For platforms that define HAVE_ARCH_HUGE_VMAP and support PMD vmap mappings,
have vmalloc attempt to allocate PMD-sized pages first, before falling back
to small pages. Allocations which use something other than PAGE_KERNEL
protections are not permitted to use huge pages yet, not all callers expect
this (e.g., module allocations vs strict module rwx).
This gives a 6x reduction in dTLB misses for a `git diff` (of linux), from
45600 to 6500 and a 2.2% reduction in cycles on a 2-node POWER9.
This can result in more internal fragmentation and memory overhead for a
given allocation. It can also cause greater NUMA unbalance on hashdist
allocations.
There may be other callers that expect small pages under vmalloc but use
PAGE_KERNEL, I'm not sure if it's feasible to catch them all. An
alternative would be a new function or flag which enables large mappings,
and use that in callers.
Signed-off-by: Nicholas Piggin <npig...@gmail.com>
---
include/linux/vmalloc.h | 2 +
mm/vmalloc.c | 135 +++++++++++++++++++++++++++++-----------
2 files changed, 102 insertions(+), 35 deletions(-)
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 291313a7e663..853b82eac192 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -24,6 +24,7 @@ struct notifier_block; /* in notifier.h */
#define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully
initialized */
#define VM_NO_GUARD 0x00000040 /* don't add guard page */
#define VM_KASAN 0x00000080 /* has allocated kasan shadow
memory */
+#define VM_HUGE_PAGES 0x00000100 /* may use huge pages */
/*
* VM_KASAN is used slighly differently depending on CONFIG_KASAN_VMALLOC.
@@ -58,6 +59,7 @@ struct vm_struct {
unsigned long size;
unsigned long flags;
struct page **pages;
+ unsigned int page_order;
unsigned int nr_pages;
phys_addr_t phys_addr;
const void *caller;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index c898d16ddd25..7b7e992c5ff1 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -436,7 +436,7 @@ static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long
addr,
*
* Ie. pte at addr+N*PAGE_SIZE shall point to pfn corresponding to pages[N]
*/
-static int vmap_pages_range_noflush(unsigned long start, unsigned long end,
+static int vmap_small_pages_range_noflush(unsigned long start, unsigned long
end,
pgprot_t prot, struct page **pages)
{
pgd_t *pgd;
@@ -457,13 +457,44 @@ static int vmap_pages_range_noflush(unsigned long start,
unsigned long end,
return nr;
}
+static int vmap_pages_range_noflush(unsigned long start, unsigned long end,
+ pgprot_t prot, struct page **pages,
+ unsigned int page_shift)
+{
+ if (page_shift == PAGE_SIZE) {
+ return vmap_small_pages_range_noflush(start, end, prot, pages);
+ } else {
+ unsigned long addr = start;
+ unsigned int i, nr = (end - start) >> page_shift;
+
+ for (i = 0; i < nr; i++) {
+ 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 start, unsigned long end,
- pgprot_t prot, struct page **pages)
+ pgprot_t prot, struct page **pages,
+ unsigned int page_shift)
{
int ret;
- ret = vmap_pages_range_noflush(start, end, prot, pages);
+ BUG_ON(page_shift < PAGE_SHIFT);
+
+ ret = vmap_pages_range_noflush(start, end, prot, pages, page_shift);
flush_cache_vmap(start, end);
+
return ret;
}
@@ -2064,7 +2095,7 @@ void *vm_map_ram(struct page **pages, unsigned int count,
int node, pgprot_t pro
kasan_unpoison_vmalloc(mem, size);
- if (vmap_pages_range(addr, addr + size, prot, pages) < 0) {
+ if (vmap_pages_range(addr, addr + size, prot, pages, PAGE_SHIFT) < 0) {
vm_unmap_ram(mem, count);
return NULL;
}
@@ -2230,7 +2261,7 @@ void __init vmalloc_init(void)
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);
+ return vmap_pages_range_noflush(addr, addr + size, prot, pages,
PAGE_SHIFT);
}
/**
@@ -2277,7 +2308,7 @@ int map_vm_area(struct vm_struct *area, pgprot_t prot,
struct page **pages)
unsigned long end = addr + get_vm_area_size(area);
int err;
- err = vmap_pages_range(addr, end, prot, pages);
+ err = vmap_pages_range(addr, end, prot, pages, PAGE_SHIFT);
return err > 0 ? 0 : err;
}
@@ -2325,9 +2356,11 @@ static struct vm_struct *__get_vm_area_node(unsigned
long size,
if (unlikely(!size))
return NULL;
- if (flags & VM_IOREMAP)
- align = 1ul << clamp_t(int, get_count_order_long(size),
- PAGE_SHIFT, IOREMAP_MAX_ORDER);
+ if (flags & VM_IOREMAP) {
+ align = max(align,
+ 1ul << clamp_t(int, get_count_order_long(size),
+ PAGE_SHIFT, IOREMAP_MAX_ORDER));
+ }
area = kzalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node);
if (unlikely(!area))
@@ -2534,7 +2567,7 @@ static void __vunmap(const void *addr, int
deallocate_pages)
struct page *page = area->pages[i];
BUG_ON(!page);
- __free_pages(page, 0);
+ __free_pages(page, area->page_order);
}
atomic_long_sub(area->nr_pages, &nr_vmalloc_pages);
@@ -2672,26 +2705,29 @@ void *vmap(struct page **pages, unsigned int count,
