![Mel Gorman](/assets/img/avatar_default.png)
An IPI is sent to flush remote TLBs when a page is unmapped that was potentially accesssed by other CPUs. There are many circumstances where this happens but the obvious one is kswapd reclaiming pages belonging to a running process as kswapd and the task are likely running on separate CPUs. On small machines, this is not a significant problem but as machine gets larger with more cores and more memory, the cost of these IPIs can be high. This patch uses a simple structure that tracks CPUs that potentially have TLB entries for pages being unmapped. When the unmapping is complete, the full TLB is flushed on the assumption that a refill cost is lower than flushing individual entries. Architectures wishing to do this must give the following guarantee. If a clean page is unmapped and not immediately flushed, the architecture must guarantee that a write to that linear address from a CPU with a cached TLB entry will trap a page fault. This is essentially what the kernel already depends on but the window is much larger with this patch applied and is worth highlighting. The architecture should consider whether the cost of the full TLB flush is higher than sending an IPI to flush each individual entry. An additional architecture helper called flush_tlb_local is required. It's a trivial wrapper with some accounting in the x86 case. The impact of this patch depends on the workload as measuring any benefit requires both mapped pages co-located on the LRU and memory pressure. The case with the biggest impact is multiple processes reading mapped pages taken from the vm-scalability test suite. The test case uses NR_CPU readers of mapped files that consume 10*RAM. Linear mapped reader on a 4-node machine with 64G RAM and 48 CPUs 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 Ops lru-file-mmap-read-elapsed 159.62 ( 0.00%) 120.68 ( 24.40%) Ops lru-file-mmap-read-time_range 30.59 ( 0.00%) 2.80 ( 90.85%) Ops lru-file-mmap-read-time_stddv 6.70 ( 0.00%) 0.64 ( 90.38%) 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 User 581.00 611.43 System 5804.93 4111.76 Elapsed 161.03 122.12 This is showing that the readers completed 24.40% faster with 29% less system CPU time. From vmstats, it is known that the vanilla kernel was interrupted roughly 900K times per second during the steady phase of the test and the patched kernel was interrupts 180K times per second. The impact is lower on a single socket machine. 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 Ops lru-file-mmap-read-elapsed 25.33 ( 0.00%) 20.38 ( 19.54%) Ops lru-file-mmap-read-time_range 0.91 ( 0.00%) 1.44 (-58.24%) Ops lru-file-mmap-read-time_stddv 0.28 ( 0.00%) 0.47 (-65.34%) 4.2.0-rc1 4.2.0-rc1 vanilla flushfull-v7 User 58.09 57.64 System 111.82 76.56 Elapsed 27.29 22.55 It's still a noticeable improvement with vmstat showing interrupts went from roughly 500K per second to 45K per second. The patch will have no impact on workloads with no memory pressure or have relatively few mapped pages. It will have an unpredictable impact on the workload running on the CPU being flushed as it'll depend on how many TLB entries need to be refilled and how long that takes. Worst case, the TLB will be completely cleared of active entries when the target PFNs were not resident at all. [sasha.levin@oracle.com: trace tlb flush after disabling preemption in try_to_unmap_flush] Signed-off-by: Mel Gorman <mgorman@suse.de> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Dave Hansen <dave.hansen@intel.com> Acked-by: Ingo Molnar <mingo@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Michal Hocko <mhocko@suse.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
291 lines
8.4 KiB
C
291 lines
8.4 KiB
C
#ifndef _LINUX_RMAP_H
|
|
#define _LINUX_RMAP_H
|
|
/*
|
|
* Declarations for Reverse Mapping functions in mm/rmap.c
|
|
*/
|
|
|
|
#include <linux/list.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/rwsem.h>
|
|
#include <linux/memcontrol.h>
|
|
|
|
/*
|
|
* The anon_vma heads a list of private "related" vmas, to scan if
|
|
* an anonymous page pointing to this anon_vma needs to be unmapped:
|
|
* the vmas on the list will be related by forking, or by splitting.
|
|
*
|
|
* Since vmas come and go as they are split and merged (particularly
|
|
* in mprotect), the mapping field of an anonymous page cannot point
|
|
* directly to a vma: instead it points to an anon_vma, on whose list
|
|
* the related vmas can be easily linked or unlinked.
|
|
*
|
|
* After unlinking the last vma on the list, we must garbage collect
|
|
* the anon_vma object itself: we're guaranteed no page can be
|
|
* pointing to this anon_vma once its vma list is empty.
|
|
*/
|
|
struct anon_vma {
|
|
struct anon_vma *root; /* Root of this anon_vma tree */
|
|
struct rw_semaphore rwsem; /* W: modification, R: walking the list */
|
|
/*
|
|
* The refcount is taken on an anon_vma when there is no
|
|
* guarantee that the vma of page tables will exist for
|
|
* the duration of the operation. A caller that takes
|
|
* the reference is responsible for clearing up the
|
|
* anon_vma if they are the last user on release
|
|
*/
|
|
atomic_t refcount;
|
|
|
|
/*
|
|
* Count of child anon_vmas and VMAs which points to this anon_vma.
