December 2024 - Linux-stable-mirror

[PATCH v2 1/2] HID: hid-plantronics: Add mic mute mapping and generalize quirks

by Wade Wang

From: Terry Junge <linuxhid(a)cosmicgizmosystems.com> Add mapping for headset mute key events. Remove PLT_QUIRK_DOUBLE_VOLUME_KEYS quirk and made it generic. The quirk logic did not keep track of the actual previous key so any key event occurring in less than or equal to 5ms was ignored. Remove PLT_QUIRK_FOLLOWED_OPPOSITE_VOLUME_KEYS quirk. It had the same logic issue as the double key quirk and was actually masking the as designed behavior of most of the headsets. It's occurrence should be minimized with the ALSA control naming quirk that is part of the patch set. Signed-off-by: Terry Junge <linuxhid(a)cosmicgizmosystems.com> Signed-off-by: Wade Wang <wade.wang(a)hp.com> Cc: stable(a)vger.kernel.org --- V1 -> V2: Optimize out 2 macros - no functional changes drivers/hid/hid-plantronics.c | 144 ++++++++++++++++------------------ 1 file changed, 67 insertions(+), 77 deletions(-) diff --git a/drivers/hid/hid-plantronics.c b/drivers/hid/hid-plantronics.c index 25cfd964dc25..acb9eb18f7cc 100644 --- a/drivers/hid/hid-plantronics.c +++ b/drivers/hid/hid-plantronics.c @@ -6,9 +6,6 @@ * Copyright (c) 2015-2018 Terry Junge <terry.junge(a)plantronics.com> */ -/* - */ - #include "hid-ids.h" #include <linux/hid.h> @@ -23,30 +20,28 @@ #define PLT_VOL_UP 0x00b1 #define PLT_VOL_DOWN 0x00b2 +#define PLT_MIC_MUTE 0x00b5 #define PLT1_VOL_UP (PLT_HID_1_0_PAGE | PLT_VOL_UP) #define PLT1_VOL_DOWN (PLT_HID_1_0_PAGE | PLT_VOL_DOWN) +#define PLT1_MIC_MUTE (PLT_HID_1_0_PAGE | PLT_MIC_MUTE) #define PLT2_VOL_UP (PLT_HID_2_0_PAGE | PLT_VOL_UP) #define PLT2_VOL_DOWN (PLT_HID_2_0_PAGE | PLT_VOL_DOWN) +#define PLT2_MIC_MUTE (PLT_HID_2_0_PAGE | PLT_MIC_MUTE) +#define HID_TELEPHONY_MUTE (HID_UP_TELEPHONY | 0x2f) +#define HID_CONSUMER_MUTE (HID_UP_CONSUMER | 0xe2) #define PLT_DA60 0xda60 #define PLT_BT300_MIN 0x0413 #define PLT_BT300_MAX 0x0418 - -#define PLT_ALLOW_CONSUMER (field->application == HID_CP_CONSUMERCONTROL && \ - (usage->hid & HID_USAGE_PAGE) == HID_UP_CONSUMER) - -#define PLT_QUIRK_DOUBLE_VOLUME_KEYS BIT(0) -#define PLT_QUIRK_FOLLOWED_OPPOSITE_VOLUME_KEYS BIT(1) - #define PLT_DOUBLE_KEY_TIMEOUT 5 /* ms */ -#define PLT_FOLLOWED_OPPOSITE_KEY_TIMEOUT 220 /* ms */ struct plt_drv_data { unsigned long device_type; - unsigned long last_volume_key_ts; - u32 quirks; + unsigned long last_key_ts; + unsigned long double_key_to; + __u16 last_key; }; static int plantronics_input_mapping(struct hid_device *hdev, @@ -58,34 +53,43 @@ static int plantronics_input_mapping(struct hid_device *hdev, unsigned short mapped_key; struct plt_drv_data *drv_data = hid_get_drvdata(hdev); unsigned long plt_type = drv_data->device_type; + int allow_mute = usage->hid == HID_TELEPHONY_MUTE; + int allow_consumer = field->application == HID_CP_CONSUMERCONTROL && + (usage->hid & HID_USAGE_PAGE) == HID_UP_CONSUMER && + usage->hid != HID_CONSUMER_MUTE; /* special case for PTT products */ if (field->application == HID_GD_JOYSTICK) goto defaulted; - /* handle volume up/down mapping */ /* non-standard types or multi-HID interfaces - plt_type is PID */ if (!(plt_type & HID_USAGE_PAGE)) { switch (plt_type) { case PLT_DA60: - if (PLT_ALLOW_CONSUMER) + if (allow_consumer) goto defaulted; - goto ignored; + if (usage->hid == HID_CONSUMER_MUTE) { + mapped_key = KEY_MICMUTE; + goto mapped; + } + break; default: - if (PLT_ALLOW_CONSUMER) + if (allow_consumer || allow_mute) goto defaulted; } + goto ignored; } - /* handle standard types - plt_type is 0xffa0uuuu or 0xffa2uuuu */ - /* 'basic telephony compliant' - allow default consumer page map */ - else if ((plt_type & HID_USAGE) >= PLT_BASIC_TELEPHONY && - (plt_type & HID_USAGE) != PLT_BASIC_EXCEPTION) { - if (PLT_ALLOW_CONSUMER) - goto defaulted; - } - /* not 'basic telephony' - apply legacy mapping */ - /* only map if the field is in the device's primary vendor page */ - else if (!((field->application ^ plt_type) & HID_USAGE_PAGE)) { + + /* handle standard consumer control mapping */ + /* and standard telephony mic mute mapping */ + if (allow_consumer || allow_mute) + goto defaulted; + + /* handle vendor unique types - plt_type is 0xffa0uuuu or 0xffa2uuuu */ + /* if not 'basic telephony compliant' - map vendor unique controls */ + if (!((plt_type & HID_USAGE) >= PLT_BASIC_TELEPHONY && + (plt_type & HID_USAGE) != PLT_BASIC_EXCEPTION) && + !((field->application ^ plt_type) & HID_USAGE_PAGE)) switch (usage->hid) { case PLT1_VOL_UP: case PLT2_VOL_UP: @@ -95,8 +99,11 @@ static int plantronics_input_mapping(struct hid_device *hdev, case PLT2_VOL_DOWN: mapped_key = KEY_VOLUMEDOWN; goto mapped; + case PLT1_MIC_MUTE: + case PLT2_MIC_MUTE: + mapped_key = KEY_MICMUTE; + goto mapped; } - } /* * Future mapping of call control or other usages, @@ -105,6 +112,8 @@ static int plantronics_input_mapping(struct hid_device *hdev, */ ignored: + hid_dbg(hdev, "usage: %08x (appl: %08x) - ignored\n", + usage->hid, field->application); return -1; defaulted: @@ -123,38 +132,26 @@ static int plantronics_event(struct hid_device *hdev, struct hid_field *field, struct hid_usage *usage, __s32 value) { struct plt_drv_data *drv_data = hid_get_drvdata(hdev); + unsigned long prev_tsto, cur_ts; + __u16 prev_key, cur_key; - if (drv_data->quirks & PLT_QUIRK_DOUBLE_VOLUME_KEYS) { - unsigned long prev_ts, cur_ts; + /* Usages are filtered in plantronics_usages. */ - /* Usages are filtered in plantronics_usages. */ + /* HZ too low for ms resolution - double key detection disabled */ + /* or it is a key release - handle key presses only. */ + if (!drv_data->double_key_to || !value) + return 0; - if (!value) /* Handle key presses only. */ - return 0; + prev_tsto = drv_data->last_key_ts + drv_data->double_key_to; + cur_ts = drv_data->last_key_ts = jiffies; + prev_key = drv_data->last_key; + cur_key = drv_data->last_key = usage->code; - prev_ts = drv_data->last_volume_key_ts; - cur_ts = jiffies; - if (jiffies_to_msecs(cur_ts - prev_ts) <= PLT_DOUBLE_KEY_TIMEOUT) - return 1; /* Ignore the repeated key. */ - - drv_data->last_volume_key_ts = cur_ts; + /* If the same key occurs in <= double_key_to -- ignore it */ + if (prev_key == cur_key && time_before_eq(cur_ts, prev_tsto)) { + hid_dbg(hdev, "double key %d ignored\n", cur_key); + return 1; /* Ignore the repeated key. */ } - if (drv_data->quirks & PLT_QUIRK_FOLLOWED_OPPOSITE_VOLUME_KEYS) { - unsigned long prev_ts, cur_ts; - - /* Usages are filtered in plantronics_usages. */ - - if (!value) /* Handle key presses only. */ - return 0; - - prev_ts = drv_data->last_volume_key_ts; - cur_ts = jiffies; - if (jiffies_to_msecs(cur_ts - prev_ts) <= PLT_FOLLOWED_OPPOSITE_KEY_TIMEOUT) - return 1; /* Ignore the followed opposite volume key. */ - - drv_data->last_volume_key_ts = cur_ts; - } - return 0; } @@ -196,12 +193,16 @@ static int plantronics_probe(struct hid_device *hdev, ret = hid_parse(hdev); if (ret) { hid_err(hdev, "parse failed\n"); - goto err; + return ret; } drv_data->device_type = plantronics_device_type(hdev); - drv_data->quirks = id->driver_data; - drv_data->last_volume_key_ts = jiffies - msecs_to_jiffies(PLT_DOUBLE_KEY_TIMEOUT); + drv_data->double_key_to = msecs_to_jiffies(PLT_DOUBLE_KEY_TIMEOUT); + drv_data->last_key_ts = jiffies - drv_data->double_key_to; + + /* if HZ does not allow ms resolution - disable double key detection */ + if (drv_data->double_key_to < PLT_DOUBLE_KEY_TIMEOUT) + drv_data->double_key_to = 0; hid_set_drvdata(hdev, drv_data); @@ -210,29 +211,10 @@ static int plantronics_probe(struct hid_device *hdev, if (ret) hid_err(hdev, "hw start failed\n"); -err: return ret; } static const struct hid_device_id plantronics_devices[] = { - { HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, - USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3210_SERIES), - .driver_data = PLT_QUIRK_DOUBLE_VOLUME_KEYS }, - { HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, - USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3220_SERIES), - .driver_data = PLT_QUIRK_DOUBLE_VOLUME_KEYS }, - { HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, - USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3215_SERIES), - .driver_data = PLT_QUIRK_DOUBLE_VOLUME_KEYS }, - { HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, - USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3225_SERIES), - .driver_data = PLT_QUIRK_DOUBLE_VOLUME_KEYS }, - { HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, - USB_DEVICE_ID_PLANTRONICS_BLACKWIRE_3325_SERIES), - .driver_data = PLT_QUIRK_FOLLOWED_OPPOSITE_VOLUME_KEYS }, - { HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, - USB_DEVICE_ID_PLANTRONICS_ENCOREPRO_500_SERIES), - .driver_data = PLT_QUIRK_FOLLOWED_OPPOSITE_VOLUME_KEYS }, { HID_USB_DEVICE(USB_VENDOR_ID_PLANTRONICS, HID_ANY_ID) }, { } }; @@ -241,6 +223,14 @@ MODULE_DEVICE_TABLE(hid, plantronics_devices); static const struct hid_usage_id plantronics_usages[] = { { HID_CP_VOLUMEUP, EV_KEY, HID_ANY_ID }, { HID_CP_VOLUMEDOWN, EV_KEY, HID_ANY_ID }, + { HID_TELEPHONY_MUTE, EV_KEY, HID_ANY_ID }, + { HID_CONSUMER_MUTE, EV_KEY, HID_ANY_ID }, + { PLT2_VOL_UP, EV_KEY, HID_ANY_ID }, + { PLT2_VOL_DOWN, EV_KEY, HID_ANY_ID }, + { PLT2_MIC_MUTE, EV_KEY, HID_ANY_ID }, + { PLT1_VOL_UP, EV_KEY, HID_ANY_ID }, + { PLT1_VOL_DOWN, EV_KEY, HID_ANY_ID }, + { PLT1_MIC_MUTE, EV_KEY, HID_ANY_ID }, { HID_TERMINATOR, HID_TERMINATOR, HID_TERMINATOR } }; -- 2.43.0

