android_kernel_xiaomi_sm8350/block/blk-merge.c
Greg Kroah-Hartman 7ea7cc9f8b This is the 5.4.62 stable release
-----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAl9Qtz8ACgkQONu9yGCS
 aT7xMw/9H2aAnbYRKpq4NX95OcfujmE1S4zv99TGOus2SPO+C6JiAo4WE40OYfWj
 H4q2XKa2jAKAvxLwf5zfUKdWNTqTpz+9NiCeF7QUEbGZ+fj7d39s1Quo6KNhCfUX
 pyQX7oa9nsaIbwzCz5RB0AqRGVzTMwh4lGdhtxTQfl/LMYWtub9UOkUvWimxlO5i
 bWqiqIOZWOzIoPj9KHEOg4KsE6L5D69PjfT2M/qfuOd4TWUw5i1Dv2ckRG1A5r3H
 q8oGrNwgMcco1mpC7lG0IZteNfNZHZqVeOGVdF54HsY+tpLBE9G6HbvfDQknyOPy
 BP3zBcPovWz3S2wRwHyZHjJdQdIprWW+zwikVoqMbTXt8VkNh0qXDgrfScEn6Fah
 hi6oOYvKOCb9YlD6IH7zfvZJzwRdmhIV26dztk1vI51dyvWUh+lmeWuFeGWCYUy6
 PYc9O1RjpzZqNezdHz4ZoueX+4G63fXJ1pTwYhReS4Wj7AYTqUgwIV+ZYKcTmmuD
 bXiWzQXt+4sbR2Mhah5E9wdJlIOc46i+ui6VEUxqZBq8UH0t5C8xxTjO61EAtd4F
 vlfs57jI8/VwWMxUPI4Qni933h1B4zBUlhvTqK7W0QQgEUsO6mIQQB5bDy0A0HOT
 3lImaFt4f+HI7vEltqE1qds1IXK7c0HvFbGC1fRI1ZdS0VdUiY8=
 =F1JD
 -----END PGP SIGNATURE-----

Merge 5.4.62 into android11-5.4-lts

Changes in 5.4.62
	powerpc/64s: Don't init FSCR_DSCR in __init_FSCR()
	binfmt_flat: revert "binfmt_flat: don't offset the data start"
	gre6: Fix reception with IP6_TNL_F_RCV_DSCP_COPY
	net: Fix potential wrong skb->protocol in skb_vlan_untag()
	net: nexthop: don't allow empty NHA_GROUP
	net: qrtr: fix usage of idr in port assignment to socket
	net: sctp: Fix negotiation of the number of data streams.
	net/smc: Prevent kernel-infoleak in __smc_diag_dump()
	tipc: fix uninit skb->data in tipc_nl_compat_dumpit()
	net: ena: Make missed_tx stat incremental
	net/sched: act_ct: Fix skb double-free in tcf_ct_handle_fragments() error flow
	ipvlan: fix device features
	ALSA: hda/hdmi: Add quirk to force connectivity
	ALSA: pci: delete repeated words in comments
	ALSA: hda/realtek: Fix pin default on Intel NUC 8 Rugged
	ALSA: hda/hdmi: Use force connectivity quirk on another HP desktop
	ASoC: img: Fix a reference count leak in img_i2s_in_set_fmt
	ASoC: img-parallel-out: Fix a reference count leak
	ASoC: tegra: Fix reference count leaks.
	mfd: intel-lpss: Add Intel Emmitsburg PCH PCI IDs
	arm64: dts: qcom: msm8916: Pull down PDM GPIOs during sleep
	powerpc/xive: Ignore kmemleak false positives
	media: pci: ttpci: av7110: fix possible buffer overflow caused by bad DMA value in debiirq()
	blktrace: ensure our debugfs dir exists
	scsi: target: tcmu: Fix crash on ARM during cmd completion
	mfd: intel-lpss: Add Intel Tiger Lake PCH-H PCI IDs
	iommu/iova: Don't BUG on invalid PFNs
	drm/amdkfd: Fix reference count leaks.
