android_kernel_xiaomi_sm8350/mm/page_io.c
Greg Kroah-Hartman 00c4652b41 This is the 5.4.193 stable release
-----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAmJ84EgACgkQONu9yGCS
 aT75fxAAj9FUW/Vi1U4/QwbAE3ZHI46D++xmpVsuoXJg8M49twIFwLAtae+oeaFL
 D0AoAhdXJx4kHIOk6XHty3sQb2TZnQw7eSRY4BuB4vT/Tnsy3Ap3L2rbwjwdjSr4
 NJWJ+Cr7w8arU4ZgQks+sGamSBWIm69+36VD6N9LjuHofwL0mJi9bZ5JbLvc1pv1
 +t5InguLQXvFK1ZZ/0IMpVnhrmm+lMynUKCif9yN7CXiRATmktSfguUGMO5sae7X
 X3SG64cxp1wh2P+gDEVytZfI/7FWCW/Uu5w1sDnXNhjG3Mizm+3j+olK1/wmj4uo
 UmP2K8CGfTGVlRG6GXVFmWXJLlUYJfyRC13L2t6fuqio9HK/anNGrsqQiD1YOTTF
 TgaFOTkPVfeNI+stAX/pxfiRihlF9INyH32yMacKJ5nKZYgJBTWiamktDwL2FRx3
 8N5UdnYqeHWHNQdnT3Z0c8qIW9uHamvs7hwphPV6tr9iJqZafBlt4mD+livrHcg9
 s/MF1rodYeHP2a/oGBNmWlHFf31lqY/cciy0PPCNfrK4WPS0KaLC87YGxigqhxfi
 MNdcOX2akUEAOVDIOyuO3tES2rKj6ffL5B/F+YAQO/4wNqBCQPsLs4hGlJBLlBI7
 PNuT3hf3sV2n2NWavFSKuyfIzupzjqeybi+wZdmOT/mXKuoza0I=
 =Isyq
 -----END PGP SIGNATURE-----

Merge 5.4.193 into android11-5.4-lts

Changes in 5.4.193
	MIPS: Fix CP0 counter erratum detection for R4k CPUs
	parisc: Merge model and model name into one line in /proc/cpuinfo
	ALSA: fireworks: fix wrong return count shorter than expected by 4 bytes
	gpiolib: of: fix bounds check for 'gpio-reserved-ranges'
	Revert "SUNRPC: attempt AF_LOCAL connect on setup"
	firewire: fix potential uaf in outbound_phy_packet_callback()
	firewire: remove check of list iterator against head past the loop body
	firewire: core: extend card->lock in fw_core_handle_bus_reset
	ACPICA: Always create namespace nodes using acpi_ns_create_node()
	genirq: Synchronize interrupt thread startup
	ASoC: da7219: Fix change notifications for tone generator frequency
	ASoC: wm8958: Fix change notifications for DSP controls
	ASoC: meson: Fix event generation for G12A tohdmi mux
	s390/dasd: fix data corruption for ESE devices
	s390/dasd: prevent double format of tracks for ESE devices
	s390/dasd: Fix read for ESE with blksize < 4k
	s390/dasd: Fix read inconsistency for ESE DASD devices
	can: grcan: grcan_close(): fix deadlock
	can: grcan: use ofdev->dev when allocating DMA memory
	nfc: replace improper check device_is_registered() in netlink related functions
	nfc: nfcmrvl: main: reorder destructive operations in nfcmrvl_nci_unregister_dev to avoid bugs
	NFC: netlink: fix sleep in atomic bug when firmware download timeout
	hwmon: (adt7470) Fix warning on module removal
	ASoC: dmaengine: Restore NULL prepare_slave_config() callback
	RDMA/siw: Fix a condition race issue in MPA request processing
	net: ethernet: mediatek: add missing of_node_put() in mtk_sgmii_init()
	net: stmmac: dwmac-sun8i: add missing of_node_put() in sun8i_dwmac_register_mdio_mux()
	net: emaclite: Add error handling for of_address_to_resource()
	selftests: mirror_gre_bridge_1q: Avoid changing PVID while interface is operational
	bnxt_en: Fix possible bnxt_open() failure caused by wrong RFS flag
	smsc911x: allow using IRQ0
