diff options
90 files changed, 748 insertions, 371 deletions
diff --git a/Documentation/admin-guide/device-mapper/verity.rst b/Documentation/admin-guide/device-mapper/verity.rst index 1a6b91368e59..a65c1602cb23 100644 --- a/Documentation/admin-guide/device-mapper/verity.rst +++ b/Documentation/admin-guide/device-mapper/verity.rst @@ -141,6 +141,10 @@ root_hash_sig_key_desc <key_description> also gain new certificates at run time if they are signed by a certificate already in the secondary trusted keyring. +try_verify_in_tasklet + If verity hashes are in cache, verify data blocks in kernel tasklet instead + of workqueue. This option can reduce IO latency. + Theory of operation =================== diff --git a/Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml b/Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml index 64995cbb0f97..41c9760227cd 100644 --- a/Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml +++ b/Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml @@ -8,7 +8,6 @@ title: Samsung S3FWRN5 NCI NFC Controller maintainers: - Krzysztof Kozlowski <[email protected]> - - Krzysztof Opasiak <[email protected]> properties: compatible: diff --git a/MAINTAINERS b/MAINTAINERS index cf0f18502372..8b73135ddb21 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4459,13 +4459,15 @@ M: Josef Bacik <[email protected]> M: David Sterba <[email protected]> S: Maintained -W: http://btrfs.wiki.kernel.org/ -Q: http://patchwork.kernel.org/project/linux-btrfs/list/ +W: https://btrfs.readthedocs.io +W: https://btrfs.wiki.kernel.org/ +Q: https://patchwork.kernel.org/project/linux-btrfs/list/ C: irc://irc.libera.chat/btrfs T: git git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux.git F: Documentation/filesystems/btrfs.rst F: fs/btrfs/ F: include/linux/btrfs* +F: include/trace/events/btrfs.h F: include/uapi/linux/btrfs* BTTV VIDEO4LINUX DRIVER @@ -5266,6 +5268,7 @@ F: tools/testing/selftests/cgroup/ CONTROL GROUP - BLOCK IO CONTROLLER (BLKIO) M: Tejun Heo <[email protected]> +M: Josef Bacik <[email protected]> M: Jens Axboe <[email protected]> @@ -5273,6 +5276,7 @@ T: git git://git.kernel.dk/linux-block F: Documentation/admin-guide/cgroup-v1/blkio-controller.rst F: block/bfq-cgroup.c F: block/blk-cgroup.c +F: block/blk-iocost.c F: block/blk-iolatency.c F: block/blk-throttle.c F: include/linux/blk-cgroup.h @@ -18211,7 +18215,6 @@ F: include/media/drv-intf/s3c_camif.h SAMSUNG S3FWRN5 NFC DRIVER M: Krzysztof Kozlowski <[email protected]> -M: Krzysztof Opasiak <[email protected]> L: [email protected] (subscribers-only) S: Maintained F: Documentation/devicetree/bindings/net/nfc/samsung,s3fwrn5.yaml @@ -21293,7 +21296,7 @@ L: [email protected] S: Maintained W: https://github.com/petkan/pegasus -T: git git://github.com/petkan/pegasus.git +T: git https://github.com/petkan/pegasus.git F: drivers/net/usb/pegasus.* USB PHY LAYER @@ -21330,7 +21333,7 @@ L: [email protected] S: Maintained W: https://github.com/petkan/rtl8150 -T: git git://github.com/petkan/rtl8150.git +T: git https://github.com/petkan/rtl8150.git F: drivers/net/usb/rtl8150.c USB SERIAL SUBSYSTEM diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index da7ee8bec165..7add8e79912b 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -257,7 +257,7 @@ enum { PCS_7 = 0x94, /* 7+ port PCS (Denverton) */ /* em constants */ - EM_MAX_SLOTS = 8, + EM_MAX_SLOTS = SATA_PMP_MAX_PORTS, EM_MAX_RETRY = 5, /* em_ctl bits */ diff --git a/drivers/ata/ahci_brcm.c b/drivers/ata/ahci_brcm.c index f61795c546cf..6f216eb25610 100644 --- a/drivers/ata/ahci_brcm.c +++ b/drivers/ata/ahci_brcm.c @@ -448,7 +448,7 @@ static int brcm_ahci_probe(struct platform_device *pdev) if (!of_id) return -ENODEV; - priv->version = (enum brcm_ahci_version)of_id->data; + priv->version = (unsigned long)of_id->data; priv->dev = dev; res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "top-ctrl"); diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c index b734e069034d..a950767f7948 100644 --- a/drivers/ata/ahci_imx.c +++ b/drivers/ata/ahci_imx.c @@ -1067,7 +1067,7 @@ static int imx_ahci_probe(struct platform_device *pdev) imxpriv->ahci_pdev = pdev; imxpriv->no_device = false; imxpriv->first_time = true; - imxpriv->type = (enum ahci_imx_type)of_id->data; + imxpriv->type = (unsigned long)of_id->data; imxpriv->sata_clk = devm_clk_get(dev, "sata"); if (IS_ERR(imxpriv->sata_clk)) { @@ -1235,4 +1235,4 @@ module_platform_driver(imx_ahci_driver); MODULE_DESCRIPTION("Freescale i.MX AHCI SATA platform driver"); MODULE_AUTHOR("Richard Zhu <[email protected]>"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("ahci:imx"); +MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/ata/ahci_qoriq.c b/drivers/ata/ahci_qoriq.c index 6cd61842ad48..9cf9bf36a874 100644 --- a/drivers/ata/ahci_qoriq.c +++ b/drivers/ata/ahci_qoriq.c @@ -280,7 +280,7 @@ static int ahci_qoriq_probe(struct platform_device *pdev) return -ENOMEM; if (of_id) - qoriq_priv->type = (enum ahci_qoriq_type)of_id->data; + qoriq_priv->type = (unsigned long)of_id->data; else qoriq_priv->type = (enum ahci_qoriq_type)acpi_id->driver_data; diff --git a/drivers/ata/ahci_st.c b/drivers/ata/ahci_st.c index 5a2cac60a29a..8607b68eee53 100644 --- a/drivers/ata/ahci_st.c +++ b/drivers/ata/ahci_st.c @@ -236,7 +236,7 @@ static struct platform_driver st_ahci_driver = { .driver = { .name = DRV_NAME, .pm = &st_ahci_pm_ops, - .of_match_table = of_match_ptr(st_ahci_match), + .of_match_table = st_ahci_match, }, .probe = st_ahci_probe, .remove = ata_platform_remove_one, diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c index 7bb5db17f864..1e08704d5117 100644 --- a/drivers/ata/ahci_xgene.c +++ b/drivers/ata/ahci_xgene.c @@ -785,7 +785,7 @@ static int xgene_ahci_probe(struct platform_device *pdev) of_devid = of_match_device(xgene_ahci_of_match, dev); if (of_devid) { if (of_devid->data) - version = (enum xgene_ahci_version) of_devid->data; + version = (unsigned long) of_devid->data; } #ifdef CONFIG_ACPI else { diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c index 590ebea99601..0195eb29f6c2 100644 --- a/drivers/ata/sata_rcar.c +++ b/drivers/ata/sata_rcar.c @@ -875,7 +875,7 @@ static int sata_rcar_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; - priv->type = (enum sata_rcar_type)of_device_get_match_data(dev); + priv->type = (unsigned long)of_device_get_match_data(dev); pm_runtime_enable(dev); ret = pm_runtime_get_sync(dev); diff --git a/drivers/char/hw_random/bcm2835-rng.c b/drivers/char/hw_random/bcm2835-rng.c index e7dd457e9b22..e98fcac578d6 100644 --- a/drivers/char/hw_random/bcm2835-rng.c +++ b/drivers/char/hw_random/bcm2835-rng.c @@ -71,7 +71,7 @@ static int bcm2835_rng_read(struct hwrng *rng, void *buf, size_t max, while ((rng_readl(priv, RNG_STATUS) >> 24) == 0) { if (!wait) return 0; - cpu_relax(); + hwrng_msleep(rng, 1000); } num_words = rng_readl(priv, RNG_STATUS) >> 24; diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 09c7ed2650ca..9c5ef818ca36 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -795,7 +795,8 @@ static void __make_buffer_clean(struct dm_buffer *b) { BUG_ON(b->hold_count); - if (!b->state) /* fast case */ + /* smp_load_acquire() pairs with read_endio()'s smp_mb__before_atomic() */ + if (!smp_load_acquire(&b->state)) /* fast case */ return; wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE); @@ -816,7 +817,7 @@ static struct dm_buffer *__get_unclaimed_buffer(struct dm_bufio_client *c) BUG_ON(test_bit(B_DIRTY, &b->state)); if (static_branch_unlikely(&no_sleep_enabled) && c->no_sleep && - unlikely(test_bit(B_READING, &b->state))) + unlikely(test_bit_acquire(B_READING, &b->state))) continue; if (!b->hold_count) { @@ -1058,7 +1059,7 @@ found_buffer: * If the user called both dm_bufio_prefetch and dm_bufio_get on * the same buffer, it would deadlock if we waited. */ - if (nf == NF_GET && unlikely(test_bit(B_READING, &b->state))) + if (nf == NF_GET && unlikely(test_bit_acquire(B_READING, &b->state))) return NULL; b->hold_count++; @@ -1218,7 +1219,7 @@ void dm_bufio_release(struct dm_buffer *b) * invalid buffer. */ if ((b->read_error || b->write_error) && - !test_bit(B_READING, &b->state) && + !test_bit_acquire(B_READING, &b->state) && !test_bit(B_WRITING, &b->state) && !test_bit(B_DIRTY, &b->state)) { __unlink_buffer(b); @@ -1479,7 +1480,7 @@ EXPORT_SYMBOL_GPL(dm_bufio_release_move); static void forget_buffer_locked(struct dm_buffer *b) { - if (likely(!b->hold_count) && likely(!b->state)) { + if (likely(!b->hold_count) && likely(!smp_load_acquire(&b->state))) { __unlink_buffer(b); __free_buffer_wake(b); } @@ -1639,7 +1640,7 @@ static bool __try_evict_buffer(struct dm_buffer *b, gfp_t gfp) { if (!(gfp & __GFP_FS) || (static_branch_unlikely(&no_sleep_enabled) && b->c->no_sleep)) { - if (test_bit(B_READING, &b->state) || + if (test_bit_acquire(B_READING, &b->state) || test_bit(B_WRITING, &b->state) || test_bit(B_DIRTY, &b->state)) return false; diff --git a/drivers/md/dm-cache-policy.h b/drivers/md/dm-cache-policy.h index c05fc3436cef..06eb31af626f 100644 --- a/drivers/md/dm-cache-policy.h +++ b/drivers/md/dm-cache-policy.h @@ -166,7 +166,7 @@ struct dm_cache_policy_type { struct dm_cache_policy_type *real; /* - * Policies may store a hint for each each cache block. + * Policies may store a hint for each cache block. * Currently the size of this hint must be 0 or 4 bytes but we * expect to relax this in future. */ diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index 811b0a5379d0..2f1cc66d2641 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -2035,7 +2035,7 @@ static void disable_passdown_if_not_supported(struct clone *clone) reason = "max discard sectors smaller than a region"; if (reason) { - DMWARN("Destination device (%pd) %s: Disabling discard passdown.", + DMWARN("Destination device (%pg) %s: Disabling discard passdown.", dest_dev, reason); clear_bit(DM_CLONE_DISCARD_PASSDOWN, &clone->flags); } diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 98976aaa9db9..6b3f867d0b70 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -434,10 +434,10 @@ static struct mapped_device *dm_hash_rename(struct dm_ioctl *param, hc = __get_name_cell(new); if (hc) { - DMWARN("Unable to change %s on mapped device %s to one that " - "already exists: %s", - change_uuid ? "uuid" : "name", - param->name, new); + DMERR("Unable to change %s on mapped device %s to one that " + "already exists: %s", + change_uuid ? "uuid" : "name", + param->name, new); dm_put(hc->md); up_write(&_hash_lock); kfree(new_data); @@ -449,8 +449,8 @@ static struct mapped_device *dm_hash_rename(struct dm_ioctl *param, */ hc = __get_name_cell(param->name); if (!hc) { - DMWARN("Unable to rename non-existent device, %s to %s%s", - param->name, change_uuid ? "uuid " : "", new); + DMERR("Unable to rename non-existent device, %s to %s%s", + param->name, change_uuid ? "uuid " : "", new); up_write(&_hash_lock); kfree(new_data); return ERR_PTR(-ENXIO); @@ -460,9 +460,9 @@ static struct mapped_device *dm_hash_rename(struct dm_ioctl *param, * Does this device already have a uuid? */ if (change_uuid && hc->uuid) { - DMWARN("Unable to change uuid of mapped device %s to %s " - "because uuid is already set to %s", - param->name, new, hc->uuid); + DMERR("Unable to change uuid of mapped device %s to %s " + "because uuid is already set to %s", + param->name, new, hc->uuid); dm_put(hc->md); up_write(&_hash_lock); kfree(new_data); @@ -750,7 +750,7 @@ static int get_target_version(struct file *filp, struct dm_ioctl *param, size_t static int check_name(const char *name) { if (strchr(name, '/')) { - DMWARN("invalid device name"); + DMERR("invalid device name"); return -EINVAL; } @@ -773,7 +773,7 @@ static struct dm_table *dm_get_inactive_table(struct mapped_device *md, int *src down_read(&_hash_lock); hc = dm_get_mdptr(md); if (!hc || hc->md != md) { - DMWARN("device has been removed from the dev hash table."); + DMERR("device has been removed from the dev hash table."); goto out; } @@ -1026,7 +1026,7 @@ static int dev_rename(struct file *filp, struct dm_ioctl *param, size_t param_si if (new_data < param->data || invalid_str(new_data, (void *) param + param_size) || !