7 months, 3 weeks

3
5
0 0

[PATCH 1/7] mm/hugetlb: Fix avoid_reserve to allow taking folio from subpool

by Peter Xu

Since commit 04f2cbe35699 ("hugetlb: guarantee that COW faults for a process that called mmap(MAP_PRIVATE) on hugetlbfs will succeed"), avoid_reserve was introduced for a special case of CoW on hugetlb private mappings, and only if the owner VMA is trying to allocate yet another hugetlb folio that is not reserved within the private vma reserved map. Later on, in commit d85f69b0b533 ("mm/hugetlb: alloc_huge_page handle areas hole punched by fallocate"), alloc_huge_page() enforced to not consume any global reservation as long as avoid_reserve=true. This operation doesn't look correct, because even if it will enforce the allocation to not use global reservation at all, it will still try to take one reservation from the spool (if the subpool existed). Then since the spool reserved pages take from global reservation, it'll also take one reservation globally. Logically it can cause global reservation to go wrong. I wrote a reproducer below, trigger this special path, and every run of such program will cause global reservation count to increment by one, until it hits the number of free pages: #define _GNU_SOURCE /* See feature_test_macros(7) */ #include <stdio.h> #include <fcntl.h> #include <errno.h> #include <unistd.h> #include <stdlib.h> #include <sys/mman.h> #define MSIZE (2UL << 20) int main(int argc, char *argv[]) { const char *path; int *buf; int fd, ret; pid_t child; if (argc < 2) { printf("usage: %s <hugetlb_file>\n", argv[0]); return -1; } path = argv[1]; fd = open(path, O_RDWR | O_CREAT, 0666); if (fd < 0) { perror("open failed"); return -1; } ret = fallocate(fd, 0, 0, MSIZE); if (ret != 0) { perror("fallocate"); return -1; } buf = mmap(NULL, MSIZE, PROT_READ|PROT_WRITE, MAP_PRIVATE, fd, 0); if (buf == MAP_FAILED) { perror("mmap() failed"); return -1; } /* Allocate a page */ *buf = 1; child = fork(); if (child == 0) { /* child doesn't need to do anything */ exit(0); } /* Trigger CoW from owner */ *buf = 2; munmap(buf, MSIZE); close(fd); unlink(path); return 0; } It can only reproduce with a sub-mount when there're reserved pages on the spool, like: # sysctl vm.nr_hugepages=128 # mkdir ./hugetlb-pool # mount -t hugetlbfs -o min_size=8M,pagesize=2M none ./hugetlb-pool Then run the reproducer on the mountpoint: # ./reproducer ./hugetlb-pool/test Fix it by taking the reservation from spool if available. In general, avoid_reserve is IMHO more about "avoid vma resv map", not spool's. I copied stable, however I have no intention for backporting if it's not a clean cherry-pick, because private hugetlb mapping, and then fork() on top is too rare to hit. Cc: linux-stable <stable(a)vger.kernel.org> Fixes: d85f69b0b533 ("mm/hugetlb: alloc_huge_page handle areas hole punched by fallocate") Signed-off-by: Peter Xu <peterx(a)redhat.com> --- mm/hugetlb.c | 22 +++------------------- 1 file changed, 3 insertions(+), 19 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index cec4b121193f..9ce69fd22a01 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1394,8 +1394,7 @@ static unsigned long available_huge_pages(struct hstate *h) static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, - unsigned long address, int avoid_reserve, - long chg) + unsigned long address, long chg) { struct folio *folio = NULL; struct mempolicy *mpol; @@ -1411,10 +1410,6 @@ static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h, if (!vma_has_reserves(vma, chg) && !available_huge_pages(h)) goto err; - /* If reserves cannot be used, ensure enough pages are in the pool */ - if (avoid_reserve && !available_huge_pages(h)) - goto err; - gfp_mask = htlb_alloc_mask(h); nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask); @@ -1430,7 +1425,7 @@ static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h, folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, nid, nodemask); - if (folio && !avoid_reserve && vma_has_reserves(vma, chg)) { + if (folio && vma_has_reserves(vma, chg)) { folio_set_hugetlb_restore_reserve(folio); h->resv_huge_pages--; } @@ -3007,17 +3002,6 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, gbl_chg = hugepage_subpool_get_pages(spool, 1); if (gbl_chg < 0) goto out_end_reservation; - - /* - * Even though there was no reservation in the region/reserve - * map, there could be reservations associated with the - * subpool that can be used. This would be indicated if the - * return value of hugepage_subpool_get_pages() is zero. - * However, if avoid_reserve is specified we still avoid even - * the subpool reservations. - */ - if (avoid_reserve) - gbl_chg = 1; } /* If this allocation is not consuming a reservation, charge it now. @@ -3040,7 +3024,7 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, * from the global free pool (global change). gbl_chg == 0 indicates * a reservation exists for the allocation. */ - folio = dequeue_hugetlb_folio_vma(h, vma, addr, avoid_reserve, gbl_chg); + folio = dequeue_hugetlb_folio_vma(h, vma, addr, gbl_chg); if (!folio) { spin_unlock_irq(&hugetlb_lock); folio = alloc_buddy_hugetlb_folio_with_mpol(h, vma, addr); -- 2.47.0

7 months, 3 weeks

2
3
0 0

[PATCH 1/2] dm-verity FEC: Fix RS FEC repair for roots unaligned to block size (take 2)

