diff options
Diffstat (limited to 'include/linux')
138 files changed, 2413 insertions, 1245 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 96bd672dc336..7b71dd74baeb 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1077,6 +1077,11 @@ static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context) return 0; } +static inline bool acpi_sleep_state_supported(u8 sleep_state) +{ + return false; +} + #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC diff --git a/include/linux/alcor_pci.h b/include/linux/alcor_pci.h index 8274ed525e9f..c4a0b23846d8 100644 --- a/include/linux/alcor_pci.h +++ b/include/linux/alcor_pci.h @@ -268,13 +268,6 @@ struct alcor_pci_priv { unsigned long id; /* idr id */ struct alcor_dev_cfg *cfg; - - /* PCI ASPM related vars */ - int pdev_cap_off; - u8 pdev_aspm_cap; - int parent_cap_off; - u8 parent_aspm_cap; - u8 ext_config_dev_aspm; }; void alcor_write8(struct alcor_pci_priv *priv, u8 val, unsigned int addr); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 8f14dca5fed7..1520793c72da 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -196,11 +196,17 @@ void mark_buffer_write_io_error(struct buffer_head *bh); void touch_buffer(struct buffer_head *bh); void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset); +void folio_set_bh(struct buffer_head *bh, struct folio *folio, + unsigned long offset); bool try_to_free_buffers(struct folio *); +struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size, + bool retry); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry); void create_empty_buffers(struct page *, unsigned long, unsigned long b_state); +void folio_create_empty_buffers(struct folio *folio, unsigned long blocksize, + unsigned long b_state); void end_buffer_read_sync(struct buffer_head *bh, int uptodate); void end_buffer_write_sync(struct buffer_head *bh, int uptodate); void end_buffer_async_write(struct buffer_head *bh, int uptodate); diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 908e19d17f49..a5cfd44fab45 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -76,9 +76,11 @@ struct cpu_cacheinfo { unsigned int num_levels; unsigned int num_leaves; bool cpu_map_populated; + bool early_ci_levels; }; struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu); +int early_cache_level(unsigned int cpu); int init_cache_level(unsigned int cpu); int init_of_cache_level(unsigned int cpu); int populate_cache_leaves(unsigned int cpu); @@ -129,4 +131,10 @@ static inline int get_cpu_cacheinfo_id(int cpu, int level) return -1; } +#ifdef CONFIG_ARM64 +#define use_arch_cache_info() (true) +#else +#define use_arch_cache_info() (false) +#endif + #endif /* _LINUX_CACHEINFO_H */ diff --git a/include/linux/cdx/cdx_bus.h b/include/linux/cdx/cdx_bus.h new file mode 100644 index 000000000000..35ef41d8a61a --- /dev/null +++ b/include/linux/cdx/cdx_bus.h @@ -0,0 +1,174 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * CDX bus public interface + * + * Copyright (C) 2022-2023, Advanced Micro Devices, Inc. + * + */ + +#ifndef _CDX_BUS_H_ +#define _CDX_BUS_H_ + +#include <linux/device.h> +#include <linux/list.h> +#include <linux/mod_devicetable.h> + +#define MAX_CDX_DEV_RESOURCES 4 +#define CDX_ANY_ID (0xFFFF) +#define CDX_CONTROLLER_ID_SHIFT 4 +#define CDX_BUS_NUM_MASK 0xF + +/* Forward declaration for CDX controller */ +struct cdx_controller; + +enum { + CDX_DEV_RESET_CONF, +}; + +struct cdx_device_config { + u8 type; +}; + +typedef int (*cdx_scan_cb)(struct cdx_controller *cdx); + +typedef int (*cdx_dev_configure_cb)(struct cdx_controller *cdx, + u8 bus_num, u8 dev_num, + struct cdx_device_config *dev_config); + +/** + * CDX_DEVICE_DRIVER_OVERRIDE - macro used to describe a CDX device with + * override_only flags. + * @vend: the 16 bit CDX Vendor ID + * @dev: the 16 bit CDX Device ID + * @driver_override: the 32 bit CDX Device override_only + * + * This macro is used to create a struct cdx_device_id that matches only a + * driver_override device. + */ +#define CDX_DEVICE_DRIVER_OVERRIDE(vend, dev, driver_override) \ + .vendor = (vend), .device = (dev), .override_only = (driver_override) + +/** + * struct cdx_ops - Callbacks supported by CDX controller. + * @scan: scan the devices on the controller + * @dev_configure: configuration like reset, master_enable, + * msi_config etc for a CDX device + */ +struct cdx_ops { + cdx_scan_cb scan; + cdx_dev_configure_cb dev_configure; +}; + +/** + * struct cdx_controller: CDX controller object + * @dev: Linux device associated with the CDX controller. + * @priv: private data + * @id: Controller ID + * @ops: CDX controller ops + */ +struct cdx_controller { + struct device *dev; + void *priv; + u32 id; + struct cdx_ops *ops; +}; + +/** + * struct cdx_device - CDX device object + * @dev: Linux driver model device object + * @cdx: CDX controller associated with the device + * @vendor: Vendor ID for CDX device + * @device: Device ID for CDX device + * @bus_num: Bus number for this CDX device + * @dev_num: Device number for this device + * @res: array of MMIO region entries + * @res_attr: resource binary attribute + * @res_count: number of valid MMIO regions + * @dma_mask: Default DMA mask + * @flags: CDX device flags + * @req_id: Requestor ID associated with CDX device + * @driver_override: driver name to force a match; do not set directly, + * because core frees it; use driver_set_override() to + * set or clear it. + */ +struct cdx_device { + struct device dev; + struct cdx_controller *cdx; + u16 vendor; + u16 device; + u8 bus_num; + u8 dev_num; + struct resource res[MAX_CDX_DEV_RESOURCES]; + u8 res_count; + u64 dma_mask; + u16 flags; + u32 req_id; + const char *driver_override; +}; + +#define to_cdx_device(_dev) \ + container_of(_dev, struct cdx_device, dev) + +/** + * struct cdx_driver - CDX device driver + * @driver: Generic device driver + * @match_id_table: table of supported device matching Ids + * @probe: Function called when a device is added + * @remove: Function called when a device is removed + * @shutdown: Function called at shutdown time to quiesce the device + * @reset_prepare: Function called before is reset to notify driver + * @reset_done: Function called after reset is complete to notify driver + * @driver_managed_dma: Device driver doesn't use kernel DMA API for DMA. + * For most device drivers, no need to care about this flag + * as long as all DMAs are handled through the kernel DMA API. + * For some special ones, for example VFIO drivers, they know + * how to manage the DMA themselves and set this flag so that + * the IOMMU layer will allow them to setup and manage their + * own I/O address space. + */ +struct cdx_driver { + struct device_driver driver; + const struct cdx_device_id *match_id_table; + int (*probe)(struct cdx_device *dev); + int (*remove)(struct cdx_device *dev); + void (*shutdown)(struct cdx_device *dev); + void (*reset_prepare)(struct cdx_device *dev); + void (*reset_done)(struct cdx_device *dev); + bool driver_managed_dma; +}; + +#define to_cdx_driver(_drv) \ + container_of(_drv, struct cdx_driver, driver) + +/* Macro to avoid include chaining to get THIS_MODULE */ +#define cdx_driver_register(drv) \ + __cdx_driver_register(drv, THIS_MODULE) + +/** + * __cdx_driver_register - registers a CDX device driver + * @cdx_driver: CDX driver to register + * @owner: module owner + * + * Return: -errno on failure, 0 on success. + */ +int __must_check __cdx_driver_register(struct cdx_driver *cdx_driver, + struct module *owner); + +/** + * cdx_driver_unregister - unregisters a device driver from the + * CDX bus. + * @cdx_driver: CDX driver to register + */ +void cdx_driver_unregister(struct cdx_driver *cdx_driver); + +extern struct bus_type cdx_bus_type; + +/** + * cdx_dev_reset - Reset CDX device + * @dev: device pointer + * + * Return: 0 for success, -errno on failure + */ +int cdx_dev_reset(struct device *dev); + +#endif /* _CDX_BUS_H_ */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 3410aecffdb4..885f5395fcd0 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -692,7 +692,7 @@ static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) */ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu); void cgroup_rstat_flush(struct cgroup *cgrp); -void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp); +void cgroup_rstat_flush_atomic(struct cgroup *cgrp); void cgroup_rstat_flush_hold(struct cgroup *cgrp); void cgroup_rstat_flush_release(void); diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 6f3175f0678a..28ff6f1a6ada 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -608,6 +608,25 @@ struct clk *clk_register_gate(struct device *dev, const char *name, __devm_clk_hw_register_gate((dev), NULL, (name), (parent_name), NULL, \ NULL, (flags), (reg), (bit_idx), \ (clk_gate_flags), (lock)) +/** + * devm_clk_hw_register_gate_parent_data - register a gate clock with the + * clock framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_data: parent clk data + * @flags: framework-specific flags for this clock + * @reg: register address to control gating of this clock + * @bit_idx: which bit in the register controls gating of this clock + * @clk_gate_flags: gate-specific flags for this clock + * @lock: shared register lock for this clock + */ +#define devm_clk_hw_register_gate_parent_data(dev, name, parent_data, flags, \ + reg, bit_idx, clk_gate_flags, \ + lock) \ + __devm_clk_hw_register_gate((dev), NULL, (name), NULL, NULL, \ + (parent_data), (flags), (reg), (bit_idx), \ + (clk_gate_flags), (lock)) + void clk_unregister_gate(struct clk *clk); void clk_hw_unregister_gate(struct clk_hw *hw); int clk_gate_is_enabled(struct clk_hw *hw); @@ -1135,10 +1154,8 @@ struct clk_fractional_divider { void __iomem *reg; u8 mshift; u8 mwidth; - u32 mmask; u8 nshift; u8 nwidth; - u32 nmask; u8 flags; void (*approximation)(struct clk_hw *hw, unsigned long rate, unsigned long *parent_rate, diff --git a/include/linux/cm4000_cs.h b/include/linux/cm4000_cs.h deleted file mode 100644 index ea4958e07a14..000000000000 --- a/include/linux/cm4000_cs.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _CM4000_H_ -#define _CM4000_H_ - -#include <uapi/linux/cm4000_cs.h> - - -#define DEVICE_NAME "cmm" -#define MODULE_NAME "cm4000_cs" - -#endif /* _CM4000_H_ */ diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 52a9ff65faee..a6e512cfb670 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -81,13 +81,6 @@ static inline unsigned long compact_gap(unsigned int order) } #ifdef CONFIG_COMPACTION -extern unsigned int sysctl_compaction_proactiveness; -extern int sysctl_compaction_handler(struct ctl_table *table, int write, - void *buffer, size_t *length, loff_t *ppos); -extern int compaction_proactiveness_sysctl_handler(struct ctl_table *table, - int write, void *buffer, size_t *length, loff_t *ppos); -extern int sysctl_extfrag_threshold; -extern int sysctl_compact_unevictable_allowed; extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order); extern int fragmentation_index(struct zone *zone, unsigned int order); diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 3a7909ed5498..d3cbb6c16bab 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -98,7 +98,7 @@ static inline void exception_exit(enum ctx_state prev_ctx) { } static inline int ct_state(void) { return -1; } static inline int __ct_state(void) { return -1; } static __always_inline bool context_tracking_guest_enter(void) { return false; } -static inline void context_tracking_guest_exit(void) { } +static __always_inline void context_tracking_guest_exit(void) { } #define CT_WARN_ON(cond) do { } while (0) #endif /* !CONFIG_CONTEXT_TRACKING_USER */ diff --git a/include/linux/cpu.h b/include/linux/cpu.h index f83e4519c5f0..8582a7142623 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -182,7 +182,7 @@ void arch_cpu_idle(void); void arch_cpu_idle_prepare(void); void arch_cpu_idle_enter(void); void arch_cpu_idle_exit(void); -void arch_cpu_idle_dead(void); +void __noreturn arch_cpu_idle_dead(void); int cpu_report_state(int cpu); int cpu_check_up_prepare(int cpu); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 541013487a0e..26e2eb399484 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -15,7 +15,6 @@ #include <linux/kobject.h> #include <linux/notifier.h> #include <linux/of.h> -#include <linux/of_device.h> #include <linux/pm_opp.h> #include <linux/pm_qos.h> #include <linux/spinlock.h> diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index d58e0476ee8e..980b76a1237e 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -80,18 +80,11 @@ extern nodemask_t cpuset_mems_allowed(struct task_struct *p); void cpuset_init_current_mems_allowed(void); int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask); -extern bool __cpuset_node_allowed(int node, gfp_t gfp_mask); - -static inline bool cpuset_node_allowed(int node, gfp_t gfp_mask) -{ - if (cpusets_enabled()) - return __cpuset_node_allowed(node, gfp_mask); - return true; -} +extern bool cpuset_node_allowed(int node, gfp_t gfp_mask); static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { - return __cpuset_node_allowed(zone_to_nid(z), gfp_mask); + return cpuset_node_allowed(zone_to_nid(z), gfp_mask); } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) @@ -223,11 +216,6 @@ static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) return 1; } -static inline bool cpuset_node_allowed(int node, gfp_t gfp_mask) -{ - return true; -} - static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return true; diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 0da97dba9ef8..6639f48dac36 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -48,10 +48,13 @@ struct task_delay_info { u64 wpcopy_start; u64 wpcopy_delay; /* wait for write-protect copy */ + u64 irq_delay; /* wait for IRQ/SOFTIRQ */ + u32 freepages_count; /* total count of memory reclaim */ u32 thrashing_count; /* total count of thrash waits */ u32 compact_count; /* total count of memory compact */ u32 wpcopy_count; /* total count of write-protect copy */ + u32 irq_count; /* total count of IRQ/SOFTIRQ */ }; #endif @@ -81,6 +84,7 @@ extern void __delayacct_compact_start(void); extern void __delayacct_compact_end(void); extern void __delayacct_wpcopy_start(void); extern void __delayacct_wpcopy_end(void); +extern void __delayacct_irq(struct task_struct *task, u32 delta); static inline void delayacct_tsk_init(struct task_struct *tsk) { @@ -215,6 +219,15 @@ static inline void delayacct_wpcopy_end(void) __delayacct_wpcopy_end(); } +static inline void delayacct_irq(struct task_struct *task, u32 delta) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (task->delays) + __delayacct_irq(task, delta); +} + #else static inline void delayacct_init(void) {} @@ -253,6 +266,8 @@ static inline void delayacct_wpcopy_start(void) {} static inline void delayacct_wpcopy_end(void) {} +static inline void delayacct_irq(struct task_struct *task, u32 delta) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ diff --git a/include/linux/device.h b/include/linux/device.h index 1508e637bb26..472dd24d4823 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -243,21 +243,26 @@ void __iomem *devm_of_iomap(struct device *dev, resource_size_t *size); /* allows to add/remove a custom action to devres stack */ -int devm_add_action(struct device *dev, void (*action)(void *), void *data); void devm_remove_action(struct device *dev, void (*action)(void *), void *data); void devm_release_action(struct device *dev, void (*action)(void *), void *data); -static inline int devm_add_action_or_reset(struct device *dev, - void (*action)(void *), void *data) +int __devm_add_action(struct device *dev, void (*action)(void *), void *data, const char *name); +#define devm_add_action(release, action, data) \ + __devm_add_action(release, action, data, #action) + +static inline int __devm_add_action_or_reset(struct device *dev, void (*action)(void *), + void *data, const char *name) { int ret; - ret = devm_add_action(dev, action, data); + ret = __devm_add_action(dev, action, data, name); if (ret) action(data); return ret; } +#define devm_add_action_or_reset(release, action, data) \ + __devm_add_action_or_reset(release, action, data, #action) /** * devm_alloc_percpu - Resource-managed alloc_percpu @@ -561,7 +566,7 @@ struct device { const char *init_name; /* initial name of the device */ const struct device_type *type; - struct bus_type *bus; /* type of bus device is on */ + const struct bus_type *bus; /* type of bus device is on */ struct device_driver *driver; /* which driver has allocated this device */ void *platform_data; /* Platform specific data, device @@ -626,7 +631,7 @@ struct device { spinlock_t devres_lock; struct list_head devres_head; - struct class *class; + const struct class *class; const struct attribute_group **groups; /* optional groups */ void (*release)(struct device *dev); @@ -1010,13 +1015,13 @@ bool device_is_bound(struct device *dev); * Easy functions for dynamically creating devices on the fly */ __printf(5, 6) struct device * -device_create(struct class *cls, struct device *parent, dev_t devt, +device_create(const struct class *cls, struct device *parent, dev_t devt, void *drvdata, const char *fmt, ...); __printf(6, 7) struct device * -device_create_with_groups(struct class *cls, struct device *parent, dev_t devt, +device_create_with_groups(const struct class *cls, struct device *parent, dev_t devt, void *drvdata, const struct attribute_group **groups, const char *fmt, ...); -void device_destroy(struct class *cls, dev_t devt); +void device_destroy(const struct class *cls, dev_t devt); int __must_check device_add_groups(struct device *dev, const struct attribute_group **groups); @@ -1083,8 +1088,7 @@ void device_link_remove(void *consumer, struct device *supplier); void device_links_supplier_sync_state_pause(void); void device_links_supplier_sync_state_resume(void); -extern __printf(3, 4) -int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); +__printf(3, 4) int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); /* Create alias, so I can be autoloaded. */ #define MODULE_ALIAS_CHARDEV(major,minor) \ @@ -1092,10 +1096,4 @@ int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); #define MODULE_ALIAS_CHARDEV_MAJOR(major) \ MODULE_ALIAS("char-major-" __stringify(major) "-*") -#ifdef CONFIG_SYSFS_DEPRECATED -extern long sysfs_deprecated; -#else -#define sysfs_deprecated 0 -#endif - #endif /* _DEVICE_H_ */ diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 6ce32ef4b8fd..ae10c4322754 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -26,7 +26,6 @@ struct fwnode_handle; * * @name: The name of the bus. * @dev_name: Used for subsystems to enumerate devices like ("foo%u", dev->id). - * @dev_root: Default device to use as the parent. * @bus_groups: Default attributes of the bus. * @dev_groups: Default attributes of the devices on the bus. * @drv_groups: Default attributes of the device drivers on the bus. @@ -66,7 +65,6 @@ struct fwnode_handle; * @iommu_ops: IOMMU specific operations for this bus, used to attach IOMMU * driver implementations to a bus and allow the driver to do * bus-specific setup - * @lock_key: Lock class key for use by the lock validator * @need_parent_lock: When probing or removing a device on this bus, the * device core should lock the device's parent. * @@ -82,7 +80,6 @@ struct fwnode_handle; struct bus_type { const char *name; const char *dev_name; - struct device *dev_root; const struct attribute_group **bus_groups; const struct attribute_group **dev_groups; const struct attribute_group **drv_groups; @@ -112,16 +109,16 @@ struct bus_type { bool need_parent_lock; }; -extern int __must_check bus_register(struct bus_type *bus); +int __must_check bus_register(const struct bus_type *bus); -extern void bus_unregister(const struct bus_type *bus); +void bus_unregister(const struct bus_type *bus); -extern int __must_check bus_rescan_devices(struct bus_type *bus); +int __must_check bus_rescan_devices(const struct bus_type *bus); struct bus_attribute { struct attribute attr; - ssize_t (*show)(struct bus_type *bus, char *buf); - ssize_t (*store)(struct bus_type *bus, const char *buf, size_t count); + ssize_t (*show)(const struct bus_type *bus, char *buf); + ssize_t (*store)(const struct bus_type *bus, const char *buf, size_t count); }; #define BUS_ATTR_RW(_name) \ @@ -246,10 +243,8 @@ void bus_sort_breadthfirst(struct bus_type *bus, */ struct notifier_block; -extern int bus_register_notifier(const struct bus_type *bus, - struct notifier_block *nb); -extern int bus_unregister_notifier(const struct bus_type *bus, - struct notifier_block *nb); +int bus_register_notifier(const struct bus_type *bus, struct notifier_block *nb); +int bus_unregister_notifier(const struct bus_type *bus, struct notifier_block *nb); /** * enum bus_notifier_event - Bus Notifier events that have happened @@ -281,7 +276,7 @@ enum bus_notifier_event { BUS_NOTIFY_DRIVER_NOT_BOUND, }; -extern struct kset *bus_get_kset(const struct bus_type *bus); +struct kset *bus_get_kset(const struct bus_type *bus); struct device *bus_get_dev_root(const struct bus_type *bus); #endif diff --git a/include/linux/device/class.h b/include/linux/device/class.h index 42cc3fb44a84..9deeaeb457bb 100644 --- a/include/linux/device/class.h +++ b/include/linux/device/class.h @@ -25,10 +25,8 @@ struct fwnode_handle; /** * struct class - device classes * @name: Name of the class. - * @owner: The module owner. * @class_groups: Default attributes of this class. * @dev_groups: Default attributes of the devices that belong to the class. - * @dev_kobj: The kobject that represents this class and links it into the hierarchy. * @dev_uevent: Called when a device is added, removed from this class, or a * few other things that generate uevents to add the environment * variables. @@ -53,16 +51,14 @@ struct fwnode_handle; */ struct class { const char *name; - struct module *owner; const struct attribute_group **class_groups; const struct attribute_group **dev_groups; - struct kobject *dev_kobj; int (*dev_uevent)(const struct device *dev, struct kobj_uevent_env *env); char *(*devnode)(const struct device *dev, umode_t *mode); - void (*class_release)(struct class *class); + void (*class_release)(const struct class *class); void (*dev_release)(struct device *dev); int (*shutdown_pre)(struct device *dev); @@ -73,8 +69,6 @@ struct class { void (*get_ownership)(const struct device *dev, kuid_t *uid, kgid_t *gid); const struct dev_pm_ops *pm; - - struct subsys_private *p; }; struct class_dev_iter { @@ -82,19 +76,9 @@ struct class_dev_iter { const struct device_type *type; }; -extern struct kobject *sysfs_dev_block_kobj; -extern struct kobject *sysfs_dev_char_kobj; -extern int __must_check __class_register(struct class *class, - struct lock_class_key *key); -extern void class_unregister(struct class *class); - -/* This is a #define to keep the compiler from merging different - * instances of the __key variable */ -#define class_register(class) \ -({ \ - static struct lock_class_key __key; \ - __class_register(class, &__key); \ -}) +int __must_check class_register(const struct class *class); +void class_unregister(const struct class *class); +bool class_is_registered(const struct class *class); struct class_compat; struct class_compat *class_compat_register(const char *name); @@ -104,19 +88,15 @@ int class_compat_create_link(struct class_compat *cls, struct device *dev, void class_compat_remove_link(struct class_compat *cls, struct device *dev, struct device *device_link); -extern void class_dev_iter_init(struct class_dev_iter *iter, - struct class *class, - struct device *start, - const struct device_type *type); -extern struct device *class_dev_iter_next(struct class_dev_iter *iter); -extern void class_dev_iter_exit(struct class_dev_iter *iter); +void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class, + const struct device *start, const struct device_type *type); +struct device *class_dev_iter_next(struct class_dev_iter *iter); +void class_dev_iter_exit(struct class_dev_iter *iter); -extern int class_for_each_device(struct class *class, struct device *start, - void *data, - int (*fn)(struct device *dev, void *data)); -extern struct device *class_find_device(struct class *class, - struct device *start, const void *data, - int (*match)(struct device *, const void *)); +int class_for_each_device(const struct class *class, const struct device *start, void *data, + int (*fn)(struct device *dev, void *data)); +struct device *class_find_device(const struct class *class, const struct device *start, + const void *data, int (*match)(struct device *, const void *)); /** * class_find_device_by_name - device iterator for locating a particular device @@ -124,7 +104,7 @@ extern struct device *class_find_device(struct class *class, * @class: class type * @name: name of the device to match */ -static inline struct device *class_find_device_by_name(struct class *class, +static inline struct device *class_find_device_by_name(const struct class *class, const char *name) { return class_find_device(class, NULL, name, device_match_name); @@ -136,8 +116,8 @@ static inline struct device *class_find_device_by_name(struct class *class, * @class: class type * @np: of_node of the device to match. */ -static inline struct device * -class_find_device_by_of_node(struct class *class, const struct device_node *np) +static inline struct device *class_find_device_by_of_node(const struct class *class, + const struct device_node *np) { return class_find_device(class, NULL, np, device_match_of_node); } @@ -148,9 +128,8 @@ class_find_device_by_of_node(struct class *class, const struct device_node *np) * @class: class type * @fwnode: fwnode of the device to match. */ -static inline struct device * -class_find_device_by_fwnode(struct class *class, - const struct fwnode_handle *fwnode) +static inline struct device *class_find_device_by_fwnode(const struct class *class, + const struct fwnode_handle *fwnode) { return class_find_device(class, NULL, fwnode, device_match_fwnode); } @@ -161,7 +140,7 @@ class_find_device_by_fwnode(struct class *class, * @class: class type * @devt: device type of the device to match. */ -static inline struct device *class_find_device_by_devt(struct class *class, +static inline struct device *class_find_device_by_devt(const struct class *class, dev_t devt) { return class_find_device(class, NULL, &devt, device_match_devt); @@ -175,14 +154,14 @@ struct acpi_device; * @class: class type * @adev: ACPI_COMPANION device to match. */ -static inline struct device * -class_find_device_by_acpi_dev(struct class *class, const struct acpi_device *adev) +static inline struct device *class_find_device_by_acpi_dev(const struct class *class, + const struct acpi_device *adev) { return class_find_device(class, NULL, adev, device_match_acpi_dev); } #else -static inline struct device * -class_find_device_by_acpi_dev(struct class *class, const void *adev) +static inline struct device *class_find_device_by_acpi_dev(const struct class *class, + const void *adev) { return NULL; } @@ -190,10 +169,10 @@ class_find_device_by_acpi_dev(struct class *class, const void *adev) struct class_attribute { struct attribute attr; - ssize_t (*show)(struct class *class, struct class_attribute *attr, + ssize_t (*show)(const struct class *class, const struct class_attribute *attr, char *buf); - ssize_t (*store)(struct class *class, struct class_attribute *attr, - const char *buf, size_t count); + ssize_t (*store)(const struct class *class, const struct class_attribute *attr, + const char *buf, size_t count); }; #define CLASS_ATTR_RW(_name) \ @@ -203,20 +182,18 @@ struct class_attribute { #define CLASS_ATTR_WO(_name) \ struct class_attribute class_attr_##_name = __ATTR_WO(_name) -extern int __must_check class_create_file_ns(struct class *class, - const struct class_attribute *attr, - const void *ns); -extern void class_remove_file_ns(struct class *class, - const struct class_attribute *attr, - const void *ns); +int __must_check class_create_file_ns(const struct class *class, const struct class_attribute *attr, + const void *ns); +void class_remove_file_ns(const struct class *class, const struct class_attribute *attr, + const void *ns); -static inline int __must_check class_create_file(struct class *class, - const struct class_attribute *attr) +static inline int __must_check class_create_file(const struct class *class, + const struct class_attribute *attr) { return class_create_file_ns(class, attr, NULL); } -static inline void class_remove_file(struct class *class, +static inline void class_remove_file(const struct class *class, const struct class_attribute *attr) { return class_remove_file_ns(class, attr, NULL); @@ -235,46 +212,21 @@ struct class_attribute_string { struct class_attribute_string class_attr_##_name = \ _CLASS_ATTR_STRING(_name, _mode, _str) -extern ssize_t show_class_attr_string(struct class *class, struct class_attribute *attr, - char *buf); +ssize_t show_class_attr_string(const struct class *class, const struct class_attribute *attr, + char *buf); struct class_interface { struct list_head node; - struct class *class; + const struct class *class; - int (*add_dev) (struct device *, struct class_interface *); - void (*remove_dev) (struct device *, struct class_interface *); + int (*add_dev) (struct device *dev); + void (*remove_dev) (struct device *dev); }; -extern int __must_check class_interface_register(struct class_interface *); -extern void class_interface_unregister(struct class_interface *); - -extern struct class * __must_check __class_create(struct module *owner, - const char *name, - struct lock_class_key *key); -extern void class_destroy(struct class *cls); - -/* This is a #define to keep the compiler from merging different - * instances of the __key variable */ - -/** - * class_create - create a struct class structure - * @owner: pointer to the module that is to "own" this struct class - * @name: pointer to a string for the name of