diff options
128 files changed, 974 insertions, 553 deletions
@@ -435,7 +435,7 @@ Martin Kepplinger <martink@posteo.de> <martin.kepplinger@ginzinger.com> Martin Kepplinger <martink@posteo.de> <martin.kepplinger@puri.sm> Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com> Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com> <martyna.szapar-mudlaw@intel.com> -Mathieu Othacehe <m.othacehe@gmail.com> <othacehe@gnu.org> +Mathieu Othacehe <othacehe@gnu.org> <m.othacehe@gmail.com> Mat Martineau <martineau@kernel.org> <mathew.j.martineau@linux.intel.com> Mat Martineau <martineau@kernel.org> <mathewm@codeaurora.org> Matthew Wilcox <willy@infradead.org> <matthew.r.wilcox@intel.com> diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst index 5034915f4e8e..8872203df088 100644 --- a/Documentation/admin-guide/mm/transhuge.rst +++ b/Documentation/admin-guide/mm/transhuge.rst @@ -436,7 +436,7 @@ AnonHugePmdMapped). The number of file transparent huge pages mapped to userspace is available by reading ShmemPmdMapped and ShmemHugePages fields in ``/proc/meminfo``. To identify what applications are mapping file transparent huge pages, it -is necessary to read ``/proc/PID/smaps`` and count the FileHugeMapped fields +is necessary to read ``/proc/PID/smaps`` and count the FilePmdMapped fields for each mapping. Note that reading the smaps file is expensive and reading it diff --git a/MAINTAINERS b/MAINTAINERS index 4e93a00df185..dba82fb32d04 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14752,7 +14752,7 @@ F: drivers/memory/mtk-smi.c F: include/soc/mediatek/smi.h MEDIATEK SWITCH DRIVER -M: Arınç ÜNAL <arinc.unal@arinc9.com> +M: Chester A. Unal <chester.a.unal@arinc9.com> M: Daniel Golle <daniel@makrotopia.org> M: DENG Qingfang <dqfext@gmail.com> M: Sean Wang <sean.wang@mediatek.com> @@ -18456,7 +18456,7 @@ F: Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml F: drivers/pinctrl/mediatek/ PIN CONTROLLER - MEDIATEK MIPS -M: Arınç ÜNAL <arinc.unal@arinc9.com> +M: Chester A. Unal <chester.a.unal@arinc9.com> M: Sergio Paracuellos <sergio.paracuellos@gmail.com> L: linux-mediatek@lists.infradead.org (moderated for non-subscribers) L: linux-mips@vger.kernel.org @@ -19500,7 +19500,7 @@ S: Maintained F: arch/mips/ralink RALINK MT7621 MIPS ARCHITECTURE -M: Arınç ÜNAL <arinc.unal@arinc9.com> +M: Chester A. Unal <chester.a.unal@arinc9.com> M: Sergio Paracuellos <sergio.paracuellos@gmail.com> L: linux-mips@vger.kernel.org S: Maintained @@ -20903,6 +20903,8 @@ F: kernel/sched/ SCHEDULER - SCHED_EXT R: Tejun Heo <tj@kernel.org> R: David Vernet <void@manifault.com> +R: Andrea Righi <arighi@nvidia.com> +R: Changwoo Min <changwoo@igalia.com> L: linux-kernel@vger.kernel.org S: Maintained W: https://github.com/sched-ext/scx @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 13 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 6a99a459b80b..51745ed1bbab 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -1106,7 +1106,7 @@ int open_for_data(struct cdrom_device_info *cdi) } } - cd_dbg(CD_OPEN, "all seems well, opening the devicen"); + cd_dbg(CD_OPEN, "all seems well, opening the device\n"); /* all seems well, we can open the device */ ret = cdo->open(cdi, 0); /* open for data */ diff --git a/drivers/clk/imx/clk-imx8mp-audiomix.c b/drivers/clk/imx/clk-imx8mp-audiomix.c index b2cb157703c5..c409fc7e0618 100644 --- a/drivers/clk/imx/clk-imx8mp-audiomix.c +++ b/drivers/clk/imx/clk-imx8mp-audiomix.c @@ -278,7 +278,8 @@ static int clk_imx8mp_audiomix_reset_controller_register(struct device *dev, #else /* !CONFIG_RESET_CONTROLLER */ -static int clk_imx8mp_audiomix_reset_controller_register(struct clk_imx8mp_audiomix_priv *priv) +static int clk_imx8mp_audiomix_reset_controller_register(struct device *dev, + struct clk_imx8mp_audiomix_priv *priv) { return 0; } diff --git a/drivers/clk/thead/clk-th1520-ap.c b/drivers/clk/thead/clk-th1520-ap.c index 17e32ae08720..1015fab95251 100644 --- a/drivers/clk/thead/clk-th1520-ap.c +++ b/drivers/clk/thead/clk-th1520-ap.c @@ -779,6 +779,13 @@ static struct ccu_div dpu1_clk = { }, }; +static CLK_FIXED_FACTOR_HW(emmc_sdio_ref_clk, "emmc-sdio-ref", + &video_pll_clk.common.hw, 4, 1, 0); + +static const struct clk_parent_data emmc_sdio_ref_clk_pd[] = { + { .hw = &emmc_sdio_ref_clk.hw }, +}; + static CCU_GATE(CLK_BROM, brom_clk, "brom", ahb2_cpusys_hclk_pd, 0x100, BIT(4), 0); static CCU_GATE(CLK_BMU, bmu_clk, "bmu", axi4_cpusys2_aclk_pd, 0x100, BIT(5), 0); static CCU_GATE(CLK_AON2CPU_A2X, aon2cpu_a2x_clk, "aon2cpu-a2x", axi4_cpusys2_aclk_pd, @@ -798,7 +805,7 @@ static CCU_GATE(CLK_PERISYS_APB4_HCLK, perisys_apb4_hclk, "perisys-apb4-hclk", p 0x150, BIT(12), 0); static CCU_GATE(CLK_NPU_AXI, npu_axi_clk, "npu-axi", axi_aclk_pd, 0x1c8, BIT(5), 0); static CCU_GATE(CLK_CPU2VP, cpu2vp_clk, "cpu2vp", axi_aclk_pd, 0x1e0, BIT(13), 0); -static CCU_GATE(CLK_EMMC_SDIO, emmc_sdio_clk, "emmc-sdio", video_pll_clk_pd, 0x204, BIT(30), 0); +static CCU_GATE(CLK_EMMC_SDIO, emmc_sdio_clk, "emmc-sdio", emmc_sdio_ref_clk_pd, 0x204, BIT(30), 0); static CCU_GATE(CLK_GMAC1, gmac1_clk, "gmac1", gmac_pll_clk_pd, 0x204, BIT(26), 0); static CCU_GATE(CLK_PADCTRL1, padctrl1_clk, "padctrl1", perisys_apb_pclk_pd, 0x204, BIT(24), 0); static CCU_GATE(CLK_DSMART, dsmart_clk, "dsmart", perisys_apb_pclk_pd, 0x204, BIT(23), 0); @@ -1059,6 +1066,10 @@ static int th1520_clk_probe(struct platform_device *pdev) return ret; priv->hws[CLK_PLL_GMAC_100M] = &gmac_pll_clk_100m.hw; + ret = devm_clk_hw_register(dev, &emmc_sdio_ref_clk.hw); + if (ret) + return ret; + ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get, priv); if (ret) return ret; diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c index ec5db1478b2f..18ae45dcbfb2 100644 --- a/drivers/md/dm-ebs-target.c +++ b/drivers/md/dm-ebs-target.c @@ -442,7 +442,7 @@ static int ebs_iterate_devices(struct dm_target *ti, static struct target_type ebs_target = { .name = "ebs", .version = {1, 0, 1}, - .features = DM_TARGET_PASSES_INTEGRITY, + .features = 0, .module = THIS_MODULE, .ctr = ebs_ctr, .dtr = ebs_dtr, diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index bf0f9dddd146..05cf4e3f2bbe 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -2332,10 +2332,9 @@ static struct thin_c *get_first_thin(struct pool *pool) struct thin_c *tc = NULL; rcu_read_lock(); - if (!list_empty(&pool->active_thins)) { - tc = list_entry_rcu(pool->active_thins.next, struct thin_c, list); + tc = list_first_or_null_rcu(&pool->active_thins, struct thin_c, list); + if (tc) thin_get(tc); - } rcu_read_unlock(); return tc; diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index 62b1a44b8dd2..e61855da6461 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -40,35 +40,23 @@ static inline u64 fec_interleave(struct dm_verity *v, u64 offset) } /* - * Decode an RS block using Reed-Solomon. - */ -static int fec_decode_rs8(struct dm_verity *v, struct dm_verity_fec_io *fio, - u8 *data, u8 *fec, int neras) -{ - int i; - uint16_t par[DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN]; - - for (i = 0; i < v->fec->roots; i++) - par[i] = fec[i]; - - return decode_rs8(fio->rs, data, par, v->fec->rsn, NULL, neras, - fio->erasures, 0, NULL); -} - -/* * Read error-correcting codes for the requested RS block. Returns a pointer * to the data block. Caller is responsible for releasing buf. */ static u8 *fec_read_parity(struct dm_verity *v, u64 rsb, int index, - unsigned int *offset, struct dm_buffer **buf, - unsigned short ioprio) + unsigned int *offset, unsigned int par_buf_offset, + struct dm_buffer **buf, unsigned short ioprio) { u64 position, block, rem; u8 *res; + /* We have already part of parity bytes read, skip to the next block */ + if (par_buf_offset) + index++; + position = (index + rsb) * v->fec->roots; block = div64_u64_rem(position, v->fec->io_size, &rem); - *offset = (unsigned int)rem; + *offset = par_buf_offset ? 0 : (unsigned int)rem; res = dm_bufio_read_with_ioprio(v->fec->bufio, block, buf, ioprio); if (IS_ERR(res)) { @@ -128,11 +116,13 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_io *io, { int r, corrected = 0, res; struct dm_buffer *buf; - unsigned int n, i, offset; + unsigned int n, i, j, offset, par_buf_offset = 0; + uint16_t par_buf[DM_VERITY_FEC_RSM - DM_VERITY_FEC_MIN_RSN]; u8 *par, *block; struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size); - par = fec_read_parity(v, rsb, block_offset, &offset, &buf, bio_prio(bio)); + par = fec_read_parity(v, rsb, block_offset, &offset, + par_buf_offset, &buf, bio_prio(bio)); if (IS_ERR(par)) return PTR_ERR(par); @@ -142,7 +132,11 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_io *io, */ fec_for_each_buffer_rs_block(fio, n, i) { block = fec_buffer_rs_block(v, fio, n, i); - res = fec_decode_rs8(v, fio, block, &par[offset], neras); + for (j = 0; j < v->fec->roots - par_buf_offset; j++) + par_buf[par_buf_offset + j] = par[offset + j]; + /* Decode an RS block using Reed-Solomon */ + res = decode_rs8(fio->rs, block, par_buf, v->fec->rsn, + NULL, neras, fio->erasures, 0, NULL); if (res < 0) { r = res; goto error; @@ -155,12 +149,22 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_io *io, if (block_offset >= 1 << v->data_dev_block_bits) goto done; - /* read the next block when we run out of parity bytes */ - offset += v->fec->roots; + /* Read the next block when we run out of parity bytes */ + offset += (v->fec->roots - par_buf_offset); + /* Check if parity bytes are split between blocks */ + if (offset < v->fec->io_size && (offset + v->fec->roots) > v->fec->io_size) { + par_buf_offset = v->fec->io_size - offset; + for (j = 0; j < par_buf_offset; j++) + par_buf[j] = par[offset + j]; + offset += par_buf_offset; + } else + par_buf_offset = 0; + if (offset >= v->fec->io_size) { dm_bufio_release(buf); - par = fec_read_parity(v, rsb, block_offset, &offset, &buf, bio_prio(bio)); + par = fec_read_parity(v, rsb, block_offset, &offset, + par_buf_offset, &buf, bio_prio(bio)); if (IS_ERR(par)) return PTR_ERR(par); } @@ -724,10 +728,7 @@ int verity_fec_ctr(struct dm_verity *v) return -E2BIG; } - if ((f->roots << SECTOR_SHIFT) & ((1 << v->data_dev_block_bits) - 1)) - f->io_size = 1 << v->data_dev_block_bits; - else - f->io_size = v->fec->roots << SECTOR_SHIFT; + f->io_size = 1 << v->data_dev_block_bits; f->bufio = dm_bufio_client_create(f->dev->bdev, f->io_size, diff --git a/drivers/md/persistent-data/dm-array.c b/drivers/md/persistent-data/dm-array.c index 157c9bd2fed7..8f8792e55806 100644 --- a/drivers/md/persistent-data/dm-array.c +++ b/drivers/md/persistent-data/dm-array.c @@ -917,23 +917,27 @@ static int load_ablock(struct dm_array_cursor *c) if (c->block) unlock_ablock(c->info, c->block); - c->block = NULL; - c->ab = NULL; c->index = 0; r = dm_btree_cursor_get_value(&c->cursor, &key, &value_le); if (r) { DMERR("dm_btree_cursor_get_value failed"); - dm_btree_cursor_end(&c->cursor); + goto out; } else { r = get_ablock(c->info, le64_to_cpu(value_le), &c->block, &c->ab); if (r) { DMERR("get_ablock failed"); - dm_btree_cursor_end(&c->cursor); + goto out; } } + return 0; + +out: + dm_btree_cursor_end(&c->cursor); + c->block = NULL; + c->ab = NULL; return r; } @@ -956,10 +960,10 @@ EXPORT_SYMBOL_GPL(dm_array_cursor_begin); void dm_array_cursor_end(struct dm_array_cursor *c) { - if (c->block) { + if (c->block) unlock_ablock(c->info, c->block); - dm_btree_cursor_end(&c->cursor); - } + + dm_btree_cursor_end(&c->cursor); } EXPORT_SYMBOL_GPL(dm_array_cursor_end); @@ -999,6 +1003,7 @@ int dm_array_cursor_skip(struct dm_array_cursor *c, uint32_t count) } count -= remaining; + c->index += (remaining - 1); r = dm_array_cursor_next(c); } while (!r); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 611b02c8a8b3..c4bb8dfe1a45 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -173,6 +173,11 @@ enum nvme_quirks { * MSI (but not MSI-X) interrupts are broken and never fire. */ NVME_QUIRK_BROKEN_MSI = (1 << 21), + + /* + * Align dma pool segment size to 512 bytes + */ + NVME_QUIRK_DMAPOOL_ALIGN_512 = (1 << 22), }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 1a5ba80f1811..e2634f437f33 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2834,15 +2834,20 @@ static int nvme_disable_prepare_reset(struct nvme_dev *dev, bool shutdown) static int nvme_setup_prp_pools(struct nvme_dev *dev) { + size_t small_align = 256; + dev->prp_page_pool = dma_pool_create("prp list page", dev->dev, NVME_CTRL_PAGE_SIZE, NVME_CTRL_PAGE_SIZE, 0); if (!dev->prp_page_pool) return -ENOMEM; + if (dev->ctrl.quirks & NVME_QUIRK_DMAPOOL_ALIGN_512) + small_align = 512; + /* Optimisation for I/Os between 4k and 128k */ dev->prp_small_pool = dma_pool_create("prp list 256", dev->dev, - 256, 256, 0); + 256, small_align, 0); if (!dev->prp_small_pool) { dma_pool_destroy(dev->prp_page_pool); return -ENOMEM; @@ -3607,7 +3612,7 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_VDEVICE(REDHAT, 0x0010), /* Qemu emulated controller */ .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1217, 0x8760), /* O2 Micro 64GB Steam Deck */ - .driver_data = NVME_QUIRK_QDEPTH_ONE }, + .driver_data = NVME_QUIRK_DMAPOOL_ALIGN_512, }, { PCI_DEVICE(0x126f, 0x2262), /* Silicon Motion generic */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS | NVME_QUIRK_BOGUS_NID, }, diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 28c76a3e1bd2..b127d41dbbfe 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -2024,14 +2024,6 @@ static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl) return __nvme_tcp_alloc_io_queues(ctrl); } -static void nvme_tcp_destroy_io_queues(struct nvme_ctrl *ctrl, bool remove) -{ - nvme_tcp_stop_io_queues(ctrl); - if (remove) - nvme_remove_io_tag_set(ctrl); - nvme_tcp_free_io_queues(ctrl); -} - static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new) { int ret, nr_queues; @@ -2176,9 +2168,11 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl, nvme_sync_io_queues(ctrl); nvme_tcp_stop_io_queues(ctrl); nvme_cancel_tagset(ctrl); - if (remove) + if (remove) { nvme_unquiesce_io_queues(ctrl); - nvme_tcp_destroy_io_queues(ctrl, remove); + nvme_remove_io_tag_set(ctrl); + } + nvme_tcp_free_io_queues(ctrl); } static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl, @@ -2267,7 +2261,9 @@ destroy_io: nvme_sync_io_queues(ctrl); nvme_tcp_stop_io_queues(ctrl); nvme_cancel_tagset(ctrl); - nvme_tcp_destroy_io_queues(ctrl, new); + if (new) + nvme_remove_io_tag_set(ctrl); + nvme_tcp_free_io_queues(ctrl); } destroy_admin: nvme_stop_keep_alive(ctrl); diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 2962794ce881..fa89b0549c36 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -139,7 +139,7 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req, unsigned long idx; ctrl = req->sq->ctrl; - xa_for_each(&ctrl->subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) { /* we don't have the right data for file backed ns */ if (!ns->bdev) continue; @@ -331,9 +331,10 @@ static u32 nvmet_format_ana_group(struct nvmet_req *req, u32 grpid, u32 count = 0; if (!(req->cmd->get_log_page.lsp & NVME_ANA_LOG_RGO)) { - xa_for_each(&ctrl->subsys->namespaces, idx, ns) + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) { if (ns->anagrpid == grpid) desc->nsids[count++] = cpu_to_le32(ns->nsid); + } } desc->grpid = cpu_to_le32(grpid); @@ -772,7 +773,7 @@ static void nvmet_execute_identify_endgrp_list(struct nvmet_req *req) goto out; } - xa_for_each(&ctrl->subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) { if (ns->nsid <= min_endgid) continue; @@ -815,7 +816,7 @@ static void nvmet_execute_identify_nslist(struct nvmet_req *req, bool match_css) goto out; } - xa_for_each(&ctrl->subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) { if (ns->nsid <= min_nsid) continue; if (match_css && req->ns->csi != req->cmd->identify.csi) diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index eeee9e9b854c..2b030f0efc38 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -810,18 +810,6 @@ static struct configfs_attribute *nvmet_ns_attrs[] = { NULL, }; -bool nvmet_subsys_nsid_exists(struct nvmet_subsys *subsys, u32 nsid) -{ - struct config_item *ns_item; - char name[12]; - - snprintf(name, sizeof(name), "%u", nsid); - mutex_lock(&subsys->namespaces_group.cg_subsys->su_mutex); - ns_item = config_group_find_item(&subsys->namespaces_group, name); - mutex_unlock(&subsys->namespaces_group.cg_subsys->su_mutex); - return ns_item != NULL; -} - static void nvmet_ns_release(struct config_item *item) { struct nvmet_ns *ns = to_nvmet_ns(item); @@ -2254,12 +2242,17 @@ static ssize_t nvmet_root_discovery_nqn_store(struct config_item *item, const char *page, size_t count) { struct list_head *entry; + char *old_nqn, *new_nqn; size_t len; len = strcspn(page, "\n"); if (!len || len > NVMF_NQN_FIELD_LEN - 1) return -EINVAL; + new_nqn = kstrndup(page, len, GFP_KERNEL); + if (!new_nqn) + return -ENOMEM; + down_write(&nvmet_config_sem); list_for_each(entry, &nvmet_subsystems_group.cg_children) { struct config_item *item = @@ -2268,13 +2261,15 @@ static ssize_t nvmet_root_discovery_nqn_store(struct config_item *item, if (!strncmp(config_item_name(item), page, len)) { pr_err("duplicate NQN %s\n", config_item_name(item)); up_write(&nvmet_config_sem); + kfree(new_nqn); return -EINVAL; } } - memset(nvmet_disc_subsys->subsysnqn, 0, NVMF_NQN_FIELD_LEN); - memcpy(nvmet_disc_subsys->subsysnqn, page, len); + old_nqn = nvmet_disc_subsys->subsysnqn; + nvmet_disc_subsys->subsysnqn = new_nqn; up_write(&nvmet_config_sem); + kfree(old_nqn); return len; } diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 1f4e9989663b..fde6c555af61 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -127,7 +127,7 @@ static u32 nvmet_max_nsid(struct nvmet_subsys *subsys) unsigned long idx; u32 nsid = 0; - xa_for_each(&subsys->namespaces, idx, cur) + nvmet_for_each_enabled_ns(&subsys->namespaces, idx, cur) nsid = cur->nsid; return