kernel-fxtec-pro1x/include/linux/pagemap.h
Minchan Kim c27ea19ea4 ANDROID: GKI: attribute page lock and waitqueue functions as sched
trace_sched_blocked_trace in CFS is really useful for debugging via
trace because it tell where the process was stuck on callstack.

For example,
           <...>-6143  ( 6136) [005] d..2    50.278987: sched_blocked_reason: pid=6136 iowait=0 caller=SyS_mprotect+0x88/0x208
           <...>-6136  ( 6136) [005] d..2    50.278990: sched_blocked_reason: pid=6142 iowait=0 caller=do_page_fault+0x1f4/0x3b0
           <...>-6142  ( 6136) [006] d..2    50.278996: sched_blocked_reason: pid=6144 iowait=0 caller=SyS_prctl+0x52c/0xb58
           <...>-6144  ( 6136) [006] d..2    50.279007: sched_blocked_reason: pid=6136 iowait=0 caller=vm_mmap_pgoff+0x74/0x104

However, sometime it gives pointless information like this.
    RenderThread-2322  ( 1805) [006] d.s3    50.319046: sched_blocked_reason: pid=6136 iowait=1 caller=__lock_page_killable+0x17c/0x220
     logd.writer-594   (  587) [002] d.s3    50.334011: sched_blocked_reason: pid=6126 iowait=1 caller=wait_on_page_bit+0x194/0x208
  kworker/u16:13-333   (  333) [007] d.s4    50.343161: sched_blocked_reason: pid=6136 iowait=1 caller=__lock_page_killable+0x17c/0x220

Such wait_on_page_bit, __lock_page_killable are pointless because it doesn't
carry on higher information to identify the callstack.

The reason is page_lock and waitqueue are special synchronization method unlike
other normal locks(mutex, spinlock).
Let's mark them as "__sched" so get_wchan which used in trace_sched_blocked_trace
could detect it and skip them. It will produce more meaningful callstack
function like this.

           <...>-2867  ( 1068) [002] d.h4   124.209701: sched_blocked_reason: pid=329 iowait=0 caller=worker_thread+0x378/0x470
           <...>-2867  ( 1068) [002] d.s3   124.209763: sched_blocked_reason: pid=8454 iowait=1 caller=__filemap_fdatawait_range+0xa0/0x104
           <...>-2867  ( 1068) [002] d.s4   124.209803: sched_blocked_reason: pid=869 iowait=0 caller=worker_thread+0x378/0x470
 ScreenDecoratio-2364  ( 1867) [002] d.s3   124.209973: sched_blocked_reason: pid=8454 iowait=1 caller=f2fs_wait_on_page_writeback+0x84/0xcc
 ScreenDecoratio-2364  ( 1867) [002] d.s4   124.209986: sched_blocked_reason: pid=869 iowait=0 caller=worker_thread+0x378/0x470
           <...>-329   (  329) [000] d..3   124.210435: sched_blocked_reason: pid=538 iowait=0 caller=worker_thread+0x378/0x470
  kworker/u16:13-538   (  538) [007] d..3   124.210450: sched_blocked_reason: pid=6 iowait=0 caller=worker_thread+0x378/0x470

Bug: 144961676
Bug: 144713689
Change-Id: I30397400c5d056946bdfbc86c9ef5f4d7e6c98fe
Signed-off-by: Minchan Kim <minchan@google.com>
Signed-off-by: Jimmy Shiu <jimmyshiu@google.com>
Bug: 152417756
(cherry picked from commit 8a780c0eb6800cecbfce21362c2d2a3bcab14e1c)
Signed-off-by: Saravana Kannan <saravanak@google.com>
2020-04-17 22:51:44 -07:00

649 lines
19 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_PAGEMAP_H
#define _LINUX_PAGEMAP_H
/*
* Copyright 1995 Linus Torvalds
*/
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/list.h>
#include <linux/highmem.h>
#include <linux/compiler.h>
#include <linux/uaccess.h>
#include <linux/gfp.h>
#include <linux/bitops.h>
#include <linux/hardirq.h> /* for in_interrupt() */
#include <linux/hugetlb_inline.h>
struct pagevec;
/*
* Bits in mapping->flags.
