diff options
Diffstat (limited to 'include/linux')
520 files changed, 13617 insertions, 6085 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 34829f2c517a..0687a442fec7 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -24,6 +24,7 @@ struct irq_domain_ops; #define _LINUX #endif #include <acpi/acpi.h> +#include <acpi/acpi_numa.h> #ifdef CONFIG_ACPI @@ -35,7 +36,6 @@ struct irq_domain_ops; #include <acpi/acpi_bus.h> #include <acpi/acpi_drivers.h> -#include <acpi/acpi_numa.h> #include <acpi/acpi_io.h> #include <asm/acpi.h> @@ -237,14 +237,6 @@ acpi_table_parse_cedt(enum acpi_cedt_type id, int acpi_parse_mcfg (struct acpi_table_header *header); void acpi_table_print_madt_entry (struct acpi_subtable_header *madt); -static inline bool acpi_gicc_is_usable(struct acpi_madt_generic_interrupt *gicc) -{ - return gicc->flags & ACPI_MADT_ENABLED; -} - -/* the following numa functions are architecture-dependent */ -void acpi_numa_slit_init (struct acpi_table_slit *slit); - #if defined(CONFIG_X86) || defined(CONFIG_LOONGARCH) void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa); #else @@ -267,7 +259,11 @@ static inline void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { } #endif -int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma); +#ifdef CONFIG_RISCV +void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa); +#else +static inline void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa) { } +#endif #ifndef PHYS_CPUID_INVALID typedef u32 phys_cpuid_t; @@ -284,6 +280,9 @@ static inline bool invalid_phys_cpuid(phys_cpuid_t phys_id) return phys_id == PHYS_CPUID_INVALID; } + +int __init acpi_get_madt_revision(void); + /* Validate the processor object's proc_id */ bool acpi_duplicate_processor_id(int proc_id); /* Processor _CTS control */ @@ -309,6 +308,8 @@ int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, int acpi_unmap_cpu(int cpu); #endif /* CONFIG_ACPI_HOTPLUG_CPU */ +acpi_handle acpi_get_processor_handle(int cpu); + #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr); #endif @@ -421,7 +422,7 @@ extern char *wmi_get_acpi_device_uid(const char *guid); extern char acpi_video_backlight_string[]; extern long acpi_is_video_device(acpi_handle handle); -extern int acpi_blacklisted(void); + extern void acpi_osi_setup(char *str); extern bool acpi_osi_is_win8(void); @@ -573,10 +574,15 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); #define OSC_SB_CPCV2_SUPPORT 0x00000040 #define OSC_SB_PCLPI_SUPPORT 0x00000080 #define OSC_SB_OSLPI_SUPPORT 0x00000100 +#define OSC_SB_FAST_THERMAL_SAMPLING_SUPPORT 0x00000200 +#define OSC_SB_OVER_16_PSTATES_SUPPORT 0x00000400 +#define OSC_SB_GED_SUPPORT 0x00000800 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT 0x00001000 -#define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00002000 +#define OSC_SB_IRQ_RESOURCE_SOURCE_SUPPORT 0x00002000 #define OSC_SB_CPC_FLEXIBLE_ADR_SPACE 0x00004000 +#define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00020000 #define OSC_SB_NATIVE_USB4_SUPPORT 0x00040000 +#define OSC_SB_BATTERY_CHARGE_LIMITING_SUPPORT 0x00080000 #define OSC_SB_PRM_SUPPORT 0x00200000 #define OSC_SB_FFH_OPR_SUPPORT 0x00400000 @@ -762,6 +768,7 @@ static inline u64 acpi_arch_get_root_pointer(void) } #endif +int acpi_get_local_u64_address(acpi_handle handle, u64 *addr); int acpi_get_local_address(acpi_handle handle, u32 *addr); const char *acpi_get_subsystem_id(acpi_handle handle); @@ -778,8 +785,6 @@ const char *acpi_get_subsystem_id(acpi_handle handle); #define acpi_dev_uid_match(adev, uid2) (adev && false) #define acpi_dev_hid_uid_match(adev, hid2, uid2) (adev && false) -#include <acpi/acpi_numa.h> - struct fwnode_handle; static inline bool acpi_dev_found(const char *hid) @@ -1077,6 +1082,11 @@ static inline bool acpi_sleep_state_supported(u8 sleep_state) return false; } +static inline acpi_handle acpi_get_processor_handle(int cpu) +{ + return NULL; +} + #endif /* !CONFIG_ACPI */ extern void arch_post_acpi_subsys_init(void); @@ -1233,7 +1243,7 @@ bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); bool acpi_gpio_get_io_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); -int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *name, int index, +int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *con_id, int index, bool *wake_capable); #else static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, @@ -1246,7 +1256,7 @@ static inline bool acpi_gpio_get_io_resource(struct acpi_resource *ares, { return false; } -static inline int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *name, +static inline int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *con_id, int index, bool *wake_capable) { return -ENXIO; @@ -1259,10 +1269,10 @@ static inline int acpi_dev_gpio_irq_wake_get(struct acpi_device *adev, int index return acpi_dev_gpio_irq_wake_get_by(adev, NULL, index, wake_capable); } -static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, +static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *con_id, int index) { - return acpi_dev_gpio_irq_wake_get_by(adev, name, index, NULL); + return acpi_dev_gpio_irq_wake_get_by(adev, con_id, index, NULL); } static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 1cb65592c95d..d4ed5622cf2b 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -39,7 +39,7 @@ void iort_get_rmr_sids(struct fwnode_handle *iommu_fwnode, void iort_put_rmr_sids(struct fwnode_handle *iommu_fwnode, struct list_head *head); /* IOMMU interface */ -int iort_dma_get_ranges(struct device *dev, u64 *size); +int iort_dma_get_ranges(struct device *dev, u64 *limit); int iort_iommu_configure_id(struct device *dev, const u32 *id_in); void iort_iommu_get_resv_regions(struct device *dev, struct list_head *head); phys_addr_t acpi_iort_dma_get_max_cpu_address(void); @@ -55,7 +55,7 @@ void iort_get_rmr_sids(struct fwnode_handle *iommu_fwnode, struct list_head *hea static inline void iort_put_rmr_sids(struct fwnode_handle *iommu_fwnode, struct list_head *head) { } /* IOMMU interface */ -static inline int iort_dma_get_ranges(struct device *dev, u64 *size) +static inline int iort_dma_get_ranges(struct device *dev, u64 *limit) { return -ENODEV; } static inline int iort_iommu_configure_id(struct device *dev, const u32 *id_in) { return -ENODEV; } diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h new file mode 100644 index 000000000000..8c61ccd161ba --- /dev/null +++ b/include/linux/alloc_tag.h @@ -0,0 +1,217 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * allocation tagging + */ +#ifndef _LINUX_ALLOC_TAG_H +#define _LINUX_ALLOC_TAG_H + +#include <linux/bug.h> +#include <linux/codetag.h> +#include <linux/container_of.h> +#include <linux/preempt.h> +#include <asm/percpu.h> +#include <linux/cpumask.h> +#include <linux/smp.h> +#include <linux/static_key.h> +#include <linux/irqflags.h> + +struct alloc_tag_counters { + u64 bytes; + u64 calls; +}; + +/* + * An instance of this structure is created in a special ELF section at every + * allocation callsite. At runtime, the special section is treated as + * an array of these. Embedded codetag utilizes codetag framework. + */ +struct alloc_tag { + struct codetag ct; + struct alloc_tag_counters __percpu *counters; +} __aligned(8); + +#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG + +#define CODETAG_EMPTY ((void *)1) + +static inline bool is_codetag_empty(union codetag_ref *ref) +{ + return ref->ct == CODETAG_EMPTY; +} + +static inline void set_codetag_empty(union codetag_ref *ref) +{ + if (ref) + ref->ct = CODETAG_EMPTY; +} + +#else /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */ + +static inline bool is_codetag_empty(union codetag_ref *ref) { return false; } +static inline void set_codetag_empty(union codetag_ref *ref) {} + +#endif /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */ + +#ifdef CONFIG_MEM_ALLOC_PROFILING + +struct codetag_bytes { + struct codetag *ct; + s64 bytes; +}; + +size_t alloc_tag_top_users(struct codetag_bytes *tags, size_t count, bool can_sleep); + +static inline struct alloc_tag *ct_to_alloc_tag(struct codetag *ct) +{ + return container_of(ct, struct alloc_tag, ct); +} + +#ifdef ARCH_NEEDS_WEAK_PER_CPU +/* + * When percpu variables are required to be defined as weak, static percpu + * variables can't be used inside a function (see comments for DECLARE_PER_CPU_SECTION). + * Instead we will accound all module allocations to a single counter. + */ +DECLARE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag); + +#define DEFINE_ALLOC_TAG(_alloc_tag) \ + static struct alloc_tag _alloc_tag __used __aligned(8) \ + __section("alloc_tags") = { \ + .ct = CODE_TAG_INIT, \ + .counters = &_shared_alloc_tag }; + +#else /* ARCH_NEEDS_WEAK_PER_CPU */ + +#define DEFINE_ALLOC_TAG(_alloc_tag) \ + static DEFINE_PER_CPU(struct alloc_tag_counters, _alloc_tag_cntr); \ + static struct alloc_tag _alloc_tag __used __aligned(8) \ + __section("alloc_tags") = { \ + .ct = CODE_TAG_INIT, \ + .counters = &_alloc_tag_cntr }; + +#endif /* ARCH_NEEDS_WEAK_PER_CPU */ + +DECLARE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT, + mem_alloc_profiling_key); + +static inline bool mem_alloc_profiling_enabled(void) +{ + return static_branch_maybe(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT, + &mem_alloc_profiling_key); +} + +static inline struct alloc_tag_counters alloc_tag_read(struct alloc_tag *tag) +{ + struct alloc_tag_counters v = { 0, 0 }; + struct alloc_tag_counters *counter; + int cpu; + + for_each_possible_cpu(cpu) { + counter = per_cpu_ptr(tag->counters, cpu); + v.bytes += counter->bytes; + v.calls += counter->calls; + } + + return v; +} + +#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG +static inline void alloc_tag_add_check(union codetag_ref *ref, struct alloc_tag *tag) +{ + WARN_ONCE(ref && ref->ct, + "alloc_tag was not cleared (got tag for %s:%u)\n", + ref->ct->filename, ref->ct->lineno); + + WARN_ONCE(!tag, "current->alloc_tag not set\n"); +} + +static inline void alloc_tag_sub_check(union codetag_ref *ref) +{ + WARN_ONCE(ref && !ref->ct, "alloc_tag was not set\n"); +} +#else +static inline void alloc_tag_add_check(union codetag_ref *ref, struct alloc_tag *tag) {} +static inline void alloc_tag_sub_check(union codetag_ref *ref) {} +#endif + +/* Caller should verify both ref and tag to be valid */ +static inline void __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) +{ + ref->ct = &tag->ct; + /* + * We need in increment the call counter every time we have a new + * allocation or when we split a large allocation into smaller ones. + * Each new reference for every sub-allocation needs to increment call + * counter because when we free each part the counter will be decremented. + */ + this_cpu_inc(tag->counters->calls); +} + +static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag) +{ + alloc_tag_add_check(ref, tag); + if (!ref || !tag) + return; + + __alloc_tag_ref_set(ref, tag); +} + +static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes) +{ + alloc_tag_add_check(ref, tag); + if (!ref || !tag) + return; + + __alloc_tag_ref_set(ref, tag); + this_cpu_add(tag->counters->bytes, bytes); +} + +static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) +{ + struct alloc_tag *tag; + + alloc_tag_sub_check(ref); + if (!ref || !ref->ct) + return; + + if (is_codetag_empty(ref)) { + ref->ct = NULL; + return; + } + + tag = ct_to_alloc_tag(ref->ct); + + this_cpu_sub(tag->counters->bytes, bytes); + this_cpu_dec(tag->counters->calls); + + ref->ct = NULL; +} + +#define alloc_tag_record(p) ((p) = current->alloc_tag) + +#else /* CONFIG_MEM_ALLOC_PROFILING */ + +#define DEFINE_ALLOC_TAG(_alloc_tag) +static inline bool mem_alloc_profiling_enabled(void) { return false; } +static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, + size_t bytes) {} +static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) {} +#define alloc_tag_record(p) do {} while (0) + +#endif /* CONFIG_MEM_ALLOC_PROFILING */ + +#define alloc_hooks_tag(_tag, _do_alloc) \ +({ \ + struct alloc_tag * __maybe_unused _old = alloc_tag_save(_tag); \ + typeof(_do_alloc) _res = _do_alloc; \ + alloc_tag_restore(_tag, _old); \ + _res; \ +}) + +#define alloc_hooks(_do_alloc) \ +({ \ + DEFINE_ALLOC_TAG(_alloc_tag); \ + alloc_hooks_tag(&_alloc_tag, _do_alloc); \ +}) + +#endif /* _LINUX_ALLOC_TAG_H */ diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index c60a6a14638c..958a55bcc708 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -112,11 +112,18 @@ extern struct bus_type amba_bustype; #define amba_get_drvdata(d) dev_get_drvdata(&d->dev) #define amba_set_drvdata(d,p) dev_set_drvdata(&d->dev, p) +/* + * use a macro to avoid include chaining to get THIS_MODULE + */ +#define amba_driver_register(drv) \ + __amba_driver_register(drv, THIS_MODULE) + #ifdef CONFIG_ARM_AMBA -int amba_driver_register(struct amba_driver *); +int __amba_driver_register(struct amba_driver *, struct module *); void amba_driver_unregister(struct amba_driver *); #else -static inline int amba_driver_register(struct amba_driver *drv) +static inline int __amba_driver_register(struct amba_driver *drv, + struct module *owner) { return -EINVAL; } diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h deleted file mode 100644 index d21838835abd..000000000000 --- a/include/linux/amd-pstate.h +++ /dev/null @@ -1,127 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * linux/include/linux/amd-pstate.h - * - * Copyright (C) 2022 Advanced Micro Devices, Inc. - * - * Author: Meng Li <li.meng@amd.com> - */ - -#ifndef _LINUX_AMD_PSTATE_H -#define _LINUX_AMD_PSTATE_H - -#include <linux/pm_qos.h> - -#define AMD_CPPC_EPP_PERFORMANCE 0x00 -#define AMD_CPPC_EPP_BALANCE_PERFORMANCE 0x80 -#define AMD_CPPC_EPP_BALANCE_POWERSAVE 0xBF -#define AMD_CPPC_EPP_POWERSAVE 0xFF - -/********************************************************************* - * AMD P-state INTERFACE * - *********************************************************************/ -/** - * struct amd_aperf_mperf - * @aperf: actual performance frequency clock count - * @mperf: maximum performance frequency clock count - * @tsc: time stamp counter - */ -struct amd_aperf_mperf { - u64 aperf; - u64 mperf; - u64 tsc; -}; - -/** - * struct amd_cpudata - private CPU data for AMD P-State - * @cpu: CPU number - * @req: constraint request to apply - * @cppc_req_cached: cached performance request hints - * @highest_perf: the maximum performance an individual processor may reach, - * assuming ideal conditions - * For platforms that do not support the preferred core feature, the - * highest_pef may be configured with 166 or 255, to avoid max frequency - * calculated wrongly. we take the fixed value as the highest_perf. - * @nominal_perf: the maximum sustained performance level of the processor, - * assuming ideal operating conditions - * @lowest_nonlinear_perf: the lowest performance level at which nonlinear power - * savings are achieved - * @lowest_perf: the absolute lowest performance level of the processor - * @prefcore_ranking: the preferred core ranking, the higher value indicates a higher - * priority. - * @max_freq: the frequency that mapped to highest_perf - * @min_freq: the frequency that mapped to lowest_perf - * @nominal_freq: the frequency that mapped to nominal_perf - * @lowest_nonlinear_freq: the frequency that mapped to lowest_nonlinear_perf - * @cur: Difference of Aperf/Mperf/tsc count between last and current sample - * @prev: Last Aperf/Mperf/tsc count value read from register - * @freq: current cpu frequency value - * @boost_supported: check whether the Processor or SBIOS supports boost mode - * @hw_prefcore: check whether HW supports preferred core featue. - * Only when hw_prefcore and early prefcore param are true, - * AMD P-State driver supports preferred core featue. - * @epp_policy: Last saved policy used to set energy-performance preference - * @epp_cached: Cached CPPC energy-performance preference value - * @policy: Cpufreq policy value - * @cppc_cap1_cached Cached MSR_AMD_CPPC_CAP1 register value - * - * The amd_cpudata is key private data for each CPU thread in AMD P-State, and - * represents all the attributes and goals that AMD P-State requests at runtime. - */ -struct amd_cpudata { - int cpu; - - struct freq_qos_request req[2]; - u64 cppc_req_cached; - - u32 highest_perf; - u32 nominal_perf; - u32 lowest_nonlinear_perf; - u32 lowest_perf; - u32 prefcore_ranking; - u32 min_limit_perf; - u32 max_limit_perf; - u32 min_limit_freq; - u32 max_limit_freq; - - u32 max_freq; - u32 min_freq; - u32 nominal_freq; - u32 lowest_nonlinear_freq; - - struct amd_aperf_mperf cur; - struct amd_aperf_mperf prev; - - u64 freq; - bool boost_supported; - bool hw_prefcore; - - /* EPP feature related attributes*/ - s16 epp_policy; - s16 epp_cached; - u32 policy; - u64 cppc_cap1_cached; - bool suspended; -}; - -/* - * enum amd_pstate_mode - driver working mode of amd pstate - */ -enum amd_pstate_mode { - AMD_PSTATE_UNDEFINED = 0, - AMD_PSTATE_DISABLE, - AMD_PSTATE_PASSIVE, - AMD_PSTATE_ACTIVE, - AMD_PSTATE_GUIDED, - AMD_PSTATE_MAX, -}; - -static const char * const amd_pstate_mode_string[] = { - [AMD_PSTATE_UNDEFINED] = "undefined", - [AMD_PSTATE_DISABLE] = "disable", - [AMD_PSTATE_PASSIVE] = "passive", - [AMD_PSTATE_ACTIVE] = "active", - [AMD_PSTATE_GUIDED] = "guided", - NULL, -}; -#endif /* _LINUX_AMD_PSTATE_H */ diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h index 93a5f16d03f3..edef565c2a1a 100644 --- a/include/linux/anon_inodes.h +++ b/include/linux/anon_inodes.h @@ -9,12 +9,17 @@ #ifndef _LINUX_ANON_INODES_H #define _LINUX_ANON_INODES_H +#include <linux/types.h> + struct file_operations; struct inode; struct file *anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags); +struct file *anon_inode_getfile_fmode(const char *name, + const struct file_operations *fops, + void *priv, int flags, fmode_t f_mode); struct file *anon_inode_create_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index a63d61ca55af..b721f360d759 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -60,14 +60,14 @@ void topology_scale_freq_tick(void); void topology_set_scale_freq_source(struct scale_freq_data *data, const struct cpumask *cpus); void topology_clear_scale_freq_source(enum scale_freq_source source, const struct cpumask *cpus); -DECLARE_PER_CPU(unsigned long, thermal_pressure); +DECLARE_PER_CPU(unsigned long, hw_pressure); -static inline unsigned long topology_get_thermal_pressure(int cpu) +static inline unsigned long topology_get_hw_pressure(int cpu) { - return per_cpu(thermal_pressure, cpu); + return per_cpu(hw_pressure, cpu); } -void topology_update_thermal_pressure(const struct cpumask *cpus, +void topology_update_hw_pressure(const struct cpumask *cpus, unsigned long capped_freq); struct cpu_topology { diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index c906f666ff5d..89683f31ae12 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -126,6 +126,7 @@ /* FFA Bus/Device/Driver related */ struct ffa_device { u32 id; + u32 properties; int vm_id; bool mode_32bit; uuid_t uuid; @@ -148,7 +149,7 @@ struct ffa_driver { struct device_driver driver; }; -#define to_ffa_driver(d) container_of(d, struct ffa_driver, driver) +#define to_ffa_driver(d) container_of_const(d, struct ffa_driver, driver) static inline void ffa_dev_set_drvdata(struct ffa_device *fdev, void *data) { @@ -211,6 +212,9 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) { return false; } extern const struct bus_type ffa_bus_type; +/* The FF-A 1.0 partition structure lacks the uuid[4] */ +#define FFA_1_0_PARTITON_INFO_SZ (8) + /* FFA transport related */ struct ffa_partition_info { u16 id; @@ -221,12 +225,29 @@ struct ffa_partition_info { #define FFA_PARTITION_DIRECT_SEND BIT(1) /* partition can send and receive indirect messages. */ #define FFA_PARTITION_INDIRECT_MSG BIT(2) +/* partition can receive notifications */ +#define FFA_PARTITION_NOTIFICATION_RECV BIT(3) /* partition runs in the AArch64 execution state. */ #define FFA_PARTITION_AARCH64_EXEC BIT(8) u32 properties; u32 uuid[4]; }; +static inline +bool ffa_partition_check_property(struct ffa_device *dev, u32 property) +{ + return dev->properties & property; +} + +#define ffa_partition_supports_notify_recv(dev) \ + ffa_partition_check_property(dev, FFA_PARTITION_NOTIFICATION_RECV) + +#define ffa_partition_supports_indirect_msg(dev) \ + ffa_partition_check_property(dev, FFA_PARTITION_INDIRECT_MSG) + +#define ffa_partition_supports_direct_recv(dev) \ + ffa_partition_check_property(dev, FFA_PARTITION_DIRECT_RECV) + /* For use with FFA_MSG_SEND_DIRECT_{REQ,RESP} which pass data via registers */ struct ffa_send_direct_data { unsigned long data0; /* w3/x3 */ @@ -236,6 +257,14 @@ struct ffa_send_direct_data { unsigned long data4; /* w7/x7 */ }; +struct ffa_indirect_msg_hdr { + u32 flags; + u32 res0; + u32 offset; + u32 send_recv_id; + u32 size; +}; + struct ffa_mem_region_addr_range { /* The base IPA of the constituent memory region, aligned to 4 kiB */ u64 address; @@ -396,6 +425,7 @@ struct ffa_msg_ops { void (*mode_32bit_set)(struct ffa_device *dev); int (*sync_send_receive)(struct ffa_device *dev, struct ffa_send_direct_data *data); + int (*indirect_send)(struct ffa_device *dev, void *buf, size_t sz); }; struct ffa_mem_ops { diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index 956bcba5dbf2..2f9d36b72bd8 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -2242,7 +2242,7 @@ raw_atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) /** * raw_atomic_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: int value to add + * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -4368,7 +4368,7 @@ raw_atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) /** * raw_atomic64_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: s64 value to add + * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -4690,4 +4690,4 @@ raw_atomic64_dec_if_positive(atomic64_t *v) } #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// 14850c0b0db20c62fdc78ccd1d42b98b88d76331 +// b565db590afeeff0d7c9485ccbca5bb6e155749f diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index debd487fe971..9409a6ddf3e0 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -1349,7 +1349,7 @@ atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) /** * atomic_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: int value to add + * @i: int value to subtract * @v: pointer to atomic_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -2927,7 +2927,7 @@ atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) /** * atomic64_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: s64 value to add + * @i: s64 value to subtract * @v: pointer to atomic64_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -4505,7 +4505,7 @@ atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) /** * atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: long value to add + * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -5050,4 +5050,4 @@ atomic_long_dec_if_positive(atomic_long_t *v) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// ce5b65e0f1f8a276268b667194581d24bed219d4 +// 8829b337928e9508259079d32581775ececd415b diff --git a/include/linux/atomic/atomic-long.h b/include/linux/atomic/atomic-long.h index 3ef844b3ab8a..f86b29d90877 100644 --- a/include/linux/atomic/atomic-long.h +++ b/include/linux/atomic/atomic-long.h @@ -1535,7 +1535,7 @@ raw_atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) /** * raw_atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering - * @i: long value to add + * @i: long value to subtract * @v: pointer to atomic_long_t * * Atomically updates @v to (@v - @i) with full ordering. @@ -1809,4 +1809,4 @@ raw_atomic_long_dec_if_positive(atomic_long_t *v) } #endif /* _LINUX_ATOMIC_LONG_H */ -// 1c4a26fc77f345342953770ebe3c4d08e7ce2f9a +// eadf183c3600b8b92b91839dd3be6bcc560c752d diff --git a/include/linux/auxiliary_bus.h b/include/linux/auxiliary_bus.h index de21d9d24a95..662b8ae54b6a 100644 --- a/include/linux/auxiliary_bus.h +++ b/include/linux/auxiliary_bus.h @@ -58,6 +58,10 @@ * in * @name: Match name found by the auxiliary device driver, * @id: unique identitier if multiple devices of the same name are exported, + * @sysfs: embedded struct which hold all sysfs related fields, + * @sysfs.irqs: irqs xarray contains irq indices which are used by the device, + * @sysfs.lock: Synchronize irq sysfs creation, + * @sysfs.irq_dir_exists: whether "irqs" directory exists, * * An auxiliary_device represents a part of its parent device's functionality. * It is given a name that, combined with the registering drivers @@ -139,6 +143,11 @@ struct auxiliary_device { struct device dev; const char *name; u32 id; + struct { + struct xarray irqs; + struct mutex lock; /* Synchronize irq sysfs creation */ + bool irq_dir_exists; + } sysfs; }; /** @@ -203,7 +212,7 @@ static inline struct auxiliary_device *to_auxiliary_dev(struct device *dev) return container_of(dev, struct auxiliary_device, dev); } -static inline struct auxiliary_driver *to_auxiliary_drv(struct device_driver *drv) +static inline const struct auxiliary_driver *to_auxiliary_drv(const struct device_driver *drv) { return container_of(drv, struct auxiliary_driver, driver); } @@ -212,8 +221,24 @@ int auxiliary_device_init(struct auxiliary_device *auxdev); int __auxiliary_device_add(struct auxiliary_device *auxdev, const char *modname); #define auxiliary_device_add(auxdev) __auxiliary_device_add(auxdev, KBUILD_MODNAME) +#ifdef CONFIG_SYSFS +int auxiliary_device_sysfs_irq_add(struct auxiliary_device *auxdev, int irq); +void auxiliary_device_sysfs_irq_remove(struct auxiliary_device *auxdev, + int irq); +#else /* CONFIG_SYSFS */ +static inline int +auxiliary_device_sysfs_irq_add(struct auxiliary_device *auxdev, int irq) +{ + return 0; +} + +static inline void +auxiliary_device_sysfs_irq_remove(struct auxiliary_device *auxdev, int irq) {} +#endif + static inline void auxiliary_device_uninit(struct auxiliary_device *auxdev) { + mutex_destroy(&auxdev->sysfs.lock); put_device(&auxdev->dev); } diff --git a/include/linux/backing-file.h b/include/linux/backing-file.h index 3f1fe1774f1b..4b61b0e57720 100644 --- a/include/linux/backing-file.h +++ b/include/linux/backing-file.h @@ -22,6 +22,9 @@ struct backing_file_ctx { struct file *backing_file_open(const struct path *user_path, int flags, const struct path *real_path, const struct cred *cred); +struct file *backing_tmpfile_open(const struct path *user_path, int flags, + const struct path *real_parentpath, + umode_t mode, const struct cred *cred); ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter, struct kiocb *iocb, int flags, struct backing_file_ctx *ctx); diff --git a/include/linux/backlight.h b/include/linux/backlight.h index 614653e07e3a..ea9c1bc8148e 100644 --- a/include/linux/backlight.h +++ b/include/linux/backlight.h @@ -13,6 +13,7 @@ #include <linux/fb.h> #include <linux/mutex.h> #include <linux/notifier.h> +#include <linux/types.h> /** * enum backlight_update_reason - what method was used to update backlight @@ -110,7 +111,6 @@ enum backlight_scale { }; struct backlight_device; -struct fb_info; /** * struct backlight_ops - backlight operations @@ -160,18 +160,18 @@ struct backlight_ops { int (*get_brightness)(struct backlight_device *); /** - * @check_fb: Check the framebuffer device. + * @controls_device: Check against the display device * - * Check if given framebuffer device is the one bound to this backlight. - * This operation is optional and if not implemented it is assumed that the - * fbdev is always the one bound to the backlight. + * Check if the backlight controls the given display device. This + * operation is optional and if not implemented it is assumed that + * the display is always the one controlled by the backlight. * * RETURNS: * - * If info is NULL or the info matches the fbdev bound to the backlight return true. - * If info does not match the fbdev bound to the backlight return false. + * If display_dev is NULL or display_dev matches the device controlled by + * the backlight, return true. Otherwise return false. */ - int (*check_fb)(struct backlight_device *bd, struct fb_info *info); + bool (*controls_device)(struct backlight_device *bd, struct device *display_dev); }; /** @@ -209,33 +209,18 @@ struct backlight_properties { * attribute: /sys/class/backlight/<backlight>/bl_power * When the power property is updated update_status() is called. * - * The possible values are: (0: full on, 1 to 3: power saving - * modes; 4: full off), see FB_BLANK_XXX. + * The possible values are: (0: full on, 4: full off), see + * BACKLIGHT_POWER constants. * - * When the backlight device is enabled @power is set - * to FB_BLANK_UNBLANK. When the backlight device is disabled - * @power is set to FB_BLANK_POWERDOWN. + * When the backlight device is enabled, @power is set to + * BACKLIGHT_POWER_ON. When the backlight device is disabled, + * @power is set to BACKLIGHT_POWER_OFF. */ int power; - /** - * @fb_blank: The power state from the FBIOBLANK ioctl. - * - * When the FBIOBLANK ioctl is called @fb_blank is set to the - * blank parameter and the update_status() operation is called. - * - * When the backlight device is enabled @fb_blank is set - * to FB_BLANK_UNBLANK. When the backlight device is disabled - * @fb_blank is set to FB_BLANK_POWERDOWN. - * - * Backlight drivers should avoid using this property. It has been - * replaced by state & BL_CORE_FBLANK (although most drivers should - * use backlight_is_blank() as the preferred means to get the blank - * state). - * - * fb_blank is deprecated and will be removed. - */ - int fb_blank; +#define BACKLIGHT_POWER_ON (0) +#define BACKLIGHT_POWER_OFF (4) +#define BACKLIGHT_POWER_REDUCED (1) // deprecated; don't use in new code /** * @type: The type of backlight supported. @@ -365,8 +350,7 @@ static inline int backlight_enable(struct backlight_device *bd) if (!bd) return 0; - bd->props.power = FB_BLANK_UNBLANK; - bd->props.fb_blank = FB_BLANK_UNBLANK; + bd->props.power = BACKLIGHT_POWER_ON; bd->props.state &= ~BL_CORE_FBBLANK; return backlight_update_status(bd); @@ -381,8 +365,7 @@ static inline int backlight_disable(struct backlight_device *bd) if (!bd) return 0; - bd->props.power = FB_BLANK_POWERDOWN; - bd->props.fb_blank = FB_BLANK_POWERDOWN; + bd->props.power = BACKLIGHT_POWER_OFF; bd->props.state |= BL_CORE_FBBLANK; return backlight_update_status(bd); @@ -395,15 +378,13 @@ static inline int backlight_disable(struct backlight_device *bd) * Display is expected to be blank if any of these is true:: * * 1) if power in not UNBLANK - * 2) if fb_blank is not UNBLANK - * 3) if state indicate BLANK or SUSPENDED + * 2) if state indicate BLANK or SUSPENDED * * Returns true if display is expected to be blank, false otherwise. */ static inline bool backlight_is_blank(const struct backlight_device *bd) { - return bd->props.power != FB_BLANK_UNBLANK || - bd->props.fb_blank != FB_BLANK_UNBLANK || + return bd->props.power != BACKLIGHT_POWER_ON || bd->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK); } diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 70f97f685bff..e6c00e860951 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -19,13 +19,13 @@ struct linux_binprm { #ifdef CONFIG_MMU struct vm_area_struct *vma; unsigned long vma_pages; + unsigned long argmin; /* rlimit marker for copy_strings() */ #else # define MAX_ARG_PAGES 32 struct page *page[MAX_ARG_PAGES]; #endif struct mm_struct *mm; unsigned long p; /* current top of mem */ - unsigned long argmin; /* rlimit marker for copy_strings() */ unsigned int /* Should an execfd be passed to userspace? */ have_execfd:1, diff --git a/include/linux/bio-integrity.h b/include/linux/bio-integrity.h new file mode 100644 index 000000000000..dd831c269e99 --- /dev/null +++ b/include/linux/bio-integrity.h @@ -0,0 +1,152 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_BIO_INTEGRITY_H +#define _LINUX_BIO_INTEGRITY_H + +#include <linux/bio.h> + +enum bip_flags { + BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */ + BIP_MAPPED_INTEGRITY = 1 << 1, /* ref tag has been remapped */ + BIP_CTRL_NOCHECK = 1 << 2, /* disable HBA integrity checking */ + BIP_DISK_NOCHECK = 1 << 3, /* disable disk integrity checking */ + BIP_IP_CHECKSUM = 1 << 4, /* IP checksum */ + BIP_COPY_USER = 1 << 5, /* Kernel bounce buffer in use */ +}; + +struct bio_integrity_payload { + struct bio *bip_bio; /* parent bio */ + + struct bvec_iter bip_iter; + + unsigned short bip_vcnt; /* # of integrity bio_vecs */ + unsigned short bip_max_vcnt; /* integrity bio_vec slots */ + unsigned short bip_flags; /* control flags */ + + struct bvec_iter bio_iter; /* for rewinding parent bio */ + + struct work_struct bip_work; /* I/O completion */ + + struct bio_vec *bip_vec; + struct bio_vec bip_inline_vecs[];/* embedded bvec array */ +}; + +#ifdef CONFIG_BLK_DEV_INTEGRITY + +#define bip_for_each_vec(bvl, bip, iter) \ + for_each_bvec(bvl, (bip)->bip_vec, iter, (bip)->bip_iter) + +#define bio_for_each_integrity_vec(_bvl, _bio, _iter) \ + for_each_bio(_bio) \ + bip_for_each_vec(_bvl, _bio->bi_integrity, _iter) + +static inline struct bio_integrity_payload *bio_integrity(struct bio *bio) +{ + if (bio->bi_opf & REQ_INTEGRITY) + return bio->bi_integrity; + + return NULL; +} + +static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag) +{ + struct bio_integrity_payload *bip = bio_integrity(bio); + + if (bip) + return bip->bip_flags & flag; + + return false; +} + +static inline sector_t bip_get_seed(struct bio_integrity_payload *bip) +{ + return bip->bip_iter.bi_sector; +} + +static inline void bip_set_seed(struct bio_integrity_payload *bip, + sector_t seed) +{ + bip->bip_iter.bi_sector = seed; +} + +struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, gfp_t gfp, + unsigned int nr); +int bio_integrity_add_page(struct bio *bio, struct page *page, unsigned int len, + unsigned int offset); +int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t len, u32 seed); +void bio_integrity_unmap_user(struct bio *bio); +bool bio_integrity_prep(struct bio *bio); +void bio_integrity_advance(struct bio *bio, unsigned int bytes_done); +void bio_integrity_trim(struct bio *bio); +int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask); +int bioset_integrity_create(struct bio_set *bs, int pool_size); +void bioset_integrity_free(struct bio_set *bs); +void bio_integrity_init(void); + +#else /* CONFIG_BLK_DEV_INTEGRITY */ + +static inline struct bio_integrity_payload *bio_integrity(struct bio *bio) +{ + return NULL; +} + +static inline int bioset_integrity_create(struct bio_set *bs, int pool_size) +{ + return 0; +} + +static inline void bioset_integrity_free(struct bio_set *bs) +{ +} + +static inline int bio_integrity_map_user(struct bio *bio, void __user *ubuf, + ssize_t len, u32 seed) +{ + return -EINVAL; +} + +static inline void bio_integrity_unmap_user(struct bio *bio) +{ +} + +static inline bool bio_integrity_prep(struct bio *bio) +{ + return true; +} + +static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src, + gfp_t gfp_mask) +{ + return 0; +} + +static inline void bio_integrity_advance(struct bio *bio, + unsigned int bytes_done) +{ +} + +static inline void bio_integrity_trim(struct bio *bio) +{ +} + +static inline void bio_integrity_init(void) +{ +} + +static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag) +{ + return false; +} + +static inline struct bio_integrity_payload * +bio_integrity_alloc(struct bio *bio, gfp_t gfp, unsigned int nr) +{ + return ERR_PTR(-EINVAL); +} + +static inline int bio_integrity_add_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int offset) +{ + return 0; +} +#endif /* CONFIG_BLK_DEV_INTEGRITY */ +#endif /* _LINUX_BIO_INTEGRITY_H */ diff --git a/include/linux/bio.h b/include/linux/bio.h index 875d792bffff..a46e2047bea4 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -321,69 +321,6 @@ static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio) #define bio_for_each_folio_all(fi, bio) \ for (bio_first_folio(&fi, bio, 0); fi.folio; bio_next_folio(&fi, bio)) -enum bip_flags { - BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */ - BIP_MAPPED_INTEGRITY = 1 << 1, /* ref tag has been remapped */ - BIP_CTRL_NOCHECK = 1 << 2, /* disable HBA integrity checking */ - BIP_DISK_NOCHECK = 1 << 3, /* disable disk integrity checking */ - BIP_IP_CHECKSUM = 1 << 4, /* IP checksum */ - BIP_INTEGRITY_USER = 1 << 5, /* Integrity payload is user address */ - BIP_COPY_USER = 1 << 6, /* Kernel bounce buffer in use */ -}; - -/* - * bio integrity payload - */ -struct bio_integrity_payload { - struct bio *bip_bio; /* parent bio */ - - struct bvec_iter bip_iter; - - unsigned short bip_vcnt; /* # of integrity bio_vecs */ - unsigned short bip_max_vcnt; /* integrity bio_vec slots */ - unsigned short bip_flags; /* control flags */ - - struct bvec_iter bio_iter; /* for rewinding parent bio */ - - struct work_struct bip_work; /* I/O completion */ - - struct bio_vec *bip_vec; - struct bio_vec bip_inline_vecs[];/* embedded bvec array */ -}; - -#if defined(CONFIG_BLK_DEV_INTEGRITY) - -static inline struct bio_integrity_payload *bio_integrity(struct bio *bio) -{ - if (bio->bi_opf & REQ_INTEGRITY) - return bio->bi_integrity; - - return NULL; -} - -static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag) -{ - struct bio_integrity_payload *bip = bio_integrity(bio); - - if (bip) - return bip->bip_flags & flag; - - return false; -} - -static inline sector_t bip_get_seed(struct bio_integrity_payload *bip) -{ - return bip->bip_iter.bi_sector; -} - -static inline void bip_set_seed(struct bio_integrity_payload *bip, - sector_t seed) -{ - bip->bip_iter.bi_sector = seed; -} - -#endif /* CONFIG_BLK_DEV_INTEGRITY */ - void bio_trim(struct bio *bio, sector_t offset, sector_t size); extern struct bio *bio_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs); @@ -615,6 +552,13 @@ static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2) bl->tail = bl2->tail; } +static inline void bio_list_merge_init(struct bio_list *bl, + struct bio_list *bl2) +{ + bio_list_merge(bl, bl2); + bio_list_init(bl2); +} + static inline void bio_list_merge_head(struct bio_list *bl, struct bio_list *bl2) { @@ -714,95 +658,6 @@ static inline bool bioset_initialized(struct bio_set *bs) return bs->bio_slab != NULL; } -#if defined(CONFIG_BLK_DEV_INTEGRITY) - -#define bip_for_each_vec(bvl, bip, iter) \ - for_each_bvec(bvl, (bip)->bip_vec, iter, (bip)->bip_iter) - -#define bio_for_each_integrity_vec(_bvl, _bio, _iter) \ - for_each_bio(_bio) \ - bip_for_each_vec(_bvl, _bio->bi_integrity, _iter) - -int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t len, u32 seed); -extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int); -extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int); -extern bool bio_integrity_prep(struct bio *); -extern void bio_integrity_advance(struct bio *, unsigned int); -extern void bio_integrity_trim(struct bio *); -extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t); -extern int bioset_integrity_create(struct bio_set *, int); -extern void bioset_integrity_free(struct bio_set *); -extern void bio_integrity_init(void); - -#else /* CONFIG_BLK_DEV_INTEGRITY */ - -static inline void *bio_integrity(struct bio *bio) -{ - return NULL; -} - -static inline int bioset_integrity_create(struct bio_set *bs, int pool_size) -{ - return 0; -} - -static inline void bioset_integrity_free (struct bio_set *bs) -{ - return; -} - -static inline bool bio_integrity_prep(struct bio *bio) -{ - return true; -} - -static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src, - gfp_t gfp_mask) -{ - return 0; -} - -static inline void bio_integrity_advance(struct bio *bio, - unsigned int bytes_done) -{ - return; -} - -static inline void bio_integrity_trim(struct bio *bio) -{ - return; -} - -static inline void bio_integrity_init(void) -{ - return; -} - -static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag) -{ - return false; -} - -static inline void *bio_integrity_alloc(struct bio * bio, gfp_t gfp, - unsigned int nr) -{ - return ERR_PTR(-EINVAL); -} - -static inline int bio_integrity_add_page(struct bio *bio, struct page *page, - unsigned int len, unsigned int offset) -{ - return 0; -} - -static inline int bio_integrity_map_user(struct bio *bio, void __user *ubuf, - ssize_t len, u32 seed) -{ - return -EINVAL; -} - -#endif /* CONFIG_BLK_DEV_INTEGRITY */ - /* * Mark a bio as polled. Note that for async polled IO, the caller must * expect -EWOULDBLOCK if we cannot allocate a request (or other resources). @@ -824,5 +679,9 @@ static inline void bio_clear_polled(struct bio *bio) struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, unsigned int nr_pages, blk_opf_t opf, gfp_t gfp); +struct bio *bio_chain_and_submit(struct bio *prev, struct bio *new); + +struct bio *blk_alloc_discard_bio(struct block_device *bdev, + sector_t *sector, sector_t *nr_sects, gfp_t gfp_mask); #endif /* __LINUX_BIO_H */ diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index aa4096126553..d3b66d77df7a 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -83,6 +83,10 @@ struct device; * bitmap_to_arr64(buf, src, nbits) Copy nbits from buf to u64[] dst * bitmap_get_value8(map, start) Get 8bit value from map at start * bitmap_set_value8(map, value, start) Set 8bit value to map at start + * bitmap_read(map, start, nbits) Read an nbits-sized value from + * map at start + * bitmap_write(map, value, start, nbits) Write an nbits-sized value to + * map at start * * Note, bitmap_zero() and bitmap_fill() operate over the region of * unsigned longs, that is, bits behind bitmap till the unsigned long @@ -222,9 +226,11 @@ void bitmap_fold(unsigned long *dst, const unsigned long *orig, #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1))) +#define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE) + static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = 0; @@ -234,7 +240,7 @@ static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = ~0UL; @@ -245,7 +251,7 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits); if (small_const_nbits(nbits)) *dst = *src; @@ -264,6 +270,18 @@ static inline void bitmap_copy_clear_tail(unsigned long *dst, dst[nbits / BITS_PER_LONG] &= BITMAP_LAST_WORD_MASK(nbits); } +static inline void bitmap_copy_and_extend(unsigned long *to, + const unsigned long *from, + unsigned int count, unsigned int size) +{ + unsigned int copy = BITS_TO_LONGS(count); + + memcpy(to, from, copy * sizeof(long)); + if (count % BITS_PER_LONG) + to[copy - 1] &= BITMAP_LAST_WORD_MASK(count); + memset(to + copy, 0, bitmap_size(size) - copy * sizeof(long)); +} + /* * On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64 * machines the order of hi and lo parts of numbers match the bitmap structure. @@ -722,38 +740,83 @@ static inline void bitmap_from_u64(unsigned long *dst, u64 mask) } /** - * bitmap_get_value8 - get an 8-bit value within a memory region + * bitmap_read - read a value of n-bits from the memory region * @map: address to the bitmap memory region - * @start: bit offset of the 8-bit value; must be a multiple of 8 + * @start: bit offset of the n-bit value + * @nbits: size of value in bits, nonzero, up to BITS_PER_LONG * - * Returns the 8-bit value located at the @start bit offset within the @src - * memory region. + * Returns: value of @nbits bits located at the @start bit offset within the + * @map memory region. For @nbits = 0 and @nbits > BITS_PER_LONG the return + * value is undefined. */ -static inline unsigned long bitmap_get_value8(const unsigned long *map, - unsigned long start) +static inline unsigned long bitmap_read(const unsigned long *map, + unsigned long start, + unsigned long nbits) { - const size_t index = BIT_WORD(start); - const unsigned long offset = start % BITS_PER_LONG; + size_t index = BIT_WORD(start); + unsigned long offset = start % BITS_PER_LONG; + unsigned long space = BITS_PER_LONG - offset; + unsigned long value_low, value_high; + + if (unlikely(!nbits || nbits > BITS_PER_LONG)) + return 0; + + if (space >= nbits) + return (map[index] >> offset) & BITMAP_LAST_WORD_MASK(nbits); - return (map[index] >> offset) & 0xFF; + value_low = map[index] & BITMAP_FIRST_WORD_MASK(start); + value_high = map[index + 1] & BITMAP_LAST_WORD_MASK(start + nbits); + return (value_low >> offset) | (value_high << space); } /** - * bitmap_set_value8 - set an 8-bit value within a memory region + * bitmap_write - write n-bit value within a memory region * @map: address to the bitmap memory region - * @value: the 8-bit value; values wider than 8 bits may clobber bitmap - * @start: bit offset of the 8-bit value; must be a multiple of 8 + * @value: value to write, clamped to nbits + * @start: bit offset of the n-bit value + * @nbits: size of value in bits, nonzero, up to BITS_PER_LONG. + * + * bitmap_write() behaves as-if implemented as @nbits calls of __assign_bit(), + * i.e. bits beyond @nbits are ignored: + * + * for (bit = 0; bit < nbits; bit++) + * __assign_bit(start + bit, bitmap, val & BIT(bit)); + * + * For @nbits == 0 and @nbits > BITS_PER_LONG no writes are performed. */ -static inline void bitmap_set_value8(unsigned long *map, unsigned long value, - unsigned long start) -{ - const size_t index = BIT_WORD(start); - const unsigned long offset = start % BITS_PER_LONG; - - map[index] &= ~(0xFFUL << offset); +static inline void bitmap_write(unsigned long *map, unsigned long value, + unsigned long start, unsigned long nbits) +{ + size_t index; + unsigned long offset; + unsigned long space; + unsigned long mask; + bool fit; + + if (unlikely(!nbits || nbits > BITS_PER_LONG)) + return; + + mask = BITMAP_LAST_WORD_MASK(nbits); + value &= mask; + offset = start % BITS_PER_LONG; + space = BITS_PER_LONG - offset; + fit = space >= nbits; + index = BIT_WORD(start); + + map[index] &= (fit ? (~(mask << offset)) : ~BITMAP_FIRST_WORD_MASK(start)); map[index] |= value << offset; + if (fit) + return; + + map[index + 1] &= BITMAP_FIRST_WORD_MASK(start + nbits); + map[index + 1] |= (value >> space); } +#define bitmap_get_value8(map, start) \ + bitmap_read(map, start, BITS_PER_BYTE) +#define bitmap_set_value8(map, value, start) \ + bitmap_write(map, value, start, BITS_PER_BYTE) + #endif /* __ASSEMBLY__ */ #endif /* __LINUX_BITMAP_H */ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 2ba557e067fe..ba35bbf07798 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -8,19 +8,14 @@ #include <uapi/linux/kernel.h> -/* Set bits in the first 'n' bytes when loaded from memory */ -#ifdef __LITTLE_ENDIAN -# define aligned_byte_mask(n) ((1UL << 8*(n))-1) -#else -# define aligned_byte_mask(n) (~0xffUL << (BITS_PER_LONG - 8 - 8*(n))) -#endif - #define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) #define BITS_TO_LONGS(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(long)) #define BITS_TO_U64(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u64)) #define BITS_TO_U32(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u32)) #define BITS_TO_BYTES(nr) __KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(char)) +#define BYTES_TO_BITS(nb) ((nb) * BITS_PER_BYTE) + extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); extern unsigned int __sw_hweight32(unsigned int w); @@ -52,12 +47,17 @@ extern unsigned long __sw_hweight64(__u64 w); __builtin_constant_p(*(const unsigned long *)(addr))) ? \ const##op(nr, addr) : op(nr, addr)) +/* + * The following macros are non-atomic versions of their non-underscored + * counterparts. + */ #define __set_bit(nr, addr) bitop(___set_bit, nr, addr) #define __clear_bit(nr, addr) bitop(___clear_bit, nr, addr) #define __change_bit(nr, addr) bitop(___change_bit, nr, addr) #define __test_and_set_bit(nr, addr) bitop(___test_and_set_bit, nr, addr) #define __test_and_clear_bit(nr, addr) bitop(___test_and_clear_bit, nr, addr) #define __test_and_change_bit(nr, addr) bitop(___test_and_change_bit, nr, addr) + #define test_bit(nr, addr) bitop(_test_bit, nr, addr) #define test_bit_acquire(nr, addr) bitop(_test_bit_acquire, nr, addr) @@ -80,6 +80,7 @@ __check_bitop_pr(__test_and_set_bit); __check_bitop_pr(__test_and_clear_bit); __check_bitop_pr(__test_and_change_bit); __check_bitop_pr(test_bit); +__check_bitop_pr(test_bit_acquire); #undef __check_bitop_pr @@ -200,7 +201,7 @@ static __always_inline __s64 sign_extend64(__u64 value, int index) return (__s64)(value << shift) >> shift; } -static inline unsigned fls_long(unsigned long l) +static inline unsigned int fls_long(unsigned long l) { if (sizeof(l) == 4) return fls(l); @@ -236,7 +237,7 @@ static inline int get_count_order_long(unsigned long l) * The result is not defined if no bits are set, so check that @word * is non-zero before calling this. */ -static inline unsigned long __ffs64(u64 word) +static inline unsigned int __ffs64(u64 word) { #if BITS_PER_LONG == 32 if (((u32)word) == 0UL) @@ -252,18 +253,12 @@ static inline unsigned long __ffs64(u64 word) * @word: The word to search * @n: Bit to find */ -static inline unsigned long fns(unsigned long word, unsigned int n) +static inline unsigned int fns(unsigned long word, unsigned int n) { - unsigned int bit; + while (word && n--) + word &= word - 1; - while (word) { - bit = __ffs(word); - if (n-- == 0) - return bit; - __clear_bit(bit, &word); - } - - return BITS_PER_LONG; + return word ? __ffs(word) : BITS_PER_LONG; } /** @@ -272,23 +267,11 @@ static inline unsigned long fns(unsigned long word, unsigned int n) * @addr: the address to start counting from * @value: the value to assign */ -static __always_inline void assign_bit(long nr, volatile unsigned long *addr, - bool value) -{ - if (value) - set_bit(nr, addr); - else - clear_bit(nr, addr); -} +#define assign_bit(nr, addr, value) \ + ((value) ? set_bit((nr), (addr)) : clear_bit((nr), (addr))) -static __always_inline void __assign_bit(long nr, volatile unsigned long *addr, - bool value) -{ - if (value) - __set_bit(nr, addr); - else - __clear_bit(nr, addr); -} +#define __assign_bit(nr, addr, value) \ + ((value) ? __set_bit((nr), (addr)) : __clear_bit((nr), (addr))) /** * __ptr_set_bit - Set bit in a pointer's value diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h index e253e7bd0d17..de98049b7ded 100644 --- a/include/linux/blk-integrity.h +++ b/include/linux/blk-integrity.h @@ -3,55 +3,43 @@ #define _LINUX_BLK_INTEGRITY_H #include <linux/blk-mq.h> +#include <linux/bio-integrity.h> struct request; enum blk_integrity_flags { - BLK_INTEGRITY_VERIFY = 1 << 0, - BLK_INTEGRITY_GENERATE = 1 << 1, + BLK_INTEGRITY_NOVERIFY = 1 << 0, + BLK_INTEGRITY_NOGENERATE = 1 << 1, BLK_INTEGRITY_DEVICE_CAPABLE = 1 << 2, - BLK_INTEGRITY_IP_CHECKSUM = 1 << 3, + BLK_INTEGRITY_REF_TAG = 1 << 3, + BLK_INTEGRITY_STACKED = 1 << 4, }; -struct blk_integrity_iter { - void *prot_buf; - void *data_buf; - sector_t seed; - unsigned int data_size; - unsigned short interval; - unsigned char tuple_size; - unsigned char pi_offset; - const char *disk_name; -}; - -typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *); -typedef void (integrity_prepare_fn) (struct request *); -typedef void (integrity_complete_fn) (struct request *, unsigned int); - -struct blk_integrity_profile { - integrity_processing_fn *generate_fn; - integrity_processing_fn *verify_fn; - integrity_prepare_fn *prepare_fn; - integrity_complete_fn *complete_fn; - const char *name; -}; +const char *blk_integrity_profile_name(struct blk_integrity *bi); +bool queue_limits_stack_integrity(struct queue_limits *t, + struct queue_limits *b); +static inline bool queue_limits_stack_integrity_bdev(struct queue_limits *t, + struct block_device *bdev) +{ + return queue_limits_stack_integrity(t, &bdev->bd_disk->queue->limits); +} #ifdef CONFIG_BLK_DEV_INTEGRITY -void blk_integrity_register(struct gendisk *, struct blk_integrity *); -void blk_integrity_unregister(struct gendisk *); -int blk_integrity_compare(struct gendisk *, struct gendisk *); int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, struct scatterlist *); int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); -static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) +static inline bool +blk_integrity_queue_supports_integrity(struct request_queue *q) { - struct blk_integrity *bi = &disk->queue->integrity; + return q->limits.integrity.tuple_size; +} - if (!bi->profile) +static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) +{ + if (!blk_integrity_queue_supports_integrity(disk->queue)) return NULL; - - return bi; + return &disk->queue->limits.integrity; } static inline struct blk_integrity * @@ -60,18 +48,6 @@ bdev_get_integrity(struct block_device *bdev) return blk_get_integrity(bdev->bd_disk); } -static inline bool -blk_integrity_queue_supports_integrity(struct request_queue *q) -{ - return q->integrity.profile; -} - -static inline void blk_queue_max_integrity_segments(struct request_queue *q, - unsigned int segs) -{ - q->limits.max_integrity_segments = segs; -} - static inline unsigned short queue_max_integrity_segments(const struct request_queue *q) { @@ -106,14 +82,13 @@ static inline bool blk_integrity_rq(struct request *rq) } /* - * Return the first bvec that contains integrity data. Only drivers that are - * limited to a single integrity segment should use this helper. + * Return the current bvec that contains the integrity data. bip_iter may be + * advanced to iterate over the integrity data. */ -static inline struct bio_vec *rq_integrity_vec(struct request *rq) +static inline struct bio_vec rq_integrity_vec(struct request *rq) { - if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1)) - return NULL; - return rq->bio->bi_integrity->bip_vec; + return mp_bvec_iter_bvec(rq->bio->bi_integrity->bip_vec, + rq->bio->bi_integrity->bip_iter); } #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline int blk_rq_count_integrity_sg(struct request_queue *q, @@ -140,21 +115,6 @@ blk_integrity_queue_supports_integrity(struct request_queue *q) { return false; } -static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b) -{ - return 0; -} -static inline void blk_integrity_register(struct gendisk *d, - struct blk_integrity *b) -{ -} -static inline void blk_integrity_unregister(struct gendisk *d) -{ -} -static inline void blk_queue_max_integrity_segments(struct request_queue *q, - unsigned int segs) -{ -} static inline unsigned short queue_max_integrity_segments(const struct request_queue *q) { @@ -177,9 +137,11 @@ static inline int blk_integrity_rq(struct request *rq) return 0; } -static inline struct bio_vec *rq_integrity_vec(struct request *rq) +static inline struct bio_vec rq_integrity_vec(struct request *rq) { - return NULL; + /* the optimizer will remove all calls to this function */ + return (struct bio_vec){ }; } #endif /* CONFIG_BLK_DEV_INTEGRITY */ + #endif /* _LINUX_BLK_INTEGRITY_H */ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index d3d8fd8e229b..8d304b1d16b1 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -27,38 +27,61 @@ typedef enum rq_end_io_ret (rq_end_io_fn)(struct request *, blk_status_t); * request flags */ typedef __u32 __bitwise req_flags_t; -/* drive already may have started this one */ -#define RQF_STARTED ((__force req_flags_t)(1 << 1)) -/* request for flush sequence */ -#define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << 4)) -/* merge of different types, fail separately */ -#define RQF_MIXED_MERGE ((__force req_flags_t)(1 << 5)) -/* don't call prep for this one */ -#define RQF_DONTPREP ((__force req_flags_t)(1 << 7)) -/* use hctx->sched_tags */ -#define RQF_SCHED_TAGS ((__force req_flags_t)(1 << 8)) -/* use an I/O scheduler for this request */ -#define RQF_USE_SCHED ((__force req_flags_t)(1 << 9)) -/* vaguely specified driver internal error. Ignored by the block layer */ -#define RQF_FAILED ((__force req_flags_t)(1 << 10)) -/* don't warn about errors */ -#define RQF_QUIET ((__force req_flags_t)(1 << 11)) -/* account into disk and partition IO statistics */ -#define RQF_IO_STAT ((__force req_flags_t)(1 << 13)) -/* runtime pm request */ -#define RQF_PM ((__force req_flags_t)(1 << 15)) -/* on IO scheduler merge hash */ -#define RQF_HASHED ((__force req_flags_t)(1 << 16)) -/* track IO completion time */ -#define RQF_STATS ((__force req_flags_t)(1 << 17)) -/* Look at ->special_vec for the actual data payload instead of the - bio chain. */ -#define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18)) -/* The per-zone write lock is held for this request */ -#define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19)) -/* ->timeout has been called, don't expire again */ -#define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) -#define RQF_RESV ((__force req_flags_t)(1 << 23)) +/* Keep rqf_name[] in sync with the definitions below */ +enum { + /* drive already may have started this one */ + __RQF_STARTED, + /* request for flush sequence */ + __RQF_FLUSH_SEQ, + /* merge of different types, fail separately */ + __RQF_MIXED_MERGE, + /* don't call prep for this one */ + __RQF_DONTPREP, + /* use hctx->sched_tags */ + __RQF_SCHED_TAGS, + /* use an I/O scheduler for this request */ + __RQF_USE_SCHED, + /* vaguely specified driver internal error. Ignored by block layer */ + __RQF_FAILED, + /* don't warn about errors */ + __RQF_QUIET, + /* account into disk and partition IO statistics */ + __RQF_IO_STAT, + /* runtime pm request */ + __RQF_PM, + /* on IO scheduler merge hash */ + __RQF_HASHED, + /* track IO completion time */ + __RQF_STATS, + /* Look at ->special_vec for the actual data payload instead of the + bio chain. */ + __RQF_SPECIAL_PAYLOAD, + /* request completion needs to be signaled to zone write plugging. */ + __RQF_ZONE_WRITE_PLUGGING, + /* ->timeout has been called, don't expire again */ + __RQF_TIMED_OUT, + __RQF_RESV, + __RQF_BITS +}; + +#define RQF_STARTED ((__force req_flags_t)(1 << __RQF_STARTED)) +#define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << __RQF_FLUSH_SEQ)) +#define RQF_MIXED_MERGE ((__force req_flags_t)(1 << __RQF_MIXED_MERGE)) +#define RQF_DONTPREP ((__force req_flags_t)(1 << __RQF_DONTPREP)) +#define RQF_SCHED_TAGS ((__force req_flags_t)(1 << __RQF_SCHED_TAGS)) +#define RQF_USE_SCHED ((__force req_flags_t)(1 << __RQF_USE_SCHED)) +#define RQF_FAILED ((__force req_flags_t)(1 << __RQF_FAILED)) +#define RQF_QUIET ((__force req_flags_t)(1 << __RQF_QUIET)) +#define RQF_IO_STAT ((__force req_flags_t)(1 << __RQF_IO_STAT)) +#define RQF_PM ((__force req_flags_t)(1 << __RQF_PM)) +#define RQF_HASHED ((__force req_flags_t)(1 << __RQF_HASHED)) +#define RQF_STATS ((__force req_flags_t)(1 << __RQF_STATS)) +#define RQF_SPECIAL_PAYLOAD \ + ((__force req_flags_t)(1 << __RQF_SPECIAL_PAYLOAD)) +#define RQF_ZONE_WRITE_PLUGGING \ + ((__force req_flags_t)(1 << __RQF_ZONE_WRITE_PLUGGING)) +#define RQF_TIMED_OUT ((__force req_flags_t)(1 << __RQF_TIMED_OUT)) +#define RQF_RESV ((__force req_flags_t)(1 << __RQF_RESV)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ @@ -278,8 +301,12 @@ enum blk_eh_timer_return { BLK_EH_RESET_TIMER, }; -#define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */ -#define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */ +/* Keep alloc_policy_name[] in sync with the definitions below */ +enum { + BLK_TAG_ALLOC_FIFO, /* allocate starting from 0 */ + BLK_TAG_ALLOC_RR, /* allocate starting from last allocated tag */ + BLK_TAG_ALLOC_MAX +}; /** * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware @@ -644,6 +671,7 @@ struct blk_mq_ops { #endif }; +/* Keep hctx_flag_name[] in sync with the definitions below */ enum { BLK_MQ_F_SHOULD_MERGE = 1 << 0, BLK_MQ_F_TAG_QUEUE_SHARED = 1 << 1, @@ -653,27 +681,17 @@ enum { */ BLK_MQ_F_STACKING = 1 << 2, BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3, - BLK_MQ_F_BLOCKING = 1 << 5, + BLK_MQ_F_BLOCKING = 1 << 4, /* Do not allow an I/O scheduler to be configured. */ - BLK_MQ_F_NO_SCHED = 1 << 6, + BLK_MQ_F_NO_SCHED = 1 << 5, + /* * Select 'none' during queue registration in case of a single hwq * or shared hwqs instead of 'mq-deadline'. */ - BLK_MQ_F_NO_SCHED_BY_DEFAULT = 1 << 7, - BLK_MQ_F_ALLOC_POLICY_START_BIT = 8, + BLK_MQ_F_NO_SCHED_BY_DEFAULT = 1 << 6, + BLK_MQ_F_ALLOC_POLICY_START_BIT = 7, BLK_MQ_F_ALLOC_POLICY_BITS = 1, - - BLK_MQ_S_STOPPED = 0, - BLK_MQ_S_TAG_ACTIVE = 1, - BLK_MQ_S_SCHED_RESTART = 2, - - /* hw queue is inactive after all its CPUs become offline */ - BLK_MQ_S_INACTIVE = 3, - - BLK_MQ_MAX_DEPTH = 10240, - - BLK_MQ_CPU_WORK_BATCH = 8, }; #define BLK_MQ_FLAG_TO_ALLOC_POLICY(flags) \ ((flags >> BLK_MQ_F_ALLOC_POLICY_START_BIT) & \ @@ -682,8 +700,19 @@ enum { ((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \ << BLK_MQ_F_ALLOC_POLICY_START_BIT) +#define BLK_MQ_MAX_DEPTH (10240) #define BLK_MQ_NO_HCTX_IDX (-1U) +enum { + /* Keep hctx_state_name[] in sync with the definitions below */ + BLK_MQ_S_STOPPED, + BLK_MQ_S_TAG_ACTIVE, + BLK_MQ_S_SCHED_RESTART, + /* hw queue is inactive after all its CPUs become offline */ + BLK_MQ_S_INACTIVE, + BLK_MQ_S_MAX +}; + struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, struct queue_limits *lim, void *queuedata, struct lock_class_key *lkclass); @@ -1150,85 +1179,4 @@ static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, } void blk_dump_rq_flags(struct request *, char *); -#ifdef CONFIG_BLK_DEV_ZONED -static inline unsigned int blk_rq_zone_no(struct request *rq) -{ - return disk_zone_no(rq->q->disk, blk_rq_pos(rq)); -} - -static inline unsigned int blk_rq_zone_is_seq(struct request *rq) -{ - return disk_zone_is_seq(rq->q->disk, blk_rq_pos(rq)); -} - -/** - * blk_rq_is_seq_zoned_write() - Check if @rq requires write serialization. - * @rq: Request to examine. - * - * Note: REQ_OP_ZONE_APPEND requests do not require serialization. - */ -static inline bool blk_rq_is_seq_zoned_write(struct request *rq) -{ - return op_needs_zoned_write_locking(req_op(rq)) && - blk_rq_zone_is_seq(rq); -} - -bool blk_req_needs_zone_write_lock(struct request *rq); -bool blk_req_zone_write_trylock(struct request *rq); -void __blk_req_zone_write_lock(struct request *rq); -void __blk_req_zone_write_unlock(struct request *rq); - -static inline void blk_req_zone_write_lock(struct request *rq) -{ - if (blk_req_needs_zone_write_lock(rq)) - __blk_req_zone_write_lock(rq); -} - -static inline void blk_req_zone_write_unlock(struct request *rq) -{ - if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED) - __blk_req_zone_write_unlock(rq); -} - -static inline bool blk_req_zone_is_write_locked(struct request *rq) -{ - return rq->q->disk->seq_zones_wlock && - test_bit(blk_rq_zone_no(rq), rq->q->disk->seq_zones_wlock); -} - -static inline bool blk_req_can_dispatch_to_zone(struct request *rq) -{ - if (!blk_req_needs_zone_write_lock(rq)) - return true; - return !blk_req_zone_is_write_locked(rq); -} -#else /* CONFIG_BLK_DEV_ZONED */ -static inline bool blk_rq_is_seq_zoned_write(struct request *rq) -{ - return false; -} - -static inline bool blk_req_needs_zone_write_lock(struct request *rq) -{ - return false; -} - -static inline void blk_req_zone_write_lock(struct request *rq) -{ -} - -static inline void blk_req_zone_write_unlock(struct request *rq) -{ -} -static inline bool blk_req_zone_is_write_locked(struct request *rq) -{ - return false; -} - -static inline bool blk_req_can_dispatch_to_zone(struct request *rq) -{ - return true; -} -#endif /* CONFIG_BLK_DEV_ZONED */ - #endif /* BLK_MQ_H */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index cb1526ec44b5..36ed96133217 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -45,12 +45,17 @@ struct block_device { struct request_queue * bd_queue; struct disk_stats __percpu *bd_stats; unsigned long bd_stamp; - bool bd_read_only; /* read-only policy */ - u8 bd_partno; - bool bd_write_holder; - bool bd_has_submit_bio; + atomic_t __bd_flags; // partition number + flags +#define BD_PARTNO 255 // lower 8 bits; assign-once +#define BD_READ_ONLY (1u<<8) // read-only policy +#define BD_WRITE_HOLDER (1u<<9) +#define BD_HAS_SUBMIT_BIO (1u<<10) +#define BD_RO_WARNED (1u<<11) +#ifdef CONFIG_FAIL_MAKE_REQUEST +#define BD_MAKE_IT_FAIL (1u<<12) +#endif dev_t bd_dev; - struct inode *bd_inode; /* will die */ + struct address_space *bd_mapping; /* page cache */ atomic_t bd_openers; spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ @@ -65,10 +70,6 @@ struct block_device { struct mutex bd_fsfreeze_mutex; /* serialize freeze/thaw */ struct partition_meta_info *bd_meta_info; -#ifdef CONFIG_FAIL_MAKE_REQUEST - bool bd_make_it_fail; -#endif - bool bd_ro_warned; int bd_writers; /* * keep this out-of-line as it's both big and not needed in the fast @@ -88,15 +89,9 @@ struct block_device { /* * Block error status values. See block/blk-core:blk_errors for the details. - * Alpha cannot write a byte atomically, so we need to use 32-bit value. */ -#if defined(CONFIG_ALPHA) && !defined(__alpha_bwx__) -typedef u32 __bitwise blk_status_t; -typedef u32 blk_short_t; -#else typedef u8 __bitwise blk_status_t; typedef u16 blk_short_t; -#endif #define BLK_STS_OK 0 #define BLK_STS_NOTSUPP ((__force blk_status_t)1) #define BLK_STS_TIMEOUT ((__force blk_status_t)2) @@ -137,25 +132,13 @@ typedef u16 blk_short_t; #define BLK_STS_DEV_RESOURCE ((__force blk_status_t)13) /* - * BLK_STS_ZONE_RESOURCE is returned from the driver to the block layer if zone - * related resources are unavailable, but the driver can guarantee the queue - * will be rerun in the future once the resources become available again. - * - * This is different from BLK_STS_DEV_RESOURCE in that it explicitly references - * a zone specific resource and IO to a different zone on the same device could - * still be served. Examples of that are zones that are write-locked, but a read - * to the same zone could be served. - */ -#define BLK_STS_ZONE_RESOURCE ((__force blk_status_t)14) - -/* * BLK_STS_ZONE_OPEN_RESOURCE is returned from the driver in the completion * path if the device returns a status indicating that too many zone resources * are currently open. The same command should be successful if resubmitted * after the number of open zones decreases below the device's limits, which is * reported in the request_queue's max_open_zones. */ -#define BLK_STS_ZONE_OPEN_RESOURCE ((__force blk_status_t)15) +#define BLK_STS_ZONE_OPEN_RESOURCE ((__force blk_status_t)14) /* * BLK_STS_ZONE_ACTIVE_RESOURCE is returned from the driver in the completion @@ -164,20 +147,25 @@ typedef u16 blk_short_t; * after the number of active zones decreases below the device's limits, which * is reported in the request_queue's max_active_zones. */ -#define BLK_STS_ZONE_ACTIVE_RESOURCE ((__force blk_status_t)16) +#define BLK_STS_ZONE_ACTIVE_RESOURCE ((__force blk_status_t)15) /* * BLK_STS_OFFLINE is returned from the driver when the target device is offline * or is being taken offline. This could help differentiate the case where a * device is intentionally being shut down from a real I/O error. */ -#define BLK_STS_OFFLINE ((__force blk_status_t)17) +#define BLK_STS_OFFLINE ((__force blk_status_t)16) /* * BLK_STS_DURATION_LIMIT is returned from the driver when the target device * aborted the command because it exceeded one of its Command Duration Limits. */ -#define BLK_STS_DURATION_LIMIT ((__force blk_status_t)18) +#define BLK_STS_DURATION_LIMIT ((__force blk_status_t)17) + +/* + * Invalid size or alignment. + */ +#define BLK_STS_INVAL ((__force blk_status_t)19) /** * blk_path_error - returns true if error may be path related @@ -234,7 +222,12 @@ struct bio { struct bvec_iter bi_iter; - blk_qc_t bi_cookie; + union { + /* for polled bios: */ + blk_qc_t bi_cookie; + /* for plugged zoned writes only: */ + unsigned int __bi_nr_segments; + }; bio_end_io_t *bi_end_io; void *bi_private; #ifdef CONFIG_BLK_CGROUP @@ -304,7 +297,8 @@ enum { BIO_QOS_THROTTLED, /* bio went through rq_qos throttle path */ BIO_QOS_MERGED, /* but went through rq_qos merge path */ BIO_REMAPPED, - BIO_ZONE_WRITE_LOCKED, /* Owns a zoned device zone write lock */ + BIO_ZONE_WRITE_PLUGGING, /* bio handled through zone write plugging */ + BIO_EMULATES_ZONE_APPEND, /* bio emulates a zone append operation */ BIO_FLAG_LAST }; @@ -360,6 +354,7 @@ enum req_op { REQ_OP_LAST = (__force blk_opf_t)36, }; +/* Keep cmd_flag_name[] in sync with the definitions below */ enum req_flag_bits { __REQ_FAILFAST_DEV = /* no driver retries of device errors */ REQ_OP_BITS, @@ -381,7 +376,7 @@ enum req_flag_bits { __REQ_SWAP, /* swap I/O */ __REQ_DRV, /* for driver use */ __REQ_FS_PRIVATE, /* for file system (submitter) use */ - + __REQ_ATOMIC, /* for atomic write operations */ /* * Command specific flags, keep last: */ @@ -413,6 +408,7 @@ enum req_flag_bits { #define REQ_SWAP (__force blk_opf_t)(1ULL << __REQ_SWAP) #define REQ_DRV (__force blk_opf_t)(1ULL << __REQ_DRV) #define REQ_FS_PRIVATE (__force blk_opf_t)(1ULL << __REQ_FS_PRIVATE) +#define REQ_ATOMIC (__force blk_opf_t)(1ULL << __REQ_ATOMIC) #define REQ_NOUNMAP (__force blk_opf_t)(1ULL << __REQ_NOUNMAP) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 69e7da33ca49..e85ec73a07d5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -105,9 +105,16 @@ enum { struct disk_events; struct badblocks; +enum blk_integrity_checksum { + BLK_INTEGRITY_CSUM_NONE = 0, + BLK_INTEGRITY_CSUM_IP = 1, + BLK_INTEGRITY_CSUM_CRC = 2, + BLK_INTEGRITY_CSUM_CRC64 = 3, +} __packed ; + struct blk_integrity { - const struct blk_integrity_profile *profile; unsigned char flags; + enum blk_integrity_checksum csum_type; unsigned char tuple_size; unsigned char pi_offset; unsigned char interval_exp; @@ -179,22 +186,22 @@ struct gendisk { #ifdef CONFIG_BLK_DEV_ZONED /* - * Zoned block device information for request dispatch control. - * nr_zones is the total number of zones of the device. This is always - * 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones - * bits which indicates if a zone is conventional (bit set) or - * sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones - * bits which indicates if a zone is write locked, that is, if a write - * request targeting the zone was dispatched. - * - * Reads of this information must be protected with blk_queue_enter() / - * blk_queue_exit(). Modifying this information is only allowed while - * no requests are being processed. See also blk_mq_freeze_queue() and - * blk_mq_unfreeze_queue(). + * Zoned block device information. Reads of this information must be + * protected with blk_queue_enter() / blk_queue_exit(). Modifying this + * information is only allowed while no requests are being processed. + * See also blk_mq_freeze_queue() and blk_mq_unfreeze_queue(). */ unsigned int nr_zones; + unsigned int zone_capacity; + unsigned int last_zone_capacity; unsigned long *conv_zones_bitmap; - unsigned long *seq_zones_wlock; + unsigned int zone_wplugs_hash_bits; + spinlock_t zone_wplugs_lock; + struct mempool_s *zone_wplugs_pool; + struct hlist_head *zone_wplugs_hash; + struct list_head zone_wplugs_err_list; + struct work_struct zone_wplugs_work; + struct workqueue_struct *zone_wplugs_wq; #endif /* CONFIG_BLK_DEV_ZONED */ #if IS_ENABLED(CONFIG_CDROM) @@ -213,11 +220,6 @@ struct gendisk { struct blk_independent_access_ranges *ia_ranges; }; -static inline bool disk_live(struct gendisk *disk) -{ - return !inode_unhashed(disk->part0->bd_inode); -} - /** * disk_openers - returns how many openers are there for a disk * @disk: disk to check @@ -233,6 +235,19 @@ static inline unsigned int disk_openers(struct gendisk *disk) return atomic_read(&disk->part0->bd_openers); } +/** + * disk_has_partscan - return %true if partition scanning is enabled on a disk + * @disk: disk to check + * + * Returns %true if partitions scanning is enabled for @disk, or %false if + * partition scanning is disabled either permanently or temporarily. + */ +static inline bool disk_has_partscan(struct gendisk *disk) +{ + return !