linux_dsm_epyc7002/include/linux/vmalloc.h
Rick Edgecombe 868b104d73 mm/vmalloc: Add flag for freeing of special permsissions
Add a new flag VM_FLUSH_RESET_PERMS, for enabling vfree operations to
immediately clear executable TLB entries before freeing pages, and handle
resetting permissions on the directmap. This flag is useful for any kind
of memory with elevated permissions, or where there can be related
permissions changes on the directmap. Today this is RO+X and RO memory.

Although this enables directly vfreeing non-writeable memory now,
non-writable memory cannot be freed in an interrupt because the allocation
itself is used as a node on deferred free list. So when RO memory needs to
be freed in an interrupt the code doing the vfree needs to have its own
work queue, as was the case before the deferred vfree list was added to
vmalloc.

For architectures with set_direct_map_ implementations this whole operation
can be done with one TLB flush when centralized like this. For others with
directmap permissions, currently only arm64, a backup method using
set_memory functions is used to reset the directmap. When arm64 adds
set_direct_map_ functions, this backup can be removed.

When the TLB is flushed to both remove TLB entries for the vmalloc range
mapping and the direct map permissions, the lazy purge operation could be
done to try to save a TLB flush later. However today vm_unmap_aliases
could flush a TLB range that does not include the directmap. So a helper
is added with extra parameters that can allow both the vmalloc address and
the direct mapping to be flushed during this operation. The behavior of the
normal vm_unmap_aliases function is unchanged.

Suggested-by: Dave Hansen <dave.hansen@intel.com>
Suggested-by: Andy Lutomirski <luto@kernel.org>
Suggested-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <akpm@linux-foundation.org>
Cc: <ard.biesheuvel@linaro.org>
Cc: <deneen.t.dock@intel.com>
Cc: <kernel-hardening@lists.openwall.com>
Cc: <kristen@linux.intel.com>
Cc: <linux_dti@icloud.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20190426001143.4983-17-namit@vmware.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2019-04-30 12:37:58 +02:00

225 lines
6.7 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_VMALLOC_H
#define _LINUX_VMALLOC_H
#include <linux/spinlock.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/llist.h>
#include <asm/page.h> /* pgprot_t */
#include <linux/rbtree.h>
#include <linux/overflow.h>
struct vm_area_struct; /* vma defining user mapping in mm_types.h */
struct notifier_block; /* in notifier.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_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 */
/*
* Memory with VM_FLUSH_RESET_PERMS cannot be freed in an interrupt or with
* vfree_atomic().
*/
#define VM_FLUSH_RESET_PERMS 0x00000100 /* Reset direct map and flush TLB on unmap */
/* 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 llist_node 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);
#ifndef CONFIG_MMU
extern void *__vmalloc_node_flags(unsigned long size, int node, gfp_t flags);
static inline void *__vmalloc_node_flags_caller(unsigned long size, int node,
gfp_t flags, void *caller)
{
return __vmalloc_node_flags(size, node, flags);
}
#else
extern void *__vmalloc_node_flags_caller(unsigned long size,
int node, gfp_t flags, void *caller);
#endif
extern void vfree(const void *addr);
extern void vfree_atomic(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);
static inline void set_vm_flush_reset_perms(void *addr)
{
struct vm_struct *vm = find_vm_area(addr);
if (vm)
vm->flags |= VM_FLUSH_RESET_PERMS;
}
#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)
{
}
static inline void set_vm_flush_reset_perms(void *addr)
{
}
#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
#ifdef CONFIG_MMU
#define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START)
#else
#define VMALLOC_TOTAL 0UL
#endif
int register_vmap_purge_notifier(struct notifier_block *nb);
int unregister_vmap_purge_notifier(struct notifier_block *nb);
#endif /* _LINUX_VMALLOC_H */