	drm/radeon: fix multiple reference count leak
	drm/amdgpu: fix ref count leak in amdgpu_driver_open_kms
	drm/amd/display: fix ref count leak in amdgpu_drm_ioctl
	drm/amdgpu: fix ref count leak in amdgpu_display_crtc_set_config
	drm/amdgpu/display: fix ref count leak when pm_runtime_get_sync fails
	scsi: lpfc: Fix shost refcount mismatch when deleting vport
	xfs: Don't allow logging of XFS_ISTALE inodes
	scsi: target: Fix xcopy sess release leak
	selftests/powerpc: Purge extra count_pmc() calls of ebb selftests
	f2fs: fix error path in do_recover_data()
	omapfb: fix multiple reference count leaks due to pm_runtime_get_sync
	PCI: Fix pci_create_slot() reference count leak
	ARM: dts: ls1021a: output PPS signal on FIPER2
	rtlwifi: rtl8192cu: Prevent leaking urb
	mips/vdso: Fix resource leaks in genvdso.c
	ALSA: hda: Add support for Loongson 7A1000 controller
	cec-api: prevent leaking memory through hole in structure
	HID: quirks: add NOGET quirk for Logitech GROUP
	f2fs: fix use-after-free issue
	drm/nouveau/drm/noveau: fix reference count leak in nouveau_fbcon_open
	drm/nouveau: fix reference count leak in nv50_disp_atomic_commit
	drm/nouveau: Fix reference count leak in nouveau_connector_detect
	locking/lockdep: Fix overflow in presentation of average lock-time
	btrfs: file: reserve qgroup space after the hole punch range is locked
	btrfs: make btrfs_qgroup_check_reserved_leak take btrfs_inode
	scsi: iscsi: Do not put host in iscsi_set_flashnode_param()
	ceph: fix potential mdsc use-after-free crash
	ceph: do not access the kiocb after aio requests
	scsi: fcoe: Memory leak fix in fcoe_sysfs_fcf_del()
	EDAC/ie31200: Fallback if host bridge device is already initialized
	hugetlbfs: prevent filesystem stacking of hugetlbfs
	media: davinci: vpif_capture: fix potential double free
	KVM: arm64: Fix symbol dependency in __hyp_call_panic_nvhe
	powerpc/spufs: add CONFIG_COREDUMP dependency
	USB: sisusbvga: Fix a potential UB casued by left shifting a negative value
	brcmfmac: Set timeout value when configuring power save
	efi: provide empty efi_enter_virtual_mode implementation
	arm64: Fix __cpu_logical_map undefined issue
	Revert "ath10k: fix DMA related firmware crashes on multiple devices"
	sched/uclamp: Protect uclamp fast path code with static key
	sched/uclamp: Fix a deadlock when enabling uclamp static key
	usb: cdns3: gadget: always zeroed TRB buffer when enable endpoint
	PM / devfreq: rk3399_dmc: Add missing of_node_put()
	PM / devfreq: rk3399_dmc: Disable devfreq-event device when fails
	PM / devfreq: rk3399_dmc: Fix kernel oops when rockchip,pmu is absent
	drm/xen: fix passing zero to 'PTR_ERR' warning
	drm/xen-front: Fix misused IS_ERR_OR_NULL checks
	s390/numa: set node distance to LOCAL_DISTANCE
	btrfs: factor out inode items copy loop from btrfs_log_inode()
	btrfs: only commit the delayed inode when doing a full fsync
	btrfs: only commit delayed items at fsync if we are logging a directory
	mm/shuffle: don't move pages between zones and don't read garbage memmaps
	mm: fix kthread_use_mm() vs TLB invalidate
	mm/cma.c: switch to bitmap_zalloc() for cma bitmap allocation
	cma: don't quit at first error when activating reserved areas
	gpu/drm: ingenic: Use the plane's src_[x,y] to configure DMA length
	drm/ingenic: Fix incorrect assumption about plane->index
	drm/amd/display: Trigger modesets on MST DSC connectors
	drm/amd/display: Add additional config guards for DCN
	drm/amd/display: Fix dmesg warning from setting abm level
	mm/vunmap: add cond_resched() in vunmap_pmd_range
	EDAC: sb_edac: get rid of unused vars
	EDAC: skx_common: get rid of unused type var
	EDAC/{i7core,sb,pnd2,skx}: Fix error event severity
	PCI: qcom: Add missing ipq806x clocks in PCIe driver
	PCI: qcom: Change duplicate PCI reset to phy reset
	PCI: qcom: Add missing reset for ipq806x
	cpufreq: intel_pstate: Fix EPP setting via sysfs in active mode
	ALSA: usb-audio: Add capture support for Saffire 6 (USB 1.1)
	media: gpio-ir-tx: improve precision of transmitted signal due to scheduling
	block: respect queue limit of max discard segment
	block: virtio_blk: fix handling single range discard request
	drm/msm/adreno: fix updating ring fence
	block: Fix page_is_mergeable() for compound pages
	bfq: fix blkio cgroup leakage v4
	hwmon: (nct7904) Correct divide by 0
	blk-mq: insert request not through ->queue_rq into sw/scheduler queue
	blkcg: fix memleak for iolatency
	nvme-fc: Fix wrong return value in __nvme_fc_init_request()
	nvme: multipath: round-robin: fix single non-optimized path case
	null_blk: fix passing of REQ_FUA flag in null_handle_rq
	i2c: core: Don't fail PRP0001 enumeration when no ID table exist
	i2c: rcar: in slave mode, clear NACK earlier
	usb: gadget: f_tcm: Fix some resource leaks in some error paths
	spi: stm32: clear only asserted irq flags on interrupt
	jbd2: make sure jh have b_transaction set in refile/unfile_buffer
	ext4: don't BUG on inconsistent journal feature
	ext4: handle read only external journal device
	jbd2: abort journal if free a async write error metadata buffer
	ext4: handle option set by mount flags correctly
	ext4: handle error of ext4_setup_system_zone() on remount
	ext4: correctly restore system zone info when remount fails
	fs: prevent BUG_ON in submit_bh_wbc()
	spi: stm32h7: fix race condition at end of transfer
	spi: stm32: fix fifo threshold level in case of short transfer
	spi: stm32: fix stm32_spi_prepare_mbr in case of odd clk_rate
	spi: stm32: always perform registers configuration prior to transfer
	drm/amd/powerplay: correct Vega20 cached smu feature state
	drm/amd/powerplay: correct UVD/VCE PG state on custom pptable uploading
	drm/amd/display: Switch to immediate mode for updating infopackets
	netfilter: avoid ipv6 -> nf_defrag_ipv6 module dependency