(disk->flags & (GENHD_FL_NO_PART | GENHD_FL_HIDDEN)) && + !test_bit(GD_SUPPRESS_PART_SCAN, &disk->state); +} + /* * The gendisk is refcounted by the part0 block_device, and the bd_device * therein is also used for device model presentation in sysfs. @@ -253,6 +268,7 @@ static inline dev_t disk_devt(struct gendisk *disk) return MKDEV(disk->major, disk->first_minor); } +/* blk_validate_limits() validates bsize, so drivers don't usually need to */ static inline int blk_validate_block_size(unsigned long bsize) { if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize)) @@ -267,17 +283,75 @@ static inline bool blk_op_is_passthrough(blk_opf_t op) return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT; } +/* flags set by the driver in queue_limits.features */ +typedef unsigned int __bitwise blk_features_t; + +/* supports a volatile write cache */ +#define BLK_FEAT_WRITE_CACHE ((__force blk_features_t)(1u << 0)) + +/* supports passing on the FUA bit */ +#define BLK_FEAT_FUA ((__force blk_features_t)(1u << 1)) + +/* rotational device (hard drive or floppy) */ +#define BLK_FEAT_ROTATIONAL ((__force blk_features_t)(1u << 2)) + +/* contributes to the random number pool */ +#define BLK_FEAT_ADD_RANDOM ((__force blk_features_t)(1u << 3)) + +/* do disk/partitions IO accounting */ +#define BLK_FEAT_IO_STAT ((__force blk_features_t)(1u << 4)) + +/* don't modify data until writeback is done */ +#define BLK_FEAT_STABLE_WRITES ((__force blk_features_t)(1u << 5)) + +/* always completes in submit context */ +#define BLK_FEAT_SYNCHRONOUS ((__force blk_features_t)(1u << 6)) + +/* supports REQ_NOWAIT */ +#define BLK_FEAT_NOWAIT ((__force blk_features_t)(1u << 7)) + +/* supports DAX */ +#define BLK_FEAT_DAX ((__force blk_features_t)(1u << 8)) + +/* supports I/O polling */ +#define BLK_FEAT_POLL ((__force blk_features_t)(1u << 9)) + +/* is a zoned device */ +#define BLK_FEAT_ZONED ((__force blk_features_t)(1u << 10)) + +/* supports PCI(e) p2p requests */ +#define BLK_FEAT_PCI_P2PDMA ((__force blk_features_t)(1u << 12)) + +/* skip this queue in blk_mq_(un)quiesce_tagset */ +#define BLK_FEAT_SKIP_TAGSET_QUIESCE ((__force blk_features_t)(1u << 13)) + +/* bounce all highmem pages */ +#define BLK_FEAT_BOUNCE_HIGH ((__force blk_features_t)(1u << 14)) + +/* undocumented magic for bcache */ +#define BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE \ + ((__force blk_features_t)(1u << 15)) + /* - * BLK_BOUNCE_NONE: never bounce (default) - * BLK_BOUNCE_HIGH: bounce all highmem pages + * Flags automatically inherited when stacking limits. */ -enum blk_bounce { - BLK_BOUNCE_NONE, - BLK_BOUNCE_HIGH, -}; +#define BLK_FEAT_INHERIT_MASK \ + (BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA | BLK_FEAT_ROTATIONAL | \ + BLK_FEAT_STABLE_WRITES | BLK_FEAT_ZONED | BLK_FEAT_BOUNCE_HIGH | \ + BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE) + +/* internal flags in queue_limits.flags */ +typedef unsigned int __bitwise blk_flags_t; + +/* do not send FLUSH/FUA commands despite advertising a write cache */ +#define BLK_FLAG_WRITE_CACHE_DISABLED ((__force blk_flags_t)(1u << 0)) + +/* I/O topology is misaligned */ +#define BLK_FLAG_MISALIGNED ((__force blk_flags_t)(1u << 1)) struct queue_limits { - enum blk_bounce bounce; + blk_features_t features; + blk_flags_t flags; unsigned long seg_boundary_mask; unsigned long virt_boundary_mask; @@ -302,14 +376,20 @@ struct queue_limits { unsigned int discard_alignment; unsigned int zone_write_granularity; + /* atomic write limits */ + unsigned int atomic_write_hw_max; + unsigned int atomic_write_max_sectors; + unsigned int atomic_write_hw_boundary; + unsigned int atomic_write_boundary_sectors; + unsigned int atomic_write_hw_unit_min; + unsigned int atomic_write_unit_min; + unsigned int atomic_write_hw_unit_max; + unsigned int atomic_write_unit_max; + unsigned short max_segments; unsigned short max_integrity_segments; unsigned short max_discard_segments; - unsigned char misaligned; - unsigned char discard_misaligned; - unsigned char raid_partial_stripes_expensive; - bool zoned; unsigned int max_open_zones; unsigned int max_active_zones; @@ -319,20 +399,20 @@ struct queue_limits { * due to possible offsets. */ unsigned int dma_alignment; + unsigned int dma_pad_mask; + + struct blk_integrity integrity; }; typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, void *data); -void disk_set_zoned(struct gendisk *disk); - #define BLK_ALL_ZONES ((unsigned int)-1) int blkdev_report_zones(struct block_device *bdev, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, sector_t sectors, sector_t nr_sectors); -int blk_revalidate_disk_zones(struct gendisk *disk, - void (*update_driver_data)(struct gendisk *disk)); +int blk_revalidate_disk_zones(struct gendisk *disk); /* * Independent access ranges: struct blk_independent_access_range describes @@ -407,10 +487,6 @@ struct request_queue { struct queue_limits limits; -#ifdef CONFIG_BLK_DEV_INTEGRITY - struct blk_integrity integrity; -#endif /* CONFIG_BLK_DEV_INTEGRITY */ - #ifdef CONFIG_PM struct device *dev; enum rpm_status rpm_status; @@ -432,8 +508,6 @@ struct request_queue { */ int id; - unsigned int dma_pad_mask; - /* * queue settings */ @@ -449,8 +523,6 @@ struct request_queue { atomic_t nr_active_requests_shared_tags; - unsigned int required_elevator_features; - struct blk_mq_tags *sched_shared_tags; struct list_head icq_list; @@ -516,60 +588,37 @@ struct request_queue { }; /* Keep blk_queue_flag_name[] in sync with the definitions below */ -#define QUEUE_FLAG_STOPPED 0 /* queue is stopped */ -#define QUEUE_FLAG_DYING 1 /* queue being torn down */ -#define QUEUE_FLAG_NOMERGES 3 /* disable merge attempts */ -#define QUEUE_FLAG_SAME_COMP 4 /* complete on same CPU-group */ -#define QUEUE_FLAG_FAIL_IO 5 /* fake timeout */ -#define QUEUE_FLAG_NONROT 6 /* non-rotational device (SSD) */ -#define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ -#define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */ -#define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */ -#define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ -#define QUEUE_FLAG_SYNCHRONOUS 11 /* always completes in submit context */ -#define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ -#define QUEUE_FLAG_HW_WC 13 /* Write back caching supported */ -#define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ -#define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */ -#define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */ -#define QUEUE_FLAG_WC 17 /* Write back caching */ -#define QUEUE_FLAG_FUA 18 /* device supports FUA writes */ -#define QUEUE_FLAG_DAX 19 /* device supports DAX */ -#define QUEUE_FLAG_STATS 20 /* track IO start and completion times */ -#define QUEUE_FLAG_REGISTERED 22 /* queue has been registered to a disk */ -#define QUEUE_FLAG_QUIESCED 24 /* queue has been quiesced */ -#define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ -#define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */ -#define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */ -#define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */ -#define QUEUE_FLAG_NOWAIT 29 /* device supports NOWAIT */ -#define QUEUE_FLAG_SQ_SCHED 30 /* single queue style io dispatch */ -#define QUEUE_FLAG_SKIP_TAGSET_QUIESCE 31 /* quiesce_tagset skip the queue*/ - -#define QUEUE_FLAG_MQ_DEFAULT ((1UL << QUEUE_FLAG_IO_STAT) | \ - (1UL << QUEUE_FLAG_SAME_COMP) | \ - (1UL << QUEUE_FLAG_NOWAIT)) +enum { + QUEUE_FLAG_DYING, /* queue being torn down */ + QUEUE_FLAG_NOMERGES, /* disable merge attempts */ + QUEUE_FLAG_SAME_COMP, /* complete on same CPU-group */ + QUEUE_FLAG_FAIL_IO, /* fake timeout */ + QUEUE_FLAG_NOXMERGES, /* No extended merges */ + QUEUE_FLAG_SAME_FORCE, /* force complete on same CPU */ + QUEUE_FLAG_INIT_DONE, /* queue is initialized */ + QUEUE_FLAG_STATS, /* track IO start and completion times */ + QUEUE_FLAG_REGISTERED, /* queue has been registered to a disk */ + QUEUE_FLAG_QUIESCED, /* queue has been quiesced */ + QUEUE_FLAG_RQ_ALLOC_TIME, /* record rq->alloc_time_ns */ + QUEUE_FLAG_HCTX_ACTIVE, /* at least one blk-mq hctx is active */ + QUEUE_FLAG_SQ_SCHED, /* single queue style io dispatch */ + QUEUE_FLAG_MAX +}; + +#define QUEUE_FLAG_MQ_DEFAULT (1UL << QUEUE_FLAG_SAME_COMP) void blk_queue_flag_set(unsigned int flag, struct request_queue *q); void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); -bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); -#define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) #define blk_queue_init_done(q) test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) #define blk_queue_noxmerges(q) \ test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags) -#define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) -#define blk_queue_stable_writes(q) \ - test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags) -#define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) -#define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) -#define blk_queue_zone_resetall(q) \ - test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags) -#define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) -#define blk_queue_pci_p2pdma(q) \ - test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) +#define blk_queue_nonrot(q) (!((q)->limits.features & BLK_FEAT_ROTATIONAL)) +#define blk_queue_io_stat(q) ((q)->limits.features & BLK_FEAT_IO_STAT) +#define blk_queue_dax(q) ((q)->limits.features & BLK_FEAT_DAX) +#define blk_queue_pci_p2pdma(q) ((q)->limits.features & BLK_FEAT_PCI_P2PDMA) #ifdef CONFIG_BLK_RQ_ALLOC_TIME #define blk_queue_rq_alloc_time(q) \ test_bit(QUEUE_FLAG_RQ_ALLOC_TIME, &(q)->queue_flags) @@ -585,7 +634,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) #define blk_queue_sq_sched(q) test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags) #define blk_queue_skip_tagset_quiesce(q) \ - test_bit(QUEUE_FLAG_SKIP_TAGSET_QUIESCE, &(q)->queue_flags) + ((q)->limits.features & BLK_FEAT_SKIP_TAGSET_QUIESCE) extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); @@ -615,43 +664,37 @@ static inline enum rpm_status queue_rpm_status(struct request_queue *q) static inline bool blk_queue_is_zoned(struct request_queue *q) { - return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && q->limits.zoned; + return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && + (q->limits.features & BLK_FEAT_ZONED); } #ifdef CONFIG_BLK_DEV_ZONED -unsigned int bdev_nr_zones(struct block_device *bdev); - static inline unsigned int disk_nr_zones(struct gendisk *disk) { - return blk_queue_is_zoned(disk->queue) ? disk->nr_zones : 0; + return disk->nr_zones; } - -static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) +bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs); +#else /* CONFIG_BLK_DEV_ZONED */ +static inline unsigned int disk_nr_zones(struct gendisk *disk) { - if (!blk_queue_is_zoned(disk->queue)) - return 0; - return sector >> ilog2(disk->queue->limits.chunk_sectors); + return 0; } - -static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector) +static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs) { - if (!blk_queue_is_zoned(disk->queue)) - return false; - if (!disk->conv_zones_bitmap) - return true; - return !test_bit(disk_zone_no(disk, sector), disk->conv_zones_bitmap); + return false; } +#endif /* CONFIG_BLK_DEV_ZONED */ -static inline void disk_set_max_open_zones(struct gendisk *disk, - unsigned int max_open_zones) +static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) { - disk->queue->limits.max_open_zones = max_open_zones; + if (!blk_queue_is_zoned(disk->queue)) + return 0; + return sector >> ilog2(disk->queue->limits.chunk_sectors); } -static inline void disk_set_max_active_zones(struct gendisk *disk, - unsigned int max_active_zones) +static inline unsigned int bdev_nr_zones(struct block_device *bdev) { - disk->queue->limits.max_active_zones = max_active_zones; + return disk_nr_zones(bdev->bd_disk); } static inline unsigned int bdev_max_open_zones(struct block_device *bdev) @@ -664,35 +707,6 @@ static inline unsigned int bdev_max_active_zones(struct block_device *bdev) return bdev->bd_disk->queue->limits.max_active_zones; } -#else /* CONFIG_BLK_DEV_ZONED */ -static inline unsigned int bdev_nr_zones(struct block_device *bdev) -{ - return 0; -} - -static inline unsigned int disk_nr_zones(struct gendisk *disk) -{ - return 0; -} -static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector) -{ - return false; -} -static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) -{ - return 0; -} -static inline unsigned int bdev_max_open_zones(struct block_device *bdev) -{ - return 0; -} - -static inline unsigned int bdev_max_active_zones(struct block_device *bdev) -{ - return 0; -} -#endif /* CONFIG_BLK_DEV_ZONED */ - static inline unsigned int blk_queue_depth(struct request_queue *q) { if (q->queue_depth) @@ -722,15 +736,35 @@ void invalidate_disk(struct gendisk *disk); void set_disk_ro(struct gendisk *disk, bool read_only); void disk_uevent(struct gendisk *disk, enum kobject_action action); +static inline u8 bdev_partno(const struct block_device *bdev) +{ + return atomic_read(&bdev->__bd_flags) & BD_PARTNO; +} + +static inline bool bdev_test_flag(const struct block_device *bdev, unsigned flag) +{ + return atomic_read(&bdev->__bd_flags) & flag; +} + +static inline void bdev_set_flag(struct block_device *bdev, unsigned flag) +{ + atomic_or(flag, &bdev->__bd_flags); +} + +static inline void bdev_clear_flag(struct block_device *bdev, unsigned flag) +{ + atomic_andnot(flag, &bdev->__bd_flags); +} + static inline int get_disk_ro(struct gendisk *disk) { - return disk->part0->bd_read_only || + return bdev_test_flag(disk->part0, BD_READ_ONLY) || test_bit(GD_READ_ONLY, &disk->state); } static inline int bdev_read_only(struct block_device *bdev) { - return bdev->bd_read_only || get_disk_ro(bdev->bd_disk); + return bdev_test_flag(bdev, BD_READ_ONLY) || get_disk_ro(bdev->bd_disk); } bool set_capacity_and_notify(struct gendisk *disk, sector_t size); @@ -855,20 +889,23 @@ static inline unsigned int bio_zone_no(struct bio *bio) return disk_zone_no(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector); } -static inline unsigned int bio_zone_is_seq(struct bio *bio) +static inline bool bio_straddles_zones(struct bio *bio) { - return disk_zone_is_seq(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector); + return bio_sectors(bio) && + bio_zone_no(bio) != + disk_zone_no(bio->bi_bdev->bd_disk, bio_end_sector(bio) - 1); } /* - * Return how much of the chunk is left to be used for I/O at a given offset. + * Return how much within the boundary is left to be used for I/O at a given + * offset. */ -static inline unsigned int blk_chunk_sectors_left(sector_t offset, - unsigned int chunk_sectors) +static inline unsigned int blk_boundary_sectors_left(sector_t offset, + unsigned int boundary_sectors) { - if (unlikely(!is_power_of_2(chunk_sectors))) - return chunk_sectors - sector_div(offset, chunk_sectors); - return chunk_sectors - (offset & (chunk_sectors - 1)); + if (unlikely(!is_power_of_2(boundary_sectors))) + return boundary_sectors - sector_div(offset, boundary_sectors); + return boundary_sectors - (offset & (boundary_sectors - 1)); } /** @@ -885,7 +922,6 @@ static inline unsigned int blk_chunk_sectors_left(sector_t offset, */ static inline struct queue_limits queue_limits_start_update(struct request_queue *q) - __acquires(q->limits_lock) { mutex_lock(&q->limits_lock); return q->limits; @@ -894,65 +930,59 @@ int queue_limits_commit_update(struct request_queue *q, struct queue_limits *lim); int queue_limits_set(struct request_queue *q, struct queue_limits *lim); +/** + * queue_limits_cancel_update - cancel an atomic update of queue limits + * @q: queue to update + * + * This functions cancels an atomic update of the queue limits started by + * queue_limits_start_update() and should be used when an error occurs after + * starting update. + */ +static inline void queue_limits_cancel_update(struct request_queue *q) +{ + mutex_unlock(&q->limits_lock); +} + +/* + * These helpers are for drivers that have sloppy feature negotiation and might + * have to disable DISCARD, WRITE_ZEROES or SECURE_DISCARD from the I/O + * completion handler when the device returned an indicator that the respective + * feature is not actually supported. They are racy and the driver needs to + * cope with that. Try to avoid this scheme if you can. + */ +static inline void blk_queue_disable_discard(struct request_queue *q) +{ + q->limits.max_discard_sectors = 0; +} + +static inline void blk_queue_disable_secure_erase(struct request_queue *q) +{ + q->limits.max_secure_erase_sectors = 0; +} + +static inline void blk_queue_disable_write_zeroes(struct request_queue *q) +{ + q->limits.max_write_zeroes_sectors = 0; +} + /* * Access functions for manipulating queue properties */ -void blk_queue_bounce_limit(struct request_queue *q, enum blk_bounce limit); -extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); -extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); -extern void blk_queue_max_segments(struct request_queue *, unsigned short); -extern void blk_queue_max_discard_segments(struct request_queue *, - unsigned short); -void blk_queue_max_secure_erase_sectors(struct request_queue *q, - unsigned int max_sectors); -extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); -extern void blk_queue_max_discard_sectors(struct request_queue *q, - unsigned int max_discard_sectors); -extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q, - unsigned int max_write_same_sectors); -extern void blk_queue_logical_block_size(struct request_queue *, unsigned int); -extern void blk_queue_max_zone_append_sectors(struct request_queue *q, - unsigned int max_zone_append_sectors); -extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); -void blk_queue_zone_write_granularity(struct request_queue *q, - unsigned int size); -extern void blk_queue_alignment_offset(struct request_queue *q, - unsigned int alignment); -void disk_update_readahead(struct gendisk *disk); extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); -extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt); -extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt); extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth); extern void blk_set_stacking_limits(struct queue_limits *lim); extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t offset); void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev, sector_t offset, const char *pfx); -extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int); -extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); -extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); -extern void blk_queue_dma_alignment(struct request_queue *, int); -extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); -extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); struct blk_independent_access_ranges * disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges); void disk_set_independent_access_ranges(struct gendisk *disk, struct blk_independent_access_ranges *iars); -/* - * Elevator features for blk_queue_required_elevator_features: - */ -/* Supports zoned block devices sequential write constraint */ -#define ELEVATOR_F_ZBD_SEQ_WRITE (1U << 0) - -extern void blk_queue_required_elevator_features(struct request_queue *q, - unsigned int features); -extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q, - struct device *dev); - bool __must_check blk_get_queue(struct request_queue *); extern void blk_put_queue(struct request_queue *); @@ -1067,6 +1097,7 @@ int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector, #define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */ #define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */ +#define BLKDEV_ZERO_KILLABLE (1 << 2) /* interruptible by fatal signals */ extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop, @@ -1097,7 +1128,7 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, static inline bool bdev_is_partition(struct block_device *bdev) { - return bdev->bd_partno; + return bdev_partno(bdev) != 0; } enum blk_default_limits { @@ -1156,12 +1187,29 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q) return q->limits.max_segment_size; } -static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q) +static inline unsigned int queue_limits_max_zone_append_sectors(struct queue_limits *l) { + unsigned int max_sectors = min(l->chunk_sectors, l->max_hw_sectors); - const struct queue_limits *l = &q->limits; + return min_not_zero(l->max_zone_append_sectors, max_sectors); +} - return min(l->max_zone_append_sectors, l->max_sectors); +static inline unsigned int queue_max_zone_append_sectors(struct request_queue *q) +{ + if (!blk_queue_is_zoned(q)) + return 0; + + return queue_limits_max_zone_append_sectors(&q->limits); +} + +static inline bool queue_emulates_zone_append(struct request_queue *q) +{ + return blk_queue_is_zoned(q) && !q->limits.max_zone_append_sectors; +} + +static inline bool bdev_emulates_zone_append(struct block_device *bdev) +{ + return queue_emulates_zone_append(bdev_get_queue(bdev)); } static inline unsigned int @@ -1177,12 +1225,7 @@ static inline unsigned int bdev_max_segments(struct block_device *bdev) static inline unsigned queue_logical_block_size(const struct request_queue *q) { - int retval = 512; - - if (q && q->limits.logical_block_size) - retval = q->limits.logical_block_size; - - return retval; + return q->limits.logical_block_size; } static inline unsigned int bdev_logical_block_size(struct block_device *bdev) @@ -1268,29 +1311,38 @@ static inline bool bdev_nonrot(struct block_device *bdev) static inline bool bdev_synchronous(struct block_device *bdev) { - return test_bit(QUEUE_FLAG_SYNCHRONOUS, - &bdev_get_queue(bdev)->queue_flags); + return bdev->bd_disk->queue->limits.features & BLK_FEAT_SYNCHRONOUS; } static inline bool bdev_stable_writes(struct block_device *bdev) { - return test_bit(QUEUE_FLAG_STABLE_WRITES, - &bdev_get_queue(bdev)->queue_flags); + struct request_queue *q = bdev_get_queue(bdev); + + if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) && + q->limits.integrity.csum_type != BLK_INTEGRITY_CSUM_NONE) + return true; + return q->limits.features & BLK_FEAT_STABLE_WRITES; +} + +static inline bool blk_queue_write_cache(struct request_queue *q) +{ + return (q->limits.features & BLK_FEAT_WRITE_CACHE) && + !(q->limits.flags & BLK_FLAG_WRITE_CACHE_DISABLED); } static inline bool bdev_write_cache(struct block_device *bdev) { - return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags); + return blk_queue_write_cache(bdev_get_queue(bdev)); } static inline bool bdev_fua(struct block_device *bdev) { - return test_bit(QUEUE_FLAG_FUA, &bdev_get_queue(bdev)->queue_flags); + return bdev_get_queue(bdev)->limits.features & BLK_FEAT_FUA; } static inline bool bdev_nowait(struct block_device *bdev) { - return test_bit(QUEUE_FLAG_NOWAIT, &bdev_get_queue(bdev)->queue_flags); + return bdev->bd_disk->queue->limits.features & BLK_FEAT_NOWAIT; } static inline bool bdev_is_zoned(struct block_device *bdev) @@ -1303,18 +1355,6 @@ static inline unsigned int bdev_zone_no(struct block_device *bdev, sector_t sec) return disk_zone_no(bdev->bd_disk, sec); } -/* Whether write serialization is required for @op on zoned devices. */ -static inline bool op_needs_zoned_write_locking(enum req_op op) -{ - return op == REQ_OP_WRITE || op == REQ_OP_WRITE_ZEROES; -} - -static inline bool bdev_op_is_zoned_write(struct block_device *bdev, - enum req_op op) -{ - return bdev_is_zoned(bdev) && op_needs_zoned_write_locking(op); -} - static inline sector_t bdev_zone_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); @@ -1330,6 +1370,12 @@ static inline sector_t bdev_offset_from_zone_start(struct block_device *bdev, return sector & (bdev_zone_sectors(bdev) - 1); } +static inline sector_t bio_offset_from_zone_start(struct bio *bio) +{ + return bdev_offset_from_zone_start(bio->bi_bdev, + bio->bi_iter.bi_sector); +} + static inline bool bdev_is_zone_start(struct block_device *bdev, sector_t sector) { @@ -1338,7 +1384,31 @@ static inline bool bdev_is_zone_start(struct block_device *bdev, static inline int queue_dma_alignment(const struct request_queue *q) { - return q ? q->limits.dma_alignment : 511; + return q->limits.dma_alignment; +} + +static inline unsigned int +queue_atomic_write_unit_max_bytes(const struct request_queue *q) +{ + return q->limits.atomic_write_unit_max; +} + +static inline unsigned int +queue_atomic_write_unit_min_bytes(const struct request_queue *q) +{ + return q->limits.atomic_write_unit_min; +} + +static inline unsigned int +queue_atomic_write_boundary_bytes(const struct request_queue *q) +{ + return q->limits.atomic_write_boundary_sectors << SECTOR_SHIFT; +} + +static inline unsigned int +queue_atomic_write_max_bytes(const struct request_queue *q) +{ + return q->limits.atomic_write_max_sectors << SECTOR_SHIFT; } static inline unsigned int bdev_dma_alignment(struct block_device *bdev) @@ -1353,10 +1423,16 @@ static inline bool bdev_iter_is_aligned(struct block_device *bdev, bdev_logical_block_size(bdev) - 1); } +static inline int blk_lim_dma_alignment_and_pad(struct queue_limits *lim) +{ + return lim->dma_alignment | lim->dma_pad_mask; +} + static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr, unsigned int len) { - unsigned int alignment = queue_dma_alignment(q) | q->dma_pad_mask; + unsigned int alignment = blk_lim_dma_alignment_and_pad(&q->limits); + return !(addr & alignment) && !(len & alignment); } @@ -1366,11 +1442,6 @@ static inline unsigned int blksize_bits(unsigned int size) return order_base_2(size >> SECTOR_SHIFT) + SECTOR_SHIFT; } -static inline unsigned int block_size(struct block_device *bdev) -{ - return 1 << bdev->bd_inode->i_blkbits; -} - int kblockd_schedule_work(struct work_struct *work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); @@ -1476,7 +1547,7 @@ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) } int bdev_read_only(struct block_device *bdev); -int set_blocksize(struct block_device *bdev, int size); +int set_blocksize(struct file *file, int size); int lookup_bdev(const char *pathname, dev_t *dev); @@ -1538,6 +1609,8 @@ void blkdev_put_no_open(struct block_device *bdev); struct block_device *I_BDEV(struct inode *inode); struct block_device *file_bdev(struct file *bdev_file); +bool disk_live(struct gendisk *disk); +unsigned int block_size(struct block_device *bdev); #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); @@ -1545,7 +1618,7 @@ int sync_blockdev(struct block_device *bdev); int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend); int sync_blockdev_nowait(struct block_device *bdev); void sync_bdevs(bool wait); -void bdev_statx_dioalign(struct inode *inode, struct kstat *stat); +void bdev_statx(struct path *, struct kstat *, u32); void printk_all_partitions(void); int __init early_lookup_bdev(const char *pathname, dev_t *dev); #else @@ -1563,7 +1636,8 @@ static inline int sync_blockdev_nowait(struct block_device *bdev) static inline void sync_bdevs(bool wait) { } -static inline void bdev_statx_dioalign(struct inode *inode, struct kstat *stat) +static inline void bdev_statx(struct path *path, struct kstat *stat, + u32 request_mask) { } static inline void printk_all_partitions(void) @@ -1585,6 +1659,27 @@ struct io_comp_batch { void (*complete)(struct io_comp_batch *); }; +static inline bool bdev_can_atomic_write(struct block_device *bdev) +{ + struct request_queue *bd_queue = bdev->bd_queue; + struct queue_limits *limits = &bd_queue->limits; + + if (!limits->atomic_write_unit_min) + return false; + + if (bdev_is_partition(bdev)) { + sector_t bd_start_sect = bdev->bd_start_sect; + unsigned int alignment = + max(limits->atomic_write_unit_min, + limits->atomic_write_hw_boundary); + + if (!IS_ALIGNED(bd_start_sect, alignment >> SECTOR_SHIFT)) + return false; + } + + return true; +} + #define DEFINE_IO_COMP_BATCH(name) struct io_comp_batch name = { } #endif /* _LINUX_BLKDEV_H */ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 890e152d553e..3b94ec161e8c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -184,8 +184,8 @@ struct bpf_map_ops { }; enum { - /* Support at most 10 fields in a BTF type */ - BTF_FIELDS_MAX = 10, + /* Support at most 11 fields in a BTF type */ + BTF_FIELDS_MAX = 11, }; enum btf_field_type { @@ -202,6 +202,7 @@ enum btf_field_type { BPF_GRAPH_NODE = BPF_RB_NODE | BPF_LIST_NODE, BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD, BPF_REFCOUNT = (1 << 9), + BPF_WORKQUEUE = (1 << 10), }; typedef void (*btf_dtor_kfunc_t)(void *); @@ -238,6 +239,7 @@ struct btf_record { u32 field_mask; int spin_lock_off; int timer_off; + int wq_off; int refcount_off; struct btf_field fields[]; }; @@ -273,7 +275,7 @@ struct bpf_map { u32 btf_value_type_id; u32 btf_vmlinux_value_type_id; struct btf *btf; -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG struct obj_cgroup *objcg; #endif char name[BPF_OBJ_NAME_LEN]; @@ -312,6 +314,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type) return "bpf_spin_lock"; case BPF_TIMER: return "bpf_timer"; + case BPF_WORKQUEUE: + return "bpf_wq"; case BPF_KPTR_UNREF: case BPF_KPTR_REF: return "kptr"; @@ -340,6 +344,8 @@ static inline u32 btf_field_type_size(enum btf_field_type type) return sizeof(struct bpf_spin_lock); case BPF_TIMER: return sizeof(struct bpf_timer); + case BPF_WORKQUEUE: + return sizeof(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: @@ -367,6 +373,8 @@ static inline u32 btf_field_type_align(enum btf_field_type type) return __alignof__(struct bpf_spin_lock); case BPF_TIMER: return __alignof__(struct bpf_timer); + case BPF_WORKQUEUE: + return __alignof__(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: @@ -406,6 +414,7 @@ static inline void bpf_obj_init_field(const struct btf_field *field, void *addr) /* RB_ROOT_CACHED 0-inits, no need to do anything after memset */ case BPF_SPIN_LOCK: case BPF_TIMER: + case BPF_WORKQUEUE: case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: @@ -525,6 +534,7 @@ static inline void zero_map_value(struct bpf_map *map, void *dst) void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); void bpf_timer_cancel_and_free(void *timer); +void bpf_wq_cancel_and_free(void *timer); void bpf_list_head_free(const struct btf_field *field, void *list_head, struct bpf_spin_lock *spin_lock); void bpf_rb_root_free(const struct btf_field *field, void *rb_root, @@ -1116,8 +1126,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i void *func_addr); void *arch_alloc_bpf_trampoline(unsigned int size); void arch_free_bpf_trampoline(void *image, unsigned int size); -void arch_protect_bpf_trampoline(void *image, unsigned int size); -void arch_unprotect_bpf_trampoline(void *image, unsigned int size); +int __must_check arch_protect_bpf_trampoline(void *image, unsigned int size); int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr); @@ -1266,6 +1275,7 @@ int bpf_dynptr_check_size(u32 size); u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr); const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u32 len); void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len); +bool __bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr); #ifdef CONFIG_BPF_JIT int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); @@ -1602,6 +1612,7 @@ struct bpf_link_ops { struct bpf_link_info *info); int (*update_map)(struct bpf_link *link, struct bpf_map *new_map, struct bpf_map *old_map); + __poll_t (*poll)(struct file *file, struct poll_table_struct *pts); }; struct bpf_tramp_link { @@ -1622,6 +1633,12 @@ struct bpf_tracing_link { struct bpf_prog *tgt_prog; }; +struct bpf_raw_tp_link { + struct bpf_link link; + struct bpf_raw_event_map *btp; + u64 cookie; +}; + struct bpf_link_primer { struct bpf_link *link; struct file *file; @@ -1714,9 +1731,9 @@ struct bpf_struct_ops { int (*init_member)(const struct btf_type *t, const struct btf_member *member, void *kdata, const void *udata); - int (*reg)(void *kdata); - void (*unreg)(void *kdata); - int (*update)(void *kdata, void *old_kdata); + int (*reg)(void *kdata, struct bpf_link *link); + void (*unreg)(void *kdata, struct bpf_link *link); + int (*update)(void *kdata, void *old_kdata, struct bpf_link *link); int (*validate)(void *kdata); void *cfi_stubs; struct module *owner; @@ -2204,6 +2221,7 @@ void bpf_map_free_record(struct bpf_map *map); struct btf_record *btf_record_dup(const struct btf_record *rec); bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b); void bpf_obj_free_timer(const struct btf_record *rec, void *obj); +void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj); void bpf_obj_free_fields(const struct btf_record *rec, void *obj); void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu); @@ -2235,7 +2253,7 @@ struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id); int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid, unsigned long nr_pages, struct page **page_array); -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node); void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags); @@ -2244,31 +2262,18 @@ void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags); #else -static inline void * -bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, - int node) -{ - return kmalloc_node(size, flags, node); -} - -static inline void * -bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) -{ - return kzalloc(size, flags); -} - -static inline void * -bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, gfp_t flags) -{ - return kvcalloc(n, size, flags); -} - -static inline void __percpu * -bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, - gfp_t flags) -{ - return __alloc_percpu_gfp(size, align, flags); -} +/* + * These specialized allocators have to be macros for their allocations to be + * accounted separately (to have separate alloc_tag). + */ +#define bpf_map_kmalloc_node(_map, _size, _flags, _node) \ + kmalloc_node(_size, _flags, _node) +#define bpf_map_kzalloc(_map, _size, _flags) \ + kzalloc(_size, _flags) +#define bpf_map_kvcalloc(_map, _n, _size, _flags) \ + kvcalloc(_n, _size, _flags) +#define bpf_map_alloc_percpu(_map, _size, _align, _flags) \ + __alloc_percpu_gfp(_size, _align, _flags) #endif static inline int @@ -2333,6 +2338,7 @@ int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer); int bpf_link_settle(struct bpf_link_primer *primer); void bpf_link_cleanup(struct bpf_link_primer *primer); void bpf_link_inc(struct bpf_link *link); +struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link); void bpf_link_put(struct bpf_link *link); int bpf_link_new_fd(struct bpf_link *link); struct bpf_link *bpf_link_get_from_fd(u32 ufd); @@ -2492,7 +2498,7 @@ struct sk_buff; struct bpf_dtab_netdev; struct bpf_cpu_map_entry; -void __dev_flush(void); +void __dev_flush(struct list_head *flush_list); int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, @@ -2505,7 +2511,7 @@ int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress); -void __cpu_map_flush(void); +void __cpu_map_flush(struct list_head *flush_list); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, struct net_device *dev_rx); int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, @@ -2642,8 +2648,6 @@ void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr); void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr); -bool dev_check_flush(void); -bool cpu_map_check_flush(void); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -2704,6 +2708,11 @@ static inline void bpf_link_inc(struct bpf_link *link) { } +static inline struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link) +{ + return NULL; +} + static inline void bpf_link_put(struct bpf_link *link) { } @@ -2731,7 +2740,7 @@ static inline struct bpf_token *bpf_token_get_from_fd(u32 ufd) return ERR_PTR(-EOPNOTSUPP); } -static inline void __dev_flush(void) +static inline void __dev_flush(struct list_head *flush_list) { } @@ -2777,7 +2786,7 @@ int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, return 0; } -static inline void __cpu_map_flush(void) +static inline void __cpu_map_flush(struct list_head *flush_list) { } @@ -2926,8 +2935,7 @@ bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr) return ret; } -void __bpf_free_used_btfs(struct bpf_prog_aux *aux, - struct btf_mod_pair *used_btfs, u32 len); +void __bpf_free_used_btfs(struct btf_mod_pair *used_btfs, u32 len); static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) @@ -3005,6 +3013,7 @@ int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); +int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog); void sock_map_unhash(struct sock *sk); void sock_map_destroy(struct sock *sk); @@ -3103,6 +3112,11 @@ static inline int sock_map_bpf_prog_query(const union bpf_attr *attr, { return -EINVAL; } + +static inline int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ @@ -3252,8 +3266,8 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); -int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags, - struct bpf_dynptr_kern *ptr); +int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags, + struct bpf_dynptr *ptr); #else static inline bool bpf_sock_common_is_valid_access(int off, int size, enum bpf_access_type type, @@ -3275,8 +3289,8 @@ static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, { return 0; } -static inline int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags, - struct bpf_dynptr_kern *ptr) +static inline int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags, + struct bpf_dynptr *ptr) { return -EOPNOTSUPP; } diff --git a/include/linux/bpf_crypto.h b/include/linux/bpf_crypto.h new file mode 100644 index 000000000000..a41e71d4e2d9 --- /dev/null +++ b/include/linux/bpf_crypto.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#ifndef _BPF_CRYPTO_H +#define _BPF_CRYPTO_H + +struct bpf_crypto_type { + void *(*alloc_tfm)(const char *algo); + void (*free_tfm)(void *tfm); + int (*has_algo)(const char *algo); + int (*setkey)(void *tfm, const u8 *key, unsigned int keylen); + int (*setauthsize)(void *tfm, unsigned int authsize); + int (*encrypt)(void *tfm, const u8 *src, u8 *dst, unsigned int len, u8 *iv); + int (*decrypt)(void *tfm, const u8 *src, u8 *dst, unsigned int len, u8 *iv); + unsigned int (*ivsize)(void *tfm); + unsigned int (*statesize)(void *tfm); + u32 (*get_flags)(void *tfm); + struct module *owner; + char name[14]; +}; + +int bpf_crypto_register_type(const struct bpf_crypto_type *type); +int bpf_crypto_unregister_type(const struct bpf_crypto_type *type); + +#endif /* _BPF_CRYPTO_H */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7cb1b75eee38..7b776dae36e5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -73,7 +73,10 @@ enum bpf_iter_state { struct bpf_reg_state { /* Ordering of fields matters. See states_equal() */ enum bpf_reg_type type; - /* Fixed part of pointer offset, pointer types only */ + /* + * Fixed part of pointer offset, pointer types only. + * Or constant delta between "linked" scalars with the same ID. + */ s32 off; union { /* valid when type == PTR_TO_PACKET */ @@ -167,6 +170,13 @@ struct bpf_reg_state { * Similarly to dynptrs, we use ID to track "belonging" of a reference * to a specific instance of bpf_iter. */ + /* + * Upper bit of ID is used to remember relationship between "linked" + * registers. Example: + * r1 = r2; both will have r1->id == r2->id == N + * r1 += 10; r1->id == N | BPF_ADD_CONST and r1->off == 10 + */ +#define BPF_ADD_CONST (1U << 31) u32 id; /* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned * from a pointer-cast helper, bpf_sk_fullsock() and @@ -421,11 +431,13 @@ struct bpf_verifier_state { struct bpf_active_lock active_lock; bool speculative; bool active_rcu_lock; + u32 active_preempt_lock; /* If this state was ever pointed-to by other state's loop_entry field * this flag would be set to true. Used to avoid freeing such states * while they are still in use. */ bool used_as_loop_entry; + bool in_sleepable; /* first and last insn idx of this verifier state */ u32 first_insn_idx; @@ -502,6 +514,13 @@ struct bpf_loop_inline_state { u32 callback_subprogno; /* valid when fit_for_inline is true */ }; +/* pointer and state for maps */ +struct bpf_map_ptr_state { + struct bpf_map *map_ptr; + bool poison; + bool unpriv; +}; + /* Possible states for alu_state member. */ #define BPF_ALU_SANITIZE_SRC (1U << 0) #define BPF_ALU_SANITIZE_DST (1U << 1) @@ -514,7 +533,7 @@ struct bpf_loop_inline_state { struct bpf_insn_aux_data { union { enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ - unsigned long map_ptr_state; /* pointer/poison value for maps */ + struct bpf_map_ptr_state map_ptr_state; s32 call_imm; /* saved imm field of call insn */ u32 alu_limit; /* limit for add/sub register with pointer */ struct { @@ -737,6 +756,8 @@ struct bpf_verifier_env { /* Same as scratched_regs but for stack slots */ u64 scratched_stack_slots; u64 prev_log_pos, prev_insn_print_pos; + /* buffer used to temporary hold constants as scalar registers */ + struct bpf_reg_state fake_reg[2]; /* buffer used to generate temporary string representations, * e.g., in reg_type_str() to generate reg_type string */ @@ -835,8 +856,8 @@ static inline u32 type_flag(u32 type) /* only use after check_attach_btf_id() */ static inline enum bpf_prog_type resolve_prog_type(const struct bpf_prog *prog) { - return prog->type == BPF_PROG_TYPE_EXT ? - prog->aux->dst_prog->type : prog->type; + return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->saved_dst_prog_type) ? + prog->aux->saved_dst_prog_type : prog->type; } static inline bool bpf_prog_check_recur(const struct bpf_prog *prog) diff --git a/include/linux/bpfptr.h b/include/linux/bpfptr.h index 79b2f78eec1a..1af241525a17 100644 --- a/include/linux/bpfptr.h +++ b/include/linux/bpfptr.h @@ -65,9 +65,9 @@ static inline int copy_to_bpfptr_offset(bpfptr_t dst, size_t offset, return copy_to_sockptr_offset((sockptr_t) dst, offset, src, size); } -static inline void *kvmemdup_bpfptr(bpfptr_t src, size_t len) +static inline void *kvmemdup_bpfptr_noprof(bpfptr_t src, size_t len) { - void *p = kvmalloc(len, GFP_USER | __GFP_NOWARN); + void *p = kvmalloc_noprof(len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); @@ -77,6 +77,7 @@ static inline void *kvmemdup_bpfptr(bpfptr_t src, size_t len) } return p; } +#define kvmemdup_bpfptr(...) alloc_hooks(kvmemdup_bpfptr_noprof(__VA_ARGS__)) static inline long strncpy_from_bpfptr(char *dst, bpfptr_t src, size_t count) { diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 1394ba302367..028b3e00378e 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -271,12 +271,100 @@ #define BCM5482_SSD_SGMII_SLAVE_EN 0x0002 /* Slave mode enable */ #define BCM5482_SSD_SGMII_SLAVE_AD 0x0001 /* Slave auto-detection */ +/* BroadR-Reach LRE Registers. */ +#define MII_BCM54XX_LRECR 0x00 /* LRE Control Register */ +#define MII_BCM54XX_LRESR 0x01 /* LRE Status Register */ +#define MII_BCM54XX_LREPHYSID1 0x02 /* LRE PHYS ID 1 */ +#define MII_BCM54XX_LREPHYSID2 0x03 /* LRE PHYS ID 2 */ +#define MII_BCM54XX_LREANAA 0x04 /* LDS Auto-Negotiation Advertised Ability */ +#define MII_BCM54XX_LREANAC 0x05 /* LDS Auto-Negotiation Advertised Control */ +#define MII_BCM54XX_LREANPT 0x06 /* LDS Ability Next Page Transmit */ +#define MII_BCM54XX_LRELPA 0x07 /* LDS Link Partner Ability */ +#define MII_BCM54XX_LRELPNPM 0x08 /* LDS Link Partner Next Page Message */ +#define MII_BCM54XX_LRELPNPC 0x09 /* LDS Link Partner Next Page Control */ +#define MII_BCM54XX_LRELDSE 0x0a /* LDS Expansion Register */ +#define MII_BCM54XX_LREES 0x0f /* LRE Extended Status */ + +/* LRE control register. */ +#define LRECR_RESET 0x8000 /* Reset to default state */ +#define LRECR_LOOPBACK 0x4000 /* Internal Loopback */ +#define LRECR_LDSRES 0x2000 /* Restart LDS Process */ +#define LRECR_LDSEN 0x1000 /* LDS Enable */ +#define LRECR_PDOWN 0x0800 /* Enable low power state */ +#define LRECR_ISOLATE 0x0400 /* Isolate data paths from MII */ +#define LRECR_SPEED100 0x0200 /* Select 100 Mbps */ +#define LRECR_SPEED10 0x0000 /* Select 10 Mbps */ +#define LRECR_4PAIRS 0x0020 /* Select 4 Pairs */ +#define LRECR_2PAIRS 0x0010 /* Select 2 Pairs */ +#define LRECR_1PAIR 0x0000 /* Select 1 Pair */ +#define LRECR_MASTER 0x0008 /* Force Master when LDS disabled */ +#define LRECR_SLAVE 0x0000 /* Force Slave when LDS disabled */ + +/* LRE status register. */ +#define LRESR_100_1PAIR 0x2000 /* Can do 100Mbps 1 Pair */ +#define LRESR_100_4PAIR 0x1000 /* Can do 100Mbps 4 Pairs */ +#define LRESR_100_2PAIR 0x0800 /* Can do 100Mbps 2 Pairs */ +#define LRESR_10_2PAIR 0x0400 /* Can do 10Mbps 2 Pairs */ +#define LRESR_10_1PAIR 0x0200 /* Can do 10Mbps 1 Pair */ +#define LRESR_ESTATEN 0x0100 /* Extended Status in R15 */ +#define LRESR_RESV 0x0080 /* Unused... */ +#define LRESR_MFPS 0x0040 /* Can suppress Management Frames Preamble */ +#define LRESR_LDSCOMPLETE 0x0020 /* LDS Auto-negotiation complete */ +#define LRESR_8023 0x0010 /* Has IEEE 802.3 Support */ +#define LRESR_LDSABILITY 0x0008 /* LDS auto-negotiation capable */ +#define LRESR_LSTATUS 0x0004 /* Link status */ +#define LRESR_JCD 0x0002 /* Jabber detected */ +#define LRESR_ERCAP 0x0001 /* Ext-reg capability */ + +/* LDS Auto-Negotiation Advertised Ability. */ +#define LREANAA_PAUSE_ASYM 0x8000 /* Can pause asymmetrically */ +#define LREANAA_PAUSE 0x4000 /* Can pause */ +#define LREANAA_100_1PAIR 0x0020 /* Can do 100Mbps 1 Pair */ +#define LREANAA_100_4PAIR 0x0010 /* Can do 100Mbps 4 Pair */ +#define LREANAA_100_2PAIR 0x0008 /* Can do 100Mbps 2 Pair */ +#define LREANAA_10_2PAIR 0x0004 /* Can do 10Mbps 2 Pair */ +#define LREANAA_10_1PAIR 0x0002 /* Can do 10Mbps 1 Pair */ + +#define LRE_ADVERTISE_FULL (LREANAA_100_1PAIR | LREANAA_100_4PAIR | \ + LREANAA_100_2PAIR | LREANAA_10_2PAIR | \ + LREANAA_10_1PAIR) + +#define LRE_ADVERTISE_ALL LRE_ADVERTISE_FULL + +/* LDS Link Partner Ability. */ +#define LRELPA_PAUSE_ASYM 0x8000 /* Supports asymmetric pause */ +#define LRELPA_PAUSE 0x4000 /* Supports pause capability */ +#define LRELPA_100_1PAIR 0x0020 /* 100Mbps 1 Pair capable */ +#define LRELPA_100_4PAIR 0x0010 /* 100Mbps 4 Pair capable */ +#define LRELPA_100_2PAIR 0x0008 /* 100Mbps 2 Pair capable */ +#define LRELPA_10_2PAIR 0x0004 /* 10Mbps 2 Pair capable */ +#define LRELPA_10_1PAIR 0x0002 /* 10Mbps 1 Pair capable */ + +/* LDS Expansion register. */ +#define LDSE_DOWNGRADE 0x8000 /* Can do LDS Speed Downgrade */ +#define LDSE_MASTER 0x4000 /* Master / Slave */ +#define LDSE_PAIRS_MASK 0x3000 /* Pair Count Mask */ +#define LDSE_PAIRS_SHIFT 12 +#define LDSE_4PAIRS (2 << LDSE_PAIRS_SHIFT) /* 4 Pairs Connection */ +#define LDSE_2PAIRS (1 << LDSE_PAIRS_SHIFT) /* 2 Pairs Connection */ +#define LDSE_1PAIR (0 << LDSE_PAIRS_SHIFT) /* 1 Pair Connection */ +#define LDSE_CABLEN_MASK 0x0FFF /* Cable Length Mask */ + /* BCM54810 Registers */ #define BCM54810_EXP_BROADREACH_LRE_MISC_CTL (MII_BCM54XX_EXP_SEL_ER + 0x90) #define BCM54810_EXP_BROADREACH_LRE_MISC_CTL_EN (1 << 0) #define BCM54810_SHD_CLK_CTL 0x3 #define BCM54810_SHD_CLK_CTL_GTXCLK_EN (1 << 9) +/* BCM54811 Registers */ +#define BCM54811_EXP_BROADREACH_LRE_OVERLAY_CTL (MII_BCM54XX_EXP_SEL_ER + 0x9A) +/* Access Control Override Enable */ +#define BCM54811_EXP_BROADREACH_LRE_OVERLAY_CTL_EN BIT(15) +/* Access Control Override Value */ +#define BCM54811_EXP_BROADREACH_LRE_OVERLAY_CTL_OVERRIDE_VAL BIT(14) +/* Access Control Value */ +#define BCM54811_EXP_BROADREACH_LRE_OVERLAY_CTL_VAL BIT(13) + /* BCM54612E Registers */ #define BCM54612E_EXP_SPARE0 (MII_BCM54XX_EXP_SEL_ETC + 0x34) #define BCM54612E_LED4_CLK125OUT_EN (1 << 1) diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index 9e97ced2896d..14fa93268630 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -65,7 +65,8 @@ struct bsg_job { void bsg_job_done(struct bsg_job *job, int result, unsigned int reply_payload_rcv_len); struct request_queue *bsg_setup_queue(struct device *dev, const char *name, - bsg_job_fn *job_fn, bsg_timeout_fn *timeout, int dd_job_size); + struct queue_limits *lim, bsg_job_fn *job_fn, + bsg_timeout_fn *timeout, int dd_job_size); void bsg_remove_queue(struct request_queue *q); void bsg_job_put(struct bsg_job *job); int __must_check bsg_job_get(struct bsg_job *job); diff --git a/include/linux/btf.h b/include/linux/btf.h index f9e56fd12a9f..cffb43133c68 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -82,7 +82,7 @@ * as to avoid issues such as the compiler inlining or eliding either a static * kfunc, or a global kfunc in an LTO build. */ -#define __bpf_kfunc __used noinline +#define __bpf_kfunc __used __retain noinline #define __bpf_kfunc_start_defs() \ __diag_push(); \ @@ -140,6 +140,7 @@ extern const struct file_operations btf_fops; const char *btf_get_name(const struct btf *btf); void btf_get(struct btf *btf); void btf_put(struct btf *btf); +const struct btf_header *btf_header(const struct btf *btf); int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr, u32 uattr_sz); struct btf *btf_get_by_fd(int fd); int btf_get_info_by_fd(const struct btf *btf, @@ -212,8 +213,10 @@ int btf_get_fd_by_id(u32 id); u32 btf_obj_id(const struct btf *btf); bool btf_is_kernel(const struct btf *btf); bool btf_is_module(const struct btf *btf); +bool btf_is_vmlinux(const struct btf *btf); struct module *btf_try_get_module(const struct btf *btf); u32 btf_nr_types(const struct btf *btf); +struct btf *btf_base_btf(const struct btf *btf); bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, u32 expected_offset, u32 expected_size); @@ -339,6 +342,11 @@ static inline u8 btf_int_offset(const struct btf_type *t) return BTF_INT_OFFSET(*(u32 *)(t + 1)); } +static inline __u8 btf_int_bits(const struct btf_type *t) +{ + return BTF_INT_BITS(*(__u32 *)(t + 1)); +} + static inline bool btf_type_is_scalar(const struct btf_type *t) { return btf_type_is_int(t) || btf_type_is_enum(t); @@ -478,6 +486,11 @@ static inline struct btf_param *btf_params(const struct btf_type *t) return (struct btf_param *)(t + 1); } +static inline struct btf_decl_tag *btf_decl_tag(const struct btf_type *t) +{ + return (struct btf_decl_tag *)(t + 1); +} + static inline int btf_id_cmp_func(const void *a, const void *b) { const int *pa = a, *pb = b; @@ -515,9 +528,38 @@ static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf * } #endif +enum btf_field_iter_kind { + BTF_FIELD_ITER_IDS, + BTF_FIELD_ITER_STRS, +}; + +struct btf_field_desc { + /* once-per-type offsets */ + int t_off_cnt, t_offs[2]; + /* member struct size, or zero, if no members */ + int m_sz; + /* repeated per-member offsets */ + int m_off_cnt, m_offs[1]; +}; + +struct btf_field_iter { + struct btf_field_desc desc; + void *p; + int m_idx; + int off_idx; + int vlen; +}; + #ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); +void btf_set_base_btf(struct btf *btf, const struct btf *base_btf); +int btf_relocate(struct btf *btf, const struct btf *base_btf, __u32 **map_ids); +int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t, + enum btf_field_iter_kind iter_kind); +__u32 *btf_field_iter_next(struct btf_field_iter *it); + const char *btf_name_by_offset(const struct btf *btf, u32 offset); +const char *btf_str_by_offset(const struct btf *btf, u32 offset); struct btf *btf_parse_vmlinux(void); struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog); u32 *btf_kfunc_id_set_contains(const struct btf *btf, u32 kfunc_btf_id, @@ -531,6 +573,7 @@ s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id); int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt, struct module *owner); struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id); +bool btf_is_projection_of(const char *pname, const char *tname); bool btf_is_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, enum bpf_prog_type prog_type, int arg); @@ -543,6 +586,28 @@ static inline const struct btf_type *btf_type_by_id(const struct btf *btf, { return NULL; } + +static inline void btf_set_base_btf(struct btf *btf, const struct btf *base_btf) +{ +} + +static inline int btf_relocate(void *log, struct btf *btf, const struct btf *base_btf, + __u32 **map_ids) +{ + return -EOPNOTSUPP; +} + +static inline int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t, + enum btf_field_iter_kind iter_kind) +{ + return -EOPNOTSUPP; +} + +static inline __u32 *btf_field_iter_next(struct btf_field_iter *it) +{ + return NULL; +} + static inline const char *btf_name_by_offset(const struct btf *btf, u32 offset) { diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index e24aabfe8ecc..c0e3e1426a82 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -3,6 +3,8 @@ #ifndef _LINUX_BTF_IDS_H #define _LINUX_BTF_IDS_H +#include <linux/types.h> /* for u32 */ + struct btf_id_set { u32 cnt; u32 ids[]; diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index d78454a4dd1f..14acf1bbe0ce 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -53,7 +53,7 @@ typedef void (bh_end_io_t)(struct buffer_head *bh, int uptodate); * filesystem and block layers. Nowadays the basic I/O unit * is the bio, and buffer_heads are used for extracting block * mappings (via a get_block_t call), for tracking state within - * a page (via a page_mapping) and for wrapping bio submission + * a folio (via a folio_mapping) and for wrapping bio submission * for backward compatibility reasons (e.g. submit_bh). */ struct buffer_head { @@ -303,12 +303,38 @@ static inline void put_bh(struct buffer_head *bh) atomic_dec(&bh->b_count); } +/** + * brelse - Release a buffer. + * @bh: The buffer to release. + * + * Decrement a buffer_head's reference count. If @bh is NULL, this + * function is a no-op. + * + * If all buffers on a folio have zero reference count, are clean + * and unlocked, and if the folio is unlocked and not under writeback + * then try_to_free_buffers() may strip the buffers from the folio in + * preparation for freeing it (sometimes, rarely, buffers are removed + * from a folio but it ends up not being freed, and buffers may later + * be reattached). + * + * Context: Any context. + */ static inline void brelse(struct buffer_head *bh) { if (bh) __brelse(bh); } +/** + * bforget - Discard any dirty data in a buffer. + * @bh: The buffer to forget. + * + * Call this function instead of brelse() if the data written to a buffer + * no longer needs to be written back. It will clear the buffer's dirty + * flag so writeback of this buffer will be skipped. + * + * Context: Any context. + */ static inline void bforget(struct buffer_head *bh) { if (bh) @@ -338,7 +364,7 @@ static inline struct buffer_head *getblk_unmovable(struct block_device *bdev, { gfp_t gfp; - gfp = mapping_gfp_constraint(bdev->bd_inode->i_mapping, ~__GFP_FS); + gfp = mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS); gfp |= __GFP_NOFAIL; return bdev_getblk(bdev, block, size, gfp); @@ -349,7 +375,7 @@ static inline struct buffer_head *__getblk(struct block_device *bdev, { gfp_t gfp; - gfp = mapping_gfp_constraint(bdev->bd_inode->i_mapping, ~__GFP_FS); + gfp = mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS); gfp |= __GFP_MOVABLE | __GFP_NOFAIL; return bdev_getblk(bdev, block, size, gfp); @@ -437,17 +463,21 @@ static inline void bh_readahead_batch(int nr, struct buffer_head *bhs[], } /** - * __bread() - reads a specified block and returns the bh - * @bdev: the block_device to read from - * @block: number of block - * @size: size (in bytes) to read + * __bread() - Read a block. + * @bdev: The block device to read from. + * @block: Block number in units of block size. + * @size: The block size of this device in bytes. * - * Reads a specified block, and returns buffer head that contains it. - * The page cache is allocated from movable area so that it can be migrated. - * It returns NULL if the block was unreadable. + * Read a specified block, and return the buffer head that refers + * to it. The memory is allocated from the movable area so that it can + * be migrated. The returned buffer head has its refcount increased. + * The caller should call brelse() when it has finished with the buffer. + * + * Context: May sleep waiting for I/O. + * Return: NULL if the block was unreadable. */ -static inline struct buffer_head * -__bread(struct block_device *bdev, sector_t block, unsigned size) +static inline struct buffer_head *__bread(struct block_device *bdev, + sector_t block, unsigned size) { return __bread_gfp(bdev, block, size, __GFP_MOVABLE); } diff --git a/include/linux/bus/stm32_firewall_device.h b/include/linux/bus/stm32_firewall_device.h new file mode 100644 index 000000000000..18e0a2fc3816 --- /dev/null +++ b/include/linux/bus/stm32_firewall_device.h @@ -0,0 +1,142 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023, STMicroelectronics - All Rights Reserved + */ + +#ifndef STM32_FIREWALL_DEVICE_H +#define STM32_FIREWALL_DEVICE_H + +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/types.h> + +#define STM32_FIREWALL_MAX_EXTRA_ARGS 5 + +/* Opaque reference to stm32_firewall_controller */ +struct stm32_firewall_controller; + +/** + * struct stm32_firewall - Information on a device's firewall. Each device can have more than one + * firewall. + * + * @firewall_ctrl: Pointer referencing a firewall controller of the device. It is + * opaque so a device cannot manipulate the controller's ops or access + * the controller's data + * @extra_args: Extra arguments that are implementation dependent + * @entry: Name of the firewall entry + * @extra_args_size: Number of extra arguments + * @firewall_id: Firewall ID associated the device for this firewall controller + */ +struct stm32_firewall { + struct stm32_firewall_controller *firewall_ctrl; + u32 extra_args[STM32_FIREWALL_MAX_EXTRA_ARGS]; + const char *entry; + size_t extra_args_size; + u32 firewall_id; +}; + +#if IS_ENABLED(CONFIG_STM32_FIREWALL) +/** + * stm32_firewall_get_firewall - Get the firewall(s) associated to given device. + * The firewall controller reference is always the first argument + * of each of the access-controller property entries. + * The firewall ID is always the second argument of each of the + * access-controller property entries. + * If there's no argument linked to the phandle, then the firewall ID + * field is set to U32_MAX, which is an invalid ID. + * + * @np: Device node to parse + * @firewall: Array of firewall references + * @nb_firewall: Number of firewall references to get. Must be at least 1. + * + * Returns 0 on success, -ENODEV if there's no match with a firewall controller or appropriate errno + * code if error occurred. + */ +int stm32_firewall_get_firewall(struct device_node *np, struct stm32_firewall *firewall, + unsigned int nb_firewall); + +/** + * stm32_firewall_grant_access - Request firewall access rights and grant access. + * + * @firewall: Firewall reference containing the ID to check against its firewall + * controller + * + * Returns 0 if access is granted, -EACCES if access is denied, -ENODEV if firewall is null or + * appropriate errno code if error occurred + */ +int stm32_firewall_grant_access(struct stm32_firewall *firewall); + +/** + * stm32_firewall_release_access - Release access granted from a call to + * stm32_firewall_grant_access(). + * + * @firewall: Firewall reference containing the ID to check against its firewall + * controller + */ +void stm32_firewall_release_access(struct stm32_firewall *firewall); + +/** + * stm32_firewall_grant_access_by_id - Request firewall access rights of a given device + * based on a specific firewall ID + * + * Warnings: + * There is no way to ensure that the given ID will correspond to the firewall referenced in the + * device node if the ID did not come from stm32_firewall_get_firewall(). In that case, this + * function must be used with caution. + * This function should be used for subsystem resources that do not have the same firewall ID + * as their parent. + * U32_MAX is an invalid ID. + * + * @firewall: Firewall reference containing the firewall controller + * @subsystem_id: Firewall ID of the subsystem resource + * + * Returns 0 if access is granted, -EACCES if access is denied, -ENODEV if firewall is null or + * appropriate errno code if error occurred + */ +int stm32_firewall_grant_access_by_id(struct stm32_firewall *firewall, u32 subsystem_id); + +/** + * stm32_firewall_release_access_by_id - Release access granted from a call to + * stm32_firewall_grant_access_by_id(). + * + * Warnings: + * There is no way to ensure that the given ID will correspond to the firewall referenced in the + * device node if the ID did not come from stm32_firewall_get_firewall(). In that case, this + * function must be used with caution. + * This function should be used for subsystem resources that do not have the same firewall ID + * as their parent. + * U32_MAX is an invalid ID. + * + * @firewall: Firewall reference containing the firewall controller + * @subsystem_id: Firewall ID of the subsystem resource + */ +void stm32_firewall_release_access_by_id(struct stm32_firewall *firewall, u32 subsystem_id); + +#else /* CONFIG_STM32_FIREWALL */ + +int stm32_firewall_get_firewall(struct device_node *np, struct stm32_firewall *firewall, + unsigned int nb_firewall); +{ + return -ENODEV; +} + +int stm32_firewall_grant_access(struct stm32_firewall *firewall) +{ + return -ENODEV; +} + +void stm32_firewall_release_access(struct stm32_firewall *firewall) +{ +} + +int stm32_firewall_grant_access_by_id(struct stm32_firewall *firewall, u32 subsystem_id) +{ + return -ENODEV; +} + +void stm32_firewall_release_access_by_id(struct stm32_firewall *firewall, u32 subsystem_id) +{ +} + +#endif /* CONFIG_STM32_FIREWALL */ +#endif /* STM32_FIREWALL_DEVICE_H */ diff --git a/include/linux/bvec.h b/include/linux/bvec.h index bd1e361b351c..f41c7f0ef91e 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -280,4 +280,18 @@ static inline void *bvec_virt(struct bio_vec *bvec) return page_address(bvec->bv_page) + bvec->bv_offset; } +/** + * bvec_phys - return the physical address for a bvec + * @bvec: bvec to return the physical address for + */ +static inline phys_addr_t bvec_phys(const struct bio_vec *bvec) +{ + /* + * Note this open codes page_to_phys because page_to_phys is defined in + * <asm/io.h>, which we don't want to pull in here. If it ever moves to + * a sensible place we should start using it. + */ + return PFN_PHYS(page_to_pfn(bvec->bv_page)) + bvec->bv_offset; +} + #endif /* __LINUX_BVEC_H */ diff --git a/include/linux/cache.h b/include/linux/cache.h index 0ecb17bb6883..ca2a05682a54 100644 --- a/include/linux/cache.h +++ b/include/linux/cache.h @@ -13,6 +13,32 @@ #define SMP_CACHE_BYTES L1_CACHE_BYTES #endif +/** + * SMP_CACHE_ALIGN - align a value to the L2 cacheline size + * @x: value to align + * + * On some architectures, L2 ("SMP") CL size is bigger than L1, and sometimes, + * this needs to be accounted. + * + * Return: aligned value. + */ +#ifndef SMP_CACHE_ALIGN +#define SMP_CACHE_ALIGN(x) ALIGN(x, SMP_CACHE_BYTES) +#endif + +/* + * ``__aligned_largest`` aligns a field to the value most optimal for the + * target architecture to perform memory operations. Get the actual value + * to be able to use it anywhere else. + */ +#ifndef __LARGEST_ALIGN +#define __LARGEST_ALIGN sizeof(struct { long x; } __aligned_largest) +#endif + +#ifndef LARGEST_ALIGN +#define LARGEST_ALIGN(x) ALIGN(x, __LARGEST_ALIGN) +#endif + /* * __read_mostly is used to keep rarely changing variables out of frequently * updated cachelines. Its use should be reserved for data that is used @@ -95,6 +121,39 @@ __u8 __cacheline_group_end__##GROUP[0] #endif +/** + * __cacheline_group_begin_aligned - declare an aligned group start + * @GROUP: name of the group + * @...: optional group alignment + * + * The following block inside a struct: + * + * __cacheline_group_begin_aligned(grp); + * field a; + * field b; + * __cacheline_group_end_aligned(grp); + * + * will always be aligned to either the specified alignment or + * ``SMP_CACHE_BYTES``. + */ +#define __cacheline_group_begin_aligned(GROUP, ...) \ + __cacheline_group_begin(GROUP) \ + __aligned((__VA_ARGS__ + 0) ? : SMP_CACHE_BYTES) + +/** + * __cacheline_group_end_aligned - declare an aligned group end + * @GROUP: name of the group + * @...: optional alignment (same as was in __cacheline_group_begin_aligned()) + * + * Note that the end marker is aligned to sizeof(long) to allow more precise + * size assertion. It also declares a padding at the end to avoid next field + * falling into this cacheline. + */ +#define __cacheline_group_end_aligned(GROUP, ...) \ + __cacheline_group_end(GROUP) __aligned(sizeof(long)); \ + struct { } __cacheline_group_pad__##GROUP \ + __aligned((__VA_ARGS__ + 0) ? : SMP_CACHE_BYTES) + #ifndef CACHELINE_ASSERT_GROUP_MEMBER #define CACHELINE_ASSERT_GROUP_MEMBER(TYPE, GROUP, MEMBER) \ BUILD_BUG_ON(!(offsetof(TYPE, MEMBER) >= \ diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 2cb15fe4fe12..108060612bb8 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -3,7 +3,8 @@ #define _LINUX_CACHEINFO_H #include <linux/bitops.h> -#include <linux/cpumask.h> +#include <linux/cpuhplock.h> +#include <linux/cpumask_types.h> #include <linux/smp.h> struct device_node; @@ -113,23 +114,37 @@ int acpi_get_cache_info(unsigned int cpu, const struct attribute_group *cache_get_priv_group(struct cacheinfo *this_leaf); /* - * Get the id of the cache associated with @cpu at level @level. + * Get the cacheinfo structure for the cache associated with @cpu at + * level @level. * cpuhp lock must be held. */ -static inline int get_cpu_cacheinfo_id(int cpu, int level) +static inline struct cacheinfo *get_cpu_cacheinfo_level(int cpu, int level) { struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu); int i; + lockdep_assert_cpus_held(); + for (i = 0; i < ci->num_leaves; i++) { if (ci->info_list[i].level == level) { if (ci->info_list[i].attributes & CACHE_ID) - return ci->info_list[i].id; - return -1; + return &ci->info_list[i]; + return NULL; } } - return -1; + return NULL; +} + +/* + * Get the id of the cache associated with @cpu at level @level. + * cpuhp lock must be held. + */ +static inline int get_cpu_cacheinfo_id(int cpu, int level) +{ + struct cacheinfo *ci = get_cpu_cacheinfo_level(cpu, level); + + return ci ? ci->id : -1; } #ifdef CONFIG_ARM64 diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 1b92aed49363..23492213ea35 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -186,7 +186,7 @@ void close_candev(struct net_device *dev); int can_change_mtu(struct net_device *dev, int new_mtu); int can_eth_ioctl_hwts(struct net_device *netdev, struct ifreq *ifr, int cmd); int can_ethtool_op_get_ts_info_hwts(struct net_device *dev, - struct ethtool_ts_info *info); + struct kernel_ethtool_ts_info *info); int register_candev(struct net_device *dev); void unregister_candev(struct net_device *dev); diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index 60693a145894..caa4b4430634 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -82,16 +82,6 @@ enum cc_attr { CC_ATTR_GUEST_SEV_SNP, /** - * @CC_ATTR_HOTPLUG_DISABLED: Hotplug is not supported or disabled. - * - * The platform/OS is running as a guest/virtual machine does not - * support CPU hotplug feature. - * - * Examples include TDX Guest. - */ - CC_ATTR_HOTPLUG_DISABLED, - - /** * @CC_ATTR_HOST_SEV_SNP: AMD SNP enabled on the host. * * The host kernel is running with the necessary features diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 98c6fd0b39b6..fdfb61ccf55a 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -77,7 +77,7 @@ struct cdrom_device_ops { unsigned int clearing, int slot); int (*tray_move) (struct cdrom_device_info *, int); int (*lock_door) (struct cdrom_device_info *, int); - int (*select_speed) (struct cdrom_device_info *, int); + int (*select_speed) (struct cdrom_device_info *, unsigned long); int (*get_last_session) (struct cdrom_device_info *, struct cdrom_multisession *); int (*get_mcn) (struct cdrom_device_info *, diff --git a/include/linux/cdx/cdx_bus.h b/include/linux/cdx/cdx_bus.h index b57118aaa679..79bb80e56790 100644 --- a/include/linux/cdx/cdx_bus.h +++ b/include/linux/cdx/cdx_bus.h @@ -211,7 +211,7 @@ struct cdx_driver { }; #define to_cdx_driver(_drv) \ - container_of(_drv, struct cdx_driver, driver) + container_of_const(_drv, struct cdx_driver, driver) /* Macro to avoid include chaining to get THIS_MODULE */ #define cdx_driver_register(drv) \ diff --git a/include/linux/ceph/ceph_debug.h b/include/linux/ceph/ceph_debug.h index 11a92a946016..5f904591fa5f 100644 --- a/include/linux/ceph/ceph_debug.h +++ b/include/linux/ceph/ceph_debug.h @@ -27,17 +27,13 @@ ##__VA_ARGS__) # else /* faux printk call just to see any compiler warnings. */ -# define dout(fmt, ...) do { \ - if (0) \ - printk(KERN_DEBUG fmt, ##__VA_ARGS__); \ - } while (0) -# define doutc(client, fmt, ...) do { \ - if (0) \ - printk(KERN_DEBUG "[%pU %llu] " fmt, \ - &client->fsid, \ - client->monc.auth->global_id, \ - ##__VA_ARGS__); \ - } while (0) +# define dout(fmt, ...) \ + no_printk(KERN_DEBUG fmt, ##__VA_ARGS__) +# define doutc(client, fmt, ...) \ + no_printk(KERN_DEBUG "[%pU %llu] " fmt, \ + &client->fsid, \ + client->monc.auth->global_id, \ + ##__VA_ARGS__) # endif #else diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index ea48c861cd36..ae04035b6cbe 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -119,7 +119,12 @@ enum { /* * Enable hugetlb accounting for the memory controller. */ - CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING = (1 << 19), + CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING = (1 << 19), + + /* + * Enable legacy local pids.events. + */ + CGRP_ROOT_PIDS_LOCAL_EVENTS = (1 << 20), }; /* cftype->flags */ @@ -534,9 +539,6 @@ struct cgroup { /* used to store eBPF programs */ struct cgroup_bpf bpf; - /* If there is block congestion on this cgroup. */ - atomic_t congestion_count; - /* Used to store internal freezer state */ struct cgroup_freezer_state freezer; @@ -676,9 +678,7 @@ struct cftype { __poll_t (*poll)(struct kernfs_open_file *of, struct poll_table_struct *pt); -#ifdef CONFIG_DEBUG_LOCK_ALLOC struct lock_class_key lockdep_key; -#endif }; /* diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 34aaf0e87def..c60ba0ab1462 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -10,7 +10,6 @@ */ #include <linux/sched.h> -#include <linux/cpumask.h> #include <linux/nodemask.h> #include <linux/rculist.h> #include <linux/cgroupstats.h> @@ -690,7 +689,7 @@ 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_hold(struct cgroup *cgrp); -void cgroup_rstat_flush_release(void); +void cgroup_rstat_flush_release(struct cgroup *cgrp); /* * Basic resource stats. diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index c2d09bc4f976..d9e613803df1 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_GUARDS_H -#define __LINUX_GUARDS_H +#ifndef _LINUX_CLEANUP_H +#define _LINUX_CLEANUP_H #include <linux/compiler.h> @@ -63,17 +63,20 @@ #define __free(_name) __cleanup(__free_##_name) -#define __get_and_null_ptr(p) \ - ({ __auto_type __ptr = &(p); \ - __auto_type __val = *__ptr; \ - *__ptr = NULL; __val; }) +#define __get_and_null(p, nullvalue) \ + ({ \ + __auto_type __ptr = &(p); \ + __auto_type __val = *__ptr; \ + *__ptr = nullvalue; \ + __val; \ + }) static inline __must_check const volatile void * __must_check_fn(const volatile void *val) { return val; } #define no_free_ptr(p) \ - ((typeof(p)) __must_check_fn(__get_and_null_ptr(p))) + ((typeof(p)) __must_check_fn(__get_and_null(p, NULL))) #define return_ptr(p) return no_free_ptr(p) @@ -247,4 +250,4 @@ __DEFINE_LOCK_GUARD_0(_name, _lock) { return class_##_name##_lock_ptr(_T); } -#endif /* __LINUX_GUARDS_H */ +#endif /* _LINUX_CLEANUP_H */ diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 9aac31d856f3..b0df28ddd394 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -12,7 +12,7 @@ #ifdef CONFIG_GENERIC_CLOCKEVENTS # include <linux/clocksource.h> -# include <linux/cpumask.h> +# include <linux/cpumask_types.h> # include <linux/ktime.h> # include <linux/notifier.h> diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 0ad8b550bb4b..d35b677b08fe 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -21,6 +21,7 @@ #include <asm/div64.h> #include <asm/io.h> +struct clocksource_base; struct clocksource; struct module; @@ -50,6 +51,7 @@ struct module; * multiplication * @name: Pointer to clocksource name * @list: List head for registration (internal) + * @freq_khz: Clocksource frequency in khz. * @rating: Rating value for selection (higher is better) * To avoid rating inflation the following * list should give you a guide as to how @@ -70,6 +72,8 @@ struct module; * validate the clocksource from which the snapshot was * taken. * @flags: Flags describing special properties + * @base: Hardware abstraction for clock on which a clocksource + * is based * @enable: Optional function to enable the clocksource * @disable: Optional function to disable the clocksource * @suspend: Optional suspend function for the clocksource @@ -107,10 +111,12 @@ struct clocksource { u64 max_cycles; const char *name; struct list_head list; + u32 freq_khz; int rating; enum clocksource_ids id; enum vdso_clock_mode vdso_clock_mode; unsigned long flags; + struct clocksource_base *base; int (*enable)(struct clocksource *cs); void (*disable)(struct clocksource *cs); @@ -306,4 +312,25 @@ static inline unsigned int clocksource_get_max_watchdog_retry(void) void clocksource_verify_percpu(struct clocksource *cs); +/** + * struct clocksource_base - hardware abstraction for clock on which a clocksource + * is based + * @id: Defaults to CSID_GENERIC. The id value is used for conversion + * functions which require that the current clocksource is based + * on a clocksource_base with a particular ID in certain snapshot + * functions to allow callers to validate the clocksource from + * which the snapshot was taken. + * @freq_khz: Nominal frequency of the base clock in kHz + * @offset: Offset between the base clock and the clocksource + * @numerator: Numerator of the clock ratio between base clock and the clocksource + * @denominator: Denominator of the clock ratio between base clock and the clocksource + */ +struct clocksource_base { + enum clocksource_ids id; + u32 freq_khz; + u64 offset; + u32 numerator; + u32 denominator; +}; + #endif /* _LINUX_CLOCKSOURCE_H */ diff --git a/include/linux/clocksource_ids.h b/include/linux/clocksource_ids.h index a4fa3436940c..2bb4d8c2f1b0 100644 --- a/include/linux/clocksource_ids.h +++ b/include/linux/clocksource_ids.h @@ -9,6 +9,7 @@ enum clocksource_ids { CSID_X86_TSC_EARLY, CSID_X86_TSC, CSID_X86_KVM_CLK, + CSID_X86_ART, CSID_MAX, }; diff --git a/include/linux/closure.h b/include/linux/closure.h index c554c6a08768..2af44427107d 100644 --- a/include/linux/closure.h +++ b/include/linux/closure.h @@ -159,6 +159,7 @@ struct closure { #ifdef CONFIG_DEBUG_CLOSURES #define CLOSURE_MAGIC_DEAD 0xc054dead #define CLOSURE_MAGIC_ALIVE 0xc054a11e +#define CLOSURE_MAGIC_STACK 0xc05451cc unsigned int magic; struct list_head all; @@ -194,6 +195,18 @@ static inline void closure_sync(struct closure *cl) __closure_sync(cl); } +int __closure_sync_timeout(struct closure *cl, unsigned long timeout); + +static inline int closure_sync_timeout(struct closure *cl, unsigned long timeout) +{ +#ifdef CONFIG_DEBUG_CLOSURES + BUG_ON(closure_nr_remaining(cl) != 1 && !cl->closure_get_happened); +#endif + return cl->closure_get_happened + ? __closure_sync_timeout(cl, timeout) + : 0; +} + #ifdef CONFIG_DEBUG_CLOSURES void closure_debug_create(struct closure *cl); @@ -273,6 +286,21 @@ static inline void closure_get(struct closure *cl) } /** + * closure_get_not_zero + */ +static inline bool closure_get_not_zero(struct closure *cl) +{ + unsigned old = atomic_read(&cl->remaining); + do { + if (!(old & CLOSURE_REMAINING_MASK)) + return false; + + } while (!atomic_try_cmpxchg_acquire(&cl->remaining, &old, old + 1)); + + return true; +} + +/** * closure_init - Initialize a closure, setting the refcount to 1 * @cl: closure to initialize * @parent: parent of the new closure. cl will take a refcount on it for its @@ -296,6 +324,18 @@ static inline void closure_init_stack(struct closure *cl) { memset(cl, 0, sizeof(struct closure)); atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER); +#ifdef CONFIG_DEBUG_CLOSURES + cl->magic = CLOSURE_MAGIC_STACK; +#endif +} + +static inline void closure_init_stack_release(struct closure *cl) +{ + memset(cl, 0, sizeof(struct closure)); + atomic_set_release(&cl->remaining, CLOSURE_REMAINING_INITIALIZER); +#ifdef CONFIG_DEBUG_CLOSURES + cl->magic = CLOSURE_MAGIC_STACK; +#endif } /** @@ -343,6 +383,8 @@ do { \ */ #define closure_return(_cl) continue_at((_cl), NULL, NULL) +void closure_return_sync(struct closure *cl); + /** * continue_at_nobarrier - jump to another function without barrier * diff --git a/include/linux/cmpxchg-emu.h b/include/linux/cmpxchg-emu.h new file mode 100644 index 000000000000..998deec67740 --- /dev/null +++ b/include/linux/cmpxchg-emu.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Emulated 1-byte and 2-byte cmpxchg operations for architectures + * lacking direct support for these sizes. These are implemented in terms + * of 4-byte cmpxchg operations. + * + * Copyright (C) 2024 Paul E. McKenney. + */ + +#ifndef __LINUX_CMPXCHG_EMU_H +#define __LINUX_CMPXCHG_EMU_H + +uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new); + +#endif /* __LINUX_CMPXCHG_EMU_H */ diff --git a/include/linux/codetag.h b/include/linux/codetag.h new file mode 100644 index 000000000000..c2a579ccd455 --- /dev/null +++ b/include/linux/codetag.h @@ -0,0 +1,81 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * code tagging framework + */ +#ifndef _LINUX_CODETAG_H +#define _LINUX_CODETAG_H + +#include <linux/types.h> + +struct codetag_iterator; +struct codetag_type; +struct codetag_module; +struct seq_buf; +struct module; + +/* + * An instance of this structure is created in a special ELF section at every + * code location being tagged. At runtime, the special section is treated as + * an array of these. + */ +struct codetag { + unsigned int flags; /* used in later patches */ + unsigned int lineno; + const char *modname; + const char *function; + const char *filename; +} __aligned(8); + +union codetag_ref { + struct codetag *ct; +}; + +struct codetag_type_desc { + const char *section; + size_t tag_size; + void (*module_load)(struct codetag_type *cttype, + struct codetag_module *cmod); + bool (*module_unload)(struct codetag_type *cttype, + struct codetag_module *cmod); +}; + +struct codetag_iterator { + struct codetag_type *cttype; + struct codetag_module *cmod; + unsigned long mod_id; + struct codetag *ct; +}; + +#ifdef MODULE +#define CT_MODULE_NAME KBUILD_MODNAME +#else +#define CT_MODULE_NAME NULL +#endif + +#define CODE_TAG_INIT { \ + .modname = CT_MODULE_NAME, \ + .function = __func__, \ + .filename = __FILE__, \ + .lineno = __LINE__, \ + .flags = 0, \ +} + +void codetag_lock_module_list(struct codetag_type *cttype, bool lock); +bool codetag_trylock_module_list(struct codetag_type *cttype); +struct codetag_iterator codetag_get_ct_iter(struct codetag_type *cttype); +struct codetag *codetag_next_ct(struct codetag_iterator *iter); + +void codetag_to_text(struct seq_buf *out, struct codetag *ct); + +struct codetag_type * +codetag_register_type(const struct codetag_type_desc *desc); + +#if defined(CONFIG_CODE_TAGGING) && defined(CONFIG_MODULES) +void codetag_load_module(struct module *mod); +bool codetag_unload_module(struct module *mod); +#else +static inline void codetag_load_module(struct module *mod) {} +static inline bool codetag_unload_module(struct module *mod) { return true; } +#endif + +#endif /* _LINUX_CODETAG_H */ diff --git a/include/linux/compat.h b/include/linux/compat.h index 233f61ec8afc..56cebaff0c91 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -608,7 +608,7 @@ asmlinkage long compat_sys_fstatfs(unsigned int fd, asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user *buf); asmlinkage long compat_sys_truncate(const char __user *, compat_off_t); -asmlinkage long compat_sys_ftruncate(unsigned int, compat_ulong_t); +asmlinkage long compat_sys_ftruncate(unsigned int, compat_off_t); /* No generic prototype for truncate64, ftruncate64, fallocate */ asmlinkage long compat_sys_openat(int dfd, const char __user *filename, int flags, umode_t mode); diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 49feac0162a5..4c1a39dcb624 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -118,3 +118,13 @@ #define __diag_ignore_all(option, comment) \ __diag_clang(13, ignore, option) + +/* + * clang has horrible behavior with "g" or "rm" constraints for asm + * inputs, turning them into something worse than "m". Avoid using + * constraints with multiple possible uses (but "ir" seems to be ok): + * + * https://github.com/llvm/llvm-project/issues/20571 + */ +#define ASM_INPUT_G "ir" +#define ASM_INPUT_RM "r" diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index aff92b1d284f..f805adaa316e 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -64,26 +64,6 @@ __builtin_unreachable(); \ } while (0) -/* - * GCC 'asm goto' with outputs miscompiles certain code sequences: - * - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=113921 - * - * Work around it via the same compiler barrier quirk that we used - * to use for the old 'asm goto' workaround. - * - * Also, always mark such 'asm goto' statements as volatile: all - * asm goto statements are supposed to be volatile as per the - * documentation, but some versions of gcc didn't actually do - * that for asms with outputs: - * - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98619 - */ -#ifdef CONFIG_GCC_ASM_GOTO_OUTPUT_WORKAROUND -#define asm_goto_output(x...) \ - do { asm volatile goto(x); asm (""); } while (0) -#endif - #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 8c252e073bd8..2df665fa2964 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -194,16 +194,22 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, * This data_race() macro is useful for situations in which data races * should be forgiven. One example is diagnostic code that accesses * shared variables but is not a part of the core synchronization design. + * For example, if accesses to a given variable are protected by a lock, + * except for diagnostic code, then the accesses under the lock should + * be plain C-language accesses and those in the diagnostic code should + * use data_race(). This way, KCSAN will complain if buggy lockless + * accesses to that variable are introduced, even if the buggy accesses + * are protected by READ_ONCE() or WRITE_ONCE(). * * This macro *does not* affect normal code generation, but is a hint - * to tooling that data races here are to be ignored. + * to tooling that data races here are to be ignored. If the access must + * be atomic *and* KCSAN should ignore the access, use both data_race() + * and READ_ONCE(), for example, data_race(READ_ONCE(x)). */ #define data_race(expr) \ ({ \ - __unqual_scalar_typeof(({ expr; })) __v = ({ \ - __kcsan_disable_current(); \ - expr; \ - }); \ + __kcsan_disable_current(); \ + __auto_type __v = (expr); \ __kcsan_enable_current(); \ __v; \ }) @@ -291,6 +297,15 @@ static inline void *offset_to_ptr(const int *off) #define is_unsigned_type(type) (!is_signed_type(type)) /* + * Useful shorthand for "is this condition known at compile-time?" + * + * Note that the condition may involve non-constant values, + * but the compiler may know enough about the details of the + * values to determine that the condition is statically true. + */ +#define statically_true(x) (__builtin_constant_p(x) && (x)) + +/* * This is needed in functions which generate the stack canary, see * arch/x86/kernel/smpboot.c::start_secondary() for an example. */ diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 8bdf6e0918c1..32284cd26d52 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -362,6 +362,19 @@ #define __used __attribute__((__used__)) /* + * The __used attribute guarantees that the attributed variable will be + * always emitted by a compiler. It doesn't prevent the compiler from + * throwing 'unused' warnings when it can't detect how the variable is + * actually used. It's a compiler implementation details either emit + * the warning in that case or not. + * + * The combination of both 'used' and 'unused' attributes ensures that + * the variable would be emitted, and will not trigger 'unused' warnings. + * The attribute is applicable for functions, static and global variables. + */ +#define __always_used __used __maybe_unused + +/* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-warn_005funused_005fresult-function-attribute * clang: https://clang.llvm.org/docs/AttributeReference.html#nodiscard-warn-unused-result */ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 2abaa3a825a9..f14c275950b5 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -143,6 +143,29 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } # define __preserve_most #endif +/* + * Annotating a function/variable with __retain tells the compiler to place + * the object in its own section and set the flag SHF_GNU_RETAIN. This flag + * instructs the linker to retain the object during garbage-cleanup or LTO + * phases. + * + * Note that the __used macro is also used to prevent functions or data + * being optimized out, but operates at the compiler/IR-level and may still + * allow unintended removal of objects during linking. + * + * Optional: only supported since gcc >= 11, clang >= 13 + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-retain-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#retain + */ +#if __has_attribute(__retain__) && \ + (defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || \ + defined(CONFIG_LTO_CLANG)) +# define __retain __attribute__((__retain__)) +#else +# define __retain +#endif + /* Compiler specific macros. */ #ifdef __clang__ #include <linux/compiler-clang.h> @@ -273,15 +296,44 @@ struct ftrace_likely_data { * disable all instrumentation. See Kconfig.kcsan where this is mandatory. */ # define __no_kcsan __no_sanitize_thread __disable_sanitizer_instrumentation +/* + * Type qualifier to mark variables where all data-racy accesses should be + * ignored by KCSAN. Note, the implementation simply marks these variables as + * volatile, since KCSAN will treat such accesses as "marked". + */ +# define __data_racy volatile # define __no_sanitize_or_inline __no_kcsan notrace __maybe_unused #else # define __no_kcsan +# define __data_racy +#endif + +#ifdef __SANITIZE_MEMORY__ +/* + * Similarly to KASAN and KCSAN, KMSAN loses function attributes of inlined + * functions, therefore disabling KMSAN checks also requires disabling inlining. + * + * __no_sanitize_or_inline effectively prevents KMSAN from reporting errors + * within the function and marks all its outputs as initialized. + */ +# define __no_sanitize_or_inline __no_kmsan_checks notrace __maybe_unused #endif #ifndef __no_sanitize_or_inline #define __no_sanitize_or_inline __always_inline #endif +/* + * Apply __counted_by() when the Endianness matches to increase test coverage. + */ +#ifdef __LITTLE_ENDIAN +#define __counted_by_le(member) __counted_by(member) +#define __counted_by_be(member) +#else +#define __counted_by_le(member) +#define __counted_by_be(member) __counted_by(member) +#endif + /* Do not trap wrapping arithmetic within an annotated function. */ #ifdef CONFIG_UBSAN_SIGNED_WRAP # define __signed_wrap __attribute__((no_sanitize("signed-integer-overflow"))) @@ -380,6 +432,15 @@ struct ftrace_likely_data { #define asm_goto_output(x...) asm volatile goto(x) #endif +/* + * Clang has trouble with constraints with multiple + * alternative behaviors (mainly "g" and "rm"). + */ +#ifndef ASM_INPUT_G + #define ASM_INPUT_G "g" + #define ASM_INPUT_RM "rm" +#endif + #ifdef CONFIG_CC_HAS_ASM_INLINE #define asm_inline asm __inline #else diff --git a/include/linux/configfs.h b/include/linux/configfs.h index 2606711adb18..c771e9d0d0b9 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -216,6 +216,9 @@ struct configfs_group_operations { struct config_group *(*make_group)(struct config_group *group, const char *name); void (*disconnect_notify)(struct config_group *group, struct config_item *item); void (*drop_item)(struct config_group *group, struct config_item *item); + bool (*is_visible)(struct config_item *item, struct configfs_attribute *attr, int n); + bool (*is_bin_visible)(struct config_item *item, struct configfs_bin_attribute *attr, + int n); }; struct configfs_subsystem { diff --git a/include/linux/coredump.h b/include/linux/coredump.h index d3eba4360150..0904ba010341 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -30,6 +30,8 @@ struct coredump_params { struct core_vma_metadata *vma_meta; }; +extern unsigned int core_file_note_size_limit; + /* * These are the only things you should do on a core-file: use only these * functions to write out all the necessary info. diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 5f288d475490..f09ace92176e 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -12,6 +12,7 @@ #include <linux/io.h> #include <linux/perf_event.h> #include <linux/sched.h> +#include <linux/platform_device.h> /* Peripheral id registers (0xFD0-0xFEC) */ #define CORESIGHT_PERIPHIDR4 0xfd0 @@ -658,4 +659,9 @@ coresight_find_output_type(struct coresight_platform_data *pdata, enum coresight_dev_type type, union coresight_dev_subtype subtype); +int coresight_init_driver(const char *drv, struct amba_driver *amba_drv, + struct platform_driver *pdev_drv); + +void coresight_remove_driver(struct amba_driver *amba_drv, + struct platform_driver *pdev_drv); #endif /* _LINUX_COREISGHT_H */ diff --git a/include/linux/counter.h b/include/linux/counter.h index 702e9108bbb4..426b7d58a438 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -6,14 +6,15 @@ #ifndef _COUNTER_H_ #define _COUNTER_H_ +#include <linux/array_size.h> #include <linux/cdev.h> #include <linux/device.h> -#include <linux/kernel.h> #include <linux/kfifo.h> #include <linux/mutex.h> #include <linux/spinlock_types.h> #include <linux/types.h> #include <linux/wait.h> + #include <uapi/linux/counter.h> struct counter_device; @@ -359,7 +360,6 @@ struct counter_ops { * @num_counts: number of Counts specified in @counts * @ext: optional array of Counter device extensions * @num_ext: number of Counter device extensions specified in @ext - * @priv: optional private data supplied by driver * @dev: internal device structure * @chrdev: internal character device structure * @events_list: list of current watching Counter events @@ -602,6 +602,9 @@ struct counter_array { #define COUNTER_COMP_FLOOR(_read, _write) \ COUNTER_COMP_COUNT_U64("floor", _read, _write) +#define COUNTER_COMP_FREQUENCY(_read) \ + COUNTER_COMP_SIGNAL_U64("frequency", _read, NULL) + #define COUNTER_COMP_POLARITY(_read, _write, _available) \ { \ .type = COUNTER_COMP_SIGNAL_POLARITY, \ diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 861c3bfc5f17..bdcec1732445 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -16,8 +16,8 @@ #include <linux/node.h> #include <linux/compiler.h> -#include <linux/cpumask.h> #include <linux/cpuhotplug.h> +#include <linux/cpuhplock.h> #include <linux/cpu_smt.h> struct device; @@ -132,38 +132,6 @@ static inline int add_cpu(unsigned int cpu) { return 0;} #endif /* CONFIG_SMP */ extern const struct bus_type cpu_subsys; -extern int lockdep_is_cpus_held(void); - -#ifdef CONFIG_HOTPLUG_CPU -extern void cpus_write_lock(void); -extern void cpus_write_unlock(void); -extern void cpus_read_lock(void); -extern void cpus_read_unlock(void); -extern int cpus_read_trylock(void); -extern void lockdep_assert_cpus_held(void); -extern void cpu_hotplug_disable(void); -extern void cpu_hotplug_enable(void); -void clear_tasks_mm_cpumask(int cpu); -int remove_cpu(unsigned int cpu); -int cpu_device_down(struct device *dev); -extern void smp_shutdown_nonboot_cpus(unsigned int primary_cpu); - -#else /* CONFIG_HOTPLUG_CPU */ - -static inline void cpus_write_lock(void) { } -static inline void cpus_write_unlock(void) { } -static inline void cpus_read_lock(void) { } -static inline void cpus_read_unlock(void) { } -static inline int cpus_read_trylock(void) { return true; } -static inline void lockdep_assert_cpus_held(void) { } -static inline void cpu_hotplug_disable(void) { } -static inline void cpu_hotplug_enable(void) { } -static inline int remove_cpu(unsigned int cpu) { return -EPERM; } -static inline void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { } -#endif /* !CONFIG_HOTPLUG_CPU */ - -DEFINE_LOCK_GUARD_0(cpus_read_lock, cpus_read_lock(), cpus_read_unlock()) - #ifdef CONFIG_PM_SLEEP_SMP extern int freeze_secondary_cpus(int primary); extern void thaw_secondary_cpus(void); diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index a3bdc8a98f2c..2c774fb3c091 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -15,7 +15,6 @@ #include <linux/of.h> #include <linux/thermal.h> -#include <linux/cpumask.h> struct cpufreq_policy; diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h index cae324d10965..20b5729903d7 100644 --- a/include/linux/cpu_rmap.h +++ b/include/linux/cpu_rmap.h @@ -7,7 +7,7 @@ * Copyright 2011 Solarflare Communications Inc. */ -#include <linux/cpumask.h> +#include <linux/cpumask_types.h> #include <linux/gfp.h> #include <linux/slab.h> #include <linux/kref.h> diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 9956afb9acc2..d4d2f4d1d7cb 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -241,6 +241,12 @@ struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); void cpufreq_enable_fast_switch(struct cpufreq_policy *policy); void cpufreq_disable_fast_switch(struct cpufreq_policy *policy); bool has_target_index(void); + +DECLARE_PER_CPU(unsigned long, cpufreq_pressure); +static inline unsigned long cpufreq_get_pressure(int cpu) +{ + return READ_ONCE(per_cpu(cpufreq_pressure, cpu)); +} #else static inline unsigned int cpufreq_get(unsigned int cpu) { @@ -264,6 +270,10 @@ static inline bool cpufreq_supports_freq_invariance(void) } static inline void disable_cpufreq(void) { } static inline void cpufreq_update_limits(unsigned int cpu) { } +static inline unsigned long cpufreq_get_pressure(int cpu) +{ + return 0; +} #endif #ifdef CONFIG_CPU_FREQ_STAT @@ -386,7 +396,7 @@ struct cpufreq_driver { int (*online)(struct cpufreq_policy *policy); int (*offline)(struct cpufreq_policy *policy); - int (*exit)(struct cpufreq_policy *policy); + void (*exit)(struct cpufreq_policy *policy); int (*suspend)(struct cpufreq_policy *policy); int (*resume)(struct cpufreq_policy *policy); @@ -775,7 +785,7 @@ ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf); #ifdef CONFIG_CPU_FREQ int cpufreq_boost_trigger_state(int state); -int cpufreq_boost_enabled(void); +bool cpufreq_boost_enabled(void); int cpufreq_enable_boost_support(void); bool policy_has_boost_freq(struct cpufreq_policy *policy); @@ -1154,9 +1164,9 @@ static inline int cpufreq_boost_trigger_state(int state) { return 0; } -static inline int cpufreq_boost_enabled(void) +static inline bool cpufreq_boost_enabled(void) { - return 0; + return false; } static inline int cpufreq_enable_boost_support(void) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 35e78ddb2b37..9316c39260e0 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -27,7 +27,7 @@ * startup callbacks sequentially from CPUHP_OFFLINE + 1 to CPUHP_ONLINE * during a CPU online operation. During a CPU offline operation the * installed teardown callbacks are invoked in the reverse order from - * CPU_ONLINE - 1 down to CPUHP_OFFLINE. + * CPUHP_ONLINE - 1 down to CPUHP_OFFLINE. * * The state space has three sections: PREPARE, STARTING and ONLINE. * @@ -100,7 +100,6 @@ enum cpuhp_state { CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, - CPUHP_PROFILE_PREPARE, CPUHP_X2APIC_PREPARE, CPUHP_SMPCFD_PREPARE, CPUHP_RELAY_PREPARE, @@ -122,6 +121,7 @@ enum cpuhp_state { CPUHP_KVM_PPC_BOOK3S_PREPARE, CPUHP_ZCOMP_PREPARE, CPUHP_TIMERS_PREPARE, + CPUHP_TMIGR_PREPARE, CPUHP_MIPS_SOC_PREPARE, CPUHP_BP_PREPARE_DYN, CPUHP_BP_PREPARE_DYN_END = CPUHP_BP_PREPARE_DYN + 20, @@ -146,6 +146,8 @@ enum cpuhp_state { CPUHP_AP_IRQ_MIPS_GIC_STARTING, CPUHP_AP_IRQ_LOONGARCH_STARTING, CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING, + CPUHP_AP_IRQ_RISCV_IMSIC_STARTING, + CPUHP_AP_IRQ_RISCV_SBI_IPI_STARTING, CPUHP_AP_ARM_MVEBU_COHERENCY, CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING, CPUHP_AP_PERF_X86_STARTING, @@ -170,6 +172,7 @@ enum cpuhp_state { CPUHP_AP_ARMADA_TIMER_STARTING, CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_ARC_TIMER_STARTING, + CPUHP_AP_REALTEK_TIMER_STARTING, CPUHP_AP_RISCV_TIMER_STARTING, CPUHP_AP_CLINT_TIMER_STARTING, CPUHP_AP_CSKY_TIMER_STARTING, diff --git a/include/linux/cpuhplock.h b/include/linux/cpuhplock.h new file mode 100644 index 000000000000..f7aa20f62b87 --- /dev/null +++ b/include/linux/cpuhplock.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * include/linux/cpuhplock.h - CPU hotplug locking + * + * Locking functions for CPU hotplug. + */ +#ifndef _LINUX_CPUHPLOCK_H_ +#define _LINUX_CPUHPLOCK_H_ + +#include <linux/cleanup.h> +#include <linux/errno.h> + +struct device; + +extern int lockdep_is_cpus_held(void); + +#ifdef CONFIG_HOTPLUG_CPU +void cpus_write_lock(void); +void cpus_write_unlock(void); +void cpus_read_lock(void); +void cpus_read_unlock(void); +int cpus_read_trylock(void); +void lockdep_assert_cpus_held(void); +void cpu_hotplug_disable_offlining(void); +void cpu_hotplug_disable(void); +void cpu_hotplug_enable(void); +void clear_tasks_mm_cpumask(int cpu); +int remove_cpu(unsigned int cpu); +int cpu_device_down(struct device *dev); +void smp_shutdown_nonboot_cpus(unsigned int primary_cpu); + +#else /* CONFIG_HOTPLUG_CPU */ + +static inline void cpus_write_lock(void) { } +static inline void cpus_write_unlock(void) { } +static inline void cpus_read_lock(void) { } +static inline void cpus_read_unlock(void) { } +static inline int cpus_read_trylock(void) { return true; } +static inline void lockdep_assert_cpus_held(void) { } +static inline void cpu_hotplug_disable_offlining(void) { } +static inline void cpu_hotplug_disable(void) { } +static inline void cpu_hotplug_enable(void) { } +static inline int remove_cpu(unsigned int cpu) { return -EPERM; } +static inline void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { } +#endif /* !CONFIG_HOTPLUG_CPU */ + +DEFINE_LOCK_GUARD_0(cpus_read_lock, cpus_read_lock(), cpus_read_unlock()) + +#endif /* _LINUX_CPUHPLOCK_H_ */ diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 1c29947db848..53158de44b83 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -9,25 +9,13 @@ */ #include <linux/cleanup.h> #include <linux/kernel.h> -#include <linux/threads.h> #include <linux/bitmap.h> +#include <linux/cpumask_types.h> #include <linux/atomic.h> #include <linux/bug.h> #include <linux/gfp_types.h> #include <linux/numa.h> -/* Don't assign or return these: may not be this big! */ -typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; - -/** - * cpumask_bits - get the bits in a cpumask - * @maskp: the struct cpumask * - * - * You should only assume nr_cpu_ids bits of this mask are valid. This is - * a macro so it's const-correct. - */ -#define cpumask_bits(maskp) ((maskp)->bits) - /** * cpumask_pr_args - printf args to output a cpumask * @maskp: cpumask to be printed @@ -93,6 +81,7 @@ static inline void set_nr_cpu_ids(unsigned int nr) * * cpu_possible_mask- has bit 'cpu' set iff cpu is populatable * cpu_present_mask - has bit 'cpu' set iff cpu is populated + * cpu_enabled_mask - has bit 'cpu' set iff cpu can be brought online * cpu_online_mask - has bit 'cpu' set iff cpu available to scheduler * cpu_active_mask - has bit 'cpu' set iff cpu available to migration * @@ -125,11 +114,13 @@ static inline void set_nr_cpu_ids(unsigned int nr) extern struct cpumask __cpu_possible_mask; extern struct cpumask __cpu_online_mask; +extern struct cpumask __cpu_enabled_mask; extern struct cpumask __cpu_present_mask; extern struct cpumask __cpu_active_mask; extern struct cpumask __cpu_dying_mask; #define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask) #define cpu_online_mask ((const struct cpumask *)&__cpu_online_mask) +#define cpu_enabled_mask ((const struct cpumask *)&__cpu_enabled_mask) #define cpu_present_mask ((const struct cpumask *)&__cpu_present_mask) #define cpu_active_mask ((const struct cpumask *)&__cpu_active_mask) #define cpu_dying_mask ((const struct cpumask *)&__cpu_dying_mask) @@ -188,6 +179,23 @@ unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask } /** + * cpumask_first_and_and - return the first cpu from *srcp1 & *srcp2 & *srcp3 + * @srcp1: the first input + * @srcp2: the second input + * @srcp3: the third input + * + * Return: >= nr_cpu_ids if no cpus set in all. + */ +static inline +unsigned int cpumask_first_and_and(const struct cpumask *srcp1, + const struct cpumask *srcp2, + const struct cpumask *srcp3) +{ + return find_first_and_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), + cpumask_bits(srcp3), small_cpumask_bits); +} + +/** * cpumask_last - get the last CPU in a cpumask * @srcp: - the cpumask pointer * @@ -369,6 +377,16 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta for_each_or_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) /** + * for_each_cpu_from - iterate over CPUs present in @mask, from @cpu to the end of @mask. + * @cpu: the (optionally unsigned) integer iterator + * @mask: the cpumask pointer + * + * After the loop, cpu is >= nr_cpu_ids. + */ +#define for_each_cpu_from(cpu, mask) \ + for_each_set_bit_from(cpu, cpumask_bits(mask), small_cpumask_bits) + +/** * cpumask_any_but - return a "random" in a cpumask, but not this one. * @mask: the cpumask to search * @cpu: the cpu to ignore. @@ -389,6 +407,29 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) } /** + * cpumask_any_and_but - pick a "random" cpu from *mask1 & *mask2, but not this one. + * @mask1: the first input cpumask + * @mask2: the second input cpumask + * @cpu: the cpu to ignore + * + * Returns >= nr_cpu_ids if no cpus set. + */ +static inline +unsigned int cpumask_any_and_but(const struct cpumask *mask1, + const struct cpumask *mask2, + unsigned int cpu) +{ + unsigned int i; + + cpumask_check(cpu); + i = cpumask_first_and(mask1, mask2); + if (i != cpu) + return i; + + return cpumask_next_and(cpu, mask1, mask2); +} + +/** * cpumask_nth - get the Nth cpu in a cpumask * @srcp: the cpumask pointer * @cpu: the Nth cpu to find, starting from 0 @@ -494,6 +535,22 @@ static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) } /** + * cpumask_assign_cpu - assign a cpu in a cpumask + * @cpu: cpu number (< nr_cpu_ids) + * @dstp: the cpumask pointer + * @bool: the value to assign + */ +static __always_inline void cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value) +{ + assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value); +} + +static __always_inline void __cpumask_assign_cpu(int cpu, struct cpumask *dstp, bool value) +{ + __assign_bit(cpumask_check(cpu), cpumask_bits(dstp), value); +} + +/** * cpumask_test_cpu - test for a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer @@ -853,51 +910,10 @@ static inline int cpulist_parse(const char *buf, struct cpumask *dstp) */ static inline unsigned int cpumask_size(void) { - return BITS_TO_LONGS(large_cpumask_bits) * sizeof(long); + return bitmap_size(large_cpumask_bits); } -/* - * cpumask_var_t: struct cpumask for stack usage. - * - * Oh, the wicked games we play! In order to make kernel coding a - * little more difficult, we typedef cpumask_var_t to an array or a - * pointer: doing &mask on an array is a noop, so it still works. - * - * i.e. - * cpumask_var_t tmpmask; - * if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL)) - * return -ENOMEM; - * - * ... use 'tmpmask' like a normal struct cpumask * ... - * - * free_cpumask_var(tmpmask); - * - * - * However, one notable exception is there. alloc_cpumask_var() allocates - * only nr_cpumask_bits bits (in the other hand, real cpumask_t always has - * NR_CPUS bits). Therefore you don't have to dereference cpumask_var_t. - * - * cpumask_var_t tmpmask; - * if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL)) - * return -ENOMEM; - * - * var = *tmpmask; - * - * This code makes NR_CPUS length memcopy and brings to a memory corruption. - * cpumask_copy() provide safe copy functionality. - * - * Note that there is another evil here: If you define a cpumask_var_t - * as a percpu variable then the way to obtain the address of the cpumask - * structure differently influences what this_cpu_* operation needs to be - * used. Please use this_cpu_cpumask_var_t in those cases. The direct use - * of this_cpu_ptr() or this_cpu_read() will lead to failures when the - * other type of cpumask_var_t implementation is configured. - * - * Please also note that __cpumask_var_read_mostly can be used to declare - * a cpumask_var_t variable itself (not its content) as read mostly. - */ #ifdef CONFIG_CPUMASK_OFFSTACK -typedef struct cpumask *cpumask_var_t; #define this_cpu_cpumask_var_ptr(x) this_cpu_read(x) #define __cpumask_var_read_mostly __read_mostly @@ -944,7 +960,6 @@ static inline bool cpumask_available(cpumask_var_t mask) } #else -typedef struct cpumask cpumask_var_t[1]; #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) #define __cpumask_var_read_mostly @@ -1009,6 +1024,7 @@ extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS); #else #define for_each_possible_cpu(cpu) for_each_cpu((cpu), cpu_possible_mask) #define for_each_online_cpu(cpu) for_each_cpu((cpu), cpu_online_mask) +#define for_each_enabled_cpu(cpu) for_each_cpu((cpu), cpu_enabled_mask) #define for_each_present_cpu(cpu) for_each_cpu((cpu), cpu_present_mask) #endif @@ -1017,49 +1033,17 @@ void init_cpu_present(const struct cpumask *src); void init_cpu_possible(const struct cpumask *src); void init_cpu_online(const struct cpumask *src); -static inline void reset_cpu_possible_mask(void) -{ - bitmap_zero(cpumask_bits(&__cpu_possible_mask), NR_CPUS); -} - -static inline void -set_cpu_possible(unsigned int cpu, bool possible) -{ - if (possible) - cpumask_set_cpu(cpu, &__cpu_possible_mask); - else - cpumask_clear_cpu(cpu, &__cpu_possible_mask); -} +#define assign_cpu(cpu, mask, val) \ + assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val)) -static inline void -set_cpu_present(unsigned int cpu, bool present) -{ - if (present) - cpumask_set_cpu(cpu, &__cpu_present_mask); - else - cpumask_clear_cpu(cpu, &__cpu_present_mask); -} +#define set_cpu_possible(cpu, possible) assign_cpu((cpu), &__cpu_possible_mask, (possible)) +#define set_cpu_enabled(cpu, enabled) assign_cpu((cpu), &__cpu_enabled_mask, (enabled)) +#define set_cpu_present(cpu, present) assign_cpu((cpu), &__cpu_present_mask, (present)) +#define set_cpu_active(cpu, active) assign_cpu((cpu), &__cpu_active_mask, (active)) +#define set_cpu_dying(cpu, dying) assign_cpu((cpu), &__cpu_dying_mask, (dying)) void set_cpu_online(unsigned int cpu, bool online); -static inline void -set_cpu_active(unsigned int cpu, bool active) -{ - if (active) - cpumask_set_cpu(cpu, &__cpu_active_mask); - else - cpumask_clear_cpu(cpu, &__cpu_active_mask); -} - -static inline void -set_cpu_dying(unsigned int cpu, bool dying) -{ - if (dying) - cpumask_set_cpu(cpu, &__cpu_dying_mask); - else - cpumask_clear_cpu(cpu, &__cpu_dying_mask); -} - /** * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask * * @bitmap: the bitmap @@ -1112,6 +1096,7 @@ static __always_inline unsigned int num_online_cpus(void) return raw_atomic_read(&__num_online_cpus); } #define num_possible_cpus() cpumask_weight(cpu_possible_mask) +#define num_enabled_cpus() cpumask_weight(cpu_enabled_mask) #define num_present_cpus() cpumask_weight(cpu_present_mask) #define num_active_cpus() cpumask_weight(cpu_active_mask) @@ -1120,6 +1105,11 @@ static inline bool cpu_online(unsigned int cpu) return cpumask_test_cpu(cpu, cpu_online_mask); } +static inline bool cpu_enabled(unsigned int cpu) +{ + return cpumask_test_cpu(cpu, cpu_enabled_mask); +} + static inline bool cpu_possible(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_possible_mask); @@ -1144,6 +1134,7 @@ static inline bool cpu_dying(unsigned int cpu) #define num_online_cpus() 1U #define num_possible_cpus() 1U +#define num_enabled_cpus() 1U #define num_present_cpus() 1U #define num_active_cpus() 1U @@ -1157,6 +1148,11 @@ static inline bool cpu_possible(unsigned int cpu) return cpu == 0; } +static inline bool cpu_enabled(unsigned int cpu) +{ + return cpu == 0; +} + static inline bool cpu_present(unsigned int cpu) { return cpu == 0; diff --git a/include/linux/cpumask_types.h b/include/linux/cpumask_types.h new file mode 100644 index 000000000000..461ed1b6bcdb --- /dev/null +++ b/include/linux/cpumask_types.