EXPORT_SYMBOL(vmap);
static void *__vmalloc_node(unsigned long size, unsigned long align,
- gfp_t gfp_mask, pgprot_t prot,
- int node, const void *caller);
+ gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags,
+ int node, const void *caller);
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 long addr = (unsigned long)area->addr;
+ unsigned long size = get_vm_area_size(area);
+ unsigned int page_order = page_shift - PAGE_SHIFT;
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;
+ 0 : __GFP_HIGHMEM;
- nr_pages = get_vm_area_size(area) >> PAGE_SHIFT;
+ nr_pages = size >> page_shift;
array_size = (nr_pages * sizeof(struct page *));
/* Please note that the recursion is strictly bounded. */
if (array_size > PAGE_SIZE) {
pages = __vmalloc_node(array_size, 1, nested_gfp|highmem_mask,
- PAGE_KERNEL, node, area->caller);
+ PAGE_KERNEL, 0, node, area->caller);
} else {
pages = kmalloc_node(array_size, nested_gfp, node);
}
@@ -2704,14 +2740,13 @@ static void *__vmalloc_area_node(struct vm_struct
*area, gfp_t gfp_mask,
area->pages = pages;
area->nr_pages = nr_pages;
+ area->page_order = page_order;
for (i = 0; i < area->nr_pages; i++) {
struct page *page;
- if (node == NUMA_NO_NODE)
- page = alloc_page(alloc_mask|highmem_mask);
- else
- page = alloc_pages_node(node, alloc_mask|highmem_mask,
0);
+ page = alloc_pages_node(node,
+ alloc_mask|highmem_mask, page_order);
if (unlikely(!page)) {
/* Successfully allocated i pages, free them in
__vunmap() */
@@ -2725,8 +2760,9 @@ static void *__vmalloc_area_node(struct vm_struct *area,
gfp_t gfp_mask,
}
atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
- if (map_vm_area(area, prot, pages))
+ if (vmap_pages_range(addr, addr + size, prot, pages, page_shift) < 0)
goto fail;
+
return area->addr;
fail:
@@ -2760,22 +2796,39 @@ void *__vmalloc_node_range(unsigned long size, unsigned
long align,
pgprot_t prot, unsigned long vm_flags, int node,
const void *caller)
{
- struct vm_struct *area;
+ struct vm_struct *area = NULL;
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())
goto fail;
- area = __get_vm_area_node(real_size, align, VM_ALLOC | VM_UNINITIALIZED
|
+ if (IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMAP) &&
+ (vm_flags & VM_HUGE_PAGES)) {
+ unsigned long size_per_node;
+
+ size_per_node = size;
+ if (node == NUMA_NO_NODE)
+ size_per_node /= num_online_nodes();
+ if (size_per_node >= PMD_SIZE)
+ shift = PMD_SHIFT;
+ }
+
+again:
+ align = max(real_align, 1UL << shift);
+ size = ALIGN(real_size, align);
+
+ 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
@@ -2789,8 +2842,16 @@ 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;
+ 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;
}
@@ -2825,16 +2886,19 @@ EXPORT_SYMBOL_GPL(__vmalloc_node_range);
* Return: pointer to the allocated memory or %NULL on error
*/
static void *__vmalloc_node(unsigned long size, unsigned long align,
- gfp_t gfp_mask, pgprot_t prot,
- int node, const void *caller)
+ gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags,
+ int node, const void *caller)
{
return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END,
- gfp_mask, prot, 0, node, caller);
+ gfp_mask, prot, vm_flags, node, caller);
}
void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
{
- return __vmalloc_node(size, 1, gfp_mask, prot, NUMA_NO_NODE,
+ unsigned long vm_flags = 0;
+ if (pgprot_val(prot) == pgprot_val(PAGE_KERNEL))
+ vm_flags |= VM_HUGE_PAGES;
+ return __vmalloc_node(size, 1, gfp_mask, prot, vm_flags, NUMA_NO_NODE,
__builtin_return_address(0));
}
EXPORT_SYMBOL(__vmalloc);
@@ -2842,7 +2906,7 @@ EXPORT_SYMBOL(__vmalloc);
static inline void *__vmalloc_node_flags(unsigned long size,
int node, gfp_t flags)
{
- return __vmalloc_node(size, 1, flags, PAGE_KERNEL,
+ return __vmalloc_node(size, 1, flags, PAGE_KERNEL, VM_HUGE_PAGES,
node, __builtin_return_address(0));
}
@@ -2850,7 +2914,8 @@ static inline void *__vmalloc_node_flags(unsigned long
size,
void *__vmalloc_node_flags_caller(unsigned long size, int node, gfp_t flags,
void *caller)
{
- return __vmalloc_node(size, 1, flags, PAGE_KERNEL, node, caller);
+ return __vmalloc_node(size, 1, flags, PAGE_KERNEL, VM_HUGE_PAGES,
+ node, caller);
}
/**
@@ -2925,7 +2990,7 @@ EXPORT_SYMBOL(vmalloc_user);
*/
void *vmalloc_node(unsigned long size, int node)
{
- return __vmalloc_node(size, 1, GFP_KERNEL, PAGE_KERNEL,
+ return __vmalloc_node(size, 1, GFP_KERNEL, PAGE_KERNEL, VM_HUGE_PAGES,
node, __builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_node);
@@ -3014,7 +3079,7 @@ void *vmalloc_exec(unsigned long size)
*/
void *vmalloc_32(unsigned long size)
{
- return __vmalloc_node(size, 1, GFP_VMALLOC32, PAGE_KERNEL,
+ return __vmalloc_node(size, 1, GFP_VMALLOC32, PAGE_KERNEL, 0,
NUMA_NO_NODE, __builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_32);
--
2.23.0