	can: j1939: transport: j1939_xtp_rx_dat_one(): compare own packets to detect corruptions
	ALSA: hda/realtek: Add model alc298-samsung-headphone
	s390/cio: add cond_resched() in the slow_eval_known_fn() loop
	ASoC: wm8994: Avoid attempts to read unreadable registers
	selftests: disable rp_filter for icmp_redirect.sh
	scsi: fcoe: Fix I/O path allocation
	scsi: ufs: Fix possible infinite loop in ufshcd_hold
	scsi: ufs: Improve interrupt handling for shared interrupts
	scsi: ufs: Clean up completed request without interrupt notification
	scsi: qla2xxx: Fix login timeout
	scsi: qla2xxx: Check if FW supports MQ before enabling
	scsi: qla2xxx: Fix null pointer access during disconnect from subsystem
	Revert "scsi: qla2xxx: Fix crash on qla2x00_mailbox_command"
	macvlan: validate setting of multiple remote source MAC addresses
	net: gianfar: Add of_node_put() before goto statement
	powerpc/perf: Fix soft lockups due to missed interrupt accounting
	arm64: Move handling of erratum 1418040 into C code
	arm64: Allow booting of late CPUs affected by erratum 1418040
	block: fix get_max_io_size()
	block: loop: set discard granularity and alignment for block device backed loop
	HID: i2c-hid: Always sleep 60ms after I2C_HID_PWR_ON commands
	blk-mq: order adding requests to hctx->dispatch and checking SCHED_RESTART
	btrfs: reset compression level for lzo on remount
	btrfs: check the right error variable in btrfs_del_dir_entries_in_log
	btrfs: fix space cache memory leak after transaction abort
	btrfs: detect nocow for swap after snapshot delete
	fbcon: prevent user font height or width change from causing potential out-of-bounds access
	USB: lvtest: return proper error code in probe
	vt: defer kfree() of vc_screenbuf in vc_do_resize()
	vt_ioctl: change VT_RESIZEX ioctl to check for error return from vc_resize()
	serial: samsung: Removes the IRQ not found warning
	serial: pl011: Fix oops on -EPROBE_DEFER
	serial: pl011: Don't leak amba_ports entry on driver register error
	serial: stm32: avoid kernel warning on absence of optional IRQ
	serial: 8250_exar: Fix number of ports for Commtech PCIe cards
	serial: 8250: change lock order in serial8250_do_startup()
	writeback: Protect inode->i_io_list with inode->i_lock
	writeback: Avoid skipping inode writeback
	writeback: Fix sync livelock due to b_dirty_time processing
	XEN uses irqdesc::irq_data_common::handler_data to store a per interrupt XEN data pointer which contains XEN specific information.
	usb: host: xhci: fix ep context print mismatch in debugfs
	xhci: Do warm-reset when both CAS and XDEV_RESUME are set
	xhci: Always restore EP_SOFT_CLEAR_TOGGLE even if ep reset failed
	arm64: vdso32: make vdso32 install conditional
	PM: sleep: core: Fix the handling of pending runtime resume requests
	powerpc/perf: Fix crashes with generic_compat_pmu & BHRB
	device property: Fix the secondary firmware node handling in set_primary_fwnode()
	crypto: af_alg - Work around empty control messages without MSG_MORE
	genirq/matrix: Deal with the sillyness of for_each_cpu() on UP
	irqchip/stm32-exti: Avoid losing interrupts due to clearing pending bits by mistake
	x86/hotplug: Silence APIC only after all interrupts are migrated
	drm/amdgpu: Fix buffer overflow in INFO ioctl
	drm/amdgpu/gfx10: refine mgcg setting
	drm/amd/powerplay: Fix hardmins not being sent to SMU for RV
	drm/amd/pm: correct Vega10 swctf limit setting
	drm/amd/pm: correct Vega12 swctf limit setting
	drm/amd/pm: correct Vega20 swctf limit setting
	drm/amd/pm: correct the thermal alert temperature limit settings
	USB: yurex: Fix bad gfp argument
	usb: uas: Add quirk for PNY Pro Elite
	USB: quirks: Add no-lpm quirk for another Raydium touchscreen
	USB: quirks: Ignore duplicate endpoint on Sound Devices MixPre-D
	USB: Ignore UAS for JMicron JMS567 ATA/ATAPI Bridge
	usb: host: ohci-exynos: Fix error handling in exynos_ohci_probe()
	USB: gadget: u_f: add overflow checks to VLA macros
	USB: gadget: f_ncm: add bounds checks to ncm_unwrap_ntb()
	USB: gadget: u_f: Unbreak offset calculation in VLAs
	USB: cdc-acm: rework notification_buffer resizing
	usb: storage: Add unusual_uas entry for Sony PSZ drives
	drm/i915: Fix cmd parser desc matching with masks
	usb: dwc3: gadget: Don't setup more than requested
	usb: dwc3: gadget: Fix handling ZLP
	usb: dwc3: gadget: Handle ZLP for sg requests
	fbmem: pull fbcon_update_vcs() out of fb_set_var()
	kheaders: remove unneeded 'cat' command piped to 'head' / 'tail'
	kheaders: optimize md5sum calculation for in-tree builds
	kheaders: optimize header copy for in-tree builds
	kheaders: remove the last bashism to allow sh to run it
	kheaders: explain why include/config/autoconf.h is excluded from md5sum
	kbuild: add variables for compression tools
	kbuild: fix broken builds because of GZIP,BZIP2,LZOP variables
	HID: hiddev: Fix slab-out-of-bounds write in hiddev_ioctl_usage()
	ALSA: usb-audio: Update documentation comment for MS2109 quirk
	io_uring: Fix NULL pointer dereference in io_sq_wq_submit_work()
	Linux 5.4.62

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: I7cac9619b0d3edfee94fc6f31efa5d5b545cfeb5
2020-09-14 11:09:54 +02:00

919 lines
25 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* Functions related to segment and merge handling
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/scatterlist.h>
#include <trace/events/block.h>
#include "blk.h"
static inline bool bio_will_gap(struct request_queue *q,
struct request *prev_rq, struct bio *prev, struct bio *next)
{
struct bio_vec pb, nb;
if (!bio_has_data(prev) || !queue_virt_boundary(q))
return false;
/*
* Don't merge if the 1st bio starts with non-zero offset, otherwise it
* is quite difficult to respect the sg gap limit. We work hard to
* merge a huge number of small single bios in case of mkfs.