this class. - * - * This is used to create a struct class pointer that can then be used - * in calls to device_create(). - * - * Returns &struct class pointer on success, or ERR_PTR() on error. - * - * Note, the pointer created here is to be destroyed when finished by - * making a call to class_destroy(). - */ -#define class_create(owner, name) \ -({ \ - static struct lock_class_key __key; \ - __class_create(owner, name, &__key); \ -}) +int __must_check class_interface_register(struct class_interface *); +void class_interface_unregister(struct class_interface *); +struct class * __must_check class_create(const char *name); +void class_destroy(const struct class *cls); #endif /* _DEVICE_CLASS_H_ */ diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index 50d0a416a5e7..c244267a6744 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -95,7 +95,7 @@ enum probe_type { */ struct device_driver { const char *name; - struct bus_type *bus; + const struct bus_type *bus; struct module *owner; const char *mod_name; /* used for built-in modules */ @@ -122,13 +122,12 @@ struct device_driver { }; -extern int __must_check driver_register(struct device_driver *drv); -extern void driver_unregister(struct device_driver *drv); +int __must_check driver_register(struct device_driver *drv); +void driver_unregister(struct device_driver *drv); -extern struct device_driver *driver_find(const char *name, - struct bus_type *bus); -extern int driver_probe_done(void); -extern void wait_for_device_probe(void); +struct device_driver *driver_find(const char *name, const struct bus_type *bus); +int driver_probe_done(void); +void wait_for_device_probe(void); void __init wait_for_init_devices_probe(void); /* sysfs interface for exporting driver attributes */ @@ -147,18 +146,15 @@ struct driver_attribute { #define DRIVER_ATTR_WO(_name) \ struct driver_attribute driver_attr_##_name = __ATTR_WO(_name) -extern int __must_check driver_create_file(struct device_driver *driver, - const struct driver_attribute *attr); -extern void driver_remove_file(struct device_driver *driver, - const struct driver_attribute *attr); +int __must_check driver_create_file(struct device_driver *driver, + const struct driver_attribute *attr); +void driver_remove_file(struct device_driver *driver, + const struct driver_attribute *attr); int driver_set_override(struct device *dev, const char **override, const char *s, size_t len); -extern int __must_check driver_for_each_device(struct device_driver *drv, - struct device *start, - void *data, - int (*fn)(struct device *dev, - void *)); +int __must_check driver_for_each_device(struct device_driver *drv, struct device *start, + void *data, int (*fn)(struct device *dev, void *)); struct device *driver_find_device(struct device_driver *drv, struct device *start, const void *data, int (*match)(struct device *dev, const void *data)); diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 41bf4bdb117a..31f114f486c4 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -269,6 +269,8 @@ static inline bool dev_is_dma_coherent(struct device *dev) return dev->dma_coherent; } #else +#define dma_default_coherent true + static inline bool dev_is_dma_coherent(struct device *dev) { return true; diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 41682278d2e8..061dd84d09f3 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -128,17 +128,16 @@ struct ddebug_class_param { const struct ddebug_class_map *map; }; -#if defined(CONFIG_DYNAMIC_DEBUG_CORE) - -int ddebug_add_module(struct _ddebug_info *dyndbg, const char *modname); +/* + * pr_debug() and friends are globally enabled or modules have selectively + * enabled them. + */ +#if defined(CONFIG_DYNAMIC_DEBUG) || \ + (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) -extern int ddebug_remove_module(const char *mod_name); extern __printf(2, 3) void __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...); -extern int ddebug_dyndbg_module_param_cb(char *param, char *val, - const char *modname); - struct device; extern __printf(3, 4) @@ -287,10 +286,6 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, KERN_DEBUG, prefix_str, prefix_type, \ rowsize, groupsize, buf, len, ascii) -struct kernel_param; -int param_set_dyndbg_classes(const char *instr, const struct kernel_param *kp); -int param_get_dyndbg_classes(char *buffer, const struct kernel_param *kp); - /* for test only, generally expect drm.debug style macro wrappers */ #define __pr_debug_cls(cls, fmt, ...) do { \ BUILD_BUG_ON_MSG(!__builtin_constant_p(cls), \ @@ -298,21 +293,38 @@ int param_get_dyndbg_classes(char *buffer, const struct kernel_param *kp); dynamic_pr_debug_cls(cls, fmt, ##__VA_ARGS__); \ } while (0) -#else /* !CONFIG_DYNAMIC_DEBUG_CORE */ +#else /* !(CONFIG_DYNAMIC_DEBUG || (CONFIG_DYNAMIC_DEBUG_CORE && DYNAMIC_DEBUG_MODULE)) */ #include <linux/string.h> #include <linux/errno.h> #include <linux/printk.h> -static inline int ddebug_add_module(struct _ddebug_info *dinfo, const char *modname) -{ - return 0; -} +#define DEFINE_DYNAMIC_DEBUG_METADATA(name, fmt) +#define DYNAMIC_DEBUG_BRANCH(descriptor) false -static inline int ddebug_remove_module(const char *mod) -{ - return 0; -} +#define dynamic_pr_debug(fmt, ...) \ + do { if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); } while (0) +#define dynamic_dev_dbg(dev, fmt, ...) \ + do { if (0) dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); } while (0) +#define dynamic_hex_dump(prefix_str, prefix_type, rowsize, \ + groupsize, buf, len, ascii) \ + do { if (0) \ + print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, \ + rowsize, groupsize, buf, len, ascii); \ + } while (0) + +#endif /* CONFIG_DYNAMIC_DEBUG || (CONFIG_DYNAMIC_DEBUG_CORE && DYNAMIC_DEBUG_MODULE) */ + + +#ifdef CONFIG_DYNAMIC_DEBUG_CORE + +extern int ddebug_dyndbg_module_param_cb(char *param, char *val, + const char *modname); +struct kernel_param; +int param_set_dyndbg_classes(const char *instr, const struct kernel_param *kp); +int param_get_dyndbg_classes(char *buffer, const struct kernel_param *kp); + +#else static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, const char *modname) @@ -326,25 +338,15 @@ static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, return -EINVAL; } -#define dynamic_pr_debug(fmt, ...) \ - do { if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); } while (0) -#define dynamic_dev_dbg(dev, fmt, ...) \ - do { if (0) dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); } while (0) -#define dynamic_hex_dump(prefix_str, prefix_type, rowsize, \ - groupsize, buf, len, ascii) \ - do { if (0) \ - print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, \ - rowsize, groupsize, buf, len, ascii); \ - } while (0) - struct kernel_param; static inline int param_set_dyndbg_classes(const char *instr, const struct kernel_param *kp) { return 0; } static inline int param_get_dyndbg_classes(char *buffer, const struct kernel_param *kp) { return 0; } -#endif /* !CONFIG_DYNAMIC_DEBUG_CORE */ +#endif + extern const struct kernel_param_ops param_ops_dyndbg_classes; -#endif +#endif /* _DYNAMIC_DEBUG_H */ diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 601700fedc91..9edb29101ec8 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -220,6 +220,7 @@ struct export_operations { #define EXPORT_OP_NOATOMIC_ATTR (0x10) /* Filesystem cannot supply atomic attribute updates */ +#define EXPORT_OP_FLUSH_ON_CLOSE (0x20) /* fs flushes file data on close */ unsigned long flags; }; diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h index cad828e21c72..29cd11d5a3cf 100644 --- a/include/linux/firmware/cirrus/cs_dsp.h +++ b/include/linux/firmware/cirrus/cs_dsp.h @@ -156,6 +156,7 @@ struct cs_dsp { unsigned int sysclk_reg; unsigned int sysclk_mask; unsigned int sysclk_shift; + bool no_core_startstop; struct list_head alg_regions; diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 0e4c70987e6a..f5da51677069 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -71,6 +71,10 @@ #define XILINX_ZYNQMP_PM_FPGA_FULL 0x0U #define XILINX_ZYNQMP_PM_FPGA_PARTIAL BIT(0) +/* FPGA Status Reg */ +#define XILINX_ZYNQMP_PM_FPGA_CONFIG_STAT_OFFSET 7U +#define XILINX_ZYNQMP_PM_FPGA_READ_CONFIG_REG 0U + /* * Node IDs for the Error Events. */ @@ -124,6 +128,7 @@ enum pm_api_id { PM_CLOCK_GETRATE = 42, PM_CLOCK_SETPARENT = 43, PM_CLOCK_GETPARENT = 44, + PM_FPGA_READ = 46, PM_SECURE_AES = 47, PM_FEATURE_CHECK = 63, }; @@ -519,6 +524,7 @@ int zynqmp_pm_aes_engine(const u64 address, u32 *out); int zynqmp_pm_sha_hash(const u64 address, const u32 size, const u32 flags); int zynqmp_pm_fpga_load(const u64 address, const u32 size, const u32 flags); int zynqmp_pm_fpga_get_status(u32 *value); +int zynqmp_pm_fpga_get_config_status(u32 *value); int zynqmp_pm_write_ggs(u32 index, u32 value); int zynqmp_pm_read_ggs(u32 index, u32 *value); int zynqmp_pm_write_pggs(u32 index, u32 value); @@ -725,6 +731,11 @@ static inline int zynqmp_pm_fpga_get_status(u32 *value) return -ENODEV; } +static inline int zynqmp_pm_fpga_get_config_status(u32 *value) +{ + return -ENODEV; +} + static inline int zynqmp_pm_write_ggs(u32 index, u32 value) { return -ENODEV; diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index 1c2bde0ead73..47fefc7f363b 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -13,6 +13,8 @@ * @nmissed: The counter for missing events. * @flags: The status flag. * @rethook: The rethook data structure. (internal data) + * @entry_data_size: The private data storage size. + * @nr_maxactive: The max number of active functions. * @entry_handler: The callback function for function entry. * @exit_handler: The callback function for function exit. */ @@ -29,9 +31,13 @@ struct fprobe { unsigned long nmissed; unsigned int flags; struct rethook *rethook; + size_t entry_data_size; + int nr_maxactive; - void (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs); - void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs); + int (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, + struct pt_regs *regs, void *entry_data); + void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip, + struct pt_regs *regs, void *entry_data); }; /* This fprobe is soft-disabled. */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 67495ef79bb2..21a981680856 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -343,6 +343,20 @@ enum rw_hint { /* can use bio alloc cache */ #define IOCB_ALLOC_CACHE (1 << 21) +/* for use in trace events */ +#define TRACE_IOCB_STRINGS \ + { IOCB_HIPRI, "HIPRI" }, \ + { IOCB_DSYNC, "DSYNC" }, \ + { IOCB_SYNC, "SYNC" }, \ + { IOCB_NOWAIT, "NOWAIT" }, \ + { IOCB_APPEND, "APPEND" }, \ + { IOCB_EVENTFD, "EVENTFD"}, \ + { IOCB_DIRECT, "DIRECT" }, \ + { IOCB_WRITE, "WRITE" }, \ + { IOCB_WAITQ, "WAITQ" }, \ + { IOCB_NOIO, "NOIO" }, \ + { IOCB_ALLOC_CACHE, "ALLOC_CACHE" } + struct kiocb { struct file *ki_filp; loff_t ki_pos; diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 3e56cb6f40d1..6954e4ed5bbf 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -548,6 +548,7 @@ bool is_ftrace_trampoline(unsigned long addr); * DIRECT - there is a direct function to call * CALL_OPS - the record can use callsite-specific ops * CALL_OPS_EN - the function is set up to use callsite-specific ops + * TOUCHED - A callback was added since boot up * * When a new ftrace_ops is registered and wants a function to save * pt_regs, the rec->flags REGS is set. When the function has been @@ -567,9 +568,10 @@ enum { FTRACE_FL_DIRECT_EN = (1UL << 23), FTRACE_FL_CALL_OPS = (1UL << 22), FTRACE_FL_CALL_OPS_EN = (1UL << 21), + FTRACE_FL_TOUCHED = (1UL << 20), }; -#define FTRACE_REF_MAX_SHIFT 21 +#define FTRACE_REF_MAX_SHIFT 20 #define FTRACE_REF_MAX ((1UL << FTRACE_REF_MAX_SHIFT) - 1) #define ftrace_rec_count(rec) ((rec)->flags & FTRACE_REF_MAX) @@ -628,6 +630,7 @@ enum { FTRACE_ITER_PROBE = (1 << 4), FTRACE_ITER_MOD = (1 << 5), FTRACE_ITER_ENABLED = (1 << 6), + FTRACE_ITER_TOUCHED = (1 << 7), }; void arch_ftrace_update_code(int command); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 65a78773dcca..ed8cb537c6a7 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -319,7 +319,7 @@ extern void page_frag_free(void *addr); #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) -void page_alloc_init(void); +void page_alloc_init_cpuhp(void); void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp); void drain_all_pages(struct zone *zone); void drain_local_pages(struct zone *zone); @@ -361,9 +361,4 @@ extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, #endif void free_contig_range(unsigned long pfn, unsigned long nr_pages); -#ifdef CONFIG_CMA -/* CMA stuff */ -extern void init_cma_reserved_pageblock(struct page *page); -#endif - #endif /* __LINUX_GFP_H */ diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index 5088637fe5c2..6583a58670c5 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -47,16 +47,14 @@ typedef unsigned int __bitwise gfp_t; #define ___GFP_ACCOUNT 0x400000u #define ___GFP_ZEROTAGS 0x800000u #ifdef CONFIG_KASAN_HW_TAGS -#define ___GFP_SKIP_ZERO 0x1000000u -#define ___GFP_SKIP_KASAN_UNPOISON 0x2000000u -#define ___GFP_SKIP_KASAN_POISON 0x4000000u +#define ___GFP_SKIP_ZERO 0x1000000u +#define ___GFP_SKIP_KASAN 0x2000000u #else -#define ___GFP_SKIP_ZERO 0 -#define ___GFP_SKIP_KASAN_UNPOISON 0 -#define ___GFP_SKIP_KASAN_POISON 0 +#define ___GFP_SKIP_ZERO 0 +#define ___GFP_SKIP_KASAN 0 #endif #ifdef CONFIG_LOCKDEP -#define ___GFP_NOLOCKDEP 0x8000000u +#define ___GFP_NOLOCKDEP 0x4000000u #else #define ___GFP_NOLOCKDEP 0 #endif @@ -234,25 +232,24 @@ typedef unsigned int __bitwise gfp_t; * memory tags at the same time as zeroing memory has minimal additional * performace impact. * - * %__GFP_SKIP_KASAN_UNPOISON makes KASAN skip unpoisoning on page allocation. - * Only effective in HW_TAGS mode. - * - * %__GFP_SKIP_KASAN_POISON makes KASAN skip poisoning on page deallocation. - * Typically, used for userspace pages. Only effective in HW_TAGS mode. + * %__GFP_SKIP_KASAN makes KASAN skip unpoisoning on page allocation. + * Used for userspace and vmalloc pages; the latter are unpoisoned by + * kasan_unpoison_vmalloc instead. For userspace pages, results in + * poisoning being skipped as well, see should_skip_kasan_poison for + * details. Only effective in HW_TAGS mode. */ #define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) #define __GFP_COMP ((__force gfp_t)___GFP_COMP) #define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) #define __GFP_ZEROTAGS ((__force gfp_t)___GFP_ZEROTAGS) #define __GFP_SKIP_ZERO ((__force gfp_t)___GFP_SKIP_ZERO) -#define __GFP_SKIP_KASAN_UNPOISON ((__force gfp_t)___GFP_SKIP_KASAN_UNPOISON) -#define __GFP_SKIP_KASAN_POISON ((__force gfp_t)___GFP_SKIP_KASAN_POISON) +#define __GFP_SKIP_KASAN ((__force gfp_t)___GFP_SKIP_KASAN) /* Disable lockdep for GFP context tracking */ #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) /* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT (27 + IS_ENABLED(CONFIG_LOCKDEP)) +#define __GFP_BITS_SHIFT (26 + IS_ENABLED(CONFIG_LOCKDEP)) #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) /** @@ -335,8 +332,7 @@ typedef unsigned int __bitwise gfp_t; #define GFP_DMA __GFP_DMA #define GFP_DMA32 __GFP_DMA32 #define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM) -#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE | \ - __GFP_SKIP_KASAN_POISON | __GFP_SKIP_KASAN_UNPOISON) +#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE | __GFP_SKIP_KASAN) #define GFP_TRANSHUGE_LIGHT ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM) #define GFP_TRANSHUGE (GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM) diff --git a/include/linux/hex.h b/include/linux/hex.h new file mode 100644 index 000000000000..2618382e5b0c --- /dev/null +++ b/include/linux/hex.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_HEX_H +#define _LINUX_HEX_H + +#include <linux/types.h> + +extern const char hex_asc[]; +#define hex_asc_lo(x) hex_asc[((x) & 0x0f)] +#define hex_asc_hi(x) hex_asc[((x) & 0xf0) >> 4] + +static inline char *hex_byte_pack(char *buf, u8 byte) +{ + *buf++ = hex_asc_hi(byte); + *buf++ = hex_asc_lo(byte); + return buf; +} + +extern const char hex_asc_upper[]; +#define hex_asc_upper_lo(x) hex_asc_upper[((x) & 0x0f)] +#define hex_asc_upper_hi(x) hex_asc_upper[((x) & 0xf0) >> 4] + +static inline char *hex_byte_pack_upper(char *buf, u8 byte) +{ + *buf++ = hex_asc_upper_hi(byte); + *buf++ = hex_asc_upper_lo(byte); + return buf; +} + +extern int hex_to_bin(unsigned char ch); +extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); +extern char *bin2hex(char *dst, const void *src, size_t count); + +bool mac_pton(const char *s, u8 *mac); + +#endif diff --git a/include/linux/hid.h b/include/linux/hid.h index 1ea8c7a3570b..4e4c4fe36911 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -156,6 +156,7 @@ struct hid_item { #define HID_UP_DIGITIZER 0x000d0000 #define HID_UP_PID 0x000f0000 #define HID_UP_BATTERY 0x00850000 +#define HID_UP_CAMERA 0x00900000 #define HID_UP_HPVENDOR 0xff7f0000 #define HID_UP_HPVENDOR2 0xff010000 #define HID_UP_MSVENDOR 0xff000000 @@ -873,7 +874,7 @@ extern bool hid_is_usb(const struct hid_device *hdev); /* We ignore a few input applications that are not widely used */ #define IS_INPUT_APPLICATION(a) \ (((a >= HID_UP_GENDESK) && (a <= HID_GD_MULTIAXIS)) \ - || ((a >= HID_DG_PEN) && (a <= HID_DG_WHITEBOARD)) \ + || ((a >= HID_DG_DIGITIZER) && (a <= HID_DG_WHITEBOARD)) \ || (a == HID_GD_SYSTEM_CONTROL) || (a == HID_CP_CONSUMER_CONTROL) \ || (a == HID_GD_WIRELESS_RADIO_CTLS)) diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 8fc10089e19e..4de1dbcd3ef6 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -243,12 +243,10 @@ static inline void clear_highpage(struct page *page) static inline void clear_highpage_kasan_tagged(struct page *page) { - u8 tag; + void *kaddr = kmap_local_page(page); - tag = page_kasan_tag(page); - page_kasan_tag_reset(page); - clear_highpage(page); - page_kasan_tag_set(page, tag); + clear_page(kasan_reset_tag(kaddr)); + kunmap_local(kaddr); } #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE @@ -317,7 +315,29 @@ static inline void copy_user_highpage(struct page *to, struct page *from, #endif +#ifndef __HAVE_ARCH_COPY_HIGHPAGE + +static inline void copy_highpage(struct page *to, struct page *from) +{ + char *vfrom, *vto; + + vfrom = kmap_local_page(from); + vto = kmap_local_page(to); + copy_page(vto, vfrom); + kmsan_copy_page_meta(to, from); + kunmap_local(vto); + kunmap_local(vfrom); +} + +#endif + #ifdef copy_mc_to_kernel +/* + * If architecture supports machine check exception handling, define the + * #MC versions of copy_user_highpage and copy_highpage. They copy a memory + * page with #MC in source page (@from) handled, and return the number + * of bytes not copied if there was a #MC, otherwise 0 for success. + */ static inline int copy_mc_user_highpage(struct page *to, struct page *from, unsigned long vaddr, struct vm_area_struct *vma) { @@ -334,29 +354,35 @@ static inline int copy_mc_user_highpage(struct page *to, struct page *from, return ret; } -#else -static inline int copy_mc_user_highpage(struct page *to, struct page *from, - unsigned long vaddr, struct vm_area_struct *vma) -{ - copy_user_highpage(to, from, vaddr, vma); - return 0; -} -#endif - -#ifndef __HAVE_ARCH_COPY_HIGHPAGE -static inline void copy_highpage(struct page *to, struct page *from) +static inline int copy_mc_highpage(struct page *to, struct page *from) { + unsigned long ret; char *vfrom, *vto; vfrom = kmap_local_page(from); vto = kmap_local_page(to); - copy_page(vto, vfrom); - kmsan_copy_page_meta(to, from); + ret = copy_mc_to_kernel(vto, vfrom, PAGE_SIZE); + if (!ret) + kmsan_copy_page_meta(to, from); kunmap_local(vto); kunmap_local(vfrom); + + return ret; +} +#else +static inline int copy_mc_user_highpage(struct page *to, struct page *from, + unsigned long vaddr, struct vm_area_struct *vma) +{ + copy_user_highpage(to, from, vaddr, vma); + return 0; } +static inline int copy_mc_highpage(struct page *to, struct page *from) +{ + copy_highpage(to, from); + return 0; +} #endif static inline void memcpy_page(struct page *dst_page, size_t dst_off, diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 70bd867eba94..20284387b841 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -39,47 +39,12 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, unsigned long cp_flags); -vm_fault_t vmf_insert_pfn_pmd_prot(struct vm_fault *vmf, pfn_t pfn, - pgprot_t pgprot, bool write); -/** - * vmf_insert_pfn_pmd - insert a pmd size pfn - * @vmf: Structure describing the fault - * @pfn: pfn to insert - * @pgprot: page protection to use - * @write: whether it's a write fault - * - * Insert a pmd size pfn. See vmf_insert_pfn() for additional info. - * - * Return: vm_fault_t value. - */ -static inline vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, - bool write) -{ - return vmf_insert_pfn_pmd_prot(vmf, pfn, vmf->vma->vm_page_prot, write); -} -vm_fault_t vmf_insert_pfn_pud_prot(struct vm_fault *vmf, pfn_t pfn, - pgprot_t pgprot, bool write); - -/** - * vmf_insert_pfn_pud - insert a pud size pfn - * @vmf: Structure describing the fault - * @pfn: pfn to insert - * @pgprot: page protection to use - * @write: whether it's a write fault - * - * Insert a pud size pfn. See vmf_insert_pfn() for additional info. - * - * Return: vm_fault_t value. - */ -static inline vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, - bool write) -{ - return vmf_insert_pfn_pud_prot(vmf, pfn, vmf->vma->vm_page_prot, write); -} +vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write); +vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write); enum transparent_hugepage_flag { - TRANSPARENT_HUGEPAGE_NEVER_DAX, + TRANSPARENT_HUGEPAGE_UNSUPPORTED, TRANSPARENT_HUGEPAGE_FLAG, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 7c977d234aba..6d041aa9f0fe 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -124,14 +124,6 @@ void hugepage_put_subpool(struct hugepage_subpool *spool); void hugetlb_dup_vma_private(struct vm_area_struct *vma); void clear_vma_resv_huge_pages(struct vm_area_struct *vma); -int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); -int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *, - loff_t *); -int hugetlb_treat_movable_handler(struct ctl_table *, int, void *, size_t *, - loff_t *); -int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, void *, size_t *, - loff_t *); - int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, @@ -158,13 +150,12 @@ unsigned long hugetlb_total_pages(void); vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); #ifdef CONFIG_USERFAULTFD -int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, pte_t *dst_pte, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, - unsigned long src_addr, - enum mcopy_atomic_mode mode, - struct page **pagep, - bool wp_copy); +int hugetlb_mfill_atomic_pte(pte_t *dst_pte, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + uffd_flags_t flags, + struct folio **foliop); #endif /* CONFIG_USERFAULTFD */ bool hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, @@ -192,6 +183,23 @@ extern struct list_head huge_boot_pages; /* arch callbacks */ +#ifndef CONFIG_HIGHPTE +/* + * pte_offset_huge() and pte_alloc_huge() are helpers for those architectures + * which may go down to the lowest PTE level in their huge_pte_offset() and + * huge_pte_alloc(): to avoid reliance on pte_offset_map() without pte_unmap(). + */ +static inline pte_t *pte_offset_huge(pmd_t *pmd, unsigned long address) +{ + return pte_offset_kernel(pmd, address); +} +static inline pte_t *pte_alloc_huge(struct mm_struct *mm, pmd_t *pmd, + unsigned long address) +{ + return pte_alloc(mm, pmd) ? NULL : pte_offset_huge(pmd, address); +} +#endif + pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz); /* @@ -393,14 +401,12 @@ static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, } #ifdef CONFIG_USERFAULTFD -static inline int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, - pte_t *dst_pte, - struct vm_area_struct *dst_vma, - unsigned long dst_addr, - unsigned long src_addr, - enum mcopy_atomic_mode mode, - struct page **pagep, - bool wp_copy) +static inline int hugetlb_mfill_atomic_pte(pte_t *dst_pte, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, + unsigned long src_addr, + uffd_flags_t flags, + struct folio **foliop) { BUG(); return 0; @@ -818,7 +824,7 @@ static inline unsigned huge_page_shift(struct hstate *h) static inline bool hstate_is_gigantic(struct hstate *h) { - return huge_page_order(h) >= MAX_ORDER; + return huge_page_order(h) > MAX_ORDER; } static inline unsigned int pages_per_huge_page(const struct hstate *h) diff --git a/include/linux/iio/iio-gts-helper.h b/include/linux/iio/iio-gts-helper.h new file mode 100644 index 000000000000..dd64e544a3da --- /dev/null +++ b/include/linux/iio/iio-gts-helper.h @@ -0,0 +1,206 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* gain-time-scale conversion helpers for IIO light sensors + * + * Copyright (c) 2023 Matti Vaittinen <mazziesaccount@gmail.com> + */ + +#ifndef __IIO_GTS_HELPER__ +#define __IIO_GTS_HELPER__ + +#include <linux/types.h> + +struct device; + +/** + * struct iio_gain_sel_pair - gain - selector values + * + * In many cases devices like light sensors allow setting signal amplification + * (gain) using a register interface. This structure describes amplification + * and corresponding selector (register value) + * + * @gain: Gain (multiplication) value. Gain must be positive, negative + * values are reserved for error handling. + * @sel: Selector (usually register value) used to indicate this gain. + * NOTE: Only selectors >= 0 supported. + */ +struct iio_gain_sel_pair { + int gain; + int sel; +}; + +/** + * struct iio_itime_sel_mul - integration time description + * + * In many cases devices like light sensors allow setting the duration of + * collecting data. Typically this duration has also an impact to the magnitude + * of measured values (gain). This structure describes the relation of + * integration time and amplification as well as corresponding selector + * (register value). + * + * An example could be a sensor allowing 50, 100, 200 and 400 mS times. The + * respective multiplication values could be 50 mS => 1, 100 mS => 2, + * 200 mS => 4 and 400 mS => 8 assuming the impact of integration time would be + * linear in a way that when collecting data for 50 mS caused value X, doubling + * the data collection time caused value 2X etc. + * + * @time_us: Integration time in microseconds. Time values must be positive, + * negative values are reserved for error handling. + * @sel: Selector (usually register value) used to indicate this time + * NOTE: Only selectors >= 0 supported. + * @mul: Multiplication to the values caused by this time. + * NOTE: Only multipliers > 0 supported. + */ +struct iio_itime_sel_mul { + int time_us; + int sel; + int mul; +}; + +struct iio_gts { + u64 max_scale; + const struct iio_gain_sel_pair *hwgain_table; + int num_hwgain; + const struct iio_itime_sel_mul *itime_table; + int num_itime; + int **per_time_avail_scale_tables; + int *avail_all_scales_table; + int num_avail_all_scales; + int *avail_time_tables; + int num_avail_time_tables; +}; + +#define GAIN_SCALE_GAIN(_gain, _sel) \ +{ \ + .gain = (_gain), \ + .sel = (_sel), \ +} + +#define GAIN_SCALE_ITIME_US(_itime, _sel, _mul) \ +{ \ + .time_us = (_itime), \ + .sel = (_sel), \ + .mul = (_mul), \ +} + +static inline const struct iio_itime_sel_mul * +iio_gts_find_itime_by_time(struct iio_gts *gts, int time) +{ + int i; + + if (!gts->num_itime) + return NULL; + + for (i = 0; i < gts->num_itime; i++) + if (gts->itime_table[i].time_us == time) + return >s->itime_table[i]; + + return NULL; +} + +static inline const struct iio_itime_sel_mul * +iio_gts_find_itime_by_sel(struct iio_gts *gts, int sel) +{ + int i; + + for (i = 0; i < gts->num_itime; i++) + if (gts->itime_table[i].sel == sel) + return >s->itime_table[i]; + + return NULL; +} + +int devm_iio_init_iio_gts(struct device *dev, int max_scale_int, int max_scale_nano, + const struct iio_gain_sel_pair *gain_tbl, int num_gain, + const struct iio_itime_sel_mul *tim_tbl, int num_times, + struct iio_gts *gts); +/** + * iio_gts_find_int_time_by_sel - find integration time matching a selector + * @gts: Gain time scale descriptor + * @sel: selector for which matching integration time is searched for + * + * Return: integration time matching given selector or -EINVAL if + * integration time was not found. + */ +static inline int iio_gts_find_int_time_by_sel(struct iio_gts *gts, int sel) +{ + const struct iio_itime_sel_mul *itime; + + itime = iio_gts_find_itime_by_sel(gts, sel); + if (!itime) + return -EINVAL; + + return itime->time_us; +} + +/** + * iio_gts_find_sel_by_int_time - find selector matching integration time + * @gts: Gain time scale descriptor + * @gain: HW-gain for which matching selector is searched for + * + * Return: a selector matching given integration time or -EINVAL if + * selector was not found. + */ +static inline int iio_gts_find_sel_by_int_time(struct iio_gts *gts, int time) +{ + const struct iio_itime_sel_mul *itime; + + itime = iio_gts_find_itime_by_time(gts, time); + if (!itime) + return -EINVAL; + + return itime->sel; +} + +/** + * iio_gts_valid_time - check if given integration time is valid + * @gts: Gain time scale descriptor + * @time_us: Integration time to check + * + * Return: True if given time is supported by device. False if not. + */ +static inline bool iio_gts_valid_time(struct iio_gts *gts, int time_us) +{ + return iio_gts_find_itime_by_time(gts, time_us) != NULL; +} + +int iio_gts_find_sel_by_gain(struct iio_gts *gts, int gain); + +/** + * iio_gts_valid_gain - check if given HW-gain is valid + * @gts: Gain time scale descriptor + * @gain: HW-gain to check + * + * Return: True if given time is supported by device. False if not. + */ +static inline bool iio_gts_valid_gain(struct iio_gts *gts, int gain) +{ + return iio_gts_find_sel_by_gain(gts, gain) >= 0; +} + +int iio_find_closest_gain_low(struct iio_gts *gts, int gain, bool *in_range); +int iio_gts_find_gain_by_sel(struct iio_gts *gts, int sel); +int iio_gts_get_min_gain(struct iio_gts *gts); +int iio_gts_find_int_time_by_sel(struct iio_gts *gts, int sel); +int iio_gts_find_sel_by_int_time(struct iio_gts *gts, int time); + +int iio_gts_total_gain_to_scale(struct iio_gts *gts, int total_gain, + int *scale_int, int *scale_nano); +int iio_gts_find_gain_sel_for_scale_using_time(struct iio_gts *gts, int time_sel, + int scale_int, int scale_nano, + int *gain_sel); +int iio_gts_get_scale(struct iio_gts *gts, int gain, int time, int *scale_int, + int *scale_nano); +int iio_gts_find_new_gain_sel_by_old_gain_time(struct iio_gts *gts, + int old_gain, int old_time_sel, + int new_time_sel, int *new_gain); +int iio_gts_find_new_gain_by_old_gain_time(struct iio_gts *gts, int old_gain, + int old_time, int new_time, + int *new_gain); +int iio_gts_avail_times(struct iio_gts *gts, const int **vals, int *type, + int *length); +int iio_gts_all_avail_scales(struct iio_gts *gts, const int **vals, int *type, + int *length); +int iio_gts_avail_scales_for_time(struct iio_gts *gts, int time, + const int **vals, int *type, int *length); + +#endif diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index f6360d9a492d..51f52c5c6092 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -151,14 +151,8 @@ void iio_trigger_unregister(struct iio_trigger *trig_info); **/ int iio_trigger_set_immutable(struct iio_dev *indio_dev, struct iio_trigger *trig); -/** - * iio_trigger_poll() - called on a trigger occurring - * @trig: trigger which occurred - * - * Typically called in relevant hardware interrupt handler. - **/ void iio_trigger_poll(struct iio_trigger *trig); -void iio_trigger_poll_chained(struct iio_trigger *trig); +void iio_trigger_poll_nested(struct iio_trigger *trig); irqreturn_t iio_trigger_generic_data_rdy_poll(int irq, void *private); diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index d12cd18aab3f..e6d8aca6886d 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -118,15 +118,12 @@ int icc_std_aggregate(struct icc_node *node, u32 tag, u32 avg_bw, struct icc_node *icc_node_create(int id); void icc_node_destroy(int id); int icc_link_create(struct icc_node *node, const int dst_id); -int icc_link_destroy(struct icc_node *src, struct icc_node *dst); void icc_node_add(struct icc_node *node, struct icc_provider *provider); void icc_node_del(struct icc_node *node); int icc_nodes_remove(struct icc_provider *provider); void icc_provider_init(struct icc_provider *provider); int icc_provider_register(struct icc_provider *provider); void icc_provider_deregister(struct icc_provider *provider); -int icc_provider_add(struct icc_provider *provider); -void icc_provider_del(struct icc_provider *provider); struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec); void icc_sync_state(struct device *dev); @@ -152,11 +149,6 @@ static inline int icc_link_create(struct icc_node *node, const int dst_id) return -ENOTSUPP; } -static inline int icc_link_destroy(struct icc_node *src, struct icc_node *dst) -{ - return -ENOTSUPP; -} - static inline void icc_node_add(struct icc_node *node, struct icc_provider *provider) { } @@ -179,15 +171,6 @@ static inline int icc_provider_register(struct icc_provider *provider) static inline void icc_provider_deregister(struct icc_provider *provider) { } -static inline int icc_provider_add(struct icc_provider *provider) -{ - return -ENOTSUPP; -} - -static inline void icc_provider_del(struct icc_provider *provider) -{ -} - static inline struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec) { return ERR_PTR(-ENOTSUPP); diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 09d4f17c8d3b..7376c1df9c90 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -69,7 +69,10 @@ io_mapping_map_atomic_wc(struct io_mapping *mapping, BUG_ON(offset >= mapping->size); phys_addr = mapping->base + offset; - preempt_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); + else + migrate_disable(); pagefault_disable(); return __iomap_local_pfn_prot(PHYS_PFN(phys_addr), mapping->prot); } @@ -79,7 +82,10 @@ io_mapping_unmap_atomic(void __iomem *vaddr) { kunmap_local_indexed((void __force *)vaddr); pagefault_enable(); - preempt_enable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); + else + migrate_enable(); } static inline void __iomem * @@ -162,7 +168,10 @@ static inline void __iomem * io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset) { - preempt_disable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); + else + migrate_disable(); pagefault_disable(); return io_mapping_map_wc(mapping, offset, PAGE_SIZE); } @@ -172,7 +181,10 @@ io_mapping_unmap_atomic(void __iomem *vaddr) { io_mapping_unmap(vaddr); pagefault_enable(); - preempt_enable(); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); + else + migrate_enable(); } static inline void __iomem * diff --git a/include/linux/ioasid.h b/include/linux/ioasid.h deleted file mode 100644 index af1c9d62e642..000000000000 --- a/include/linux/ioasid.h +++ /dev/null @@ -1,83 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_IOASID_H -#define __LINUX_IOASID_H - -#include <linux/types.h> -#include <linux/errno.h> - -#define INVALID_IOASID ((ioasid_t)-1) -typedef unsigned int ioasid_t; -typedef ioasid_t (*ioasid_alloc_fn_t)(ioasid_t min, ioasid_t max, void *data); -typedef void (*ioasid_free_fn_t)(ioasid_t ioasid, void *data); - -struct ioasid_set { - int dummy; -}; - -/** - * struct ioasid_allocator_ops - IOASID allocator helper functions and data - * - * @alloc: helper function to allocate IOASID - * @free: helper function to free IOASID - * @list: for tracking ops that share helper functions but not data - * @pdata: data belong to the allocator, provided when calling alloc() - */ -struct ioasid_allocator_ops { - ioasid_alloc_fn_t alloc; - ioasid_free_fn_t free; - struct list_head list; - void *pdata; -}; - -#define DECLARE_IOASID_SET(name) struct ioasid_set name = { 0 } - -#if IS_ENABLED(CONFIG_IOASID) -ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, ioasid_t max, - void *private); -void ioasid_free(ioasid_t ioasid); -void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, - bool (*getter)(void *)); -int ioasid_register_allocator(struct ioasid_allocator_ops *allocator); -void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator); -int ioasid_set_data(ioasid_t ioasid, void *data); -static inline bool pasid_valid(ioasid_t ioasid) -{ - return ioasid != INVALID_IOASID; -} - -#else /* !CONFIG_IOASID */ -static inline ioasid_t ioasid_alloc(struct ioasid_set *set, ioasid_t min, - ioasid_t max, void *private) -{ - return INVALID_IOASID; -} - -static inline void ioasid_free(ioasid_t ioasid) { } - -static inline void *ioasid_find(struct ioasid_set *set, ioasid_t ioasid, - bool (*getter)(void *)) -{ - return NULL; -} - -static inline int ioasid_register_allocator(struct ioasid_allocator_ops *allocator) -{ - return -ENOTSUPP; -} - -static inline void ioasid_unregister_allocator(struct ioasid_allocator_ops *allocator) -{ -} - -static inline int ioasid_set_data(ioasid_t ioasid, void *data) -{ - return -ENOTSUPP; -} - -static inline bool pasid_valid(ioasid_t ioasid) -{ - return false; -} - -#endif /* CONFIG_IOASID */ -#endif /* __LINUX_IOASID_H */ diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 0f8123504e5e..e2b836c2e119 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -377,12 +377,6 @@ struct iomap_dio_ops { */ #define IOMAP_DIO_PARTIAL (1 << 2) -/* - * The caller will sync the write if needed; do not sync it within - * iomap_dio_rw. Overrides IOMAP_DIO_FORCE_WAIT. - */ -#define IOMAP_DIO_NOSYNC (1 << 3) - ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, unsigned int dio_flags, void *private, size_t done_before); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 6595454d4f48..e8c9a7da1060 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -13,7 +13,6 @@ #include <linux/errno.h> #include <linux/err.h> #include <linux/of.h> -#include <linux/ioasid.h> #include <uapi/linux/iommu.h> #define IOMMU_READ (1 << 0) @@ -192,6 +191,7 @@ enum iommu_dev_features { }; #define IOMMU_PASID_INVALID (-1U) +typedef unsigned int ioasid_t; #ifdef CONFIG_IOMMU_API @@ -455,12 +455,11 @@ static inline const struct iommu_ops *dev_iommu_ops(struct device *dev) return dev->iommu->iommu_dev->ops; } -extern int bus_iommu_probe(struct bus_type *bus); -extern bool iommu_present(struct bus_type *bus); +extern int bus_iommu_probe(const struct bus_type *bus); +extern bool iommu_present(const struct bus_type *bus); extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap); extern bool iommu_group_has_isolated_msi(struct iommu_group *group); -extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus); -extern struct iommu_group *iommu_group_get_by_id(int id); +extern struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus); extern void iommu_domain_free(struct iommu_domain *domain); extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); @@ -699,7 +698,6 @@ static inline void dev_iommu_priv_set(struct device *dev, void *priv) } int iommu_probe_device(struct device *dev); -void iommu_release_device(struct device *dev); int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f); int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features f); @@ -732,7 +730,7 @@ struct iommu_device {}; struct iommu_fault_param {}; struct iommu_iotlb_gather {}; -static inline bool iommu_present(struct bus_type *bus) +static inline bool iommu_present(const struct bus_type *bus) { return false; } @@ -742,12 +740,7 @@ static inline bool device_iommu_capable(struct device *dev, enum iommu_cap cap) return false; } -static inline struct iommu_domain *iommu_domain_alloc(struct bus_type *bus) -{ - return NULL; -} - -static inline struct iommu_group *iommu_group_get_by_id(int id) +static inline struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus) { return NULL; } @@ -1173,6 +1166,15 @@ static inline bool tegra_dev_iommu_get_stream_id(struct device *dev, u32 *stream } #ifdef CONFIG_IOMMU_SVA +static inline void mm_pasid_init(struct mm_struct *mm) +{ + mm->pasid = IOMMU_PASID_INVALID; +} +static inline bool mm_valid_pasid(struct mm_struct *mm) +{ + return mm->pasid != IOMMU_PASID_INVALID; +} +void mm_pasid_drop(struct mm_struct *mm); struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm); void iommu_sva_unbind_device(struct iommu_sva *handle); @@ -1192,6 +1194,9 @@ static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle) { return IOMMU_PASID_INVALID; } +static inline void mm_pasid_init(struct mm_struct *mm) {} +static inline bool mm_valid_pasid(struct mm_struct *mm) { return false; } +static inline void mm_pasid_drop(struct mm_struct *mm) {} #endif /* CONFIG_IOMMU_SVA */ #endif /* __LINUX_IOMMU_H */ diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index c0b5b3ac34f1..1129a36a74c4 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -40,9 +40,10 @@ enum { }; struct iommufd_access * -iommufd_access_create(struct iommufd_ctx *ictx, u32 ioas_id, - const struct iommufd_access_ops *ops, void *data); +iommufd_access_create(struct iommufd_ctx *ictx, + const struct iommufd_access_ops *ops, void *data, u32 *id); void iommufd_access_destroy(struct iommufd_access *access); +int iommufd_access_attach(struct iommufd_access *access, u32 ioas_id); void iommufd_ctx_get(struct iommufd_ctx *ictx); diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 0065209cc004..fe3c9993b5bf 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -67,8 +67,7 @@ static inline void *dereference_symbol_descriptor(void *ptr) #ifdef CONFIG_KALLSYMS unsigned long kallsyms_sym_address(int idx); -int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, - unsigned long), +int kallsyms_on_each_symbol(int (*fn)(void *, const char *, unsigned long), void *data); int kallsyms_on_each_match_symbol(int (*fn)(void *, unsigned long), const char *name, void *data); @@ -166,8 +165,8 @@ static inline bool kallsyms_show_value(const struct cred *cred) return false; } -static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *, - unsigned long), void *data) +static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, unsigned long), + void *data) { return -EOPNOTSUPP; } diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 40bce7495af8..0d91e0af0125 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -20,6 +20,7 @@ #include <linux/compiler.h> #include <linux/container_of.h> #include <linux/bitops.h> +#include <linux/hex.h> #include <linux/kstrtox.h> #include <linux/log2.h> #include <linux/math.h> @@ -263,34 +264,6 @@ extern enum system_states { SYSTEM_SUSPEND, } system_state; -extern const char hex_asc[]; -#define hex_asc_lo(x) hex_asc[((x) & 0x0f)] -#define hex_asc_hi(x) hex_asc[((x) & 0xf0) >> 4] - -static inline char *hex_byte_pack(char *buf, u8 byte) -{ - *buf++ = hex_asc_hi(byte); - *buf++ = hex_asc_lo(byte); - return buf; -} - -extern const char hex_asc_upper[]; -#define hex_asc_upper_lo(x) hex_asc_upper[((x) & 0x0f)] -#define hex_asc_upper_hi(x) hex_asc_upper[((x) & 0xf0) >> 4] - -static inline char *hex_byte_pack_upper(char *buf, u8 byte) -{ - *buf++ = hex_asc_upper_hi(byte); - *buf++ = hex_asc_upper_lo(byte); - return buf; -} - -extern int hex_to_bin(unsigned char ch); -extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); -extern char *bin2hex(char *dst, const void *src, size_t count); - -bool mac_pton(const char *s, u8 *mac); - /* * General tracing related utility functions - trace_printk(), * tracing_on/tracing_off and tracing_start()/tracing_stop diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 6883c5922701..22b5cd24f581 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -190,7 +190,6 @@ int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name, void *buf, unsigned int size, bool get_value); void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name); -void *kexec_image_load_default(struct kimage *image); #ifndef arch_kexec_kernel_image_probe static inline int @@ -207,13 +206,6 @@ static inline int arch_kimage_file_post_load_cleanup(struct kimage *image) } #endif -#ifndef arch_kexec_kernel_image_load -static inline void *arch_kexec_kernel_image_load(struct kimage *image) -{ - return kexec_image_load_default(image); -} -#endif - #ifdef CONFIG_KEXEC_SIG #ifdef CONFIG_SIGNED_PE_FILE_VERIFICATION int kexec_kernel_verify_pe_sig(const char *kernel, unsigned long kernel_len); diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h index 30b17647ce3c..e0c23a32cdf0 100644 --- a/include/linux/kmsan.h +++ b/include/linux/kmsan.h @@ -54,7 +54,8 @@ void __init kmsan_init_runtime(void); * Freed pages are either returned to buddy allocator or held back to be used * as metadata pages. */ -bool __init kmsan_memblock_free_pages(struct page *page, unsigned int order); +bool __init __must_check kmsan_memblock_free_pages(struct page *page, + unsigned int order); /** * kmsan_alloc_page() - Notify KMSAN about an alloc_pages() call. @@ -137,9 +138,11 @@ void kmsan_kfree_large(const void *ptr); * vmalloc metadata address range. Returns 0 on success, callers must check * for non-zero return value. */ -int kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end, - pgprot_t prot, struct page **pages, - unsigned int page_shift); +int __must_check kmsan_vmap_pages_range_noflush(unsigned long start, + unsigned long end, + pgprot_t prot, + struct page **pages, + unsigned int page_shift); /** * kmsan_vunmap_kernel_range_noflush() - Notify KMSAN about a vunmap. @@ -163,9 +166,9 @@ void kmsan_vunmap_range_noflush(unsigned long start, unsigned long end); * virtual memory. Returns 0 on success, callers must check for non-zero return * value. */ -int kmsan_ioremap_page_range(unsigned long addr, unsigned long end, - phys_addr_t phys_addr, pgprot_t prot, - unsigned int page_shift); +int __must_check kmsan_ioremap_page_range(unsigned long addr, unsigned long end, + phys_addr_t phys_addr, pgprot_t prot, + unsigned int page_shift); /** * kmsan_iounmap_page_range() - Notify KMSAN about a iounmap_page_range() call. @@ -237,8 +240,8 @@ static inline void kmsan_init_runtime(void) { } -static inline bool kmsan_memblock_free_pages(struct page *page, - unsigned int order) +static inline bool __must_check kmsan_memblock_free_pages(struct page *page, + unsigned int order) { return true; } @@ -251,10 +254,9 @@ static inline void kmsan_task_exit(struct task_struct *task) { } -static inline int kmsan_alloc_page(struct page *page, unsigned int order, - gfp_t flags) +static inline void kmsan_alloc_page(struct page *page, unsigned int order, + gfp_t flags) { - return 0; } static inline void kmsan_free_page(struct page *page, unsigned int order) @@ -283,11 +285,9 @@ static inline void kmsan_kfree_large(const void *ptr) { } -static inline int kmsan_vmap_pages_range_noflush(unsigned long start, - unsigned long end, - pgprot_t prot, - struct page **pages, - unsigned int page_shift) +static inline int __must_check kmsan_vmap_pages_range_noflush( + unsigned long start, unsigned long end, pgprot_t prot, + struct page **pages, unsigned int page_shift) { return 0; } @@ -297,10 +297,11 @@ static inline void kmsan_vunmap_range_noflush(unsigned long start, { } -static inline int kmsan_ioremap_page_range(unsigned long start, - unsigned long end, - phys_addr_t phys_addr, pgprot_t prot, - unsigned int page_shift) +static inline int __must_check kmsan_ioremap_page_range(unsigned long start, + unsigned long end, + phys_addr_t phys_addr, + pgprot_t prot, + unsigned int page_shift) { return 0; } diff --git a/include/linux/kobject.h b/include/linux/kobject.h index bdab370a24f4..c392c811d9ad 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -79,43 +79,37 @@ struct kobject { unsigned int uevent_suppress:1; }; -extern __printf(2, 3) -int kobject_set_name(struct kobject *kobj, const char *name, ...); -extern __printf(2, 0) -int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, - va_list vargs); +__printf(2, 3) int kobject_set_name(struct kobject *kobj, const char *name, ...); +__printf(2, 0) int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs); static inline const char *kobject_name(const struct kobject *kobj) { return kobj->name; } -extern void kobject_init(struct kobject *kobj, const struct kobj_type *ktype); -extern __printf(3, 4) __must_check -int kobject_add(struct kobject *kobj, struct kobject *parent, - const char *fmt, ...); -extern __printf(4, 5) __must_check -int kobject_init_and_add(struct kobject *kobj, - const struct kobj_type *ktype, struct kobject *parent, - const char *fmt, ...); +void kobject_init(struct kobject *kobj, const struct kobj_type *ktype); +__printf(3, 4) __must_check int kobject_add(struct kobject *kobj, + struct kobject *parent, + const char *fmt, ...); +__printf(4, 5) __must_check int kobject_init_and_add(struct kobject *kobj, + const struct kobj_type *ktype, + struct kobject *parent, + const char *fmt, ...); -extern void kobject_del(struct kobject *kobj); +void kobject_del(struct kobject *kobj); -extern struct kobject * __must_check kobject_create_and_add(const char *name, - struct kobject *parent); +struct kobject * __must_check kobject_create_and_add(const char *name, struct kobject *parent); -extern int __must_check kobject_rename(struct kobject *, const char *new_name); -extern int __must_check kobject_move(struct kobject *, struct kobject *); +int __must_check kobject_rename(struct kobject *, const char *new_name); +int __must_check kobject_move(struct kobject *, struct kobject *); -extern struct kobject *kobject_get(struct kobject *kobj); -extern struct kobject * __must_check kobject_get_unless_zero( - struct kobject *kobj); -extern void kobject_put(struct kobject *kobj); +struct kobject *kobject_get(struct kobject *kobj); +struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj); +void kobject_put(struct kobject *kobj); -extern const void *kobject_namespace(const struct kobject *kobj); -extern void kobject_get_ownership(const struct kobject *kobj, - kuid_t *uid, kgid_t *gid); -extern char *kobject_get_path(const struct kobject *kobj, gfp_t flag); +const void *kobject_namespace(const struct kobject *kobj); +void kobject_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid); +char *kobject_get_path(const struct kobject *kobj, gfp_t flag); struct kobj_type { void (*release)(struct kobject *kobj); @@ -176,12 +170,11 @@ struct kset { const struct kset_uevent_ops *uevent_ops; } __randomize_layout; -extern void kset_init(struct kset *kset); -extern int __must_check kset_register(struct kset *kset); -extern void kset_unregister(struct kset *kset); -extern struct kset * __must_check kset_create_and_add(const char *name, - const struct kset_uevent_ops *u, - struct kobject *parent_kobj); +void kset_init(struct kset *kset); +int __must_check kset_register(struct kset *kset); +void kset_unregister(struct kset *kset); +struct kset * __must_check kset_create_and_add(const char *name, const struct kset_uevent_ops *u, + struct kobject *parent_kobj); static inline struct kset *to_kset(struct kobject *kobj) { @@ -203,7 +196,7 @@ static inline const struct kobj_type *get_ktype(const struct kobject *kobj) return kobj->ktype; } -extern struct kobject *kset_find_obj(struct kset *, const char *); +struct kobject *kset_find_obj(struct kset *, const char *); /* The global /sys/kernel/ kobject for people to chain off of */ extern struct kobject *kernel_kobj; diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 7e232ba59b86..7a9b76fb6c3f 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -18,13 +18,26 @@ #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags); + +void ksm_add_vma(struct vm_area_struct *vma); +int ksm_enable_merge_any(struct mm_struct *mm); + int __ksm_enter(struct mm_struct *mm); void __ksm_exit(struct mm_struct *mm); static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { - if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) - return __ksm_enter(mm); + int ret; + + if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) { + ret = __ksm_enter(mm); + if (ret) + return ret; + } + + if (test_bit(MMF_VM_MERGE_ANY, &oldmm->flags)) + set_bit(MMF_VM_MERGE_ANY, &mm->flags); + return 0; } @@ -51,8 +64,21 @@ struct page *ksm_might_need_to_copy(struct page *page, void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); +#ifdef CONFIG_MEMORY_FAILURE +void collect_procs_ksm(struct page *page, struct list_head *to_kill, + int force_early); +#endif + +#ifdef CONFIG_PROC_FS +long ksm_process_profit(struct mm_struct *); +#endif /* CONFIG_PROC_FS */ + #else /* !CONFIG_KSM */ +static inline void ksm_add_vma(struct vm_area_struct *vma) +{ +} + static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { return 0; @@ -62,6 +88,13 @@ static inline void ksm_exit(struct mm_struct *mm) { } +#ifdef CONFIG_MEMORY_FAILURE +static inline void collect_procs_ksm(struct page *page, + struct list_head *to_kill, int force_early) +{ +} +#endif + #ifdef CONFIG_MMU static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags) diff --git a/include/linux/libgcc.h b/include/linux/libgcc.h index b8dc75f0c830..fc388da6a027 100644 --- a/include/linux/libgcc.h +++ b/include/linux/libgcc.h @@ -27,4 +27,11 @@ typedef union { long long ll; } DWunion; +long long notrace __ashldi3(long long u, word_type b); +long long notrace __ashrdi3(long long u, word_type b); +word_type notrace __cmpdi2(long long a, long long b); +long long notrace __lshrdi3(long long u, word_type b); +long long notrace __muldi3(long long u, long long v); +word_type notrace __ucmpdi2(unsigned long long a, unsigned long long b); + #endif /* __ASM_LIBGCC_H */ diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 293e29960c6e..9b9b38e89563 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -13,6 +13,7 @@ #include <linux/ftrace.h> #include <linux/completion.h> #include <linux/list.h> +#include <linux/livepatch_sched.h> #if IS_ENABLED(CONFIG_LIVEPATCH) diff --git a/include/linux/livepatch_sched.h b/include/linux/livepatch_sched.h new file mode 100644 index 000000000000..013794fb5da0 --- /dev/null +++ b/include/linux/livepatch_sched.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_LIVEPATCH_SCHED_H_ +#define _LINUX_LIVEPATCH_SCHED_H_ + +#include <linux/jump_label.h> +#include <linux/static_call_types.h> + +#ifdef CONFIG_LIVEPATCH + +void __klp_sched_try_switch(void); + +#if !defined(CONFIG_PREEMPT_DYNAMIC) || !defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) + +DECLARE_STATIC_KEY_FALSE(klp_sched_try_switch_key); + +static __always_inline void klp_sched_try_switch(void) +{ + if (static_branch_unlikely(&klp_sched_try_switch_key)) + __klp_sched_try_switch(); +} + +#endif /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */ + +#else /* !CONFIG_LIVEPATCH */ +static inline void klp_sched_try_switch(void) {} +static inline void __klp_sched_try_switch(void) {} +#endif /* CONFIG_LIVEPATCH */ + +#endif /* _LINUX_LIVEPATCH_SCHED_H_ */ diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 0168ac9fdda8..f42594a9efe0 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -99,21 +99,11 @@ struct nsm_handle { /* * Rigorous type checking on sockaddr type conversions */ -static inline struct sockaddr_in *nlm_addr_in(const struct nlm_host *host) -{ - return (struct sockaddr_in *)&host->h_addr; -} - static inline struct sockaddr *nlm_addr(const struct nlm_host *host) { return (struct sockaddr *)&host->h_addr; } -static inline struct sockaddr_in *nlm_srcaddr_in(const struct nlm_host *host) -{ - return (struct sockaddr_in *)&host->h_srcaddr; -} - static inline struct sockaddr *nlm_srcaddr(const struct nlm_host *host) { return (struct sockaddr *)&host->h_srcaddr; @@ -131,7 +121,16 @@ struct nlm_lockowner { uint32_t pid; }; -struct nlm_wait; +/* + * This is the representation of a blocked client lock. + */ +struct nlm_wait { + struct list_head b_list; /* linked list */ + wait_queue_head_t b_wait; /* where to wait on */ + struct nlm_host *b_host; + struct file_lock *b_lock; /* local file lock */ + __be32 b_status; /* grant callback status */ +}; /* * Memory chunk for NLM client RPC request. @@ -212,9 +211,11 @@ struct nlm_rqst * nlm_alloc_call(struct nlm_host *host); int nlm_async_call(struct nlm_rqst *, u32, const struct rpc_call_ops *); int nlm_async_reply(struct nlm_rqst *, u32, const struct rpc_call_ops *); void nlmclnt_release_call(struct nlm_rqst *); -struct nlm_wait * nlmclnt_prepare_block(struct nlm_host *host, struct file_lock *fl); -void nlmclnt_finish_block(struct nlm_wait *block); -int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout); +void nlmclnt_prepare_block(struct nlm_wait *block, struct nlm_host *host, + struct file_lock *fl); +void nlmclnt_queue_block(struct nlm_wait *block); +__be32 nlmclnt_dequeue_block(struct nlm_wait *block); +int nlmclnt_wait(struct nlm_wait *block, struct nlm_rqst *req, long timeout); __be32 nlmclnt_grant(const struct sockaddr *addr, const struct nlm_lock *lock); void nlmclnt_recovery(struct nlm_host *); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 50ad19662a32..f82ee3fac1cd 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -597,6 +597,8 @@ extern int hashdist; /* Distribute hashes across NUMA nodes? */ #endif #ifdef CONFIG_MEMTEST +extern phys_addr_t early_memtest_bad_size; /* Size of faulty ram found by memtest */ +extern bool early_memtest_done; /* Was early memtest done? */ extern void early_memtest(phys_addr_t start, phys_addr_t end); #else static inline void early_memtest(phys_addr_t start, phys_addr_t end) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b6eda2ab205d..222d7370134c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -97,6 +97,7 @@ struct shrinker_info { struct rcu_head rcu; atomic_long_t *nr_deferred; unsigned long *map; + int map_nr_max; }; struct lruvec_stats_percpu { @@ -1037,7 +1038,8 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, } void mem_cgroup_flush_stats(void); -void mem_cgroup_flush_stats_delayed(void); +void mem_cgroup_flush_stats_atomic(void); +void mem_cgroup_flush_stats_ratelimited(void); void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); @@ -1535,7 +1537,11 @@ static inline void mem_cgroup_flush_stats(void) { } -static inline void mem_cgroup_flush_stats_delayed(void) +static inline void mem_cgroup_flush_stats_atomic(void) +{ +} + +static inline void mem_cgroup_flush_stats_ratelimited(void) { } diff --git a/include/linux/memfd.h b/include/linux/memfd.h index 4f1600413f91..e7abf6fa4c52 100644 --- a/include/linux/memfd.h +++ b/include/linux/memfd.h @@ -5,9 +5,9 @@ #include <linux/file.h> #ifdef CONFIG_MEMFD_CREATE -extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg); +extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg); #else -static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned long a) +static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a) { return -EINVAL; } diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h index 117d02708439..eda1ffd99c1a 100644 --- a/include/linux/mfd/palmas.h +++ b/include/linux/mfd/palmas.h @@ -128,12 +128,6 @@ struct palmas_pmic_driver_data { struct regulator_config config); }; -struct palmas_adc_wakeup_property { - int adc_channel_number; - int adc_high_threshold; - int adc_low_threshold; -}; - struct palmas_gpadc_platform_data { /* Channel 3 current source is only enabled during conversion */ int ch3_current; /* 0: off; 1: 10uA; 2: 400uA; 3: 800 uA */ @@ -152,8 +146,6 @@ struct palmas_gpadc_platform_data { int start_polarity; int auto_conversion_period_ms; - struct palmas_adc_wakeup_property *adc_wakeup1_data; - struct palmas_adc_wakeup_property *adc_wakeup2_data; }; struct palmas_reg_init { diff --git a/include/linux/mhi.h b/include/linux/mhi.h index a5441ad33c74..f6de4b6ecfc7 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -766,13 +766,6 @@ int mhi_prepare_for_transfer_autoqueue(struct mhi_device *mhi_dev); void mhi_unprepare_from_transfer(struct mhi_device *mhi_dev); /** - * mhi_poll - Poll for any available data in DL direction - * @mhi_dev: Device associated with the channels - * @budget: # of events to process - */ -int mhi_poll(struct mhi_device *mhi_dev, u32 budget); - -/** * mhi_queue_dma - Send or receive DMA mapped buffers from client device * over MHI channel * @mhi_dev: Device associated with the channels diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index b42696d74c9f..dc5e2cb302a5 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1100,7 +1100,9 @@ struct mlx5_ifc_roce_cap_bits { u8 sw_r_roce_src_udp_port[0x1]; u8 fl_rc_qp_when_roce_disabled[0x1]; u8 fl_rc_qp_when_roce_enabled[0x1]; - u8 reserved_at_7[0x17]; + u8 reserved_at_7[0x1]; + u8 qp_ooo_transmit_default[0x1]; + u8 reserved_at_9[0x15]; u8 qp_ts_format[0x2]; u8 reserved_at_20[0x60]; @@ -1516,7 +1518,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_b0[0x1]; u8 uplink_follow[0x1]; u8 ts_cqe_to_dest_cqn[0x1]; - u8 reserved_at_b3[0x7]; + u8 reserved_at_b3[0x6]; + u8 go_back_n[0x1]; u8 shampo[0x1]; u8 reserved_at_bb[0x5]; @@ -1531,7 +1534,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_eq_sz[0x8]; u8 relaxed_ordering_write[0x1]; - u8 relaxed_ordering_read[0x1]; + u8 relaxed_ordering_read_pci_enabled[0x1]; u8 log_max_mkey[0x6]; u8 reserved_at_f0[0x6]; u8 terminate_scatter_list_mkey[0x1]; @@ -1747,9 +1750,12 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_320[0x3]; u8 log_max_transport_domain[0x5]; - u8 reserved_at_328[0x3]; + u8 reserved_at_328[0x2]; + u8 relaxed_ordering_read[0x1]; u8 log_max_pd[0x5]; - u8 reserved_at_330[0xb]; + u8 reserved_at_330[0x9]; + u8 q_counter_aggregation[0x1]; + u8 q_counter_other_vport[0x1]; u8 log_max_xrcd[0x5]; u8 nic_receive_steering_discard[0x1]; @@ -3291,7 +3297,8 @@ struct mlx5_ifc_qpc_bits { u8 log_rq_stride[0x3]; u8 no_sq[0x1]; u8 log_sq_size[0x4]; - u8 reserved_at_55[0x3]; + u8 reserved_at_55[0x1]; + u8 retry_mode[0x2]; u8 ts_format[0x2]; u8 reserved_at_5a[0x1]; u8 rlky[0x1]; @@ -5629,10 +5636,15 @@ struct mlx5_ifc_query_q_counter_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x80]; + u8 other_vport[0x1]; + u8 reserved_at_41[0xf]; + u8 vport_number[0x10]; + + u8 reserved_at_60[0x60]; u8 clear[0x1]; - u8 reserved_at_c1[0x1f]; + u8 aggregate[0x1]; + u8 reserved_at_c2[0x1e]; u8 reserved_at_e0[0x18]; u8 counter_set_id[0x8]; @@ -9315,7 +9327,8 @@ struct mlx5_ifc_alloc_flow_counter_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x38]; + u8 reserved_at_40[0x33]; + u8 flow_counter_bulk_log_size[0x5]; u8 flow_counter_bulk[0x8]; }; diff --git a/include/linux/mm.h b/include/linux/mm.h index 1f79667824eb..27ce77080c79 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -29,6 +29,7 @@ #include <linux/pgtable.h> #include <linux/kasan.h> #include <linux/memremap.h> +#include <linux/slab.h> struct mempolicy; struct anon_vma; @@ -38,6 +39,7 @@ struct pt_regs; extern int sysctl_page_lock_unfairness; +void mm_core_init(void); void init_mm_internals(void); #ifndef CONFIG_NUMA /* Don't use mapnrs, do it properly */ @@ -96,17 +98,6 @@ extern int mmap_rnd_compat_bits __read_mostly; #include <asm/page.h> #include <asm/processor.h> -/* - * Architectures that support memory tagging (assigning tags to memory regions, - * embedding these tags into addresses that point to these memory regions, and - * checking that the memory and the pointer tags match on memory accesses) - * redefine this macro to strip tags from pointers. - * It's defined as noop for architectures that don't support memory tagging. - */ -#ifndef untagged_addr -#define untagged_addr(addr) (addr) -#endif - #ifndef __pa_symbol #define __pa_symbol(x) __pa(RELOC_HIDE((unsigned long)(x), 0)) #endif @@ -256,6 +247,8 @@ void setup_initial_init_mm(void *start_code, void *end_code, struct vm_area_struct *vm_area_alloc(struct mm_struct *); struct vm_area_struct *vm_area_dup(struct vm_area_struct *); void vm_area_free(struct vm_area_struct *); +/* Use only if VMA has no other users */ +void __vm_area_free(struct vm_area_struct *vma); #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; @@ -478,7 +471,8 @@ static inline bool fault_flag_allow_retry_first(enum fault_flag flags) { FAULT_FLAG_USER, "USER" }, \ { FAULT_FLAG_REMOTE, "REMOTE" }, \ { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" }, \ - { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" } + { FAULT_FLAG_INTERRUPTIBLE, "INTERRUPTIBLE" }, \ + { FAULT_FLAG_VMA_LOCK, "VMA_LOCK" } /* * vm_fault is filled by the pagefault handler and passed to the vma's @@ -623,6 +617,131 @@ struct vm_operations_struct { unsigned long addr); }; +#ifdef CONFIG_NUMA_BALANCING +static inline void vma_numab_state_init(struct vm_area_struct *vma) +{ + vma->numab_state = NULL; +} +static inline void vma_numab_state_free(struct vm_area_struct *vma) +{ + kfree(vma->numab_state); +} +#else +static inline void vma_numab_state_init(struct vm_area_struct *vma) {} +static inline void vma_numab_state_free(struct vm_area_struct *vma) {} +#endif /* CONFIG_NUMA_BALANCING */ + +#ifdef CONFIG_PER_VMA_LOCK +/* + * Try to read-lock a vma. The function is allowed to occasionally yield false + * locked result to avoid performance overhead, in which case we fall back to + * using mmap_lock. The function should never yield false unlocked result. + */ +static inline bool vma_start_read(struct vm_area_struct *vma) +{ + /* Check before locking. A race might cause false locked result. */ + if (vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq)) + return false; + + if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0)) + return false; + + /* + * Overflow might produce false locked result. + * False unlocked result is impossible because we modify and check + * vma->vm_lock_seq under vma->vm_lock protection and mm->mm_lock_seq + * modification invalidates all existing locks. + */ + if (unlikely(vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))) { + up_read(&vma->vm_lock->lock); + return false; + } + return true; +} + +static inline void vma_end_read(struct vm_area_struct *vma) +{ + rcu_read_lock(); /* keeps vma alive till the end of up_read */ + up_read(&vma->vm_lock->lock); + rcu_read_unlock(); +} + +static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq) +{ + mmap_assert_write_locked(vma->vm_mm); + + /* + * current task is holding mmap_write_lock, both vma->vm_lock_seq and + * mm->mm_lock_seq can't be concurrently modified. + */ + *mm_lock_seq = READ_ONCE(vma->vm_mm->mm_lock_seq); + return (vma->vm_lock_seq == *mm_lock_seq); +} + +static inline void vma_start_write(struct vm_area_struct *vma) +{ + int mm_lock_seq; + + if (__is_vma_write_locked(vma, &mm_lock_seq)) + return; + + down_write(&vma->vm_lock->lock); + vma->vm_lock_seq = mm_lock_seq; + up_write(&vma->vm_lock->lock); +} + +static inline bool vma_try_start_write(struct vm_area_struct *vma) +{ + int mm_lock_seq; + + if (__is_vma_write_locked(vma, &mm_lock_seq)) + return true; + + if (!down_write_trylock(&vma->vm_lock->lock)) + return false; + + vma->vm_lock_seq = mm_lock_seq; + up_write(&vma->vm_lock->lock); + return true; +} + +static inline void vma_assert_write_locked(struct vm_area_struct *vma) +{ + int mm_lock_seq; + + VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma); +} + +static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) +{ + /* When detaching vma should be write-locked */ + if (detached) + vma_assert_write_locked(vma); + vma->detached = detached; +} + +struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm, + unsigned long address); + +#else /* CONFIG_PER_VMA_LOCK */ + +static inline void vma_init_lock(struct vm_area_struct *vma) {} +static inline bool vma_start_read(struct vm_area_struct *vma) + { return false; } +static inline void vma_end_read(struct vm_area_struct *vma) {} +static inline void vma_start_write(struct vm_area_struct *vma) {} +static inline bool vma_try_start_write(struct vm_area_struct *vma) + { return true; } +static inline void vma_assert_write_locked(struct vm_area_struct *vma) {} +static inline void vma_mark_detached(struct vm_area_struct *vma, + bool detached) {} + +#endif /* CONFIG_PER_VMA_LOCK */ + +/* + * WARNING: vma_init does not initialize vma->vm_lock. + * Use vm_area_alloc()/vm_area_free() if vma needs locking. + */ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { static const struct vm_operations_struct dummy_vm_ops = {}; @@ -631,6 +750,8 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) vma->vm_mm = mm; vma->vm_ops = &dummy_vm_ops; INIT_LIST_HEAD(&vma->anon_vma_chain); + vma_mark_detached(vma, false); + vma_numab_state_init(vma); } /* Use when VMA is not part of the VMA tree and needs no locking */ @@ -644,28 +765,28 @@ static inline void vm_flags_init(struct vm_area_struct *vma, static inline void vm_flags_reset(struct vm_area_struct *vma, vm_flags_t flags) { - mmap_assert_write_locked(vma->vm_mm); + vma_start_write(vma); vm_flags_init(vma, flags); } static inline void vm_flags_reset_once(struct vm_area_struct *vma, vm_flags_t flags) { - mmap_assert_write_locked(vma->vm_mm); + vma_start_write(vma); WRITE_ONCE(ACCESS_PRIVATE(vma, __vm_flags), flags); } static inline void vm_flags_set(struct vm_area_struct *vma, vm_flags_t flags) { - mmap_assert_write_locked(vma->vm_mm); + vma_start_write(vma); ACCESS_PRIVATE(vma, __vm_flags) |= flags; } static inline void vm_flags_clear(struct vm_area_struct *vma, vm_flags_t flags) { - mmap_assert_write_locked(vma->vm_mm); + vma_start_write(vma); ACCESS_PRIVATE(vma, __vm_flags) &= ~flags; } @@ -686,7 +807,7 @@ static inline void __vm_flags_mod(struct vm_area_struct *vma, static inline void vm_flags_mod(struct vm_area_struct *vma, vm_flags_t set, vm_flags_t clear) { - mmap_assert_write_locked(vma->vm_mm); + vma_start_write(vma); __vm_flags_mod(vma, set, clear); } @@ -1554,6 +1675,16 @@ static inline int xchg_page_access_time(struct page *page, int time) last_time = page_cpupid_xchg_last(page, time >> PAGE_ACCESS_TIME_BUCKETS); return last_time << PAGE_ACCESS_TIME_BUCKETS; } + +static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) +{ + unsigned int pid_bit; + + pid_bit = hash_32(current->pid, ilog2(BITS_PER_LONG)); + if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->access_pids[1])) { + __set_bit(pid_bit, &vma->numab_state->access_pids[1]); + } +} #else /* !CONFIG_NUMA_BALANCING */ static inline int page_cpupid_xchg_last(struct page *page, int cpupid) { @@ -1603,6 +1734,10 @@ static inline bool cpupid_match_pid(struct task_struct *task, int cpupid) { return false; } + +static inline void vma_set_access_pid_bit(struct vm_area_struct *vma) +{ +} #endif /* CONFIG_NUMA_BALANCING */ #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) @@ -2636,12 +2771,6 @@ static inline bool ptlock_init(struct page *page) { return true; } static inline void ptlock_free(struct page *page) {} #endif /* USE_SPLIT_PTE_PTLOCKS */ -static inline void pgtable_init(void) -{ - ptlock_cache_init(); - pgtable_cache_init(); -} - static inline bool pgtable_pte_page_ctor(struct page *page) { if (!ptlock_init(page)) @@ -2785,7 +2914,6 @@ extern unsigned long free_reserved_area(void *start, void *end, int poison, const char *s); extern void adjust_managed_page_count(struct page *page, long count); -extern void mem_init_print_info(void); extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end); @@ -2896,7 +3024,6 @@ extern void setup_per_cpu_pageset(void); extern int min_free_kbytes; extern int watermark_boost_factor; extern int watermark_scale_factor; -extern bool arch_has_descending_max_zone_pfns(void); /* nommu.c */ extern atomic_long_t mmap_pages_allocated; @@ -3185,8 +3312,6 @@ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); -vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr, - pfn_t pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); @@ -3256,7 +3381,6 @@ extern int apply_to_existing_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); -extern void __init init_mem_debugging_and_hardening(void); #ifdef CONFIG_PAGE_POISONING extern void __kernel_poison_pages(struct page *page, int numpages); extern void __kernel_unpoison_pages(struct page *page, int numpages); @@ -3425,6 +3549,22 @@ void vmemmap_populate_print_last(void); void vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap); #endif + +#ifdef CONFIG_ARCH_WANT_OPTIMIZE_VMEMMAP +static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) +{ + return is_power_of_2(sizeof(struct page)) && + pgmap && (pgmap_vmemmap_nr(pgmap) > 1) && !altmap; +} +#else +static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) +{ + return false; +} +#endif + void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, unsigned long nr_pages); @@ -3442,8 +3582,6 @@ int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); -extern int sysctl_memory_failure_early_kill; -extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); @@ -3453,6 +3591,7 @@ extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); void num_poisoned_pages_inc(unsigned long pfn); void num_poisoned_pages_sub(unsigned long pfn, long i); +struct task_struct *task_early_kill(struct task_struct *tsk, int force_early); #else static inline void memory_failure_queue(unsigned long pfn, int flags) { @@ -3473,6 +3612,12 @@ static inline void num_poisoned_pages_sub(unsigned long pfn, long i) } #endif +#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_KSM) +void add_to_kill_ksm(struct task_struct *tsk, struct page *p, + struct vm_area_struct *vma, struct list_head *to_kill, + unsigned long ksm_addr); +#endif + #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) extern void memblk_nr_poison_inc(unsigned long pfn); extern void memblk_nr_poison_sub(unsigned long pfn, long i); @@ -3542,14 +3687,12 @@ extern const struct attribute_group memory_failure_attr_group; extern void clear_huge_page(struct page *page, unsigned long addr_hint, unsigned int pages_per_huge_page); -extern void copy_user_huge_page(struct page *dst, struct page *src, - unsigned long addr_hint, - struct vm_area_struct *vma, - unsigned int pages_per_huge_page); -extern long copy_huge_page_from_user(struct page *dst_page, - const void __user *usr_src, - unsigned int pages_per_huge_page, - bool allow_pagefault); +int copy_user_large_folio(struct folio *dst, struct folio *src, + unsigned long addr_hint, + struct vm_area_struct *vma); +long copy_folio_from_user(struct folio *dst_folio, + const void __user *usr_src, + bool allow_pagefault); /** * vma_is_special_huge - Are transhuge page-table entries considered special? diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index de1e622dd366..0e1d239a882c 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -557,6 +557,12 @@ pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr, /* The current status of the pte should be "cleared" before calling */ WARN_ON_ONCE(!pte_none(*pte)); + /* + * NOTE: userfaultfd_wp_unpopulated() doesn't need this whole + * thing, because when zapping either it means it's dropping the + * page, or in TTU where the present pte will be quickly replaced + * with a swap pte. There's no way of leaking the bit. + */ if (vma_is_anonymous(vma) || !userfaultfd_wp(vma)) return; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index a57e6ae78e65..306a3d1a0fa6 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -471,6 +471,16 @@ struct anon_vma_name { char name[]; }; +struct vma_lock { + struct rw_semaphore lock; +}; + +struct vma_numab_state { + unsigned long next_scan; + unsigned long next_pid_reset; + unsigned long access_pids[2]; +}; + /* * This struct describes a virtual memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory @@ -480,17 +490,19 @@ struct anon_vma_name { struct vm_area_struct { /* The first cache line has the info for VMA tree walking. */ - unsigned long vm_start; /* Our start address within vm_mm. */ - unsigned long vm_end; /* The first byte after our end address - within vm_mm. */ + union { + struct { + /* VMA covers [vm_start; vm_end) addresses within mm */ + unsigned long vm_start; + unsigned long vm_end; + }; +#ifdef CONFIG_PER_VMA_LOCK + struct rcu_head vm_rcu; /* Used for deferred freeing. */ +#endif + }; struct mm_struct *vm_mm; /* The address space we belong to. */ - - /* - * Access permissions of this VMA. - * See vmf_insert_mixed_prot() for discussion. - */ - pgprot_t vm_page_prot; + pgprot_t vm_page_prot; /* Access permissions of this VMA. */ /* * Flags, see mm.h. @@ -501,6 +513,14 @@ struct vm_area_struct { vm_flags_t __private __vm_flags; }; +#ifdef CONFIG_PER_VMA_LOCK + int vm_lock_seq; + struct vma_lock *vm_lock; + + /* Flag to indicate areas detached from the mm->mm_mt tree */ + bool detached; +#endif + /* * For areas with an address space and backing store, * linkage into the address_space->i_mmap interval tree. @@ -547,9 +567,19 @@ struct vm_area_struct { #ifdef CONFIG_NUMA struct mempolicy *vm_policy; /* NUMA policy for the VMA */ #endif +#ifdef CONFIG_NUMA_BALANCING + struct vma_numab_state *numab_state; /* NUMA Balancing state */ +#endif struct vm_userfaultfd_ctx vm_userfaultfd_ctx; } __randomize_layout; +#ifdef CONFIG_SCHED_MM_CID +struct mm_cid { + u64 time; + int cid; +}; +#endif + struct kioctx_table; struct mm_struct { struct { @@ -600,15 +630,19 @@ struct mm_struct { atomic_t mm_count; #ifdef CONFIG_SCHED_MM_CID /** - * @cid_lock: Protect cid bitmap updates vs lookups. + * @pcpu_cid: Per-cpu current cid. * - * Prevent situations where updates to the cid bitmap happen - * concurrently with lookups. Those can lead to situations - * where a lookup cannot find a free bit simply because it was - * unlucky enough to load, non-atomically, bitmap words as they - * were being concurrently updated by the updaters. + * Keep track of the currently allocated mm_cid for each cpu. + * The per-cpu mm_cid values are serialized by their respective + * runqueue locks. */ - raw_spinlock_t cid_lock; + struct mm_cid __percpu *pcpu_cid; + /* + * @mm_cid_next_scan: Next mm_cid scan (in jiffies). + * + * When the next mm_cid scan is due (in jiffies). + */ + unsigned long mm_cid_next_scan; #endif #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* size of all page tables */ @@ -637,6 +671,9 @@ struct mm_struct { * init_mm.mmlist, and are protected * by mmlist_lock */ +#ifdef CONFIG_PER_VMA_LOCK + int mm_lock_seq; +#endif unsigned long hiwater_rss; /* High-watermark of RSS usage */ @@ -873,6 +910,37 @@ static inline void vma_iter_init(struct vma_iterator *vmi, } #ifdef CONFIG_SCHED_MM_CID + +enum mm_cid_state { + MM_CID_UNSET = -1U, /* Unset state has lazy_put flag set. */ + MM_CID_LAZY_PUT = (1U << 31), +}; + +static inline bool mm_cid_is_unset(int cid) +{ + return cid == MM_CID_UNSET; +} + +static inline bool mm_cid_is_lazy_put(int cid) +{ + return !mm_cid_is_unset(cid) && (cid & MM_CID_LAZY_PUT); +} + +static inline bool mm_cid_is_valid(int cid) +{ + return !(cid & MM_CID_LAZY_PUT); +} + +static inline int mm_cid_set_lazy_put(int cid) +{ + return cid | MM_CID_LAZY_PUT; +} + +static inline int mm_cid_clear_lazy_put(int cid) +{ + return cid & ~MM_CID_LAZY_PUT; +} + /* Accessor for struct mm_struct's cidmask. */ static inline cpumask_t *mm_cidmask(struct mm_struct *mm) { @@ -886,16 +954,40 @@ static inline cpumask_t *mm_cidmask(struct mm_struct *mm) static inline void mm_init_cid(struct mm_struct *mm) { - raw_spin_lock_init(&mm->cid_lock); + int i; + + for_each_possible_cpu(i) { + struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, i); + + pcpu_cid->cid = MM_CID_UNSET; + pcpu_cid->time = 0; + } cpumask_clear(mm_cidmask(mm)); } +static inline int mm_alloc_cid(struct mm_struct *mm) +{ + mm->pcpu_cid = alloc_percpu(struct mm_cid); + if (!mm->pcpu_cid) + return -ENOMEM; + mm_init_cid(mm); + return 0; +} + +static inline void mm_destroy_cid(struct mm_struct *mm) +{ + free_percpu(mm->pcpu_cid); + mm->pcpu_cid = NULL; +} + static inline unsigned int mm_cid_size(void) { return cpumask_size(); } #else /* CONFIG_SCHED_MM_CID */ static inline void mm_init_cid(struct mm_struct *mm) { } +static inline int mm_alloc_cid(struct mm_struct *mm) { return 0; } +static inline void mm_destroy_cid(struct mm_struct *mm) { } static inline unsigned int mm_cid_size(void) { return 0; @@ -1037,6 +1129,7 @@ typedef struct { * mapped after the fault. * @FAULT_FLAG_ORIG_PTE_VALID: whether the fault has vmf->orig_pte cached. * We should only access orig_pte if this flag set. + * @FAULT_FLAG_VMA_LOCK: The fault is handled under VMA lock. * * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify * whether we would allow page faults to retry by specifying these two @@ -1074,6 +1167,7 @@ enum fault_flag { FAULT_FLAG_INTERRUPTIBLE = 1 << 9, FAULT_FLAG_UNSHARE = 1 << 10, FAULT_FLAG_ORIG_PTE_VALID = 1 << 11, + FAULT_FLAG_VMA_LOCK = 1 << 12, }; typedef unsigned int __bitwise zap_flags_t; diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 96e113e23d04..aab8f1b28d26 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -60,6 +60,29 @@ static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write) #endif /* CONFIG_TRACING */ +static inline void mmap_assert_locked(struct mm_struct *mm) +{ + lockdep_assert_held(&mm->mmap_lock); + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); +} + +static inline void mmap_assert_write_locked(struct mm_struct *mm) +{ + lockdep_assert_held_write(&mm->mmap_lock); + VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); +} + +#ifdef CONFIG_PER_VMA_LOCK +static inline void vma_end_write_all(struct mm_struct *mm) +{ + mmap_assert_write_locked(mm); + /* No races during update due to exclusive mmap_lock being held */ + WRITE_ONCE(mm->mm_lock_seq, mm->mm_lock_seq + 1); +} +#else +static inline void vma_end_write_all(struct mm_struct *mm) {} +#endif + static inline void mmap_init_lock(struct mm_struct *mm) { init_rwsem(&mm->mmap_lock); @@ -102,12 +125,14 @@ static inline bool mmap_write_trylock(struct mm_struct *mm) static inline void mmap_write_unlock(struct mm_struct *mm) { __mmap_lock_trace_released(mm, true); + vma_end_write_all(mm); up_write(&mm->mmap_lock); } static inline void mmap_write_downgrade(struct mm_struct *mm) { __mmap_lock_trace_acquire_returned(mm, false, true); + vma_end_write_all(mm); downgrade_write(&mm->mmap_lock); } @@ -150,18 +175,6 @@ static inline void mmap_read_unlock_non_owner(struct mm_struct *mm) up_read_non_owner(&mm->mmap_lock); } -static inline void mmap_assert_locked(struct mm_struct *mm) -{ - lockdep_assert_held(&mm->mmap_lock); - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); -} - -static inline void mmap_assert_write_locked(struct mm_struct *mm) -{ - lockdep_assert_held_write(&mm->mmap_lock); - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); -} - static inline int mmap_lock_is_contended(struct mm_struct *mm) { return rwsem_is_contended(&mm->mmap_lock); diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h index b9b970f7ab45..f2b7a3f04099 100644 --- a/include/linux/mmu_context.h +++ b/include/linux/mmu_context.h @@ -28,4 +28,18 @@ static inline void leave_mm(int cpu) { } # define task_cpu_possible(cpu, p) cpumask_test_cpu((cpu), task_cpu_possible_mask(p)) #endif +#ifndef mm_untag_mask +static inline unsigned long mm_untag_mask(struct mm_struct *mm) +{ + return -1UL; +} +#endif + +#ifndef arch_pgtable_dma_compat +static inline bool arch_pgtable_dma_compat(struct mm_struct *mm) +{ + return true; +} +#endif + #endif diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9fb1b03b83b2..a4889c9d4055 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -26,11 +26,13 @@ /* Free memory management - zoned buddy allocator. */ #ifndef CONFIG_ARCH_FORCE_MAX_ORDER -#define MAX_ORDER 11 +#define MAX_ORDER 10 #else #define MAX_ORDER CONFIG_ARCH_FORCE_MAX_ORDER #endif -#define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1)) +#define MAX_ORDER_NR_PAGES (1 << MAX_ORDER) + +#define IS_MAX_ORDER_ALIGNED(pfn) IS_ALIGNED(pfn, MAX_ORDER_NR_PAGES) /* * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed @@ -93,7 +95,7 @@ static inline bool migratetype_is_mergeable(int mt) } #define for_each_migratetype_order(order, type) \ - for (order = 0; order < MAX_ORDER; order++) \ + for (order = 0; order <= MAX_ORDER; order++) \ for (type = 0; type < MIGRATE_TYPES; type++) extern int page_group_by_mobility_disabled; @@ -108,18 +110,6 @@ struct free_area { unsigned long nr_free; }; -static inline struct page *get_page_from_free_area(struct free_area *area, - int migratetype) -{ - return list_first_entry_or_null(&area->free_list[migratetype], - struct page, lru); -} - -static inline bool free_area_empty(struct free_area *area, int migratetype) -{ - return list_empty(&area->free_list[migratetype]); -} - struct pglist_data; #ifdef CONFIG_NUMA @@ -453,18 +443,14 @@ enum { struct lru_gen_mm_state { /* set to max_seq after each iteration */ unsigned long seq; - /* where the current iteration continues (inclusive) */ + /* where the current iteration continues after */ struct list_head *head; - /* where the last iteration ended (exclusive) */ + /* where the last iteration ended before */ struct list_head *tail; - /* to wait for the last page table walker to finish */ - struct wait_queue_head wait; /* Bloom filters flip after each iteration */ unsigned long *filters[NR_BLOOM_FILTERS]; /* the mm stats for debugging */ unsigned long stats[NR_HIST_GENS][NR_MM_STATS]; - /* the number of concurrent page table walkers */ - int nr_walkers; }; struct lru_gen_mm_walk { @@ -922,7 +908,7 @@ struct zone { CACHELINE_PADDING(_pad1_); /* free areas of different sizes */ - struct free_area free_area[MAX_ORDER]; + struct free_area free_area[MAX_ORDER + 1]; /* zone flags, see below */ unsigned long flags; @@ -1369,7 +1355,7 @@ typedef struct pglist_data { #ifdef CONFIG_LRU_GEN /* kswap mm walk data */ - struct lru_gen_mm_walk mm_walk; + struct lru_gen_mm_walk mm_walk; /* lru_gen_folio list */ struct lru_gen_memcg memcg_lru; #endif @@ -1745,7 +1731,7 @@ static inline bool movable_only_nodes(nodemask_t *nodes) #define SECTION_BLOCKFLAGS_BITS \ ((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS) -#if (MAX_ORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS +#if (MAX_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS #error Allocator MAX_ORDER exceeds SECTION_SIZE #endif diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 549590e9c644..ccaaeda792c0 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -9,6 +9,7 @@ #define LINUX_MOD_DEVICETABLE_H #ifdef __KERNEL__ +#include <linux/mei.h> #include <linux/types.h> #include <linux/uuid.h> typedef unsigned long kernel_ulong_t; @@ -911,4 +912,19 @@ struct ishtp_device_id { kernel_ulong_t driver_data; }; +/** + * struct cdx_device_id - CDX device identifier + * @vendor: Vendor ID + * @device: Device ID + * @override_only: Match only when dev->driver_override is this driver. + * + * Type of entries in the "device Id" table for CDX devices supported by + * a CDX device driver. + */ +struct cdx_device_id { + __u16 vendor; + __u16 device; + __u32 override_only; +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/include/linux/module.h b/include/linux/module.h index 3730ed99e5f7..9e56763dff81 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -27,6 +27,7 @@ #include <linux/tracepoint-defs.h> #include <linux/srcu.h> #include <linux/static_call_types.h> +#include <linux/dynamic_debug.h> #include <linux/percpu.h> #include <asm/module.h> @@ -320,17 +321,47 @@ struct mod_tree_node { struct latch_tree_node node; }; -struct module_layout { - /* The actual code + data. */ +enum mod_mem_type { + MOD_TEXT = 0, + MOD_DATA, + MOD_RODATA, + MOD_RO_AFTER_INIT, + MOD_INIT_TEXT, + MOD_INIT_DATA, + MOD_INIT_RODATA, + + MOD_MEM_NUM_TYPES, + MOD_INVALID = -1, +}; + +#define mod_mem_type_is_init(type) \ + ((type) == MOD_INIT_TEXT || \ + (type) == MOD_INIT_DATA || \ + (type) == MOD_INIT_RODATA) + +#define mod_mem_type_is_core(type) (!mod_mem_type_is_init(type)) + +#define mod_mem_type_is_text(type) \ + ((type) == MOD_TEXT || \ + (type) == MOD_INIT_TEXT) + +#define mod_mem_type_is_data(type) (!mod_mem_type_is_text(type)) + +#define mod_mem_type_is_core_data(type) \ + (mod_mem_type_is_core(type) && \ + mod_mem_type_is_data(type)) + +#define for_each_mod_mem_type(type) \ + for (enum mod_mem_type (type) = 0; \ + (type) < MOD_MEM_NUM_TYPES; (type)++) + +#define for_class_mod_mem_type(type, class) \ + for_each_mod_mem_type(type) \ + if (mod_mem_type_is_##class(type)) + +struct module_memory { void *base; - /* Total size. */ unsigned int size; - /* The size of the executable code. */ - unsigned int text_size; - /* Size of RO section of the module (text+rodata) */ - unsigned int ro_size; - /* Size of RO after init section */ - unsigned int ro_after_init_size; #ifdef CONFIG_MODULES_TREE_LOOKUP struct mod_tree_node mtn; @@ -339,9 +370,9 @@ struct module_layout { #ifdef CONFIG_MODULES_TREE_LOOKUP /* Only touch one cacheline for common rbtree-for-core-layout case. */ -#define __module_layout_align ____cacheline_aligned +#define __module_memory_align ____cacheline_aligned #else -#define __module_layout_align +#define __module_memory_align #endif struct mod_kallsyms { @@ -426,12 +457,7 @@ struct module { /* Startup function. */ int (*init)(void); - /* Core layout: rbtree is accessed frequently, so keep together. */ - struct module_layout core_layout __module_layout_align; - struct module_layout init_layout; -#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC - struct module_layout data_layout; -#endif + struct module_memory mem[MOD_MEM_NUM_TYPES] __module_memory_align; /* Arch-specific module values */ struct mod_arch_specific arch; @@ -554,6 +580,9 @@ struct module { struct error_injection_entry *ei_funcs; unsigned int num_ei_funcs; #endif +#ifdef CONFIG_DYNAMIC_DEBUG_CORE + struct _ddebug_info dyndbg_info; +#endif } ____cacheline_aligned __randomize_layout; #ifndef MODULE_ARCH_INIT #define MODULE_ARCH_INIT {} @@ -581,23 +610,35 @@ bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr); bool