nsid; @@ -441,11 +441,14 @@ u16 nvmet_req_find_ns(struct nvmet_req *req) struct nvmet_subsys *subsys = nvmet_req_subsys(req); req->ns = xa_load(&subsys->namespaces, nsid); - if (unlikely(!req->ns)) { + if (unlikely(!req->ns || !req->ns->enabled)) { req->error_loc = offsetof(struct nvme_common_command, nsid); - if (nvmet_subsys_nsid_exists(subsys, nsid)) - return NVME_SC_INTERNAL_PATH_ERROR; - return NVME_SC_INVALID_NS | NVME_STATUS_DNR; + if (!req->ns) /* ns doesn't exist! */ + return NVME_SC_INVALID_NS | NVME_STATUS_DNR; + + /* ns exists but it's disabled */ + req->ns = NULL; + return NVME_SC_INTERNAL_PATH_ERROR; } percpu_ref_get(&req->ns->ref); @@ -583,8 +586,6 @@ int nvmet_ns_enable(struct nvmet_ns *ns) goto out_unlock; ret = -EMFILE; - if (subsys->nr_namespaces == NVMET_MAX_NAMESPACES) - goto out_unlock; ret = nvmet_bdev_ns_enable(ns); if (ret == -ENOTBLK) @@ -599,38 +600,19 @@ int nvmet_ns_enable(struct nvmet_ns *ns) list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) nvmet_p2pmem_ns_add_p2p(ctrl, ns); - ret = percpu_ref_init(&ns->ref, nvmet_destroy_namespace, - 0, GFP_KERNEL); - if (ret) - goto out_dev_put; - - if (ns->nsid > subsys->max_nsid) - subsys->max_nsid = ns->nsid; - - ret = xa_insert(&subsys->namespaces, ns->nsid, ns, GFP_KERNEL); - if (ret) - goto out_restore_subsys_maxnsid; - if (ns->pr.enable) { ret = nvmet_pr_init_ns(ns); if (ret) - goto out_remove_from_subsys; + goto out_dev_put; } - subsys->nr_namespaces++; - nvmet_ns_changed(subsys, ns->nsid); ns->enabled = true; + xa_set_mark(&subsys->namespaces, ns->nsid, NVMET_NS_ENABLED); ret = 0; out_unlock: mutex_unlock(&subsys->lock); return ret; - -out_remove_from_subsys: - xa_erase(&subsys->namespaces, ns->nsid); -out_restore_subsys_maxnsid: - subsys->max_nsid = nvmet_max_nsid(subsys); - percpu_ref_exit(&ns->ref); out_dev_put: list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) pci_dev_put(radix_tree_delete(&ctrl->p2p_ns_map, ns->nsid)); @@ -649,15 +631,37 @@ void nvmet_ns_disable(struct nvmet_ns *ns) goto out_unlock; ns->enabled = false; - xa_erase(&ns->subsys->namespaces, ns->nsid); - if (ns->nsid == subsys->max_nsid) - subsys->max_nsid = nvmet_max_nsid(subsys); + xa_clear_mark(&subsys->namespaces, ns->nsid, NVMET_NS_ENABLED); list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) pci_dev_put(radix_tree_delete(&ctrl->p2p_ns_map, ns->nsid)); mutex_unlock(&subsys->lock); + if (ns->pr.enable) + nvmet_pr_exit_ns(ns); + + mutex_lock(&subsys->lock); + nvmet_ns_changed(subsys, ns->nsid); + nvmet_ns_dev_disable(ns); +out_unlock: + mutex_unlock(&subsys->lock); +} + +void nvmet_ns_free(struct nvmet_ns *ns) +{ + struct nvmet_subsys *subsys = ns->subsys; + + nvmet_ns_disable(ns); + + mutex_lock(&subsys->lock); + + xa_erase(&subsys->namespaces, ns->nsid); + if (ns->nsid == subsys->max_nsid) + subsys->max_nsid = nvmet_max_nsid(subsys); + + mutex_unlock(&subsys->lock); + /* * Now that we removed the namespaces from the lookup list, we * can kill the per_cpu ref and wait for any remaining references @@ -671,21 +675,9 @@ void nvmet_ns_disable(struct nvmet_ns *ns) wait_for_completion(&ns->disable_done); percpu_ref_exit(&ns->ref); - if (ns->pr.enable) - nvmet_pr_exit_ns(ns); - mutex_lock(&subsys->lock); - subsys->nr_namespaces--; - nvmet_ns_changed(subsys, ns->nsid); - nvmet_ns_dev_disable(ns); -out_unlock: mutex_unlock(&subsys->lock); -} - -void nvmet_ns_free(struct nvmet_ns *ns) -{ - nvmet_ns_disable(ns); down_write(&nvmet_ana_sem); nvmet_ana_group_enabled[ns->anagrpid]--; @@ -699,15 +691,33 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid) { struct nvmet_ns *ns; + mutex_lock(&subsys->lock); + + if (subsys->nr_namespaces == NVMET_MAX_NAMESPACES) + goto out_unlock; + ns = kzalloc(sizeof(*ns), GFP_KERNEL); if (!ns) - return NULL; + goto out_unlock; init_completion(&ns->disable_done); ns->nsid = nsid; ns->subsys = subsys; + if (percpu_ref_init(&ns->ref, nvmet_destroy_namespace, 0, GFP_KERNEL)) + goto out_free; + + if (ns->nsid > subsys->max_nsid) + subsys->max_nsid = nsid; + + if (xa_insert(&subsys->namespaces, ns->nsid, ns, GFP_KERNEL)) + goto out_exit; + + subsys->nr_namespaces++; + + mutex_unlock(&subsys->lock); + down_write(&nvmet_ana_sem); ns->anagrpid = NVMET_DEFAULT_ANA_GRPID; nvmet_ana_group_enabled[ns->anagrpid]++; @@ -718,6 +728,14 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid) ns->csi = NVME_CSI_NVM; return ns; +out_exit: + subsys->max_nsid = nvmet_max_nsid(subsys); + percpu_ref_exit(&ns->ref); +out_free: + kfree(ns); +out_unlock: + mutex_unlock(&subsys->lock); + return NULL; } static void nvmet_update_sq_head(struct nvmet_req *req) @@ -1394,7 +1412,7 @@ static void nvmet_setup_p2p_ns_map(struct nvmet_ctrl *ctrl, ctrl->p2p_client = get_device(req->p2p_client); - xa_for_each(&ctrl->subsys->namespaces, idx, ns) + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) nvmet_p2pmem_ns_add_p2p(ctrl, ns); } diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index 0bda83d0fc3e..eaf31c823cbe 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -36,7 +36,7 @@ void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id) */ id->nsfeat |= 1 << 4; /* NPWG = Namespace Preferred Write Granularity. 0's based */ - id->npwg = lpp0b; + id->npwg = to0based(bdev_io_min(bdev) / bdev_logical_block_size(bdev)); /* NPWA = Namespace Preferred Write Alignment. 0's based */ id->npwa = id->npwg; /* NPDG = Namespace Preferred Deallocate Granularity. 0's based */ diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 58328b35dc96..7233549f7c8a 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -24,6 +24,7 @@ #define NVMET_DEFAULT_VS NVME_VS(2, 1, 0) +#define NVMET_NS_ENABLED XA_MARK_1 #define NVMET_ASYNC_EVENTS 4 #define NVMET_ERROR_LOG_SLOTS 128 #define NVMET_NO_ERROR_LOC ((u16)-1) @@ -33,6 +34,12 @@ #define NVMET_FR_MAX_SIZE 8 #define NVMET_PR_LOG_QUEUE_SIZE 64 +#define nvmet_for_each_ns(xa, index, entry) \ + xa_for_each(xa, index, entry) + +#define nvmet_for_each_enabled_ns(xa, index, entry) \ + xa_for_each_marked(xa, index, entry, NVMET_NS_ENABLED) + /* * Supported optional AENs: */ diff --git a/drivers/nvme/target/pr.c b/drivers/nvme/target/pr.c index 90e9f5bbe581..cd22d8333314 100644 --- a/drivers/nvme/target/pr.c +++ b/drivers/nvme/target/pr.c @@ -60,7 +60,7 @@ u16 nvmet_set_feat_resv_notif_mask(struct nvmet_req *req, u32 mask) goto success; } - xa_for_each(&ctrl->subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) { if (ns->pr.enable) WRITE_ONCE(ns->pr.notify_mask, mask); } @@ -1056,7 +1056,7 @@ int nvmet_ctrl_init_pr(struct nvmet_ctrl *ctrl) * nvmet_pr_init_ns(), see more details in nvmet_ns_enable(). * So just check ns->pr.enable. */ - xa_for_each(&subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&subsys->namespaces, idx, ns) { if (ns->pr.enable) { ret = nvmet_pr_alloc_and_insert_pc_ref(ns, ctrl->cntlid, &ctrl->hostid); @@ -1067,7 +1067,7 @@ int nvmet_ctrl_init_pr(struct nvmet_ctrl *ctrl) return 0; free_per_ctrl_refs: - xa_for_each(&subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&subsys->namespaces, idx, ns) { if (ns->pr.enable) { pc_ref = xa_erase(&ns->pr_per_ctrl_refs, ctrl->cntlid); if (pc_ref) @@ -1087,7 +1087,7 @@ void nvmet_ctrl_destroy_pr(struct nvmet_ctrl *ctrl) kfifo_free(&ctrl->pr_log_mgr.log_queue); mutex_destroy(&ctrl->pr_log_mgr.lock); - xa_for_each(&ctrl->subsys->namespaces, idx, ns) { + nvmet_for_each_enabled_ns(&ctrl->subsys->namespaces, idx, ns) { if (ns->pr.enable) { pc_ref = xa_erase(&ns->pr_per_ctrl_refs, ctrl->cntlid); if (pc_ref) diff --git a/drivers/ufs/core/ufshcd-priv.h b/drivers/ufs/core/ufshcd-priv.h index 9ffd94ddf8c7..786f20ef2238 100644 --- a/drivers/ufs/core/ufshcd-priv.h +++ b/drivers/ufs/core/ufshcd-priv.h @@ -237,12 +237,6 @@ static inline void ufshcd_vops_config_scaling_param(struct ufs_hba *hba, hba->vops->config_scaling_param(hba, p, data); } -static inline void ufshcd_vops_reinit_notify(struct ufs_hba *hba) -{ - if (hba->vops && hba->vops->reinit_notify) - hba->vops->reinit_notify(hba); -} - static inline int ufshcd_vops_mcq_config_resource(struct ufs_hba *hba) { if (hba->vops && hba->vops->mcq_config_resource) diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 8a01e4393159..9c26e8767515 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -8858,7 +8858,6 @@ static int ufshcd_probe_hba(struct ufs_hba *hba, bool init_dev_params) ufshcd_device_reset(hba); ufs_put_device_desc(hba); ufshcd_hba_stop(hba); - ufshcd_vops_reinit_notify(hba); ret = ufshcd_hba_enable(hba); if (ret) { dev_err(hba->dev, "Host controller enable failed\n"); @@ -10591,14 +10590,17 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) } /* - * Set the default power management level for runtime and system PM. + * Set the default power management level for runtime and system PM if + * not set by the host controller drivers. * Default power saving mode is to keep UFS link in Hibern8 state * and UFS device in sleep state. */ - hba->rpm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state( + if (!hba->rpm_lvl) + hba->rpm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state( UFS_SLEEP_PWR_MODE, UIC_LINK_HIBERN8_STATE); - hba->spm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state( + if (!hba->spm_lvl) + hba->spm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state( UFS_SLEEP_PWR_MODE, UIC_LINK_HIBERN8_STATE); diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index 68040b2ab5f8..91e94fe990b4 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -368,6 +368,11 @@ static int ufs_qcom_power_up_sequence(struct ufs_hba *hba) if (ret) return ret; + if (phy->power_count) { + phy_power_off(phy); + phy_exit(phy); + } + /* phy initialization - calibrate the phy */ ret = phy_init(phy); if (ret) { @@ -866,6 +871,7 @@ static u32 ufs_qcom_get_ufs_hci_version(struct ufs_hba *hba) */ static void ufs_qcom_advertise_quirks(struct ufs_hba *hba) { + const struct ufs_qcom_drvdata *drvdata = of_device_get_match_data(hba->dev); struct ufs_qcom_host *host = ufshcd_get_variant(hba); if (host->hw_ver.major == 0x2) @@ -874,9 +880,8 @@ static void ufs_qcom_advertise_quirks(struct ufs_hba *hba) if (host->hw_ver.major > 0x3) hba->quirks |= UFSHCD_QUIRK_REINIT_AFTER_MAX_GEAR_SWITCH; - if (of_device_is_compatible(hba->dev->of_node, "qcom,sm8550-ufshc") || - of_device_is_compatible(hba->dev->of_node, "qcom,sm8650-ufshc")) - hba->quirks |= UFSHCD_QUIRK_BROKEN_LSDBS_CAP; + if (drvdata && drvdata->quirks) + hba->quirks |= drvdata->quirks; } static void ufs_qcom_set_phy_gear(struct ufs_qcom_host *host) @@ -1064,6 +1069,7 @@ static int ufs_qcom_init(struct ufs_hba *hba) struct device *dev = hba->dev; struct ufs_qcom_host *host; struct ufs_clk_info *clki; + const struct ufs_qcom_drvdata *drvdata = of_device_get_match_data(hba->dev); host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL); if (!host) @@ -1143,6 +1149,9 @@ static int ufs_qcom_init(struct ufs_hba *hba) dev_warn(dev, "%s: failed to configure the testbus %d\n", __func__, err); + if (drvdata && drvdata->no_phy_retention) + hba->spm_lvl = UFS_PM_LVL_5; + return 0; out_variant_clear: @@ -1579,13 +1588,6 @@ static void ufs_qcom_config_scaling_param(struct ufs_hba *hba, } #endif -static void ufs_qcom_reinit_notify(struct ufs_hba *hba) -{ - struct ufs_qcom_host *host = ufshcd_get_variant(hba); - - phy_power_off(host->generic_phy); -} - /* Resources */ static const struct ufshcd_res_info ufs_res_info[RES_MAX] = { {.name = "ufs_mem",}, @@ -1825,7 +1827,6 @@ static const struct ufs_hba_variant_ops ufs_hba_qcom_vops = { .device_reset = ufs_qcom_device_reset, .config_scaling_param = ufs_qcom_config_scaling_param, .program_key = ufs_qcom_ice_program_key, - .reinit_notify = ufs_qcom_reinit_notify, .mcq_config_resource = ufs_qcom_mcq_config_resource, .get_hba_mac = ufs_qcom_get_hba_mac, .op_runtime_config = ufs_qcom_op_runtime_config, @@ -1868,9 +1869,15 @@ static void ufs_qcom_remove(struct platform_device *pdev) platform_device_msi_free_irqs_all(hba->dev); } +static const struct ufs_qcom_drvdata ufs_qcom_sm8550_drvdata = { + .quirks = UFSHCD_QUIRK_BROKEN_LSDBS_CAP, + .no_phy_retention = true, +}; + static const struct of_device_id ufs_qcom_of_match[] __maybe_unused = { { .compatible = "qcom,ufshc" }, - { .compatible = "qcom,sm8550-ufshc" }, + { .compatible = "qcom,sm8550-ufshc", .data = &ufs_qcom_sm8550_drvdata }, + { .compatible = "qcom,sm8650-ufshc", .data = &ufs_qcom_sm8550_drvdata }, {}, }; MODULE_DEVICE_TABLE(of, ufs_qcom_of_match); diff --git a/drivers/ufs/host/ufs-qcom.h b/drivers/ufs/host/ufs-qcom.h index b9de170983c9..919f53682beb 100644 --- a/drivers/ufs/host/ufs-qcom.h +++ b/drivers/ufs/host/ufs-qcom.h @@ -217,6 +217,11 @@ struct ufs_qcom_host { bool esi_enabled; }; +struct ufs_qcom_drvdata { + enum ufshcd_quirks quirks; + bool no_phy_retention; +}; + static inline u32 ufs_qcom_get_debug_reg_offset(struct ufs_qcom_host *host, u32 reg) { diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 1ab58da9f38a..1a4ed5a357d3 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -1661,14 +1661,15 @@ static vm_fault_t vfio_pci_mmap_huge_fault(struct vm_fault *vmf, unsigned long pfn, pgoff = vmf->pgoff - vma->vm_pgoff; vm_fault_t ret = VM_FAULT_SIGBUS; - if (order && (vmf->address & ((PAGE_SIZE << order) - 1) || + pfn = vma_to_pfn(vma) + pgoff; + + if (order && (pfn & ((1 << order) - 1) || + vmf->address & ((PAGE_SIZE << order) - 1) || vmf->address + (PAGE_SIZE << order) > vma->vm_end)) { ret = VM_FAULT_FALLBACK; goto out; } - pfn = vma_to_pfn(vma); - down_read(&vdev->memory_lock); if (vdev->pm_runtime_engaged || !__vfio_pci_memory_enabled(vdev)) @@ -1676,18 +1677,18 @@ static vm_fault_t vfio_pci_mmap_huge_fault(struct vm_fault *vmf, switch (order) { case 0: - ret = vmf_insert_pfn(vma, vmf->address, pfn + pgoff); + ret = vmf_insert_pfn(vma, vmf->address, pfn); break; #ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP case PMD_ORDER: - ret = vmf_insert_pfn_pmd(vmf, __pfn_to_pfn_t(pfn + pgoff, - PFN_DEV), false); + ret = vmf_insert_pfn_pmd(vmf, + __pfn_to_pfn_t(pfn, PFN_DEV), false); break; #endif #ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP case PUD_ORDER: - ret = vmf_insert_pfn_pud(vmf, __pfn_to_pfn_t(pfn + pgoff, - PFN_DEV), false); + ret = vmf_insert_pfn_pud(vmf, + __pfn_to_pfn_t(pfn, PFN_DEV), false); break; #endif default: diff --git a/drivers/watchdog/stm32_iwdg.c b/drivers/watchdog/stm32_iwdg.c index d700e0d49bb9..8ad06b54c5ad 100644 --- a/drivers/watchdog/stm32_iwdg.c +++ b/drivers/watchdog/stm32_iwdg.c @@ -286,7 +286,7 @@ static int stm32_iwdg_irq_init(struct platform_device *pdev, if (!wdt->data->has_early_wakeup) return 0; - irq = platform_get_irq(pdev, 0); + irq = platform_get_irq_optional(pdev, 0); if (irq <= 0) return 0; diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index 819c75233235..3bc9ce6c575e 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -57,6 +57,8 @@ static void v9fs_issue_write(struct netfs_io_subrequest *subreq) int err, len; len = p9_client_write(fid, subreq->start, &subreq->io_iter, &err); + if (len > 0) + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); netfs_write_subrequest_terminated(subreq, len ?: err, false); } @@ -80,8 +82,10 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq) if (pos + total >= i_size_read(rreq->inode)) __set_bit(NETFS_SREQ_HIT_EOF, &subreq->flags); - if (!err) + if (!err) { subreq->transferred += total; + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + } netfs_read_subreq_terminated(subreq, err, false); } diff --git a/fs/afs/write.c b/fs/afs/write.c index 34107b55f834..ccb6aa8027c5 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -122,7 +122,7 @@ static void afs_issue_write_worker(struct work_struct *work) if (subreq->debug_index == 3) return netfs_write_subrequest_terminated(subreq, -ENOANO, false); - if (!test_bit(NETFS_SREQ_RETRYING, &subreq->flags)) { + if (!subreq->retry_count) { set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); return netfs_write_subrequest_terminated(subreq, -EAGAIN, false); } @@ -149,6 +149,9 @@ static void afs_issue_write_worker(struct work_struct *work) afs_wait_for_operation(op); ret = afs_put_operation(op); switch (ret) { + case 0: + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + break; case -EACCES: case -EPERM: case -ENOKEY: diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 3af8bb0c8d75..4d9305fa37a8 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4878,25 +4878,29 @@ out_fail: return ret; } +struct btrfs_uring_encoded_data { + struct btrfs_ioctl_encoded_io_args args; + struct iovec iovstack[UIO_FASTIOV]; + struct iovec *iov; + struct iov_iter iter; +}; + static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue_flags) { size_t copy_end_kernel = offsetofend(struct btrfs_ioctl_encoded_io_args, flags); size_t copy_end; - struct btrfs_ioctl_encoded_io_args args = { 0 }; int ret; u64 disk_bytenr, disk_io_size; struct file *file; struct btrfs_inode *inode; struct btrfs_fs_info *fs_info; struct extent_io_tree *io_tree; - struct iovec iovstack[UIO_FASTIOV]; - struct iovec *iov = iovstack; - struct iov_iter iter; loff_t pos; struct kiocb kiocb; struct extent_state *cached_state = NULL; u64 start, lockend; void __user *sqe_addr; + struct btrfs_uring_encoded_data *data = io_uring_cmd_get_async_data(cmd)->op_data; if (!capable(CAP_SYS_ADMIN)) { ret = -EPERM; @@ -4910,43 +4914,64 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue if (issue_flags & IO_URING_F_COMPAT) { #if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) - struct btrfs_ioctl_encoded_io_args_32 args32; - copy_end = offsetofend(struct btrfs_ioctl_encoded_io_args_32, flags); - if (copy_from_user(&args32, sqe_addr, copy_end)) { - ret = -EFAULT; - goto out_acct; - } - args.iov = compat_ptr(args32.iov); - args.iovcnt = args32.iovcnt; - args.offset = args32.offset; - args.flags = args32.flags; #else return -ENOTTY; #endif } else { copy_end = copy_end_kernel; - if (copy_from_user(&args, sqe_addr, copy_end)) { - ret = -EFAULT; + } + + if (!data) { + data = kzalloc(sizeof(*data), GFP_NOFS); + if (!data) { + ret = -ENOMEM; goto out_acct; } - } - if (args.flags != 0) - return -EINVAL; + io_uring_cmd_get_async_data(cmd)->op_data = data; - ret = import_iovec(ITER_DEST, args.iov, args.iovcnt, ARRAY_SIZE(iovstack), - &iov, &iter); - if (ret < 0) - goto out_acct; + if (issue_flags & IO_URING_F_COMPAT) { +#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT) + struct btrfs_ioctl_encoded_io_args_32 args32; - if (iov_iter_count(&iter) == 0) { - ret = 0; - goto out_free; + if (copy_from_user(&args32, sqe_addr, copy_end)) { + ret = -EFAULT; + goto out_acct; + } + + data->args.iov = compat_ptr(args32.iov); + data->args.iovcnt = args32.iovcnt; + data->args.offset = args32.offset; + data->args.flags = args32.flags; +#endif + } else { + if (copy_from_user(&data->args, sqe_addr, copy_end)) { + ret = -EFAULT; + goto out_acct; + } + } + + if (data->args.flags != 0) { + ret = -EINVAL; + goto out_acct; + } + + data->iov = data->iovstack; + ret = import_iovec(ITER_DEST, data->args.iov, data->args.iovcnt, + ARRAY_SIZE(data->iovstack), &data->iov, + &data->iter); + if (ret < 0) + goto out_acct; + + if (iov_iter_count(&data->iter) == 0) { + ret = 0; + goto out_free; + } } - pos = args.offset; - ret = rw_verify_area(READ, file, &pos, args.len); + pos = data->args.offset; + ret = rw_verify_area(READ, file, &pos, data->args.len); if (ret < 0) goto out_free; @@ -4959,15 +4984,16 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue start = ALIGN_DOWN(pos, fs_info->sectorsize); lockend = start + BTRFS_MAX_UNCOMPRESSED - 1; - ret = btrfs_encoded_read(&kiocb, &iter, &args, &cached_state, + ret = btrfs_encoded_read(&kiocb, &data->iter, &data->args, &cached_state, &disk_bytenr, &disk_io_size); if (ret < 0 && ret != -EIOCBQUEUED) goto out_free; file_accessed(file); - if (copy_to_user(sqe_addr + copy_end, (const char *)&args + copy_end_kernel, - sizeof(args) - copy_end_kernel)) { + if (copy_to_user(sqe_addr + copy_end, + (const char *)&data->args + copy_end_kernel, + sizeof(data->args) - copy_end_kernel)) { if (ret == -EIOCBQUEUED) { unlock_extent(io_tree, start, lockend, &cached_state); btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); @@ -4977,40 +5003,22 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue } if (ret == -EIOCBQUEUED) { - u64 count; - - /* - * If we've optimized things by storing the iovecs on the stack, - * undo this. - */ - if (!iov) { - iov = kmalloc(sizeof(struct iovec) * args.iovcnt, GFP_NOFS); - if (!iov) { - unlock_extent(io_tree, start, lockend, &cached_state); - btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); - ret = -ENOMEM; - goto out_acct; - } - - memcpy(iov, iovstack, sizeof(struct iovec) * args.iovcnt); - } - - count = min_t(u64, iov_iter_count(&iter), disk_io_size); + u64 count = min_t(u64, iov_iter_count(&data->iter), disk_io_size); /* Match ioctl by not returning past EOF if uncompressed. */ - if (!args.compression) - count = min_t(u64, count, args.len); + if (!data->args.compression) + count = min_t(u64, count, data->args.len); - ret = btrfs_uring_read_extent(&kiocb, &iter, start, lockend, - cached_state, disk_bytenr, - disk_io_size, count, - args.compression, iov, cmd); + ret = btrfs_uring_read_extent(&kiocb, &data->iter, start, lockend, + cached_state, disk_bytenr, disk_io_size, + count, data->args.compression, + data->iov, cmd); goto out_acct; } out_free: - kfree(iov); + kfree(data->iov); out_acct: if (ret > 0) diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 204c928beaf9..531312efee8d 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1541,6 +1541,10 @@ static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg, u64 extent_gen; int ret; + if (unlikely(!extent_root)) { + btrfs_err(fs_info, "no valid extent root for scrub"); + return -EUCLEAN; + } memset(stripe->sectors, 0, sizeof(struct scrub_sector_verification) * stripe->nr_sectors); scrub_stripe_reset_bitmaps(stripe); diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index ddf0d5a448a7..c9e92c6941ec 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -174,10 +174,10 @@ int zlib_compress_folios(struct list_head *ws, struct address_space *mapping, copy_page(workspace->buf + i * PAGE_SIZE, data_in); start += PAGE_SIZE; - workspace->strm.avail_in = - (in_buf_folios << PAGE_SHIFT); } workspace->strm.next_in = workspace->buf; + workspace->strm.avail_in = min(bytes_left, + in_buf_folios << PAGE_SHIFT); } else { unsigned int pg_off; unsigned int cur_len; diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 11ed523e528e..df905ae82929 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -748,8 +748,9 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info) (u64)lim->max_segments << PAGE_SHIFT), fs_info->sectorsize); fs_info->fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_ZONED; - if (fs_info->max_zone_append_size < fs_info->max_extent_size) - fs_info->max_extent_size = fs_info->max_zone_append_size; + + fs_info->max_extent_size = min_not_zero(fs_info->max_extent_size, + fs_info->max_zone_append_size); /* * Check mount options here, because we might change fs_info->zoned diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 89b11336a836..1806bff8e59b 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -15,6 +15,7 @@ #include <linux/namei.h> #include <linux/poll.h> #include <linux/mount.h> +#include <linux/security.h> #include <linux/statfs.h> #include <linux/ctype.h> #include <linux/string.h> @@ -576,7 +577,7 @@ static int cachefiles_daemon_dir(struct cachefiles_cache *cache, char *args) */ static int cachefiles_daemon_secctx(struct cachefiles_cache *cache, char *args) { - char *secctx; + int err; _enter(",%s", args); @@ -585,16 +586,16 @@ static int cachefiles_daemon_secctx(struct cachefiles_cache *cache, char *args) return -EINVAL; } - if (cache->secctx) { + if (cache->have_secid) { pr_err("Second security context specified\n"); return -EINVAL; } - secctx = kstrdup(args, GFP_KERNEL); - if (!secctx) - return -ENOMEM; + err = security_secctx_to_secid(args, strlen(args), &cache->secid); + if (err) + return err; - cache->secctx = secctx; + cache->have_secid = true; return 0; } @@ -820,7 +821,6 @@ static void cachefiles_daemon_unbind(struct cachefiles_cache *cache) put_cred(cache->cache_cred); kfree(cache->rootdirname); - kfree(cache->secctx); kfree(cache->tag); _leave(""); diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index 7b99bd98de75..38c236e38cef 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -122,7 +122,6 @@ struct cachefiles_cache { #define CACHEFILES_STATE_CHANGED 3 /* T if state changed (poll trigger) */ #define CACHEFILES_ONDEMAND_MODE 4 /* T if in on-demand read mode */ char *rootdirname; /* name of cache root directory */ - char *secctx; /* LSM security context */ char *tag; /* cache binding tag */ refcount_t unbind_pincount;/* refcount to do daemon unbind */ struct xarray reqs; /* xarray of pending on-demand requests */ @@ -130,6 +129,8 @@ struct cachefiles_cache { struct xarray ondemand_ids; /* xarray for ondemand_id allocation */ u32 ondemand_id_next; u32 msg_id_next; + u32 secid; /* LSM security id */ + bool have_secid; /* whether "secid" was set */ }; static inline bool cachefiles_in_ondemand_mode(struct cachefiles_cache *cache) diff --git a/fs/cachefiles/security.c b/fs/cachefiles/security.c index fe777164f1d8..fc6611886b3b 100644 --- a/fs/cachefiles/security.c +++ b/fs/cachefiles/security.c @@ -18,7 +18,7 @@ int cachefiles_get_security_ID(struct cachefiles_cache *cache) struct cred *new; int ret; - _enter("{%s}", cache->secctx); + _enter("{%u}", cache->have_secid ? cache->secid : 0); new = prepare_kernel_cred(current); if (!new) { @@ -26,8 +26,8 @@ int cachefiles_get_security_ID(struct cachefiles_cache *cache) goto error; } - if (cache->secctx) { - ret = set_security_override_from_ctx(new, cache->secctx); + if (cache->have_secid) { + ret = set_security_override(new, cache->secid); if (ret < 0) { put_cred(new); pr_err("Security denies permission to nominate security context: error %d\n", diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index fe0a9b8a0cd0..3103b932b674 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -122,7 +122,7 @@ static int exfat_readdir(struct inode *inode, loff_t *cpos, struct exfat_dir_ent type = exfat_get_entry_type(ep); if (type == TYPE_UNUSED) { brelse(bh); - break; + goto out; } if (type != TYPE_FILE && type != TYPE_DIR) { @@ -170,6 +170,7 @@ static int exfat_readdir(struct inode *inode, loff_t *cpos, struct exfat_dir_ent } } +out: dir_entry->namebuf.lfn[0] = '\0'; *cpos = EXFAT_DEN_TO_B(dentry); return 0; diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c index 773c320d68f3..9e5492ac409b 100644 --- a/fs/exfat/fatent.c +++ b/fs/exfat/fatent.c @@ -216,6 +216,16 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain if (err) goto dec_used_clus; + + if (num_clusters >= sbi->num_clusters - EXFAT_FIRST_CLUSTER) { + /* + * The cluster chain includes a loop, scan the + * bitmap to get the number of used clusters. + */ + exfat_count_used_clusters(sb, &sbi->used_clusters); + + return 0; + } } while (clu != EXFAT_EOF_CLUSTER); } diff --git a/fs/exfat/file.c b/fs/exfat/file.c index fb38769c3e39..05b51e721783 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -545,6 +545,7 @@ static int exfat_extend_valid_size(struct file *file, loff_t new_valid_size) while (pos < new_valid_size) { u32 len; struct folio *folio; + unsigned long off; len = PAGE_SIZE - (pos & (PAGE_SIZE - 1)); if (pos + len > new_valid_size) @@ -554,6 +555,9 @@ static int exfat_extend_valid_size(struct file *file, loff_t new_valid_size) if (err) goto out; + off = offset_in_folio(folio, pos); + folio_zero_new_buffers(folio, off, off + len); + err = ops->write_end(file, mapping, pos, len, len, folio, NULL); if (err < 0) goto out; @@ -563,6 +567,8 @@ static int exfat_extend_valid_size(struct file *file, loff_t new_valid_size) cond_resched(); } + return 0; + out: return err; } diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index 97d2774760fe..099f80645072 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -330,8 +330,8 @@ static int exfat_find_empty_entry(struct inode *inode, while ((dentry = exfat_search_empty_slot(sb, &hint_femp, p_dir, num_entries, es)) < 0) { - if (dentry == -EIO) - break; + if (dentry != -ENOSPC) + return dentry; if (exfat_check_max_dentries(inode)) return -ENOSPC; diff --git a/fs/file.c b/fs/file.c index fb1011cf6b4a..25c6e53b03f8 100644 --- a/fs/file.c +++ b/fs/file.c @@ -22,6 +22,7 @@ #include <linux/close_range.h> #include <linux/file_ref.h> #include <net/sock.h> +#include <linux/init_task.h> #include "internal.h" diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 494ac372ace0..e540d05549ff 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1681,6 +1681,8 @@ static int fuse_dir_open(struct inode *inode, struct file *file) */ if (ff->open_flags & (FOPEN_STREAM | FOPEN_NONSEEKABLE)) nonseekable_open(inode, file); + if (!(ff->open_flags & FOPEN_KEEP_CACHE)) + invalidate_inode_pages2(inode->i_mapping); } return err; diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 3bee9b5dba5e..fe09c2093a93 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -349,11 +349,13 @@ static int hfs_fill_super(struct super_block *sb, struct fs_context *fc) goto bail_no_root; res = hfs_cat_find_brec(sb, HFS_ROOT_CNID, &fd); if (!res) { - if (fd.entrylength > sizeof(rec) || fd.entrylength < 0) { + if (fd.entrylength != sizeof(rec.dir)) { res = -EIO; goto bail_hfs_find; } hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, fd.entrylength); + if (rec.type != HFS_CDR_DIR) + res = -EIO; } if (res) goto bail_hfs_find; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 955f19e27e47..54dc27d92781 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1774,7 +1774,8 @@ static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos) */ static int iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct writeback_control *wbc, struct folio *folio, - struct inode *inode, loff_t pos, unsigned len) + struct inode *inode, loff_t pos, loff_t end_pos, + unsigned len) { struct iomap_folio_state *ifs = folio->private; size_t poff = offset_in_folio(folio, pos); @@ -1793,15 +1794,60 @@ new_ioend: if (ifs) atomic_add(len, &ifs->write_bytes_pending); + + /* + * Clamp io_offset and io_size to the incore EOF so that ondisk + * file size updates in the ioend completion are byte-accurate. + * This avoids recovering files with zeroed tail regions when + * writeback races with appending writes: + * + * Thread 1: Thread 2: + * ------------ ----------- + * write [A, A+B] + * update inode size to A+B + * submit I/O [A, A+BS] + * write [A+B, A+B+C] + * update inode size to A+B+C + * <I/O completes, updates disk size to min(A+B+C, A+BS)> + * <power failure> + * + * After reboot: + * 1) with A+B+C < A+BS, the file has zero padding in range + * [A+B, A+B+C] + * + * |< Block Size (BS) >| + * |DDDDDDDDDDDD0000000000000| + * ^ ^ ^ + * A A+B A+B+C + * (EOF) + * + * 2) with A+B+C > A+BS, the file has zero padding in range + * [A+B, A+BS] + * + * |< Block Size (BS) >|< Block Size (BS) >| + * |DDDDDDDDDDDD0000000000000|00000000000000000000000000| + * ^ ^ ^ ^ + * A A+B A+BS A+B+C + * (EOF) + * + * D = Valid Data + * 0 = Zero Padding + * + * Note that this defeats the ability to chain the ioends of + * appending writes. + */ wpc->ioend->io_size += len; + if (wpc->ioend->io_offset + wpc->ioend->io_size > end_pos) + wpc->ioend->io_size = end_pos - wpc->ioend->io_offset; + wbc_account_cgroup_owner(wbc, folio, len); return 0; } static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc, struct writeback_control *wbc, struct folio *folio, - struct inode *inode, u64 pos, unsigned dirty_len, - unsigned *count) + struct inode *inode, u64 pos, u64 end_pos, + unsigned dirty_len, unsigned *count) { int error; @@ -1826,7 +1872,7 @@ static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc, break; default: error = iomap_add_to_ioend(wpc, wbc, folio, inode, pos, - map_len); + end_pos, map_len); if (!error) (*count)++; break; @@ -1897,11 +1943,11 @@ static bool iomap_writepage_handle_eof(struct folio *folio, struct inode *inode, * remaining memory is zeroed when mapped, and writes to that * region are not written out to the file. * - * Also adjust the writeback range to skip all blocks entirely - * beyond i_size. + * Also adjust the end_pos to the end of file and skip writeback + * for all blocks entirely beyond i_size. */ folio_zero_segment(folio, poff, folio_size(folio)); - *end_pos = round_up(isize, i_blocksize(inode)); + *end_pos = isize; } return true; @@ -1914,6 +1960,7 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc, struct inode *inode = folio->mapping->host; u64 pos = folio_pos(folio); u64 end_pos = pos + folio_size(folio); + u64 end_aligned = 0; unsigned count = 0; int error = 0; u32 rlen; @@ -1955,9 +2002,10 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc, /* * Walk through the folio to find dirty areas to write back. */ - while ((rlen = iomap_find_dirty_range(folio, &pos, end_pos))) { + end_aligned = round_up(end_pos, i_blocksize(inode)); + while ((rlen = iomap_find_dirty_range(folio, &pos, end_aligned))) { error = iomap_writepage_map_blocks(wpc, wbc, folio, inode, - pos, rlen, &count); + pos, end_pos, rlen, &count); if (error) break; pos += rlen; diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 9153ff3a08e7..e8e80761ac73 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -772,9 +772,9 @@ start_journal_io: /* * If the journal is not located on the file system device, * then we must flush the file system device before we issue - * the commit record + * the commit record and update the journal tail sequence. */ - if (commit_transaction->t_need_data_flush && + if ((commit_transaction->t_need_data_flush || update_tail) && (journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) blkdev_issue_flush(journal->j_fs_dev); diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index 4556e4689024..ce63d5fde9c3 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c @@ -654,7 +654,7 @@ static void flush_descriptor(journal_t *journal, set_buffer_jwrite(descriptor); BUFFER_TRACE(descriptor, "write"); set_buffer_dirty(descriptor); - write_dirty_buffer(descriptor, REQ_SYNC); + write_dirty_buffer(descriptor, JBD2_JOURNAL_REQ_FLAGS); } #endif diff --git a/fs/namespace.c b/fs/namespace.c index 23e81c2a1e3f..6eec7794f707 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2055,9 +2055,15 @@ SYSCALL_DEFINE1(oldumount, char __user *, name) static bool is_mnt_ns_file(struct dentry *dentry) { + struct ns_common *ns; + /* Is this a proxy for a mount namespace? */ - return dentry->d_op == &ns_dentry_operations && - dentry->d_fsdata == &mntns_operations; + if (dentry->d_op != &ns_dentry_operations) + return false; + + ns = d_inode(dentry)->i_private; + + return ns->ops == &mntns_operations; } struct ns_common *from_mnt_ns(struct mnt_namespace *mnt) diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 7ac34550c403..4dc9b8286355 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -275,22 +275,14 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) netfs_stat(&netfs_n_rh_download); if (rreq->netfs_ops->prepare_read) { ret = rreq->netfs_ops->prepare_read(subreq); - if (ret < 0) { - atomic_dec(&rreq->nr_outstanding); - netfs_put_subrequest(subreq, false, - netfs_sreq_trace_put_cancel); - break; - } + if (ret < 0) + goto prep_failed; trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); } slice = netfs_prepare_read_iterator(subreq); - if (slice < 0) { - atomic_dec(&rreq->nr_outstanding); - netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); - ret = slice; - break; - } + if (slice < 0) + goto