linux-stable/include/linux/vmalloc.h
Uladzislau Rezki (Sony) 96e2db4561 mm/vmalloc: rework the drain logic
A current "lazy drain" model suffers from at least two issues.

First one is related to the unsorted list of vmap areas, thus in order to
identify the [min:max] range of areas to be drained, it requires a full
list scan.  What is a time consuming if the list is too long.

Second one and as a next step is about merging all fragments with a free
space.  What is also a time consuming because it has to iterate over
entire list which holds outstanding lazy areas.

See below the "preemptirqsoff" tracer that illustrates a high latency.  It
is ~24676us.  Our workloads like audio and video are effected by such long
latency:

<snip>
  tracer: preemptirqsoff

  preemptirqsoff latency trace v1.1.5 on 4.9.186-perf+
  --------------------------------------------------------------------
  latency: 24676 us, #4/4, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 P:8)
     -----------------
     | task: crtc_commit:112-261 (uid:0 nice:0 policy:1 rt_prio:16)
     -----------------
   => started at: __purge_vmap_area_lazy
   => ended at:   __purge_vmap_area_lazy

                   _------=> CPU#
                  / _-----=> irqs-off
                 | / _----=> need-resched
                 || / _---=> hardirq/softirq
                 ||| / _--=> preempt-depth
                 |||| /     delay
   cmd     pid   ||||| time  |   caller
      \   /      |||||  \    |   /
crtc_com-261     1...1    1us*: _raw_spin_lock <-__purge_vmap_area_lazy
[...]
crtc_com-261     1...1 24675us : _raw_spin_unlock <-__purge_vmap_area_lazy
crtc_com-261     1...1 24677us : trace_preempt_on <-__purge_vmap_area_lazy
crtc_com-261     1...1 24683us : <stack trace>
 => free_vmap_area_noflush
 => remove_vm_area
 => __vunmap
 => vfree
 => drm_property_free_blob
 => drm_mode_object_unreference
 => drm_property_unreference_blob
 => __drm_atomic_helper_crtc_destroy_state
 => sde_crtc_destroy_state
 => drm_atomic_state_default_clear
 => drm_atomic_state_clear
 => drm_atomic_state_free
 => complete_commit
 => _msm_drm_commit_work_cb
 => kthread_worker_fn
 => kthread
 => ret_from_fork
<snip>

To address those two issues we can redesign a purging of the outstanding
lazy areas.  Instead of queuing vmap areas to the list, we replace it by
the separate rb-tree.  In hat case an area is located in the tree/list in
ascending order.  It will give us below advantages:

a) Outstanding vmap areas are merged creating bigger coalesced blocks,
   thus it becomes less fragmented.

b) It is possible to calculate a flush range [min:max] without scanning
   all elements.  It is O(1) access time or complexity;

c) The final merge of areas with the rb-tree that represents a free
   space is faster because of (a).  As a result the lock contention is
   also reduced.

Link: https://lkml.kernel.org/r/20201116220033.1837-2-urezki@gmail.com
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Cc: Hillf Danton <hdanton@sina.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: huang ying <huang.ying.caritas@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-12-15 12:13:41 -08:00

249 lines
7.6 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>
#include <asm/vmalloc.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_DMA_COHERENT 0x00000010 /* dma_alloc_coherent */
#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 */
#define VM_MAP_PUT_PAGES 0x00000100 /* put pages and free array in vfree */
/*
* VM_KASAN is used slighly differently depending on CONFIG_KASAN_VMALLOC.
*
* If IS_ENABLED(CONFIG_KASAN_VMALLOC), VM_KASAN is set on a vm_struct after
* shadow memory has been mapped. It's used to handle allocation errors so that
* we don't try to poision shadow on free if it was never allocated.
*
* Otherwise, VM_KASAN is set for kasan_module_alloc() allocations and used to
* determine which allocations need the module shadow freed.
*/
/*
* 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;
struct rb_node rb_node; /* address sorted rbtree */
struct list_head list; /* address sorted list */
/*
* The following two variables can be packed, because
* a vmap_area object can be either:
* 1) in "free" tree (root is vmap_area_root)
* 2) or "busy" tree (root is free_vmap_area_root)
*/
union {
unsigned long subtree_max_size; /* in "free" tree */
struct vm_struct *vm; /* in "busy" tree */
};
};
/*
* 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);
extern void vm_unmap_aliases(void);
#ifdef CONFIG_MMU
extern void __init vmalloc_init(void);
extern unsigned long vmalloc_nr_pages(void);
#else
static inline void vmalloc_init(void)
{
}
static inline unsigned long vmalloc_nr_pages(void) { return 0; }
#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_32(unsigned long size);
extern void *vmalloc_32_user(unsigned long size);
extern void *__vmalloc(unsigned long size, gfp_t gfp_mask);
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);
void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask,
int node, const void *caller);
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);
void *vmap_pfn(unsigned long *pfns, unsigned int count, 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 pgoff, unsigned long size);
extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
unsigned long pgoff);
/*
* Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values
* and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings()
* needs to be called.
*/
#ifndef ARCH_PAGE_TABLE_SYNC_MASK
#define ARCH_PAGE_TABLE_SYNC_MASK 0
#endif
/*
* There is no default implementation for arch_sync_kernel_mappings(). It is
* relied upon the compiler to optimize calls out if ARCH_PAGE_TABLE_SYNC_MASK
* is 0.
*/
void arch_sync_kernel_mappings(unsigned long start, unsigned long end);
/*
* 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_caller(unsigned long size,
unsigned long flags,
unsigned long start, unsigned long end,
const void *caller);
void free_vm_area(struct vm_struct *area);
extern struct vm_struct *remove_vm_area(const void *addr);
extern struct vm_struct *find_vm_area(const void *addr);
#ifdef CONFIG_MMU
extern int map_kernel_range_noflush(unsigned long start, unsigned long size,
pgprot_t prot, struct page **pages);
int map_kernel_range(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;
}
#define map_kernel_range map_kernel_range_noflush
static inline void
unmap_kernel_range_noflush(unsigned long addr, unsigned long size)
{
}
#define unmap_kernel_range unmap_kernel_range_noflush
static inline void set_vm_flush_reset_perms(void *addr)
{
}
#endif
/* 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 */