is_module_percpu_address(unsigned long addr); bool is_module_text_address(unsigned long addr); +static inline bool within_module_mem_type(unsigned long addr, + const struct module *mod, + enum mod_mem_type type) +{ + unsigned long base, size; + + base = (unsigned long)mod->mem[type].base; + size = mod->mem[type].size; + return addr - base < size; +} + static inline bool within_module_core(unsigned long addr, const struct module *mod) { -#ifdef CONFIG_ARCH_WANTS_MODULES_DATA_IN_VMALLOC - if ((unsigned long)mod->data_layout.base <= addr && - addr < (unsigned long)mod->data_layout.base + mod->data_layout.size) - return true; -#endif - return (unsigned long)mod->core_layout.base <= addr && - addr < (unsigned long)mod->core_layout.base + mod->core_layout.size; + for_class_mod_mem_type(type, core) { + if (within_module_mem_type(addr, mod, type)) + return true; + } + return false; } static inline bool within_module_init(unsigned long addr, const struct module *mod) { - return (unsigned long)mod->init_layout.base <= addr && - addr < (unsigned long)mod->init_layout.base + mod->init_layout.size; + for_class_mod_mem_type(type, init) { + if (within_module_mem_type(addr, mod, type)) + return true; + } + return false; } static inline bool within_module(unsigned long addr, const struct module *mod) @@ -622,10 +663,46 @@ void symbol_put_addr(void *addr); to handle the error case (which only happens with rmmod --wait). */ extern void __module_get(struct module *module); -/* This is the Right Way to get a module: if it fails, it's being removed, - * so pretend it's not there. */ +/** + * try_module_get() - take module refcount unless module is being removed + * @module: the module we should check for + * + * Only try to get a module reference count if the module is not being removed. + * This call will fail if the module is already being removed. + * + * Care must also be taken to ensure the module exists and is alive prior to + * usage of this call. This can be gauranteed through two means: + * + * 1) Direct protection: you know an earlier caller must have increased the + * module reference through __module_get(). This can typically be achieved + * by having another entity other than the module itself increment the + * module reference count. + * + * 2) Implied protection: there is an implied protection against module + * removal. An example of this is the implied protection used by kernfs / + * sysfs. The sysfs store / read file operations are guaranteed to exist + * through the use of kernfs's active reference (see kernfs_active()) and a + * sysfs / kernfs file removal cannot happen unless the same file is not + * active. Therefore, if a sysfs file is being read or written to the module + * which created it must still exist. It is therefore safe to use + * try_module_get() on module sysfs store / read ops. + * + * One of the real values to try_module_get() is the module_is_live() check + * which ensures that the caller of try_module_get() can yield to userspace + * module removal requests and gracefully fail if the module is on its way out. + * + * Returns true if the reference count was successfully incremented. + */ extern bool try_module_get(struct module *module); +/** + * module_put() - release a reference count to a module + * @module: the module we should release a reference count for + * + * If you successfully bump a reference count to a module with try_module_get(), + * when you are finished you must call module_put() to release that reference + * count. + */ extern void module_put(struct module *module); #else /*!CONFIG_MODULE_UNLOAD*/ @@ -782,7 +859,7 @@ void *dereference_module_function_descriptor(struct module *mod, void *ptr) #ifdef CONFIG_SYSFS extern struct kset *module_kset; -extern struct kobj_type module_ktype; +extern const struct kobj_type module_ktype; #endif /* CONFIG_SYSFS */ #define symbol_request(x) try_then_request_module(symbol_get(x), "symbol:" #x) @@ -836,8 +913,7 @@ static inline bool module_sig_ok(struct module *module) #if defined(CONFIG_MODULES) && defined(CONFIG_KALLSYMS) int module_kallsyms_on_each_symbol(const char *modname, - int (*fn)(void *, const char *, - struct module *, unsigned long), + int (*fn)(void *, const char *, unsigned long), void *data); /* For kallsyms to ask for address resolution. namebuf should be at @@ -870,8 +946,7 @@ unsigned long find_kallsyms_symbol_value(struct module *mod, const char *name); #else /* CONFIG_MODULES && CONFIG_KALLSYMS */ static inline int module_kallsyms_on_each_symbol(const char *modname, - int (*fn)(void *, const char *, - struct module *, unsigned long), + int (*fn)(void *, const char *, unsigned long), void *data) { return -EOPNOTSUPP; diff --git a/include/linux/module_symbol.h b/include/linux/module_symbol.h new file mode 100644 index 000000000000..7ace7ba30203 --- /dev/null +++ b/include/linux/module_symbol.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _LINUX_MODULE_SYMBOL_H +#define _LINUX_MODULE_SYMBOL_H + +/* This ignores the intensely annoying "mapping symbols" found in ELF files. */ +static inline int is_mapping_symbol(const char *str) +{ + if (str[0] == '.' && str[1] == 'L') + return true; + if (str[0] == 'L' && str[1] == '0') + return true; + return str[0] == '$' && + (str[1] == 'a' || str[1] == 'd' || str[1] == 't' || str[1] == 'x') + && (str[2] == '\0' || str[2] == '.'); +} + +#endif /* _LINUX_MODULE_SYMBOL_H */ diff --git a/include/linux/namei.h b/include/linux/namei.h index 0d797f3367ca..1463cbda4888 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -57,12 +57,20 @@ static inline int user_path_at(int dfd, const char __user *name, unsigned flags, return user_path_at_empty(dfd, name, flags, path, NULL); } +struct dentry *lookup_one_qstr_excl(const struct qstr *name, + struct dentry *base, + unsigned int flags); extern int kern_path(const char *, unsigned, struct path *); extern struct dentry *kern_path_create(int, const char *, struct path *, unsigned int); extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int); extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); +int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, + struct path *parent, struct qstr *last, int *type, + const struct path *root); +int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, + unsigned int, struct path *); extern struct dentry *try_lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); @@ -81,6 +89,7 @@ extern int follow_down(struct path *path, unsigned int flags); extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); +extern struct dentry *lock_rename_child(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); extern int __must_check nd_jump_link(const struct path *path); diff --git a/include/linux/nfs.h b/include/linux/nfs.h index b06375e88e58..ceb70a926b95 100644 --- a/include/linux/nfs.h +++ b/include/linux/nfs.h @@ -10,6 +10,7 @@ #include <linux/sunrpc/msg_prot.h> #include <linux/string.h> +#include <linux/crc32.h> #include <uapi/linux/nfs.h> /* @@ -44,4 +45,23 @@ enum nfs3_stable_how { /* used by direct.c to mark verf as invalid */ NFS_INVALID_STABLE_HOW = -1 }; + +#ifdef CONFIG_CRC32 +/** + * nfs_fhandle_hash - calculate the crc32 hash for the filehandle + * @fh - pointer to filehandle + * + * returns a crc32 hash for the filehandle that is compatible with + * the one displayed by "wireshark". + */ +static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) +{ + return ~crc32_le(0xFFFFFFFF, &fh->data[0], fh->size); +} +#else /* CONFIG_CRC32 */ +static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh) +{ + return 0; +} +#endif /* CONFIG_CRC32 */ #endif /* _LINUX_NFS_H */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index bf89fe6fc3ba..279262057a92 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -31,6 +31,10 @@ #include <linux/sunrpc/auth.h> #include <linux/sunrpc/clnt.h> +#ifdef CONFIG_NFS_FSCACHE +#include <linux/netfs.h> +#endif + #include <linux/nfs.h> #include <linux/nfs2.h> #include <linux/nfs3.h> @@ -191,6 +195,39 @@ struct nfs_inode { /* Open contexts for shared mmap writes */ struct list_head open_files; + /* Keep track of out-of-order replies. + * The ooo array contains start/end pairs of + * numbers from the changeid sequence when + * the inode's iversion has been updated. + * It also contains end/start pair (i.e. reverse order) + * of sections of the changeid sequence that have + * been seen in replies from the server. + * Normally these should match and when both + * A:B and B:A are found in ooo, they are both removed. + * And if a reply with A:B causes an iversion update + * of A:B, then neither are added. + * When a reply has pre_change that doesn't match + * iversion, then the changeid pair and any consequent + * change in iversion ARE added. Later replies + * might fill in the gaps, or possibly a gap is caused + * by a change from another client. + * When a file or directory is opened, if the ooo table + * is not empty, then we assume the gaps were due to + * another client and we invalidate the cached data. + * + * We can only track a limited number of concurrent gaps. + * Currently that limit is 16. + * We allocate the table on demand. If there is insufficient + * memory, then we probably cannot cache the file anyway + * so there is no loss. + */ + struct { + int cnt; + struct { + u64 start, end; + } gap[16]; + } *ooo; + #if IS_ENABLED(CONFIG_NFS_V4) struct nfs4_cached_acl *nfs4_acl; /* NFSv4 state */ @@ -204,14 +241,15 @@ struct nfs_inode { /* how many bytes have been written/read and how many bytes queued up */ __u64 write_io; __u64 read_io; -#ifdef CONFIG_NFS_FSCACHE - struct fscache_cookie *fscache; -#endif - struct inode vfs_inode; - #ifdef CONFIG_NFS_V4_2 struct nfs4_xattr_cache *xattr_cache; #endif + union { + struct inode vfs_inode; +#ifdef CONFIG_NFS_FSCACHE + struct netfs_inode netfs; /* netfs context and VFS inode */ +#endif + }; }; struct nfs4_copy_state { @@ -276,7 +314,6 @@ struct nfs4_copy_state { #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ #define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ #define NFS_INO_PRESERVE_UNLINKED (4) /* preserve file if removed while open */ -#define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ #define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ @@ -329,15 +366,6 @@ static inline int NFS_STALE(const struct inode *inode) return test_bit(NFS_INO_STALE, &NFS_I(inode)->flags); } -static inline struct fscache_cookie *nfs_i_fscache(struct inode *inode) -{ -#ifdef CONFIG_NFS_FSCACHE - return NFS_I(inode)->fscache; -#else - return NULL; -#endif -} - static inline __u64 NFS_FILEID(const struct inode *inode) { return NFS_I(inode)->fileid; @@ -617,6 +645,20 @@ nfs_fileid_to_ino_t(u64 fileid) return ino; } +static inline void nfs_ooo_clear(struct nfs_inode *nfsi) +{ + nfsi->cache_validity &= ~NFS_INO_DATA_INVAL_DEFER; + kfree(nfsi->ooo); + nfsi->ooo = NULL; +} + +static inline bool nfs_ooo_test(struct nfs_inode *nfsi) +{ + return (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER) || + (nfsi->ooo && nfsi->ooo->cnt > 0); + +} + #define NFS_JUKEBOX_RETRY_TIME (5 * HZ) /* We need to block new opens while a file is being unlinked. diff --git a/include/linux/nfs_iostat.h b/include/linux/nfs_iostat.h index 027874c36c88..8d946089d151 100644 --- a/include/linux/nfs_iostat.h +++ b/include/linux/nfs_iostat.h @@ -119,16 +119,4 @@ enum nfs_stat_eventcounters { __NFSIOS_COUNTSMAX, }; -/* - * NFS local caching servicing counters - */ -enum nfs_stat_fscachecounters { - NFSIOS_FSCACHE_PAGES_READ_OK, - NFSIOS_FSCACHE_PAGES_READ_FAIL, - NFSIOS_FSCACHE_PAGES_WRITTEN_OK, - NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL, - NFSIOS_FSCACHE_PAGES_UNCACHED, - __NFSIOS_FSCACHEMAX, -}; - #endif /* _LINUX_NFS_IOSTAT */ diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index a2f1ca657623..aa9f4c6ebe26 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -105,6 +105,9 @@ struct nfs_pageio_descriptor { struct pnfs_layout_segment *pg_lseg; struct nfs_io_completion *pg_io_completion; struct nfs_direct_req *pg_dreq; +#ifdef CONFIG_NFS_FSCACHE + void *pg_netfs; +#endif unsigned int pg_bsize; /* default bsize for mirrors */ u32 pg_mirror_count; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index e86cf6642d21..29a1b39794bf 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -670,6 +670,7 @@ struct nfs_pgio_res { struct { unsigned int replen; /* used by read */ int eof; /* used by read */ + void * scratch; /* used by read */ }; struct { struct nfs_writeverf * verf; /* used by write */ @@ -1619,6 +1620,9 @@ struct nfs_pgio_header { const struct nfs_rw_ops *rw_ops; struct nfs_io_completion *io_completion; struct nfs_direct_req *dreq; +#ifdef CONFIG_NFS_FSCACHE + void *netfs; +#endif int pnfs_error; int error; /* merge with pnfs_error */ diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 1f62f7ba71ca..fa030d93b768 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -239,6 +239,7 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id); struct nvmem_device *of_nvmem_device_get(struct device_node *np, const char *name); +struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem); #else static inline struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id) @@ -251,6 +252,12 @@ static inline struct nvmem_device *of_nvmem_device_get(struct device_node *np, { return ERR_PTR(-EOPNOTSUPP); } + +static inline struct device_node * +of_nvmem_layout_get_container(struct nvmem_device *nvmem) +{ + return ERR_PTR(-EOPNOTSUPP); +} #endif /* CONFIG_NVMEM && CONFIG_OF */ #endif /* ifndef _LINUX_NVMEM_CONSUMER_H */ diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 0262b86194eb..dae26295e6be 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -9,6 +9,7 @@ #ifndef _LINUX_NVMEM_PROVIDER_H #define _LINUX_NVMEM_PROVIDER_H +#include <linux/device/driver.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/gpio/consumer.h> @@ -20,7 +21,8 @@ typedef int (*nvmem_reg_write_t)(void *priv, unsigned int offset, void *val, size_t bytes); /* used for vendor specific post processing of cell data */ typedef int (*nvmem_cell_post_process_t)(void *priv, const char *id, int index, - unsigned int offset, void *buf, size_t bytes); + unsigned int offset, void *buf, + size_t bytes); enum nvmem_type { NVMEM_TYPE_UNKNOWN = 0, @@ -50,18 +52,25 @@ struct nvmem_keepout { * struct nvmem_cell_info - NVMEM cell description * @name: Name. * @offset: Offset within the NVMEM device. + * @raw_len: Length of raw data (without post processing). * @bytes: Length of the cell. * @bit_offset: Bit offset if cell is smaller than a byte. * @nbits: Number of bits. * @np: Optional device_node pointer. + * @read_post_process: Callback for optional post processing of cell data + * on reads. + * @priv: Opaque data passed to the read_post_process hook. */ struct nvmem_cell_info { const char *name; unsigned int offset; + size_t raw_len; unsigned int bytes; unsigned int bit_offset; unsigned int nbits; struct device_node *np; + nvmem_cell_post_process_t read_post_process; + void *priv; }; /** @@ -82,12 +91,12 @@ struct nvmem_cell_info { * @no_of_node: Device should not use the parent's of_node even if it's !NULL. * @reg_read: Callback to read data. * @reg_write: Callback to write data. - * @cell_post_process: Callback for vendor specific post processing of cell data * @size: Device size. * @word_size: Minimum read/write access granularity. * @stride: Minimum read/write access stride. * @priv: User context passed to read/write callbacks. * @ignore_wp: Write Protect pin is managed by the provider. + * @layout: Fixed layout associated with this nvmem device. * * Note: A default "nvmem<id>" name will be assigned to the device if * no name is specified in its configuration. In such case "<id>" is @@ -109,11 +118,11 @@ struct nvmem_config { bool read_only; bool root_only; bool ignore_wp; + struct nvmem_layout *layout; struct device_node *of_node; bool no_of_node; nvmem_reg_read_t reg_read; nvmem_reg_write_t reg_write; - nvmem_cell_post_process_t cell_post_process; int size; int word_size; int stride; @@ -142,6 +151,38 @@ struct nvmem_cell_table { struct list_head node; }; +/** + * struct nvmem_layout - NVMEM layout definitions + * + * @name: Layout name. + * @of_match_table: Open firmware match table. + * @add_cells: Will be called if a nvmem device is found which + * has this layout. The function will add layout + * specific cells with nvmem_add_one_cell(). + * @fixup_cell_info: Will be called before a cell is added. Can be + * used to modify the nvmem_cell_info. + * @owner: Pointer to struct module. + * @node: List node. + * + * A nvmem device can hold a well defined structure which can just be + * evaluated during runtime. For example a TLV list, or a list of "name=val" + * pairs. A nvmem layout can parse the nvmem device and add appropriate + * cells. + */ +struct nvmem_layout { + const char *name; + const struct of_device_id *of_match_table; + int (*add_cells)(struct device *dev, struct nvmem_device *nvmem, + struct nvmem_layout *layout); + void (*fixup_cell_info)(struct nvmem_device *nvmem, + struct nvmem_layout *layout, + struct nvmem_cell_info *cell); + + /* private */ + struct module *owner; + struct list_head node; +}; + #if IS_ENABLED(CONFIG_NVMEM) struct nvmem_device *nvmem_register(const struct nvmem_config *cfg); @@ -156,6 +197,14 @@ void nvmem_del_cell_table(struct nvmem_cell_table *table); int nvmem_add_one_cell(struct nvmem_device *nvmem, const struct nvmem_cell_info *info); +int __nvmem_layout_register(struct nvmem_layout *layout, struct module *owner); +#define nvmem_layout_register(layout) \ + __nvmem_layout_register(layout, THIS_MODULE) +void nvmem_layout_unregister(struct nvmem_layout *layout); + +const void *nvmem_layout_get_match_data(struct nvmem_device *nvmem, + struct nvmem_layout *layout); + #else static inline struct nvmem_device *nvmem_register(const struct nvmem_config *c) @@ -179,5 +228,24 @@ static inline int nvmem_add_one_cell(struct nvmem_device *nvmem, return -EOPNOTSUPP; } +static inline int nvmem_layout_register(struct nvmem_layout *layout) +{ + return -EOPNOTSUPP; +} + +static inline void nvmem_layout_unregister(struct nvmem_layout *layout) {} + +static inline const void * +nvmem_layout_get_match_data(struct nvmem_device *nvmem, + struct nvmem_layout *layout) +{ + return NULL; +} + #endif /* CONFIG_NVMEM */ + +#define module_nvmem_layout_driver(__layout_driver) \ + module_driver(__layout_driver, nvmem_layout_register, \ + nvmem_layout_unregister) + #endif /* ifndef _LINUX_NVMEM_PROVIDER_H */ diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 9ac3df3fccf0..03f82c2c2ebf 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -2,47 +2,7 @@ #ifndef _LINUX_OBJTOOL_H #define _LINUX_OBJTOOL_H -#ifndef __ASSEMBLY__ - -#include <linux/types.h> - -/* - * This struct is used by asm and inline asm code to manually annotate the - * location of registers on the stack. - */ -struct unwind_hint { - u32 ip; - s16 sp_offset; - u8 sp_reg; - u8 type; - u8 signal; - u8 end; -}; -#endif - -/* - * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP - * (the caller's SP right before it made the call). Used for all callable - * functions, i.e. all C code and all callable asm functions. - * - * UNWIND_HINT_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset - * points to a fully populated pt_regs from a syscall, interrupt, or exception. - * - * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that - * sp_reg+sp_offset points to the iret return frame. - * - * UNWIND_HINT_FUNC: Generate the unwind metadata of a callable function. - * Useful for code which doesn't have an ELF function annotation. - * - * UNWIND_HINT_ENTRY: machine entry without stack, SYSCALL/SYSENTER etc. - */ -#define UNWIND_HINT_TYPE_CALL 0 -#define UNWIND_HINT_TYPE_REGS 1 -#define UNWIND_HINT_TYPE_REGS_PARTIAL 2 -#define UNWIND_HINT_TYPE_FUNC 3 -#define UNWIND_HINT_TYPE_ENTRY 4 -#define UNWIND_HINT_TYPE_SAVE 5 -#define UNWIND_HINT_TYPE_RESTORE 6 +#include <linux/objtool_types.h> #ifdef CONFIG_OBJTOOL @@ -50,7 +10,7 @@ struct unwind_hint { #ifndef __ASSEMBLY__ -#define UNWIND_HINT(sp_reg, sp_offset, type, signal, end) \ +#define UNWIND_HINT(type, sp_reg, sp_offset, signal) \ "987: \n\t" \ ".pushsection .discard.unwind_hints\n\t" \ /* struct unwind_hint */ \ @@ -59,7 +19,6 @@ struct unwind_hint { ".byte " __stringify(sp_reg) "\n\t" \ ".byte " __stringify(type) "\n\t" \ ".byte " __stringify(signal) "\n\t" \ - ".byte " __stringify(end) "\n\t" \ ".balign 4 \n\t" \ ".popsection\n\t" @@ -89,7 +48,7 @@ struct unwind_hint { #define ANNOTATE_NOENDBR \ "986: \n\t" \ ".pushsection .discard.noendbr\n\t" \ - _ASM_PTR " 986b\n\t" \ + ".long 986b - .\n\t" \ ".popsection\n\t" #define ASM_REACHABLE \ @@ -107,7 +66,7 @@ struct unwind_hint { #define ANNOTATE_INTRA_FUNCTION_CALL \ 999: \ .pushsection .discard.intra_function_calls; \ - .long 999b; \ + .long 999b - .; \ .popsection; /* @@ -131,23 +90,22 @@ struct unwind_hint { * the debuginfo as necessary. It will also warn if it sees any * inconsistencies. */ -.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 end=0 -.Lunwind_hint_ip_\@: +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 +.Lhere_\@: .pushsection .discard.unwind_hints /* struct unwind_hint */ - .long .Lunwind_hint_ip_\@ - . + .long .Lhere_\@ - . .short \sp_offset .byte \sp_reg .byte \type .byte \signal - .byte \end .balign 4 .popsection .endm .macro STACK_FRAME_NON_STANDARD func:req .pushsection .discard.func_stack_frame_non_standard, "aw" - _ASM_PTR \func + .long \func - . .popsection .endm @@ -160,8 +118,24 @@ struct unwind_hint { .macro ANNOTATE_NOENDBR .Lhere_\@: .pushsection .discard.noendbr - .quad .Lhere_\@ + .long .Lhere_\@ - . + .popsection +.endm + +/* + * Use objtool to validate the entry requirement that all code paths do + * VALIDATE_UNRET_END before RET. + * + * NOTE: The macro must be used at the beginning of a global symbol, otherwise + * it will be ignored. + */ +.macro VALIDATE_UNRET_BEGIN +#if defined(CONFIG_NOINSTR_VALIDATION) && defined(CONFIG_CPU_UNRET_ENTRY) +.Lhere_\@: + .pushsection .discard.validate_unret + .long .Lhere_\@ - . .popsection +#endif .endm .macro REACHABLE @@ -177,15 +151,14 @@ struct unwind_hint { #ifndef __ASSEMBLY__ -#define UNWIND_HINT(sp_reg, sp_offset, type, signal, end) \ - "\n\t" +#define UNWIND_HINT(type, sp_reg, sp_offset, signal) "\n\t" #define STACK_FRAME_NON_STANDARD(func) #define STACK_FRAME_NON_STANDARD_FP(func) #define ANNOTATE_NOENDBR #define ASM_REACHABLE #else #define ANNOTATE_INTRA_FUNCTION_CALL -.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 end=0 +.macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm diff --git a/include/linux/objtool_types.h b/include/linux/objtool_types.h new file mode 100644 index 000000000000..453a4f4ef39d --- /dev/null +++ b/include/linux/objtool_types.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_OBJTOOL_TYPES_H +#define _LINUX_OBJTOOL_TYPES_H + +#ifndef __ASSEMBLY__ + +#include <linux/types.h> + +/* + * This struct is used by asm and inline asm code to manually annotate the + * location of registers on the stack. + */ +struct unwind_hint { + u32 ip; + s16 sp_offset; + u8 sp_reg; + u8 type; + u8 signal; +}; + +#endif /* __ASSEMBLY__ */ + +/* + * UNWIND_HINT_TYPE_UNDEFINED: A blind spot in ORC coverage which can result in + * a truncated and unreliable stack unwind. + * + * UNWIND_HINT_TYPE_END_OF_STACK: The end of the kernel stack unwind before + * hitting user entry, boot code, or fork entry (when there are no pt_regs + * available). + * + * UNWIND_HINT_TYPE_CALL: Indicates that sp_reg+sp_offset resolves to PREV_SP + * (the caller's SP right before it made the call). Used for all callable + * functions, i.e. all C code and all callable asm functions. + * + * UNWIND_HINT_TYPE_REGS: Used in entry code to indicate that sp_reg+sp_offset + * points to a fully populated pt_regs from a syscall, interrupt, or exception. + * + * UNWIND_HINT_TYPE_REGS_PARTIAL: Used in entry code to indicate that + * sp_reg+sp_offset points to the iret return frame. + * + * UNWIND_HINT_TYPE_FUNC: Generate the unwind metadata of a callable function. + * Useful for code which doesn't have an ELF function annotation. + * + * UNWIND_HINT_TYPE_{SAVE,RESTORE}: Save the unwind metadata at a certain + * location so that it can be restored later. + */ +#define UNWIND_HINT_TYPE_UNDEFINED 0 +#define UNWIND_HINT_TYPE_END_OF_STACK 1 +#define UNWIND_HINT_TYPE_CALL 2 +#define UNWIND_HINT_TYPE_REGS 3 +#define UNWIND_HINT_TYPE_REGS_PARTIAL 4 +/* The below hint types don't have corresponding ORC types */ +#define UNWIND_HINT_TYPE_FUNC 5 +#define UNWIND_HINT_TYPE_SAVE 6 +#define UNWIND_HINT_TYPE_RESTORE 7 + +#endif /* _LINUX_OBJTOOL_TYPES_H */ diff --git a/include/linux/of.h b/include/linux/of.h index 0af611307db2..6ecde0515677 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -16,14 +16,10 @@ #include <linux/errno.h> #include <linux/kobject.h> #include <linux/mod_devicetable.h> -#include <linux/spinlock.h> -#include <linux/topology.h> -#include <linux/notifier.h> #include <linux/property.h> #include <linux/list.h> #include <asm/byteorder.h> -#include <asm/errno.h> typedef u32 phandle; typedef u32 ihandle; @@ -145,7 +141,6 @@ extern struct device_node *of_root; extern struct device_node *of_chosen; extern struct device_node *of_aliases; extern struct device_node *of_stdout; -extern raw_spinlock_t devtree_lock; /* * struct device_node flag descriptions @@ -361,6 +356,8 @@ extern const void *of_get_property(const struct device_node *node, const char *name, int *lenp); extern struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); +extern struct device_node *of_cpu_device_node_get(int cpu); +extern int of_cpu_node_to_id(struct device_node *np); extern struct device_node *of_get_next_cpu_node(struct device_node *prev); extern struct device_node *of_get_cpu_state_node(struct device_node *cpu_node, int index); @@ -373,7 +370,9 @@ extern int of_n_addr_cells(struct device_node *np); extern int of_n_size_cells(struct device_node *np); extern const struct of_device_id *of_match_node( const struct of_device_id *matches, const struct device_node *node); -extern int of_modalias_node(struct device_node *node, char *modalias, int len); +extern const void *of_device_get_match_data(const struct device *dev); +extern int of_alias_from_compatible(const struct device_node *node, char *alias, + int len); extern void of_print_phandle_args(const char *msg, const struct of_phandle_args *args); extern int __of_parse_phandle_with_args(const struct device_node *np, const char *list_name, const char *cells_name, int cell_count, @@ -384,6 +383,10 @@ extern int of_parse_phandle_with_args_map(const struct device_node *np, extern int of_count_phandle_with_args(const struct device_node *np, const char *list_name, const char *cells_name); +/* module functions */ +extern ssize_t of_modalias(const struct device_node *np, char *str, ssize_t len); +extern int of_request_module(const struct device_node *np); + /* phandle iterator functions */ extern int of_phandle_iterator_init(struct of_phandle_iterator *it, const struct device_node *np, @@ -439,8 +442,6 @@ const char *of_prop_next_string(struct property *prop, const char *cur); bool of_console_check(struct device_node *dn, char *name, int index); -extern int of_cpu_node_to_id(struct device_node *np); - int of_map_id(struct device_node *np, u32 id, const char *map_name, const char *map_mask_name, struct device_node **target, u32 *id_out); @@ -635,6 +636,16 @@ static inline struct device_node *of_get_cpu_node(int cpu, return NULL; } +static inline struct device_node *of_cpu_device_node_get(int cpu) +{ + return NULL; +} + +static inline int of_cpu_node_to_id(struct device_node *np) +{ + return -ENODEV; +} + static inline struct device_node *of_get_next_cpu_node(struct device_node *prev) { return NULL; @@ -741,6 +752,17 @@ static inline int of_count_phandle_with_args(const struct device_node *np, return -ENOSYS; } +static inline ssize_t of_modalias(const struct device_node *np, char *str, + ssize_t len) +{ + return -ENODEV; +} + +static inline int of_request_module(const struct device_node *np) +{ + return -ENODEV; +} + static inline int of_phandle_iterator_init(struct of_phandle_iterator *it, const struct device_node *np, const char *list_name, @@ -837,11 +859,6 @@ static inline void of_property_clear_flag(struct property *p, unsigned long flag { } -static inline int of_cpu_node_to_id(struct device_node *np) -{ - return -ENODEV; -} - static inline int of_map_id(struct device_node *np, u32 id, const char *map_name, const char *map_mask_name, struct device_node **target, u32 *id_out) @@ -854,6 +871,11 @@ static inline phys_addr_t of_dma_get_max_cpu_address(struct device_node *np) return PHYS_ADDR_MAX; } +static inline const void *of_device_get_match_data(const struct device *dev) +{ + return NULL; +} + #define of_match_ptr(_ptr) NULL #define of_match_node(_matches, _node) NULL #endif /* CONFIG_OF */ @@ -1512,6 +1534,8 @@ enum of_reconfig_change { OF_RECONFIG_CHANGE_REMOVE, }; +struct notifier_block; + #ifdef CONFIG_OF_DYNAMIC extern int of_reconfig_notifier_register(struct notifier_block *); extern int of_reconfig_notifier_unregister(struct notifier_block *); diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 376671594746..26a19daf0d09 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -35,6 +35,22 @@ struct of_pci_range { for (; of_pci_range_parser_one(parser, range);) #define for_each_of_range for_each_of_pci_range +/* + * of_range_count - Get the number of "ranges" or "dma-ranges" entries + * @parser: Parser state initialized by of_range_parser_init() + * + * Returns the number of entries or 0 if none. + * + * Note that calling this within or after the for_each_of_range() iterator will + * be inaccurate giving the number of entries remaining. + */ +static inline int of_range_count(const struct of_range_parser *parser) +{ + if (!parser || !parser->node || !parser->range || parser->range == parser->end) + return 0; + return (parser->end - parser->range) / (parser->na + parser->pna + parser->ns); +} + /* Translate a DMA address from device space to CPU space */ extern u64 of_translate_dma_address(struct device_node *dev, const __be32 *in_addr); @@ -56,6 +72,8 @@ void __iomem *of_io_request_and_map(struct device_node *device, extern const __be32 *__of_get_address(struct device_node *dev, int index, int bar_no, u64 *size, unsigned int *flags); +int of_property_read_reg(struct device_node *np, int idx, u64 *addr, u64 *size); + extern int of_pci_range_parser_init(struct of_pci_range_parser *parser, struct device_node *node); extern int of_pci_dma_range_parser_init(struct of_pci_range_parser *parser, @@ -68,6 +86,8 @@ extern int of_pci_address_to_resource(struct device_node *dev, int bar, extern int of_pci_range_to_resource(struct of_pci_range *range, struct device_node *np, struct resource *res); +extern int of_range_to_resource(struct device_node *np, int index, + struct resource *res); extern bool of_dma_is_coherent(struct device_node *np); #else /* CONFIG_OF_ADDRESS */ static inline void __iomem *of_io_request_and_map(struct device_node *device, @@ -88,6 +108,11 @@ static inline const __be32 *__of_get_address(struct device_node *dev, int index, return NULL; } +static inline int of_property_read_reg(struct device_node *np, int idx, u64 *addr, u64 *size) +{ + return -ENOSYS; +} + static inline int of_pci_range_parser_init(struct of_pci_range_parser *parser, struct device_node *node) { @@ -120,6 +145,12 @@ static inline int of_pci_range_to_resource(struct of_pci_range *range, return -ENOSYS; } +static inline int of_range_to_resource(struct device_node *np, int index, + struct resource *res) +{ + return -ENOSYS; +} + static inline bool of_dma_is_coherent(struct device_node *np) { return false; diff --git a/include/linux/of_device.h b/include/linux/of_device.h index f4b57614979d..2c7a3d4bc775 100644 --- a/include/linux/of_device.h +++ b/include/linux/of_device.h @@ -2,14 +2,14 @@ #ifndef _LINUX_OF_DEVICE_H #define _LINUX_OF_DEVICE_H -#include <linux/cpu.h> #include <linux/platform_device.h> #include <linux/of_platform.h> /* temporary until merge */ #include <linux/of.h> -#include <linux/mod_devicetable.h> struct device; +struct of_device_id; +struct kobj_uevent_env; #ifdef CONFIG_OF extern const struct of_device_id *of_match_device( @@ -26,27 +26,11 @@ static inline int of_driver_match_device(struct device *dev, return of_match_device(drv->of_match_table, dev) != NULL; } -extern int of_device_add(struct platform_device *pdev); -extern int of_device_register(struct platform_device *ofdev); -extern void of_device_unregister(struct platform_device *ofdev); - -extern const void *of_device_get_match_data(const struct device *dev); - extern ssize_t of_device_modalias(struct device *dev, char *str, ssize_t len); -extern int of_device_request_module(struct device *dev); extern void of_device_uevent(const struct device *dev, struct kobj_uevent_env *env); extern int of_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *env); -static inline struct device_node *of_cpu_device_node_get(int cpu) -{ - struct device *cpu_dev; - cpu_dev = get_cpu_device(cpu); - if (!cpu_dev) - return of_get_cpu_node(cpu, NULL); - return of_node_get(cpu_dev->of_node); -} - int of_dma_configure_id(struct device *dev, struct device_node *np, bool force_dma, const u32 *id); @@ -67,22 +51,12 @@ static inline int of_driver_match_device(struct device *dev, static inline void of_device_uevent(const struct device *dev, struct kobj_uevent_env *env) { } -static inline const void *of_device_get_match_data(const struct device *dev) -{ - return NULL; -} - static inline int of_device_modalias(struct device *dev, char *str, ssize_t len) { return -ENODEV; } -static inline int of_device_request_module(struct device *dev) -{ - return -ENODEV; -} - static inline int of_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *env) { @@ -95,11 +69,6 @@ static inline const struct of_device_id *of_match_device( return NULL; } -static inline struct device_node *of_cpu_device_node_get(int cpu) -{ - return NULL; -} - static inline int of_dma_configure_id(struct device *dev, struct device_node *np, bool force_dma, diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h index d15b6cd5e1c3..d8045bcfc35e 100644 --- a/include/linux/of_platform.h +++ b/include/linux/of_platform.h @@ -6,12 +6,13 @@ * <benh@kernel.crashing.org> */ -#include <linux/device.h> #include <linux/mod_devicetable.h> -#include <linux/pm.h> #include <linux/of_device.h> #include <linux/platform_device.h> +struct device; +struct of_device_id; + /** * struct of_dev_auxdata - lookup table entry for device names & platform_data * @compatible: compatible value of node to match against node @@ -52,6 +53,11 @@ extern const struct of_device_id of_default_bus_match_table[]; extern struct platform_device *of_device_alloc(struct device_node *np, const char *bus_id, struct device *parent); + +extern int of_device_add(struct platform_device *pdev); +extern int of_device_register(struct platform_device *ofdev); +extern void of_device_unregister(struct platform_device *ofdev); + #ifdef CONFIG_OF extern struct platform_device *of_find_device_by_node(struct device_node *np); #else diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 1b89dd027d48..1c68d67b832f 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -136,9 +136,6 @@ enum pageflags { PG_arch_2, PG_arch_3, #endif -#ifdef CONFIG_KASAN_HW_TAGS - PG_skip_kasan_poison, -#endif __NR_PAGEFLAGS, PG_readahead = PG_reclaim, @@ -590,12 +587,6 @@ TESTCLEARFLAG(Young, young, PF_ANY) PAGEFLAG(Idle, idle, PF_ANY) #endif -#ifdef CONFIG_KASAN_HW_TAGS -PAGEFLAG(SkipKASanPoison, skip_kasan_poison, PF_HEAD) -#else -PAGEFLAG_FALSE(SkipKASanPoison, skip_kasan_poison) -#endif - /* * PageReported() is used to track reported free pages within the Buddy * allocator. We can use the non-atomic version of the test and set @@ -815,14 +806,9 @@ static inline void ClearPageCompound(struct page *page) #ifdef CONFIG_HUGETLB_PAGE int PageHuge(struct page *page); -int PageHeadHuge(struct page *page); -static inline bool folio_test_hugetlb(struct folio *folio) -{ - return PageHeadHuge(&folio->page); -} +bool folio_test_hugetlb(struct folio *folio); #else TESTPAGEFLAG_FALSE(Huge, hugetlb) -TESTPAGEFLAG_FALSE(HeadHuge, headhuge) #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -917,9 +903,14 @@ static inline bool is_page_hwpoison(struct page *page) #define PageType(page, flag) \ ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) +static inline int page_type_has_type(unsigned int page_type) +{ + return (int)page_type < PAGE_MAPCOUNT_RESERVE; +} + static inline int page_has_type(struct page *page) { - return (int)page->page_type < PAGE_MAPCOUNT_RESERVE; + return page_type_has_type(page->page_type); } #define PAGE_TYPE_OPS(uname, lname) \ diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index bc2e39090a1f..67314f648aeb 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -29,8 +29,6 @@ struct page_ext_operations { bool need_shared_flags; }; -extern bool deferred_struct_pages; - #ifdef CONFIG_PAGE_EXTENSION /* diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 5f1ae07d724b..e83c4c095041 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -41,14 +41,14 @@ extern unsigned int pageblock_order; * Huge pages are a constant size, but don't exceed the maximum allocation * granularity. */ -#define pageblock_order min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_ORDER - 1) +#define pageblock_order min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_ORDER) #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ #else /* CONFIG_HUGETLB_PAGE */ /* If huge pages are not used, group by MAX_ORDER_NR_PAGES */ -#define pageblock_order (MAX_ORDER-1) +#define pageblock_order MAX_ORDER #endif /* CONFIG_HUGETLB_PAGE */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index c4698dcc70ba..a56308a9d1a4 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -504,11 +504,11 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, #define FGP_NOFS 0x00000010 #define FGP_NOWAIT 0x00000020 #define FGP_FOR_MMAP 0x00000040 -#define FGP_ENTRY 0x00000080 -#define FGP_STABLE 0x00000100 +#define FGP_STABLE 0x00000080 #define FGP_WRITEBEGIN (FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE) +void *filemap_get_entry(struct address_space *mapping, pgoff_t index); struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, int fgp_flags, gfp_t gfp); struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, @@ -522,7 +522,8 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, * Looks up the page cache entry at @mapping & @index. If a folio is * present, it is returned with an increased refcount. * - * Otherwise, %NULL is returned. + * Return: A folio or ERR_PTR(-ENOENT) if there is no folio in the cache for + * this index. Will not return a shadow, swap or DAX entry. */ static inline struct folio *filemap_get_folio(struct address_space *mapping, pgoff_t index) @@ -539,8 +540,8 @@ static inline struct folio *filemap_get_folio(struct address_space *mapping, * present, it is returned locked with an increased refcount. * * Context: May sleep. - * Return: A folio or %NULL if there is no folio in the cache for this - * index. Will not return a shadow, swap or DAX entry. + * Return: A folio or ERR_PTR(-ENOENT) if there is no folio in the cache for + * this index. Will not return a shadow, swap or DAX entry. */ static inline struct folio *filemap_lock_folio(struct address_space *mapping, pgoff_t index) @@ -557,8 +558,8 @@ static inline struct folio *filemap_lock_folio(struct address_space *mapping, * a new folio is created. The folio is locked, marked as accessed, and * returned. * - * Return: A found or created folio. NULL if no folio is found and failed to - * create a folio. + * Return: A found or created folio. ERR_PTR(-ENOMEM) if no folio is found + * and failed to create a folio. */ static inline struct folio *filemap_grab_folio(struct address_space *mapping, pgoff_t index) diff --git a/include/linux/pci-doe.h b/include/linux/pci-doe.h index 43765eaf2342..1f14aed4354b 100644 --- a/include/linux/pci-doe.h +++ b/include/linux/pci-doe.h @@ -13,69 +13,13 @@ #ifndef LINUX_PCI_DOE_H #define LINUX_PCI_DOE_H -struct pci_doe_protocol { - u16 vid; - u8 type; -}; - struct pci_doe_mb; -/** - * struct pci_doe_task - represents a single query/response - * - * @prot: DOE Protocol - * @request_pl: The request payload - * @request_pl_sz: Size of the request payload (bytes) - * @response_pl: The response payload - * @response_pl_sz: Size of the response payload (bytes) - * @rv: Return value. Length of received response or error (bytes) - * @complete: Called when task is complete - * @private: Private data for the consumer - * @work: Used internally by the mailbox - * @doe_mb: Used internally by the mailbox - * - * Payloads are treated as opaque byte streams which are transmitted verbatim, - * without byte-swapping. If payloads contain little-endian register values, - * the caller is responsible for conversion with cpu_to_le32() / le32_to_cpu(). - * - * The payload sizes and rv are specified in bytes with the following - * restrictions concerning the protocol. - * - * 1) The request_pl_sz must be a multiple of double words (4 bytes) - * 2) The response_pl_sz must be >= a single double word (4 bytes) - * 3) rv is returned as bytes but it will be a multiple of double words - * - * NOTE there is no need for the caller to initialize work or doe_mb. - */ -struct pci_doe_task { - struct pci_doe_protocol prot; - __le32 *request_pl; - size_t request_pl_sz; - __le32 *response_pl; - size_t response_pl_sz; - int rv; - void (*complete)(struct pci_doe_task *task); - void *private; - - /* No need for the user to initialize these fields */ - struct work_struct work; - struct pci_doe_mb *doe_mb; -}; - -/** - * pci_doe_for_each_off - Iterate each DOE capability - * @pdev: struct pci_dev to iterate - * @off: u16 of config space offset of each mailbox capability found - */ -#define pci_doe_for_each_off(pdev, off) \ - for (off = pci_find_next_ext_capability(pdev, off, \ - PCI_EXT_CAP_ID_DOE); \ - off > 0; \ - off = pci_find_next_ext_capability(pdev, off, \ - PCI_EXT_CAP_ID_DOE)) +struct pci_doe_mb *pci_find_doe_mailbox(struct pci_dev *pdev, u16 vendor, + u8 type); -struct pci_doe_mb *pcim_doe_create_mb(struct pci_dev *pdev, u16 cap_offset); -bool pci_doe_supports_prot(struct pci_doe_mb *doe_mb, u16 vid, u8 type); -int pci_doe_submit_task(struct pci_doe_mb *doe_mb, struct pci_doe_task *task); +int pci_doe(struct pci_doe_mb *doe_mb, u16 vendor, u8 type, + const void *request, size_t request_sz, + void *response, size_t response_sz); #endif diff --git a/include/linux/pci.h b/include/linux/pci.h index a5dda515fcd1..60b8772b5bd4 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -512,6 +512,9 @@ struct pci_dev { #ifdef CONFIG_PCI_P2PDMA struct pci_p2pdma __rcu *p2pdma; #endif +#ifdef CONFIG_PCI_DOE + struct xarray doe_mbs; /* Data Object Exchange mailboxes */ +#endif u16 acs_cap; /* ACS Capability offset */ phys_addr_t rom; /* Physical address if not from BAR */ size_t romlen; /* Length if not from BAR */ @@ -1445,10 +1448,44 @@ int devm_request_pci_bus_resources(struct device *dev, /* Temporary until new and working PCI SBR API in place */ int pci_bridge_secondary_bus_reset(struct pci_dev *dev); -#define pci_bus_for_each_resource(bus, res, i) \ - for (i = 0; \ - (res = pci_bus_resource_n(bus, i)) || i < PCI_BRIDGE_RESOURCE_NUM; \ - i++) +#define __pci_bus_for_each_res0(bus, res, ...) \ + for (unsigned int __b = 0; \ + (res = pci_bus_resource_n(bus, __b)) || __b < PCI_BRIDGE_RESOURCE_NUM; \ + __b++) + +#define __pci_bus_for_each_res1(bus, res, __b) \ + for (__b = 0; \ + (res = pci_bus_resource_n(bus, __b)) || __b < PCI_BRIDGE_RESOURCE_NUM; \ + __b++) + +/** + * pci_bus_for_each_resource - iterate over PCI bus resources + * @bus: the PCI bus + * @res: pointer to the current resource + * @...: optional index of the current resource + * + * Iterate over PCI bus resources. The first part is to go over PCI bus + * resource array, which has at most the %PCI_BRIDGE_RESOURCE_NUM entries. + * After that continue with the separate list of the additional resources, + * if not empty. That's why the Logical OR is being used. + * + * Possible usage: + * + * struct pci_bus *bus = ...; + * struct resource *res; + * unsigned int i; + * + * // With optional index + * pci_bus_for_each_resource(bus, res, i) + * pr_info("PCI bus resource[%u]: %pR\n", i, res); + * + * // Without index + * pci_bus_for_each_resource(bus, res) + * _do_something_(res); + */ +#define pci_bus_for_each_resource(bus, res, ...) \ + CONCATENATE(__pci_bus_for_each_res, COUNT_ARGS(__VA_ARGS__)) \ + (bus, res, __VA_ARGS__) int __must_check pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res, resource_size_t size, @@ -1997,14 +2034,27 @@ int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma); * These helpers provide future and backwards compatibility * for accessing popular PCI BAR info */ -#define pci_resource_start(dev, bar) ((dev)->resource[(bar)].start) -#define pci_resource_end(dev, bar) ((dev)->resource[(bar)].end) -#define pci_resource_flags(dev, bar) ((dev)->resource[(bar)].flags) -#define pci_resource_len(dev,bar) \ - ((pci_resource_end((dev), (bar)) == 0) ? 0 : \ - \ - (pci_resource_end((dev), (bar)) - \ - pci_resource_start((dev), (bar)) + 1)) +#define pci_resource_n(dev, bar) (&(dev)->resource[(bar)]) +#define pci_resource_start(dev, bar) (pci_resource_n(dev, bar)->start) +#define pci_resource_end(dev, bar) (pci_resource_n(dev, bar)->end) +#define pci_resource_flags(dev, bar) (pci_resource_n(dev, bar)->flags) +#define pci_resource_len(dev,bar) \ + (pci_resource_end((dev), (bar)) ? \ + resource_size(pci_resource_n((dev), (bar))) : 0) + +#define __pci_dev_for_each_res0(dev, res, ...) \ + for (unsigned int __b = 0; \ + res = pci_resource_n(dev, __b), __b < PCI_NUM_RESOURCES; \ + __b++) + +#define __pci_dev_for_each_res1(dev, res, __b) \ + for (__b = 0; \ + res = pci_resource_n(dev, __b), __b < PCI_NUM_RESOURCES; \ + __b++) + +#define pci_dev_for_each_resource(dev, res, ...) \ + CONCATENATE(__pci_dev_for_each_res, COUNT_ARGS(__VA_ARGS__)) \ + (dev, res, __VA_ARGS__) /* * Similar to the helpers above, these manipulate per-pci_dev diff --git a/include/linux/pe.h b/include/linux/pe.h index 6ffabf1e6d03..5e1e11540870 100644 --- a/include/linux/pe.h +++ b/include/linux/pe.h @@ -118,6 +118,9 @@ #define IMAGE_DLLCHARACTERISTICS_WDM_DRIVER 0x2000 #define IMAGE_DLLCHARACTERISTICS_TERMINAL_SERVER_AWARE 0x8000 +#define IMAGE_DLLCHARACTERISTICS_EX_CET_COMPAT 0x0001 +#define IMAGE_DLLCHARACTERISTICS_EX_FORWARD_CFI_COMPAT 0x0040 + /* they actually defined 0x00000000 as well, but I think we'll skip that one. */ #define IMAGE_SCN_RESERVED_0 0x00000001 #define IMAGE_SCN_RESERVED_1 0x00000002 @@ -165,6 +168,7 @@ #define IMAGE_SCN_MEM_WRITE 0x80000000 /* writeable */ #define IMAGE_DEBUG_TYPE_CODEVIEW 2 +#define IMAGE_DEBUG_TYPE_EX_DLLCHARACTERISTICS 20 #ifndef __ASSEMBLY__ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index c63cd44777ec..c5a51481bbb9 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -817,7 +817,7 @@ static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) #endif #ifndef flush_tlb_fix_spurious_fault -#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address) +#define flush_tlb_fix_spurious_fault(vma, address, ptep) flush_tlb_page(vma, address) #endif /* @@ -1191,9 +1191,10 @@ static inline void untrack_pfn(struct vm_area_struct *vma, } /* - * untrack_pfn_moved is called while mremapping a pfnmap for a new region. + * untrack_pfn_clear is called while mremapping a pfnmap for a new region + * or fails to copy pgtable during duplicate vm area. */ -static inline void untrack_pfn_moved(struct vm_area_struct *vma) +static inline void untrack_pfn_clear(struct vm_area_struct *vma) { } #else @@ -1205,7 +1206,7 @@ extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, extern int track_pfn_copy(struct vm_area_struct *vma); extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size, bool mm_wr_locked); -extern void untrack_pfn_moved(struct vm_area_struct *vma); +extern void untrack_pfn_clear(struct vm_area_struct *vma); #endif #ifdef CONFIG_MMU diff --git a/include/linux/platform_data/spi-s3c64xx.h b/include/linux/platform_data/spi-s3c64xx.h index 5df1ace6d2c9..3101152ce449 100644 --- a/include/linux/platform_data/spi-s3c64xx.h +++ b/include/linux/platform_data/spi-s3c64xx.h @@ -29,6 +29,7 @@ struct s3c64xx_spi_csinfo { * struct s3c64xx_spi_info - SPI Controller defining structure * @src_clk_nr: Clock source index for the CLK_CFG[SPI_CLKSEL] field. * @num_cs: Number of CS this controller emulates. + * @no_cs: Used when CS line is not connected. * @cfg_gpio: Configure pins for this SPI controller. */ struct s3c64xx_spi_info { diff --git a/include/linux/platform_data/usb3503.h b/include/linux/platform_data/usb3503.h index d01ef97ddf36..f3c942f396f8 100644 --- a/include/linux/platform_data/usb3503.h +++ b/include/linux/platform_data/usb3503.h @@ -12,6 +12,7 @@ enum usb3503_mode { USB3503_MODE_UNKNOWN, USB3503_MODE_HUB, USB3503_MODE_STANDBY, + USB3503_MODE_BYPASS, }; struct usb3503_platform_data { diff --git a/include/linux/power/generic-adc-battery.h b/include/linux/power/generic-adc-battery.h deleted file mode 100644 index c68cbf34cd34..000000000000 --- a/include/linux/power/generic-adc-battery.h +++ /dev/null @@ -1,23 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2012, Anish Kumar <anish198519851985@gmail.com> - */ - -#ifndef GENERIC_ADC_BATTERY_H -#define GENERIC_ADC_BATTERY_H - -/** - * struct gab_platform_data - platform_data for generic adc iio battery driver. - * @battery_info: recommended structure to specify static power supply - * parameters - * @cal_charge: calculate charge level. - * @jitter_delay: delay required after the interrupt to check battery - * status.Default set is 10ms. - */ -struct gab_platform_data { - struct power_supply_info battery_info; - int (*cal_charge)(long value); - int jitter_delay; -}; - -#endif /* GENERIC_ADC_BATTERY_H */ diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index aa2c4a7c4826..a427f13c757f 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -301,6 +301,7 @@ struct power_supply { bool initialized; bool removing; atomic_t use_cnt; + struct power_supply_battery_info *battery_info; #ifdef CONFIG_THERMAL struct thermal_zone_device *tzd; struct thermal_cooling_device *tcd; @@ -791,10 +792,17 @@ devm_power_supply_get_by_phandle(struct device *dev, const char *property) { return NULL; } #endif /* CONFIG_OF */ +extern const enum power_supply_property power_supply_battery_info_properties[]; +extern const size_t power_supply_battery_info_properties_size; extern int power_supply_get_battery_info(struct power_supply *psy, struct power_supply_battery_info **info_out); extern void power_supply_put_battery_info(struct power_supply *psy, struct power_supply_battery_info *info); +extern bool power_supply_battery_info_has_prop(struct power_supply_battery_info *info, + enum power_supply_property psp); +extern int power_supply_battery_info_get_prop(struct power_supply_battery_info *info, + enum power_supply_property psp, + union power_supply_propval *val); extern int power_supply_ocv2cap_simple(struct power_supply_battery_ocv_table *table, int table_len, int ocv); extern struct power_supply_battery_ocv_table * diff --git a/include/linux/property.h b/include/linux/property.h index 0a29db15ff34..66df1a15d518 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -16,7 +16,6 @@ #include <linux/types.h> struct device; -struct net_device; enum dev_prop_type { DEV_PROP_U8, @@ -40,20 +39,20 @@ struct fwnode_handle *__dev_fwnode(struct device *dev); const struct device *: __dev_fwnode_const, \ struct device *: __dev_fwnode)(dev) -bool device_property_present(struct device *dev, const char *propname); -int device_property_read_u8_array(struct device *dev, const char *propname, +bool device_property_present(const struct device *dev, const char *propname); +int device_property_read_u8_array(const struct device *dev, const char *propname, u8 *val, size_t nval); -int device_property_read_u16_array(struct device *dev, const char *propname, +int device_property_read_u16_array(const struct device *dev, const char *propname, u16 *val, size_t nval); -int device_property_read_u32_array(struct device *dev, const char *propname, +int device_property_read_u32_array(const struct device *dev, const char *propname, u32 *val, size_t nval); -int device_property_read_u64_array(struct device *dev, const char *propname, +int device_property_read_u64_array(const struct device *dev, const char *propname, u64 *val, size_t nval); -int device_property_read_string_array(struct device *dev, const char *propname, +int device_property_read_string_array(const struct device *dev, const char *propname, const char **val, size_t nval); -int device_property_read_string(struct device *dev, const char *propname, +int device_property_read_string(const struct device *dev, const char *propname, const char **val); -int device_property_match_string(struct device *dev, +int device_property_match_string(const struct device *dev, const char *propname, const char *string); bool fwnode_property_present(const struct fwnode_handle *fwnode, @@ -105,11 +104,11 @@ struct fwnode_handle *fwnode_get_next_parent(struct fwnode_handle *fwnode); for (parent = fwnode_get_parent(fwnode); parent; \ parent = fwnode_get_next_parent(parent)) -struct device *fwnode_get_next_parent_dev(struct fwnode_handle *fwnode); +struct device *fwnode_get_next_parent_dev(const struct fwnode_handle *fwnode); unsigned int fwnode_count_parents(const struct fwnode_handle *fwn); struct fwnode_handle *fwnode_get_nth_parent(struct fwnode_handle *fwn, unsigned int depth); -bool fwnode_is_ancestor_of(struct fwnode_handle *ancestor, struct fwnode_handle *child); +bool fwnode_is_ancestor_of(const struct fwnode_handle *ancestor, const struct fwnode_handle *child); struct fwnode_handle *fwnode_get_next_child_node( const struct fwnode_handle *fwnode, struct fwnode_handle *child); struct fwnode_handle *fwnode_get_next_available_child_node( @@ -143,57 +142,57 @@ int fwnode_irq_get_byname(const struct fwnode_handle *fwnode, const char *name); unsigned int device_get_child_node_count(const struct device *dev); -static inline bool device_property_read_bool(struct device *dev, +static inline bool device_property_read_bool(const struct device *dev, const char *propname) { return device_property_present(dev, propname); } -static inline int device_property_read_u8(struct device *dev, +static inline int device_property_read_u8(const struct device *dev, const char *propname, u8 *val) { return device_property_read_u8_array(dev, propname, val, 1); } -static inline int device_property_read_u16(struct device *dev, +static inline int device_property_read_u16(const struct device *dev, const char *propname, u16 *val) { return device_property_read_u16_array(dev, propname, val, 1); } -static inline int device_property_read_u32(struct device *dev, +static inline int device_property_read_u32(const struct device *dev, const char *propname, u32 *val) { return device_property_read_u32_array(dev, propname, val, 1); } -static inline int device_property_read_u64(struct device *dev, +static inline int device_property_read_u64(const struct device *dev, const char *propname, u64 *val) { return device_property_read_u64_array(dev, propname, val, 1); } -static inline int device_property_count_u8(struct device *dev, const char *propname) +static inline int device_property_count_u8(const struct device *dev, const char *propname) { return device_property_read_u8_array(dev, propname, NULL, 0); } -static inline int device_property_count_u16(struct device *dev, const char *propname) +static inline int device_property_count_u16(const struct device *dev, const char *propname) { return device_property_read_u16_array(dev, propname, NULL, 0); } -static inline int device_property_count_u32(struct device *dev, const char *propname) +static inline int device_property_count_u32(const struct device *dev, const char *propname) { return device_property_read_u32_array(dev, propname, NULL, 0); } -static inline int device_property_count_u64(struct device *dev, const char *propname) +static inline int device_property_count_u64(const struct device *dev, const char *propname) { return device_property_read_u64_array(dev, propname, NULL, 0); } -static inline int device_property_string_array_count(struct device *dev, +static inline int device_property_string_array_count(const struct device *dev, const char *propname) { return device_property_read_string_array(dev, propname, NULL, 0); @@ -396,7 +395,7 @@ enum dev_dma_attr device_get_dma_attr(const struct device *dev); const void *device_get_match_data(const struct device *dev); int device_get_phy_mode(struct device *dev); -int fwnode_get_phy_mode(struct fwnode_handle *fwnode); +int fwnode_get_phy_mode(const struct fwnode_handle *fwnode); void __iomem *fwnode_iomap(struct fwnode_handle *fwnode, int index); @@ -433,7 +432,7 @@ static inline bool fwnode_graph_is_endpoint(const struct fwnode_handle *fwnode) struct fwnode_handle * fwnode_graph_get_endpoint_by_id(const struct fwnode_handle *fwnode, u32 port, u32 endpoint, unsigned long flags); -unsigned int fwnode_graph_get_endpoint_count(struct fwnode_handle *fwnode, +unsigned int fwnode_graph_get_endpoint_count(const struct fwnode_handle *fwnode, unsigned long flags); #define fwnode_graph_for_each_endpoint(fwnode, child) \ diff --git a/include/linux/psi.h b/include/linux/psi.h index b029a847def1..ab26200c2803 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -24,7 +24,7 @@ void psi_memstall_leave(unsigned long *flags); int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); struct psi_trigger *psi_trigger_create(struct psi_group *group, - char *buf, enum psi_res res); + char *buf, enum psi_res res, struct file *file); void psi_trigger_destroy(struct psi_trigger *t); __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 1e0a0d7ace3a..040c089581c6 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -151,6 +151,9 @@ struct psi_trigger { /* Deferred event(s) from previous ratelimit window */ bool pending_event; + + /* Trigger type - PSI_AVGS for unprivileged, PSI_POLL for RT */ + enum psi_aggregators aggregator; }; struct psi_group { @@ -171,30 +174,34 @@ struct psi_group { /* Aggregator work control */ struct delayed_work avgs_work; + /* Unprivileged triggers against N*PSI_FREQ windows */ + struct list_head avg_triggers; + u32 avg_nr_triggers[NR_PSI_STATES - 1]; + /* Total stall times and sampled pressure averages */ u64 total[NR_PSI_AGGREGATORS][NR_PSI_STATES - 1]; unsigned long avg[NR_PSI_STATES - 1][3]; - /* Monitor work control */ - struct task_struct __rcu *poll_task; - struct timer_list poll_timer; - wait_queue_head_t poll_wait; - atomic_t poll_wakeup; - atomic_t poll_scheduled; + /* Monitor RT polling work control */ + struct task_struct __rcu *rtpoll_task; + struct timer_list rtpoll_timer; + wait_queue_head_t rtpoll_wait; + atomic_t rtpoll_wakeup; + atomic_t rtpoll_scheduled; /* Protects data used by the monitor */ - struct mutex trigger_lock; - - /* Configured polling triggers */ - struct list_head triggers; - u32 nr_triggers[NR_PSI_STATES - 1]; - u32 poll_states; - u64 poll_min_period; - - /* Total stall times at the start of monitor activation */ - u64 polling_total[NR_PSI_STATES - 1]; - u64 polling_next_update; - u64 polling_until; + struct mutex rtpoll_trigger_lock; + + /* Configured RT polling triggers */ + struct list_head rtpoll_triggers; + u32 rtpoll_nr_triggers[NR_PSI_STATES - 1]; + u32 rtpoll_states; + u64 rtpoll_min_period; + + /* Total stall times at the start of RT polling monitor activation */ + u64 rtpoll_total[NR_PSI_STATES - 1]; + u64 rtpoll_next_update; + u64 rtpoll_until; }; #else /* CONFIG_PSI */ diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index d1c53e9d8c75..7ee7ed5de722 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -156,13 +156,13 @@ RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p) { - rb->__rb_parent_color = rb_color(rb) | (unsigned long)p; + rb->__rb_parent_color = rb_color(rb) + (unsigned long)p; } static inline void rb_set_parent_color(struct rb_node *rb, struct rb_node *p, int color) { - rb->__rb_parent_color = (unsigned long)p | color; + rb->__rb_parent_color = (unsigned long)p + color; } static inline void diff --git a/include/linux/sched.h b/include/linux/sched.h index 3f5395ae86bc..eed5d65b8d1f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -36,6 +36,7 @@ #include <linux/seqlock.h> #include <linux/kcsan.h> #include <linux/rv.h> +#include <linux/livepatch_sched.h> #include <asm/kmap_size.h> /* task_struct member predeclarations (sorted alphabetically): */ @@ -69,6 +70,7 @@ struct sighand_struct; struct signal_struct; struct task_delay_info; struct task_group; +struct user_event_mm; /* * Task state bitmask. NOTE! These bits are also @@ -1313,7 +1315,10 @@ struct task_struct { #ifdef CONFIG_SCHED_MM_CID int mm_cid; /* Current cid in mm */ + int last_mm_cid; /* Most recent cid in mm */ + int migrate_from_cpu; int mm_cid_active; /* Whether cid bitmap is active */ + struct callback_head cid_work; #endif struct tlbflush_unmap_batch tlb_ubc; @@ -1525,6 +1530,10 @@ struct task_struct { union rv_task_monitor rv[RV_PER_TASK_MONITORS]; #endif +#ifdef CONFIG_USER_EVENTS + struct user_event_mm *user_event_mm; +#endif + /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. @@ -2067,6 +2076,9 @@ extern int __cond_resched(void); #if defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) +void sched_dynamic_klp_enable(void); +void sched_dynamic_klp_disable(void); + DECLARE_STATIC_CALL(cond_resched, __cond_resched); static __always_inline int _cond_resched(void) @@ -2075,6 +2087,7 @@ static __always_inline int _cond_resched(void) } #elif defined(CONFIG_PREEMPT_DYNAMIC) && defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) + extern int dynamic_cond_resched(void); static __always_inline int _cond_resched(void) @@ -2082,20 +2095,25 @@ static __always_inline int _cond_resched(void) return dynamic_cond_resched(); } -#else +#else /* !CONFIG_PREEMPTION */ static inline int _cond_resched(void) { + klp_sched_try_switch(); return __cond_resched(); } -#endif /* CONFIG_PREEMPT_DYNAMIC */ +#endif /* PREEMPT_DYNAMIC && CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */ -#else +#else /* CONFIG_PREEMPTION && !CONFIG_PREEMPT_DYNAMIC */ -static inline int _cond_resched(void) { return 0; } +static inline int _cond_resched(void) +{ + klp_sched_try_switch(); + return 0; +} -#endif /* !