by Milan Broz

This patch fixes an issue that was fixed in the commit df7b59ba9245 ("dm verity: fix FEC for RS roots unaligned to block size") but later broken again in the commit 8ca7cab82bda ("dm verity fec: fix misaligned RS roots IO") If the Reed-Solomon roots setting spans multiple blocks, the code does not use proper parity bytes and randomly fails to repair even trivial errors. This bug cannot happen if the sector size is multiple of RS roots setting (Android case with roots 2). The previous solution was to find a dm-bufio block size that is multiple of the device sector size and roots size. Unfortunately, the optimization in commit 8ca7cab82bda ("dm verity fec: fix misaligned RS roots IO") is incorrect and uses data block size for some roots (for example, it uses 4096 block size for roots = 20). This patch uses a different approach: - It always uses a configured data block size for dm-bufio to avoid possible misaligned IOs. - and it caches the processed parity bytes, so it can join it if it spans two blocks. As the RS calculation is called only if an error is detected and the process is computationally intensive, copying a few more bytes should not introduce performance issues. The issue was reported to cryptsetup with trivial reproducer https://gitlab.com/cryptsetup/cryptsetup/-/issues/923 Reproducer (with roots=20): # create verity device with RS FEC dd if=/dev/urandom of=data.img bs=4096 count=8 status=none veritysetup format data.img hash.img --fec-device=fec.img --fec-roots=20 | \ awk '/^Root hash/{ print $3 }' >roothash # create an erasure that should always be repairable with this roots setting dd if=/dev/zero of=data.img conv=notrunc bs=1 count=4 seek=4 status=none # try to read it through dm-verity veritysetup open data.img test hash.img --fec-device=fec.img --fec-roots=20 $(cat roothash) dd if=/dev/mapper/test of=/dev/null bs=4096 status=noxfer Even now the log says it cannot repair it: : verity-fec: 7:1: FEC 0: failed to correct: -74 : device-mapper: verity: 7:1: data block 0 is corrupted ... With this fix, errors are properly repaired. : verity-fec: 7:1: FEC 0: corrected 4 errors Signed-off-by: Milan Broz <gmazyland(a)gmail.com> Fixes: 8ca7cab82bda ("dm verity fec: fix misaligned RS roots IO") Cc: stable(a)vger.kernel.org --- drivers/md/dm-verity-fec.c | 40 +++++++++++++++++++++++++------------- 1 file changed, 26 insertions(+), 14 deletions(-) diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index 62b1a44b8dd2..6bd9848518d4 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -60,15 +60,19 @@ static int fec_decode_rs8(struct dm_verity *v, struct dm_verity_fec_io *fio, * to the data block. Caller is responsible for releasing buf. */ static u8 *fec_read_parity(struct dm_verity *v, u64 rsb, int index, - unsigned int *offset, struct dm_buffer **buf, - unsigned short ioprio) + unsigned int *offset, unsigned int par_buf_offset, + struct dm_buffer **buf, unsigned short ioprio) { u64 position, block, rem; u8 *res; + /* We have already part of parity bytes read, skip to the next block */ + if (par_buf_offset) + index++; + position = (index + rsb) * v->fec->roots; block = div64_u64_rem(position, v->fec->io_size, &rem); - *offset = (unsigned int)rem; + *offset = par_buf_offset ? 0 : (unsigned int)rem; res = dm_bufio_read_with_ioprio(v->fec->bufio, block, buf, ioprio); if (IS_ERR(res)) { @@ -128,11 +132,12 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_io *io, { int r, corrected = 0, res; struct dm_buffer *buf; - unsigned int n, i, offset; - u8 *par, *block; + unsigned int n, i, offset, par_buf_offset = 0; + u8 *par, *block, par_buf[DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN]; struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size); - par = fec_read_parity(v, rsb, block_offset, &offset, &buf, bio_prio(bio)); + par = fec_read_parity(v, rsb, block_offset, &offset, + par_buf_offset, &buf, bio_prio(bio)); if (IS_ERR(par)) return PTR_ERR(par); @@ -142,7 +147,8 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_io *io, */ fec_for_each_buffer_rs_block(fio, n, i) { block = fec_buffer_rs_block(v, fio, n, i); - res = fec_decode_rs8(v, fio, block, &par[offset], neras); + memcpy(&par_buf[par_buf_offset], &par[offset], v->fec->roots - par_buf_offset); + res = fec_decode_rs8(v, fio, block, par_buf, neras); if (res < 0) { r = res; goto error; @@ -155,12 +161,21 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_io *io, if (block_offset >= 1 << v->data_dev_block_bits) goto done; - /* read the next block when we run out of parity bytes */ - offset += v->fec->roots; + /* Read the next block when we run out of parity bytes */ + offset += (v->fec->roots - par_buf_offset); + /* Check if parity bytes are split between blocks */ + if (offset < v->fec->io_size && (offset + v->fec->roots) > v->fec->io_size) { + par_buf_offset = v->fec->io_size - offset; + memcpy(par_buf, &par[offset], par_buf_offset); + offset += par_buf_offset; + } else + par_buf_offset = 0; + if (offset >= v->fec->io_size) { dm_bufio_release(buf); - par = fec_read_parity(v, rsb, block_offset, &offset, &buf, bio_prio(bio)); + par = fec_read_parity(v, rsb, block_offset, &offset, + par_buf_offset, &buf, bio_prio(bio)); if (IS_ERR(par)) return PTR_ERR(par); } @@ -724,10 +739,7 @@ int verity_fec_ctr(struct dm_verity *v) return -E2BIG; } - if ((f->roots << SECTOR_SHIFT) & ((1 << v->data_dev_block_bits) - 1)) - f->io_size = 1 << v->data_dev_block_bits; - else - f->io_size = v->fec->roots << SECTOR_SHIFT; + f->io_size = 1 << v->data_dev_block_bits; f->bufio = dm_bufio_client_create(f->dev->bdev, f->io_size, -- 2.45.2

7 months, 3 weeks

2
1
0 0