	btrfs: always log symlinks in full mode
	net: igmp: respect RCU rules in ip_mc_source() and ip_mc_msfilter()
	drm/amdkfd: Use drm_priv to pass VM from KFD to amdgpu
	NFSv4: Don't invalidate inode attributes on delegation return
	kvm: x86/cpuid: Only provide CPUID leaf 0xA if host has architectural PMU
	x86/kvm: Preserve BSP MSR_KVM_POLL_CONTROL across suspend/resume
	KVM: LAPIC: Enable timer posted-interrupt only when mwait/hlt is advertised
	net: ipv6: ensure we call ipv6_mc_down() at most once
	block-map: add __GFP_ZERO flag for alloc_page in function bio_copy_kern
	mm: fix unexpected zeroed page mapping with zram swap
	ALSA: pcm: Fix races among concurrent hw_params and hw_free calls
	ALSA: pcm: Fix races among concurrent read/write and buffer changes
	ALSA: pcm: Fix races among concurrent prepare and hw_params/hw_free calls
	ALSA: pcm: Fix races among concurrent prealloc proc writes
	ALSA: pcm: Fix potential AB/BA lock with buffer_mutex and mmap_lock
	tcp: make sure treq->af_specific is initialized
	dm: fix mempool NULL pointer race when completing IO
	dm: interlock pending dm_io and dm_wait_for_bios_completion
	PCI: aardvark: Clear all MSIs at setup
	PCI: aardvark: Fix reading MSI interrupt number
	mmc: rtsx: add 74 Clocks in power on flow
	Linux 5.4.193

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: I535ab835023ebb753a9bf8073c15f8e434862567
2022-05-16 08:51:00 +02:00

389 lines
9.1 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* linux/mm/page_io.c
*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
*
* Swap reorganised 29.12.95,
* Asynchronous swapping added 30.12.95. Stephen Tweedie
* Removed race in async swapping. 14.4.1996. Bruno Haible
* Add swap of shared pages through the page cache. 20.2.1998. Stephen Tweedie
* Always use brw_page, life becomes simpler. 12 May 1998 Eric Biederman
*/
#include <linux/mm.h>
#include <linux/kernel_stat.h>
#include <linux/gfp.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/bio.h>
#include <linux/swapops.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/frontswap.h>
#include <linux/blkdev.h>
#include <linux/psi.h>
#include <linux/uio.h>
#include <linux/sched/task.h>
#include <asm/pgtable.h>
static struct bio *get_swap_bio(gfp_t gfp_flags,
struct page *page, bio_end_io_t end_io)
{
struct bio *bio;
bio = bio_alloc(gfp_flags, 1);
if (bio) {
struct block_device *bdev;
bio->bi_iter.bi_sector = map_swap_page(page, &bdev);
bio_set_dev(bio, bdev);
bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9;
bio->bi_end_io = end_io;
bio_add_page(bio, page, PAGE_SIZE * hpage_nr_pages(page), 0);
}
return bio;
}
void end_swap_bio_write(struct bio *bio)
{
struct page *page = bio_first_page_all(bio);
if (bio->bi_status) {
SetPageError(page);
/*
* We failed to write the page out to swap-space.
* Re-dirty the page in order to avoid it being reclaimed.
* Also print a dire warning that things will go BAD (tm)
* very quickly.