*/
enum mapping_flags {
AS_EIO = 0, /* IO error on async write */
AS_ENOSPC = 1, /* ENOSPC on async write */
AS_MM_ALL_LOCKS = 2, /* under mm_take_all_locks() */
AS_UNEVICTABLE = 3, /* e.g., ramdisk, SHM_LOCK */
AS_EXITING = 4, /* final truncate in progress */
/* writeback related tags are not used */
AS_NO_WRITEBACK_TAGS = 5,
};
/**
* mapping_set_error - record a writeback error in the address_space
* @mapping - the mapping in which an error should be set
* @error - the error to set in the mapping
*
* When writeback fails in some way, we must record that error so that
* userspace can be informed when fsync and the like are called. We endeavor
* to report errors on any file that was open at the time of the error. Some
* internal callers also need to know when writeback errors have occurred.
*
* When a writeback error occurs, most filesystems will want to call
* mapping_set_error to record the error in the mapping so that it can be
* reported when the application calls fsync(2).
*/
static inline void mapping_set_error(struct address_space *mapping, int error)
{
if (likely(!error))
return;
/* Record in wb_err for checkers using errseq_t based tracking */
filemap_set_wb_err(mapping, error);
/* Record it in flags for now, for legacy callers */
if (error == -ENOSPC)
set_bit(AS_ENOSPC, &mapping->flags);
else
set_bit(AS_EIO, &mapping->flags);
}
static inline void mapping_set_unevictable(struct address_space *mapping)
{
set_bit(AS_UNEVICTABLE, &mapping->flags);
}
static inline void mapping_clear_unevictable(struct address_space *mapping)
{
clear_bit(AS_UNEVICTABLE, &mapping->flags);
}
static inline int mapping_unevictable(struct address_space *mapping)
{
if (mapping)
return test_bit(AS_UNEVICTABLE, &mapping->flags);
return !!mapping;
}
static inline void mapping_set_exiting(struct address_space *mapping)
{
set_bit(AS_EXITING, &mapping->flags);
}
static inline int mapping_exiting(struct address_space *mapping)
{
return test_bit(AS_EXITING, &mapping->flags);
}
static inline void mapping_set_no_writeback_tags(struct address_space *mapping)
{
set_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags);
}
static inline int mapping_use_writeback_tags(struct address_space *mapping)
{
return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags);
}
static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
{
return mapping->gfp_mask;
}
/* Restricts the given gfp_mask to what the mapping allows. */
static inline gfp_t mapping_gfp_constraint(struct address_space *mapping,
gfp_t gfp_mask)
{
return mapping_gfp_mask(mapping) & gfp_mask;
}
/*
* This is non-atomic. Only to be used before the mapping is activated.
* Probably needs a barrier...
*/
static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
{
m->gfp_mask = mask;
}
void release_pages(struct page **pages, int nr);
/*
* speculatively take a reference to a page.
* If the page is free (_refcount == 0), then _refcount is untouched, and 0
* is returned. Otherwise, _refcount is incremented by 1 and 1 is returned.
*
* This function must be called inside the same rcu_read_lock() section as has
* been used to lookup the page in the pagecache radix-tree (or page table):
* this allows allocators to use a synchronize_rcu() to stabilize _refcount.
*
* Unless an RCU grace period has passed, the count of all pages coming out
* of the allocator must be considered unstable. page_count may return higher
* than expected, and put_page must be able to do the right thing when the
* page has been finished with, no matter what it is subsequently allocated
* for (because put_page is what is used here to drop an invalid speculative
* reference).
*
* This is the interesting part of the lockless pagecache (and lockless
* get_user_pages) locking protocol, where the lookup-side (eg. find_get_page)
* has the following pattern:
* 1. find page in radix tree
* 2. conditionally increment refcount
* 3. check the page is still in pagecache (if no, goto 1)
*
* Remove-side that cares about stability of _refcount (eg. reclaim) has the
* following (with the i_pages lock held):
* A. atomically check refcount is correct and set it to 0 (atomic_cmpxchg)
* B. remove page from pagecache
* C. free the page
*
* There are 2 critical interleavings that matter:
* - 2 runs before A: in this case, A sees elevated refcount and bails out
* - A runs before 2: in this case, 2 sees zero refcount and retries;
* subsequently, B will complete and 1 will find no page, causing the
* lookup to return NULL.
*
* It is possible that between 1 and 2, the page is removed then the exact same
* page is inserted into the same position in pagecache. That's OK: the
* old find_get_page using a lock could equally have run before or after
* such a re-insertion, depending on order that locks are granted.
*
* Lookups racing against pagecache insertion isn't a big problem: either 1
* will find the page or it will not. Likewise, the old find_get_page could run
* either before the insertion or afterwards, depending on timing.