FAILED: patch "[PATCH] x86/hyperv: Fix hv tsc page based sched_clock for hibernation" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x bcc80dec91ee745b3d66f3e48f0ec2efdea97149 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024122324-twitter-clustered-891d@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From bcc80dec91ee745b3d66f3e48f0ec2efdea97149 Mon Sep 17 00:00:00 2001 From: Naman Jain <namjain(a)linux.microsoft.com> Date: Tue, 17 Sep 2024 11:09:17 +0530 Subject: [PATCH] x86/hyperv: Fix hv tsc page based sched_clock for hibernation read_hv_sched_clock_tsc() assumes that the Hyper-V clock counter is bigger than the variable hv_sched_clock_offset, which is cached during early boot, but depending on the timing this assumption may be false when a hibernated VM starts again (the clock counter starts from 0 again) and is resuming back (Note: hv_init_tsc_clocksource() is not called during hibernation/resume); consequently, read_hv_sched_clock_tsc() may return a negative integer (which is interpreted as a huge positive integer since the return type is u64) and new kernel messages are prefixed with huge timestamps before read_hv_sched_clock_tsc() grows big enough (which typically takes several seconds). Fix the issue by saving the Hyper-V clock counter just before the suspend, and using it to correct the hv_sched_clock_offset in resume. This makes hv tsc page based sched_clock continuous and ensures that post resume, it starts from where it left off during suspend. Override x86_platform.save_sched_clock_state and x86_platform.restore_sched_clock_state routines to correct this as soon as possible. Note: if Invariant TSC is available, the issue doesn't happen because 1) we don't register read_hv_sched_clock_tsc() for sched clock: See commit e5313f1c5404 ("clocksource/drivers/hyper-v: Rework clocksource and sched clock setup"); 2) the common x86 code adjusts TSC similarly: see __restore_processor_state() -> tsc_verify_tsc_adjust(true) and x86_platform.restore_sched_clock_state(). Cc: stable(a)vger.kernel.org Fixes: 1349401ff1aa ("clocksource/drivers/hyper-v: Suspend/resume Hyper-V clocksource for hibernation") Co-developed-by: Dexuan Cui <decui(a)microsoft.com> Signed-off-by: Dexuan Cui <decui(a)microsoft.com> Signed-off-by: Naman Jain <namjain(a)linux.microsoft.com> Reviewed-by: Michael Kelley <mhklinux(a)outlook.com> Link: https://lore.kernel.org/r/20240917053917.76787-1-namjain@linux.microsoft.com Signed-off-by: Wei Liu <wei.liu(a)kernel.org> Message-ID: <20240917053917.76787-1-namjain(a)linux.microsoft.com> diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index d18078834ded..dc12fe5ef3ca 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -223,6 +223,63 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs) hyperv_cleanup(); } #endif /* CONFIG_CRASH_DUMP */ + +static u64 hv_ref_counter_at_suspend; +static void (*old_save_sched_clock_state)(void); +static void (*old_restore_sched_clock_state)(void); + +/* + * Hyper-V clock counter resets during hibernation. Save and restore clock + * offset during suspend/resume, while also considering the time passed + * before suspend. This is to make sure that sched_clock using hv tsc page + * based clocksource, proceeds from where it left off during suspend and + * it shows correct time for the timestamps of kernel messages after resume. + */ +static void save_hv_clock_tsc_state(void) +{ + hv_ref_counter_at_suspend = hv_read_reference_counter(); +} + +static void restore_hv_clock_tsc_state(void) +{ + /* + * Adjust the offsets used by hv tsc clocksource to + * account for the time spent before hibernation. + * adjusted value = reference counter (time) at suspend + * - reference counter (time) now. + */ + hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter()); +} + +/* + * Functions to override save_sched_clock_state and restore_sched_clock_state + * functions of x86_platform. The Hyper-V clock counter is reset during + * suspend-resume and the offset used to measure time needs to be + * corrected, post resume. + */ +static void hv_save_sched_clock_state(void) +{ + old_save_sched_clock_state(); + save_hv_clock_tsc_state(); +} + +static void hv_restore_sched_clock_state(void) +{ + restore_hv_clock_tsc_state(); + old_restore_sched_clock_state(); +} + +static void __init x86_setup_ops_for_tsc_pg_clock(void) +{ + if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) + return; + + old_save_sched_clock_state = x86_platform.save_sched_clock_state; + x86_platform.save_sched_clock_state = hv_save_sched_clock_state; + + old_restore_sched_clock_state = x86_platform.restore_sched_clock_state; + x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state; +} #endif /* CONFIG_HYPERV */ static uint32_t __init ms_hyperv_platform(void) @@ -579,6 +636,7 @@ static void __init ms_hyperv_init_platform(void) /* Register Hyper-V specific clocksource */ hv_init_clocksource(); + x86_setup_ops_for_tsc_pg_clock(); hv_vtl_init_platform(); #endif /* diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index 99177835cade..b39dee7b93af 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -27,7 +27,8 @@ #include <asm/mshyperv.h> static struct clock_event_device __percpu *hv_clock_event; -static u64 hv_sched_clock_offset __ro_after_init; +/* Note: offset can hold negative values after hibernation. */ +static u64 hv_sched_clock_offset __read_mostly; /* * If false, we're using the old mechanism for stimer0 interrupts @@ -470,6 +471,17 @@ static void resume_hv_clock_tsc(struct clocksource *arg) hv_set_msr(HV_MSR_REFERENCE_TSC, tsc_msr.as_uint64); } +/* + * Called during resume from hibernation, from overridden + * x86_platform.restore_sched_clock_state routine. This is to adjust offsets + * used to calculate time for hv tsc page based sched_clock, to account for + * time spent before hibernation. + */ +void hv_adj_sched_clock_offset(u64 offset) +{ + hv_sched_clock_offset -= offset; +} + #ifdef HAVE_VDSO_CLOCKMODE_HVCLOCK static int hv_cs_enable(struct clocksource *cs) { diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h index 6cdc873ac907..aa5233b1eba9 100644 --- a/include/clocksource/hyperv_timer.h +++ b/include/clocksource/hyperv_timer.h @@ -38,6 +38,8 @@ extern void hv_remap_tsc_clocksource(void); extern unsigned long hv_get_tsc_pfn(void); extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void); +extern void hv_adj_sched_clock_offset(u64 offset); + static __always_inline bool hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc, u64 *time)