*/
if (prev_rq)
bio_get_first_bvec(prev_rq->bio, &pb);
else
bio_get_first_bvec(prev, &pb);
if (pb.bv_offset & queue_virt_boundary(q))
return true;
/*
* We don't need to worry about the situation that the merged segment
* ends in unaligned virt boundary:
*
* - if 'pb' ends aligned, the merged segment ends aligned
* - if 'pb' ends unaligned, the next bio must include
* one single bvec of 'nb', otherwise the 'nb' can't
* merge with 'pb'
*/
bio_get_last_bvec(prev, &pb);
bio_get_first_bvec(next, &nb);
if (biovec_phys_mergeable(q, &pb, &nb))
return false;
return __bvec_gap_to_prev(q, &pb, nb.bv_offset);
}
static inline bool req_gap_back_merge(struct request *req, struct bio *bio)
{
return bio_will_gap(req->q, req, req->biotail, bio);
}
static inline bool req_gap_front_merge(struct request *req, struct bio *bio)
{
return bio_will_gap(req->q, NULL, bio, req->bio);
}
static struct bio *blk_bio_discard_split(struct request_queue *q,
struct bio *bio,
struct bio_set *bs,
unsigned *nsegs)
{
unsigned int max_discard_sectors, granularity;
int alignment;
sector_t tmp;
unsigned split_sectors;
*nsegs = 1;
/* Zero-sector (unknown) and one-sector granularities are the same. */
granularity = max(q->limits.discard_granularity >> 9, 1U);
max_discard_sectors = min(q->limits.max_discard_sectors,
bio_allowed_max_sectors(q));
max_discard_sectors -= max_discard_sectors % granularity;
if (unlikely(!max_discard_sectors)) {
/* XXX: warn */
return NULL;
}
if (bio_sectors(bio) <= max_discard_sectors)
return NULL;
split_sectors = max_discard_sectors;
/*
* If the next starting sector would be misaligned, stop the discard at
* the previous aligned sector.
*/
alignment = (q->limits.discard_alignment >> 9) % granularity;
tmp = bio->bi_iter.bi_sector + split_sectors - alignment;
tmp = sector_div(tmp, granularity);
if (split_sectors > tmp)
split_sectors -= tmp;
return bio_split(bio, split_sectors, GFP_NOIO, bs);
}
static struct bio *blk_bio_write_zeroes_split(struct request_queue *q,
struct bio *bio, struct bio_set *bs, unsigned *nsegs)
{
*nsegs = 0;
if (!q->limits.max_write_zeroes_sectors)
return NULL;
if (bio_sectors(bio) <= q->limits.max_write_zeroes_sectors)
return NULL;
return bio_split(bio, q->limits.max_write_zeroes_sectors, GFP_NOIO, bs);
}
static struct bio *blk_bio_write_same_split(struct request_queue *q,
struct bio *bio,
struct bio_set *bs,
unsigned *nsegs)
{
*nsegs = 1;
if (!q->limits.max_write_same_sectors)
return NULL;
if (bio_sectors(bio) <= q->limits.max_write_same_sectors)
return NULL;
return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs);
}
/*
* Return the maximum number of sectors from the start of a bio that may be
* submitted as a single request to a block device. If enough sectors remain,
* align the end to the physical block size. Otherwise align the end to the
* logical block size. This approach minimizes the number of non-aligned
* requests that are submitted to a block device if the start of a bio is not
* aligned to a physical block boundary.
*/
static inline unsigned get_max_io_size(struct request_queue *q,
struct bio *bio)
{
unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector);
unsigned max_sectors = sectors;
unsigned pbs = queue_physical_block_size(q) >> SECTOR_SHIFT;
unsigned lbs = queue_logical_block_size(q) >> SECTOR_SHIFT;
unsigned start_offset = bio->bi_iter.bi_sector & (pbs - 1);
max_sectors += start_offset;
max_sectors &= ~(pbs - 1);
if (max_sectors > start_offset)
return max_sectors - start_offset;
return sectors & ~(lbs - 1);
}
static inline unsigned get_max_segment_size(const struct request_queue *q,
struct page *start_page,
unsigned long offset)
{
unsigned long mask = queue_segment_boundary(q);
offset = mask & (page_to_phys(start_page) + offset);
/*
* overflow may be triggered in case of zero page physical address
* on 32bit arch, use queue's max segment size when that happens.