*/
static inline int page_cache_get_speculative(struct page *page)
{
#ifdef CONFIG_TINY_RCU
# ifdef CONFIG_PREEMPT_COUNT
VM_BUG_ON(!in_atomic() && !irqs_disabled());
# endif
/*
* Preempt must be disabled here - we rely on rcu_read_lock doing
* this for us.
*
* Pagecache won't be truncated from interrupt context, so if we have
* found a page in the radix tree here, we have pinned its refcount by
* disabling preempt, and hence no need for the "speculative get" that
* SMP requires.
*/
VM_BUG_ON_PAGE(page_count(page) == 0, page);
page_ref_inc(page);
#else
if (unlikely(!get_page_unless_zero(page))) {
/*
* Either the page has been freed, or will be freed.
* In either case, retry here and the caller should
* do the right thing (see comments above).
*/
return 0;
}
#endif
VM_BUG_ON_PAGE(PageTail(page), page);
return 1;
}
/*
* Same as above, but add instead of inc (could just be merged)
*/
static inline int page_cache_add_speculative(struct page *page, int count)
{
VM_BUG_ON(in_interrupt());
#if !defined(CONFIG_SMP) && defined(CONFIG_TREE_RCU)
# ifdef CONFIG_PREEMPT_COUNT
VM_BUG_ON(!in_atomic() && !irqs_disabled());
# endif
VM_BUG_ON_PAGE(page_count(page) == 0, page);
page_ref_add(page, count);
#else
if (unlikely(!page_ref_add_unless(page, count, 0)))
return 0;
#endif
VM_BUG_ON_PAGE(PageCompound(page) && page != compound_head(page), page);
return 1;
}
#ifdef CONFIG_NUMA
extern struct page *__page_cache_alloc(gfp_t gfp);
#else
static inline struct page *__page_cache_alloc(gfp_t gfp)
{
return alloc_pages(gfp, 0);
}
#endif
static inline struct page *page_cache_alloc(struct address_space *x)
{
return __page_cache_alloc(mapping_gfp_mask(x));
}
static inline gfp_t readahead_gfp_mask(struct address_space *x)
{
return mapping_gfp_mask(x) | __GFP_NORETRY | __GFP_NOWARN;
}
typedef int filler_t(void *, struct page *);
pgoff_t page_cache_next_hole(struct address_space *mapping,
pgoff_t index, unsigned long max_scan);
pgoff_t page_cache_prev_hole(struct address_space *mapping,
pgoff_t index, unsigned long max_scan);
#define FGP_ACCESSED 0x00000001
#define FGP_LOCK 0x00000002
#define FGP_CREAT 0x00000004
#define FGP_WRITE 0x00000008
#define FGP_NOFS 0x00000010
#define FGP_NOWAIT 0x00000020
#define FGP_FOR_MMAP 0x00000040
struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
int fgp_flags, gfp_t cache_gfp_mask);
/**
* find_get_page - find and get a page reference
* @mapping: the address_space to search
* @offset: the page index
*
* Looks up the page cache slot at @mapping & @offset. If there is a
* page cache page, it is returned with an increased refcount.
*
* Otherwise, %NULL is returned.
*/
static inline struct page *find_get_page(struct address_space *mapping,
pgoff_t offset)
{
return pagecache_get_page(mapping, offset, 0, 0);
}
static inline struct page *find_get_page_flags(struct address_space *mapping,
pgoff_t offset, int fgp_flags)
{
return pagecache_get_page(mapping, offset, fgp_flags, 0);
}
/**
* find_lock_page - locate, pin and lock a pagecache page
* @mapping: the address_space to search
* @offset: the page index
*
* Looks up the page cache slot at @mapping & @offset. If there is a
* page cache page, it is returned locked and with an increased
* refcount.
*
* Otherwise, %NULL is returned.
*
* find_lock_page() may sleep.
*/
static inline struct page *find_lock_page(struct address_space *mapping,
pgoff_t offset)
{
return pagecache_get_page(mapping, offset, FGP_LOCK, 0);
}
/**
* find_or_create_page - locate or add a pagecache page
* @mapping: the page's address_space
* @index: the page's index into the mapping
* @gfp_mask: page allocation mode
*
* Looks up the page cache slot at @mapping & @offset. If there is a
* page cache page, it is returned locked and with an increased
* refcount.
*
* If the page is not present, a new page is allocated using @gfp_mask
* and added to the page cache and the VM's LRU list. The page is
* returned locked and with an increased refcount.
*
* On memory exhaustion, %NULL is returned.
*
* find_or_create_page() may sleep, even if @gfp_flags specifies an
* atomic allocation!