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_CPUMASK_TYPES_H +#define __LINUX_CPUMASK_TYPES_H + +#include <linux/bitops.h> +#include <linux/threads.h> + +/* Don't assign or return these: may not be this big! */ +typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; + +/** + * cpumask_bits - get the bits in a cpumask + * @maskp: the struct cpumask * + * + * You should only assume nr_cpu_ids bits of this mask are valid. This is + * a macro so it's const-correct. + */ +#define cpumask_bits(maskp) ((maskp)->bits) + +/* + * cpumask_var_t: struct cpumask for stack usage. + * + * Oh, the wicked games we play! In order to make kernel coding a + * little more difficult, we typedef cpumask_var_t to an array or a + * pointer: doing &mask on an array is a noop, so it still works. + * + * i.e. + * cpumask_var_t tmpmask; + * if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL)) + * return -ENOMEM; + * + * ... use 'tmpmask' like a normal struct cpumask * ... + * + * free_cpumask_var(tmpmask); + * + * + * However, one notable exception is there. alloc_cpumask_var() allocates + * only nr_cpumask_bits bits (in the other hand, real cpumask_t always has + * NR_CPUS bits). Therefore you don't have to dereference cpumask_var_t. + * + * cpumask_var_t tmpmask; + * if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL)) + * return -ENOMEM; + * + * var = *tmpmask; + * + * This code makes NR_CPUS length memcopy and brings to a memory corruption. + * cpumask_copy() provide safe copy functionality. + * + * Note that there is another evil here: If you define a cpumask_var_t + * as a percpu variable then the way to obtain the address of the cpumask + * structure differently influences what this_cpu_* operation needs to be + * used. Please use this_cpu_cpumask_var_t in those cases. The direct use + * of this_cpu_ptr() or this_cpu_read() will lead to failures when the + * other type of cpumask_var_t implementation is configured. + * + * Please also note that __cpumask_var_read_mostly can be used to declare + * a cpumask_var_t variable itself (not its content) as read mostly. + */ +#ifdef CONFIG_CPUMASK_OFFSTACK +typedef struct cpumask *cpumask_var_t; +#else +typedef struct cpumask cpumask_var_t[1]; +#endif /* CONFIG_CPUMASK_OFFSTACK */ + +#endif /* __LINUX_CPUMASK_TYPES_H */ diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 0ce6ff0d9c9a..de4cf0ee96f7 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -70,7 +70,6 @@ extern int cpuset_init(void); extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(void); -extern void cpuset_wait_for_hotplug(void); extern void inc_dl_tasks_cs(struct task_struct *task); extern void dec_dl_tasks_cs(struct task_struct *task); extern void cpuset_lock(void); @@ -185,8 +184,6 @@ static inline void cpuset_update_active_cpus(void) partition_sched_domains(1, NULL, NULL); } -static inline void cpuset_wait_for_hotplug(void) { } - static inline void inc_dl_tasks_cs(struct task_struct *task) { } static inline void dec_dl_tasks_cs(struct task_struct *task) { } static inline void cpuset_lock(void) { } diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index d33352c2e386..44305336314e 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -37,17 +37,16 @@ static inline void arch_kexec_unprotect_crashkres(void) { } #ifndef arch_crash_handle_hotplug_event -static inline void arch_crash_handle_hotplug_event(struct kimage *image) { } +static inline void arch_crash_handle_hotplug_event(struct kimage *image, void *arg) { } #endif -int crash_check_update_elfcorehdr(void); +int crash_check_hotplug_support(void); -#ifndef crash_hotplug_cpu_support -static inline int crash_hotplug_cpu_support(void) { return 0; } -#endif - -#ifndef crash_hotplug_memory_support -static inline int crash_hotplug_memory_support(void) { return 0; } +#ifndef arch_crash_hotplug_support +static inline int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags) +{ + return 0; +} #endif #ifndef crash_get_elfcorehdr_size diff --git a/include/linux/crc32.h b/include/linux/crc32.h index 9e8a032c1788..87f788c0d607 100644 --- a/include/linux/crc32.h +++ b/include/linux/crc32.h @@ -9,7 +9,9 @@ #include <linux/bitrev.h> u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len); +u32 __pure crc32_le_base(u32 crc, unsigned char const *p, size_t len); u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len); +u32 __pure crc32_be_base(u32 crc, unsigned char const *p, size_t len); /** * crc32_le_combine - Combine two crc32 check values into one. For two @@ -37,6 +39,7 @@ static inline u32 crc32_le_combine(u32 crc1, u32 crc2, size_t len2) } u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len); +u32 __pure __crc32c_le_base(u32 crc, unsigned char const *p, size_t len); /** * __crc32c_le_combine - Combine two crc32c check values into one. For two diff --git a/include/linux/cxl-event.h b/include/linux/cxl-event.h index 03fa6d50d46f..0bea1afbd747 100644 --- a/include/linux/cxl-event.h +++ b/include/linux/cxl-event.h @@ -3,6 +3,10 @@ #ifndef _LINUX_CXL_EVENT_H #define _LINUX_CXL_EVENT_H +#include <linux/types.h> +#include <linux/uuid.h> +#include <linux/workqueue_types.h> + /* * Common Event Record Format * CXL rev 3.0 section 8.2.9.2.1; Table 8-42 @@ -17,6 +21,21 @@ struct cxl_event_record_hdr { u8 reserved[15]; } __packed; +struct cxl_event_media_hdr { + struct cxl_event_record_hdr hdr; + __le64 phys_addr; + u8 descriptor; + u8 type; + u8 transaction_type; + /* + * The meaning of Validity Flags from bit 2 is + * different across DRAM and General Media records + */ + u8 validity_flags[2]; + u8 channel; + u8 rank; +} __packed; + #define CXL_EVENT_RECORD_DATA_LENGTH 0x50 struct cxl_event_generic { struct cxl_event_record_hdr hdr; @@ -29,14 +48,7 @@ struct cxl_event_generic { */ #define CXL_EVENT_GEN_MED_COMP_ID_SIZE 0x10 struct cxl_event_gen_media { - struct cxl_event_record_hdr hdr; - __le64 phys_addr; - u8 descriptor; - u8 type; - u8 transaction_type; - u8 validity_flags[2]; - u8 channel; - u8 rank; + struct cxl_event_media_hdr media_hdr; u8 device[3]; u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE]; u8 reserved[46]; @@ -48,14 +60,7 @@ struct cxl_event_gen_media { */ #define CXL_EVENT_DER_CORRECTION_MASK_SIZE 0x20 struct cxl_event_dram { - struct cxl_event_record_hdr hdr; - __le64 phys_addr; - u8 descriptor; - u8 type; - u8 transaction_type; - u8 validity_flags[2]; - u8 channel; - u8 rank; + struct cxl_event_media_hdr media_hdr; u8 nibble_mask[3]; u8 bank_group; u8 bank; @@ -96,6 +101,8 @@ union cxl_event { struct cxl_event_gen_media gen_media; struct cxl_event_dram dram; struct cxl_event_mem_module mem_module; + /* dram & gen_media event header */ + struct cxl_event_media_hdr media_hdr; } __packed; /* @@ -140,4 +147,29 @@ struct cxl_cper_event_rec { union cxl_event event; } __packed; +struct cxl_cper_work_data { + enum cxl_event_type event_type; + struct cxl_cper_event_rec rec; +}; + +#ifdef CONFIG_ACPI_APEI_GHES +int cxl_cper_register_work(struct work_struct *work); +int cxl_cper_unregister_work(struct work_struct *work); +int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd); +#else +static inline int cxl_cper_register_work(struct work_struct *work) +{ + return 0; +} + +static inline int cxl_cper_unregister_work(struct work_struct *work) +{ + return 0; +} +static inline int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd) +{ + return 0; +} +#endif + #endif /* _LINUX_CXL_EVENT_H */ diff --git a/include/linux/damon.h b/include/linux/damon.h index 886d07294f4e..27c546bfc6d4 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -105,6 +105,8 @@ struct damon_target { * @DAMOS_NOHUGEPAGE: Call ``madvise()`` for the region with MADV_NOHUGEPAGE. * @DAMOS_LRU_PRIO: Prioritize the region on its LRU lists. * @DAMOS_LRU_DEPRIO: Deprioritize the region on its LRU lists. + * @DAMOS_MIGRATE_HOT: Migrate the regions prioritizing warmer regions. + * @DAMOS_MIGRATE_COLD: Migrate the regions prioritizing colder regions. * @DAMOS_STAT: Do nothing but count the stat. * @NR_DAMOS_ACTIONS: Total number of DAMOS actions * @@ -122,6 +124,8 @@ enum damos_action { DAMOS_NOHUGEPAGE, DAMOS_LRU_PRIO, DAMOS_LRU_DEPRIO, + DAMOS_MIGRATE_HOT, + DAMOS_MIGRATE_COLD, DAMOS_STAT, /* Do nothing but only record the stat */ NR_DAMOS_ACTIONS, }; @@ -297,6 +301,7 @@ struct damos_stat { * enum damos_filter_type - Type of memory for &struct damos_filter * @DAMOS_FILTER_TYPE_ANON: Anonymous pages. * @DAMOS_FILTER_TYPE_MEMCG: Specific memcg's pages. + * @DAMOS_FILTER_TYPE_YOUNG: Recently accessed pages. * @DAMOS_FILTER_TYPE_ADDR: Address range. * @DAMOS_FILTER_TYPE_TARGET: Data Access Monitoring target. * @NR_DAMOS_FILTER_TYPES: Number of filter types. @@ -315,6 +320,7 @@ struct damos_stat { enum damos_filter_type { DAMOS_FILTER_TYPE_ANON, DAMOS_FILTER_TYPE_MEMCG, + DAMOS_FILTER_TYPE_YOUNG, DAMOS_FILTER_TYPE_ADDR, DAMOS_FILTER_TYPE_TARGET, NR_DAMOS_FILTER_TYPES, @@ -372,6 +378,7 @@ struct damos_access_pattern { * @apply_interval_us: The time between applying the @action. * @quota: Control the aggressiveness of this scheme. * @wmarks: Watermarks for automated (in)activation of this scheme. + * @target_nid: Destination node if @action is "migrate_{hot,cold}". * @filters: Additional set of &struct damos_filter for &action. * @stat: Statistics of this scheme. * @list: List head for siblings. @@ -387,6 +394,10 @@ struct damos_access_pattern { * monitoring context are inactive, DAMON stops monitoring either, and just * repeatedly checks the watermarks. * + * @target_nid is used to set the migration target node for migrate_hot or + * migrate_cold actions, which means it's only meaningful when @action is either + * "migrate_hot" or "migrate_cold". + * * Before applying the &action to a memory region, &struct damon_operations * implementation could check pages of the region and skip &action to respect * &filters @@ -408,6 +419,9 @@ struct damos { /* public: */ struct damos_quota quota; struct damos_watermarks wmarks; + union { + int target_nid; + }; struct list_head filters; struct damos_stat stat; struct list_head list; @@ -724,9 +738,11 @@ struct damos *damon_new_scheme(struct damos_access_pattern *pattern, enum damos_action action, unsigned long apply_interval_us, struct damos_quota *quota, - struct damos_watermarks *wmarks); + struct damos_watermarks *wmarks, + int target_nid); void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); void damon_destroy_scheme(struct damos *s); +int damos_commit_quota_goals(struct damos_quota *dst, struct damos_quota *src); struct damon_target *damon_new_target(void); void damon_add_target(struct damon_ctx *ctx, struct damon_target *t); @@ -740,6 +756,7 @@ void damon_destroy_ctx(struct damon_ctx *ctx); int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs); void damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, ssize_t nr_schemes); +int damon_commit_ctx(struct damon_ctx *old_ctx, struct damon_ctx *new_ctx); int damon_nr_running_ctxs(void); bool damon_is_registered_ops(enum damon_ops_id id); int damon_register_ops(struct damon_operations *ops); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index bf53e3894aae..bff956f7b2b9 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -71,7 +71,7 @@ extern const struct qstr dotdot_name; # define DNAME_INLINE_LEN 40 /* 192 bytes */ #else # ifdef CONFIG_SMP -# define DNAME_INLINE_LEN 40 /* 128 bytes */ +# define DNAME_INLINE_LEN 36 /* 128 bytes */ # else # define DNAME_INLINE_LEN 44 /* 128 bytes */ # endif @@ -89,13 +89,18 @@ struct dentry { struct inode *d_inode; /* Where the name belongs to - NULL is * negative */ unsigned char d_iname[DNAME_INLINE_LEN]; /* small names */ + /* --- cacheline 1 boundary (64 bytes) was 32 bytes ago --- */ /* Ref lookup also touches following */ - struct lockref d_lockref; /* per-dentry lock and refcount */ const struct dentry_operations *d_op; struct super_block *d_sb; /* The root of the dentry tree */ unsigned long d_time; /* used by d_revalidate */ void *d_fsdata; /* fs-specific data */ + /* --- cacheline 2 boundary (128 bytes) --- */ + struct lockref d_lockref; /* per-dentry lock and refcount + * keep separate from RCU lookup area if + * possible! + */ union { struct list_head d_lru; /* LRU list */ @@ -278,6 +283,8 @@ static inline unsigned d_count(const struct dentry *dentry) return dentry->d_lockref.count; } +ino_t d_parent_ino(struct dentry *dentry); + /* * helper function for dentry_operations.d_dname() members */ diff --git a/include/linux/dev_printk.h b/include/linux/dev_printk.h index 6bfe70decc9f..ca32b5bb28eb 100644 --- a/include/linux/dev_printk.h +++ b/include/linux/dev_printk.h @@ -130,6 +130,16 @@ void _dev_info(const struct device *dev, const char *fmt, ...) }) /* + * Dummy dev_printk for disabled debugging statements to use whilst maintaining + * gcc's format checking. + */ +#define dev_no_printk(level, dev, fmt, ...) \ + ({ \ + if (0) \ + _dev_printk(level, dev, fmt, ##__VA_ARGS__); \ + }) + +/* * #defines for all the dev_<level> macros to prefix with whatever * possible use of #define dev_fmt(fmt) ... */ @@ -158,10 +168,7 @@ void _dev_info(const struct device *dev, const char *fmt, ...) dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__) #else #define dev_dbg(dev, fmt, ...) \ -({ \ - if (0) \ - dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ -}) + dev_no_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__) #endif #ifdef CONFIG_PRINTK @@ -247,20 +254,14 @@ do { \ } while (0) #else #define dev_dbg_ratelimited(dev, fmt, ...) \ -do { \ - if (0) \ - dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ -} while (0) + dev_no_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__) #endif #ifdef VERBOSE_DEBUG #define dev_vdbg dev_dbg #else #define dev_vdbg(dev, fmt, ...) \ -({ \ - if (0) \ - dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \ -}) + dev_no_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__) #endif /* @@ -276,4 +277,12 @@ do { \ __printf(3, 4) int dev_err_probe(const struct device *dev, int err, const char *fmt, ...); +/* Simple helper for dev_err_probe() when ERR_PTR() is to be returned. */ +#define dev_err_ptr_probe(dev, ___err, fmt, ...) \ + ERR_PTR(dev_err_probe(dev, ___err, fmt, ##__VA_ARGS__)) + +/* Simple helper for dev_err_probe() when ERR_CAST() is to be returned. */ +#define dev_err_cast_probe(dev, ___err_ptr, fmt, ...) \ + ERR_PTR(dev_err_probe(dev, PTR_ERR(___err_ptr), fmt, ##__VA_ARGS__)) + #endif /* _DEVICE_PRINTK_H_ */ diff --git a/include/linux/devcoredump.h b/include/linux/devcoredump.h index c008169ed2c6..377892604ff4 100644 --- a/include/linux/devcoredump.h +++ b/include/linux/devcoredump.h @@ -12,6 +12,9 @@ #include <linux/scatterlist.h> #include <linux/slab.h> +/* if data isn't read by userspace after 5 minutes then delete it */ +#define DEVCD_TIMEOUT (HZ * 60 * 5) + /* * _devcd_free_sgtable - free all the memory of the given scatterlist table * (i.e. both pages and scatterlist instances) @@ -50,19 +53,22 @@ static inline void _devcd_free_sgtable(struct scatterlist *table) kfree(delete_iter); } - #ifdef CONFIG_DEV_COREDUMP void dev_coredumpv(struct device *dev, void *data, size_t datalen, gfp_t gfp); -void dev_coredumpm(struct device *dev, struct module *owner, - void *data, size_t datalen, gfp_t gfp, - ssize_t (*read)(char *buffer, loff_t offset, size_t count, - void *data, size_t datalen), - void (*free)(void *data)); +void dev_coredumpm_timeout(struct device *dev, struct module *owner, + void *data, size_t datalen, gfp_t gfp, + ssize_t (*read)(char *buffer, loff_t offset, + size_t count, void *data, + size_t datalen), + void (*free)(void *data), + unsigned long timeout); void dev_coredumpsg(struct device *dev, struct scatterlist *table, size_t datalen, gfp_t gfp); + +void dev_coredump_put(struct device *dev); #else static inline void dev_coredumpv(struct device *dev, void *data, size_t datalen, gfp_t gfp) @@ -71,11 +77,13 @@ static inline void dev_coredumpv(struct device *dev, void *data, } static inline void -dev_coredumpm(struct device *dev, struct module *owner, - void *data, size_t datalen, gfp_t gfp, - ssize_t (*read)(char *buffer, loff_t offset, size_t count, - void *data, size_t datalen), - void (*free)(void *data)) +dev_coredumpm_timeout(struct device *dev, struct module *owner, + void *data, size_t datalen, gfp_t gfp, + ssize_t (*read)(char *buffer, loff_t offset, + size_t count, void *data, + size_t datalen), + void (*free)(void *data), + unsigned long timeout) { free(data); } @@ -85,6 +93,34 @@ static inline void dev_coredumpsg(struct device *dev, struct scatterlist *table, { _devcd_free_sgtable(table); } +static inline void dev_coredump_put(struct device *dev) +{ +} #endif /* CONFIG_DEV_COREDUMP */ +/** + * dev_coredumpm - create device coredump with read/free methods + * @dev: the struct device for the crashed device + * @owner: the module that contains the read/free functions, use %THIS_MODULE + * @data: data cookie for the @read/@free functions + * @datalen: length of the data + * @gfp: allocation flags + * @read: function to read from the given buffer + * @free: function to free the given buffer + * + * Creates a new device coredump for the given device. If a previous one hasn't + * been read yet, the new coredump is discarded. The data lifetime is determined + * by the device coredump framework and when it is no longer needed the @free + * function will be called to free the data. + */ +static inline void dev_coredumpm(struct device *dev, struct module *owner, + void *data, size_t datalen, gfp_t gfp, + ssize_t (*read)(char *buffer, loff_t offset, size_t count, + void *data, size_t datalen), + void (*free)(void *data)) +{ + dev_coredumpm_timeout(dev, owner, data, datalen, gfp, read, free, + DEVCD_TIMEOUT); +} + #endif /* __DEVCOREDUMP_H */ diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 82b2195efaca..53ca3a913d06 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -180,6 +180,11 @@ int dm_get_device(struct dm_target *ti, const char *path, blk_mode_t mode, void dm_put_device(struct dm_target *ti, struct dm_dev *d); /* + * Helper function for getting devices + */ +int dm_devt_from_path(const char *path, dev_t *dev_p); + +/* * Information about a target type */ @@ -358,22 +363,17 @@ struct dm_target { bool discards_supported:1; /* - * Set if this target requires that discards be split on - * 'max_discard_sectors' boundaries. - */ - bool max_discard_granularity:1; - - /* - * Set if this target requires that secure_erases be split on - * 'max_secure_erase_sectors' boundaries. + * Automatically set by dm-core if this target supports + * REQ_OP_ZONE_RESET_ALL. Otherwise, this operation will be emulated + * using REQ_OP_ZONE_RESET. Target drivers must not set this manually. */ - bool max_secure_erase_granularity:1; + bool zone_reset_all_supported:1; /* - * Set if this target requires that write_zeroes be split on - * 'max_write_zeroes_sectors' boundaries. + * Set if this target requires that discards be split on + * 'max_discard_sectors' boundaries. */ - bool max_write_zeroes_granularity:1; + bool max_discard_granularity:1; /* * Set if we need to limit the number of in-flight bios when swapping. @@ -397,6 +397,27 @@ struct dm_target { * bio_set_dev(). NOTE: ideally a target should _not_ need this. */ bool needs_bio_set_dev:1; + + /* + * Set if the target supports flush optimization. If all the targets in + * a table have flush_bypasses_map set, the dm core will not send + * flushes to the targets via a ->map method. It will iterate over + * dm_table->devices and send flushes to the devices directly. This + * optimization reduces the number of flushes being sent when multiple + * targets in a table use the same underlying device. + * + * This optimization may be enabled on targets that just pass the + * flushes to the underlying devices without performing any other + * actions on the flush request. Currently, dm-linear and dm-stripe + * support it. + */ + bool flush_bypasses_map:1; + + /* + * Set if the target calls bio_integrity_alloc on bios received + * in the map method. + */ + bool mempool_needs_integrity:1; }; void *dm_per_bio_data(struct bio *bio, size_t data_size); diff --git a/include/linux/device.h b/include/linux/device.h index b9f5464f44ed..34eb20f5966f 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -132,6 +132,8 @@ ssize_t device_show_bool(struct device *dev, struct device_attribute *attr, char *buf); ssize_t device_store_bool(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); +ssize_t device_show_string(struct device *dev, struct device_attribute *attr, + char *buf); /** * DEVICE_ATTR - Define a device attribute. @@ -251,6 +253,19 @@ ssize_t device_store_bool(struct device *dev, struct device_attribute *attr, struct dev_ext_attribute dev_attr_##_name = \ { __ATTR(_name, _mode, device_show_bool, device_store_bool), &(_var) } +/** + * DEVICE_STRING_ATTR_RO - Define a device attribute backed by a r/o string. + * @_name: Attribute name. + * @_mode: File mode. + * @_var: Identifier of string. + * + * Like DEVICE_ULONG_ATTR(), but @_var is a string. Because the length of the + * string allocation is unknown, the attribute must be read-only. + */ +#define DEVICE_STRING_ATTR_RO(_name, _mode, _var) \ + struct dev_ext_attribute dev_attr_##_name = \ + { __ATTR(_name, (_mode) & ~0222, device_show_string, NULL), (_var) } + #define DEVICE_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) \ struct device_attribute dev_attr_##_name = \ __ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) @@ -691,6 +706,7 @@ struct device_physical_location { * and optionall (if the coherent mask is large enough) also * for dma allocations. This flag is managed by the dma ops * instance from ->dma_supported. + * @dma_skip_sync: DMA sync operations can be skipped for coherent buffers. * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information @@ -803,6 +819,9 @@ struct device { #ifdef CONFIG_DMA_OPS_BYPASS bool dma_ops_bypass : 1; #endif +#ifdef CONFIG_DMA_NEED_SYNC + bool dma_skip_sync:1; +#endif }; /** @@ -1012,13 +1031,6 @@ static inline void device_lock_assert(struct device *dev) lockdep_assert_held(&dev->mutex); } -static inline struct device_node *dev_of_node(struct device *dev) -{ - if (!IS_ENABLED(CONFIG_OF) || !dev) - return NULL; - return dev->of_node; -} - static inline bool dev_has_sync_state(struct device *dev) { if (!dev) @@ -1125,10 +1137,18 @@ void unlock_device_hotplug(void); int lock_device_hotplug_sysfs(void); int device_offline(struct device *dev); int device_online(struct device *dev); + void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode); -void device_set_of_node_from_dev(struct device *dev, const struct device *dev2); void device_set_node(struct device *dev, struct fwnode_handle *fwnode); +void device_set_of_node_from_dev(struct device *dev, const struct device *dev2); + +static inline struct device_node *dev_of_node(struct device *dev) +{ + if (!IS_ENABLED(CONFIG_OF) || !dev) + return NULL; + return dev->of_node; +} static inline int dev_num_vf(struct device *dev) { @@ -1157,12 +1177,12 @@ static inline void *dev_get_platdata(const struct device *dev) * Manual binding of a device to driver. See drivers/base/bus.c * for information on use. */ -int __must_check device_driver_attach(struct device_driver *drv, +int __must_check device_driver_attach(const struct device_driver *drv, struct device *dev); int __must_check device_bind_driver(struct device *dev); void device_release_driver(struct device *dev); int __must_check device_attach(struct device *dev); -int __must_check driver_attach(struct device_driver *drv); +int __must_check driver_attach(const struct device_driver *drv); void device_initial_probe(struct device *dev); int __must_check device_reprobe(struct device *dev); @@ -1201,23 +1221,10 @@ static inline void device_remove_group(struct device *dev, return device_remove_groups(dev, groups); } -int __must_check devm_device_add_groups(struct device *dev, - const struct attribute_group **groups); int __must_check devm_device_add_group(struct device *dev, const struct attribute_group *grp); /* - * Platform "fixup" functions - allow the platform to have their say - * about devices and actions that the general device layer doesn't - * know about. - */ -/* Notify platform of device discovery */ -extern int (*platform_notify)(struct device *dev); - -extern int (*platform_notify_remove)(struct device *dev); - - -/* * get_device - atomically increment the reference count for the device. * */ diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 5ef4ec1c36c3..807831d6bf0f 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -81,7 +81,7 @@ struct bus_type { const struct attribute_group **dev_groups; const struct attribute_group **drv_groups; - int (*match)(struct device *dev, struct device_driver *drv); + int (*match)(struct device *dev, const struct device_driver *drv); int (*uevent)(const struct device *dev, struct kobj_uevent_env *env); int (*probe)(struct device *dev); void (*sync_state)(struct device *dev); diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index 7738f458995f..1fc8b68786de 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -146,16 +146,16 @@ struct driver_attribute { #define DRIVER_ATTR_WO(_name) \ struct driver_attribute driver_attr_##_name = __ATTR_WO(_name) -int __must_check driver_create_file(struct device_driver *driver, +int __must_check driver_create_file(const struct device_driver *driver, const struct driver_attribute *attr); -void driver_remove_file(struct device_driver *driver, +void driver_remove_file(const 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); 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 *driver_find_device(const struct device_driver *drv, struct device *start, const void *data, int (*match)(struct device *dev, const void *data)); @@ -165,7 +165,7 @@ struct device *driver_find_device(struct device_driver *drv, * @drv: the driver we're iterating * @name: name of the device to match */ -static inline struct device *driver_find_device_by_name(struct device_driver *drv, +static inline struct device *driver_find_device_by_name(const struct device_driver *drv, const char *name) { return driver_find_device(drv, NULL, name, device_match_name); @@ -178,7 +178,7 @@ static inline struct device *driver_find_device_by_name(struct device_driver *dr * @np: of_node pointer to match. */ static inline struct device * -driver_find_device_by_of_node(struct device_driver *drv, +driver_find_device_by_of_node(const struct device_driver *drv, const struct device_node *np) { return driver_find_device(drv, NULL, np, device_match_of_node); @@ -203,13 +203,13 @@ driver_find_device_by_fwnode(struct device_driver *drv, * @drv: the driver we're iterating * @devt: devt pointer to match. */ -static inline struct device *driver_find_device_by_devt(struct device_driver *drv, +static inline struct device *driver_find_device_by_devt(const struct device_driver *drv, dev_t devt) { return driver_find_device(drv, NULL, &devt, device_match_devt); } -static inline struct device *driver_find_next_device(struct device_driver *drv, +static inline struct device *driver_find_next_device(const struct device_driver *drv, struct device *start) { return driver_find_device(drv, start, NULL, device_match_any); @@ -223,14 +223,14 @@ static inline struct device *driver_find_next_device(struct device_driver *drv, * @adev: ACPI_COMPANION device to match. */ static inline struct device * -driver_find_device_by_acpi_dev(struct device_driver *drv, +driver_find_device_by_acpi_dev(const struct device_driver *drv, const struct acpi_device *adev) { return driver_find_device(drv, NULL, adev, device_match_acpi_dev); } #else static inline struct device * -driver_find_device_by_acpi_dev(struct device_driver *drv, const void *adev) +driver_find_device_by_acpi_dev(const struct device_driver *drv, const void *adev) { return NULL; } diff --git a/include/linux/devm-helpers.h b/include/linux/devm-helpers.h index 74891802200d..708ca9131402 100644 --- a/include/linux/devm-helpers.h +++ b/include/linux/devm-helpers.h @@ -41,7 +41,7 @@ static inline void devm_delayed_work_drop(void *res) * detached. A few drivers need delayed work which must be cancelled before * driver is detached to avoid accessing removed resources. * devm_delayed_work_autocancel() can be used to omit the explicit - * cancelleation when driver is detached. + * cancellation when driver is detached. */ static inline int devm_delayed_work_autocancel(struct device *dev, struct delayed_work *w, @@ -66,7 +66,7 @@ static inline void devm_work_drop(void *res) * A few drivers need to queue work which must be cancelled before driver * is detached to avoid accessing removed resources. * devm_work_autocancel() can be used to omit the explicit - * cancelleation when driver is detached. + * cancellation when driver is detached. */ static inline int devm_work_autocancel(struct device *dev, struct work_struct *w, diff --git a/include/linux/dfl.h b/include/linux/dfl.h index 0a7a00a0ee7f..1f02db0c1897 100644 --- a/include/linux/dfl.h +++ b/include/linux/dfl.h @@ -71,7 +71,7 @@ struct dfl_driver { }; #define to_dfl_dev(d) container_of(d, struct dfl_device, dev) -#define to_dfl_drv(d) container_of(d, struct dfl_driver, drv) +#define to_dfl_drv(d) container_of_const(d, struct dfl_driver, drv) /* * use a macro to avoid include chaining to get THIS_MODULE. diff --git a/include/linux/dim.h b/include/linux/dim.h index f343bc9aa2ec..1b581ff25a15 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -10,6 +10,15 @@ #include <linux/types.h> #include <linux/workqueue.h> +struct net_device; + +/* Number of DIM profiles and period mode. */ +#define NET_DIM_PARAMS_NUM_PROFILES 5 +#define NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE 256 +#define NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE 128 +#define NET_DIM_DEF_PROFILE_CQE 1 +#define NET_DIM_DEF_PROFILE_EQE 1 + /* * Number of events between DIM iterations. * Causes a moderation of the algorithm run. @@ -38,12 +47,45 @@ * @pkts: CQ packet counter suggestion (by DIM) * @comps: Completion counter * @cq_period_mode: CQ period count mode (from CQE/EQE) + * @rcu: for asynchronous kfree_rcu */ struct dim_cq_moder { u16 usec; u16 pkts; u16 comps; u8 cq_period_mode; + struct rcu_head rcu; +}; + +#define DIM_PROFILE_RX BIT(0) /* support rx profile modification */ +#define DIM_PROFILE_TX BIT(1) /* support tx profile modification */ + +#define DIM_COALESCE_USEC BIT(0) /* support usec field modification */ +#define DIM_COALESCE_PKTS BIT(1) /* support pkts field modification */ +#define DIM_COALESCE_COMPS BIT(2) /* support comps field modification */ + +/** + * struct dim_irq_moder - Structure for irq moderation information. + * Used to collect irq moderation related information. + * + * @profile_flags: DIM_PROFILE_* + * @coal_flags: DIM_COALESCE_* for Rx and Tx + * @dim_rx_mode: Rx DIM period count mode: CQE or EQE + * @dim_tx_mode: Tx DIM period count mode: CQE or EQE + * @rx_profile: DIM profile list for Rx + * @tx_profile: DIM profile list for Tx + * @rx_dim_work: Rx DIM worker scheduled by net_dim() + * @tx_dim_work: Tx DIM worker scheduled by net_dim() + */ +struct dim_irq_moder { + u8 profile_flags; + u8 coal_flags; + u8 dim_rx_mode; + u8 dim_tx_mode; + struct dim_cq_moder __rcu *rx_profile; + struct dim_cq_moder __rcu *tx_profile; + void (*rx_dim_work)(struct work_struct *work); + void (*tx_dim_work)(struct work_struct *work); }; /** @@ -192,6 +234,77 @@ enum dim_step_result { }; /** + * net_dim_init_irq_moder - collect information to initialize irq moderation + * @dev: target network device + * @profile_flags: Rx or Tx profile modification capability + * @coal_flags: irq moderation params flags + * @rx_mode: CQ period mode for Rx + * @tx_mode: CQ period mode for Tx + * @rx_dim_work: Rx worker called after dim decision + * @tx_dim_work: Tx worker called after dim decision + * + * Return: 0 on success or a negative error code. + */ +int net_dim_init_irq_moder(struct net_device *dev, u8 profile_flags, + u8 coal_flags, u8 rx_mode, u8 tx_mode, + void (*rx_dim_work)(struct work_struct *work), + void (*tx_dim_work)(struct work_struct *work)); + +/** + * net_dim_free_irq_moder - free fields for irq moderation + * @dev: target network device + */ +void net_dim_free_irq_moder(struct net_device *dev); + +/** + * net_dim_setting - initialize DIM's cq mode and schedule worker + * @dev: target network device + * @dim: DIM context + * @is_tx: true indicates the tx direction, false indicates the rx direction + */ +void net_dim_setting(struct net_device *dev, struct dim *dim, bool is_tx); + +/** + * net_dim_work_cancel - synchronously cancel dim's worker + * @dim: DIM context + */ +void net_dim_work_cancel(struct dim *dim); + +/** + * net_dim_get_rx_irq_moder - get DIM rx results based on profile_ix + * @dev: target network device + * @dim: DIM context + * + * Return: DIM irq moderation + */ +struct dim_cq_moder +net_dim_get_rx_irq_moder(struct net_device *dev, struct dim *dim); + +/** + * net_dim_get_tx_irq_moder - get DIM tx results based on profile_ix + * @dev: target network device + * @dim: DIM context + * + * Return: DIM irq moderation + */ +struct dim_cq_moder +net_dim_get_tx_irq_moder(struct net_device *dev, struct dim *dim); + +/** + * net_dim_set_rx_mode - set DIM rx cq mode + * @dev: target network device + * @rx_mode: target rx cq mode + */ +void net_dim_set_rx_mode(struct net_device *dev, u8 rx_mode); + +/** + * net_dim_set_tx_mode - set DIM tx cq mode + * @dev: target network device + * @tx_mode: target tx cq mode + */ +void net_dim_set_tx_mode(struct net_device *dev, u8 tx_mode); + +/** * dim_on_top - check if current state is a good place to stop (top location) * @dim: DIM context * diff --git a/include/linux/dio.h b/include/linux/dio.h index 2b5923909f96..464331c4c4a7 100644 --- a/include/linux/dio.h +++ b/include/linux/dio.h @@ -93,7 +93,7 @@ struct dio_driver { struct device_driver driver; }; -#define to_dio_driver(drv) container_of(drv, struct dio_driver, driver) +#define to_dio_driver(drv) container_of_const(drv, struct dio_driver, driver) /* DIO/DIO-II boards all have the following 8bit registers. * These are offsets from the base of the device. diff --git a/include/linux/dlm.h b/include/linux/dlm.h index c58c4f790c04..bacda9898f2b 100644 --- a/include/linux/dlm.h +++ b/include/linux/dlm.h @@ -35,6 +35,9 @@ struct dlm_lockspace_ops { int num_slots, int our_slot, uint32_t generation); }; +/* only relevant for kernel lockspaces, will be removed in future */ +#define DLM_LSFL_SOFTIRQ __DLM_LSFL_RESERVED0 + /* * dlm_new_lockspace * @@ -55,6 +58,11 @@ struct dlm_lockspace_ops { * used to select the directory node. Must be the same on all nodes. * DLM_LSFL_NEWEXCL * dlm_new_lockspace() should return -EEXIST if the lockspace exists. + * DLM_LSFL_SOFTIRQ + * dlm request callbacks (ast, bast) are softirq safe. Flag should be + * preferred by users. Will be default in some future. If set the + * strongest context for ast, bast callback is softirq as it avoids + * an additional context switch. * * lvblen: length of lvb in bytes. Must be multiple of 8. * dlm_new_lockspace() returns an error if this does not match @@ -121,7 +129,14 @@ int dlm_release_lockspace(dlm_lockspace_t *lockspace, int force); * call. * * AST routines should not block (at least not for long), but may make - * any locking calls they please. + * any locking calls they please. If DLM_LSFL_SOFTIRQ for kernel + * users of dlm_new_lockspace() is passed the ast and bast callbacks + * can be processed in softirq context. Also some of the callback + * contexts are in the same context as the DLM lock request API, users + * must not hold locks while calling dlm lock request API and trying + * to acquire this lock in the callback again, this will end in a + * lock recursion. For newer implementation the DLM_LSFL_SOFTIRQ + * should be used. */ int dlm_lock(dlm_lockspace_t *lockspace, diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 8ff4add71f88..36216d28d8bd 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -370,8 +370,10 @@ struct dma_buf { */ struct module *owner; +#if IS_ENABLED(CONFIG_DEBUG_FS) /** @list_node: node for dma_buf accounting and debugging. */ struct list_head list_node; +#endif /** @priv: exporter specific private data for this buffer object. */ void *priv; diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 3eb3589ff43e..edbe13d00776 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -54,6 +54,24 @@ static inline phys_addr_t translate_dma_to_phys(struct device *dev, return (phys_addr_t)-1; } +static inline dma_addr_t dma_range_map_min(const struct bus_dma_region *map) +{ + dma_addr_t ret = (dma_addr_t)U64_MAX; + + for (; map->size; map++) + ret = min(ret, map->dma_start); + return ret; +} + +static inline dma_addr_t dma_range_map_max(const struct bus_dma_region *map) +{ + dma_addr_t ret = 0; + + for (; map->size; map++) + ret = max(ret, map->dma_start + map->size - 1); + return ret; +} + #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include <asm/dma-direct.h> #ifndef phys_to_dma_unencrypted diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h index ec7f25def392..29c5650c1038 100644 --- a/include/linux/dma-fence-array.h +++ b/include/linux/dma-fence-array.h @@ -33,6 +33,7 @@ struct dma_fence_array_cb { * @num_pending: fences in the array still pending * @fences: array of the fences * @work: internal irq_work function + * @callbacks: array of callback helpers */ struct dma_fence_array { struct dma_fence base; @@ -43,6 +44,8 @@ struct dma_fence_array { struct dma_fence **fences; struct irq_work work; + + struct dma_fence_array_cb callbacks[] __counted_by(num_fences); }; /** diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h index 4bdf0b96da28..68c3c1e41014 100644 --- a/include/linux/dma-fence-chain.h +++ b/include/linux/dma-fence-chain.h @@ -85,11 +85,13 @@ dma_fence_chain_contained(struct dma_fence *fence) * dma_fence_chain_alloc * * Returns a new struct dma_fence_chain object or NULL on failure. + * + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). The typecast is + * intentional to enforce typesafety. */ -static inline struct dma_fence_chain *dma_fence_chain_alloc(void) -{ - return kmalloc(sizeof(struct dma_fence_chain), GFP_KERNEL); -}; +#define dma_fence_chain_alloc() \ + ((struct dma_fence_chain *)kmalloc(sizeof(struct dma_fence_chain), GFP_KERNEL)) /** * dma_fence_chain_free diff --git a/include/linux/dma-heap.h b/include/linux/dma-heap.h index 0c05561cad6e..064bad725061 100644 --- a/include/linux/dma-heap.h +++ b/include/linux/dma-heap.h @@ -23,8 +23,8 @@ struct dma_heap; struct dma_heap_ops { struct dma_buf *(*allocate)(struct dma_heap *heap, unsigned long len, - unsigned long fd_flags, - unsigned long heap_flags); + u32 fd_flags, + u64 heap_flags); }; /** diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h index 4abc60f04209..02a1c825896b 100644 --- a/include/linux/dma-map-ops.h +++ b/include/linux/dma-map-ops.h @@ -18,8 +18,11 @@ struct iommu_ops; * * DMA_F_PCI_P2PDMA_SUPPORTED: Indicates the dma_map_ops implementation can * handle PCI P2PDMA pages in the map_sg/unmap_sg operation. + * DMA_F_CAN_SKIP_SYNC: DMA sync operations can be skipped if the device is + * coherent and it's not an SWIOTLB buffer. */ #define DMA_F_PCI_P2PDMA_SUPPORTED (1 << 0) +#define DMA_F_CAN_SKIP_SYNC (1 << 1) struct dma_map_ops { unsigned int flags; @@ -29,7 +32,7 @@ struct dma_map_ops { unsigned long attrs); void (*free)(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle, unsigned long attrs); - struct page *(*alloc_pages)(struct device *dev, size_t size, + struct page *(*alloc_pages_op)(struct device *dev, size_t size, dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); void (*free_pages)(struct device *dev, size_t size, struct page *vaddr, @@ -273,6 +276,15 @@ static inline bool dev_is_dma_coherent(struct device *dev) } #endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */ +static inline void dma_reset_need_sync(struct device *dev) +{ +#ifdef CONFIG_DMA_NEED_SYNC + /* Reset it only once so that the function can be called on hotpath */ + if (unlikely(dev->dma_skip_sync)) + dev->dma_skip_sync = false; +#endif +} + /* * Check whether potential kmalloc() buffers are safe for non-coherent DMA. */ @@ -426,11 +438,9 @@ bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg, #endif #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS -void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - bool coherent); +void arch_setup_dma_ops(struct device *dev, bool coherent); #else -static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base, - u64 size, bool coherent) +static inline void arch_setup_dma_ops(struct device *dev, bool coherent) { } #endif /* CONFIG_ARCH_HAS_SETUP_DMA_OPS */ diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 4a658de44ee9..f693aafe221f 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -117,14 +117,6 @@ dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr, size_t size, enum dma_data_direction dir, unsigned long attrs); void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs); -void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, - enum dma_data_direction dir); -void dma_sync_single_for_device(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir); -void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, - int nelems, enum dma_data_direction dir); -void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, - int nelems, enum dma_data_direction dir); void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs); void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr, @@ -147,7 +139,6 @@ u64 dma_get_required_mask(struct device *dev); bool dma_addressing_limited(struct device *dev); size_t dma_max_mapping_size(struct device *dev); size_t dma_opt_mapping_size(struct device *dev); -bool dma_need_sync(struct device *dev, dma_addr_t dma_addr); unsigned long dma_get_merge_boundary(struct device *dev); struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size, enum dma_data_direction dir, gfp_t gfp, unsigned long attrs); @@ -195,22 +186,6 @@ static inline void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir, unsigned long attrs) { } -static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir) -{ -} -static inline void dma_sync_single_for_device(struct device *dev, - dma_addr_t addr, size_t size, enum dma_data_direction dir) -{ -} -static inline void dma_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sg, int nelems, enum dma_data_direction dir) -{ -} -static inline void dma_sync_sg_for_device(struct device *dev, - struct scatterlist *sg, int nelems, enum dma_data_direction dir) -{ -} static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) { return -ENOMEM; @@ -277,10 +252,6 @@ static inline size_t dma_opt_mapping_size(struct device *dev) { return 0; } -static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) -{ - return false; -} static inline unsigned long dma_get_merge_boundary(struct device *dev) { return 0; @@ -310,6 +281,82 @@ static inline int dma_mmap_noncontiguous(struct device *dev, } #endif /* CONFIG_HAS_DMA */ +#if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC) +void __dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size, + enum dma_data_direction dir); +void __dma_sync_single_for_device(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir); +void __dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, + int nelems, enum dma_data_direction dir); +void __dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, + int nelems, enum dma_data_direction dir); +bool __dma_need_sync(struct device *dev, dma_addr_t dma_addr); + +static inline bool dma_dev_need_sync(const struct device *dev) +{ + /* Always call DMA sync operations when debugging is enabled */ + return !dev->dma_skip_sync || IS_ENABLED(CONFIG_DMA_API_DEBUG); +} + +static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ + if (dma_dev_need_sync(dev)) + __dma_sync_single_for_cpu(dev, addr, size, dir); +} + +static inline void dma_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ + if (dma_dev_need_sync(dev)) + __dma_sync_single_for_device(dev, addr, size, dir); +} + +static inline void dma_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sg, int nelems, enum dma_data_direction dir) +{ + if (dma_dev_need_sync(dev)) + __dma_sync_sg_for_cpu(dev, sg, nelems, dir); +} + +static inline void dma_sync_sg_for_device(struct device *dev, + struct scatterlist *sg, int nelems, enum dma_data_direction dir) +{ + if (dma_dev_need_sync(dev)) + __dma_sync_sg_for_device(dev, sg, nelems, dir); +} + +static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + return dma_dev_need_sync(dev) ? __dma_need_sync(dev, dma_addr) : false; +} +#else /* !CONFIG_HAS_DMA || !CONFIG_DMA_NEED_SYNC */ +static inline bool dma_dev_need_sync(const struct device *dev) +{ + return false; +} +static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir) +{ +} +static inline void dma_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ +} +static inline void dma_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sg, int nelems, enum dma_data_direction dir) +{ +} +static inline void dma_sync_sg_for_device(struct device *dev, + struct scatterlist *sg, int nelems, enum dma_data_direction dir) +{ +} +static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr) +{ + return false; +} +#endif /* !CONFIG_HAS_DMA || !CONFIG_DMA_NEED_SYNC */ + struct page *dma_alloc_pages(struct device *dev, size_t size, dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp); void dma_free_pages(struct device *dev, size_t size, struct page *page, diff --git a/include/linux/dma/imx-dma.h b/include/linux/dma/imx-dma.h index cfec5f946e23..76a8de9ae151 100644 --- a/include/linux/dma/imx-dma.h +++ b/include/linux/dma/imx-dma.h @@ -41,6 +41,7 @@ enum sdma_peripheral_type { IMX_DMATYPE_SAI, /* SAI */ IMX_DMATYPE_MULTI_SAI, /* MULTI FIFOs For Audio */ IMX_DMATYPE_HDMI, /* HDMI Audio */ + IMX_DMATYPE_I2C, /* I2C */ }; enum imx_dma_prio { diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 752dbde4cec1..b137fdb56093 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -161,6 +161,16 @@ struct dma_interleaved_template { }; /** + * struct dma_vec - DMA vector + * @addr: Bus address of the start of the vector + * @len: Length in bytes of the DMA vector + */ +struct dma_vec { + dma_addr_t addr; + size_t len; +}; + +/** * enum dma_ctrl_flags - DMA flags to augment operation preparation, * control completion, and communicate status. * @DMA_PREP_INTERRUPT - trigger an interrupt (callback) upon completion of @@ -910,6 +920,10 @@ struct dma_device { struct dma_async_tx_descriptor *(*device_prep_dma_interrupt)( struct dma_chan *chan, unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_peripheral_dma_vec)( + struct dma_chan *chan, const struct dma_vec *vecs, + size_t nents, enum dma_transfer_direction direction, + unsigned long flags); struct dma_async_tx_descriptor *(*device_prep_slave_sg)( struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len, enum dma_transfer_direction direction, @@ -973,6 +987,25 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_single( dir, flags, NULL); } +/** + * dmaengine_prep_peripheral_dma_vec() - Prepare a DMA scatter-gather descriptor + * @chan: The channel to be used for this descriptor + * @vecs: The array of DMA vectors that should be transferred + * @nents: The number of DMA vectors in the array + * @dir: Specifies the direction of the data transfer + * @flags: DMA engine flags + */ +static inline struct dma_async_tx_descriptor *dmaengine_prep_peripheral_dma_vec( + struct dma_chan *chan, const struct dma_vec *vecs, size_t nents, + enum dma_transfer_direction dir, unsigned long flags) +{ + if (!chan || !chan->device || !chan->device->device_prep_peripheral_dma_vec) + return NULL; + + return chan->device->device_prep_peripheral_dma_vec(chan, vecs, nents, + dir, flags); +} + static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_sg( struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len, enum dma_transfer_direction dir, unsigned long flags) @@ -1575,7 +1608,8 @@ int dma_async_device_register(struct dma_device *device); int dmaenginem_async_device_register(struct dma_device *device); void dma_async_device_unregister(struct dma_device *device); int dma_async_device_channel_register(struct dma_device *device, - struct dma_chan *chan); + struct dma_chan *chan, + const char *name); void dma_async_device_channel_unregister(struct dma_device *device, struct dma_chan *chan); void dma_run_dependencies(struct dma_async_tx_descriptor *tx); diff --git a/include/linux/dmar.h b/include/linux/dmar.h index e34b601b71fd..499bb2c63483 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -117,7 +117,7 @@ extern int dmar_remove_dev_scope(struct dmar_pci_notify_info *info, int count); /* Intel IOMMU detection */ void detect_intel_iommu(void); -extern int enable_drhd_fault_handling(void); +extern int enable_drhd_fault_handling(unsigned int cpu); extern int dmar_device_add(acpi_handle handle); extern int dmar_device_remove(acpi_handle handle); diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index f3664ee12170..d13aabdeb4b2 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -8,12 +8,18 @@ #include <net/dsa.h> #include <linux/types.h> +/* VBID is limited to three bits only and zero is reserved. + * Only 7 bridges can be enumerated. + */ +#define DSA_TAG_8021Q_MAX_NUM_BRIDGES 7 + int dsa_tag_8021q_register(struct dsa_switch *ds, __be16 proto); void dsa_tag_8021q_unregister(struct dsa_switch *ds); int dsa_tag_8021q_bridge_join(struct dsa_switch *ds, int port, - struct dsa_bridge bridge); + struct dsa_bridge bridge, bool *tx_fwd_offload, + struct netlink_ext_ack *extack); void dsa_tag_8021q_bridge_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge); diff --git a/include/linux/dsa/lan9303.h b/include/linux/dsa/lan9303.h index b4f22112ba75..3ce7cbcc37a3 100644 --- a/include/linux/dsa/lan9303.h +++ b/include/linux/dsa/lan9303.h @@ -5,8 +5,8 @@ struct lan9303; struct lan9303_phy_ops { /* PHY 1 and 2 access*/ - int (*phy_read)(struct lan9303 *chip, int port, int regnum); - int (*phy_write)(struct lan9303 *chip, int port, + int (*phy_read)(struct lan9303 *chip, int addr, int regnum); + int (*phy_write)(struct lan9303 *chip, int addr, int regnum, u16 val); }; diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 4fcbf4d4fd0a..ff44ec346162 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -305,9 +305,9 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor, #define DYNAMIC_DEBUG_BRANCH(descriptor) false #define dynamic_pr_debug(fmt, ...) \ - do { if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); } while (0) + no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #define dynamic_dev_dbg(dev, fmt, ...) \ - do { if (0) dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); } while (0) + dev_no_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__) #define dynamic_hex_dump(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) \ do { if (0) \ diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h index 5693a4be0d9a..281298e77a15 100644 --- a/include/linux/dynamic_queue_limits.h +++ b/include/linux/dynamic_queue_limits.h @@ -50,6 +50,9 @@ struct dql { unsigned int adj_limit; /* limit + num_completed */ unsigned int last_obj_cnt; /* Count at last queuing */ + /* Stall threshold (in jiffies), defined by user */ + unsigned short stall_thrs; + unsigned long history_head; /* top 58 bits of jiffies */ /* stall entries, a bit per entry */ unsigned long history[DQL_HIST_LEN]; @@ -71,8 +74,6 @@ struct dql { unsigned int min_limit; /* Minimum limit */ unsigned int slack_hold_time; /* Time to measure slack */ - /* Stall threshold (in jiffies), defined by user */ - unsigned short stall_thrs; /* Longest stall detected, reported to user */ unsigned short stall_max; unsigned long last_reap; /* Last reap (in jiffies) */ @@ -83,27 +84,11 @@ struct dql { #define DQL_MAX_OBJECT (UINT_MAX / 16) #define DQL_MAX_LIMIT ((UINT_MAX / 2) - DQL_MAX_OBJECT) -/* - * Record number of objects queued. Assumes that caller has already checked - * availability in the queue with dql_avail. - */ -static inline void dql_queued(struct dql *dql, unsigned int count) +/* Populate the bitmap to be processed later in dql_check_stall() */ +static inline void dql_queue_stall(struct dql *dql) { unsigned long map, now, now_hi, i; - BUG_ON(count > DQL_MAX_OBJECT); - - dql->last_obj_cnt = count; - - /* We want to force a write first, so that cpu do not attempt - * to get cache line containing last_obj_cnt, num_queued, adj_limit - * in Shared state, but directly does a Request For Ownership - * It is only a hint, we use barrier() only. - */ - barrier(); - - dql->num_queued += count; - now = jiffies; now_hi = now / BITS_PER_LONG; @@ -133,6 +118,31 @@ static inline void dql_queued(struct dql *dql, unsigned int count) WRITE_ONCE(DQL_HIST_ENT(dql, now_hi), map | BIT_MASK(now)); } +/* + * Record number of objects queued. Assumes that caller has already checked + * availability in the queue with dql_avail. + */ +static inline void dql_queued(struct dql *dql, unsigned int count) +{ + if (WARN_ON_ONCE(count > DQL_MAX_OBJECT)) + return; + + dql->last_obj_cnt = count; + + /* We want to force a write first, so that cpu do not attempt + * to get cache line containing last_obj_cnt, num_queued, adj_limit + * in Shared state, but directly does a Request For Ownership + * It is only a hint, we use barrier() only. + */ + barrier(); + + dql->num_queued += count; + + /* Only populate stall information if the threshold is set */ + if (READ_ONCE(dql->stall_thrs)) + dql_queue_stall(dql); +} + /* Returns how many objects can be queued, < 0 indicates over limit. */ static inline int dql_avail(const struct dql *dql) { diff --git a/include/linux/eeprom_93xx46.h b/include/linux/eeprom_93xx46.h deleted file mode 100644 index 34c2175e6a1e..000000000000 --- a/include/linux/eeprom_93xx46.h +++ /dev/null @@ -1,32 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Module: eeprom_93xx46 - * platform description for 93xx46 EEPROMs. - */ -#include <linux/gpio/consumer.h> - -struct eeprom_93xx46_platform_data { - unsigned char flags; -#define EE_ADDR8 0x01 /* 8 bit addr. cfg */ -#define EE_ADDR16 0x02 /* 16 bit addr. cfg */ -#define EE_READONLY 0x08 /* forbid writing */ -#define EE_SIZE1K 0x10 /* 1 kb of data, that is a 93xx46 */ -#define EE_SIZE2K 0x20 /* 2 kb of data, that is a 93xx56 */ -#define EE_SIZE4K 0x40 /* 4 kb of data, that is a 93xx66 */ - - unsigned int quirks; -/* Single word read transfers only; no sequential read. */ -#define EEPROM_93XX46_QUIRK_SINGLE_WORD_READ (1 << 0) -/* Instructions such as EWEN are (addrlen + 2) in length. */ -#define EEPROM_93XX46_QUIRK_INSTRUCTION_LENGTH (1 << 1) -/* Add extra cycle after address during a read */ -#define EEPROM_93XX46_QUIRK_EXTRA_READ_CYCLE BIT(2) - - /* - * optional hooks to control additional logic - * before and after spi transfer. - */ - void (*prepare)(void *); - void (*finish)(void *); - struct gpio_desc *select; -}; diff --git a/include/linux/efi.h b/include/linux/efi.h index d59b0947fba0..6bf3c4fe8511 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -74,10 +74,10 @@ typedef void *efi_handle_t; */ typedef guid_t efi_guid_t __aligned(__alignof__(u32)); -#define EFI_GUID(a, b, c, d...) (efi_guid_t){ { \ +#define EFI_GUID(a, b, c, d...) ((efi_guid_t){ { \ (a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff, \ (b) & 0xff, ((b) >> 8) & 0xff, \ - (c) & 0xff, ((c) >> 8) & 0xff, d } } + (c) & 0xff, ((c) >> 8) & 0xff, d } }) /* * Generic EFI table header @@ -385,6 +385,7 @@ void efi_native_runtime_setup(void); #define EFI_MEMORY_ATTRIBUTES_TABLE_GUID EFI_GUID(0xdcfa911d, 0x26eb, 0x469f, 0xa2, 0x20, 0x38, 0xb7, 0xdc, 0x46, 0x12, 0x20) #define EFI_CONSOLE_OUT_DEVICE_GUID EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4, 0x9a, 0x46, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d) #define APPLE_PROPERTIES_PROTOCOL_GUID EFI_GUID(0x91bd12fe, 0xf6c3, 0x44fb, 0xa5, 0xb7, 0x51, 0x22, 0xab, 0x30, 0x3a, 0xe0) +#define APPLE_SET_OS_PROTOCOL_GUID EFI_GUID(0xc5c5da95, 0x7d5c, 0x45e6, 0xb2, 0xf1, 0x3f, 0xd5, 0x2b, 0xb1, 0x00, 0x77) #define EFI_TCG2_PROTOCOL_GUID EFI_GUID(0x607f766c, 0x7455, 0x42be, 0x93, 0x0b, 0xe4, 0xd7, 0x6d, 0xb2, 0x72, 0x0f) #define EFI_TCG2_FINAL_EVENTS_TABLE_GUID EFI_GUID(0x1e2ed096, 0x30e2, 0x4254, 0xbd, 0x89, 0x86, 0x3b, 0xbe, 0xf8, 0x23, 0x25) #define EFI_LOAD_FILE_PROTOCOL_GUID EFI_GUID(0x56ec3091, 0x954c, 0x11d2, 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) @@ -607,7 +608,11 @@ typedef struct { u32 num_entries; u32 desc_size; u32 flags; - efi_memory_desc_t entry[0]; + /* + * There are @num_entries following, each of size @desc_size bytes, + * including an efi_memory_desc_t header. See efi_memdesc_ptr(). + */ + efi_memory_desc_t entry[]; } efi_memory_attributes_table_t; typedef struct { @@ -783,7 +788,7 @@ extern int efi_memattr_apply_permissions(struct mm_struct *mm, efi_memattr_perm_setter fn); /* - * efi_early_memdesc_ptr - get the n-th EFI memmap descriptor + * efi_memdesc_ptr - get the n-th EFI memmap descriptor * @map: the start of efi memmap * @desc_size: the size of space for each EFI memmap descriptor * @n: the index of efi memmap descriptor @@ -801,7 +806,7 @@ extern int efi_memattr_apply_permissions(struct mm_struct *mm, * during bootup since for_each_efi_memory_desc_xxx() is available after the * kernel initializes the EFI subsystem to set up struct efi_memory_map. */ -#define efi_early_memdesc_ptr(map, desc_size, n) \ +#define efi_memdesc_ptr(map, desc_size, n) \ (efi_memory_desc_t *)((void *)(map) + ((n) * (desc_size))) /* Iterate through an efi_memory_map */ @@ -1072,12 +1077,11 @@ static inline u64 efivar_reserved_space(void) { return 0; } #endif /* - * The maximum size of VariableName + Data = 1024 - * Therefore, it's reasonable to save that much - * space in each part of the structure, - * and we use a page for reading/writing. + * There is no actual upper limit specified for the variable name size. + * + * This limit exists only for practical purposes, since name conversions + * are bounds-checked and name data is occasionally stored in-line. */ - #define EFI_VAR_NAME_LEN 1024 int efivars_register(struct efivars *efivars, diff --git a/include/linux/eisa.h b/include/linux/eisa.h index b012e30afebd..f98200cae637 100644 --- a/include/linux/eisa.h +++ b/include/linux/eisa.h @@ -60,7 +60,7 @@ struct eisa_driver { struct device_driver driver; }; -#define to_eisa_driver(drv) container_of(drv,struct eisa_driver, driver) +#define to_eisa_driver(drv) container_of_const(drv,struct eisa_driver, driver) /* These external functions are only available when EISA support is enabled. */ #ifdef CONFIG_EISA diff --git a/include/linux/elf.h b/include/linux/elf.h index c9a46c4e183b..5c402788da19 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -65,7 +65,7 @@ extern Elf64_Dyn _DYNAMIC []; struct file; struct coredump_params; -#ifndef ARCH_HAVE_EXTRA_ELF_NOTES +#ifndef CONFIG_ARCH_HAVE_EXTRA_ELF_NOTES static inline int elf_coredump_extra_notes_size(void) { return 0; } static inline int elf_coredump_extra_notes_write(struct coredump_params *cprm) { return 0; } #else diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 70cd7258cd29..1ff52020cf75 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -172,6 +172,7 @@ struct em_perf_table __rcu *em_table_alloc(struct em_perf_domain *pd); void em_table_free(struct em_perf_table __rcu *table); int em_dev_compute_costs(struct device *dev, struct em_perf_state *table, int nr_states); +int em_dev_update_chip_binning(struct device *dev); /** * em_pd_get_efficient_state() - Get an efficient performance state from the EM @@ -386,6 +387,10 @@ int em_dev_compute_costs(struct device *dev, struct em_perf_state *table, { return -EINVAL; } +static inline int em_dev_update_chip_binning(struct device *dev) +{ + return -EINVAL; +} #endif #endif diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 297231854ada..0ed47d00549b 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -71,6 +71,12 @@ static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }; #define eth_stp_addr eth_reserved_addr_base +static const u8 eth_ipv4_mcast_addr_base[ETH_ALEN] __aligned(2) = +{ 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 }; + +static const u8 eth_ipv6_mcast_addr_base[ETH_ALEN] __aligned(2) = +{ 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 }; + /** * is_link_local_ether_addr - Determine if given Ethernet address is link-local * @addr: Pointer to a six-byte array containing the Ethernet address @@ -430,18 +436,16 @@ static inline bool ether_addr_equal_masked(const u8 *addr1, const u8 *addr2, static inline bool ether_addr_is_ipv4_mcast(const u8 *addr) { - u8 base[ETH_ALEN] = { 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 }; u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0x80, 0x00, 0x00 }; - return ether_addr_equal_masked(addr, base, mask); + return ether_addr_equal_masked(addr, eth_ipv4_mcast_addr_base, mask); } static inline bool ether_addr_is_ipv6_mcast(const u8 *addr) { - u8 base[ETH_ALEN] = { 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 }; u8 mask[ETH_ALEN] = { 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 }; - return ether_addr_equal_masked(addr, base, mask); + return ether_addr_equal_masked(addr, eth_ipv6_mcast_addr_base, mask); } static inline bool ether_addr_is_ip_mcast(const u8 *addr) @@ -632,6 +636,14 @@ static inline void eth_skb_pkt_type(struct sk_buff *skb, } } +static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb) +{ + struct ethhdr *eth = (struct ethhdr *)skb->data; + + skb_pull_inline(skb, ETH_HLEN); + return eth; +} + /** * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame * @skb: Buffer to pad diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 9901e563f706..989c94eddb2b 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -18,6 +18,7 @@ #include <linux/if_ether.h> #include <linux/netlink.h> #include <uapi/linux/ethtool.h> +#include <uapi/linux/net_tstamp.h> struct compat_ethtool_rx_flow_spec { u32 flow_type; @@ -159,6 +160,49 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) return index % n_rx_rings; } +/** + * struct ethtool_rxfh_context - a custom RSS context configuration + * @indir_size: Number of u32 entries in indirection table + * @key_size: Size of hash key, in bytes + * @priv_size: Size of driver private data, in bytes + * @hfunc: RSS hash function identifier. One of the %ETH_RSS_HASH_* + * @input_xfrm: Defines how the input data is transformed. Valid values are one + * of %RXH_XFRM_*. + * @indir_configured: indir has been specified (at create time or subsequently) + * @key_configured: hkey has been specified (at create time or subsequently) + */ +struct ethtool_rxfh_context { + u32 indir_size; + u32 key_size; + u16 priv_size; + u8 hfunc; + u8 input_xfrm; + u8 indir_configured:1; + u8 key_configured:1; + /* private: driver private data, indirection table, and hash key are + * stored sequentially in @data area. Use below helpers to access. + */ + u32 key_off; + u8 data[] __aligned(sizeof(void *)); +}; + +static inline void *ethtool_rxfh_context_priv(struct ethtool_rxfh_context *ctx) +{ + return ctx->data; +} + +static inline u32 *ethtool_rxfh_context_indir(struct ethtool_rxfh_context *ctx) +{ + return (u32 *)(ctx->data + ALIGN(ctx->priv_size, sizeof(u32))); +} + +static inline u8 *ethtool_rxfh_context_key(struct ethtool_rxfh_context *ctx) +{ + return &ctx->data[ctx->key_off]; +} + +void ethtool_rxfh_context_lost(struct net_device *dev, u32 context_id); + /* declare a link mode bitmap */ #define __ETHTOOL_DECLARE_LINK_MODE_MASK(name) \ DECLARE_BITMAP(name, __ETHTOOL_LINK_MODE_MASK_NBITS) @@ -284,7 +328,9 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, #define ETHTOOL_COALESCE_TX_AGGR_MAX_BYTES BIT(24) #define ETHTOOL_COALESCE_TX_AGGR_MAX_FRAMES BIT(25) #define ETHTOOL_COALESCE_TX_AGGR_TIME_USECS BIT(26) -#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(26, 0) +#define ETHTOOL_COALESCE_RX_PROFILE BIT(27) +#define ETHTOOL_COALESCE_TX_PROFILE BIT(28) +#define ETHTOOL_COALESCE_ALL_PARAMS GENMASK(28, 0) #define ETHTOOL_COALESCE_USECS \ (ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_TX_USECS) @@ -480,21 +526,40 @@ struct ethtool_rmon_stats { ); }; +/** + * struct ethtool_ts_stats - HW timestamping statistics + * @pkts: Number of packets successfully timestamped by the hardware. + * @lost: Number of hardware timestamping requests where the timestamping + * information from the hardware never arrived for submission with + * the skb. + * @err: Number of arbitrary timestamp generation error events that the + * hardware encountered, exclusive of @lost statistics. Cases such + * as resource exhaustion, unavailability, firmware errors, and + * detected illogical timestamp values not submitted with the skb + * are inclusive to this counter. + */ +struct ethtool_ts_stats { + struct_group(tx_stats, + u64 pkts; + u64 lost; + u64 err; + ); +}; + #define ETH_MODULE_EEPROM_PAGE_LEN 128 #define ETH_MODULE_MAX_I2C_ADDRESS 0x7f /** - * struct ethtool_module_eeprom - EEPROM dump from specified page - * @offset: Offset within the specified EEPROM page to begin read, in bytes. - * @length: Number of bytes to read. - * @page: Page number to read from. - * @bank: Page bank number to read from, if applicable by EEPROM spec. + * struct ethtool_module_eeprom - plug-in module EEPROM read / write parameters + * @offset: When @offset is 0-127, it is used as an address to the Lower Memory + * (@page must be 0). Otherwise, it is used as an address to the + * Upper Memory. + * @length: Number of bytes to read / write. + * @page: Page number. + * @bank: Bank number, if supported by EEPROM spec. * @i2c_address: I2C address of a page. Value less than 0x7f expected. Most * EEPROMs use 0x50 or 0x51. * @data: Pointer to buffer with EEPROM data of @length size. - * - * This can be used to manage pages during EEPROM dump in ethtool and pass - * required information to the driver. */ struct ethtool_module_eeprom { u32 offset; @@ -642,6 +707,22 @@ struct ethtool_rxfh_param { }; /** + * struct kernel_ethtool_ts_info - kernel copy of struct ethtool_ts_info + * @cmd: command number = %ETHTOOL_GET_TS_INFO + * @so_timestamping: bit mask of the sum of the supported SO_TIMESTAMPING flags + * @phc_index: device index of the associated PHC, or -1 if there is none + * @tx_types: bit mask of the supported hwtstamp_tx_types enumeration values + * @rx_filters: bit mask of the supported hwtstamp_rx_filters enumeration values + */ +struct kernel_ethtool_ts_info { + u32 cmd; + u32 so_timestamping; + int phc_index; + enum hwtstamp_tx_types tx_types; + enum hwtstamp_rx_filters rx_filters; +}; + +/** * struct ethtool_ops - optional netdev operations * @cap_link_lanes_supported: indicates if the driver supports lanes * parameter. @@ -649,6 +730,16 @@ struct ethtool_rxfh_param { * contexts. * @cap_rss_sym_xor_supported: indicates if the driver supports symmetric-xor * RSS. + * @rxfh_indir_space: max size of RSS indirection tables, if indirection table + * size as returned by @get_rxfh_indir_size may change during lifetime + * of the device. Leave as 0 if the table size is constant. + * @rxfh_key_space: same as @rxfh_indir_space, but for the key. + * @rxfh_priv_size: size of the driver private data area the core should + * allocate for an RSS context (in &struct ethtool_rxfh_context). + * @rxfh_max_num_contexts: maximum (exclusive) supported RSS context ID. + * If this is zero then the core may choose any (nonzero) ID, otherwise + * the core will only use IDs strictly less than this value, as the + * @rss_context argument to @create_rxfh_context and friends. * @supported_coalesce_params: supported types of interrupt coalescing. * @supported_ring_params: supported ring params. * @get_drvinfo: Report driver/device information. Modern drivers no @@ -745,6 +836,32 @@ struct ethtool_rxfh_param { * will remain unchanged. * Returns a negative error code or zero. An error code must be returned * if at least one unsupported change was requested. + * @create_rxfh_context: Create a new RSS context with the specified RX flow + * hash indirection table, hash key, and hash function. + * The &struct ethtool_rxfh_context for this context is passed in @ctx; + * note that the indir table, hkey and hfunc are not yet populated as + * of this call. The driver does not need to update these; the core + * will do so if this op succeeds. + * However, if @rxfh.indir is set to %NULL, the driver must update the + * indir table in @ctx with the (default or inherited) table actually in + * use; similarly, if @rxfh.key is %NULL, @rxfh.hfunc is + * %ETH_RSS_HASH_NO_CHANGE, or @rxfh.input_xfrm is %RXH_XFRM_NO_CHANGE, + * the driver should update the corresponding information in @ctx. + * If the driver provides this method, it must also provide + * @modify_rxfh_context and @remove_rxfh_context. + * Returns a negative error code or zero. + * @modify_rxfh_context: Reconfigure the specified RSS context. Allows setting + * the contents of the RX flow hash indirection table, hash key, and/or + * hash function associated with the given context. + * Parameters which are set to %NULL or zero will remain unchanged. + * The &struct ethtool_rxfh_context for this context is passed in @ctx; + * note that it will still contain the *old* settings. The driver does + * not need to update these; the core will do so if this op succeeds. + * Returns