*new_data || strlen(new_data) > (change_uuid ? DM_UUID_LEN - 1 : DM_NAME_LEN - 1)) { - DMWARN("Invalid new mapped device name or uuid string supplied."); + DMERR("Invalid new mapped device name or uuid string supplied."); return -EINVAL; } @@ -1061,7 +1061,7 @@ static int dev_set_geometry(struct file *filp, struct dm_ioctl *param, size_t pa if (geostr < param->data || invalid_str(geostr, (void *) param + param_size)) { - DMWARN("Invalid geometry supplied."); + DMERR("Invalid geometry supplied."); goto out; } @@ -1069,13 +1069,13 @@ static int dev_set_geometry(struct file *filp, struct dm_ioctl *param, size_t pa indata + 1, indata + 2, indata + 3, &dummy); if (x != 4) { - DMWARN("Unable to interpret geometry settings."); + DMERR("Unable to interpret geometry settings."); goto out; } if (indata[0] > 65535 || indata[1] > 255 || indata[2] > 255 || indata[3] > ULONG_MAX) { - DMWARN("Geometry exceeds range limits."); + DMERR("Geometry exceeds range limits."); goto out; } @@ -1387,7 +1387,7 @@ static int populate_table(struct dm_table *table, char *target_params; if (!param->target_count) { - DMWARN("populate_table: no targets specified"); + DMERR("populate_table: no targets specified"); return -EINVAL; } @@ -1395,7 +1395,7 @@ static int populate_table(struct dm_table *table, r = next_target(spec, next, end, &spec, &target_params); if (r) { - DMWARN("unable to find target"); + DMERR("unable to find target"); return r; } @@ -1404,7 +1404,7 @@ static int populate_table(struct dm_table *table, (sector_t) spec->length, target_params); if (r) { - DMWARN("error adding target to table"); + DMERR("error adding target to table"); return r; } @@ -1451,8 +1451,8 @@ static int table_load(struct file *filp, struct dm_ioctl *param, size_t param_si if (immutable_target_type && (immutable_target_type != dm_table_get_immutable_target_type(t)) && !dm_table_get_wildcard_target(t)) { - DMWARN("can't replace immutable target type %s", - immutable_target_type->name); + DMERR("can't replace immutable target type %s", + immutable_target_type->name); r = -EINVAL; goto err_unlock_md_type; } @@ -1461,12 +1461,12 @@ static int table_load(struct file *filp, struct dm_ioctl *param, size_t param_si /* setup md->queue to reflect md's type (may block) */ r = dm_setup_md_queue(md, t); if (r) { - DMWARN("unable to set up device queue for new table."); + DMERR("unable to set up device queue for new table."); goto err_unlock_md_type; } } else if (!is_valid_type(dm_get_md_type(md), dm_table_get_type(t))) { - DMWARN("can't change device type (old=%u vs new=%u) after initial table load.", - dm_get_md_type(md), dm_table_get_type(t)); + DMERR("can't change device type (old=%u vs new=%u) after initial table load.", + dm_get_md_type(md), dm_table_get_type(t)); r = -EINVAL; goto err_unlock_md_type; } @@ -1477,7 +1477,7 @@ static int table_load(struct file *filp, struct dm_ioctl *param, size_t param_si down_write(&_hash_lock); hc = dm_get_mdptr(md); if (!hc || hc->md != md) { - DMWARN("device has been removed from the dev hash table."); + DMERR("device has been removed from the dev hash table."); up_write(&_hash_lock); r = -ENXIO; goto err_destroy_table; @@ -1686,19 +1686,19 @@ static int target_message(struct file *filp, struct dm_ioctl *param, size_t para if (tmsg < (struct dm_target_msg *) param->data || invalid_str(tmsg->message, (void *) param + param_size)) { - DMWARN("Invalid target message parameters."); + DMERR("Invalid target message parameters."); r = -EINVAL; goto out; } r = dm_split_args(&argc, &argv, tmsg->message); if (r) { - DMWARN("Failed to split target message parameters"); + DMERR("Failed to split target message parameters"); goto out; } if (!argc) { - DMWARN("Empty message received."); + DMERR("Empty message received."); r = -EINVAL; goto out_argv; } @@ -1718,12 +1718,12 @@ static int target_message(struct file *filp, struct dm_ioctl *param, size_t para ti = dm_table_find_target(table, tmsg->sector); if (!ti) { - DMWARN("Target message sector outside device."); + DMERR("Target message sector outside device."); r = -EINVAL; } else if (ti->type->message) r = ti->type->message(ti, argc, argv, result, maxlen); else { - DMWARN("Target type does not support messages"); + DMERR("Target type does not support messages"); r = -EINVAL; } @@ -1814,11 +1814,11 @@ static int check_version(unsigned int cmd, struct dm_ioctl __user *user) if ((DM_VERSION_MAJOR != version[0]) || (DM_VERSION_MINOR < version[1])) { - DMWARN("ioctl interface mismatch: " - "kernel(%u.%u.%u), user(%u.%u.%u), cmd(%d)", - DM_VERSION_MAJOR, DM_VERSION_MINOR, - DM_VERSION_PATCHLEVEL, - version[0], version[1], version[2], cmd); + DMERR("ioctl interface mismatch: " + "kernel(%u.%u.%u), user(%u.%u.%u), cmd(%d)", + DM_VERSION_MAJOR, DM_VERSION_MINOR, + DM_VERSION_PATCHLEVEL, + version[0], version[1], version[2], cmd); r = -EINVAL; } @@ -1927,11 +1927,11 @@ static int validate_params(uint cmd, struct dm_ioctl *param) if (cmd == DM_DEV_CREATE_CMD) { if (!*param->name) { - DMWARN("name not supplied when creating device"); + DMERR("name not supplied when creating device"); return -EINVAL; } } else if (*param->uuid && *param->name) { - DMWARN("only supply one of name or uuid, cmd(%u)", cmd); + DMERR("only supply one of name or uuid, cmd(%u)", cmd); return -EINVAL; } @@ -1978,7 +1978,7 @@ static int ctl_ioctl(struct file *file, uint command, struct dm_ioctl __user *us fn = lookup_ioctl(cmd, &ioctl_flags); if (!fn) { - DMWARN("dm_ctl_ioctl: unknown command 0x%x", command); + DMERR("dm_ctl_ioctl: unknown command 0x%x", command); return -ENOTTY; } @@ -2203,7 +2203,7 @@ int __init dm_early_create(struct dm_ioctl *dmi, (sector_t) spec_array[i]->length, target_params_array[i]); if (r) { - DMWARN("error adding target to table"); + DMERR("error adding target to table"); goto err_destroy_table; } } @@ -2216,7 +2216,7 @@ int __init dm_early_create(struct dm_ioctl *dmi, /* setup md->queue to reflect md's type (may block) */ r = dm_setup_md_queue(md, t); if (r) { - DMWARN("unable to set up device queue for new table."); + DMERR("unable to set up device queue for new table."); goto err_destroy_table; } diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index c640be453313..54263679a7b1 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -2529,7 +2529,7 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs) * of the "sync" directive. * * With reshaping capability added, we must ensure that - * that the "sync" directive is disallowed during the reshape. + * the "sync" directive is disallowed during the reshape. */ if (test_bit(__CTR_FLAG_SYNC, &rs->ctr_flags)) continue; @@ -2590,7 +2590,7 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs) /* * Adjust data_offset and new_data_offset on all disk members of @rs - * for out of place reshaping if requested by contructor + * for out of place reshaping if requested by constructor * * We need free space at the beginning of each raid disk for forward * and at the end for backward reshapes which userspace has to provide diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 3001b10a3fbf..a41209a43506 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -238,7 +238,7 @@ static void dm_done(struct request *clone, blk_status_t error, bool mapped) dm_requeue_original_request(tio, true); break; default: - DMWARN("unimplemented target endio return value: %d", r); + DMCRIT("unimplemented target endio return value: %d", r); BUG(); } } @@ -409,7 +409,7 @@ static int map_request(struct dm_rq_target_io *tio) dm_kill_unmapped_request(rq, BLK_STS_IOERR); break; default: - DMWARN("unimplemented target map return value: %d", r); + DMCRIT("unimplemented target map return value: %d", r); BUG(); } diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c index 8326f9fe0e91..f105a71915ab 100644 --- a/drivers/md/dm-stats.c +++ b/drivers/md/dm-stats.c @@ -1220,7 +1220,7 @@ int dm_stats_message(struct mapped_device *md, unsigned argc, char **argv, return 2; /* this wasn't a stats message */ if (r == -EINVAL) - DMWARN("Invalid parameters for message %s", argv[0]); + DMCRIT("Invalid parameters for message %s", argv[0]); return r; } diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index d8034ff0cb24..078da18bb86d 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -234,12 +234,12 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, return 0; if ((start >= dev_size) || (start + len > dev_size)) { - DMWARN("%s: %pg too small for target: " - "start=%llu, len=%llu, dev_size=%llu", - dm_device_name(ti->table->md), bdev, - (unsigned long long)start, - (unsigned long long)len, - (unsigned long long)dev_size); + DMERR("%s: %pg too small for target: " + "start=%llu, len=%llu, dev_size=%llu", + dm_device_name(ti->table->md), bdev, + (unsigned long long)start, + (unsigned long long)len, + (unsigned long long)dev_size); return 1; } @@ -251,10 +251,10 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, unsigned int zone_sectors = bdev_zone_sectors(bdev); if (start & (zone_sectors - 1)) { - DMWARN("%s: start=%llu not aligned to h/w zone size %u of %pg", - dm_device_name(ti->table->md), - (unsigned long long)start, - zone_sectors, bdev); + DMERR("%s: start=%llu not aligned to h/w zone size %u of %pg", + dm_device_name(ti->table->md), + (unsigned long long)start, + zone_sectors, bdev); return 1; } @@ -268,10 +268,10 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, * the sector range. */ if (len & (zone_sectors - 1)) { - DMWARN("%s: len=%llu not aligned to h/w zone size %u of %pg", - dm_device_name(ti->table->md), - (unsigned long long)len, - zone_sectors, bdev); + DMERR("%s: len=%llu not aligned to h/w zone size %u of %pg", + dm_device_name(ti->table->md), + (unsigned long long)len, + zone_sectors, bdev); return 1; } } @@ -280,20 +280,20 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, return 0; if (start & (logical_block_size_sectors - 1)) { - DMWARN("%s: start=%llu not aligned to h/w " - "logical block size %u of %pg", - dm_device_name(ti->table->md), - (unsigned long long)start, - limits->logical_block_size, bdev); + DMERR("%s: start=%llu not aligned to h/w " + "logical block size %u of %pg", + dm_device_name(ti->table->md), + (unsigned long long)start, + limits->logical_block_size, bdev); return 1; } if (len & (logical_block_size_sectors - 1)) { - DMWARN("%s: len=%llu not aligned to h/w " - "logical block size %u of %pg", - dm_device_name(ti->table->md), - (unsigned long long)len, - limits->logical_block_size, bdev); + DMERR("%s: len=%llu not aligned to h/w " + "logical block size %u of %pg", + dm_device_name(ti->table->md), + (unsigned long long)len, + limits->logical_block_size, bdev); return 1; } @@ -434,8 +434,8 @@ void dm_put_device(struct dm_target *ti, struct dm_dev *d) } } if (!found) { - DMWARN("%s: device %s not in table devices list", - dm_device_name(ti->table->md), d->name); + DMERR("%s: device %s not in table devices list", + dm_device_name(ti->table->md), d->name); return; } if (refcount_dec_and_test(&dd->count)) { @@ -618,12 +618,12 @@ static int validate_hardware_logical_block_alignment(struct dm_table *t, } if (remaining) { - DMWARN("%s: table line %u (start sect %llu len %llu) " - "not aligned to h/w logical block size %u", - dm_device_name(t->md), i, - (unsigned long long) ti->begin, - (unsigned long long) ti->len, - limits->logical_block_size); + DMERR("%s: table line %u (start sect %llu len %llu) " + "not aligned to h/w logical block size %u", + dm_device_name(t->md), i, + (unsigned long long) ti->begin, + (unsigned long long) ti->len, + limits->logical_block_size); return -EINVAL; } @@ -1008,7 +1008,7 @@ static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device * struct dm_md_mempools *pools; if (unlikely(type == DM_TYPE_NONE)) { - DMWARN("no table type is set, can't allocate mempools"); + DMERR("no table type is set, can't