prep_iter_failed; rreq->netfs_ops->issue_read(subreq); goto done; @@ -302,6 +294,8 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) trace_netfs_sreq(subreq, netfs_sreq_trace_submit); netfs_stat(&netfs_n_rh_zero); slice = netfs_prepare_read_iterator(subreq); + if (slice < 0) + goto prep_iter_failed; __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); netfs_read_subreq_terminated(subreq, 0, false); goto done; @@ -310,6 +304,8 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) if (source == NETFS_READ_FROM_CACHE) { trace_netfs_sreq(subreq, netfs_sreq_trace_submit); slice = netfs_prepare_read_iterator(subreq); + if (slice < 0) + goto prep_iter_failed; netfs_read_cache_to_pagecache(rreq, subreq); goto done; } @@ -318,6 +314,14 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) WARN_ON_ONCE(1); break; + prep_iter_failed: + ret = slice; + prep_failed: + subreq->error = ret; + atomic_dec(&rreq->nr_outstanding); + netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_cancel); + break; + done: size -= slice; start += slice; diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index 88f2adfab75e..173e8b5e6a93 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -104,7 +104,6 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * trace_netfs_rreq(wreq, netfs_rreq_trace_wait_ip); wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS, TASK_UNINTERRUPTIBLE); - smp_rmb(); /* Read error/transferred after RIP flag */ ret = wreq->error; if (ret == 0) { ret = wreq->transferred; diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index 3cbb289535a8..e8624f5c7fcc 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -62,10 +62,14 @@ static void netfs_unlock_read_folio(struct netfs_io_subrequest *subreq, } else { trace_netfs_folio(folio, netfs_folio_trace_read_done); } + + folioq_clear(folioq, slot); } else { // TODO: Use of PG_private_2 is deprecated. if (test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) netfs_pgpriv2_mark_copy_to_cache(subreq, rreq, folioq, slot); + else + folioq_clear(folioq, slot); } if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { @@ -77,8 +81,6 @@ static void netfs_unlock_read_folio(struct netfs_io_subrequest *subreq, folio_unlock(folio); } } - - folioq_clear(folioq, slot); } /* @@ -247,16 +249,17 @@ donation_changed: /* Deal with the trickiest case: that this subreq is in the middle of a * folio, not touching either edge, but finishes first. In such a - * case, we donate to the previous subreq, if there is one, so that the - * donation is only handled when that completes - and remove this - * subreq from the list. + * case, we donate to the previous subreq, if there is one and if it is + * contiguous, so that the donation is only handled when that completes + * - and remove this subreq from the list. * * If the previous subreq finished first, we will have acquired their * donation and should be able to unlock folios and/or donate nextwards. */ if (!subreq->consumed && !prev_donated && - !list_is_first(&subreq->rreq_link, &rreq->subrequests)) { + !list_is_first(&subreq->rreq_link, &rreq->subrequests) && + subreq->start == prev->start + prev->len) { prev = list_prev_entry(subreq, rreq_link); WRITE_ONCE(prev->next_donated, prev->next_donated + subreq->len); subreq->start += subreq->len; @@ -378,8 +381,7 @@ static void netfs_rreq_assess(struct netfs_io_request *rreq) task_io_account_read(rreq->transferred); trace_netfs_rreq(rreq, netfs_rreq_trace_wake_ip); - clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); - wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); + clear_and_wake_up_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags); trace_netfs_rreq(rreq, netfs_rreq_trace_done); netfs_clear_subrequests(rreq, false); @@ -438,7 +440,7 @@ void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq, rreq->origin == NETFS_READPAGE || rreq->origin == NETFS_READ_FOR_WRITE)) { netfs_consume_read_data(subreq, was_async); - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); } } EXPORT_SYMBOL(netfs_read_subreq_progress); @@ -497,7 +499,7 @@ void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq, rreq->origin == NETFS_READPAGE || rreq->origin == NETFS_READ_FOR_WRITE)) { netfs_consume_read_data(subreq, was_async); - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); + __set_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); } rreq->transferred += subreq->transferred; } @@ -511,10 +513,13 @@ void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq, } else { trace_netfs_sreq(subreq, netfs_sreq_trace_short); if (subreq->transferred > subreq->consumed) { - __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - __clear_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags); - set_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags); - } else if (!__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) { + /* If we didn't read new data, abandon retry. */ + if (subreq->retry_count && + test_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags)) { + __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); + set_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags); + } + } else if (test_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags)) { __set_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); set_bit(NETFS_RREQ_NEED_RETRY, &rreq->flags); } else { diff --git a/fs/netfs/read_pgpriv2.c b/fs/netfs/read_pgpriv2.c index ba5af89d37fa..54d5004fec18 100644 --- a/fs/netfs/read_pgpriv2.c +++ b/fs/netfs/read_pgpriv2.c @@ -170,6 +170,10 @@ void netfs_pgpriv2_write_to_the_cache(struct netfs_io_request *rreq) trace_netfs_write(wreq, netfs_write_trace_copy_to_cache); netfs_stat(&netfs_n_wh_copy_to_cache); + if (!wreq->io_streams[1].avail) { + netfs_put_request(wreq, false, netfs_rreq_trace_put_return); + goto couldnt_start; + } for (;;) { error = netfs_pgpriv2_copy_folio(wreq, folio); diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c index 0350592ea804..21b4a54e545e 100644 --- a/fs/netfs/read_retry.c +++ b/fs/netfs/read_retry.c @@ -49,13 +49,15 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) * up to the first permanently failed one. */ if (!rreq->netfs_ops->prepare_read && - !test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags)) { + !rreq->cache_resources.ops) { struct netfs_io_subrequest *subreq; list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) break; if (__test_and_clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) { + __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + subreq->retry_count++; netfs_reset_iter(subreq); netfs_reissue_read(rreq, subreq); } @@ -137,7 +139,8 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) stream0->sreq_max_len = subreq->len; __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); + __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); + subreq->retry_count++; spin_lock_bh(&rreq->lock); list_add_tail(&subreq->rreq_link, &rreq->subrequests); @@ -213,7 +216,6 @@ abandon: subreq->error = -ENOMEM; __clear_bit(NETFS_SREQ_FAILED, &subreq->flags); __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - __clear_bit(NETFS_SREQ_RETRYING, &subreq->flags); } spin_lock_bh(&rreq->lock); list_splice_tail_init(&queue, &rreq->subrequests); diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 1d438be2e1b4..ca3a11ed9b54 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -179,7 +179,6 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, struct iov_iter source = subreq->io_iter; iov_iter_revert(&source, subreq->len - source.count); - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); netfs_reissue_write(stream, subreq, &source); } @@ -234,7 +233,7 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, /* Renegotiate max_len (wsize) */ trace_netfs_sreq(subreq, netfs_sreq_trace_retry); __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); + subreq->retry_count++; stream->prepare_write(subreq); part = min(len, stream->sreq_max_len); @@ -279,7 +278,7 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, subreq->start = start; subreq->debug_index = atomic_inc_return(&wreq->subreq_counter); subreq->stream_nr = to->stream_nr; - __set_bit(NETFS_SREQ_RETRYING, &subreq->flags); + subreq->retry_count = 1; trace_netfs_sreq_ref(wreq->debug_id, subreq->debug_index, refcount_read(&subreq->ref), @@ -501,8 +500,7 @@ reassess_streams: goto need_retry; if ((notes & MADE_PROGRESS) && test_bit(NETFS_RREQ_PAUSE, &wreq->flags)) { trace_netfs_rreq(wreq, netfs_rreq_trace_unpause); - clear_bit_unlock(NETFS_RREQ_PAUSE, &wreq->flags); - wake_up_bit(&wreq->flags, NETFS_RREQ_PAUSE); + clear_and_wake_up_bit(NETFS_RREQ_PAUSE, &wreq->flags); } if (notes & NEED_REASSESS) { @@ -605,8 +603,7 @@ void netfs_write_collection_worker(struct work_struct *work) _debug("finished"); trace_netfs_rreq(wreq, netfs_rreq_trace_wake_ip); - clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &wreq->flags); - wake_up_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS); + clear_and_wake_up_bit(NETFS_RREQ_IN_PROGRESS, &wreq->flags); if (wreq->iocb) { size_t written = min(wreq->transferred, wreq->len); @@ -714,8 +711,7 @@ void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error, trace_netfs_sreq(subreq, netfs_sreq_trace_terminated); - clear_bit_unlock(NETFS_SREQ_IN_PROGRESS, &subreq->flags); - wake_up_bit(&subreq->flags, NETFS_SREQ_IN_PROGRESS); + clear_and_wake_up_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); /* If we are at the head of the queue, wake up the collector, * transferring a ref to it if we were the ones to do so. diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index bf6d507578e5..ff0e82505a0b 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -244,6 +244,8 @@ void netfs_reissue_write(struct netfs_io_stream *stream, iov_iter_advance(source, size); iov_iter_truncate(&subreq->io_iter, size); + subreq->retry_count++; + __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); netfs_do_issue_write(stream, subreq); } diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 810269ee0a50..d49e4ce27999 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -263,6 +263,12 @@ int nfs_netfs_readahead(struct readahead_control *ractl) static atomic_t nfs_netfs_debug_id; static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *file) { + if (!file) { + if (WARN_ON_ONCE(rreq->origin != NETFS_PGPRIV2_COPY_TO_CACHE)) + return -EIO; + return 0; + } + rreq->netfs_priv = get_nfs_open_context(nfs_file_open_context(file)); rreq->debug_id = atomic_inc_return(&nfs_netfs_debug_id); /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ @@ -274,7 +280,8 @@ static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *fi static void nfs_netfs_free_request(struct netfs_io_request *rreq) { - put_nfs_open_context(rreq->netfs_priv); + if (rreq->netfs_priv) + put_nfs_open_context(rreq->netfs_priv); } static struct nfs_netfs_io_data *nfs_netfs_alloc(struct netfs_io_subrequest *sreq) diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index dec553034027..e933f9c65d90 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -47,10 +47,8 @@ static void show_mark_fhandle(struct seq_file *m, struct inode *inode) size = f->handle_bytes >> 2; ret = exportfs_encode_fid(inode, (struct fid *)f->f_handle, &size); - if ((ret == FILEID_INVALID) || (ret < 0)) { - WARN_ONCE(1, "Can't encode file handler for inotify: %d\n", ret); + if ((ret == FILEID_INVALID) || (ret < 0)) return; - } f->handle_type = ret; f->handle_bytes = size * sizeof(u32); diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index 2b0daced98eb..3404e7a30c33 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -893,7 +893,7 @@ static int ocfs2_get_next_id(struct super_block *sb, struct kqid *qid) int status = 0; trace_ocfs2_get_next_id(from_kqid(&init_user_ns, *qid), type); - if (!sb_has_quota_loaded(sb, type)) { + if (!sb_has_quota_active(sb, type)) { status = -ESRCH; goto out; } diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 73d3367c533b..2956d888c131 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -867,6 +867,7 @@ out: brelse(oinfo->dqi_libh); brelse(oinfo->dqi_lqi_bh); kfree(oinfo); + info->dqi_priv = NULL; return status; } diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 3601ddfeddc2..0c28e5fa3407 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -415,13 +415,13 @@ int ovl_set_attr(struct ovl_fs *ofs, struct dentry *upperdentry, return err; } -struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real, +struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct inode *realinode, bool is_upper) { struct ovl_fh *fh; int fh_type, dwords; int buflen = MAX_HANDLE_SZ; - uuid_t *uuid = &real->d_sb->s_uuid; + uuid_t *uuid = &realinode->i_sb->s_uuid; int err; /* Make sure the real fid stays 32bit aligned */ @@ -438,13 +438,13 @@ struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real, * the price or reconnecting the dentry. */ dwords = buflen >> 2; - fh_type = exportfs_encode_fh(real, (void *)fh->fb.fid, &dwords, 0); + fh_type = exportfs_encode_inode_fh(realinode, (void *)fh->fb.fid, + &dwords, NULL, 0); buflen = (dwords << 2); err = -EIO; - if (WARN_ON(fh_type < 0) || - WARN_ON(buflen > MAX_HANDLE_SZ) || - WARN_ON(fh_type == FILEID_INVALID)) + if (fh_type < 0 || fh_type == FILEID_INVALID || + WARN_ON(buflen > MAX_HANDLE_SZ)) goto out_err; fh->fb.version = OVL_FH_VERSION; @@ -480,7 +480,7 @@ struct ovl_fh *ovl_get_origin_fh(struct ovl_fs *ofs, struct dentry *origin) if (!ovl_can_decode_fh(origin->d_sb)) return NULL; - return ovl_encode_real_fh(ofs, origin, false); + return ovl_encode_real_fh(ofs, d_inode(origin), false); } int ovl_set_origin_fh(struct ovl_fs *ofs, const struct ovl_fh *fh, @@ -505,7 +505,7 @@ static int ovl_set_upper_fh(struct ovl_fs *ofs, struct dentry *upper, const struct ovl_fh *fh; int err; - fh = ovl_encode_real_fh(ofs, upper, true); + fh = ovl_encode_real_fh(ofs, d_inode(upper), true); if (IS_ERR(fh)) return PTR_ERR(fh); diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index 5868cb222955..444aeeccb6da 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -176,35 +176,37 @@ static int ovl_connect_layer(struct dentry *dentry) * * Return 0 for upper file handle, > 0 for lower file handle or < 0 on error. */ -static int ovl_check_encode_origin(struct dentry *dentry) +static int ovl_check_encode_origin(struct inode *inode) { - struct ovl_fs *ofs = OVL_FS(dentry->d_sb); + struct ovl_fs *ofs = OVL_FS(inode->i_sb); bool decodable = ofs->config.nfs_export; + struct dentry *dentry; + int err; /* No upper layer? */ if (!ovl_upper_mnt(ofs)) return 1; /* Lower file handle for non-upper non-decodable */ - if (!ovl_dentry_upper(dentry) && !decodable) + if (!ovl_inode_upper(inode) && !decodable) return 1; /* Upper file handle for pure upper */ - if (!ovl_dentry_lower(dentry)) + if (!ovl_inode_lower(inode)) return 0; /* * Root is never indexed, so if there's an upper layer, encode upper for * root. */ - if (dentry == dentry->d_sb->s_root) + if (inode == d_inode(inode->i_sb->s_root)) return 0; /* * Upper decodable file handle for non-indexed upper. */ - if (ovl_dentry_upper(dentry) && decodable && - !ovl_test_flag(OVL_INDEX, d_inode(dentry))) + if (ovl_inode_upper(inode) && decodable && + !ovl_test_flag(OVL_INDEX, inode)) return 0; /* @@ -213,14 +215,23 @@ static int ovl_check_encode_origin(struct dentry *dentry) * ovl_connect_layer() will try to make origin's layer "connected" by * copying up a "connectable" ancestor. */ - if (d_is_dir(dentry) && decodable) - return ovl_connect_layer(dentry); + if (!decodable || !S_ISDIR(inode->i_mode)) + return 1; + + dentry = d_find_any_alias(inode); + if (!dentry) + return -ENOENT; + + err = ovl_connect_layer(dentry); + dput(dentry); + if (err < 0) + return err; /* Lower file handle for indexed and non-upper dir/non-dir */ return 1; } -static int ovl_dentry_to_fid(struct ovl_fs *ofs, struct dentry *dentry, +static int ovl_dentry_to_fid(struct ovl_fs *ofs, struct inode *inode, u32 *fid, int buflen) { struct ovl_fh *fh = NULL; @@ -231,13 +242,13 @@ static int ovl_dentry_to_fid(struct ovl_fs *ofs, struct dentry *dentry, * Check if we should encode a lower or upper file handle and maybe * copy up an ancestor to make lower file handle connectable. */ - err = enc_lower = ovl_check_encode_origin(dentry); + err = enc_lower = ovl_check_encode_origin(inode); if (enc_lower < 0) goto fail; /* Encode an upper or lower file handle */ - fh = ovl_encode_real_fh(ofs, enc_lower ? ovl_dentry_lower(dentry) : - ovl_dentry_upper(dentry), !enc_lower); + fh = ovl_encode_real_fh(ofs, enc_lower ? ovl_inode_lower(inode) : + ovl_inode_upper(inode), !enc_lower); if (IS_ERR(fh)) return PTR_ERR(fh); @@ -251,8 +262,8 @@ out: return err; fail: - pr_warn_ratelimited("failed to encode file handle (%pd2, err=%i)\n", - dentry, err); + pr_warn_ratelimited("failed to encode file handle (ino=%lu, err=%i)\n", + inode->i_ino, err); goto out; } @@ -260,19 +271,13 @@ static int ovl_encode_fh(struct inode *inode, u32 *fid, int *max_len, struct inode *parent) { struct ovl_fs *ofs = OVL_FS(inode->i_sb); - struct dentry *dentry; int bytes, buflen = *max_len << 2; /* TODO: encode connectable file handles */ if (parent) return FILEID_INVALID; - dentry = d_find_any_alias(inode); - if (!dentry) - return FILEID_INVALID; - - bytes = ovl_dentry_to_fid(ofs, dentry, fid, buflen); - dput(dentry); + bytes = ovl_dentry_to_fid(ofs, inode, fid, buflen); if (bytes <= 0) return FILEID_INVALID; diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index 7e27b7d4adee..cea820cb3b55 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -542,7 +542,7 @@ int ovl_verify_origin_xattr(struct ovl_fs *ofs, struct dentry *dentry, struct ovl_fh *fh; int err; - fh = ovl_encode_real_fh(ofs, real, is_upper); + fh = ovl_encode_real_fh(ofs, d_inode(real), is_upper); err = PTR_ERR(fh); if (IS_ERR(fh)) { fh = NULL; @@ -738,7 +738,7 @@ int ovl_get_index_name(struct ovl_fs *ofs, struct dentry *origin, struct ovl_fh *fh; int err; - fh = ovl_encode_real_fh(ofs, origin, false); + fh = ovl_encode_real_fh(ofs, d_inode(origin), false); if (IS_ERR(fh)) return PTR_ERR(fh); diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index b361f35762be..0021e2025020 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -865,7 +865,7 @@ int ovl_copy_up_with_data(struct dentry *dentry); int ovl_maybe_copy_up(struct dentry *dentry, int flags); int ovl_copy_xattr(struct super_block *sb, const struct path *path, struct dentry *new); int ovl_set_attr(struct ovl_fs *ofs, struct dentry *upper, struct kstat *stat); -struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct dentry *real, +struct ovl_fh *ovl_encode_real_fh(struct ovl_fs *ofs, struct inode *realinode, bool is_upper); struct ovl_fh *ovl_get_origin_fh(struct ovl_fs *ofs, struct dentry *origin); int ovl_set_origin_fh(struct ovl_fs *ofs, const struct ovl_fh *fh, diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 38a5a3e9cba2..f02cd362309a 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1810,7 +1810,7 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, } for (; addr != end; addr += PAGE_SIZE, idx++) { - unsigned long cur_flags = flags; + u64 cur_flags = flags; pagemap_entry_t pme; if (folio && (flags & PM_PRESENT) && diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c index 85925ec0051a..3310d1ad4d0e 100644 --- a/fs/qnx6/inode.c +++ b/fs/qnx6/inode.c @@ -179,8 +179,7 @@ static int qnx6_statfs(struct dentry *dentry, struct kstatfs *buf) */ static const char *qnx6_checkroot(struct super_block *s) { - static char match_root[2][3] = {".