diff options
48 files changed, 754 insertions, 206 deletions
diff --git a/Documentation/filesystems/caching/fscache.rst b/Documentation/filesystems/caching/fscache.rst index a74d7b052dc1..de1f32526cc1 100644 --- a/Documentation/filesystems/caching/fscache.rst +++ b/Documentation/filesystems/caching/fscache.rst @@ -318,10 +318,10 @@ where the columns are: Debugging ========= -If CONFIG_FSCACHE_DEBUG is enabled, the FS-Cache facility can have runtime -debugging enabled by adjusting the value in:: +If CONFIG_NETFS_DEBUG is enabled, the FS-Cache facility and NETFS support can +have runtime debugging enabled by adjusting the value in:: - /sys/module/fscache/parameters/debug + /sys/module/netfs/parameters/debug This is a bitmask of debugging streams to enable: @@ -343,6 +343,6 @@ This is a bitmask of debugging streams to enable: The appropriate set of values should be OR'd together and the result written to the control file. For example:: - echo $((1|8|512)) >/sys/module/fscache/parameters/debug + echo $((1|8|512)) >/sys/module/netfs/parameters/debug will turn on all function entry debugging. diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 665fa9524986..ddfccc226751 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -477,6 +477,7 @@ config LENOVO_YMC tristate "Lenovo Yoga Tablet Mode Control" depends on ACPI_WMI depends on INPUT + depends on IDEAPAD_LAPTOP select INPUT_SPARSEKMAP help This driver maps the Tablet Mode Control switch to SW_TABLET_MODE input diff --git a/drivers/platform/x86/amd/pmf/spc.c b/drivers/platform/x86/amd/pmf/spc.c index a3dec14c3004..3c153fb1425e 100644 --- a/drivers/platform/x86/amd/pmf/spc.c +++ b/drivers/platform/x86/amd/pmf/spc.c @@ -150,36 +150,26 @@ static int amd_pmf_get_slider_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_ return 0; } -static int amd_pmf_get_sensor_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in) +static void amd_pmf_get_sensor_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in) { struct amd_sfh_info sfh_info; - int ret; + + /* Get the latest information from SFH */ + in->ev_info.user_present = false; /* Get ALS data */ - ret = amd_get_sfh_info(&sfh_info, MT_ALS); - if (!ret) + if (!amd_get_sfh_info(&sfh_info, MT_ALS)) in->ev_info.ambient_light = sfh_info.ambient_light; else - return ret; + dev_dbg(dev->dev, "ALS is not enabled/detected\n"); /* get HPD data */ - ret = amd_get_sfh_info(&sfh_info, MT_HPD); - if (ret) - return ret; - - switch (sfh_info.user_present) { - case SFH_NOT_DETECTED: - in->ev_info.user_present = 0xff; /* assume no sensors connected */ - break; - case SFH_USER_PRESENT: - in->ev_info.user_present = 1; - break; - case SFH_USER_AWAY: - in->ev_info.user_present = 0; - break; + if (!amd_get_sfh_info(&sfh_info, MT_HPD)) { + if (sfh_info.user_present == SFH_USER_PRESENT) + in->ev_info.user_present = true; + } else { + dev_dbg(dev->dev, "HPD is not enabled/detected\n"); } - - return 0; } void amd_pmf_populate_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in) diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index 1ace711f7442..98ec30fce9fd 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -126,6 +126,7 @@ struct ideapad_rfk_priv { struct ideapad_private { struct acpi_device *adev; + struct mutex vpc_mutex; /* protects the VPC calls */ struct rfkill *rfk[IDEAPAD_RFKILL_DEV_NUM]; struct ideapad_rfk_priv rfk_priv[IDEAPAD_RFKILL_DEV_NUM]; struct platform_device *platform_device; @@ -146,6 +147,7 @@ struct ideapad_private { bool touchpad_ctrl_via_ec : 1; bool ctrl_ps2_aux_port : 1; bool usb_charging : 1; + bool ymc_ec_trigger : 1; } features; struct { bool initialized; @@ -194,6 +196,12 @@ MODULE_PARM_DESC(touchpad_ctrl_via_ec, "Enable registering a 'touchpad' sysfs-attribute which can be used to manually " "tell the EC to enable/disable the touchpad. This may not work on all models."); +static bool ymc_ec_trigger __read_mostly; +module_param(ymc_ec_trigger, bool, 0444); +MODULE_PARM_DESC(ymc_ec_trigger, + "Enable EC triggering work-around to force emitting tablet mode events. " + "If you need this please report this to: [email protected]"); + /* * shared data */ @@ -294,6 +302,8 @@ static int debugfs_status_show(struct seq_file *s, void *data) struct ideapad_private *priv = s->private; unsigned long value; + guard(mutex)(&priv->vpc_mutex); + if (!read_ec_data(priv->adev->handle, VPCCMD_R_BL_MAX, &value)) seq_printf(s, "Backlight max: %lu\n", value); if (!read_ec_data(priv->adev->handle, VPCCMD_R_BL, &value)) @@ -412,7 +422,8 @@ static ssize_t camera_power_show(struct device *dev, unsigned long result; int err; - err = read_ec_data(priv->adev->handle, VPCCMD_R_CAMERA, &result); + scoped_guard(mutex, &priv->vpc_mutex) + err = read_ec_data(priv->adev->handle, VPCCMD_R_CAMERA, &result); if (err) return err; @@ -431,7 +442,8 @@ static ssize_t camera_power_store(struct device *dev, if (err) return err; - err = write_ec_cmd(priv->adev->handle, VPCCMD_W_CAMERA, state); + scoped_guard(mutex, &priv->vpc_mutex) + err = write_ec_cmd(priv->adev->handle, VPCCMD_W_CAMERA, state); if (err) return err; @@ -484,7 +496,8 @@ static ssize_t fan_mode_show(struct device *dev, unsigned long result; int err; - err = read_ec_data(priv->adev->handle, VPCCMD_R_FAN, &result); + scoped_guard(mutex, &priv->vpc_mutex) + err = read_ec_data(priv->adev->handle, VPCCMD_R_FAN, &result); if (err) return err; @@ -506,7 +519,8 @@ static ssize_t fan_mode_store(struct device *dev, if (state > 4 || state == 3) return -EINVAL; - err = write_ec_cmd(priv->adev->handle, VPCCMD_W_FAN, state); + scoped_guard(mutex, &priv->vpc_mutex) + err = write_ec_cmd(priv->adev->handle, VPCCMD_W_FAN, state); if (err) return err; @@ -591,7 +605,8 @@ static ssize_t touchpad_show(struct device *dev, unsigned long result; int err; - err = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &result); + scoped_guard(mutex, &priv->vpc_mutex) + err = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &result); if (err) return err; @@ -612,7 +627,8 @@ static ssize_t touchpad_store(struct device *dev, if (err) return err; - err = write_ec_cmd(priv->adev->handle, VPCCMD_W_TOUCHPAD, state); + scoped_guard(mutex, &priv->vpc_mutex) + err = write_ec_cmd(priv->adev->handle, VPCCMD_W_TOUCHPAD, state); if (err) return err; @@ -1005,6 +1021,8 @@ static int ideapad_rfk_set(void *data, bool blocked) struct ideapad_rfk_priv *priv = data; int opcode = ideapad_rfk_data[priv->dev].opcode; + guard(mutex)(&priv->priv->vpc_mutex); + return write_ec_cmd(priv->priv->adev->handle, opcode, !blocked); } @@ -1018,6 +1036,8 @@ static void ideapad_sync_rfk_state(struct ideapad_private *priv) int i; if (priv->features.hw_rfkill_switch) { + guard(mutex)(&priv->vpc_mutex); + if (read_ec_data(priv->adev->handle, VPCCMD_R_RF, &hw_blocked)) return; hw_blocked = !hw_blocked; @@ -1191,8 +1211,9 @@ static void ideapad_input_novokey(struct ideapad_private *priv) { unsigned long long_pressed; - if (read_ec_data(priv->adev->handle, VPCCMD_R_NOVO, &long_pressed)) - return; + scoped_guard(mutex, &priv->vpc_mutex) + if (read_ec_data(priv->adev->handle, VPCCMD_R_NOVO, &long_pressed)) + return; if (long_pressed) ideapad_input_report(priv, 17); @@ -1204,8 +1225,9 @@ static void ideapad_check_special_buttons(struct ideapad_private *priv) { unsigned long bit, value; - if (read_ec_data(priv->adev->handle, VPCCMD_R_SPECIAL_BUTTONS, &value)) - return; + scoped_guard(mutex, &priv->vpc_mutex) + if (read_ec_data(priv->adev->handle, VPCCMD_R_SPECIAL_BUTTONS, &value)) + return; for_each_set_bit (bit, &value, 16) { switch (bit) { @@ -1238,6 +1260,8 @@ static int ideapad_backlight_get_brightness(struct backlight_device *blightdev) unsigned long now; int err; + guard(mutex)(&priv->vpc_mutex); + err = read_ec_data(priv->adev->handle, VPCCMD_R_BL, &now); if (err) return err; @@ -1250,6 +1274,8 @@ static int ideapad_backlight_update_status(struct backlight_device *blightdev) struct ideapad_private *priv = bl_get_data(blightdev); int err; + guard(mutex)(&priv->vpc_mutex); + err = write_ec_cmd(priv->adev->handle, VPCCMD_W_BL, blightdev->props.brightness); if (err) @@ -1327,6 +1353,8 @@ static void ideapad_backlight_notify_power(struct ideapad_private *priv) if (!blightdev) return; + guard(mutex)(&priv->vpc_mutex); + if (read_ec_data(priv->adev->handle, VPCCMD_R_BL_POWER, &power)) return; @@ -1339,7 +1367,8 @@ static void ideapad_backlight_notify_brightness(struct ideapad_private *priv) /* if we control brightness via acpi video driver */ if (!priv->blightdev) - read_ec_data(priv->adev->handle, VPCCMD_R_BL, &now); + scoped_guard(mutex, &priv->vpc_mutex) + read_ec_data(priv->adev->handle, VPCCMD_R_BL, &now); else backlight_force_update(priv->blightdev, BACKLIGHT_UPDATE_HOTKEY); } @@ -1564,7 +1593,8 @@ static void ideapad_sync_touchpad_state(struct ideapad_private *priv, bool send_ int ret; /* Without reading from EC touchpad LED doesn't switch state */ - ret = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &value); + scoped_guard(mutex, &priv->vpc_mutex) + ret = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &value); if (ret) return; @@ -1592,16 +1622,92 @@ static void ideapad_sync_touchpad_state(struct ideapad_private *priv, bool send_ priv->r_touchpad_val = value; } +static const struct dmi_system_id ymc_ec_trigger_quirk_dmi_table[] = { + { + /* Lenovo Yoga 7 14ARB7 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "82QF"), + }, + }, + { + /* Lenovo Yoga 7 14ACN6 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "82N7"), + }, + }, + { } +}; + +static void ideapad_laptop_trigger_ec(void) +{ + struct ideapad_private *priv; + int ret; + + guard(mutex)(&ideapad_shared_mutex); + + priv = ideapad_shared; + if (!priv) + return; + + if (!priv->features.ymc_ec_trigger) + return; + + scoped_guard(mutex, &priv->vpc_mutex) + ret = write_ec_cmd(priv->adev->handle, VPCCMD_W_YMC, 1); + if (ret) + dev_warn(&priv->platform_device->dev, "Could not write YMC: %d\n", ret); +} + +static int ideapad_laptop_nb_notify(struct notifier_block *nb, + unsigned long action, void *data) +{ + switch (action) { + case IDEAPAD_LAPTOP_YMC_EVENT: + ideapad_laptop_trigger_ec(); + break; + } + + return 0; +} + +static struct notifier_block ideapad_laptop_notifier = { + .notifier_call = ideapad_laptop_nb_notify, +}; + +static BLOCKING_NOTIFIER_HEAD(ideapad_laptop_chain_head); + +int ideapad_laptop_register_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&ideapad_laptop_chain_head, nb); +} +EXPORT_SYMBOL_NS_GPL(ideapad_laptop_register_notifier, IDEAPAD_LAPTOP); + +int ideapad_laptop_unregister_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&ideapad_laptop_chain_head, nb); +} +EXPORT_SYMBOL_NS_GPL(ideapad_laptop_unregister_notifier, IDEAPAD_LAPTOP); + +void ideapad_laptop_call_notifier(unsigned long action, void *data) +{ + blocking_notifier_call_chain(&ideapad_laptop_chain_head, action, data); +} +EXPORT_SYMBOL_NS_GPL(ideapad_laptop_call_notifier, IDEAPAD_LAPTOP); + static void ideapad_acpi_notify(acpi_handle handle, u32 event, void *data) { struct ideapad_private *priv = data; unsigned long vpc1, vpc2, bit; - if (read_ec_data(handle, VPCCMD_R_VPC1, &vpc1)) - return; + scoped_guard(mutex, &priv->vpc_mutex) { + if (read_ec_data(handle, VPCCMD_R_VPC1, &vpc1)) + return; - if (read_ec_data(handle, VPCCMD_R_VPC2, &vpc2)) - return; + if (read_ec_data(handle, VPCCMD_R_VPC2, &vpc2)) + return; + } vpc1 = (vpc2 << 8) | vpc1; @@ -1728,6 +1834,8 @@ static void ideapad_check_features(struct ideapad_private *priv) priv->features.ctrl_ps2_aux_port = ctrl_ps2_aux_port || dmi_check_system(ctrl_ps2_aux_port_list); priv->features.touchpad_ctrl_via_ec = touchpad_ctrl_via_ec; + priv->features.ymc_ec_trigger = + ymc_ec_trigger || dmi_check_system(ymc_ec_trigger_quirk_dmi_table); if (!read_ec_data(handle, VPCCMD_R_FAN, &val)) priv->features.fan_mode = true; @@ -1906,6 +2014,10 @@ static int ideapad_acpi_add(struct platform_device *pdev) priv->adev = adev; priv->platform_device = pdev; + err = devm_mutex_init(&pdev->dev, &priv->vpc_mutex); + if (err) + return err; + ideapad_check_features(priv); err = ideapad_sysfs_init(priv); @@ -1974,6 +2086,8 @@ static int ideapad_acpi_add(struct platform_device *pdev) if (err) goto shared_init_failed; + ideapad_laptop_register_notifier(&ideapad_laptop_notifier); + return 0; shared_init_failed: @@ -2006,6 +2120,8 @@ static void ideapad_acpi_remove(struct platform_device *pdev) struct ideapad_private *priv = dev_get_drvdata(&pdev->dev); int i; + ideapad_laptop_unregister_notifier(&ideapad_laptop_notifier); + ideapad_shared_exit(priv); acpi_remove_notify_handler(priv->adev->handle, diff --git a/drivers/platform/x86/ideapad-laptop.h b/drivers/platform/x86/ideapad-laptop.h index 4498a96de597..948cc61800a9 100644 --- a/drivers/platform/x86/ideapad-laptop.h +++ b/drivers/platform/x86/ideapad-laptop.h @@ -12,6 +12,15 @@ #include <linux/acpi.h> #include <linux/jiffies.h> #include <linux/errno.h> +#include <linux/notifier.h> + +enum ideapad_laptop_notifier_actions { + IDEAPAD_LAPTOP_YMC_EVENT, +}; + +int ideapad_laptop_register_notifier(struct notifier_block *nb); +int ideapad_laptop_unregister_notifier(struct notifier_block *nb); +void ideapad_laptop_call_notifier(unsigned long action, void *data); enum { VPCCMD_R_VPC1 = 0x10, diff --git a/drivers/platform/x86/lenovo-ymc.c b/drivers/platform/x86/lenovo-ymc.c index e1fbc35504d4..e0bbd6a14a89 100644 --- a/drivers/platform/x86/lenovo-ymc.c +++ b/drivers/platform/x86/lenovo-ymc.c @@ -20,32 +20,10 @@ #define LENOVO_YMC_QUERY_INSTANCE 0 #define LENOVO_YMC_QUERY_METHOD 0x01 -static bool ec_trigger __read_mostly; -module_param(ec_trigger, bool, 0444); -MODULE_PARM_DESC(ec_trigger, "Enable EC triggering work-around to force emitting tablet mode events"); - static bool force; module_param(force, bool, 0444); MODULE_PARM_DESC(force, "Force loading on boards without a convertible DMI chassis-type"); -static const struct dmi_system_id ec_trigger_quirk_dmi_table[] = { - { - /* Lenovo Yoga 7 14ARB7 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "82QF"), - }, - }, - { - /* Lenovo Yoga 7 14ACN6 */ - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_MATCH(DMI_PRODUCT_NAME, "82N7"), - }, - }, - { } -}; - static const struct dmi_system_id allowed_chasis_types_dmi_table[] = { { .matches = { @@ -62,21 +40,8 @@ static const struct dmi_system_id allowed_chasis_types_dmi_table[] = { struct lenovo_ymc_private { struct input_dev *input_dev; - struct acpi_device *ec_acpi_dev; }; -static void lenovo_ymc_trigger_ec(struct wmi_device *wdev, struct lenovo_ymc_private *priv) -{ - int err; - - if (!priv->ec_acpi_dev) - return; - - err = write_ec_cmd(priv->ec_acpi_dev->handle, VPCCMD_W_YMC, 1); - if (err) - dev_warn(&wdev->dev, "Could not write YMC: %d\n", err); -} - static const struct key_entry lenovo_ymc_keymap[] = { /* Laptop */ { KE_SW, 0x01, { .sw = { SW_TABLET_MODE, 0 } } }, @@ -125,11 +90,9 @@ static void lenovo_ymc_notify(struct wmi_device *wdev, union acpi_object *data) free_obj: kfree(obj); - lenovo_ymc_trigger_ec(wdev, priv); + ideapad_laptop_call_notifier(IDEAPAD_LAPTOP_YMC_EVENT, &code); } -static void acpi_dev_put_helper(void *p) { acpi_dev_put(p); } - static int lenovo_ymc_probe(struct wmi_device *wdev, const void *ctx) { struct lenovo_ymc_private *priv; @@ -143,29 +106,10 @@ static int lenovo_ymc_probe(struct wmi_device *wdev, const void *ctx) return -ENODEV; } - ec_trigger |= dmi_check_system(ec_trigger_quirk_dmi_table); - priv = devm_kzalloc(&wdev->dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; - if (ec_trigger) { - pr_debug("Lenovo YMC enable EC triggering.\n"); - priv->ec_acpi_dev = acpi_dev_get_first_match_dev("VPC2004", NULL, -1); - - if (!priv->ec_acpi_dev) { - dev_err(&wdev->dev, "Could not find EC ACPI device.