*/
static inline struct page *find_or_create_page(struct address_space *mapping,
pgoff_t offset, gfp_t gfp_mask)
{
return pagecache_get_page(mapping, offset,
FGP_LOCK|FGP_ACCESSED|FGP_CREAT,
gfp_mask);
}
/**
* grab_cache_page_nowait - returns locked page at given index in given cache
* @mapping: target address_space
* @index: the page index
*
* Same as grab_cache_page(), but do not wait if the page is unavailable.
* This is intended for speculative data generators, where the data can
* be regenerated if the page couldn't be grabbed. This routine should
* be safe to call while holding the lock for another page.
*
* Clear __GFP_FS when allocating the page to avoid recursion into the fs
* and deadlock against the caller's locked page.
*/
static inline struct page *grab_cache_page_nowait(struct address_space *mapping,
pgoff_t index)
{
return pagecache_get_page(mapping, index,
FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT,
mapping_gfp_mask(mapping));
}
struct page *find_get_entry(struct address_space *mapping, pgoff_t offset);
struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset);
unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
unsigned int nr_entries, struct page **entries,
pgoff_t *indices);
unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start,
pgoff_t end, unsigned int nr_pages,
struct page **pages);
static inline unsigned find_get_pages(struct address_space *mapping,
pgoff_t *start, unsigned int nr_pages,
struct page **pages)
{
return find_get_pages_range(mapping, start, (pgoff_t)-1, nr_pages,
pages);
}
unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start,
unsigned int nr_pages, struct page **pages);
unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
pgoff_t end, int tag, unsigned int nr_pages,
struct page **pages);
static inline unsigned find_get_pages_tag(struct address_space *mapping,
pgoff_t *index, int tag, unsigned int nr_pages,
struct page **pages)
{
return find_get_pages_range_tag(mapping, index, (pgoff_t)-1, tag,
nr_pages, pages);
}
unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
int tag, unsigned int nr_entries,
struct page **entries, pgoff_t *indices);
struct page *grab_cache_page_write_begin(struct address_space *mapping,
pgoff_t index, unsigned flags);
/*
* Returns locked page at given index in given cache, creating it if needed.
*/
static inline struct page *grab_cache_page(struct address_space *mapping,
pgoff_t index)
{
return find_or_create_page(mapping, index, mapping_gfp_mask(mapping));
}
extern struct page * read_cache_page(struct address_space *mapping,
pgoff_t index, filler_t *filler, void *data);
extern struct page * read_cache_page_gfp(struct address_space *mapping,
pgoff_t index, gfp_t gfp_mask);
extern int read_cache_pages(struct address_space *mapping,
struct list_head *pages, filler_t *filler, void *data);
static inline struct page *read_mapping_page(struct address_space *mapping,
pgoff_t index, void *data)
{
return read_cache_page(mapping, index, NULL, data);
}
/*
* Get index of the page with in radix-tree
* (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE)
*/
static inline pgoff_t page_to_index(struct page *page)
{
pgoff_t pgoff;
if (likely(!PageTransTail(page)))
return page->index;
/*
* We don't initialize ->index for tail pages: calculate based on
* head page
*/
pgoff = compound_head(page)->index;
pgoff += page - compound_head(page);
return pgoff;
}
/*
* Get the offset in PAGE_SIZE.
* (TODO: hugepage should have ->index in PAGE_SIZE)
*/
static inline pgoff_t page_to_pgoff(struct page *page)
{
if (unlikely(PageHeadHuge(page)))
return page->index << compound_order(page);
return page_to_index(page);
}
/*
* Return byte-offset into filesystem object for page.
*/
static inline loff_t page_offset(struct page *page)
{
return ((loff_t)page->index) << PAGE_SHIFT;
}
static inline loff_t page_file_offset(struct page *page)
{
return ((loff_t)page_index(page)) << PAGE_SHIFT;
}
extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
unsigned long address);
static inline pgoff_t linear_page_index(struct vm_area_struct *vma,
unsigned long address)
{
pgoff_t pgoff;
if (unlikely(is_vm_hugetlb_page(vma)))
return linear_hugepage_index(vma, address);
pgoff = (address - vma->vm_start) >> PAGE_SHIFT;
pgoff += vma->vm_pgoff;
return pgoff;
}
extern void __sched __lock_page(struct page *page);
extern int __sched __lock_page_killable(struct page *page);
extern int __sched __lock_page_or_retry(struct page *page, struct mm_struct *mm,
unsigned int flags);
extern void unlock_page(struct page *page);
static inline int trylock_page(struct page *page)
{
page = compound_head(page);
return (likely(!test_and_set_bit_lock(PG_locked, &page->flags)));
}
/*
* lock_page may only be called if we have the page's inode pinned.