a negative error code or zero. An error code must be returned + * if at least one unsupported change was requested. + * @remove_rxfh_context: Remove the specified RSS context. + * The &struct ethtool_rxfh_context for this context is passed in @ctx. + * Returns a negative error code or zero. * @get_channels: Get number of channels. * @set_channels: Set number of channels. Returns a negative error code or * zero. @@ -755,7 +872,10 @@ struct ethtool_rxfh_param { * @get_ts_info: Get the time stamping and PTP hardware clock capabilities. * It may be called with RCU, or rtnl or reference on the device. * Drivers supporting transmit time stamps in software should set this to - * ethtool_op_get_ts_info(). + * ethtool_op_get_ts_info(). Drivers must not zero statistics which they + * don't report. The stats structure is initialized to ETHTOOL_STAT_NOT_SET + * indicating driver does not report statistics. + * @get_ts_stats: Query the device hardware timestamping statistics. * @get_module_info: Get the size and type of the eeprom contained within * a plug-in module. * @get_module_eeprom: Get the eeprom information from the plug-in module @@ -799,6 +919,8 @@ struct ethtool_rxfh_param { * @get_module_eeprom_by_page: Get a region of plug-in module EEPROM data from * specified page. Returns a negative error code or the amount of bytes * read. + * @set_module_eeprom_by_page: Write to a region of plug-in module EEPROM, + * from kernel space only. Returns a negative error code or zero. * @get_eth_phy_stats: Query some of the IEEE 802.3 PHY statistics. * @get_eth_mac_stats: Query some of the IEEE 802.3 MAC statistics. * @get_eth_ctrl_stats: Query some of the IEEE 802.3 MAC Ctrl statistics. @@ -829,6 +951,10 @@ struct ethtool_ops { u32 cap_link_lanes_supported:1; u32 cap_rss_ctx_supported:1; u32 cap_rss_sym_xor_supported:1; + u32 rxfh_indir_space; + u16 rxfh_key_space; + u16 rxfh_priv_size; + u32 rxfh_max_num_contexts; u32 supported_coalesce_params; u32 supported_ring_params; void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); @@ -891,13 +1017,27 @@ struct ethtool_ops { int (*get_rxfh)(struct net_device *, struct ethtool_rxfh_param *); int (*set_rxfh)(struct net_device *, struct ethtool_rxfh_param *, struct netlink_ext_ack *extack); + int (*create_rxfh_context)(struct net_device *, + struct ethtool_rxfh_context *ctx, + const struct ethtool_rxfh_param *rxfh, + struct netlink_ext_ack *extack); + int (*modify_rxfh_context)(struct net_device *, + struct ethtool_rxfh_context *ctx, + const struct ethtool_rxfh_param *rxfh, + struct netlink_ext_ack *extack); + int (*remove_rxfh_context)(struct net_device *, + struct ethtool_rxfh_context *ctx, + u32 rss_context, + struct netlink_ext_ack *extack); void (*get_channels)(struct net_device *, struct ethtool_channels *); int (*set_channels)(struct net_device *, struct ethtool_channels *); int (*get_dump_flag)(struct net_device *, struct ethtool_dump *); int (*get_dump_data)(struct net_device *, struct ethtool_dump *, void *); int (*set_dump)(struct net_device *, struct ethtool_dump *); - int (*get_ts_info)(struct net_device *, struct ethtool_ts_info *); + int (*get_ts_info)(struct net_device *, struct kernel_ethtool_ts_info *); + void (*get_ts_stats)(struct net_device *dev, + struct ethtool_ts_stats *ts_stats); int (*get_module_info)(struct net_device *, struct ethtool_modinfo *); int (*get_module_eeprom)(struct net_device *, @@ -931,6 +1071,9 @@ struct ethtool_ops { int (*get_module_eeprom_by_page)(struct net_device *dev, const struct ethtool_module_eeprom *page, struct netlink_ext_ack *extack); + int (*set_module_eeprom_by_page)(struct net_device *dev, + const struct ethtool_module_eeprom *page, + struct netlink_ext_ack *extack); void (*get_eth_phy_stats)(struct net_device *dev, struct ethtool_eth_phy_stats *phy_stats); void (*get_eth_mac_stats)(struct net_device *dev, @@ -973,6 +1116,21 @@ int ethtool_virtdev_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd, u32 *dev_speed, u8 *dev_duplex); +/** + * struct ethtool_netdev_state - per-netdevice state for ethtool features + * @rss_ctx: XArray of custom RSS contexts + * @rss_lock: Protects entries in @rss_ctx. May be taken from + * within RTNL. + * @wol_enabled: Wake-on-LAN is enabled + * @module_fw_flash_in_progress: Module firmware flashing is in progress. + */ +struct ethtool_netdev_state { + struct xarray rss_ctx; + struct mutex rss_lock; + unsigned wol_enabled:1; + unsigned module_fw_flash_in_progress:1; +}; + struct phy_device; struct phy_tdr_config; struct phy_plca_cfg; @@ -1038,7 +1196,8 @@ int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index); /* Some generic methods drivers may use in their ethtool_ops */ u32 ethtool_op_get_link(struct net_device *dev); -int ethtool_op_get_ts_info(struct net_device *dev, struct ethtool_ts_info *eti); +int ethtool_op_get_ts_info(struct net_device *dev, + struct kernel_ethtool_ts_info *eti); /** * ethtool_mm_frag_size_add_to_min - Translate (standard) additional fragment @@ -1087,7 +1246,8 @@ static inline int ethtool_mm_frag_size_min_to_add(u32 val_min, u32 *val_add, * @info: buffer to hold the result * Returns zero on success, non-zero otherwise. */ -int ethtool_get_ts_info_by_layer(struct net_device *dev, struct ethtool_ts_info *info); +int ethtool_get_ts_info_by_layer(struct net_device *dev, + struct kernel_ethtool_ts_info *info); /** * ethtool_sprintf - Write formatted string to ethtool string data @@ -1130,4 +1290,24 @@ struct ethtool_forced_speed_map { void ethtool_forced_speed_maps_init(struct ethtool_forced_speed_map *maps, u32 size); + +/* C33 PSE extended state and substate. */ +struct ethtool_c33_pse_ext_state_info { + enum ethtool_c33_pse_ext_state c33_pse_ext_state; + union { + enum ethtool_c33_pse_ext_substate_error_condition error_condition; + enum ethtool_c33_pse_ext_substate_mr_pse_enable mr_pse_enable; + enum ethtool_c33_pse_ext_substate_option_detect_ted option_detect_ted; + enum ethtool_c33_pse_ext_substate_option_vport_lim option_vport_lim; + enum ethtool_c33_pse_ext_substate_ovld_detected ovld_detected; + enum ethtool_c33_pse_ext_substate_power_not_available power_not_available; + enum ethtool_c33_pse_ext_substate_short_detected short_detected; + u32 __c33_pse_ext_substate; + }; +}; + +struct ethtool_c33_pse_pw_limit_range { + u32 min; + u32 max; +}; #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/linux/evm.h b/include/linux/evm.h index d48d6da32315..ddece4a6b25d 100644 --- a/include/linux/evm.h +++ b/include/linux/evm.h @@ -26,6 +26,8 @@ extern int evm_protected_xattr_if_enabled(const char *req_xattr_name); extern int evm_read_protected_xattrs(struct dentry *dentry, u8 *buffer, int buffer_size, char type, bool canonical_fmt); +extern bool evm_metadata_changed(struct inode *inode, + struct inode *metadata_inode); #ifdef CONFIG_FS_POSIX_ACL extern int posix_xattr_acl(const char *xattrname); #else @@ -76,5 +78,11 @@ static inline int evm_read_protected_xattrs(struct dentry *dentry, u8 *buffer, return -EOPNOTSUPP; } +static inline bool evm_metadata_changed(struct inode *inode, + struct inode *metadata_inode) +{ + return false; +} + #endif /* CONFIG_EVM */ #endif /* LINUX_EVM_H */ diff --git a/include/linux/execmem.h b/include/linux/execmem.h new file mode 100644 index 000000000000..32cef1144117 --- /dev/null +++ b/include/linux/execmem.h @@ -0,0 +1,132 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_EXECMEM_ALLOC_H +#define _LINUX_EXECMEM_ALLOC_H + +#include <linux/types.h> +#include <linux/moduleloader.h> + +#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ + !defined(CONFIG_KASAN_VMALLOC) +#include <linux/kasan.h> +#define MODULE_ALIGN (PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT) +#else +#define MODULE_ALIGN PAGE_SIZE +#endif + +/** + * enum execmem_type - types of executable memory ranges + * + * There are several subsystems that allocate executable memory. + * Architectures define different restrictions on placement, + * permissions, alignment and other parameters for memory that can be used + * by these subsystems. + * Types in this enum identify subsystems that allocate executable memory + * and let architectures define parameters for ranges suitable for + * allocations by each subsystem. + * + * @EXECMEM_DEFAULT: default parameters that would be used for types that + * are not explicitly defined. + * @EXECMEM_MODULE_TEXT: parameters for module text sections + * @EXECMEM_KPROBES: parameters for kprobes + * @EXECMEM_FTRACE: parameters for ftrace + * @EXECMEM_BPF: parameters for BPF + * @EXECMEM_MODULE_DATA: parameters for module data sections + * @EXECMEM_TYPE_MAX: + */ +enum execmem_type { + EXECMEM_DEFAULT, + EXECMEM_MODULE_TEXT = EXECMEM_DEFAULT, + EXECMEM_KPROBES, + EXECMEM_FTRACE, + EXECMEM_BPF, + EXECMEM_MODULE_DATA, + EXECMEM_TYPE_MAX, +}; + +/** + * enum execmem_range_flags - options for executable memory allocations + * @EXECMEM_KASAN_SHADOW: allocate kasan shadow + */ +enum execmem_range_flags { + EXECMEM_KASAN_SHADOW = (1 << 0), +}; + +/** + * struct execmem_range - definition of an address space suitable for code and + * related data allocations + * @start: address space start + * @end: address space end (inclusive) + * @fallback_start: start of the secondary address space range for fallback + * allocations on architectures that require it + * @fallback_end: start of the secondary address space (inclusive) + * @pgprot: permissions for memory in this address space + * @alignment: alignment required for text allocations + * @flags: options for memory allocations for this range + */ +struct execmem_range { + unsigned long start; + unsigned long end; + unsigned long fallback_start; + unsigned long fallback_end; + pgprot_t pgprot; + unsigned int alignment; + enum execmem_range_flags flags; +}; + +/** + * struct execmem_info - architecture parameters for code allocations + * @ranges: array of parameter sets defining architecture specific + * parameters for executable memory allocations. The ranges that are not + * explicitly initialized by an architecture use parameters defined for + * @EXECMEM_DEFAULT. + */ +struct execmem_info { + struct execmem_range ranges[EXECMEM_TYPE_MAX]; +}; + +/** + * execmem_arch_setup - define parameters for allocations of executable memory + * + * A hook for architectures to define parameters for allocations of + * executable memory. These parameters should be filled into the + * @execmem_info structure. + * + * For architectures that do not implement this method a default set of + * parameters will be used + * + * Return: a structure defining architecture parameters and restrictions + * for allocations of executable memory + */ +struct execmem_info *execmem_arch_setup(void); + +/** + * execmem_alloc - allocate executable memory + * @type: type of the allocation + * @size: how many bytes of memory are required + * + * Allocates memory that will contain executable code, either generated or + * loaded from kernel modules. + * + * Allocates memory that will contain data coupled with executable code, + * like data sections in kernel modules. + * + * The memory will have protections defined by architecture for executable + * region of the @type. + * + * Return: a pointer to the allocated memory or %NULL + */ +void *execmem_alloc(enum execmem_type type, size_t size); + +/** + * execmem_free - free executable memory + * @ptr: pointer to the memory that should be freed + */ +void execmem_free(void *ptr); + +#if defined(CONFIG_EXECMEM) && !defined(CONFIG_ARCH_WANTS_EXECMEM_LATE) +void execmem_init(void); +#else +static inline void execmem_init(void) {} +#endif + +#endif /* _LINUX_EXECMEM_ALLOC_H */ diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index bb37ad5cc954..893a1d21dc1c 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -158,6 +158,7 @@ struct fid { #define EXPORT_FH_CONNECTABLE 0x1 /* Encode file handle with parent */ #define EXPORT_FH_FID 0x2 /* File handle may be non-decodeable */ +#define EXPORT_FH_DIR_ONLY 0x4 /* Only decode file handle for a directory */ /** * struct export_operations - for nfsd to communicate with file systems @@ -305,6 +306,7 @@ static inline int exportfs_encode_fid(struct inode *inode, struct fid *fid, extern struct dentry *exportfs_decode_fh_raw(struct vfsmount *mnt, struct fid *fid, int fh_len, int fileid_type, + unsigned int flags, int (*acceptable)(void *, struct dentry *), void *context); extern struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid, diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index a357287eac1e..01bee2b289c2 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -259,15 +259,14 @@ struct node_footer { #define CUR_ADDRS_PER_INODE(inode) (DEF_ADDRS_PER_INODE - \ get_extra_isize(inode)) #define DEF_NIDS_PER_INODE 5 /* Node IDs in an Inode */ -#define ADDRS_PER_INODE(inode) addrs_per_inode(inode) +#define ADDRS_PER_INODE(inode) addrs_per_page(inode, true) /* Address Pointers in a Direct Block */ #define DEF_ADDRS_PER_BLOCK ((F2FS_BLKSIZE - sizeof(struct node_footer)) / sizeof(__le32)) -#define ADDRS_PER_BLOCK(inode) addrs_per_block(inode) +#define ADDRS_PER_BLOCK(inode) addrs_per_page(inode, false) /* Node IDs in an Indirect Block */ #define NIDS_PER_BLOCK ((F2FS_BLKSIZE - sizeof(struct node_footer)) / sizeof(__le32)) -#define ADDRS_PER_PAGE(page, inode) \ - (IS_INODE(page) ? ADDRS_PER_INODE(inode) : ADDRS_PER_BLOCK(inode)) +#define ADDRS_PER_PAGE(page, inode) (addrs_per_page(inode, IS_INODE(page))) #define NODE_DIR1_BLOCK (DEF_ADDRS_PER_INODE + 1) #define NODE_DIR2_BLOCK (DEF_ADDRS_PER_INODE + 2) @@ -394,7 +393,8 @@ struct f2fs_nat_block { /* * F2FS uses 4 bytes to represent block address. As a result, supported size of - * disk is 16 TB and it equals to 16 * 1024 * 1024 / 2 segments. + * disk is 16 TB for a 4K page size and 64 TB for a 16K page size and it equals + * to 16 * 1024 * 1024 / 2 segments. */ #define F2FS_MAX_SEGMENT ((16 * 1024 * 1024) / 2) @@ -424,8 +424,10 @@ struct f2fs_sit_block { /* * For segment summary * - * One summary block contains exactly 512 summary entries, which represents - * exactly one segment by default. Not allow to change the basic units. + * One summary block with 4KB size contains exactly 512 summary entries, which + * represents exactly one segment with 2MB size. + * Similarly, in the case of block with 16KB size, it represents one segment with 8MB size. + * Not allow to change the basic units. * * NOTE: For initializing fields, you must use set_summary * @@ -556,6 +558,7 @@ typedef __le32 f2fs_hash_t; /* * space utilization of regular dentry and inline dentry (w/o extra reservation) + * when block size is 4KB. * regular dentry inline dentry (def) inline dentry (min) * bitmap 1 * 27 = 27 1 * 23 = 23 1 * 1 = 1 * reserved 1 * 3 = 3 1 * 7 = 7 1 * 1 = 1 diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h index 6d5edef09d45..354413950d34 100644 --- a/include/linux/fault-inject.h +++ b/include/linux/fault-inject.h @@ -91,22 +91,19 @@ static inline void fault_config_init(struct fault_config *config, struct kmem_cache; -bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order); - #ifdef CONFIG_FAIL_PAGE_ALLOC -bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order); +bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order); #else -static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { return false; } #endif /* CONFIG_FAIL_PAGE_ALLOC */ -int should_failslab(struct kmem_cache *s, gfp_t gfpflags); #ifdef CONFIG_FAILSLAB -extern bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags); +int should_failslab(struct kmem_cache *s, gfp_t gfpflags); #else -static inline bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags) +static inline int should_failslab(struct kmem_cache *s, gfp_t gfpflags) { return false; } diff --git a/include/linux/fb.h b/include/linux/fb.h index 0dd27364d56f..db7d97b10964 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -12,7 +12,7 @@ #include <linux/types.h> #include <linux/workqueue.h> -#include <asm/fb.h> +#include <asm/video.h> struct backlight_device; struct device; @@ -225,6 +225,7 @@ struct fb_deferred_io { struct mutex lock; /* mutex that protects the pageref list */ struct list_head pagereflist; /* list of pagerefs for touched pages */ /* callback */ + struct page *(*get_page)(struct fb_info *info, unsigned long offset); void (*deferred_io)(struct fb_info *info, struct list_head *pagelist); }; #endif @@ -694,6 +695,10 @@ extern int fb_deferred_io_fsync(struct file *file, loff_t start, __FB_GEN_DEFAULT_DEFERRED_OPS_RDWR(__prefix, __damage_range, sys) \ __FB_GEN_DEFAULT_DEFERRED_OPS_DRAW(__prefix, __damage_area, sys) +#define FB_GEN_DEFAULT_DEFERRED_DMAMEM_OPS(__prefix, __damage_range, __damage_area) \ + __FB_GEN_DEFAULT_DEFERRED_OPS_RDWR(__prefix, __damage_range, sys) \ + __FB_GEN_DEFAULT_DEFERRED_OPS_DRAW(__prefix, __damage_area, sys) + /* * Initializes struct fb_ops for deferred I/O. */ @@ -738,6 +743,15 @@ extern struct fb_info *framebuffer_alloc(size_t size, struct device *dev); extern void framebuffer_release(struct fb_info *info); extern void fb_bl_default_curve(struct fb_info *fb_info, u8 off, u8 min, u8 max); +#if IS_ENABLED(CONFIG_FB_BACKLIGHT) +struct backlight_device *fb_bl_device(struct fb_info *info); +#else +static inline struct backlight_device *fb_bl_device(struct fb_info *info) +{ + return NULL; +} +#endif + /* fbmon.c */ #define FB_MAXTIMINGS 0 #define FB_VSYNCTIMINGS 1 diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index 78c8326d74ae..2944d4aa413b 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -33,16 +33,6 @@ struct fdtable { struct rcu_head rcu; }; -static inline bool close_on_exec(unsigned int fd, const struct fdtable *fdt) -{ - return test_bit(fd, fdt->close_on_exec); -} - -static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt) -{ - return test_bit(fd, fdt->open_fds); -} - /* * Open file table structure */ @@ -107,6 +97,11 @@ struct file *lookup_fdget_rcu(unsigned int fd); struct file *task_lookup_fdget_rcu(struct task_struct *task, unsigned int fd); struct file *task_lookup_next_fdget_rcu(struct task_struct *task, unsigned int *fd); +static inline bool close_on_exec(unsigned int fd, const struct files_struct *files) +{ + return test_bit(fd, files_fdtable(files)->close_on_exec); +} + struct task_struct; void put_files_struct(struct files_struct *fs); diff --git a/include/linux/file.h b/include/linux/file.h index 169692cb1906..59b146a14dca 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -84,6 +84,7 @@ static inline void fdput_pos(struct fd f) } DEFINE_CLASS(fd, struct fd, fdput(_T), fdget(fd), int fd) +DEFINE_CLASS(fd_raw, struct fd, fdput(_T), fdget_raw(fd), int fd) extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); @@ -96,6 +97,26 @@ extern void put_unused_fd(unsigned int fd); DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T), get_unused_fd_flags(flags), unsigned flags) +/* + * take_fd() will take care to set @fd to -EBADF ensuring that + * CLASS(get_unused_fd) won't call put_unused_fd(). This makes it + * easier to rely on CLASS(get_unused_fd): + * + * struct file *f; + * + * CLASS(get_unused_fd, fd)(O_CLOEXEC); + * if (fd < 0) + * return fd; + * + * f = dentry_open(&path, O_RDONLY, current_cred()); + * if (IS_ERR(f)) + * return PTR_ERR(f); + * + * fd_install(fd, f); + * return take_fd(fd); + */ +#define take_fd(fd) __get_and_null(fd, -EBADF) + extern void fd_install(unsigned int fd, struct file *file); int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags); diff --git a/include/linux/filter.h b/include/linux/filter.h index 219ee7a76874..b6672ff61407 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -75,6 +75,9 @@ struct ctl_table_header; /* unused opcode to mark special load instruction. Same as BPF_MSH */ #define BPF_PROBE_MEM32 0xa0 +/* unused opcode to mark special atomic instruction */ +#define BPF_PROBE_ATOMIC 0xe0 + /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 @@ -178,6 +181,25 @@ struct ctl_table_header; .off = 0, \ .imm = 0 }) +/* Special (internal-only) form of mov, used to resolve per-CPU addrs: + * dst_reg = src_reg + <percpu_base_off> + * BPF_ADDR_PERCPU is used as a special insn->off value. + */ +#define BPF_ADDR_PERCPU (-1) + +#define BPF_MOV64_PERCPU_REG(DST, SRC) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_MOV | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = BPF_ADDR_PERCPU, \ + .imm = 0 }) + +static inline bool insn_is_mov_percpu_addr(const struct bpf_insn *insn) +{ + return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->off == BPF_ADDR_PERCPU; +} + /* Short form of mov, dst_reg = imm32 */ #define BPF_MOV64_IMM(DST, IMM) \ @@ -228,6 +250,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) return insn->code == (BPF_ALU | BPF_MOV | BPF_X) && insn->imm == 1; } +/* addr_space_cast from as(0) to as(1) is for converting bpf arena pointers + * to pointers in user vma. + */ +static inline bool insn_is_cast_user(const struct bpf_insn *insn) +{ + return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && + insn->off == BPF_ADDR_SPACE_CAST && + insn->imm == 1U << 16; +} + /* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */ #define BPF_LD_IMM64(DST, IMM) \ BPF_LD_IMM64_RAW(DST, 0, IMM) @@ -644,14 +676,16 @@ static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog, cant_migrate(); if (static_branch_unlikely(&bpf_stats_enabled_key)) { struct bpf_prog_stats *stats; - u64 start = sched_clock(); + u64 duration, start = sched_clock(); unsigned long flags; ret = dfunc(ctx, prog->insnsi, prog->bpf_func); + + duration = sched_clock() - start; stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); u64_stats_inc(&stats->cnt); - u64_stats_add(&stats->nsecs, sched_clock() - start); + u64_stats_add(&stats->nsecs, duration); u64_stats_update_end_irqrestore(&stats->syncp, flags); } else { ret = dfunc(ctx, prog->insnsi, prog->bpf_func); @@ -699,21 +733,128 @@ struct bpf_nh_params { }; }; +/* flags for bpf_redirect_info kern_flags */ +#define BPF_RI_F_RF_NO_DIRECT BIT(0) /* no napi_direct on return_frame */ +#define BPF_RI_F_RI_INIT BIT(1) +#define BPF_RI_F_CPU_MAP_INIT BIT(2) +#define BPF_RI_F_DEV_MAP_INIT BIT(3) +#define BPF_RI_F_XSK_MAP_INIT BIT(4) + struct bpf_redirect_info { u64 tgt_index; void *tgt_value; struct bpf_map *map; u32 flags; - u32 kern_flags; u32 map_id; enum bpf_map_type map_type; struct bpf_nh_params nh; + u32 kern_flags; }; -DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); +struct bpf_net_context { + struct bpf_redirect_info ri; + struct list_head cpu_map_flush_list; + struct list_head dev_map_flush_list; + struct list_head xskmap_map_flush_list; +}; -/* flags for bpf_redirect_info kern_flags */ -#define BPF_RI_F_RF_NO_DIRECT BIT(0) /* no napi_direct on return_frame */ +static inline struct bpf_net_context *bpf_net_ctx_set(struct bpf_net_context *bpf_net_ctx) +{ + struct task_struct *tsk = current; + + if (tsk->bpf_net_context != NULL) + return NULL; + bpf_net_ctx->ri.kern_flags = 0; + + tsk->bpf_net_context = bpf_net_ctx; + return bpf_net_ctx; +} + +static inline void bpf_net_ctx_clear(struct bpf_net_context *bpf_net_ctx) +{ + if (bpf_net_ctx) + current->bpf_net_context = NULL; +} + +static inline struct bpf_net_context *bpf_net_ctx_get(void) +{ + return current->bpf_net_context; +} + +static inline struct bpf_redirect_info *bpf_net_ctx_get_ri(void) +{ + struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); + + if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_RI_INIT)) { + memset(&bpf_net_ctx->ri, 0, offsetof(struct bpf_net_context, ri.nh)); + bpf_net_ctx->ri.kern_flags |= BPF_RI_F_RI_INIT; + } + + return &bpf_net_ctx->ri; +} + +static inline struct list_head *bpf_net_ctx_get_cpu_map_flush_list(void) +{ + struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); + + if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_CPU_MAP_INIT)) { + INIT_LIST_HEAD(&bpf_net_ctx->cpu_map_flush_list); + bpf_net_ctx->ri.kern_flags |= BPF_RI_F_CPU_MAP_INIT; + } + + return &bpf_net_ctx->cpu_map_flush_list; +} + +static inline struct list_head *bpf_net_ctx_get_dev_flush_list(void) +{ + struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); + + if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_DEV_MAP_INIT)) { + INIT_LIST_HEAD(&bpf_net_ctx->dev_map_flush_list); + bpf_net_ctx->ri.kern_flags |= BPF_RI_F_DEV_MAP_INIT; + } + + return &bpf_net_ctx->dev_map_flush_list; +} + +static inline struct list_head *bpf_net_ctx_get_xskmap_flush_list(void) +{ + struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); + + if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_XSK_MAP_INIT)) { + INIT_LIST_HEAD(&bpf_net_ctx->xskmap_map_flush_list); + bpf_net_ctx->ri.kern_flags |= BPF_RI_F_XSK_MAP_INIT; + } + + return &bpf_net_ctx->xskmap_map_flush_list; +} + +static inline void bpf_net_ctx_get_all_used_flush_lists(struct list_head **lh_map, + struct list_head **lh_dev, + struct list_head **lh_xsk) +{ + struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get(); + u32 kern_flags = bpf_net_ctx->ri.kern_flags; + struct list_head *lh; + + *lh_map = *lh_dev = *lh_xsk = NULL; + + if (!IS_ENABLED(CONFIG_BPF_SYSCALL)) + return; + + lh = &bpf_net_ctx->dev_map_flush_list; + if (kern_flags & BPF_RI_F_DEV_MAP_INIT && !list_empty(lh)) + *lh_dev = lh; + + lh = &bpf_net_ctx->cpu_map_flush_list; + if (kern_flags & BPF_RI_F_CPU_MAP_INIT && !list_empty(lh)) + *lh_map = lh; + + lh = &bpf_net_ctx->xskmap_map_flush_list; + if (IS_ENABLED(CONFIG_XDP_SOCKETS) && + kern_flags & BPF_RI_F_XSK_MAP_INIT && !list_empty(lh)) + *lh_xsk = lh; +} /* Compute the linear packet data range [data, data_end) which * will be accessed by various program types (cls_bpf, act_bpf, @@ -887,20 +1028,22 @@ bpf_ctx_narrow_access_offset(u32 off, u32 size, u32 size_default) #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) -static inline void bpf_prog_lock_ro(struct bpf_prog *fp) +static inline int __must_check bpf_prog_lock_ro(struct bpf_prog *fp) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON if (!fp->jited) { set_vm_flush_reset_perms(fp); - set_memory_ro((unsigned long)fp, fp->pages); + return set_memory_ro((unsigned long)fp, fp->pages); } #endif + return 0; } -static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) +static inline int __must_check +bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { set_vm_flush_reset_perms(hdr); - set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT); + return set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT); } int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); @@ -957,12 +1100,15 @@ u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); bool bpf_jit_needs_zext(void); +bool bpf_jit_inlines_helper_call(s32 imm); bool bpf_jit_supports_subprog_tailcalls(void); +bool bpf_jit_supports_percpu_insn(void); bool bpf_jit_supports_kfunc_call(void); bool bpf_jit_supports_far_kfunc_call(void); bool bpf_jit_supports_exceptions(void); bool bpf_jit_supports_ptr_xchg(void); bool bpf_jit_supports_arena(void); +bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena); u64 bpf_arch_uaddress_limit(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); bool bpf_helper_changes_pkt_data(void *func); @@ -979,25 +1125,23 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt); -void bpf_clear_redirect_map(struct bpf_map *map); - static inline bool xdp_return_frame_no_direct(void) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); return ri->kern_flags & BPF_RI_F_RF_NO_DIRECT; } static inline void xdp_set_return_frame_no_direct(void) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); ri->kern_flags |= BPF_RI_F_RF_NO_DIRECT; } static inline void xdp_clear_return_frame_no_direct(void) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); ri->kern_flags &= ~BPF_RI_F_RF_NO_DIRECT; } @@ -1090,8 +1234,7 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **ro_image, struct bpf_binary_header **rw_hdr, u8 **rw_image, bpf_jit_fill_hole_t bpf_fill_ill_insns); -int bpf_jit_binary_pack_finalize(struct bpf_prog *prog, - struct bpf_binary_header *ro_header, +int bpf_jit_binary_pack_finalize(struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header); void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header); @@ -1169,18 +1312,18 @@ static inline bool bpf_jit_kallsyms_enabled(void) return false; } -const char *__bpf_address_lookup(unsigned long addr, unsigned long *size, +int __bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym); bool is_bpf_text_address(unsigned long addr); int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym); struct bpf_prog *bpf_prog_ksym_find(unsigned long addr); -static inline const char * +static inline int bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym) { - const char *ret = __bpf_address_lookup(addr, size, off, sym); + int ret = __bpf_address_lookup(addr, size, off, sym); if (ret && modname) *modname = NULL; @@ -1224,11 +1367,11 @@ static inline bool bpf_jit_kallsyms_enabled(void) return false; } -static inline const char * +static inline int __bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym) { - return NULL; + return 0; } static inline bool is_bpf_text_address(unsigned long addr) @@ -1247,11 +1390,11 @@ static inline struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) return NULL; } -static inline const char * +static inline int bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym) { - return NULL; + return 0; } static inline void bpf_prog_kallsyms_add(struct bpf_prog *fp) @@ -1367,7 +1510,7 @@ struct bpf_sock_ops_kern { struct bpf_sysctl_kern { struct ctl_table_header *head; - struct ctl_table *table; + const struct ctl_table *table; void *cur_val; size_t cur_len; void *new_val; @@ -1553,7 +1696,7 @@ static __always_inline long __bpf_xdp_redirect_map(struct bpf_map *map, u64 inde u64 flags, const u64 flag_mask, void *lookup_elem(struct bpf_map *map, u32 key)) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct bpf_redirect_info *ri = bpf_net_ctx_get_ri(); const u64 action_mask = XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX; /* Lower bits of the flags are used as return code on lookup failure */ diff --git a/include/linux/find.h b/include/linux/find.h index c69598e383c1..5dfca4225fef 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -29,6 +29,8 @@ unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, const unsign unsigned long n); extern unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); +unsigned long _find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2, + const unsigned long *addr3, unsigned long size); extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); @@ -220,7 +222,7 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size) * idx = find_first_bit(addr, size); * * Returns the bit number of the N'th set bit. - * If no such, returns @size. + * If no such, returns >= @size. */ static inline unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n) @@ -345,6 +347,31 @@ unsigned long find_first_and_bit(const unsigned long *addr1, } #endif +/** + * find_first_and_and_bit - find the first set bit in 3 memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @addr3: The third address to base the search on + * @size: The bitmap size in bits + * + * Returns the bit number for the first set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_first_and_and_bit(const unsigned long *addr1, + const unsigned long *addr2, + const unsigned long *addr3, + unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr1 & *addr2 & *addr3 & GENMASK(size - 1, 0); + + return val ? __ffs(val) : size; + } + + return _find_first_and_and_bit(addr1, addr2, addr3, size); +} + #ifndef find_first_zero_bit /** * find_first_zero_bit - find the first cleared bit in a memory region diff --git a/include/linux/firewire.h b/include/linux/firewire.h index dd9f2d765e68..1cca14cf5652 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -462,7 +462,7 @@ struct fw_iso_packet { /* rx: Sync bit, wait for matching sy */ u32 tag:2; /* tx: Tag in packet header */ u32 sy:4; /* tx: Sy in packet header */ - u32 header_length:8; /* Length of immediate header */ + u32 header_length:8; /* Size of immediate header */ u32 header[]; /* tx: Top of 1394 isoch. data_block */ }; diff --git a/include/linux/firmware.h b/include/linux/firmware.h index f026f8926d79..aae1b85ffc10 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -98,6 +98,10 @@ static inline bool firmware_request_builtin(struct firmware *fw, #if IS_REACHABLE(CONFIG_FW_LOADER) int request_firmware(const struct firmware **fw, const char *name, struct device *device); +int firmware_request_nowait_nowarn( + struct module *module, const char *name, + struct device *device, gfp_t gfp, void *context, + void (*cont)(const struct firmware *fw, void *context)); int firmware_request_nowarn(const struct firmware **fw, const char *name, struct device *device); int firmware_request_platform(const struct firmware **fw, const char *name, @@ -123,6 +127,14 @@ static inline int request_firmware(const struct firmware **fw, return -EINVAL; } +static inline int firmware_request_nowait_nowarn( + struct module *module, const char *name, + struct device *device, gfp_t gfp, void *context, + void (*cont)(const struct firmware *fw, void *context)) +{ + return -EINVAL; +} + static inline int firmware_request_nowarn(const struct firmware **fw, const char *name, struct device *device) diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h index 23384a54d575..7cae703b3137 100644 --- a/include/linux/firmware/cirrus/cs_dsp.h +++ b/include/linux/firmware/cirrus/cs_dsp.h @@ -42,6 +42,16 @@ #define CS_DSP_ACKED_CTL_MIN_VALUE 0 #define CS_DSP_ACKED_CTL_MAX_VALUE 0xFFFFFF +/* + * Write sequence operation codes + */ +#define CS_DSP_WSEQ_FULL 0x00 +#define CS_DSP_WSEQ_ADDR8 0x02 +#define CS_DSP_WSEQ_L16 0x04 +#define CS_DSP_WSEQ_H16 0x05 +#define CS_DSP_WSEQ_UNLOCK 0xFD +#define CS_DSP_WSEQ_END 0xFF + /** * struct cs_dsp_region - Describes a logical memory region in DSP address space * @type: Memory region type @@ -167,7 +177,7 @@ struct cs_dsp { const struct cs_dsp_region *mem; int num_mems; - int fw_ver; + int wmfw_ver; bool booted; bool running; @@ -213,13 +223,13 @@ int cs_dsp_adsp2_init(struct cs_dsp *dsp); int cs_dsp_halo_init(struct cs_dsp *dsp); int cs_dsp_adsp1_power_up(struct cs_dsp *dsp, - const struct firmware *wmfw_firmware, char *wmfw_filename, - const struct firmware *coeff_firmware, char *coeff_filename, + const struct firmware *wmfw_firmware, const char *wmfw_filename, + const struct firmware *coeff_firmware, const char *coeff_filename, const char *fw_name); void cs_dsp_adsp1_power_down(struct cs_dsp *dsp); int cs_dsp_power_up(struct cs_dsp *dsp, - const struct firmware *wmfw_firmware, char *wmfw_filename, - const struct firmware *coeff_firmware, char *coeff_filename, + const struct firmware *wmfw_firmware, const char *wmfw_filename, + const struct firmware *coeff_firmware, const char *coeff_filename, const char *fw_name); void cs_dsp_power_down(struct cs_dsp *dsp); int cs_dsp_run(struct cs_dsp *dsp); @@ -238,8 +248,12 @@ void cs_dsp_cleanup_debugfs(struct cs_dsp *dsp); int cs_dsp_coeff_write_acked_control(struct cs_dsp_coeff_ctl *ctl, unsigned int event_id); int cs_dsp_coeff_write_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off, const void *buf, size_t len); +int cs_dsp_coeff_lock_and_write_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off, + const void *buf, size_t len); int cs_dsp_coeff_read_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off, void *buf, size_t len); +int cs_dsp_coeff_lock_and_read_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off, + void *buf, size_t len); struct cs_dsp_coeff_ctl *cs_dsp_get_ctl(struct cs_dsp *dsp, const char *name, int type, unsigned int alg); @@ -255,6 +269,23 @@ struct cs_dsp_alg_region *cs_dsp_find_alg_region(struct cs_dsp *dsp, const char *cs_dsp_mem_region_name(unsigned int type); /** + * struct cs_dsp_wseq - Describes a write sequence + * @ctl: Write sequence cs_dsp control + * @ops: Operations contained within + */ +struct cs_dsp_wseq { + struct cs_dsp_coeff_ctl *ctl; + struct list_head ops; +}; + +int cs_dsp_wseq_init(struct cs_dsp *dsp, struct cs_dsp_wseq *wseqs, unsigned int num_wseqs); +int cs_dsp_wseq_write(struct cs_dsp *dsp, struct cs_dsp_wseq *wseq, u32 addr, u32 data, + u8 op_code, bool update); +int cs_dsp_wseq_multi_write(struct cs_dsp *dsp, struct cs_dsp_wseq *wseq, + const struct reg_sequence *reg_seq, int num_regs, + u8 op_code, bool update); + +/** * struct cs_dsp_chunk - Describes a buffer holding data formatted for the DSP * @data: Pointer to underlying buffer memory * @max: Pointer to end of the buffer memory diff --git a/include/linux/firmware/mediatek/mtk-adsp-ipc.h b/include/linux/firmware/mediatek/mtk-adsp-ipc.h index 5b1d16fa3f56..6e86799a7dc4 100644 --- a/include/linux/firmware/mediatek/mtk-adsp-ipc.h +++ b/include/linux/firmware/mediatek/mtk-adsp-ipc.h @@ -40,7 +40,7 @@ struct mtk_adsp_chan { struct mtk_adsp_ipc { struct mtk_adsp_chan chans[MTK_ADSP_MBOX_NUM]; struct device *dev; - struct mtk_adsp_ipc_ops *ops; + const struct mtk_adsp_ipc_ops *ops; void *private_data; }; diff --git a/include/linux/firmware/qcom/qcom_qseecom.h b/include/linux/firmware/qcom/qcom_qseecom.h index 366243ee9609..1dc5b3b50aa9 100644 --- a/include/linux/firmware/qcom/qcom_qseecom.h +++ b/include/linux/firmware/qcom/qcom_qseecom.h @@ -73,9 +73,9 @@ static inline void qseecom_dma_free(struct qseecom_client *client, size_t size, /** * qcom_qseecom_app_send() - Send to and receive data from a given QSEE app. * @client: The QSEECOM client associated with the target app. - * @req: DMA address of the request buffer sent to the app. + * @req: Request buffer sent to the app (must be TZ memory). * @req_size: Size of the request buffer. - * @rsp: DMA address of the response buffer, written to by the app. + * @rsp: Response buffer, written to by the app (must be TZ memory). * @rsp_size: Size of the response buffer. * * Sends a request to the QSEE app associated with the given client and read @@ -90,8 +90,8 @@ static inline void qseecom_dma_free(struct qseecom_client *client, size_t size, * Return: Zero on success, nonzero on failure. */ static inline int qcom_qseecom_app_send(struct qseecom_client *client, - dma_addr_t req, size_t req_size, - dma_addr_t rsp, size_t rsp_size) + void *req, size_t req_size, + void *rsp, size_t rsp_size) { return qcom_scm_qseecom_app_send(client->app_id, req, req_size, rsp, rsp_size); } diff --git a/include/linux/firmware/qcom/qcom_scm.h b/include/linux/firmware/qcom/qcom_scm.h index aaa19f93ac43..9f14976399ab 100644 --- a/include/linux/firmware/qcom/qcom_scm.h +++ b/include/linux/firmware/qcom/qcom_scm.h @@ -115,11 +115,40 @@ int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val, int qcom_scm_lmh_profile_change(u32 profile_id); bool qcom_scm_lmh_dcvsh_available(void); +/* + * Request TZ to program set of access controlled registers necessary + * irrespective of any features + */ +#define QCOM_SCM_GPU_ALWAYS_EN_REQ BIT(0) +/* + * Request TZ to program BCL id to access controlled register when BCL is + * enabled + */ +#define QCOM_SCM_GPU_BCL_EN_REQ BIT(1) +/* + * Request TZ to program set of access controlled register for CLX feature + * when enabled + */ +#define QCOM_SCM_GPU_CLX_EN_REQ BIT(2) +/* + * Request TZ to program tsense ids to access controlled registers for reading + * gpu temperature sensors + */ +#define QCOM_SCM_GPU_TSENSE_EN_REQ BIT(3) + +int qcom_scm_gpu_init_regs(u32 gpu_req); + +int qcom_scm_shm_bridge_enable(void); +int qcom_scm_shm_bridge_create(struct device *dev, u64 pfn_and_ns_perm_flags, + u64 ipfn_and_s_perm_flags, u64 size_and_flags, + u64 ns_vmids, u64 *handle); +int qcom_scm_shm_bridge_delete(struct device *dev, u64 handle); + #ifdef CONFIG_QCOM_QSEECOM int qcom_scm_qseecom_app_get_id(const char *app_name, u32 *app_id); -int qcom_scm_qseecom_app_send(u32 app_id, dma_addr_t req, size_t req_size, - dma_addr_t rsp, size_t rsp_size); +int qcom_scm_qseecom_app_send(u32 app_id, void *req, size_t req_size, + void *rsp, size_t rsp_size); #else /* CONFIG_QCOM_QSEECOM */ @@ -129,8 +158,8 @@ static inline int qcom_scm_qseecom_app_get_id(const char *app_name, u32 *app_id) } static inline int qcom_scm_qseecom_app_send(u32 app_id, - dma_addr_t req, size_t req_size, - dma_addr_t rsp, size_t rsp_size) + void *req, size_t req_size, + void *rsp, size_t rsp_size) { return -EINVAL; } diff --git a/include/linux/firmware/qcom/qcom_tzmem.h b/include/linux/firmware/qcom/qcom_tzmem.h new file mode 100644 index 000000000000..b83b63a0c049 --- /dev/null +++ b/include/linux/firmware/qcom/qcom_tzmem.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023-2024 Linaro Ltd. + */ + +#ifndef __QCOM_TZMEM_H +#define __QCOM_TZMEM_H + +#include <linux/cleanup.h> +#include <linux/gfp.h> +#include <linux/types.h> + +struct device; +struct qcom_tzmem_pool; + +/** + * enum qcom_tzmem_policy - Policy for pool growth. + */ +enum qcom_tzmem_policy { + /**< Static pool, never grow above initial size. */ + QCOM_TZMEM_POLICY_STATIC = 1, + /**< When out of memory, add increment * current size of memory. */ + QCOM_TZMEM_POLICY_MULTIPLIER, + /**< When out of memory add as much as is needed until max_size. */ + QCOM_TZMEM_POLICY_ON_DEMAND, +}; + +/** + * struct qcom_tzmem_pool_config - TZ memory pool configuration. + * @initial_size: Number of bytes to allocate for the pool during its creation. + * @policy: Pool size growth policy. + * @increment: Used with policies that allow pool growth. + * @max_size: Size above which the pool will never grow. + */ +struct qcom_tzmem_pool_config { + size_t initial_size; + enum qcom_tzmem_policy policy; + size_t increment; + size_t max_size; +}; + +struct qcom_tzmem_pool * +qcom_tzmem_pool_new(const struct qcom_tzmem_pool_config *config); +void qcom_tzmem_pool_free(struct qcom_tzmem_pool *pool); +struct qcom_tzmem_pool * +devm_qcom_tzmem_pool_new(struct device *dev, + const struct qcom_tzmem_pool_config *config); + +void *qcom_tzmem_alloc(struct qcom_tzmem_pool *pool, size_t size, gfp_t gfp); +void qcom_tzmem_free(void *ptr); + +DEFINE_FREE(qcom_tzmem, void *, if (_T) qcom_tzmem_free(_T)) + +phys_addr_t qcom_tzmem_to_phys(void *ptr); + +#endif /* __QCOM_TZMEM */ diff --git a/include/linux/firmware/xlnx-event-manager.h b/include/linux/firmware/xlnx-event-manager.h index 82e8254b0f80..645dd34155e6 100644 --- a/include/linux/firmware/xlnx-event-manager.h +++ b/include/linux/firmware/xlnx-event-manager.h @@ -1,4 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* + * Xilinx Event Management Driver + * + * Copyright (C) 2024, Advanced Micro Devices, Inc. + */ #ifndef _FIRMWARE_XLNX_EVENT_MANAGER_H_ #define _FIRMWARE_XLNX_EVENT_MANAGER_H_ @@ -7,6 +12,11 @@ #define CB_MAX_PAYLOAD_SIZE (4U) /*In payload maximum 32bytes */ +#define EVENT_SUBSYSTEM_RESTART (4U) + +#define PM_DEV_ACPU_0_0 (0x1810c0afU) +#define PM_DEV_ACPU_0 (0x1810c003U) + /************************** Exported Function *****************************/ typedef void (*event_cb_func_t)(const u32 *payload, void *data); diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 1a069a56c961..d7d07afc0532 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -52,6 +52,9 @@ #define API_ID_MASK GENMASK(7, 0) #define MODULE_ID_MASK GENMASK(11, 8) +/* Firmware feature check version mask */ +#define FIRMWARE_VERSION_MASK 0xFFFFU + /* ATF only commands */ #define TF_A_PM_REGISTER_SGI 0xa04 #define PM_GET_TRUSTZONE_VERSION 0xa03 diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 6aeebe0a6777..0d99bf11d260 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -15,10 +15,14 @@ #define FORTIFY_REASON(func, write) (FIELD_PREP(BIT(0), write) | \ FIELD_PREP(GENMASK(7, 1), func)) +/* Overridden by KUnit tests. */ #ifndef fortify_panic # define fortify_panic(func, write, avail, size, retfail) \ __fortify_panic(FORTIFY_REASON(func, write), avail, size) #endif +#ifndef fortify_warn_once +# define fortify_warn_once(x...) WARN_ONCE(x) +#endif #define FORTIFY_READ 0 #define FORTIFY_WRITE 1 @@ -71,17 +75,30 @@ void __write_overflow_field(size_t avail, size_t wanted) __compiletime_warning(" __ret; \ }) -#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) +#if defined(__SANITIZE_ADDRESS__) + +#if !defined(CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX) && !defined(CONFIG_GENERIC_ENTRY) +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); +#elif defined(CONFIG_KASAN_GENERIC) +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__asan_memset); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memmove); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memcpy); +#else /* CONFIG_KASAN_SW_TAGS */ +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__hwasan_memset); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memmove); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memcpy); +#endif + extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); -extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); -extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); -extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); + #else #if defined(__SANITIZE_MEMORY__) @@ -106,6 +123,7 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) #define __underlying_strlen __builtin_strlen #define __underlying_strncat __builtin_strncat #define __underlying_strncpy __builtin_strncpy + #endif /** @@ -583,11 +601,7 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, /* * Warn when writing beyond destination field size. * - * We must ignore p_size_field == 0 for existing 0-element - * fake flexible arrays, until they are all converted to - * proper flexible arrays. - * - * The implementation of __builtin_*object_size() behaves + * Note the implementation of __builtin_*object_size() behaves * like sizeof() when not directly referencing a flexible * array member, which means there will be many bounds checks * that will appear at run-time, without a way for them to be @@ -595,7 +609,7 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, * is specifically the flexible array member). * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101832 */ - if (p_size_field != 0 && p_size_field != SIZE_MAX && + if (p_size_field != SIZE_MAX && p_size != p_size_field && p_size_field < size) return true; @@ -609,7 +623,7 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, const size_t __q_size = (q_size); \ const size_t __p_size_field = (p_size_field); \ const size_t __q_size_field = (q_size_field); \ - WARN_ONCE(fortify_memcpy_chk(__fortify_size, __p_size, \ + fortify_warn_once(fortify_memcpy_chk(__fortify_size, __p_size, \ __q_size, __p_size_field, \ __q_size_field, FORTIFY_FUNC_ ##op), \ #op ": detected field-spanning write (size %zu) of single %s (size %zu)\n", \ @@ -725,18 +739,20 @@ __FORTIFY_INLINE void *memchr_inv(const void * const POS0 p, int c, size_t size) return __real_memchr_inv(p, c, size); } -extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup) +extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup_noprof) __realloc_size(2); -__FORTIFY_INLINE void *kmemdup(const void * const POS0 p, size_t size, gfp_t gfp) +__FORTIFY_INLINE void *kmemdup_noprof(const void * const POS0 p, size_t size, gfp_t gfp) { const size_t p_size = __struct_size(p); if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) - fortify_panic(FORTIFY_FUNC_kmemdup, FORTIFY_READ, p_size, size, NULL); + fortify_panic(FORTIFY_FUNC_kmemdup, FORTIFY_READ, p_size, size, + __real_kmemdup(p, 0, gfp)); return __real_kmemdup(p, size, gfp); } +#define kmemdup(...) alloc_hooks(kmemdup_noprof(__VA_ARGS__)) /** * strcpy - Copy a string into another string buffer diff --git a/include/linux/fpga/fpga-bridge.h b/include/linux/fpga/fpga-bridge.h index 223da48a6d18..94c4edd047e5 100644 --- a/include/linux/fpga/fpga-bridge.h +++ b/include/linux/fpga/fpga-bridge.h @@ -45,6 +45,7 @@ struct fpga_bridge_info { * @dev: FPGA bridge device * @mutex: enforces exclusive reference to bridge * @br_ops: pointer to struct of FPGA bridge ops + * @br_ops_owner: module containing the br_ops * @info: fpga image specific information * @node: FPGA bridge list node * @priv: low level driver private date @@ -54,6 +55,7 @@ struct fpga_bridge { struct device dev; struct mutex mutex; /* for exclusive reference to bridge */ const struct fpga_bridge_ops *br_ops; + struct module *br_ops_owner; struct fpga_image_info *info; struct list_head node; void *priv; @@ -79,10 +81,12 @@ int of_fpga_bridge_get_to_list(struct device_node *np, struct fpga_image_info *info, struct list_head *bridge_list); +#define fpga_bridge_register(parent, name, br_ops, priv) \ + __fpga_bridge_register(parent, name, br_ops, priv, THIS_MODULE) struct fpga_bridge * -fpga_bridge_register(struct device *parent, const char *name, - const struct fpga_bridge_ops *br_ops, - void *priv); +__fpga_bridge_register(struct device *parent, const char *name, + const struct fpga_bridge_ops *br_ops, void *priv, + struct module *owner); void fpga_bridge_unregister(struct fpga_bridge *br); #endif /* _LINUX_FPGA_BRIDGE_H */ diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 54f63459efd6..0d4fe068f3d8 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -201,6 +201,7 @@ struct fpga_manager_ops { * @state: state of fpga manager * @compat_id: FPGA manager id for compatibility check. * @mops: pointer to struct of fpga manager ops + * @mops_owner: module containing the mops * @priv: low level driver private date */ struct fpga_manager { @@ -210,6 +211,7 @@ struct fpga_manager { enum fpga_mgr_states state; struct fpga_compat_id *compat_id; const struct fpga_manager_ops *mops; + struct module *mops_owner; void *priv; }; @@ -230,18 +232,30 @@ struct fpga_manager *fpga_mgr_get(struct device *dev); void fpga_mgr_put(struct fpga_manager *mgr); +#define fpga_mgr_register_full(parent, info) \ + __fpga_mgr_register_full(parent, info, THIS_MODULE) struct fpga_manager * -fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info); +__fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info, + struct module *owner); +#define fpga_mgr_register(parent, name, mops, priv) \ + __fpga_mgr_register(parent, name, mops, priv, THIS_MODULE) struct fpga_manager * -fpga_mgr_register(struct device *parent, const char *name, - const struct fpga_manager_ops *mops, void *priv); +__fpga_mgr_register(struct device *parent, const char *name, + const struct fpga_manager_ops *mops, void *priv, struct module *owner); + void fpga_mgr_unregister(struct fpga_manager *mgr); +#define devm_fpga_mgr_register_full(parent, info) \ + __devm_fpga_mgr_register_full(parent, info, THIS_MODULE) struct fpga_manager * -devm_fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info); +__devm_fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info, + struct module *owner); +#define devm_fpga_mgr_register(parent, name, mops, priv) \ + __devm_fpga_mgr_register(parent, name, mops, priv, THIS_MODULE) struct fpga_manager * -devm_fpga_mgr_register(struct device *parent, const char *name, - const struct fpga_manager_ops *mops, void *priv); +__devm_fpga_mgr_register(struct device *parent, const char *name, + const struct fpga_manager_ops *mops, void *priv, + struct module *owner); #endif /*_LINUX_FPGA_MGR_H */ diff --git a/include/linux/fpga/fpga-region.h b/include/linux/fpga/fpga-region.h index 9d4d32909340..5fbc05fe70a6 100644 --- a/include/linux/fpga/fpga-region.h +++ b/include/linux/fpga/fpga-region.h @@ -36,6 +36,7 @@ struct fpga_region_info { * @mgr: FPGA manager * @info: FPGA image info * @compat_id: FPGA region id for compatibility check. + * @ops_owner: module containing the get_bridges function * @priv: private data * @get_bridges: optional function to get bridges to a list */ @@ -46,6 +47,7 @@ struct fpga_region { struct fpga_manager *mgr; struct fpga_image_info *info; struct fpga_compat_id *compat_id; + struct module *ops_owner; void *priv; int (*get_bridges)(struct fpga_region *region); }; @@ -58,12 +60,17 @@ fpga_region_class_find(struct device *start, const void *data, int fpga_region_program_fpga(struct fpga_region *region); +#define fpga_region_register_full(parent, info) \ + __fpga_region_register_full(parent, info, THIS_MODULE) struct fpga_region * -fpga_region_register_full(struct device *parent, const struct fpga_region_info *info); +__fpga_region_register_full(struct device *parent, const struct fpga_region_info *info, + struct module *owner); +#define fpga_region_register(parent, mgr, get_bridges) \ + __fpga_region_register(parent, mgr, get_bridges, THIS_MODULE) struct fpga_region * -fpga_region_register(struct device *parent, struct fpga_manager *mgr, - int (*get_bridges)(struct fpga_region *)); +__fpga_region_register(struct device *parent, struct fpga_manager *mgr, + int (*get_bridges)(struct fpga_region *), struct module *owner); void fpga_region_unregister(struct fpga_region *region); #endif /* _FPGA_REGION_H */ diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h index 3e03758151f4..f39869588117 100644 --- a/include/linux/fprobe.h +++ b/include/linux/fprobe.h @@ -7,6 +7,16 @@ #include <linux/ftrace.h> #include <linux/rethook.h> +struct fprobe; + +typedef int (*fprobe_entry_cb)(struct fprobe *fp, unsigned long entry_ip, + unsigned long ret_ip, struct pt_regs *regs, + void *entry_data); + +typedef void (*fprobe_exit_cb)(struct fprobe *fp, unsigned long entry_ip, + unsigned long ret_ip, struct pt_regs *regs, + void *entry_data); + /** * struct fprobe - ftrace based probe. * @ops: The ftrace_ops. @@ -34,12 +44,8 @@ struct fprobe { size_t entry_data_size; int nr_maxactive; - int (*entry_handler)(struct fprobe *fp, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, - void *entry_data); - void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs, - void *entry_data); + fprobe_entry_cb entry_handler; + fprobe_exit_cb exit_handler; }; /* This fprobe is soft-disabled. */ diff --git a/include/linux/fpu.h b/include/linux/fpu.h new file mode 100644 index 000000000000..2fb63e22913b --- /dev/null +++ b/include/linux/fpu.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_FPU_H +#define _LINUX_FPU_H + +#ifdef _LINUX_FPU_COMPILATION_UNIT +#error FP code must be compiled separately. See Documentation/core-api/floating-point.rst. +#endif + +#include <asm/fpu.h> + +#endif diff --git a/include/linux/fs.h b/include/linux/fs.h index 8dfd53b52744..fb0426f349fc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -73,6 +73,8 @@ struct fscrypt_inode_info; struct fscrypt_operations; struct fsverity_info; struct fsverity_operations; +struct fsnotify_mark_connector; +struct fsnotify_sb_info; struct fs_context; struct fs_parameter_spec; struct fileattr; @@ -110,23 +112,28 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, */ /* file is open for reading */ -#define FMODE_READ ((__force fmode_t)0x1) +#define FMODE_READ ((__force fmode_t)(1 << 0)) /* file is open for writing */ -#define FMODE_WRITE ((__force fmode_t)0x2) +#define FMODE_WRITE ((__force fmode_t)(1 << 1)) /* file is seekable */ -#define FMODE_LSEEK ((__force fmode_t)0x4) +#define FMODE_LSEEK ((__force fmode_t)(1 << 2)) /* file can be accessed using pread */ -#define FMODE_PREAD ((__force fmode_t)0x8) +#define FMODE_PREAD ((__force fmode_t)(1 << 3)) /* file can be accessed using pwrite */ -#define FMODE_PWRITE ((__force fmode_t)0x10) +#define FMODE_PWRITE ((__force fmode_t)(1 << 4)) /* File is opened for execution with sys_execve / sys_uselib */ -#define FMODE_EXEC ((__force fmode_t)0x20) +#define FMODE_EXEC ((__force fmode_t)(1 << 5)) /* File writes are restricted (block device specific) */ -#define FMODE_WRITE_RESTRICTED ((__force fmode_t)0x40) +#define FMODE_WRITE_RESTRICTED ((__force fmode_t)(1 << 6)) +/* File supports atomic writes */ +#define FMODE_CAN_ATOMIC_WRITE ((__force fmode_t)(1 << 7)) + +/* FMODE_* bit 8 */ + /* 32bit hashes as llseek() offset (for directories) */ -#define FMODE_32BITHASH ((__force fmode_t)0x200) +#define FMODE_32BITHASH ((__force fmode_t)(1 << 9)) /* 64bit hashes as llseek() offset (for directories) */ -#define FMODE_64BITHASH ((__force fmode_t)0x400) +#define FMODE_64BITHASH ((__force fmode_t)(1 << 10)) /* * Don't update ctime and mtime. @@ -134,60 +141,53 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, * Currently a special hack for the XFS open_by_handle ioctl, but we'll * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon. */ -#define FMODE_NOCMTIME ((__force fmode_t)0x800) +#define FMODE_NOCMTIME ((__force fmode_t)(1 << 11)) /* Expect random access pattern */ -#define FMODE_RANDOM ((__force fmode_t)0x1000) +#define FMODE_RANDOM ((__force fmode_t)(1 << 12)) /* File is huge (eg. /dev/mem): treat loff_t as unsigned */ -#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000) +#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)(1 << 13)) /* File is opened with O_PATH; almost nothing can be done with it */ -#define FMODE_PATH ((__force fmode_t)0x4000) +#define FMODE_PATH ((__force fmode_t)(1 << 14)) /* File needs atomic accesses to f_pos */ -#define FMODE_ATOMIC_POS ((__force fmode_t)0x8000) +#define FMODE_ATOMIC_POS ((__force fmode_t)(1 << 15)) /* Write access to underlying fs */ -#define FMODE_WRITER ((__force fmode_t)0x10000) +#define FMODE_WRITER ((__force fmode_t)(1 << 16)) /* Has read method(s) */ -#define FMODE_CAN_READ ((__force fmode_t)0x20000) +#define FMODE_CAN_READ ((__force fmode_t)(1 << 17)) /* Has write method(s) */ -#define FMODE_CAN_WRITE ((__force fmode_t)0x40000) +#define FMODE_CAN_WRITE ((__force fmode_t)(1 << 18)) -#define FMODE_OPENED ((__force fmode_t)0x80000) -#define FMODE_CREATED ((__force fmode_t)0x100000) +#define FMODE_OPENED ((__force fmode_t)(1 << 19)) +#define FMODE_CREATED ((__force fmode_t)(1 << 20)) /* File is stream-like */ -#define FMODE_STREAM ((__force fmode_t)0x200000) +#define FMODE_STREAM ((__force fmode_t)(1 << 21)) /* File supports DIRECT IO */ -#define FMODE_CAN_ODIRECT ((__force fmode_t)0x400000) +#define FMODE_CAN_ODIRECT ((__force fmode_t)(1 << 22)) -#define FMODE_NOREUSE ((__force fmode_t)0x800000) +#define FMODE_NOREUSE ((__force fmode_t)(1 << 23)) -/* File supports non-exclusive O_DIRECT writes from multiple threads */ -#define FMODE_DIO_PARALLEL_WRITE ((__force fmode_t)0x1000000) +/* FMODE_* bit 24 */ /* File is embedded in backing_file object */ -#define FMODE_BACKING ((__force fmode_t)0x2000000) +#define FMODE_BACKING ((__force fmode_t)(1 << 25)) /* File was opened by fanotify and shouldn't generate fanotify events */ -#define FMODE_NONOTIFY ((__force fmode_t)0x4000000) +#define FMODE_NONOTIFY ((__force fmode_t)(1 << 26)) /* File is capable of returning -EAGAIN if I/O will block */ -#define FMODE_NOWAIT ((__force fmode_t)0x8000000) +#define FMODE_NOWAIT ((__force fmode_t)(1 << 27)) /* File represents mount that needs unmounting */ -#define FMODE_NEED_UNMOUNT ((__force fmode_t)0x10000000) +#define FMODE_NEED_UNMOUNT ((__force fmode_t)(1 << 28)) /* File does not contribute to nr_files count */ -#define FMODE_NOACCOUNT ((__force fmode_t)0x20000000) - -/* File supports async buffered reads */ -#define FMODE_BUF_RASYNC ((__force fmode_t)0x40000000) - -/* File supports async nowait buffered writes */ -#define FMODE_BUF_WASYNC ((__force fmode_t)0x80000000) +#define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29)) /* * Attribute flags. These should be or-ed together to figure out what @@ -319,6 +319,7 @@ struct readahead_control; #define IOCB_SYNC (__force int) RWF_SYNC #define IOCB_NOWAIT (__force int) RWF_NOWAIT #define IOCB_APPEND (__force int) RWF_APPEND +#define IOCB_ATOMIC (__force int) RWF_ATOMIC /* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) @@ -353,6 +354,7 @@ struct readahead_control; { IOCB_SYNC, "SYNC" }, \ { IOCB_NOWAIT, "NOWAIT" }, \ { IOCB_APPEND, "APPEND" }, \ + { IOCB_ATOMIC, "ATOMIC"}, \ { IOCB_EVENTFD, "EVENTFD"}, \ { IOCB_DIRECT, "DIRECT" }, \ { IOCB_WRITE, "WRITE" }, \ @@ -622,8 +624,6 @@ is_uncached_acl(struct posix_acl *acl) #define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 -struct fsnotify_mark_connector; - /* * Keep mostly read-only and often accessed (especially for * the RCU path lookup and 'stat' data) fields at the beginning @@ -664,9 +664,13 @@ struct inode { }; dev_t i_rdev; loff_t i_size; - struct timespec64 __i_atime; - struct timespec64 __i_mtime; - struct timespec64 __i_ctime; /* use inode_*_ctime accessors! */ + time64_t i_atime_sec; + time64_t i_mtime_sec; + time64_t i_ctime_sec; + u32 i_atime_nsec; + u32 i_mtime_nsec; + u32 i_ctime_nsec; + u32 i_generation; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; u8 i_blkbits; @@ -723,10 +727,10 @@ struct inode { unsigned i_dir_seq; }; - __u32 i_generation; #ifdef CONFIG_FSNOTIFY __u32 i_fsnotify_mask; /* all events this inode cares about */ + /* 32-bit hole reserved for expanding i_fsnotify_mask */ struct fsnotify_mark_connector __rcu *i_fsnotify_marks; #endif @@ -1035,12 +1039,13 @@ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ - unsigned char f_handle[]; + unsigned char f_handle[] __counted_by(handle_bytes); }; static inline struct file *get_file(struct file *f) { - atomic_long_inc(&f->f_count); + long prior = atomic_long_fetch_inc_relaxed(&f->f_count); + WARN_ONCE(!prior, "struct file::f_count incremented from zero; use-after-free condition present!