diff options
89 files changed, 989 insertions, 418 deletions
diff --git a/Documentation/dev-tools/checkpatch.rst b/Documentation/dev-tools/checkpatch.rst index fa2988dd465732..deb3f67a633cfc 100644 --- a/Documentation/dev-tools/checkpatch.rst +++ b/Documentation/dev-tools/checkpatch.rst @@ -1002,6 +1002,29 @@ Functions and Variables return bar; + **UNINITIALIZED_PTR_WITH_FREE** + Pointers with __free attribute should be declared at the place of use + and initialized (see include/linux/cleanup.h). In this case + declarations at the top of the function rule can be relaxed. Not doing + so may lead to undefined behavior as the memory assigned (garbage, + in case not initialized) to the pointer is freed automatically when + the pointer goes out of scope. + + Also see: https://lore.kernel.org/lkml/58fd478f408a34b578ee8d949c5c4b4da4d4f41d.camel@HansenPartnership.com/ + + Example:: + + type var __free(free_func); + ... // var not used, but, in future someone might add a return here + var = malloc(var_size); + ... + + should be initialized as:: + + ... + type var __free(free_func) = malloc(var_size); + ... + Permissions ----------- diff --git a/Documentation/translations/zh_CN/core-api/irq/irq-domain.rst b/Documentation/translations/zh_CN/core-api/irq/irq-domain.rst index 4a2d3b27aa4d21..aaefeda0e16444 100644 --- a/Documentation/translations/zh_CN/core-api/irq/irq-domain.rst +++ b/Documentation/translations/zh_CN/core-api/irq/irq-domain.rst @@ -109,10 +109,6 @@ irq_domain维护着从hwirq号到Linux IRQ的radix的树状映射。 当一个hw 如果hwirq号可以非常大，树状映射是一个很好的选择，因为它不需要分配一个和最大hwirq 号一样大的表。 缺点是，hwirq到IRQ号的查找取决于表中有多少条目。 -irq_domain_add_tree()和irq_domain_create_tree()在功能上是等价的，除了第一 -个参数不同——前者接受一个Open Firmware特定的 'struct device_node' ，而后者接受 -一个更通用的抽象 'struct fwnode_handle' 。 - 很少有驱动应该需要这个映射。 无映射 diff --git a/MAINTAINERS b/MAINTAINERS index 56975a34e0de44..5b11839cba9de1 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -28321,6 +28321,7 @@ M: Matthew Wilcox <willy@infradead.org> L: linux-fsdevel@vger.kernel.org L: linux-mm@kvack.org S: Supported +F: Documentation/core-api/idr.rst F: Documentation/core-api/xarray.rst F: include/linux/idr.h F: include/linux/xarray.h diff --git a/Makefile b/Makefile index 2f545ec1690fb9..e404e4767944ed 100644 --- a/Makefile +++ b/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 -PATCHLEVEL = 18 +PATCHLEVEL = 19 SUBLEVEL = 0 -EXTRAVERSION = +EXTRAVERSION = -rc1 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c index 502133979e2289..4cbbe2ee58aba7 100644 --- a/arch/powerpc/platforms/pseries/cmm.c +++ b/arch/powerpc/platforms/pseries/cmm.c @@ -532,6 +532,7 @@ static int cmm_migratepage(struct balloon_dev_info *b_dev_info, spin_lock_irqsave(&b_dev_info->pages_lock, flags); balloon_page_insert(b_dev_info, newpage); + __count_vm_event(BALLOON_MIGRATE); b_dev_info->isolated_pages--; spin_unlock_irqrestore(&b_dev_info->pages_lock, flags); @@ -550,7 +551,6 @@ static int cmm_migratepage(struct balloon_dev_info *b_dev_info, static void cmm_balloon_compaction_init(void) { - balloon_devinfo_init(&b_dev_info); b_dev_info.migratepage = cmm_migratepage; } #else /* CONFIG_BALLOON_COMPACTION */ @@ -572,6 +572,7 @@ static int cmm_init(void) if (!firmware_has_feature(FW_FEATURE_CMO) && !simulate) return -EOPNOTSUPP; + balloon_devinfo_init(&b_dev_info); cmm_balloon_compaction_init(); rc = register_oom_notifier(&cmm_oom_nb); diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index e8b6af199c738e..9293ce50574dad 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -656,14 +656,11 @@ static int amd_uncore_df_event_init(struct perf_event *event) struct hw_perf_event *hwc = &event->hw; int ret = amd_uncore_event_init(event); - if (ret || pmu_version < 2) - return ret; - hwc->config = event->attr.config & (pmu_version >= 2 ? AMD64_PERFMON_V2_RAW_EVENT_MASK_NB : AMD64_RAW_EVENT_MASK_NB); - return 0; + return ret; } static int amd_uncore_df_add(struct perf_event *event, int flags) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 853fe073bab301..bdf3f0d0fe2167 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3378,6 +3378,9 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) if (!test_bit(bit, cpuc->active_mask)) continue; + /* Event may have already been cleared: */ + if (!event) + continue; /* * There may be unprocessed PEBS records in the PEBS buffer, diff --git a/arch/x86/hyperv/.gitignore b/arch/x86/hyperv/.gitignore new file mode 100644 index 00000000000000..333615d993b56c --- /dev/null +++ b/arch/x86/hyperv/.gitignore @@ -0,0 +1 @@ +mshv-asm-offsets.h diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 77d6944489905b..858320b6ebb7ef 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -316,9 +316,6 @@ config BLK_DEV_RBD tristate "Rados block device (RBD)" depends on INET && BLOCK select CEPH_LIB - select CRC32 - select CRYPTO_AES - select CRYPTO help Say Y here if you want include the Rados block device, which stripes a block device over objects stored in the Ceph distributed object diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c index 033c44326552ab..fffb47b62f437b 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c @@ -429,7 +429,14 @@ static void sn65dsi83_handle_errors(struct sn65dsi83 *ctx) */ ret = regmap_read(ctx->regmap, REG_IRQ_STAT, &irq_stat); - if (ret || irq_stat) { + + /* + * Some hardware (Toradex Verdin AM62) is known to report the + * PLL_UNLOCK error interrupt while working without visible + * problems. In lack of a reliable way to discriminate such cases + * from user-visible PLL_UNLOCK cases, ignore that bit entirely. + */ + if (ret || irq_stat & ~REG_IRQ_STAT_CHA_PLL_UNLOCK) { /* * IRQ acknowledged is not always possible (the bridge can be in * a state where it doesn't answer anymore). To prevent an @@ -654,7 +661,7 @@ static void sn65dsi83_atomic_enable(struct drm_bridge *bridge, if (ctx->irq) { /* Enable irq to detect errors */ regmap_write(ctx->regmap, REG_IRQ_GLOBAL, REG_IRQ_GLOBAL_IRQ_EN); - regmap_write(ctx->regmap, REG_IRQ_EN, 0xff); + regmap_write(ctx->regmap, REG_IRQ_EN, 0xff & ~REG_IRQ_EN_CHA_PLL_UNLOCK_EN); } else { /* Use the polling task */ sn65dsi83_monitor_start(ctx); diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c index ce76c55913f725..b143589717e648 100644 --- a/drivers/gpu/drm/drm_plane.c +++ b/drivers/gpu/drm/drm_plane.c @@ -338,14 +338,14 @@ static int drm_plane_create_hotspot_properties(struct drm_plane *plane) prop_x = drm_property_create_signed_range(plane->dev, 0, "HOTSPOT_X", INT_MIN, INT_MAX); - if (IS_ERR(prop_x)) - return PTR_ERR(prop_x); + if (!prop_x) + return -ENOMEM; prop_y = drm_property_create_signed_range(plane->dev, 0, "HOTSPOT_Y", INT_MIN, INT_MAX); - if (IS_ERR(prop_y)) { + if (!prop_y) { drm_property_destroy(plane->dev, prop_x); - return PTR_ERR(prop_y); + return -ENOMEM; } drm_object_attach_property(&plane->base, prop_x, 0); diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c index 951d715dea3011..d019177462cf7f 100644 --- a/drivers/gpu/drm/mgag200/mgag200_mode.c +++ b/drivers/gpu/drm/mgag200/mgag200_mode.c @@ -161,6 +161,30 @@ static void mgag200_set_startadd(struct mga_device *mdev, WREG_ECRT(0x00, crtcext0); } +/* + * Set the opmode for the hardware swapper for Big-Endian processor + * support for the frame buffer aperture and DMAWIN space. + */ +static void mgag200_set_datasiz(struct mga_device *mdev, u32 format) +{ +#if defined(__BIG_ENDIAN) + u32 opmode = RREG32(MGAREG_OPMODE); + + opmode &= ~(GENMASK(17, 16) | GENMASK(9, 8) | GENMASK(3, 2)); + + /* Big-endian byte-swapping */ + switch (format) { + case DRM_FORMAT_RGB565: + opmode |= 0x10100; + break; + case DRM_FORMAT_XRGB8888: + opmode |= 0x20200; + break; + } + WREG32(MGAREG_OPMODE, opmode); +#endif +} + void mgag200_init_registers(struct mga_device *mdev) { u8 crtc11, misc; @@ -496,6 +520,7 @@ void mgag200_primary_plane_helper_atomic_update(struct drm_plane *plane, struct drm_atomic_helper_damage_iter iter; struct drm_rect damage; + mgag200_set_datasiz(mdev, fb->format->format); drm_atomic_helper_damage_iter_init(&iter, old_plane_state, plane_state); drm_atomic_for_each_plane_damage(&iter, &damage) { mgag200_handle_damage(mdev, shadow_plane_state->data, fb, &damage); diff --git a/drivers/gpu/drm/nouveau/dispnv04/nouveau_i2c_encoder.c b/drivers/gpu/drm/nouveau/dispnv04/nouveau_i2c_encoder.c index e2bf99c433366b..a60209097a20a6 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/nouveau_i2c_encoder.c +++ b/drivers/gpu/drm/nouveau/dispnv04/nouveau_i2c_encoder.c @@ -94,26 +94,6 @@ fail_unregister: return err; } -/** - * nouveau_i2c_encoder_destroy - Unregister the I2C device backing an encoder - * @drm_encoder: Encoder to be unregistered. - * - * This should be called from the @destroy method of an I2C slave - * encoder driver once I2C access is no longer needed. - */ -void nouveau_i2c_encoder_destroy(struct drm_encoder *drm_encoder) -{ - struct nouveau_i2c_encoder *encoder = to_encoder_i2c(drm_encoder); - struct i2c_client *client = nouveau_i2c_encoder_get_client(drm_encoder); - struct module *module = client->dev.driver->owner; - - i2c_unregister_device(client); - encoder->i2c_client = NULL; - - module_put(module); -} -EXPORT_SYMBOL(nouveau_i2c_encoder_destroy); - /* * Wrapper fxns which can be plugged in to drm_encoder_helper_funcs: */ diff --git a/drivers/gpu/drm/nouveau/include/dispnv04/i2c/encoder_i2c.h b/drivers/gpu/drm/nouveau/include/dispnv04/i2c/encoder_i2c.h index 31334aa90781b3..869820701a56eb 100644 --- a/drivers/gpu/drm/nouveau/include/dispnv04/i2c/encoder_i2c.h +++ b/drivers/gpu/drm/nouveau/include/dispnv04/i2c/encoder_i2c.h @@ -202,7 +202,24 @@ static inline struct i2c_client *nouveau_i2c_encoder_get_client(struct drm_encod return to_encoder_i2c(encoder)->i2c_client; } -void nouveau_i2c_encoder_destroy(struct drm_encoder *encoder); +/** + * nouveau_i2c_encoder_destroy - Unregister the I2C device backing an encoder + * @drm_encoder: Encoder to be unregistered. + * + * This should be called from the @destroy method of an I2C slave + * encoder driver once I2C access is no longer needed. + */ +static __always_inline void nouveau_i2c_encoder_destroy(struct drm_encoder *drm_encoder) +{ + struct nouveau_i2c_encoder *encoder = to_encoder_i2c(drm_encoder); + struct i2c_client *client = nouveau_i2c_encoder_get_client(drm_encoder); + struct module *module = client->dev.driver->owner; + + i2c_unregister_device(client); + encoder->i2c_client = NULL; + + module_put(module); +} /* * Wrapper fxns which can be plugged in to drm_encoder_helper_funcs: diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h index 226c7ec56b8ed9..b8b97e10ae83ed 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h @@ -73,6 +73,10 @@ struct nvkm_gsp { const struct firmware *bl; const struct firmware *rm; + + struct { + struct nvkm_falcon_fw sb; + } falcon; } fws; struct nvkm_firmware fw; diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index 869d4335c0f45c..4a193b7d6d9e40 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -183,11 +183,11 @@ nouveau_fence_context_new(struct nouveau_channel *chan, struct nouveau_fence_cha fctx->context = drm->runl[chan->runlist].context_base + chan->chid; if (chan == drm->cechan) - strcpy(fctx->name, "copy engine channel"); + strscpy(fctx->name, "copy engine channel"); else if (chan == drm->channel) - strcpy(fctx->name, "generic kernel channel"); + strscpy(fctx->name, "generic kernel channel"); else - strcpy(fctx->name, cli->name); + strscpy(fctx->name, cli->name); kref_init(&fctx->fence_ref); if (!priv->uevent) diff --git a/drivers/gpu/drm/nouveau/nouveau_hwmon.c b/drivers/gpu/drm/nouveau/nouveau_hwmon.c index 5c07a9ee8b775f..34effe6d86ad50 100644 --- a/drivers/gpu/drm/nouveau/nouveau_hwmon.c +++ b/drivers/gpu/drm/nouveau/nouveau_hwmon.c @@ -125,7 +125,7 @@ nouveau_hwmon_get_pwm1_max(struct device *d, if (ret < 0) return ret; - return sprintf(buf, "%i\n", ret); + return sysfs_emit(buf, "%i\n", ret); } static ssize_t @@ -141,7 +141,7 @@ nouveau_hwmon_get_pwm1_min(struct device *d, if (ret < 0) return ret; - return sprintf(buf, "%i\n", ret); + return sysfs_emit(buf, "%i\n", ret); } static ssize_t diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c index 5b721bd9d79949..50376024666042 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c @@ -259,18 +259,16 @@ nvkm_gsp_fwsec_v3(struct nvkm_gsp *gsp, const char *name, } static int -nvkm_gsp_fwsec(struct nvkm_gsp *gsp, const char *name, u32 init_cmd) +nvkm_gsp_fwsec_init(struct nvkm_gsp *gsp, struct nvkm_falcon_fw *fw, const char *name, u32 init_cmd) { struct nvkm_subdev *subdev = &gsp->subdev; struct nvkm_device *device = subdev->device; struct nvkm_bios *bios = device->bios; const union nvfw_falcon_ucode_desc *desc; struct nvbios_pmuE flcn_ucode; - u8 idx, ver, hdr; u32 data; u16 size, vers; - struct nvkm_falcon_fw fw = {}; - u32 mbox0 = 0; + u8 idx, ver, hdr; int ret; /* Lookup in VBIOS. */ @@ -291,8 +289,8 @@ nvkm_gsp_fwsec(struct nvkm_gsp *gsp, const char *name, u32 init_cmd) vers = (desc->v2.Hdr & 0x0000ff00) >> 8; switch (vers) { - case 2: ret = nvkm_gsp_fwsec_v2(gsp, name, &desc->v2, size, init_cmd, &fw); break; - case 