\0\0", "..\0"}; - int i, error = 0; + int error = 0; struct qnx6_dir_entry *dir_entry; struct inode *root = d_inode(s->s_root); struct address_space *mapping = root->i_mapping; @@ -189,11 +188,9 @@ static const char *qnx6_checkroot(struct super_block *s) if (IS_ERR(folio)) return "error reading root directory"; dir_entry = kmap_local_folio(folio, 0); - for (i = 0; i < 2; i++) { - /* maximum 3 bytes - due to match_root limitation */ - if (strncmp(dir_entry[i].de_fname, match_root[i], 3)) - error = 1; - } + if (memcmp(dir_entry[0].de_fname, ".", 2) || + memcmp(dir_entry[1].de_fname, "..", 3)) + error = 1; folio_release_kmap(folio, dir_entry); if (error) return "error reading root directory."; diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index bd42a419458e..6cb1e81993f8 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1319,14 +1319,16 @@ cifs_readv_callback(struct mid_q_entry *mid) } if (rdata->result == -ENODATA) { - __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; + __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); } else { size_t trans = rdata->subreq.transferred + rdata->got_bytes; if (trans < rdata->subreq.len && rdata->subreq.start + trans == ictx->remote_i_size) { - __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; + __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); + } else if (rdata->got_bytes > 0) { + __set_bit(NETFS_SREQ_MADE_PROGRESS, &rdata->subreq.flags); } } @@ -1670,10 +1672,13 @@ cifs_writev_callback(struct mid_q_entry *mid) if (written > wdata->subreq.len) written &= 0xFFFF; - if (written < wdata->subreq.len) + if (written < wdata->subreq.len) { result = -ENOSPC; - else + } else { result = written; + if (written > 0) + __set_bit(NETFS_SREQ_MADE_PROGRESS, &wdata->subreq.flags); + } break; case MID_REQUEST_SUBMITTED: case MID_RETRY_NEEDED: diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 959359301250..0577556f0a41 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4615,6 +4615,7 @@ smb2_readv_callback(struct mid_q_entry *mid) __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; } + __set_bit(NETFS_SREQ_MADE_PROGRESS, &rdata->subreq.flags); } trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, rdata->credits.value, server->credits, server->in_flight, @@ -4842,10 +4843,12 @@ smb2_writev_callback(struct mid_q_entry *mid) cifs_stats_bytes_written(tcon, written); - if (written < wdata->subreq.len) + if (written < wdata->subreq.len) { wdata->result = -ENOSPC; - else + } else if (written > 0) { wdata->subreq.len = written; + __set_bit(NETFS_SREQ_MADE_PROGRESS, &wdata->subreq.flags); + } break; case MID_REQUEST_SUBMITTED: case MID_RETRY_NEEDED: @@ -5014,7 +5017,7 @@ smb2_async_writev(struct cifs_io_subrequest *wdata) } #endif - if (test_bit(NETFS_SREQ_RETRYING, &wdata->subreq.flags)) + if (wdata->subreq.retry_count > 0) smb2_set_replay(server, &rqst); cifs_dbg(FYI, "async write at %llu %u bytes iter=%zx\n", diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h index 0d5448c0b86c..a3ce553413de 100644 --- a/include/linux/io_uring/cmd.h +++ b/include/linux/io_uring/cmd.h @@ -18,6 +18,11 @@ struct io_uring_cmd { u8 pdu[32]; /* available inline for free use */ }; +struct io_uring_cmd_data { + struct io_uring_sqe sqes[2]; + void *op_data; +}; + static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) { return sqe->cmd; @@ -113,4 +118,9 @@ static inline struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd return cmd_to_io_kiocb(cmd)->tctx->task; } +static inline struct io_uring_cmd_data *io_uring_cmd_get_async_data(struct io_uring_cmd *cmd) +{ + return cmd_to_io_kiocb(cmd)->async_data; +} + #endif /* _LINUX_IO_URING_CMD_H */ diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 5675af6b740c..75bf54e76f3b 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -335,7 +335,7 @@ struct iomap_ioend { u16 io_type; u16 io_flags; /* IOMAP_F_* */ struct inode *io_inode; /* file being written to */ - size_t io_size; /* size of the extent */ + size_t io_size; /* size of data within eof */ loff_t io_offset; /* offset in the file */ sector_t io_sector; /* start sector of ioend */ struct bio io_bio; /* MUST BE LAST! */ diff --git a/include/linux/memfd.h b/include/linux/memfd.h index 3f2cf339ceaf..d437e3070850 100644 --- a/include/linux/memfd.h +++ b/include/linux/memfd.h @@ -7,6 +7,7 @@ #ifdef CONFIG_MEMFD_CREATE extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg); struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx); +unsigned int *memfd_file_seals_ptr(struct file *file); #else static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a) { @@ -16,6 +17,19 @@ static inline struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx) { return ERR_PTR(-EINVAL); } + +static inline unsigned int *memfd_file_seals_ptr(struct file *file) +{ + return NULL; +} #endif +/* Retrieve memfd seals associated with the file, if any. */ +static inline unsigned int memfd_file_seals(struct file *file) +{ + unsigned int *sealsp = memfd_file_seals_ptr(file); + + return sealsp ? *sealsp : 0; +} + #endif /* __LINUX_MEMFD_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 338a76ce9083..b1c3db9cf355 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3125,6 +3125,7 @@ static inline bool pagetable_pmd_ctor(struct ptdesc *ptdesc) if (!pmd_ptlock_init(ptdesc)) return false; __folio_set_pgtable(folio); + ptdesc_pmd_pts_init(ptdesc); lruvec_stat_add_folio(folio, NR_PAGETABLE); return true; } @@ -4101,6 +4102,37 @@ void mem_dump_obj(void *object); static inline void mem_dump_obj(void *object) {} #endif +static inline bool is_write_sealed(int seals) +{ + return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE); +} + +/** + * is_readonly_sealed - Checks whether write-sealed but mapped read-only, + * in which case writes should be disallowing moving + * forwards. + * @seals: the seals to check + * @vm_flags: the VMA flags to check + * + * Returns whether readonly sealed, in which case writess should be disallowed + * going forward. + */ +static inline bool is_readonly_sealed(int seals, vm_flags_t vm_flags) +{ + /* + * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as + * MAP_SHARED and read-only, take care to not allow mprotect to + * revert protections on such mappings. Do this only for shared + * mappings. For private mappings, don't need to mask + * VM_MAYWRITE as we still want them to be COW-writable. + */ + if (is_write_sealed(seals) && + ((vm_flags & (VM_SHARED | VM_WRITE)) == VM_SHARED)) + return true; + + return false; +} + /** * seal_check_write - Check for F_SEAL_WRITE or F_SEAL_FUTURE_WRITE flags and * handle them. @@ -4112,24 +4144,15 @@ static inline void mem_dump_obj(void *object) {} */ static inline int seal_check_write(int seals, struct vm_area_struct *vma) { - if (seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { - /* - * New PROT_WRITE and MAP_SHARED mmaps are not allowed when - * write seals are active. - */ - if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) - return -EPERM; - - /* - * Since an F_SEAL_[FUTURE_]WRITE sealed memfd can be mapped as - * MAP_SHARED and read-only, take care to not allow mprotect to - * revert protections on such mappings. Do this only for shared - * mappings. For private mappings, don't need to mask - * VM_MAYWRITE as we still want them to be COW-writable. - */ - if (vma->vm_flags & VM_SHARED) - vm_flags_clear(vma, VM_MAYWRITE); - } + if (!is_write_sealed(seals)) + return 0; + + /* + * New PROT_WRITE and MAP_SHARED mmaps are not allowed when + * write seals are active. + */ + if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) + return -EPERM; return 0; } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7361a8f3ab68..332cee285662 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -445,6 +445,7 @@ FOLIO_MATCH(compound_head, _head_2a); * @pt_index: Used for s390 gmap. * @pt_mm: Used for x86 pgds. * @pt_frag_refcount: For fragmented page table tracking. Powerpc only. + * @pt_share_count: Used for HugeTLB PMD page table share count. * @_pt_pad_2: Padding to ensure proper alignment. * @ptl: Lock for the page table. * @__page_type: Same as page->page_type. Unused for page tables. @@ -471,6 +472,9 @@ struct ptdesc { pgoff_t pt_index; struct mm_struct *pt_mm; atomic_t pt_frag_refcount; +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING + atomic_t pt_share_count; +#endif }; union { @@ -516,6 +520,32 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page)); const struct page *: (const struct ptdesc *)(p), \ struct page *: (struct ptdesc *)(p))) +#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ + atomic_set(&ptdesc->pt_share_count, 0); +} + +static inline void ptdesc_pmd_pts_inc(struct ptdesc *ptdesc) +{ + atomic_inc(&ptdesc->pt_share_count); +} + +static inline void ptdesc_pmd_pts_dec(struct ptdesc *ptdesc) +{ + atomic_dec(&ptdesc->pt_share_count); +} + +static inline int ptdesc_pmd_pts_count(struct ptdesc *ptdesc) +{ + return atomic_read(&ptdesc->pt_share_count); +} +#else +static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc) +{ +} +#endif + /* * Used for sizing the vmemmap region on some architectures */ diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 5eaceef41e6c..ecdd5ced16a8 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -185,6 +185,7 @@ struct netfs_io_subrequest { short error; /* 0 or error that occurred */ unsigned short debug_index; /* Index in list (for debugging output) */ unsigned int nr_segs; /* Number of segs in io_iter */ + u8 retry_count; /* The number of retries (0 on initial pass) */ enum netfs_io_source source; /* Where to read from/write to */ unsigned char stream_nr; /* I/O stream this belongs to */ unsigned char curr_folioq_slot; /* Folio currently being read */ @@ -194,14 +195,13 @@ struct netfs_io_subrequest { #define NETFS_SREQ_COPY_TO_CACHE 0 /* Set if should copy the data to the cache */ #define NETFS_SREQ_CLEAR_TAIL 1 /* Set if the rest of the read should be cleared */ #define NETFS_SREQ_SEEK_DATA_READ 3 /* Set if ->read() should SEEK_DATA first */ -#define NETFS_SREQ_NO_PROGRESS 4 /* Set if we didn't manage to read any data */ +#define NETFS_SREQ_MADE_PROGRESS 4 /* Set if we transferred at least some data */ #define NETFS_SREQ_ONDEMAND 5 /* Set if it's from on-demand read mode */ #define NETFS_SREQ_BOUNDARY 6 /* Set if ends on hard boundary (eg. ceph object) */ #define NETFS_SREQ_HIT_EOF 7 /* Set if short due to EOF */ #define NETFS_SREQ_IN_PROGRESS 8 /* Unlocked when the subrequest completes */ #define NETFS_SREQ_NEED_RETRY 9 /* Set if the filesystem requests a retry */ -#define NETFS_SREQ_RETRYING 10 /* Set if we're retrying */ -#define NETFS_SREQ_FAILED 11 /* Set if the subreq failed unretryably */ +#define NETFS_SREQ_FAILED 10 /* Set if the subreq failed unretryably */ }; enum netfs_io_origin { @@ -269,7 +269,6 @@ struct netfs_io_request { size_t prev_donated; /* Fallback for subreq->prev_donated */ refcount_t ref; unsigned long flags; -#define NETFS_RREQ_COPY_TO_CACHE 1 /* Need to write to the cache */ #define NETFS_RREQ_NO_UNLOCK_FOLIO 2 /* Don't unlock no_unlock_folio on completion */ #define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 35842d1e3879..5b520fe86b60 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -221,10 +221,7 @@ do { \ } while (0) #define PERCPU_PTR(__p) \ -({ \ - unsigned long __pcpu_ptr = (__force unsigned long)(__p); \ - (typeof(*(__p)) __force __kernel *)(__pcpu_ptr); \ -}) + (typeof(*(__p)) __force __kernel *)((__force unsigned long)(__p)) #ifdef CONFIG_SMP diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index d650ae6b58d3..74e5b9960c54 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -329,7 +329,6 @@ struct ufs_pwr_mode_info { * @program_key: program or evict an inline encryption key * @fill_crypto_prdt: initialize crypto-related fields in the PRDT * @event_notify: called to notify important events - * @reinit_notify: called to notify reinit of UFSHCD during max gear switch * @mcq_config_resource: called to configure MCQ platform resources * @get_hba_mac: reports maximum number of outstanding commands supported by * the controller. Should be implemented for UFSHCI 4.0 or later @@ -381,7 +380,6 @@ struct ufs_hba_variant_ops { void *prdt, unsigned int num_segments); void (*event_notify)(struct ufs_hba *hba, enum ufs_event_type evt, void *data); - void (*reinit_notify)(struct ufs_hba *); int (*mcq_config_resource)(struct ufs_hba *hba); int (*get_hba_mac)(struct ufs_hba *hba); int (*op_runtime_config)(struct ufs_hba *hba); diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index d3403c8216db..ff691f37462c 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -320,7 +320,7 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) ret |= io_alloc_cache_init(&ctx->rw_cache, IO_ALLOC_CACHE_MAX, sizeof(struct io_async_rw)); ret |= io_alloc_cache_init(&ctx->uring_cache, IO_ALLOC_CACHE_MAX, - sizeof(struct uring_cache)); + sizeof(struct io_uring_cmd_data)); spin_lock_init(&ctx->msg_lock); ret |= io_alloc_cache_init(&ctx->msg_cache, IO_ALLOC_CACHE_MAX, sizeof(struct io_kiocb)); diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index d407576ddfb7..eec5eb7de843 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -139,6 +139,7 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len, struct io_uring_buf_ring *br = bl->buf_ring; __u16 tail, head = bl->head; struct io_uring_buf *buf; + void __user *ret; tail = smp_load_acquire(&br->tail); if (unlikely(tail == head)) @@ -153,6 +154,7 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len, req->flags |= REQ_F_BUFFER_RING | REQ_F_BUFFERS_COMMIT; req->buf_list = bl; req->buf_index = buf->bid; + ret = u64_to_user_ptr(buf->addr); if (issue_flags & IO_URING_F_UNLOCKED || !io_file_can_poll(req)) { /* @@ -168,7 +170,7 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len, io_kbuf_commit(req, bl, *len, 1); req->buf_list = NULL; } - return u64_to_user_ptr(buf->addr); + return ret; } void __user *io_buffer_select(struct io_kiocb *req, size_t *len, diff --git a/io_uring/net.c b/io_uring/net.c index df1f7dc6f1c8..c6cd38cc5dc4 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -754,6 +754,7 @@ static int io_recvmsg_prep_setup(struct io_kiocb *req) if (req->opcode == IORING_OP_RECV) { kmsg->msg.msg_name = NULL; kmsg->msg.msg_namelen = 0; + kmsg->msg.msg_inq = 0; kmsg->msg.msg_control = NULL; kmsg->msg.msg_get_inq = 1; kmsg->msg.msg_controllen = 0; diff --git a/io_uring/opdef.c b/io_uring/opdef.c index 3de75eca1c92..e8baef4e5146 100644 --- a/io_uring/opdef.c +++ b/io_uring/opdef.c @@ -7,6 +7,7 @@ #include <linux/fs.h> #include <linux/file.h> #include <linux/io_uring.h> +#include <linux/io_uring/cmd.h> #include "io_uring.h" #include "opdef.h" @@ -414,7 +415,7 @@ const struct io_issue_def io_issue_defs[] = { .plug = 1, .iopoll = 1, .iopoll_queue = 1, - .async_size = 2 * sizeof(struct io_uring_sqe), + .async_size = sizeof(struct io_uring_cmd_data), .prep = io_uring_cmd_prep, .issue = io_uring_cmd, }, diff --git a/io_uring/rw.c b/io_uring/rw.c index 0bcb83e4ce3c..29bb3010f9c0 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -983,6 +983,8 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags) io_kbuf_recycle(req, issue_flags); if (ret < 0) req_set_fail(req); + } else if (!