head, size, align, vstart, vend); #if DEBUG_AUGMENT_LOWEST_MATCH_CHECK - find_vmap_lowest_match_check(size); + if (!IS_ERR_VALUE(nva_start_addr)) + find_vmap_lowest_match_check(root, head, size, align); #endif return nva_start_addr; @@ -1144,110 +1868,260 @@ __alloc_vmap_area(unsigned long size, unsigned long align, */ static void free_vmap_area(struct vmap_area *va) { + struct vmap_node *vn = addr_to_node(va->va_start); + /* * Remove from the busy tree/list. */ - spin_lock(&vmap_area_lock); - unlink_va(va, &vmap_area_root); - spin_unlock(&vmap_area_lock); + spin_lock(&vn->busy.lock); + unlink_va(va, &vn->busy.root); + spin_unlock(&vn->busy.lock); /* * Insert/Merge it back to the free tree/list. */ spin_lock(&free_vmap_area_lock); - merge_or_add_vmap_area(va, &free_vmap_area_root, &free_vmap_area_list); + merge_or_add_vmap_area_augment(va, &free_vmap_area_root, &free_vmap_area_list); spin_unlock(&free_vmap_area_lock); } +static inline void +preload_this_cpu_lock(spinlock_t *lock, gfp_t gfp_mask, int node) +{ + struct vmap_area *va = NULL, *tmp; + + /* + * Preload this CPU with one extra vmap_area object. It is used + * when fit type of free area is NE_FIT_TYPE. It guarantees that + * a CPU that does an allocation is preloaded. + * + * We do it in non-atomic context, thus it allows us to use more + * permissive allocation masks to be more stable under low memory + * condition and high memory pressure. + */ + if (!this_cpu_read(ne_fit_preload_node)) + va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); + + spin_lock(lock); + + tmp = NULL; + if (va && !__this_cpu_try_cmpxchg(ne_fit_preload_node, &tmp, va)) + kmem_cache_free(vmap_area_cachep, va); +} + +static struct vmap_pool * +size_to_va_pool(struct vmap_node *vn, unsigned long size) +{ + unsigned int idx = (size - 1) / PAGE_SIZE; + + if (idx < MAX_VA_SIZE_PAGES) + return &vn->pool[idx]; + + return NULL; +} + +static bool +node_pool_add_va(struct vmap_node *n, struct vmap_area *va) +{ + struct vmap_pool *vp; + + vp = size_to_va_pool(n, va_size(va)); + if (!vp) + return false; + + spin_lock(&n->pool_lock); + list_add(&va->list, &vp->head); + WRITE_ONCE(vp->len, vp->len + 1); + spin_unlock(&n->pool_lock); + + return true; +} + +static struct vmap_area * +node_pool_del_va(struct vmap_node *vn, unsigned long size, + unsigned long align, unsigned long vstart, + unsigned long vend) +{ + struct vmap_area *va = NULL; + struct vmap_pool *vp; + int err = 0; + + vp = size_to_va_pool(vn, size); + if (!vp || list_empty(&vp->head)) + return NULL; + + spin_lock(&vn->pool_lock); + if (!list_empty(&vp->head)) { + va = list_first_entry(&vp->head, struct vmap_area, list); + + if (IS_ALIGNED(va->va_start, align)) { + /* + * Do some sanity check and emit a warning + * if one of below checks detects an error. + */ + err |= (va_size(va) != size); + err |= (va->va_start < vstart); + err |= (va->va_end > vend); + + if (!WARN_ON_ONCE(err)) { + list_del_init(&va->list); + WRITE_ONCE(vp->len, vp->len - 1); + } else { + va = NULL; + } + } else { + list_move_tail(&va->list, &vp->head); + va = NULL; + } + } + spin_unlock(&vn->pool_lock); + + return va; +} + +static struct vmap_area * +node_alloc(unsigned long size, unsigned long align, + unsigned long vstart, unsigned long vend, + unsigned long *addr, unsigned int *vn_id) +{ + struct vmap_area *va; + + *vn_id = 0; + *addr = -EINVAL; + + /* + * Fallback to a global heap if not vmalloc or there + * is only one node. + */ + if (vstart != VMALLOC_START || vend != VMALLOC_END || + nr_vmap_nodes == 1) + return NULL; + + *vn_id = raw_smp_processor_id() % nr_vmap_nodes; + va = node_pool_del_va(id_to_node(*vn_id), size, align, vstart, vend); + *vn_id = encode_vn_id(*vn_id); + + if (va) + *addr = va->va_start; + + return va; +} + +static inline void setup_vmalloc_vm(struct vm_struct *vm, + struct vmap_area *va, unsigned long flags, const void *caller) +{ + vm->flags = flags; + vm->addr = (void *)va->va_start; + vm->size = vm->requested_size = va_size(va); + vm->caller = caller; + va->vm = vm; +} + /* * Allocate a region of KVA of the specified size and alignment, within the - * vstart and vend. + * vstart and vend. If vm is passed in, the two will also be bound. */ static struct vmap_area *alloc_vmap_area(unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend, - int node, gfp_t gfp_mask) + int node, gfp_t gfp_mask, + unsigned long va_flags, struct vm_struct *vm) { - struct vmap_area *va, *pva; + struct vmap_node *vn; + struct vmap_area *va; + unsigned long freed; unsigned long addr; + unsigned int vn_id; + bool allow_block; int purged = 0; int ret; - BUG_ON(!size); - BUG_ON(offset_in_page(size)); - BUG_ON(!is_power_of_2(align)); + if (unlikely(!size || offset_in_page(size) || !is_power_of_2(align))) + return ERR_PTR(-EINVAL); if (unlikely(!vmap_initialized)) return ERR_PTR(-EBUSY); - might_sleep(); + /* Only reclaim behaviour flags are relevant. */ gfp_mask = gfp_mask & GFP_RECLAIM_MASK; + allow_block = gfpflags_allow_blocking(gfp_mask); + might_sleep_if(allow_block); - va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); - if (unlikely(!va)) - return ERR_PTR(-ENOMEM); - - /* - * Only scan the relevant parts containing pointers to other objects - * to avoid false negatives. - */ - kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask); - -retry: /* - * Preload this CPU with one extra vmap_area object. It is used - * when fit type of free area is NE_FIT_TYPE. Please note, it - * does not guarantee that an allocation occurs on a CPU that - * is preloaded, instead we minimize the case when it is not. - * It can happen because of cpu migration, because there is a - * race until the below spinlock is taken. + * If a VA is obtained from a global heap(if it fails here) + * it is anyway marked with this "vn_id" so it is returned + * to this pool's node later. Such way gives a possibility + * to populate pools based on users demand. * - * The preload is done in non-atomic context, thus it allows us - * to use more permissive allocation masks to be more stable under - * low memory condition and high memory pressure. In rare case, - * if not preloaded, GFP_NOWAIT is used. - * - * Set "pva" to NULL here, because of "retry" path. + * On success a ready to go VA is returned. */ - pva = NULL; + va = node_alloc(size, align, vstart, vend, &addr, &vn_id); + if (!va) { + va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); + if (unlikely(!va)) + return ERR_PTR(-ENOMEM); - if (!this_cpu_read(ne_fit_preload_node)) /* - * Even if it fails we do not really care about that. - * Just proceed as it is. If needed "overflow" path - * will refill the cache we allocate from. + * Only scan the relevant parts containing pointers to other objects + * to avoid false negatives. */ - pva = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); + kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask); + } - spin_lock(&free_vmap_area_lock); +retry: + if (IS_ERR_VALUE(addr)) { + preload_this_cpu_lock(&free_vmap_area_lock, gfp_mask, node); + addr = __alloc_vmap_area(&free_vmap_area_root, &free_vmap_area_list, + size, align, vstart, vend); + spin_unlock(&free_vmap_area_lock); - if (pva && __this_cpu_cmpxchg(ne_fit_preload_node, NULL, pva)) - kmem_cache_free(vmap_area_cachep, pva); + /* + * This is not a fast path. Check if yielding is needed. This + * is the only reschedule point in the vmalloc() path. + */ + if (allow_block) + cond_resched(); + } + + trace_alloc_vmap_area(addr, size, align, vstart, vend, IS_ERR_VALUE(addr)); /* - * If an allocation fails, the "vend" address is + * If an allocation fails, the error value is * returned. Therefore trigger the overflow path. */ - addr = __alloc_vmap_area(size, align, vstart, vend); - spin_unlock(&free_vmap_area_lock); + if (IS_ERR_VALUE(addr)) { + if (allow_block) + goto overflow; - if (unlikely(addr == vend)) - goto overflow; + /* + * We can not trigger any reclaim logic because + * sleeping is not allowed, thus fail an allocation. + */ + goto out_free_va; + } va->va_start = addr; va->va_end = addr + size; va->vm = NULL; + va->flags = (va_flags | vn_id); + + if (vm) { + vm->addr = (void *)va->va_start; + vm->size = va_size(va); + va->vm = vm; + } + vn = addr_to_node(va->va_start); - spin_lock(&vmap_area_lock); - insert_vmap_area(va, &vmap_area_root, &vmap_area_list); - spin_unlock(&vmap_area_lock); + spin_lock(&vn->busy.lock); + insert_vmap_area(va, &vn->busy.root, &vn->busy.head); + spin_unlock(&vn->busy.lock); BUG_ON(!IS_ALIGNED(va->va_start, align)); BUG_ON(va->va_start < vstart); BUG_ON(va->va_end > vend); - ret = kasan_populate_vmalloc(addr, size); + ret = kasan_populate_vmalloc(addr, size, gfp_mask); if (ret) { free_vmap_area(va); return ERR_PTR(ret); @@ -1257,24 +2131,24 @@ retry: overflow: if (!purged) { - purge_vmap_area_lazy(); + reclaim_and_purge_vmap_areas(); purged = 1; goto retry; } - if (gfpflags_allow_blocking(gfp_mask)) { - unsigned long freed = 0; - blocking_notifier_call_chain(&vmap_notify_list, 0, &freed); - if (freed > 0) { - purged = 0; - goto retry; - } + freed = 0; + blocking_notifier_call_chain(&vmap_notify_list, 0, &freed); + + if (freed > 0) { + purged = 0; + goto retry; } if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) - pr_warn("vmap allocation for size %lu failed: use vmalloc=<size> to increase size\n", - size); + pr_warn("vmalloc_node_range for size %lu failed: Address range restricted to %#lx - %#lx\n", + size, vstart, vend); +out_free_va: kmem_cache_free(vmap_area_cachep, va); return ERR_PTR(-EBUSY); } @@ -1316,11 +2190,9 @@ static unsigned long lazy_max_pages(void) return log * (32UL * 1024 * 1024 / PAGE_SIZE); } -static atomic_long_t vmap_lazy_nr = ATOMIC_LONG_INIT(0); - /* - * Serialize vmap purging. There is no actual criticial section protected - * by this look, but we want to avoid concurrent calls for performance + * Serialize vmap purging. There is no actual critical section protected + * by this lock, but we want to avoid concurrent calls for performance * reasons and to make the pcpu_get_vm_areas more deterministic. */ static DEFINE_MUTEX(vmap_purge_lock); @@ -1328,116 +2200,265 @@ static DEFINE_MUTEX(vmap_purge_lock); /* for per-CPU blocks */ static void purge_fragmented_blocks_allcpus(void); -/* - * called before a call to iounmap() if the caller wants vm_area_struct's - * immediately freed. - */ -void set_iounmap_nonlazy(void) +static void +reclaim_list_global(struct list_head *head) { - atomic_long_set(&vmap_lazy_nr, lazy_max_pages()+1); + struct vmap_area *va, *n; + + if (list_empty(head)) + return; + + spin_lock(&free_vmap_area_lock); + list_for_each_entry_safe(va, n, head, list) + merge_or_add_vmap_area_augment(va, + &free_vmap_area_root, &free_vmap_area_list); + spin_unlock(&free_vmap_area_lock); } -/* - * Purges all lazily-freed vmap areas. - */ -static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end) +static void +decay_va_pool_node(struct vmap_node *vn, bool full_decay) { - unsigned long resched_threshold; - struct llist_node *valist; - struct vmap_area *va; - struct vmap_area *n_va; + LIST_HEAD(decay_list); + struct rb_root decay_root = RB_ROOT; + struct vmap_area *va, *nva; + unsigned long n_decay, pool_len; + int i; - lockdep_assert_held(&vmap_purge_lock); + for (i = 0; i < MAX_VA_SIZE_PAGES; i++) { + LIST_HEAD(tmp_list); - valist = llist_del_all(&vmap_purge_list); - if (unlikely(valist == NULL)) - return false; + if (list_empty(&vn->pool[i].head)) + continue; - /* - * TODO: to calculate a flush range without looping. - * The list can be up to lazy_max_pages() elements. - */ - llist_for_each_entry(va, valist, purge_list) { - if (va->va_start < start) - start = va->va_start; - if (va->va_end > end) - end = va->va_end; - } + /* Detach the pool, so no-one can access it. */ + spin_lock(&vn->pool_lock); + list_replace_init(&vn->pool[i].head, &tmp_list); + spin_unlock(&vn->pool_lock); - flush_tlb_kernel_range(start, end); - resched_threshold = lazy_max_pages() << 1; + pool_len = n_decay = vn->pool[i].len; + WRITE_ONCE(vn->pool[i].len, 0); - spin_lock(&free_vmap_area_lock); - llist_for_each_entry_safe(va, n_va, valist, purge_list) { - unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT; - unsigned long orig_start = va->va_start; - unsigned long orig_end = va->va_end; + /* Decay a pool by ~25% out of left objects. */ + if (!full_decay) + n_decay >>= 2; + pool_len -= n_decay; + + list_for_each_entry_safe(va, nva, &tmp_list, list) { + if (!n_decay--) + break; + + list_del_init(&va->list); + merge_or_add_vmap_area(va, &decay_root, &decay_list); + } /* - * Finally insert or merge lazily-freed area. It is - * detached and there is no need to "unlink" it from - * anything. + * Attach the pool back if it has been partly decayed. + * Please note, it is supposed that nobody(other contexts) + * can populate the pool therefore a simple list replace + * operation takes place here. */ - va = merge_or_add_vmap_area(va, &free_vmap_area_root, - &free_vmap_area_list); + if (!list_empty(&tmp_list)) { + spin_lock(&vn->pool_lock); + list_replace_init(&tmp_list, &vn->pool[i].head); + WRITE_ONCE(vn->pool[i].len, pool_len); + spin_unlock(&vn->pool_lock); + } + } - if (is_vmalloc_or_module_addr((void *)orig_start)) - kasan_release_vmalloc(orig_start, orig_end, - va->va_start, va->va_end); + reclaim_list_global(&decay_list); +} - atomic_long_sub(nr, &vmap_lazy_nr); +static void +kasan_release_vmalloc_node(struct vmap_node *vn) +{ + struct vmap_area *va; + unsigned long start, end; - if (atomic_long_read(&vmap_lazy_nr) < resched_threshold) - cond_resched_lock(&free_vmap_area_lock); + start = list_first_entry(&vn->purge_list, struct vmap_area, list)->va_start; + end = list_last_entry(&vn->purge_list, struct vmap_area, list)->va_end; + + list_for_each_entry(va, &vn->purge_list, list) { + if (is_vmalloc_or_module_addr((void *) va->va_start)) + kasan_release_vmalloc(va->va_start, va->va_end, + va->va_start, va->va_end, + KASAN_VMALLOC_PAGE_RANGE); } - spin_unlock(&free_vmap_area_lock); - return true; + + kasan_release_vmalloc(start, end, start, end, KASAN_VMALLOC_TLB_FLUSH); +} + +static void purge_vmap_node(struct work_struct *work) +{ + struct vmap_node *vn = container_of(work, + struct vmap_node, purge_work); + unsigned long nr_purged_pages = 0; + struct vmap_area *va, *n_va; + LIST_HEAD(local_list); + + if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) + kasan_release_vmalloc_node(vn); + + vn->nr_purged = 0; + + list_for_each_entry_safe(va, n_va, &vn->purge_list, list) { + unsigned long nr = va_size(va) >> PAGE_SHIFT; + unsigned int vn_id = decode_vn_id(va->flags); + + list_del_init(&va->list); + + nr_purged_pages += nr; + vn->nr_purged++; + + if (is_vn_id_valid(vn_id) && !vn->skip_populate) + if (node_pool_add_va(vn, va)) + continue; + + /* Go back to global. */ + list_add(&va->list, &local_list); + } + + atomic_long_sub(nr_purged_pages, &vmap_lazy_nr); + + reclaim_list_global(&local_list); } /* - * Kick off a purge of the outstanding lazy areas. Don't bother if somebody - * is already purging. + * Purges all lazily-freed vmap areas. */ -static void try_purge_vmap_area_lazy(void) +static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end, + bool full_pool_decay) { - if (mutex_trylock(&vmap_purge_lock)) { - __purge_vmap_area_lazy(ULONG_MAX, 0); - mutex_unlock(&vmap_purge_lock); + unsigned long nr_purged_areas = 0; + unsigned int nr_purge_helpers; + static cpumask_t purge_nodes; + unsigned int nr_purge_nodes; + struct vmap_node *vn; + int i; + + lockdep_assert_held(&vmap_purge_lock); + + /* + * Use cpumask to mark which node has to be processed. + */ + purge_nodes = CPU_MASK_NONE; + + for_each_vmap_node(vn) { + INIT_LIST_HEAD(&vn->purge_list); + vn->skip_populate = full_pool_decay; + decay_va_pool_node(vn, full_pool_decay); + + if (RB_EMPTY_ROOT(&vn->lazy.root)) + continue; + + spin_lock(&vn->lazy.lock); + WRITE_ONCE(vn->lazy.root.rb_node, NULL); + list_replace_init(&vn->lazy.head, &vn->purge_list); + spin_unlock(&vn->lazy.lock); + + start = min(start, list_first_entry(&vn->purge_list, + struct vmap_area, list)->va_start); + + end = max(end, list_last_entry(&vn->purge_list, + struct vmap_area, list)->va_end); + + cpumask_set_cpu(node_to_id(vn), &purge_nodes); } + + nr_purge_nodes = cpumask_weight(&purge_nodes); + if (nr_purge_nodes > 0) { + flush_tlb_kernel_range(start, end); + + /* One extra worker is per a lazy_max_pages() full set minus one. */ + nr_purge_helpers = atomic_long_read(&vmap_lazy_nr) / lazy_max_pages(); + nr_purge_helpers = clamp(nr_purge_helpers, 1U, nr_purge_nodes) - 1; + + for_each_cpu(i, &purge_nodes) { + vn = &vmap_nodes[i]; + + if (nr_purge_helpers > 0) { + INIT_WORK(&vn->purge_work, purge_vmap_node); + + if (cpumask_test_cpu(i, cpu_online_mask)) + schedule_work_on(i, &vn->purge_work); + else + schedule_work(&vn->purge_work); + + nr_purge_helpers--; + } else { + vn->purge_work.func = NULL; + purge_vmap_node(&vn->purge_work); + nr_purged_areas += vn->nr_purged; + } + } + + for_each_cpu(i, &purge_nodes) { + vn = &vmap_nodes[i]; + + if (vn->purge_work.func) { + flush_work(&vn->purge_work); + nr_purged_areas += vn->nr_purged; + } + } + } + + trace_purge_vmap_area_lazy(start, end, nr_purged_areas); + return nr_purged_areas > 0; } /* - * Kick off a purge of the outstanding lazy areas. + * Reclaim vmap areas by purging fragmented blocks and purge_vmap_area_list. */ -static void purge_vmap_area_lazy(void) +static void reclaim_and_purge_vmap_areas(void) + { mutex_lock(&vmap_purge_lock); purge_fragmented_blocks_allcpus(); - __purge_vmap_area_lazy(ULONG_MAX, 0); + __purge_vmap_area_lazy(ULONG_MAX, 0, true); + mutex_unlock(&vmap_purge_lock); +} + +static void drain_vmap_area_work(struct work_struct *work) +{ + mutex_lock(&vmap_purge_lock); + __purge_vmap_area_lazy(ULONG_MAX, 0, false); mutex_unlock(&vmap_purge_lock); } /* - * Free a vmap area, caller ensuring that the area has been unmapped - * and flush_cache_vunmap had been called for the correct range - * previously. + * Free a vmap area, caller ensuring that the area has been unmapped, + * unlinked and flush_cache_vunmap had been called for the correct + * range previously. */ static void free_vmap_area_noflush(struct vmap_area *va) { + unsigned long nr_lazy_max = lazy_max_pages(); + unsigned long va_start = va->va_start; + unsigned int vn_id = decode_vn_id(va->flags); + struct vmap_node *vn; unsigned long nr_lazy; - spin_lock(&vmap_area_lock); - unlink_va(va, &vmap_area_root); - spin_unlock(&vmap_area_lock); + if (WARN_ON_ONCE(!list_empty(&va->list))) + return; - nr_lazy = atomic_long_add_return((va->va_end - va->va_start) >> - PAGE_SHIFT, &vmap_lazy_nr); + nr_lazy = atomic_long_add_return_relaxed(va_size(va) >> PAGE_SHIFT, + &vmap_lazy_nr); - /* After this point, we may free va at any time */ - llist_add(&va->purge_list, &vmap_purge_list); + /* + * If it was request by a certain node we would like to + * return it to that node, i.e. its pool for later reuse. + */ + vn = is_vn_id_valid(vn_id) ? + id_to_node(vn_id):addr_to_node(va->va_start); - if (unlikely(nr_lazy > lazy_max_pages())) - try_purge_vmap_area_lazy(); + spin_lock(&vn->lazy.lock); + insert_vmap_area(va, &vn->lazy.root, &vn->lazy.head); + spin_unlock(&vn->lazy.lock); + + trace_free_vmap_area_noflush(va_start, nr_lazy, nr_lazy_max); + + /* After this point, we may free va at any time */ + if (unlikely(nr_lazy > nr_lazy_max)) + schedule_work(&drain_vmap_work); } /* @@ -1446,22 +2467,74 @@ static void free_vmap_area_noflush(struct vmap_area *va) static void free_unmap_vmap_area(struct vmap_area *va) { flush_cache_vunmap(va->va_start, va->va_end); - unmap_kernel_range_noflush(va->va_start, va->va_end - va->va_start); + vunmap_range_noflush(va->va_start, va->va_end); if (debug_pagealloc_enabled_static()) flush_tlb_kernel_range(va->va_start, va->va_end); free_vmap_area_noflush(va); } -static struct vmap_area *find_vmap_area(unsigned long addr) +struct vmap_area *find_vmap_area(unsigned long addr) { + struct vmap_node *vn; struct vmap_area *va; + int i, j; - spin_lock(&vmap_area_lock); - va = __find_vmap_area(addr); - spin_unlock(&vmap_area_lock); + if (unlikely(!vmap_initialized)) + return NULL; - return va; + /* + * An addr_to_node_id(addr) converts an address to a node index + * where a VA is located. If VA spans several zones and passed + * addr is not the same as va->va_start, what is not common, we + * may need to scan extra nodes. See an example: + * + * <----va----> + * -|-----|-----|-----|-----|- + * 1 2 0 1 + * + * VA resides in node 1 whereas it spans 1, 2 an 0. If passed + * addr is within 2 or 0 nodes we should do extra work. + */ + i = j = addr_to_node_id(addr); + do { + vn = &vmap_nodes[i]; + + spin_lock(&vn->busy.lock); + va = __find_vmap_area(addr, &vn->busy.root); + spin_unlock(&vn->busy.lock); + + if (va) + return va; + } while ((i = (i + nr_vmap_nodes - 1) % nr_vmap_nodes) != j); + + return NULL; +} + +static struct vmap_area *find_unlink_vmap_area(unsigned long addr) +{ + struct vmap_node *vn; + struct vmap_area *va; + int i, j; + + /* + * Check the comment in the find_vmap_area() about the loop. + */ + i = j = addr_to_node_id(addr); + do { + vn = &vmap_nodes[i]; + + spin_lock(&vn->busy.lock); + va = __find_vmap_area(addr, &vn->busy.root); + if (va) + unlink_va(va, &vn->busy.root); + spin_unlock(&vn->busy.lock); + + if (va) + return va; + } while ((i = (i + nr_vmap_nodes - 1) % nr_vmap_nodes) != j); + + return NULL; } /*** Per cpu kva allocator ***/ @@ -1494,31 +2567,94 @@ static struct vmap_area *find_vmap_area(unsigned long addr) #define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE) +/* + * Purge threshold to prevent overeager purging of fragmented blocks for + * regular operations: Purge if vb->free is less than 1/4 of the capacity. + */ +#define VMAP_PURGE_THRESHOLD (VMAP_BBMAP_BITS / 4) + +#define VMAP_RAM 0x1 /* indicates vm_map_ram area*/ +#define VMAP_BLOCK 0x2 /* mark out the vmap_block sub-type*/ +#define VMAP_FLAGS_MASK 0x3 + struct vmap_block_queue { spinlock_t lock; struct list_head free; + + /* + * An xarray requires an extra memory dynamically to + * be allocated. If it is an issue, we can use rb-tree + * instead. + */ + struct xarray vmap_blocks; }; struct vmap_block { spinlock_t lock; struct vmap_area *va; unsigned long free, dirty; + DECLARE_BITMAP(used_map, VMAP_BBMAP_BITS); unsigned long dirty_min, dirty_max; /*< dirty range */ struct list_head free_list; struct rcu_head rcu_head; struct list_head purge; + unsigned int cpu; }; /* Queue of free and dirty vmap blocks, for allocation and flushing purposes */ static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue); /* - * Radix tree of vmap blocks, indexed by address, to quickly find a vmap block - * in the free path. Could get rid of this if we change the API to return a - * "cookie" from alloc, to be passed to free. But no big deal yet. + * In order to fast access to any "vmap_block" associated with a + * specific address, we use a hash. + * + * A per-cpu vmap_block_queue is used in both ways, to serialize + * an access to free block chains among CPUs(alloc path) and it + * also acts as a vmap_block hash(alloc/free paths). It means we + * overload it, since we already have the per-cpu array which is + * used as a hash table. When used as a hash a 'cpu' passed to + * per_cpu() is not actually a CPU but rather a hash index. + * + * A hash function is addr_to_vb_xa() which hashes any address + * to a specific index(in a hash) it belongs to. This then uses a + * per_cpu() macro to access an array with generated index. + * + * An example: + * + * CPU_1 CPU_2 CPU_0 + * | | | + * V V V + * 0 10 20 30 40 50 60 + * |------|------|------|------|------|------|...<vmap address space> + * CPU0 CPU1 CPU2 CPU0 CPU1 CPU2 + * + * - CPU_1 invokes vm_unmap_ram(6), 6 belongs to CPU0 zone, thus + * it access: CPU0/INDEX0 -> vmap_blocks -> xa_lock; + * + * - CPU_2 invokes vm_unmap_ram(11), 11 belongs to CPU1 zone, thus + * it access: CPU1/INDEX1 -> vmap_blocks -> xa_lock; + * + * - CPU_0 invokes vm_unmap_ram(20), 20 belongs to CPU2 zone, thus + * it access: CPU2/INDEX2 -> vmap_blocks -> xa_lock. + * + * This technique almost always avoids lock contention on insert/remove, + * however xarray spinlocks protect against any contention that remains. */ -static DEFINE_SPINLOCK(vmap_block_tree_lock); -static RADIX_TREE(vmap_block_tree, GFP_ATOMIC); +static struct xarray * +addr_to_vb_xa(unsigned long addr) +{ + int index = (addr / VMAP_BLOCK_SIZE) % nr_cpu_ids; + + /* + * Please note, nr_cpu_ids points on a highest set + * possible bit, i.e. we never invoke cpumask_next() + * if an index points on it which is nr_cpu_ids - 1. + */ + if (!cpu_possible(index)) + index = cpumask_next(index, cpu_possible_mask); + + return &per_cpu(vmap_block_queue, index).vmap_blocks; +} /* * We should probably have a fallback mechanism to allocate virtual memory @@ -1556,107 +2692,139 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) struct vmap_block_queue *vbq; struct vmap_block *vb; struct vmap_area *va; + struct xarray *xa; unsigned long vb_idx; int node, err; void *vaddr; node = numa_node_id(); - vb = kmalloc_node(sizeof(struct vmap_block), - gfp_mask & GFP_RECLAIM_MASK, node); + vb = kmalloc_node(sizeof(struct vmap_block), gfp_mask, node); if (unlikely(!vb)) return ERR_PTR(-ENOMEM); va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE, VMALLOC_START, VMALLOC_END, - node, gfp_mask); + node, gfp_mask, + VMAP_RAM|VMAP_BLOCK, NULL); if (IS_ERR(va)) { kfree(vb); return ERR_CAST(va); } - err = radix_tree_preload(gfp_mask); - if (unlikely(err)) { - kfree(vb); - free_vmap_area(va); - return ERR_PTR(err); - } - vaddr = vmap_block_vaddr(va->va_start, 0); spin_lock_init(&vb->lock); vb->va = va; /* At least something should be left free */ BUG_ON(VMAP_BBMAP_BITS <= (1UL << order)); + bitmap_zero(vb->used_map, VMAP_BBMAP_BITS); vb->free = VMAP_BBMAP_BITS - (1UL << order); vb->dirty = 0; vb->dirty_min = VMAP_BBMAP_BITS; vb->dirty_max = 0; + bitmap_set(vb->used_map, 0, (1UL << order)); INIT_LIST_HEAD(&vb->free_list); + vb->cpu = raw_smp_processor_id(); + xa = addr_to_vb_xa(va->va_start); vb_idx = addr_to_vb_idx(va->va_start); - spin_lock(&vmap_block_tree_lock); - err = radix_tree_insert(&vmap_block_tree, vb_idx, vb); - spin_unlock(&vmap_block_tree_lock); - BUG_ON(err); - radix_tree_preload_end(); - - vbq = &get_cpu_var(vmap_block_queue); + err = xa_insert(xa, vb_idx, vb, gfp_mask); + if (err) { + kfree(vb); + free_vmap_area(va); + return ERR_PTR(err); + } + /* + * list_add_tail_rcu could happened in another core + * rather than vb->cpu due to task migration, which + * is safe as list_add_tail_rcu will ensure the list's + * integrity together with list_for_each_rcu from read + * side. + */ + vbq = per_cpu_ptr(&vmap_block_queue, vb->cpu); spin_lock(&vbq->lock); list_add_tail_rcu(&vb->free_list, &vbq->free); spin_unlock(&vbq->lock); - put_cpu_var(vmap_block_queue); return vaddr; } static void free_vmap_block(struct vmap_block *vb) { + struct vmap_node *vn; struct vmap_block *tmp; - unsigned long vb_idx; + struct xarray *xa; - vb_idx = addr_to_vb_idx(vb->va->va_start); - spin_lock(&vmap_block_tree_lock); - tmp = radix_tree_delete(&vmap_block_tree, vb_idx); - spin_unlock(&vmap_block_tree_lock); + xa = addr_to_vb_xa(vb->va->va_start); + tmp = xa_erase(xa, addr_to_vb_idx(vb->va->va_start)); BUG_ON(tmp != vb); + vn = addr_to_node(vb->va->va_start); + spin_lock(&vn->busy.lock); + unlink_va(vb->va, &vn->busy.root); + spin_unlock(&vn->busy.lock); + free_vmap_area_noflush(vb->va); kfree_rcu(vb, rcu_head); } +static bool purge_fragmented_block(struct vmap_block *vb, + struct list_head *purge_list, bool force_purge) +{ + struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, vb->cpu); + + if (vb->free + vb->dirty != VMAP_BBMAP_BITS || + vb->dirty == VMAP_BBMAP_BITS) + return false; + + /* Don't overeagerly purge usable blocks unless requested */ + if (!