3: ret = nvkm_gsp_fwsec_v3(gsp, name, &desc->v3, size, init_cmd, &fw); break; + case 2: ret = nvkm_gsp_fwsec_v2(gsp, name, &desc->v2, size, init_cmd, fw); break; + case 3: ret = nvkm_gsp_fwsec_v3(gsp, name, &desc->v3, size, init_cmd, fw); break; default: nvkm_error(subdev, "%s(v%d): version unknown\n", name, vers); return -EINVAL; @@ -303,15 +301,19 @@ nvkm_gsp_fwsec(struct nvkm_gsp *gsp, const char *name, u32 init_cmd) return ret; } - /* Boot. */ - ret = nvkm_falcon_fw_boot(&fw, subdev, true, &mbox0, NULL, 0, 0); - nvkm_falcon_fw_dtor(&fw); - if (ret) - return ret; - return 0; } +static int +nvkm_gsp_fwsec_boot(struct nvkm_gsp *gsp, struct nvkm_falcon_fw *fw) +{ + struct nvkm_subdev *subdev = &gsp->subdev; + u32 mbox0 = 0; + + /* Boot */ + return nvkm_falcon_fw_boot(fw, subdev, true, &mbox0, NULL, 0, 0); +} + int nvkm_gsp_fwsec_sb(struct nvkm_gsp *gsp) { @@ -320,7 +322,7 @@ nvkm_gsp_fwsec_sb(struct nvkm_gsp *gsp) int ret; u32 err; - ret = nvkm_gsp_fwsec(gsp, "fwsec-sb", NVFW_FALCON_APPIF_DMEMMAPPER_CMD_SB); + ret = nvkm_gsp_fwsec_boot(gsp, &gsp->fws.falcon.sb); if (ret) return ret; @@ -335,26 +337,47 @@ nvkm_gsp_fwsec_sb(struct nvkm_gsp *gsp) } int +nvkm_gsp_fwsec_sb_ctor(struct nvkm_gsp *gsp) +{ + return nvkm_gsp_fwsec_init(gsp, &gsp->fws.falcon.sb, "fwsec-sb", + NVFW_FALCON_APPIF_DMEMMAPPER_CMD_SB); +} + +void +nvkm_gsp_fwsec_sb_dtor(struct nvkm_gsp *gsp) +{ + nvkm_falcon_fw_dtor(&gsp->fws.falcon.sb); +} + +int nvkm_gsp_fwsec_frts(struct nvkm_gsp *gsp) { struct nvkm_subdev *subdev = &gsp->subdev; struct nvkm_device *device = subdev->device; + struct nvkm_falcon_fw fw = {}; int ret; u32 err, wpr2_lo, wpr2_hi; - ret = nvkm_gsp_fwsec(gsp, "fwsec-frts", NVFW_FALCON_APPIF_DMEMMAPPER_CMD_FRTS); + ret = nvkm_gsp_fwsec_init(gsp, &fw, "fwsec-frts", NVFW_FALCON_APPIF_DMEMMAPPER_CMD_FRTS); if (ret) return ret; + ret = nvkm_gsp_fwsec_boot(gsp, &fw); + if (ret) + goto fwsec_dtor; + /* Verify. */ err = nvkm_rd32(device, 0x001400 + (0xe * 4)) >> 16; if (err) { nvkm_error(subdev, "fwsec-frts: 0x%04x\n", err); - return -EIO; + ret = -EIO; + } else { + wpr2_lo = nvkm_rd32(device, 0x1fa824); + wpr2_hi = nvkm_rd32(device, 0x1fa828); + nvkm_debug(subdev, "fwsec-frts: WPR2 @ %08x - %08x\n", wpr2_lo, wpr2_hi); } - wpr2_lo = nvkm_rd32(device, 0x1fa824); - wpr2_hi = nvkm_rd32(device, 0x1fa828); - nvkm_debug(subdev, "fwsec-frts: WPR2 @ %08x - %08x\n", wpr2_lo, wpr2_hi); - return 0; +fwsec_dtor: + nvkm_falcon_fw_dtor(&fw); + return ret; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h index c3494b7ac572bc..86bdd203bc107c 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/priv.h @@ -6,7 +6,10 @@ enum nvkm_acr_lsf_id; int nvkm_gsp_fwsec_frts(struct nvkm_gsp *); + +int nvkm_gsp_fwsec_sb_ctor(struct nvkm_gsp *); int nvkm_gsp_fwsec_sb(struct nvkm_gsp *); +void nvkm_gsp_fwsec_sb_dtor(struct nvkm_gsp *); struct nvkm_gsp_fwif { int version; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c index 32e6a065d6d7a5..2a7e80c6d70f39 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c @@ -1817,12 +1817,16 @@ r535_gsp_rm_boot_ctor(struct nvkm_gsp *gsp) RM_RISCV_UCODE_DESC *desc; int ret; + ret = nvkm_gsp_fwsec_sb_ctor(gsp); + if (ret) + return ret; + hdr = nvfw_bin_hdr(&gsp->subdev, fw->data); desc = (void *)fw->data + hdr->header_offset; ret = nvkm_gsp_mem_ctor(gsp, hdr->data_size, &gsp->boot.fw); if (ret) - return ret; + goto dtor_fwsec; memcpy(gsp->boot.fw.data, fw->data + hdr->data_offset, hdr->data_size); @@ -1831,6 +1835,9 @@ r535_gsp_rm_boot_ctor(struct nvkm_gsp *gsp) gsp->boot.manifest_offset = desc->manifestOffset; gsp->boot.app_version = desc->appVersion; return 0; +dtor_fwsec: + nvkm_gsp_fwsec_sb_dtor(gsp); + return ret; } static const struct nvkm_firmware_func @@ -2101,6 +2108,7 @@ r535_gsp_dtor(struct nvkm_gsp *gsp) mutex_destroy(&gsp->cmdq.mutex); nvkm_gsp_dtor_fws(gsp); + nvkm_gsp_fwsec_sb_dtor(gsp); nvkm_gsp_mem_dtor(&gsp->rmargs); nvkm_gsp_mem_dtor(&gsp->wpr_meta); diff --git a/drivers/gpu/drm/panel/panel-novatek-nt35560.c b/drivers/gpu/drm/panel/panel-novatek-nt35560.c index 561e6643dcbb67..6e5173f98a2264 100644 --- a/drivers/gpu/drm/panel/panel-novatek-nt35560.c +++ b/drivers/gpu/drm/panel/panel-novatek-nt35560.c @@ -213,7 +213,7 @@ static const struct backlight_properties nt35560_bl_props = { static void nt35560_read_id(struct mipi_dsi_multi_context *dsi_ctx) { - struct device dev = dsi_ctx->dsi->dev; + struct device *dev = &dsi_ctx->dsi->dev; u8 vendor, version, panel; u16 val; @@ -225,7 +225,7 @@ static void nt35560_read_id(struct mipi_dsi_multi_context *dsi_ctx) return; if (vendor == 0x00) { - dev_err(&dev, "device vendor ID is zero\n"); + dev_err(dev, "device vendor ID is zero\n"); dsi_ctx->accum_err = -ENODEV; return; } @@ -236,12 +236,12 @@ static void nt35560_read_id(struct mipi_dsi_multi_context *dsi_ctx) case DISPLAY_SONY_ACX424AKP_ID2: case DISPLAY_SONY_ACX424AKP_ID3: case DISPLAY_SONY_ACX424AKP_ID4: - dev_info(&dev, + dev_info(dev, "MTP vendor: %02x, version: %02x, panel: %02x\n", vendor, version, panel); break; default: - dev_info(&dev, + dev_info(dev, "unknown vendor: %02x, version: %02x, panel: %02x\n", vendor, version, panel); break; diff --git a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c index 5718d9d83a49f3..52c95131af5afd 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_crtc.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_crtc.c @@ -586,7 +586,7 @@ out: drm_modeset_unlock(&crtc->mutex); } -static void tilcdc_crtc_destroy(struct drm_crtc *crtc) +void tilcdc_crtc_destroy(struct drm_crtc *crtc) { struct tilcdc_drm_private *priv = crtc->dev->dev_private; diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c index 7caec4d38ddf0c..3dcbec312bacb4 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c +++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c @@ -172,8 +172,7 @@ static void tilcdc_fini(struct drm_device *dev) if (priv->crtc) tilcdc_crtc_shutdown(priv->crtc); - if (priv->is_registered) - drm_dev_unregister(dev); + drm_dev_unregister(dev); drm_kms_helper_poll_fini(dev); drm_atomic_helper_shutdown(dev); @@ -220,21 +219,21 @@ static int tilcdc_init(const struct drm_driver *ddrv, struct device *dev) priv->wq = alloc_ordered_workqueue("tilcdc", 0); if (!priv->wq) { ret = -ENOMEM; - goto init_failed; + goto put_drm; } priv->mmio = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->mmio)) { dev_err(dev, "failed to request / ioremap\n"); ret = PTR_ERR(priv->mmio); - goto init_failed; + goto free_wq; } priv->clk = clk_get(dev, "fck"); if (IS_ERR(priv->clk)) { dev_err(dev, "failed to get functional clock\n"); ret = -ENODEV; - goto init_failed; + goto free_wq; } pm_runtime_enable(dev); @@ -313,7 +312,7 @@ static int tilcdc_init(const struct drm_driver *ddrv, struct device *dev) ret = tilcdc_crtc_create(ddev); if (ret < 0) { dev_err(dev, "failed to create crtc\n"); - goto init_failed; + goto disable_pm; } modeset_init(ddev); @@ -324,46 +323,46 @@ static int tilcdc_init(const struct drm_driver *ddrv, struct device *dev) if (ret) { dev_err(dev, "failed to register cpufreq notifier\n"); priv->freq_transition.notifier_call = NULL; - goto init_failed; + goto destroy_crtc; } #endif if (priv->is_componentized) { ret = component_bind_all(dev, ddev); if (ret < 0) - goto init_failed; + goto unregister_cpufreq_notif; ret = tilcdc_add_component_encoder(ddev); if (ret < 0) - goto init_failed; + goto unbind_component; } else { ret = tilcdc_attach_external_device(ddev); if (ret) - goto init_failed; + goto unregister_cpufreq_notif; } if (!priv->external_connector && ((priv->num_encoders == 0) || (priv->num_connectors == 0))) { dev_err(dev, "no encoders/connectors found\n"); ret = -EPROBE_DEFER; - goto init_failed; + goto unbind_component; } ret = drm_vblank_init(ddev, 1); if (ret < 0) { dev_err(dev, "failed to initialize vblank\n"); - goto init_failed; + goto unbind_component; } ret = platform_get_irq(pdev, 0); if (ret < 0) - goto init_failed; + goto unbind_component; priv->irq = ret; ret = tilcdc_irq_install(ddev, priv->irq); if (ret < 0) { dev_err(dev, "failed to install IRQ handler\n"); - goto init_failed; + goto unbind_component; } drm_mode_config_reset(ddev); @@ -372,16 +371,34 @@ static int tilcdc_init(const struct drm_driver *ddrv, struct device *dev) ret = drm_dev_register(ddev, 0); if (ret) - goto init_failed; - priv->is_registered = true; + goto stop_poll; drm_client_setup_with_color_mode(ddev, bpp); return 0; -init_failed: - tilcdc_fini(ddev); +stop_poll: + drm_kms_helper_poll_fini(ddev); + tilcdc_irq_uninstall(ddev); +unbind_component: + if (priv->is_componentized) + component_unbind_all(dev, ddev); +unregister_cpufreq_notif: +#ifdef CONFIG_CPU_FREQ + cpufreq_unregister_notifier(&priv->freq_transition, + CPUFREQ_TRANSITION_NOTIFIER); +destroy_crtc: +#endif + tilcdc_crtc_destroy(priv->crtc); +disable_pm: + pm_runtime_disable(dev); + clk_put(priv->clk); +free_wq: + destroy_workqueue(priv->wq); +put_drm: platform_set_drvdata(pdev, NULL); + ddev->dev_private = NULL; + drm_dev_put(ddev); return ret; } diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.h b/drivers/gpu/drm/tilcdc/tilcdc_drv.h index b818448c83f612..58b276f82a669a 100644 --- a/drivers/gpu/drm/tilcdc/tilcdc_drv.h +++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.h @@ -82,7 +82,6 @@ struct tilcdc_drm_private { struct drm_encoder *external_encoder; struct drm_connector *external_connector; - bool is_registered; bool is_componentized; bool irq_enabled; }; @@ -164,6 +163,7 @@ void tilcdc_crtc_set_panel_info(struct drm_crtc *crtc, void tilcdc_crtc_set_simulate_vesa_sync(struct drm_crtc *crtc, bool simulate_vesa_sync); void tilcdc_crtc_shutdown(struct drm_crtc *crtc); +void tilcdc_crtc_destroy(struct drm_crtc *crtc); int tilcdc_crtc_update_fb(struct drm_crtc *crtc, struct drm_framebuffer *fb, struct drm_pending_vblank_event *event); diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index b47020fca19923..e6abc7b40b1895 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -434,6 +434,11 @@ int ttm_bo_access(struct ttm_buffer_object *bo, unsigned long offset, if (ret) return ret; + if (!bo->resource) { + ret = -ENODATA; + goto unlock; + } + switch (bo->resource->mem_type) { case TTM_PL_SYSTEM: fallthrough; @@ -448,6 +453,7 @@ int ttm_bo_access(struct ttm_buffer_object *bo, unsigned long offset, ret = -EIO; } +unlock: ttm_bo_unreserve(bo); return ret; diff --git a/drivers/irqchip/irq-mchp-eic.c b/drivers/irqchip/irq-mchp-eic.c index 2474fa467a059e..31093a8ab67c3a 100644 --- a/drivers/irqchip/irq-mchp-eic.c +++ b/drivers/irqchip/irq-mchp-eic.c @@ -170,7 +170,7 @@ static int mchp_eic_domain_alloc(struct irq_domain *domain, unsigned int virq, ret = irq_domain_translate_twocell(domain, fwspec, &hwirq, &type); if (ret || hwirq >= MCHP_EIC_NIRQ) - return ret; + return ret ?: -EINVAL; switch (type) { case IRQ_TYPE_EDGE_RISING: diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index c18358271618d2..d5d6ef7ba8381a 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -950,6 +950,19 @@ static struct pgpath *parse_path(struct dm_arg_set *as, struct path_selector *ps q = bdev_get_queue(p->path.dev->bdev); attached_handler_name = scsi_dh_attached_handler_name(q, GFP_KERNEL); + if (IS_ERR(attached_handler_name)) { + if (PTR_ERR(attached_handler_name) == -ENODEV) { + if (m->hw_handler_name) { + DMERR("hardware handlers are only allowed for SCSI devices"); + kfree(m->hw_handler_name); + m->hw_handler_name = NULL; + } + attached_handler_name = NULL; + } else { + r = PTR_ERR(attached_handler_name); + goto bad; + } + } if (attached_handler_name || m->hw_handler_name) { INIT_DELAYED_WORK(&p->activate_path, activate_path_work); r = setup_scsi_dh(p->path.dev->bdev, m, &attached_handler_name, &ti->error); diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index 9d1de68dee278c..d7d41b054b9824 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -106,7 +106,6 @@ config PHANTOM config RPMB tristate "RPMB partition interface" - depends on MMC || SCSI_UFSHCD help Unified RPMB unit interface for RPMB capable devices such as eMMC and UFS. Provides interface for in-kernel security controllers to access diff --git a/drivers/scsi/imm.c b/drivers/scsi/imm.c index 5c602c0577989f..45b0e33293a591 100644 --- a/drivers/scsi/imm.c +++ b/drivers/scsi/imm.c @@ -1260,6 +1260,7 @@ static void imm_detach(struct parport *pb) imm_struct *dev; list_for_each_entry(dev, &imm_hosts, list) { if (dev->dev->port == pb) { + disable_delayed_work_sync(&dev->imm_tq); list_del_init(&dev->list); scsi_remove_host(dev->host); scsi_host_put(dev->host); diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index 95123689e9d1fe..dbd58a7e7bc1f3 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -61,8 +61,8 @@ #include <linux/hdreg.h> #include <linux/reboot.h> #include <linux/stringify.h> +#include <linux/irq.h> #include <asm/io.h> -#include <asm/irq.h> #include <asm/processor.h> #include <scsi/scsi.h> #include <scsi/scsi_host.h> @@ -7844,6 +7844,30 @@ static int ipr_dump_mailbox_wait(struct ipr_cmnd *ipr_cmd) } /** + * ipr_set_affinity_nobalance + * @ioa_cfg: ipr_ioa_cfg