![Jeremy Fitzhardinge](/assets/img/avatar_default.png)
On stock 2.6.37-rc4, running:
# mount lilith:/export /mnt/lilith
# find /mnt/lilith/ -type f -print0 | xargs -0 file
crashes the machine fairly quickly under Xen. Often it results in oops
messages, but the couple of times I tried just now, it just hung quietly
and made Xen print some rude messages:
(XEN) mm.c:2389:d80 Bad type (saw 7400000000000001 != exp
3000000000000000) for mfn 1d7058 (pfn 18fa7)
(XEN) mm.c:964:d80 Attempt to create linear p.t. with write perms
(XEN) mm.c:2389:d80 Bad type (saw 7400000000000010 != exp
1000000000000000) for mfn 1d2e04 (pfn 1d1fb)
(XEN) mm.c:2965:d80 Error while pinning mfn 1d2e04
Which means the domain tried to map a pagetable page RW, which would
allow it to map arbitrary memory, so Xen stopped it. This is because
vm_unmap_ram() left some pages mapped in the vmalloc area after NFS had
finished with them, and those pages got recycled as pagetable pages
while still having these RW aliases.
Removing those mappings immediately removes the Xen-visible aliases, and
so it has no problem with those pages being reused as pagetable pages.
Deferring the TLB flush doesn't upset Xen because it can flush the TLB
itself as needed to maintain its invariants.
When unmapping a region in the vmalloc space, clear the ptes
immediately. There's no point in deferring this because there's no
amortization benefit.
The TLBs are left dirty, and they are flushed lazily to amortize the
cost of the IPIs.
This specific motivation for this patch is an oops-causing regression
since 2.6.36 when using NFS under Xen, triggered by the NFS client's use
of vm_map_ram() introduced in 56e4ebf877
("NFS: readdir with vmapped
pages") . XFS also uses vm_map_ram() and could cause similar problems.
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Bryan Schumaker <bjschuma@netapp.com>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Alex Elder <aelder@sgi.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
129 lines
4.1 KiB
C
129 lines
4.1 KiB
C
#ifndef _LINUX_VMALLOC_H
|
|
#define _LINUX_VMALLOC_H
|
|
|
|
#include <linux/spinlock.h>
|
|
#include <linux/init.h>
|
|
#include <asm/page.h> /* pgprot_t */
|
|
|
|
struct vm_area_struct; /* vma defining user mapping in mm_types.h */
|
|
|
|
/* bits in flags of vmalloc's vm_struct below */
|
|
#define VM_IOREMAP 0x00000001 /* ioremap() and friends */
|
|
#define VM_ALLOC 0x00000002 /* vmalloc() */
|
|
#define VM_MAP 0x00000004 /* vmap()ed pages */
|
|
#define VM_USERMAP 0x00000008 /* suitable for remap_vmalloc_range */
|
|
#define VM_VPAGES 0x00000010 /* buffer for pages was vmalloc'ed */
|
|
/* bits [20..32] reserved for arch specific ioremap internals */
|
|
|
|
/*
|
|
* Maximum alignment for ioremap() regions.
|
|
* Can be overriden by arch-specific value.
|
|
*/
|
|
#ifndef IOREMAP_MAX_ORDER
|
|
#define IOREMAP_MAX_ORDER (7 + PAGE_SHIFT) /* 128 pages */
|
|
#endif
|
|
|
|
struct vm_struct {
|
|
struct vm_struct *next;
|
|
void *addr;
|
|
unsigned long size;
|
|
unsigned long flags;
|
|
struct page **pages;
|
|
unsigned int nr_pages;
|
|
phys_addr_t phys_addr;
|
|
void *caller;
|
|
};
|
|
|
|
/*
|
|
* Highlevel APIs for driver use
|
|
*/
|
|
extern void vm_unmap_ram(const void *mem, unsigned int count);
|
|
extern void *vm_map_ram(struct page **pages, unsigned int count,
|
|
int node, pgprot_t prot);
|
|
extern void vm_unmap_aliases(void);
|
|
|
|
#ifdef CONFIG_MMU
|
|
extern void __init vmalloc_init(void);
|
|
#else
|
|
static inline void vmalloc_init(void)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
extern void *vmalloc(unsigned long size);
|
|
extern void *vzalloc(unsigned long size);
|
|
extern void *vmalloc_user(unsigned long size);
|
|
extern void *vmalloc_node(unsigned long size, int node);
|
|
extern void *vzalloc_node(unsigned long size, int node);
|
|
extern void *vmalloc_exec(unsigned long size);
|
|
extern void *vmalloc_32(unsigned long size);
|
|
extern void *vmalloc_32_user(unsigned long size);
|
|
extern void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot);
|
|
extern void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask,
|
|
pgprot_t prot);
|
|
extern void vfree(const void *addr);
|
|
|
|
extern void *vmap(struct page **pages, unsigned int count,
|
|
unsigned long flags, pgprot_t prot);
|
|
extern void vunmap(const void *addr);
|
|
|
|
extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
|
|
unsigned long pgoff);
|
|
void vmalloc_sync_all(void);
|
|
|
|
/*
|
|
* Lowlevel-APIs (not for driver use!)
|
|
*/
|
|
|
|
static inline size_t get_vm_area_size(const struct vm_struct *area)
|
|
{
|
|
/* return actual size without guard page */
|
|
return area->size - PAGE_SIZE;
|
|
}
|
|
|
|
extern struct vm_struct *get_vm_area(unsigned long size, unsigned long flags);
|
|
extern struct vm_struct *get_vm_area_caller(unsigned long size,
|
|
unsigned long flags, void *caller);
|
|
extern struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
|
|
unsigned long start, unsigned long end);
|
|
extern struct vm_struct *__get_vm_area_caller(unsigned long size,
|
|
unsigned long flags,
|
|
unsigned long start, unsigned long end,
|
|
void *caller);
|
|
extern struct vm_struct *get_vm_area_node(unsigned long size,
|
|
unsigned long flags, int node,
|
|
gfp_t gfp_mask);
|
|
extern struct vm_struct *remove_vm_area(const void *addr);
|
|
|
|
extern int map_vm_area(struct vm_struct *area, pgprot_t prot,
|
|
struct page ***pages);
|
|
extern int map_kernel_range_noflush(unsigned long start, unsigned long size,
|
|
pgprot_t prot, struct page **pages);
|
|
extern void unmap_kernel_range_noflush(unsigned long addr, unsigned long size);
|
|
extern void unmap_kernel_range(unsigned long addr, unsigned long size);
|
|
|
|
/* Allocate/destroy a 'vmalloc' VM area. */
|
|
extern struct vm_struct *alloc_vm_area(size_t size);
|
|
extern void free_vm_area(struct vm_struct *area);
|
|
|
|
/* for /dev/kmem */
|
|
extern long vread(char *buf, char *addr, unsigned long count);
|
|
extern long vwrite(char *buf, char *addr, unsigned long count);
|
|
|
|
/*
|
|
* Internals. Dont't use..
|
|
*/
|
|
extern rwlock_t vmlist_lock;
|
|
extern struct vm_struct *vmlist;
|
|
extern __init void vm_area_register_early(struct vm_struct *vm, size_t align);
|
|
|
|
#ifdef CONFIG_SMP
|
|
struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
|
|
const size_t *sizes, int nr_vms,
|
|
size_t align, gfp_t gfp_mask);
|
|
|
|
void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms);
|
|
#endif
|
|
|
|
#endif /* _LINUX_VMALLOC_H */
|