allocate mempools"); return -EINVAL; } @@ -1112,7 +1112,7 @@ static bool integrity_profile_exists(struct gendisk *disk) * Get a disk whose integrity profile reflects the table's profile. * Returns NULL if integrity support was inconsistent or unavailable. */ -static struct gendisk * dm_table_get_integrity_disk(struct dm_table *t) +static struct gendisk *dm_table_get_integrity_disk(struct dm_table *t) { struct list_head *devices = dm_table_get_devices(t); struct dm_dev_internal *dd = NULL; @@ -1185,10 +1185,10 @@ static int dm_table_register_integrity(struct dm_table *t) * profile the new profile should not conflict. */ if (blk_integrity_compare(dm_disk(md), template_disk) < 0) { - DMWARN("%s: conflict with existing integrity profile: " - "%s profile mismatch", - dm_device_name(t->md), - template_disk->disk_name); + DMERR("%s: conflict with existing integrity profile: " + "%s profile mismatch", + dm_device_name(t->md), + template_disk->disk_name); return 1; } @@ -1327,7 +1327,7 @@ static int dm_table_construct_crypto_profile(struct dm_table *t) if (t->md->queue && !blk_crypto_has_capabilities(profile, t->md->queue->crypto_profile)) { - DMWARN("Inline encryption capabilities of new DM table were more restrictive than the old table's. This is not supported!"); + DMERR("Inline encryption capabilities of new DM table were more restrictive than the old table's. This is not supported!"); dm_destroy_crypto_profile(profile); return -EINVAL; } diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 8a00cc42e498..ccf5b852fbf7 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -1401,14 +1401,16 @@ static int verity_ctr(struct dm_target *ti, unsigned argc, char **argv) /* WQ_UNBOUND greatly improves performance when running on ramdisk */ wq_flags = WQ_MEM_RECLAIM | WQ_UNBOUND; - if (v->use_tasklet) { - /* - * Allow verify_wq to preempt softirq since verification in - * tasklet will fall-back to using it for error handling - * (or if the bufio cache doesn't have required hashes). - */ - wq_flags |= WQ_HIGHPRI; - } + /* + * Using WQ_HIGHPRI improves throughput and completion latency by + * reducing wait times when reading from a dm-verity device. + * + * Also as required for the "try_verify_in_tasklet" feature: WQ_HIGHPRI + * allows verify_wq to preempt softirq since verification in tasklet + * will fall-back to using it for error handling (or if the bufio cache + * doesn't have required hashes). + */ + wq_flags |= WQ_HIGHPRI; v->verify_wq = alloc_workqueue("kverityd", wq_flags, num_online_cpus()); if (!v->verify_wq) { ti->error = "Cannot allocate workqueue"; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 60549b65c799..95a1ee3d314e 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -864,7 +864,7 @@ int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo) sector_t sz = (sector_t)geo->cylinders * geo->heads * geo->sectors; if (geo->start > sz) { - DMWARN("Start sector is beyond the geometry limits."); + DMERR("Start sector is beyond the geometry limits."); return -EINVAL; } @@ -1149,7 +1149,7 @@ static void clone_endio(struct bio *bio) /* The target will handle the io */ return; default: - DMWARN("unimplemented target endio return value: %d", r); + DMCRIT("unimplemented target endio return value: %d", r); BUG(); } } @@ -1455,7 +1455,7 @@ static void __map_bio(struct bio *clone) dm_io_dec_pending(io, BLK_STS_DM_REQUEUE); break; default: - DMWARN("unimplemented target map return value: %d", r); + DMCRIT("unimplemented target map return value: %d", r); BUG(); } } @@ -2005,7 +2005,7 @@ static struct mapped_device *alloc_dev(int minor) md = kvzalloc_node(sizeof(*md), GFP_KERNEL, numa_node_id); if (!md) { - DMWARN("unable to allocate device, out of memory."); + DMERR("unable to allocate device, out of memory."); return NULL; } @@ -2065,7 +2065,6 @@ static struct mapped_device *alloc_dev(int minor) md->disk->minors = 1; md->disk->flags |= GENHD_FL_NO_PART; md->disk->fops = &dm_blk_dops; - md->disk->queue = md->queue; md->disk->private_data = md; sprintf(md->disk->disk_name, "dm-%d", minor); diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c index 5669c92c93f7..c5c3b4e92f28 100644 --- a/drivers/net/dsa/qca/qca8k-8xxx.c +++ b/drivers/net/dsa/qca/qca8k-8xxx.c @@ -137,27 +137,42 @@ static void qca8k_rw_reg_ack_handler(struct dsa_switch *ds, struct sk_buff *skb) struct qca8k_mgmt_eth_data *mgmt_eth_data; struct qca8k_priv *priv = ds->priv; struct qca_mgmt_ethhdr *mgmt_ethhdr; + u32 command; u8 len, cmd; + int i; mgmt_ethhdr = (struct qca_mgmt_ethhdr *)skb_mac_header(skb); mgmt_eth_data = &priv->mgmt_eth_data; - cmd = FIELD_GET(QCA_HDR_MGMT_CMD, mgmt_ethhdr->command); - len = FIELD_GET(QCA_HDR_MGMT_LENGTH, mgmt_ethhdr->command); + command = get_unaligned_le32(&mgmt_ethhdr->command); + cmd = FIELD_GET(QCA_HDR_MGMT_CMD, command); + len = FIELD_GET(QCA_HDR_MGMT_LENGTH, command); /* Make sure the seq match the requested packet */ - if (mgmt_ethhdr->seq == mgmt_eth_data->seq) + if (get_unaligned_le32(&mgmt_ethhdr->seq) == mgmt_eth_data->seq) mgmt_eth_data->ack = true; if (cmd == MDIO_READ) { - mgmt_eth_data->data[0] = mgmt_ethhdr->mdio_data; + u32 *val = mgmt_eth_data->data; + + *val = get_unaligned_le32(&mgmt_ethhdr->mdio_data); /* Get the rest of the 12 byte of data. * The read/write function will extract the requested data. */ - if (len > QCA_HDR_MGMT_DATA1_LEN) - memcpy(mgmt_eth_data->data + 1, skb->data, - QCA_HDR_MGMT_DATA2_LEN); + if (len > QCA_HDR_MGMT_DATA1_LEN) { + __le32 *data2 = (__le32 *)skb->data; + int data_len = min_t(int, QCA_HDR_MGMT_DATA2_LEN, + len - QCA_HDR_MGMT_DATA1_LEN); + + val++; + + for (i = sizeof(u32); i <= data_len; i += sizeof(u32)) { + *val = get_unaligned_le32(data2); + val++; + data2++; + } + } } complete(&mgmt_eth_data->rw_done); @@ -169,8 +184,10 @@ static struct sk_buff *qca8k_alloc_mdio_header(enum mdio_cmd cmd, u32 reg, u32 * struct qca_mgmt_ethhdr *mgmt_ethhdr; unsigned int real_len; struct sk_buff *skb; - u32 *data2; + __le32 *data2; + u32 command; u16 hdr; + int i; skb = dev_alloc_skb(QCA_HDR_MGMT_PKT_LEN); if (!skb) @@ -199,20 +216,32 @@ static struct sk_buff *qca8k_alloc_mdio_header(enum mdio_cmd cmd, u32 reg, u32 * hdr |= FIELD_PREP(QCA_HDR_XMIT_DP_BIT, BIT(0)); hdr |= FIELD_PREP(QCA_HDR_XMIT_CONTROL, QCA_HDR_XMIT_TYPE_RW_REG); - mgmt_ethhdr->command = FIELD_PREP(QCA_HDR_MGMT_ADDR, reg); - mgmt_ethhdr->command |= FIELD_PREP(QCA_HDR_MGMT_LENGTH, real_len); - mgmt_ethhdr->command |= FIELD_PREP(QCA_HDR_MGMT_CMD, cmd); - mgmt_ethhdr->command |= FIELD_PREP(QCA_HDR_MGMT_CHECK_CODE, + command = FIELD_PREP(QCA_HDR_MGMT_ADDR, reg); + command |= FIELD_PREP(QCA_HDR_MGMT_LENGTH, real_len); + command |= FIELD_PREP(QCA_HDR_MGMT_CMD, cmd); + command |= FIELD_PREP(QCA_HDR_MGMT_CHECK_CODE, QCA_HDR_MGMT_CHECK_CODE_VAL); + put_unaligned_le32(command, &mgmt_ethhdr->command); + if (cmd == MDIO_WRITE) - mgmt_ethhdr->mdio_data = *val; + put_unaligned_le32(*val, &mgmt_ethhdr->mdio_data); mgmt_ethhdr->hdr = htons(hdr); data2 = skb_put_zero(skb, QCA_HDR_MGMT_DATA2_LEN + QCA_HDR_MGMT_PADDING_LEN); - if (cmd == MDIO_WRITE && len > QCA_HDR_MGMT_DATA1_LEN) - memcpy(data2, val + 1, len - QCA_HDR_MGMT_DATA1_LEN); + if (cmd == MDIO_WRITE && len > QCA_HDR_MGMT_DATA1_LEN) { + int data_len = min_t(int, QCA_HDR_MGMT_DATA2_LEN, + len - QCA_HDR_MGMT_DATA1_LEN); + + val++; + + for (i = sizeof(u32); i <= data_len; i += sizeof(u32)) { + put_unaligned_le32(*val, data2); + data2++; + val++; + } + } return skb; } @@ -220,9 +249,11 @@ static struct sk_buff *qca8k_alloc_mdio_header(enum mdio_cmd cmd, u32 reg, u32 * static void qca8k_mdio_header_fill_seq_num(struct sk_buff *skb, u32 seq_num) { struct qca_mgmt_ethhdr *mgmt_ethhdr; + u32 seq; + seq = FIELD_PREP(QCA_HDR_MGMT_SEQ_NUM, seq_num); mgmt_ethhdr = (struct qca_mgmt_ethhdr *)skb->data; - mgmt_ethhdr->seq = FIELD_PREP(QCA_HDR_MGMT_SEQ_NUM, seq_num); + put_unaligned_le32(seq, &mgmt_ethhdr->seq); } static int qca8k_read_eth(struct qca8k_priv *priv, u32 reg, u32 *val, int len) @@ -1487,9 +1518,9 @@ static void qca8k_mib_autocast_handler(struct dsa_switch *ds, struct sk_buff *sk struct qca8k_priv *priv = ds->priv; const struct qca8k_mib_desc *mib; struct mib_ethhdr *mib_ethhdr; - int i, mib_len, offset = 0; - u64 *data; + __le32 *data2; u8 port; + int i; mib_ethhdr = (struct mib_ethhdr *)skb_mac_header(skb); mib_eth_data = &priv->mib_eth_data; @@ -1501,28 +1532,24 @@ static void qca8k_mib_autocast_handler(struct dsa_switch *ds, struct sk_buff *sk if (port != mib_eth_data->req_port) goto exit; - data = mib_eth_data->data; + data2 = (__le32 *)skb->data; for (i = 0; i < priv->info->mib_count; i++) { mib = &ar8327_mib[i]; /* First 3 mib are present in the skb head */ if (i < 3) { - data[i] = mib_ethhdr->data[i]; + mib_eth_data->data[i] = get_unaligned_le32(mib_ethhdr->data + i); continue; } - mib_len = sizeof(uint32_t); - /* Some mib are 64 bit wide */ if (mib->size == 2) - mib_len = sizeof(uint64_t); - - /* Copy the mib value from packet to the */ - memcpy(data + i, skb->data + offset, mib_len); + mib_eth_data->data[i] = get_unaligned_le64((__le64 *)data2); + else + mib_eth_data->data[i] = get_unaligned_le32(data2); - /* Set the offset for the next mib */ - offset += mib_len; + data2 += mib->size; } exit: diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index a36803e79e92..8a6f788f6294 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -613,6 +613,7 @@ static int bnxt_dl_reload_up(struct devlink *dl, enum devlink_reload_action acti static bool bnxt_nvm_test(struct bnxt *bp, struct netlink_ext_ack *extack) { + bool rc = false; u32 datalen; u16 index; u8 *buf; @@ -632,20 +633,20 @@ static bool bnxt_nvm_test(struct bnxt *bp, struct netlink_ext_ack *extack) if (bnxt_get_nvram_item(bp->dev, index, 0, datalen, buf)) { NL_SET_ERR_MSG_MOD(extack, "nvm test vpd read error"); - goto err; + goto done; } if (bnxt_flash_nvram(bp->dev, BNX_DIR_TYPE_VPD, BNX_DIR_ORDINAL_FIRST, BNX_DIR_EXT_NONE, 0, 0, buf, datalen)) { NL_SET_ERR_MSG_MOD(extack, "nvm test vpd write error"); - goto err; + goto done; } - return true; + rc = true; -err: +done: kfree(buf); - return false; + return rc; } static bool bnxt_dl_selftest_check(struct devlink *dl, unsigned int id, diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c index 00fafc0f8512..430eccea8e5e 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.c +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -419,8 +419,10 @@ int hnae_ae_register(struct hnae_ae_dev *hdev, struct module *owner) hdev->cls_dev.release = hnae_release; (void)dev_set_name(&hdev->cls_dev, "hnae%d", hdev->id); ret = device_register(&hdev->cls_dev); - if (ret) + if (ret) { + put_device(&hdev->cls_dev); return ret; + } __module_get(THIS_MODULE); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 7e75706f76db..87f36d1ce800 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -2183,9 +2183,6 @@ static int i40e_set_ringparam(struct net_device *netdev, err = i40e_setup_rx_descriptors(&rx_rings[i]); if (err) goto rx_unwind; - err = i40e_alloc_rx_bi(&rx_rings[i]); - if (err) - goto rx_unwind; /* now allocate the Rx buffers to make sure the OS * has enough memory, any failure here means abort diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 2c07fa8ecfc8..b5dcd15ced36 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3566,12 +3566,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) if (ring->vsi->type == I40E_VSI_MAIN) xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); - kfree(ring->rx_bi); ring->xsk_pool = i40e_xsk_pool(ring); if (ring->xsk_pool) { - ret = i40e_alloc_rx_bi_zc(ring); - if (ret) - return ret; ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool); /* For AF_XDP ZC, we disallow packets to span on @@ -3589,9 +3585,6 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) ring->queue_index); } else { - ret = i40e_alloc_rx_bi(ring); - if (ret) - return ret; ring->rx_buf_len = vsi->rx_buf_len; if (ring->vsi->type == I40E_VSI_MAIN) { ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, @@ -13296,6 +13289,14 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog, i40e_reset_and_rebuild(pf, true, true); } + if (!i40e_enabled_xdp_vsi(vsi) && prog) { + if (i40e_realloc_rx_bi_zc(vsi, true)) + return -ENOMEM; + } else if (i40e_enabled_xdp_vsi(vsi) && !prog) { + if (i40e_realloc_rx_bi_zc(vsi, false)) + return -ENOMEM; + } + for (i = 0; i < vsi->num_queue_pairs; i++) WRITE_ONCE(vsi->rx_rings[i]->xdp_prog, vsi->xdp_prog); @@ -13528,6 +13529,7 @@ int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair) i40e_queue_pair_disable_irq(vsi, queue_pair); err = i40e_queue_pair_toggle_rings(vsi, queue_pair, false /* off */); + i40e_clean_rx_ring(vsi->rx_rings[queue_pair]); i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */); i40e_queue_pair_clean_rings(vsi, queue_pair); i40e_queue_pair_reset_stats(vsi, queue_pair); diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 69e67eb6aea7..b97c95f89fa0 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1457,14 +1457,6 @@ err: return -ENOMEM; } -int i40e_alloc_rx_bi(struct i40e_ring *rx_ring) -{ - unsigned long sz = sizeof(*rx_ring->rx_bi) * rx_ring->count; - - rx_ring->rx_bi = kzalloc(sz, GFP_KERNEL); - return rx_ring->rx_bi ? 