struct for an ipr device + * @flag: bool + * true: ensable "IRQ_NO_BALANCING" bit for msix interrupt + * false: disable "IRQ_NO_BALANCING" bit for msix interrupt + * Description: This function will be called to disable/enable + * "IRQ_NO_BALANCING" to avoid irqbalance daemon + * kicking in during adapter reset. + **/ +static void ipr_set_affinity_nobalance(struct ipr_ioa_cfg *ioa_cfg, bool flag) +{ + int irq, i; + + for (i = 0; i < ioa_cfg->nvectors; i++) { + irq = pci_irq_vector(ioa_cfg->pdev, i); + + if (flag) + irq_set_status_flags(irq, IRQ_NO_BALANCING); + else + irq_clear_status_flags(irq, IRQ_NO_BALANCING); + } +} + +/** * ipr_reset_restore_cfg_space - Restore PCI config space. * @ipr_cmd: ipr command struct * @@ -7866,6 +7890,7 @@ static int ipr_reset_restore_cfg_space(struct ipr_cmnd *ipr_cmd) return IPR_RC_JOB_CONTINUE; } + ipr_set_affinity_nobalance(ioa_cfg, false); ipr_fail_all_ops(ioa_cfg); if (ioa_cfg->sis64) { @@ -7945,6 +7970,7 @@ static int ipr_reset_start_bist(struct ipr_cmnd *ipr_cmd) rc = pci_write_config_byte(ioa_cfg->pdev, PCI_BIST, PCI_BIST_START); if (rc == PCIBIOS_SUCCESSFUL) { + ipr_set_affinity_nobalance(ioa_cfg, true); ipr_cmd->job_step = ipr_reset_bist_done; ipr_reset_start_timer(ipr_cmd, IPR_WAIT_FOR_BIST_TIMEOUT); rc = IPR_RC_JOB_RETURN; diff --git a/drivers/scsi/libsas/sas_init.c b/drivers/scsi/libsas/sas_init.c index 8566bb1208a057..6b15ad1bcadabe 100644 --- a/drivers/scsi/libsas/sas_init.c +++ b/drivers/scsi/libsas/sas_init.c @@ -141,6 +141,7 @@ Undo_event_q: Undo_ports: sas_unregister_ports(sas_ha); Undo_phys: + sas_unregister_phys(sas_ha); return error; } diff --git a/drivers/scsi/libsas/sas_internal.h b/drivers/scsi/libsas/sas_internal.h index 6706f2be8d274b..d104c87f04f523 100644 --- a/drivers/scsi/libsas/sas_internal.h +++ b/drivers/scsi/libsas/sas_internal.h @@ -54,6 +54,7 @@ void sas_unregister_dev(struct asd_sas_port *port, struct domain_device *dev); void sas_scsi_recover_host(struct Scsi_Host *shost); int sas_register_phys(struct sas_ha_struct *sas_ha); +void sas_unregister_phys(struct sas_ha_struct *sas_ha); struct asd_sas_event *sas_alloc_event(struct asd_sas_phy *phy, gfp_t gfp_flags); void sas_free_event(struct asd_sas_event *event); @@ -145,20 +146,6 @@ static inline void sas_fail_probe(struct domain_device *dev, const char *func, i func, dev->parent ? "exp-attached" : "direct-attached", SAS_ADDR(dev->sas_addr), err); - - /* - * If the device probe failed, the expander phy attached address - * needs to be reset so that the phy will not be treated as flutter - * in the next revalidation - */ - if (dev->parent && !dev_is_expander(dev->dev_type)) { - struct sas_phy *phy = dev->phy; - struct domain_device *parent = dev->parent; - struct ex_phy *ex_phy = &parent->ex_dev.ex_phy[phy->number]; - - memset(ex_phy->attached_sas_addr, 0, SAS_ADDR_SIZE); - } - sas_unregister_dev(dev->port, dev); } diff --git a/drivers/scsi/libsas/sas_phy.c b/drivers/scsi/libsas/sas_phy.c index 635835c28ecd43..58f08dc2c1872c 100644 --- a/drivers/scsi/libsas/sas_phy.c +++ b/drivers/scsi/libsas/sas_phy.c @@ -116,6 +116,7 @@ static void sas_phye_shutdown(struct work_struct *work) int sas_register_phys(struct sas_ha_struct *sas_ha) { int i; + int err; /* Now register the phys. */ for (i = 0; i < sas_ha->num_phys; i++) { @@ -132,8 +133,10 @@ int sas_register_phys(struct sas_ha_struct *sas_ha) phy->frame_rcvd_size = 0; phy->phy = sas_phy_alloc(&sas_ha->shost->shost_gendev, i); - if (!phy->phy) - return -ENOMEM; + if (!phy->phy) { + err = -ENOMEM; + goto rollback; + } phy->phy->identify.initiator_port_protocols = phy->iproto; @@ -146,10 +149,34 @@ int sas_register_phys(struct sas_ha_struct *sas_ha) phy->phy->maximum_linkrate = SAS_LINK_RATE_UNKNOWN; phy->phy->negotiated_linkrate = SAS_LINK_RATE_UNKNOWN; - sas_phy_add(phy->phy); + err = sas_phy_add(phy->phy); + if (err) { + sas_phy_free(phy->phy); + goto rollback; + } } return 0; +rollback: + for (i-- ; i >= 0 ; i--) { + struct asd_sas_phy *phy = sas_ha->sas_phy[i]; + + sas_phy_delete(phy->phy); + sas_phy_free(phy->phy); + } + return err; +} + +void sas_unregister_phys(struct sas_ha_struct *sas_ha) +{ + int i; + + for (i = 0 ; i < sas_ha->num_phys ; i++) { + struct asd_sas_phy *phy = sas_ha->sas_phy[i]; + + sas_phy_delete(phy->phy); + sas_phy_free(phy->phy); + } } const work_func_t sas_phy_event_fns[PHY_NUM_EVENTS] = { diff --git a/drivers/scsi/mpi3mr/mpi3mr.h b/drivers/scsi/mpi3mr/mpi3mr.h index 6742684e2990a7..31d68c151b2076 100644 --- a/drivers/scsi/mpi3mr/mpi3mr.h +++ b/drivers/scsi/mpi3mr/mpi3mr.h @@ -56,8 +56,8 @@ extern struct list_head mrioc_list; extern int prot_mask; extern atomic64_t event_counter; -#define MPI3MR_DRIVER_VERSION "8.15.0.5.50" -#define MPI3MR_DRIVER_RELDATE "12-August-2025" +#define MPI3MR_DRIVER_VERSION "8.15.0.5.51" +#define MPI3MR_DRIVER_RELDATE "18-November-2025" #define MPI3MR_DRIVER_NAME "mpi3mr" #define MPI3MR_DRIVER_LICENSE "GPL" diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c index b88633e1efe275..d4ca878d088697 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_os.c +++ b/drivers/scsi/mpi3mr/mpi3mr_os.c @@ -1184,6 +1184,8 @@ static void mpi3mr_update_tgtdev(struct mpi3mr_ioc *mrioc, if (is_added == true) tgtdev->io_throttle_enabled = (flags & MPI3_DEVICE0_FLAGS_IO_THROTTLING_REQUIRED) ? 1 : 0; + if (!mrioc->sas_transport_enabled) + tgtdev->non_stl = 1; switch (flags & MPI3_DEVICE0_FLAGS_MAX_WRITE_SAME_MASK) { case MPI3_DEVICE0_FLAGS_MAX_WRITE_SAME_256_LB: @@ -4844,7 +4846,7 @@ static int mpi3mr_target_alloc(struct scsi_target *starget) spin_lock_irqsave(&mrioc->tgtdev_lock, flags); if (starget->channel == mrioc->scsi_device_channel) { tgt_dev = __mpi3mr_get_tgtdev_by_perst_id(mrioc, starget->id); - if (tgt_dev && !tgt_dev->is_hidden) { + if (tgt_dev && !tgt_dev->is_hidden && tgt_dev->non_stl) { scsi_tgt_priv_data->starget = starget; scsi_tgt_priv_data->dev_handle = tgt_dev->dev_handle; scsi_tgt_priv_data->perst_id = tgt_dev->perst_id; diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 3a57f07d73f587..16a44c0917e18b 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -17,6 +17,7 @@ #include <linux/crash_dump.h> #include <linux/trace_events.h> #include <linux/trace.h> +#include <linux/irq.h> #include <scsi/scsi_tcq.h> #include <scsi/scsicam.h> @@ -7776,6 +7777,31 @@ static void qla_pci_error_cleanup(scsi_qla_host_t *vha) } +/** + * qla2xxx_set_affinity_nobalance + * @pdev: pci_dev struct for a qla2xxx device + * @flag: bool + * true: enable "IRQ_NO_BALANCING" bit for msix interrupt + * false: disable "IRQ_NO_BALANCING" bit for msix interrupt + * Description: This function will be called to disable/enable + * "IRQ_NO_BALANCING" to avoid irqbalance daemon + * kicking in during adapter reset. + **/ + +static void qla2xxx_set_affinity_nobalance(struct pci_dev *pdev, bool flag) +{ + int irq, i; + + for (i = 0; i < QLA_BASE_VECTORS; i++) { + irq = pci_irq_vector(pdev, i); + + if (flag) + irq_set_status_flags(irq, IRQ_NO_BALANCING); + else + irq_clear_status_flags(irq, IRQ_NO_BALANCING); + } +} + static pci_ers_result_t qla2xxx_pci_error_detected(struct pci_dev *pdev, pci_channel_state_t state) { @@ -7794,6 +7820,8 @@ qla2xxx_pci_error_detected(struct pci_dev *pdev, pci_channel_state_t state) goto out; } + qla2xxx_set_affinity_nobalance(pdev, false); + switch (state) { case pci_channel_io_normal: qla_pci_set_eeh_busy(vha); @@ -7930,6 +7958,8 @@ exit_slot_reset: ql_dbg(ql_dbg_aer, base_vha, 0x900e, "Slot Reset returning %x.\n", ret); + qla2xxx_set_affinity_nobalance(pdev, true); + return ret; } diff --git a/drivers/scsi/qla4xxx/ql4_nx.c b/drivers/scsi/qla4xxx/ql4_nx.c index da2fc66ffedd5d..b0a62aaa1cca90 100644 --- a/drivers/scsi/qla4xxx/ql4_nx.c +++ b/drivers/scsi/qla4xxx/ql4_nx.c @@ -1552,7 +1552,7 @@ static int qla4_82xx_cmdpeg_ready(struct scsi_qla_host *ha, int pegtune_val) (val == PHAN_INITIALIZE_ACK)) return 0; set_current_state(TASK_UNINTERRUPTIBLE); - schedule_timeout(500); + schedule_timeout(msecs_to_jiffies(500)); } while (--retries); diff --git a/drivers/scsi/scsi_dh.c b/drivers/scsi/scsi_dh.c index 7b56e00c7df6b0..b9d80531781494 100644 --- a/drivers/scsi/scsi_dh.c +++ b/drivers/scsi/scsi_dh.c @@ -353,7 +353,8 @@ EXPORT_SYMBOL_GPL(scsi_dh_attach); * that may have a device handler attached * @gfp - the GFP mask used in the kmalloc() call when allocating memory * - * Returns name of attached handler, NULL if no handler is attached. + * Returns name of attached handler, NULL if no handler is attached, or + * and error pointer if an error occurred. * Caller must take care to free the returned string. */ const char *scsi_dh_attached_handler_name(struct request_queue *q, gfp_t gfp) @@ -363,10 +364,11 @@ const char *scsi_dh_attached_handler_name(struct request_queue *q, gfp_t gfp) sdev = scsi_device_from_queue(q); if (!sdev) - return NULL; + return ERR_PTR(-ENODEV); if (sdev->handler) - handler_name = kstrdup(sdev->handler->name, gfp); + handler_name = kstrdup(sdev->handler->name, gfp) ? : + ERR_PTR(-ENOMEM); put_device(&sdev->sdev_gendev); return handler_name; } diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 51ad2ad07e4390..93031326ac3ee9 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -2801,7 +2801,7 @@ EXPORT_SYMBOL_GPL(sdev_evt_send_simple); * * Must be called with user context, may sleep. * - * Returns zero if unsuccessful or an error if not. + * Returns zero if successful or an error if not. */ int scsi_device_quiesce(struct scsi_device *sdev) diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c index b8457477cee9eb..9f167ff8da7b07 100644 --- a/drivers/target/sbp/sbp_target.c +++ b/drivers/target/sbp/sbp_target.c @@ -5,8 +5,7 @@ * Copyright (C) 2011 Chris Boot <bootc@bootc.net> */ -#define KMSG_COMPONENT "sbp_target" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "sbp_target: " fmt #include <linux/kernel.h> #include <linux/module.h> diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index e8b7955d40f29a..50d21888a0c9a7 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1524,6 +1524,7 @@ target_cmd_init_cdb(struct se_cmd *cmd, unsigned char *cdb, gfp_t gfp) if (scsi_command_size(cdb) > sizeof(cmd->__t_task_cdb)) { cmd->t_task_cdb = kzalloc(scsi_command_size(cdb), gfp); if (!cmd->t_task_cdb) { + cmd->t_task_cdb = &cmd->__t_task_cdb[0]; pr_err("Unable to allocate cmd->t_task_cdb" " %u > sizeof(cmd->__t_task_cdb): %lu ops\n", scsi_command_size(cdb), diff --git a/drivers/ufs/Kconfig b/drivers/ufs/Kconfig index 90226f72c158aa..f662e7ce71f1bd 100644 --- a/drivers/ufs/Kconfig +++ b/drivers/ufs/Kconfig @@ -6,6 +6,7 @@ menuconfig SCSI_UFSHCD tristate "Universal Flash Storage Controller" depends on SCSI && SCSI_DMA + depends on RPMB || !RPMB select PM_DEVFREQ select DEVFREQ_GOV_SIMPLE_ONDEMAND select NLS diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 040a0ceb170a7f..80c0b49f30b012 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -1455,15 +1455,14 @@ out: static void ufshcd_clock_scaling_unprepare(struct ufs_hba *hba, int err) { up_write(&hba->clk_scaling_lock); + mutex_unlock(&hba->wb_mutex); + blk_mq_unquiesce_tagset(&hba->host->tag_set); + mutex_unlock(&hba->host->scan_mutex); /* Enable Write Booster if current gear requires it else disable it */ if (ufshcd_enable_wb_if_scaling_up(hba) && !err) ufshcd_wb_toggle(hba, hba->pwr_info.gear_rx >= hba->clk_scaling.wb_gear); - mutex_unlock(&hba->wb_mutex); - - blk_mq_unquiesce_tagset(&hba->host->tag_set); - mutex_unlock(&hba->host->scan_mutex); ufshcd_release(hba); } @@ -6504,6 +6503,11 @@ static void ufshcd_clk_scaling_suspend(struct ufs_hba *hba, bool suspend) static void ufshcd_err_handling_prepare(struct ufs_hba *hba) { + /* + * A WLUN resume failure could potentially lead to the HBA being + * runtime suspended, so take an extra reference on hba->dev. + */ + pm_runtime_get_sync(hba->dev); ufshcd_rpm_get_sync(hba); if (pm_runtime_status_suspended(&hba->ufs_device_wlun->sdev_gendev) || hba->is_sys_suspended) { @@ -6543,6 +6547,7 @@ static void ufshcd_err_handling_unprepare(struct ufs_hba *hba) if (ufshcd_is_clkscaling_supported(hba)) ufshcd_clk_scaling_suspend(hba, false); ufshcd_rpm_put(hba); + pm_runtime_put(hba->dev); } static inline bool ufshcd_err_handling_should_stop(struct ufs_hba *hba) @@ -6557,28 +6562,42 @@ static inline bool ufshcd_err_handling_should_stop(struct ufs_hba *hba) #ifdef CONFIG_PM static void ufshcd_recover_pm_error(struct ufs_hba *hba) { + struct scsi_target *starget = hba->ufs_device_wlun->sdev_target; struct Scsi_Host *shost = hba->host; struct scsi_device *sdev; struct request_queue *q; - int ret; + bool resume_sdev_queues = false; hba->is_sys_suspended = false; + /* - * Set RPM status of wlun device to RPM_ACTIVE, - * this also clears its runtime error. + * Ensure the parent's error status is cleared before proceeding + * to the child, as the parent must be active to activate the child. */ - ret = pm_runtime_set_active(&hba->ufs_device_wlun->sdev_gendev); + if (hba->dev->power.runtime_error) { + /* hba->dev has no functional parent thus simplily set RPM_ACTIVE */ + pm_runtime_set_active(hba->dev); + resume_sdev_queues = true; + } + + if (hba->ufs_device_wlun->sdev_gendev.power.runtime_error) { + /* + * starget, parent of wlun, might be suspended if wlun resume failed. + * Make sure parent is resumed before set child (wlun) active. + */ + pm_runtime_get_sync(&starget->dev); + pm_runtime_set_active(&hba->ufs_device_wlun->sdev_gendev); + pm_runtime_put_sync(&starget->dev); + resume_sdev_queues = true; + } - /* hba device might have a runtime error otherwise */ - if (ret) - ret = pm_runtime_set_active(hba->dev); /* * If wlun device had runtime error, we also need to resume those * consumer scsi devices in case any of them has failed to be * resumed due to supplier runtime resume failure. This is to unblock * blk_queue_enter in case there are bios waiting inside it. */ - if (!ret) { + if (resume_sdev_queues) { shost_for_each_device(sdev, shost) { q = sdev->request_queue; if (q->dev && (q->rpm_status == RPM_SUSPENDED || @@ -6679,19 +6698,22 @@ static void ufshcd_err_handler(struct work_struct *work) hba->saved_uic_err, hba->force_reset, ufshcd_is_link_broken(hba) ? "; link is broken" : ""); - /* - * Use ufshcd_rpm_get_noresume() here to safely perform link recovery - * even if an error occurs during runtime suspend or runtime resume. - * This avoids potential deadlocks that could happen if we tried to - * resume the device while a PM operation is already in progress. - */ - ufshcd_rpm_get_noresume(hba); - if (hba->pm_op_in_progress) { - ufshcd_link_recovery(hba); + if (hba->ufs_device_wlun) { + /* + * Use ufshcd_rpm_get_noresume() here to safely perform link + * recovery even if an error occurs during runtime suspend or + * runtime resume. This avoids potential deadlocks that could + * happen if we tried to resume the device while a PM operation + * is already in progress. + */ + ufshcd_rpm_get_noresume(hba); + if (hba->pm_op_in_progress) { + ufshcd_link_recovery(hba); + ufshcd_rpm_put(hba); + return; + } ufshcd_rpm_put(hba); - return; } - ufshcd_rpm_put(hba); down(&hba->host_sem); spin_lock_irqsave(hba->host->host_lock, flags); diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c index 8d119b3223cbda..8ebee0cc531370 100644 --- a/drivers/ufs/host/ufs-qcom.c +++ b/drivers/ufs/host/ufs-qcom.c @@ -1769,10 +1769,9 @@ static void ufs_qcom_dump_testbus(struct ufs_hba *hba) { struct ufs_qcom_host *host = ufshcd_get_variant(hba); int i, j, nminor = 0, testbus_len = 0; - u32 *testbus __free(kfree) = NULL; char *prefix; - testbus = kmalloc_array(256, sizeof(u32), GFP_KERNEL); + u32 *testbus __free(kfree) = kmalloc_array(256, sizeof(u32), GFP_KERNEL); if (!testbus) return; @@ -1794,13 +1793,12 @@ static void ufs_qcom_dump_testbus(struct ufs_hba *hba) static int ufs_qcom_dump_regs(struct ufs_hba *hba, size_t offset, size_t len, const char *prefix, void __iomem *base) { - u32 *regs __free(kfree) = NULL; size_t pos; if (offset % 4 != 0 || len % 4 != 0) return -EINVAL; - regs = kzalloc(len, GFP_ATOMIC); + u32 *regs __free(kfree) = kzalloc(len, GFP_ATOMIC); if (!regs) return -ENOMEM; diff --git a/fs/ceph/Kconfig b/fs/ceph/Kconfig index 3e7def3d31c16f..3d64a316ca31d3 100644 --- a/fs/ceph/Kconfig +++ b/fs/ceph/Kconfig @@ -3,9 +3,6 @@ config CEPH_FS tristate "Ceph distributed file system" depends on INET select CEPH_LIB - select CRC32 - select CRYPTO_AES - select CRYPTO select NETFS_SUPPORT select FS_ENCRYPTION_ALGS if FS_ENCRYPTION default n diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index b1a8ff612c41dc..2f663972da99cc 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -18,6 +18,7 @@ #include "crypto.h" #include <linux/ceph/decode.h> #include <linux/ceph/messenger.h> +#include <trace/events/ceph.h> /* * Capability management @@ -4452,6 +4453,9 @@ void ceph_handle_caps(struct ceph_mds_session *session, session->s_mds, ceph_cap_op_name(op), vino.ino, vino.snap, inode, seq, issue_seq, mseq); + trace_ceph_handle_caps(mdsc, session, op, &vino, ceph_inode(inode), + seq, issue_seq, mseq); + mutex_lock(&session->s_mutex); if (!inode) { diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 1740047aef0f9a..7e4eab824daef8 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -24,6 +24,7 @@ #include <linux/ceph/pagelist.h> #include <linux/ceph/auth.h> #include <linux/ceph/debugfs.h> +#include <trace/events/ceph.h> #define RECONNECT_MAX_SIZE (INT_MAX - PAGE_SIZE) @@ -3288,6 +3289,8 @@ static void complete_request(struct ceph_mds_client *mdsc, { req->r_end_latency = ktime_get(); + trace_ceph_mdsc_complete_request(mdsc, req); + if (req->r_callback) req->r_callback(mdsc, req); complete_all(&req->r_completion); @@ -3419,6 +3422,8 @@ static int __send_request(struct ceph_mds_session *session, { int err; + trace_ceph_mdsc_send_request(session, req); + err = __prepare_send_request(session, req, drop_cap_releases); if (!err) { ceph_msg_get(req->r_request); @@ -3470,6 +3475,8 @@ static void __do_request(struct ceph_mds_client *mdsc, } if (mdsc->mdsmap->m_epoch == 0) { doutc(cl, "no mdsmap, waiting for map\n"); + trace_ceph_mdsc_suspend_request(mdsc, session, req, + ceph_mdsc_suspend_reason_no_mdsmap); list_add(&req->r_wait, &mdsc->waiting_for_map); return; } @@ -3491,6 +3498,8 @@ static void __do_request(struct ceph_mds_client *mdsc, goto finish; } doutc(cl, "no mds or not active, waiting for map\n"); + trace_ceph_mdsc_suspend_request(mdsc, session, req, + ceph_mdsc_suspend_reason_no_active_mds); list_add(&req->r_wait, &mdsc->waiting_for_map); return; } @@ -3536,9 +3545,11 @@ static void __do_request(struct ceph_mds_client *mdsc, * it to the mdsc queue. */ if (session->s_state == CEPH_MDS_SESSION_REJECTED) { - if (ceph_test_mount_opt(mdsc->fsc, CLEANRECOVER)) + if (ceph_test_mount_opt(mdsc->fsc, CLEANRECOVER)) { + trace_ceph_mdsc_suspend_request(mdsc, session, req, + ceph_mdsc_suspend_reason_rejected); list_add(&req->r_wait, &mdsc->waiting_for_map); - else + } else err = -EACCES; goto out_session; } @@ -3552,6 +3563,8 @@ static void __do_request(struct ceph_mds_client *mdsc, if (random) req->r_resend_mds = mds; } + trace_ceph_mdsc_suspend_request(mdsc, session, req, + ceph_mdsc_suspend_reason_session); list_add(&req->r_wait, &session->s_waiting); goto out_session; } @@ -3652,6 +3665,7 @@ static void __wake_requests(struct ceph_mds_client *mdsc, list_del_init(&req->r_wait); doutc(cl, " wake request %p tid %llu\n", req, req->r_tid); + trace_ceph_mdsc_resume_request(mdsc, req); __do_request(mdsc, req); } } @@ -3678,6 +3692,7 @@ static void kick_requests(struct ceph_mds_client *mdsc, int mds) req->r_session->s_mds == mds) { doutc(cl, " kicking tid %llu\n", req->r_tid); list_del_init(&req->r_wait); + trace_ceph_mdsc_resume_request(mdsc, req); __do_request(mdsc, req); } } @@ -3724,6 +3739,7 @@ int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, struct inode *dir, doutc(cl, "submit_request on %p for inode %p\n", req, dir); mutex_lock(&mdsc->mutex); __register_request(mdsc, req, dir); + trace_ceph_mdsc_submit_request(mdsc, req); __do_request(mdsc, req); err = req->r_err; mutex_unlock(&mdsc->mutex); diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index c65f2b202b2b3e..521507ea826000 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -374,7 +374,7 @@ static int build_snap_context(struct ceph_mds_client *mdsc, /* alloc new snap context */ err = -ENOMEM; - if (num > (SIZE_MAX - sizeof(*snapc)) / sizeof(u64)) + if ((size_t)num > (SIZE_MAX - sizeof(*snapc)) / sizeof(u64)) goto fail; snapc = ceph_create_snap_context(num, GFP_NOFS); if (!snapc) diff --git a/fs/ceph/super.c b/fs/ceph/super.c index f6bf24b5c683ef..7c1c1dac320da3 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -30,6 +30,9 @@ #include <uapi/linux/magic.h> +#define CREATE_TRACE_POINTS +#include <trace/events/ceph.h> + static DEFINE_SPINLOCK(ceph_fsc_lock); static LIST_HEAD(ceph_fsc_list); diff --git a/fs/fat/cache.c b/fs/fat/cache.c index 2af424e200b35e..630f3056658ef3 100644 --- a/fs/fat/cache.c +++ b/fs/fat/cache.c @@ -29,11 +29,6 @@ struct fat_cache_id { int dcluster; }; -static inline int fat_max_cache(struct inode *inode) -{ - return FAT_MAX_CACHE; -} - static struct kmem_cache *fat_cache_cachep; static void init_once(void *foo) @@ -145,7 +140,7 @@ static void fat_cache_add(struct inode *inode, struct fat_cache_id *new) cache = fat_cache_merge(inode, new); if (cache == NULL) { - if (MSDOS_I(inode)->nr_caches < fat_max_cache(inode)) { + if (MSDOS_I(inode)->nr_caches < FAT_MAX_CACHE) { MSDOS_I(inode)->nr_caches++; spin_unlock(&MSDOS_I(inode)->cache_lru_lock); diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index b267ec580da995..58bf58b68955c5 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -10,6 +10,7 @@ #include <linux/fs.h> #include <linux/types.h> #include <linux/slab.h> +#include <linux/string.h> #include <linux/highmem.h> #include <linux/swap.h> #include <linux/quotaops.h> @@ -1037,7 +1038,7 @@ static int ocfs2_create_new_meta_bhs(handle_t *handle, memset(bhs[i]->b_data, 0, osb->sb->s_blocksize); eb = (struct ocfs2_extent_block *) bhs[i]->b_data; /* Ok, setup the minimal stuff here. */ - strcpy(eb->h_signature, OCFS2_EXTENT_BLOCK_SIGNATURE); + strscpy(eb->h_signature, OCFS2_EXTENT_BLOCK_SIGNATURE); eb->h_blkno = cpu_to_le64(first_blkno); eb->h_fs_generation = cpu_to_le32(osb->fs_generation); eb->h_suballoc_slot = @@ -3654,7 +3655,6 @@ static int ocfs2_merge_rec_left(struct ocfs2_path *right_path, * So we use the new rightmost path. */ ocfs2_mv_path(right_path, left_path); - left_path = NULL; } else ocfs2_complete_edge_insert(handle, left_path, right_path, subtree_index); @@ -6164,7 +6164,7 @@ static int ocfs2_get_truncate_log_info(struct ocfs2_super *osb, struct buffer_head *bh = NULL; struct ocfs2_dinode *di; struct ocfs2_truncate_log *tl; - unsigned int tl_count; + unsigned int tl_count, tl_used; inode = ocfs2_get_system_file_inode(osb, TRUNCATE_LOG_SYSTEM_INODE, @@ -6185,8 +6185,10 @@ static int ocfs2_get_truncate_log_info(struct ocfs2_super *osb, di = (struct ocfs2_dinode *)bh->b_data; tl = &di->id2.i_dealloc; tl_count = le16_to_cpu(tl->tl_count); + tl_used = le16_to_cpu(tl->tl_used); if (unlikely(tl_count > ocfs2_truncate_recs_per_inode(osb->sb) || - tl_count == 0)) { + tl_count == 0 || + tl_used > tl_count)) { status = -EFSCORRUPTED; iput(inode); brelse(bh); @@ -6744,7 +6746,7 @@ static int ocfs2_reuse_blk_from_dealloc(handle_t *handle, /* We can't guarantee that buffer head is still cached, so * polutlate the extent block again. */ - strcpy(eb->h_signature, OCFS2_EXTENT_BLOCK_SIGNATURE); + strscpy(eb->h_signature, OCFS2_EXTENT_BLOCK_SIGNATURE); eb->h_blkno = cpu_to_le64(bf->free_blk); eb->h_fs_generation = cpu_to_le32(osb->fs_generation); eb->h_suballoc_slot = cpu_to_le16(real_slot); diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c index 8f714406528d62..701d27d908d4b2 100644 --- a/fs/ocfs2/buffer_head_io.c +++ b/fs/ocfs2/buffer_head_io.c @@ -434,7 +434,7 @@ int ocfs2_write_super_or_backup(struct ocfs2_super *osb, BUG_ON(buffer_jbd(bh)); ocfs2_check_super_or_backup(osb->sb, bh->b_blocknr); - if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) { + if (unlikely(ocfs2_emergency_state(osb))) { ret = -EROFS; mlog_errno(ret); goto out; diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c index 2f61d39e4e509b..6bc4e064ace464 100644 --- a/fs/ocfs2/cluster/nodemanager.c +++ b/fs/ocfs2/cluster/nodemanager.c @@ -4,6 +4,7 @@ */ #include <linux/slab.h> +#include <linux/string.