\n"); return f; } @@ -1177,7 +1182,7 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ #define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 #define SB_I_UNTRUSTED_MOUNTER 0x00000040 -#define SB_I_EVM_UNSUPPORTED 0x00000080 +#define SB_I_EVM_HMAC_UNSUPPORTED 0x00000080 #define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ #define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ @@ -1251,7 +1256,7 @@ struct super_block { /* * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and - * s_fsnotify_marks together for cache efficiency. They are frequently + * s_fsnotify_info together for cache efficiency. They are frequently * accessed and rarely modified. */ void *s_fs_info; /* Filesystem private info */ @@ -1263,7 +1268,7 @@ struct super_block { time64_t s_time_max; #ifdef CONFIG_FSNOTIFY __u32 s_fsnotify_mask; - struct fsnotify_mark_connector __rcu *s_fsnotify_marks; + struct fsnotify_sb_info *s_fsnotify_info; #endif /* @@ -1304,12 +1309,6 @@ struct super_block { /* Number of inodes with nlink == 0 but still referenced */ atomic_long_t s_remove_count; - /* - * Number of inode/mount/sb objects that are being watched, note that - * inodes objects are currently double-accounted. - */ - atomic_long_t s_fsnotify_connectors; - /* Read-only state of the superblock is being changed */ int s_readonly_remount; @@ -1547,23 +1546,27 @@ struct timespec64 inode_set_ctime_current(struct inode *inode); static inline time64_t inode_get_atime_sec(const struct inode *inode) { - return inode->__i_atime.tv_sec; + return inode->i_atime_sec; } static inline long inode_get_atime_nsec(const struct inode *inode) { - return inode->__i_atime.tv_nsec; + return inode->i_atime_nsec; } static inline struct timespec64 inode_get_atime(const struct inode *inode) { - return inode->__i_atime; + struct timespec64 ts = { .tv_sec = inode_get_atime_sec(inode), + .tv_nsec = inode_get_atime_nsec(inode) }; + + return ts; } static inline struct timespec64 inode_set_atime_to_ts(struct inode *inode, struct timespec64 ts) { - inode->__i_atime = ts; + inode->i_atime_sec = ts.tv_sec; + inode->i_atime_nsec = ts.tv_nsec; return ts; } @@ -1572,28 +1575,32 @@ static inline struct timespec64 inode_set_atime(struct inode *inode, { struct timespec64 ts = { .tv_sec = sec, .tv_nsec = nsec }; + return inode_set_atime_to_ts(inode, ts); } static inline time64_t inode_get_mtime_sec(const struct inode *inode) { - return inode->__i_mtime.tv_sec; + return inode->i_mtime_sec; } static inline long inode_get_mtime_nsec(const struct inode *inode) { - return inode->__i_mtime.tv_nsec; + return inode->i_mtime_nsec; } static inline struct timespec64 inode_get_mtime(const struct inode *inode) { - return inode->__i_mtime; + struct timespec64 ts = { .tv_sec = inode_get_mtime_sec(inode), + .tv_nsec = inode_get_mtime_nsec(inode) }; + return ts; } static inline struct timespec64 inode_set_mtime_to_ts(struct inode *inode, struct timespec64 ts) { - inode->__i_mtime = ts; + inode->i_mtime_sec = ts.tv_sec; + inode->i_mtime_nsec = ts.tv_nsec; return ts; } @@ -1607,23 +1614,27 @@ static inline struct timespec64 inode_set_mtime(struct inode *inode, static inline time64_t inode_get_ctime_sec(const struct inode *inode) { - return inode->__i_ctime.tv_sec; + return inode->i_ctime_sec; } static inline long inode_get_ctime_nsec(const struct inode *inode) { - return inode->__i_ctime.tv_nsec; + return inode->i_ctime_nsec; } static inline struct timespec64 inode_get_ctime(const struct inode *inode) { - return inode->__i_ctime; + struct timespec64 ts = { .tv_sec = inode_get_ctime_sec(inode), + .tv_nsec = inode_get_ctime_nsec(inode) }; + + return ts; } static inline struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts) { - inode->__i_ctime = ts; + inode->i_ctime_sec = ts.tv_sec; + inode->i_ctime_nsec = ts.tv_nsec; return ts; } @@ -1908,7 +1919,7 @@ struct file *kernel_tmpfile_open(struct mnt_idmap *idmap, umode_t mode, int open_flag, const struct cred *cred); struct file *kernel_file_open(const struct path *path, int flags, - struct inode *inode, const struct cred *cred); + const struct cred *cred); int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), @@ -1935,6 +1946,8 @@ void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode, extern bool may_open_dev(const struct path *path); umode_t mode_strip_sgid(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode); +bool in_group_or_capable(struct mnt_idmap *idmap, + const struct inode *inode, vfsgid_t vfsgid); /* * This is the "filldir" function type, used by readdir() to let @@ -2003,8 +2016,11 @@ struct iov_iter; struct io_uring_cmd; struct offset_ctx; +typedef unsigned int __bitwise fop_flags_t; + struct file_operations { struct module *owner; + fop_flags_t fop_flags; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); @@ -2017,7 +2033,6 @@ struct file_operations { long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); - unsigned long mmap_supported_flags; int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); @@ -2048,6 +2063,17 @@ struct file_operations { unsigned int poll_flags); } __randomize_layout; +/* Supports async buffered reads */ +#define FOP_BUFFER_RASYNC ((__force fop_flags_t)(1 << 0)) +/* Supports async buffered writes */ +#define FOP_BUFFER_WASYNC ((__force fop_flags_t)(1 << 1)) +/* Supports synchronous page faults for mappings */ +#define FOP_MMAP_SYNC ((__force fop_flags_t)(1 << 2)) +/* Supports non-exclusive O_DIRECT writes from multiple threads */ +#define FOP_DIO_PARALLEL_WRITE ((__force fop_flags_t)(1 << 3)) +/* Contains huge pages */ +#define FOP_HUGE_PAGES ((__force fop_flags_t)(1 << 4)) + /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, int (*) (struct file *, struct dir_context *)); @@ -2098,18 +2124,6 @@ struct inode_operations { struct offset_ctx *(*get_offset_ctx)(struct inode *inode); } ____cacheline_aligned; -static inline ssize_t call_read_iter(struct file *file, struct kiocb *kio, - struct iov_iter *iter) -{ - return file->f_op->read_iter(kio, iter); -} - -static inline ssize_t call_write_iter(struct file *file, struct kiocb *kio, - struct iov_iter *iter) -{ - return file->f_op->write_iter(kio, iter); -} - static inline int call_mmap(struct file *file, struct vm_area_struct *vma) { return file->f_op->mmap(file, vma); @@ -2119,6 +2133,7 @@ extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); +int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write); int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *len, unsigned int remap_flags, @@ -2253,7 +2268,13 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) + +#ifdef CONFIG_SWAP #define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) +#else +#define IS_SWAPFILE(inode) ((void)(inode), 0U) +#endif + #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) #define IS_IMA(inode) ((inode)->i_flags & S_IMA) #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) @@ -2371,6 +2392,9 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. * + * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding + * i_count. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2394,6 +2418,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_DONTCACHE (1 << 16) #define I_SYNC_QUEUED (1 << 17) #define I_PINNING_NETFS_WB (1 << 18) +#define __I_LRU_ISOLATING 19 +#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) @@ -2686,7 +2712,7 @@ static inline struct file *file_clone_open(struct file *file) } extern int filp_close(struct file *, fl_owner_t id); -extern struct filename *getname_flags(const char __user *, int, int *); +extern struct filename *getname_flags(const char __user *, int); extern struct filename *getname_uflags(const char __user *, int); extern struct filename *getname(const char __user *); extern struct filename *getname_kernel(const char *); @@ -3030,7 +3056,12 @@ extern struct inode *inode_insert5(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data); -extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *); +struct inode *iget5_locked(struct super_block *, unsigned long, + int (*test)(struct inode *, void *), + int (*set)(struct inode *, void *), void *); +struct inode *iget5_locked_rcu(struct super_block *, unsigned long, + int (*test)(struct inode *, void *), + int (*set)(struct inode *, void *), void *); extern struct inode * iget_locked(struct super_block *, unsigned long); extern struct inode *find_inode_nowait(struct super_block *, unsigned long, @@ -3085,11 +3116,7 @@ int setattr_should_drop_sgid(struct mnt_idmap *idmap, * This must be used for allocating filesystems specific inodes to set * up the inode reclaim context correctly. */ -static inline void * -alloc_inode_sb(struct super_block *sb, struct kmem_cache *cache, gfp_t gfp) -{ - return kmem_cache_alloc_lru(cache, &sb->s_inode_lru, gfp); -} +#define alloc_inode_sb(_sb, _cache, _gfp) kmem_cache_alloc_lru(_cache, &_sb->s_inode_lru, _gfp) extern void __insert_inode_hash(struct inode *, unsigned long hashval); static inline void insert_inode_hash(struct inode *inode) @@ -3236,6 +3263,9 @@ extern const struct inode_operations page_symlink_inode_operations; extern void kfree_link(void *); void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *); void generic_fill_statx_attr(struct inode *inode, struct kstat *stat); +void generic_fill_statx_atomic_writes(struct kstat *stat, + unsigned int unit_min, + unsigned int unit_max); extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int); extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int); void __inode_add_bytes(struct inode *inode, loff_t bytes); @@ -3340,6 +3370,8 @@ void simple_offset_init(struct offset_ctx *octx); int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); int simple_offset_empty(struct dentry *dentry); +int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry); int simple_offset_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, @@ -3354,6 +3386,10 @@ extern int generic_file_fsync(struct file *, loff_t, loff_t, int); extern int generic_check_addressable(unsigned, u64); extern void generic_set_sb_d_ops(struct super_block *sb); +extern int generic_ci_match(const struct inode *parent, + const struct qstr *name, + const struct qstr *folded_name, + const u8 *de_name, u32 de_name_len); static inline bool sb_has_encoding(const struct super_block *sb) { @@ -3406,7 +3442,8 @@ static inline int iocb_flags(struct file *file) return res; } -static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) +static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags, + int rw_type) { int kiocb_flags = 0; @@ -3425,6 +3462,12 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) return -EOPNOTSUPP; kiocb_flags |= IOCB_NOIO; } + if (flags & RWF_ATOMIC) { + if (rw_type != WRITE) + return -EOPNOTSUPP; + if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE)) + return -EOPNOTSUPP; + } kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; @@ -3439,20 +3482,6 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) return 0; } -static inline ino_t parent_ino(struct dentry *dentry) -{ - ino_t res; - - /* - * Don't strictly need d_lock here? If the parent ino could change - * then surely we'd have a deeper race in the caller? - */ - spin_lock(&dentry->d_lock); - res = dentry->d_parent->d_inode->i_ino; - spin_unlock(&dentry->d_lock); - return res; -} - /* Transaction based IO helpers */ /* @@ -3577,7 +3606,7 @@ static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx) static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx) { return ctx->actor(ctx, "..", 2, ctx->pos, - parent_ino(file->f_path.dentry), DT_DIR); + d_parent_ino(file->f_path.dentry), DT_DIR); } static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx) { @@ -3616,4 +3645,23 @@ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, extern int generic_fadvise(struct file *file, loff_t offset, loff_t len, int advice); +static inline bool vfs_empty_path(int dfd, const char __user *path) +{ + char c; + + if (dfd < 0) + return false; + + /* We now allow NULL to be used for empty path. */ + if (!path) + return true; + + if (unlikely(get_user(c, path))) + return false; + + return !c; +} + +bool generic_atomic_write_valid(struct iov_iter *iter, loff_t pos); + #endif /* _LINUX_FS_H */ diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 01542c4b87a2..6cf713a7e6c6 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -28,7 +28,7 @@ typedef int fs_param_type(struct p_log *, */ fs_param_type fs_param_is_bool, fs_param_is_u32, fs_param_is_s32, fs_param_is_u64, fs_param_is_enum, fs_param_is_string, fs_param_is_blob, fs_param_is_blockdev, - fs_param_is_path, fs_param_is_fd; + fs_param_is_path, fs_param_is_fd, fs_param_is_uid, fs_param_is_gid; /* * Specification of the type of value a parameter wants. @@ -57,6 +57,8 @@ struct fs_parse_result { int int_32; /* For spec_s32/spec_enum */ unsigned int uint_32; /* For spec_u32{,_octal,_hex}/spec_enum */ u64 uint_64; /* For spec_u64 */ + kuid_t uid; + kgid_t gid; }; }; @@ -131,5 +133,11 @@ static inline bool fs_validate_description(const char *name, #define fsparam_bdev(NAME, OPT) __fsparam(fs_param_is_blockdev, NAME, OPT, 0, NULL) #define fsparam_path(NAME, OPT) __fsparam(fs_param_is_path, NAME, OPT, 0, NULL) #define fsparam_fd(NAME, OPT) __fsparam(fs_param_is_fd, NAME, OPT, 0, NULL) +#define fsparam_uid(NAME, OPT) __fsparam(fs_param_is_uid, NAME, OPT, 0, NULL) +#define fsparam_gid(NAME, OPT) __fsparam(fs_param_is_gid, NAME, OPT, 0, NULL) + +/* String parameter that allows empty argument */ +#define fsparam_string_empty(NAME, OPT) \ + __fsparam(fs_param_is_string, NAME, OPT, fs_param_can_be_empty, NULL) #endif /* _LINUX_FS_PARSER_H */ diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index bdf7f3eddf0a..4c91a019972b 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -19,6 +19,7 @@ enum fscache_cache_trace; enum fscache_cookie_trace; enum fscache_access_trace; +enum fscache_volume_trace; enum fscache_cache_state { FSCACHE_CACHE_IS_NOT_PRESENT, /* No cache is present for this name */ @@ -97,6 +98,11 @@ extern void fscache_withdraw_cookie(struct fscache_cookie *cookie); extern void fscache_io_error(struct fscache_cache *cache); +extern struct fscache_volume * +fscache_try_get_volume(struct fscache_volume *volume, + enum fscache_volume_trace where); +extern void fscache_put_volume(struct fscache_volume *volume, + enum fscache_volume_trace where); extern void fscache_end_volume_access(struct fscache_volume *volume, struct fscache_cookie *cookie, enum fscache_access_trace why); diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 6e8562cbcc43..9de27643607f 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -172,9 +172,12 @@ extern void __fscache_invalidate(struct fscache_cookie *, const void *, loff_t, extern int __fscache_begin_read_operation(struct netfs_cache_resources *, struct fscache_cookie *); extern int __fscache_begin_write_operation(struct netfs_cache_resources *, struct fscache_cookie *); -extern void __fscache_write_to_cache(struct fscache_cookie *, struct address_space *, - loff_t, size_t, loff_t, netfs_io_terminated_t, void *, - bool); +void __fscache_write_to_cache(struct fscache_cookie *cookie, + struct address_space *mapping, + loff_t start, size_t len, loff_t i_size, + netfs_io_terminated_t term_func, + void *term_func_priv, + bool using_pgpriv2, bool cond); extern void __fscache_clear_page_bits(struct address_space *, loff_t, size_t); /** @@ -597,7 +600,8 @@ static inline void fscache_clear_page_bits(struct address_space *mapping, * @i_size: The new size of the inode * @term_func: The function to call upon completion * @term_func_priv: The private data for @term_func - * @caching: If PG_fscache has been set + * @using_pgpriv2: If we're using PG_private_2 to mark in-progress write + * @caching: If we actually want to do the caching * * Helper function for a netfs to write dirty data from an inode into the cache * object that's backing it. @@ -608,19 +612,21 @@ static inline void fscache_clear_page_bits(struct address_space *mapping, * marked with PG_fscache. * * If given, @term_func will be called upon completion and supplied with - * @term_func_priv. Note that the PG_fscache flags will have been cleared by - * this point, so the netfs must retain its own pin on the mapping. + * @term_func_priv. Note that if @using_pgpriv2 is set, the PG_private_2 flags + * will have been cleared by this point, so the netfs must retain its own pin + * on the mapping. */ static inline void fscache_write_to_cache(struct fscache_cookie *cookie, struct address_space *mapping, loff_t start, size_t len, loff_t i_size, netfs_io_terminated_t term_func, void *term_func_priv, - bool caching) + bool using_pgpriv2, bool caching) { if (caching) __fscache_write_to_cache(cookie, mapping, start, len, i_size, - term_func, term_func_priv, caching); + term_func, term_func_priv, + using_pgpriv2, caching); else if (term_func) term_func(term_func_priv, -ENOBUFS, false); diff --git a/include/linux/fsi.h b/include/linux/fsi.h index 3df8c54868df..8c5eef808788 100644 --- a/include/linux/fsi.h +++ b/include/linux/fsi.h @@ -44,7 +44,7 @@ struct fsi_driver { }; #define to_fsi_dev(devp) container_of(devp, struct fsi_device, dev) -#define to_fsi_drv(drvp) container_of(drvp, struct fsi_driver, drv) +#define to_fsi_drv(drvp) container_of_const(drvp, struct fsi_driver, drv) extern int fsi_driver_register(struct fsi_driver *fsi_drv); extern void fsi_driver_unregister(struct fsi_driver *fsi_drv); diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index a1b3de87a3d1..083c860fd28e 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -56,7 +56,7 @@ struct fsl_mc_driver { }; #define to_fsl_mc_driver(_drv) \ - container_of(_drv, struct fsl_mc_driver, driver) + container_of_const(_drv, struct fsl_mc_driver, driver) /** * enum fsl_mc_pool_type - Types of allocatable MC bus resources diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 1a9de119a0f7..278620e063ab 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -17,10 +17,23 @@ #include <linux/slab.h> #include <linux/bug.h> +/* Are there any inode/mount/sb objects watched with priority prio or above? */ +static inline bool fsnotify_sb_has_priority_watchers(struct super_block *sb, + int prio) +{ + struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb); + + /* Were any marks ever added to any object on this sb? */ + if (!sbinfo) + return false; + + return atomic_long_read(&sbinfo->watched_objects[prio]); +} + /* Are there any inode/mount/sb objects that are being watched at all? */ static inline bool fsnotify_sb_has_watchers(struct super_block *sb) { - return atomic_long_read(&sb->s_fsnotify_connectors); + return fsnotify_sb_has_priority_watchers(sb, 0); } /* @@ -99,10 +112,22 @@ static inline int fsnotify_file(struct file *file, __u32 mask) { const struct path *path; - if (file->f_mode & FMODE_NONOTIFY) + /* + * FMODE_NONOTIFY are fds generated by fanotify itself which should not + * generate new events. We also don't want to generate events for + * FMODE_PATH fds (involves open & close events) as they are just + * handle creation / destruction events and not "real" file events. + */ + if (file->f_mode & (FMODE_NONOTIFY | FMODE_PATH)) return 0; path = &file->f_path; + /* Permission events require group prio >= FSNOTIFY_PRIO_CONTENT */ + if (mask & ALL_FSNOTIFY_PERM_EVENTS && + !fsnotify_sb_has_priority_watchers(path->dentry->d_sb, + FSNOTIFY_PRIO_CONTENT)) + return 0; + return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); } diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 8f40c349b228..8be029bc50b1 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -177,6 +177,17 @@ struct fsnotify_event { }; /* + * fsnotify group priorities. + * Events are sent in order from highest priority to lowest priority. + */ +enum fsnotify_group_prio { + FSNOTIFY_PRIO_NORMAL = 0, /* normal notifiers, no permissions */ + FSNOTIFY_PRIO_CONTENT, /* fanotify permission events */ + FSNOTIFY_PRIO_PRE_CONTENT, /* fanotify pre-content events */ + __FSNOTIFY_PRIO_NUM +}; + +/* * A group is a "thing" that wants to receive notification about filesystem * events. The mask holds the subset of event types this group cares about. * refcnt on a group is up to the implementor and at any moment if it goes 0 @@ -201,14 +212,7 @@ struct fsnotify_group { wait_queue_head_t notification_waitq; /* read() on the notification file blocks on this waitq */ unsigned int q_len; /* events on the queue */ unsigned int max_events; /* maximum events allowed on the list */ - /* - * Valid fsnotify group priorities. Events are send in order from highest - * priority to lowest priority. We default to the lowest priority. - */ - #define FS_PRIO_0 0 /* normal notifiers, no permissions */ - #define FS_PRIO_1 1 /* fanotify content based access control */ - #define FS_PRIO_2 2 /* fanotify pre-content access */ - unsigned int priority; + enum fsnotify_group_prio priority; /* priority for sending events */ bool shutdown; /* group is being shut down, don't queue more events */ #define FSNOTIFY_GROUP_USER 0x01 /* user allocated group */ @@ -457,13 +461,6 @@ FSNOTIFY_ITER_FUNCS(sb, SB) type++) /* - * fsnotify_connp_t is what we embed in objects which connector can be attached - * to. fsnotify_connp_t * is how we refer from connector back to object. - */ -struct fsnotify_mark_connector; -typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t; - -/* * Inode/vfsmount/sb point to this structure which tracks all marks attached to * the inode/vfsmount/sb. The reference to inode/vfsmount/sb is held by this * structure. We destroy this structure when there are no more marks attached @@ -471,12 +468,14 @@ typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t; */ struct fsnotify_mark_connector { spinlock_t lock; - unsigned short type; /* Type of object [lock] */ + unsigned char type; /* Type of object [lock] */ + unsigned char prio; /* Highest priority group */ +#define FSNOTIFY_CONN_FLAG_IS_WATCHED 0x01 #define FSNOTIFY_CONN_FLAG_HAS_IREF 0x02 unsigned short flags; /* flags [lock] */ union { /* Object pointer [lock] */ - fsnotify_connp_t *obj; + void *obj; /* Used listing heads to free after srcu period expires */ struct fsnotify_mark_connector *destroy_next; }; @@ -484,6 +483,37 @@ struct fsnotify_mark_connector { }; /* + * Container for per-sb fsnotify state (sb marks and more). + * Attached lazily on first marked object on the sb and freed when killing sb. + */ +struct fsnotify_sb_info { + struct fsnotify_mark_connector __rcu *sb_marks; + /* + * Number of inode/mount/sb objects that are being watched in this sb. + * Note that inodes objects are currently double-accounted. + * + * The value in watched_objects[prio] is the number of objects that are + * watched by groups of priority >= prio, so watched_objects[0] is the + * total number of watched objects in this sb. + */ + atomic_long_t watched_objects[__FSNOTIFY_PRIO_NUM]; +}; + +static inline struct fsnotify_sb_info *fsnotify_sb_info(struct super_block *sb) +{ +#ifdef CONFIG_FSNOTIFY + return READ_ONCE(sb->s_fsnotify_info); +#else + return NULL; +#endif +} + +static inline atomic_long_t *fsnotify_sb_watched_objects(struct super_block *sb) +{ + return &fsnotify_sb_info(sb)->watched_objects[0]; +} + +/* * A mark is simply an object attached to an in core inode which allows an * fsnotify listener to indicate they are either no longer interested in events * of a type matching mask or only interested in those events. @@ -546,6 +576,7 @@ extern int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data extern void __fsnotify_inode_delete(struct inode *inode); extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); extern void fsnotify_sb_delete(struct super_block *sb); +extern void fsnotify_sb_free(struct super_block *sb); extern u32 fsnotify_get_cookie(void); static inline __u32 fsnotify_parent_needed_mask(__u32 mask) @@ -563,12 +594,14 @@ static inline __u32 fsnotify_parent_needed_mask(__u32 mask) static inline int fsnotify_inode_watches_children(struct inode *inode) { + __u32 parent_mask = READ_ONCE(inode->i_fsnotify_mask); + /* FS_EVENT_ON_CHILD is set if the inode may care */ - if (!(inode->i_fsnotify_mask & FS_EVENT_ON_CHILD)) + if (!(parent_mask & FS_EVENT_ON_CHILD)) return 0; /* this inode might care about child events, does it care about the * specific set of events that can happen on a child? */ - return inode->i_fsnotify_mask & FS_EVENTS_POSS_ON_CHILD; + return parent_mask & FS_EVENTS_POSS_ON_CHILD; } /* @@ -582,7 +615,7 @@ static inline void fsnotify_update_flags(struct dentry *dentry) /* * Serialisation of setting PARENT_WATCHED on the dentries is provided * by d_lock. If inotify_inode_watched changes after we have taken - * d_lock, the following __fsnotify_update_child_dentry_flags call will + * d_lock, the following fsnotify_set_children_dentry_flags call will * find our entry, so it will spin until we complete here, and update * us with the new state. */ @@ -758,30 +791,35 @@ extern void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn); extern void fsnotify_init_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); /* Find mark belonging to given group in the list of marks */ -extern struct fsnotify_mark *fsnotify_find_mark(fsnotify_connp_t *connp, - struct fsnotify_group *group); +struct fsnotify_mark *fsnotify_find_mark(void *obj, unsigned int obj_type, + struct fsnotify_group *group); /* attach the mark to the object */ -extern int fsnotify_add_mark(struct fsnotify_mark *mark, - fsnotify_connp_t *connp, unsigned int obj_type, - int add_flags); -extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark, - fsnotify_connp_t *connp, - unsigned int obj_type, int add_flags); +int fsnotify_add_mark(struct fsnotify_mark *mark, void *obj, + unsigned int obj_type, int add_flags); +int fsnotify_add_mark_locked(struct fsnotify_mark *mark, void *obj, + unsigned int obj_type, int add_flags); /* attach the mark to the inode */ static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark, struct inode *inode, int add_flags) { - return fsnotify_add_mark(mark, &inode->i_fsnotify_marks, - FSNOTIFY_OBJ_TYPE_INODE, add_flags); + return fsnotify_add_mark(mark, inode, FSNOTIFY_OBJ_TYPE_INODE, + add_flags); } static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark, struct inode *inode, int add_flags) { - return fsnotify_add_mark_locked(mark, &inode->i_fsnotify_marks, - FSNOTIFY_OBJ_TYPE_INODE, add_flags); + return fsnotify_add_mark_locked(mark, inode, FSNOTIFY_OBJ_TYPE_INODE, + add_flags); +} + +static inline struct fsnotify_mark *fsnotify_find_inode_mark( + struct inode *inode, + struct fsnotify_group *group) +{ + return fsnotify_find_mark(inode, FSNOTIFY_OBJ_TYPE_INODE, group); } /* given a group and a mark, flag mark to be freed when all references are dropped */ @@ -845,6 +883,9 @@ static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt) static inline void fsnotify_sb_delete(struct super_block *sb) {} +static inline void fsnotify_sb_free(struct super_block *sb) +{} + static inline void fsnotify_update_flags(struct dentry *dentry) {} diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 54d53f345d14..fd5e84d0ec47 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -83,19 +83,18 @@ static inline void early_trace_init(void) { } struct module; struct ftrace_hash; -struct ftrace_direct_func; #if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_MODULES) && \ defined(CONFIG_DYNAMIC_FTRACE) -const char * +int ftrace_mod_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym); #else -static inline const char * +static inline int ftrace_mod_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym) { - return NULL; + return 0; } #endif @@ -228,6 +227,7 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops); * ftrace_enabled. * DIRECT - Used by the direct ftrace_ops helper for direct functions * (internal ftrace only, should not be used by others) + * SUBOP - Is controlled by another op in field managed. */ enum { FTRACE_OPS_FL_ENABLED = BIT(0), @@ -248,6 +248,7 @@ enum { FTRACE_OPS_FL_TRACE_ARRAY = BIT(15), FTRACE_OPS_FL_PERMANENT = BIT(16), FTRACE_OPS_FL_DIRECT = BIT(17), + FTRACE_OPS_FL_SUBOP = BIT(18), }; #ifndef CONFIG_DYNAMIC_FTRACE_WITH_ARGS @@ -335,7 +336,9 @@ struct ftrace_ops { unsigned long trampoline; unsigned long trampoline_size; struct list_head list; + struct list_head subop_list; ftrace_ops_func_t ops_func; + struct ftrace_ops *managed; #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS unsigned long direct_call; #endif @@ -414,7 +417,6 @@ struct ftrace_func_entry { }; #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS -extern int ftrace_direct_func_count; unsigned long ftrace_find_rec_direct(unsigned long ip); int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr); int unregister_ftrace_direct(struct ftrace_ops *ops, unsigned long addr, @@ -426,7 +428,6 @@ void ftrace_stub_direct_tramp(void); #else struct ftrace_ops; -# define ftrace_direct_func_count 0 static inline unsigned long ftrace_find_rec_direct(unsigned long ip) { return 0; @@ -470,7 +471,7 @@ static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, extern int stack_tracer_enabled; -int stack_trace_sysctl(struct ctl_table *table, int write, void *buffer, +int stack_trace_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); /* DO NOT MODIFY THIS VARIABLE DIRECTLY! */ @@ -512,6 +513,15 @@ static inline void stack_tracer_disable(void) { } static inline void stack_tracer_enable(void) { } #endif +enum { + FTRACE_UPDATE_CALLS = (1 << 0), + FTRACE_DISABLE_CALLS = (1 << 1), + FTRACE_UPDATE_TRACE_FUNC = (1 << 2), + FTRACE_START_FUNC_RET = (1 << 3), + FTRACE_STOP_FUNC_RET = (1 << 4), + FTRACE_MAY_SLEEP = (1 << 5), +}; + #ifdef CONFIG_DYNAMIC_FTRACE void ftrace_arch_code_modify_prepare(void); @@ -606,15 +616,6 @@ void ftrace_set_global_notrace(unsigned char *buf, int len, int reset); void ftrace_free_filter(struct ftrace_ops *ops); void ftrace_ops_set_global_filter(struct ftrace_ops *ops); -enum { - FTRACE_UPDATE_CALLS = (1 << 0), - FTRACE_DISABLE_CALLS = (1 << 1), - FTRACE_UPDATE_TRACE_FUNC = (1 << 2), - FTRACE_START_FUNC_RET = (1 << 3), - FTRACE_STOP_FUNC_RET = (1 << 4), - FTRACE_MAY_SLEEP = (1 << 5), -}; - /* * The FTRACE_UPDATE_* enum is used to pass information back * from the ftrace_update_record() and ftrace_test_record() @@ -822,7 +823,8 @@ static inline int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr); #if defined(CONFIG_DYNAMIC_FTRACE_WITH_REGS) || \ - defined(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS) + defined(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS) || \ + defined(CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS) /** * ftrace_modify_call - convert from one addr to another (no nop) * @rec: the call site record (e.g. mcount/fentry) @@ -1029,19 +1031,31 @@ struct ftrace_graph_ret { unsigned long long rettime; } __packed; +struct fgraph_ops; + /* Type of the callback handlers for tracing function graph*/ -typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *); /* return */ -typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *); /* entry */ +typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *, + struct fgraph_ops *); /* return */ +typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *, + struct fgraph_ops *); /* entry */ -extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace); +extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace, struct fgraph_ops *gops); +bool ftrace_pids_enabled(struct ftrace_ops *ops); #ifdef CONFIG_FUNCTION_GRAPH_TRACER struct fgraph_ops { trace_func_graph_ent_t entryfunc; trace_func_graph_ret_t retfunc; + struct ftrace_ops ops; /* for the hash lists */ + void *private; + trace_func_graph_ent_t saved_func; + int idx; }; +void *fgraph_reserve_data(int idx, int size_bytes); +void *fgraph_retrieve_data(int idx, int *size_bytes); + /* * Stack of return addresses for functions * of a thread. @@ -1057,9 +1071,7 @@ struct ftrace_ret_stack { #ifdef HAVE_FUNCTION_GRAPH_FP_TEST unsigned long fp; #endif -#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR unsigned long *retp; -#endif }; /* @@ -1074,10 +1086,11 @@ function_graph_enter(unsigned long ret, unsigned long func, unsigned long frame_pointer, unsigned long *retp); struct ftrace_ret_stack * -ftrace_graph_get_ret_stack(struct task_struct *task, int idx); +ftrace_graph_get_ret_stack(struct task_struct *task, int skip); unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, unsigned long ret, unsigned long *retp); +unsigned long *fgraph_get_task_var(struct fgraph_ops *gops); /* * Sometimes we don't want to trace a function with the function @@ -1116,6 +1129,9 @@ extern void ftrace_graph_init_task(struct task_struct *t); extern void ftrace_graph_exit_task(struct task_struct *t); extern void ftrace_graph_init_idle_task(struct task_struct *t, int cpu); +/* Used by assembly, but to quiet sparse warnings */ +extern struct ftrace_ops *function_trace_op; + static inline void pause_graph_tracing(void) { atomic_inc(¤t->tracing_graph_pause); @@ -1159,7 +1175,7 @@ extern int tracepoint_printk; extern void disable_trace_on_warning(void); extern int __disable_trace_on_warning; -int tracepoint_printk_sysctl(struct ctl_table *table, int write, +int tracepoint_printk_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); #else /* CONFIG_TRACING */ diff --git a/include/linux/gameport.h b/include/linux/gameport.h index 07e370113b2b..86d62fdafd7a 100644 --- a/include/linux/gameport.h +++ b/include/linux/gameport.h @@ -58,7 +58,7 @@ struct gameport_driver { bool ignore; }; -#define to_gameport_driver(d) container_of(d, struct gameport_driver, driver) +#define to_gameport_driver(d) container_of_const(d, struct gameport_driver, driver) int gameport_open(struct gameport *gameport, struct gameport_driver *drv, int mode); void gameport_close(struct gameport *gameport); diff --git a/include/linux/genetlink.h b/include/linux/genetlink.h deleted file mode 100644 index c285968e437a..000000000000 --- a/include/linux/genetlink.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_GENERIC_NETLINK_H -#define __LINUX_GENERIC_NETLINK_H - -#include <uapi/linux/genetlink.h> - - -/* All generic netlink requests are serialized by a global lock. */ -extern void genl_lock(void); -extern void genl_unlock(void); - -/* for synchronisation between af_netlink and genetlink */ -extern atomic_t genl_sk_destructing_cnt; -extern wait_queue_head_t genl_sk_destructing_waitq; - -#define MODULE_ALIAS_GENL_FAMILY(family)\ - MODULE_ALIAS_NET_PF_PROTO_NAME(PF_NETLINK, NETLINK_GENERIC, "-family-" family) - -#endif /* __LINUX_GENERIC_NETLINK_H */ diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h index a419d93789ff..621b87a87d74 100644 --- a/include/linux/genl_magic_struct.h +++ b/include/linux/genl_magic_struct.h @@ -15,8 +15,8 @@ #endif #include <linux/args.h> -#include <linux/genetlink.h> #include <linux/types.h> +#include <net/genetlink.h> extern int CONCATENATE(GENL_MAGIC_FAMILY, _genl_register)(void); extern void CONCATENATE(GENL_MAGIC_FAMILY, _genl_unregister)(void); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index c775ea3c6015..f53f76e0b17e 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -6,6 +6,8 @@ #include <linux/mmzone.h> #include <linux/topology.h> +#include <linux/alloc_tag.h> +#include <linux/sched.h> struct vm_area_struct; struct mempolicy; @@ -155,6 +157,31 @@ static inline int gfp_zonelist(gfp_t flags) } /* + * gfp flag masking for nested internal allocations. + * + * For code that needs to do allocations inside the public allocation API (e.g. + * memory allocation tracking code) the allocations need to obey the caller + * allocation context constrains to prevent allocation context mismatches (e.g. + * GFP_KERNEL allocations in GFP_NOFS contexts) from potential deadlock + * situations. + * + * It is also assumed that these nested allocations are for internal kernel + * object storage purposes only and are not going to be used for DMA, etc. Hence + * we strip out all the zone information and leave just the context information + * intact. + * + * Further, internal allocations must fail before the higher level allocation + * can fail, so we must make them fail faster and fail silently. We also don't + * want them to deplete emergency reserves. Hence nested allocations must be + * prepared for these allocations to fail. + */ +static inline gfp_t gfp_nested_mask(gfp_t flags) +{ + return ((flags & (GFP_KERNEL | GFP_ATOMIC | __GFP_NOLOCKDEP)) | + (__GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN)); +} + +/* * We get the zone list from the current node and the gfp_mask. * This zone list contains a maximum of MAX_NUMNODES*MAX_NR_ZONES zones. * There are two zonelists per node, one for all zones with memory and @@ -175,42 +202,46 @@ static inline void arch_free_page(struct page *page, int order) { } static inline void arch_alloc_page(struct page *page, int order) { } #endif -struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid, +struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask); -struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid, +#define __alloc_pages(...) alloc_hooks(__alloc_pages_noprof(__VA_ARGS__)) + +struct folio *__folio_alloc_noprof(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask); +#define __folio_alloc(...) alloc_hooks(__folio_alloc_noprof(__VA_ARGS__)) -unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, +unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid, nodemask_t *nodemask, int nr_pages, struct list_head *page_list, struct page **page_array); +#define __alloc_pages_bulk(...) alloc_hooks(alloc_pages_bulk_noprof(__VA_ARGS__)) -unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp, +unsigned long alloc_pages_bulk_array_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array); +#define alloc_pages_bulk_array_mempolicy(...) \ + alloc_hooks(alloc_pages_bulk_array_mempolicy_noprof(__VA_ARGS__)) /* Bulk allocate order-0 pages */ -static inline unsigned long -alloc_pages_bulk_list(gfp_t gfp, unsigned long nr_pages, struct list_head *list) -{ - return __alloc_pages_bulk(gfp, numa_mem_id(), NULL, nr_pages, list, NULL); -} +#define alloc_pages_bulk_list(_gfp, _nr_pages, _list) \ + __alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, _list, NULL) -static inline unsigned long -alloc_pages_bulk_array(gfp_t gfp, unsigned long nr_pages, struct page **page_array) -{ - return __alloc_pages_bulk(gfp, numa_mem_id(), NULL, nr_pages, NULL, page_array); -} +#define alloc_pages_bulk_array(_gfp, _nr_pages, _page_array) \ + __alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, NULL, _page_array) static inline unsigned long -alloc_pages_bulk_array_node(gfp_t gfp, int nid, unsigned long nr_pages, struct page **page_array) +alloc_pages_bulk_array_node_noprof(gfp_t gfp, int nid, unsigned long nr_pages, + struct page **page_array) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); - return __alloc_pages_bulk(gfp, nid, NULL, nr_pages, NULL, page_array); + return alloc_pages_bulk_noprof(gfp, nid, NULL, nr_pages, NULL, page_array); } +#define alloc_pages_bulk_array_node(...) \ + alloc_hooks(alloc_pages_bulk_array_node_noprof(__VA_ARGS__)) + static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask) { gfp_t warn_gfp = gfp_mask & (__GFP_THISNODE|__GFP_NOWARN); @@ -230,82 +261,112 @@ static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask) * online. For more general interface, see alloc_pages_node(). */ static inline struct page * -__alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) +__alloc_pages_node_noprof(int nid, gfp_t gfp_mask, unsigned int order) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); warn_if_node_offline(nid, gfp_mask); - return __alloc_pages(gfp_mask, order, nid, NULL); + return __alloc_pages_noprof(gfp_mask, order, nid, NULL); } +#define __alloc_pages_node(...) alloc_hooks(__alloc_pages_node_noprof(__VA_ARGS__)) + static inline -struct folio *__folio_alloc_node(gfp_t gfp, unsigned int order, int nid) +struct folio *__folio_alloc_node_noprof(gfp_t gfp, unsigned int order, int nid) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); warn_if_node_offline(nid, gfp); - return __folio_alloc(gfp, order, nid, NULL); + return __folio_alloc_noprof(gfp, order, nid, NULL); } +#define __folio_alloc_node(...) alloc_hooks(__folio_alloc_node_noprof(__VA_ARGS__)) + /* * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE, * prefer the current CPU's closest node. Otherwise node must be valid and * online. */ -static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, - unsigned int order) +static inline struct page *alloc_pages_node_noprof(int nid, gfp_t gfp_mask, + unsigned int order) { if (nid == NUMA_NO_NODE) nid = numa_mem_id(); - return __alloc_pages_node(nid, gfp_mask, order); + return __alloc_pages_node_noprof(nid, gfp_mask, order); } +#define alloc_pages_node(...) alloc_hooks(alloc_pages_node_noprof(__VA_ARGS__)) + #ifdef CONFIG_NUMA -struct page *alloc_pages(gfp_t gfp, unsigned int order); -struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, +struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order); +struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, + struct mempolicy *mpol, pgoff_t ilx, int nid); +struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order); +struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid); -struct folio *folio_alloc(gfp_t gfp, unsigned int order); -struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma, +struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr, bool hugepage); #else -static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) +static inline struct page *alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { - return alloc_pages_node(numa_node_id(), gfp_mask, order); + return alloc_pages_node_noprof(numa_node_id(), gfp_mask, order); } -static inline struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, +static inline struct page *alloc_pages_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *mpol, pgoff_t ilx, int nid) { - return alloc_pages(gfp, order); + return alloc_pages_noprof(gfp, order); } -static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order) +static inline struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { return __folio_alloc_node(gfp, order, numa_node_id()); } -#define vma_alloc_folio(gfp, order, vma, addr, hugepage) \ - folio_alloc(gfp, order) +static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, + struct mempolicy *mpol, pgoff_t ilx, int nid) +{ + return folio_alloc_noprof(gfp, order); +} +#define vma_alloc_folio_noprof(gfp, order, vma, addr, hugepage) \ + folio_alloc_noprof(gfp, order) #endif + +#define alloc_pages(...) alloc_hooks(alloc_pages_noprof(__VA_ARGS__)) +#define alloc_pages_mpol(...) alloc_hooks(alloc_pages_mpol_noprof(__VA_ARGS__)) +#define folio_alloc(...) alloc_hooks(folio_alloc_noprof(__VA_ARGS__)) +#define folio_alloc_mpol(...) alloc_hooks(folio_alloc_mpol_noprof(__VA_ARGS__)) +#define vma_alloc_folio(...) alloc_hooks(vma_alloc_folio_noprof(__VA_ARGS__)) + #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) -static inline struct page *alloc_page_vma(gfp_t gfp, + +static inline struct page *alloc_page_vma_noprof(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr) { - struct folio *folio = vma_alloc_folio(gfp, 0, vma, addr, false); + struct folio *folio = vma_alloc_folio_noprof(gfp, 0, vma, addr, false); return &folio->page; } +#define alloc_page_vma(...) alloc_hooks(alloc_page_vma_noprof(__VA_ARGS__)) + +extern unsigned long get_free_pages_noprof(gfp_t gfp_mask, unsigned int order); +#define __get_free_pages(...) alloc_hooks(get_free_pages_noprof(__VA_ARGS__)) + +extern unsigned long get_zeroed_page_noprof(gfp_t gfp_mask); +#define get_zeroed_page(...) alloc_hooks(get_zeroed_page_noprof(__VA_ARGS__)) -extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); -extern unsigned long get_zeroed_page(gfp_t gfp_mask); +void *alloc_pages_exact_noprof(size_t size, gfp_t gfp_mask) __alloc_size(1); +#define alloc_pages_exact(...) alloc_hooks(alloc_pages_exact_noprof(__VA_ARGS__)) -void *alloc_pages_exact(size_t size, gfp_t gfp_mask) __alloc_size(1); void free_pages_exact(void *virt, size_t size); -__meminit void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2); -#define __get_free_page(gfp_mask) \ - __get_free_pages((gfp_mask), 0) +__meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2); +#define alloc_pages_exact_nid(...) \ + alloc_hooks(alloc_pages_exact_nid_noprof(__VA_ARGS__)) -#define __get_dma_pages(gfp_mask, order) \ - __get_free_pages((gfp_mask) | GFP_DMA, (order)) +#define __get_free_page(gfp_mask) \ + __get_free_pages((gfp_mask), 0) + +#define __get_dma_pages(gfp_mask, order) \ + __get_free_pages((gfp_mask) | GFP_DMA, (order)) extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); @@ -374,10 +435,14 @@ extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma); #ifdef CONFIG_CONTIG_ALLOC /* The below functions must be run on a range from a single zone. */ -extern int alloc_contig_range(unsigned long start, unsigned long end, +extern int alloc_contig_range_noprof(unsigned long start, unsigned long end, unsigned migratetype, gfp_t gfp_mask); -extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, - int nid, nodemask_t *nodemask); +#define alloc_contig_range(...) alloc_hooks(alloc_contig_range_noprof(__VA_ARGS__)) + +extern struct page *alloc_contig_pages_noprof(unsigned long nr_pages, gfp_t gfp_mask, + int nid, nodemask_t *nodemask); +#define alloc_contig_pages(...) alloc_hooks(alloc_contig_pages_noprof(__VA_ARGS__)) + #endif void free_contig_range(unsigned long pfn, unsigned long nr_pages); diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index 13becafe41df..313be4ad79fd 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -55,6 +55,9 @@ enum { #ifdef CONFIG_LOCKDEP ___GFP_NOLOCKDEP_BIT, #endif +#ifdef CONFIG_SLAB_OBJ_EXT + ___GFP_NO_OBJ_EXT_BIT, +#endif ___GFP_LAST_BIT }; @@ -95,6 +98,11 @@ enum { #else #define ___GFP_NOLOCKDEP 0 #endif +#ifdef CONFIG_SLAB_OBJ_EXT +#define ___GFP_NO_OBJ_EXT BIT(___GFP_NO_OBJ_EXT_BIT) +#else +#define ___GFP_NO_OBJ_EXT 0 +#endif /* * Physical address zone modifiers (see linux/mmzone.h - low four bits) @@ -135,12 +143,15 @@ enum { * node with no fallbacks or placement policy enforcements. * * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg. + * + * %__GFP_NO_OBJ_EXT causes slab allocation to have no object extension. */ #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) #define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) #define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) #define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE) #define __GFP_ACCOUNT ((__force gfp_t)___GFP_ACCOUNT) +#define __GFP_NO_OBJ_EXT ((__force gfp_t)___GFP_NO_OBJ_EXT) /** * DOC: Watermark modifiers diff --git a/include/linux/gpio.h b/include/linux/gpio.h index 7ecc25c543ce..063f71b18a7c 100644 --- a/include/linux/gpio.h +++ b/include/linux/gpio.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * <linux/gpio.h> + * NOTE: This header *must not* be included. * * This is the LEGACY GPIO bulk include file, including legacy APIs. It is * used for GPIO drivers still referencing the global GPIO numberspace, @@ -16,8 +16,6 @@ struct device; -/* see Documentation/driver-api/gpio/legacy.rst */ - /* make these flag values available regardless of GPIO kconfig options */ #define GPIOF_DIR_OUT (0 << 0) #define GPIOF_DIR_IN (1 << 0) @@ -74,6 +72,12 @@ static inline bool gpio_is_valid(int number) * Until they are all fixed, leave 0-512 space for them. */ #define GPIO_DYNAMIC_BASE 512 +/* + * Define the maximum of the possible GPIO in the global numberspace. + * While the GPIO base and numbers are positive, we limit it with signed + * maximum as a lot of code is using negative values for special cases. + */ +#define GPIO_DYNAMIC_MAX INT_MAX /* Always use the library code for GPIO management calls, * or when sleeping may be involved. @@ -114,10 +118,6 @@ static inline int gpio_to_irq(unsigned gpio) } int gpio_request_one(unsigned gpio, unsigned long flags, const char *label); -int gpio_request_array(const struct gpio *array, size_t num); -void gpio_free_array(const struct gpio *array, size_t num); - -/* CONFIG_GPIOLIB: bindings for managed devices that want to request gpios */ int devm_gpio_request(struct device *dev, unsigned gpio, const char *label); int devm_gpio_request_one(struct device *dev, unsigned gpio, @@ -146,11 +146,6 @@ static inline int gpio_request_one(unsigned gpio, return -ENOSYS; } -static inline int gpio_request_array(const struct gpio *array, size_t num) -{ - return -ENOSYS; -} - static inline void gpio_free(unsigned gpio) { might_sleep(); @@ -159,14 +154,6 @@ static inline void gpio_free(unsigned gpio) WARN_ON(1); } -static inline void gpio_free_array(const struct gpio *array, size_t num) -{ - might_sleep(); - - /* GPIO can never have been requested */ - WARN_ON(1); -} - static inline int gpio_direction_input(unsigned gpio) { return -ENOSYS; diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index f8617eaf08ba..2dd7cb9cc270 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -376,9 +376,7 @@ struct gpio_irq_chip { * @names: if set, must be an array of strings to use as alternative * names for the GPIOs in this chip. Any entry in the array * may be NULL if there is no alias for the GPIO, however the - * array must be @ngpio entries long. A name can include a single printk - * format specifier for an unsigned int. It is substituted by the actual - * number of the gpio. + * array must be @ngpio entries long. * @can_sleep: flag must be set iff get()/set() methods sleep, as they * must while accessing GPIO expander chips over I2C or SPI. This * implies that if the chip supports IRQs, these IRQs need to be threaded @@ -634,10 +632,6 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, devm_gpiochip_add_data_with_key(dev, gc, data, NULL, NULL) #endif /* CONFIG_LOCKDEP */ -static inline int gpiochip_add(struct gpio_chip *gc) -{ - return gpiochip_add_data(gc, NULL); -} void gpiochip_remove(struct gpio_chip *gc); int devm_gpiochip_add_data_with_key(struct device *dev, struct gpio_chip *gc, void *data, struct lock_class_key *lock_key, @@ -793,7 +787,6 @@ struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *gc, enum gpiod_flags dflags); void gpiochip_free_own_desc(struct gpio_desc *desc); -struct gpio_desc *gpiochip_get_desc(struct gpio_chip *gc, unsigned int hwnum); struct gpio_desc * gpio_device_get_desc(struct gpio_device *gdev, unsigned int hwnum); diff --git a/include/linux/gpio/property.h b/include/linux/gpio/property.h index 1a14e239221f..0d2209308002 100644 --- a/include/linux/gpio/property.h +++ b/include/linux/gpio/property.h @@ -4,7 +4,11 @@ #include <linux/property.h> +struct software_node; + #define PROPERTY_ENTRY_GPIO(_name_, _chip_node_, _idx_, _flags_) \ PROPERTY_ENTRY_REF(_name_, _chip_node_, _idx_, _flags_) +extern const struct software_node swnode_gpio_undefined; + #endif /* __LINUX_GPIO_PROPERTY_H */ diff --git a/include/linux/greybus.h b/include/linux/greybus.h index 634c9511cf78..4d58e27ceaf6 100644 --- a/include/linux/greybus.h +++ b/include/linux/greybus.h @@ -64,7 +64,7 @@ struct greybus_driver { struct device_driver driver; }; -#define to_greybus_driver(d) container_of(d, struct greybus_driver, driver) +#define to_greybus_driver(d) container_of_const(d, struct greybus_driver, driver) static inline void greybus_set_drvdata(struct gb_bundle *bundle, void *data) { diff --git a/include/linux/habanalabs/cpucp_if.h b/include/linux/habanalabs/cpucp_if.h index f316c8d0f3fc..7ed3fdd55dda 100644 --- a/include/linux/habanalabs/cpucp_if.h +++ b/include/linux/habanalabs/cpucp_if.h @@ -42,6 +42,12 @@ enum eq_event_id { EQ_EVENT_PWR_BRK_ENTRY, EQ_EVENT_PWR_BRK_EXIT, EQ_EVENT_HEARTBEAT, + EQ_EVENT_CPLD_RESET_REASON, + EQ_EVENT_CPLD_SHUTDOWN, + EQ_EVENT_POWER_EVT_START, + EQ_EVENT_POWER_EVT_END, + EQ_EVENT_THERMAL_EVT_START, + EQ_EVENT_THERMAL_EVT_END, }; /* @@ -391,6 +397,9 @@ struct hl_eq_entry { #define EQ_CTL_READY_SHIFT 31 #define EQ_CTL_READY_MASK 0x80000000 +#define EQ_CTL_EVENT_MODE_SHIFT 28 +#define EQ_CTL_EVENT_MODE_MASK 0x70000000 + #define EQ_CTL_EVENT_TYPE_SHIFT 16 #define EQ_CTL_EVENT_TYPE_MASK 0x0FFF0000 @@ -853,9 +862,6 @@ struct cpucp_packet { * result cannot be used to hold general purpose data. */ __le32 status_mask; - - /* random, used once number, for security packets */ - __le32 nonce; }; union { @@ -864,6 +870,9 @@ struct cpucp_packet { /* For Generic packet sub index */ __le32 pkt_subidx; + + /* random, used once number, for security packets */ + __le32 nonce; }; }; @@ -1140,6 +1149,7 @@ struct cpucp_security_info { * (0 = fully functional, 1 = lower-half is not functional, * 2 = upper-half is not functional) * @sec_info: security information + * @cpld_timestamp: CPLD programmed F/W timestamp. * @pll_map: Bit map of supported PLLs for current ASIC version. * @mme_binning_mask: MME binning mask, * bits [0:6] <==> dcore0 mme fma @@ -1165,7 +1175,7 @@ struct cpucp_security_info { struct cpucp_info { struct cpucp_sensor sensors[CPUCP_MAX_SENSORS]; __u8 kernel_version[VERSION_MAX_LEN]; - __le32 reserved; + __le32 reserved1; __le32 card_type; __le32 card_location; __le32 cpld_version; @@ -1187,7 +1197,7 @@ struct cpucp_info { __u8 substrate_version; __u8 eq_health_check_supported; struct cpucp_security_info sec_info; - __le32 fw_hbm_region_size; + __le32 cpld_timestamp; __u8 pll_map[PLL_MAP_LEN]; __le64 mme_binning_mask; __u8 fw_os_version[VERSION_MAX_LEN]; diff --git a/include/linux/habanalabs/hl_boot_if.h b/include/linux/habanalabs/hl_boot_if.h index 93366d5621fd..d2a9fc96424b 100644 --- a/include/linux/habanalabs/hl_boot_if.h +++ b/include/linux/habanalabs/hl_boot_if.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 * - * Copyright 2018-2020 HabanaLabs, Ltd. + * Copyright 2018-2023 HabanaLabs, Ltd. * All Rights Reserved. * */ @@ -49,7 +49,6 @@ enum cpu_boot_err { #define CPU_BOOT_ERR_FATAL_MASK \ ((1 << CPU_BOOT_ERR_DRAM_INIT_FAIL) | \ (1 << CPU_BOOT_ERR_PLL_FAIL) | \ - (1 << CPU_BOOT_ERR_DEVICE_UNUSABLE_FAIL) | \ (1 << CPU_BOOT_ERR_BINNING_FAIL) | \ (1 << CPU_BOOT_ERR_DRAM_SKIPPED) | \ (1 << CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL) | \ @@ -194,6 +193,8 @@ enum cpu_boot_dev_sts { CPU_BOOT_DEV_STS_FW_NIC_STAT_EXT_EN = 24, CPU_BOOT_DEV_STS_IS_IDLE_CHECK_EN = 25, CPU_BOOT_DEV_STS_MAP_HWMON_EN = 26, + CPU_BOOT_DEV_STS_NIC_MEM_CLEAR_EN = 27, + CPU_BOOT_DEV_STS_MMU_PGTBL_DRAM_EN = 28, CPU_BOOT_DEV_STS_ENABLED = 31, CPU_BOOT_DEV_STS_SCND_EN = 63, CPU_BOOT_DEV_STS_LAST = 64 /* we have 2 registers of 32 bits */ @@ -331,6 +332,17 @@ enum cpu_boot_dev_sts { * HWMON enum mapping to cpucp enums. * Initialized in: linux * + * CPU_BOOT_DEV_STS0_NIC_MEM_CLEAR_EN + * If set, means f/w supports nic hbm memory clear and + * tmr,txs hbm memory init. + * Initialized in: zephyr-mgmt + * + * CPU_BOOT_DEV_STS_MMU_PGTBL_DRAM_EN + * MMU page tables are located in DRAM. + * F/W initializes security settings for MMU + * page tables to reside in DRAM. + * Initialized in: zephyr-mgmt + * * CPU_BOOT_DEV_STS0_ENABLED Device status register enabled. * This is a main indication that the * running FW populates the device status @@ -367,6 +379,8 @@ enum cpu_boot_dev_sts { #define CPU_BOOT_DEV_STS0_FW_NIC_STAT_EXT_EN (1 << CPU_BOOT_DEV_STS_FW_NIC_STAT_EXT_EN) #define CPU_BOOT_DEV_STS0_IS_IDLE_CHECK_EN (1 << CPU_BOOT_DEV_STS_IS_IDLE_CHECK_EN) #define CPU_BOOT_DEV_STS0_MAP_HWMON_EN (1 << CPU_BOOT_DEV_STS_MAP_HWMON_EN) +#define CPU_BOOT_DEV_STS0_NIC_MEM_CLEAR_EN (1 << CPU_BOOT_DEV_STS_NIC_MEM_CLEAR_EN) +#define CPU_BOOT_DEV_STS0_MMU_PGTBL_DRAM_EN (1 << CPU_BOOT_DEV_STS_MMU_PGTBL_DRAM_EN) #define CPU_BOOT_DEV_STS0_ENABLED (1 << CPU_BOOT_DEV_STS_ENABLED) #define CPU_BOOT_DEV_STS1_ENABLED (1 << CPU_BOOT_DEV_STS_ENABLED) @@ -450,11 +464,11 @@ struct cpu_dyn_regs { __le32 gic_dma_core_irq_ctrl; __le32 gic_host_halt_irq; __le32 gic_host_ints_irq; - __le32 gic_host_soft_rst_irq; + __le32 reserved0; __le32 gic_rot_qm_irq_ctrl; - __le32 cpu_rst_status; + __le32 reserved1; __le32 eng_arc_irq_ctrl; - __le32 reserved1[20]; /* reserve for future use */ + __le32 reserved2[20]; /* reserve for future use */ }; /* TODO: remove the desc magic after the code is updated to use message */ @@ -551,8 +565,9 @@ enum lkd_fw_ascii_msg_lvls { LKD_FW_ASCII_MSG_DBG = 3, }; -#define LKD_FW_ASCII_MSG_MAX_LEN 128 -#define LKD_FW_ASCII_MSG_MAX 4 /* consider ABI when changing */ +#define LKD_FW_ASCII_MSG_MAX_LEN 128 +#define LKD_FW_ASCII_MSG_MAX 4 /* consider ABI when changing */ +#define LKD_FW_ASCII_MSG_MIN_DESC_VERSION 3 struct lkd_fw_ascii_msg { __u8 valid; diff --git a/include/linux/hid.h b/include/linux/hid.h index b12cb1c8e682..1533c9dcd3a6 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -474,9 +474,9 @@ struct hid_usage { __s8 wheel_factor; /* 120/resolution_multiplier */ __u16 code; /* input driver code */ __u8 type; /* input driver type */ - __s8 hat_min; /* hat switch fun */ - __s8 hat_max; /* ditto */ - __s8 hat_dir; /* ditto */ + __s16 hat_min; /* hat switch fun */ + __s16 hat_max; /* ditto */ + __s16 hat_dir; /* ditto */ __s16 wheel_accumulated; /* hi-res wheel */ }; @@ -1125,6 +1125,13 @@ int __must_check hid_hw_open(struct hid_device *hdev); void hid_hw_close(struct hid_device *hdev); void hid_hw_request(struct hid_device *hdev, struct hid_report *report, enum hid_class_request reqtype); +int __hid_hw_raw_request(struct hid_device *hdev, + unsigned char reportnum, __u8 *buf, + size_t len, enum hid_report_type rtype, + enum hid_class_request reqtype, + __u64 source, bool from_bpf); +int __hid_hw_output_report(struct hid_device *hdev, __u8 *buf, size_t len, __u64 source, + bool from_bpf); int hid_hw_raw_request(struct hid_device *hdev, unsigned char reportnum, __u8 *buf, size_t len, enum hid_report_type rtype, diff --git a/include/linux/hid_bpf.h b/include/linux/hid_bpf.h index 7118ac28d468..d4d063cf63b5 100644 --- a/include/linux/hid_bpf.h +++ b/include/linux/hid_bpf.h @@ -4,7 +4,8 @@ #define __HID_BPF_H #include <linux/bpf.h> -#include <linux/spinlock.h> +#include <linux/mutex.h> +#include <linux/srcu.h> #include <uapi/linux/hid.h> struct hid_device; @@ -20,15 +21,9 @@ struct hid_device; * struct hid_bpf_ctx - User accessible data for all HID programs * * ``data`` is not directly accessible from the context. We need to issue - * a call to ``hid_bpf_get_data()`` in order to get a pointer to that field. + * a call to hid_bpf_get_data() in order to get a pointer to that field. * - * All of these fields are currently read-only. - * - * @index: program index in the jump table. No special meaning (a smaller index - * doesn't mean the program will be executed before another program with - * a bigger index). - * @hid: the ``struct hid_device`` representing the device itself - * @report_type: used for ``hid_bpf_device_event()`` + * @hid: the &struct hid_device representing the device itself * @allocated_size: Allocated size of data. * * This is how much memory is available and can be requested @@ -45,73 +40,147 @@ struct hid_device; * ``size`` must always be less or equal than ``allocated_size`` (it is enforced * once all BPF programs have been run). * @retval: Return value of the previous program. + * + * ``hid`` and ``allocated_size`` are read-only, ``size`` and ``retval`` are read-write. */ struct hid_bpf_ctx { - __u32 index; - const struct hid_device *hid; + struct hid_device *hid; __u32 allocated_size; - enum hid_report_type report_type; union { __s32 retval; __s32 size; }; }; -/** - * enum hid_bpf_attach_flags - flags used when attaching a HIF-BPF program - * - * @HID_BPF_FLAG_NONE: no specific flag is used, the kernel choses where to - * insert the program - * @HID_BPF_FLAG_INSERT_HEAD: insert the given program before any other program - * currently attached to the device. This doesn't - * guarantee that this program will always be first - * @HID_BPF_FLAG_MAX: sentinel value, not to be used by the callers - */ -enum hid_bpf_attach_flags { - HID_BPF_FLAG_NONE = 0, - HID_BPF_FLAG_INSERT_HEAD = _BITUL(0), - HID_BPF_FLAG_MAX, -}; - -/* Following functions are tracepoints that BPF programs can attach to */ -int hid_bpf_device_event(struct hid_bpf_ctx *ctx); -int hid_bpf_rdesc_fixup(struct hid_bpf_ctx *ctx); - /* * Below is HID internal */ -/* internal function to call eBPF programs, not to be used by anybody */ -int __hid_bpf_tail_call(struct hid_bpf_ctx *ctx); - #define HID_BPF_MAX_PROGS_PER_DEV 64 #define HID_BPF_FLAG_MASK (((HID_BPF_FLAG_MAX - 1) << 1) - 1) -/* types of HID programs to attach to */ -enum hid_bpf_prog_type { - HID_BPF_PROG_TYPE_UNDEF = -1, - HID_BPF_PROG_TYPE_DEVICE_EVENT, /* an event is emitted from the device */ - HID_BPF_PROG_TYPE_RDESC_FIXUP, - HID_BPF_PROG_TYPE_MAX, -}; struct hid_report_enum; -struct hid_bpf_ops { +struct hid_ops { struct hid_report *(*hid_get_report)(struct hid_report_enum *report_enum, const u8 *data); int (*hid_hw_raw_request)(struct hid_device *hdev, unsigned char reportnum, __u8 *buf, size_t len, enum hid_report_type rtype, - enum hid_class_request reqtype); + enum hid_class_request reqtype, + u64 source, bool from_bpf); + int (*hid_hw_output_report)(struct hid_device *hdev, __u8 *buf, size_t len, + u64 source, bool from_bpf); + int (*hid_input_report)(struct hid_device *hid, enum hid_report_type type, + u8 *data, u32 size, int interrupt, u64 source, bool from_bpf, + bool lock_already_taken); struct module *owner; const struct bus_type *bus_type; }; -extern struct hid_bpf_ops *hid_bpf_ops; +extern struct hid_ops *hid_ops; -struct hid_bpf_prog_list { - u16 prog_idx[HID_BPF_MAX_PROGS_PER_DEV]; - u8 prog_cnt; +/** + * struct hid_bpf_ops - A BPF struct_ops of callbacks allowing to attach HID-BPF + * programs to a HID device + * @hid_id: the HID uniq ID to attach to. This is writeable before ``load()``, and + * cannot be changed after + * @flags: flags used while attaching the struct_ops to the device. Currently only + * available value is %0 or ``BPF_F_BEFORE``. + * Writeable only before ``load()`` + */ +struct hid_bpf_ops { + /* hid_id needs to stay first so we can easily change it + * from userspace. + */ + int hid_id; + u32 flags; + + /* private: do not show up in the docs */ + struct list_head list; + + /* public: rest should show up in the docs */ + + /** + * @hid_device_event: called whenever an event is coming in from the device + * + * It has the following arguments: + * + * ``ctx``: The HID-BPF context as &struct hid_bpf_ctx + * + * Return: %0 on success and keep processing; a positive + * value to change the incoming size buffer; a negative + * error code to interrupt the processing of this event + * + * Context: Interrupt context. + */ + int (*hid_device_event)(struct hid_bpf_ctx *ctx, enum hid_report_type report_type, + u64 source); + + /** + * @hid_rdesc_fixup: called when the probe function parses the report descriptor + * of the HID device + * + * It has the following arguments: + * + * ``ctx``: The HID-BPF context as &struct hid_bpf_ctx + * + * Return: %0 on success and keep processing; a positive + * value to change the incoming size buffer; a negative + * error code to interrupt the processing of this device + */ + int (*hid_rdesc_fixup)(struct hid_bpf_ctx *ctx); + + /** + * @hid_hw_request: called whenever a hid_hw_raw_request() call is emitted + * on the HID device + * + * It has the following arguments: + * + * ``ctx``: The HID-BPF context as &struct hid_bpf_ctx + * + * ``reportnum``: the report number, as in hid_hw_raw_request() + * + * ``rtype``: the report type (``HID_INPUT_REPORT``, ``HID_FEATURE_REPORT``, + * ``HID_OUTPUT_REPORT``) + * + * ``reqtype``: the request + * + * ``source``: a u64 referring to a uniq but identifiable source. If %0, the + * kernel itself emitted that call. For hidraw, ``source`` is set + * to the associated ``struct file *``. + * + * Return: %0 to keep processing the request by hid-core; any other value + * stops hid-core from processing that event. A positive value should be + * returned with the number of bytes returned in the incoming buffer; a + * negative error code interrupts the processing of this call. + */ + int (*hid_hw_request)(struct hid_bpf_ctx *ctx, unsigned char reportnum, + enum hid_report_type rtype, enum hid_class_request reqtype, + u64 source); + + /** + * @hid_hw_output_report: called whenever a hid_hw_output_report() call is emitted + * on the HID device + * + * It has the following arguments: + * + * ``ctx``: The HID-BPF context as &struct hid_bpf_ctx + * + * ``source``: a u64 referring to a uniq but identifiable source. If %0, the + * kernel itself emitted that call. For hidraw, ``source`` is set + * to the associated ``struct file *``. + * + * Return: %0 to keep processing the request by hid-core; any other value + * stops hid-core from processing that event. A positive value should be + * returned with the number of bytes written to the device; a negative error + * code interrupts the processing of this call. + */ + int (*hid_hw_output_report)(struct hid_bpf_ctx *ctx, u64 source); + + + /* private: do not show up in the docs */ + struct hid_device *hdev; }; /* stored in each device */ @@ -121,38 +190,51 @@ struct hid_bpf { * to this HID device */ u32 allocated_data; - - struct hid_bpf_prog_list __rcu *progs[HID_BPF_PROG_TYPE_MAX]; /* attached BPF progs */ bool destroyed; /* prevents the assignment of any progs */ - spinlock_t progs_lock; /* protects RCU update of progs */ -}; - -/* specific HID-BPF link when a program is attached to a device */ -struct hid_bpf_link { - struct bpf_link link; - int hid_table_index; + struct hid_bpf_ops *rdesc_ops; + struct list_head prog_list; + struct mutex prog_list_lock; /* protects prog_list update */ + struct srcu_struct srcu; /* protects prog_list read-only access */ }; #ifdef CONFIG_HID_BPF u8 *dispatch_hid_bpf_device_event(struct hid_device *hid, enum hid_report_type type, u8 *data, - u32 *size, int interrupt); + u32 *size, int interrupt, u64 source, bool from_bpf); +int dispatch_hid_bpf_raw_requests(struct hid_device *hdev, + unsigned char reportnum, __u8 *buf, + u32 size, enum hid_report_type rtype, + enum hid_class_request reqtype, + u64 source, bool from_bpf); +int dispatch_hid_bpf_output_report(struct hid_device *hdev, __u8 *buf, u32 size, + u64 source, bool from_bpf); int hid_bpf_connect_device(struct hid_device *hdev); void hid_bpf_disconnect_device(struct hid_device *hdev); void hid_bpf_destroy_device(struct hid_device *hid); -void hid_bpf_device_init(struct hid_device *hid); +int hid_bpf_device_init(struct hid_device *hid); u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, u8 *rdesc, unsigned int *size); #else /* CONFIG_HID_BPF */ static inline u8 *dispatch_hid_bpf_device_event(struct hid_device *hid, enum hid_report_type type, - u8 *data, u32 *size, int interrupt) { return data; } + u8 *data, u32 *size, int interrupt, + u64 source, bool from_bpf) { return data; } +static inline int dispatch_hid_bpf_raw_requests(struct hid_device *hdev, + unsigned char reportnum, u8 *buf, + u32 size, enum hid_report_type rtype, + enum hid_class_request reqtype, + u64 source, bool from_bpf) { return 0; } +static inline int dispatch_hid_bpf_output_report(struct hid_device *hdev, __u8 *buf, u32 size, + u64 source, bool from_bpf) { return 0; } static inline int hid_bpf_connect_device(struct hid_device *hdev) { return 0; } static inline void hid_bpf_disconnect_device(struct hid_device *hdev) {} static inline void hid_bpf_destroy_device(struct hid_device *hid) {} -static inline void hid_bpf_device_init(struct hid_device *hid) {} -static inline u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, u8 *rdesc, unsigned int *size) -{ - return kmemdup(rdesc, *size, GFP_KERNEL); -} +static inline int hid_bpf_device_init(struct hid_device *hid) { return 0; } +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). The typecast is + * intentional to enforce typesafety. + */ +#define call_hid_bpf_rdesc_fixup(_hdev, _rdesc, _size) \ + ((u8 *)kmemdup(_rdesc, *(_size), GFP_KERNEL)) #endif /* CONFIG_HID_BPF */ diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index a3028e400a9c..dd100e849f5e 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -131,22 +131,17 @@ static inline void __kunmap_atomic(const void *addr) preempt_enable(); } -unsigned int __nr_free_highpages(void); -extern atomic_long_t _totalhigh_pages; +unsigned long __nr_free_highpages(void); +unsigned long __totalhigh_pages(void); -static inline unsigned int nr_free_highpages(void) +static inline unsigned long nr_free_highpages(void) { return __nr_free_highpages(); } static inline unsigned long totalhigh_pages(void) { - return (unsigned long)atomic_long_read(&_totalhigh_pages); -} - -static inline void totalhigh_pages_add(long count) -{ - atomic_long_add(count, &_totalhigh_pages); + return __totalhigh_pages(); } static inline bool is_kmap_addr(const void *x) @@ -239,8 +234,8 @@ static inline void __kunmap_atomic(const void *addr) preempt_enable(); } -static inline unsigned int nr_free_highpages(void) { return 0; } -static inline unsigned long totalhigh_pages(void) { return 0UL; } +static inline unsigned long nr_free_highpages(void) { return 0; } +static inline unsigned long totalhigh_pages(void) { return 0; } static inline bool is_kmap_addr(const void *x) { diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 00341b56d291..930a591b9b61 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -179,7 +179,7 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset); static inline void *kmap_atomic(struct page *page); /* Highmem related interfaces for management code */ -static inline unsigned int nr_free_highpages(void); +static inline unsigned long nr_free_highpages(void); static inline unsigned long totalhigh_pages(void); #ifndef ARCH_HAS_FLUSH_ANON_PAGE @@ -352,6 +352,9 @@ static inline int copy_mc_user_highpage(struct page *to, struct page *from, kunmap_local(vto); kunmap_local(vfrom); + if (ret) + memory_failure_queue(page_to_pfn(from), 0); + return ret; } @@ -368,6 +371,9 @@ static inline int copy_mc_highpage(struct page *to, struct page *from) kunmap_local(vto); kunmap_local(vfrom); + if (ret) + memory_failure_queue(page_to_pfn(from), 0); + return ret; } #else diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index de0c89105076..e25d9ebfdf89 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -6,6 +6,7 @@ #include <linux/mm_types.h> #include <linux/fs.h> /* only for vma_is_dax() */ +#include <linux/kobject.h> vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf); int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, @@ -63,9 +64,7 @@ ssize_t single_hugepage_flag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf, enum transparent_hugepage_flag flag); extern struct kobj_attribute shmem_enabled_attr; - -#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) -#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER) +extern struct kobj_attribute thpsize_shmem_enabled_attr; /* * Mask of all large folio orders supported for anonymous THP; all orders up to @@ -75,26 +74,47 @@ extern struct kobj_attribute shmem_enabled_attr; #define THP_ORDERS_ALL_ANON ((BIT(PMD_ORDER + 1) - 1) & ~(BIT(0) | BIT(1))) /* - * Mask of all large folio orders supported for file THP. + * Mask of all large folio orders supported for file THP. Folios in a DAX + * file is never split and the MAX_PAGECACHE_ORDER limit does not apply to + * it. */ -#define THP_ORDERS_ALL_FILE (BIT(PMD_ORDER) | BIT(PUD_ORDER)) +#define THP_ORDERS_ALL_FILE_DAX \ + (BIT(PMD_ORDER) | BIT(PUD_ORDER)) +#define THP_ORDERS_ALL_FILE_DEFAULT \ + ((BIT(MAX_PAGECACHE_ORDER + 1) - 1) & ~BIT(0)) /* * Mask of all large folio orders supported for THP. */ -#define THP_ORDERS_ALL (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE) +#define THP_ORDERS_ALL \ + (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE_DAX | THP_ORDERS_ALL_FILE_DEFAULT) -#define thp_vma_allowable_order(vma, vm_flags, smaps, in_pf, enforce_sysfs, order) \ - (!!thp_vma_allowable_orders(vma, vm_flags, smaps, in_pf, enforce_sysfs, BIT(order))) +#define TVA_SMAPS (1 << 0) /* Will be used for procfs */ +#define TVA_IN_PF (1 << 1) /* Page fault handler */ +#define TVA_ENFORCE_SYSFS (1 << 2) /* Obey sysfs configuration */ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define thp_vma_allowable_order(vma, vm_flags, tva_flags, order) \ + (!!thp_vma_allowable_orders(vma, vm_flags, tva_flags, BIT(order))) + +#ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES #define HPAGE_PMD_SHIFT PMD_SHIFT -#define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT) +#define HPAGE_PUD_SHIFT PUD_SHIFT +#else +#define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) +#define HPAGE_PUD_SHIFT ({ BUILD_BUG(); 0; }) +#endif + +#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) +#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER) #define HPAGE_PMD_MASK (~(HPAGE_PMD_SIZE - 1)) +#define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT) -#define HPAGE_PUD_SHIFT PUD_SHIFT -#define HPAGE_PUD_SIZE ((1UL) << HPAGE_PUD_SHIFT) +#define HPAGE_PUD_ORDER (HPAGE_PUD_SHIFT-PAGE_SHIFT) +#define HPAGE_PUD_NR (1<<HPAGE_PUD_ORDER) #define HPAGE_PUD_MASK (~(HPAGE_PUD_SIZE - 1)) +#define HPAGE_PUD_SIZE ((1UL) << HPAGE_PUD_SHIFT) + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE extern unsigned long transparent_hugepage_flags; extern unsigned long huge_anon_orders_always; @@ -114,18 +134,6 @@ static inline bool hugepage_global_always(void) (1<<TRANSPARENT_HUGEPAGE_FLAG); } -static inline bool hugepage_flags_enabled(void) -{ - /* - * We cover both the anon and the file-backed case here; we must return - * true if globally enabled, even when all anon sizes are set to never. - * So we don't need to look at huge_anon_orders_inherit. - */ - return hugepage_global_enabled() || - huge_anon_orders_always || - huge_anon_orders_madvise; -} - static inline int highest_order(unsigned long orders) { return fls_long(orders) - 1; @@ -210,17 +218,15 @@ static inline bool file_thp_enabled(struct vm_area_struct *vma) } unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, - unsigned long vm_flags, bool smaps, - bool in_pf, bool enforce_sysfs, + unsigned long vm_flags, + unsigned long tva_flags, unsigned long orders); /** * thp_vma_allowable_orders - determine hugepage orders that are allowed for vma * @vma: the vm area to check * @vm_flags: use these vm_flags instead of vma->vm_flags - * @smaps: whether answer will be used for smaps file - * @in_pf: whether answer will be used by page fault handler - * @enforce_sysfs: whether sysfs config should be taken into account + * @tva_flags: Which TVA flags to honour * @orders: bitfield of all orders to consider * * Calculates the intersection of the requested hugepage orders and the allowed @@ -233,12 +239,12 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, */ static inline unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, - unsigned long vm_flags, bool smaps, - bool in_pf, bool enforce_sysfs, + unsigned long vm_flags, + unsigned long tva_flags, unsigned long orders) { /* Optimization to check if required orders are enabled early. */ - if (enforce_sysfs && vma_is_anonymous(vma)) { + if ((tva_flags & TVA_ENFORCE_SYSFS) && vma_is_anonymous(vma)) { unsigned long mask = READ_ONCE(huge_anon_orders_always); if (vm_flags & VM_HUGEPAGE) @@ -252,18 +258,62 @@ unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, return 0; } - return __thp_vma_allowable_orders(vma, vm_flags, smaps, in_pf, - enforce_sysfs, orders); + return __thp_vma_allowable_orders(vma, vm_flags, tva_flags, orders); } +struct thpsize { + struct kobject kobj; + struct list_head node; + int order; +}; + +#define to_thpsize(kobj) container_of(kobj, struct thpsize, kobj) + +enum mthp_stat_item { + MTHP_STAT_ANON_FAULT_ALLOC, + MTHP_STAT_ANON_FAULT_FALLBACK, + MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE, + MTHP_STAT_SWPOUT, + MTHP_STAT_SWPOUT_FALLBACK, + MTHP_STAT_SHMEM_ALLOC, + MTHP_STAT_SHMEM_FALLBACK, + MTHP_STAT_SHMEM_FALLBACK_CHARGE, + MTHP_STAT_SPLIT, + MTHP_STAT_SPLIT_FAILED, + MTHP_STAT_SPLIT_DEFERRED, + __MTHP_STAT_COUNT +}; + +struct mthp_stat { + unsigned long stats[ilog2(MAX_PTRS_PER_PTE) + 1][__MTHP_STAT_COUNT]; +}; + +#ifdef CONFIG_SYSFS +DECLARE_PER_CPU(struct mthp_stat, mthp_stats); + +static inline void count_mthp_stat(int order, enum mthp_stat_item item) +{ + if (order <= 0 || order > PMD_ORDER) + return; + + this_cpu_inc(mthp_stats.stats[order][item]); +} +#else +static inline void count_mthp_stat(int order, enum mthp_stat_item item) +{ +} +#endif + #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); +unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, unsigned long flags, + vm_flags_t vm_flags); -void folio_prep_large_rmappable(struct folio *folio); bool can_split_folio(struct folio *folio, int *pextra_pins); int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, unsigned int new_order); @@ -344,17 +394,15 @@ static inline bool folio_test_pmd_mappable(struct folio *folio) struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap); -struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, int flags, struct dev_pagemap **pgmap); vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf); -extern struct page *huge_zero_page; +extern struct folio *huge_zero_folio; extern unsigned long huge_zero_pfn; -static inline bool is_huge_zero_page(struct page *page) +static inline bool is_huge_zero_folio(const struct folio *folio) { - return READ_ONCE(huge_zero_page) == page; + return READ_ONCE(huge_zero_folio) == folio; } static inline bool is_huge_zero_pmd(pmd_t pmd) @@ -367,8 +415,8 @@ static inline bool is_huge_zero_pud(pud_t pud) return false; } -struct page *mm_get_huge_zero_page(struct mm_struct *mm); -void mm_put_huge_zero_page(struct mm_struct *mm); +struct folio *mm_get_huge_zero_folio(struct mm_struct *mm); +void mm_put_huge_zero_folio(struct mm_struct *mm); #define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot)) @@ -377,14 +425,12 @@ static inline bool thp_migration_supported(void) return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION); } -#else /* CONFIG_TRANSPARENT_HUGEPAGE */ -#define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) -#define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) -#define HPAGE_PMD_SIZE ({ BUILD_BUG(); 0; }) +void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address, + pmd_t *pmd, bool freeze, struct folio *folio); +bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmdp, struct folio *folio); -#define HPAGE_PUD_SHIFT ({ BUILD_BUG(); 0; }) -#define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; }) -#define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; }) +#else /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline bool folio_test_pmd_mappable(struct folio *folio) { @@ -404,19 +450,25 @@ static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma, } static inline unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma, - unsigned long vm_flags, bool smaps, - bool in_pf, bool enforce_sysfs, + unsigned long vm_flags, + unsigned long tva_flags, unsigned long orders) { return 0; } -static inline void folio_prep_large_rmappable(struct folio *folio) {} - #define transparent_hugepage_flags 0UL #define thp_get_unmapped_area NULL +static inline unsigned long +thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags, vm_flags_t vm_flags) +{ + return 0; +} + static inline bool can_split_folio(struct folio *folio, int *pextra_pins) { @@ -440,6 +492,16 @@ static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze, struct folio *folio) {} static inline void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct folio *folio) {} +static inline void split_huge_pmd_locked(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, + bool freeze, struct folio *folio) {} + +static inline bool unmap_huge_pmd_locked(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp, + struct folio *folio) +{ + return false; +} #define split_huge_pud(__vma, __pmd, __address) \ do { } while (0) @@ -483,7 +545,7 @@ static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) return 0; } -static inline bool is_huge_zero_page(struct page *page) +static inline bool is_huge_zero_folio(const struct folio *folio) { return false; } @@ -498,7 +560,7 @@ static inline bool is_huge_zero_pud(pud_t pud) return false; } -static inline void mm_put_huge_zero_page(struct mm_struct *mm) +static inline void mm_put_huge_zero_folio(struct mm_struct *mm) { return; } @@ -509,15 +571,19 @@ static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, return NULL; } -static inline struct page *follow_devmap_pud(struct vm_area_struct *vma, - unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap) +static inline bool thp_migration_supported(void) +{ + return false; +} + +static inline int highest_order(unsigned long orders) { - return NULL; + return 0; } -static inline bool thp_migration_supported(void) +static inline int next_order(unsigned long *orders, int prev) { - return false; + return 0; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -535,16 +601,4 @@ static inline int split_folio_to_order(struct folio *folio, int new_order) #define split_folio_to_list(f, l) split_folio_to_list_to_order(f, l, 0) #define split_folio(f) split_folio_to_order(f, 0) -/* - * archs that select ARCH_WANTS_THP_SWAP but don't support THP_SWP due to - * limitations in the implementation like arm64 MTE can override this to - * false - */ -#ifndef arch_thp_swp_supported -static inline bool arch_thp_swp_supported(void) -{ - return true; -} -#endif - #endif /* _LINUX_HUGE_MM_H */ diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 77b30a8c6076..45bf05ad5c53 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -20,12 +20,6 @@ struct user_struct; struct mmu_gather; struct node; -#ifndef CONFIG_ARCH_HAS_HUGEPD -typedef struct { unsigned long pd; } hugepd_t; -#define is_hugepd(hugepd) (0) -#define __hugepd(x) ((hugepd_t) { (x) }) -#endif - void free_huge_folio(struct folio *folio); #ifdef CONFIG_HUGETLB_PAGE @@ -174,8 +168,11 @@ u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx); pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud); +bool hugetlbfs_pagecache_present(struct hstate *h, + struct vm_area_struct *vma, + unsigned long address); -struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage); +struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio); extern int sysctl_hugetlb_shm_group; extern struct list_head huge_boot_pages[MAX_NUMNODES]; @@ -272,13 +269,9 @@ void hugetlb_vma_unlock_write(struct vm_area_struct *vma); int hugetlb_vma_trylock_write(struct vm_area_struct *vma); void hugetlb_vma_assert_locked(struct vm_area_struct *vma); void hugetlb_vma_lock_release(struct kref *kref); - -int pmd_huge(pmd_t pmd); -int pud_huge(pud_t pud); long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags); - bool is_hugetlb_entry_migration(pte_t pte); bool is_hugetlb_entry_hwpoisoned(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); @@ -298,8 +291,8 @@ static inline unsigned long hugetlb_total_pages(void) return 0; } -static inline struct address_space *hugetlb_page_mapping_lock_write( - struct page *hpage) +static inline struct address_space *hugetlb_folio_mapping_lock_write( + struct folio *folio) { return NULL; } @@ -329,13 +322,6 @@ static inline void hugetlb_zap_end( { } -static inline struct page *hugetlb_follow_page_mask( - struct vm_area_struct *vma, unsigned long address, unsigned int flags, - unsigned int *page_mask) -{ - BUILD_BUG(); /* should never be compiled in if !CONFIG_HUGETLB_PAGE*/ -} - static inline int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *dst_vma, @@ -399,16 +385,6 @@ static inline void hugetlb_vma_assert_locked(struct vm_area_struct *vma) { } -static inline int pmd_huge(pmd_t pmd) -{ - return 0; -} - -static inline int pud_huge(pud_t pud) -{ - return 0; -} - static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { @@ -493,16 +469,6 @@ static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } #endif /* !CONFIG_HUGETLB_PAGE */ -/* - * hugepages at page global directory. If arch support - * hugepages at pgd level, they need to define this. - */ -#ifndef pgd_huge -#define pgd_huge(x) 0 -#endif -#ifndef p4d_huge -#define p4d_huge(x) 0 -#endif #ifndef pgd_write static inline int pgd_write(pgd_t pgd) @@ -554,17 +520,13 @@ static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode) return container_of(inode, struct hugetlbfs_inode_info, vfs_inode); } -extern const struct file_operations hugetlbfs_file_operations; extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, int creat_flags, int page_size_log); -static inline bool is_file_hugepages(struct file *file) +static inline bool is_file_hugepages(const struct file *file) { - if (file->f_op == &hugetlbfs_file_operations) - return true; - - return is_file_shm_hugepages(file); + return file->f_op->fop_flags & FOP_HUGE_PAGES; } static inline struct hstate *hstate_inode(struct inode *i) @@ -648,47 +610,35 @@ static __always_inline \ bool folio_test_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ return test_bit(HPG_##flname, private); \ - } \ -static inline int HPage##uname(struct page *page) \ - { return test_bit(HPG_##flname, &(page->private)); } + } #define SETHPAGEFLAG(uname, flname) \ static __always_inline \ void folio_set_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ set_bit(HPG_##flname, private); \ - } \ -static inline void SetHPage##uname(struct page *page) \ - { set_bit(HPG_##flname, &(page->private)); } + } #define CLEARHPAGEFLAG(uname, flname) \ static __always_inline \ void folio_clear_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ clear_bit(HPG_##flname, private); \ - } \ -static inline void ClearHPage##uname(struct page *page) \ - { clear_bit(HPG_##flname, &(page->private)); } + } #else #define TESTHPAGEFLAG(uname, flname) \ static inline bool \ folio_test_hugetlb_##flname(struct folio *folio) \ - { return 0; } \ -static inline int HPage##uname(struct page *page) \ { return 0; } #define SETHPAGEFLAG(uname, flname) \ static inline void \ folio_set_hugetlb_##flname(struct folio *folio) \ - { } \ -static inline void SetHPage##uname(struct page *page) \ { } #define CLEARHPAGEFLAG(uname, flname) \ static inline void \ folio_clear_hugetlb_##flname(struct folio *folio) \ - { } \ -static inline void ClearHPage##uname(struct page *page) \ { } #endif @@ -713,6 +663,7 @@ HPAGEFLAG(RawHwpUnreliable, raw_hwp_unreliable) /* Defines one hugetlb page size */ struct hstate { struct mutex resize_lock; + struct lock_class_key resize_key; int next_nid_to_alloc; int next_nid_to_free; unsigned int order; @@ -730,11 +681,6 @@ struct hstate { unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; -#ifdef CONFIG_CGROUP_HUGETLB - /* cgroup control files */ - struct cftype cgroup_files_dfl[8]; - struct cftype cgroup_files_legacy[10]; -#endif char name[HSTATE_NAME_LEN]; }; @@ -747,7 +693,8 @@ int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, - nodemask_t *nmask, gfp_t gfp_mask); + nodemask_t *nmask, gfp_t gfp_mask, + bool allow_alloc_fallback); int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t idx); void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, @@ -859,9 +806,9 @@ static inline int is_hugepage_only_range(struct mm_struct *mm, #define is_hugepage_only_range is_hugepage_only_range #endif -#ifndef arch_clear_hugepage_flags -static inline void arch_clear_hugepage_flags(struct page *page) { } -#define arch_clear_hugepage_flags arch_clear_hugepage_flags +#ifndef arch_clear_hugetlb_flags +static inline void arch_clear_hugetlb_flags(struct folio *folio) { } +#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags #endif #ifndef arch_make_huge_pte @@ -888,8 +835,8 @@ static inline int hstate_index(struct hstate *h) return h - hstates; } -extern int dissolve_free_huge_page(struct page *page); -extern int dissolve_free_huge_pages(unsigned long start_pfn, +int dissolve_free_hugetlb_folio(struct folio *folio); +int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn); #ifdef CONFIG_MEMORY_FAILURE @@ -970,13 +917,64 @@ static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) return modified_mask; } +static inline bool htlb_allow_alloc_fallback(int reason) +{ + bool allowed_fallback = false; + + /* + * Note: the memory offline, memory failure and migration syscalls will + * be allowed to fallback to other nodes due to lack of a better chioce, + * that might break the per-node hugetlb pool. While other cases will + * set the __GFP_THISNODE to avoid breaking the per-node hugetlb pool. + */ + switch (reason) { + case MR_MEMORY_HOTPLUG: + case MR_MEMORY_FAILURE: + case MR_SYSCALL: + case MR_MEMPOLICY_MBIND: + allowed_fallback = true; + break; + default: + break; + } + + return allowed_fallback; +} + static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { - if (huge_page_size(h) == PMD_SIZE) + const unsigned long size = huge_page_size(h); + + VM_WARN_ON(size == PAGE_SIZE); + + /* + * hugetlb must use the exact same PT locks as core-mm page table + * walkers would. When modifying a PTE table, hugetlb must take the + * PTE PT lock, when modifying a PMD table, hugetlb must take the PMD + * PT lock etc. + * + * The expectation is that any hugetlb folio smaller than a PMD is + * always mapped into a single PTE table and that any hugetlb folio + * smaller than a PUD (but at least as big as a PMD) is always mapped + * into a single PMD table. + * + * If that does not hold for an architecture, then that architecture + * must disable split PT locks such that all *_lockptr() functions + * will give us the same result: the per-MM PT lock. + * + * Note that with e.g., CONFIG_PGTABLE_LEVELS=2 where + * PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE, we'd use pud_lockptr() + * and core-mm would use pmd_lockptr(). However, in such configurations + * split PMD locks are disabled -- they don't make sense on a single + * PGDIR page table -- and the end result is the same. + */ + if (size >= PUD_SIZE) + return pud_lockptr(mm, (pud_t *) pte); + else if (size >= PMD_SIZE || IS_ENABLED(CONFIG_HIGHPTE)) return pmd_lockptr(mm, (pmd_t *) pte); - VM_BUG_ON(huge_page_size(h) == PAGE_SIZE); - return &mm->page_table_lock; + /* pte_alloc_huge() only applies with !CONFIG_HIGHPTE */ + return ptep_lockptr(mm, pte); } #ifndef hugepages_supported @@ -1065,7 +1063,8 @@ static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, static inline struct folio * alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, - nodemask_t *nmask, gfp_t gfp_mask) + nodemask_t *nmask, gfp_t gfp_mask, + bool allow_alloc_fallback) { return NULL; } @@ -1150,12 +1149,12 @@ static inline int hstate_index(struct hstate *h) return 0; } -static inline int dissolve_free_huge_page(struct page *page) +static inline int dissolve_free_hugetlb_folio(struct folio *folio) { return 0; } -static inline int dissolve_free_huge_pages(unsigned long start_pfn, +static inline int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn) { return 0; @@ -1181,6 +1180,11 @@ static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) return 0; } +static inline bool htlb_allow_alloc_fallback(int reason) +{ + return false; +} + static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { @@ -1221,6 +1225,12 @@ static inline void hugetlb_register_node(struct node *node) static inline void hugetlb_unregister_node(struct node *node) { } + +static inline bool hugetlbfs_pagecache_present( + struct hstate *h, struct vm_area_struct *vma, unsigned long address) +{ + return false; +} #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h index 136e9842120e..b424555753b1 100644 --- a/include/linux/hw_random.h +++ b/include/linux/hw_random.h @@ -13,9 +13,8 @@ #define LINUX_HWRANDOM_H_ #include <linux/completion.h> -#include <linux/types.h> -#include <linux/list.h> #include <linux/kref.h> +#include <linux/types.h> /** * struct hwrng - Hardware Random Number Generator driver diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index edf96f249eb5..e94314760aab 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -45,6 +45,7 @@ enum hwmon_chip_attributes { hwmon_chip_power_samples, hwmon_chip_temp_samples, hwmon_chip_beep_enable, + hwmon_chip_pec, }; #define HWMON_C_TEMP_RESET_HISTORY BIT(hwmon_chip_temp_reset_history) @@ -60,6 +61,7 @@ enum hwmon_chip_attributes { #define HWMON_C_POWER_SAMPLES BIT(hwmon_chip_power_samples) #define HWMON_C_TEMP_SAMPLES BIT(hwmon_chip_temp_samples) #define HWMON_C_BEEP_ENABLE BIT(hwmon_chip_beep_enable) +#define HWMON_C_PEC BIT(hwmon_chip_pec) enum hwmon_temp_attributes { hwmon_temp_enable, diff --git a/include/linux/hwspinlock.h b/include/linux/hwspinlock.h index bfe7c1f1ac6d..f0231dbc4777 100644 --- a/include/linux/hwspinlock.h +++ b/include/linux/hwspinlock.h @@ -68,6 +68,7 @@ int __hwspin_lock_timeout(struct hwspinlock *, unsigned int, int, int __hwspin_trylock(struct hwspinlock *, int, unsigned long *); void __hwspin_unlock(struct hwspinlock *, int, unsigned long *); int of_hwspin_lock_get_id_byname(struct device_node *np, const char *name); +int hwspin_lock_bust(struct hwspinlock *hwlock, unsigned int id); int devm_hwspin_lock_free(struct device *dev, struct hwspinlock *hwlock); struct hwspinlock *devm_hwspin_lock_request(struct device *dev); struct hwspinlock *devm_hwspin_lock_request_specific(struct device *dev, @@ -127,6 +128,11 @@ void __hwspin_unlock(struct hwspinlock *hwlock, int mode, unsigned long *flags) { } +static inline int hwspin_lock_bust(struct hwspinlock *hwlock, unsigned int id) +{ + return 0; +} + static inline int of_hwspin_lock_get_id(struct device_node *np, int index) { return 0; diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 96ceb4095425..22c22fb91042 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -820,6 +820,8 @@ struct vmbus_requestor { #define VMBUS_RQST_RESET (U64_MAX - 3) struct vmbus_device { + /* preferred ring buffer size in KB, 0 means no preferred size for this device */ + size_t pref_ring_size; u16 dev_type; guid_t guid; bool perf_device; @@ -1328,11 +1330,7 @@ struct hv_device { #define device_to_hv_device(d) container_of_const(d, struct hv_device, device) - -static inline struct hv_driver *drv_to_hv_drv(struct device_driver *d) -{ - return container_of(d, struct hv_driver, driver); -} +#define drv_to_hv_drv(d) container_of_const(d, struct hv_driver, driver) static inline void hv_set_drvdata(struct hv_device *dev, void *data) { diff --git a/include/linux/i2c-mux.h b/include/linux/i2c-mux.h index 98ef73b7c8fd..1784ac7afb11 100644 --- a/include/linux/i2c-mux.h +++ b/include/linux/i2c-mux.h @@ -56,8 +56,7 @@ struct i2c_adapter *i2c_root_adapter(struct device *dev); * callback functions to perform hardware-specific mux control. */ int i2c_mux_add_adapter(struct i2c_mux_core *muxc, - u32 force_nr, u32 chan_id, - unsigned int class); + u32 force_nr, u32 chan_id); void i2c_mux_del_adapters(struct i2c_mux_core *muxc); diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 5e6cd43a6dbd..377def497298 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -30,7 +30,6 @@ extern const struct device_type i2c_client_type; /* --- General options ------------------------------------------------ */ struct i2c_msg; -struct i2c_algorithm; struct i2c_adapter; struct i2c_client; struct i2c_driver; @@ -304,7 +303,7 @@ struct i2c_driver { u32 flags; }; -#define to_i2c_driver(d) container_of(d, struct i2c_driver, driver) +#define to_i2c_driver(d) container_of_const(d, struct i2c_driver, driver) /** * struct i2c_client - represent an I2C slave device @@ -512,46 +511,54 @@ i2c_register_board_info(int busnum, struct i2c_board_info const *info, #endif /* I2C_BOARDINFO */ /** - * struct i2c_algorithm - represent I2C transfer method - * @master_xfer: Issue a set of i2c transactions to the given I2C adapter - * defined by the msgs array, with num messages available to transfer via - * the adapter specified by adap. - * @master_xfer_atomic: same as @master_xfer. Yet, only using atomic context - * so e.g. PMICs can be accessed very late before shutdown. Optional. - * @smbus_xfer: Issue smbus transactions to the given I2C adapter. If this + * struct i2c_algorithm - represent I2C transfer methods + * @xfer: Transfer a given number of messages defined by the msgs array via + * the specified adapter. + * @xfer_atomic: Same as @xfer. Yet, only using atomic context so e.g. PMICs + * can be accessed very late before shutdown. Optional. + * @smbus_xfer: Issue SMBus transactions to the given I2C adapter. If this * is not present, then the bus layer will try and convert the SMBus calls * into I2C transfers instead. - * @smbus_xfer_atomic: same as @smbus_xfer. Yet, only using atomic context + * @smbus_xfer_atomic: Same as @smbus_xfer. Yet, only using atomic context * so e.g. PMICs can be accessed very late before shutdown. Optional. * @functionality: Return the flags that this algorithm/adapter pair supports * from the ``I2C_FUNC_*`` flags. - * @reg_slave: Register given client to I2C slave mode of this adapter - * @unreg_slave: Unregister given client from I2C slave mode of this adapter + * @reg_target: Register given client to local target mode of this adapter + * @unreg_target: Unregister given client from local target mode of this adapter + * + * @master_xfer: deprecated, use @xfer + * @master_xfer_atomic: deprecated, use @xfer_atomic + * @reg_slave: deprecated, use @reg_target + * @unreg_slave: deprecated, use @unreg_target * - * The following structs are for those who like to implement new bus drivers: * i2c_algorithm is the interface to a class of hardware solutions which can * be addressed using the same bus algorithms - i.e. bit-banging or the PCF8584 * to name two of the most common. * - * The return codes from the ``master_xfer{_atomic}`` fields should indicate the + * The return codes from the ``xfer{_atomic}`` fields should indicate the * type of error code that occurred during the transfer, as documented in the * Kernel Documentation file Documentation/i2c/fault-codes.rst. Otherwise, the * number of messages executed should be returned. */ struct i2c_algorithm { /* - * If an adapter algorithm can't do I2C-level access, set master_xfer + * If an adapter algorithm can't do I2C-level access, set xfer * to NULL. If an adapter algorithm can do SMBus access, set * smbus_xfer. If set to NULL, the SMBus protocol is simulated * using common I2C messages. - * - * master_xfer should return the number of messages successfully - * processed, or a negative value on error */ - int (*master_xfer)(struct i2c_adapter *adap, struct i2c_msg *msgs, - int num); - int (*master_xfer_atomic)(struct i2c_adapter *adap, + union { + int (*xfer)(struct i2c_adapter *adap, struct i2c_msg *msgs, + int num); + int (*master_xfer)(struct i2c_adapter *adap, struct i2c_msg *msgs, + int num); + }; + union { + int (*xfer_atomic)(struct i2c_adapter *adap, struct i2c_msg *msgs, int num); + int (*master_xfer_atomic)(struct i2c_adapter *adap, + struct i2c_msg *msgs, int num); + }; int (*smbus_xfer)(struct i2c_adapter *adap, u16 addr, unsigned short flags, char read_write, u8 command, int size, union i2c_smbus_data *data); @@ -563,8 +570,14 @@ struct i2c_algorithm { u32 (*functionality)(struct i2c_adapter *adap); #if IS_ENABLED(CONFIG_I2C_SLAVE) - int (*reg_slave)(struct i2c_client *client); - int (*unreg_slave)(struct i2c_client *client); + union { + int (*reg_target)(struct i2c_client *client); + int (*reg_slave)(struct i2c_client *client); + }; + union { + int (*unreg_target)(struct i2c_client *client); + int (*unreg_slave)(struct i2c_client *client); + }; #endif }; @@ -852,7 +865,6 @@ static inline void i2c_mark_adapter_resumed(struct i2c_adapter *adap) /* i2c adapter classes (bitmask) */ #define I2C_CLASS_HWMON (1<<0) /* lm_sensors, ... */ -#define I2C_CLASS_SPD (1<<7) /* Memory modules */ /* Warn users that the adapter doesn't support classes anymore */ #define I2C_CLASS_DEPRECATED (1<<8) @@ -961,8 +973,6 @@ int i2c_handle_smbus_host_notify(struct i2c_adapter *adap, unsigned short addr); #define builtin_i2c_driver(__i2c_driver) \ builtin_driver(__i2c_driver, i2c_add_driver) -#endif /* I2C */ - /* must call put_device() when done with returned i2c_client device */ struct i2c_client *i2c_find_device_by_fwnode(struct fwnode_handle *fwnode); @@ -972,6 +982,28 @@ struct i2c_adapter *i2c_find_adapter_by_fwnode(struct fwnode_handle *fwnode); /* must call i2c_put_adapter() when done with returned i2c_adapter device */ struct i2c_adapter *i2c_get_adapter_by_fwnode(struct fwnode_handle *fwnode); +#else /* I2C */ + +static inline struct i2c_client * +i2c_find_device_by_fwnode(struct fwnode_handle *fwnode) +{ + return NULL; +} + +static inline struct i2c_adapter * +i2c_find_adapter_by_fwnode(struct fwnode_handle *fwnode) +{ + return NULL; +} + +static inline struct i2c_adapter * +i2c_get_adapter_by_fwnode(struct fwnode_handle *fwnode) +{ + return NULL; +} + +#endif /* !I2C */ + #if IS_ENABLED(CONFIG_OF) /* must call put_device() when done with returned i2c_client device */ static inline struct i2c_client *of_find_i2c_device_by_node(struct device_node *node) @@ -1034,7 +1066,7 @@ static inline int of_i2c_get_board_info(struct device *dev, struct acpi_resource; struct acpi_resource_i2c_serialbus; -#if IS_ENABLED(CONFIG_ACPI) +#if IS_REACHABLE(CONFIG_ACPI) && IS_REACHABLE(CONFIG_I2C) bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, struct acpi_resource_i2c_serialbus **i2c); int i2c_acpi_client_count(struct acpi_device *adev); diff --git a/include/linux/i3c/device.h b/include/linux/i3c/device.h index e119f11948ef..0a8a44ac2f02 100644 --- a/include/linux/i3c/device.h +++ b/include/linux/i3c/device.h @@ -183,10 +183,7 @@ struct i3c_driver { const struct i3c_device_id *id_table; }; -static inline struct i3c_driver *drv_to_i3cdrv(struct device_driver *drv) -{ - return container_of(drv, struct i3c_driver, driver); -} +#define drv_to_i3cdrv(__drv) container_of_const(__drv, struct i3c_driver, driver) struct device *i3cdev_to_dev(struct i3c_device *i3cdev); diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h index 0ca27dd86956..074f632868d9 100644 --- a/include/linux/i3c/master.h +++ b/include/linux/i3c/master.h @@ -33,6 +33,7 @@ enum { struct i3c_master_controller; struct i3c_bus; struct i3c_device; +extern const struct bus_type i3c_bus_type; /** * struct i3c_i2c_dev_desc - Common part of the I3C/I2C device descriptor diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 3385a2cc5b09..30cef3b940eb 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -373,6 +373,7 @@ struct ieee80211_trigger { /** * ieee80211_has_tods - check if IEEE80211_FCTL_TODS is set * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame has to-DS set */ static inline bool ieee80211_has_tods(__le16 fc) { @@ -382,6 +383,7 @@ static inline bool ieee80211_has_tods(__le16 fc) /** * ieee80211_has_fromds - check if IEEE80211_FCTL_FROMDS is set * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame has from-DS set */ static inline bool ieee80211_has_fromds(__le16 fc) { @@ -391,6 +393,7 @@ static inline bool ieee80211_has_fromds(__le16 fc) /** * ieee80211_has_a4 - check if IEEE80211_FCTL_TODS and IEEE80211_FCTL_FROMDS are set * @fc: frame control bytes in little-endian byteorder + * Return: whether or not it's a 4-address frame (from-DS and to-DS set) */ static inline bool ieee80211_has_a4(__le16 fc) { @@ -401,6 +404,7 @@ static inline bool ieee80211_has_a4(__le16 fc) /** * ieee80211_has_morefrags - check if IEEE80211_FCTL_MOREFRAGS is set * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame has more fragments (more frags bit set) */ static inline bool ieee80211_has_morefrags(__le16 fc) { @@ -410,6 +414,7 @@ static inline bool ieee80211_has_morefrags(__le16 fc) /** * ieee80211_has_retry - check if IEEE80211_FCTL_RETRY is set * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the retry flag is set */ static inline bool ieee80211_has_retry(__le16 fc) { @@ -419,6 +424,7 @@ static inline bool ieee80211_has_retry(__le16 fc) /** * ieee80211_has_pm - check if IEEE80211_FCTL_PM is set * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the power management flag is set */ static inline bool ieee80211_has_pm(__le16 fc) { @@ -428,6 +434,7 @@ static inline bool ieee80211_has_pm(__le16 fc) /** * ieee80211_has_moredata - check if IEEE80211_FCTL_MOREDATA is set * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the more data flag is set */ static inline bool ieee80211_has_moredata(__le16 fc) { @@ -437,6 +444,7 @@ static inline bool ieee80211_has_moredata(__le16 fc) /** * ieee80211_has_protected - check if IEEE80211_FCTL_PROTECTED is set * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the protected flag is set */ static inline bool ieee80211_has_protected(__le16 fc) { @@ -446,6 +454,7 @@ static inline bool ieee80211_has_protected(__le16 fc) /** * ieee80211_has_order - check if IEEE80211_FCTL_ORDER is set * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the order flag is set */ static inline bool ieee80211_has_order(__le16 fc) { @@ -455,6 +464,7 @@ static inline bool ieee80211_has_order(__le16 fc) /** * ieee80211_is_mgmt - check if type is IEEE80211_FTYPE_MGMT * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame type is management */ static inline bool ieee80211_is_mgmt(__le16 fc) { @@ -465,6 +475,7 @@ static inline bool ieee80211_is_mgmt(__le16 fc) /** * ieee80211_is_ctl - check if type is IEEE80211_FTYPE_CTL * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame type is control */ static inline bool ieee80211_is_ctl(__le16 fc) { @@ -475,6 +486,7 @@ static inline bool ieee80211_is_ctl(__le16 fc) /** * ieee80211_is_data - check if type is IEEE80211_FTYPE_DATA * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a data frame */ static inline bool ieee80211_is_data(__le16 fc) { @@ -485,6 +497,7 @@ static inline bool ieee80211_is_data(__le16 fc) /** * ieee80211_is_ext - check if type is IEEE80211_FTYPE_EXT * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame type is extended */ static inline bool ieee80211_is_ext(__le16 fc) { @@ -496,6 +509,7 @@ static inline bool ieee80211_is_ext(__le16 fc) /** * ieee80211_is_data_qos - check if type is IEEE80211_FTYPE_DATA and IEEE80211_STYPE_QOS_DATA is set * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a QoS data frame */ static inline bool ieee80211_is_data_qos(__le16 fc) { @@ -510,6 +524,8 @@ static inline bool ieee80211_is_data_qos(__le16 fc) /** * ieee80211_is_data_present - check if type is IEEE80211_FTYPE_DATA and has data * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a QoS data frame that has data + * (i.e. is not null data) */ static inline bool ieee80211_is_data_present(__le16 fc) { @@ -524,6 +540,7 @@ static inline bool ieee80211_is_data_present(__le16 fc) /** * ieee80211_is_assoc_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ASSOC_REQ * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is an association request */ static inline bool ieee80211_is_assoc_req(__le16 fc) { @@ -534,6 +551,7 @@ static inline bool ieee80211_is_assoc_req(__le16 fc) /** * ieee80211_is_assoc_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ASSOC_RESP * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is an association response */ static inline bool ieee80211_is_assoc_resp(__le16 fc) { @@ -544,6 +562,7 @@ static inline bool ieee80211_is_assoc_resp(__le16 fc) /** * ieee80211_is_reassoc_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_REASSOC_REQ * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a reassociation request */ static inline bool ieee80211_is_reassoc_req(__le16 fc) { @@ -554,6 +573,7 @@ static inline bool ieee80211_is_reassoc_req(__le16 fc) /** * ieee80211_is_reassoc_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_REASSOC_RESP * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a reassociation response */ static inline bool ieee80211_is_reassoc_resp(__le16 fc) { @@ -564,6 +584,7 @@ static inline bool ieee80211_is_reassoc_resp(__le16 fc) /** * ieee80211_is_probe_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_PROBE_REQ * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a probe request */ static inline bool ieee80211_is_probe_req(__le16 fc) { @@ -574,6 +595,7 @@ static inline bool ieee80211_is_probe_req(__le16 fc) /** * ieee80211_is_probe_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_PROBE_RESP * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a probe response */ static inline bool ieee80211_is_probe_resp(__le16 fc) { @@ -584,6 +606,7 @@ static inline bool ieee80211_is_probe_resp(__le16 fc) /** * ieee80211_is_beacon - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_BEACON * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a (regular, not S1G) beacon */ static inline bool ieee80211_is_beacon(__le16 fc) { @@ -595,6 +618,7 @@ static inline bool ieee80211_is_beacon(__le16 fc) * ieee80211_is_s1g_beacon - check if IEEE80211_FTYPE_EXT && * IEEE80211_STYPE_S1G_BEACON * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is an S1G beacon */ static inline bool ieee80211_is_s1g_beacon(__le16 fc) { @@ -604,30 +628,21 @@ static inline bool ieee80211_is_s1g_beacon(__le16 fc) } /** - * ieee80211_next_tbtt_present - check if IEEE80211_FTYPE_EXT && - * IEEE80211_STYPE_S1G_BEACON && IEEE80211_S1G_BCN_NEXT_TBTT - * @fc: frame control bytes in little-endian byteorder - */ -static inline bool ieee80211_next_tbtt_present(__le16 fc) -{ - return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) == - cpu_to_le16(IEEE80211_FTYPE_EXT | IEEE80211_STYPE_S1G_BEACON) && - fc & cpu_to_le16(IEEE80211_S1G_BCN_NEXT_TBTT); -} - -/** - * ieee80211_is_s1g_short_beacon - check if next tbtt present bit is set. Only - * true for S1G beacons when they're short. + * ieee80211_is_s1g_short_beacon - check if frame is an S1G short beacon * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is an S1G short beacon, + * i.e. it is an S1G beacon with 'next TBTT' flag set */ static inline bool ieee80211_is_s1g_short_beacon(__le16 fc) { - return ieee80211_is_s1g_beacon(fc) && ieee80211_next_tbtt_present(fc); + return ieee80211_is_s1g_beacon(fc) && + (fc & cpu_to_le16(IEEE80211_S1G_BCN_NEXT_TBTT)); } /** * ieee80211_is_atim - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ATIM * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is an ATIM frame */ static inline bool ieee80211_is_atim(__le16 fc) { @@ -638,6 +653,7 @@ static inline bool ieee80211_is_atim(__le16 fc) /** * ieee80211_is_disassoc - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_DISASSOC * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a disassociation frame */ static inline bool ieee80211_is_disassoc(__le16 fc) { @@ -648,6 +664,7 @@ static inline bool ieee80211_is_disassoc(__le16 fc) /** * ieee80211_is_auth - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_AUTH * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is an authentication frame */ static inline bool ieee80211_is_auth(__le16 fc) { @@ -658,6 +675,7 @@ static inline bool ieee80211_is_auth(__le16 fc) /** * ieee80211_is_deauth - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_DEAUTH * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a deauthentication frame */ static inline bool ieee80211_is_deauth(__le16 fc) { @@ -668,6 +686,7 @@ static inline bool ieee80211_is_deauth(__le16 fc) /** * ieee80211_is_action - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ACTION * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is an action frame */ static inline bool ieee80211_is_action(__le16 fc) { @@ -678,6 +697,7 @@ static inline bool ieee80211_is_action(__le16 fc) /** * ieee80211_is_back_req - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_BACK_REQ * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a block-ACK request frame */ static inline bool ieee80211_is_back_req(__le16 fc) { @@ -688,6 +708,7 @@ static inline bool ieee80211_is_back_req(__le16 fc) /** * ieee80211_is_back - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_BACK * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a block-ACK frame */ static inline bool ieee80211_is_back(__le16 fc) { @@ -698,6 +719,7 @@ static inline bool ieee80211_is_back(__le16 fc) /** * ieee80211_is_pspoll - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_PSPOLL * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a PS-poll frame */ static inline bool ieee80211_is_pspoll(__le16 fc) { @@ -708,6 +730,7 @@ static inline bool ieee80211_is_pspoll(__le16 fc) /** * ieee80211_is_rts - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_RTS * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is an RTS frame */ static inline bool ieee80211_is_rts(__le16 fc) { @@ -718,6 +741,7 @@ static inline bool ieee80211_is_rts(__le16 fc) /** * ieee80211_is_cts - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CTS * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a CTS frame */ static inline bool ieee80211_is_cts(__le16 fc) { @@ -728,6 +752,7 @@ static inline bool ieee80211_is_cts(__le16 fc) /** * ieee80211_is_ack - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_ACK * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is an ACK frame */ static inline bool ieee80211_is_ack(__le16 fc) { @@ -738,6 +763,7 @@ static inline bool ieee80211_is_ack(__le16 fc) /** * ieee80211_is_cfend - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CFEND * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a CF-end frame */ static inline bool ieee80211_is_cfend(__le16 fc) { @@ -748,6 +774,7 @@ static inline bool ieee80211_is_cfend(__le16 fc) /** * ieee80211_is_cfendack - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CFENDACK * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a CF-end-ack frame */ static inline bool ieee80211_is_cfendack(__le16 fc) { @@ -758,6 +785,7 @@ static inline bool ieee80211_is_cfendack(__le16 fc) /** * ieee80211_is_nullfunc - check if frame is a regular (non-QoS) nullfunc frame * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a nullfunc frame */ static inline bool ieee80211_is_nullfunc(__le16 fc) { @@ -768,6 +796,7 @@ static inline bool ieee80211_is_nullfunc(__le16 fc) /** * ieee80211_is_qos_nullfunc - check if frame is a QoS nullfunc frame * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a QoS nullfunc frame */ static inline bool ieee80211_is_qos_nullfunc(__le16 fc) { @@ -778,6 +807,7 @@ static inline bool ieee80211_is_qos_nullfunc(__le16 fc) /** * ieee80211_is_trigger - check if frame is trigger frame * @fc: frame control field in little-endian byteorder + * Return: whether or not the frame is a trigger frame */ static inline bool ieee80211_is_trigger(__le16 fc) { @@ -788,6 +818,7 @@ static inline bool ieee80211_is_trigger(__le16 fc) /** * ieee80211_is_any_nullfunc - check if frame is regular or QoS nullfunc frame * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is a nullfunc or QoS nullfunc frame */ static inline bool ieee80211_is_any_nullfunc(__le16 fc) { @@ -797,6 +828,8 @@ static inline bool ieee80211_is_any_nullfunc(__le16 fc) /** * ieee80211_is_first_frag - check if IEEE80211_SCTL_FRAG is not set * @seq_ctrl: frame sequence control bytes in little-endian byteorder + * Return: whether or not the frame is the first fragment (also true if + * it's not fragmented at all) */ static inline bool ieee80211_is_first_frag(__le16 seq_ctrl) { @@ -806,6 +839,7 @@ static inline bool ieee80211_is_first_frag(__le16 seq_ctrl) /** * ieee80211_is_frag - check if a frame is a fragment * @hdr: 802.11 header of the frame + * Return: whether or not the frame is a fragment */ static inline bool ieee80211_is_frag(struct ieee80211_hdr *hdr) { @@ -1101,7 +1135,7 @@ enum ieee80211_vht_opmode_bits { }; /** - * enum ieee80211_s1g_chanwidth + * enum ieee80211_s1g_chanwidth - S1G channel widths * These are defined in IEEE802.11-2016ah Table 10-20 * as BSS Channel Width * @@ -1287,6 +1321,24 @@ struct ieee80211_ttlm_elem { u8 optional[]; } __packed; +/** + * struct ieee80211_bss_load_elem - BSS Load elemen + * + * Defined in section 9.4.2.26 in IEEE 802.11-REVme D4.1 + * + * @sta_count: total number of STAs currently associated with the AP. + * @channel_util: Percentage of time that the access point sensed the channel + * was busy. This value is in range [0, 255], the highest value means + * 100% busy. + * @avail_admission_capa: remaining amount of medium time used for admission + * control. + */ +struct ieee80211_bss_load_elem { + __le16 sta_count; + u8 channel_util; + __le16 avail_admission_capa; +} __packed; + struct ieee80211_mgmt { __le16 frame_control; __le16 duration; @@ -2341,6 +2393,8 @@ struct ieee80211_eht_operation_info { * @max_vht_nss: current maximum NSS as advertised by the STA in * operating mode notification, can be 0 in which case the * capability data will be used to derive this (from MCS support) + * Return: The maximum NSS that can be used for the given bandwidth/MCS + * combination * * Due to the VHT Extended NSS Bandwidth Support, the maximum NSS can * vary for a given BW/MCS. This function parses the data. @@ -2352,44 +2406,6 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, int mcs, bool ext_nss_bw_capable, unsigned int max_vht_nss); -/** - * enum ieee80211_ap_reg_power - regulatory power for a Access Point - * - * @IEEE80211_REG_UNSET_AP: Access Point has no regulatory power mode - * @IEEE80211_REG_LPI_AP: Indoor Access Point - * @IEEE80211_REG_SP_AP: Standard power Access Point - * @IEEE80211_REG_VLP_AP: Very low power Access Point - * @IEEE80211_REG_AP_POWER_AFTER_LAST: internal - * @IEEE80211_REG_AP_POWER_MAX: maximum value - */ -enum ieee80211_ap_reg_power { - IEEE80211_REG_UNSET_AP, - IEEE80211_REG_LPI_AP, - IEEE80211_REG_SP_AP, - IEEE80211_REG_VLP_AP, - IEEE80211_REG_AP_POWER_AFTER_LAST, - IEEE80211_REG_AP_POWER_MAX = - IEEE80211_REG_AP_POWER_AFTER_LAST - 1, -}; - -/** - * enum ieee80211_client_reg_power - regulatory power for a client - * - * @IEEE80211_REG_UNSET_CLIENT: Client has no regulatory power mode - * @IEEE80211_REG_DEFAULT_CLIENT: Default Client - * @IEEE80211_REG_SUBORDINATE_CLIENT: Subordinate Client - * @IEEE80211_REG_CLIENT_POWER_AFTER_LAST: internal - * @IEEE80211_REG_CLIENT_POWER_MAX: maximum value - */ -enum ieee80211_client_reg_power { - IEEE80211_REG_UNSET_CLIENT, - IEEE80211_REG_DEFAULT_CLIENT, - IEEE80211_REG_SUBORDINATE_CLIENT, - IEEE80211_REG_CLIENT_POWER_AFTER_LAST, - IEEE80211_REG_CLIENT_POWER_MAX = - IEEE80211_REG_CLIENT_POWER_AFTER_LAST - 1, -}; - /* 802.11ax HE MAC capabilities */ #define IEEE80211_HE_MAC_CAP0_HTC_HE 0x01 #define IEEE80211_HE_MAC_CAP0_TWT_REQ 0x02 @@ -2742,9 +2758,11 @@ static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len) #define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x40000000 #define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x80000000 -#define IEEE80211_6GHZ_CTRL_REG_LPI_AP 0 -#define IEEE80211_6GHZ_CTRL_REG_SP_AP 1 -#define IEEE80211_6GHZ_CTRL_REG_VLP_AP 2 +#define IEEE80211_6GHZ_CTRL_REG_LPI_AP 0 +#define IEEE80211_6GHZ_CTRL_REG_SP_AP 1 +#define IEEE80211_6GHZ_CTRL_REG_VLP_AP 2 +#define IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP 3 +#define IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP 4 /** * struct ieee80211_he_6ghz_oper - HE 6 GHz operation Information field @@ -2769,22 +2787,6 @@ struct ieee80211_he_6ghz_oper { u8 minrate; } __packed; -/* - * In "9.4.2.161 Transmit Power Envelope element" of "IEEE Std 802.11ax-2021", - * it show four types in "Table 9-275a-Maximum Transmit Power Interpretation - * subfield encoding", and two category for each type in "Table E-12-Regulatory - * Info subfield encoding in the United States". - * So it it totally max 8 Transmit Power Envelope element. - */ -#define IEEE80211_TPE_MAX_IE_COUNT 8 -/* - * In "Table 9-277—Meaning of Maximum Transmit Power Count subfield" - * of "IEEE Std 802.11ax™‐2021", the max power level is 8. - */ -#define IEEE80211_MAX_NUM_PWR_LEVEL 8 - -#define IEEE80211_TPE_MAX_POWER_COUNT 8 - /* transmit power interpretation type of transmit power envelope element */ enum ieee80211_tx_power_intrpt_type { IEEE80211_TPE_LOCAL_EIRP, @@ -2793,24 +2795,107 @@ enum ieee80211_tx_power_intrpt_type { IEEE80211_TPE_REG_CLIENT_EIRP_PSD, }; +/* category type of transmit power envelope element */ +enum ieee80211_tx_power_category_6ghz { + IEEE80211_TPE_CAT_6GHZ_DEFAULT = 0, + IEEE80211_TPE_CAT_6GHZ_SUBORDINATE = 1, +}; + +/* + * For IEEE80211_TPE_LOCAL_EIRP / IEEE80211_TPE_REG_CLIENT_EIRP, + * setting to 63.5 dBm means no constraint. + */ +#define IEEE80211_TPE_MAX_TX_PWR_NO_CONSTRAINT 127 + +/* + * For IEEE80211_TPE_LOCAL_EIRP_PSD / IEEE80211_TPE_REG_CLIENT_EIRP_PSD, + * setting to 127 indicates no PSD limit for the 20 MHz channel. + */ +#define IEEE80211_TPE_PSD_NO_LIMIT 127 + /** * struct ieee80211_tx_pwr_env - Transmit Power Envelope - * @tx_power_info: Transmit Power Information field - * @tx_power: Maximum Transmit Power field + * @info: Transmit Power Information field + * @variable: Maximum Transmit Power field * * This structure represents the payload of the "Transmit Power * Envelope element" as described in IEEE Std 802.11ax-2021 section * 9.4.2.161 */ struct ieee80211_tx_pwr_env { - u8 tx_power_info; - s8 tx_power[IEEE80211_TPE_MAX_POWER_COUNT]; + u8 info; + u8 variable[]; } __packed; #define IEEE80211_TX_PWR_ENV_INFO_COUNT 0x7 #define IEEE80211_TX_PWR_ENV_INFO_INTERPRET 0x38 #define IEEE80211_TX_PWR_ENV_INFO_CATEGORY 0xC0 +#define IEEE80211_TX_PWR_ENV_EXT_COUNT 0xF + +static inline bool ieee80211_valid_tpe_element(const u8 *data, u8 len) +{ + const struct ieee80211_tx_pwr_env *env = (const void *)data; + u8 count, interpret, category; + u8 needed = sizeof(*env); + u8 N; /* also called N in the spec */ + + if (len < needed) + return false; + + count = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_COUNT); + interpret = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_INTERPRET); + category = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_CATEGORY); + + switch (category) { + case IEEE80211_TPE_CAT_6GHZ_DEFAULT: + case IEEE80211_TPE_CAT_6GHZ_SUBORDINATE: + break; + default: + return false; + } + + switch (interpret) { + case IEEE80211_TPE_LOCAL_EIRP: + case IEEE80211_TPE_REG_CLIENT_EIRP: + if (count > 3) + return false; + + /* count == 0 encodes 1 value for 20 MHz, etc. */ + needed += count + 1; + + if (len < needed) + return false; + + /* there can be extension fields not accounted for in 'count' */ + + return true; + case IEEE80211_TPE_LOCAL_EIRP_PSD: + case IEEE80211_TPE_REG_CLIENT_EIRP_PSD: + if (count > 4) + return false; + + N = count ? 