7 months, 3 weeks

3
2
0 0

FAILED: patch "[PATCH] x86/hyperv: Fix hv tsc page based sched_clock for hibernation" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x bcc80dec91ee745b3d66f3e48f0ec2efdea97149 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024122327-imaginary-gizzard-8e8b@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From bcc80dec91ee745b3d66f3e48f0ec2efdea97149 Mon Sep 17 00:00:00 2001 From: Naman Jain <namjain(a)linux.microsoft.com> Date: Tue, 17 Sep 2024 11:09:17 +0530 Subject: [PATCH] x86/hyperv: Fix hv tsc page based sched_clock for hibernation read_hv_sched_clock_tsc() assumes that the Hyper-V clock counter is bigger than the variable hv_sched_clock_offset, which is cached during early boot, but depending on the timing this assumption may be false when a hibernated VM starts again (the clock counter starts from 0 again) and is resuming back (Note: hv_init_tsc_clocksource() is not called during hibernation/resume); consequently, read_hv_sched_clock_tsc() may return a negative integer (which is interpreted as a huge positive integer since the return type is u64) and new kernel messages are prefixed with huge timestamps before read_hv_sched_clock_tsc() grows big enough (which typically takes several seconds). Fix the issue by saving the Hyper-V clock counter just before the suspend, and using it to correct the hv_sched_clock_offset in resume. This makes hv tsc page based sched_clock continuous and ensures that post resume, it starts from where it left off during suspend. Override x86_platform.save_sched_clock_state and x86_platform.restore_sched_clock_state routines to correct this as soon as possible. Note: if Invariant TSC is available, the issue doesn't happen because 1) we don't register read_hv_sched_clock_tsc() for sched clock: See commit e5313f1c5404 ("clocksource/drivers/hyper-v: Rework clocksource and sched clock setup"); 2) the common x86 code adjusts TSC similarly: see __restore_processor_state() -> tsc_verify_tsc_adjust(true) and x86_platform.restore_sched_clock_state(). Cc: stable(a)vger.kernel.org Fixes: 1349401ff1aa ("clocksource/drivers/hyper-v: Suspend/resume Hyper-V clocksource for hibernation") Co-developed-by: Dexuan Cui <decui(a)microsoft.com> Signed-off-by: Dexuan Cui <decui(a)microsoft.com> Signed-off-by: Naman Jain <namjain(a)linux.microsoft.com> Reviewed-by: Michael Kelley <mhklinux(a)outlook.com> Link: https://lore.kernel.org/r/20240917053917.76787-1-namjain@linux.microsoft.com Signed-off-by: Wei Liu <wei.liu(a)kernel.org> Message-ID: <20240917053917.76787-1-namjain(a)linux.microsoft.com> diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index d18078834ded..dc12fe5ef3ca 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -223,6 +223,63 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs) hyperv_cleanup(); } #endif /* CONFIG_CRASH_DUMP */ + +static u64 hv_ref_counter_at_suspend; +static void (*old_save_sched_clock_state)(void); +static void (*old_restore_sched_clock_state)(void); + +/* + * Hyper-V clock counter resets during hibernation. Save and restore clock + * offset during suspend/resume, while also considering the time passed + * before suspend. This is to make sure that sched_clock using hv tsc page + * based clocksource, proceeds from where it left off during suspend and + * it shows correct time for the timestamps of kernel messages after resume. + */ +static void save_hv_clock_tsc_state(void) +{ + hv_ref_counter_at_suspend = hv_read_reference_counter(); +} + +static void restore_hv_clock_tsc_state(void) +{ + /* + * Adjust the offsets used by hv tsc clocksource to + * account for the time spent before hibernation. + * adjusted value = reference counter (time) at suspend + * - reference counter (time) now. + */ + hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter()); +} + +/* + * Functions to override save_sched_clock_state and restore_sched_clock_state + * functions of x86_platform. The Hyper-V clock counter is reset during + * suspend-resume and the offset used to measure time needs to be + * corrected, post resume. + */ +static void hv_save_sched_clock_state(void) +{ + old_save_sched_clock_state(); + save_hv_clock_tsc_state(); +} + +static void hv_restore_sched_clock_state(void) +{ + restore_hv_clock_tsc_state(); + old_restore_sched_clock_state(); +} + +static void __init x86_setup_ops_for_tsc_pg_clock(void) +{ + if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) + return; + + old_save_sched_clock_state = x86_platform.save_sched_clock_state; + x86_platform.save_sched_clock_state = hv_save_sched_clock_state; + + old_restore_sched_clock_state = x86_platform.restore_sched_clock_state; + x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state; +} #endif /* CONFIG_HYPERV */ static uint32_t __init ms_hyperv_platform(void) @@ -579,6 +636,7 @@ static void __init ms_hyperv_init_platform(void) /* Register Hyper-V specific clocksource */ hv_init_clocksource(); + x86_setup_ops_for_tsc_pg_clock(); hv_vtl_init_platform(); #endif /* diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index 99177835cade..b39dee7b93af 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -27,7 +27,8 @@ #include <asm/mshyperv.h> static struct clock_event_device __percpu *hv_clock_event; -static u64 hv_sched_clock_offset __ro_after_init; +/* Note: offset can hold negative values after hibernation. */ +static u64 hv_sched_clock_offset __read_mostly; /* * If false, we're using the old mechanism for stimer0 interrupts @@ -470,6 +471,17 @@ static void resume_hv_clock_tsc(struct clocksource *arg) hv_set_msr(HV_MSR_REFERENCE_TSC, tsc_msr.as_uint64); } +/* + * Called during resume from hibernation, from overridden + * x86_platform.restore_sched_clock_state routine. This is to adjust offsets + * used to calculate time for hv tsc page based sched_clock, to account for + * time spent before hibernation. + */ +void hv_adj_sched_clock_offset(u64 offset) +{ + hv_sched_clock_offset -= offset; +} + #ifdef HAVE_VDSO_CLOCKMODE_HVCLOCK static int hv_cs_enable(struct clocksource *cs) { diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h index 6cdc873ac907..aa5233b1eba9 100644 --- a/include/clocksource/hyperv_timer.h +++ b/include/clocksource/hyperv_timer.h @@ -38,6 +38,8 @@ extern void hv_remap_tsc_clocksource(void); extern unsigned long hv_get_tsc_pfn(void); extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void); +extern void hv_adj_sched_clock_offset(u64 offset); + static __always_inline bool hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc, u64 *time)