0 : -ENOMEM; -} - static void i40e_clear_rx_bi(struct i40e_ring *rx_ring) { memset(rx_ring->rx_bi, 0, sizeof(*rx_ring->rx_bi) * rx_ring->count); @@ -1593,6 +1585,11 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring) rx_ring->xdp_prog = rx_ring->vsi->xdp_prog; + rx_ring->rx_bi = + kcalloc(rx_ring->count, sizeof(*rx_ring->rx_bi), GFP_KERNEL); + if (!rx_ring->rx_bi) + return -ENOMEM; + return 0; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 41f86e9535a0..768290dc6f48 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -469,7 +469,6 @@ int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size); bool __i40e_chk_linearize(struct sk_buff *skb); int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags); -int i40e_alloc_rx_bi(struct i40e_ring *rx_ring); /** * i40e_get_head - Retrieve head from head writeback diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 6d4009e0cbd6..cd7b52fb6b46 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -10,14 +10,6 @@ #include "i40e_txrx_common.h" #include "i40e_xsk.h" -int i40e_alloc_rx_bi_zc(struct i40e_ring *rx_ring) -{ - unsigned long sz = sizeof(*rx_ring->rx_bi_zc) * rx_ring->count; - - rx_ring->rx_bi_zc = kzalloc(sz, GFP_KERNEL); - return rx_ring->rx_bi_zc ? 0 : -ENOMEM; -} - void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring) { memset(rx_ring->rx_bi_zc, 0, @@ -30,6 +22,58 @@ static struct xdp_buff **i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx) } /** + * i40e_realloc_rx_xdp_bi - reallocate SW ring for either XSK or normal buffer + * @rx_ring: Current rx ring + * @pool_present: is pool for XSK present + * + * Try allocating memory and return ENOMEM, if failed to allocate. + * If allocation was successful, substitute buffer with allocated one. + * Returns 0 on success, negative on failure + */ +static int i40e_realloc_rx_xdp_bi(struct i40e_ring *rx_ring, bool pool_present) +{ + size_t elem_size = pool_present ? sizeof(*rx_ring->rx_bi_zc) : + sizeof(*rx_ring->rx_bi); + void *sw_ring = kcalloc(rx_ring->count, elem_size, GFP_KERNEL); + + if (!sw_ring) + return -ENOMEM; + + if (pool_present) { + kfree(rx_ring->rx_bi); + rx_ring->rx_bi = NULL; + rx_ring->rx_bi_zc = sw_ring; + } else { + kfree(rx_ring->rx_bi_zc); + rx_ring->rx_bi_zc = NULL; + rx_ring->rx_bi = sw_ring; + } + return 0; +} + +/** + * i40e_realloc_rx_bi_zc - reallocate rx SW rings + * @vsi: Current VSI + * @zc: is zero copy set + * + * Reallocate buffer for rx_rings that might be used by XSK. + * XDP requires more memory, than rx_buf provides. + * Returns 0 on success, negative on failure + */ +int i40e_realloc_rx_bi_zc(struct i40e_vsi *vsi, bool zc) +{ + struct i40e_ring *rx_ring; + unsigned long q; + + for_each_set_bit(q, vsi->af_xdp_zc_qps, vsi->alloc_queue_pairs) { + rx_ring = vsi->rx_rings[q]; + if (i40e_realloc_rx_xdp_bi(rx_ring, zc)) + return -ENOMEM; + } + return 0; +} + +/** * i40e_xsk_pool_enable - Enable/associate an AF_XDP buffer pool to a * certain ring/qid * @vsi: Current VSI @@ -69,6 +113,10 @@ static int i40e_xsk_pool_enable(struct i40e_vsi *vsi, if (err) return err; + err = i40e_realloc_rx_xdp_bi(vsi->rx_rings[qid], true); + if (err) + return err; + err = i40e_queue_pair_enable(vsi, qid); if (err) return err; @@ -113,6 +161,9 @@ static int i40e_xsk_pool_disable(struct i40e_vsi *vsi, u16 qid) xsk_pool_dma_unmap(pool, I40E_RX_DMA_ATTR); if (if_running) { + err = i40e_realloc_rx_xdp_bi(vsi->rx_rings[qid], false); + if (err) + return err; err = i40e_queue_pair_enable(vsi, qid); if (err) return err; diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h index bb962987f300..821df248f8be 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h @@ -32,7 +32,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget); bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, struct i40e_ring *tx_ring); int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags); -int i40e_alloc_rx_bi_zc(struct i40e_ring *rx_ring); +int i40e_realloc_rx_bi_zc(struct i40e_vsi *vsi, bool zc); void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring); #endif /* _I40E_XSK_H_ */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c index 9809f551fc2e..9ec5f38d38a8 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c @@ -815,6 +815,7 @@ free_flowid: cn10k_mcs_free_rsrc(pfvf, MCS_TX, MCS_RSRC_TYPE_FLOWID, txsc->hw_flow_id, false); fail: + kfree(txsc); return ERR_PTR(ret); } @@ -870,6 +871,7 @@ free_flowid: cn10k_mcs_free_rsrc(pfvf, MCS_RX, MCS_RSRC_TYPE_FLOWID, rxsc->hw_flow_id, false); fail: + kfree(rxsc); return ERR_PTR(ret); } diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 4fba7cb0144b..7cd381530aa4 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -4060,19 +4060,23 @@ static int mtk_probe(struct platform_device *pdev) eth->irq[i] = platform_get_irq(pdev, i); if (eth->irq[i] < 0) { dev_err(&pdev->dev, "no IRQ%d resource found\n", i); - return -ENXIO; + err = -ENXIO; + goto err_wed_exit; } } for (i = 0; i < ARRAY_SIZE(eth->clks); i++) { eth->clks[i] = devm_clk_get(eth->dev, mtk_clks_source_name[i]); if (IS_ERR(eth->clks[i])) { - if (PTR_ERR(eth->clks[i]) == -EPROBE_DEFER) - return -EPROBE_DEFER; + if (PTR_ERR(eth->clks[i]) == -EPROBE_DEFER) { + err = -EPROBE_DEFER; + goto err_wed_exit; + } if (eth->soc->required_clks & BIT(i)) { dev_err(&pdev->dev, "clock %s not found\n", mtk_clks_source_name[i]); - return -EINVAL; + err = -EINVAL; + goto err_wed_exit; } eth->clks[i] = NULL; } @@ -4083,7 +4087,7 @@ static int mtk_probe(struct platform_device *pdev) err = mtk_hw_init(eth); if (err) - return err; + goto err_wed_exit; eth->hwlro = MTK_HAS_CAPS(eth->soc->caps, MTK_HWLRO); @@ -4179,6 +4183,8 @@ err_free_dev: mtk_free_dev(eth); err_deinit_hw: mtk_hw_deinit(eth); +err_wed_exit: + mtk_wed_exit(); return err; } @@ -4198,6 +4204,7 @@ static int mtk_remove(struct platform_device *pdev) phylink_disconnect_phy(mac->phylink); } + mtk_wed_exit(); mtk_hw_deinit(eth); netif_napi_del(ð->tx_napi); diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c index ae00e572390d..2d8ca99f2467 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe.c @@ -397,12 +397,6 @@ int mtk_foe_entry_set_wdma(struct mtk_eth *eth, struct mtk_foe_entry *entry, return 0; } -static inline bool mtk_foe_entry_usable(struct mtk_foe_entry *entry) -{ - return !(entry->ib1 & MTK_FOE_IB1_STATIC) && - FIELD_GET(MTK_FOE_IB1_STATE, entry->ib1) != MTK_FOE_STATE_BIND; -} - static bool mtk_flow_entry_match(struct mtk_eth *eth, struct mtk_flow_entry *entry, struct mtk_foe_entry *data) diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index 099b6e0df619..65e01bf4b4d2 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -1072,16 +1072,16 @@ void mtk_wed_add_hw(struct device_node *np, struct mtk_eth *eth, pdev = of_find_device_by_node(np); if (!pdev) - return; + goto err_of_node_put; get_device(&pdev->dev); irq = platform_get_irq(pdev, 0); if (irq < 0) - return; + goto err_put_device; regs = syscon_regmap_lookup_by_phandle(np, NULL); if (IS_ERR(regs)) - return; + goto err_put_device; rcu_assign_pointer(mtk_soc_wed_ops, &wed_ops); @@ -1124,8 +1124,16 @@ void mtk_wed_add_hw(struct device_node *np, struct mtk_eth *eth, hw_list[index] = hw; + mutex_unlock(&hw_lock); + + return; + unlock: mutex_unlock(&hw_lock); +err_put_device: + put_device(&pdev->dev); +err_of_node_put: + of_node_put(np); } void mtk_wed_exit(void) @@ -1146,6 +1154,7 @@ void mtk_wed_exit(void) hw_list[i] = NULL; debugfs_remove(hw->debugfs_dir); put_device(hw->dev); + of_node_put(hw->node); kfree(hw); } } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 5d58fd99be3c..19d4848df17d 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -2817,11 +2817,15 @@ err_out: * than the full array, but leave the qcq shells in place */ for (i = lif->nxqs; i < lif->ionic->ntxqs_per_lif; i++) { - lif->txqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; - ionic_qcq_free(lif, lif->txqcqs[i]); + if (lif->txqcqs && lif->txqcqs[i]) { + lif->txqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; + ionic_qcq_free(lif, lif->txqcqs[i]); + } - lif->rxqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; - ionic_qcq_free(lif, lif->rxqcqs[i]); + if (lif->rxqcqs && lif->rxqcqs[i]) { + lif->rxqcqs[i]->flags &= ~IONIC_QCQ_F_INTR; + ionic_qcq_free(lif, lif->rxqcqs[i]); + } } if (err) diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index d1e1aa19a68e..7022fb2005a2 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -3277,6 +3277,30 @@ static int efx_ef10_set_mac_address(struct efx_nic *efx) bool was_enabled = efx->port_enabled; int rc; +#ifdef CONFIG_SFC_SRIOV + /* If this function is a VF and we have access to the parent PF, + * then use the PF control path to attempt to change the VF MAC address. + */ + if (efx->pci_dev->is_virtfn && efx->pci_dev->physfn) { + struct efx_nic *efx_pf = pci_get_drvdata(efx->pci_dev->physfn); + struct efx_ef10_nic_data *nic_data = efx->nic_data; + u8 mac[ETH_ALEN]; + + /* net_dev->dev_addr can be zeroed by efx_net_stop in + * efx_ef10_sriov_set_vf_mac, so pass in a copy. + */ + ether_addr_copy(mac, efx->net_dev->dev_addr); + + rc = efx_ef10_sriov_set_vf_mac(efx_pf, nic_data->vf_index, mac); + if (!rc) + return 0; + + netif_dbg(efx, drv, efx->net_dev, + "Updating VF mac via PF failed (%d), setting directly\n", + rc); + } +#endif + efx_device_detach_sync(efx); efx_net_stop(efx->net_dev); @@ -3297,40 +3321,6 @@ static int efx_ef10_set_mac_address(struct efx_nic *efx) efx_net_open(efx->net_dev); efx_device_attach_if_not_resetting(efx); -#ifdef CONFIG_SFC_SRIOV - if (efx->pci_dev->is_virtfn && efx->pci_dev->physfn) { - struct efx_ef10_nic_data *nic_data = efx->nic_data; - struct pci_dev *pci_dev_pf = efx->pci_dev->physfn; - - if (rc == -EPERM) { - struct efx_nic *efx_pf; - - /* Switch to PF and change MAC address on vport */ - efx_pf = pci_get_drvdata(pci_dev_pf); - - rc = efx_ef10_sriov_set_vf_mac(efx_pf, - nic_data->vf_index, - efx->net_dev->dev_addr); - } else if (!rc) { - struct efx_nic *efx_pf = pci_get_drvdata(pci_dev_pf); - struct efx_ef10_nic_data *nic_data = efx_pf->nic_data; - unsigned int i; - - /* MAC address successfully changed by VF (with MAC - * spoofing) so update the parent PF if possible. - */ - for (i = 0; i < efx_pf->vf_count; ++i) { - struct ef10_vf *vf = nic_data->vf + i; - - if (vf->efx == efx) { - ether_addr_copy(vf->mac, - efx->net_dev->dev_addr); - return 0; - } - } - } - } else -#endif if (rc == -EPERM) { netif_err(efx, drv, efx->net_dev, "Cannot change MAC address; use sfboot to enable" diff --git a/drivers/net/ethernet/sfc/filter.h b/drivers/net/ethernet/sfc/filter.h index be72e71da027..5f201a547e5b 100644 --- a/drivers/net/ethernet/sfc/filter.h +++ b/drivers/net/ethernet/sfc/filter.h @@ -162,9 +162,9 @@ struct efx_filter_spec { u32 priority:2; u32 flags:6; u32 dmaq_id:12; - u32 vport_id; u32 