linux_dsm_epyc7002/include/linux/vmalloc.h
Andrey Ryabinin a5af5aa8b6 kasan, module, vmalloc: rework shadow allocation for modules
Current approach in handling shadow memory for modules is broken.

Shadow memory could be freed only after memory shadow corresponds it is no
longer used.  vfree() called from interrupt context could use memory its
freeing to store 'struct llist_node' in it:

    void vfree(const void *addr)
    {
    ...
        if (unlikely(in_interrupt())) {
            struct vfree_deferred *p = this_cpu_ptr(&vfree_deferred);
            if (llist_add((struct llist_node *)addr, &p->list))
                    schedule_work(&p->wq);

Later this list node used in free_work() which actually frees memory.
Currently module_memfree() called in interrupt context will free shadow
before freeing module's memory which could provoke kernel crash.

So shadow memory should be freed after module's memory.  However, such
deallocation order could race with kasan_module_alloc() in module_alloc().

Free shadow right before releasing vm area.  At this point vfree()'d
memory is not used anymore and yet not available for other allocations.
New VM_KASAN flag used to indicate that vm area has dynamically allocated
shadow memory so kasan frees shadow only if it was previously allocated.

Signed-off-by: Andrey Ryabinin <a.ryabinin@samsung.com>
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-03-12 18:46:08 -07:00

204 lines
5.9 KiB
C

#ifndef _LINUX_VMALLOC_H
#define _LINUX_VMALLOC_H
#include <linux/spinlock.h>
#include <linux/init.h>
#include <linux/list.h>
#include <asm/page.h> /* pgprot_t */
#include <linux/rbtree.h>
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 */
#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 */
/* 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;
const void *caller;
};
struct vmap_area {
unsigned long va_start;
unsigned long va_end;
unsigned long flags;
struct rb_node rb_node; /* address sorted rbtree */
struct list_head list; /* address sorted list */
struct list_head purge_list; /* "lazy purge" list */
struct vm_struct *vm;
struct rcu_head rcu_head;
};
/*
* 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_node_range(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);
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_partial(struct vm_area_struct *vma,
unsigned long uaddr, void *kaddr,
unsigned long size);
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)
{
if (!(area->flags & VM_NO_GUARD))
/* return actual size without guard page */
return area->size - PAGE_SIZE;
else
return area->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, const 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,
const void *caller);
extern struct vm_struct *remove_vm_area(const void *addr);
extern struct vm_struct *find_vm_area(const void *addr);
extern int map_vm_area(struct vm_struct *area, pgprot_t prot,
struct page **pages);
#ifdef CONFIG_MMU
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);
#else
static inline int
map_kernel_range_noflush(unsigned long start, unsigned long size,
pgprot_t prot, struct page **pages)
{
return size >> PAGE_SHIFT;
}
static inline void
unmap_kernel_range_noflush(unsigned long addr, unsigned long size)
{
}
static inline void
unmap_kernel_range(unsigned long addr, unsigned long size)
{
}
#endif
/* Allocate/destroy a 'vmalloc' VM area. */
extern struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes);
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 struct list_head vmap_area_list;
extern __init void vm_area_add_early(struct vm_struct *vm);
extern __init void vm_area_register_early(struct vm_struct *vm, size_t align);
#ifdef CONFIG_SMP
# ifdef CONFIG_MMU
struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
const size_t *sizes, int nr_vms,
size_t align);
void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms);
# else
static inline struct vm_struct **
pcpu_get_vm_areas(const unsigned long *offsets,
const size_t *sizes, int nr_vms,
size_t align)
{
return NULL;
}
static inline void
pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms)
{
}
# endif
#endif
struct vmalloc_info {
unsigned long used;
unsigned long largest_chunk;
};
#ifdef CONFIG_MMU
#define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START)
extern void get_vmalloc_info(struct vmalloc_info *vmi);
#else
#define VMALLOC_TOTAL 0UL
#define get_vmalloc_info(vmi) \
do { \
(vmi)->used = 0; \
(vmi)->largest_chunk = 0; \
} while (0)
#endif
#endif /* _LINUX_VMALLOC_H */