(force_purge || vb->free < VMAP_PURGE_THRESHOLD)) + return false; + + /* prevent further allocs after releasing lock */ + WRITE_ONCE(vb->free, 0); + /* prevent purging it again */ + WRITE_ONCE(vb->dirty, VMAP_BBMAP_BITS); + vb->dirty_min = 0; + vb->dirty_max = VMAP_BBMAP_BITS; + spin_lock(&vbq->lock); + list_del_rcu(&vb->free_list); + spin_unlock(&vbq->lock); + list_add_tail(&vb->purge, purge_list); + return true; +} + +static void free_purged_blocks(struct list_head *purge_list) +{ + struct vmap_block *vb, *n_vb; + + list_for_each_entry_safe(vb, n_vb, purge_list, purge) { + list_del(&vb->purge); + free_vmap_block(vb); + } +} + static void purge_fragmented_blocks(int cpu) { LIST_HEAD(purge); struct vmap_block *vb; - struct vmap_block *n_vb; struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu); rcu_read_lock(); list_for_each_entry_rcu(vb, &vbq->free, free_list) { + unsigned long free = READ_ONCE(vb->free); + unsigned long dirty = READ_ONCE(vb->dirty); - if (!(vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS)) + if (free + dirty != VMAP_BBMAP_BITS || + dirty == VMAP_BBMAP_BITS) continue; spin_lock(&vb->lock); - if (vb->free + vb->dirty == VMAP_BBMAP_BITS && vb->dirty != VMAP_BBMAP_BITS) { - vb->free = 0; /* prevent further allocs after releasing lock */ - vb->dirty = VMAP_BBMAP_BITS; /* prevent purging it again */ - vb->dirty_min = 0; - vb->dirty_max = VMAP_BBMAP_BITS; - spin_lock(&vbq->lock); - list_del_rcu(&vb->free_list); - spin_unlock(&vbq->lock); - spin_unlock(&vb->lock); - list_add_tail(&vb->purge, &purge); - } else - spin_unlock(&vb->lock); + purge_fragmented_block(vb, &purge, true); + spin_unlock(&vb->lock); } rcu_read_unlock(); - - list_for_each_entry_safe(vb, n_vb, &purge, purge) { - list_del(&vb->purge); - free_vmap_block(vb); - } + free_purged_blocks(&purge); } static void purge_fragmented_blocks_allcpus(void) @@ -1682,15 +2850,18 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) * get_order(0) returns funny result. Just warn and terminate * early. */ - return NULL; + return ERR_PTR(-EINVAL); } order = get_order(size); rcu_read_lock(); - vbq = &get_cpu_var(vmap_block_queue); + vbq = raw_cpu_ptr(&vmap_block_queue); list_for_each_entry_rcu(vb, &vbq->free, free_list) { unsigned long pages_off; + if (READ_ONCE(vb->free) < (1UL << order)) + continue; + spin_lock(&vb->lock); if (vb->free < (1UL << order)) { spin_unlock(&vb->lock); @@ -1699,7 +2870,8 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) pages_off = VMAP_BBMAP_BITS - vb->free; vaddr = vmap_block_vaddr(vb->va->va_start, pages_off); - vb->free -= 1UL << order; + WRITE_ONCE(vb->free, vb->free - (1UL << order)); + bitmap_set(vb->used_map, pages_off, (1UL << order)); if (vb->free == 0) { spin_lock(&vbq->lock); list_del_rcu(&vb->free_list); @@ -1710,7 +2882,6 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) break; } - put_cpu_var(vmap_block_queue); rcu_read_unlock(); /* Allocate new block if nothing was found */ @@ -1723,9 +2894,9 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask) static void vb_free(unsigned long addr, unsigned long size) { unsigned long offset; - unsigned long vb_idx; unsigned int order; struct vmap_block *vb; + struct xarray *xa; BUG_ON(offset_in_page(size)); BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); @@ -1733,27 +2904,27 @@ static void vb_free(unsigned long addr, unsigned long size) flush_cache_vunmap(addr, addr + size); order = get_order(size); - offset = (addr & (VMAP_BLOCK_SIZE - 1)) >> PAGE_SHIFT; - vb_idx = addr_to_vb_idx(addr); - rcu_read_lock(); - vb = radix_tree_lookup(&vmap_block_tree, vb_idx); - rcu_read_unlock(); - BUG_ON(!vb); + xa = addr_to_vb_xa(addr); + vb = xa_load(xa, addr_to_vb_idx(addr)); - unmap_kernel_range_noflush(addr, size); + spin_lock(&vb->lock); + bitmap_clear(vb->used_map, offset, (1UL << order)); + spin_unlock(&vb->lock); + + vunmap_range_noflush(addr, addr + size); if (debug_pagealloc_enabled_static()) flush_tlb_kernel_range(addr, addr + size); spin_lock(&vb->lock); - /* Expand dirty range */ + /* Expand the not yet TLB flushed dirty range */ vb->dirty_min = min(vb->dirty_min, offset); vb->dirty_max = max(vb->dirty_max, offset + (1UL << order)); - vb->dirty += 1UL << order; + WRITE_ONCE(vb->dirty, vb->dirty + (1UL << order)); if (vb->dirty == VMAP_BBMAP_BITS) { BUG_ON(vb->free); spin_unlock(&vb->lock); @@ -1764,21 +2935,30 @@ static void vb_free(unsigned long addr, unsigned long size) static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush) { + LIST_HEAD(purge_list); int cpu; if (unlikely(!vmap_initialized)) return; - might_sleep(); + mutex_lock(&vmap_purge_lock); for_each_possible_cpu(cpu) { struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu); struct vmap_block *vb; + unsigned long idx; rcu_read_lock(); - list_for_each_entry_rcu(vb, &vbq->free, free_list) { + xa_for_each(&vbq->vmap_blocks, idx, vb) { spin_lock(&vb->lock); - if (vb->dirty) { + + /* + * Try to purge a fragmented block first. If it's + * not purgeable, check whether there is dirty + * space to be flushed. + */ + if (!purge_fragmented_block(vb, &purge_list, false) && + vb->dirty_max && vb->dirty != VMAP_BBMAP_BITS) { unsigned long va_start = vb->va->va_start; unsigned long s, e; @@ -1788,16 +2968,19 @@ static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush) start = min(s, start); end = max(e, end); + /* Prevent that this is flushed again */ + vb->dirty_min = VMAP_BBMAP_BITS; + vb->dirty_max = 0; + flush = 1; } spin_unlock(&vb->lock); } rcu_read_unlock(); } + free_purged_blocks(&purge_list); - mutex_lock(&vmap_purge_lock); - purge_fragmented_blocks_allcpus(); - if (!__purge_vmap_area_lazy(start, end) && flush) + if (!__purge_vmap_area_lazy(start, end, false) && flush) flush_tlb_kernel_range(start, end); mutex_unlock(&vmap_purge_lock); } @@ -1817,10 +3000,7 @@ static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush) */ void vm_unmap_aliases(void) { - unsigned long start = ULONG_MAX, end = 0; - int flush = 0; - - _vm_unmap_aliases(start, end, flush); + _vm_unmap_aliases(ULONG_MAX, 0, 0); } EXPORT_SYMBOL_GPL(vm_unmap_aliases); @@ -1832,7 +3012,7 @@ EXPORT_SYMBOL_GPL(vm_unmap_aliases); void vm_unmap_ram(const void *mem, unsigned int count) { unsigned long size = (unsigned long)count << PAGE_SHIFT; - unsigned long addr = (unsigned long)mem; + unsigned long addr = (unsigned long)kasan_reset_tag(mem); struct vmap_area *va; might_sleep(); @@ -1849,10 +3029,11 @@ void vm_unmap_ram(const void *mem, unsigned int count) return; } - va = find_vmap_area(addr); - BUG_ON(!va); - debug_check_no_locks_freed((void *)va->va_start, - (va->va_end - va->va_start)); + va = find_unlink_vmap_area(addr); + if (WARN_ON_ONCE(!va)) + return; + + debug_check_no_locks_freed((void *)va->va_start, va_size(va)); free_unmap_vmap_area(va); } EXPORT_SYMBOL(vm_unmap_ram); @@ -1862,7 +3043,6 @@ EXPORT_SYMBOL(vm_unmap_ram); * @pages: an array of pointers to the pages to be mapped * @count: number of pages * @node: prefer to allocate data structures on this node - * @prot: memory protection to use. PAGE_KERNEL for regular RAM * * If you use this function for less than VMAP_MAX_ALLOC pages, it could be * faster than vmap so it's good. But if you mix long-life and short-life @@ -1886,7 +3066,9 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node) } else { struct vmap_area *va; va = alloc_vmap_area(size, PAGE_SIZE, - VMALLOC_START, VMALLOC_END, node, GFP_KERNEL); + VMALLOC_START, VMALLOC_END, + node, GFP_KERNEL, VMAP_RAM, + NULL); if (IS_ERR(va)) return NULL; @@ -1894,18 +3076,48 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node) mem = (void *)addr; } - kasan_unpoison_vmalloc(mem, size); - - if (map_kernel_range(addr, size, PAGE_KERNEL, pages) < 0) { + if (vmap_pages_range(addr, addr + size, PAGE_KERNEL, + pages, PAGE_SHIFT) < 0) { vm_unmap_ram(mem, count); return NULL; } + + /* + * Mark the pages as accessible, now that they are mapped. + * With hardware tag-based KASAN, marking is skipped for + * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). + */ + mem = kasan_unpoison_vmalloc(mem, size, KASAN_VMALLOC_PROT_NORMAL); + return mem; } EXPORT_SYMBOL(vm_map_ram); static struct vm_struct *vmlist __initdata; +static inline unsigned int vm_area_page_order(struct vm_struct *vm) +{ +#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC + return vm->page_order; +#else + return 0; +#endif +} + +unsigned int get_vm_area_page_order(struct vm_struct *vm) +{ + return vm_area_page_order(vm); +} + +static inline void set_vm_area_page_order(struct vm_struct *vm, unsigned int order) +{ +#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC + vm->page_order = order; +#else + BUG_ON(order != 0); +#endif +} + /** * vm_area_add_early - add vmap area early during boot * @vm: vm_struct to add @@ -1946,133 +3158,22 @@ void __init vm_area_add_early(struct vm_struct *vm) */ void __init vm_area_register_early(struct vm_struct *vm, size_t align) { - static size_t vm_init_off __initdata; - unsigned long addr; - - addr = ALIGN(VMALLOC_START + vm_init_off, align); - vm_init_off = PFN_ALIGN(addr + vm->size) - VMALLOC_START; + unsigned long addr = ALIGN(VMALLOC_START, align); + struct vm_struct *cur, **p; - vm->addr = (void *)addr; - - vm_area_add_early(vm); -} - -static void vmap_init_free_space(void) -{ - unsigned long vmap_start = 1; - const unsigned long vmap_end = ULONG_MAX; - struct vmap_area *busy, *free; - - /* - * B F B B B F - * -|-----|.....|-----|-----|-----|.....|- - * | The KVA space | - * |<--------------------------------->| - */ - list_for_each_entry(busy, &vmap_area_list, list) { - if (busy->va_start - vmap_start > 0) { - free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); - if (!WARN_ON_ONCE(!free)) { - free->va_start = vmap_start; - free->va_end = busy->va_start; - - insert_vmap_area_augment(free, NULL, - &free_vmap_area_root, - &free_vmap_area_list); - } - } - - vmap_start = busy->va_end; - } - - if (vmap_end - vmap_start > 0) { - free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); - if (!WARN_ON_ONCE(!free)) { - free->va_start = vmap_start; - free->va_end = vmap_end; - - insert_vmap_area_augment(free, NULL, - &free_vmap_area_root, - &free_vmap_area_list); - } - } -} - -void __init vmalloc_init(void) -{ - struct vmap_area *va; - struct vm_struct *tmp; - int i; - - /* - * Create the cache for vmap_area objects. - */ - vmap_area_cachep = KMEM_CACHE(vmap_area, SLAB_PANIC); - - for_each_possible_cpu(i) { - struct vmap_block_queue *vbq; - struct vfree_deferred *p; - - vbq = &per_cpu(vmap_block_queue, i); - spin_lock_init(&vbq->lock); - INIT_LIST_HEAD(&vbq->free); - p = &per_cpu(vfree_deferred, i); - init_llist_head(&p->list); - INIT_WORK(&p->wq, free_work); - } - - /* Import existing vmlist entries. */ - for (tmp = vmlist; tmp; tmp = tmp->next) { - va = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); - if (WARN_ON_ONCE(!va)) - continue; + BUG_ON(vmap_initialized); - va->va_start = (unsigned long)tmp->addr; - va->va_end = va->va_start + tmp->size; - va->vm = tmp; - insert_vmap_area(va, &vmap_area_root, &vmap_area_list); + for (p = &vmlist; (cur = *p) != NULL; p = &cur->next) { + if ((unsigned long)cur->addr - addr >= vm->size) + break; + addr = ALIGN((unsigned long)cur->addr + cur->size, align); } - /* - * Now we can initialize a free vmap space. - */ - vmap_init_free_space(); - vmap_initialized = true; -} - -/** - * unmap_kernel_range - unmap kernel VM area and flush cache and TLB - * @addr: start of the VM area to unmap - * @size: size of the VM area to unmap - * - * Similar to unmap_kernel_range_noflush() but flushes vcache before - * the unmapping and tlb after. - */ -void unmap_kernel_range(unsigned long addr, unsigned long size) -{ - unsigned long end = addr + size; - - flush_cache_vunmap(addr, end); - unmap_kernel_range_noflush(addr, size); - flush_tlb_kernel_range(addr, end); -} - -static inline void setup_vmalloc_vm_locked(struct vm_struct *vm, - struct vmap_area *va, unsigned long flags, const void *caller) -{ - vm->flags = flags; - vm->addr = (void *)va->va_start; - vm->size = va->va_end - va->va_start; - vm->caller = caller; - va->vm = vm; -} - -static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, - unsigned long flags, const void *caller) -{ - spin_lock(&vmap_area_lock); - setup_vmalloc_vm_locked(vm, va, flags, caller); - spin_unlock(&vmap_area_lock); + BUG_ON(addr > VMALLOC_END - vm->size); + vm->addr = (void *)addr; + vm->next = *p; + *p = vm; + kasan_populate_early_vm_area_shadow(vm->addr, vm->size); } static void clear_vm_uninitialized_flag(struct vm_struct *vm) @@ -2080,22 +3181,23 @@ static void clear_vm_uninitialized_flag(struct vm_struct *vm) /* * Before removing VM_UNINITIALIZED, * we should make sure that vm has proper values. - * Pair with smp_rmb() in show_numa_info(). + * Pair with smp_rmb() in vread_iter() and vmalloc_info_show(). */ smp_wmb(); vm->flags &= ~VM_UNINITIALIZED; } -static struct vm_struct *__get_vm_area_node(unsigned long size, - unsigned long align, unsigned long flags, unsigned long start, - unsigned long end, int node, gfp_t gfp_mask, const void *caller) +struct vm_struct *__get_vm_area_node(unsigned long size, + unsigned long align, unsigned long shift, unsigned long flags, + unsigned long start, unsigned long end, int node, + gfp_t gfp_mask, const void *caller) { struct vmap_area *va; struct vm_struct *area; unsigned long requested_size = size; BUG_ON(in_interrupt()); - size = PAGE_ALIGN(size); + size = ALIGN(size, 1ul << shift); if (unlikely(!size)) return NULL; @@ -2110,15 +3212,27 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, if (!