*/
return min_not_zero(mask - offset + 1,
(unsigned long)queue_max_segment_size(q));
}
/**
* bvec_split_segs - verify whether or not a bvec should be split in the middle
* @q: [in] request queue associated with the bio associated with @bv
* @bv: [in] bvec to examine
* @nsegs: [in,out] Number of segments in the bio being built. Incremented
* by the number of segments from @bv that may be appended to that
* bio without exceeding @max_segs
* @sectors: [in,out] Number of sectors in the bio being built. Incremented
* by the number of sectors from @bv that may be appended to that
* bio without exceeding @max_sectors
* @max_segs: [in] upper bound for *@nsegs
* @max_sectors: [in] upper bound for *@sectors
*
* When splitting a bio, it can happen that a bvec is encountered that is too
* big to fit in a single segment and hence that it has to be split in the
* middle. This function verifies whether or not that should happen. The value
* %true is returned if and only if appending the entire @bv to a bio with
* *@nsegs segments and *@sectors sectors would make that bio unacceptable for
* the block driver.
*/
static bool bvec_split_segs(const struct request_queue *q,
const struct bio_vec *bv, unsigned *nsegs,
unsigned *sectors, unsigned max_segs,
unsigned max_sectors)
{
unsigned max_len = (min(max_sectors, UINT_MAX >> 9) - *sectors) << 9;
unsigned len = min(bv->bv_len, max_len);
unsigned total_len = 0;
unsigned seg_size = 0;
while (len && *nsegs < max_segs) {
seg_size = get_max_segment_size(q, bv->bv_page,
bv->bv_offset + total_len);
seg_size = min(seg_size, len);
(*nsegs)++;
total_len += seg_size;
len -= seg_size;
if ((bv->bv_offset + total_len) & queue_virt_boundary(q))
break;
}
*sectors += total_len >> 9;
/* tell the caller to split the bvec if it is too big to fit */
return len > 0 || bv->bv_len > max_len;
}
/**
* blk_bio_segment_split - split a bio in two bios
* @q: [in] request queue pointer
* @bio: [in] bio to be split
* @bs: [in] bio set to allocate the clone from
* @segs: [out] number of segments in the bio with the first half of the sectors
*
* Clone @bio, update the bi_iter of the clone to represent the first sectors
* of @bio and update @bio->bi_iter to represent the remaining sectors. The
* following is guaranteed for the cloned bio:
* - That it has at most get_max_io_size(@q, @bio) sectors.
* - That it has at most queue_max_segments(@q) segments.
*
* Except for discard requests the cloned bio will point at the bi_io_vec of
* the original bio. It is the responsibility of the caller to ensure that the
* original bio is not freed before the cloned bio. The caller is also
* responsible for ensuring that @bs is only destroyed after processing of the
* split bio has finished.
*/
static struct bio *blk_bio_segment_split(struct request_queue *q,
struct bio *bio,
struct bio_set *bs,
unsigned *segs)
{
struct bio_vec bv, bvprv, *bvprvp = NULL;
struct bvec_iter iter;
unsigned nsegs = 0, sectors = 0;
const unsigned max_sectors = get_max_io_size(q, bio);
const unsigned max_segs = queue_max_segments(q);
bio_for_each_bvec(bv, bio, iter) {
/*
* If the queue doesn't support SG gaps and adding this
* offset would create a gap, disallow it.
*/
if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset))
goto split;
if (nsegs < max_segs &&
sectors + (bv.bv_len >> 9) <= max_sectors &&
bv.bv_offset + bv.bv_len <= PAGE_SIZE) {
nsegs++;
sectors += bv.bv_len >> 9;
} else if (bvec_split_segs(q, &bv, &nsegs, &sectors, max_segs,
max_sectors)) {
goto split;
}
bvprv = bv;
bvprvp = &bvprv;
}
*segs = nsegs;
return NULL;
split:
*segs = nsegs;
return bio_split(bio, sectors, GFP_NOIO, bs);
}
/**
* __blk_queue_split - split a bio and submit the second half
* @q: [in] request queue pointer
* @bio: [in, out] bio to be split
* @nr_segs: [out] number of segments in the first bio
*
* Split a bio into two bios, chain the two bios, submit the second half and
* store a pointer to the first half in *@bio. If the second bio is still too
* big it will be split by a recursive call to this function. Since this
* function may allocate a new bio from @q->bio_split, it is the responsibility
* of the caller to ensure that @q is only released after processing of the
* split bio has finished.
*/
void __blk_queue_split(struct request_queue *q, struct bio **bio,
unsigned int *nr_segs)
{
struct bio *split;
switch (bio_op(*bio)) {
case REQ_OP_DISCARD:
case REQ_OP_SECURE_ERASE:
split = blk_bio_discard_split(q, *bio, &q->bio_split, nr_segs);
break;
case REQ_OP_WRITE_ZEROES:
split = blk_bio_write_zeroes_split(q, *bio, &q->bio_split,
nr_segs);
break;
case REQ_OP_WRITE_SAME:
split = blk_bio_write_same_split(q, *bio, &q->bio_split,
nr_segs);
break;
default:
split = blk_bio_segment_split(q, *bio, &q->bio_split, nr_segs);
break;
}
if (split) {
/* there isn't chance to merge the splitted bio */
split->bi_opf |= REQ_NOMERGE;
/*
* Since we're recursing into make_request here, ensure
* that we mark this bio as already having entered the queue.
* If not, and the queue is going away, we can get stuck
* forever on waiting for the queue reference to drop. But
* that will never happen, as we're already holding a
* reference to it.