(req->flags & REQ_F_APOLL_MULTISHOT)) { + cflags = io_put_kbuf(req, ret, issue_flags); } else { /* * Any successful return value will keep the multishot read diff --git a/io_uring/timeout.c b/io_uring/timeout.c index bbe58638eca7..362689b17ccc 100644 --- a/io_uring/timeout.c +++ b/io_uring/timeout.c @@ -85,7 +85,27 @@ static void io_timeout_complete(struct io_kiocb *req, struct io_tw_state *ts) io_req_task_complete(req, ts); } -static bool io_kill_timeout(struct io_kiocb *req, int status) +static __cold bool io_flush_killed_timeouts(struct list_head *list, int err) +{ + if (list_empty(list)) + return false; + + while (!list_empty(list)) { + struct io_timeout *timeout; + struct io_kiocb *req; + + timeout = list_first_entry(list, struct io_timeout, list); + list_del_init(&timeout->list); + req = cmd_to_io_kiocb(timeout); + if (err) + req_set_fail(req); + io_req_queue_tw_complete(req, err); + } + + return true; +} + +static void io_kill_timeout(struct io_kiocb *req, struct list_head *list) __must_hold(&req->ctx->timeout_lock) { struct io_timeout_data *io = req->async_data; @@ -93,21 +113,17 @@ static bool io_kill_timeout(struct io_kiocb *req, int status) if (hrtimer_try_to_cancel(&io->timer) != -1) { struct io_timeout *timeout = io_kiocb_to_cmd(req, struct io_timeout); - if (status) - req_set_fail(req); atomic_set(&req->ctx->cq_timeouts, atomic_read(&req->ctx->cq_timeouts) + 1); - list_del_init(&timeout->list); - io_req_queue_tw_complete(req, status); - return true; + list_move_tail(&timeout->list, list); } - return false; } __cold void io_flush_timeouts(struct io_ring_ctx *ctx) { - u32 seq; struct io_timeout *timeout, *tmp; + LIST_HEAD(list); + u32 seq; raw_spin_lock_irq(&ctx->timeout_lock); seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); @@ -131,10 +147,11 @@ __cold void io_flush_timeouts(struct io_ring_ctx *ctx) if (events_got < events_needed) break; - io_kill_timeout(req, 0); + io_kill_timeout(req, &list); } ctx->cq_last_tm_flush = seq; raw_spin_unlock_irq(&ctx->timeout_lock); + io_flush_killed_timeouts(&list, 0); } static void io_req_tw_fail_links(struct io_kiocb *link, struct io_tw_state *ts) @@ -661,7 +678,7 @@ __cold bool io_kill_timeouts(struct io_ring_ctx *ctx, struct io_uring_task *tctx bool cancel_all) { struct io_timeout *timeout, *tmp; - int canceled = 0; + LIST_HEAD(list); /* * completion_lock is needed for io_match_task(). Take it before @@ -672,11 +689,11 @@ __cold bool io_kill_timeouts(struct io_ring_ctx *ctx, struct io_uring_task *tctx list_for_each_entry_safe(timeout, tmp, &ctx->timeout_list, list) { struct io_kiocb *req = cmd_to_io_kiocb(timeout); - if (io_match_task(req, tctx, cancel_all) && - io_kill_timeout(req, -ECANCELED)) - canceled++; + if (io_match_task(req, tctx, cancel_all)) + io_kill_timeout(req, &list); } raw_spin_unlock_irq(&ctx->timeout_lock); spin_unlock(&ctx->completion_lock); - return canceled != 0; + + return io_flush_killed_timeouts(&list, -ECANCELED); } diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index af842e9b4eb9..ce7726a04883 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -16,26 +16,35 @@ #include "rsrc.h" #include "uring_cmd.h" -static struct uring_cache *io_uring_async_get(struct io_kiocb *req) +static struct io_uring_cmd_data *io_uring_async_get(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; - struct uring_cache *cache; + struct io_uring_cmd_data *cache; cache = io_alloc_cache_get(&ctx->uring_cache); if (cache) { + cache->op_data = NULL; req->flags |= REQ_F_ASYNC_DATA; req->async_data = cache; return cache; } - if (!io_alloc_async_data(req)) - return req->async_data; + if (!io_alloc_async_data(req)) { + cache = req->async_data; + cache->op_data = NULL; + return cache; + } return NULL; } static void io_req_uring_cleanup(struct io_kiocb *req, unsigned int issue_flags) { struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd); - struct uring_cache *cache = req->async_data; + struct io_uring_cmd_data *cache = req->async_data; + + if (cache->op_data) { + kfree(cache->op_data); + cache->op_data = NULL; + } if (issue_flags & IO_URING_F_UNLOCKED) return; @@ -183,7 +192,7 @@ static int io_uring_cmd_prep_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd); - struct uring_cache *cache; + struct io_uring_cmd_data *cache; cache = io_uring_async_get(req); if (unlikely(!cache)) @@ -260,7 +269,7 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags) ret = file->f_op->uring_cmd(ioucmd, issue_flags); if (ret == -EAGAIN) { - struct uring_cache *cache = req->async_data; + struct io_uring_cmd_data *cache = req->async_data; if (ioucmd->sqe != (void *) cache) memcpy(cache, ioucmd->sqe, uring_sqe_size(req->ctx)); diff --git a/io_uring/uring_cmd.h b/io_uring/uring_cmd.h index 7dba0f1efc58..f6837ee0955b 100644 --- a/io_uring/uring_cmd.h +++ b/io_uring/uring_cmd.h @@ -1,9 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -struct uring_cache { - struct io_uring_sqe sqes[2]; -}; - int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags); int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe); diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index 383fd43ac612..7e1340da5aca 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -89,6 +89,7 @@ find $cpio_dir -type f -print0 | # Create archive and try to normalize metadata for reproducibility. tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \ + --exclude=".__afs*" --exclude=".nfs*" \ --owner=0 --group=0 --sort=name --numeric-owner --mode=u=rw,go=r,a+X \ -I $XZ -cf $tarfile -C $cpio_dir/ . > /dev/null diff --git a/kernel/kcov.c b/kernel/kcov.c index 28a6be6e64fd..187ba1b80bda 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -166,7 +166,7 @@ static void kcov_remote_area_put(struct kcov_remote_area *area, * Unlike in_serving_softirq(), this function returns false when called during * a hardirq or an NMI that happened in the softirq context. */ -static inline bool in_softirq_really(void) +static __always_inline bool in_softirq_really(void) { return in_serving_softirq() && !in_hardirq() && !in_nmi(); } diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 7fff1d045477..19d2699cf638 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -4763,7 +4763,7 @@ static void scx_ops_bypass(bool bypass) * sees scx_rq_bypassing() before moving tasks to SCX. */ if (!scx_enabled()) { - rq_unlock_irqrestore(rq, &rf); + rq_unlock(rq, &rf); continue; } @@ -7013,7 +7013,7 @@ __bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id, return -ENOENT; INIT_LIST_HEAD(&kit->cursor.node); - kit->cursor.flags |= SCX_DSQ_LNODE_ITER_CURSOR | flags; + kit->cursor.flags = SCX_DSQ_LNODE_ITER_CURSOR | flags; kit->cursor.priv = READ_ONCE(kit->dsq->seq); return 0; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 8b07576814a5..f7d8fc204579 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3680,23 +3680,27 @@ void workqueue_softirq_dead(unsigned int cpu) * check_flush_dependency - check for flush dependency sanity * @target_wq: workqueue being flushed * @target_work: work item being flushed (NULL for workqueue flushes) + * @from_cancel: are we called from the work cancel path * * %current is trying to flush the whole @target_wq or @target_work on it. - * If @target_wq doesn't have %WQ_MEM_RECLAIM, verify that %current is not - * reclaiming memory or running on a workqueue which doesn't have - * %WQ_MEM_RECLAIM as that can break forward-progress guarantee leading to - * a deadlock. + * If this is not the cancel path (which implies work being flushed is either + * already running, or will not be at all), check if @target_wq doesn't have + * %WQ_MEM_RECLAIM and verify that %current is not reclaiming memory or running + * on a workqueue which doesn't have %WQ_MEM_RECLAIM as that can break forward- + * progress guarantee leading to a deadlock. */ static void check_flush_dependency(struct workqueue_struct *target_wq, - struct work_struct *target_work) + struct work_struct *target_work, + bool from_cancel) { - work_func_t target_func = target_work ? target_work->func : NULL; + work_func_t target_func; struct worker *worker; - if (target_wq->flags & WQ_MEM_RECLAIM) + if (from_cancel || target_wq->flags & WQ_MEM_RECLAIM) return; worker = current_wq_worker(); + target_func = target_work ? target_work->func : NULL; WARN_ONCE(current->flags & PF_MEMALLOC, "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%ps", @@ -3980,7 +3984,7 @@ void __flush_workqueue(struct workqueue_struct *wq) list_add_tail(&this_flusher.list, &wq->flusher_overflow); } - check_flush_dependency(wq, NULL); + check_flush_dependency(wq, NULL, false); mutex_unlock(&wq->mutex); @@ -4155,7 +4159,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, } wq = pwq->wq; - check_flush_dependency(wq, work); + check_flush_dependency(wq, work, from_cancel); insert_wq_barrier(pwq, barr, work, worker); raw_spin_unlock_irq(&pool->lock); @@ -5641,6 +5645,7 @@ static void wq_adjust_max_active(struct workqueue_struct *wq) } while (activated); } +__printf(1, 0) static struct workqueue_struct *__alloc_workqueue(const char *fmt, unsigned int flags, int max_active, va_list args) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index d0ae808f3a14..047397136f15 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -4354,6 +4354,7 @@ int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, ret = 1; } if (ret < 0 && range_lo > min) { + mas_reset(mas); ret = mas_empty_area(mas, min, range_hi, 1); if (ret == 0) ret = 1; diff --git a/mm/damon/core.c b/mm/damon/core.c index 8b8e2933dcd4..0776452a1abb 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -868,6 +868,11 @@ static int damon_commit_schemes(struct damon_ctx *dst, struct damon_ctx *src) NUMA_NO_NODE); if (!new_scheme) return -ENOMEM; + err = damos_commit(new_scheme, src_scheme); + if (err) { + damon_destroy_scheme(new_scheme); + return err; + } damon_add_scheme(dst, new_scheme); } return 0; @@ -961,8 +966,11 @@ static int damon_commit_targets( return -ENOMEM; err = damon_commit_target(new_target, false, src_target, damon_target_has_pid(src)); - if (err) + if (err) { + damon_destroy_target(new_target); return err; + } + damon_add_target(dst, new_target); } return 0; } diff --git a/mm/filemap.c b/mm/filemap.c index f61cf51c2238..33b60d448fca 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -124,15 +124,6 @@ * ->private_lock (zap_pte_range->block_dirty_folio) */ -static void mapping_set_update(struct xa_state *xas, - struct address_space *mapping) -{ - if (dax_mapping(mapping) || shmem_mapping(mapping)) - return; - xas_set_update(xas, workingset_update_node); - xas_set_lru(xas, &shadow_nodes); -} - static void page_cache_delete(struct address_space *mapping, struct folio *folio, void *shadow) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index cec4b121193f..c498874a7170 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -7211,7 +7211,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, spte = hugetlb_walk(svma, saddr, vma_mmu_pagesize(svma)); if (spte) { - get_page(virt_to_page(spte)); + ptdesc_pmd_pts_inc(virt_to_ptdesc(spte)); break; } } @@ -7226,7 +7226,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, (pmd_t *)((unsigned long)spte & PAGE_MASK)); mm_inc_nr_pmds(mm); } else { - put_page(virt_to_page(spte)); + ptdesc_pmd_pts_dec(virt_to_ptdesc(spte)); } spin_unlock(&mm->page_table_lock); out: @@ -7238,10 +7238,6 @@ out: /* * unmap huge page backed by shared pte. * - * Hugetlb pte page is ref counted at the time of mapping. If pte is shared - * indicated by page_count > 1, unmap is achieved by clearing pud and - * decrementing the ref count. If count == 1, the pte page is not shared. - * * Called with page table lock held. * * returns: 1 successfully unmapped a shared pte page @@ -7250,18 +7246,20 @@ out: int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { + unsigned long sz = huge_page_size(hstate_vma(vma)); pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); - BUG_ON(page_count(virt_to_page(ptep)) == 0); - if (page_count(virt_to_page(ptep)) == 1) + if (sz != PMD_SIZE) + return 0; + if (!ptdesc_pmd_pts_count(virt_to_ptdesc(ptep))) return 0; pud_clear(pud); - put_page(virt_to_page(ptep)); + ptdesc_pmd_pts_dec(virt_to_ptdesc(ptep)); mm_dec_nr_pmds(mm); return 1; } diff --git a/mm/internal.h b/mm/internal.h index 3bd08bafad04..9826f7dce607 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -1504,6 +1504,12 @@ static inline void shrinker_debugfs_remove(struct dentry *debugfs_entry, /* Only track the nodes of mappings with shadow entries */ void workingset_update_node(struct xa_node *node); extern struct list_lru shadow_nodes; +#define mapping_set_update(xas, mapping) do { \ + if (!dax_mapping(mapping) && !shmem_mapping(mapping)) { \ + xas_set_update(xas, workingset_update_node); \ + xas_set_lru(xas, &shadow_nodes); \ + } \ +} while (0) /* mremap.c */ unsigned long move_page_tables(struct vm_area_struct *vma, diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 6f8d46d107b4..653dbb1ff05c 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -19,6 +19,7 @@ #include <linux/rcupdate_wait.h> #include <linux/swapops.h> #include <linux/shmem_fs.h> +#include <linux/dax.h> #include <linux/ksm.h> #include <asm/tlb.h> @@ -1837,6 +1838,8 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr, if (result != SCAN_SUCCEED) goto out; + mapping_set_update(&xas, mapping); + __folio_set_locked(new_folio); if (is_shmem) __folio_set_swapbacked(new_folio); diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 2a945c07ae99..737af23f4f4e 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -373,7 +373,7 @@ static void print_unreferenced(struct seq_file *seq, for (i = 0; i < nr_entries; i++) { void *ptr = (void *)entries[i]; - warn_or_seq_printf(seq, " [<%pK>] %pS\n", ptr, ptr); + warn_or_seq_printf(seq, " %pS\n", ptr); } } diff --git a/mm/list_lru.c b/mm/list_lru.c index f93ada6a207b..7d69434c70e0 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -77,7 +77,6 @@ again: spin_lock(&l->lock); nr_items = READ_ONCE(l->nr_items); if (likely(nr_items != LONG_MIN)) { - WARN_ON(nr_items < 0); rcu_read_unlock(); return l; } @@ -450,6 +449,7 @@ static void memcg_reparent_list_lru_one(struct list_lru *lru, int nid, list_splice_init(&src->list, &dst->list); if (src->nr_items) { + WARN_ON(src->nr_items < 0); dst->nr_items += src->nr_items; set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru)); } diff --git a/mm/memfd.c b/mm/memfd.c index c17c3ea701a1..35a370d75c9a 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -170,7 +170,7 @@ static int memfd_wait_for_pins(struct address_space *mapping) return error; } -static unsigned int *memfd_file_seals_ptr(struct file *file) +unsigned int *memfd_file_seals_ptr(struct file *file) { if (shmem_file(file)) return &SHMEM_I(file_inode(file))->seals; diff --git a/mm/mmap.c b/mm/mmap.c index d32b7e701058..aec208f90337 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -47,6 +47,7 @@ #include <linux/oom.h> #include <linux/sched/mm.h> #include <linux/ksm.h> +#include <linux/memfd.h> #include <linux/uaccess.h> #include <asm/cacheflush.h> @@ -368,6 +369,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr, if (file) { struct inode *inode = file_inode(file); + unsigned int seals = memfd_file_seals(file); unsigned long flags_mask; if (!file_mmap_ok(file, inode, pgoff, len)) @@ -408,6 +410,8 @@ unsigned long do_mmap(struct file *file, unsigned long addr, vm_flags |= VM_SHARED | VM_MAYSHARE; if (!(file->f_mode & FMODE_WRITE)) vm_flags &= ~(VM_MAYWRITE | VM_SHARED); + else if (is_readonly_sealed(seals, vm_flags)) + vm_flags &= ~VM_MAYWRITE; fallthrough; case MAP_PRIVATE: if (!(file->f_mode & FMODE_READ)) @@ -888,7 +892,7 @@ __get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, if (get_area) { addr = get_area(file, addr, len, pgoff, flags); - } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) + } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && !file && !addr /* no hint */ && IS_ALIGNED(len, PMD_SIZE)) { /* Ensures that larger anonymous mappings are THP aligned. */ diff --git a/mm/readahead.c b/mm/readahead.c index ea650b8b02fb..e151f4b13ca4 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -646,7 +646,11 @@ void page_cache_async_ra(struct readahead_control *ractl, 1UL << order); if (index == expected) { ra->start += ra->size; - ra->size = get_next_ra_size(ra, max_pages); + /* + * In the case of MADV_HUGEPAGE, the actual size might exceed + * the readahead window. + */ + ra->size = max(ra->size, get_next_ra_size(ra, max_pages)); ra->async_size = ra->size; goto readit; } diff --git a/mm/shmem.c b/mm/shmem.c index f6fb053ac50d..ac58d4fb2e6f 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1535,7 +1535,7 @@ try_split: !shmem_falloc->waitq && index >= shmem_falloc->start && index < shmem_falloc->next) - shmem_falloc->nr_unswapped++; + shmem_falloc->nr_unswapped += nr_pages; else shmem_falloc = NULL; spin_unlock(&inode->i_lock); @@ -1689,6 +1689,7 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode, unsigned long mask = READ_ONCE(huge_shmem_orders_always); unsigned long within_size_orders = READ_ONCE(huge_shmem_orders_within_size); unsigned long vm_flags = vma ? vma->vm_flags : 0; + pgoff_t aligned_index; bool global_huge; loff_t i_size; int order; @@ -1723,9 +1724,9 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode, /* Allow mTHP that will be fully within i_size. */ order = highest_order(within_size_orders); while (within_size_orders) { - index = round_up(index + 1, order); + aligned_index = round_up(index + 1, 1 << order); i_size = round_up(i_size_read(inode), PAGE_SIZE); - if (i_size >> PAGE_SHIFT >= index) { + if (i_size >> PAGE_SHIFT >= aligned_index) { mask |= within_size_orders; break; } diff --git a/mm/util.c b/mm/util.c index c1c3b06ab4f9..60aa40f612b8 100644 --- a/mm/util.c +++ b/mm/util.c @@ -297,12 +297,7 @@ void *memdup_user_nul(const void __user *src, size_t len) { char *p; - /* - * Always use GFP_KERNEL, since copy_from_user() can sleep and - * cause pagefault, which makes it pointless to use GFP_NOFS - * or GFP_ATOMIC. - */ - p = kmalloc_track_caller(len + 1, GFP_KERNEL); + p = kmem_buckets_alloc_track_caller(user_buckets, len + 1, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); diff --git a/mm/vmscan.c b/mm/vmscan.c index 76378bc257e3..9a859b7d18d7 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -374,7 +374,14 @@ unsigned long zone_reclaimable_pages(struct zone *zone) if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL)) nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) + zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON); - + /* + * If there are no reclaimable file-backed or anonymous pages, + * ensure zones with sufficient free pages are not skipped. + * This prevents zones like DMA32 