*/
static inline __sched void lock_page(struct page *page)
{
might_sleep();
if (!trylock_page(page))
__lock_page(page);
}
/*
* lock_page_killable is like lock_page but can be interrupted by fatal
* signals. It returns 0 if it locked the page and -EINTR if it was
* killed while waiting.
*/
static inline __sched int lock_page_killable(struct page *page)
{
might_sleep();
if (!trylock_page(page))
return __lock_page_killable(page);
return 0;
}
/*
* lock_page_or_retry - Lock the page, unless this would block and the
* caller indicated that it can handle a retry.
*
* Return value and mmap_sem implications depend on flags; see
* __lock_page_or_retry().
*/
static inline __sched int lock_page_or_retry(struct page *page,
struct mm_struct *mm,
unsigned int flags)
{
might_sleep();
return trylock_page(page) || __lock_page_or_retry(page, mm, flags);
}
/*
* This is exported only for wait_on_page_locked/wait_on_page_writeback, etc.,
* and should not be used directly.
*/
extern void __sched wait_on_page_bit(struct page *page, int bit_nr);
extern int __sched wait_on_page_bit_killable(struct page *page, int bit_nr);
/*
* Wait for a page to be unlocked.
*
* This must be called with the caller "holding" the page,
* ie with increased "page->count" so that the page won't
* go away during the wait..
*/
static inline __sched void wait_on_page_locked(struct page *page)
{
if (PageLocked(page))
wait_on_page_bit(compound_head(page), PG_locked);
}
static inline __sched int wait_on_page_locked_killable(struct page *page)
{
if (!PageLocked(page))
return 0;
return wait_on_page_bit_killable(compound_head(page), PG_locked);
}
/*
* Wait for a page to complete writeback
*/
static inline __sched void wait_on_page_writeback(struct page *page)
{
if (PageWriteback(page))
wait_on_page_bit(page, PG_writeback);
}
extern void end_page_writeback(struct page *page);
void wait_for_stable_page(struct page *page);
void page_endio(struct page *page, bool is_write, int err);
/*
* Add an arbitrary waiter to a page's wait queue
*/
extern void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter);
/*
* Fault everything in given userspace address range in.
*/
static inline int fault_in_pages_writeable(char __user *uaddr, int size)
{
char __user *end = uaddr + size - 1;
if (unlikely(size == 0))
return 0;
if (unlikely(uaddr > end))
return -EFAULT;
/*
* Writing zeroes into userspace here is OK, because we know that if
* the zero gets there, we'll be overwriting it.
*/
do {
if (unlikely(__put_user(0, uaddr) != 0))
return -EFAULT;
uaddr += PAGE_SIZE;
} while (uaddr <= end);
/* Check whether the range spilled into the next page. */
if (((unsigned long)uaddr & PAGE_MASK) ==
((unsigned long)end & PAGE_MASK))
return __put_user(0, end);
return 0;
}
static inline int fault_in_pages_readable(const char __user *uaddr, int size)
{
volatile char c;
const char __user *end = uaddr + size - 1;
if (unlikely(size == 0))
return 0;
if (unlikely(uaddr > end))
return -EFAULT;
do {
if (unlikely(__get_user(c, uaddr) != 0))
return -EFAULT;
uaddr += PAGE_SIZE;
} while (uaddr <= end);
/* Check whether the range spilled into the next page. */
if (((unsigned long)uaddr & PAGE_MASK) ==
((unsigned long)end & PAGE_MASK)) {
return __get_user(c, end);
}
(void)c;
return 0;
}
int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
pgoff_t index, gfp_t gfp_mask);
int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
pgoff_t index, gfp_t gfp_mask);
extern void delete_from_page_cache(struct page *page);
extern void __delete_from_page_cache(struct page *page, void *shadow);
int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask);
void delete_from_page_cache_batch(struct address_space *mapping,
struct pagevec *pvec);
/*
* Like add_to_page_cache_locked, but used to add newly allocated pages:
* the page is new, so we can just run __SetPageLocked() against it.
*/
static inline int add_to_page_cache(struct page *page,
struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask)
{
int error;
__SetPageLocked(page);
error = add_to_page_cache_locked(page, mapping, offset, gfp_mask);
if (unlikely(error))
__ClearPageLocked(page);
return error;
}
static inline unsigned long dir_pages(struct inode *inode)
{
return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >>
PAGE_SHIFT;
}
#endif /* _LINUX_PAGEMAP_H */