summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorNicholas Piggin <npiggin@gmail.com>2021-04-29 22:58:49 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-04-30 11:20:40 -0700
commit121e6f3258fe393e22c36f61a319be8a4f2c05ae (patch)
tree0e4b1115e5964be35140a54e60d625f6a25d26c6 /mm
parent5d87510de15f31d1b26cffced7bc4d504539a2c7 (diff)
mm/vmalloc: hugepage vmalloc mappings
Support huge page vmalloc mappings. Config option HAVE_ARCH_HUGE_VMALLOC enables support on architectures that define HAVE_ARCH_HUGE_VMAP and supports PMD sized vmap mappings. vmalloc will attempt to allocate PMD-sized pages if allocating PMD size or larger, and fall back to small pages if that was unsuccessful. Architectures must ensure that any arch specific vmalloc allocations that require PAGE_SIZE mappings (e.g., module allocations vs strict module rwx) use the VM_NOHUGE flag to inhibit larger mappings. This can result in more internal fragmentation and memory overhead for a given allocation, an option nohugevmalloc is added to disable at boot. [colin.king@canonical.com: fix read of uninitialized pointer area] Link: https://lkml.kernel.org/r/20210318155955.18220-1-colin.king@canonical.com Link: https://lkml.kernel.org/r/20210317062402.533919-14-npiggin@gmail.com Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Ding Tianhong <dingtianhong@huawei.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Russell King <linux@armlinux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Uladzislau Rezki (Sony) <urezki@gmail.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/page_alloc.c5
-rw-r--r--mm/vmalloc.c220
2 files changed, 177 insertions, 48 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 56a8103580d6..39ff5c604cef 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -72,6 +72,7 @@
#include <linux/padata.h>
#include <linux/khugepaged.h>
#include <linux/buffer_head.h>
+#include <linux/vmalloc.h>
#include <asm/sections.h>
#include <asm/tlbflush.h>
@@ -8222,6 +8223,7 @@ void *__init alloc_large_system_hash(const char *tablename,
void *table = NULL;
gfp_t gfp_flags;
bool virt;
+ bool huge;
/* allow the kernel cmdline to have a say */
if (!numentries) {
@@ -8289,6 +8291,7 @@ void *__init alloc_large_system_hash(const char *tablename,
} else if (get_order(size) >= MAX_ORDER || hashdist) {
table = __vmalloc(size, gfp_flags);
virt = true;
+ huge = is_vm_area_hugepages(table);
} else {
/*
* If bucketsize is not a power-of-two, we may free
@@ -8305,7 +8308,7 @@ void *__init alloc_large_system_hash(const char *tablename,
pr_info("%s hash table entries: %ld (order: %d, %lu bytes, %s)\n",
tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size,
- virt ? "vmalloc" : "linear");
+ virt ? (huge ? "vmalloc hugepage" : "vmalloc") : "linear");
if (_hash_shift)
*_hash_shift = log2qty;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 41c1dbdd2677..59c815eb7e74 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -42,6 +42,19 @@
#include "internal.h"
#include "pgalloc-track.h"
+#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;
@@ -483,31 +496,12 @@ static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long addr,
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;
@@ -529,6 +523,66 @@ int map_kernel_range_noflush(unsigned long addr, unsigned long size,
return 0;
}
+static 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),
+ __pa(page_address(pages[i])), prot,
+ page_shift);
+ if (err)
+ return err;
+
+ addr += 1UL << page_shift;
+ }
+
+ return 0;
+}
+
+static int vmap_pages_range(unsigned long addr, unsigned long end,
+ pgprot_t prot, struct page **pages, unsigned int page_shift)
+{
+ int err;
+
+ err = vmap_pages_range_noflush(addr, end, prot, pages, page_shift);
+ flush_cache_vmap(addr, end);
+ return err;
+}
+
+/**
+ * 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)
+{
+ return vmap_pages_range_noflush(addr, addr + size, prot, pages, PAGE_SHIFT);
+}
+
int map_kernel_range(unsigned long start, unsigned long size, pgprot_t prot,
struct page **pages)
{
@@ -2112,6 +2166,24 @@ 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
+}
+
+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
@@ -2422,6 +2494,7 @@ 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]);
@@ -2431,6 +2504,7 @@ static inline void set_area_direct_map(const struct vm_struct *area,
static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages)
{
unsigned long start = ULONG_MAX, end = 0;
+ unsigned int page_order = vm_area_page_order(area);
int flush_reset = area->flags & VM_FLUSH_RESET_PERMS;
int flush_dmap = 0;
int i;
