The patch titled
Subject: mm/vmalloc: allocate small pages for area->pages
has been added to the -mm tree. Its filename is
mm-vmalloc-allocate-small-pages-for-area-pages.patch
This patch should soon appear at
https://ozlabs.org/~akpm/mmots/broken-out/mm-vmalloc-allocate-small-pages-for-area-pages.patch
and later at
https://ozlabs.org/~akpm/mmotm/broken-out/mm-vmalloc-allocate-small-pages-for-area-pages.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Xu Yu <xuyu@xxxxxxxxxxxxxxxxx>
Subject: mm/vmalloc: allocate small pages for area->pages
The area->pages stores the struct pages allocated for vmalloc mappings.
The allocated memory can be hugepage if arch has HAVE_ARCH_HUGE_VMALLOC
set, while area->pages itself does not have to be hugepage backed.
Suppose that we want to vmalloc 1026M of memory, then area->pages is
2052K in size, which is large than PMD_SIZE when the pagesize is 4K.
Currently, 4096K will be allocated for area->pages, wherein 2044K is
wasted.
This introduces __vmalloc_node_no_huge, and makes area->pages backed by
small pages, because I think to allocate hugepage for area->pages is
unnecessary and vulnerable to abuse.
Link: https://lkml.kernel.org/r/dd04f516643fde4206c1fe93818526a768125c75.1638870169.git.xuyu@xxxxxxxxxxxxxxxxx
Signed-off-by: Xu Yu <xuyu@xxxxxxxxxxxxxxxxx>
Cc: Nicholas Piggin <npiggin@xxxxxxxxx>
Cc: Uladzislau Rezki <uladzislau.rezki@xxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/vmalloc.h | 2 ++
mm/vmalloc.c | 15 ++++++++++++---
2 files changed, 14 insertions(+), 3 deletions(-)
--- a/include/linux/vmalloc.h~mm-vmalloc-allocate-small-pages-for-area-pages
+++ a/include/linux/vmalloc.h
@@ -157,6 +157,8 @@ extern void *__vmalloc_node_range(unsign
const void *caller) __alloc_size(1);
void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask,
int node, const void *caller) __alloc_size(1);
+void *__vmalloc_node_no_huge(unsigned long size, unsigned long align,
+ gfp_t gfp_mask, int node, const void *caller) __alloc_size(1);
void *vmalloc_no_huge(unsigned long size) __alloc_size(1);
extern void vfree(const void *addr);
--- a/mm/vmalloc.c~mm-vmalloc-allocate-small-pages-for-area-pages
+++ a/mm/vmalloc.c
@@ -2928,19 +2928,20 @@ static void *__vmalloc_area_node(struct
unsigned long size = get_vm_area_size(area);
unsigned long array_size;
unsigned int nr_small_pages = size >> PAGE_SHIFT;
+ unsigned int max_small_pages = ALIGN(size, 1UL << page_shift) >> PAGE_SHIFT;
unsigned int page_order;
unsigned int flags;
int ret;
- array_size = (unsigned long)nr_small_pages * sizeof(struct page *);
+ array_size = (unsigned long)max_small_pages * sizeof(struct page *);
gfp_mask |= __GFP_NOWARN;
if (!(gfp_mask & (GFP_DMA | GFP_DMA32)))
gfp_mask |= __GFP_HIGHMEM;
/* Please note that the recursion is strictly bounded. */
if (array_size > PAGE_SIZE) {
- area->pages = __vmalloc_node(array_size, 1, nested_gfp, node,
- area->caller);
+ area->pages = __vmalloc_node_no_huge(array_size, 1, nested_gfp,
+ node, area->caller);
} else {
area->pages = kmalloc_node(array_size, nested_gfp, node);
}
@@ -3147,6 +3148,14 @@ void *__vmalloc_node(unsigned long size,
return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END,
gfp_mask, PAGE_KERNEL, 0, node, caller);
}
+
+void *__vmalloc_node_no_huge(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,
+ gfp_mask, PAGE_KERNEL, VM_NO_HUGE_VMAP, node, caller);
+}
+
/*
* This is only for performance analysis of vmalloc and stress purpose.
* It is required by vmalloc test module, therefore do not use it other
_
Patches currently in -mm which might be from xuyu@xxxxxxxxxxxxxxxxx are
mm-vmalloc-allocate-small-pages-for-area-pages.patch