rss_context; - __be16 outer_vid __aligned(4); /* allow jhash2() of match values */ + u32 vport_id; + __be16 outer_vid; __be16 inner_vid; u8 loc_mac[ETH_ALEN]; u8 rem_mac[ETH_ALEN]; diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index 4826e6a7e4ce..9220afeddee8 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -660,17 +660,17 @@ bool efx_filter_spec_equal(const struct efx_filter_spec *left, (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_TX))) return false; - return memcmp(&left->outer_vid, &right->outer_vid, + return memcmp(&left->vport_id, &right->vport_id, sizeof(struct efx_filter_spec) - - offsetof(struct efx_filter_spec, outer_vid)) == 0; + offsetof(struct efx_filter_spec, vport_id)) == 0; } u32 efx_filter_spec_hash(const struct efx_filter_spec *spec) { - BUILD_BUG_ON(offsetof(struct efx_filter_spec, outer_vid) & 3); - return jhash2((const u32 *)&spec->outer_vid, + BUILD_BUG_ON(offsetof(struct efx_filter_spec, vport_id) & 3); + return jhash2((const u32 *)&spec->vport_id, (sizeof(struct efx_filter_spec) - - offsetof(struct efx_filter_spec, outer_vid)) / 4, + offsetof(struct efx_filter_spec, vport_id)) / 4, 0); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 65c96773c6d2..8273e6a175c8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1214,6 +1214,7 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) if (priv->plat->tx_queues_to_use > 1) priv->phylink_config.mac_capabilities &= ~(MAC_10HD | MAC_100HD | MAC_1000HD); + priv->phylink_config.mac_managed_pm = true; phylink = phylink_create(&priv->phylink_config, fwnode, mode, &stmmac_phylink_mac_ops); diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index 91f10f746dff..1c16548415cd 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -1328,7 +1328,7 @@ static int happy_meal_init(struct happy_meal *hp) void __iomem *erxregs = hp->erxregs; void __iomem *bregs = hp->bigmacregs; void __iomem *tregs = hp->tcvregs; - const char *bursts; + const char *bursts = "64"; u32 regtmp, rxcfg; /* If auto-negotiation timer is running, kill it. */ diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 11f767a20444..eea777ec2541 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -20,6 +20,7 @@ #include <linux/vmalloc.h> #include <linux/rtnetlink.h> #include <linux/ucs2_string.h> +#include <linux/string.h> #include "hyperv_net.h" #include "netvsc_trace.h" @@ -335,9 +336,10 @@ static void rndis_filter_receive_response(struct net_device *ndev, if (resp->msg_len <= sizeof(struct rndis_message) + RNDIS_EXT_LEN) { memcpy(&request->response_msg, resp, RNDIS_HEADER_SIZE + sizeof(*req_id)); - memcpy((void *)&request->response_msg + RNDIS_HEADER_SIZE + sizeof(*req_id), + unsafe_memcpy((void *)&request->response_msg + RNDIS_HEADER_SIZE + sizeof(*req_id), data + RNDIS_HEADER_SIZE + sizeof(*req_id), - resp->msg_len - RNDIS_HEADER_SIZE - sizeof(*req_id)); + resp->msg_len - RNDIS_HEADER_SIZE - sizeof(*req_id), + "request->response_msg is followed by a padding of RNDIS_EXT_LEN inside rndis_request"); if (request->request_msg.ndis_msg_type == RNDIS_MSG_QUERY && request->request_msg.msg. query_req.oid == RNDIS_OID_GEN_MEDIA_CONNECT_STATUS) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 8f8f73099de8..c5cfe8555199 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -361,7 +361,7 @@ static void macvlan_broadcast_enqueue(struct macvlan_port *port, } spin_unlock(&port->bc_queue.lock); - schedule_work(&port->bc_work); + queue_work(system_unbound_wq, &port->bc_work); if (err) goto free_nskb; diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index 8549e0e356c9..b60db8b6f477 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -254,8 +254,7 @@ static int dp83822_config_intr(struct phy_device *phydev) DP83822_EEE_ERROR_CHANGE_INT_EN); if (!dp83822->fx_enabled) - misr_status |= DP83822_MDI_XOVER_INT_EN | - DP83822_ANEG_ERR_INT_EN | + misr_status |= DP83822_ANEG_ERR_INT_EN | DP83822_WOL_PKT_INT_EN; err = phy_write(phydev, MII_DP83822_MISR2, misr_status); diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 6939563d3b7c..417527f8bbf5 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -853,6 +853,14 @@ static int dp83867_config_init(struct phy_device *phydev) else val &= ~DP83867_SGMII_TYPE; phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_SGMIICTL, val); + + /* This is a SW workaround for link instability if RX_CTRL is + * not strapped to mode 3 or 4 in HW. This is required for SGMII + * in addition to clearing bit 7, handled above. + */ + if (dp83867->rxctrl_strap_quirk) + phy_set_bits_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4, + BIT(8)); } val = phy_read(phydev, DP83867_CFG3); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 75464df191ef..6547b6cc6cbe 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1661,6 +1661,9 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy, if (phy_interrupt_is_valid(phy)) phy_request_interrupt(phy); + if (pl->config->mac_managed_pm) + phy->mac_managed_pm = true; + return 0; } diff --git a/drivers/net/wwan/wwan_hwsim.c b/drivers/net/wwan/wwan_hwsim.c index ff09a8cedf93..2397a903d8f5 100644 --- a/drivers/net/wwan/wwan_hwsim.c +++ b/drivers/net/wwan/wwan_hwsim.c @@ -311,7 +311,7 @@ err_unreg_dev: return ERR_PTR(err); err_free_dev: - kfree(dev); + put_device(&dev->dev); return ERR_PTR(err); } diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index dce3a16996b9..4ec18ceb2f21 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -138,6 +138,7 @@ struct share_check { u64 root_objectid; u64 inum; int share_count; + bool have_delayed_delete_refs; }; static inline int extent_is_shared(struct share_check *sc) @@ -820,16 +821,11 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, struct preftrees *preftrees, struct share_check *sc) { struct btrfs_delayed_ref_node *node; - struct btrfs_delayed_extent_op *extent_op = head->extent_op; struct btrfs_key key; - struct btrfs_key tmp_op_key; struct rb_node *n; int count; int ret = 0; - if (extent_op && extent_op->update_key) - btrfs_disk_key_to_cpu(&tmp_op_key, &extent_op->key); - spin_lock(&head->lock); for (n = rb_first_cached(&head->ref_tree); n; n = rb_next(n)) { node = rb_entry(n, struct btrfs_delayed_ref_node, @@ -855,10 +851,16 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, case BTRFS_TREE_BLOCK_REF_KEY: { /* NORMAL INDIRECT METADATA backref */ struct btrfs_delayed_tree_ref *ref; + struct btrfs_key *key_ptr = NULL; + + if (head->extent_op && head->extent_op->update_key) { + btrfs_disk_key_to_cpu(&key, &head->extent_op->key); + key_ptr = &key; + } ref = btrfs_delayed_node_to_tree_ref(node); ret = add_indirect_ref(fs_info, preftrees, ref->root, - &tmp_op_key, ref->level + 1, + key_ptr, ref->level + 1, node->bytenr, count, sc, GFP_ATOMIC); break; @@ -884,13 +886,22 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, key.offset = ref->offset; /* - * Found a inum that doesn't match our known inum, we - * know it's shared. + * If we have a share check context and a reference for + * another inode, we can't exit immediately. This is + * because even if this is a BTRFS_ADD_DELAYED_REF + * reference we may find next a BTRFS_DROP_DELAYED_REF + * which cancels out this ADD reference. + * + * If this is a DROP reference and there was no previous + * ADD reference, then we need to signal that when we + * process references from the extent tree (through + * add_inline_refs() and add_keyed_refs()), we should + * not exit early if we find a reference for another + * inode, because one of the delayed DROP references + * may cancel that reference in the extent tree. */ - if (sc && sc->inum && ref->objectid != sc->inum) { - ret = BACKREF_FOUND_SHARED; - goto out; - } + if (sc && count < 0) + sc->have_delayed_delete_refs = true; ret = add_indirect_ref(fs_info, preftrees, ref->root, &key, 0, node->bytenr, count, sc, @@ -920,7 +931,7 @@ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, } if (!ret) ret = extent_is_shared(sc); -out: + spin_unlock(&head->lock); return ret; } @@ -1023,7 +1034,8 @@ static int add_inline_refs(const struct btrfs_fs_info *fs_info, key.type = BTRFS_EXTENT_DATA_KEY; key.offset = btrfs_extent_data_ref_offset(leaf, dref); - if (sc && sc->inum && key.objectid != sc->inum) { + if (sc && sc->inum && key.objectid != sc->inum && + !sc->have_delayed_delete_refs) { ret = BACKREF_FOUND_SHARED; break; } @@ -1033,6 +1045,7 @@ static int add_inline_refs(const struct btrfs_fs_info *fs_info, ret = add_indirect_ref(fs_info, preftrees, root, &key, 0, bytenr, count, sc, GFP_NOFS); + break; } default: @@ -1122,7 +1135,8 @@ static int add_keyed_refs(struct btrfs_root *extent_root, key.type = BTRFS_EXTENT_DATA_KEY; key.offset = btrfs_extent_data_ref_offset(leaf, dref); - if (sc && sc->inum && key.objectid != sc->inum) { + if (sc && sc->inum && key.objectid != sc->inum && + !sc->have_delayed_delete_refs) { ret = BACKREF_FOUND_SHARED; break; } @@ -1522,6 +1536,9 @@ static bool lookup_backref_shared_cache(struct btrfs_backref_shared_cache *cache { struct btrfs_backref_shared_cache_entry *entry; + if (!cache->use_cache) + return false; + if (WARN_ON_ONCE(level >= BTRFS_MAX_LEVEL)) return false; @@ -1557,6 +1574,19 @@ static bool lookup_backref_shared_cache(struct btrfs_backref_shared_cache *cache return false; *is_shared = entry->is_shared; + /* + * If the node at this level is shared, than all nodes below are also + * shared. Currently some of the nodes below may be marked as not shared + * because we have just switched from one leaf to another, and switched + * also other nodes above the leaf and below the current level, so mark + * them as shared. + */ + if (*is_shared) { + for (int i = 0; i < level; i++) { + cache->entries[i].is_shared = true; + cache->entries[i].gen = entry->gen; + } + } return true; } @@ -1573,6 +1603,9 @@ static void store_backref_shared_cache(struct btrfs_backref_shared_cache *cache, struct btrfs_backref_shared_cache_entry *entry; u64 gen; + if (!cache->use_cache) + return; + if (WARN_ON_ONCE(level >= BTRFS_MAX_LEVEL)) return; @@ -1648,6 +1681,7 @@ int btrfs_is_data_extent_shared(struct btrfs_root *root, u64 inum, u64 bytenr, .root_objectid = root->root_key.objectid, .inum = inum, .share_count = 0, + .have_delayed_delete_refs = false, }; int level; @@ -1669,6 +1703,7 @@ int btrfs_is_data_extent_shared(struct btrfs_root *root, u64 inum, u64 bytenr, /* -1 means we are in the bytenr of the data extent. */ level = -1; ULIST_ITER_INIT(&uiter); + cache->use_cache = true; while (1) { bool is_shared; bool cached; @@ -1698,6 +1733,24 @@ int btrfs_is_data_extent_shared(struct btrfs_root *root, u64 inum, u64 bytenr, extent_gen > btrfs_root_last_snapshot(&root->root_item)) break; + /* + * If our data extent was not directly shared (without multiple + * reference items), than it might have a single reference item + * with a count > 1 for the same offset, which means there are 2 + * (or more) file extent items that point to the data extent - + * this happens when a file extent item needs to be split and + * then one item gets moved to another leaf due to a b+tree leaf + * split when inserting some item. In this case the file extent + * items may be located in different leaves and therefore some + * of the leaves may be referenced through shared subtrees while + * others are not. Since our extent buffer cache only works for + * a single path (by far the most common case and simpler to + * deal with), we can not use it if we have multiple leaves + * (which implies multiple paths). + */ + if (level == -1 && tmp->nnodes > 1) + cache->use_cache = false; + if (level >= 0) store_backref_shared_cache(cache, root, bytenr, level, false); @@ -1713,6 +1766,7 @@ int btrfs_is_data_extent_shared(struct btrfs_root *root, u64 inum, u64 bytenr, break; } shared.share_count = 0; + shared.have_delayed_delete_refs = false; cond_resched(); } diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h index 52ae6957b414..8e69584d538d 100644 --- a/fs/btrfs/backref.h +++ b/fs/btrfs/backref.h @@ -29,6 +29,7 @@ struct