7 months, 3 weeks

3
2
0 0

FAILED: patch "[PATCH] x86/hyperv: Fix hv tsc page based sched_clock for hibernation" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x bcc80dec91ee745b3d66f3e48f0ec2efdea97149 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024122325-flavoring-mute-cb7e@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From bcc80dec91ee745b3d66f3e48f0ec2efdea97149 Mon Sep 17 00:00:00 2001 From: Naman Jain <namjain(a)linux.microsoft.com> Date: Tue, 17 Sep 2024 11:09:17 +0530 Subject: [PATCH] x86/hyperv: Fix hv tsc page based sched_clock for hibernation read_hv_sched_clock_tsc() assumes that the Hyper-V clock counter is bigger than the variable hv_sched_clock_offset, which is cached during early boot, but depending on the timing this assumption may be false when a hibernated VM starts again (the clock counter starts from 0 again) and is resuming back (Note: hv_init_tsc_clocksource() is not called during hibernation/resume); consequently, read_hv_sched_clock_tsc() may return a negative integer (which is interpreted as a huge positive integer since the return type is u64) and new kernel messages are prefixed with huge timestamps before read_hv_sched_clock_tsc() grows big enough (which typically takes several seconds). Fix the issue by saving the Hyper-V clock counter just before the suspend, and using it to correct the hv_sched_clock_offset in resume. This makes hv tsc page based sched_clock continuous and ensures that post resume, it starts from where it left off during suspend. Override x86_platform.save_sched_clock_state and x86_platform.restore_sched_clock_state routines to correct this as soon as possible. Note: if Invariant TSC is available, the issue doesn't happen because 1) we don't register read_hv_sched_clock_tsc() for sched clock: See commit e5313f1c5404 ("clocksource/drivers/hyper-v: Rework clocksource and sched clock setup"); 2) the common x86 code adjusts TSC similarly: see __restore_processor_state() -> tsc_verify_tsc_adjust(true) and x86_platform.restore_sched_clock_state(). Cc: stable(a)vger.kernel.org Fixes: 1349401ff1aa ("clocksource/drivers/hyper-v: Suspend/resume Hyper-V clocksource for hibernation") Co-developed-by: Dexuan Cui <decui(a)microsoft.com> Signed-off-by: Dexuan Cui <decui(a)microsoft.com> Signed-off-by: Naman Jain <namjain(a)linux.microsoft.com> Reviewed-by: Michael Kelley <mhklinux(a)outlook.com> Link: https://lore.kernel.org/r/20240917053917.76787-1-namjain@linux.microsoft.com Signed-off-by: Wei Liu <wei.liu(a)kernel.org> Message-ID: <20240917053917.76787-1-namjain(a)linux.microsoft.com> diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index d18078834ded..dc12fe5ef3ca 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -223,6 +223,63 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs) hyperv_cleanup(); } #endif /* CONFIG_CRASH_DUMP */ + +static u64 hv_ref_counter_at_suspend; +static void (*old_save_sched_clock_state)(void); +static void (*old_restore_sched_clock_state)(void); + +/* + * Hyper-V clock counter resets during hibernation. Save and restore clock + * offset during suspend/resume, while also considering the time passed + * before suspend. This is to make sure that sched_clock using hv tsc page + * based clocksource, proceeds from where it left off during suspend and + * it shows correct time for the timestamps of kernel messages after resume. + */ +static void save_hv_clock_tsc_state(void) +{ + hv_ref_counter_at_suspend = hv_read_reference_counter(); +} + +static void restore_hv_clock_tsc_state(void) +{ + /* + * Adjust the offsets used by hv tsc clocksource to + * account for the time spent before hibernation. + * adjusted value = reference counter (time) at suspend + * - reference counter (time) now. + */ + hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter()); +} + +/* + * Functions to override save_sched_clock_state and restore_sched_clock_state + * functions of x86_platform. The Hyper-V clock counter is reset during + * suspend-resume and the offset used to measure time needs to be + * corrected, post resume. + */ +static void hv_save_sched_clock_state(void) +{ + old_save_sched_clock_state(); + save_hv_clock_tsc_state(); +} + +static void hv_restore_sched_clock_state(void) +{ + restore_hv_clock_tsc_state(); + old_restore_sched_clock_state(); +} + +static void __init x86_setup_ops_for_tsc_pg_clock(void) +{ + if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) + return; + + old_save_sched_clock_state = x86_platform.save_sched_clock_state; + x86_platform.save_sched_clock_state = hv_save_sched_clock_state; + + old_restore_sched_clock_state = x86_platform.restore_sched_clock_state; + x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state; +} #endif /* CONFIG_HYPERV */ static uint32_t __init ms_hyperv_platform(void) @@ -579,6 +636,7 @@ static void __init ms_hyperv_init_platform(void) /* Register Hyper-V specific clocksource */ hv_init_clocksource(); + x86_setup_ops_for_tsc_pg_clock(); hv_vtl_init_platform(); #endif /* diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index 99177835cade..b39dee7b93af 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -27,7 +27,8 @@ #include <asm/mshyperv.h> static struct clock_event_device __percpu *hv_clock_event; -static u64 hv_sched_clock_offset __ro_after_init; +/* Note: offset can hold negative values after hibernation. */ +static u64 hv_sched_clock_offset __read_mostly; /* * If false, we're using the old mechanism for stimer0 interrupts @@ -470,6 +471,17 @@ static void resume_hv_clock_tsc(struct clocksource *arg) hv_set_msr(HV_MSR_REFERENCE_TSC, tsc_msr.as_uint64); } +/* + * Called during resume from hibernation, from overridden + * x86_platform.restore_sched_clock_state routine. This is to adjust offsets + * used to calculate time for hv tsc page based sched_clock, to account for + * time spent before hibernation. + */ +void hv_adj_sched_clock_offset(u64 offset) +{ + hv_sched_clock_offset -= offset; +} + #ifdef HAVE_VDSO_CLOCKMODE_HVCLOCK static int hv_cs_enable(struct clocksource *cs) { diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h index 6cdc873ac907..aa5233b1eba9 100644 --- a/include/clocksource/hyperv_timer.h +++ b/include/clocksource/hyperv_timer.h @@ -38,6 +38,8 @@ extern void hv_remap_tsc_clocksource(void); extern unsigned long hv_get_tsc_pfn(void); extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void); +extern void hv_adj_sched_clock_offset(u64 offset); + static __always_inline bool hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc, u64 *time)