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/configfs.h> @@ -590,7 +591,7 @@ static struct config_item *o2nm_node_group_make_item(struct config_group *group, if (node == NULL) return ERR_PTR(-ENOMEM); - strcpy(node->nd_name, name); /* use item.ci_namebuf instead? */ + strscpy(node->nd_name, name); /* use item.ci_namebuf instead? */ config_item_init_type_name(&node->nd_item, name, &o2nm_node_type); spin_lock_init(&node->nd_lock); diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index 2785ff245e79e4..782afd9fa93481 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -136,7 +136,7 @@ static void ocfs2_init_dir_trailer(struct inode *inode, struct ocfs2_dir_block_trailer *trailer; trailer = ocfs2_trailer_from_bh(bh, inode->i_sb); - strcpy(trailer->db_signature, OCFS2_DIR_TRAILER_SIGNATURE); + strscpy(trailer->db_signature, OCFS2_DIR_TRAILER_SIGNATURE); trailer->db_compat_rec_len = cpu_to_le16(sizeof(struct ocfs2_dir_block_trailer)); trailer->db_parent_dinode = cpu_to_le64(OCFS2_I(inode)->ip_blkno); @@ -2213,14 +2213,14 @@ static struct ocfs2_dir_entry *ocfs2_fill_initial_dirents(struct inode *inode, de->name_len = 1; de->rec_len = cpu_to_le16(OCFS2_DIR_REC_LEN(de->name_len)); - strcpy(de->name, "."); + strscpy(de->name, "."); ocfs2_set_de_type(de, S_IFDIR); de = (struct ocfs2_dir_entry *) ((char *)de + le16_to_cpu(de->rec_len)); de->inode = cpu_to_le64(OCFS2_I(parent)->ip_blkno); de->rec_len = cpu_to_le16(size - OCFS2_DIR_REC_LEN(1)); de->name_len = 2; - strcpy(de->name, ".."); + strscpy(de->name, ".."); ocfs2_set_de_type(de, S_IFDIR); return de; @@ -2378,7 +2378,7 @@ static int ocfs2_dx_dir_attach_index(struct ocfs2_super *osb, dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data; memset(dx_root, 0, osb->sb->s_blocksize); - strcpy(dx_root->dr_signature, OCFS2_DX_ROOT_SIGNATURE); + strscpy(dx_root->dr_signature, OCFS2_DX_ROOT_SIGNATURE); dx_root->dr_suballoc_slot = cpu_to_le16(meta_ac->ac_alloc_slot); dx_root->dr_suballoc_loc = cpu_to_le64(suballoc_loc); dx_root->dr_suballoc_bit = cpu_to_le16(dr_suballoc_bit); @@ -2454,7 +2454,7 @@ static int ocfs2_dx_dir_format_cluster(struct ocfs2_super *osb, dx_leaf = (struct ocfs2_dx_leaf *) bh->b_data; memset(dx_leaf, 0, osb->sb->s_blocksize); - strcpy(dx_leaf->dl_signature, OCFS2_DX_LEAF_SIGNATURE); + strscpy(dx_leaf->dl_signature, OCFS2_DX_LEAF_SIGNATURE); dx_leaf->dl_fs_generation = cpu_to_le32(osb->fs_generation); dx_leaf->dl_blkno = cpu_to_le64(bh->b_blocknr); dx_leaf->dl_list.de_count = diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 21d797ccccd068..732c61599159cc 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -179,7 +179,7 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end, file->f_path.dentry->d_name.name, (unsigned long long)datasync); - if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) + if (unlikely(ocfs2_emergency_state(osb))) return -EROFS; err = file_write_and_wait_range(file, start, end); @@ -209,7 +209,7 @@ int ocfs2_should_update_atime(struct inode *inode, struct timespec64 now; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); - if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) + if (unlikely(ocfs2_emergency_state(osb))) return 0; if ((inode->i_flags & S_NOATIME) || @@ -1136,6 +1136,12 @@ int ocfs2_setattr(struct mnt_idmap *idmap, struct dentry *dentry, attr->ia_valid & ATTR_GID ? from_kgid(&init_user_ns, attr->ia_gid) : 0); + status = ocfs2_emergency_state(osb); + if (unlikely(status)) { + mlog_errno(status); + goto bail; + } + /* ensuring we don't even attempt to truncate a symlink */ if (S_ISLNK(inode->i_mode)) attr->ia_valid &= ~ATTR_SIZE; @@ -1943,7 +1949,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, handle_t *handle; unsigned long long max_off = inode->i_sb->s_maxbytes; - if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) + if (unlikely(ocfs2_emergency_state(osb))) return -EROFS; inode_lock(inode); @@ -2707,7 +2713,7 @@ static loff_t ocfs2_remap_file_range(struct file *file_in, loff_t pos_in, return -EINVAL; if (!ocfs2_refcount_tree(osb)) return -EOPNOTSUPP; - if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) + if (unlikely(ocfs2_emergency_state(osb))) return -EROFS; /* Lock both files against IO */ diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 8340525e5589c0..b5fcc2725a2962 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -1442,6 +1442,14 @@ int ocfs2_validate_inode_block(struct super_block *sb, goto bail; } + if ((!di->i_links_count && !di->i_links_count_hi) || !di->i_mode) { + mlog(ML_ERROR, "Invalid dinode #%llu: " + "Corrupt state (nlink = %u or mode = %u) detected!\n", + (unsigned long long)bh->b_blocknr, + ocfs2_read_links_count(di), le16_to_cpu(di->i_mode)); + rc = -EFSCORRUPTED; + goto bail; + } /* * Errors after here are fatal. */ @@ -1604,8 +1612,7 @@ static int ocfs2_filecheck_repair_inode_block(struct super_block *sb, trace_ocfs2_filecheck_repair_inode_block( (unsigned long long)bh->b_blocknr); - if (ocfs2_is_hard_readonly(OCFS2_SB(sb)) || - ocfs2_is_soft_readonly(OCFS2_SB(sb))) { + if (unlikely(ocfs2_emergency_state(OCFS2_SB(sb)))) { mlog(ML_ERROR, "Filecheck: cannot repair dinode #%llu " "on readonly filesystem\n", diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index ce978a2497d9de..99637e34d9daf8 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -909,7 +909,7 @@ static int ocfs2_move_extents(struct ocfs2_move_extents_context *context) struct buffer_head *di_bh = NULL; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); - if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) + if (unlikely(ocfs2_emergency_state(osb))) return -EROFS; inode_lock(inode); diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index c90b254da75eb5..4ec6dbed65a86c 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -23,6 +23,7 @@ #include <linux/fs.h> #include <linux/types.h> #include <linux/slab.h> +#include <linux/string.h> #include <linux/highmem.h> #include <linux/quotaops.h> #include <linux/iversion.h> @@ -568,7 +569,7 @@ static int __ocfs2_mknod_locked(struct inode *dir, ocfs2_set_links_count(fe, inode->i_nlink); fe->i_last_eb_blk = 0; - strcpy(fe->i_signature, OCFS2_INODE_SIGNATURE); + strscpy(fe->i_signature, OCFS2_INODE_SIGNATURE); fe->i_flags |= cpu_to_le32(OCFS2_VALID_FL); ktime_get_coarse_real_ts64(&ts); fe->i_atime = fe->i_ctime = fe->i_mtime = diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 6aaa94c554c12a..7b50e03dfa664a 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -680,6 +680,24 @@ static inline int ocfs2_is_soft_readonly(struct ocfs2_super *osb) return ret; } +static inline int ocfs2_is_readonly(struct ocfs2_super *osb) +{ + int ret; + spin_lock(&osb->osb_lock); + ret = osb->osb_flags & (OCFS2_OSB_SOFT_RO | OCFS2_OSB_HARD_RO); + spin_unlock(&osb->osb_lock); + + return ret; +} + +static inline int ocfs2_emergency_state(struct ocfs2_super *osb) +{ + if (ocfs2_is_readonly(osb)) + return -EROFS; + + return 0; +} + static inline int ocfs2_clusterinfo_valid(struct ocfs2_super *osb) { return (osb->s_feature_incompat & diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c index b0733c08ed13b1..ac3ec2c2111963 100644 --- a/fs/ocfs2/resize.c +++ b/fs/ocfs2/resize.c @@ -276,7 +276,7 @@ int ocfs2_group_extend(struct inode * inode, int new_clusters) u32 first_new_cluster; u64 lgd_blkno; - if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) + if (unlikely(ocfs2_emergency_state(osb))) return -EROFS; if (new_clusters < 0) @@ -466,7 +466,7 @@ int ocfs2_group_add(struct inode *inode, struct ocfs2_new_group_input *input) u16 cl_bpc; u64 bg_ptr; - if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) + if (unlikely(ocfs2_emergency_state(osb))) return -EROFS; main_bm_inode = ocfs2_get_system_file_inode(osb, diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index a28c127b9934bc..fca2fd07c881d1 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -10,6 +10,7 @@ #include <linux/list.h> #include <linux/spinlock.h> +#include <linux/string.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/kmod.h> @@ -670,7 +671,7 @@ static int __init ocfs2_stack_glue_init(void) { int ret; - strcpy(cluster_stack_name, OCFS2_STACK_PLUGIN_O2CB); + strscpy(cluster_stack_name, OCFS2_STACK_PLUGIN_O2CB); ocfs2_table_header = register_sysctl("fs/ocfs2/nm", ocfs2_nm_table); if (!ocfs2_table_header) { diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index 6ac4dcd54588cf..8e6e5235b30c46 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -11,6 +11,7 @@ #include <linux/fs.h> #include <linux/types.h> #include <linux/slab.h> +#include <linux/string.h> #include <linux/highmem.h> #include <cluster/masklog.h> @@ -372,7 +373,7 @@ static int ocfs2_block_group_fill(handle_t *handle, } memset(bg, 0, sb->s_blocksize); - strcpy(bg->bg_signature, OCFS2_GROUP_DESC_SIGNATURE); + strscpy(bg->bg_signature, OCFS2_GROUP_DESC_SIGNATURE); bg->bg_generation = cpu_to_le32(osb->fs_generation); bg->bg_size = cpu_to_le16(ocfs2_group_bitmap_size(sb, 1, osb->s_feature_incompat)); @@ -1992,6 +1993,16 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac, } cl = (struct ocfs2_chain_list *) &fe->id2.i_chain; + if (!le16_to_cpu(cl->cl_next_free_rec) || + le16_to_cpu(cl->cl_next_free_rec) > le16_to_cpu(cl->cl_count)) { + status = ocfs2_error(ac->ac_inode->i_sb, + "Chain allocator dinode %llu has invalid next " + "free chain record %u, but only %u total\n", + (unsigned long long)le64_to_cpu(fe->i_blkno), + le16_to_cpu(cl->cl_next_free_rec), + le16_to_cpu(cl->cl_count)); + goto bail; + } victim = ocfs2_find_victim_chain(cl); ac->ac_chain = victim; diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 2c7ba1480f7a1b..3cbafac50cd137 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -2487,7 +2487,7 @@ static int ocfs2_handle_error(struct super_block *sb) rv = -EIO; } else { /* default option */ rv = -EROFS; - if (sb_rdonly(sb) && (ocfs2_is_soft_readonly(osb) || ocfs2_is_hard_readonly(osb))) + if (sb_rdonly(sb) && ocfs2_emergency_state(osb)) return rv; pr_crit("OCFS2: File system is now read-only.\n"); diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index dc1761e8481422..1b21fbc16d73a2 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -49,9 +49,13 @@ #include "ocfs2_trace.h" struct ocfs2_xattr_def_value_root { - struct ocfs2_xattr_value_root xv; - struct ocfs2_extent_rec er; + /* Must be last as it ends in a flexible-array member. */ + TRAILING_OVERLAP(struct ocfs2_xattr_value_root, xv, xr_list.l_recs, + struct ocfs2_extent_rec er; + ); }; +static_assert(offsetof(struct ocfs2_xattr_def_value_root, xv.xr_list.l_recs) == + offsetof(struct ocfs2_xattr_def_value_root, er)); struct ocfs2_xattr_bucket { /* The inode these xattrs are associated with */ @@ -971,13 +975,39 @@ static int ocfs2_xattr_ibody_list(struct inode *inode, struct ocfs2_xattr_header *header = NULL; struct ocfs2_inode_info *oi = OCFS2_I(inode); int ret = 0; + u16 xattr_count; + size_t max_entries; + u16 inline_size; if (!(oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL)) return ret; + inline_size = le16_to_cpu(di->i_xattr_inline_size); + + /* Validate inline size is reasonable */ + if (inline_size > inode->i_sb->s_blocksize || + inline_size < sizeof(struct ocfs2_xattr_header)) { + ocfs2_error(inode->i_sb, + "Invalid xattr inline size %u in inode %llu\n", + inline_size, + (unsigned long long)OCFS2_I(inode)->ip_blkno); + return -EFSCORRUPTED; + } + header = (struct ocfs2_xattr_header *) - ((void *)di + inode->i_sb->s_blocksize - - le16_to_cpu(di->i_xattr_inline_size)); + ((void *)di + inode->i_sb->s_blocksize - inline_size); + + xattr_count = le16_to_cpu(header->xh_count); + max_entries = (inline_size - sizeof(struct ocfs2_xattr_header)) / + sizeof(struct ocfs2_xattr_entry); + + if (xattr_count > max_entries) { + ocfs2_error(inode->i_sb, + "xattr entry count %u exceeds maximum %zu in inode %llu\n", + xattr_count, max_entries, + (unsigned long long)OCFS2_I(inode)->ip_blkno); + return -EFSCORRUPTED; + } ret = ocfs2_xattr_list_entries(inode, header, buffer, buffer_size); diff --git a/include/linux/args.h b/include/linux/args.h index 2e8e65d975c778..0562dc51435e2d 100644 --- a/include/linux/args.h +++ b/include/linux/args.h @@ -6,9 +6,9 @@ /* * How do these macros work? * - * In __COUNT_ARGS() _0 to _12 are just placeholders from the start + * In __COUNT_ARGS() _0 to _15 are just placeholders from the start * in order to make sure _n is positioned over the correct number - * from 12 to 0 (depending on X, which is a variadic argument list). + * from 15 to 0 (depending on X, which is a variadic argument list). * They serve no purpose other than occupying a position. Since each * macro parameter must have a distinct identifier, those identifiers * are as good as any. diff --git a/include/linux/file.h b/include/linux/file.h index cf389fde9bc28c..27484b444d3155 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -161,12 +161,10 @@ typedef struct fd_prepare class_fd_prepare_t; /* Do not use directly. */ static inline void class_fd_prepare_destructor(const struct fd_prepare *fdf) { - if (unlikely(fdf->err)) { - if (likely(fdf->__fd >= 0)) - put_unused_fd(fdf->__fd); - if (unlikely(!IS_ERR_OR_NULL(fdf->__file))) - fput(fdf->__file); - } + if (unlikely(fdf->__fd >= 0)) + put_unused_fd(fdf->__fd); + if (unlikely(!IS_ERR_OR_NULL(fdf->__file))) + fput(fdf->__file); } /* Do not use directly. */ @@ -230,7 +228,8 @@ static inline int class_fd_prepare_lock_err(const struct fd_prepare *fdf) VFS_WARN_ON_ONCE(fdp->__fd < 0); \ VFS_WARN_ON_ONCE(IS_ERR_OR_NULL(fdp->__file)); \ fd_install(fdp->__fd, fdp->__file); \ - fdp->__fd; \ + retain_and_null_ptr(fdp->__file); \ + take_fd(fdp->__fd); \ }) /* Do not use directly. */ diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index ae7f21aad0ac35..a4d9f964dfdea9 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -369,14 +369,13 @@ enum split_type { SPLIT_TYPE_NON_UNIFORM, }; -bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins); int __split_huge_page_to_list_to_order(struct page *page, struct list_head *list, unsigned int new_order); int folio_split_unmapped(struct folio *folio, unsigned int new_order); -int min_order_for_split(struct folio *folio); +unsigned int min_order_for_split(struct folio *folio); int split_folio_to_list(struct folio *folio, struct list_head *list); -bool folio_split_supported(struct folio *folio, unsigned int new_order, - enum split_type split_type, bool warns); +int folio_check_splittable(struct folio *folio, unsigned int new_order, + enum split_type split_type); int folio_split(struct folio *folio, unsigned int new_order, struct page *page, struct list_head *list); @@ -407,7 +406,7 @@ static inline int split_huge_page_to_order(struct page *page, unsigned int new_o static inline int try_folio_split_to_order(struct folio *folio, struct