2b3f9b8187
The below is one path where race between page_ext and offline of the respective memory blocks will cause use-after-free on the access of page_ext structure. process1 process2 --------- --------- a)doing /proc/page_owner doing memory offline through offline_pages. b)PageBuddy check is failed thus proceed to get the page_owner information through page_ext access. page_ext = lookup_page_ext(page); migrate_pages(); ................. Since all pages are successfully migrated as part of the offline operation,send MEM_OFFLINE notification where for page_ext it calls: offline_page_ext()--> __free_page_ext()--> free_page_ext()--> vfree(ms->page_ext) mem_section->page_ext = NULL c) Check for the PAGE_EXT flags in the page_ext->flags access results into the use-after-free(leading to the translation faults). As mentioned above, there is really no synchronization between page_ext access and its freeing in the memory_offline. The memory offline steps(roughly) on a memory block is as below: 1) Isolate all the pages 2) while(1) try free the pages to buddy.(->free_list[MIGRATE_ISOLATE]) 3) delete the pages from this buddy list. 4) Then free page_ext.(Note: The struct page is still alive as it is freed only during hot remove of the memory which frees the memmap, which steps the user might not perform). This design leads to the state where struct page is alive but the struct page_ext is freed, where the later is ideally part of the former which just representing the page_flags (check [3] for why this design is chosen). The above mentioned race is just one example __but the problem persists in the other paths too involving page_ext->flags access(eg: page_is_idle())__. Fix all the paths where offline races with page_ext access by maintaining synchronization with rcu lock and is achieved in 3 steps: 1) Invalidate all the page_ext's of the sections of a memory block by storing a flag in the LSB of mem_section->page_ext. 2) Wait till all the existing readers to finish working with the ->page_ext's with synchronize_rcu(). Any parallel process that starts after this call will not get page_ext, through lookup_page_ext(), for the block parallel offline operation is being performed. 3) Now safely free all sections ->page_ext's of the block on which offline operation is being performed. Note: If synchronize_rcu() takes time then optimizations can be done in this path through call_rcu()[2]. Thanks to David Hildenbrand for his views/suggestions on the initial discussion[1] and Pavan kondeti for various inputs on this patch. [1] https://lore.kernel.org/linux-mm/59edde13-4167-8550-86f0-11fc67882107@quicinc.com/ [2] https://lore.kernel.org/all/a26ce299-aed1-b8ad-711e-a49e82bdd180@quicinc.com/T/#u [3] https://lore.kernel.org/all/6fa6b7aa-731e-891c-3efb-a03d6a700efa@redhat.com/ Bug: 236222283 Link: https://lore.kernel.org/all/1661496993-11473-1-git-send-email-quic_charante@quicinc.com/ Change-Id: Ib439ae19c61a557a5c70ea90e3c4b35a5583ba0d Suggested-by: David Hildenbrand <david@redhat.com> Suggested-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Charan Teja Kalla <quic_charante@quicinc.com> (fixed merge conflicts and still exported lookup_page_ext)
95 lines
2.0 KiB
C
95 lines
2.0 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __LINUX_PAGE_EXT_H
|
|
#define __LINUX_PAGE_EXT_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/stacktrace.h>
|
|
#include <linux/stackdepot.h>
|
|
|
|
struct pglist_data;
|
|
struct page_ext_operations {
|
|
size_t offset;
|
|
size_t size;
|
|
bool (*need)(void);
|
|
void (*init)(void);
|
|
};
|
|
|
|
#ifdef CONFIG_PAGE_EXTENSION
|
|
|
|
enum page_ext_flags {
|
|
PAGE_EXT_OWNER,
|
|
PAGE_EXT_OWNER_ALLOCATED,
|
|
#if defined(CONFIG_PAGE_PINNER)
|
|
/* page refcount was increased by GUP or follow_page(FOLL_GET) */
|
|
PAGE_EXT_GET,
|
|
/* page migration failed */
|
|
PAGE_EXT_PINNER_MIGRATION_FAILED,
|
|
#endif
|
|
#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT)
|
|
PAGE_EXT_YOUNG,
|
|
PAGE_EXT_IDLE,
|
|
#endif
|
|
};
|
|
|
|
/*
|
|
* Page Extension can be considered as an extended mem_map.
|
|
* A page_ext page is associated with every page descriptor. The
|
|
* page_ext helps us add more information about the page.
|
|
* All page_ext are allocated at boot or memory hotplug event,
|
|
* then the page_ext for pfn always exists.
|
|
*/
|
|
struct page_ext {
|
|
unsigned long flags;
|
|
};
|
|
|
|
extern unsigned long page_ext_size;
|
|
extern void pgdat_page_ext_init(struct pglist_data *pgdat);
|
|
|
|
#ifdef CONFIG_SPARSEMEM
|
|
static inline void page_ext_init_flatmem(void)
|
|
{
|
|
}
|
|
extern void page_ext_init(void);
|
|
#else
|
|
extern void page_ext_init_flatmem(void);
|
|
static inline void page_ext_init(void)
|
|
{
|
|
}
|
|
#endif
|
|
struct page_ext *lookup_page_ext(const struct page *page);
|
|
extern struct page_ext *page_ext_get(struct page *page);
|
|
extern void page_ext_put(struct page_ext *page_ext);
|
|
|
|
static inline struct page_ext *page_ext_next(struct page_ext *curr)
|
|
{
|
|
void *next = curr;
|
|
next += page_ext_size;
|
|
return next;
|
|
}
|
|
|
|
#else /* !CONFIG_PAGE_EXTENSION */
|
|
struct page_ext;
|
|
|
|
static inline void pgdat_page_ext_init(struct pglist_data *pgdat)
|
|
{
|
|
}
|
|
|
|
static inline void page_ext_init(void)
|
|
{
|
|
}
|
|
|
|
static inline void page_ext_init_flatmem(void)
|
|
{
|
|
}
|
|
|
|
static inline struct page_ext *page_ext_get(struct page *page)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline void page_ext_put(struct page_ext *page_ext)
|
|
{
|
|
}
|
|
#endif /* CONFIG_PAGE_EXTENSION */
|
|
#endif /* __LINUX_PAGE_EXT_H */
|