@@ -2455,11 +2529,14 @@ static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages)
* map. Find the start and end range of the direct mappings to make sure
* 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;
}
}
@@ -2500,13 +2577,14 @@ static void __vunmap(const void *addr, int deallocate_pages)
vm_remove_mappings(area, deallocate_pages);
if (deallocate_pages) {
+ unsigned int page_order = vm_area_page_order(area);
int i;
- for (i = 0; i < area->nr_pages; i++) {
+ for (i = 0; i < area->nr_pages; i += 1U << page_order) {
struct page *page = area->pages[i];
BUG_ON(!page);
- __free_pages(page, 0);
+ __free_pages(page, page_order);
}
atomic_long_sub(area->nr_pages, &nr_vmalloc_pages);
@@ -2697,15 +2775,19 @@ EXPORT_SYMBOL_GPL(vmap_pfn);
#endif /* CONFIG_VMAP_PFN */
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)
{
const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO;
- unsigned int nr_pages = get_vm_area_size(area) >> PAGE_SHIFT;
+ unsigned long addr = (unsigned long)area->addr;
+ unsigned long size = get_vm_area_size(area);
unsigned long array_size;
- unsigned int i;
+ unsigned int nr_small_pages = size >> PAGE_SHIFT;
+ unsigned int page_order;
struct page **pages;
+ unsigned int i;
- array_size = (unsigned long)nr_pages * sizeof(struct page *);
+ array_size = (unsigned long)nr_small_pages * sizeof(struct page *);
gfp_mask |= __GFP_NOWARN;
if (!(gfp_mask & (GFP_DMA | GFP_DMA32)))
gfp_mask |= __GFP_HIGHMEM;
@@ -2724,30 +2806,38 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
}
area->pages = pages;
- area->nr_pages = nr_pages;
+ area->nr_pages = nr_small_pages;
+ set_vm_area_page_order(area, page_shift - PAGE_SHIFT);
- for (i = 0; i < area->nr_pages; i++) {
- struct page *page;
+ page_order = vm_area_page_order(area);
- if (node == NUMA_NO_NODE)
- page = alloc_page(gfp_mask);
- else
- page = alloc_pages_node(node, gfp_mask, 0);
+ /*
+ * 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 < area->nr_pages; i += 1U << page_order) {
+ struct page *page;
+ int p;
+ /* Compound pages required for remap_vmalloc_page */
+ page = alloc_pages_node(node, gfp_mask | __GFP_COMP, page_order);
if (unlikely(!page)) {
/* Successfully allocated i pages, free them in __vfree() */
area->nr_pages = i;
atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
goto fail;
}
- area->pages[i] = page;
+
+ for (p = 0; p < (1U << page_order); p++)
+ area->pages[i + p] = page + p;
+
if (gfpflags_allow_blocking(gfp_mask))
cond_resched();
}
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)
+ if (vmap_pages_range(addr, addr + size, prot, pages, page_shift) < 0)
goto fail;
return area->addr;
@@ -2755,7 +2845,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
fail:
warn_alloc(gfp_mask, NULL,
"vmalloc: allocation failure, allocated %ld of %ld bytes",
- (area->nr_pages*PAGE_SIZE), area->size);
+ (area->nr_pages*PAGE_SIZE), size);
__vfree(area->addr);
return NULL;
}
@@ -2786,19 +2876,45 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
struct vm_struct *area;
void *addr;
unsigned long real_size = size;
+ unsigned long real_align = align;
+ unsigned int shift = PAGE_SHIFT;
- size = PAGE_ALIGN(size);
- if (!size || (size >> PAGE_SHIFT) > totalram_pages())
+ if (!size || (size >> PAGE_SHIFT) > totalram_pages()) {
+ area = NULL;
goto fail;
+ }
+
+ if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP) &&
+ arch_vmap_pmd_supported(prot)) {
+ unsigned long size_per_node;
- area = __get_vm_area_node(real_size, align, VM_ALLOC | VM_UNINITIALIZED |
+ /*
+ * 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.
+ */
+
+ size_per_node = size;
+ if (node == NUMA_NO_NODE)
+ size_per_node /= num_online_nodes();
+ if (size_per_node >= PMD_SIZE) {
+ shift = PMD_SHIFT;
+ align = max(real_align, 1UL << shift);
+ size = ALIGN(real_size, 1UL << shift);
+ }
+ }
+
+again:
+ size = PAGE_ALIGN(size);
+ area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNINITIALIZED |
vm_flags, start, end, node, gfp_mask, caller);
if (!area)
goto fail;
- addr = __vmalloc_area_node(area, gfp_mask, prot, node);
+ addr = __vmalloc_area_node(area, gfp_mask, prot, shift, node);
if (!addr)
- return NULL;
+ goto fail;
/*
* In this function, newly allocated vm_struct has VM_UNINITIALIZED
@@ -2812,8 +2928,18 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
return addr;
fail:
- warn_alloc(gfp_mask, NULL,
+ if (shift > PAGE_SHIFT) {
+ shift = PAGE_SHIFT;
+ align = real_align;
+ size = real_size;
+ goto again;
+ }
+
+ if (!area) {
+ /* Warn for area allocation, page allocations already warn */
+ warn_alloc(gfp_mask, NULL,
"vmalloc: allocation failure: %lu bytes", real_size);
+ }
return NULL;
}