*/
bio_set_flag(*bio, BIO_QUEUE_ENTERED);
bio_chain(split, *bio);
trace_block_split(q, split, (*bio)->bi_iter.bi_sector);
generic_make_request(*bio);
*bio = split;
}
}
/**
* blk_queue_split - split a bio and submit the second half
* @q: [in] request queue pointer
* @bio: [in, out] bio to be split
*
* Split a bio into two bios, chains the two bios, submit the second half and
* store a pointer to the first half in *@bio. Since this function may allocate
* a new bio from @q->bio_split, it is the responsibility of the caller to
* ensure that @q is only released after processing of the split bio has
* finished.
*/
void blk_queue_split(struct request_queue *q, struct bio **bio)
{
unsigned int nr_segs;
__blk_queue_split(q, bio, &nr_segs);
}
EXPORT_SYMBOL(blk_queue_split);
unsigned int blk_recalc_rq_segments(struct request *rq)
{
unsigned int nr_phys_segs = 0;
unsigned int nr_sectors = 0;
struct req_iterator iter;
struct bio_vec bv;
if (!rq->bio)
return 0;
switch (bio_op(rq->bio)) {
case REQ_OP_DISCARD:
case REQ_OP_SECURE_ERASE:
case REQ_OP_WRITE_ZEROES:
return 0;
case REQ_OP_WRITE_SAME:
return 1;
}
rq_for_each_bvec(bv, rq, iter)
bvec_split_segs(rq->q, &bv, &nr_phys_segs, &nr_sectors,
UINT_MAX, UINT_MAX);
return nr_phys_segs;
}
static inline struct scatterlist *blk_next_sg(struct scatterlist **sg,
struct scatterlist *sglist)
{
if (!*sg)
return sglist;
/*
* If the driver previously mapped a shorter list, we could see a
* termination bit prematurely unless it fully inits the sg table
* on each mapping. We KNOW that there must be more entries here
* or the driver would be buggy, so force clear the termination bit
* to avoid doing a full sg_init_table() in drivers for each command.
*/
sg_unmark_end(*sg);
return sg_next(*sg);
}
static unsigned blk_bvec_map_sg(struct request_queue *q,
struct bio_vec *bvec, struct scatterlist *sglist,
struct scatterlist **sg)
{
unsigned nbytes = bvec->bv_len;
unsigned nsegs = 0, total = 0;
while (nbytes > 0) {
unsigned offset = bvec->bv_offset + total;
unsigned len = min(get_max_segment_size(q, bvec->bv_page,
offset), nbytes);
struct page *page = bvec->bv_page;
/*
* Unfortunately a fair number of drivers barf on scatterlists
* that have an offset larger than PAGE_SIZE, despite other
* subsystems dealing with that invariant just fine. For now
* stick to the legacy format where we never present those from
* the block layer, but the code below should be removed once
* these offenders (mostly MMC/SD drivers) are fixed.
*/
page += (offset >> PAGE_SHIFT);
offset &= ~PAGE_MASK;
*sg = blk_next_sg(sg, sglist);
sg_set_page(*sg, page, len, offset);
total += len;
nbytes -= len;
nsegs++;
}
return nsegs;
}
static inline int __blk_bvec_map_sg(struct bio_vec bv,
struct scatterlist *sglist, struct scatterlist **sg)
{
*sg = blk_next_sg(sg, sglist);
sg_set_page(*sg, bv.bv_page, bv.bv_len, bv.bv_offset);
return 1;
}
/* only try to merge bvecs into one sg if they are from two bios */
static inline bool
__blk_segment_map_sg_merge(struct request_queue *q, struct bio_vec *bvec,
struct bio_vec *bvprv, struct scatterlist **sg)
{
int nbytes = bvec->bv_len;
if (!*sg)
return false;
if ((*sg)->length + nbytes > queue_max_segment_size(q))
return false;
if (!biovec_phys_mergeable(q, bvprv, bvec))
return false;
(*sg)->length += nbytes;
return true;
}
static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
struct scatterlist *sglist,
struct scatterlist **sg)
{
struct bio_vec uninitialized_var(bvec), bvprv = { NULL };
struct bvec_iter iter;
int nsegs = 0;
bool new_bio = false;
for_each_bio(bio) {
bio_for_each_bvec(bvec, bio, iter) {
/*
* Only try to merge bvecs from two bios given we
* have done bio internal merge when adding pages
* to bio
*/
if (new_bio &&
__blk_segment_map_sg_merge(q, &bvec, &bvprv, sg))
goto next_bvec;
if (bvec.bv_offset + bvec.bv_len <= PAGE_SIZE)
nsegs += __blk_bvec_map_sg(bvec, sglist, sg);
else
nsegs += blk_bvec_map_sg(q, &bvec, sglist, sg);
next_bvec:
new_bio = false;
}
if (likely(bio->bi_iter.bi_size)) {
bvprv = bvec;
new_bio = true;
}
}
return nsegs;
}
/*
* map a request to scatterlist, return number of sg entries setup. Caller
* must make sure sg can hold rq->nr_phys_segments entries
*/
int blk_rq_map_sg(struct request_queue *q, struct request *rq,
struct scatterlist *sglist)
{
struct scatterlist *sg = NULL;
int nsegs = 0;
if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
nsegs = __blk_bvec_map_sg(rq->special_vec, sglist, &sg);
else if (rq->bio && bio_op(rq->bio) == REQ_OP_WRITE_SAME)
nsegs = __blk_bvec_map_sg(bio_iovec(rq->bio), sglist, &sg);
else if (rq->bio)
nsegs = __blk_bios_map_sg(q, rq->bio, sglist, &sg);