from being ignored in reclaim + * scenarios where they can still help alleviate memory pressure. + */ + if (nr == 0) + nr = zone_page_state_snapshot(zone, NR_FREE_PAGES); return nr; } diff --git a/mm/zswap.c b/mm/zswap.c index f6316b66fb23..5a27af8d86ea 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -880,6 +880,18 @@ static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node) return 0; } +/* Prevent CPU hotplug from freeing up the per-CPU acomp_ctx resources */ +static struct crypto_acomp_ctx *acomp_ctx_get_cpu(struct crypto_acomp_ctx __percpu *acomp_ctx) +{ + cpus_read_lock(); + return raw_cpu_ptr(acomp_ctx); +} + +static void acomp_ctx_put_cpu(void) +{ + cpus_read_unlock(); +} + static bool zswap_compress(struct page *page, struct zswap_entry *entry, struct zswap_pool *pool) { @@ -893,8 +905,7 @@ static bool zswap_compress(struct page *page, struct zswap_entry *entry, gfp_t gfp; u8 *dst; - acomp_ctx = raw_cpu_ptr(pool->acomp_ctx); - + acomp_ctx = acomp_ctx_get_cpu(pool->acomp_ctx); mutex_lock(&acomp_ctx->mutex); dst = acomp_ctx->buffer; @@ -950,6 +961,7 @@ unlock: zswap_reject_alloc_fail++; mutex_unlock(&acomp_ctx->mutex); + acomp_ctx_put_cpu(); return comp_ret == 0 && alloc_ret == 0; } @@ -960,7 +972,7 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio) struct crypto_acomp_ctx *acomp_ctx; u8 *src; - acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); + acomp_ctx = acomp_ctx_get_cpu(entry->pool->acomp_ctx); mutex_lock(&acomp_ctx->mutex); src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO); @@ -990,6 +1002,7 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio) if (src != acomp_ctx->buffer) zpool_unmap_handle(zpool, entry->handle); + acomp_ctx_put_cpu(); } /********************************* diff --git a/rust/kernel/workqueue.rs b/rust/kernel/workqueue.rs index 4d1d2062f6eb..fd3e97192ed8 100644 --- a/rust/kernel/workqueue.rs +++ b/rust/kernel/workqueue.rs @@ -519,7 +519,15 @@ impl_has_work! { impl{T} HasWork<Self> for ClosureWork<T> { self.work } } -// SAFETY: TODO. +// SAFETY: The `__enqueue` implementation in RawWorkItem uses a `work_struct` initialized with the +// `run` method of this trait as the function pointer because: +// - `__enqueue` gets the `work_struct` from the `Work` field, using `T::raw_get_work`. +// - The only safe way to create a `Work` object is through `Work::new`. +// - `Work::new` makes sure that `T::Pointer::run` is passed to `init_work_with_key`. +// - Finally `Work` and `RawWorkItem` guarantee that the correct `Work` field +// will be used because of the ID const generic bound. This makes sure that `T::raw_get_work` +// uses the correct offset for the `Work` field, and `Work::new` picks the correct +// implementation of `WorkItemPointer` for `Arc<T>`. unsafe impl<T, const ID: u64> WorkItemPointer<ID> for Arc<T> where T: WorkItem<ID, Pointer = Self>, @@ -537,7 +545,13 @@ where } } -// SAFETY: TODO. +// SAFETY: The `work_struct` raw pointer is guaranteed to be valid for the duration of the call to +// the closure because we get it from an `Arc`, which means that the ref count will be at least 1, +// and we don't drop the `Arc` ourselves. If `queue_work_on` returns true, it is further guaranteed +// to be valid until a call to the function pointer in `work_struct` because we leak the memory it +// points to, and only reclaim it if the closure returns false, or in `WorkItemPointer::run`, which +// is what the function pointer in the `work_struct` must be pointing to, according to the safety +// requirements of `WorkItemPointer`. unsafe impl<T, const ID: u64> RawWorkItem<ID> for Arc<T> where T: WorkItem<ID, Pointer = Self>, diff --git a/scripts/mksysmap b/scripts/mksysmap index c12723a04655..3accbdb269ac 100755 --- a/scripts/mksysmap +++ b/scripts/mksysmap @@ -26,7 +26,7 @@ # (do not forget a space before each pattern) # local symbols for ARM, MIPS, etc. -/ \\$/d +/ \$/d # local labels, .LBB, .Ltmpxxx, .L__unnamed_xx, .LASANPC, etc. / \.L/d @@ -39,7 +39,7 @@ / __pi_\.L/d # arm64 local symbols in non-VHE KVM namespace -/ __kvm_nvhe_\\$/d +/ __kvm_nvhe_\$/d / __kvm_nvhe_\.L/d # lld arm/aarch64/mips thunks diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 5b5745f00eb3..19ec72a69e90 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -132,7 +132,8 @@ struct devtable { * based at address m. */ #define DEF_FIELD(m, devid, f) \ - typeof(((struct devid *)0)->f) f = TO_NATIVE(*(typeof(f) *)((m) + OFF_##devid##_##f)) + typeof(((struct devid *)0)->f) f = \ + get_unaligned_native((typeof(f) *)((m) + OFF_##devid##_##f)) /* Define a variable f that holds the address of field f of struct devid * based at address m. Due to the way typeof works, for a field of type @@ -600,7 +601,7 @@ static void do_pnp_card_entry(struct module *mod, void *symval) static void do_pcmcia_entry(struct module *mod, void *symval) { char alias[256] = {}; - unsigned int i; + DEF_FIELD(symval, pcmcia_device_id, match_flags); DEF_FIELD(symval, pcmcia_device_id, manf_id); DEF_FIELD(symval, pcmcia_device_id, card_id); @@ -609,10 +610,6 @@ static void do_pcmcia_entry(struct module *mod, void *symval) DEF_FIELD(symval, pcmcia_device_id, device_no); DEF_FIELD_ADDR(symval, pcmcia_device_id, prod_id_hash); - for (i=0; i<4; i++) { - (*prod_id_hash)[i] = TO_NATIVE((*prod_id_hash)[i]); - } - ADD(alias, "m", match_flags & PCMCIA_DEV_ID_MATCH_MANF_ID, manf_id); ADD(alias, "c", match_flags & PCMCIA_DEV_ID_MATCH_CARD_ID, @@ -623,10 +620,14 @@ static void do_pcmcia_entry(struct module *mod, void *symval) function); ADD(alias, "pfn", match_flags & PCMCIA_DEV_ID_MATCH_DEVICE_NO, device_no); - ADD(alias, "pa", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID1, (*prod_id_hash)[0]); - ADD(alias, "pb", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID2, (*prod_id_hash)[1]); - ADD(alias, "pc", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID3, (*prod_id_hash)[2]); - ADD(alias, "pd", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID4, (*prod_id_hash)[3]); + ADD(alias, "pa", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID1, + get_unaligned_native(*prod_id_hash + 0)); + ADD(alias, "pb", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID2, + get_unaligned_native(*prod_id_hash + 1)); + ADD(alias, "pc", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID3, + get_unaligned_native(*prod_id_hash + 2)); + ADD(alias, "pd", match_flags & PCMCIA_DEV_ID_MATCH_PROD_ID4, + get_unaligned_native(*prod_id_hash + 3)); module_alias_printf(mod, true, "pcmcia:%s", alias); } @@ -654,10 +655,9 @@ static void do_input(char *alias, { unsigned int i; - for (i = min / BITS_PER_LONG; i < max / BITS_PER_LONG + 1; i++) - arr[i] = TO_NATIVE(arr[i]); - for (i = min; i < max; i++) - if (arr[i / BITS_PER_LONG] & (1ULL << (i%BITS_PER_LONG))) + for (i = min; i <= max; i++) + if (get_unaligned_native(arr + i / BITS_PER_LONG) & + (1ULL << (i % BITS_PER_LONG))) sprintf(alias + strlen(alias), "%X,*", i); } @@ -812,15 +812,13 @@ static void do_virtio_entry(struct module *mod, void *symval) * Each byte of the guid will be represented by two hex characters * in the name. */ - static void do_vmbus_entry(struct module *mod, void *symval) { - int i; DEF_FIELD_ADDR(symval, hv_vmbus_device_id, guid); - char guid_name[(sizeof(*guid) + 1) * 2]; + char guid_name[sizeof(*guid) * 2 + 1]; - for (i = 0; i < (sizeof(*guid) * 2); i += 2) - sprintf(&guid_name[i], "%02x", TO_NATIVE((guid->b)[i/2])); + for (int i = 0; i < sizeof(*guid); i++) + sprintf(&guid_name[i * 2], "%02x", guid->b[i]); module_alias_printf(mod, false, "vmbus:%s", guid_name); } diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 94ee49207a45..7ea59dc4926b 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1138,9 +1138,9 @@ static Elf_Addr addend_386_rel(uint32_t *location, unsigned int r_type) { switch (r_type) { case R_386_32: - return TO_NATIVE(*location); + return get_unaligned_native(location); case R_386_PC32: - return TO_NATIVE(*location) + 4; + return get_unaligned_native(location) + 4; } return (Elf_Addr)(-1); @@ -1161,24 +1161,24 @@ static Elf_Addr addend_arm_rel(void *loc, Elf_Sym *sym, unsigned int r_type) switch (r_type) { case R_ARM_ABS32: case R_ARM_REL32: - inst = TO_NATIVE(*(uint32_t *)loc); + inst = get_unaligned_native((uint32_t *)loc); return inst + sym->st_value; case R_ARM_MOVW_ABS_NC: case R_ARM_MOVT_ABS: - inst = TO_NATIVE(*(uint32_t *)loc); + inst = get_unaligned_native((uint32_t *)loc); offset = sign_extend32(((inst & 0xf0000) >> 4) | (inst & 0xfff), 15); return offset + sym->st_value; case R_ARM_PC24: case R_ARM_CALL: case R_ARM_JUMP24: - inst = TO_NATIVE(*(uint32_t *)loc); + inst = get_unaligned_native((uint32_t *)loc); offset = sign_extend32((inst & 0x00ffffff) << 2, 25); return offset + sym->st_value + 8; case R_ARM_THM_MOVW_ABS_NC: case R_ARM_THM_MOVT_ABS: - upper = TO_NATIVE(*(uint16_t *)loc); - lower = TO_NATIVE(*((uint16_t *)loc + 1)); + upper = get_unaligned_native((uint16_t *)loc); + lower = get_unaligned_native((uint16_t *)loc + 1); offset = sign_extend32(((upper & 0x000f) << 12) | ((upper & 0x0400) << 1) | ((lower & 0x7000) >> 4) | @@ -1195,8 +1195,8 @@ static Elf_Addr addend_arm_rel(void *loc, Elf_Sym *sym, unsigned int r_type) * imm11 = lower[10:0] * imm32 = SignExtend(S:J2:J1:imm6:imm11:'0') */ - upper = TO_NATIVE(*(uint16_t *)loc); - lower = TO_NATIVE(*((uint16_t *)loc + 1)); + upper = get_unaligned_native((uint16_t *)loc); + lower = get_unaligned_native((uint16_t *)loc + 1); sign = (upper >> 10) & 1; j1 = (lower >> 13) & 1; @@ -1219,8 +1219,8 @@ static Elf_Addr addend_arm_rel(void *loc, Elf_Sym *sym, unsigned int r_type) * I2 = NOT(J2 XOR S) * imm32 = SignExtend(S:I1:I2:imm10:imm11:'0') */ - upper = TO_NATIVE(*(uint16_t *)loc); - lower = TO_NATIVE(*((uint16_t *)loc + 1)); + upper = get_unaligned_native((uint16_t *)loc); + lower = get_unaligned_native((uint16_t *)loc + 1); sign = (upper >> 10) & 1; j1 = (lower >> 13) & 1; @@ -1241,7 +1241,7 @@ static Elf_Addr addend_mips_rel(uint32_t *location, unsigned int r_type) { uint32_t inst; - inst = TO_NATIVE(*location); + inst = get_unaligned_native(location); switch (r_type) { case R_MIPS_LO16: return inst & 0xffff; diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h index 8b72c227ebf4..ffd0a52a606e 100644 --- a/scripts/mod/modpost.h +++ b/scripts/mod/modpost.h @@ -65,6 +65,20 @@ #define TO_NATIVE(x) \ (target_is_big_endian == host_is_big_endian ? x : bswap(x)) +#define __get_unaligned_t(type, ptr) ({ \ + const struct { type x; } __attribute__((__packed__)) *__pptr = \ + (typeof(__pptr))(ptr); \ + __pptr->x; \ +}) + +#define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr)) + +#define get_unaligned_native(ptr) \ +({ \ + typeof(*(ptr)) _val = get_unaligned(ptr); \ + TO_NATIVE(_val); \ +}) + #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) #define strstarts(str, prefix) (strncmp(str, prefix, strlen(prefix)) == 0) diff --git a/scripts/package/PKGBUILD b/scripts/package/PKGBUILD index f83493838cf9..dca706617adc 100644 --- a/scripts/package/PKGBUILD +++ b/scripts/package/PKGBUILD @@ -103,7 +103,7 @@ _package-headers() { _package-api-headers() { pkgdesc="Kernel headers sanitized for use in userspace" - provides=(linux-api-headers) + provides=(linux-api-headers="${pkgver}") conflicts=(linux-api-headers) _prologue diff --git a/scripts/sorttable.h b/scripts/sorttable.h index 7bd0184380d3..a7c5445baf00 100644 --- a/scripts/sorttable.h +++ b/scripts/sorttable.h @@ -110,7 +110,7 @@ static inline unsigned long orc_ip(const int *ip) static int orc_sort_cmp(const void *_a, const void *_b) { - struct orc_entry *orc_a; + struct orc_entry *orc_a, *orc_b; const int *a = g_orc_ip_table + *(int *)_a; const int *b = g_orc_ip_table + *(int *)_b; unsigned long a_val = orc_ip(a); @@ -128,6 +128,9 @@ static int orc_sort_cmp(const void *_a, const void *_b) * whitelisted .o files which didn't get objtool generation. */ orc_a = g_orc_table + (a - g_orc_ip_table); + orc_b = g_orc_table + (b - g_orc_ip_table); + if (orc_a->type == ORC_TYPE_UNDEFINED && orc_b->type == ORC_TYPE_UNDEFINED) + return 0; return orc_a->type == ORC_TYPE_UNDEFINED ? -1 : 1; } diff --git a/security/selinux/avc.c b/security/selinux/avc.c index cc0b0af20296..1f2680bcc43a 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -174,13 +174,15 @@ int avc_get_hash_stats(char *page) * using a linked list for extended_perms_decision lookup because the list is * always small. i.e. less than 5, typically 1 */ -static struct extended_perms_decision *avc_xperms_decision_lookup(u8 driver, - struct avc_xperms_node *xp_node) +static struct extended_perms_decision * +avc_xperms_decision_lookup(u8 driver, u8 base_perm, + struct avc_xperms_node *xp_node) { struct avc_xperms_decision_node *xpd_node; list_for_each_entry(xpd_node, &xp_node->xpd_head, xpd_list) { - if (xpd_node->xpd.driver == driver) + if (xpd_node->xpd.driver == driver && + xpd_node->xpd.base_perm == base_perm) return &xpd_node->xpd; } return NULL; @@ -205,11 +207,12 @@ avc_xperms_has_perm(struct extended_perms_decision *xpd, } static void avc_xperms_allow_perm(struct avc_xperms_node *xp_node, - u8 driver, u8 perm) + u8 driver, u8 base_perm, u8 perm) { struct extended_perms_decision *xpd; security_xperm_set(xp_node->xp.drivers.p, driver); - xpd = avc_xperms_decision_lookup(driver, xp_node); + xp_node->xp.base_perms |= base_perm; + xpd = avc_xperms_decision_lookup(driver, base_perm, xp_node); if (xpd && xpd->allowed) security_xperm_set(xpd->allowed->p, perm); } @@ -245,6 +248,7 @@ static void avc_xperms_free(struct avc_xperms_node *xp_node) static void avc_copy_xperms_decision(struct extended_perms_decision *dest, struct extended_perms_decision *src) { + dest->base_perm = src->base_perm; dest->driver = src->driver; dest->used = src->used; if (dest->used & XPERMS_ALLOWED) @@ -272,6 +276,7 @@ static inline void avc_quick_copy_xperms_decision(u8 perm, */ u8 i = perm >> 5; + dest->base_perm = src->base_perm; dest->used = src->used; if (dest->used & XPERMS_ALLOWED) dest->allowed->p[i] = src->allowed->p[i]; @@ -357,6 +362,7 @@ static int avc_xperms_populate(struct avc_node *node, memcpy(dest->xp.drivers.p, src->xp.drivers.p, sizeof(dest->xp.drivers.p)); dest->xp.len = src->xp.len; + dest->xp.base_perms = src->xp.base_perms; /* for each source xpd allocate a destination xpd and copy */ list_for_each_entry(src_xpd, &src->xpd_head, xpd_list) { @@ -807,6 +813,7 @@ out: * @event : Updating event * @perms : Permission mask bits * @driver: xperm driver information + * @base_perm: the base permission associated with the extended permission * @xperm: xperm permissions * @ssid: AVC entry source sid * @tsid: AVC entry target sid @@ -820,10 +827,9 @@ out: * otherwise, this function updates the AVC entry. The original AVC-entry object * will release later by RCU. */ -static int avc_update_node(u32 event, u32 perms, u8 driver, u8 xperm, u32 ssid, - u32 tsid, u16 tclass, u32 seqno, - struct extended_perms_decision *xpd, - u32 flags) +static int avc_update_node(u32 event, u32 perms, u8 driver, u8 base_perm, + u8 xperm, u32 ssid, u32 tsid, u16 tclass, u32 seqno, + struct extended_perms_decision *xpd, u32 flags) { u32 hvalue; int rc = 0; @@ -880,7 +886,7 @@ static int avc_update_node(u32 event, u32 perms, u8 driver, u8 xperm, u32 ssid, case AVC_CALLBACK_GRANT: node->ae.avd.allowed |= perms; if (node->ae.xp_node && (flags & AVC_EXTENDED_PERMS)) - avc_xperms_allow_perm(node->ae.xp_node, driver, xperm); + avc_xperms_allow_perm(node->ae.xp_node, driver, base_perm, xperm); break; case AVC_CALLBACK_TRY_REVOKE: case AVC_CALLBACK_REVOKE: @@ -987,10 +993,9 @@ static noinline void avc_compute_av(u32 ssid, u32 tsid, u16 tclass, avc_insert(ssid, tsid, tclass, avd, xp_node); } -static noinline int avc_denied(u32 ssid, u32 tsid, - u16 tclass, u32 requested, - u8 driver, u8 xperm, unsigned int flags, - struct av_decision *avd) +static noinline int avc_denied(u32 ssid, u32 tsid, u16 tclass, u32 requested, + u8 driver, u8 base_perm, u8 xperm, + unsigned int flags, struct av_decision *avd) { if (flags & AVC_STRICT) return -EACCES; @@ -999,7 +1004,7 @@ static noinline int avc_denied(u32 ssid, u32 tsid, !(avd->flags & AVD_FLAGS_PERMISSIVE)) return -EACCES; - avc_update_node(AVC_CALLBACK_GRANT, requested, driver, + avc_update_node(AVC_CALLBACK_GRANT, requested, driver, base_perm, xperm, ssid, tsid, tclass, avd->seqno, NULL, flags); return 0; } @@ -1012,7 +1017,8 @@ static noinline int avc_denied(u32 ssid, u32 tsid, * driver field is used to specify which set contains the permission. */ int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested, - u8 driver, u8 xperm, struct common_audit_data *ad) + u8 driver, u8 base_perm, u8 xperm, + struct common_audit_data *ad) { struct avc_node *node; struct av_decision avd; @@ -1047,22 +1053,23 @@ int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested, local_xpd.auditallow = &auditallow; local_xpd.dontaudit = &dontaudit; - xpd = avc_xperms_decision_lookup(driver, xp_node); + xpd = avc_xperms_decision_lookup(driver, base_perm, xp_node); if (unlikely(!xpd)) { /* * Compute the extended_perms_decision only if the driver - * is flagged + * is flagged and the base permission is known. */ - if (!security_xperm_test(xp_node->xp.drivers.p, driver)) { + if (!security_xperm_test(xp_node->xp.drivers.p, driver) || + !