btrfs_backref_shared_cache { * a given data extent should never exceed the maximum b+tree height. */ struct btrfs_backref_shared_cache_entry entries[BTRFS_MAX_LEVEL]; + bool use_cache; }; typedef int (iterate_extent_inodes_t)(u64 inum, u64 offset, u64 root, diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 32c415cfbdfe..deebc8ddbd93 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -774,10 +774,8 @@ int btrfs_cache_block_group(struct btrfs_block_group *cache, bool wait) btrfs_queue_work(fs_info->caching_workers, &caching_ctl->work); out: - /* REVIEW */ if (wait && caching_ctl) ret = btrfs_caching_ctl_wait_done(cache, caching_ctl); - /* wait_event(caching_ctl->wait, space_cache_v1_done(cache)); */ if (caching_ctl) btrfs_put_caching_control(caching_ctl); diff --git a/fs/btrfs/extent-io-tree.c b/fs/btrfs/extent-io-tree.c index 618275af19c4..83cb0378096f 100644 --- a/fs/btrfs/extent-io-tree.c +++ b/fs/btrfs/extent-io-tree.c @@ -1641,16 +1641,17 @@ int lock_extent(struct extent_io_tree *tree, u64 start, u64 end, int err; u64 failed_start; - while (1) { + err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, &failed_start, + cached_state, NULL, GFP_NOFS); + while (err == -EEXIST) { + if (failed_start != start) + clear_extent_bit(tree, start, failed_start - 1, + EXTENT_LOCKED, cached_state); + + wait_extent_bit(tree, failed_start, end, EXTENT_LOCKED); err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, &failed_start, cached_state, NULL, GFP_NOFS); - if (err == -EEXIST) { - wait_extent_bit(tree, failed_start, end, EXTENT_LOCKED); - start = failed_start; - } else - break; - WARN_ON(start > end); } return err; } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 4ef4167072b8..ec6e1752af2c 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -348,6 +348,7 @@ static bool proto_cmd_ok(const struct send_ctx *sctx, int cmd) switch (sctx->proto) { case 1: return cmd <= BTRFS_SEND_C_MAX_V1; case 2: return cmd <= BTRFS_SEND_C_MAX_V2; + case 3: return cmd <= BTRFS_SEND_C_MAX_V3; default: return false; } } @@ -6469,7 +6470,9 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end) if (ret < 0) goto out; } - if (sctx->cur_inode_needs_verity) { + + if (proto_cmd_ok(sctx, BTRFS_SEND_C_ENABLE_VERITY) + && sctx->cur_inode_needs_verity) { ret = process_verity(sctx); if (ret < 0) goto out; diff --git a/fs/btrfs/send.h b/fs/btrfs/send.h index 0a4537775e0c..f7585cfa7e52 100644 --- a/fs/btrfs/send.h +++ b/fs/btrfs/send.h @@ -10,7 +10,12 @@ #include <linux/types.h> #define BTRFS_SEND_STREAM_MAGIC "btrfs-stream" +/* Conditional support for the upcoming protocol version. */ +#ifdef CONFIG_BTRFS_DEBUG +#define BTRFS_SEND_STREAM_VERSION 3 +#else #define BTRFS_SEND_STREAM_VERSION 2 +#endif /* * In send stream v1, no command is larger than 64K. In send stream v2, no limit diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 998cd26a1b3b..fe05bc51f9f2 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -590,14 +590,17 @@ struct erofs_fscache *erofs_domain_register_cookie(struct super_block *sb, struct super_block *psb = erofs_pseudo_mnt->mnt_sb; mutex_lock(&erofs_domain_cookies_lock); + spin_lock(&psb->s_inode_list_lock); list_for_each_entry(inode, &psb->s_inodes, i_sb_list) { ctx = inode->i_private; if (!ctx || ctx->domain != domain || strcmp(ctx->name, name)) continue; igrab(inode); + spin_unlock(&psb->s_inode_list_lock); mutex_unlock(&erofs_domain_cookies_lock); return ctx; } + spin_unlock(&psb->s_inode_list_lock); ctx = erofs_fscache_domain_init_cookie(sb, name, need_inode); mutex_unlock(&erofs_domain_cookies_lock); return ctx; diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 559380a535af..c7f24fc7efd5 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -813,15 +813,14 @@ retry: ++spiltted; if (fe->pcl->pageofs_out != (map->m_la & ~PAGE_MASK)) fe->pcl->multibases = true; - - if ((map->m_flags & EROFS_MAP_FULL_MAPPED) && - !(map->m_flags & EROFS_MAP_PARTIAL_REF) && - fe->pcl->length == map->m_llen) - fe->pcl->partial = false; if (fe->pcl->length < offset + end - map->m_la) { fe->pcl->length = offset + end - map->m_la; fe->pcl->pageofs_out = map->m_la & ~PAGE_MASK; } + if ((map->m_flags & EROFS_MAP_FULL_MAPPED) && + !(map->m_flags & EROFS_MAP_PARTIAL_REF) && + fe->pcl->length == map->m_llen) + fe->pcl->partial = false; next_part: /* shorten the remaining extent to update progress */ map->m_llen = offset + cur - map->m_la; @@ -888,15 +887,13 @@ static void z_erofs_do_decompressed_bvec(struct z_erofs_decompress_backend *be, if (!((bvec->offset + be->pcl->pageofs_out) & ~PAGE_MASK)) { unsigned int pgnr; - struct page *oldpage; pgnr = (bvec->offset + be->pcl->pageofs_out) >> PAGE_SHIFT; DBG_BUGON(pgnr >= be->nr_pages); - oldpage = be->decompressed_pages[pgnr]; - be->decompressed_pages[pgnr] = bvec->page; - - if (!oldpage) + if (!be->decompressed_pages[pgnr]) { + be->decompressed_pages[pgnr] = bvec->page; return; + } } /* (cold path) one pcluster is requested multiple times */ diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h index e7f04c4fbb81..d98c95212985 100644 --- a/fs/erofs/zdata.h +++ b/fs/erofs/zdata.h @@ -126,10 +126,10 @@ static inline unsigned int z_erofs_pclusterpages(struct z_erofs_pcluster *pcl) } /* - * bit 31: I/O error occurred on this page - * bit 0 - 30: remaining parts to complete this page + * bit 30: I/O error occurred on this page + * bit 0 - 29: remaining parts to complete this page */ -#define Z_EROFS_PAGE_EIO (1 << 31) +#define Z_EROFS_PAGE_EIO (1 << 30) static inline void z_erofs_onlinepage_init(struct page *page) { diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 44c27ef39c43..0bb66927e3d0 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -57,8 +57,7 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) pos = ALIGN(iloc(EROFS_SB(sb), vi->nid) + vi->inode_isize + vi->xattr_isize, 8); - kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(pos), - EROFS_KMAP_ATOMIC); + kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(pos), EROFS_KMAP); if (IS_ERR(kaddr)) { err = PTR_ERR(kaddr); goto out_unlock; @@ -73,7 +72,7 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) vi->z_advise = Z_EROFS_ADVISE_FRAGMENT_PCLUSTER; vi->z_fragmentoff = le64_to_cpu(*(__le64 *)h) ^ (1ULL << 63); vi->z_tailextent_headlcn = 0; - goto unmap_done; + goto done; } vi->z_advise = le16_to_cpu(h->h_advise); vi->z_algorithmtype[0] = h->h_algorithmtype & 15; @@ -85,7 +84,7 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) erofs_err(sb, "unknown HEAD%u format %u for nid %llu, please upgrade kernel", headnr + 1, vi->z_algorithmtype[headnr], vi->nid); err = -EOPNOTSUPP; - goto unmap_done; + goto out_put_metabuf; } vi->z_logical_clusterbits = LOG_BLOCK_SIZE + (h->h_clusterbits & 7); @@ -95,7 +94,7 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) erofs_err(sb, "per-inode big pcluster without sb feature for nid %llu", vi->nid); err = -EFSCORRUPTED; - goto unmap_done; + goto out_put_metabuf; } if (vi->datalayout == EROFS_INODE_FLAT_COMPRESSION && !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1) ^ @@ -103,12 +102,8 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) erofs_err(sb, "big pcluster head1/2 of compact indexes should be consistent for nid %llu", vi->nid); err = -EFSCORRUPTED; - goto unmap_done; + goto out_put_metabuf; } -unmap_done: - erofs_put_metabuf(&buf); - if (err) - goto out_unlock; if (vi->z_advise & Z_EROFS_ADVISE_INLINE_PCLUSTER) { struct erofs_map_blocks map = { @@ -127,7 +122,7 @@ unmap_done: err = -EFSCORRUPTED; } if (err < 0) - goto out_unlock; + goto out_put_metabuf; } if (vi->z_advise & Z_EROFS_ADVISE_FRAGMENT_PCLUSTER && @@ -141,11 +136,14 @@ unmap_done: EROFS_GET_BLOCKS_FINDTAIL); erofs_put_metabuf(&map.buf); if (err < 0) - goto out_unlock; + goto out_put_metabuf; } +done: /* paired with smp_mb() at the beginning of the function */ smp_mb(); set_bit(EROFS_I_Z_INITED_BIT, &vi->flags); +out_put_metabuf: + erofs_put_metabuf(&buf); out_unlock: clear_and_wake_up_bit(EROFS_I_BL_Z_BIT, &vi->flags); return err; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index f2a9f2274c3b..528bd44b59e2 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -106,6 +106,7 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup *cgroup_get_from_path(const char *path); struct cgroup *cgroup_get_from_fd(int fd); +struct cgroup *cgroup_v1v2_get_from_fd(int fd); int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); diff --git a/include/linux/dsa/tag_qca.h b/include/linux/dsa/tag_qca.h index 50be7cbd93a5..b1b5720d89a5 100644 --- a/include/linux/dsa/tag_qca.h +++ b/include/linux/dsa/tag_qca.h @@ -61,9 +61,9 @@ struct sk_buff; /* Special struct emulating a Ethernet header */ struct qca_mgmt_ethhdr { - u32 command; /* command bit 31:0 */ - u32 seq; /* seq 63:32 */ - u32 mdio_data; /* first 4byte mdio */ + __le32 command; /* command bit 31:0 */ + __le32 seq; /* seq 63:32 */ + __le32 mdio_data; /* first 4byte mdio */ __be16 hdr; /* qca hdr */ } __packed; @@ -73,7 +73,7 @@ enum mdio_cmd { }; struct mib_ethhdr { - u32 data[3]; /* first 3 mib counter */ + __le32 data[3]; /* first 3 mib counter */ __be16 hdr; /* qca hdr */ } __packed; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a36edb0ec199..eddf8ee270e7 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3663,8 +3663,9 @@ static inline bool netif_attr_test_online(unsigned long j, static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp, unsigned int nr_bits) { - /* n is a prior cpu */ - cpu_max_bits_warn(n + 1, nr_bits); + /* -1 is a legal arg here. */ + if (n != -1) + cpu_max_bits_warn(n, nr_bits); if (srcp) return find_next_bit(srcp, nr_bits, n + 1); @@ -3685,8 +3686,9 @@ static inline int netif_attrmask_next_and(int n, const unsigned long *src1p, const unsigned long *src2p, unsigned int nr_bits) { - /* n is a prior cpu */ - cpu_max_bits_warn(n + 1, nr_bits); + /* -1 is a legal arg here. */ + if (n != -1) + cpu_max_bits_warn(n, nr_bits); if (src1p && src2p) return find_next_and_bit(src1p, src2p, nr_bits, n + 1); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 664dd409feb9..3f01ac8017e0 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -122,6 +122,7 @@ enum phylink_op_type { * (See commit 7cceb599d15d ("net: phylink: avoid mac_config calls") * @poll_fixed_state: if true, starts link_poll, * if MAC link is at %MLO_AN_FIXED mode. + * @mac_managed_pm: if true, indicate the MAC driver is responsible for PHY PM. * @ovr_an_inband: if true, override PCS to MLO_AN_INBAND * @get_fixed_state: callback to execute to determine the fixed link state, * if MAC link is at %MLO_AN_FIXED mode. @@ -134,6 +135,7 @@ struct phylink_config { enum phylink_op_type type; bool legacy_pre_march2020; bool poll_fixed_state; + bool mac_managed_pm; bool ovr_an_inband; void (*get_fixed_state)(struct phylink_config *config, struct phylink_link_state *state); diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 8f780170e2f8..3d08e67b3cfc 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -37,6 +37,7 @@ struct genl_info; * do additional, common, filtering and return an error * @post_doit: called after an operation's doit callback, it may * undo operations done by pre_doit, for example release locks + * @module: pointer to the owning module (set to THIS_MODULE) * @mcgrps: multicast groups used by this family * @n_mcgrps: number of multicast groups * @resv_start_op: first operation for which reserved fields of the header @@ -173,9 +174,9 @@ struct genl_ops { }; /** - * struct genl_info - info that is available during dumpit op call + * struct genl_dumpit_info - info that is available during dumpit op call * @family: generic netlink family - for internal genl code usage - * @ops: generic netlink ops - for internal genl code usage + * @op: generic netlink ops - for internal genl code usage * @attrs: netlink attributes */ struct genl_dumpit_info { @@ -354,6 +355,7 @@ int genlmsg_multicast_allns(const struct genl_family *family, /** * genlmsg_unicast - unicast a netlink message + * @net: network namespace