|
|
*
|
|
* This counter is used for making decision about reusing anon_vma
|
|
* instead of forking new one. See comments in function anon_vma_clone.
|
|
*/
|
|
unsigned degree;
|
|
|
|
struct anon_vma *parent; /* Parent of this anon_vma */
|
|
|
|
/*
|
|
* NOTE: the LSB of the rb_root.rb_node is set by
|
|
* mm_take_all_locks() _after_ taking the above lock. So the
|
|
* rb_root must only be read/written after taking the above lock
|
|
* to be sure to see a valid next pointer. The LSB bit itself
|
|
* is serialized by a system wide lock only visible to
|
|
* mm_take_all_locks() (mm_all_locks_mutex).
|
|
*/
|
|
struct rb_root rb_root; /* Interval tree of private "related" vmas */
|
|
};
|
|
|
|
/*
|
|
* The copy-on-write semantics of fork mean that an anon_vma
|
|
* can become associated with multiple processes. Furthermore,
|
|
* each child process will have its own anon_vma, where new
|
|
* pages for that process are instantiated.
|
|
*
|
|
* This structure allows us to find the anon_vmas associated
|
|
* with a VMA, or the VMAs associated with an anon_vma.
|
|
* The "same_vma" list contains the anon_vma_chains linking
|
|
* all the anon_vmas associated with this VMA.
|
|
* The "rb" field indexes on an interval tree the anon_vma_chains
|
|
* which link all the VMAs associated with this anon_vma.
|
|
*/
|
|
struct anon_vma_chain {
|
|
struct vm_area_struct *vma;
|
|
struct anon_vma *anon_vma;
|
|
struct list_head same_vma; /* locked by mmap_sem & page_table_lock */
|
|
struct rb_node rb; /* locked by anon_vma->rwsem */
|
|
unsigned long rb_subtree_last;
|
|
#ifdef CONFIG_DEBUG_VM_RB
|
|
unsigned long cached_vma_start, cached_vma_last;
|
|
#endif
|
|
};
|
|
|
|
enum ttu_flags {
|
|
TTU_UNMAP = 1, /* unmap mode */
|
|
TTU_MIGRATION = 2, /* migration mode */
|
|
TTU_MUNLOCK = 4, /* munlock mode */
|
|
|
|
TTU_IGNORE_MLOCK = (1 << 8), /* ignore mlock */
|
|
TTU_IGNORE_ACCESS = (1 << 9), /* don't age */
|
|
TTU_IGNORE_HWPOISON = (1 << 10),/* corrupted page is recoverable */
|
|
TTU_BATCH_FLUSH = (1 << 11), /* Batch TLB flushes where possible
|
|
* and caller guarantees they will
|
|
* do a final flush if necessary */
|
|
};
|
|
|
|
#ifdef CONFIG_MMU
|
|
static inline void get_anon_vma(struct anon_vma *anon_vma)
|
|
{
|
|
atomic_inc(&anon_vma->refcount);
|
|
}
|
|
|
|
void __put_anon_vma(struct anon_vma *anon_vma);
|
|
|
|
static inline void put_anon_vma(struct anon_vma *anon_vma)
|
|
{
|
|
if (atomic_dec_and_test(&anon_vma->refcount))
|
|
__put_anon_vma(anon_vma);
|
|
}
|
|
|
|
static inline void vma_lock_anon_vma(struct vm_area_struct *vma)
|
|
{
|
|
struct anon_vma *anon_vma = vma->anon_vma;
|
|
if (anon_vma)
|
|
down_write(&anon_vma->root->rwsem);
|
|
}
|
|
|
|
static inline void vma_unlock_anon_vma(struct vm_area_struct *vma)
|
|
{
|
|
struct anon_vma *anon_vma = vma->anon_vma;
|
|
if (anon_vma)
|
|
up_write(&anon_vma->root->rwsem);
|
|
}
|
|
|
|
static inline void anon_vma_lock_write(struct anon_vma *anon_vma)
|
|
{
|
|
down_write(&anon_vma->root->rwsem);
|
|
}
|
|
|
|
static inline void anon_vma_unlock_write(struct anon_vma *anon_vma)
|
|
{
|
|
up_write(&anon_vma->root->rwsem);
|
|
}
|
|
|
|
static inline void anon_vma_lock_read(struct anon_vma *anon_vma)
|
|
{
|
|
down_read(&anon_vma->root->rwsem);
|
|
}
|
|
|
|
static inline void anon_vma_unlock_read(struct anon_vma *anon_vma)
|
|
{
|
|
up_read(&anon_vma->root->rwsem);
|
|
}
|
|
|
|
|
|
/*
|
|
* anon_vma helper functions.