if (unlikely(rq->rq_flags & RQF_COPY_USER) &&
(blk_rq_bytes(rq) & q->dma_pad_mask)) {
unsigned int pad_len =
(q->dma_pad_mask & ~blk_rq_bytes(rq)) + 1;
sg->length += pad_len;
rq->extra_len += pad_len;
}
if (q->dma_drain_size && q->dma_drain_needed(rq)) {
if (op_is_write(req_op(rq)))
memset(q->dma_drain_buffer, 0, q->dma_drain_size);
sg_unmark_end(sg);
sg = sg_next(sg);
sg_set_page(sg, virt_to_page(q->dma_drain_buffer),
q->dma_drain_size,
((unsigned long)q->dma_drain_buffer) &
(PAGE_SIZE - 1));
nsegs++;
rq->extra_len += q->dma_drain_size;
}
if (sg)
sg_mark_end(sg);
/*
* Something must have been wrong if the figured number of
* segment is bigger than number of req's physical segments
*/
WARN_ON(nsegs > blk_rq_nr_phys_segments(rq));
return nsegs;
}
EXPORT_SYMBOL(blk_rq_map_sg);
static inline unsigned int blk_rq_get_max_segments(struct request *rq)
{
if (req_op(rq) == REQ_OP_DISCARD)
return queue_max_discard_segments(rq->q);
return queue_max_segments(rq->q);
}
static inline int ll_new_hw_segment(struct request *req, struct bio *bio,
unsigned int nr_phys_segs)
{
if (req->nr_phys_segments + nr_phys_segs > blk_rq_get_max_segments(req))
goto no_merge;
if (blk_integrity_merge_bio(req->q, req, bio) == false)
goto no_merge;
/*
* This will form the start of a new hw segment. Bump both
* counters.
*/
req->nr_phys_segments += nr_phys_segs;
return 1;
no_merge:
req_set_nomerge(req->q, req);
return 0;
}
int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs)
{
if (req_gap_back_merge(req, bio))
return 0;
if (blk_integrity_rq(req) &&
integrity_req_gap_back_merge(req, bio))
return 0;
if (blk_rq_sectors(req) + bio_sectors(bio) >
blk_rq_get_max_sectors(req, blk_rq_pos(req))) {
req_set_nomerge(req->q, req);
return 0;
}
if (!bio_crypt_ctx_mergeable(req->bio, blk_rq_bytes(req), bio))
return 0;
return ll_new_hw_segment(req, bio, nr_segs);
}
int ll_front_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs)
{
if (req_gap_front_merge(req, bio))
return 0;
if (blk_integrity_rq(req) &&
integrity_req_gap_front_merge(req, bio))
return 0;
if (blk_rq_sectors(req) + bio_sectors(bio) >
blk_rq_get_max_sectors(req, bio->bi_iter.bi_sector)) {
req_set_nomerge(req->q, req);
return 0;
}
if (!bio_crypt_ctx_mergeable(bio, bio->bi_iter.bi_size, req->bio))
return 0;
return ll_new_hw_segment(req, bio, nr_segs);
}
static bool req_attempt_discard_merge(struct request_queue *q, struct request *req,
struct request *next)
{
unsigned short segments = blk_rq_nr_discard_segments(req);
if (segments >= queue_max_discard_segments(q))
goto no_merge;
if (blk_rq_sectors(req) + bio_sectors(next->bio) >
blk_rq_get_max_sectors(req, blk_rq_pos(req)))
goto no_merge;
req->nr_phys_segments = segments + blk_rq_nr_discard_segments(next);
return true;
no_merge:
req_set_nomerge(q, req);
return false;
}
static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
struct request *next)
{
int total_phys_segments;
if (req_gap_back_merge(req, next->bio))
return 0;
/*
* Will it become too large?
*/
if ((blk_rq_sectors(req) + blk_rq_sectors(next)) >
blk_rq_get_max_sectors(req, blk_rq_pos(req)))
return 0;
total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
if (total_phys_segments > blk_rq_get_max_segments(req))
return 0;
if (blk_integrity_merge_rq(q, req, next) == false)
return 0;
if (!bio_crypt_ctx_mergeable(req->bio, blk_rq_bytes(req), next->bio))
return 0;
/* Merge is OK... */
req->nr_phys_segments = total_phys_segments;
return 1;
}
/**
* blk_rq_set_mixed_merge - mark a request as mixed merge
* @rq: request to mark as mixed merge
*
* Description:
* @rq is about to be mixed merged. Make sure the attributes
* which can be mixed are set in each bio and mark @rq as mixed
* merged.
*/
void blk_rq_set_mixed_merge(struct request *rq)
{
unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
struct bio *bio;
if (rq->rq_flags & RQF_MIXED_MERGE)
return;
/*
* @rq will no longer represent mixable attributes for all the
* contained bios. It will just track those of the first one.
* Distributes the attributs to each bio.
*/
for (bio = rq->bio; bio; bio = bio->bi_next) {
WARN_ON_ONCE((bio->bi_opf & REQ_FAILFAST_MASK) &&
(bio->bi_opf & REQ_FAILFAST_MASK) != ff);
bio->bi_opf |= ff;
}
rq->rq_flags |= RQF_MIXED_MERGE;
}
static void blk_account_io_merge(struct request *req)
{
if (blk_do_io_stat(req)) {
struct hd_struct *part;
part_stat_lock();
part = req->part;
part_dec_in_flight(req->q, part, rq_data_dir(req));
hd_struct_put(part);
part_stat_unlock();
}
}
/*
* Two cases of handling DISCARD merge:
* If max_discard_segments > 1, the driver takes every bio
* as a range and send them to controller together. The ranges
* needn't to be contiguous.