to look up @portid in * @skb: netlink message as socket buffer * @portid: netlink portid of the destination socket */ @@ -373,7 +375,7 @@ static inline int genlmsg_reply(struct sk_buff *skb, struct genl_info *info) } /** - * gennlmsg_data - head of message payload + * genlmsg_data - head of message payload * @gnlh: genetlink message header */ static inline void *genlmsg_data(const struct genlmsghdr *gnlh) diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h index 473b0b0fa4ab..efc9085c6892 100644 --- a/include/net/sock_reuseport.h +++ b/include/net/sock_reuseport.h @@ -43,21 +43,20 @@ struct sock *reuseport_migrate_sock(struct sock *sk, extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog); extern int reuseport_detach_prog(struct sock *sk); -static inline bool reuseport_has_conns(struct sock *sk, bool set) +static inline bool reuseport_has_conns(struct sock *sk) { struct sock_reuseport *reuse; bool ret = false; rcu_read_lock(); reuse = rcu_dereference(sk->sk_reuseport_cb); - if (reuse) { - if (set) - reuse->has_conns = 1; - ret = reuse->has_conns; - } + if (reuse && reuse->has_conns) + ret = true; rcu_read_unlock(); return ret; } +void reuseport_has_conns_set(struct sock *sk); + #endif /* _SOCK_REUSEPORT_H */ diff --git a/kernel/bpf/cgroup_iter.c b/kernel/bpf/cgroup_iter.c index 0d200a993489..9fcf09f2ef00 100644 --- a/kernel/bpf/cgroup_iter.c +++ b/kernel/bpf/cgroup_iter.c @@ -196,7 +196,7 @@ static int bpf_iter_attach_cgroup(struct bpf_prog *prog, return -EINVAL; if (fd) - cgrp = cgroup_get_from_fd(fd); + cgrp = cgroup_v1v2_get_from_fd(fd); else if (id) cgrp = cgroup_get_from_id(id); else /* walk the entire hierarchy by default. */ diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 7f486677ab1f..2319946715e0 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1392,6 +1392,9 @@ static void cgroup_destroy_root(struct cgroup_root *root) cgroup_free_root(root); } +/* + * Returned cgroup is without refcount but it's valid as long as cset pins it. + */ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root) { @@ -1403,6 +1406,7 @@ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset, res_cgroup = cset->dfl_cgrp; } else { struct cgrp_cset_link *link; + lockdep_assert_held(&css_set_lock); list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; @@ -1414,6 +1418,7 @@ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset, } } + BUG_ON(!res_cgroup); return res_cgroup; } @@ -1436,23 +1441,36 @@ current_cgns_cgroup_from_root(struct cgroup_root *root) rcu_read_unlock(); - BUG_ON(!res); return res; } +/* + * Look up cgroup associated with current task's cgroup namespace on the default + * hierarchy. + * + * Unlike current_cgns_cgroup_from_root(), this doesn't need locks: + * - Internal rcu_read_lock is unnecessary because we don't dereference any rcu + * pointers. + * - css_set_lock is not needed because we just read cset->dfl_cgrp. + * - As a bonus returned cgrp is pinned with the current because it cannot + * switch cgroup_ns asynchronously. + */ +static struct cgroup *current_cgns_cgroup_dfl(void) +{ + struct css_set *cset; + + cset = current->nsproxy->cgroup_ns->root_cset; + return __cset_cgroup_from_root(cset, &cgrp_dfl_root); +} + /* look up cgroup associated with given css_set on the specified hierarchy */ static struct cgroup *cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root) { - struct cgroup *res = NULL; - lockdep_assert_held(&cgroup_mutex); lockdep_assert_held(&css_set_lock); - res = __cset_cgroup_from_root(cset, root); - - BUG_ON(!res); - return res; + return __cset_cgroup_from_root(cset, root); } /* @@ -6191,9 +6209,7 @@ struct cgroup *cgroup_get_from_id(u64 id) if (!cgrp) return ERR_PTR(-ENOENT); - spin_lock_irq(&css_set_lock); - root_cgrp = current_cgns_cgroup_from_root(&cgrp_dfl_root); - spin_unlock_irq(&css_set_lock); + root_cgrp = current_cgns_cgroup_dfl(); if (!cgroup_is_descendant(cgrp, root_cgrp)) { cgroup_put(cgrp); return ERR_PTR(-ENOENT); @@ -6294,16 +6310,42 @@ void cgroup_fork(struct task_struct *child) INIT_LIST_HEAD(&child->cg_list); } -static struct cgroup *cgroup_get_from_file(struct file *f) +/** + * cgroup_v1v2_get_from_file - get a cgroup pointer from a file pointer + * @f: file corresponding to cgroup_dir + * + * Find the cgroup from a file pointer associated with a cgroup directory. + * Returns a pointer to the cgroup on success. ERR_PTR is returned if the + * cgroup cannot be found. + */ +static struct cgroup *cgroup_v1v2_get_from_file(struct file *f) { struct cgroup_subsys_state *css; - struct cgroup *cgrp; css = css_tryget_online_from_dir(f->f_path.dentry, NULL); if (IS_ERR(css)) return ERR_CAST(css); - cgrp = css->cgroup; + return css->cgroup; +} + +/** + * cgroup_get_from_file - same as cgroup_v1v2_get_from_file, but only supports + * cgroup2. + * @f: file corresponding to cgroup2_dir + */ +static struct cgroup *cgroup_get_from_file(struct file *f) +{ + struct cgroup *cgrp = cgroup_v1v2_get_from_file(f); + + if (IS_ERR(cgrp)) + return ERR_CAST(cgrp); + + if (!cgroup_on_dfl(cgrp)) { + cgroup_put(cgrp); + return ERR_PTR(-EBADF); + } + return cgrp; } @@ -6772,10 +6814,8 @@ struct cgroup *cgroup_get_from_path(const char *path) struct cgroup *cgrp = ERR_PTR(-ENOENT); struct cgroup *root_cgrp; - spin_lock_irq(&css_set_lock); - root_cgrp = current_cgns_cgroup_from_root(&cgrp_dfl_root); + root_cgrp = current_cgns_cgroup_dfl(); kn = kernfs_walk_and_get(root_cgrp->kn, path); - spin_unlock_irq(&css_set_lock); if (!kn) goto out; @@ -6800,15 +6840,15 @@ out: EXPORT_SYMBOL_GPL(cgroup_get_from_path); /** - * cgroup_get_from_fd - get a cgroup pointer from a fd - * @fd: fd obtained by open(cgroup2_dir) + * cgroup_v1v2_get_from_fd - get a cgroup pointer from a fd + * @fd: fd obtained by open(cgroup_dir) * * Find the cgroup from a fd which should be obtained * by opening a cgroup directory. Returns a pointer to the * cgroup on success. ERR_PTR is returned if the cgroup * cannot be found. */ -struct cgroup *cgroup_get_from_fd(int fd) +struct cgroup *cgroup_v1v2_get_from_fd(int fd) { struct cgroup *cgrp; struct file *f; @@ -6817,10 +6857,29 @@ struct cgroup *cgroup_get_from_fd(int fd) if (!f) return ERR_PTR(-EBADF); - cgrp = cgroup_get_from_file(f); + cgrp = cgroup_v1v2_get_from_file(f); fput(f); return cgrp; } + +/** + * cgroup_get_from_fd - same as cgroup_v1v2_get_from_fd, but only supports + * cgroup2. + * @fd: fd obtained by open(cgroup2_dir) + */ +struct cgroup *cgroup_get_from_fd(int fd) +{ + struct cgroup *cgrp = cgroup_v1v2_get_from_fd(fd); + + if (IS_ERR(cgrp)) + return ERR_CAST(cgrp); + + if (!cgroup_on_dfl(cgrp)) { + cgroup_put(cgrp); + return ERR_PTR(-EBADF); + } + return cgrp; +} EXPORT_SYMBOL_GPL(cgroup_get_from_fd); static u64 power_of_ten(int power) diff --git a/net/atm/mpoa_proc.c b/net/atm/mpoa_proc.c index 829db9eba0cb..aaf64b953915 100644 --- a/net/atm/mpoa_proc.c +++ b/net/atm/mpoa_proc.c @@ -219,11 +219,12 @@ static ssize_t proc_mpc_write(struct file *file, const char __user *buff, if (!page) return -ENOMEM; - for (p = page, len = 0; len < nbytes; p++, len++) { + for (p = page, len = 0; len < nbytes; p++) { if (get_user(*p, buff++)) { free_page((unsigned long)page); return -EFAULT; } + len += 1; if (*p == '\0' || *p == '\n') break; } diff --git a/net/core/dev.c b/net/core/dev.c index fa53830d0683..3be256051e99 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5136,11 +5136,13 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, case TC_ACT_SHOT: mini_qdisc_qstats_cpu_drop(miniq); kfree_skb_reason(skb, SKB_DROP_REASON_TC_INGRESS); + *ret = NET_RX_DROP; return NULL; case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: consume_skb(skb); + *ret = NET_RX_SUCCESS; return NULL; case TC_ACT_REDIRECT: /* skb_mac_header check was done by cls/act_bpf, so @@ -5153,8 +5155,10 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, *another = true; break; } + *ret = NET_RX_SUCCESS; return NULL; case TC_ACT_CONSUMED: + *ret = NET_RX_SUCCESS; return NULL; default: break; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index ca70525621c7..1efdc47a999b 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -500,11 +500,11 @@ bool sk_msg_is_readable(struct sock *sk) } EXPORT_SYMBOL_GPL(sk_msg_is_readable); -static struct sk_msg *alloc_sk_msg(void) +static struct sk_msg *alloc_sk_msg(gfp_t gfp) { struct sk_msg *msg; - msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_KERNEL); + msg = kzalloc(sizeof(*msg), gfp | __GFP_NOWARN); if (unlikely(!msg)) return NULL; sg_init_marker(msg->sg.data, NR_MSG_FRAG_IDS); @@ -520,7 +520,7 @@ static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk, if (!sk_rmem_schedule(sk, skb, skb->truesize)) return NULL; - return alloc_sk_msg(); + return alloc_sk_msg(GFP_KERNEL); } static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, @@ -597,7 +597,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb, static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len) { - struct sk_msg *msg = alloc_sk_msg(); + struct sk_msg *msg = alloc_sk_msg(GFP_ATOMIC); struct sock *sk = psock->sk; int err; diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 5daa1fa54249..fb90e1e00773 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -21,6 +21,22 @@ static DEFINE_IDA(reuseport_ida); static int reuseport_resurrect(struct sock *sk, struct sock_reuseport *old_reuse, struct sock_reuseport *reuse, bool bind_inany); +void reuseport_has_conns_set(struct sock *sk) +{ + struct sock_reuseport *reuse; + + if (!rcu_access_pointer(sk->sk_reuseport_cb)) + return; + + spin_lock_bh(&reuseport_lock); + reuse = rcu_dereference_protected(sk->sk_reuseport_cb, + lockdep_is_held(&reuseport_lock)); + if (likely(reuse)) + reuse->has_conns = 1; + spin_unlock_bh(&reuseport_lock); +} +EXPORT_SYMBOL(reuseport_has_conns_set); + static int reuseport_sock_index(struct sock *sk, const struct sock_reuseport *reuse, bool closed) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 1a59918d3b30..a9fde48cffd4 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -3145,7 +3145,7 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, case NETDEV_CHANGELOWERSTATE: { struct netdev_notifier_changelowerstate_info *info = ptr; struct dsa_port *dp; - int err; + int err = 0; if (dsa_slave_dev_check(dev)) { dp = dsa_slave_to_port(dev); diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 5bf357734b11..a50429a62f74 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -150,15 +150,15 @@ struct sk_buff *hsr_get_untagged_frame(struct hsr_frame_info *frame, struct hsr_port *port) { if (!frame->skb_std) { - if (frame->skb_hsr) { + if (frame->skb_hsr) frame->skb_std = create_stripped_skb_hsr(frame->skb_hsr, frame); - } else { - /* Unexpected */ - WARN_ONCE(1, "%s:%d: Unexpected frame received (port_src %s)\n", - __FILE__, __LINE__, port->dev->name); + else + netdev_warn_once(port->dev, + "Unexpected frame received in hsr_get_untagged_frame()\n"); + + if (!frame->skb_std) return NULL; - } } return skb_clone(frame->skb_std, GFP_ATOMIC); diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 0ee7fd259730..4d1af0cd7d99 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -70,7 +70,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len } inet->inet_daddr = fl4->daddr; inet->inet_dport = usin->sin_port; - reuseport_has_conns(sk, true); + reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); inet->inet_id = get_random_u16(); diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index ff85db52b2e5..ded5bef02f77 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -78,6 +78,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) flow.flowi4_tos = iph->tos & IPTOS_RT_MASK; flow.flowi4_scope = RT_SCOPE_UNIVERSE; flow.flowi4_l3mdev = l3mdev_master_ifindex_rcu(xt_in(par)); + flow.flowi4_uid = sock_net_uid(xt_net(par), NULL); return rpfilter_lookup_reverse(xt_net(par), &flow, xt_in(par), info->flags) ^ invert; } diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index e886147eed11..fc65d69f23e1 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -65,6 +65,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, struct flowi4 fl4 = { .flowi4_scope = RT_SCOPE_UNIVERSE, .flowi4_iif = LOOPBACK_IFINDEX, + .flowi4_uid = sock_net_uid(nft_net(pkt), NULL), }; const struct net_device *oif; const struct net_device *found; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 662d717d5123..c83e5271030b 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -448,7 +448,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); /* Fall back to scoring if group has connections */ - if (result && !reuseport_has_conns(sk, false)) + if (result && !reuseport_has_conns(sk)) return result; result = result ? : sk; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 417834b7169d..9c3f5202a97b 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -7214,9 +7214,11 @@ err_reg_dflt: __addrconf_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL); err_reg_all: kfree(dflt); + net->ipv6.devconf_dflt = NULL; #endif err_alloc_dflt: kfree(all); + net->ipv6.devconf_all = NULL; err_alloc_all: kfree(net->ipv6.inet6_addr_lst); err_alloc_addr: diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index df665d4e8f0f..5ecb56522f9d 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -256,7 +256,7 @@ ipv4_connected: goto out; } - reuseport_has_conns(sk, true); + reuseport_has_conns_set(sk); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); out: diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index 69d86b040a6a..a01d9b842bd0 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -40,6 +40,7 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, .flowi6_l3mdev = l3mdev_master_ifindex_rcu(dev), .flowlabel = (* (__be32 *) iph) & IPV6_FLOWINFO_MASK, .flowi6_proto = iph->nexthdr, + .flowi6_uid = sock_net_uid(net, NULL), .daddr = iph->saddr, }; int lookup_flags; diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index 91faac610e03..36dc14b34388 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -66,6 +66,7 @@ static u32 __nft_fib6_eval_type(const struct nft_fib *priv, struct flowi6 fl6 = { .flowi6_iif = LOOPBACK_IFINDEX, .flowi6_proto = pkt->tprot, + .flowi6_uid = sock_net_uid(nft_net(pkt), NULL), }; u32 ret = 0; @@ -163,6 +164,7 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, struct flowi6 fl6 = { .flowi6_iif = LOOPBACK_IFINDEX, .flowi6_proto = pkt->tprot, + .flowi6_uid = sock_net_uid(nft_net(pkt), NULL), }; struct rt6_info *rt; int lookup_flags; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 8d09f0ea5b8c..129ec5a9b0eb 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -195,7 +195,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); /* Fall back to scoring if group has connections */ - if (result && !reuseport_has_conns(sk, false)) + if (result && !reuseport_has_conns(sk)) return result; result = result ? : sk; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index a0653a8dfa82..58d9cbc9ccdc 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5865,8 +5865,9 @@ static bool nft_setelem_valid_key_end(const struct nft_set *set, (NFT_SET_CONCAT | NFT_SET_INTERVAL)) { if (flags & NFT_SET_ELEM_INTERVAL_END) return false; - if (!nla[NFTA_SET_ELEM_KEY_END] && - !(flags & NFT_SET_ELEM_CATCHALL)) + + if (nla[NFTA_SET_ELEM_KEY_END] && + flags & NFT_SET_ELEM_CATCHALL) return false; } else { if (nla[NFTA_SET_ELEM_KEY_END]) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index c98af0ada706..4a27dfb1ba0f 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1099,12 +1099,13 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, skip: if (!ingress) { - notify_and_destroy(net, skb, n, classid, - rtnl_dereference(dev->qdisc), new); + old = rtnl_dereference(dev->qdisc); if (new && !new->ops->attach) qdisc_refcount_inc(new); rcu_assign_pointer(dev->qdisc, new ? : &noop_qdisc); + notify_and_destroy(net, skb, n, classid, old, new); + if (new && new->ops->attach) new->ops->attach(new); } else { diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 817cd0695b35..3ed0c3342189 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -2224,8 +2224,12 @@ retry: static void cake_reset(struct Qdisc *sch) { + struct cake_sched_data *q = qdisc_priv(sch); u32 c; + if (!q->tins) + return; + for (c = 0; c < CAKE_MAX_TINS; c++) cake_clear_tin(sch, c); } diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 99d318b60568..8c4fee063436 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -478,24 +478,26 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt, if (opt) { err = fq_codel_change(sch, opt, extack); if (err) - return err; + goto init_failure; } err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) - return err; + goto init_failure; if (!q->flows) { q->flows = kvcalloc(q->flows_cnt, sizeof(struct fq_codel_flow), GFP_KERNEL); - if (!q->flows) - return -ENOMEM; - + if (!q->flows) { + err = -ENOMEM; + goto init_failure; + } q->backlogs = kvcalloc(q->flows_cnt, sizeof(u32), GFP_KERNEL); - if (!q->backlogs) - return -ENOMEM; - + if (!q->backlogs) { + err = -ENOMEM; + goto alloc_failure; + } for (i = 0; i < q->flows_cnt; i++) { struct fq_codel_flow *flow = q->flows + i; @@ -508,6 +510,13 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt, else sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; + +alloc_failure: + kvfree(q->flows); + q->flows = NULL; +init_failure: + q->flows_cnt = 0; + return err; } static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 0366a1a029a9..1871a1c0224d 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -455,7 +455,8 @@ static void sfb_reset(struct Qdisc *sch) { struct sfb_sched_data *q = qdisc_priv(sch); - qdisc_reset(q->qdisc); + if (likely(q->qdisc)) + qdisc_reset(q->qdisc); q->slot = 0; q->double_buffering = false; sfb_zero_all_buckets(q); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index e6ee797640b4..c305d8dd23f8 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -896,7 +896,8 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) } memcpy(lgr->pnet_id, ibdev->pnetid[ibport - 1], SMC_MAX_PNETID_LEN); - if (smc_wr_alloc_lgr_mem(lgr)) + rc = smc_wr_alloc_lgr_mem(lgr); + if (rc) goto free_wq; smc_llc_lgr_init(lgr, smc); diff --git a/net/tipc/discover.c b/net/tipc/discover.c index da69e1abf68f..e8630707901e 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -148,8 +148,8 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d, { struct net *net = d->net; struct tipc_net *tn = tipc_net(net); - bool trial = time_before(jiffies, tn->addr_trial_end); u32 self = tipc_own_addr(net); + bool trial = time_before(jiffies, tn->addr_trial_end) && !self; if (mtyp == DSC_TRIAL_FAIL_MSG) { if (!trial) diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 5522865deae9..14fd05fd6107 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -568,7 +568,7 @@ bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, sub.seq.upper = upper; sub.timeout = TIPC_WAIT_FOREVER; sub.filter = filter; - *(u32 *)&sub.usr_handle = port; + *(u64 *)&sub.usr_handle = (u64)port; con = tipc_conn_alloc(tipc_topsrv(net)); if (IS_ERR(con)) diff --git a/net/tls/tls_strp.c b/net/tls/tls_strp.c index 9b79e334dbd9..955ac3e0bf4d 100644 --- a/net/tls/tls_strp.c +++ b/net/tls/tls_strp.c @@ -273,7 +273,7 @@ static int tls_strp_read_copyin(struct tls_strparser *strp) return desc.error; } -static int tls_strp_read_short(struct tls_strparser *strp) +static int tls_strp_read_copy(struct tls_strparser *strp, bool qshort) { struct skb_shared_info *shinfo; struct page *page; @@ -283,7 +283,7 @@ static int tls_strp_read_short(struct tls_strparser *strp) * to read the data out. Otherwise the connection will stall. * Without pressure threshold of INT_MAX will never be ready. */ - if (likely(!tcp_epollin_ready(strp->sk, INT_MAX))) + if (likely(qshort && !tcp_epollin_ready(strp->sk, INT_MAX))) return 0; shinfo = skb_shinfo(strp->anchor); @@ -315,6 +315,27 @@ static int tls_strp_read_short(struct tls_strparser *strp) return 0; } +static bool tls_strp_check_no_dup(struct tls_strparser *strp) +{ + unsigned int len = strp->stm.offset + strp->stm.full_len; + struct sk_buff *skb; + u32 seq; + + skb = skb_shinfo(strp->anchor)->frag_list; + seq = TCP_SKB_CB(skb)->seq; + + while (skb->len < len) { + seq += skb->len; + len -= skb->len; + skb = skb->next; + + if (TCP_SKB_CB(skb)->seq != seq) + return false; + } + + return true; +} + static void tls_strp_load_anchor_with_queue(struct tls_strparser *strp, int len) { struct tcp_sock *tp = tcp_sk(strp->sk); @@ -373,7 +394,7 @@ static int tls_strp_read_sock(struct tls_strparser *strp) return tls_strp_read_copyin(strp); if (inq < strp->stm.full_len) - return tls_strp_read_short(strp); + return tls_strp_read_copy(strp, true); if (!strp->stm.full_len) { tls_strp_load_anchor_with_queue(strp, inq); @@ -387,9 +408,12 @@ static int tls_strp_read_sock(struct tls_strparser *strp) strp->stm.full_len = sz; if (!strp->stm.full_len || inq < strp->stm.full_len) - return tls_strp_read_short(strp); + return tls_strp_read_copy(strp, true); } + if (!tls_strp_check_no_dup(strp)) + return tls_strp_read_copy(strp, false); + strp->msg_ready = 1; tls_rx_msg_ready(strp); diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 2a6b0bc648c4..69c58362c0ed 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -70,6 +70,7 @@ TEST_PROGS += io_uring_zerocopy_tx.sh TEST_GEN_FILES += bind_bhash TEST_GEN_PROGS += sk_bind_sendto_listen TEST_GEN_PROGS += sk_connect_zero_addr +TEST_PROGS += test_ingress_egress_chaining.sh TEST_FILES := settings diff --git a/tools/testing/selftests/net/test_ingress_egress_chaining.sh b/tools/testing/selftests/net/test_ingress_egress_chaining.sh new file mode 100644 index 000000000000..08adff6bb3b6 --- /dev/null +++ b/tools/testing/selftests/net/test_ingress_egress_chaining.sh @@ -0,0 +1,79 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test runs a simple ingress tc setup between two veth pairs, +# and chains a single egress rule to test ingress chaining to egress. +# +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +if [ "$(id -u)" -ne 0 ];then + echo "SKIP: Need root privileges" + exit $ksft_skip +fi + +needed_mods="act_mirred cls_flower sch_ingress" +for mod in $needed_mods; do + modinfo $mod &>/dev/null || { echo "SKIP: Need act_mirred module"; exit $ksft_skip; } +done + +ns="ns$((RANDOM%899+100))" +veth1="veth1$((RANDOM%899+100))" +veth2="veth2$((RANDOM%899+100))" +peer1="peer1$((RANDOM%899+100))" +peer2="peer2$((RANDOM%899+100))" +ip_peer1=198.51.100.5 +ip_peer2=198.51.100.6 + +function fail() { + echo "FAIL: $@" >> /dev/stderr + exit 1 +} + +function cleanup() { + killall -q -9 udpgso_bench_rx + ip link del $veth1 &> /dev/null + ip link del $veth2 &> /dev/null + ip netns del $ns &> /dev/null +} +trap cleanup EXIT + +function config() { + echo "Setup veth pairs [$veth1, $peer1], and veth pair [$veth2, $peer2]" + ip link add $veth1 type veth peer name $peer1 + ip link add $veth2 type veth peer name $peer2 + ip addr add $ip_peer1/24 dev $peer1 + ip link set $peer1 up + ip netns add $ns + ip link set dev $peer2 netns $ns + ip netns exec $ns ip addr add $ip_peer2/24 dev $peer2 + ip netns exec $ns ip link set $peer2 up + ip link set $veth1 up + ip link set $veth2 up + + echo "Add tc filter ingress->egress forwarding $veth1 <-> $veth2" + tc qdisc add dev $veth2 ingress + tc qdisc add dev $veth1 ingress + tc filter add dev $veth2 ingress prio 1 proto all flower \ + action mirred egress redirect dev $veth1 + tc filter add dev $veth1 ingress prio 1 proto all flower \ + action mirred egress redirect dev $veth2 + + echo "Add tc filter egress->ingress forwarding $peer1 -> $veth1, bypassing the veth pipe" + tc qdisc add dev $peer1 clsact + tc filter add dev $peer1 egress prio 20 proto ip flower \ + action mirred ingress redirect dev $veth1 +} + +function test_run() { + echo "Run tcp traffic" + ./udpgso_bench_rx -t & + sleep 1 + ip netns exec $ns timeout -k 2 10 ./udpgso_bench_tx -t -l 2 -4 -D $ip_peer1 || fail "traffic failed" + echo "Test passed" +} + +config +test_run +trap - EXIT +cleanup |