|
|
*/
|
|
void anon_vma_init(void); /* create anon_vma_cachep */
|
|
int anon_vma_prepare(struct vm_area_struct *);
|
|
void unlink_anon_vmas(struct vm_area_struct *);
|
|
int anon_vma_clone(struct vm_area_struct *, struct vm_area_struct *);
|
|
int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *);
|
|
|
|
static inline void anon_vma_merge(struct vm_area_struct *vma,
|
|
struct vm_area_struct *next)
|
|
{
|
|
VM_BUG_ON_VMA(vma->anon_vma != next->anon_vma, vma);
|
|
unlink_anon_vmas(next);
|
|
}
|
|
|
|
struct anon_vma *page_get_anon_vma(struct page *page);
|
|
|
|
/*
|
|
* rmap interfaces called when adding or removing pte of page
|
|
*/
|
|
void page_move_anon_rmap(struct page *, struct vm_area_struct *, unsigned long);
|
|
void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long);
|
|
void do_page_add_anon_rmap(struct page *, struct vm_area_struct *,
|
|
unsigned long, int);
|
|
void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long);
|
|
void page_add_file_rmap(struct page *);
|
|
void page_remove_rmap(struct page *);
|
|
|
|
void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *,
|
|
unsigned long);
|
|
void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *,
|
|
unsigned long);
|
|
|
|
static inline void page_dup_rmap(struct page *page)
|
|
{
|
|
atomic_inc(&page->_mapcount);
|
|
}
|
|
|
|
/*
|
|
* Called from mm/vmscan.c to handle paging out
|
|
*/
|
|
int page_referenced(struct page *, int is_locked,
|
|
struct mem_cgroup *memcg, unsigned long *vm_flags);
|
|
|
|
#define TTU_ACTION(x) ((x) & TTU_ACTION_MASK)
|
|
|
|
int try_to_unmap(struct page *, enum ttu_flags flags);
|
|
|
|
/*
|
|
* Used by uprobes to replace a userspace page safely
|
|
*/
|
|
pte_t *__page_check_address(struct page *, struct mm_struct *,
|
|
unsigned long, spinlock_t **, int);
|
|
|
|
static inline pte_t *page_check_address(struct page *page, struct mm_struct *mm,
|
|
unsigned long address,
|
|
spinlock_t **ptlp, int sync)
|
|
{
|
|
pte_t *ptep;
|
|
|
|
__cond_lock(*ptlp, ptep = __page_check_address(page, mm, address,
|
|
ptlp, sync));
|
|
return ptep;
|
|
}
|
|
|
|
/*
|
|
* Used by swapoff to help locate where page is expected in vma.
|
|
*/
|
|
unsigned long page_address_in_vma(struct page *, struct vm_area_struct *);
|
|
|
|
/*
|
|
* Cleans the PTEs of shared mappings.
|
|
* (and since clean PTEs should also be readonly, write protects them too)
|
|
*
|
|
* returns the number of cleaned PTEs.
|
|
*/
|
|
int page_mkclean(struct page *);
|
|
|
|
/*
|
|
* called in munlock()/munmap() path to check for other vmas holding
|
|
* the page mlocked.
|
|
*/
|
|
int try_to_munlock(struct page *);
|
|
|
|
/*
|
|
* Called by memory-failure.c to kill processes.
|
|
*/
|
|
struct anon_vma *page_lock_anon_vma_read(struct page *page);
|
|
void page_unlock_anon_vma_read(struct anon_vma *anon_vma);
|
|
int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma);
|
|
|
|
/*
|
|
* rmap_walk_control: To control rmap traversing for specific needs
|
|
*
|
|
* arg: passed to rmap_one() and invalid_vma()
|
|
* rmap_one: executed on each vma where page is mapped
|
|
* done: for checking traversing termination condition
|
|
* anon_lock: for getting anon_lock by optimized way rather than default
|
|
* invalid_vma: for skipping uninterested vma
|
|
*/
|
|
struct rmap_walk_control {
|
|
void *arg;
|
|
int (*rmap_one)(struct page *page, struct vm_area_struct *vma,
|
|
unsigned long addr, void *arg);
|
|
int (*done)(struct page *page);
|
|
struct anon_vma *(*anon_lock)(struct page *page);
|
|
bool (*invalid_vma)(struct vm_area_struct *vma, void *arg);
|
|
};
|
|
|
|
int rmap_walk(struct page *page, struct rmap_walk_control *rwc);
|
|
|
|
#else /* !CONFIG_MMU */
|
|
|
|
#define anon_vma_init() do {} while (0)
|
|
#define anon_vma_prepare(vma) (0)
|
|
#define anon_vma_link(vma) do {} while (0)
|
|
|
|
static inline int page_referenced(struct page *page, int is_locked,
|
|
struct mem_cgroup *memcg,
|
|
unsigned long *vm_flags)
|
|
{
|
|
*vm_flags = 0;
|
|
return 0;
|
|
}
|
|
|
|
#define try_to_unmap(page, refs) SWAP_FAIL
|
|
|
|
static inline int page_mkclean(struct page *page)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
|
|
#endif /* CONFIG_MMU */
|
|
|
|
/*
|
|
* Return values of try_to_unmap
|
|
*/
|
|
#define SWAP_SUCCESS 0
|
|
#define SWAP_AGAIN 1
|
|
#define SWAP_FAIL 2
|
|
#define SWAP_MLOCK 3
|
|
|
|
#endif /* _LINUX_RMAP_H */
|