7 months, 3 weeks

3
2
0 0

FAILED: patch "[PATCH] x86/hyperv: Fix hv tsc page based sched_clock for hibernation" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x bcc80dec91ee745b3d66f3e48f0ec2efdea97149 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024122326-eraser-perennial-6b59@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From bcc80dec91ee745b3d66f3e48f0ec2efdea97149 Mon Sep 17 00:00:00 2001 From: Naman Jain <namjain(a)linux.microsoft.com> Date: Tue, 17 Sep 2024 11:09:17 +0530 Subject: [PATCH] x86/hyperv: Fix hv tsc page based sched_clock for hibernation read_hv_sched_clock_tsc() assumes that the Hyper-V clock counter is bigger than the variable hv_sched_clock_offset, which is cached during early boot, but depending on the timing this assumption may be false when a hibernated VM starts again (the clock counter starts from 0 again) and is resuming back (Note: hv_init_tsc_clocksource() is not called during hibernation/resume); consequently, read_hv_sched_clock_tsc() may return a negative integer (which is interpreted as a huge positive integer since the return type is u64) and new kernel messages are prefixed with huge timestamps before read_hv_sched_clock_tsc() grows big enough (which typically takes several seconds). Fix the issue by saving the Hyper-V clock counter just before the suspend, and using it to correct the hv_sched_clock_offset in resume. This makes hv tsc page based sched_clock continuous and ensures that post resume, it starts from where it left off during suspend. Override x86_platform.save_sched_clock_state and x86_platform.restore_sched_clock_state routines to correct this as soon as possible. Note: if Invariant TSC is available, the issue doesn't happen because 1) we don't register read_hv_sched_clock_tsc() for sched clock: See commit e5313f1c5404 ("clocksource/drivers/hyper-v: Rework clocksource and sched clock setup"); 2) the common x86 code adjusts TSC similarly: see __restore_processor_state() -> tsc_verify_tsc_adjust(true) and x86_platform.restore_sched_clock_state(). Cc: stable(a)vger.kernel.org Fixes: 1349401ff1aa ("clocksource/drivers/hyper-v: Suspend/resume Hyper-V clocksource for hibernation") Co-developed-by: Dexuan Cui <decui(a)microsoft.com> Signed-off-by: Dexuan Cui <decui(a)microsoft.com> Signed-off-by: Naman Jain <namjain(a)linux.microsoft.com> Reviewed-by: Michael Kelley <mhklinux(a)outlook.com> Link: https://lore.kernel.org/r/20240917053917.76787-1-namjain@linux.microsoft.com Signed-off-by: Wei Liu <wei.liu(a)kernel.org> Message-ID: <20240917053917.76787-1-namjain(a)linux.microsoft.com> diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index d18078834ded..dc12fe5ef3ca 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -223,6 +223,63 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs) hyperv_cleanup(); } #endif /* CONFIG_CRASH_DUMP */ + +static u64 hv_ref_counter_at_suspend; +static void (*old_save_sched_clock_state)(void); +static void (*old_restore_sched_clock_state)(void); + +/* + * Hyper-V clock counter resets during hibernation. Save and restore clock + * offset during suspend/resume, while also considering the time passed + * before suspend. This is to make sure that sched_clock using hv tsc page + * based clocksource, proceeds from where it left off during suspend and + * it shows correct time for the timestamps of kernel messages after resume. + */ +static void save_hv_clock_tsc_state(void) +{ + hv_ref_counter_at_suspend = hv_read_reference_counter(); +} + +static void restore_hv_clock_tsc_state(void) +{ + /* + * Adjust the offsets used by hv tsc clocksource to + * account for the time spent before hibernation. + * adjusted value = reference counter (time) at suspend + * - reference counter (time) now. + */ + hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter()); +} + +/* + * Functions to override save_sched_clock_state and restore_sched_clock_state + * functions of x86_platform. The Hyper-V clock counter is reset during + * suspend-resume and the offset used to measure time needs to be + * corrected, post resume. + */ +static void hv_save_sched_clock_state(void) +{ + old_save_sched_clock_state(); + save_hv_clock_tsc_state(); +} + +static void hv_restore_sched_clock_state(void) +{ + restore_hv_clock_tsc_state(); + old_restore_sched_clock_state(); +} + +static void __init x86_setup_ops_for_tsc_pg_clock(void) +{ + if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) + return; + + old_save_sched_clock_state = x86_platform.save_sched_clock_state; + x86_platform.save_sched_clock_state = hv_save_sched_clock_state; + + old_restore_sched_clock_state = x86_platform.restore_sched_clock_state; + x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state; +} #endif /* CONFIG_HYPERV */ static uint32_t __init ms_hyperv_platform(void) @@ -579,6 +636,7 @@ static void __init ms_hyperv_init_platform(void) /* Register Hyper-V specific clocksource */ hv_init_clocksource(); + x86_setup_ops_for_tsc_pg_clock(); hv_vtl_init_platform(); #endif /* diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index 99177835cade..b39dee7b93af 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -27,7 +27,8 @@ #include <asm/mshyperv.h> static struct clock_event_device __percpu *hv_clock_event; -static u64 hv_sched_clock_offset __ro_after_init; +/* Note: offset can hold negative values after hibernation. */ +static u64 hv_sched_clock_offset __read_mostly; /* * If false, we're using the old mechanism for stimer0 interrupts @@ -470,6 +471,17 @@ static void resume_hv_clock_tsc(struct clocksource *arg) hv_set_msr(HV_MSR_REFERENCE_TSC, tsc_msr.as_uint64); } +/* + * Called during resume from hibernation, from overridden + * x86_platform.restore_sched_clock_state routine. This is to adjust offsets + * used to calculate time for hv tsc page based sched_clock, to account for + * time spent before hibernation. + */ +void hv_adj_sched_clock_offset(u64 offset) +{ + hv_sched_clock_offset -= offset; +} + #ifdef HAVE_VDSO_CLOCKMODE_HVCLOCK static int hv_cs_enable(struct clocksource *cs) { diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h index 6cdc873ac907..aa5233b1eba9 100644 --- a/include/clocksource/hyperv_timer.h +++ b/include/clocksource/hyperv_timer.h @@ -38,6 +38,8 @@ extern void hv_remap_tsc_clocksource(void); extern unsigned long hv_get_tsc_pfn(void); extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void); +extern void hv_adj_sched_clock_offset(u64 offset); + static __always_inline bool hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc, u64 *time)