page *page, unsigned int new_order) { - if (!folio_split_supported(folio, new_order, SPLIT_TYPE_NON_UNIFORM, /* warns= */ false)) + if (folio_check_splittable(folio, new_order, SPLIT_TYPE_NON_UNIFORM)) return split_huge_page_to_order(&folio->page, new_order); return folio_split(folio, new_order, page, NULL); } @@ -631,10 +630,10 @@ static inline int split_huge_page(struct page *page) return -EINVAL; } -static inline int min_order_for_split(struct folio *folio) +static inline unsigned int min_order_for_split(struct folio *folio) { VM_WARN_ON_ONCE_FOLIO(1, folio); - return -EINVAL; + return 0; } static inline int split_folio_to_list(struct folio *folio, struct list_head *list) diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 952d3c8dd6b7a2..62f81bbeb4906b 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -730,22 +730,6 @@ static inline void msi_device_domain_free_wired(struct irq_domain *domain, unsig } #endif -static inline struct irq_domain *irq_domain_add_tree(struct device_node *of_node, - const struct irq_domain_ops *ops, - void *host_data) -{ - struct irq_domain_info info = { - .fwnode = of_fwnode_handle(of_node), - .hwirq_max = ~0U, - .ops = ops, - .host_data = host_data, - }; - struct irq_domain *d; - - d = irq_domain_instantiate(&info); - return IS_ERR(d) ? NULL : d; -} - static inline struct irq_domain *irq_domain_add_linear(struct device_node *of_node, unsigned int size, const struct irq_domain_ops *ops, diff --git a/include/linux/mm.h b/include/linux/mm.h index 7a1819c20643bb..15076261d0c2eb 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -438,7 +438,7 @@ enum { #define VM_NOHUGEPAGE INIT_VM_FLAG(NOHUGEPAGE) #define VM_MERGEABLE INIT_VM_FLAG(MERGEABLE) #define VM_STACK INIT_VM_FLAG(STACK) -#ifdef CONFIG_STACK_GROWS_UP +#ifdef CONFIG_STACK_GROWSUP #define VM_STACK_EARLY INIT_VM_FLAG(STACK_EARLY) #else #define VM_STACK_EARLY VM_NONE diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 4398e027f450ec..75ef7c9f9307ff 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -2289,7 +2289,7 @@ void sparse_init(void); #else #define sparse_init() do {} while (0) #define sparse_index_init(_sec, _nid) do {} while (0) -#define sparse_vmemmap_init_nid_early(_nid, _use) do {} while (0) +#define sparse_vmemmap_init_nid_early(_nid) do {} while (0) #define sparse_vmemmap_init_nid_late(_nid) do {} while (0) #define pfn_in_present_section pfn_valid #define subsection_map_init(_pfn, _nr_pages) do {} while (0) diff --git a/include/linux/rseq_entry.h b/include/linux/rseq_entry.h index c92167ff8a7fbd..a36b472627dec8 100644 --- a/include/linux/rseq_entry.h +++ b/include/linux/rseq_entry.h @@ -596,7 +596,7 @@ static __always_inline void rseq_exit_to_user_mode_legacy(void) void __rseq_debug_syscall_return(struct pt_regs *regs); -static inline void rseq_debug_syscall_return(struct pt_regs *regs) +static __always_inline void rseq_debug_syscall_return(struct pt_regs *regs) { if (static_branch_unlikely(&rseq_debug_enabled)) __rseq_debug_syscall_return(regs); diff --git a/include/trace/events/ceph.h b/include/trace/events/ceph.h new file mode 100644 index 00000000000000..08cb0659fbfc78 --- /dev/null +++ b/include/trace/events/ceph.h @@ -0,0 +1,234 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Ceph filesystem support module tracepoints + * + * Copyright (C) 2025 IONOS SE. All Rights Reserved. + * Written by Max Kellermann (max.kellermann@ionos.com) + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM ceph + +#if !defined(_TRACE_CEPH_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_CEPH_H + +#include <linux/tracepoint.h> + +#define ceph_mdsc_suspend_reasons \ + EM(ceph_mdsc_suspend_reason_no_mdsmap, "no-mdsmap") \ + EM(ceph_mdsc_suspend_reason_no_active_mds, "no-active-mds") \ + EM(ceph_mdsc_suspend_reason_rejected, "rejected") \ + E_(ceph_mdsc_suspend_reason_session, "session") + +#ifndef __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY +#define __NETFS_DECLARE_TRACE_ENUMS_ONCE_ONLY + +#undef EM +#undef E_ +#define EM(a, b) a, +#define E_(a, b) a + +enum ceph_mdsc_suspend_reason { ceph_mdsc_suspend_reasons } __mode(byte); + +#endif + +/* + * Export enum symbols via userspace. + */ +#undef EM +#undef E_ +#define EM(a, b) TRACE_DEFINE_ENUM(a); +#define E_(a, b) TRACE_DEFINE_ENUM(a); + +ceph_mdsc_suspend_reasons; + +/* + * Now redefine the EM() and E_() macros to map the enums to the strings that + * will be printed in the output. + */ +#undef EM +#undef E_ +#define EM(a, b) { a, b }, +#define E_(a, b) { a, b } + +TRACE_EVENT(ceph_mdsc_submit_request, + TP_PROTO(struct ceph_mds_client *mdsc, + struct ceph_mds_request *req), + + TP_ARGS(mdsc, req), + + TP_STRUCT__entry( + __field(u64, tid) + __field(int, op) + __field(u64, ino) + __field(u64, snap) + ), + + TP_fast_assign( + struct inode *inode; + + __entry->tid = req->r_tid; + __entry->op = req->r_op; + + inode = req->r_inode; + if (inode == NULL && req->r_dentry) + inode = d_inode(req->r_dentry); + + if (inode) { + __entry->ino = ceph_ino(inode); + __entry->snap = ceph_snap(inode); + } else { + __entry->ino = __entry->snap = 0; + } + ), + + TP_printk("R=%llu op=%s ino=%llx,%llx", + __entry->tid, + ceph_mds_op_name(__entry->op), + __entry->ino, __entry->snap) +); + +TRACE_EVENT(ceph_mdsc_suspend_request, + TP_PROTO(struct ceph_mds_client *mdsc, + struct ceph_mds_session *session, + struct ceph_mds_request *req, + enum ceph_mdsc_suspend_reason reason), + + TP_ARGS(mdsc, session, req, reason), + + TP_STRUCT__entry( + __field(u64, tid) + __field(int, op) + __field(int, mds) + __field(enum ceph_mdsc_suspend_reason, reason) + ), + + TP_fast_assign( + __entry->tid = req->r_tid; + __entry->op = req->r_op; + __entry->mds = session ? session->s_mds : -1; + __entry->reason = reason; + ), + + TP_printk("R=%llu op=%s reason=%s", + __entry->tid, + ceph_mds_op_name(__entry->op), + __print_symbolic(__entry->reason, ceph_mdsc_suspend_reasons)) +); + +TRACE_EVENT(ceph_mdsc_resume_request, + TP_PROTO(struct ceph_mds_client *mdsc, + struct ceph_mds_request *req), + + TP_ARGS(mdsc, req), + + TP_STRUCT__entry( + __field(u64, tid) + __field(int, op) + ), + + TP_fast_assign( + __entry->tid = req->r_tid; + __entry->op = req->r_op; + ), + + TP_printk("R=%llu op=%s", + __entry->tid, + ceph_mds_op_name(__entry->op)) +); + +TRACE_EVENT(ceph_mdsc_send_request, + TP_PROTO(struct ceph_mds_session *session, + struct ceph_mds_request *req), + + TP_ARGS(session, req), + + TP_STRUCT__entry( + __field(u64, tid) + __field(int, op) + __field(int, mds) + ), + + TP_fast_assign( + __entry->tid = req->r_tid; + __entry->op = req->r_op; + __entry->mds = session->s_mds; + ), + + TP_printk("R=%llu op=%s mds=%d", + __entry->tid, + ceph_mds_op_name(__entry->op), + __entry->mds) +); + +TRACE_EVENT(ceph_mdsc_complete_request, + TP_PROTO(struct ceph_mds_client *mdsc, + struct ceph_mds_request *req), + + TP_ARGS(mdsc, req), + + TP_STRUCT__entry( + __field(u64, tid) + __field(int, op) + __field(int, err) + __field(unsigned long, latency_ns) + ), + + TP_fast_assign( + __entry->tid = req->r_tid; + __entry->op = req->r_op; + __entry->err = req->r_err; + __entry->latency_ns = req->r_end_latency - req->r_start_latency; + ), + + TP_printk("R=%llu op=%s err=%d latency_ns=%lu", + __entry->tid, + ceph_mds_op_name(__entry->op), + __entry->err, + __entry->latency_ns) +); + +TRACE_EVENT(ceph_handle_caps, + TP_PROTO(struct ceph_mds_client *mdsc, + struct ceph_mds_session *session, + int op, + const struct ceph_vino *vino, + struct ceph_inode_info *inode, + u32 seq, u32 mseq, u32 issue_seq), + + TP_ARGS(mdsc, session, op, vino, inode, seq, mseq, issue_seq), + + TP_STRUCT__entry( + __field(int, mds) + __field(int, op) + __field(u64, ino) + __field(u64, snap) + __field(u32, seq) + __field(u32, mseq) + __field(u32, issue_seq) + ), + + TP_fast_assign( + __entry->mds = session->s_mds; + __entry->op = op; + __entry->ino = vino->ino; + __entry->snap = vino->snap; + __entry->seq = seq; + __entry->mseq = mseq; + __entry->issue_seq = issue_seq; + ), + + TP_printk("mds=%d op=%s vino=%llx.%llx seq=%u iseq=%u mseq=%u", + __entry->mds, + ceph_cap_op_name(__entry->op), + __entry->ino, + __entry->snap, + __entry->seq, + __entry->issue_seq, + __entry->mseq) +); + +#undef EM +#undef E_ +#endif /* _TRACE_CEPH_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/kernel/cpu.c b/kernel/cpu.c index b674fdf96208be..8df2d773fe3b52 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -249,6 +249,14 @@ err: return ret; } +/* + * The former STARTING/DYING states, ran with IRQs disabled and must not fail. + */ +static bool cpuhp_is_atomic_state(enum cpuhp_state state) +{ + return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; +} + #ifdef CONFIG_SMP static bool cpuhp_is_ap_state(enum cpuhp_state state) { @@ -271,14 +279,6 @@ static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup) complete(done); } -/* - * The former STARTING/DYING states, ran with IRQs disabled and must not fail. - */ -static bool cpuhp_is_atomic_state(enum cpuhp_state state) -{ - return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; -} - /* Synchronization state management */ enum cpuhp_sync_state { SYNC_STATE_DEAD, @@ -2364,7 +2364,14 @@ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, else ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #else - ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); + if (cpuhp_is_atomic_state(state)) { + guard(irqsave)(); + ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); + /* STARTING/DYING must not fail! */ + WARN_ON_ONCE(ret); + } else { + ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); + } #endif BUG_ON(ret && !bringup); return ret; diff --git a/kernel/events/core.c b/kernel/events/core.c index ece716879cbc24..dad0d3d2e85f7d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2317,8 +2317,6 @@ out: perf_event__header_size(leader); } -static void sync_child_event(struct perf_event *child_event); - static void perf_child_detach(struct perf_event *event) { struct perf_event *parent_event = event->parent; @@ -2337,7 +2335,6 @@ static void perf_child_detach(struct perf_event *event) lockdep_assert_held(&parent_event->child_mutex); */ - sync_child_event(event); list_del_init(&event->child_list); } @@ -4588,6 +4585,7 @@ out: static void perf_remove_from_owner(struct perf_event *event); static void perf_event_exit_event(struct perf_event *event, struct perf_event_context *ctx, + struct task_struct *task, bool revoke); /* @@ -4615,7 +4613,7 @@ static void perf_event_remove_on_exec(struct perf_event_context *ctx) modified = true; - perf_event_exit_event(event, ctx, false); + perf_event_exit_event(event, ctx, ctx->task, false); } raw_spin_lock_irqsave(&ctx->lock, flags); @@ -12518,7 +12516,7 @@ static void __pmu_detach_event(struct pmu *pmu, struct perf_event *event, /* * De-schedule the event and mark it REVOKED. */ - perf_event_exit_event(event, ctx, true); + perf_event_exit_event(event, ctx, ctx->task, true); /* * All _free_event() bits that rely on event->pmu: @@ -14075,14 +14073,13 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu) } EXPORT_SYMBOL_GPL(perf_pmu_migrate_context); -static void sync_child_event(struct perf_event *child_event) +static void sync_child_event(struct perf_event *child_event, + struct task_struct *task) { struct perf_event *parent_event = child_event->parent; u64 child_val; if (child_event->attr.inherit_stat) { - struct task_struct *task = child_event->ctx->task; - if (task && task != TASK_TOMBSTONE) perf_event_read_event(child_event, task); } @@ -14101,7 +14098,9 @@ static void sync_child_event(struct perf_event *child_event) static void perf_event_exit_event(struct perf_event *event, - struct perf_event_context *ctx, bool revoke) + struct perf_event_context *ctx, + struct task_struct *task, + bool revoke) { struct perf_event *parent_event = event->parent; unsigned long detach_flags = DETACH_EXIT; @@ -14124,6 +14123,9 @@ perf_event_exit_event(struct perf_event *event, mutex_lock(&parent_event->child_mutex); /* PERF_ATTACH_ITRACE might be set concurrently */ attach_state = READ_ONCE(event->attach_state); + + if (attach_state & PERF_ATTACH_CHILD) + sync_child_event(event, task); } if (revoke) @@ -14215,7 +14217,7 @@ static void perf_event_exit_task_context(struct task_struct *task, bool exit) perf_event_task(task, ctx, 0); list_for_each_entry_safe(child_event, next, &ctx->event_list, event_entry) - perf_event_exit_event(child_event, ctx, false); + perf_event_exit_event(child_event, ctx, exit ? task : NULL, false); mutex_unlock(&ctx->mutex); diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index f11ceb8be8c419..d546d32390a81d 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -79,7 +79,7 @@ struct uprobe { * The generic code assumes that it has two members of unknown type * owned by the arch-specific code: * - * insn - copy_insn() saves the original instruction here for + * insn - copy_insn() saves the original instruction here for * arch_uprobe_analyze_insn(). * * ixol - potentially modified instruction to execute out of @@ -107,8 +107,8 @@ static