(flags & VM_NO_GUARD)) size += PAGE_SIZE; - va = alloc_vmap_area(size, align, start, end, node, gfp_mask); + area->flags = flags; + area->caller = caller; + area->requested_size = requested_size; + + va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area); if (IS_ERR(va)) { kfree(area); return NULL; } - kasan_unpoison_vmalloc((void *)va->va_start, requested_size); - - setup_vmalloc_vm(area, va, flags, caller); + /* + * Mark pages for non-VM_ALLOC mappings as accessible. Do it now as a + * best-effort approach, as they can be mapped outside of vmalloc code. + * For VM_ALLOC mappings, the pages are marked as accessible after + * getting mapped in __vmalloc_node_range(). + * With hardware tag-based KASAN, marking is skipped for + * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). + */ + if (!(flags & VM_ALLOC)) + area->addr = kasan_unpoison_vmalloc(area->addr, requested_size, + KASAN_VMALLOC_PROT_NORMAL); return area; } @@ -2127,8 +3241,8 @@ struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, const void *caller) { - return __get_vm_area_node(size, 1, flags, start, end, NUMA_NO_NODE, - GFP_KERNEL, caller); + return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, start, end, + NUMA_NO_NODE, GFP_KERNEL, caller); } /** @@ -2144,7 +3258,8 @@ struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, */ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) { - return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END, + return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, + VMALLOC_START, VMALLOC_END, NUMA_NO_NODE, GFP_KERNEL, __builtin_return_address(0)); } @@ -2152,7 +3267,8 @@ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, const void *caller) { - return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END, + return __get_vm_area_node(size, 1, PAGE_SHIFT, flags, + VMALLOC_START, VMALLOC_END, NUMA_NO_NODE, GFP_KERNEL, caller); } @@ -2164,7 +3280,7 @@ struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, * It is up to the caller to do all required locking to keep the returned * pointer valid. * - * Return: pointer to the found area or %NULL on faulure + * Return: the area descriptor on success or %NULL on failure. */ struct vm_struct *find_vm_area(const void *addr) { @@ -2185,30 +3301,31 @@ struct vm_struct *find_vm_area(const void *addr) * This function returns the found VM area, but using it is NOT safe * on SMP machines, except for its size or flags. * - * Return: pointer to the found area or %NULL on faulure + * Return: the area descriptor on success or %NULL on failure. */ struct vm_struct *remove_vm_area(const void *addr) { struct vmap_area *va; + struct vm_struct *vm; might_sleep(); - spin_lock(&vmap_area_lock); - va = __find_vmap_area((unsigned long)addr); - if (va && va->vm) { - struct vm_struct *vm = va->vm; - - va->vm = NULL; - spin_unlock(&vmap_area_lock); + if (WARN(!PAGE_ALIGNED(addr), "Trying to vfree() bad address (%p)\n", + addr)) + return NULL; - kasan_free_shadow(vm); - free_unmap_vmap_area(va); + va = find_unlink_vmap_area((unsigned long)addr); + if (!va || !va->vm) + return NULL; + vm = va->vm; - return vm; - } + debug_check_no_locks_freed(vm->addr, get_vm_area_size(vm)); + debug_check_no_obj_freed(vm->addr, get_vm_area_size(vm)); + kasan_free_module_shadow(vm); + kasan_poison_vmalloc(vm->addr, get_vm_area_size(vm)); - spin_unlock(&vmap_area_lock); - return NULL; + free_unmap_vmap_area(va); + return vm; } static inline void set_area_direct_map(const struct vm_struct *area, @@ -2216,44 +3333,35 @@ static inline void set_area_direct_map(const struct vm_struct *area, { int i; + /* HUGE_VMALLOC passes small pages to set_direct_map */ for (i = 0; i < area->nr_pages; i++) if (page_address(area->pages[i])) set_direct_map(area->pages[i]); } -/* Handle removing and resetting vm mappings related to the vm_struct. */ -static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages) +/* + * Flush the vm mapping and reset the direct map. + */ +static void vm_reset_perms(struct vm_struct *area) { unsigned long start = ULONG_MAX, end = 0; - int flush_reset = area->flags & VM_FLUSH_RESET_PERMS; + unsigned int page_order = vm_area_page_order(area); int flush_dmap = 0; int i; - remove_vm_area(area->addr); - - /* If this is not VM_FLUSH_RESET_PERMS memory, no need for the below. */ - if (!flush_reset) - return; - /* - * If not deallocating pages, just do the flush of the VM area and - * return. - */ - if (!deallocate_pages) { - vm_unmap_aliases(); - return; - } - - /* - * If execution gets here, flush the vm mapping and reset the direct - * map. Find the start and end range of the direct mappings to make sure + * Find the start and end range of the direct mappings to make sure that * the vm_unmap_aliases() flush includes the direct map. */ - for (i = 0; i < area->nr_pages; i++) { + for (i = 0; i < area->nr_pages; i += 1U << page_order) { unsigned long addr = (unsigned long)page_address(area->pages[i]); + if (addr) { + unsigned long page_size; + + page_size = PAGE_SIZE << page_order; start = min(addr, start); - end = max(addr + PAGE_SIZE, end); + end = max(addr + page_size, end); flush_dmap = 1; } } @@ -2268,61 +3376,13 @@ static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages) set_area_direct_map(area, set_direct_map_default_noflush); } -static void __vunmap(const void *addr, int deallocate_pages) -{ - struct vm_struct *area; - - if (!addr) - return; - - if (WARN(!PAGE_ALIGNED(addr), "Trying to vfree() bad address (%p)\n", - addr)) - return; - - area = find_vm_area(addr); - if (unlikely(!area)) { - WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n", - addr); - return; - } - - debug_check_no_locks_freed(area->addr, get_vm_area_size(area)); - debug_check_no_obj_freed(area->addr, get_vm_area_size(area)); - - kasan_poison_vmalloc(area->addr, area->size); - - vm_remove_mappings(area, deallocate_pages); - - if (deallocate_pages) { - int i; - - for (i = 0; i < area->nr_pages; i++) { - struct page *page = area->pages[i]; - - BUG_ON(!page); - __free_pages(page, 0); - } - atomic_long_sub(area->nr_pages, &nr_vmalloc_pages); - - kvfree(area->pages); - } - - kfree(area); - return; -} - -static inline void __vfree_deferred(const void *addr) +static void delayed_vfree_work(struct work_struct *w) { - /* - * Use raw_cpu_ptr() because this can be called from preemptible - * context. Preemption is absolutely fine here, because the llist_add() - * implementation is lockless, so it works even if we are adding to - * another cpu's list. schedule_work() should be fine with this too. - */ - struct vfree_deferred *p = raw_cpu_ptr(&vfree_deferred); + struct vfree_deferred *p = container_of(w, struct vfree_deferred, wq); + struct llist_node *t, *llnode; - if (llist_add((struct llist_node *)addr, &p->list)) - schedule_work(&p->wq); + llist_for_each_safe(llnode, t, llist_del_all(&p->list)) + vfree(llnode); } /** @@ -2334,51 +3394,82 @@ static inline void __vfree_deferred(const void *addr) */ void vfree_atomic(const void *addr) { - BUG_ON(in_nmi()); + struct vfree_deferred *p = raw_cpu_ptr(&vfree_deferred); + BUG_ON(in_nmi()); kmemleak_free(addr); - if (!addr) - return; - __vfree_deferred(addr); -} - -static void __vfree(const void *addr) -{ - if (unlikely(in_interrupt())) - __vfree_deferred(addr); - else - __vunmap(addr, 1); + /* + * Use raw_cpu_ptr() because this can be called from preemptible + * context. Preemption is absolutely fine here, because the llist_add() + * implementation is lockless, so it works even if we are adding to + * another cpu's list. schedule_work() should be fine with this too. + */ + if (addr && llist_add((struct llist_node *)addr, &p->list)) + schedule_work(&p->wq); } /** - * vfree - release memory allocated by vmalloc() - * @addr: memory base address + * vfree - Release memory allocated by vmalloc() + * @addr: Memory base address * - * Free the virtually continuous memory area starting at @addr, as - * obtained from vmalloc(), vmalloc_32() or __vmalloc(). If @addr is - * NULL, no operation is performed. + * Free the virtually continuous memory area starting at @addr, as obtained + * from one of the vmalloc() family of APIs. This will usually also free the + * physical memory underlying the virtual allocation, but that memory is + * reference counted, so it will not be freed until the last user goes away. * - * Must not be called in NMI context (strictly speaking, only if we don't - * have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling - * conventions for vfree() arch-depenedent would be a really bad idea) + * If @addr is NULL, no operation is performed. * + * Context: * May sleep if called *not* from interrupt context. - * - * NOTE: assumes that the object at @addr has a size >= sizeof(llist_node) + * Must not be called in NMI context (strictly speaking, it could be + * if we have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling + * conventions for vfree() arch-dependent would be a really bad idea). */ void vfree(const void *addr) { - BUG_ON(in_nmi()); + struct vm_struct *vm; + int i; - kmemleak_free(addr); + if (unlikely(in_interrupt())) { + vfree_atomic(addr); + return; + } - might_sleep_if(!in_interrupt()); + BUG_ON(in_nmi()); + kmemleak_free(addr); + might_sleep(); if (!addr) return; - __vfree(addr); + vm = remove_vm_area(addr); + if (unlikely(!vm)) { + WARN(1, KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n", + addr); + return; + } + + if (unlikely(vm->flags & VM_FLUSH_RESET_PERMS)) + vm_reset_perms(vm); + /* All pages of vm should be charged to same memcg, so use first one. */ + if (vm->nr_pages && !(vm->flags & VM_MAP_PUT_PAGES)) + mod_memcg_page_state(vm->pages[0], MEMCG_VMALLOC, -vm->nr_pages); + for (i = 0; i < vm->nr_pages; i++) { + struct page *page = vm->pages[i]; + + BUG_ON(!page); + /* + * High-order allocs for huge vmallocs are split, so + * can be freed as an array of order-0 allocations + */ + __free_page(page); + cond_resched(); + } + if (!(vm->flags & VM_MAP_PUT_PAGES)) + atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages); + kvfree(vm->pages); + kfree(vm); } EXPORT_SYMBOL(vfree); @@ -2393,10 +3484,20 @@ EXPORT_SYMBOL(vfree); */ void vunmap(const void *addr) { + struct vm_struct *vm; + BUG_ON(in_interrupt()); might_sleep(); - if (addr) - __vunmap(addr, 0); + + if (!addr) + return; + vm = remove_vm_area(addr); + if (unlikely(!vm)) { + WARN(1, KERN_ERR "Trying to vunmap() nonexistent vm area (%p)\n", + addr); + return; + } + kfree(vm); } EXPORT_SYMBOL(vunmap); @@ -2407,8 +3508,11 @@ EXPORT_SYMBOL(vunmap); * @flags: vm_area->flags * @prot: page protection for the mapping * - * Maps @count pages from @pages into contiguous kernel virtual - * space. + * Maps @count pages from @pages into contiguous kernel virtual space. + * If @flags contains %VM_MAP_PUT_PAGES the ownership of the pages array itself + * (which must be kmalloc or vmalloc memory) and one reference per pages in it + * are transferred from the caller to vmap(), and will be freed / dropped when + * vfree() is called on the return value. * * Return: the address of the area or %NULL on failure */ @@ -2416,10 +3520,21 @@ void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot) { struct vm_struct *area; + unsigned long addr; unsigned long size; /* In bytes */ might_sleep(); + if (WARN_ON_ONCE(flags & VM_FLUSH_RESET_PERMS)) + return NULL; + + /* + * Your top guard is someone else's bottom guard. Not having a top + * guard compromises someone else's mappings too. + */ + if (WARN_ON_ONCE(flags & VM_NO_GUARD)) + flags &= ~VM_NO_GUARD; + if (count > totalram_pages()) return NULL; @@ -2428,81 +3543,404 @@ void *vmap(struct page **pages, unsigned int count, if (!area) return NULL; - if (map_kernel_range((unsigned long)area->addr, size, pgprot_nx(prot), - pages) < 0) { + addr = (unsigned long)area->addr; + if (vmap_pages_range(addr, addr + size, pgprot_nx(prot), + pages, PAGE_SHIFT) < 0) { vunmap(area->addr); return NULL; } + if (flags & VM_MAP_PUT_PAGES) { + area->pages = pages; + area->nr_pages = count; + } return area->addr; } EXPORT_SYMBOL(vmap); +#ifdef CONFIG_VMAP_PFN +struct vmap_pfn_data { + unsigned long *pfns; + pgprot_t prot; + unsigned int idx; +}; + +static int vmap_pfn_apply(pte_t *pte, unsigned long addr, void *private) +{ + struct vmap_pfn_data *data = private; + unsigned long pfn = data->pfns[data->idx]; + pte_t ptent; + + if (WARN_ON_ONCE(pfn_valid(pfn))) + return -EINVAL; + + ptent = pte_mkspecial(pfn_pte(pfn, data->prot)); + set_pte_at(&init_mm, addr, pte, ptent); + + data->idx++; + return 0; +} + +/** + * vmap_pfn - map an array of PFNs into virtually contiguous space + * @pfns: array of PFNs + * @count: number of pages to map + * @prot: page protection for the mapping + * + * Maps @count PFNs from @pfns into contiguous kernel virtual space and returns + * the start address of the