(xp_node->xp.base_perms & base_perm)) { avd.allowed &= ~requested; goto decision; } rcu_read_unlock(); - security_compute_xperms_decision(ssid, tsid, tclass, - driver, &local_xpd); + security_compute_xperms_decision(ssid, tsid, tclass, driver, + base_perm, &local_xpd); rcu_read_lock(); - avc_update_node(AVC_CALLBACK_ADD_XPERMS, requested, - driver, xperm, ssid, tsid, tclass, avd.seqno, + avc_update_node(AVC_CALLBACK_ADD_XPERMS, requested, driver, + base_perm, xperm, ssid, tsid, tclass, avd.seqno, &local_xpd, 0); } else { avc_quick_copy_xperms_decision(xperm, &local_xpd, xpd); @@ -1075,8 +1082,8 @@ int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested, decision: denied = requested & ~(avd.allowed); if (unlikely(denied)) - rc = avc_denied(ssid, tsid, tclass, requested, - driver, xperm, AVC_EXTENDED_PERMS, &avd); + rc = avc_denied(ssid, tsid, tclass, requested, driver, + base_perm, xperm, AVC_EXTENDED_PERMS, &avd); rcu_read_unlock(); @@ -1110,7 +1117,7 @@ static noinline int avc_perm_nonode(u32 ssid, u32 tsid, u16 tclass, avc_compute_av(ssid, tsid, tclass, avd, &xp_node); denied = requested & ~(avd->allowed); if (unlikely(denied)) - return avc_denied(ssid, tsid, tclass, requested, 0, 0, + return avc_denied(ssid, tsid, tclass, requested, 0, 0, 0, flags, avd); return 0; } @@ -1158,7 +1165,7 @@ inline int avc_has_perm_noaudit(u32 ssid, u32 tsid, rcu_read_unlock(); if (unlikely(denied)) - return avc_denied(ssid, tsid, tclass, requested, 0, 0, + return avc_denied(ssid, tsid, tclass, requested, 0, 0, 0, flags, avd); return 0; } diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 366c87a40bd1..171dd7fceac5 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3688,8 +3688,8 @@ static int ioctl_has_perm(const struct cred *cred, struct file *file, return 0; isec = inode_security(inode); - rc = avc_has_extended_perms(ssid, isec->sid, isec->sclass, - requested, driver, xperm, &ad); + rc = avc_has_extended_perms(ssid, isec->sid, isec->sclass, requested, + driver, AVC_EXT_IOCTL, xperm, &ad); out: return rc; } @@ -5952,7 +5952,7 @@ static int nlmsg_sock_has_extended_perms(struct sock *sk, u32 perms, u16 nlmsg_t xperm = nlmsg_type & 0xff; return avc_has_extended_perms(current_sid(), sksec->sid, sksec->sclass, - perms, driver, xperm, &ad); + perms, driver, AVC_EXT_NLMSG, xperm, &ad); } static int selinux_netlink_send(struct sock *sk, struct sk_buff *skb) diff --git a/security/selinux/include/avc.h b/security/selinux/include/avc.h index 96a614d47df8..281f40103663 100644 --- a/security/selinux/include/avc.h +++ b/security/selinux/include/avc.h @@ -136,8 +136,11 @@ int avc_has_perm_noaudit(u32 ssid, u32 tsid, u16 tclass, u32 requested, int avc_has_perm(u32 ssid, u32 tsid, u16 tclass, u32 requested, struct common_audit_data *auditdata); +#define AVC_EXT_IOCTL (1 << 0) /* Cache entry for an ioctl extended permission */ +#define AVC_EXT_NLMSG (1 << 1) /* Cache entry for an nlmsg extended permission */ int avc_has_extended_perms(u32 ssid, u32 tsid, u16 tclass, u32 requested, - u8 driver, u8 perm, struct common_audit_data *ad); + u8 driver, u8 base_perm, u8 perm, + struct common_audit_data *ad); u32 avc_policy_seqno(void); diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h index c7f2731abd03..700bd6c8bb38 100644 --- a/security/selinux/include/security.h +++ b/security/selinux/include/security.h @@ -239,6 +239,7 @@ struct extended_perms_data { struct extended_perms_decision { u8 used; u8 driver; + u8 base_perm; struct extended_perms_data *allowed; struct extended_perms_data *auditallow; struct extended_perms_data *dontaudit; @@ -246,6 +247,7 @@ struct extended_perms_decision { struct extended_perms { u16 len; /* length associated decision chain */ + u8 base_perms; /* which base permissions are covered */ struct extended_perms_data drivers; /* flag drivers that are used */ }; @@ -257,6 +259,7 @@ void security_compute_av(u32 ssid, u32 tsid, u16 tclass, struct extended_perms *xperms); void security_compute_xperms_decision(u32 ssid, u32 tsid, u16 tclass, u8 driver, + u8 base_perm, struct extended_perms_decision *xpermd); void security_compute_av_user(u32 ssid, u32 tsid, u16 tclass, diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index 3d5c563cfc4c..d9f58b5d0f49 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -582,7 +582,7 @@ static void type_attribute_bounds_av(struct policydb *policydb, } /* - * Flag which drivers have permissions. + * Flag which drivers have permissions and which base permissions are covered. */ void services_compute_xperms_drivers( struct extended_perms *xperms, @@ -592,12 +592,19 @@ void services_compute_xperms_drivers( switch (node->datum.u.xperms->specified) { case AVTAB_XPERMS_IOCTLDRIVER: + xperms->base_perms |= AVC_EXT_IOCTL; /* if one or more driver has all permissions allowed */ for (i = 0; i < ARRAY_SIZE(xperms->drivers.p); i++) xperms->drivers.p[i] |= node->datum.u.xperms->perms.p[i]; break; case AVTAB_XPERMS_IOCTLFUNCTION: + xperms->base_perms |= AVC_EXT_IOCTL; + /* if allowing permissions within a driver */ + security_xperm_set(xperms->drivers.p, + node->datum.u.xperms->driver); + break; case AVTAB_XPERMS_NLMSG: + xperms->base_perms |= AVC_EXT_NLMSG; /* if allowing permissions within a driver */ security_xperm_set(xperms->drivers.p, node->datum.u.xperms->driver); @@ -631,8 +638,7 @@ static void context_struct_compute_av(struct policydb *policydb, avd->auditallow = 0; avd->auditdeny = 0xffffffff; if (xperms) { - memset(&xperms->drivers, 0, sizeof(xperms->drivers)); - xperms->len = 0; + memset(xperms, 0, sizeof(*xperms)); } if (unlikely(!tclass || tclass > policydb->p_classes.nprim)) { @@ -969,13 +975,19 @@ void services_compute_xperms_decision(struct extended_perms_decision *xpermd, { switch (node->datum.u.xperms->specified) { case AVTAB_XPERMS_IOCTLFUNCTION: - case AVTAB_XPERMS_NLMSG: - if (xpermd->driver != node->datum.u.xperms->driver) + if (xpermd->base_perm != AVC_EXT_IOCTL || + xpermd->driver != node->datum.u.xperms->driver) return; break; case AVTAB_XPERMS_IOCTLDRIVER: - if (!security_xperm_test(node->datum.u.xperms->perms.p, - xpermd->driver)) + if (xpermd->base_perm != AVC_EXT_IOCTL || + !security_xperm_test(node->datum.u.xperms->perms.p, + xpermd->driver)) + return; + break; + case AVTAB_XPERMS_NLMSG: + if (xpermd->base_perm != AVC_EXT_NLMSG || + xpermd->driver != node->datum.u.xperms->driver) return; break; default: @@ -1010,6 +1022,7 @@ void security_compute_xperms_decision(u32 ssid, u32 tsid, u16 orig_tclass, u8 driver, + u8 base_perm, struct extended_perms_decision *xpermd) { struct selinux_policy *policy; @@ -1023,6 +1036,7 @@ void security_compute_xperms_decision(u32 ssid, struct ebitmap_node *snode, *tnode; unsigned int i, j; + xpermd->base_perm = base_perm; xpermd->driver = driver; xpermd->used = 0; memset(xpermd->allowed->p, 0, sizeof(xpermd->allowed->p)); diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index 2f36b7b6418d..625f5b046776 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -40,9 +40,9 @@ void scx_bpf_dsq_insert(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_fl void scx_bpf_dsq_insert_vtime(struct task_struct *p, u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags) __ksym __weak; u32 scx_bpf_dispatch_nr_slots(void) __ksym; void scx_bpf_dispatch_cancel(void) __ksym; -bool scx_bpf_dsq_move_to_local(u64 dsq_id) __ksym; -void scx_bpf_dsq_move_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym; -void scx_bpf_dsq_move_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym; +bool scx_bpf_dsq_move_to_local(u64 dsq_id) __ksym __weak; +void scx_bpf_dsq_move_set_slice(struct bpf_iter_scx_dsq *it__iter, u64 slice) __ksym __weak; +void scx_bpf_dsq_move_set_vtime(struct bpf_iter_scx_dsq *it__iter, u64 vtime) __ksym __weak; bool scx_bpf_dsq_move(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak; bool scx_bpf_dsq_move_vtime(struct bpf_iter_scx_dsq *it__iter, struct task_struct *p, u64 dsq_id, u64 enq_flags) __ksym __weak; u32 scx_bpf_reenqueue_local(void) __ksym; diff --git a/tools/sched_ext/scx_central.c b/tools/sched_ext/scx_central.c index 21deea320bd7..e938156ed0a0 100644 --- a/tools/sched_ext/scx_central.c +++ b/tools/sched_ext/scx_central.c @@ -97,7 +97,7 @@ restart: SCX_BUG_ON(!cpuset, "Failed to allocate cpuset"); CPU_ZERO(cpuset); CPU_SET(skel->rodata->central_cpu, cpuset); - SCX_BUG_ON(sched_setaffinity(0, sizeof(cpuset), cpuset), + SCX_BUG_ON(sched_setaffinity(0, sizeof(*cpuset), cpuset), "Failed to affinitize to central CPU %d (max %d)", skel->rodata->central_cpu, skel->rodata->nr_cpu_ids - 1); CPU_FREE(cpuset); diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index 0a0b55516028..c0c53451a16d 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -282,6 +282,24 @@ static void *mfd_assert_mmap_shared(int fd) return p; } +static void *mfd_assert_mmap_read_shared(int fd) +{ + void *p; + + p = mmap(NULL, + mfd_def_size, + PROT_READ, + MAP_SHARED, + fd, + 0); + if (p == MAP_FAILED) { + printf("mmap() failed: %m\n"); + abort(); + } + + return p; +} + static void *mfd_assert_mmap_private(int fd) { void *p; @@ -980,6 +998,30 @@ static void test_seal_future_write(void) close(fd); } +static void test_seal_write_map_read_shared(void) +{ + int fd; + void *p; + + printf("%s SEAL-WRITE-MAP-READ\n", memfd_str); + + fd = mfd_assert_new("kern_memfd_seal_write_map_read", + mfd_def_size, + MFD_CLOEXEC | MFD_ALLOW_SEALING); + + mfd_assert_add_seals(fd, F_SEAL_WRITE); + mfd_assert_has_seals(fd, F_SEAL_WRITE); + + p = mfd_assert_mmap_read_shared(fd); + + mfd_assert_read(fd); + mfd_assert_read_shared(fd); + mfd_fail_write(fd); + + munmap(p, mfd_def_size); + close(fd); +} + /* * Test SEAL_SHRINK * Test whether SEAL_SHRINK actually prevents shrinking @@ -1593,6 +1635,7 @@ int main(int argc, char **argv) test_seal_write(); test_seal_future_write(); + test_seal_write_map_read_shared(); test_seal_shrink(); test_seal_grow(); test_seal_resize(); diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c index 37d9bf6fb745..6f4c3f5a1c5d 100644 --- a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c +++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.bpf.c @@ -20,7 +20,7 @@ s32 BPF_STRUCT_OPS(ddsp_bogus_dsq_fail_select_cpu, struct task_struct *p, * If we dispatch to a bogus DSQ that will fall back to the * builtin global DSQ, we fail gracefully. */ - scx_bpf_dispatch_vtime(p, 0xcafef00d, SCX_SLICE_DFL, + scx_bpf_dsq_insert_vtime(p, 0xcafef00d, SCX_SLICE_DFL, p->scx.dsq_vtime, 0); return cpu; } diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c index dffc97d9cdf1..e4a55027778f 100644 --- a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c +++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.bpf.c @@ -17,8 +17,8 @@ s32 BPF_STRUCT_OPS(ddsp_vtimelocal_fail_select_cpu, struct task_struct *p, if (cpu >= 0) { /* Shouldn't be allowed to vtime dispatch to a builtin DSQ. */ - scx_bpf_dispatch_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, - p->scx.dsq_vtime, 0); + scx_bpf_dsq_insert_vtime(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, + p->scx.dsq_vtime, 0); return cpu; } diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c index 6a7db1502c29..fbda6bf54671 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c @@ -43,9 +43,12 @@ void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev) if (!p) return; - target = bpf_get_prandom_u32() % nr_cpus; + if (p->nr_cpus_allowed == nr_cpus) + target = bpf_get_prandom_u32() % nr_cpus; + else + target = scx_bpf_task_cpu(p); - scx_bpf_dispatch(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | target, SCX_SLICE_DFL, 0); bpf_task_release(p); } diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.c b/tools/testing/selftests/sched_ext/dsp_local_on.c index 472851b56854..0ff27e57fe43 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.c @@ -34,9 +34,10 @@ static enum scx_test_status run(void *ctx) /* Just sleeping is fine, plenty of scheduling events happening */ sleep(1); - SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_ERROR)); bpf_link__destroy(link); + SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_UNREG)); + return SCX_TEST_PASS; } @@ -50,7 +51,7 @@ static void cleanup(void *ctx) struct scx_test dsp_local_on = { .name = "dsp_local_on", .description = "Verify we can directly dispatch tasks to a local DSQs " - "from osp.dispatch()", + "from ops.dispatch()", .setup = setup, .run = run, .cleanup = cleanup, diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c index 1efb50d61040..a7cf868d5e31 100644 --- a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c +++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.bpf.c @@ -31,7 +31,7 @@ void BPF_STRUCT_OPS(enq_select_cpu_fails_enqueue, struct task_struct *p, /* Can only call from ops.select_cpu() */ scx_bpf_select_cpu_dfl(p, 0, 0, &found); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); } SEC(".struct_ops.link") diff --git a/tools/testing/selftests/sched_ext/exit.bpf.c b/tools/testing/selftests/sched_ext/exit.bpf.c index d75d4faf07f6..4bc36182d3ff 100644 --- a/tools/testing/selftests/sched_ext/exit.bpf.c +++ b/tools/testing/selftests/sched_ext/exit.bpf.c @@ -33,7 +33,7 @@ void BPF_STRUCT_OPS(exit_enqueue, struct task_struct *p, u64 enq_flags) if (exit_point == EXIT_ENQUEUE) EXIT_CLEANLY(); - scx_bpf_dispatch(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); } void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p) @@ -41,7 +41,7 @@ void BPF_STRUCT_OPS(exit_dispatch, s32 cpu, struct task_struct *p) if (exit_point == EXIT_DISPATCH) EXIT_CLEANLY(); - scx_bpf_consume(DSQ_ID); + scx_bpf_dsq_move_to_local(DSQ_ID); } void BPF_STRUCT_OPS(exit_enable, struct task_struct *p) diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c index 4d4cd8d966db..430f5e13bf55 100644 --- a/tools/testing/selftests/sched_ext/maximal.bpf.c +++ b/tools/testing/selftests/sched_ext/maximal.bpf.c @@ -12,6 +12,8 @@ char _license[] SEC("license") = "GPL"; +#define DSQ_ID 0 + s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags) { @@ -20,7 +22,7 @@ s32 BPF_STRUCT_OPS(maximal_select_cpu, struct task_struct *p, s32 prev_cpu, void BPF_STRUCT_OPS(maximal_enqueue, struct task_struct *p, u64 enq_flags) { - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, DSQ_ID, SCX_SLICE_DFL, enq_flags); } void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags) @@ -28,7 +30,7 @@ void BPF_STRUCT_OPS(maximal_dequeue, struct task_struct *p, u64 deq_flags) void BPF_STRUCT_OPS(maximal_dispatch, s32 cpu, struct task_struct *prev) { - scx_bpf_consume(SCX_DSQ_GLOBAL); + scx_bpf_dsq_move_to_local(DSQ_ID); } void BPF_STRUCT_OPS(maximal_runnable, struct task_struct *p, u64 enq_flags) @@ -123,7 +125,7 @@ void BPF_STRUCT_OPS(maximal_cgroup_set_weight, struct cgroup *cgrp, u32 weight) s32 BPF_STRUCT_OPS_SLEEPABLE(maximal_init) { - return 0; + return scx_bpf_create_dsq(DSQ_ID, -1); } void BPF_STRUCT_OPS(maximal_exit, struct scx_exit_info *info) diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c index f171ac470970..13d0f5be788d 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.bpf.c @@ -30,7 +30,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_enqueue, struct task_struct *p, } scx_bpf_put_idle_cpumask(idle_mask); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags); } SEC(".struct_ops.link") diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c index 9efdbb7da928..815f1d5d61ac 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.bpf.c @@ -67,7 +67,7 @@ void BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_enqueue, struct task_struct *p, saw_local = true; } - scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, enq_flags); + scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, enq_flags); } s32 BPF_STRUCT_OPS(select_cpu_dfl_nodispatch_init_task, diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c index 59bfc4f36167..4bb99699e920 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.bpf.c @@ -29,7 +29,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_select_cpu, struct task_struct *p, cpu = prev_cpu; dispatch: - scx_bpf_dispatch(p, dsq_id, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, dsq_id, SCX_SLICE_DFL, 0); return cpu; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c index 3bbd5fcdfb18..2a75de11b2cf 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.bpf.c @@ -18,7 +18,7 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_bad_dsq_select_cpu, struct task_struct *p s32 prev_cpu, u64 wake_flags) { /* Dispatching to a random DSQ should fail. */ - scx_bpf_dispatch(p, 0xcafef00d, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, 0xcafef00d, SCX_SLICE_DFL, 0); return prev_cpu; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c index 0fda57fe0ecf..99d075695c97 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.bpf.c @@ -18,8 +18,8 @@ s32 BPF_STRUCT_OPS(select_cpu_dispatch_dbl_dsp_select_cpu, struct task_struct *p s32 prev_cpu, u64 wake_flags) { /* Dispatching twice in a row is disallowed. */ - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); - scx_bpf_dispatch(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); + scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, 0); return prev_cpu; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c index e6c67bcf5e6e..bfcb96cd4954 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c +++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.bpf.c @@ -2,8 +2,8 @@ /* * A scheduler that validates that enqueue flags are properly stored and * applied at dispatch time when a task is directly dispatched from - * ops.select_cpu(). We validate this by using scx_bpf_dispatch_vtime(), and - * making the test a very basic vtime scheduler. + * ops.select_cpu(). We validate this by using scx_bpf_dsq_insert_vtime(), + * and making the test a very basic vtime scheduler. * * Copyright (c) 2024 Meta Platforms, Inc. and affiliates. * Copyright (c) 2024 David Vernet <dvernet@meta.com> @@ -47,13 +47,13 @@ s32 BPF_STRUCT_OPS(select_cpu_vtime_select_cpu, struct task_struct *p, cpu = prev_cpu; scx_bpf_test_and_clear_cpu_idle(cpu); ddsp: - scx_bpf_dispatch_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0); + scx_bpf_dsq_insert_vtime(p, VTIME_DSQ, SCX_SLICE_DFL, task_vtime(p), 0); return cpu; } void BPF_STRUCT_OPS(select_cpu_vtime_dispatch, s32 cpu, struct task_struct *p) { - if (scx_bpf_consume(VTIME_DSQ)) + if (scx_bpf_dsq_move_to_local(VTIME_DSQ)) consumed = true; } |