LIST_HEAD(delayed_uprobe_list); * allocated. */ struct xol_area { - wait_queue_head_t wq; /* if all slots are busy */ - unsigned long *bitmap; /* 0 = free slot */ + wait_queue_head_t wq; /* if all slots are busy */ + unsigned long *bitmap; /* 0 = free slot */ struct page *page; /* @@ -116,7 +116,7 @@ struct xol_area { * itself. The probed process or a naughty kernel module could make * the vma go away, and we must handle that reasonably gracefully. */ - unsigned long vaddr; /* Page(s) of instruction slots */ + unsigned long vaddr; /* Page(s) of instruction slots */ }; static void uprobe_warn(struct task_struct *t, const char *msg) diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 0bb29316b4362c..8b1b4c8a4f54c5 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -2470,6 +2470,9 @@ int setup_percpu_irq(unsigned int irq, struct irqaction *act) if (retval < 0) return retval; + if (!act->affinity) + act->affinity = cpu_online_mask; + retval = __setup_irq(irq, desc, act); if (retval) diff --git a/kernel/liveupdate/Kconfig b/kernel/liveupdate/Kconfig index 9b2515f31afb4b..d2aeaf13c3acb8 100644 --- a/kernel/liveupdate/Kconfig +++ b/kernel/liveupdate/Kconfig @@ -54,6 +54,7 @@ config KEXEC_HANDOVER_ENABLE_DEFAULT config LIVEUPDATE bool "Live Update Orchestrator" depends on KEXEC_HANDOVER + depends on SHMEM help Enable the Live Update Orchestrator. Live Update is a mechanism, typically based on kexec, that allows the kernel to be updated diff --git a/kernel/liveupdate/luo_core.c b/kernel/liveupdate/luo_core.c index f7ecaf7740d19d..944663d99dd9f3 100644 --- a/kernel/liveupdate/luo_core.c +++ b/kernel/liveupdate/luo_core.c @@ -399,10 +399,8 @@ static long luo_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) int err; nr = _IOC_NR(cmd); - if (nr < LIVEUPDATE_CMD_BASE || - (nr - LIVEUPDATE_CMD_BASE) >= ARRAY_SIZE(luo_ioctl_ops)) { + if (nr - LIVEUPDATE_CMD_BASE >= ARRAY_SIZE(luo_ioctl_ops)) return -EINVAL; - } ucmd.ubuffer = (void __user *)arg; err = get_user(ucmd.user_size, (u32 __user *)ucmd.ubuffer); diff --git a/kernel/liveupdate/luo_file.c b/kernel/liveupdate/luo_file.c index ddff87917b217c..a32a777f6df8f3 100644 --- a/kernel/liveupdate/luo_file.c +++ b/kernel/liveupdate/luo_file.c @@ -554,17 +554,20 @@ int luo_retrieve_file(struct luo_file_set *file_set, u64 token, { struct liveupdate_file_op_args args = {0}; struct luo_file *luo_file; + bool found = false; int err; if (list_empty(&file_set->files_list)) return -ENOENT; list_for_each_entry(luo_file, &file_set->files_list, list) { - if (luo_file->token == token) + if (luo_file->token == token) { + found = true; break; + } } - if (luo_file->token != token) + if (!found) return -ENOENT; guard(mutex)(&luo_file->mutex); diff --git a/lib/bug.c b/lib/bug.c index edd9041f89f3aa..623c467a8b76c7 100644 --- a/lib/bug.c +++ b/lib/bug.c @@ -173,6 +173,9 @@ struct bug_entry *find_bug(unsigned long bugaddr) return module_find_bug(bugaddr); } +__diag_push(); +__diag_ignore(GCC, all, "-Wsuggest-attribute=format", + "Not a valid __printf() conversion candidate."); static void __warn_printf(const char *fmt, struct pt_regs *regs) { if (!fmt) @@ -192,6 +195,7 @@ static void __warn_printf(const char *fmt, struct pt_regs *regs) printk("%s", fmt); } +__diag_pop(); static enum bug_trap_type __report_bug(struct bug_entry *bug, unsigned long bugaddr, struct pt_regs *regs) { @@ -262,7 +266,7 @@ enum bug_trap_type report_bug_entry(struct bug_entry *bug, struct pt_regs *regs) bool rcu = false; rcu = warn_rcu_enter(); - ret = __report_bug(bug, 0, regs); + ret = __report_bug(bug, bug_addr(bug), regs); warn_rcu_exit(rcu); return ret; diff --git a/mm/damon/tests/core-kunit.h b/mm/damon/tests/core-kunit.h index a1eff023e928a0..8cb369b63e08ed 100644 --- a/mm/damon/tests/core-kunit.h +++ b/mm/damon/tests/core-kunit.h @@ -924,7 +924,7 @@ static void damos_test_commit_for(struct kunit *test, struct damos *dst, } } -static void damos_test_commit(struct kunit *test) +static void damos_test_commit_pageout(struct kunit *test) { damos_test_commit_for(test, &(struct damos){ @@ -945,6 +945,10 @@ static void damos_test_commit(struct kunit *test) DAMOS_WMARK_FREE_MEM_RATE, 800, 50, 30}, }); +} + +static void damos_test_commit_migrate_hot(struct kunit *test) +{ damos_test_commit_for(test, &(struct damos){ .pattern = (struct damos_access_pattern){ @@ -1230,7 +1234,8 @@ static struct kunit_case damon_test_cases[] = { KUNIT_CASE(damos_test_commit_quota), KUNIT_CASE(damos_test_commit_dests), KUNIT_CASE(damos_test_commit_filter), - KUNIT_CASE(damos_test_commit), + KUNIT_CASE(damos_test_commit_pageout), + KUNIT_CASE(damos_test_commit_migrate_hot), KUNIT_CASE(damon_test_commit_target_regions), KUNIT_CASE(damos_test_filter_out), KUNIT_CASE(damon_test_feed_loop_next_input), diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f7c565f11a985a..40cf59301c21aa 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3464,23 +3464,6 @@ static void lru_add_split_folio(struct folio *folio, struct folio *new_folio, } } -/* Racy check whether the huge page can be split */ -bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins) -{ - int extra_pins; - - /* Additional pins from page cache */ - if (folio_test_anon(folio)) - extra_pins = folio_test_swapcache(folio) ? - folio_nr_pages(folio) : 0; - else - extra_pins = folio_nr_pages(folio); - if (pextra_pins) - *pextra_pins = extra_pins; - return folio_mapcount(folio) == folio_ref_count(folio) - extra_pins - - caller_pins; -} - static bool page_range_has_hwpoisoned(struct page *page, long nr_pages) { for (; nr_pages; page++, nr_pages--) @@ -3697,15 +3680,40 @@ static int __split_unmapped_folio(struct folio *folio, int new_order, return 0; } -bool folio_split_supported(struct folio *folio, unsigned int new_order, - enum split_type split_type, bool warns) +/** + * folio_check_splittable() - check if a folio can be split to a given order + * @folio: folio to be split + * @new_order: the smallest order of the after split folios (since buddy + * allocator like split generates folios with orders from @folio's + * order - 1 to new_order). + * @split_type: uniform or non-uniform split + * + * folio_check_splittable() checks if @folio can be split to @new_order using + * @split_type method. The truncated folio check must come first. + * + * Context: folio must be locked. + * + * Return: 0 - @folio can be split to @new_order, otherwise an error number is + * returned. + */ +int folio_check_splittable(struct folio *folio, unsigned int new_order, + enum split_type split_type) { + VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); + /* + * Folios that just got truncated cannot get split. Signal to the + * caller that there was a race. + * + * TODO: this will also currently refuse folios without a mapping in the + * swapcache (shmem or to-be-anon folios). + */ + if (!folio->mapping && !folio_test_anon(folio)) + return -EBUSY; + if (folio_test_anon(folio)) { /* order-1 is not supported for anonymous THP. */ - VM_WARN_ONCE(warns && new_order == 1, - "Cannot split to order-1 folio"); if (new_order == 1) - return false; + return -EINVAL; } else if (split_type == SPLIT_TYPE_NON_UNIFORM || new_order) { if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !mapping_large_folio_support(folio->mapping)) { @@ -3726,9 +3734,7 @@ bool folio_split_supported(struct folio *folio, unsigned int new_order, * case, the mapping does not actually support large * folios properly. */ - VM_WARN_ONCE(warns, - "Cannot split file folio to non-0 order"); - return false; + return -EINVAL; } } @@ -3741,19 +3747,31 @@ bool folio_split_supported(struct folio *folio, unsigned int new_order, * here. */ if ((split_type == SPLIT_TYPE_NON_UNIFORM || new_order) && folio_test_swapcache(folio)) { - VM_WARN_ONCE(warns, - "Cannot split swapcache folio to non-0 order"); - return false; + return -EINVAL; } - return true; + if (is_huge_zero_folio(folio)) + return -EINVAL; + + if (folio_test_writeback(folio)) + return -EBUSY; + + return 0; +} + +/* Number of folio references from the pagecache or the swapcache. */ +static unsigned int folio_cache_ref_count(const struct folio *folio) +{ + if (folio_test_anon(folio) && !folio_test_swapcache(folio)) + return 0; + return folio_nr_pages(folio); } static int __folio_freeze_and_split_unmapped(struct folio *folio, unsigned int new_order, struct page *split_at, struct xa_state *xas, struct address_space *mapping, bool do_lru, struct list_head *list, enum split_type split_type, - pgoff_t end, int *nr_shmem_dropped, int extra_pins) + pgoff_t end, int *nr_shmem_dropped) { struct folio *end_folio = folio_next(folio); struct folio *new_folio, *next; @@ -3764,10 +3782,9 @@ static int __folio_freeze_and_split_unmapped(struct folio *folio, unsigned int n VM_WARN_ON_ONCE(!mapping && end); /* Prevent deferred_split_scan() touching ->_refcount */ ds_queue = folio_split_queue_lock(folio); - if (folio_ref_freeze(folio, 1 + extra_pins)) { + if (folio_ref_freeze(folio, folio_cache_ref_count(folio) + 1)) { struct swap_cluster_info *ci = NULL; struct lruvec *lruvec; - int expected_refs; if (old_order > 1) { if (!list_empty(&folio->_deferred_list)) { @@ -3835,8 +3852,8 @@ static int __folio_freeze_and_split_unmapped(struct folio *folio, unsigned int n zone_device_private_split_cb(folio, new_folio); - expected_refs = folio_expected_ref_count(new_folio) + 1; - folio_ref_unfreeze(new_folio, expected_refs); + folio_ref_unfreeze(new_folio, + folio_cache_ref_count(new_folio) + 1); if (do_lru) lru_add_split_folio(folio, new_folio, lruvec, list); @@ -3879,8 +3896,7 @@ static int __folio_freeze_and_split_unmapped(struct folio *folio, unsigned int n * Otherwise, a parallel folio_try_get() can grab @folio * and its caller can see stale page cache entries. */ - expected_refs = folio_expected_ref_count(folio) + 1; - folio_ref_unfreeze(folio, expected_refs); + folio_ref_unfreeze(folio, folio_cache_ref_count(folio) + 1); if (do_lru) unlock_page_lruvec(lruvec); @@ -3929,40 +3945,27 @@ static int __folio_split(struct folio *folio, unsigned int new_order, struct folio *new_folio, *next; int nr_shmem_dropped = 0; int remap_flags = 0; - int extra_pins, ret; + int ret; pgoff_t end = 0; - bool is_hzp; VM_WARN_ON_ONCE_FOLIO(!folio_test_locked(folio), folio); VM_WARN_ON_ONCE_FOLIO(!folio_test_large(folio), folio); - if (folio != page_folio(split_at) || folio != page_folio(lock_at)) - return -EINVAL; - - /* - * Folios that just got truncated cannot get split. Signal to the - * caller that there was a race. - * - * TODO: this will also currently refuse shmem folios that are in the - * swapcache. - */ - if (!is_anon && !folio->mapping) - return -EBUSY; - - if (new_order >= old_order) - return -EINVAL; - - if (!folio_split_supported(folio, new_order, split_type, /* warn = */ true)) - return -EINVAL; + if (folio != page_folio(split_at) || folio != page_folio(lock_at)) { + ret = -EINVAL; + goto out; + } - is_hzp = is_huge_zero_folio(folio); - if (is_hzp) { - pr_warn_ratelimited("Called split_huge_page for huge zero page\n"); - return -EBUSY; + if (new_order >= old_order) { + ret = -EINVAL; + goto out; } - if (folio_test_writeback(folio)) - return -EBUSY; + ret = folio_check_splittable(folio, new_order, split_type); + if (ret) { + VM_WARN_ONCE(ret == -EINVAL, "Tried to split an unsplittable folio"); + goto out; + } if (is_anon) { /* @@ -4027,7 +4030,7 @@ static int __folio_split(struct folio *folio, unsigned int new_order, * Racy check if we can split the page, before unmap_folio() will * split PMDs */ - if (!can_split_folio(folio, 1, &extra_pins)) { + if (folio_expected_ref_count(folio) != folio_ref_count(folio) - 1) { ret = -EAGAIN; goto out_unlock; } @@ -4050,8 +4053,7 @@ static int __folio_split(struct folio *folio, unsigned int new_order, } ret = __folio_freeze_and_split_unmapped(folio, new_order, split_at, &xas, mapping, - true, list, split_type, end, &nr_shmem_dropped, - extra_pins); + true, list, split_type, end, &nr_shmem_dropped); fail: if (mapping) xas_unlock(&xas); @@ -4125,20 +4127,20 @@ out: */ int folio_split_unmapped(struct folio *folio, unsigned int new_order) { - int extra_pins, ret = 0; + int ret = 0; VM_WARN_ON_ONCE_FOLIO(folio_mapped(folio), folio); VM_WARN_ON_ONCE_FOLIO(!folio_test_locked(folio), folio); VM_WARN_ON_ONCE_FOLIO(!folio_test_large(folio), folio); VM_WARN_ON_ONCE_FOLIO(!folio_test_anon(folio), folio); - if (!can_split_folio(folio, 1, &extra_pins)) + if (folio_expected_ref_count(folio) != folio_ref_count(folio) - 1) return -EAGAIN; local_irq_disable(); ret = __folio_freeze_and_split_unmapped(folio, new_order, &folio->page, NULL, NULL, false, NULL, SPLIT_TYPE_UNIFORM, - 0, NULL, extra_pins); + 0, NULL); local_irq_enable(); return ret; } @@ -4230,16 +4232,29 @@ int folio_split(struct folio *folio, unsigned int new_order, SPLIT_TYPE_NON_UNIFORM); } -int min_order_for_split(struct folio *folio) +/** + * min_order_for_split() - get the minimum order @folio can be split to + * @folio: folio to split + * + * min_order_for_split() tells the minimum order @folio can be split to. + * If a file-backed folio is truncated, 0 will be returned. Any