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) */ +#endif /* !CONFIG_PREEMPTION || CONFIG_PREEMPT_DYNAMIC */ #define cond_resched() ({ \ __might_resched(__FILE__, __LINE__, 0); \ diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 0e17ae7fbfd3..0ee96ea7a0e9 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -90,4 +90,5 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK) +#define MMF_VM_MERGE_ANY 29 #endif /* _LINUX_SCHED_COREDUMP_H */ diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 8c15abd67aed..fe1a46f30d24 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -46,6 +46,12 @@ static inline bool housekeeping_enabled(enum hk_type type) static inline void housekeeping_affine(struct task_struct *t, enum hk_type type) { } + +static inline bool housekeeping_test_cpu(int cpu, enum hk_type type) +{ + return true; +} + static inline void housekeeping_init(void) { } #endif /* CONFIG_CPU_ISOLATION */ @@ -58,4 +64,10 @@ static inline bool housekeeping_cpu(int cpu, enum hk_type type) return true; } +static inline bool cpu_is_isolated(int cpu) +{ + return !housekeeping_test_cpu(cpu, HK_TYPE_DOMAIN) || + !housekeeping_test_cpu(cpu, HK_TYPE_TICK); +} + #endif /* _LINUX_SCHED_ISOLATION_H */ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 2a243616f222..8d89c8c4fac1 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -8,7 +8,6 @@ #include <linux/mm_types.h> #include <linux/gfp.h> #include <linux/sync_core.h> -#include <linux/ioasid.h> /* * Routines for handling mm_structs @@ -37,6 +36,11 @@ static inline void mmgrab(struct mm_struct *mm) atomic_inc(&mm->mm_count); } +static inline void smp_mb__after_mmgrab(void) +{ + smp_mb__after_atomic(); +} + extern void __mmdrop(struct mm_struct *mm); static inline void mmdrop(struct mm_struct *mm) @@ -79,6 +83,34 @@ static inline void mmdrop_sched(struct mm_struct *mm) } #endif +/* Helpers for lazy TLB mm refcounting */ +static inline void mmgrab_lazy_tlb(struct mm_struct *mm) +{ + if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) + mmgrab(mm); +} + +static inline void mmdrop_lazy_tlb(struct mm_struct *mm) +{ + if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) { + mmdrop(mm); + } else { + /* + * mmdrop_lazy_tlb must provide a full memory barrier, see the + * membarrier comment finish_task_switch which relies on this. + */ + smp_mb(); + } +} + +static inline void mmdrop_lazy_tlb_sched(struct mm_struct *mm) +{ + if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) + mmdrop_sched(mm); + else + smp_mb(); /* see mmdrop_lazy_tlb() above */ +} + /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. @@ -451,29 +483,4 @@ static inline void membarrier_update_current_mm(struct mm_struct *next_mm) } #endif -#ifdef CONFIG_IOMMU_SVA -static inline void mm_pasid_init(struct mm_struct *mm) -{ - mm->pasid = INVALID_IOASID; -} - -/* Associate a PASID with an mm_struct: */ -static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) -{ - mm->pasid = pasid; -} - -static inline void mm_pasid_drop(struct mm_struct *mm) -{ - if (pasid_valid(mm->pasid)) { - ioasid_free(mm->pasid); - mm->pasid = INVALID_IOASID; - } -} -#else -static inline void mm_pasid_init(struct mm_struct *mm) {} -static inline void mm_pasid_set(struct mm_struct *mm, u32 pasid) {} -static inline void mm_pasid_drop(struct mm_struct *mm) {} -#endif - #endif /* _LINUX_SCHED_MM_H */ diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index 5e799a47431e..f158b025c175 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -23,7 +23,7 @@ static __always_inline void *task_stack_page(const struct task_struct *task) #define setup_thread_stack(new,old) do { } while(0) -static inline unsigned long *end_of_stack(const struct task_struct *task) +static __always_inline unsigned long *end_of_stack(const struct task_struct *task) { #ifdef CONFIG_STACK_GROWSUP return (unsigned long *)((unsigned long)task->stack + THREAD_SIZE) - 1; diff --git a/include/linux/semaphore.h b/include/linux/semaphore.h index 6694d0019a68..04655faadc2d 100644 --- a/include/linux/semaphore.h +++ b/include/linux/semaphore.h @@ -25,8 +25,14 @@ struct semaphore { .wait_list = LIST_HEAD_INIT((name).wait_list), \ } -#define DEFINE_SEMAPHORE(name) \ - struct semaphore name = __SEMAPHORE_INITIALIZER(name, 1) +/* + * Unlike mutexes, binary semaphores do not have an owner, so up() can + * be called in a different thread from the one which called down(). + * It is also safe to call down_trylock() and up() from interrupt + * context. + */ +#define DEFINE_SEMAPHORE(_name, _n) \ + struct semaphore _name = __SEMAPHORE_INITIALIZER(_name, _n) static inline void sema_init(struct semaphore *sem, int val) { diff --git a/include/linux/seq_buf.h b/include/linux/seq_buf.h index 5b31c5147969..515d7fcb9634 100644 --- a/include/linux/seq_buf.h +++ b/include/linux/seq_buf.h @@ -159,4 +159,6 @@ extern int seq_buf_bprintf(struct seq_buf *s, const char *fmt, const u32 *binary); #endif +void seq_buf_do_printk(struct seq_buf *s, const char *lvl); + #endif /* _LINUX_SEQ_BUF_H */ diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 19376bee9667..6f78f302d272 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -18,16 +18,16 @@ struct plat_serial8250_port { unsigned long iobase; /* io base address */ void __iomem *membase; /* ioremap cookie or NULL */ resource_size_t mapbase; /* resource base */ + unsigned int uartclk; /* UART clock rate */ unsigned int irq; /* interrupt number */ unsigned long irqflags; /* request_irq flags */ - unsigned int uartclk; /* UART clock rate */ void *private_data; unsigned char regshift; /* register shift */ unsigned char iotype; /* UPIO_* */ unsigned char hub6; unsigned char has_sysrq; /* supports magic SysRq */ - upf_t flags; /* UPF_* flags */ unsigned int type; /* If UPF_FIXED_TYPE */ + upf_t flags; /* UPF_* flags */ unsigned int (*serial_in)(struct uart_port *, int); void (*serial_out)(struct uart_port *, int, int); void (*set_termios)(struct uart_port *, @@ -151,26 +151,22 @@ void serial8250_unregister_port(int line); void serial8250_suspend_port(int line); void serial8250_resume_port(int line); -extern int early_serial_setup(struct uart_port *port); - -extern int early_serial8250_setup(struct earlycon_device *device, - const char *options); -extern void serial8250_update_uartclk(struct uart_port *port, - unsigned int uartclk); -extern void serial8250_do_set_termios(struct uart_port *port, - struct ktermios *termios, const struct ktermios *old); -extern void serial8250_do_set_ldisc(struct uart_port *port, - struct ktermios *termios); -extern unsigned int serial8250_do_get_mctrl(struct uart_port *port); -extern int serial8250_do_startup(struct uart_port *port); -extern void serial8250_do_shutdown(struct uart_port *port); -extern void serial8250_do_pm(struct uart_port *port, unsigned int state, - unsigned int oldstate); -extern void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl); -extern void serial8250_do_set_divisor(struct uart_port *port, unsigned int baud, - unsigned int quot, - unsigned int quot_frac); -extern int fsl8250_handle_irq(struct uart_port *port); +int early_serial_setup(struct uart_port *port); +int early_serial8250_setup(struct earlycon_device *device, const char *options); + +void serial8250_update_uartclk(struct uart_port *port, unsigned int uartclk); +void serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios, + const struct ktermios *old); +void serial8250_do_set_ldisc(struct uart_port *port, struct ktermios *termios); +unsigned int serial8250_do_get_mctrl(struct uart_port *port); +int serial8250_do_startup(struct uart_port *port); +void serial8250_do_shutdown(struct uart_port *port); +void serial8250_do_pm(struct uart_port *port, unsigned int state, + unsigned int oldstate); +void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl); +void serial8250_do_set_divisor(struct uart_port *port, unsigned int baud, + unsigned int quot, unsigned int quot_frac); +int fsl8250_handle_irq(struct uart_port *port); int serial8250_handle_irq(struct uart_port *port, unsigned int iir); u16 serial8250_rx_chars(struct uart_8250_port *up, u16 lsr); void serial8250_read_char(struct uart_8250_port *up, u16 lsr); @@ -183,9 +179,8 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s, int serial8250_console_setup(struct uart_port *port, char *options, bool probe); int serial8250_console_exit(struct uart_port *port); -extern void serial8250_set_isa_configurator(void (*v) - (int port, struct uart_port *up, - u32 *capabilities)); +void serial8250_set_isa_configurator(void (*v)(int port, struct uart_port *up, + u32 *capabilities)); #ifdef CONFIG_SERIAL_8250_RT288X unsigned int au_serial_in(struct uart_port *p, int offset); diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 9e3e5e0d11b2..66ecec15a1bf 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -553,7 +553,7 @@ struct uart_port { #define UPSTAT_AUTOXOFF ((__force upstat_t) (1 << 4)) #define UPSTAT_SYNC_FIFO ((__force upstat_t) (1 << 5)) - int hw_stopped; /* sw-assisted CTS flow state */ + bool hw_stopped; /* sw-assisted CTS flow state */ unsigned int mctrl; /* current modem ctrl settings */ unsigned int frame_time; /* frame timing in ns */ unsigned int type; /* port type */ @@ -812,9 +812,8 @@ extern const struct earlycon_id __earlycon_table_end[]; #define EARLYCON_DECLARE(_name, fn) OF_EARLYCON_DECLARE(_name, "", fn) -extern int of_setup_earlycon(const struct earlycon_id *match, - unsigned long node, - const char *options); +int of_setup_earlycon(const struct earlycon_id *match, unsigned long node, + const char *options); #ifdef CONFIG_SERIAL_EARLYCON extern bool earlycon_acpi_spcr_enable __initdata; @@ -897,11 +896,11 @@ static inline bool uart_softcts_mode(struct uart_port *uport) * The following are helper functions for the low level drivers. */ -extern void uart_handle_dcd_change(struct uart_port *uport, bool active); -extern void uart_handle_cts_change(struct uart_port *uport, bool active); +void uart_handle_dcd_change(struct uart_port *uport, bool active); +void uart_handle_cts_change(struct uart_port *uport, bool active); -extern void uart_insert_char(struct uart_port *port, unsigned int status, - unsigned int overrun, unsigned int ch, unsigned int flag); +void uart_insert_char(struct uart_port *port, unsigned int status, + unsigned int overrun, unsigned int ch, unsigned int flag); void uart_xchar_out(struct uart_port *uport, int offset); diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 103d1000a5a2..9029abd29b1c 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -9,6 +9,7 @@ #include <linux/percpu_counter.h> #include <linux/xattr.h> #include <linux/fs_parser.h> +#include <linux/userfaultfd_k.h> /* inode in-kernel data */ @@ -45,6 +46,7 @@ struct shmem_sb_info { kuid_t uid; /* Mount uid for root directory */ kgid_t gid; /* Mount gid for root directory */ bool full_inums; /* If i_ino should be uint or ino_t */ + bool noswap; /* ignores VM reclaim / swap requests */ ino_t next_ino; /* The next per-sb inode number to use */ ino_t __percpu *ino_batch; /* The next per-cpu inode number to use */ struct mempolicy *mpol; /* default memory policy for mappings */ @@ -94,7 +96,14 @@ int shmem_unuse(unsigned int type); extern bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, struct mm_struct *mm, unsigned long vm_flags); +#ifdef CONFIG_SHMEM extern unsigned long shmem_swap_usage(struct vm_area_struct *vma); +#else +static inline unsigned long shmem_swap_usage(struct vm_area_struct *vma) +{ + return 0; +} +#endif extern unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end); @@ -151,15 +160,15 @@ extern void shmem_uncharge(struct inode *inode, long pages); #ifdef CONFIG_USERFAULTFD #ifdef CONFIG_SHMEM -extern int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, +extern int shmem_mfill_atomic_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, - bool zeropage, bool wp_copy, - struct page **pagep); + uffd_flags_t flags, + struct folio **foliop); #else /* !CONFIG_SHMEM */ -#define shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, \ - src_addr, zeropage, wp_copy, pagep) ({ BUG(); 0; }) +#define shmem_mfill_atomic_pte(dst_pmd, dst_vma, dst_addr, \ + src_addr, flags, foliop) ({ BUG(); 0; }) #endif /* CONFIG_SHMEM */ #endif /* CONFIG_USERFAULTFD */ diff --git a/include/linux/slab.h b/include/linux/slab.h index 7db48f9f0d9d..6b3e155b70bf 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -167,7 +167,6 @@ struct mem_cgroup; /* * struct kmem_cache related prototypes */ -void __init kmem_cache_init(void); bool slab_is_available(void); struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, @@ -284,7 +283,7 @@ static inline unsigned int arch_slab_minalign(void) * (PAGE_SIZE*2). Larger requests are passed to the page allocator. */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) -#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) +#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 5 #endif @@ -292,7 +291,7 @@ static inline unsigned int arch_slab_minalign(void) #ifdef CONFIG_SLUB #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) -#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT - 1) +#define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT) #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif diff --git a/include/linux/smp.h b/include/linux/smp.h index a80ab58ae3f1..91ea4a67f8ca 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -59,8 +59,8 @@ int smp_call_function_single_async(int cpu, struct __call_single_data *csd); * Cpus stopping functions in panic. All have default weak definitions. * Architecture-dependent code may override them. */ -void panic_smp_self_stop(void); -void nmi_panic_self_stop(struct pt_regs *regs); +void __noreturn panic_smp_self_stop(void); +void __noreturn nmi_panic_self_stop(struct pt_regs *regs); void crash_smp_send_stop(void); /* @@ -125,8 +125,15 @@ extern void smp_send_stop(void); /* * sends a 'reschedule' event to another CPU: */ -extern void smp_send_reschedule(int cpu); - +extern void arch_smp_send_reschedule(int cpu); +/* + * scheduler_ipi() is inline so can't be passed as callback reason, but the + * callsite IP should be sufficient for root-causing IPIs sent from here. + */ +#define smp_send_reschedule(cpu) ({ \ + trace_ipi_send_cpu(cpu, _RET_IP_, NULL); \ + arch_smp_send_reschedule(cpu); \ +}) /* * Prepare machine for booting other CPUs. diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 4fa26b9a3572..cfe42f8cd7a4 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -184,8 +184,18 @@ struct spi_device { u8 chip_select; u8 bits_per_word; bool rt; -#define SPI_NO_TX BIT(31) /* No transmit wire */ -#define SPI_NO_RX BIT(30) /* No receive wire */ +#define SPI_NO_TX BIT(31) /* No transmit wire */ +#define SPI_NO_RX BIT(30) /* No receive wire */ + /* + * TPM specification defines flow control over SPI. Client device + * can insert a wait state on MISO when address is transmitted by + * controller on MOSI. Detecting the wait state in software is only + * possible for full duplex controllers. For controllers that support + * only half-duplex, the wait state detection needs to be implemented + * in hardware. TPM devices would set this flag when hardware flow + * control is expected from SPI controller. + */ +#define SPI_TPM_HW_FLOW BIT(29) /* TPM HW flow control */ /* * All bits defined above should be covered by SPI_MODE_KERNEL_MASK. * The SPI_MODE_KERNEL_MASK has the SPI_MODE_USER_MASK counterpart, @@ -195,7 +205,7 @@ struct spi_device { * These bits must not overlap. A static assert check should make sure of that. * If adding extra bits, make sure to decrease the bit index below as well. */ -#define SPI_MODE_KERNEL_MASK (~(BIT(30) - 1)) +#define SPI_MODE_KERNEL_MASK (~(BIT(29) - 1)) u32 mode; int irq; void *controller_state; @@ -244,7 +254,7 @@ static inline void spi_dev_put(struct spi_device *spi) } /* ctldata is for the bus_controller driver's runtime state */ -static inline void *spi_get_ctldata(struct spi_device *spi) +static inline void *spi_get_ctldata(const struct spi_device *spi) { return spi->controller_state; } @@ -261,12 +271,12 @@ static inline void spi_set_drvdata(struct spi_device *spi, void *data) dev_set_drvdata(&spi->dev, data); } -static inline void *spi_get_drvdata(struct spi_device *spi) +static inline void *spi_get_drvdata(const struct spi_device *spi) { return dev_get_drvdata(&spi->dev); } -static inline u8 spi_get_chipselect(struct spi_device *spi, u8 idx) +static inline u8 spi_get_chipselect(const struct spi_device *spi, u8 idx) { return spi->chip_select; } @@ -276,7 +286,7 @@ static inline void spi_set_chipselect(struct spi_device *spi, u8 idx, u8 chipsel spi->chip_select = chipselect; } -static inline struct gpio_desc *spi_get_csgpiod(struct spi_device *spi, u8 idx) +static inline struct gpio_desc *spi_get_csgpiod(const struct spi_device *spi, u8 idx) { return spi->cs_gpiod; } @@ -1093,6 +1103,9 @@ struct spi_message { unsigned is_dma_mapped:1; + /* spi_prepare_message() was called for this message */ + bool prepared; + /* REVISIT: we might want a flag affecting the behavior of the * last transfer ... allowing things like "read 16 bit length L" * immediately followed by "read L bytes". Basically imposing @@ -1105,11 +1118,11 @@ struct spi_message { */ /* Completion is reported through a callback */ + int status; void (*complete)(void *context); void *context; unsigned frame_length; unsigned actual_length; - int status; /* For optional use by whatever driver currently owns the * spi_message ... between calls to spi_async and then later @@ -1120,9 +1133,6 @@ struct spi_message { /* List of spi_res reources when the spi message is processed */ struct list_head resources; - - /* spi_prepare_message() was called for this message */ - bool prepared; }; static inline void spi_message_init_no_memset(struct spi_message *m) @@ -1295,6 +1305,10 @@ extern int spi_split_transfers_maxsize(struct spi_controller *ctlr, struct spi_message *msg, size_t maxsize, gfp_t gfp); +extern int spi_split_transfers_maxwords(struct spi_controller *ctlr, + struct spi_message *msg, + size_t maxwords, + gfp_t gfp); /*---------------------------------------------------------------------------*/ diff --git a/include/linux/start_kernel.h b/include/linux/start_kernel.h index 8b369a41c03c..a9806a44a605 100644 --- a/include/linux/start_kernel.h +++ b/include/linux/start_kernel.h @@ -8,8 +8,8 @@ /* Define the prototype for start_kernel here, rather than cluttering up something else. */ -extern asmlinkage void __init start_kernel(void); -extern void __init arch_call_rest_init(void); -extern void __ref rest_init(void); +extern asmlinkage void __init __noreturn start_kernel(void); +extern void __init __noreturn arch_call_rest_init(void); +extern void __ref __noreturn rest_init(void); #endif /* _LINUX_START_KERNEL_H */ diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index ec5a555df96f..518bd28f5ab8 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -300,17 +300,18 @@ static inline int get_time(char **bpp, time64_t *time) return 0; } -static inline time64_t get_expiry(char **bpp) +static inline int get_expiry(char **bpp, time64_t *rvp) { - time64_t rv; + int error; struct timespec64 boot; - if (get_time(bpp, &rv)) - return 0; - if (rv < 0) - return 0; + error = get_time(bpp, rvp); + if (error) + return error; + getboottime64(&boot); - return rv - boot.tv_sec; + (*rvp) -= boot.tv_sec; + return 0; } #endif /* _LINUX_SUNRPC_CACHE_H_ */ diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index b8ca3ecaf8d7..8ada7dc802d3 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -90,8 +90,7 @@ struct rpc_task { #endif unsigned char tk_priority : 2,/* Task priority */ tk_garb_retry : 2, - tk_cred_retry : 2, - tk_rebind_retry : 2; + tk_cred_retry : 2; }; typedef void (*rpc_action)(struct rpc_task *); diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 877891536c2f..762d7231e574 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -309,17 +309,6 @@ static inline struct sockaddr *svc_daddr(const struct svc_rqst *rqst) return (struct sockaddr *) &rqst->rq_daddr; } -static inline void svc_free_res_pages(struct svc_rqst *rqstp) -{ - while (rqstp->rq_next_page != rqstp->rq_respages) { - struct page **pp = --rqstp->rq_next_page; - if (*pp) { - put_page(*pp); - *pp = NULL; - } - } -} - struct svc_deferred_req { u32 prot; /* protocol (UDP or TCP) */ struct svc_xprt *xprt; @@ -422,15 +411,16 @@ struct svc_serv *svc_create(struct svc_program *, unsigned int, int (*threadfn)(void *data)); struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node); -void svc_rqst_replace_page(struct svc_rqst *rqstp, +bool svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page); +void svc_rqst_release_pages(struct svc_rqst *rqstp); void svc_rqst_free(struct svc_rqst *); void svc_exit_thread(struct svc_rqst *); struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, int (*threadfn)(void *data)); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); int svc_pool_stats_open(struct svc_serv *serv, struct file *file); -int svc_process(struct svc_rqst *); +void svc_process(struct svc_rqst *rqstp); int bc_svc_process(struct svc_serv *, struct rpc_rqst *, struct svc_rqst *); int svc_register(const struct svc_serv *, struct net *, const int, diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 775368802762..867479204840 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -27,7 +27,7 @@ struct svc_xprt_ops { void (*xpo_detach)(struct svc_xprt *); void (*xpo_free)(struct svc_xprt *); void (*xpo_kill_temp_xprt)(struct svc_xprt *); - void (*xpo_start_tls)(struct svc_xprt *); + void (*xpo_handshake)(struct svc_xprt *xprt); }; struct svc_xprt_class { @@ -70,6 +70,9 @@ struct svc_xprt { #define XPT_LOCAL 12 /* connection from loopback interface */ #define XPT_KILL_TEMP 13 /* call xpo_kill_temp_xprt before closing */ #define XPT_CONG_CTRL 14 /* has congestion control */ +#define XPT_HANDSHAKE 15 /* xprt requests a handshake */ +#define XPT_TLS_SESSION 16 /* transport-layer security established */ +#define XPT_PEER_AUTH 17 /* peer has been authenticated */ struct svc_serv *xpt_server; /* service for transport */ atomic_t xpt_reserved; /* space on outq that is rsvd */ diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index bcc555c7ae9c..d16ae621782c 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -38,6 +38,8 @@ struct svc_sock { /* Number of queued send requests */ atomic_t sk_sendqlen; + struct completion sk_handshake_done; + struct page * sk_pages[RPCSVC_MAXPAGES]; /* received data */ }; @@ -56,7 +58,7 @@ static inline u32 svc_sock_final_rec(struct svc_sock *svsk) */ void svc_close_net(struct svc_serv *, struct net *); int svc_recv(struct svc_rqst *, long); -int svc_send(struct svc_rqst *); +void svc_send(struct svc_rqst *rqstp); void svc_drop(struct svc_rqst *); void svc_sock_update_bufs(struct svc_serv *serv); bool svc_alien_sock(struct net *net, int fd); diff --git a/include/linux/swap.h b/include/linux/swap.h index 209a425739a9..3c69cb653cb9 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -153,13 +153,28 @@ union swap_header { * memory reclaim */ struct reclaim_state { - unsigned long reclaimed_slab; + /* pages reclaimed outside of LRU-based reclaim */ + unsigned long reclaimed; #ifdef CONFIG_LRU_GEN /* per-thread mm walk data */ struct lru_gen_mm_walk *mm_walk; #endif }; +/* + * mm_account_reclaimed_pages(): account reclaimed pages outside of LRU-based + * reclaim + * @pages: number of pages reclaimed + * + * If the current process is undergoing a reclaim operation, increment the + * number of reclaimed pages by @pages. + */ +static inline void mm_account_reclaimed_pages(unsigned long pages) +{ + if (current->reclaim_state) + current->reclaim_state->reclaimed += pages; +} + #ifdef __KERNEL__ struct address_space; @@ -427,7 +442,6 @@ extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; long remove_mapping(struct address_space *mapping, struct folio *folio); -extern unsigned long reclaim_pages(struct list_head *page_list); #ifdef CONFIG_NUMA extern int node_reclaim_mode; extern int sysctl_min_unmapped_ratio; @@ -620,18 +634,18 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) { /* Cgroup2 doesn't have per-cgroup swappiness */ if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) - return vm_swappiness; + return READ_ONCE(vm_swappiness); /* root ? */ if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg)) - return vm_swappiness; + return READ_ONCE(vm_swappiness); - return memcg->swappiness; + return READ_ONCE(memcg->swappiness); } #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) { - return vm_swappiness; + return READ_ONCE(vm_swappiness); } #endif @@ -641,22 +655,18 @@ extern atomic_t zswap_stored_pages; #endif #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -extern void __cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask); -static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) +void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp); +static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { if (mem_cgroup_disabled()) return; - __cgroup_throttle_swaprate(page, gfp_mask); + __folio_throttle_swaprate(folio, gfp); } #else -static inline void cgroup_throttle_swaprate(struct page *page, gfp_t gfp_mask) -{ -} -#endif static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { - cgroup_throttle_swaprate(&folio->page, gfp); } +#endif #if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index bcef10e20ea4..7af2673b47ba 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -87,6 +87,11 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys, * @for_alloc: %true if the pool is used for memory allocation * @nareas: The area number in the pool. * @area_nslabs: The slot number in the area. + * @total_used: The total number of slots in the pool that are currently used + * across all areas. Used only for calculating used_hiwater in + * debugfs. + * @used_hiwater: The high water mark for total_used. Used only for reporting + * in debugfs. */ struct io_tlb_mem { phys_addr_t start; @@ -102,6 +107,10 @@ struct io_tlb_mem { unsigned int area_nslabs; struct io_tlb_area *areas; struct io_tlb_slot *slots; +#ifdef CONFIG_DEBUG_FS + atomic_long_t total_used; + atomic_long_t used_hiwater; +#endif }; extern struct io_tlb_mem io_tlb_default_mem; @@ -180,6 +189,4 @@ static inline bool is_swiotlb_for_alloc(struct device *dev) } #endif /* CONFIG_DMA_RESTRICTED_POOL */ -extern phys_addr_t swiotlb_unencrypted_base; - #endif /* __LINUX_SWIOTLB_H */ diff --git a/include/linux/tty.h b/include/linux/tty.h index 093935e97f42..e8d5d9997aca 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -227,7 +227,7 @@ struct tty_struct { unsigned long unused[0]; } __aligned(sizeof(unsigned long)) ctrl; - int hw_stopped; + bool hw_stopped; unsigned int receive_room; int flow_change; @@ -387,7 +387,7 @@ extern struct ktermios tty_std_termios; int vcs_init(void); -extern struct class *tty_class; +extern const struct class tty_class; /** * tty_kref_get - get a tty reference diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index ab9728138ad6..3064314f4832 