7 months, 3 weeks

3
2
0 0

[PATCH v3] USB: core: Disable LPM only for non-suspended ports

by Kai-Heng Feng

There's USB error when tegra board is shutting down: [ 180.919315] usb 2-3: Failed to set U1 timeout to 0x0,error code -113 [ 180.919995] usb 2-3: Failed to set U1 timeout to 0xa,error code -113 [ 180.920512] usb 2-3: Failed to set U2 timeout to 0x4,error code -113 [ 186.157172] tegra-xusb 3610000.usb: xHCI host controller not responding, assume dead [ 186.157858] tegra-xusb 3610000.usb: HC died; cleaning up [ 186.317280] tegra-xusb 3610000.usb: Timeout while waiting for evaluate context command The issue is caused by disabling LPM on already suspended ports. For USB2 LPM, the LPM is already disabled during port suspend. For USB3 LPM, port won't transit to U1/U2 when it's already suspended in U3, hence disabling LPM is only needed for ports that are not suspended. Cc: Wayne Chang <waynec(a)nvidia.com> Cc: stable(a)vger.kernel.org Fixes: d920a2ed8620 ("usb: Disable USB3 LPM at shutdown") Signed-off-by: Kai-Heng Feng <kaihengf(a)nvidia.com> --- v3: Use udev->port_is_suspended which reflects upstream port status v2: Add "Cc: stable(a)vger.kernel.org" drivers/usb/core/port.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/usb/core/port.c b/drivers/usb/core/port.c index e7da2fca11a4..c92fb648a1c4 100644 --- a/drivers/usb/core/port.c +++ b/drivers/usb/core/port.c @@ -452,10 +452,11 @@ static int usb_port_runtime_suspend(struct device *dev) static void usb_port_shutdown(struct device *dev) { struct usb_port *port_dev = to_usb_port(dev); + struct usb_device *udev = port_dev->child; - if (port_dev->child) { - usb_disable_usb2_hardware_lpm(port_dev->child); - usb_unlocked_disable_lpm(port_dev->child); + if (udev && !udev->port_is_suspended) { + usb_disable_usb2_hardware_lpm(udev); + usb_unlocked_disable_lpm(udev); } } -- 2.47.0

7 months, 3 weeks

4
4
0 0

[PATCH 5.4~6.6] MIPS: Probe toolchain support of -msym32

by WangYuli

From: Jiaxun Yang <jiaxun.yang(a)flygoat.com> [ Upstream commit 18ca63a2e23c5e170d2d7552b64b1f5ad019cd9b ] msym32 is not supported by LLVM toolchain. Workaround by probe toolchain support of msym32 for KBUILD_SYM32 feature. Link: https://github.com/ClangBuiltLinux/linux/issues/1544 Signed-off-by: Jiaxun Yang <jiaxun.yang(a)flygoat.com> Signed-off-by: Thomas Bogendoerfer <tsbogend(a)alpha.franken.de> Signed-off-by: WangYuli <wangyuli(a)uniontech.com> --- arch/mips/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/mips/Makefile b/arch/mips/Makefile index f49807e1f19b..0888074f4dfe 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -299,7 +299,7 @@ drivers-$(CONFIG_PCI) += arch/mips/pci/ ifdef CONFIG_64BIT ifndef KBUILD_SYM32 ifeq ($(shell expr $(load-y) \< 0xffffffff80000000), 0) - KBUILD_SYM32 = y + KBUILD_SYM32 = $(call cc-option-yn, -msym32) endif endif -- 2.47.1

7 months, 3 weeks

3
5
0 0

[PATCH net 0/3] mptcp: rx path fixes

by Matthieu Baerts (NGI0)

Here are 3 different fixes, all related to the MPTCP receive buffer: - Patch 1: fix receive buffer space when recvmsg() blocks after receiving some data. For a fix introduced in v6.12, backported to v6.1. - Patch 2: mptcp_cleanup_rbuf() can be called when no data has been copied. For 5.11. - Patch 3: prevent excessive coalescing on receive, which can affect the throughput badly. It looks better to wait a bit before backporting this one to stable versions, to get more results. For 5.10. Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Please note that there is no urgency here as well: this can of course be sent to Linus next year! Enjoy this holiday period! --- Paolo Abeni (3): mptcp: fix recvbuffer adjust on sleeping rcvmsg mptcp: don't always assume copied data in mptcp_cleanup_rbuf() mptcp: prevent excessive coalescing on receive net/mptcp/protocol.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) --- base-commit: a024e377efed31ecfb39210bed562932321345b3 change-id: 20241230-net-mptcp-rbuf-fixes-74526e59d951 Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

7 months, 3 weeks

2
4
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror December 2024