*
* Also clear PG_reclaim to avoid rotate_reclaimable_page()
*/
set_page_dirty(page);
pr_alert("Write-error on swap-device (%u:%u:%llu)\n",
MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)),
(unsigned long long)bio->bi_iter.bi_sector);
ClearPageReclaim(page);
}
end_page_writeback(page);
bio_put(bio);
}
static void end_swap_bio_read(struct bio *bio)
{
struct page *page = bio_first_page_all(bio);
struct task_struct *waiter = bio->bi_private;
if (bio->bi_status) {
SetPageError(page);
ClearPageUptodate(page);
pr_alert("Read-error on swap-device (%u:%u:%llu)\n",
MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)),
(unsigned long long)bio->bi_iter.bi_sector);
goto out;
}
SetPageUptodate(page);
out:
unlock_page(page);
WRITE_ONCE(bio->bi_private, NULL);
bio_put(bio);
if (waiter) {
blk_wake_io_task(waiter);
put_task_struct(waiter);
}
}
int generic_swapfile_activate(struct swap_info_struct *sis,
struct file *swap_file,
sector_t *span)
{
struct address_space *mapping = swap_file->f_mapping;
struct inode *inode = mapping->host;
unsigned blocks_per_page;
unsigned long page_no;
unsigned blkbits;
sector_t probe_block;
sector_t last_block;
sector_t lowest_block = -1;
sector_t highest_block = 0;
int nr_extents = 0;
int ret;
blkbits = inode->i_blkbits;
blocks_per_page = PAGE_SIZE >> blkbits;
/*
* Map all the blocks into the extent tree. This code doesn't try
* to be very smart.
*/
probe_block = 0;
page_no = 0;
last_block = i_size_read(inode) >> blkbits;
while ((probe_block + blocks_per_page) <= last_block &&
page_no < sis->max) {
unsigned block_in_page;
sector_t first_block;
cond_resched();
first_block = bmap(inode, probe_block);
if (first_block == 0)
goto bad_bmap;
/*
* It must be PAGE_SIZE aligned on-disk
*/
if (first_block & (blocks_per_page - 1)) {
probe_block++;
goto reprobe;
}
for (block_in_page = 1; block_in_page < blocks_per_page;
block_in_page++) {
sector_t block;
block = bmap(inode, probe_block + block_in_page);
if (block == 0)
goto bad_bmap;
if (block != first_block + block_in_page) {
/* Discontiguity */
probe_block++;
goto reprobe;
}
}
first_block >>= (PAGE_SHIFT - blkbits);
if (page_no) { /* exclude the header page */
if (first_block < lowest_block)
lowest_block = first_block;
if (first_block > highest_block)
highest_block = first_block;
}
/*
* We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks
*/
ret = add_swap_extent(sis, page_no, 1, first_block);
if (ret < 0)
goto out;
nr_extents += ret;
page_no++;
probe_block += blocks_per_page;
reprobe:
continue;
}
ret = nr_extents;
*span = 1 + highest_block - lowest_block;
if (page_no == 0)
page_no = 1; /* force Empty message */
sis->max = page_no;
sis->pages = page_no - 1;
sis->highest_bit = page_no - 1;
out:
return ret;
bad_bmap:
pr_err("swapon: swapfile has holes\n");
ret = -EINVAL;
goto out;
}
/*
* We may have stale swap cache pages in memory: notice
* them here and get rid of the unnecessary final write.
*/
int swap_writepage(struct page *page, struct writeback_control *wbc)
{
int ret = 0;
if (try_to_free_swap(page)) {
unlock_page(page);
goto out;
}
if (frontswap_store(page) == 0) {
set_page_writeback(page);
unlock_page(page);
end_page_writeback(page);
goto out;
}
ret = __swap_writepage(page, wbc, end_swap_bio_write);
out:
return ret;
}
static inline void count_swpout_vm_event(struct page *page)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
if (unlikely(PageTransHuge(page)))
count_vm_event(THP_SWPOUT);
#endif
count_vm_events(PSWPOUT, hpage_nr_pages(page));
}
int __swap_writepage(struct page *page, struct writeback_control *wbc,
bio_end_io_t end_write_func)
{
struct bio *bio;
int ret;
struct swap_info_struct *sis = page_swap_info(page);
VM_BUG_ON_PAGE(!PageSwapCache(page), page);
if (sis->flags & SWP_FS) {
struct kiocb kiocb;
struct file *swap_file = sis->swap_file;
struct address_space *mapping = swap_file->f_mapping;
struct bio_vec bv = {
.bv_page = page,
.bv_len = PAGE_SIZE,
.bv_offset = 0
};
struct iov_iter from;
iov_iter_bvec(&from, WRITE, &bv, 1, PAGE_SIZE);
init_sync_kiocb(&kiocb, swap_file);
kiocb.ki_pos = page_file_offset(page);
set_page_writeback(page);
unlock_page(page);
ret = mapping->a_ops->direct_IO(&kiocb, &from);
if (ret == PAGE_SIZE) {
count_vm_event(PSWPOUT);
ret = 0;
} else {
/*
* In the case of swap-over-nfs, this can be a
* temporary failure if the system has limited
* memory for allocating transmit buffers.