subsequent + * split attempt should get -EBUSY from split checking code. + * + * Return: @folio's minimum order for split + */ +unsigned int min_order_for_split(struct folio *folio) { if (folio_test_anon(folio)) return 0; - if (!folio->mapping) { - if (folio_test_pmd_mappable(folio)) - count_vm_event(THP_SPLIT_PAGE_FAILED); - return -EBUSY; - } + /* + * If the folio got truncated, we don't know the previous mapping and + * consequently the old min order. But it doesn't matter, as any split + * attempt will immediately fail with -EBUSY as the folio cannot get + * split until freed. + */ + if (!folio->mapping) + return 0; return mapping_min_folio_order(folio->mapping); } @@ -4631,7 +4646,7 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start, * can be split or not. So skip the check here. */ if (!folio_test_private(folio) && - !can_split_folio(folio, 0, NULL)) + folio_expected_ref_count(folio) != folio_ref_count(folio)) goto next; if (!folio_trylock(folio)) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 9e7815b4f0583f..51273baec9e5dc 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6579,6 +6579,7 @@ long hugetlb_reserve_pages(struct inode *inode, struct resv_map *resv_map; struct hugetlb_cgroup *h_cg = NULL; long gbl_reserve, regions_needed = 0; + int err; /* This should never happen */ if (from > to) { @@ -6612,8 +6613,10 @@ long hugetlb_reserve_pages(struct inode *inode, } else { /* Private mapping. */ resv_map = resv_map_alloc(); - if (!resv_map) + if (!resv_map) { + err = -ENOMEM; goto out_err; + } chg = to - from; @@ -6621,11 +6624,15 @@ long hugetlb_reserve_pages(struct inode *inode, set_vma_desc_resv_flags(desc, HPAGE_RESV_OWNER); } - if (chg < 0) + if (chg < 0) { + /* region_chg() above can return -ENOMEM */ + err = (chg == -ENOMEM) ? -ENOMEM : -EINVAL; goto out_err; + } - if (hugetlb_cgroup_charge_cgroup_rsvd(hstate_index(h), - chg * pages_per_huge_page(h), &h_cg) < 0) + err = hugetlb_cgroup_charge_cgroup_rsvd(hstate_index(h), + chg * pages_per_huge_page(h), &h_cg); + if (err < 0) goto out_err; if (desc && !(desc->vm_flags & VM_MAYSHARE) && h_cg) { @@ -6641,14 +6648,17 @@ long hugetlb_reserve_pages(struct inode *inode, * reservations already in place (gbl_reserve). */ gbl_reserve = hugepage_subpool_get_pages(spool, chg); - if (gbl_reserve < 0) + if (gbl_reserve < 0) { + err = gbl_reserve; goto out_uncharge_cgroup; + } /* * Check enough hugepages are available for the reservation. * Hand the pages back to the subpool if there are not */ - if (hugetlb_acct_memory(h, gbl_reserve) < 0) + err = hugetlb_acct_memory(h, gbl_reserve); + if (err < 0) goto out_put_pages; /* @@ -6667,6 +6677,7 @@ long hugetlb_reserve_pages(struct inode *inode, if (unlikely(add < 0)) { hugetlb_acct_memory(h, -gbl_reserve); + err = add; goto out_put_pages; } else if (unlikely(chg > add)) { /* @@ -6726,7 +6737,7 @@ out_err: kref_put(&resv_map->refs, resv_map_release); set_vma_desc_resv_map(desc, NULL); } - return chg < 0 ? chg : add < 0 ? add : -EINVAL; + return err; } long hugetlb_unreserve_pages(struct inode *inode, long start, long end, diff --git a/mm/shmem.c b/mm/shmem.c index 3f194c9842a8ca..b329b5302c4885 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -5794,8 +5794,15 @@ EXPORT_SYMBOL_GPL(shmem_truncate_range); #define shmem_vm_ops generic_file_vm_ops #define shmem_anon_vm_ops generic_file_vm_ops #define shmem_file_operations ramfs_file_operations -#define shmem_acct_size(flags, size) 0 -#define shmem_unacct_size(flags, size) do {} while (0) + +static inline int shmem_acct_size(unsigned long flags, loff_t size) +{ + return 0; +} + +static inline void shmem_unacct_size(unsigned long flags, loff_t size) +{ +} static inline struct inode *shmem_get_inode(struct mnt_idmap *idmap, struct super_block *sb, struct inode *dir, diff --git a/mm/vmscan.c b/mm/vmscan.c index 900c74b6aa62a5..670fe9fae5baa2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1284,7 +1284,8 @@ retry: goto keep_locked; if (folio_test_large(folio)) { /* cannot split folio, skip it */ - if (!can_split_folio(folio, 1, NULL)) + if (folio_expected_ref_count(folio) != + folio_ref_count(folio) - 1) goto activate_locked; /* * Split partially mapped folios right away. @@ -4540,7 +4541,8 @@ static int scan_folios(unsigned long nr_to_scan, struct lruvec *lruvec, int scanned = 0; int isolated = 0; int skipped = 0; - int remaining = min(nr_to_scan, MAX_LRU_BATCH); + int scan_batch = min(nr_to_scan, MAX_LRU_BATCH); + int remaining = scan_batch; struct lru_gen_folio *lrugen = &lruvec->lrugen; struct mem_cgroup *memcg = lruvec_memcg(lruvec); @@ -4600,7 +4602,7 @@ static int scan_folios(unsigned long nr_to_scan, struct lruvec *lruvec, count_memcg_events(memcg, item, isolated); count_memcg_events(memcg, PGREFILL, sorted); __count_vm_events(PGSCAN_ANON + type, isolated); - trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, MAX_LRU_BATCH, + trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, scan_batch, scanned, skipped, isolated, type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON); if (type == LRU_GEN_FILE) diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 6664ea73ccf81b..3667319b949ddc 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1280,8 +1280,7 @@ static struct ceph_osd *create_osd(struct ceph_osd_client *osdc, int onum) static struct ceph_osd *get_osd(struct ceph_osd *osd) { if (refcount_inc_not_zero(&osd->o_ref)) { - dout("get_osd %p %d -> %d\n", osd, refcount_read(&osd->o_ref)-1, - refcount_read(&osd->o_ref)); + dout("get_osd %p -> %d\n", osd, refcount_read(&osd->o_ref)); return osd; } else { dout("get_osd %p FAIL\n", osd); @@ -1291,8 +1290,7 @@ static struct ceph_osd *get_osd(struct ceph_osd *osd) static void put_osd(struct ceph_osd *osd) { - dout("put_osd %p %d -> %d\n", osd, refcount_read(&osd->o_ref), - refcount_read(&osd->o_ref) - 1); + dout("put_osd %p -> %d\n", osd, refcount_read(&osd->o_ref) - 1); if (refcount_dec_and_test(&osd->o_ref)) { osd_cleanup(osd); kfree(osd); diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index d245fa508e1cc9..34b3ab59602f73 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -806,51 +806,49 @@ static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) ceph_decode_need(p, end, len, bad); pool_end = *p + len; + ceph_decode_need(p, end, 4 + 4 + 4, bad); pi->type = ceph_decode_8(p); pi->size = ceph_decode_8(p); pi->crush_ruleset = ceph_decode_8(p); pi->object_hash = ceph_decode_8(p); - pi->pg_num = ceph_decode_32(p); pi->pgp_num = ceph_decode_32(p); - *p += 4 + 4; /* skip lpg* */ - *p += 4; /* skip last_change */ - *p += 8 + 4; /* skip snap_seq, snap_epoch */ + /* lpg*, last_change, snap_seq, snap_epoch */ + ceph_decode_skip_n(p, end, 8 + 4 + 8 + 4, bad); /* skip snaps */ - num = ceph_decode_32(p); + ceph_decode_32_safe(p, end, num, bad); while (num--) { - *p += 8; /* snapid key */ - *p += 1 + 1; /* versions */ - len = ceph_decode_32(p); - *p += len; + /* snapid key, pool snap (with versions) */ + ceph_decode_skip_n(p, end, 8 + 2, bad); + ceph_decode_skip_string(p, end, bad); } - /* skip removed_snaps */ - num = ceph_decode_32(p); - *p += num * (8 + 8); + /* removed_snaps */ + ceph_decode_skip_map(p, end, 64, 64, bad); + ceph_decode_need(p, end, 8 + 8 + 4, bad); *p += 8; /* skip auid */ pi->flags = ceph_decode_64(p); *p += 4; /* skip crash_replay_interval */ if (ev >= 7) - pi->min_size = ceph_decode_8(p); + ceph_decode_8_safe(p, end, pi->min_size, bad); else pi->min_size = pi->size - pi->size / 2; if (ev >= 8) - *p += 8 + 8; /* skip quota_max_* */ + /* quota_max_* */ + ceph_decode_skip_n(p, end, 8 + 8, bad); if (ev >= 9) { - /* skip tiers */ - num = ceph_decode_32(p); - *p += num * 8; + /* tiers */ + ceph_decode_skip_set(p, end, 64, bad); + ceph_decode_need(p, end, 8 + 1 + 8 + 8, bad); *p += 8; /* skip tier_of */ *p += 1; /* skip cache_mode */ - pi->read_tier = ceph_decode_64(p); pi->write_tier = ceph_decode_64(p); } else { @@ -858,86 +856,76 @@ static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) pi->write_tier = -1; } - if (ev >= 10) { - /* skip properties */ - num = ceph_decode_32(p); - while (num--) { - len = ceph_decode_32(p); - *p += len; /* key */ - len = ceph_decode_32(p); - *p += len; /* val */ - } - } + if (ev >= 10) + /* properties */ + ceph_decode_skip_map(p, end, string, string, bad); if (ev >= 11) { - /* skip hit_set_params */ - *p += 1 + 1; /* versions */ - len = ceph_decode_32(p); - *p += len; + /* hit_set_params (with versions) */ + ceph_decode_skip_n(p, end, 2, bad); + ceph_decode_skip_string(p, end, bad); - *p += 4; /* skip hit_set_period */ - *p += 4; /* skip hit_set_count */ + /* hit_set_period, hit_set_count */ + ceph_decode_skip_n(p, end, 4 + 4, bad); } if (ev >= 12) - *p += 4; /* skip stripe_width */ + /* stripe_width */ + ceph_decode_skip_32(p, end, bad); - if (ev >= 13) { - *p += 8; /* skip target_max_bytes */ - *p += 8; /* skip target_max_objects */ - *p += 4; /* skip cache_target_dirty_ratio_micro */ - *p += 4; /* skip cache_target_full_ratio_micro */ - *p += 4; /* skip cache_min_flush_age */ - *p += 4; /* skip cache_min_evict_age */ - } + if (ev >= 13) + /* target_max_*, cache_target_*, cache_min_* */ + ceph_decode_skip_n(p, end, 16 + 8 + 8, bad); - if (ev >= 14) { - /* skip erasure_code_profile */ - len = ceph_decode_32(p); - *p += len; - } + if (ev >= 14) + /* erasure_code_profile */ + ceph_decode_skip_string(p, end, bad); /* * last_force_op_resend_preluminous, will be overridden if the * map was encoded with RESEND_ON_SPLIT */ if (ev >= 15) - pi->last_force_request_resend = ceph_decode_32(p); + ceph_decode_32_safe(p, end, pi->last_force_request_resend, bad); else pi->last_force_request_resend = 0; if (ev >= 16) - *p += 4; /* skip min_read_recency_for_promote */ + /* min_read_recency_for_promote */ + ceph_decode_skip_32(p, end, bad); if (ev >= 17) - *p += 8; /* skip expected_num_objects */ + /* expected_num_objects */ + ceph_decode_skip_64(p, end, bad); if (ev >= 19) - *p += 4; /* skip cache_target_dirty_high_ratio_micro */ + /* cache_target_dirty_high_ratio_micro */ + ceph_decode_skip_32(p, end, bad); if (ev >= 20) - *p += 4; /* skip min_write_recency_for_promote */ + /* min_write_recency_for_promote */ + ceph_decode_skip_32(p, end, bad); if (ev >= 21) - *p += 1; /* skip use_gmt_hitset */ + /* use_gmt_hitset */ + ceph_decode_skip_8(p, end, bad); if (ev >= 22) - *p += 1; /* skip fast_read */ + /* fast_read */ + ceph_decode_skip_8(p, end, bad); - if (ev >= 23) { - *p += 4; /* skip hit_set_grade_decay_rate */ - *p += 4; /* skip hit_set_search_last_n */ - } + if (ev >= 23) + /* hit_set_grade_decay_rate, hit_set_search_last_n */ + ceph_decode_skip_n(p, end, 4 + 4, bad); if (ev >= 24) { - /* skip opts */ - *p += 1 + 1; /* versions */ - len = ceph_decode_32(p); - *p += len; + /* opts (with versions) */ + ceph_decode_skip_n(p, end, 2, bad); + ceph_decode_skip_string(p, end, bad); } if (ev >= 25) - pi->last_force_request_resend = ceph_decode_32(p); + ceph_decode_32_safe(p, end, pi->last_force_request_resend, bad); /* ignore the rest */ @@ -1438,7 +1426,7 @@ static struct ceph_pg_mapping *__decode_pg_temp(void **p, void *end, ceph_decode_32_safe(p, end, len, e_inval); if (len == 0 && incremental) return NULL; /* new_pg_temp: [] to remove */ - if (len > (SIZE_MAX - sizeof(*pg)) / sizeof(u32)) + if ((size_t)len > (SIZE_MAX - sizeof(*pg)) / sizeof(u32)) return ERR_PTR(-EINVAL); ceph_decode_need(p, end, len * sizeof(u32), e_inval); @@ -1619,7 +1607,7 @@ static struct ceph_pg_mapping *__decode_pg_upmap_items(void **p, void *end, u32 len, i; ceph_decode_32_safe(p, end, len, e_inval); - if (len > (SIZE_MAX - sizeof(*pg)) / (2 * sizeof(u32))) + if ((size_t)len > (SIZE_MAX - sizeof(*pg)) / (2 * sizeof(u32))) return ERR_PTR(-EINVAL); ceph_decode_need(p, end, 2 * len * sizeof(u32), e_inval); diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index d58ca9655ab7e6..c0250244cf7a3c 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -7732,6 +7732,12 @@ sub process { ERROR("MISSING_SENTINEL", "missing sentinel in ID array\n" . "$here\n$stat\n"); } } + +# check for uninitialized pointers with __free attribute + while ($line =~ /\*\s*($Ident)\s+__free\s*\(\s*$Ident\s*\)\s*[,;]/g) { + ERROR("UNINITIALIZED_PTR_WITH_FREE", + "pointer '$1' with __free attribute should be initialized\n" . $herecurr); + } } # If we have no input at all, then there is nothing to report on diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c index 5f9ccab26e9abb..90cf0e2969df8e 100644 --- a/security/tomoyo/domain.c +++ b/security/tomoyo/domain.c @@ -934,17 +934,12 @@ bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos, #endif if (page != dump->page) { const unsigned int offset = pos % PAGE_SIZE; - /* - * Maybe kmap()/kunmap() should be used here. - * But remove_arg_zero() uses kmap_atomic()/kunmap_atomic(). - * So do I. - */ - char *kaddr = kmap_atomic(page); + char *kaddr = kmap_local_page(page); dump->page = page; memcpy(dump->data + offset, kaddr + offset, PAGE_SIZE - offset); - kunmap_atomic(kaddr); + kunmap_local(kaddr); } /* Same with put_arg_page(page) in fs/exec.c */ #ifdef CONFIG_MMU |