\n"); - return -ENODEV; - } - err = devm_add_action_or_reset(&wdev->dev, - acpi_dev_put_helper, priv->ec_acpi_dev); - if (err) { - dev_err(&wdev->dev, - "Could not clean up EC ACPI device: %d\n", err); - return err; - } - } - input_dev = devm_input_allocate_device(&wdev->dev); if (!input_dev) return -ENOMEM; @@ -192,7 +136,6 @@ static int lenovo_ymc_probe(struct wmi_device *wdev, const void *ctx) dev_set_drvdata(&wdev->dev, priv); /* Report the state for the first time on probe */ - lenovo_ymc_trigger_ec(wdev, priv); lenovo_ymc_notify(wdev, NULL); return 0; } @@ -217,3 +160,4 @@ module_wmi_driver(lenovo_ymc_driver); MODULE_AUTHOR("Gergo Koteles <[email protected]>"); MODULE_DESCRIPTION("Lenovo Yoga Mode Control driver"); MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS(IDEAPAD_LAPTOP); diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index a97ceb105cd8..24fdc74caeba 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -75,7 +75,8 @@ static void v9fs_issue_read(struct netfs_io_subrequest *subreq) /* if we just extended the file size, any portion not in * cache won't be on server and is zeroes */ - __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + if (subreq->rreq->origin != NETFS_DIO_READ) + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); netfs_subreq_terminated(subreq, err ?: total, false); } diff --git a/fs/afs/file.c b/fs/afs/file.c index c3f0c45ae9a9..ec1be0091fdb 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -242,7 +242,8 @@ static void afs_fetch_data_notify(struct afs_operation *op) req->error = error; if (subreq) { - __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + if (subreq->rreq->origin != NETFS_DIO_READ) + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); netfs_subreq_terminated(subreq, error ?: req->actual_len, false); req->subreq = NULL; } else if (req->done) { diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index c26545d71d39..cd6d5bbb4b9d 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -72,8 +72,10 @@ #ifdef CONFIG_BINFMT_FLAT_NO_DATA_START_OFFSET #define DATA_START_OFFSET_WORDS (0) +#define MAX_SHARED_LIBS_UPDATE (0) #else #define DATA_START_OFFSET_WORDS (MAX_SHARED_LIBS) +#define MAX_SHARED_LIBS_UPDATE (MAX_SHARED_LIBS) #endif struct lib_info { @@ -880,7 +882,7 @@ static int load_flat_binary(struct linux_binprm *bprm) return res; /* Update data segment pointers for all libraries */ - for (i = 0; i < MAX_SHARED_LIBS; i++) { + for (i = 0; i < MAX_SHARED_LIBS_UPDATE; i++) { if (!libinfo.lib_list[i].loaded) continue; for (j = 0; j < MAX_SHARED_LIBS; j++) { diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 8c16bc5250ef..c4744a02db75 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -246,7 +246,8 @@ static void finish_netfs_read(struct ceph_osd_request *req) if (err >= 0) { if (sparse && err > 0) err = ceph_sparse_ext_map_end(op); - if (err < subreq->len) + if (err < subreq->len && + subreq->rreq->origin != NETFS_DIO_READ) __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); if (IS_ENCRYPTED(inode) && err > 0) { err = ceph_fscrypt_decrypt_extents(inode, @@ -282,7 +283,8 @@ static bool ceph_netfs_issue_op_inline(struct netfs_io_subrequest *subreq) size_t len; int mode; - __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + if (rreq->origin != NETFS_DIO_READ) + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); __clear_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); if (subreq->start >= inode->i_size) @@ -424,6 +426,9 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file) struct ceph_netfs_request_data *priv; int ret = 0; + /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ + __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags); + if (rreq->origin != NETFS_READAHEAD) return 0; @@ -498,6 +503,11 @@ const struct netfs_request_ops ceph_netfs_ops = { }; #ifdef CONFIG_CEPH_FSCACHE +static void ceph_set_page_fscache(struct page *page) +{ + folio_start_private_2(page_folio(page)); /* [DEPRECATED] */ +} + static void ceph_fscache_write_terminated(void *priv, ssize_t error, bool was_async) { struct inode *inode = priv; @@ -515,6 +525,10 @@ static void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, b ceph_fscache_write_terminated, inode, true, caching); } #else +static inline void ceph_set_page_fscache(struct page *page) +{ +} + static inline void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, bool caching) { } @@ -706,6 +720,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) len = wlen; set_page_writeback(page); + if (caching) + ceph_set_page_fscache(page); ceph_fscache_write_to_cache(inode, page_off, len, caching); if (IS_ENCRYPTED(inode)) { @@ -789,6 +805,8 @@ static int ceph_writepage(struct page *page, struct writeback_control *wbc) return AOP_WRITEPAGE_ACTIVATE; } + folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */ + err = writepage_nounlock(page, wbc); if (err == -ERESTARTSYS) { /* direct memory reclaimer was killed by SIGKILL. return 0 @@ -1062,7 +1080,8 @@ get_more_pages: unlock_page(page); break; } - if (PageWriteback(page)) { + if (PageWriteback(page) || + PagePrivate2(page) /* [DEPRECATED] */) { if (wbc->sync_mode == WB_SYNC_NONE) { doutc(cl, "%p under writeback\n", page); unlock_page(page); @@ -1070,6 +1089,7 @@ get_more_pages: } doutc(cl, "waiting on writeback %p\n", page); wait_on_page_writeback(page); + folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */ } if (!clear_page_dirty_for_io(page)) { @@ -1254,6 +1274,8 @@ new_request: } set_page_writeback(page); + if (caching) + ceph_set_page_fscache(page); len += thp_size(page); } ceph_fscache_write_to_cache(inode, offset, len, caching); diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 8f8de8f33abb..71cd70514efa 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -577,8 +577,6 @@ struct inode *ceph_alloc_inode(struct super_block *sb) /* Set parameters for the netfs library */ netfs_inode_init(&ci->netfs, &ceph_netfs_ops, false); - /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ - __set_bit(NETFS_ICTX_USE_PGPRIV2, &ci->netfs.flags); spin_lock_init(&ci->i_ceph_lock); diff --git a/fs/exec.c b/fs/exec.c index a126e3d1cacb..50e76cc633c4 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1692,6 +1692,7 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) unsigned int mode; vfsuid_t vfsuid; vfsgid_t vfsgid; + int err; if (!mnt_may_suid(file->f_path.mnt)) return; @@ -1708,12 +1709,17 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) /* Be careful if suid/sgid is set */ inode_lock(inode); - /* reload atomically mode/uid/gid now that lock held */ + /* Atomically reload and check mode/uid/gid now that lock held. */ mode = inode->i_mode; vfsuid = i_uid_into_vfsuid(idmap, inode); vfsgid = i_gid_into_vfsgid(idmap, inode); + err = inode_permission(idmap, inode, MAY_EXEC); inode_unlock(inode); + /* Did the exec bit vanish out from under us? Give up. */ + if (err) + return; + /* We ignore suid/sgid if there are no mappings for them in the ns */ if (!vfsuid_has_mapping(bprm->cred->user_ns, vfsuid) || !vfsgid_has_mapping(bprm->cred->user_ns, vfsgid)) diff --git a/fs/file.c b/fs/file.c index a11e59b5d602..655338effe9c 100644 --- a/fs/file.c +++ b/fs/file.c @@ -46,27 +46,23 @@ static void free_fdtable_rcu(struct rcu_head *rcu) #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) +#define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds /* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ -static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, - unsigned int count) +static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, + unsigned int copy_words) { - unsigned int cpy, set; - - cpy = count / BITS_PER_BYTE; - set = (nfdt->max_fds - count) / BITS_PER_BYTE; - memcpy(nfdt->open_fds, ofdt->open_fds, cpy); - memset((char *)nfdt->open_fds + cpy, 0, set); - memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy); - memset((char *)nfdt->close_on_exec + cpy, 0, set); - - cpy = BITBIT_SIZE(count); - set = BITBIT_SIZE(nfdt->max_fds) - cpy; - memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy); - memset((char *)nfdt->full_fds_bits + cpy, 0, set); + unsigned int nwords = fdt_words(nfdt); + + bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds, + copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); + bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec, + copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); + bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits, + copy_words, nwords); } /* @@ -84,7 +80,7 @@ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set); - copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds); + copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt)); } /* @@ -379,7 +375,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int open_files = sane_fdtable_size(old_fdt, max_fds); } - copy_fd_bitmaps(new_fdt, old_fdt, open_files); + copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG); old_fds = old_fdt->fd; new_fds = new_fdt->fd; diff --git a/fs/inode.c b/fs/inode.c index 86670941884b..10c4619faeef 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -488,6 +488,39 @@ static void inode_lru_list_del(struct inode *inode) this_cpu_dec(nr_unused); } +static void inode_pin_lru_isolating(struct inode *inode) +{ + lockdep_assert_held(&inode->i_lock); + WARN_ON(inode->i_state & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE)); + inode->i_state |= I_LRU_ISOLATING; +} + +static void inode_unpin_lru_isolating(struct inode *inode) +{ + spin_lock(&inode->i_lock); + WARN_ON(!