* Mark the page dirty and avoid
* rotate_reclaimable_page but rate-limit the
* messages but do not flag PageError like
* the normal direct-to-bio case as it could
* be temporary.
*/
set_page_dirty(page);
ClearPageReclaim(page);
pr_err_ratelimited("Write error on dio swapfile (%llu)\n",
page_file_offset(page));
}
end_page_writeback(page);
return ret;
}
ret = bdev_write_page(sis->bdev, swap_page_sector(page), page, wbc);
if (!ret) {
count_swpout_vm_event(page);
return 0;
}
ret = 0;
bio = get_swap_bio(GFP_NOIO, page, end_write_func);
if (bio == NULL) {
set_page_dirty(page);
unlock_page(page);
ret = -ENOMEM;
goto out;
}
bio->bi_opf = REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc);
bio_associate_blkg_from_page(bio, page);
count_swpout_vm_event(page);
set_page_writeback(page);
unlock_page(page);
submit_bio(bio);
out:
return ret;
}
int swap_readpage(struct page *page, bool synchronous)
{
struct bio *bio;
int ret = 0;
struct swap_info_struct *sis = page_swap_info(page);
blk_qc_t qc;
struct gendisk *disk;
unsigned long pflags;
VM_BUG_ON_PAGE(!PageSwapCache(page) && !synchronous, page);
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageUptodate(page), page);
/*
* Count submission time as memory stall. When the device is congested,
* or the submitting cgroup IO-throttled, submission can be a
* significant part of overall IO time.
*/
psi_memstall_enter(&pflags);
if (frontswap_load(page) == 0) {
SetPageUptodate(page);
unlock_page(page);
goto out;
}
if (sis->flags & SWP_FS) {
struct file *swap_file = sis->swap_file;
struct address_space *mapping = swap_file->f_mapping;
ret = mapping->a_ops->readpage(swap_file, page);
if (!ret)
count_vm_event(PSWPIN);
goto out;
}
ret = bdev_read_page(sis->bdev, swap_page_sector(page), page);
if (!ret) {
count_vm_event(PSWPIN);
goto out;
}
ret = 0;
bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read);
if (bio == NULL) {
unlock_page(page);
ret = -ENOMEM;
goto out;
}
disk = bio->bi_disk;
/*
* Keep this task valid during swap readpage because the oom killer may
* attempt to access it in the page fault retry time check.
*/
bio_set_op_attrs(bio, REQ_OP_READ, 0);
if (synchronous) {
bio->bi_opf |= REQ_HIPRI;
get_task_struct(current);
bio->bi_private = current;
}
count_vm_event(PSWPIN);
bio_get(bio);
qc = submit_bio(bio);
while (synchronous) {
set_current_state(TASK_UNINTERRUPTIBLE);
if (!READ_ONCE(bio->bi_private))
break;
if (!blk_poll(disk->queue, qc, true))
io_schedule();
}
__set_current_state(TASK_RUNNING);
bio_put(bio);
out:
psi_memstall_leave(&pflags);
return ret;
}
int swap_set_page_dirty(struct page *page)
{
struct swap_info_struct *sis = page_swap_info(page);
if (sis->flags & SWP_FS) {
struct address_space *mapping = sis->swap_file->f_mapping;
VM_BUG_ON_PAGE(!PageSwapCache(page), page);
return mapping->a_ops->set_page_dirty(page);
} else {
return __set_page_dirty_no_writeback(page);
}
}