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -11,6 +11,28 @@ #include <asm/uaccess.h> /* + * Architectures that support memory tagging (assigning tags to memory regions, + * embedding these tags into addresses that point to these memory regions, and + * checking that the memory and the pointer tags match on memory accesses) + * redefine this macro to strip tags from pointers. + * + * Passing down mm_struct allows to define untagging rules on per-process + * basis. + * + * It's defined as noop for architectures that don't support memory tagging. + */ +#ifndef untagged_addr +#define untagged_addr(addr) (addr) +#endif + +#ifndef untagged_addr_remote +#define untagged_addr_remote(mm, addr) ({ \ + mmap_assert_locked(mm); \ + untagged_addr(addr); \ +}) +#endif + +/* * Architectures should provide two primitives (raw_copy_{to,from}_user()) * and get rid of their private instances of copy_{to,from}_user() and * __copy_{to,from}_user{,_inatomic}(). diff --git a/include/linux/uio.h b/include/linux/uio.h index ed35f4427a0a..3d386849a758 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -195,6 +195,8 @@ static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset, { return copy_page_to_iter(&folio->page, offset, bytes, i); } +size_t copy_page_to_iter_nofault(struct page *page, unsigned offset, + size_t bytes, struct iov_iter *i); static __always_inline __must_check size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) diff --git a/include/linux/usb.h b/include/linux/usb.h index 9642ee02d713..25f8e62a30ec 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -170,6 +170,12 @@ usb_find_last_int_out_endpoint(struct usb_host_interface *alt, return usb_find_common_endpoints_reverse(alt, NULL, NULL, NULL, int_out); } +enum usb_wireless_status { + USB_WIRELESS_STATUS_NA = 0, + USB_WIRELESS_STATUS_DISCONNECTED, + USB_WIRELESS_STATUS_CONNECTED, +}; + /** * struct usb_interface - what usb device drivers talk to * @altsetting: array of interface structures, one for each alternate @@ -197,6 +203,10 @@ usb_find_last_int_out_endpoint(struct usb_host_interface *alt, * following a reset or suspend operation it doesn't support. * @authorized: This allows to (de)authorize individual interfaces instead * a whole device in contrast to the device authorization. + * @wireless_status: if the USB device uses a receiver/emitter combo, whether + * the emitter is connected. + * @wireless_status_work: Used for scheduling wireless status changes + * from atomic context. * @dev: driver model's view of this device * @usb_dev: if an interface is bound to the USB major, this will point * to the sysfs representation for that device. @@ -253,6 +263,8 @@ struct usb_interface { unsigned needs_binding:1; /* needs delayed unbind/rebind */ unsigned resetting_device:1; /* true: bandwidth alloc after reset */ unsigned authorized:1; /* used for interface authorization */ + enum usb_wireless_status wireless_status; + struct work_struct wireless_status_work; struct device dev; /* interface specific device info */ struct device *usb_dev; @@ -291,6 +303,11 @@ void usb_put_intf(struct usb_interface *intf); #define USB_MAXINTERFACES 32 #define USB_MAXIADS (USB_MAXINTERFACES/2) +bool usb_check_bulk_endpoints( + const struct usb_interface *intf, const u8 *ep_addrs); +bool usb_check_int_endpoints( + const struct usb_interface *intf, const u8 *ep_addrs); + /* * USB Resume Timer: Every Host controller driver should drive the resume * signalling on the bus for the amount of time defined by this macro. @@ -704,13 +721,12 @@ struct usb_device { unsigned long active_duration; -#ifdef CONFIG_PM unsigned long connect_time; unsigned do_remote_wakeup:1; unsigned reset_resume:1; unsigned port_is_suspended:1; -#endif + struct wusb_dev *wusb_dev; int slot_id; struct usb2_lpm_parameters l1_params; @@ -887,6 +903,10 @@ static inline int usb_interface_claimed(struct usb_interface *iface) extern void usb_driver_release_interface(struct usb_driver *driver, struct usb_interface *iface); + +int usb_set_wireless_status(struct usb_interface *iface, + enum usb_wireless_status status); + const struct usb_device_id *usb_match_id(struct usb_interface *interface, const struct usb_device_id *id); extern int usb_match_one_id(struct usb_interface *interface, diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h index 608dc962748b..a2448e98854f 100644 --- a/include/linux/usb/composite.h +++ b/include/linux/usb/composite.h @@ -150,6 +150,9 @@ struct usb_os_desc_table { * GetStatus() request when the recipient is Interface. * @func_suspend: callback to be called when * SetFeature(FUNCTION_SUSPEND) is reseived + * @func_suspended: Indicates whether the function is in function suspend state. + * @func_wakeup_armed: Indicates whether the function is armed by the host for + * wakeup signaling. * * A single USB function uses one or more interfaces, and should in most * cases support operation at both full and high speeds. Each function is @@ -220,6 +223,8 @@ struct usb_function { int (*get_status)(struct usb_function *); int (*func_suspend)(struct usb_function *, u8 suspend_opt); + bool func_suspended; + bool func_wakeup_armed; /* private: */ /* internals */ struct list_head list; @@ -241,6 +246,7 @@ int config_ep_by_speed_and_alt(struct usb_gadget *g, struct usb_function *f, int config_ep_by_speed(struct usb_gadget *g, struct usb_function *f, struct usb_ep *_ep); +int usb_func_wakeup(struct usb_function *func); #define MAX_CONFIG_INTERFACES 16 /* arbitrary; max 255 */ @@ -413,6 +419,8 @@ extern int composite_dev_prepare(struct usb_composite_driver *composite, extern int composite_os_desc_req_prepare(struct usb_composite_dev *cdev, struct usb_ep *ep0); void composite_dev_cleanup(struct usb_composite_dev *cdev); +void check_remote_wakeup_config(struct usb_gadget *g, + struct usb_configuration *c); static inline struct usb_composite_driver *to_cdriver( struct usb_gadget_driver *gdrv) diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 00750f7020f3..75bda0783395 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -310,6 +310,8 @@ struct usb_udc; struct usb_gadget_ops { int (*get_frame)(struct usb_gadget *); int (*wakeup)(struct usb_gadget *); + int (*func_wakeup)(struct usb_gadget *gadget, int intf_id); + int (*set_remote_wakeup)(struct usb_gadget *, int set); int (*set_selfpowered) (struct usb_gadget *, int is_selfpowered); int (*vbus_session) (struct usb_gadget *, int is_active); int (*vbus_draw) (struct usb_gadget *, unsigned mA); @@ -384,6 +386,8 @@ struct usb_gadget_ops { * @connected: True if gadget is connected. * @lpm_capable: If the gadget max_speed is FULL or HIGH, this flag * indicates that it supports LPM as per the LPM ECN & errata. + * @wakeup_capable: True if gadget is capable of sending remote wakeup. + * @wakeup_armed: True if gadget is armed by the host for remote wakeup. * @irq: the interrupt number for device controller. * @id_number: a unique ID number for ensuring that gadget names are distinct * @@ -445,6 +449,8 @@ struct usb_gadget { unsigned deactivated:1; unsigned connected:1; unsigned lpm_capable:1; + unsigned wakeup_capable:1; + unsigned wakeup_armed:1; int irq; int id_number; }; @@ -601,6 +607,7 @@ static inline int gadget_is_otg(struct usb_gadget *g) #if IS_ENABLED(CONFIG_USB_GADGET) int usb_gadget_frame_number(struct usb_gadget *gadget); int usb_gadget_wakeup(struct usb_gadget *gadget); +int usb_gadget_set_remote_wakeup(struct usb_gadget *gadget, int set); int usb_gadget_set_selfpowered(struct usb_gadget *gadget); int usb_gadget_clear_selfpowered(struct usb_gadget *gadget); int usb_gadget_vbus_connect(struct usb_gadget *gadget); @@ -616,6 +623,8 @@ static inline int usb_gadget_frame_number(struct usb_gadget *gadget) { return 0; } static inline int usb_gadget_wakeup(struct usb_gadget *gadget) { return 0; } +static inline int usb_gadget_set_remote_wakeup(struct usb_gadget *gadget, int set) +{ return 0; } static inline int usb_gadget_set_selfpowered(struct usb_gadget *gadget) { return 0; } static inline int usb_gadget_clear_selfpowered(struct usb_gadget *gadget) diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index b51c07111729..094c77eaf455 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -488,9 +488,7 @@ extern void usb_hcd_pci_shutdown(struct pci_dev *dev); extern int usb_hcd_amd_remote_wakeup_quirk(struct pci_dev *dev); -#ifdef CONFIG_PM extern const struct dev_pm_ops usb_hcd_pci_pm_ops; -#endif #endif /* CONFIG_USB_PCI */ /* pci-ish (pdev null is ok) buffer alloc/mapping support */ diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h index f7bfedb740f5..7eeb5f9c4f0d 100644 --- a/include/linux/usb/serial.h +++ b/include/linux/usb/serial.h @@ -378,7 +378,7 @@ void usb_serial_handle_dcd_change(struct usb_serial_port *usb_port, int usb_serial_bus_register(struct usb_serial_driver *device); void usb_serial_bus_deregister(struct usb_serial_driver *device); -extern struct bus_type usb_serial_bus_type; +extern const struct bus_type usb_serial_bus_type; extern struct tty_driver *usb_serial_tty_driver; static inline void usb_serial_debug_data(struct device *dev, diff --git a/include/linux/user_events.h b/include/linux/user_events.h index 592a3fbed98e..2847f5a18a86 100644 --- a/include/linux/user_events.h +++ b/include/linux/user_events.h @@ -1,54 +1,83 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2021, Microsoft Corporation. + * Copyright (c) 2022, Microsoft Corporation. * * Authors: * Beau Belgrave <beaub@linux.microsoft.com> */ -#ifndef _UAPI_LINUX_USER_EVENTS_H -#define _UAPI_LINUX_USER_EVENTS_H -#include <linux/types.h> -#include <linux/ioctl.h> +#ifndef _LINUX_USER_EVENTS_H +#define _LINUX_USER_EVENTS_H -#ifdef __KERNEL__ -#include <linux/uio.h> -#else -#include <sys/uio.h> -#endif +#include <linux/list.h> +#include <linux/refcount.h> +#include <linux/mm_types.h> +#include <linux/workqueue.h> +#include <uapi/linux/user_events.h> -#define USER_EVENTS_SYSTEM "user_events" -#define USER_EVENTS_PREFIX "u:" +#ifdef CONFIG_USER_EVENTS +struct user_event_mm { + struct list_head link; + struct list_head enablers; + struct mm_struct *mm; + struct user_event_mm *next; + refcount_t refcnt; + refcount_t tasks; + struct rcu_work put_rwork; +}; -/* Create dynamic location entry within a 32-bit value */ -#define DYN_LOC(offset, size) ((size) << 16 | (offset)) +extern void user_event_mm_dup(struct task_struct *t, + struct user_event_mm *old_mm); -/* - * Describes an event registration and stores the results of the registration. - * This structure is passed to the DIAG_IOCSREG ioctl, callers at a minimum - * must set the size and name_args before invocation. - */ -struct user_reg { +extern void user_event_mm_remove(struct task_struct *t); + +static inline void user_events_fork(struct task_struct *t, + unsigned long clone_flags) +{ + struct user_event_mm *old_mm; - /* Input: Size of the user_reg structure being used */ - __u32 size; + if (!t || !current->user_event_mm) + return; - /* Input: Pointer to string with event name, description and flags */ - __u64 name_args; + old_mm = current->user_event_mm; - /* Output: Bitwise index of the event within the status page */ - __u32 status_bit; + if (clone_flags & CLONE_VM) { + t->user_event_mm = old_mm; + refcount_inc(&old_mm->tasks); + return; + } - /* Output: Index of the event to use when writing data */ - __u32 write_index; -} __attribute__((__packed__)); + user_event_mm_dup(t, old_mm); +} -#define DIAG_IOC_MAGIC '*' +static inline void user_events_execve(struct task_struct *t) +{ + if (!t || !t->user_event_mm) + return; + + user_event_mm_remove(t); +} + +static inline void user_events_exit(struct task_struct *t) +{ + if (!t || !t->user_event_mm) + return; + + user_event_mm_remove(t); +} +#else +static inline void user_events_fork(struct task_struct *t, + unsigned long clone_flags) +{ +} -/* Requests to register a user_event */ -#define DIAG_IOCSREG _IOWR(DIAG_IOC_MAGIC, 0, struct user_reg*) +static inline void user_events_execve(struct task_struct *t) +{ +} -/* Requests to delete a user_event */ -#define DIAG_IOCSDEL _IOW(DIAG_IOC_MAGIC, 1, char*) +static inline void user_events_exit(struct task_struct *t) +{ +} +#endif /* CONFIG_USER_EVENTS */ -#endif /* _UAPI_LINUX_USER_EVENTS_H */ +#endif /* _LINUX_USER_EVENTS_H */ diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 3767f18114ef..d78b01524349 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -36,44 +36,57 @@ #define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS) -extern int sysctl_unprivileged_userfaultfd; - extern vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason); -/* - * The mode of operation for __mcopy_atomic and its helpers. - * - * This is almost an implementation detail (mcopy_atomic below doesn't take this - * as a parameter), but it's exposed here because memory-kind-specific - * implementations (e.g. hugetlbfs) need to know the mode of operation. - */ -enum mcopy_atomic_mode { - /* A normal copy_from_user into the destination range. */ - MCOPY_ATOMIC_NORMAL, - /* Don't copy; map the destination range to the zero page. */ - MCOPY_ATOMIC_ZEROPAGE, - /* Just install pte(s) with the existing page(s) in the page cache. */ - MCOPY_ATOMIC_CONTINUE, +/* A combined operation mode + behavior flags. */ +typedef unsigned int __bitwise uffd_flags_t; + +/* Mutually exclusive modes of operation. */ +enum mfill_atomic_mode { + MFILL_ATOMIC_COPY, + MFILL_ATOMIC_ZEROPAGE, + MFILL_ATOMIC_CONTINUE, + NR_MFILL_ATOMIC_MODES, }; -extern int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, +#define MFILL_ATOMIC_MODE_BITS (const_ilog2(NR_MFILL_ATOMIC_MODES - 1) + 1) +#define MFILL_ATOMIC_BIT(nr) BIT(MFILL_ATOMIC_MODE_BITS + (nr)) +#define MFILL_ATOMIC_FLAG(nr) ((__force uffd_flags_t) MFILL_ATOMIC_BIT(nr)) +#define MFILL_ATOMIC_MODE_MASK ((__force uffd_flags_t) (MFILL_ATOMIC_BIT(0) - 1)) + +static inline bool uffd_flags_mode_is(uffd_flags_t flags, enum mfill_atomic_mode expected) +{ + return (flags & MFILL_ATOMIC_MODE_MASK) == ((__force uffd_flags_t) expected); +} + +static inline uffd_flags_t uffd_flags_set_mode(uffd_flags_t flags, enum mfill_atomic_mode mode) +{ + flags &= ~MFILL_ATOMIC_MODE_MASK; + return flags | ((__force uffd_flags_t) mode); +} + +/* Flags controlling behavior. These behavior changes are mode-independent. */ +#define MFILL_ATOMIC_WP MFILL_ATOMIC_FLAG(0) + +extern int mfill_atomic_install_pte(pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, struct page *page, - bool newly_allocated, bool wp_copy); - -extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, - unsigned long src_start, unsigned long len, - atomic_t *mmap_changing, __u64 mode); -extern ssize_t mfill_zeropage(struct mm_struct *dst_mm, - unsigned long dst_start, - unsigned long len, - atomic_t *mmap_changing); -extern ssize_t mcopy_continue(struct mm_struct *dst_mm, unsigned long dst_start, - unsigned long len, atomic_t *mmap_changing); + bool newly_allocated, uffd_flags_t flags); + +extern ssize_t mfill_atomic_copy(struct mm_struct *dst_mm, unsigned long dst_start, + unsigned long src_start, unsigned long len, + atomic_t *mmap_changing, uffd_flags_t flags); +extern ssize_t mfill_atomic_zeropage(struct mm_struct *dst_mm, + unsigned long dst_start, + unsigned long len, + atomic_t *mmap_changing); +extern ssize_t mfill_atomic_continue(struct mm_struct *dst_mm, unsigned long dst_start, + unsigned long len, atomic_t *mmap_changing, + uffd_flags_t flags); extern int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start, unsigned long len, bool enable_wp, atomic_t *mmap_changing); -extern long uffd_wp_range(struct mm_struct *dst_mm, struct vm_area_struct *vma, +extern long uffd_wp_range(struct vm_area_struct *vma, unsigned long start, unsigned long len, bool enable_wp); /* mm helpers */ @@ -179,6 +192,7 @@ extern int userfaultfd_unmap_prep(struct mm_struct *mm, unsigned long start, unsigned long end, struct list_head *uf); extern void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf); +extern bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma); #else /* CONFIG_USERFAULTFD */ @@ -274,8 +288,30 @@ static inline bool uffd_disable_fault_around(struct vm_area_struct *vma) return false; } +static inline bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma) +{ + return false; +} + #endif /* CONFIG_USERFAULTFD */ +static inline bool userfaultfd_wp_use_markers(struct vm_area_struct *vma) +{ + /* Only wr-protect mode uses pte markers */ + if (!userfaultfd_wp(vma)) + return false; + + /* File-based uffd-wp always need markers */ + if (!vma_is_anonymous(vma)) + return true; + + /* + * Anonymous uffd-wp only needs the markers if WP_UNPOPULATED + * enabled (to apply markers on zero pages). + */ + return userfaultfd_wp_unpopulated(vma); +} + static inline bool pte_marker_entry_uffd_wp(swp_entry_t entry) { #ifdef CONFIG_PTE_MARKER_UFFD_WP diff --git a/include/linux/uuid.h b/include/linux/uuid.h index 6b1a3efa1e0b..43d4a79b273d 100644 --- a/include/linux/uuid.h +++ b/include/linux/uuid.h @@ -107,7 +107,4 @@ extern const u8 uuid_index[16]; int guid_parse(const char *uuid, guid_t *u); int uuid_parse(const char *uuid, uuid_t *u); -/* MEI UUID type, don't use anywhere else */ -#include <uapi/linux/uuid.h> - #endif diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 43f59ef10cc9..db1b0eaef4eb 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -10,13 +10,19 @@ #include <linux/if_ether.h> /** - * struct vdpa_calllback - vDPA callback definition. + * struct vdpa_callback - vDPA callback definition. * @callback: interrupt callback function * @private: the data passed to the callback function + * @trigger: the eventfd for the callback (Optional). + * When it is set, the vDPA driver must guarantee that + * signaling it is functional equivalent to triggering + * the callback. Then vDPA parent can signal it directly + * instead of triggering the callback. */ struct vdpa_callback { irqreturn_t (*callback)(void *data); void *private; + struct eventfd_ctx *trigger; }; /** @@ -114,7 +120,7 @@ struct vdpa_dev_set_config { }; /** - * Corresponding file area for device memory mapping + * struct vdpa_map_file - file area for device memory mapping * @file: vma->vm_file for the mapping * @offset: mapping offset in the vm_file */ @@ -143,6 +149,14 @@ struct vdpa_map_file { * @kick_vq: Kick the virtqueue * @vdev: vdpa device * @idx: virtqueue index + * @kick_vq_with_data: Kick the virtqueue and supply extra data + * (only if VIRTIO_F_NOTIFICATION_DATA is negotiated) + * @vdev: vdpa device + * @data for split virtqueue: + * 16 bits vqn and 16 bits next available index. + * @data for packed virtqueue: + * 16 bits vqn, 15 least significant bits of + * next available index and 1 bit next_wrap. * @set_vq_cb: Set the interrupt callback function for * a virtqueue * @vdev: vdpa device @@ -165,10 +179,16 @@ struct vdpa_map_file { * @vdev: vdpa device * @idx: virtqueue index * @state: pointer to returned state (last_avail_idx) + * @get_vendor_vq_stats: Get the vendor statistics of a device. + * @vdev: vdpa device + * @idx: virtqueue index + * @msg: socket buffer holding stats message + * @extack: extack for reporting error messages + * Returns integer: success (0) or error (< 0) * @get_vq_notification: Get the notification area for a virtqueue (optional) * @vdev: vdpa device * @idx: virtqueue index - * Returns the notifcation area + * Returns the notification area * @get_vq_irq: Get the irq number of a virtqueue (optional, * but must implemented if require vq irq offloading) * @vdev: vdpa device @@ -250,6 +270,15 @@ struct vdpa_map_file { * @vdev: vdpa device * Returns the iova range supported by * the device. + * @set_vq_affinity: Set the affinity of virtqueue (optional) + * @vdev: vdpa device + * @idx: virtqueue index + * @cpu_mask: the affinity mask + * Returns integer: success (0) or error (< 0) + * @get_vq_affinity: Get the affinity of virtqueue (optional) + * @vdev: vdpa device + * @idx: virtqueue index + * Returns the affinity mask * @set_group_asid: Set address space identifier for a * virtqueue group (optional) * @vdev: vdpa device @@ -290,6 +319,14 @@ struct vdpa_map_file { * @vdev: vdpa device * @idx: virtqueue index * Returns pointer to structure device or error (NULL) + * @bind_mm: Bind the device to a specific address space + * so the vDPA framework can use VA when this + * callback is implemented. (optional) + * @vdev: vdpa device + * @mm: address space to bind + * @unbind_mm: Unbind the device from the address space + * bound using the bind_mm callback. (optional) + * @vdev: vdpa device * @free: Free resources that belongs to vDPA (optional) * @vdev: vdpa device */ @@ -300,6 +337,7 @@ struct vdpa_config_ops { u64 device_area); void (*set_vq_num)(struct vdpa_device *vdev, u16 idx, u32 num); void (*kick_vq)(struct vdpa_device *vdev, u16 idx); + void (*kick_vq_with_data)(struct vdpa_device *vdev, u32 data); void (*set_vq_cb)(struct vdpa_device *vdev, u16 idx, struct vdpa_callback *cb); void (*set_vq_ready)(struct vdpa_device *vdev, u16 idx, bool ready); @@ -340,6 +378,10 @@ struct vdpa_config_ops { const void *buf, unsigned int len); u32 (*get_generation)(struct vdpa_device *vdev); struct vdpa_iova_range (*get_iova_range)(struct vdpa_device *vdev); + int (*set_vq_affinity)(struct vdpa_device *vdev, u16 idx, + const struct cpumask *cpu_mask); + const struct cpumask *(*get_vq_affinity)(struct vdpa_device *vdev, + u16 idx); /* DMA ops */ int (*set_map)(struct vdpa_device *vdev, unsigned int asid, @@ -351,6 +393,8 @@ struct vdpa_config_ops { int (*set_group_asid)(struct vdpa_device *vdev, unsigned int group, unsigned int asid); struct device *(*get_vq_dma_dev)(struct vdpa_device *vdev, u16 idx); + int (*bind_mm)(struct vdpa_device *vdev, struct mm_struct *mm); + void (*unbind_mm)(struct vdpa_device *vdev); /* Free device resources */ void (*free)(struct vdpa_device *vdev); @@ -506,6 +550,8 @@ struct vdpa_mgmtdev_ops { * @config_attr_mask: bit mask of attributes of type enum vdpa_attr that * management device support during dev_add callback * @list: list entry + * @supported_features: features supported by device + * @max_supported_vqs: maximum number of virtqueues supported by device */ struct vdpa_mgmt_dev { struct device *device; diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 93134b023968..3188d8a374bd 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -60,7 +60,6 @@ struct vfio_device { void (*put_kvm)(struct kvm *kvm); #if IS_ENABLED(CONFIG_IOMMUFD) struct iommufd_device *iommufd_device; - struct iommufd_ctx *iommufd_ictx; bool iommufd_attached; #endif }; diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 2b472514c49b..b93238db94e3 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -34,8 +34,8 @@ struct virtqueue { unsigned int index; unsigned int num_free; unsigned int num_max; - void *priv; bool reset; + void *priv; }; int virtqueue_add_outbuf(struct virtqueue *vq, @@ -84,14 +84,14 @@ bool virtqueue_enable_cb_delayed(struct virtqueue *vq); void *virtqueue_detach_unused_buf(struct virtqueue *vq); -unsigned int virtqueue_get_vring_size(struct virtqueue *vq); +unsigned int virtqueue_get_vring_size(const struct virtqueue *vq); -bool virtqueue_is_broken(struct virtqueue *vq); +bool virtqueue_is_broken(const struct virtqueue *vq); -const struct vring *virtqueue_get_vring(struct virtqueue *vq); -dma_addr_t virtqueue_get_desc_addr(struct virtqueue *vq); -dma_addr_t virtqueue_get_avail_addr(struct virtqueue *vq); -dma_addr_t virtqueue_get_used_addr(struct virtqueue *vq); +const struct vring *virtqueue_get_vring(const struct virtqueue *vq); +dma_addr_t virtqueue_get_desc_addr(const struct virtqueue *vq); +dma_addr_t virtqueue_get_avail_addr(const struct virtqueue *vq); +dma_addr_t virtqueue_get_used_addr(const struct virtqueue *vq); int virtqueue_resize(struct virtqueue *vq, u32 num, void (*recycle)(struct virtqueue *vq, void *buf)); @@ -147,7 +147,7 @@ int virtio_device_restore(struct virtio_device *dev); #endif void virtio_reset_device(struct virtio_device *dev); -size_t virtio_max_dma_size(struct virtio_device *vdev); +size_t virtio_max_dma_size(const struct virtio_device *vdev); #define virtio_device_for_each_vq(vdev, vq) \ list_for_each_entry(vq, &vdev->vqs, list) diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index 8b95b69ef694..9b33df741b63 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -58,6 +58,7 @@ do { \ struct virtio_device; struct virtqueue; +struct device; /* * Creates a virtqueue and allocates the descriptor ring. If @@ -117,4 +118,6 @@ void vring_del_virtqueue(struct virtqueue *vq); void vring_transport_features(struct virtio_device *vdev); irqreturn_t vring_interrupt(int irq, void *_vq); + +u32 vring_notification_data(struct virtqueue *_vq); #endif /* _LINUX_VIRTIO_RING_H */ diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 7f5d1caf5890..8abfa1240040 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -150,6 +150,12 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, DIRECT_MAP_LEVEL2_SPLIT, DIRECT_MAP_LEVEL3_SPLIT, #endif +#ifdef CONFIG_PER_VMA_LOCK_STATS + VMA_LOCK_SUCCESS, + VMA_LOCK_ABORT, + VMA_LOCK_RETRY, + VMA_LOCK_MISS, +#endif NR_VM_EVENT_ITEMS }; diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 69250efa03d1..c720be70c8dd 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -14,6 +14,7 @@ struct vm_area_struct; /* vma defining user mapping in mm_types.h */ struct notifier_block; /* in notifier.h */ +struct iov_iter; /* in uio.h */ /* bits in flags of vmalloc's vm_struct below */ #define VM_IOREMAP 0x00000001 /* ioremap() and friends */ @@ -131,12 +132,8 @@ extern void *vm_map_ram(struct page **pages, unsigned int count, int node); extern void vm_unmap_aliases(void); #ifdef CONFIG_MMU -extern void __init vmalloc_init(void); extern unsigned long vmalloc_nr_pages(void); #else -static inline void vmalloc_init(void) -{ -} static inline unsigned long vmalloc_nr_pages(void) { return 0; } #endif @@ -251,7 +248,7 @@ static inline void set_vm_flush_reset_perms(void *addr) #endif /* for /proc/kcore */ -extern long vread(char *buf, char *addr, unsigned long count); +extern long vread_iter(struct iov_iter *iter, const char *addr, size_t count); /* * Internals. Don't use.. diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 19cf5b6892ce..fed855bae6d8 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -125,6 +125,12 @@ static inline void vm_events_fold_cpu(int cpu) #define count_vm_tlb_events(x, y) do { (void)(y); } while (0) #endif +#ifdef CONFIG_PER_VMA_LOCK_STATS +#define count_vm_vma_lock_event(x) count_vm_event(x) +#else +#define count_vm_vma_lock_event(x) do {} while (0) +#endif + #define __count_zid_vm_events(item, zid, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta) diff --git a/include/linux/vringh.h b/include/linux/vringh.h index 1991a02c6431..c3a8117dabe8 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -32,6 +32,9 @@ struct vringh { /* Can we get away with weak barriers? */ bool weak_barriers; + /* Use user's VA */ + bool use_va; + /* Last available index we saw (ie. where we're up to). */ u16 last_avail_idx; @@ -54,6 +57,9 @@ struct vringh { void (*notify)(struct vringh *); }; +struct virtio_device; +typedef void vrh_callback_t(struct virtio_device *, struct vringh *); + /** * struct vringh_config_ops - ops for creating a host vring from a virtio driver * @find_vrhs: find the host vrings and instantiate them @@ -65,8 +71,6 @@ struct vringh { * Returns 0 on success or error status * @del_vrhs: free the host vrings found by find_vrhs(). */ -struct virtio_device; -typedef void vrh_callback_t(struct virtio_device *, struct vringh *); struct vringh_config_ops { int (*find_vrhs)(struct virtio_device *vdev, unsigned nhvrs, struct vringh *vrhs[], vrh_callback_t *callbacks[]); @@ -81,6 +85,12 @@ struct vringh_range { /** * struct vringh_iov - iovec mangler. + * @iov: array of iovecs to operate on + * @consumed: number of bytes consumed within iov[i] + * @i: index of current iovec + * @used: number of iovecs present in @iov + * @max_num: maximum number of iovecs. + * corresponds to allocated memory of @iov * * Mangles iovec in place, and restores it. * Remaining data is iov + i, of used - i elements. @@ -93,6 +103,12 @@ struct vringh_iov { /** * struct vringh_kiov - kvec mangler. + * @iov: array of iovecs to operate on + * @consumed: number of bytes consumed within iov[i] + * @i: index of current iovec + * @used: number of iovecs present in @iov + * @max_num: maximum number of iovecs. + * corresponds to allocated memory of @iov * * Mangles kvec in place, and restores it. * Remaining data is iov + i, of used - i elements. @@ -284,6 +300,12 @@ int vringh_init_iotlb(struct vringh *vrh, u64 features, struct vring_avail *avail, struct vring_used *used); +int vringh_init_iotlb_va(struct vringh *vrh, u64 features, + unsigned int num, bool weak_barriers, + struct vring_desc *desc, + struct vring_avail *avail, + struct vring_used *used); + int vringh_getdesc_iotlb(struct vringh *vrh, struct vringh_kiov *riov, struct vringh_kiov *wiov, diff --git a/include/linux/vt_buffer.h b/include/linux/vt_buffer.h index 848db1b1569f..919d999a8c1d 100644 --- a/include/linux/vt_buffer.h +++ b/include/linux/vt_buffer.h @@ -16,7 +16,7 @@ #include <linux/string.h> -#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_MDA_CONSOLE) +#if IS_ENABLED(CONFIG_VGA_CONSOLE) || IS_ENABLED(CONFIG_MDA_CONSOLE) #include <asm/vga.h> #endif diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index ac551b8ee7d9..3992c994787f 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -472,6 +472,7 @@ extern unsigned int work_busy(struct work_struct *work); extern __printf(1, 2) void set_worker_desc(const char *fmt, ...); extern void print_worker_info(const char *log_lvl, struct task_struct *task); extern void show_all_workqueues(void); +extern void show_freezable_workqueues(void); extern void show_one_workqueue(struct workqueue_struct *wq); extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task); |