(inode->i_state & I_LRU_ISOLATING)); + inode->i_state &= ~I_LRU_ISOLATING; + smp_mb(); + wake_up_bit(&inode->i_state, __I_LRU_ISOLATING); + spin_unlock(&inode->i_lock); +} + +static void inode_wait_for_lru_isolating(struct inode *inode) +{ + spin_lock(&inode->i_lock); + if (inode->i_state & I_LRU_ISOLATING) { + DEFINE_WAIT_BIT(wq, &inode->i_state, __I_LRU_ISOLATING); + wait_queue_head_t *wqh; + + wqh = bit_waitqueue(&inode->i_state, __I_LRU_ISOLATING); + spin_unlock(&inode->i_lock); + __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE); + spin_lock(&inode->i_lock); + WARN_ON(inode->i_state & I_LRU_ISOLATING); + } + spin_unlock(&inode->i_lock); +} + /** * inode_sb_list_add - add inode to the superblock list of inodes * @inode: inode to add @@ -657,6 +690,8 @@ static void evict(struct inode *inode) inode_sb_list_del(inode); + inode_wait_for_lru_isolating(inode); + /* * Wait for flusher thread to be done with the inode so that filesystem * does not start destroying it while writeback is still running. Since @@ -855,7 +890,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item, * be under pressure before the cache inside the highmem zone. */ if (inode_has_buffers(inode) || !mapping_empty(&inode->i_data)) { - __iget(inode); + inode_pin_lru_isolating(inode); spin_unlock(&inode->i_lock); spin_unlock(lru_lock); if (remove_inode_buffers(inode)) { @@ -867,7 +902,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item, __count_vm_events(PGINODESTEAL, reap); mm_account_reclaimed_pages(reap); } - iput(inode); + inode_unpin_lru_isolating(inode); spin_lock(lru_lock); return LRU_RETRY; } diff --git a/fs/libfs.c b/fs/libfs.c index 8aa34870449f..02602d00939e 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -450,6 +450,14 @@ void simple_offset_destroy(struct offset_ctx *octx) mtree_destroy(&octx->mt); } +static int offset_dir_open(struct inode *inode, struct file *file) +{ + struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode); + + file->private_data = (void *)ctx->next_offset; + return 0; +} + /** * offset_dir_llseek - Advance the read position of a directory descriptor * @file: an open directory whose position is to be updated @@ -463,6 +471,9 @@ void simple_offset_destroy(struct offset_ctx *octx) */ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) { + struct inode *inode = file->f_inode; + struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode); + switch (whence) { case SEEK_CUR: offset += file->f_pos; @@ -476,7 +487,8 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence) } /* In this case, ->private_data is protected by f_pos_lock */ - file->private_data = NULL; + if (!offset) + file->private_data = (void *)ctx->next_offset; return vfs_setpos(file, offset, LONG_MAX); } @@ -507,7 +519,7 @@ static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry) inode->i_ino, fs_umode_to_dtype(inode->i_mode)); } -static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx) +static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, long last_index) { struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode); struct dentry *dentry; @@ -515,17 +527,21 @@ static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx) while (true) { dentry = offset_find_next(octx, ctx->pos); if (!dentry) - return ERR_PTR(-ENOENT); + return; + + if (dentry2offset(dentry) >= last_index) { + dput(dentry); + return; + } if (!offset_dir_emit(ctx, dentry)) { dput(dentry); - break; + return; } ctx->pos = dentry2offset(dentry) + 1; dput(dentry); } - return NULL; } /** @@ -552,22 +568,19 @@ static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx) static int offset_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dir = file->f_path.dentry; + long last_index = (long)file->private_data; lockdep_assert_held(&d_inode(dir)->i_rwsem); if (!dir_emit_dots(file, ctx)) return 0; - /* In this case, ->private_data is protected by f_pos_lock */ - if (ctx->pos == DIR_OFFSET_MIN) - file->private_data = NULL; - else if (file->private_data == ERR_PTR(-ENOENT)) - return 0; - file->private_data = offset_iterate_dir(d_inode(dir), ctx); + offset_iterate_dir(d_inode(dir), ctx, last_index); return 0; } const struct file_operations simple_offset_dir_operations = { + .open = offset_dir_open, .llseek = offset_dir_llseek, .iterate_shared = offset_readdir, .read = generic_read_dir, diff --git a/fs/locks.c b/fs/locks.c index 9afb16e0683f..e45cad40f8b6 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -2984,7 +2984,7 @@ static int __init filelock_init(void) filelock_cache = kmem_cache_create("file_lock_cache", sizeof(struct file_lock), 0, SLAB_PANIC, NULL); - filelease_cache = kmem_cache_create("file_lock_cache", + filelease_cache = kmem_cache_create("file_lease_cache", sizeof(struct file_lease), 0, SLAB_PANIC, NULL); for_each_possible_cpu(i) { diff --git a/fs/netfs/Kconfig b/fs/netfs/Kconfig index 1b78e8b65ebc..7701c037c328 100644 --- a/fs/netfs/Kconfig +++ b/fs/netfs/Kconfig @@ -24,7 +24,7 @@ config NETFS_STATS config NETFS_DEBUG bool "Enable dynamic debugging netfslib and FS-Cache" - depends on NETFS + depends on NETFS_SUPPORT help This permits debugging to be dynamically enabled in the local caching management module. If this is set, the debugging output may be diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index a688d4c75d99..27c750d39476 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -10,6 +10,97 @@ #include "internal.h" /* + * [DEPRECATED] Unlock the folios in a read operation for when the filesystem + * is using PG_private_2 and direct writing to the cache from here rather than + * marking the page for writeback. + * + * Note that we don't touch folio->private in this code. + */ +static void netfs_rreq_unlock_folios_pgpriv2(struct netfs_io_request *rreq, + size_t *account) +{ + struct netfs_io_subrequest *subreq; + struct folio *folio; + pgoff_t start_page = rreq->start / PAGE_SIZE; + pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; + bool subreq_failed = false; + + XA_STATE(xas, &rreq->mapping->i_pages, start_page); + + /* Walk through the pagecache and the I/O request lists simultaneously. + * We may have a mixture of cached and uncached sections and we only + * really want to write out the uncached sections. This is slightly + * complicated by the possibility that we might have huge pages with a + * mixture inside. + */ + subreq = list_first_entry(&rreq->subrequests, + struct netfs_io_subrequest, rreq_link); + subreq_failed = (subreq->error < 0); + + trace_netfs_rreq(rreq, netfs_rreq_trace_unlock_pgpriv2); + + rcu_read_lock(); + xas_for_each(&xas, folio, last_page) { + loff_t pg_end; + bool pg_failed = false; + bool folio_started = false; + + if (xas_retry(&xas, folio)) + continue; + + pg_end = folio_pos(folio) + folio_size(folio) - 1; + + for (;;) { + loff_t sreq_end; + + if (!subreq) { + pg_failed = true; + break; + } + + if (!folio_started && + test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags) && + fscache_operation_valid(&rreq->cache_resources)) { + trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); + folio_start_private_2(folio); + folio_started = true; + } + + pg_failed |= subreq_failed; + sreq_end = subreq->start + subreq->len - 1; + if (pg_end < sreq_end) + break; + + *account += subreq->transferred; + if (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { + subreq = list_next_entry(subreq, rreq_link); + subreq_failed = (subreq->error < 0); + } else { + subreq = NULL; + subreq_failed = false; + } + + if (pg_end == sreq_end) + break; + } + + if (!pg_failed) { + flush_dcache_folio(folio); + folio_mark_uptodate(folio); + } + + if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { + if (folio->index == rreq->no_unlock_folio && + test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) + _debug("no unlock"); + else + folio_unlock(folio); + } + } + rcu_read_unlock(); +} + +/* * Unlock the folios in a read operation. We need to set PG_writeback on any * folios we're going to write back before we unlock them. * @@ -35,6 +126,12 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) } } + /* Handle deprecated PG_private_2 case. */ + if (test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { + netfs_rreq_unlock_folios_pgpriv2(rreq, &account); + goto out; + } + /* Walk through the pagecache and the I/O request lists simultaneously. * We may have a mixture of cached and uncached sections and we only * really want to write out the uncached sections. This is slightly @@ -52,7 +149,6 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) loff_t pg_end; bool pg_failed = false; bool wback_to_cache = false; - bool folio_started = false; if (xas_retry(&xas, folio)) continue; @@ -66,17 +162,8 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) pg_failed = true; break; } - if (test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) { - if (!folio_started && test_bit(NETFS_SREQ_COPY_TO_CACHE, - &subreq->flags)) { - trace_netfs_folio(folio, netfs_folio_trace_copy_to_cache); - folio_start_private_2(folio); - folio_started = true; - } - } else { - wback_to_cache |= - test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); - } + + wback_to_cache |= test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags); pg_failed |= subreq_failed; sreq_end = subreq->start + subreq->len - 1; if (pg_end < sreq_end) @@ -124,6 +211,7 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq) } rcu_read_unlock(); +out: task_io_account_read(account); if (rreq->netfs_ops->done) rreq->netfs_ops->done(rreq); @@ -395,7 +483,7 @@ zero_out: } /** - * netfs_write_begin - Helper to prepare for writing + * netfs_write_begin - Helper to prepare for writing [DEPRECATED] * @ctx: The netfs context * @file: The file to read from * @mapping: The mapping to read from @@ -426,6 +514,9 @@ zero_out: * inode before calling this. * * This is usable whether or not caching is enabled. + * + * Note that this should be considered deprecated and netfs_perform_write() + * used instead. */ int netfs_write_begin(struct netfs_inode *ctx, struct file *file, struct address_space *mapping, @@ -466,7 +557,7 @@ retry: if (!netfs_is_cache_enabled(ctx) && netfs_skip_folio_read(folio, pos, len, false)) { netfs_stat(&netfs_n_rh_write_zskip); - goto have_folio; + goto have_folio_no_wait; } rreq = netfs_alloc_request(mapping, file, @@ -507,6 +598,10 @@ retry: netfs_put_request(rreq, false, netfs_rreq_trace_put_return); have_folio: + ret = folio_wait_private_2_killable(folio); + if (ret < 0) + goto error; +have_folio_no_wait: *_folio = folio; _leave(" = 0"); return 0; diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index 4726c315453c..ca53c5d1622e 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -184,7 +184,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, unsigned int bdp_flags = (iocb->ki_flags & IOCB_NOWAIT) ? BDP_ASYNC : 0; ssize_t written = 0, ret, ret2; loff_t i_size, pos = iocb->ki_pos, from, to; - size_t max_chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER; + size_t max_chunk = mapping_max_folio_size(mapping); bool maybe_trouble = false; if (unlikely(test_bit(NETFS_ICTX_WRITETHROUGH, &ctx->flags) || diff --git a/fs/netfs/fscache_cookie.c b/fs/netfs/fscache_cookie.c index bce2492186d0..d4d4b3a8b106 100644 --- a/fs/netfs/fscache_cookie.c +++ b/fs/netfs/fscache_cookie.c @@ -741,6 +741,10 @@ again_locked: spin_lock(&cookie->lock); } if (test_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags)) { + if (atomic_read(&cookie->n_accesses) != 0) + /* still being accessed: postpone it */ + break; + __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_LRU_DISCARDING); wake = true; diff --git a/fs/netfs/io.c b/fs/netfs/io.c index c93851b98368..5367caf3fa28 100644 --- a/fs/netfs/io.c +++ b/fs/netfs/io.c @@ -99,6 +99,146 @@ static void netfs_rreq_completed(struct netfs_io_request *rreq, bool was_async) } /* + * [DEPRECATED] Deal with the completion of writing the data to the cache. We + * have to clear the PG_fscache bits on the folios involved and release the + * caller's ref. + * + * May be called in softirq mode and we inherit a ref from the caller. + */ +static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq, + bool was_async) +{ + struct netfs_io_subrequest *subreq; + struct folio *folio; + pgoff_t unlocked = 0; + bool have_unlocked = false; + + rcu_read_lock(); + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE); + + xas_for_each(&xas, folio, (subreq->start + subreq->len - 1) / PAGE_SIZE) { + if (xas_retry(&xas, folio)) + continue; + + /* We might have multiple writes from the same huge + * folio, but we mustn't unlock a folio more than once. + */ + if (have_unlocked && folio->index <= unlocked) + continue; + unlocked = folio_next_index(folio) - 1; + trace_netfs_folio(folio, netfs_folio_trace_end_copy); + folio_end_private_2(folio); + have_unlocked = true; + } + } + + rcu_read_unlock(); + netfs_rreq_completed(rreq, was_async); +} + +static void netfs_rreq_copy_terminated(void *priv, ssize_t transferred_or_error, + bool was_async) /* [DEPRECATED] */ +{ + struct netfs_io_subrequest *subreq = priv; + struct netfs_io_request *rreq = subreq->rreq; + + if (IS_ERR_VALUE(transferred_or_error)) { + netfs_stat(&netfs_n_rh_write_failed); + trace_netfs_failure(rreq, subreq, transferred_or_error, + netfs_fail_copy_to_cache); + } else { + netfs_stat(&netfs_n_rh_write_done); + } + + trace_netfs_sreq(subreq, netfs_sreq_trace_write_term); + + /* If we decrement nr_copy_ops to 0, the ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_copy_ops)) + netfs_rreq_unmark_after_write(rreq, was_async); + + netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated); +} + +/* + * [DEPRECATED] Perform any outstanding writes to the cache. We inherit a ref + * from the caller. + */ +static void netfs_rreq_do_write_to_cache(struct netfs_io_request *rreq) +{ + struct netfs_cache_resources *cres = &rreq->cache_resources; + struct netfs_io_subrequest *subreq, *next, *p; + struct iov_iter iter; + int ret; + + trace_netfs_rreq(rreq, netfs_rreq_trace_copy); + + /* We don't want terminating writes trying to wake us up whilst we're + * still going through the list. + */ + atomic_inc(&rreq->nr_copy_ops); + + list_for_each_entry_safe(subreq, p, &rreq->subrequests, rreq_link) { + if (!test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) { + list_del_init(&subreq->rreq_link); + netfs_put_subrequest(subreq, false, + netfs_sreq_trace_put_no_copy); + } + } + + list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { + /* Amalgamate adjacent writes */ + while (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) { + next = list_next_entry(subreq, rreq_link); + if (next->start != subreq->start + subreq->len) + break; + subreq->len += next->len; + list_del_init(&next->rreq_link); + netfs_put_subrequest(next, false, + netfs_sreq_trace_put_merged); + } + + ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len, + subreq->len, rreq->i_size, true); + if (ret < 0) { + trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write); + trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip); + continue; + } + + iov_iter_xarray(&iter, ITER_SOURCE, &rreq->mapping->i_pages, + subreq->start, subreq->len); + + atomic_inc(&rreq->nr_copy_ops); + netfs_stat(&netfs_n_rh_write); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_copy_to_cache); + trace_netfs_sreq(subreq, netfs_sreq_trace_write); + cres->ops->write(cres, subreq->start, &iter, + netfs_rreq_copy_terminated, subreq); + } + + /* If we decrement nr_copy_ops to 0, the usage ref belongs to us. */ + if (atomic_dec_and_test(&rreq->nr_copy_ops)) + netfs_rreq_unmark_after_write(rreq, false); +} + +static void netfs_rreq_write_to_cache_work(struct work_struct *work) /* [DEPRECATED] */ +{ + struct netfs_io_request *rreq = + container_of(work, struct netfs_io_request, work); + + netfs_rreq_do_write_to_cache(rreq); +} + +static void netfs_rreq_write_to_cache(struct netfs_io_request *rreq) /* [DEPRECATED] */ +{ + rreq->work.func = netfs_rreq_write_to_cache_work; + if (!queue_work(system_unbound_wq, &rreq->work)) + BUG(); +} + +/* * Handle a short read. */ static void netfs_rreq_short_read(struct netfs_io_request *rreq, @@ -275,6 +415,10 @@ again: clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags); wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); + if (test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags) && + test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags)) + return netfs_rreq_write_to_cache(rreq); + netfs_rreq_completed(rreq, was_async); } @@ -386,7 +530,8 @@ incomplete: if (transferred_or_error == 0) { if (__test_and_set_bit(NETFS_SREQ_NO_PROGRESS, &subreq->flags)) { - subreq->error = -ENODATA; + if (rreq->origin != NETFS_DIO_READ) + subreq->error = -ENODATA; goto failed; } } else { @@ -457,9 +602,14 @@ netfs_rreq_prepare_read(struct netfs_io_request *rreq, } if (subreq->len > ictx->zero_point - subreq->start) subreq->len = ictx->zero_point - subreq->start; + + /* We limit buffered reads to the EOF, but let the + * server deal with larger-than-EOF DIO/unbuffered + * reads. + */ + if (subreq->len > rreq->i_size - subreq->start) + subreq->len = rreq->i_size - subreq->start; } - if (subreq->len > rreq->i_size - subreq->start) - subreq->len = rreq->i_size - subreq->start; if (rreq->rsize && subreq->len > rreq->rsize) subreq->len = rreq->rsize; @@ -595,11 +745,10 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync) do { _debug("submit %llx + %llx >= %llx", rreq->start, rreq->submitted, rreq->i_size); - if (rreq->origin == NETFS_DIO_READ && - rreq->start + rreq->submitted >= rreq->i_size) - break; if (!netfs_rreq_submit_slice(rreq, &io_iter)) break; + if (test_bit(NETFS_SREQ_NO_PROGRESS, &rreq->flags)) + break; if (test_bit(NETFS_RREQ_BLOCKED, &rreq->flags) && test_bit(NETFS_RREQ_NONBLOCK, &rreq->flags)) break; diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c index f4a642727479..0294df70c3ff 100644 --- a/fs/netfs/objects.c +++ b/fs/netfs/objects.c @@ -24,10 +24,6 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, struct netfs_io_request *rreq; mempool_t *mempool = ctx->ops->request_pool ?: &netfs_request_pool; struct kmem_cache *cache = mempool->pool_data; - bool is_unbuffered = (origin == NETFS_UNBUFFERED_WRITE || - origin == NETFS_DIO_READ || - origin == NETFS_DIO_WRITE); - bool cached = !is_unbuffered && netfs_is_cache_enabled(ctx); int ret; for (;;) { @@ -56,12 +52,6 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, refcount_set(&rreq->ref, 1); __set_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags); - if (cached) { - __set_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags); - if (test_bit(NETFS_ICTX_USE_PGPRIV2, &ctx->flags)) - /* Filesystem uses deprecated PG_private_2 marking. */ - __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags); - } if (file && file->f_flags & O_NONBLOCK) __set_bit(NETFS_RREQ_NONBLOCK, &rreq->flags); if (rreq->netfs_ops->init_request) { diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 9258d30cffe3..3f7e37e50c7d 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -94,6 +94,8 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, { struct netfs_io_request *wreq; struct netfs_inode *ictx; + bool is_buffered = (origin == NETFS_WRITEBACK || + origin == NETFS_WRITETHROUGH); wreq = netfs_alloc_request(mapping, file, start, 0, origin); if (IS_ERR(wreq)) @@ -102,7 +104,7 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, _enter("R=%x", wreq->debug_id); ictx = netfs_inode(wreq->inode); - if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &wreq->flags)) + if (is_buffered && netfs_is_cache_enabled(ictx)) fscache_begin_write_operation(&wreq->cache_resources, netfs_i_cookie(ictx)); wreq->contiguity = wreq->start; diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 7202ce84d0eb..7a558dea75c4 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -265,6 +265,8 @@ static int nfs_netfs_init_request(struct netfs_io_request *rreq, struct file *fi { rreq->netfs_priv = get_nfs_open_context(nfs_file_open_context(file)); rreq->debug_id = atomic_inc_return(&nfs_netfs_debug_id); + /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ + __set_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags); return 0; } @@ -361,7 +363,8 @@ void nfs_netfs_read_completion(struct nfs_pgio_header *hdr) return; sreq = netfs->sreq; - if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) + if (test_bit(NFS_IOHDR_EOF, &hdr->flags) && + sreq->rreq->origin != NETFS_DIO_READ) __set_bit(NETFS_SREQ_CLEAR_TAIL, &sreq->flags); if (hdr->error) diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index fbed0027996f..e8adae1bc260 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -81,8 +81,6 @@ static inline void nfs_netfs_put(struct nfs_netfs_io_data *netfs) static inline void nfs_netfs_inode_init(struct nfs_inode *nfsi) { netfs_inode_init(&nfsi->netfs, &nfs_netfs_ops, false); - /* [DEPRECATED] Use PG_private_2 to mark folio being written to the cache. */ - __set_bit(NETFS_ICTX_USE_PGPRIV2, &nfsi->netfs.flags); } extern void nfs_netfs_initiate_read(struct nfs_pgio_header *hdr); extern void nfs_netfs_read_completion(struct nfs_pgio_header *hdr); diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index b2405dd4d4d4..3f3842e7b44a 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -217,7 +217,8 @@ static void cifs_req_issue_read(struct netfs_io_subrequest *subreq) goto out; } - __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); + if (subreq->rreq->origin != NETFS_DIO_READ) + __set_bit(NETFS_SREQ_CLEAR_TAIL, &subreq->flags); rc = rdata->server->ops->async_readv(rdata); out: diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c index e0a6b758094f..d8d03070ae44 100644 --- a/fs/smb/server/mgmt/share_config.c +++ b/fs/smb/server/mgmt/share_config.c @@ -15,6 +15,7 @@ #include "share_config.h" #include "user_config.h" #include "user_session.h" +#include "../connection.h" #include "../transport_ipc.h" #include "../misc.h" @@ -120,12 +121,13 @@ static int parse_veto_list(struct ksmbd_share_config *share, return 0; } -static struct ksmbd_share_config *share_config_request(struct unicode_map *um, +static struct ksmbd_share_config *share_config_request(struct ksmbd_work *work, const char *name) { struct ksmbd_share_config_response *resp; struct ksmbd_share_config *share = NULL; struct ksmbd_share_config *lookup; + struct unicode_map *um = work->conn->um; int ret; resp = ksmbd_ipc_share_config_request(name); @@ -181,7 +183,14 @@ static struct ksmbd_share_config *share_config_request(struct unicode_map *um, KSMBD_SHARE_CONFIG_VETO_LIST(resp), resp->veto_list_sz); if (!ret && share->path) { + if (__ksmbd_override_fsids(work, share)) { + kill_share(share); + share = NULL; + goto out; + } + ret = kern_path(share->path, 0, &share->vfs_path); + ksmbd_revert_fsids(work); if (ret) { ksmbd_debug(SMB, "failed to access '%s'\n", share->path); @@ -214,7 +223,7 @@ out: return share; } -struct ksmbd_share_config *ksmbd_share_config_get(struct unicode_map *um, +struct ksmbd_share_config *ksmbd_share_config_get(struct ksmbd_work *work, const char *name) { struct ksmbd_share_config *share; @@ -227,7 +236,7 @@ struct ksmbd_share_config *ksmbd_share_config_get(struct unicode_map *um, if (share) return share; - return share_config_request(um, name); + return share_config_request(work, name); } bool ksmbd_share_veto_filename(struct ksmbd_share_config *share, diff --git a/fs/smb/server/mgmt/share_config.h b/fs/smb/server/mgmt/share_config.h index 5f591751b923..d4ac2dd4de20 100644 --- a/fs/smb/server/mgmt/share_config.h +++ b/fs/smb/server/mgmt/share_config.h @@ -11,6 +11,8 @@ #include <linux/path.h> #include <linux/unicode.h> +struct ksmbd_work; + struct ksmbd_share_config { char *name; char *path; @@ -68,7 +70,7 @@ static inline void ksmbd_share_config_put(struct ksmbd_share_config *share) __ksmbd_share_config_put(share); } -struct ksmbd_share_config *ksmbd_share_config_get(struct