mapping. + */ +void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot) +{ + struct vmap_pfn_data data = { .pfns = pfns, .prot = pgprot_nx(prot) }; + struct vm_struct *area; + + area = get_vm_area_caller(count * PAGE_SIZE, VM_IOREMAP, + __builtin_return_address(0)); + if (!area) + return NULL; + if (apply_to_page_range(&init_mm, (unsigned long)area->addr, + count * PAGE_SIZE, vmap_pfn_apply, &data)) { + free_vm_area(area); + return NULL; + } + + flush_cache_vmap((unsigned long)area->addr, + (unsigned long)area->addr + count * PAGE_SIZE); + + return area->addr; +} +EXPORT_SYMBOL_GPL(vmap_pfn); +#endif /* CONFIG_VMAP_PFN */ + +/* + * Helper for vmalloc to adjust the gfp flags for certain allocations. + */ +static inline gfp_t vmalloc_gfp_adjust(gfp_t flags, const bool large) +{ + flags |= __GFP_NOWARN; + if (large) + flags &= ~__GFP_NOFAIL; + return flags; +} + +static inline unsigned int +vm_area_alloc_pages(gfp_t gfp, int nid, + unsigned int order, unsigned int nr_pages, struct page **pages) +{ + unsigned int nr_allocated = 0; + unsigned int nr_remaining = nr_pages; + unsigned int max_attempt_order = MAX_PAGE_ORDER; + struct page *page; + int i; + unsigned int large_order = ilog2(nr_remaining); + gfp_t large_gfp = vmalloc_gfp_adjust(gfp, large_order) & ~__GFP_DIRECT_RECLAIM; + + large_order = min(max_attempt_order, large_order); + + /* + * Initially, attempt to have the page allocator give us large order + * pages. Do not attempt allocating smaller than order chunks since + * __vmap_pages_range() expects physically contigous pages of exactly + * order long chunks. + */ + while (large_order > order && nr_remaining) { + if (nid == NUMA_NO_NODE) + page = alloc_pages_noprof(large_gfp, large_order); + else + page = alloc_pages_node_noprof(nid, large_gfp, large_order); + + if (unlikely(!page)) { + max_attempt_order = --large_order; + continue; + } + + split_page(page, large_order); + for (i = 0; i < (1U << large_order); i++) + pages[nr_allocated + i] = page + i; + + nr_allocated += 1U << large_order; + nr_remaining = nr_pages - nr_allocated; + + large_order = ilog2(nr_remaining); + large_order = min(max_attempt_order, large_order); + } + + /* + * For order-0 pages we make use of bulk allocator, if + * the page array is partly or not at all populated due + * to fails, fallback to a single page allocator that is + * more permissive. + */ + if (!order) { + while (nr_allocated < nr_pages) { + unsigned int nr, nr_pages_request; + + /* + * A maximum allowed request is hard-coded and is 100 + * pages per call. That is done in order to prevent a + * long preemption off scenario in the bulk-allocator + * so the range is [1:100]. + */ + nr_pages_request = min(100U, nr_pages - nr_allocated); + + /* memory allocation should consider mempolicy, we can't + * wrongly use nearest node when nid == NUMA_NO_NODE, + * otherwise memory may be allocated in only one node, + * but mempolicy wants to alloc memory by interleaving. + */ + if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE) + nr = alloc_pages_bulk_mempolicy_noprof(gfp, + nr_pages_request, + pages + nr_allocated); + else + nr = alloc_pages_bulk_node_noprof(gfp, nid, + nr_pages_request, + pages + nr_allocated); + + nr_allocated += nr; + + /* + * If zero or pages were obtained partly, + * fallback to a single page allocator. + */ + if (nr != nr_pages_request) + break; + } + } + + /* High-order pages or fallback path if "bulk" fails. */ + while (nr_allocated < nr_pages) { + if (!(gfp & __GFP_NOFAIL) && fatal_signal_pending(current)) + break; + + if (nid == NUMA_NO_NODE) + page = alloc_pages_noprof(gfp, order); + else + page = alloc_pages_node_noprof(nid, gfp, order); + + if (unlikely(!page)) + break; + + /* + * High-order allocations must be able to be treated as + * independent small pages by callers (as they can with + * small-page vmallocs). Some drivers do their own refcounting + * on vmalloc_to_page() pages, some use page->mapping, + * page->lru, etc. + */ + if (order) + split_page(page, order); + + /* + * Careful, we allocate and map page-order pages, but + * tracking is done per PAGE_SIZE page so as to keep the + * vm_struct APIs independent of the physical/mapped size. + */ + for (i = 0; i < (1U << order); i++) + pages[nr_allocated + i] = page + i; + + nr_allocated += 1U << order; + } + + return nr_allocated; +} + +static LLIST_HEAD(pending_vm_area_cleanup); +static void cleanup_vm_area_work(struct work_struct *work) +{ + struct vm_struct *area, *tmp; + struct llist_node *head; + + head = llist_del_all(&pending_vm_area_cleanup); + if (!head) + return; + + llist_for_each_entry_safe(area, tmp, head, llnode) { + if (!area->pages) + free_vm_area(area); + else + vfree(area->addr); + } +} + +/* + * Helper for __vmalloc_area_node() to defer cleanup + * of partially initialized vm_struct in error paths. + */ +static DECLARE_WORK(cleanup_vm_area, cleanup_vm_area_work); +static void defer_vm_area_cleanup(struct vm_struct *area) +{ + if (llist_add(&area->llnode, &pending_vm_area_cleanup)) + schedule_work(&cleanup_vm_area); +} + +/* + * Page tables allocations ignore external GFP. Enforces it by + * the memalloc scope API. It is used by vmalloc internals and + * KASAN shadow population only. + * + * GFP to scope mapping: + * + * non-blocking (no __GFP_DIRECT_RECLAIM) - memalloc_noreclaim_save() + * GFP_NOFS - memalloc_nofs_save() + * GFP_NOIO - memalloc_noio_save() + * + * Returns a flag cookie to pair with restore. + */ +unsigned int +memalloc_apply_gfp_scope(gfp_t gfp_mask) +{ + unsigned int flags = 0; + + if (!gfpflags_allow_blocking(gfp_mask)) + flags = memalloc_noreclaim_save(); + else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO) + flags = memalloc_nofs_save(); + else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0) + flags = memalloc_noio_save(); + + /* 0 - no scope applied. */ + return flags; +} + +void +memalloc_restore_scope(unsigned int flags) +{ + if (flags) + memalloc_flags_restore(flags); +} + static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, - pgprot_t prot, int node) + pgprot_t prot, unsigned int page_shift, + int node) { - struct page **pages; - unsigned int nr_pages, array_size, i; const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO; - const gfp_t alloc_mask = gfp_mask | __GFP_NOWARN; - const gfp_t highmem_mask = (gfp_mask & (GFP_DMA | GFP_DMA32)) ? - 0 : - __GFP_HIGHMEM; + bool nofail = gfp_mask & __GFP_NOFAIL; + unsigned long addr = (unsigned long)area->addr; + unsigned long size = get_vm_area_size(area); + unsigned long array_size; + unsigned int nr_small_pages = size >> PAGE_SHIFT; + unsigned int page_order; + unsigned int flags; + int ret; - nr_pages = get_vm_area_size(area) >> PAGE_SHIFT; - array_size = (nr_pages * sizeof(struct page *)); + array_size = (unsigned long)nr_small_pages * sizeof(struct page *); + + /* __GFP_NOFAIL and "noblock" flags are mutually exclusive. */ + if (!gfpflags_allow_blocking(gfp_mask)) + nofail = false; + + if (!(gfp_mask & (GFP_DMA | GFP_DMA32))) + gfp_mask |= __GFP_HIGHMEM; /* Please note that the recursion is strictly bounded. */ if (array_size > PAGE_SIZE) { - pages = __vmalloc_node(array_size, 1, nested_gfp|highmem_mask, - node, area->caller); + area->pages = __vmalloc_node_noprof(array_size, 1, nested_gfp, node, + area->caller); } else { - pages = kmalloc_node(array_size, nested_gfp, node); + area->pages = kmalloc_node_noprof(array_size, nested_gfp, node); } - if (!pages) { - remove_vm_area(area->addr); - kfree(area); - return NULL; + if (!area->pages) { + warn_alloc(gfp_mask, NULL, + "vmalloc error: size %lu, failed to allocated page array size %lu", + nr_small_pages * PAGE_SIZE, array_size); + goto fail; } - area->pages = pages; - area->nr_pages = nr_pages; + set_vm_area_page_order(area, page_shift - PAGE_SHIFT); + page_order = vm_area_page_order(area); - for (i = 0; i < area->nr_pages; i++) { - struct page *page; + /* + * High-order nofail allocations are really expensive and + * potentially dangerous (pre-mature OOM, disruptive reclaim + * and compaction etc. + * + * Please note, the __vmalloc_node_range_noprof() falls-back + * to order-0 pages if high-order attempt is unsuccessful. + */ + area->nr_pages = vm_area_alloc_pages( + vmalloc_gfp_adjust(gfp_mask, page_order), node, + page_order, nr_small_pages, area->pages); - if (node == NUMA_NO_NODE) - page = alloc_page(alloc_mask|highmem_mask); - else - page = alloc_pages_node(node, alloc_mask|highmem_mask, 0); + atomic_long_add(area->nr_pages, &nr_vmalloc_pages); + /* All pages of vm should be charged to same memcg, so use first one. */ + if (gfp_mask & __GFP_ACCOUNT && area->nr_pages) + mod_memcg_page_state(area->pages[0], MEMCG_VMALLOC, + area->nr_pages); - if (unlikely(!page)) { - /* Successfully allocated i pages, free them in __vunmap() */ - area->nr_pages = i; - atomic_long_add(area->nr_pages, &nr_vmalloc_pages); - goto fail; - } - area->pages[i] = page; - if (gfpflags_allow_blocking(gfp_mask)) - cond_resched(); + /* + * If not enough pages were obtained to accomplish an + * allocation request, free them via vfree() if any. + */ + if (area->nr_pages != nr_small_pages) { + /* + * vm_area_alloc_pages() can fail due to insufficient memory but + * also:- + * + * - a pending fatal signal + * - insufficient huge page-order pages + * + * Since we always retry allocations at order-0 in the huge page + * case a warning for either is spurious. + */ + if (!fatal_signal_pending(current) && page_order == 0) + warn_alloc(gfp_mask, NULL, + "vmalloc error: size %lu, failed to allocate pages", + area->nr_pages * PAGE_SIZE); + goto fail; } - atomic_long_add(area->nr_pages, &nr_vmalloc_pages); - if (map_kernel_range((unsigned long)area->addr, get_vm_area_size(area), - prot, pages) < 0) + /* + * page tables allocations ignore external gfp mask, enforce it + * by the scope API + */ + flags = memalloc_apply_gfp_scope(gfp_mask); + do { + ret = __vmap_pages_range(addr, addr + size, prot, area->pages, + page_shift, nested_gfp); + if (nofail && (ret < 0)) + schedule_timeout_uninterruptible(1); + } while (nofail && (ret < 0)); + memalloc_restore_scope(flags); + + if (ret < 0) { + warn_alloc(gfp_mask, NULL, + "vmalloc error: size %lu, failed to map pages", + area->nr_pages * PAGE_SIZE); goto fail; + } return area->addr; fail: - warn_alloc(gfp_mask, NULL, - "vmalloc: allocation failure, allocated %ld of %ld bytes", - (area->nr_pages*PAGE_SIZE), area->size); - __vfree(area->addr); + defer_vm_area_cleanup(area); return NULL; } +/* + * See __vmalloc_node_range() for a clear list of supported vmalloc flags. + * This gfp lists all flags currently passed through vmalloc. Currently, + * __GFP_ZERO is used by BPF and __GFP_NORETRY is used by percpu. Both drm + * and BPF also use GFP_USER. Additionally, various users pass + * GFP_KERNEL_ACCOUNT. Xfs uses __GFP_NOLOCKDEP. + */ +#define GFP_VMALLOC_SUPPORTED (GFP_KERNEL | GFP_ATOMIC | GFP_NOWAIT |\ + __GFP_NOFAIL | __GFP_ZERO | __GFP_NORETRY |\ + GFP_NOFS | GFP_NOIO | GFP_KERNEL_ACCOUNT |\ + GFP_USER | __GFP_NOLOCKDEP) + +static gfp_t vmalloc_fix_flags(gfp_t flags) +{ + gfp_t invalid_mask = flags & ~GFP_VMALLOC_SUPPORTED; + + flags &= GFP_VMALLOC_SUPPORTED; + WARN_ONCE(1, "Unexpected gfp: %#x (%pGg). Fixing up to gfp: %#x (%pGg). Fix your code!\n", + invalid_mask, &invalid_mask, flags, &flags); + return flags; +} + /** * __vmalloc_node_range - allocate virtually contiguous memory * @size: allocation size @@ -2516,32 +3954,118 @@ fail: * @caller: caller's return address * * Allocate enough pages to cover @size from the page level - * allocator with @gfp_mask flags. Map them into contiguous - * kernel virtual space, using a pagetable protection of @prot. + * allocator with @gfp_mask flags and map them into contiguous + * virtual range with protection @prot. + * + * Supported GFP classes: %GFP_KERNEL, %GFP_ATOMIC, %GFP_NOWAIT, + * %GFP_NOFS and %GFP_NOIO. Zone modifiers are not supported. + * Please note %GFP_ATOMIC and %GFP_NOWAIT are supported only + * by __vmalloc(). + * + * Retry modifiers: only %__GFP_NOFAIL is supported; %__GFP_NORETRY + * and %__GFP_RETRY_MAYFAIL are not supported. * + * %__GFP_NOWARN can be used to suppress failure messages. + * + * Can not be called from interrupt nor NMI contexts. * Return: the address of the area or %NULL on failure */ -void *__vmalloc_node_range(unsigned long size, unsigned long align, +void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller) { struct vm_struct *area; - void *addr; - unsigned long real_size = size; + void *ret; + kasan_vmalloc_flags_t kasan_flags = KASAN_VMALLOC_NONE; + unsigned long original_align = align; + unsigned int shift = PAGE_SHIFT; - size = PAGE_ALIGN(size); - if (!size || (size >> PAGE_SHIFT) > totalram_pages()) + if (WARN_ON_ONCE(!size)) + return NULL; + + if ((size >> PAGE_SHIFT) > totalram_pages()) { + warn_alloc(gfp_mask, NULL, + "vmalloc error: size %lu, exceeds total pages", + size); + return NULL; + } + + if (vmap_allow_huge && (vm_flags & VM_ALLOW_HUGE_VMAP)) { + /* + * Try huge pages. Only try for PAGE_KERNEL allocations, + * others like modules don't yet expect huge pages in + * their allocations due to apply_to_page_range not + * supporting them. + */ + + if (arch_vmap_pmd_supported(prot) && size >= PMD_SIZE) + shift = PMD_SHIFT; + else + shift = arch_vmap_pte_supported_shift(size); + + align = max(original_align, 1UL << shift); + } + +again: + area = __get_vm_area_node(size, align, shift, VM_ALLOC | + VM_UNINITIALIZED | vm_flags, start, end, node, + gfp_mask, caller); + if (!area) { + bool nofail = gfp_mask & __GFP_NOFAIL; + warn_alloc(gfp_mask, NULL, + "vmalloc error: size %lu, vm_struct allocation failed%s", + size, (nofail) ? ". Retrying." : ""); + if (nofail) { + schedule_timeout_uninterruptible(1); + goto again; + } goto fail; + } - area = __get_vm_area_node(real_size, align, VM_ALLOC | VM_UNINITIALIZED | - vm_flags, start, end, node, gfp_mask, caller); - if (!area) + /* + * Prepare arguments for __vmalloc_area_node() and + * kasan_unpoison_vmalloc(). + */ + if (pgprot_val(prot) == pgprot_val(PAGE_KERNEL)) { + if (kasan_hw_tags_enabled()) { + /* + * Modify protection bits to allow tagging. + * This must be done before mapping. + */ + prot = arch_vmap_pgprot_tagged(prot); + + /* + * Skip page_alloc poisoning and zeroing for physical + * pages backing VM_ALLOC mapping. Memory is instead + * poisoned and zeroed by kasan_unpoison_vmalloc(). + */ + gfp_mask |= __GFP_SKIP_KASAN | __GFP_SKIP_ZERO; + } + + /* Take note that the mapping is PAGE_KERNEL. */ + kasan_flags |= KASAN_VMALLOC_PROT_NORMAL; + } + + /* Allocate physical pages and map them into vmalloc space. */ + ret = __vmalloc_area_node(area, gfp_mask, prot, shift, node); + if (!ret) goto fail; - addr = __vmalloc_area_node(area, gfp_mask, prot, node); - if (!addr) - return NULL; + /* + * Mark the pages as accessible, now that they are mapped. + * The condition for setting KASAN_VMALLOC_INIT should complement the + * one in post_alloc_hook() with regards to the __GFP_SKIP_ZERO check + * to make sure that memory is initialized under the same conditions. + * Tag-based KASAN modes only assign tags to normal non-executable + * allocations, see __kasan_unpoison_vmalloc(). + */ + kasan_flags |= KASAN_VMALLOC_VM_ALLOC; + if (!want_init_on_free() && want_init_on_alloc(gfp_mask) && + (gfp_mask & __GFP_SKIP_ZERO)) + kasan_flags |= KASAN_VMALLOC_INIT; + /* KASAN_VMALLOC_PROT_NORMAL already set if required. */ + area->addr = kasan_unpoison_vmalloc(area->addr, size, kasan_flags); /* * In this function, newly allocated vm_struct has VM_UNINITIALIZED @@ -2550,13 +4074,18 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, */ clear_vm_uninitialized_flag(area); - kmemleak_vmalloc(area, size, gfp_mask); + if (!(vm_flags & VM_DEFER_KMEMLEAK)) + kmemleak_vmalloc(area, PAGE_ALIGN(size), gfp_mask); - return addr; + return area->addr; fail: - warn_alloc(gfp_mask, NULL, - "vmalloc: allocation failure: %lu bytes", real_size); + if (shift > PAGE_SHIFT) { + shift = PAGE_SHIFT; + align = original_align; + goto again; + } + return NULL; } @@ -2571,18 +4100,15 @@ fail: * Allocate enough pages to cover @size from the page level allocator with * @gfp_mask flags. Map them into contiguous kernel virtual space. * - * Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_RETRY_MAYFAIL - * and __GFP_NOFAIL are not supported - * - * Any use of gfp flags outside of GFP_KERNEL should be consulted - * with mm people. + * Semantics of @gfp_mask (including reclaim/retry modifiers such as + * __GFP_NOFAIL) are the same as in __vmalloc_node_range_noprof(). * * Return: pointer to the allocated memory or %NULL on error */ -void *__vmalloc_node(unsigned long size, unsigned long align, +void *__vmalloc_node_noprof(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) { - return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END, + return __vmalloc_node_range_noprof(size, align, VMALLOC_START, VMALLOC_END, gfp_mask, PAGE_KERNEL, 0, node, caller); } /* @@ -2591,15 +4117,17 @@ void *__vmalloc_node(unsigned long size, unsigned long align, * than that. */ #ifdef CONFIG_TEST_VMALLOC_MODULE -EXPORT_SYMBOL_GPL(__vmalloc_node); +EXPORT_SYMBOL_GPL(__vmalloc_node_noprof); #endif -void *__vmalloc(unsigned long size, gfp_t gfp_mask) +void *__vmalloc_noprof(unsigned long size, gfp_t gfp_mask) { - return __vmalloc_node(size, 1, gfp_mask, NUMA_NO_NODE, + if (unlikely(gfp_mask & ~GFP_VMALLOC_SUPPORTED)) + gfp_mask = vmalloc_fix_flags(gfp_mask); + return __vmalloc_node_noprof(size, 1, gfp_mask, NUMA_NO_NODE, __builtin_return_address(0)); } -EXPORT_SYMBOL(__vmalloc); +EXPORT_SYMBOL(__vmalloc_noprof); /** * vmalloc - allocate virtually contiguous memory @@ -2613,12 +4141,35 @@ EXPORT_SYMBOL(__vmalloc); * * Return: pointer to the allocated memory or %NULL on error */ -void *vmalloc(unsigned long size) +void *vmalloc_noprof(unsigned long size) { - return __vmalloc_node(size, 1, GFP_KERNEL, NUMA_NO_NODE, + return __vmalloc_node_noprof(size, 1, GFP_KERNEL, NUMA_NO_NODE, __builtin_return_address(0)); } -EXPORT_SYMBOL(vmalloc); +EXPORT_SYMBOL(vmalloc_noprof); + +/** + * vmalloc_huge_node - allocate virtually contiguous memory, allow huge pages + * @size: allocation size + * @gfp_mask: flags for the page level allocator + * @node: node to use for allocation or NUMA_NO_NODE + * + * Allocate enough pages to cover @size from the page level + * allocator and map them into contiguous kernel virtual space. + * If @size is greater than or equal to PMD_SIZE, allow using + * huge pages for the memory + * + * Return: pointer to the allocated memory or %NULL on error + */ +void *vmalloc_huge_node_noprof(unsigned long size, gfp_t gfp_mask, int node) +{ + if (unlikely(gfp_mask & ~GFP_VMALLOC_SUPPORTED)) + gfp_mask = vmalloc_fix_flags(gfp_mask); + return __vmalloc_node_range_noprof(size, 1, VMALLOC_START, VMALLOC_END, + gfp_mask, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP, + node, __builtin_return_address(0)); +} +EXPORT_SYMBOL_GPL(vmalloc_huge_node_noprof); /** * vzalloc - allocate virtually contiguous memory with zero fill @@ -2633,12 +4184,12 @@ EXPORT_SYMBOL(vmalloc); * * Return: pointer to the allocated memory or %NULL on error */ -void *vzalloc(unsigned long size) +void *vzalloc_noprof(unsigned long size) { - return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_ZERO, NUMA_NO_NODE, + return __vmalloc_node_noprof(size, 1, GFP_KERNEL | __GFP_ZERO, NUMA_NO_NODE, __builtin_return_address(0)); } -EXPORT_SYMBOL(vzalloc); +EXPORT_SYMBOL(vzalloc_noprof); /** * vmalloc_user - allocate zeroed virtually contiguous memory for userspace @@ -2649,14 +4200,14 @@ EXPORT_SYMBOL(vzalloc); * * Return: pointer to the allocated memory or %NULL on error */ -void *vmalloc_user(unsigned long size) +void *vmalloc_user_noprof(unsigned long size) { - return __vmalloc_node_range(size, SHMLBA, VMALLOC_START, VMALLOC_END, + return __vmalloc_node_range_noprof(size, SHMLBA, VMALLOC_START, VMALLOC_END, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL, VM_USERMAP, NUMA_NO_NODE, __builtin_return_address(0)); } -EXPORT_SYMBOL(vmalloc_user); +EXPORT_SYMBOL(vmalloc_user_noprof); /** * vmalloc_node - allocate memory on a specific node @@ -2671,12 +4222,12 @@ EXPORT_SYMBOL(vmalloc_user); * * Return: pointer to the allocated memory or %NULL on error */ -void *vmalloc_node(unsigned long size, int node) +void *vmalloc_node_noprof(unsigned long size, int node) { - return __vmalloc_node(size, 1, GFP_KERNEL, node, + return __vmalloc_node_noprof(size, 1, GFP_KERNEL, node, __builtin_return_address(0)); } -EXPORT_SYMBOL(vmalloc_node); +EXPORT_SYMBOL(vmalloc_node_noprof); /** * vzalloc_node - allocate memory on a specific node with zero fill @@ -2689,31 +4240,120 @@ EXPORT_SYMBOL(vmalloc_node); * * Return: pointer to the allocated memory or %NULL on error */ -void *vzalloc_node(unsigned long size, int node) +void *vzalloc_node_noprof(unsigned long size, int node) { - return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_ZERO, node, + return __vmalloc_node_noprof(size, 1, GFP_KERNEL | __GFP_ZERO, node, __builtin_return_address(0)); } -EXPORT_SYMBOL(vzalloc_node); +EXPORT_SYMBOL(vzalloc_node_noprof); /** - * vmalloc_exec - allocate virtually contiguous, executable memory - * @size: allocation size + * vrealloc_node_align_noprof - reallocate virtually contiguous memory; contents + * remain unchanged + * @p: object to reallocate memory for + * @size: the size to reallocate + * @align: requested alignment + * @flags: the flags for the page level allocator + * @nid: node number of the target node * - * Kernel-internal function to allocate enough pages to cover @size - * the page level allocator and map them into contiguous and - * executable kernel virtual space. + * If @p is %NULL, vrealloc_XXX() behaves exactly like vmalloc_XXX(). If @size + * is 0 and @p is not a %NULL pointer, the object pointed to is freed. * - * For tight control over page level allocator and protection flags - * use __vmalloc() instead. + * If the caller wants the new memory to be on specific node *only*, + * __GFP_THISNODE flag should be set, otherwise the function will try to avoid + * reallocation and possibly disregard the specified @nid. * - * Return: pointer to the allocated memory or %NULL on error + * If __GFP_ZERO logic is requested, callers must ensure that, starting with the + * initial memory allocation, every subsequent call to this API for the same + * memory allocation is flagged with __GFP_ZERO. Otherwise, it is possible that + * __GFP_ZERO is not fully honored by this API. + * + * Requesting an alignment that is bigger than the alignment of the existing + * allocation will fail. + * + * In any case, the contents of the object pointed to are preserved up to the + * lesser of the new and old sizes. + * + * This function must not be called concurrently with itself or vfree() for the + * same memory allocation. + * + * Return: pointer to the allocated memory; %NULL if @size is zero or in case of + * failure */ -void *vmalloc_exec(unsigned long size) +void *vrealloc_node_align_noprof(const void *p, size_t size, unsigned long align, + gfp_t flags, int nid) { - return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, - GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS, - NUMA_NO_NODE, __builtin_return_address(0)); + struct vm_struct *vm = NULL; + size_t alloced_size = 0; + size_t old_size = 0; + void *n; + + if (!size) { + vfree(p); + return NULL; + } + + if (p) { + vm = find_vm_area(p); + if (unlikely(!vm)) { + WARN(1, "Trying to vrealloc() nonexistent vm area (%p)\n", p); + return NULL; + } + + alloced_size = get_vm_area_size(vm); + old_size = vm->requested_size; + if (WARN(alloced_size < old_size, + "vrealloc() has mismatched area vs requested sizes (%p)\n", p)) + return NULL; + if (WARN(!IS_ALIGNED((unsigned long)p, align), + "will not reallocate with a bigger alignment (0x%lx)\n", align)) + return NULL; + if (unlikely(flags & __GFP_THISNODE) && nid != NUMA_NO_NODE && + nid != page_to_nid(vmalloc_to_page(p))) + goto need_realloc; + } + + /* + * TODO: Shrink the vm_area, i.e. unmap and free unused pages. What + * would be a good heuristic for when to shrink the vm_area? + */ + if (size <= old_size) { + /* Zero out "freed" memory, potentially for future realloc. */ + if (want_init_on_free() || want_init_on_alloc(flags)) + memset((void *)p + size, 0, old_size - size); + vm->requested_size = size; + kasan_poison_vmalloc(p + size, old_size - size); + return (void *)p; + } + + /* + * We already have the bytes available in the allocation; use them. + */ + if (size <= alloced_size) { + kasan_unpoison_vmalloc(p + old_size, size - old_size, + KASAN_VMALLOC_PROT_NORMAL); + /* + * No need to zero memory here, as unused memory will have + * already been zeroed at initial allocation time or during + * realloc shrink time. + */ + vm->requested_size = size; + return (void *)p; + } + +need_realloc: + /* TODO: Grow the vm_area, i.e. allocate and map additional pages. */ + n = __vmalloc_node_noprof(size, align, flags, nid, __builtin_return_address(0)); + + if (!n) + return NULL; + + if (p) { + memcpy(n, p, old_size); + vfree(p); + } + + return n; } #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32) @@ -2725,7 +4365,7 @@ void *vmalloc_exec(unsigned long size) * 64b systems should always have either DMA or DMA32 zones. For others * GFP_DMA32 should do the right thing and use the normal zone. */ -#define GFP_VMALLOC32 GFP_DMA32 | GFP_KERNEL +#define GFP_VMALLOC32 (GFP_DMA32 | GFP_KERNEL) #endif /** @@ -2737,12 +4377,12 @@ void *vmalloc_exec(unsigned long size) * * Return: pointer to the allocated memory or %NULL on error */ -void *vmalloc_32(unsigned long size) +void *vmalloc_32_noprof(unsigned long size) { - return __vmalloc_node(size, 1, GFP_VMALLOC32, NUMA_NO_NODE, + return __vmalloc_node_noprof(size, 1, GFP_VMALLOC32, NUMA_NO_NODE, __builtin_return_address(0)); } -EXPORT_SYMBOL(vmalloc_32); +EXPORT_SYMBOL(vmalloc_32_noprof); /** * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory @@ -2753,101 +4393,173 @@ EXPORT_SYMBOL(vmalloc_32); * * Return: pointer to the allocated memory or %NULL on error */ -void *vmalloc_32_user(unsigned long size) +void *vmalloc_32_user_noprof(unsigned long size) { - return __vmalloc_node_range(size, SHMLBA, VMALLOC_START, VMALLOC_END, + return __vmalloc_node_range_noprof(size, SHMLBA, VMALLOC_START, VMALLOC_END, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL, VM_USERMAP, NUMA_NO_NODE, __builtin_return_address(0)); } -EXPORT_SYMBOL(vmalloc_32_user); +EXPORT_SYMBOL(vmalloc_32_user_noprof); /* - * small helper routine , copy contents to buf from addr. - * If the page is not present, fill zero. + * Atomically zero bytes in the iterator. + * + * Returns the number of zeroed bytes. */ +static size_t zero_iter(struct iov_iter *iter, size_t count) +{ + size_t remains = count; + + while (remains > 0) { + size_t num, copied; + + num = min_t(size_t, remains, PAGE_SIZE); + copied = copy_page_to_iter_nofault(ZERO_PAGE(0), 0, num, iter); + remains -= copied; -static int aligned_vread(char *buf, char *addr, unsigned long count) + if (copied < num) + break; + } + + return count - remains; +} + +/* + * small helper routine, copy contents to iter from addr. + * If the page is not present, fill zero. + * + * Returns the number of copied bytes. + */ +static size_t aligned_vread_iter(struct iov_iter *iter, + const char *addr, size_t count) { - struct page *p; - int copied = 0; + size_t remains = count; + struct page *page; - while (count) { + while (remains > 0) { unsigned long offset, length; + size_t copied = 0; offset = offset_in_page(addr); length = PAGE_SIZE - offset; - if (length > count) - length = count; - p = vmalloc_to_page(addr); + if (length > remains) + length = remains; + page = vmalloc_to_page(addr); /* - * To do safe access to this _mapped_ area, we need - * lock. But adding lock here means that we need to add - * overhead of vmalloc()/vfree() calles for this _debug_ - * interface, rarely used. Instead of that, we'll use - * kmap() and get small overhead in this access function. + * To do safe access to this _mapped_ area, we need lock. But + * adding lock here means that we need to add overhead of + * vmalloc()/vfree() calls for this _debug_ interface, rarely + * used. Instead of that, we'll use an local mapping via + * copy_page_to_iter_nofault() and accept a small overhead in + * this access function. */ - if (p) { - /* - * we can expect USER0 is not used (see vread/vwrite's - * function description) - */ - void *map = kmap_atomic(p); - memcpy(buf, map + offset, length); - kunmap_atomic(map); - } else - memset(buf, 0, length); + if (page) + copied = copy_page_to_iter_nofault(page, offset, + length, iter); + else + copied = zero_iter(iter, length); + + addr += copied; + remains -= copied; - addr += length; - buf += length; - copied += length; - count -= length; + if (copied != length) + break; } - return copied; + + return count - remains; } -static int aligned_vwrite(char *buf, char *addr, unsigned long count) +/* + * Read from a vm_map_ram region of memory. + * + * Returns the number of copied bytes. + */ +static size_t vmap_ram_vread_iter(struct iov_iter *iter, const char *addr, + size_t count, unsigned long flags) { - struct page *p; - int copied = 0; + char *start; + struct vmap_block *vb; + struct xarray *xa; + unsigned long offset; + unsigned int rs, re; + size_t remains, n; - while (count) { - unsigned long offset, length; + /* + * If it's area created by vm_map_ram() interface directly, but + * not further subdividing and delegating management to vmap_block, + * handle it here. + */ + if (!(flags & VMAP_BLOCK)) + return aligned_vread_iter(iter, addr, count); - offset = offset_in_page(addr); - length = PAGE_SIZE - offset; - if (length > count) - length = count; - p = vmalloc_to_page(addr); - /* - * To do safe access to this _mapped_ area, we need - * lock. But adding lock here means that we need to add - * overhead of vmalloc()/vfree() calles for this _debug_ - * interface, rarely used. Instead of that, we'll use - * kmap() and get small overhead in this access function. - */ - if (p) { - /* - * we can expect USER0 is not used (see vread/vwrite's - * function description) - */ - void *map = kmap_atomic(p); - memcpy(map + offset, buf, length); - kunmap_atomic(map); + remains = count; + + /* + * Area is split into regions and tracked with vmap_block, read out + * each region and zero fill the hole between regions. + */ + xa = addr_to_vb_xa((unsigned long) addr); + vb = xa_load(xa, addr_to_vb_idx((unsigned long)addr)); + if (!vb) + goto finished_zero; + + spin_lock(&vb->lock); + if (bitmap_empty(vb->used_map, VMAP_BBMAP_BITS)) { + spin_unlock(&vb->lock); + goto finished_zero; + } + + for_each_set_bitrange(rs, re, vb->used_map, VMAP_BBMAP_BITS) { + size_t copied; + + if (remains == 0) + goto finished; + + start = vmap_block_vaddr(vb->va->va_start, rs); + + if (addr < start) { + size_t to_zero = min_t(size_t, start - addr, remains); + size_t zeroed = zero_iter(iter, to_zero); + + addr += zeroed; + remains -= zeroed; + + if (remains == 0 || zeroed != to_zero) + goto finished; } - addr += length; - buf += length; - copied += length; - count -= length; + + /*it could start reading from the middle of used region*/ + offset = offset_in_page(addr); + n = ((re - rs + 1) << PAGE_SHIFT) - offset; + if (n > remains) + n = remains; + + copied = aligned_vread_iter(iter, start + offset, n); + + addr += copied; + remains -= copied; + + if (copied != n) + goto finished; } - return copied; + + spin_unlock(&vb->lock); + +finished_zero: + /* zero-fill the left dirty or free regions */ + return count - remains + zero_iter(iter, remains); +finished: + /* We couldn't copy/zero everything */ + spin_unlock(&vb->lock); + return count - remains; } /** - * vread() - read vmalloc area in a safe way. - * @buf: buffer for reading data - * @addr: vm address. - * @count: number of bytes to be read. + * vread_iter() - read vmalloc area in a safe way to an iterator. + * @iter: the iterator to which data should be written. + * @addr: vm address. + * @count: number of bytes to be read. * * This function checks that addr is a valid vmalloc'ed area, and * copy data from that area to a given buffer. If the given memory range @@ -2861,139 +4573,111 @@ static int aligned_vwrite(char *buf, char *addr, unsigned long count) * Note: In usual ops, vread() is never necessary because the caller * should know vmalloc() area is valid and can use memcpy(). * This is for routines which have to access vmalloc area without - * any information, as /dev/kmem. + * any information, as /proc/kcore. * * Return: number of bytes for which addr and buf should be increased * (same number as @count) or %0 if [addr...addr+count) doesn't * include any intersection with valid vmalloc area */ -long vread(char *buf, char *addr, unsigned long count) +long vread_iter(struct iov_iter *iter, const char *addr, size_t count) { + struct vmap_node *vn; struct vmap_area *va; struct vm_struct *vm; - char *vaddr, *buf_start = buf; - unsigned long buflen = count; - unsigned long n; + char *vaddr; + size_t n, size, flags, remains; + unsigned long next; + + addr = kasan_reset_tag(addr); /* Don't allow overflow */ if ((unsigned long) addr + count < count) count = -(unsigned long) addr; - spin_lock(&vmap_area_lock); - list_for_each_entry(va, &vmap_area_list, list) { - if (!count) - break; + remains = count; - if (!va->vm) - continue; + vn = find_vmap_area_exceed_addr_lock((unsigned long) addr, &va); + if (!vn) + goto finished_zero; + + /* no intersects with alive vmap_area */ + if ((unsigned long)addr + remains <= va->va_start) + goto finished_zero; + + do { + size_t copied; + + if (remains == 0) + goto finished; vm = va->vm; - vaddr = (char *) vm->addr; - if (addr >= vaddr + get_vm_area_size(vm)) - continue; - while (addr < vaddr) { - if (count == 0) - goto finished; - *buf = '\0'; - buf++; - addr++; - count--; - } - n = vaddr + get_vm_area_size(vm) - addr; - if (n > count) - n = count; - if (!(vm->flags & VM_IOREMAP)) - aligned_vread(buf, addr, n); - else /* IOREMAP area is treated as memory hole */ - memset(buf, 0, n); - buf += n; - addr += n; - count -= n; - } -finished: - spin_unlock(&vmap_area_lock); + flags = va->flags & VMAP_FLAGS_MASK; + /* + * VMAP_BLOCK indicates a sub-type of vm_map_ram area, need + * be set together with VMAP_RAM. + */ + WARN_ON(flags == VMAP_BLOCK); - if (buf == buf_start) - return 0; - /* zero-fill memory holes */ - if (buf != buf_start + buflen) - memset(buf, 0, buflen - (buf - buf_start)); + if (!vm && !flags) + goto next_va; - return buflen; -} + if (vm && (vm->flags & VM_UNINITIALIZED)) + goto next_va; -/** - * vwrite() - write vmalloc area in a safe way. - * @buf: buffer for source data - * @addr: vm address. - * @count: number of bytes to be read. - * - * This function checks that addr is a valid vmalloc'ed area, and - * copy data from a buffer to the given addr. If specified range of - * [addr...addr+count) includes some valid address, data is copied from - * proper area of @buf. If there are memory holes, no copy to hole. - * IOREMAP area is treated as memory hole and no copy is done. - * - * If [addr...addr+count) doesn't includes any intersects with alive - * vm_struct area, returns 0. @buf should be kernel's buffer. - * - * Note: In usual ops, vwrite() is never necessary because the caller - * should know vmalloc() area is valid and can use memcpy(). - * This is for routines which have to access vmalloc area without - * any information, as /dev/kmem. - * - * Return: number of bytes for which addr and buf should be - * increased (same number as @count) or %0 if [addr...addr+count) - * doesn't include any intersection with valid vmalloc area - */ -long vwrite(char *buf, char *addr, unsigned long count) -{ - struct vmap_area *va; - struct vm_struct *vm; - char *vaddr; - unsigned long n, buflen; - int copied = 0; + /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ + smp_rmb(); - /* Don't allow overflow */ - if ((unsigned long) addr + count < count) - count = -(unsigned long) addr; - buflen = count; + vaddr = (char *) va->va_start; + size = vm ? get_vm_area_size(vm) : va_size(va); - spin_lock(&vmap_area_lock); - list_for_each_entry(va, &vmap_area_list, list) { - if (!count) - break; + if (addr >= vaddr + size) + goto next_va; - if (!va->vm) - continue; + if (addr < vaddr) { + size_t to_zero = min_t(size_t, vaddr - addr, remains); + size_t zeroed = zero_iter(iter, to_zero); - vm = va->vm; - vaddr = (char *) vm->addr; - if (addr >= vaddr + get_vm_area_size(vm)) - continue; - while (addr < vaddr) { - if (count == 0) + addr += zeroed; + remains -= zeroed; + + if (remains == 0 || zeroed != to_zero) goto finished; - buf++; - addr++; - count--; - } - n = vaddr + get_vm_area_size(vm) - addr; - if (n > count) - n = count; - if (!(vm->flags & VM_IOREMAP)) { - aligned_vwrite(buf, addr, n); - copied++; } - buf += n; - addr += n; - count -= n; - } + + n = vaddr + size - addr; + if (n > remains) + n = remains; + + if (flags & VMAP_RAM) + copied = vmap_ram_vread_iter(iter, addr, n, flags); + else if (!(vm && (vm->flags & (VM_IOREMAP | VM_SPARSE)))) + copied = aligned_vread_iter(iter, addr, n); + else /* IOREMAP | SPARSE area is treated as memory hole */ + copied = zero_iter(iter, n); + + addr += copied; + remains -= copied; + + if (copied != n) + goto finished; + + next_va: + next = va->va_end; + spin_unlock(&vn->busy.lock); + } while ((vn = find_vmap_area_exceed_addr_lock(next, &va))); + +finished_zero: + if (vn) + spin_unlock(&vn->busy.lock); + + /* zero-fill memory holes */ + return count - remains + zero_iter(iter, remains); finished: - spin_unlock(&vmap_area_lock); - if (!copied) - return 0; - return buflen; + /* Nothing remains, or We couldn't copy/zero everything. */ + if (vn) + spin_unlock(&vn->busy.lock); + + return count - remains; } /** @@ -3054,11 +4738,10 @@ int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, size -= PAGE_SIZE; } while (size > 0); - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP); return 0; } -EXPORT_SYMBOL(remap_vmalloc_range_partial); /** * remap_vmalloc_range - map vmalloc pages to userspace @@ -3083,54 +4766,6 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, } EXPORT_SYMBOL(remap_vmalloc_range); -static int f(pte_t *pte, unsigned long addr, void *data) -{ - pte_t ***p = data; - - if (p) { - *(*p) = pte; - (*p)++; - } - return 0; -} - -/** - * alloc_vm_area - allocate a range of kernel address space - * @size: size of the area - * @ptes: returns the PTEs for the address space - * - * Returns: NULL on failure, vm_struct on success - * - * This function reserves a range of kernel address space, and - * allocates pagetables to map that range. No actual mappings - * are created. - * - * If @ptes is non-NULL, pointers to the PTEs (in init_mm) - * allocated for the VM area are returned. - */ -struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes) -{ - struct vm_struct *area; - - area = get_vm_area_caller(size, VM_IOREMAP, - __builtin_return_address(0)); - if (area == NULL) - return NULL; - - /* - * This ensures that page tables are constructed for this region - * of kernel virtual address space and mapped into init_mm. - */ - if (apply_to_page_range(&init_mm, (unsigned long)area->addr, - size, f, ptes ? &ptes : NULL)) { - free_vm_area(area); - return NULL; - } - - return area; -} -EXPORT_SYMBOL_GPL(alloc_vm_area); - void free_vm_area(struct vm_struct *area) { struct vm_struct *ret; @@ -3186,6 +4821,7 @@ pvm_find_va_enclose_addr(unsigned long addr) * @va: * in - the VA we start the search(reverse order); * out - the VA with the highest aligned end address. + * @align: alignment for required highest address * * Returns: determined end address within vmap_area */ @@ -3242,7 +4878,6 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, int area, area2, last_area, term_area; unsigned long base, start, size, end, last_end, orig_start, orig_end; bool purged = false; - enum fit_type type; /* verify parameters and allocate data structures */ BUG_ON(offset_in_page(align) || !is_power_of_2(align)); @@ -3353,15 +4988,12 @@ retry: /* It is a BUG(), but trigger recovery instead. */ goto recovery; - type = classify_va_fit_type(va, start, size); - if (WARN_ON_ONCE(type == NOTHING_FIT)) + ret = va_clip(&free_vmap_area_root, + &free_vmap_area_list, va, start, size); + if (WARN_ON_ONCE(unlikely(ret))) /* It is a BUG(), but trigger recovery instead. */ goto recovery; - ret = adjust_va_to_fit_type(va, start, size, type); - if (unlikely(ret)) - goto recovery; - /* Allocated area. */ va = vas[area]; va->va_start = start; @@ -3372,22 +5004,30 @@ retry: /* populate the kasan shadow space */ for (area = 0; area < nr_vms; area++) { - if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area])) + if (kasan_populate_vmalloc(vas[area]->va_start, sizes[area], GFP_KERNEL)) goto err_free_shadow; - - kasan_unpoison_vmalloc((void *)vas[area]->va_start, - sizes[area]); } /* insert all vm's */ - spin_lock(&vmap_area_lock); for (area = 0; area < nr_vms; area++) { - insert_vmap_area(vas[area], &vmap_area_root, &vmap_area_list); + struct vmap_node *vn = addr_to_node(vas[area]->va_start); - setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, + spin_lock(&vn->busy.lock); + insert_vmap_area(vas[area], &vn->busy.root, &vn->busy.head); + setup_vmalloc_vm(vms[area], vas[area], VM_ALLOC, pcpu_get_vm_areas); + spin_unlock(&vn->busy.lock); } - spin_unlock(&vmap_area_lock); + + /* + * Mark allocated areas as accessible. Do it now as a best-effort + * approach, as they can be mapped outside of vmalloc code. + * With hardware tag-based KASAN, marking is skipped for + * non-VM_ALLOC mappings, see __kasan_unpoison_vmalloc(). + */ + for (area = 0; area < nr_vms; area++) + vms[area]->addr = kasan_unpoison_vmalloc(vms[area]->addr, + vms[area]->size, KASAN_VMALLOC_PROT_NORMAL); kfree(vas); return vms; @@ -3402,17 +5042,19 @@ recovery: while (area--) { orig_start = vas[area]->va_start; orig_end = vas[area]->va_end; - va = merge_or_add_vmap_area(vas[area], &free_vmap_area_root, - &free_vmap_area_list); - kasan_release_vmalloc(orig_start, orig_end, - va->va_start, va->va_end); + va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root, + &free_vmap_area_list); + if (va) + kasan_release_vmalloc(orig_start, orig_end, + va->va_start, va->va_end, + KASAN_VMALLOC_PAGE_RANGE | KASAN_VMALLOC_TLB_FLUSH); vas[area] = NULL; } overflow: spin_unlock(&free_vmap_area_lock); if (!purged) { - purge_vmap_area_lazy(); + reclaim_and_purge_vmap_areas(); purged = true; /* Before "retry", check if we recover. */ @@ -3451,10 +5093,12 @@ err_free_shadow: for (area = 0; area < nr_vms; area++) { orig_start = vas[area]->va_start; orig_end = vas[area]->va_end; - va = merge_or_add_vmap_area(vas[area], &free_vmap_area_root, - &free_vmap_area_list); - kasan_release_vmalloc(orig_start, orig_end, - va->va_start, va->va_end); + va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root, + &free_vmap_area_list); + if (va) + kasan_release_vmalloc(orig_start, orig_end, + va->va_start, va->va_end, + KASAN_VMALLOC_PAGE_RANGE | KASAN_VMALLOC_TLB_FLUSH); vas[area] = NULL; kfree(vms[area]); } @@ -3481,153 +5125,350 @@ void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) } #endif /* CONFIG_SMP */ -#ifdef CONFIG_PROC_FS -static void *s_start(struct seq_file *m, loff_t *pos) - __acquires(&vmap_purge_lock) - __acquires(&vmap_area_lock) +#ifdef CONFIG_PRINTK +bool vmalloc_dump_obj(void *object) { - mutex_lock(&vmap_purge_lock); - spin_lock(&vmap_area_lock); + const void *caller; + struct vm_struct *vm; + struct vmap_area *va; + struct vmap_node *vn; + unsigned long addr; + unsigned int nr_pages; - return seq_list_start(&vmap_area_list, *pos); -} + addr = PAGE_ALIGN((unsigned long) object); + vn = addr_to_node(addr); -static void *s_next(struct seq_file *m, void *p, loff_t *pos) -{ - return seq_list_next(p, &vmap_area_list, pos); -} + if (!spin_trylock(&vn->busy.lock)) + return false; -static void s_stop(struct seq_file *m, void *p) - __releases(&vmap_purge_lock) - __releases(&vmap_area_lock) -{ - mutex_unlock(&vmap_purge_lock); - spin_unlock(&vmap_area_lock); -} + va = __find_vmap_area(addr, &vn->busy.root); + if (!va || !va->vm) { + spin_unlock(&vn->busy.lock); + return false; + } -static void show_numa_info(struct seq_file *m, struct vm_struct *v) -{ - if (IS_ENABLED(CONFIG_NUMA)) { - unsigned int nr, *counters = m->private; + vm = va->vm; + addr = (unsigned long) vm->addr; + caller = vm->caller; + nr_pages = vm->nr_pages; + spin_unlock(&vn->busy.lock); - if (!counters) - return; + pr_cont(" %u-page vmalloc region starting at %#lx allocated at %pS\n", + nr_pages, addr, caller); - if (v->flags & VM_UNINITIALIZED) - return; - /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ - smp_rmb(); + return true; +} +#endif - memset(counters, 0, nr_node_ids * sizeof(unsigned int)); +#ifdef CONFIG_PROC_FS - for (nr = 0; nr < v->nr_pages; nr++) - counters[page_to_nid(v->pages[nr])]++; +/* + * Print number of pages allocated on each memory node. + * + * This function can only be called if CONFIG_NUMA is enabled + * and VM_UNINITIALIZED bit in v->flags is disabled. + */ +static void show_numa_info(struct seq_file *m, struct vm_struct *v, + unsigned int *counters) +{ + unsigned int nr; + unsigned int step = 1U << vm_area_page_order(v); - for_each_node_state(nr, N_HIGH_MEMORY) - if (counters[nr]) - seq_printf(m, " N%u=%u", nr, counters[nr]); - } + if (!counters) + return; + + memset(counters, 0, nr_node_ids * sizeof(unsigned int)); + + for (nr = 0; nr < v->nr_pages; nr += step) + counters[page_to_nid(v->pages[nr])] += step; + for_each_node_state(nr, N_HIGH_MEMORY) + if (counters[nr]) + seq_printf(m, " N%u=%u", nr, counters[nr]); } static void show_purge_info(struct seq_file *m) { - struct llist_node *head; + struct vmap_node *vn; struct vmap_area *va; - head = READ_ONCE(vmap_purge_list.first); - if (head == NULL) - return; - - llist_for_each_entry(va, head, purge_list) { - seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n", - (void *)va->va_start, (void *)va->va_end, - va->va_end - va->va_start); + for_each_vmap_node(vn) { + spin_lock(&vn->lazy.lock); + list_for_each_entry(va, &vn->lazy.head, list) { + seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n", + (void *)va->va_start, (void *)va->va_end, + va_size(va)); + } + spin_unlock(&vn->lazy.lock); } } -static int s_show(struct seq_file *m, void *p) +static int vmalloc_info_show(struct seq_file *m, void *p) { + struct vmap_node *vn; struct vmap_area *va; struct vm_struct *v; + unsigned int *counters; - va = list_entry(p, struct vmap_area, list); + if (IS_ENABLED(CONFIG_NUMA)) + counters = kmalloc_array(nr_node_ids, sizeof(unsigned int), GFP_KERNEL); - /* - * s_show can encounter race with remove_vm_area, !vm on behalf - * of vmap area is being tear down or vm_map_ram allocation. - */ - if (!va->vm) { - seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n", - (void *)va->va_start, (void *)va->va_end, - va->va_end - va->va_start); + for_each_vmap_node(vn) { + spin_lock(&vn->busy.lock); + list_for_each_entry(va, &vn->busy.head, list) { + if (!va->vm) { + if (va->flags & VMAP_RAM) + seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n", + (void *)va->va_start, (void *)va->va_end, + va_size(va)); - return 0; - } + continue; + } + + v = va->vm; + if (v->flags & VM_UNINITIALIZED) + continue; + + /* Pair with smp_wmb() in clear_vm_uninitialized_flag() */ + smp_rmb(); - v = va->vm; + seq_printf(m, "0x%pK-0x%pK %7ld", + v->addr, v->addr + v->size, v->size); - seq_printf(m, "0x%pK-0x%pK %7ld", - v->addr, v->addr + v->size, v->size); + if (v->caller) + seq_printf(m, " %pS", v->caller); - if (v->caller) - seq_printf(m, " %pS", v->caller); + if (v->nr_pages) + seq_printf(m, " pages=%d", v->nr_pages); - if (v->nr_pages) - seq_printf(m, " pages=%d", v->nr_pages); + if (v->phys_addr) + seq_printf(m, " phys=%pa", &v->phys_addr); - if (v->phys_addr) - seq_printf(m, " phys=%pa", &v->phys_addr); + if (v->flags & VM_IOREMAP) + seq_puts(m, " ioremap"); - if (v->flags & VM_IOREMAP) - seq_puts(m, " ioremap"); + if (v->flags & VM_SPARSE) + seq_puts(m, " sparse"); - if (v->flags & VM_ALLOC) - seq_puts(m, " vmalloc"); + if (v->flags & VM_ALLOC) + seq_puts(m, " vmalloc"); - if (v->flags & VM_MAP) - seq_puts(m, " vmap"); + if (v->flags & VM_MAP) + seq_puts(m, " vmap"); - if (v->flags & VM_USERMAP) - seq_puts(m, " user"); + if (v->flags & VM_USERMAP) + seq_puts(m, " user"); - if (v->flags & VM_DMA_COHERENT) - seq_puts(m, " dma-coherent"); + if (v->flags & VM_DMA_COHERENT) + seq_puts(m, " dma-coherent"); - if (is_vmalloc_addr(v->pages)) - seq_puts(m, " vpages"); + if (is_vmalloc_addr(v->pages)) + seq_puts(m, " vpages"); - show_numa_info(m, v); - seq_putc(m, '\n'); + if (IS_ENABLED(CONFIG_NUMA)) + show_numa_info(m, v, counters); + + seq_putc(m, '\n'); + } + spin_unlock(&vn->busy.lock); + } /* - * As a final step, dump "unpurged" areas. Note, - * that entire "/proc/vmallocinfo" output will not - * be address sorted, because the purge list is not - * sorted. + * As a final step, dump "unpurged" areas. */ - if (list_is_last(&va->list, &vmap_area_list)) - show_purge_info(m); - + show_purge_info(m); + if (IS_ENABLED(CONFIG_NUMA)) + kfree(counters); return 0; } -static const struct seq_operations vmalloc_op = { - .start = s_start, - .next = s_next, - .stop = s_stop, - .show = s_show, -}; - static int __init proc_vmalloc_init(void) { - if (IS_ENABLED(CONFIG_NUMA)) - proc_create_seq_private("vmallocinfo", 0400, NULL, - &vmalloc_op, - nr_node_ids * sizeof(unsigned int), NULL); - else - proc_create_seq("vmallocinfo", 0400, NULL, &vmalloc_op); + proc_create_single("vmallocinfo", 0400, NULL, vmalloc_info_show); return 0; } module_init(proc_vmalloc_init); #endif + +static void __init vmap_init_free_space(void) +{ + unsigned long vmap_start = 1; + const unsigned long vmap_end = ULONG_MAX; + struct vmap_area *free; + struct vm_struct *busy; + + /* + * B F B B B F + * -|-----|.....|-----|-----|-----|.....|- + * | The KVA space | + * |<--------------------------------->| + */ + for (busy = vmlist; busy; busy = busy->next) { + if ((unsigned long) busy->addr - vmap_start > 0) { + free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); + if (!WARN_ON_ONCE(!free)) { + free->va_start = vmap_start; + free->va_end = (unsigned long) busy->addr; + + insert_vmap_area_augment(free, NULL, + &free_vmap_area_root, + &free_vmap_area_list); + } + } + + vmap_start = (unsigned long) busy->addr + busy->size; + } + + if (vmap_end - vmap_start > 0) { + free = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); + if (!WARN_ON_ONCE(!free)) { + free->va_start = vmap_start; + free->va_end = vmap_end; + + insert_vmap_area_augment(free, NULL, + &free_vmap_area_root, + &free_vmap_area_list); + } + } +} + +static void vmap_init_nodes(void) +{ + struct vmap_node *vn; + int i; + +#if BITS_PER_LONG == 64 + /* + * A high threshold of max nodes is fixed and bound to 128, + * thus a scale factor is 1 for systems where number of cores + * are less or equal to specified threshold. + * + * As for NUMA-aware notes. For bigger systems, for example + * NUMA with multi-sockets, where we can end-up with thousands + * of cores in total, a "sub-numa-clustering" should be added. + * + * In this case a NUMA domain is considered as a single entity + * with dedicated sub-nodes in it which describe one group or + * set of cores. Therefore a per-domain purging is supposed to + * be added as well as a per-domain balancing. + */ + int n = clamp_t(unsigned int, num_possible_cpus(), 1, 128); + + if (n > 1) { + vn = kmalloc_array(n, sizeof(*vn), GFP_NOWAIT); + if (vn) { + /* Node partition is 16 pages. */ + vmap_zone_size = (1 << 4) * PAGE_SIZE; + nr_vmap_nodes = n; + vmap_nodes = vn; + } else { + pr_err("Failed to allocate an array. Disable a node layer\n"); + } + } +#endif + + for_each_vmap_node(vn) { + vn->busy.root = RB_ROOT; + INIT_LIST_HEAD(&vn->busy.head); + spin_lock_init(&vn->busy.lock); + + vn->lazy.root = RB_ROOT; + INIT_LIST_HEAD(&vn->lazy.head); + spin_lock_init(&vn->lazy.lock); + + for (i = 0; i < MAX_VA_SIZE_PAGES; i++) { + INIT_LIST_HEAD(&vn->pool[i].head); + WRITE_ONCE(vn->pool[i].len, 0); + } + + spin_lock_init(&vn->pool_lock); + } +} + +static unsigned long +vmap_node_shrink_count(struct shrinker *shrink, struct shrink_control *sc) +{ + unsigned long count = 0; + struct vmap_node *vn; + int i; + + for_each_vmap_node(vn) { + for (i = 0; i < MAX_VA_SIZE_PAGES; i++) + count += READ_ONCE(vn->pool[i].len); + } + + return count ? count : SHRINK_EMPTY; +} + +static unsigned long +vmap_node_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) +{ + struct vmap_node *vn; + + for_each_vmap_node(vn) + decay_va_pool_node(vn, true); + + return SHRINK_STOP; +} + +void __init vmalloc_init(void) +{ + struct shrinker *vmap_node_shrinker; + struct vmap_area *va; + struct vmap_node *vn; + struct vm_struct *tmp; + int i; + + /* + * Create the cache for vmap_area objects. + */ + vmap_area_cachep = KMEM_CACHE(vmap_area, SLAB_PANIC); + + for_each_possible_cpu(i) { + struct vmap_block_queue *vbq; + struct vfree_deferred *p; + + vbq = &per_cpu(vmap_block_queue, i); + spin_lock_init(&vbq->lock); + INIT_LIST_HEAD(&vbq->free); + p = &per_cpu(vfree_deferred, i); + init_llist_head(&p->list); + INIT_WORK(&p->wq, delayed_vfree_work); + xa_init(&vbq->vmap_blocks); + } + + /* + * Setup nodes before importing vmlist. + */ + vmap_init_nodes(); + + /* Import existing vmlist entries. */ + for (tmp = vmlist; tmp; tmp = tmp->next) { + va = kmem_cache_zalloc(vmap_area_cachep, GFP_NOWAIT); + if (WARN_ON_ONCE(!va)) + continue; + + va->va_start = (unsigned long)tmp->addr; + va->va_end = va->va_start + tmp->size; + va->vm = tmp; + + vn = addr_to_node(va->va_start); + insert_vmap_area(va, &vn->busy.root, &vn->busy.head); + } + + /* + * Now we can initialize a free vmap space. + */ + vmap_init_free_space(); + vmap_initialized = true; + + vmap_node_shrinker = shrinker_alloc(0, "vmap-node"); + if (!vmap_node_shrinker) { + pr_err("Failed to allocate vmap-node shrinker!\n"); + return; + } + + vmap_node_shrinker->count_objects = vmap_node_shrink_count; + vmap_node_shrinker->scan_objects = vmap_node_shrink_scan; + shrinker_register(vmap_node_shrinker); +} |