* Otherwise, the bios/requests will be handled as same as
* others which should be contiguous.
*/
static inline bool blk_discard_mergable(struct request *req)
{
if (req_op(req) == REQ_OP_DISCARD &&
queue_max_discard_segments(req->q) > 1)
return true;
return false;
}
static enum elv_merge blk_try_req_merge(struct request *req,
struct request *next)
{
if (blk_discard_mergable(req))
return ELEVATOR_DISCARD_MERGE;
else if (blk_rq_pos(req) + blk_rq_sectors(req) == blk_rq_pos(next))
return ELEVATOR_BACK_MERGE;
return ELEVATOR_NO_MERGE;
}
/*
* For non-mq, this has to be called with the request spinlock acquired.
* For mq with scheduling, the appropriate queue wide lock should be held.
*/
static struct request *attempt_merge(struct request_queue *q,
struct request *req, struct request *next)
{
if (!rq_mergeable(req) || !rq_mergeable(next))
return NULL;
if (req_op(req) != req_op(next))
return NULL;
if (rq_data_dir(req) != rq_data_dir(next)
|| req->rq_disk != next->rq_disk)
return NULL;
if (req_op(req) == REQ_OP_WRITE_SAME &&
!blk_write_same_mergeable(req->bio, next->bio))
return NULL;
/*
* Don't allow merge of different write hints, or for a hint with
* non-hint IO.
*/
if (req->write_hint != next->write_hint)
return NULL;
if (req->ioprio != next->ioprio)
return NULL;
/*
* If we are allowed to merge, then append bio list
* from next to rq and release next. merge_requests_fn
* will have updated segment counts, update sector
* counts here. Handle DISCARDs separately, as they
* have separate settings.
*/
switch (blk_try_req_merge(req, next)) {
case ELEVATOR_DISCARD_MERGE:
if (!req_attempt_discard_merge(q, req, next))
return NULL;
break;
case ELEVATOR_BACK_MERGE:
if (!ll_merge_requests_fn(q, req, next))
return NULL;
break;
default:
return NULL;
}
/*
* If failfast settings disagree or any of the two is already
* a mixed merge, mark both as mixed before proceeding. This
* makes sure that all involved bios have mixable attributes
* set properly.
*/
if (((req->rq_flags | next->rq_flags) & RQF_MIXED_MERGE) ||
(req->cmd_flags & REQ_FAILFAST_MASK) !=
(next->cmd_flags & REQ_FAILFAST_MASK)) {
blk_rq_set_mixed_merge(req);
blk_rq_set_mixed_merge(next);
}
/*
* At this point we have either done a back merge or front merge. We
* need the smaller start_time_ns of the merged requests to be the
* current request for accounting purposes.
*/
if (next->start_time_ns < req->start_time_ns)
req->start_time_ns = next->start_time_ns;
req->biotail->bi_next = next->bio;
req->biotail = next->biotail;
req->__data_len += blk_rq_bytes(next);
if (!blk_discard_mergable(req))
elv_merge_requests(q, req, next);
/*
* 'next' is going away, so update stats accordingly
*/
blk_account_io_merge(next);
/*
* ownership of bio passed from next to req, return 'next' for
* the caller to free
*/
next->bio = NULL;
return next;
}
struct request *attempt_back_merge(struct request_queue *q, struct request *rq)
{
struct request *next = elv_latter_request(q, rq);
if (next)
return attempt_merge(q, rq, next);
return NULL;
}
struct request *attempt_front_merge(struct request_queue *q, struct request *rq)
{
struct request *prev = elv_former_request(q, rq);
if (prev)
return attempt_merge(q, prev, rq);
return NULL;
}
int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
struct request *next)
{
struct request *free;
free = attempt_merge(q, rq, next);
if (free) {
blk_put_request(free);
return 1;
}
return 0;
}
bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
{
if (!rq_mergeable(rq) || !bio_mergeable(bio))
return false;
if (req_op(rq) != bio_op(bio))
return false;
/* different data direction or already started, don't merge */
if (bio_data_dir(bio) != rq_data_dir(rq))
return false;
/* must be same device */
if (rq->rq_disk != bio->bi_disk)
return false;
/* only merge integrity protected bio into ditto rq */
if (blk_integrity_merge_bio(rq->q, rq, bio) == false)
return false;
/* must be using the same buffer */
if (req_op(rq) == REQ_OP_WRITE_SAME &&
!blk_write_same_mergeable(rq->bio, bio))
return false;
/*
* Don't allow merge of different write hints, or for a hint with
* non-hint IO.
*/
if (rq->write_hint != bio->bi_write_hint)
return false;
if (rq->ioprio != bio_prio(bio))
return false;
/* Only merge if the crypt contexts are compatible */
if (!bio_crypt_ctx_compatible(bio, rq->bio))
return false;
return true;
}
enum elv_merge blk_try_merge(struct request *rq, struct bio *bio)
{
if (blk_discard_mergable(rq))
return ELEVATOR_DISCARD_MERGE;
else if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector)
return ELEVATOR_BACK_MERGE;
else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_iter.bi_sector)
return ELEVATOR_FRONT_MERGE;
return ELEVATOR_NO_MERGE;
}