unicode_map *um, +struct ksmbd_share_config *ksmbd_share_config_get(struct ksmbd_work *work, const char *name); bool ksmbd_share_veto_filename(struct ksmbd_share_config *share, const char *filename); diff --git a/fs/smb/server/mgmt/tree_connect.c b/fs/smb/server/mgmt/tree_connect.c index d2c81a8a11dd..94a52a75014a 100644 --- a/fs/smb/server/mgmt/tree_connect.c +++ b/fs/smb/server/mgmt/tree_connect.c @@ -16,17 +16,18 @@ #include "user_session.h" struct ksmbd_tree_conn_status -ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess, - const char *share_name) +ksmbd_tree_conn_connect(struct ksmbd_work *work, const char *share_name) { struct ksmbd_tree_conn_status status = {-ENOENT, NULL}; struct ksmbd_tree_connect_response *resp = NULL; struct ksmbd_share_config *sc; struct ksmbd_tree_connect *tree_conn = NULL; struct sockaddr *peer_addr; + struct ksmbd_conn *conn = work->conn; + struct ksmbd_session *sess = work->sess; int ret; - sc = ksmbd_share_config_get(conn->um, share_name); + sc = ksmbd_share_config_get(work, share_name); if (!sc) return status; @@ -61,7 +62,7 @@ ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess, struct ksmbd_share_config *new_sc; ksmbd_share_config_del(sc); - new_sc = ksmbd_share_config_get(conn->um, share_name); + new_sc = ksmbd_share_config_get(work, share_name); if (!new_sc) { pr_err("Failed to update stale share config\n"); status.ret = -ESTALE; diff --git a/fs/smb/server/mgmt/tree_connect.h b/fs/smb/server/mgmt/tree_connect.h index 6377a70b811c..a42cdd051041 100644 --- a/fs/smb/server/mgmt/tree_connect.h +++ b/fs/smb/server/mgmt/tree_connect.h @@ -13,6 +13,7 @@ struct ksmbd_share_config; struct ksmbd_user; struct ksmbd_conn; +struct ksmbd_work; enum { TREE_NEW = 0, @@ -50,8 +51,7 @@ static inline int test_tree_conn_flag(struct ksmbd_tree_connect *tree_conn, struct ksmbd_session; struct ksmbd_tree_conn_status -ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess, - const char *share_name); +ksmbd_tree_conn_connect(struct ksmbd_work *work, const char *share_name); void ksmbd_tree_connect_put(struct ksmbd_tree_connect *tcon); int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess, diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 37a39ab4ee65..2df1354288e6 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -1955,7 +1955,7 @@ int smb2_tree_connect(struct ksmbd_work *work) ksmbd_debug(SMB, "tree connect request for tree %s treename %s\n", name, treename); - status = ksmbd_tree_conn_connect(conn, sess, name); + status = ksmbd_tree_conn_connect(work, name); if (status.ret == KSMBD_TREE_CONN_STATUS_OK) rsp->hdr.Id.SyncId.TreeId = cpu_to_le32(status.tree_conn->id); else @@ -5596,6 +5596,11 @@ int smb2_query_info(struct ksmbd_work *work) ksmbd_debug(SMB, "GOT query info request\n"); + if (ksmbd_override_fsids(work)) { + rc = -ENOMEM; + goto err_out; + } + switch (req->InfoType) { case SMB2_O_INFO_FILE: ksmbd_debug(SMB, "GOT SMB2_O_INFO_FILE\n"); @@ -5614,6 +5619,7 @@ int smb2_query_info(struct ksmbd_work *work) req->InfoType); rc = -EOPNOTSUPP; } + ksmbd_revert_fsids(work); if (!rc) { rsp->StructureSize = cpu_to_le16(9); @@ -5623,6 +5629,7 @@ int smb2_query_info(struct ksmbd_work *work) le32_to_cpu(rsp->OutputBufferLength)); } +err_out: if (rc < 0) { if (rc == -EACCES) rsp->hdr.Status = STATUS_ACCESS_DENIED; diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c index 474dadf6b7b8..13818ecb6e1b 100644 --- a/fs/smb/server/smb_common.c +++ b/fs/smb/server/smb_common.c @@ -732,10 +732,10 @@ bool is_asterisk(char *p) return p && p[0] == '*'; } -int ksmbd_override_fsids(struct ksmbd_work *work) +int __ksmbd_override_fsids(struct ksmbd_work *work, + struct ksmbd_share_config *share) { struct ksmbd_session *sess = work->sess; - struct ksmbd_share_config *share = work->tcon->share_conf; struct cred *cred; struct group_info *gi; unsigned int uid; @@ -775,6 +775,11 @@ int ksmbd_override_fsids(struct ksmbd_work *work) return 0; } +int ksmbd_override_fsids(struct ksmbd_work *work) +{ + return __ksmbd_override_fsids(work, work->tcon->share_conf); +} + void ksmbd_revert_fsids(struct ksmbd_work *work) { const struct cred *cred; diff --git a/fs/smb/server/smb_common.h b/fs/smb/server/smb_common.h index f1092519c0c2..4a3148b0167f 100644 --- a/fs/smb/server/smb_common.h +++ b/fs/smb/server/smb_common.h @@ -447,6 +447,8 @@ int ksmbd_extract_shortname(struct ksmbd_conn *conn, int ksmbd_smb_negotiate_common(struct ksmbd_work *work, unsigned int command); int ksmbd_smb_check_shared_mode(struct file *filp, struct ksmbd_file *curr_fp); +int __ksmbd_override_fsids(struct ksmbd_work *work, + struct ksmbd_share_config *share); int ksmbd_override_fsids(struct ksmbd_work *work); void ksmbd_revert_fsids(struct ksmbd_work *work); diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c index 16bd693d0b3a..d5918eba27e3 100644 --- a/fs/squashfs/inode.c +++ b/fs/squashfs/inode.c @@ -279,8 +279,13 @@ int squashfs_read_inode(struct inode *inode, long long ino) if (err < 0) goto failed_read; - set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); inode->i_size = le32_to_cpu(sqsh_ino->symlink_size); + if (inode->i_size > PAGE_SIZE) { + ERROR("Corrupted symlink\n"); + return -EINVAL; + } + + set_nlink(inode, le32_to_cpu(sqsh_ino->nlink)); inode->i_op = &squashfs_symlink_inode_ops; inode_nohighmem(inode); inode->i_data.a_ops = &squashfs_symlink_aops; diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 8c4768c44a01..d3b66d77df7a 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -270,6 +270,18 @@ static inline void bitmap_copy_clear_tail(unsigned long *dst, dst[nbits / BITS_PER_LONG] &= BITMAP_LAST_WORD_MASK(nbits); } +static inline void bitmap_copy_and_extend(unsigned long *to, + const unsigned long *from, + unsigned int count, unsigned int size) +{ + unsigned int copy = BITS_TO_LONGS(count); + + memcpy(to, from, copy * sizeof(long)); + if (count % BITS_PER_LONG) + to[copy - 1] &= BITMAP_LAST_WORD_MASK(count); + memset(to + copy, 0, bitmap_size(size) - copy * sizeof(long)); +} + /* * On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64 * machines the order of hi and lo parts of numbers match the bitmap structure. diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 6503c85b10a3..7b776dae36e5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -856,8 +856,8 @@ static inline u32 type_flag(u32 type) /* only use after check_attach_btf_id() */ static inline enum bpf_prog_type resolve_prog_type(const struct bpf_prog *prog) { - return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->dst_prog) ? - prog->aux->dst_prog->type : prog->type; + return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->saved_dst_prog_type) ? + prog->aux->saved_dst_prog_type : prog->type; } static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) diff --git a/include/linux/file.h b/include/linux/file.h index 237931f20739..59b146a14dca 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -110,7 +110,7 @@ DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T), * * f = dentry_open(&path, O_RDONLY, current_cred()); * if (IS_ERR(f)) - * return PTR_ERR(fd); + * return PTR_ERR(f); * * fd_install(fd, f); * return take_fd(fd); diff --git a/include/linux/fs.h b/include/linux/fs.h index fd34b5755c0b..fb0426f349fc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2392,6 +2392,9 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. * + * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding + * i_count. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2415,6 +2418,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_DONTCACHE (1 << 16) #define I_SYNC_QUEUED (1 << 17) #define I_PINNING_NETFS_WB (1 << 18) +#define __I_LRU_ISOLATING 19 +#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 5d0288938cc2..983816608f15 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -73,8 +73,6 @@ struct netfs_inode { #define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ #define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ #define NETFS_ICTX_WRITETHROUGH 2 /* Write-through caching */ -#define NETFS_ICTX_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark - * write to cache on read */ }; /* @@ -269,7 +267,6 @@ struct netfs_io_request { #define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ #define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */ -#define NETFS_RREQ_WRITE_TO_CACHE 7 /* Need to write to the cache */ #define NETFS_RREQ_UPLOAD_TO_SERVER 8 /* Need to write to the server */ #define NETFS_RREQ_NONBLOCK 9 /* Don't block if possible (O_NONBLOCK) */ #define NETFS_RREQ_BLOCKED 10 /* We blocked */ diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index da23484268df..606b4a0f92da 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -51,6 +51,7 @@ EM(netfs_rreq_trace_resubmit, "RESUBMT") \ EM(netfs_rreq_trace_set_pause, "PAUSE ") \ EM(netfs_rreq_trace_unlock, "UNLOCK ") \ + EM(netfs_rreq_trace_unlock_pgpriv2, "UNLCK-2") \ EM(netfs_rreq_trace_unmark, "UNMARK ") \ EM(netfs_rreq_trace_wait_ip, "WAIT-IP") \ EM(netfs_rreq_trace_wait_pause, "WT-PAUS") \ @@ -145,6 +146,7 @@ EM(netfs_folio_trace_clear_g, "clear-g") \ EM(netfs_folio_trace_clear_s, "clear-s") \ EM(netfs_folio_trace_copy_to_cache, "mark-copy") \ + EM(netfs_folio_trace_end_copy, "end-copy") \ EM(netfs_folio_trace_filled_gaps, "filled-gaps") \ EM(netfs_folio_trace_kill, "kill") \ EM(netfs_folio_trace_kill_cc, "kill-cc") \ diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h index b133211331f6..5fad3d0fcd70 100644 --- a/include/uapi/linux/nsfs.h +++ b/include/uapi/linux/nsfs.h @@ -3,6 +3,7 @@ #define __LINUX_NSFS_H #include <linux/ioctl.h> +#include <linux/types.h> #define NSIO 0xb7 @@ -16,7 +17,7 @@ /* Get owner UID (in the caller's user namespace) for a user namespace */ #define NS_GET_OWNER_UID _IO(NSIO, 0x4) /* Get the id for a mount namespace */ -#define NS_GET_MNTNS_ID _IO(NSIO, 0x5) +#define NS_GET_MNTNS_ID _IOR(NSIO, 0x5, __u64) /* Translate pid from target pid namespace into the caller's pid namespace. */ #define NS_GET_PID_FROM_PIDNS _IOR(NSIO, 0x6, int) /* Return thread-group leader id of pid in the callers pid namespace. */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4cb5441ad75f..d8520095ca03 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -16884,8 +16884,9 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, spi = i / BPF_REG_SIZE; if (exact != NOT_EXACT && - old->stack[spi].slot_type[i % BPF_REG_SIZE] != - cur->stack[spi].slot_type[i % BPF_REG_SIZE]) + (i >= cur->allocated_stack || + old->stack[spi].slot_type[i % BPF_REG_SIZE] != + cur->stack[spi].slot_type[i % BPF_REG_SIZE])) return false; if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ) diff --git a/kernel/events/core.c b/kernel/events/core.c index aa3450bdc227..c973e3c11e03 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9706,7 +9706,8 @@ static int __perf_event_overflow(struct perf_event *event, ret = __perf_event_account_interrupt(event, throttle); - if (event->prog && !bpf_overflow_handler(event, data, regs)) + if (event->prog && event->prog->type == BPF_PROG_TYPE_PERF_EVENT && + !bpf_overflow_handler(event, data, regs)) return ret; /* diff --git a/kernel/fork.c b/kernel/fork.c index cc760491f201..18bdc87209d0 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2053,11 +2053,24 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re */ int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) { - bool thread = flags & PIDFD_THREAD; - - if (!pid || !pid_has_task(pid, thread ? PIDTYPE_PID : PIDTYPE_TGID)) + if (!pid) return -EINVAL; + scoped_guard(rcu) { + struct task_struct *tsk; + + if (flags & PIDFD_THREAD) + tsk = pid_task(pid, PIDTYPE_PID); + else + tsk = pid_task(pid, PIDTYPE_TGID); + if (!tsk) + return -EINVAL; + + /* Don't create pidfds for kernel threads for now. */ + if (tsk->flags & PF_KTHREAD) + return -EINVAL; + } + return __pidfd_prepare(pid, flags, ret); } @@ -2403,6 +2416,12 @@ __latent_entropy struct task_struct *copy_process( if (clone_flags & CLONE_PIDFD) { int flags = (clone_flags & CLONE_THREAD) ? PIDFD_THREAD : 0; + /* Don't create pidfds for kernel threads for now. */ + if (args->kthread) { + retval = -EINVAL; + goto bad_fork_free_pid; + } + /* Note that no task has been attached to @pid yet. */ retval = __pidfd_prepare(pid, flags, &pidfile); if (retval < 0) diff --git a/security/selinux/avc.c b/security/selinux/avc.c index 32eb67fb3e42..b49c44869dc4 100644 --- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -330,12 +330,12 @@ static int avc_add_xperms_decision(struct avc_node *node, { struct avc_xperms_decision_node *dest_xpd; - node->ae.xp_node->xp.len++; dest_xpd = avc_xperms_decision_alloc(src->used); if (!dest_xpd) return -ENOMEM; avc_copy_xperms_decision(&dest_xpd->xpd, src); list_add(&dest_xpd->xpd_list, &node->ae.xp_node->xpd_head); + node->ae.xp_node->xp.len++; return 0; } @@ -907,7 +907,11 @@ static int avc_update_node(u32 event, u32 perms, u8 driver, u8 xperm, u32 ssid, node->ae.avd.auditdeny &= ~perms; break; case AVC_CALLBACK_ADD_XPERMS: - avc_add_xperms_decision(node, xpd); + rc = avc_add_xperms_decision(node, xpd); + if (rc) { + avc_node_kill(node); + goto out_unlock; + } break; } avc_node_replace(node, orig); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 55c78c318ccd..bfa61e005aac 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3852,7 +3852,17 @@ static int selinux_file_mprotect(struct vm_area_struct *vma, if (default_noexec && (prot & PROT_EXEC) && !(vma->vm_flags & VM_EXEC)) { int rc = 0; - if (vma_is_initial_heap(vma)) { + /* + * We don't use the vma_is_initial_heap() helper as it has + * a history of problems and is currently broken on systems + * where there is no heap, e.g. brk == start_brk. Before + * replacing the conditional below with vma_is_initial_heap(), + * or something similar, please ensure that the logic is the + * same as what we have below or you have tested every possible + * corner case you can think to test. + */ + if (vma->vm_start >= vma->vm_mm->start_brk && + vma->vm_end <= vma->vm_mm->brk) { rc = avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__EXECHEAP, NULL); } else if (!vma->vm_file && (vma_is_initial_stack(vma) || diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index 16bdc3e25591..ef70b88bccb2 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -1432,4 +1432,58 @@ int iter_arr_with_actual_elem_count(const void *ctx) return sum; } +__u32 upper, select_n, result; +__u64 global; + +static __noinline bool nest_2(char *str) +{ + /* some insns (including branch insns) to ensure stacksafe() is triggered + * in nest_2(). This way, stacksafe() can compare frame associated with nest_1(). + */ + if (str[0] == 't') + return true; + if (str[1] == 'e') + return true; + if (str[2] == 's') + return true; + if (str[3] == 't') + return true; + return false; +} + +static __noinline bool nest_1(int n) +{ + /* case 0: allocate stack, case 1: no allocate stack */ + switch (n) { + case 0: { + char comm[16]; + + if (bpf_get_current_comm(comm, 16)) + return false; + return nest_2(comm); + } + case 1: + return nest_2((char *)&global); + default: + return false; + } +} + +SEC("raw_tp") +__success +int iter_subprog_check_stacksafe(const void *ctx) +{ + long i; + + bpf_for(i, 0, upper) { + if (!nest_1(select_n)) { + result = 1; + return 0; + } + } + + result = 2; + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c index 991c473e3859..12b4eb9d0434 100644 --- a/tools/testing/selftests/core/close_range_test.c +++ b/tools/testing/selftests/core/close_range_test.c @@ -589,4 +589,39 @@ TEST(close_range_cloexec_unshare_syzbot) EXPECT_EQ(close(fd3), 0); } +TEST(close_range_bitmap_corruption) +{ + pid_t pid; + int status; + struct __clone_args args = { + .flags = CLONE_FILES, + .exit_signal = SIGCHLD, + }; + + /* get the first 128 descriptors open */ + for (int i = 2; i < 128; i++) + EXPECT_GE(dup2(0, i), 0); + + /* get descriptor table shared */ + pid = sys_clone3(&args, sizeof(args)); + ASSERT_GE(pid, 0); + + if (pid == 0) { + /* unshare and truncate descriptor table down to 64 */ + if (sys_close_range(64, ~0U, CLOSE_RANGE_UNSHARE)) + exit(EXIT_FAILURE); + + ASSERT_EQ(fcntl(64, F_GETFD), -1); + /* ... and verify that the range 64..127 is not + stuck "fully used" according to secondary bitmap */ + EXPECT_EQ(dup(0), 64) + exit(EXIT_FAILURE); + exit(EXIT_SUCCESS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); +} + TEST_HARNESS_MAIN |