1 << (count - 1) : 1; + needed += N; + + if (len < needed) + return false; + + if (len > needed) { + u8 K = u8_get_bits(env->variable[N], + IEEE80211_TX_PWR_ENV_EXT_COUNT); + + needed += 1 + K; + if (len < needed) + return false; + } + + return true; + } + + return false; +} + /* * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size * @he_oper_ie: byte data of the He Operations IE, stating from the byte @@ -4125,7 +4210,7 @@ enum ieee80211_idle_options { }; /** - * struct ieee80211_bss_max_idle_period_ie + * struct ieee80211_bss_max_idle_period_ie - BSS max idle period element struct * * This structure refers to "BSS Max idle period element" * @@ -4160,7 +4245,7 @@ enum ieee80211_sa_query_action { }; /** - * struct ieee80211_bssid_index + * struct ieee80211_bssid_index - multiple BSSID index element structure * * This structure refers to "Multiple BSSID-index element" * @@ -4175,7 +4260,8 @@ struct ieee80211_bssid_index { }; /** - * struct ieee80211_multiple_bssid_configuration + * struct ieee80211_multiple_bssid_configuration - multiple BSSID configuration + * element structure * * This structure refers to "Multiple BSSID Configuration element" * @@ -4306,6 +4392,7 @@ struct ieee80211_he_6ghz_capa { /** * ieee80211_get_qos_ctl - get pointer to qos control bytes * @hdr: the frame + * Return: a pointer to the QoS control field in the frame header * * The qos ctrl bytes come after the frame_control, duration, seq_num * and 3 or 4 addresses of length ETH_ALEN. Checks frame_control to choose @@ -4328,6 +4415,7 @@ static inline u8 *ieee80211_get_qos_ctl(struct ieee80211_hdr *hdr) /** * ieee80211_get_tid - get qos TID * @hdr: the frame + * Return: the TID from the QoS control field */ static inline u8 ieee80211_get_tid(struct ieee80211_hdr *hdr) { @@ -4339,6 +4427,7 @@ static inline u8 ieee80211_get_tid(struct ieee80211_hdr *hdr) /** * ieee80211_get_SA - get pointer to SA * @hdr: the frame + * Return: a pointer to the source address (SA) * * Given an 802.11 frame, this function returns the offset * to the source address (SA). It does not verify that the @@ -4358,6 +4447,7 @@ static inline u8 *ieee80211_get_SA(struct ieee80211_hdr *hdr) /** * ieee80211_get_DA - get pointer to DA * @hdr: the frame + * Return: a pointer to the destination address (DA) * * Given an 802.11 frame, this function returns the offset * to the destination address (DA). It does not verify that @@ -4376,6 +4466,7 @@ static inline u8 *ieee80211_get_DA(struct ieee80211_hdr *hdr) /** * ieee80211_is_bufferable_mmpdu - check if frame is bufferable MMPDU * @skb: the skb to check, starting with the 802.11 header + * Return: whether or not the MMPDU is bufferable */ static inline bool ieee80211_is_bufferable_mmpdu(struct sk_buff *skb) { @@ -4414,6 +4505,7 @@ static inline bool ieee80211_is_bufferable_mmpdu(struct sk_buff *skb) /** * _ieee80211_is_robust_mgmt_frame - check if frame is a robust management frame * @hdr: the frame (buffer must include at least the first octet of payload) + * Return: whether or not the frame is a robust management frame */ static inline bool _ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr) { @@ -4450,6 +4542,7 @@ static inline bool _ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr) /** * ieee80211_is_robust_mgmt_frame - check if skb contains a robust mgmt frame * @skb: the skb containing the frame, length will be checked + * Return: whether or not the frame is a robust management frame */ static inline bool ieee80211_is_robust_mgmt_frame(struct sk_buff *skb) { @@ -4462,6 +4555,7 @@ static inline bool ieee80211_is_robust_mgmt_frame(struct sk_buff *skb) * ieee80211_is_public_action - check if frame is a public action frame * @hdr: the frame * @len: length of the frame + * Return: whether or not the frame is a public action frame */ static inline bool ieee80211_is_public_action(struct ieee80211_hdr *hdr, size_t len) @@ -4507,8 +4601,9 @@ ieee80211_is_protected_dual_of_public_action(struct sk_buff *skb) /** * _ieee80211_is_group_privacy_action - check if frame is a group addressed - * privacy action frame + * privacy action frame * @hdr: the frame + * Return: whether or not the frame is a group addressed privacy action frame */ static inline bool _ieee80211_is_group_privacy_action(struct ieee80211_hdr *hdr) { @@ -4524,8 +4619,9 @@ static inline bool _ieee80211_is_group_privacy_action(struct ieee80211_hdr *hdr) /** * ieee80211_is_group_privacy_action - check if frame is a group addressed - * privacy action frame + * privacy action frame * @skb: the skb containing the frame, length will be checked + * Return: whether or not the frame is a group addressed privacy action frame */ static inline bool ieee80211_is_group_privacy_action(struct sk_buff *skb) { @@ -4537,6 +4633,7 @@ static inline bool ieee80211_is_group_privacy_action(struct sk_buff *skb) /** * ieee80211_tu_to_usec - convert time units (TU) to microseconds * @tu: the TUs + * Return: the time value converted to microseconds */ static inline unsigned long ieee80211_tu_to_usec(unsigned long tu) { @@ -4548,6 +4645,7 @@ static inline unsigned long ieee80211_tu_to_usec(unsigned long tu) * @tim: the TIM IE * @tim_len: length of the TIM IE * @aid: the AID to look for + * Return: whether or not traffic is indicated in the TIM for the given AID */ static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim, u8 tim_len, u16 aid) @@ -4574,8 +4672,10 @@ static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim, } /** - * ieee80211_get_tdls_action - get tdls packet action (or -1, if not tdls packet) + * ieee80211_get_tdls_action - get TDLS action code * @skb: the skb containing the frame, length will not be checked + * Return: the TDLS action code, or -1 if it's not an encapsulated TDLS action + * frame * * This function assumes the frame is a data frame, and that the network header * is in the correct place. @@ -4615,6 +4715,7 @@ static inline int ieee80211_get_tdls_action(struct sk_buff *skb) /** * ieee80211_action_contains_tpc - checks if the frame contains TPC element * @skb: the skb containing the frame, length will be checked + * Return: %true if the frame contains a TPC element, %false otherwise * * This function checks if it's either TPC report action frame or Link * Measurement report action frame as defined in IEEE Std. 802.11-2012 8.5.2.5 @@ -4659,6 +4760,11 @@ static inline bool ieee80211_action_contains_tpc(struct sk_buff *skb) return true; } +/** + * ieee80211_is_timing_measurement - check if frame is timing measurement response + * @skb: the SKB to check + * Return: whether or not the frame is a valid timing measurement response + */ static inline bool ieee80211_is_timing_measurement(struct sk_buff *skb) { struct ieee80211_mgmt *mgmt = (void *)skb->data; @@ -4678,6 +4784,11 @@ static inline bool ieee80211_is_timing_measurement(struct sk_buff *skb) return false; } +/** + * ieee80211_is_ftm - check if frame is FTM response + * @skb: the SKB to check + * Return: whether or not the frame is a valid FTM response action frame + */ static inline bool ieee80211_is_ftm(struct sk_buff *skb) { struct ieee80211_mgmt *mgmt = (void *)skb->data; @@ -4732,6 +4843,7 @@ struct element { * @element: element pointer after for_each_element() or friends * @data: same data pointer as passed to for_each_element() or friends * @datalen: same data length as passed to for_each_element() or friends + * Return: %true if all elements were iterated, %false otherwise; see notes * * This function returns %true if all the data was parsed or considered * while walking the elements. Only use this if your for_each_element() @@ -4935,6 +5047,7 @@ struct ieee80211_mle_tdls_common_info { * ieee80211_mle_common_size - check multi-link element common size * @data: multi-link element, must already be checked for size using * ieee80211_mle_size_ok() + * Return: the size of the multi-link element's "common" subfield */ static inline u8 ieee80211_mle_common_size(const u8 *data) { @@ -4967,11 +5080,10 @@ static inline u8 ieee80211_mle_common_size(const u8 *data) /** * ieee80211_mle_get_link_id - returns the link ID * @data: the basic multi link element + * Return: the link ID, or -1 if not present * * The element is assumed to be of the correct type (BASIC) and big enough, * this must be checked using ieee80211_mle_type_ok(). - * - * If the BSS link ID can't be found, -1 will be returned */ static inline int ieee80211_mle_get_link_id(const u8 *data) { @@ -4991,12 +5103,10 @@ static inline int ieee80211_mle_get_link_id(const u8 *data) /** * ieee80211_mle_get_bss_param_ch_cnt - returns the BSS parameter change count * @data: pointer to the basic multi link element + * Return: the BSS Parameter Change Count field value, or -1 if not present * * The element is assumed to be of the correct type (BASIC) and big enough, * this must be checked using ieee80211_mle_type_ok(). - * - * If the BSS parameter change count value can't be found (the presence bit - * for it is clear), -1 will be returned. */ static inline int ieee80211_mle_get_bss_param_ch_cnt(const u8 *data) @@ -5019,13 +5129,13 @@ ieee80211_mle_get_bss_param_ch_cnt(const u8 *data) /** * ieee80211_mle_get_eml_med_sync_delay - returns the medium sync delay - * @data: pointer to the multi link EHT IE + * @data: pointer to the multi-link element + * Return: the medium synchronization delay field value from the multi-link + * element, or the default value (%IEEE80211_MED_SYNC_DELAY_DEFAULT) + * if not present * * The element is assumed to be of the correct type (BASIC) and big enough, * this must be checked using ieee80211_mle_type_ok(). - * - * If the medium synchronization is not present, then the default value is - * returned. */ static inline u16 ieee80211_mle_get_eml_med_sync_delay(const u8 *data) { @@ -5049,12 +5159,12 @@ static inline u16 ieee80211_mle_get_eml_med_sync_delay(const u8 *data) /** * ieee80211_mle_get_eml_cap - returns the EML capability - * @data: pointer to the multi link EHT IE + * @data: pointer to the multi-link element + * Return: the EML capability field value from the multi-link element, + * or 0 if not present * * The element is assumed to be of the correct type (BASIC) and big enough, * this must be checked using ieee80211_mle_type_ok(). - * - * If the EML capability is not present, 0 will be returned. */ static inline u16 ieee80211_mle_get_eml_cap(const u8 *data) { @@ -5080,13 +5190,12 @@ static inline u16 ieee80211_mle_get_eml_cap(const u8 *data) /** * ieee80211_mle_get_mld_capa_op - returns the MLD capabilities and operations. - * @data: pointer to the multi link EHT IE + * @data: pointer to the multi-link element + * Return: the MLD capabilities and operations field value from the multi-link + * element, or 0 if not present * * The element is assumed to be of the correct type (BASIC) and big enough, * this must be checked using ieee80211_mle_type_ok(). - * - * If the MLD capabilities and operations field is not present, 0 will be - * returned. */ static inline u16 ieee80211_mle_get_mld_capa_op(const u8 *data) { @@ -5117,12 +5226,11 @@ static inline u16 ieee80211_mle_get_mld_capa_op(const u8 *data) /** * ieee80211_mle_get_mld_id - returns the MLD ID - * @data: pointer to the multi link element + * @data: pointer to the multi-link element + * Return: The MLD ID in the given multi-link element, or 0 if not present * * The element is assumed to be of the correct type (BASIC) and big enough, * this must be checked using ieee80211_mle_type_ok(). - * - * If the MLD ID is not present, 0 will be returned. */ static inline u8 ieee80211_mle_get_mld_id(const u8 *data) { @@ -5157,6 +5265,7 @@ static inline u8 ieee80211_mle_get_mld_id(const u8 *data) * ieee80211_mle_size_ok - validate multi-link element size * @data: pointer to the element data * @len: length of the containing element + * Return: whether or not the multi-link element size is OK */ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) { @@ -5166,7 +5275,7 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) bool check_common_len = false; u16 control; - if (len < fixed) + if (!data || len < fixed) return false; control = le16_to_cpu(mle->control); @@ -5226,6 +5335,7 @@ static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) * @data: pointer to the element data * @type: expected type of the element * @len: length of the containing element + * Return: whether or not the multi-link element type matches and size is OK */ static inline bool ieee80211_mle_type_ok(const u8 *data, u8 type, size_t len) { @@ -5269,6 +5379,7 @@ struct ieee80211_mle_per_sta_profile { * profile size * @data: pointer to the sub element data * @len: length of the containing sub element + * Return: %true if the STA profile is large enough, %false otherwise */ static inline bool ieee80211_mle_basic_sta_prof_size_ok(const u8 *data, size_t len) @@ -5302,7 +5413,7 @@ static inline bool ieee80211_mle_basic_sta_prof_size_ok(const u8 *data, info_len += 1; return prof->sta_info_len >= info_len && - fixed + prof->sta_info_len <= len; + fixed + prof->sta_info_len - 1 <= len; } /** @@ -5353,6 +5464,7 @@ ieee80211_mle_basic_sta_prof_bss_param_ch_cnt(const struct ieee80211_mle_per_sta * element sta profile size. * @data: pointer to the sub element data * @len: length of the containing sub element + * Return: %true if the STA profile is large enough, %false otherwise */ static inline bool ieee80211_mle_reconf_sta_prof_size_ok(const u8 *data, size_t len) diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h index 719cf9cc6e1a..f8c1d2505940 100644 --- a/include/linux/iio/adc/ad_sigma_delta.h +++ b/include/linux/iio/adc/ad_sigma_delta.h @@ -37,6 +37,10 @@ struct iio_dev; * @append_status: Will be called to enable status append at the end of the sample, may be NULL. * @set_mode: Will be called to select the current mode, may be NULL. * @disable_all: Will be called to disable all channels, may be NULL. + * @disable_one: Will be called to disable a single channel after + * ad_sigma_delta_single_conversion(), may be NULL. + * Usage of this callback expects iio_chan_spec.address to contain + * the value required for the driver to identify the channel. * @postprocess_sample: Is called for each sampled data word, can be used to * modify or drop the sample data, it, may be NULL. * @has_registers: true if the device has writable and readable registers, false @@ -48,12 +52,14 @@ struct iio_dev; * be used. * @irq_flags: flags for the interrupt used by the triggered buffer * @num_slots: Number of sequencer slots + * @irq_line: IRQ for reading conversions. If 0, spi->irq will be used */ struct ad_sigma_delta_info { int (*set_channel)(struct ad_sigma_delta *, unsigned int channel); int (*append_status)(struct ad_sigma_delta *, bool append); int (*set_mode)(struct ad_sigma_delta *, enum ad_sigma_delta_mode mode); int (*disable_all)(struct ad_sigma_delta *); + int (*disable_one)(struct ad_sigma_delta *, unsigned int chan); int (*postprocess_sample)(struct ad_sigma_delta *, unsigned int raw_sample); bool has_registers; unsigned int addr_shift; @@ -62,6 +68,7 @@ struct ad_sigma_delta_info { unsigned int data_reg; unsigned long irq_flags; unsigned int num_slots; + int irq_line; }; /** @@ -89,6 +96,7 @@ struct ad_sigma_delta { unsigned int active_slots; unsigned int current_slot; unsigned int num_slots; + int irq_line; bool status_appended; /* map slots to channels in order to know what to expect from devices */ unsigned int *slots; @@ -137,6 +145,15 @@ static inline int ad_sigma_delta_disable_all(struct ad_sigma_delta *sd) return 0; } +static inline int ad_sigma_delta_disable_one(struct ad_sigma_delta *sd, + unsigned int chan) +{ + if (sd->info->disable_one) + return sd->info->disable_one(sd, chan); + + return 0; +} + static inline int ad_sigma_delta_set_mode(struct ad_sigma_delta *sd, unsigned int mode) { diff --git a/include/linux/iio/backend.h b/include/linux/iio/backend.h index a6d79381866e..8099759d7242 100644 --- a/include/linux/iio/backend.h +++ b/include/linux/iio/backend.h @@ -4,6 +4,7 @@ #include <linux/types.h> +struct iio_chan_spec; struct fwnode_handle; struct iio_backend; struct device; @@ -15,12 +16,32 @@ enum iio_backend_data_type { IIO_BACKEND_DATA_TYPE_MAX }; +enum iio_backend_data_source { + IIO_BACKEND_INTERNAL_CONTINUOS_WAVE, + IIO_BACKEND_EXTERNAL, + IIO_BACKEND_DATA_SOURCE_MAX +}; + +/** + * IIO_BACKEND_EX_INFO - Helper for an IIO extended channel attribute + * @_name: Attribute name + * @_shared: Whether the attribute is shared between all channels + * @_what: Data private to the driver + */ +#define IIO_BACKEND_EX_INFO(_name, _shared, _what) { \ + .name = (_name), \ + .shared = (_shared), \ + .read = iio_backend_ext_info_get, \ + .write = iio_backend_ext_info_set, \ + .private = (_what), \ +} + /** * struct iio_backend_data_fmt - Backend data format - * @type: Data type. - * @sign_extend: Bool to tell if the data is sign extended. - * @enable: Enable/Disable the data format module. If disabled, - * not formatting will happen. + * @type: Data type. + * @sign_extend: Bool to tell if the data is sign extended. + * @enable: Enable/Disable the data format module. If disabled, + * not formatting will happen. */ struct iio_backend_data_fmt { enum iio_backend_data_type type; @@ -28,15 +49,38 @@ struct iio_backend_data_fmt { bool enable; }; +/* vendor specific from 32 */ +enum iio_backend_test_pattern { + IIO_BACKEND_NO_TEST_PATTERN, + /* modified prbs9 */ + IIO_BACKEND_ADI_PRBS_9A = 32, + IIO_BACKEND_TEST_PATTERN_MAX +}; + +enum iio_backend_sample_trigger { + IIO_BACKEND_SAMPLE_TRIGGER_EDGE_FALLING, + IIO_BACKEND_SAMPLE_TRIGGER_EDGE_RISING, + IIO_BACKEND_SAMPLE_TRIGGER_MAX +}; + /** * struct iio_backend_ops - operations structure for an iio_backend - * @enable: Enable backend. - * @disable: Disable backend. - * @chan_enable: Enable one channel. - * @chan_disable: Disable one channel. - * @data_format_set: Configure the data format for a specific channel. - * @request_buffer: Request an IIO buffer. - * @free_buffer: Free an IIO buffer. + * @enable: Enable backend. + * @disable: Disable backend. + * @chan_enable: Enable one channel. + * @chan_disable: Disable one channel. + * @data_format_set: Configure the data format for a specific channel. + * @data_source_set: Configure the data source for a specific channel. + * @set_sample_rate: Configure the sampling rate for a specific channel. + * @test_pattern_set: Configure a test pattern. + * @chan_status: Get the channel status. + * @iodelay_set: Set digital I/O delay. + * @data_sample_trigger: Control when to sample data. + * @request_buffer: Request an IIO buffer. + * @free_buffer: Free an IIO buffer. + * @extend_chan_spec: Extend an IIO channel. + * @ext_info_set: Extended info setter. + * @ext_info_get: Extended info getter. **/ struct iio_backend_ops { int (*enable)(struct iio_backend *back); @@ -45,10 +89,30 @@ struct iio_backend_ops { int (*chan_disable)(struct iio_backend *back, unsigned int chan); int (*data_format_set)(struct iio_backend *back, unsigned int chan, const struct iio_backend_data_fmt *data); + int (*data_source_set)(struct iio_backend *back, unsigned int chan, + enum iio_backend_data_source data); + int (*set_sample_rate)(struct iio_backend *back, unsigned int chan, + u64 sample_rate_hz); + int (*test_pattern_set)(struct iio_backend *back, + unsigned int chan, + enum iio_backend_test_pattern pattern); + int (*chan_status)(struct iio_backend *back, unsigned int chan, + bool *error); + int (*iodelay_set)(struct iio_backend *back, unsigned int chan, + unsigned int taps); + int (*data_sample_trigger)(struct iio_backend *back, + enum iio_backend_sample_trigger trigger); struct iio_buffer *(*request_buffer)(struct iio_backend *back, struct iio_dev *indio_dev); void (*free_buffer)(struct iio_backend *back, struct iio_buffer *buffer); + int (*extend_chan_spec)(struct iio_backend *back, + struct iio_chan_spec *chan); + int (*ext_info_set)(struct iio_backend *back, uintptr_t private, + const struct iio_chan_spec *chan, + const char *buf, size_t len); + int (*ext_info_get)(struct iio_backend *back, uintptr_t private, + const struct iio_chan_spec *chan, char *buf); }; int iio_backend_chan_enable(struct iio_backend *back, unsigned int chan); @@ -56,10 +120,31 @@ int iio_backend_chan_disable(struct iio_backend *back, unsigned int chan); int devm_iio_backend_enable(struct device *dev, struct iio_backend *back); int iio_backend_data_format_set(struct iio_backend *back, unsigned int chan, const struct iio_backend_data_fmt *data); +int iio_backend_data_source_set(struct iio_backend *back, unsigned int chan, + enum iio_backend_data_source data); +int iio_backend_set_sampling_freq(struct iio_backend *back, unsigned int chan, + u64 sample_rate_hz); +int iio_backend_test_pattern_set(struct iio_backend *back, + unsigned int chan, + enum iio_backend_test_pattern pattern); +int iio_backend_chan_status(struct iio_backend *back, unsigned int chan, + bool *error); +int iio_backend_iodelay_set(struct iio_backend *back, unsigned int lane, + unsigned int taps); +int iio_backend_data_sample_trigger(struct iio_backend *back, + enum iio_backend_sample_trigger trigger); int devm_iio_backend_request_buffer(struct device *dev, struct iio_backend *back, struct iio_dev *indio_dev); +ssize_t iio_backend_ext_info_set(struct iio_dev *indio_dev, uintptr_t private, + const struct iio_chan_spec *chan, + const char *buf, size_t len); +ssize_t iio_backend_ext_info_get(struct iio_dev *indio_dev, uintptr_t private, + const struct iio_chan_spec *chan, char *buf); +int iio_backend_extend_chan_spec(struct iio_dev *indio_dev, + struct iio_backend *back, + struct iio_chan_spec *chan); void *iio_backend_get_priv(const struct iio_backend *conv); struct iio_backend *devm_iio_backend_get(struct device *dev, const char *name); struct iio_backend * diff --git a/include/linux/iio/buffer-dma.h b/include/linux/iio/buffer-dma.h index 18d3702fa95d..5eb66a399002 100644 --- a/include/linux/iio/buffer-dma.h +++ b/include/linux/iio/buffer-dma.h @@ -7,6 +7,7 @@ #ifndef __INDUSTRIALIO_DMA_BUFFER_H__ #define __INDUSTRIALIO_DMA_BUFFER_H__ +#include <linux/atomic.h> #include <linux/list.h> #include <linux/kref.h> #include <linux/spinlock.h> @@ -16,6 +17,9 @@ struct iio_dma_buffer_queue; struct iio_dma_buffer_ops; struct device; +struct dma_buf_attachment; +struct dma_fence; +struct sg_table; /** * enum iio_block_state - State of a struct iio_dma_buffer_block @@ -41,6 +45,10 @@ enum iio_block_state { * @queue: Parent DMA buffer queue * @kref: kref used to manage the lifetime of block * @state: Current state of the block + * @cyclic: True if this is a cyclic buffer + * @fileio: True if this buffer is used for fileio mode + * @sg_table: DMA table for the transfer when transferring a DMABUF + * @fence: DMA fence to be signaled when a DMABUF transfer is complete */ struct iio_dma_buffer_block { /* May only be accessed by the owner of the block */ @@ -63,6 +71,12 @@ struct iio_dma_buffer_block { * queue->list_lock if the block is not owned by the core. */ enum iio_block_state state; + + bool cyclic; + bool fileio; + + struct sg_table *sg_table; + struct dma_fence *fence; }; /** @@ -72,6 +86,7 @@ struct iio_dma_buffer_block { * @pos: Read offset in the active block * @block_size: Size of each block * @next_dequeue: index of next block that will be dequeued + * @enabled: Whether the buffer is operating in fileio mode */ struct iio_dma_buffer_queue_fileio { struct iio_dma_buffer_block *blocks[2]; @@ -80,6 +95,7 @@ struct iio_dma_buffer_queue_fileio { size_t block_size; unsigned int next_dequeue; + bool enabled; }; /** @@ -95,6 +111,7 @@ struct iio_dma_buffer_queue_fileio { * the DMA controller * @incoming: List of buffers on the incoming queue * @active: Whether the buffer is currently active + * @num_dmabufs: Total number of DMABUFs attached to this queue * @fileio: FileIO state */ struct iio_dma_buffer_queue { @@ -107,6 +124,7 @@ struct iio_dma_buffer_queue { struct list_head incoming; bool active; + atomic_t num_dmabufs; struct iio_dma_buffer_queue_fileio fileio; }; @@ -132,7 +150,9 @@ int iio_dma_buffer_disable(struct iio_buffer *buffer, struct iio_dev *indio_dev); int iio_dma_buffer_read(struct iio_buffer *buffer, size_t n, char __user *user_buffer); -size_t iio_dma_buffer_data_available(struct iio_buffer *buffer); +int iio_dma_buffer_write(struct iio_buffer *buffer, size_t n, + const char __user *user_buffer); +size_t iio_dma_buffer_usage(struct iio_buffer *buffer); int iio_dma_buffer_set_bytes_per_datum(struct iio_buffer *buffer, size_t bpd); int iio_dma_buffer_set_length(struct iio_buffer *buffer, unsigned int length); int iio_dma_buffer_request_update(struct iio_buffer *buffer); @@ -142,4 +162,17 @@ int iio_dma_buffer_init(struct iio_dma_buffer_queue *queue, void iio_dma_buffer_exit(struct iio_dma_buffer_queue *queue); void iio_dma_buffer_release(struct iio_dma_buffer_queue *queue); +struct iio_dma_buffer_block * +iio_dma_buffer_attach_dmabuf(struct iio_buffer *buffer, + struct dma_buf_attachment *attach); +void iio_dma_buffer_detach_dmabuf(struct iio_buffer *buffer, + struct iio_dma_buffer_block *block); +int iio_dma_buffer_enqueue_dmabuf(struct iio_buffer *buffer, + struct iio_dma_buffer_block *block, + struct dma_fence *fence, + struct sg_table *sgt, + size_t size, bool cyclic); +void iio_dma_buffer_lock_queue(struct iio_buffer *buffer); +void iio_dma_buffer_unlock_queue(struct iio_buffer *buffer); + #endif diff --git a/include/linux/iio/buffer-dmaengine.h b/include/linux/iio/buffer-dmaengine.h index cbb8ba957fad..81d9a19aeb91 100644 --- a/include/linux/iio/buffer-dmaengine.h +++ b/include/linux/iio/buffer-dmaengine.h @@ -7,14 +7,28 @@ #ifndef __IIO_DMAENGINE_H__ #define __IIO_DMAENGINE_H__ +#include <linux/iio/buffer.h> + struct iio_dev; struct device; -struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev, - const char *channel); void iio_dmaengine_buffer_free(struct iio_buffer *buffer); -int devm_iio_dmaengine_buffer_setup(struct device *dev, - struct iio_dev *indio_dev, - const char *channel); +struct iio_buffer *iio_dmaengine_buffer_setup_ext(struct device *dev, + struct iio_dev *indio_dev, + const char *channel, + enum iio_buffer_direction dir); + +#define iio_dmaengine_buffer_setup(dev, indio_dev, channel) \ + iio_dmaengine_buffer_setup_ext(dev, indio_dev, channel, \ + IIO_BUFFER_DIRECTION_IN) + +int devm_iio_dmaengine_buffer_setup_ext(struct device *dev, + struct iio_dev *indio_dev, + const char *channel, + enum iio_buffer_direction dir); + +#define devm_iio_dmaengine_buffer_setup(dev, indio_dev, channel) \ + devm_iio_dmaengine_buffer_setup_ext(dev, indio_dev, channel, \ + IIO_BUFFER_DIRECTION_IN) #endif diff --git a/include/linux/iio/buffer_impl.h b/include/linux/iio/buffer_impl.h index 89c3fd7c29ca..e72552e026f3 100644 --- a/include/linux/iio/buffer_impl.h +++ b/include/linux/iio/buffer_impl.h @@ -9,8 +9,12 @@ #include <uapi/linux/iio/buffer.h> #include <linux/iio/buffer.h> +struct dma_buf_attachment; +struct dma_fence; struct iio_dev; +struct iio_dma_buffer_block; struct iio_buffer; +struct sg_table; /** * INDIO_BUFFER_FLAG_FIXED_WATERMARK - Watermark level of the buffer can not be @@ -39,6 +43,16 @@ struct iio_buffer; * device stops sampling. Calles are balanced with @enable. * @release: called when the last reference to the buffer is dropped, * should free all resources allocated by the buffer. + * @attach_dmabuf: called from userspace via ioctl to attach one external + * DMABUF. + * @detach_dmabuf: called from userspace via ioctl to detach one previously + * attached DMABUF. + * @enqueue_dmabuf: called from userspace via ioctl to queue this DMABUF + * object to this buffer. Requires a valid DMABUF fd, that + * was previouly attached to this buffer. + * @lock_queue: called when the core needs to lock the buffer queue; + * it is used when enqueueing DMABUF objects. + * @unlock_queue: used to unlock a previously locked buffer queue * @modes: Supported operating modes by this buffer type * @flags: A bitmask combination of INDIO_BUFFER_FLAG_* * @@ -68,6 +82,17 @@ struct iio_buffer_access_funcs { void (*release)(struct iio_buffer *buffer); + struct iio_dma_buffer_block * (*attach_dmabuf)(struct iio_buffer *buffer, + struct dma_buf_attachment *attach); + void (*detach_dmabuf)(struct iio_buffer *buffer, + struct iio_dma_buffer_block *block); + int (*enqueue_dmabuf)(struct iio_buffer *buffer, + struct iio_dma_buffer_block *block, + struct dma_fence *fence, struct sg_table *sgt, + size_t size, bool cyclic); + void (*lock_queue)(struct iio_buffer *buffer); + void (*unlock_queue)(struct iio_buffer *buffer); + unsigned int modes; unsigned int flags; }; @@ -136,6 +161,12 @@ struct iio_buffer { /* @ref: Reference count of the buffer. */ struct kref ref; + + /* @dmabufs: List of DMABUF attachments */ + struct list_head dmabufs; /* P: dmabufs_mutex */ + + /* @dmabufs_mutex: Protects dmabufs */ + struct mutex dmabufs_mutex; }; /** @@ -159,6 +190,8 @@ void iio_buffer_init(struct iio_buffer *buffer); struct iio_buffer *iio_buffer_get(struct iio_buffer *buffer); void iio_buffer_put(struct iio_buffer *buffer); +void iio_buffer_signal_dmabuf_done(struct dma_fence *fence, int ret); + #else /* CONFIG_IIO_BUFFER */ static inline void iio_buffer_get(struct iio_buffer *buffer) {} diff --git a/include/linux/iio/common/inv_sensors_timestamp.h b/include/linux/iio/common/inv_sensors_timestamp.h index a47d304d1ba7..8d506f1e9df2 100644 --- a/include/linux/iio/common/inv_sensors_timestamp.h +++ b/include/linux/iio/common/inv_sensors_timestamp.h @@ -71,8 +71,7 @@ int inv_sensors_timestamp_update_odr(struct inv_sensors_timestamp *ts, uint32_t period, bool fifo); void inv_sensors_timestamp_interrupt(struct inv_sensors_timestamp *ts, - uint32_t fifo_period, size_t fifo_nb, - size_t sensor_nb, int64_t timestamp); + size_t sample_nb, int64_t timestamp); static inline int64_t inv_sensors_timestamp_pop(struct inv_sensors_timestamp *ts) { diff --git a/include/linux/iio/consumer.h b/include/linux/iio/consumer.h index e9910b41d48e..333d1d8ccb37 100644 --- a/include/linux/iio/consumer.h +++ b/include/linux/iio/consumer.h @@ -441,4 +441,14 @@ ssize_t iio_read_channel_ext_info(struct iio_channel *chan, ssize_t iio_write_channel_ext_info(struct iio_channel *chan, const char *attr, const char *buf, size_t len); +/** + * iio_read_channel_label() - read label for a given channel + * @chan: The channel being queried. + * @buf: Where to store the attribute value. Assumed to hold + * at least PAGE_SIZE bytes. + * + * Returns the number of bytes written to buf, or an error code. + */ +ssize_t iio_read_channel_label(struct iio_channel *chan, char *buf); + #endif diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index e370a7bb3300..894309294182 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -174,6 +174,27 @@ struct iio_event_spec { }; /** + * struct iio_scan_type - specification for channel data format in buffer + * @sign: 's' or 'u' to specify signed or unsigned + * @realbits: Number of valid bits of data + * @storagebits: Realbits + padding + * @shift: Shift right by this before masking out realbits. + * @repeat: Number of times real/storage bits repeats. When the + * repeat element is more than 1, then the type element in + * sysfs will show a repeat value. Otherwise, the number + * of repetitions is omitted. + * @endianness: little or big endian + */ +struct iio_scan_type { + char sign; + u8 realbits; + u8 storagebits; + u8 shift; + u8 repeat; + enum iio_endian endianness; +}; + +/** * struct iio_chan_spec - specification of a single channel * @type: What type of measurement is the channel making. * @channel: What number do we wish to assign the channel. @@ -183,18 +204,13 @@ struct iio_event_spec { * @address: Driver specific identifier. * @scan_index: Monotonic index to give ordering in scans when read * from a buffer. - * @scan_type: struct describing the scan type - * @scan_type.sign: 's' or 'u' to specify signed or unsigned - * @scan_type.realbits: Number of valid bits of data - * @scan_type.storagebits: Realbits + padding - * @scan_type.shift: Shift right by this before masking out - * realbits. - * @scan_type.repeat: Number of times real/storage bits repeats. - * When the repeat element is more than 1, then - * the type element in sysfs will show a repeat - * value. Otherwise, the number of repetitions - * is omitted. - * @scan_type.endianness: little or big endian + * @scan_type: struct describing the scan type - mutually exclusive + * with ext_scan_type. + * @ext_scan_type: Used in rare cases where there is more than one scan + * format for a channel. When this is used, the flag + * has_ext_scan_type must be set and the driver must + * implement get_current_scan_type in struct iio_info. + * @num_ext_scan_type: Number of elements in ext_scan_type. * @info_mask_separate: What information is to be exported that is specific to * this channel. * @info_mask_separate_available: What availability information is to be @@ -238,6 +254,7 @@ struct iio_event_spec { * attributes but not for event codes. * @output: Channel is output. * @differential: Channel is differential. + * @has_ext_scan_type: True if ext_scan_type is used instead of scan_type. */ struct iio_chan_spec { enum iio_chan_type type; @@ -245,14 +262,13 @@ struct iio_chan_spec { int channel2; unsigned long address; int scan_index; - struct { - char sign; - u8 realbits; - u8 storagebits; - u8 shift; - u8 repeat; - enum iio_endian endianness; - } scan_type; + union { + struct iio_scan_type scan_type; + struct { + const struct iio_scan_type *ext_scan_type; + unsigned int num_ext_scan_type; + }; + }; long info_mask_separate; long info_mask_separate_available; long info_mask_shared_by_type; @@ -270,6 +286,7 @@ struct iio_chan_spec { unsigned indexed:1; unsigned output:1; unsigned differential:1; + unsigned has_ext_scan_type:1; }; @@ -432,6 +449,9 @@ struct iio_trigger; /* forward declaration */ * for better event identification. * @validate_trigger: function to validate the trigger when the * current trigger gets changed. + * @get_current_scan_type: must be implemented by drivers that use ext_scan_type + * in the channel spec to return the index of the currently + * active ext_scan type for a channel. * @update_scan_mode: function to configure device and scan buffer when * channels have changed * @debugfs_reg_access: function to read or write register value of device @@ -516,6 +536,8 @@ struct iio_info { int (*validate_trigger)(struct iio_dev *indio_dev, struct iio_trigger *trig); + int (*get_current_scan_type)(const struct iio_dev *indio_dev, + const struct iio_chan_spec *chan); int (*update_scan_mode)(struct iio_dev *indio_dev, const unsigned long *scan_mask); int (*debugfs_reg_access)(struct iio_dev *indio_dev, @@ -788,6 +810,51 @@ static inline struct dentry *iio_get_debugfs_dentry(struct iio_dev *indio_dev) } #endif +#ifdef CONFIG_ACPI +bool iio_read_acpi_mount_matrix(struct device *dev, + struct iio_mount_matrix *orientation, + char *acpi_method); +#else +static inline bool iio_read_acpi_mount_matrix(struct device *dev, + struct iio_mount_matrix *orientation, + char *acpi_method) +{ + return false; +} +#endif + +/** + * iio_get_current_scan_type - Get the current scan type for a channel + * @indio_dev: the IIO device to get the scan type for + * @chan: the channel to get the scan type for + * + * Most devices only have one scan type per channel and can just access it + * directly without calling this function. Core IIO code and drivers that + * implement ext_scan_type in the channel spec should use this function to + * get the current scan type for a channel. + * + * Returns: the current scan type for the channel or error. + */ +static inline const struct iio_scan_type +*iio_get_current_scan_type(const struct iio_dev *indio_dev, + const struct iio_chan_spec *chan) +{ + int ret; + + if (chan->has_ext_scan_type) { + ret = indio_dev->info->get_current_scan_type(indio_dev, chan); + if (ret < 0) + return ERR_PTR(ret); + + if (ret >= chan->num_ext_scan_type) + return ERR_PTR(-EINVAL); + + return &chan->ext_scan_type[ret]; + } + + return &chan->scan_type; +} + ssize_t iio_format_value(char *buf, unsigned int type, int size, int *vals); int iio_str_to_fixpoint(const char *str, int fract_mult, int *integer, diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index 8898966bc0f0..e6a75356567a 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -9,6 +9,7 @@ #ifndef __IIO_ADIS_H__ #define __IIO_ADIS_H__ +#include <linux/cleanup.h> #include <linux/spi/spi.h> #include <linux/interrupt.h> #include <linux/iio/iio.h> @@ -21,6 +22,7 @@ #define ADIS_REG_PAGE_ID 0x00 struct adis; +struct iio_dev_attr; /** * struct adis_timeouts - ADIS chip variant timeouts @@ -84,6 +86,7 @@ struct adis_data { bool unmasked_drdy; bool has_paging; + bool has_fifo; unsigned int burst_reg_cmd; unsigned int burst_len; @@ -148,13 +151,8 @@ int __adis_reset(struct adis *adis); */ static inline int adis_reset(struct adis *adis) { - int ret; - - mutex_lock(&adis->state_lock); - ret = __adis_reset(adis); - mutex_unlock(&adis->state_lock); - - return ret; + guard(mutex)(&adis->state_lock); + return __adis_reset(adis); } int __adis_write_reg(struct adis *adis, unsigned int reg, @@ -246,13 +244,8 @@ static inline int __adis_read_reg_32(struct adis *adis, unsigned int reg, static inline int adis_write_reg(struct adis *adis, unsigned int reg, unsigned int val, unsigned int size) { - int ret; - - mutex_lock(&adis->state_lock); - ret = __adis_write_reg(adis, reg, val, size); - mutex_unlock(&adis->state_lock); - - return ret; + guard(mutex)(&adis->state_lock); + return __adis_write_reg(adis, reg, val, size); } /** @@ -265,13 +258,8 @@ static inline int adis_write_reg(struct adis *adis, unsigned int reg, static int adis_read_reg(struct adis *adis, unsigned int reg, unsigned int *val, unsigned int size) { - int ret; - - mutex_lock(&adis->state_lock); - ret = __adis_read_reg(adis, reg, val, size); - mutex_unlock(&adis->state_lock); - - return ret; + guard(mutex)(&adis->state_lock); + return __adis_read_reg(adis, reg, val, size); } /** @@ -363,12 +351,8 @@ int __adis_update_bits_base(struct adis *adis, unsigned int reg, const u32 mask, static inline int adis_update_bits_base(struct adis *adis, unsigned int reg, const u32 mask, const u32 val, u8 size) { - int ret; - - mutex_lock(&adis->state_lock); - ret = __adis_update_bits_base(adis, reg, mask, val, size); - mutex_unlock(&adis->state_lock); - return ret; + guard(mutex)(&adis->state_lock); + return __adis_update_bits_base(adis, reg, mask, val, size); } /** @@ -409,35 +393,19 @@ int __adis_enable_irq(struct adis *adis, bool enable); static inline int adis_enable_irq(struct adis *adis, bool enable) { - int ret; - - mutex_lock(&adis->state_lock); - ret = __adis_enable_irq(adis, enable); - mutex_unlock(&adis->state_lock); - - return ret; + guard(mutex)(&adis->state_lock); + return __adis_enable_irq(adis, enable); } static inline int adis_check_status(struct adis *adis) { - int ret; - - mutex_lock(&adis->state_lock); - ret = __adis_check_status(adis); - mutex_unlock(&adis->state_lock); - - return ret; -} - -static inline void adis_dev_lock(struct adis *adis) -{ - mutex_lock(&adis->state_lock); + guard(mutex)(&adis->state_lock); + return __adis_check_status(adis); } -static inline void adis_dev_unlock(struct adis *adis) -{ - mutex_unlock(&adis->state_lock); -} +#define adis_dev_auto_lock(adis) guard(mutex)(&(adis)->state_lock) +#define adis_dev_auto_scoped_lock(adis) \ + scoped_guard(mutex, &(adis)->state_lock) int adis_single_conversion(struct iio_dev *indio_dev, const struct iio_chan_spec *chan, @@ -515,11 +483,19 @@ int adis_single_conversion(struct iio_dev *indio_dev, #define ADIS_ROT_CHAN(mod, addr, si, info_sep, info_all, bits) \ ADIS_MOD_CHAN(IIO_ROT, mod, addr, si, info_sep, info_all, bits) +#define devm_adis_setup_buffer_and_trigger(adis, indio_dev, trigger_handler) \ + devm_adis_setup_buffer_and_trigger_with_attrs((adis), (indio_dev), \ + (trigger_handler), NULL, \ + NULL) + #ifdef CONFIG_IIO_ADIS_LIB_BUFFER int -devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev, - irq_handler_t trigger_handler); +devm_adis_setup_buffer_and_trigger_with_attrs(struct adis *adis, + struct iio_dev *indio_dev, + irq_handler_t trigger_handler, + const struct iio_buffer_setup_ops *ops, + const struct iio_dev_attr **buffer_attrs); int devm_adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev); @@ -529,8 +505,11 @@ int adis_update_scan_mode(struct iio_dev *indio_dev, #else /* CONFIG_IIO_BUFFER */ static inline int -devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev, - irq_handler_t trigger_handler) +devm_adis_setup_buffer_and_trigger_with_attrs(struct adis *adis, + struct iio_dev *indio_dev, + irq_handler_t trigger_handler, + const struct iio_buffer_setup_ops *ops, + const struct iio_dev_attr **buffer_attrs) { return 0; } diff --git a/include/linux/init.h b/include/linux/init.h index 58cef4c2e59a..ee1309473bc6 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -84,11 +84,15 @@ #define __exit __section(".exit.text") __exitused __cold notrace -/* Used for MEMORY_HOTPLUG */ -#define __meminit __section(".meminit.text") __cold notrace \ - __latent_entropy -#define __meminitdata __section(".meminit.data") -#define __meminitconst __section(".meminit.rodata") +#ifdef CONFIG_MEMORY_HOTPLUG +#define __meminit +#define __meminitdata +#define __meminitconst +#else +#define __meminit __init +#define __meminitdata __initdata +#define __meminitconst __initconst +#endif /* For assembly routines */ #define __HEAD .section ".head.text","ax" @@ -99,10 +103,6 @@ #define __INITRODATA .section ".init.rodata","a",%progbits #define __FINITDATA .previous -#define __MEMINIT .section ".meminit.text", "ax" -#define __MEMINITDATA .section ".meminit.data", "aw" -#define __MEMINITRODATA .section ".meminit.rodata", "a" - /* silence warnings when references are OK */ #define __REF .section ".ref.text", "ax" #define __REFDATA .section ".ref.data", "aw" diff --git a/include/linux/input.h b/include/linux/input.h index c22ac465254b..89a0be6ee0e2 100644 --- a/include/linux/input.h +++ b/include/linux/input.h @@ -275,7 +275,8 @@ struct input_handle; * it may not sleep * @events: event sequence handler. This method is being called by * input core with interrupts disabled and dev->event_lock - * spinlock held and so it may not sleep + * spinlock held and so it may not sleep. The method must return + * number of events passed to it. * @filter: similar to @event; separates normal event handlers from * "filters". * @match: called after comparing device's id with handler's id_table @@ -312,8 +313,8 @@ struct input_handler { void *private; void (*event)(struct input_handle *handle, unsigned int type, unsigned int code, int value); - void (*events)(struct input_handle *handle, - const struct input_value *vals, unsigned int count); + unsigned int (*events)(struct input_handle *handle, + struct input_value *vals, unsigned int count); bool (*filter)(struct input_handle *handle, unsigned int type, unsigned int code, int value); bool (*match)(struct input_handler *handler, struct input_dev *dev); int (*connect)(struct input_handler *handler, struct input_dev *dev, const struct input_device_id *id); diff --git a/include/linux/instrumented.h b/include/linux/instrumented.h index 1b608e00290a..711a1f0d1a73 100644 --- a/include/linux/instrumented.h +++ b/include/linux/instrumented.h @@ -148,6 +148,41 @@ instrument_copy_from_user_after(const void *to, const void __user *from, } /** + * instrument_memcpy_before - add instrumentation before non-instrumented memcpy + * @to: destination address + * @from: source address + * @n: number of bytes to copy + * + * Instrument memory accesses that happen in custom memcpy implementations. The + * instrumentation should be inserted before the memcpy call. + */ +static __always_inline void instrument_memcpy_before(void *to, const void *from, + unsigned long n) +{ + kasan_check_write(to, n); + kasan_check_read(from, n); + kcsan_check_write(to, n); + kcsan_check_read(from, n); +} + +/** + * instrument_memcpy_after - add instrumentation after non-instrumented memcpy + * @to: destination address + * @from: source address + * @n: number of bytes to copy + * @left: number of bytes not copied (if known) + * + * Instrument memory accesses that happen in custom memcpy implementations. The + * instrumentation should be inserted after the memcpy call. + */ +static __always_inline void instrument_memcpy_after(void *to, const void *from, + unsigned long n, + unsigned long left) +{ + kmsan_memmove(to, from, n - left); +} + +/** * instrument_get_user() - add instrumentation to get_user()-like macros * @to: destination variable, may not be address-taken * diff --git a/include/linux/integrity.h b/include/linux/integrity.h index 459b79683783..f5842372359b 100644 --- a/include/linux/integrity.h +++ b/include/linux/integrity.h @@ -8,6 +8,7 @@ #define _LINUX_INTEGRITY_H #include <linux/fs.h> +#include <linux/iversion.h> enum integrity_status { INTEGRITY_PASS = 0, @@ -28,4 +29,37 @@ static inline void integrity_load_keys(void) } #endif /* CONFIG_INTEGRITY */ +/* An inode's attributes for detection of changes */ +struct integrity_inode_attributes { + u64 version; /* track inode changes */ + unsigned long ino; + dev_t dev; +}; + +/* + * On stacked filesystems the i_version alone is not enough to detect file data + * or metadata change. Additional metadata is required. + */ +static inline void +integrity_inode_attrs_store(struct integrity_inode_attributes *attrs, + u64 i_version, const struct inode *inode) +{ + attrs->version = i_version; + attrs->dev = inode->i_sb->s_dev; + attrs->ino = inode->i_ino; +} + +/* + * On stacked filesystems detect whether the inode or its content has changed. + */ +static inline bool +integrity_inode_attrs_changed(const struct integrity_inode_attributes *attrs, + const struct inode *inode) +{ + return (inode->i_sb->s_dev != attrs->dev || + inode->i_ino != attrs->ino || + !inode_eq_iversion(inode, attrs->version)); +} + + #endif /* _LINUX_INTEGRITY_H */ diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index f3196f82fd8a..c0397423d3a8 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -158,6 +158,26 @@ struct rapl_if_priv { void *rpi; }; +#ifdef CONFIG_PERF_EVENTS +/** + * struct rapl_package_pmu_data: Per package data for PMU support + * @scale: Scale of 2^-32 Joules for each energy counter increase. + * @lock: Lock to protect n_active and active_list. + * @n_active: Number of active events. + * @active_list: List of active events. + * @timer_interval: Maximum timer expiration time before counter overflow. + * @hrtimer: Periodically update the counter to prevent overflow. + */ +struct rapl_package_pmu_data { + u64 scale[RAPL_DOMAIN_MAX]; + raw_spinlock_t lock; + int n_active; + struct list_head active_list; + ktime_t timer_interval; + struct hrtimer hrtimer; +}; +#endif + /* maximum rapl package domain name: package-%d-die-%d */ #define PACKAGE_DOMAIN_NAME_LENGTH 30 @@ -176,6 +196,10 @@ struct rapl_package { struct cpumask cpumask; char name[PACKAGE_DOMAIN_NAME_LENGTH]; struct rapl_if_priv *priv; +#ifdef CONFIG_PERF_EVENTS + bool has_pmu; + struct rapl_package_pmu_data pmu_data; +#endif }; struct rapl_package *rapl_find_package_domain_cpuslocked(int id, struct rapl_if_priv *priv, @@ -188,4 +212,12 @@ struct rapl_package *rapl_find_package_domain(int id, struct rapl_if_priv *priv, struct rapl_package *rapl_add_package(int id, struct rapl_if_priv *priv, bool id_is_cpu); void rapl_remove_package(struct rapl_package *rp); +#ifdef CONFIG_PERF_EVENTS +int rapl_package_add_pmu(struct rapl_package *rp); +void rapl_package_remove_pmu(struct rapl_package *rp); +#else +static inline int rapl_package_add_pmu(struct rapl_package *rp) { return 0; } +static inline void rapl_package_remove_pmu(struct rapl_package *rp) { } +#endif + #endif /* __INTEL_RAPL_H__ */ diff --git a/include/linux/intel_tcc.h b/include/linux/intel_tcc.h index 8ff8eabb4a98..fa788817acfc 100644 --- a/include/linux/intel_tcc.h +++ b/include/linux/intel_tcc.h @@ -14,5 +14,6 @@ int intel_tcc_get_tjmax(int cpu); int intel_tcc_get_offset(int cpu); int intel_tcc_set_offset(int cpu, int offset); int intel_tcc_get_temp(int cpu, int *temp, bool pkg); +u32 intel_tcc_get_offset_mask(void); #endif /* __INTEL_TCC_H__ */ diff --git a/include/linux/intel_tpmi.h b/include/linux/intel_tpmi.h index a3529b962be6..ff480b47ae64 100644 --- a/include/linux/intel_tpmi.h +++ b/include/linux/intel_tpmi.h @@ -21,22 +21,29 @@ enum intel_tpmi_id { TPMI_ID_PEM = 1, /* Power and Perf excursion Monitor */ TPMI_ID_UNCORE = 2, /* Uncore Frequency Scaling */ TPMI_ID_SST = 5, /* Speed Select Technology */ + TPMI_ID_PLR = 0xc, /* Performance Limit Reasons */ TPMI_CONTROL_ID = 0x80, /* Special ID for getting feature status */ TPMI_INFO_ID = 0x81, /* Special ID for PCI BDF and Package ID information */ }; /** * struct intel_tpmi_plat_info - Platform information for a TPMI device instance - * @package_id: CPU Package id - * @bus_number: PCI bus number - * @device_number: PCI device number + * @cdie_mask: Mask of all compute dies in the partition + * @package_id: CPU Package id + * @partition: Package partition id when multiple VSEC PCI devices per package + * @segment: PCI segment ID + * @bus_number: PCI bus number + * @device_number: PCI device number * @function_number: PCI function number * * Structure to store platform data for a TPMI device instance. This * struct is used to return data via tpmi_get_platform_data(). */ struct intel_tpmi_plat_info { + u16 cdie_mask; u8 package_id; + u8 partition; + u8 segment; u8 bus_number; u8 device_number; u8 function_number; @@ -47,4 +54,5 @@ struct resource *tpmi_get_resource_at_index(struct auxiliary_device *auxdev, int int tpmi_get_resource_count(struct auxiliary_device *auxdev); int tpmi_get_feature_status(struct auxiliary_device *auxdev, int feature_id, bool *read_blocked, bool *write_blocked); +struct dentry *tpmi_get_debugfs_dir(struct auxiliary_device *auxdev); #endif diff --git a/include/linux/interconnect-clk.h b/include/linux/interconnect-clk.h index 0cd80112bea5..9bcee3e9c56c 100644 --- a/include/linux/interconnect-clk.h +++ b/include/linux/interconnect-clk.h @@ -11,12 +11,16 @@ struct device; struct icc_clk_data { struct clk *clk; const char *name; + unsigned int master_id; + unsigned int slave_id; }; struct icc_provider *icc_clk_register(struct device *dev, unsigned int first_id, unsigned int num_clocks, const struct icc_clk_data *data); +int devm_icc_clk_register(struct device *dev, unsigned int first_id, + unsigned int num_clocks, const struct icc_clk_data *data); void icc_clk_unregister(struct icc_provider *provider); #endif diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 5c9bdd3ffccc..3f30c88e0b4c 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -5,13 +5,14 @@ #include <linux/kernel.h> #include <linux/bitops.h> -#include <linux/cpumask.h> +#include <linux/cleanup.h> #include <linux/irqreturn.h> #include <linux/irqnr.h> #include <linux/hardirq.h> #include <linux/irqflags.h> #include <linux/hrtimer.h> #include <linux/kref.h> +#include <linux/cpumask_types.h> #include <linux/workqueue.h> #include <linux/jump_label.h> @@ -168,7 +169,7 @@ static inline int __must_check request_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *name, void *dev) { - return request_threaded_irq(irq, handler, NULL, flags, name, dev); + return request_threaded_irq(irq, handler, NULL, flags | IRQF_COND_ONESHOT, name, dev); } extern int __must_check @@ -235,6 +236,9 @@ extern void enable_percpu_irq(unsigned int irq, unsigned int type); extern bool irq_percpu_is_enabled(unsigned int irq); extern void irq_wake_thread(unsigned int irq, void *dev_id); +DEFINE_LOCK_GUARD_1(disable_irq, int, + disable_irq(*_T->lock), enable_irq(*_T->lock)) + extern void disable_nmi_nosync(unsigned int irq); extern void disable_percpu_nmi(unsigned int irq); extern void enable_nmi(unsigned int irq); diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index 86cf1f7ae389..f9a81761bfce 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -85,6 +85,8 @@ struct io_pgtable_cfg { * * IO_PGTABLE_QUIRK_ARM_OUTER_WBWA: Override the outer-cacheability * attributes set in the TCR for a non-coherent page-table walker. + * + * IO_PGTABLE_QUIRK_ARM_HD: Enables dirty tracking in stage 1 pagetable. */ #define IO_PGTABLE_QUIRK_ARM_NS BIT(0) #define IO_PGTABLE_QUIRK_NO_PERMS BIT(1) @@ -92,6 +94,7 @@ struct io_pgtable_cfg { #define IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT BIT(4) #define IO_PGTABLE_QUIRK_ARM_TTBR1 BIT(5) #define IO_PGTABLE_QUIRK_ARM_OUTER_WBWA BIT(6) + #define IO_PGTABLE_QUIRK_ARM_HD BIT(7) unsigned long quirks; unsigned long pgsize_bitmap; unsigned int ias; diff --git a/include/linux/io.h b/include/linux/io.h index 235ba7d80a8f..59ec5eea696c 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -6,6 +6,7 @@ #ifndef _LINUX_IO_H #define _LINUX_IO_H +#include <linux/sizes.h> #include <linux/types.h> #include <linux/init.h> #include <linux/bug.h> @@ -16,9 +17,15 @@ struct device; struct resource; -__visible void __iowrite32_copy(void __iomem *to, const void *from, size_t count); +#ifndef __iowrite32_copy +void __iowrite32_copy(void __iomem *to, const void *from, size_t count); +#endif + void __ioread32_copy(void *to, const void __iomem *from, size_t count); + +#ifndef __iowrite64_copy void __iowrite64_copy(void __iomem *to, const void *from, size_t count); +#endif #ifdef CONFIG_MMU int ioremap_page_range(unsigned long addr, unsigned long end, diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 68ed6697fece..e123d5e17b52 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -11,7 +11,6 @@ void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); void io_uring_unreg_ringfd(void); const char *io_uring_get_opcode(u8 opcode); -int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags); bool io_is_uring_fops(struct file *file); static inline void io_uring_files_cancel(void) @@ -45,11 +44,6 @@ static inline const char *io_uring_get_opcode(u8 opcode) { return ""; } -static inline int io_uring_cmd_sock(struct io_uring_cmd *cmd, - unsigned int issue_flags) -{ - return -EOPNOTSUPP; -} static inline bool io_is_uring_fops(struct file *file) { return false; diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h index e453a997c060..447fbfd32215 100644 --- a/include/linux/io_uring/cmd.h +++ b/include/linux/io_uring/cmd.h @@ -26,12 +26,25 @@ static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) #if defined(CONFIG_IO_URING) int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, struct iov_iter *iter, void *ioucmd); + +/* + * Completes the request, i.e. posts an io_uring CQE and deallocates @ioucmd + * and the corresponding io_uring request. + * + * Note: the caller should never hard code @issue_flags and is only allowed + * to pass the mask provided by the core io_uring code. + */ void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2, unsigned issue_flags); + void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd, void (*task_work_cb)(struct io_uring_cmd *, unsigned), unsigned flags); +/* + * Note: the caller should never hard code @issue_flags and only use the + * mask provided by the core io_uring code. + */ void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd, unsigned int issue_flags); @@ -56,6 +69,17 @@ static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd, } #endif +/* + * Polled completions must ensure they are coming from a poll queue, and + * hence are completed inside the usual poll handling loops. + */ +static inline void io_uring_cmd_iopoll_done(struct io_uring_cmd *ioucmd, + ssize_t ret, ssize_t res2) +{ + lockdep_assert(in_task()); + io_uring_cmd_done(ioucmd, ret, res2, 0); +} + /* users must follow the IOU_F_TWQ_LAZY_WAKE semantics */ static inline void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd, void (*task_work_cb)(struct io_uring_cmd *, unsigned)) diff --git a/include/linux/io_uring/net.h b/include/linux/io_uring/net.h new file mode 100644 index 000000000000..b58f39fed4d5 --- /dev/null +++ b/include/linux/io_uring/net.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_IO_URING_NET_H +#define _LINUX_IO_URING_NET_H + +struct io_uring_cmd; + +#if defined(CONFIG_IO_URING) +int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags); + +#else +static inline int io_uring_cmd_sock(struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ + return -EOPNOTSUPP; +} +#endif + +#endif diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index ac333ea81d31..3315005df117 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -50,7 +50,7 @@ struct io_wq_work_list { struct io_wq_work { struct io_wq_work_node list; - unsigned flags; + atomic_t flags; /* place it here instead of io_kiocb as it fills padding and saves 4B */ int cancel_seq; }; @@ -205,21 +205,13 @@ struct io_submit_state { bool plug_started; bool need_plug; + bool cq_flush; unsigned short submit_nr; - unsigned int cqes_count; struct blk_plug plug; }; -struct io_ev_fd { - struct eventfd_ctx *cq_ev_fd; - unsigned int eventfd_async: 1; - struct rcu_head rcu; - atomic_t refs; - atomic_t ops; -}; - struct io_alloc_cache { - struct io_wq_work_node list; + void **entries; unsigned int nr_cached; unsigned int max_cached; size_t elem_size; @@ -299,6 +291,8 @@ struct io_ring_ctx { struct io_hash_table cancel_table_locked; struct io_alloc_cache apoll_cache; struct io_alloc_cache netmsg_cache; + struct io_alloc_cache rw_cache; + struct io_alloc_cache uring_cache; /* * Any cancelable uring_cmd is added to this list in @@ -341,14 +335,8 @@ struct io_ring_ctx { unsigned cq_last_tm_flush; } ____cacheline_aligned_in_smp; - struct io_uring_cqe completion_cqes[16]; - spinlock_t completion_lock; - /* IRQ completion list, under ->completion_lock */ - unsigned int locked_free_nr; - struct io_wq_work_list locked_free_list; - struct list_head io_buffers_comp; struct list_head cq_overflow_list; struct io_hash_table cancel_table; @@ -371,15 +359,11 @@ struct io_ring_ctx { struct list_head io_buffers_cache; - /* deferred free list, protected by ->uring_lock */ - struct hlist_head io_buf_list; - /* Keep this last, we don't need it for the fast path */ struct wait_queue_head poll_wq; struct io_restriction restrictions; /* slow path rsrc auxilary data, used by update/register */ - struct io_mapped_ubuf *dummy_ubuf; struct io_rsrc_data *file_data; struct io_rsrc_data *buf_data; @@ -412,12 +396,15 @@ struct io_ring_ctx { struct callback_head poll_wq_task_work; struct list_head defer_list; + struct io_alloc_cache msg_cache; + spinlock_t msg_lock; + #ifdef CONFIG_NET_RX_BUSY_POLL struct list_head napi_list; /* track busy poll napi_id */ spinlock_t napi_lock; /* napi_list lock */ /* napi busy poll default timeout */ - unsigned int napi_busy_poll_to; + ktime_t napi_busy_poll_dt; bool napi_prefer_busy_poll; bool napi_enabled; @@ -438,8 +425,6 @@ struct io_ring_ctx { }; struct io_tw_state { - /* ->uring_lock is taken, callbacks can use io_tw_lock to lock it */ - bool locked; }; enum { @@ -476,10 +461,10 @@ enum { REQ_F_SUPPORT_NOWAIT_BIT, REQ_F_ISREG_BIT, REQ_F_POLL_NO_LAZY_BIT, - REQ_F_CANCEL_SEQ_BIT, REQ_F_CAN_POLL_BIT, REQ_F_BL_EMPTY_BIT, REQ_F_BL_NO_RECYCLE_BIT, + REQ_F_BUFFERS_COMMIT_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, @@ -550,14 +535,14 @@ enum { REQ_F_HASH_LOCKED = IO_REQ_FLAG(REQ_F_HASH_LOCKED_BIT), /* don't use lazy poll wake for this request */ REQ_F_POLL_NO_LAZY = IO_REQ_FLAG(REQ_F_POLL_NO_LAZY_BIT), - /* cancel sequence is set and valid */ - REQ_F_CANCEL_SEQ = IO_REQ_FLAG(REQ_F_CANCEL_SEQ_BIT), /* file is pollable */ REQ_F_CAN_POLL = IO_REQ_FLAG(REQ_F_CAN_POLL_BIT), /* buffer list was empty after selection of buffer */ REQ_F_BL_EMPTY = IO_REQ_FLAG(REQ_F_BL_EMPTY_BIT), /* don't recycle provided buffers for this request */ REQ_F_BL_NO_RECYCLE = IO_REQ_FLAG(REQ_F_BL_NO_RECYCLE_BIT), + /* buffer ring head needs incrementing on put */ + REQ_F_BUFFERS_COMMIT = IO_REQ_FLAG(REQ_F_BUFFERS_COMMIT_BIT), }; typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts); @@ -653,7 +638,7 @@ struct io_kiocb { struct io_rsrc_node *rsrc_node; atomic_t refs; - atomic_t poll_refs; + bool cancel_seq_set; struct io_task_work io_task_work; /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */ struct hlist_node hash_node; @@ -662,6 +647,7 @@ struct io_kiocb { /* opcode allocated if it needs to store data for async defer */ void *async_data; /* linked requests, IFF REQ_F_HARDLINK or REQ_F_LINK are set */ + atomic_t poll_refs; struct io_kiocb *link; /* custom credentials, valid IFF REQ_F_CREDS is set */ const struct cred *creds; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 2e925b5eba53..04cbdae0052e 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -69,8 +69,7 @@ enum iommu_fault_type { struct iommu_fault_page_request { #define IOMMU_FAULT_PAGE_REQUEST_PASID_VALID (1 << 0) #define IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE (1 << 1) -#define IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA (1 << 2) -#define IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID (1 << 3) +#define IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID (1 << 2) u32 flags; u32 pasid; u32 grpid; @@ -125,12 +124,16 @@ struct iopf_fault { struct iopf_group { struct iopf_fault last_fault; struct list_head faults; + size_t fault_count; /* list node for iommu_fault_param::faults */ struct list_head pending_node; struct work_struct work; - struct iommu_domain *domain; + struct iommu_attach_handle *attach_handle; /* The device's fault data parameter. */ struct iommu_fault_param *fault_param; + /* Used by handler provider to hook the group on its own lists. */ + struct list_head node; + u32 cookie; }; /** @@ -318,6 +321,9 @@ enum iommu_dev_features { #define IOMMU_PASID_INVALID (-1U) typedef unsigned int ioasid_t; +/* Read but do not clear any dirty bits */ +#define IOMMU_DIRTY_NO_CLEAR (1 << 0) + #ifdef CONFIG_IOMMU_API /** @@ -354,9 +360,6 @@ struct iommu_dirty_bitmap { struct iommu_iotlb_gather *gather; }; -/* Read but do not clear any dirty bits */ -#define IOMMU_DIRTY_NO_CLEAR (1 << 0) - /** * struct iommu_dirty_ops - domain specific dirty tracking operations * @set_dirty_tracking: Enable or Disable dirty tracking on the iommu domain @@ -518,6 +521,7 @@ static inline int __iommu_copy_struct_from_user_array( * Upon failure, ERR_PTR must be returned. * @domain_alloc_paging: Allocate an iommu_domain that can be used for * UNMANAGED, DMA, and DMA_FQ domain types. + * @domain_alloc_sva: Allocate an iommu_domain for Shared Virtual Addressing. * @probe_device: Add device to iommu driver handling * @release_device: Remove device from iommu driver handling * @probe_finalize: Do final setup work after the device is added to an IOMMU @@ -547,6 +551,10 @@ static inline int __iommu_copy_struct_from_user_array( * @default_domain: If not NULL this will always be set as the default domain. * This should be an IDENTITY/BLOCKED/PLATFORM domain. * Do not use in new drivers. + * @user_pasid_table: IOMMU driver supports user-managed PASID table. There is + * no user domain for each PASID and the I/O page faults are + * forwarded through the user domain attached to the device + * RID. */ struct iommu_ops { bool (*capable)(struct device *dev, enum iommu_cap); @@ -558,6 +566,8 @@ struct iommu_ops { struct device *dev, u32 flags, struct iommu_domain *parent, const struct iommu_user_data *user_data); struct iommu_domain *(*domain_alloc_paging)(struct device *dev); + struct iommu_domain *(*domain_alloc_sva)(struct device *dev, + struct mm_struct *mm); struct iommu_device *(*probe_device)(struct device *dev); void (*release_device)(struct device *dev); @@ -578,7 +588,8 @@ struct iommu_ops { struct iommu_page_response *msg); int (*def_domain_type)(struct device *dev); - void (*remove_dev_pasid)(struct device *dev, ioasid_t pasid); + void (*remove_dev_pasid)(struct device *dev, ioasid_t pasid, + struct iommu_domain *domain); const struct iommu_domain_ops *default_domain_ops; unsigned long pgsize_bitmap; @@ -587,6 +598,7 @@ struct iommu_ops { struct iommu_domain *blocked_domain; struct iommu_domain *release_domain; struct iommu_domain *default_domain; + u8 user_pasid_table:1; }; /** @@ -777,13 +789,12 @@ 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(const struct bus_type *bus); +struct iommu_domain *iommu_paging_domain_alloc(struct device *dev); extern void iommu_domain_free(struct iommu_domain *domain); extern int iommu_attach_device(struct iommu_domain *domain, struct device *dev); extern void iommu_detach_device(struct iommu_domain *domain, struct device *dev); -extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain, - struct device *dev, ioasid_t pasid); extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev); extern struct iommu_domain *iommu_get_dma_domain(struct device *dev); extern int iommu_map(struct iommu_domain *domain, unsigned long iova, @@ -965,7 +976,6 @@ extern struct iommu_group *generic_single_device_group(struct device *dev); /** * struct iommu_fwspec - per-device IOMMU instance data - * @ops: ops for this device's IOMMU * @iommu_fwnode: firmware handle for this device's IOMMU * @flags: IOMMU_FWSPEC_* flags * @num_ids: number of associated device IDs @@ -976,7 +986,6 @@ extern struct iommu_group *generic_single_device_group(struct device *dev); * consumers. */ struct iommu_fwspec { - const struct iommu_ops *ops; struct fwnode_handle *iommu_fwnode; u32 flags; unsigned int num_ids; @@ -986,27 +995,33 @@ struct iommu_fwspec { /* ATS is supported */ #define IOMMU_FWSPEC_PCI_RC_ATS (1 << 0) +/* + * An iommu attach handle represents a relationship between an iommu domain + * and a PASID or RID of a device. It is allocated and managed by the component + * that manages the domain and is stored in the iommu group during the time the + * domain is attached. + */ +struct iommu_attach_handle { + struct iommu_domain *domain; +}; + /** * struct iommu_sva - handle to a device-mm bond */ struct iommu_sva { + struct iommu_attach_handle handle; struct device *dev; - struct iommu_domain *domain; - struct list_head handle_item; refcount_t users; }; struct iommu_mm_data { u32 pasid; struct list_head sva_domains; - struct list_head sva_handles; }; -int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode, - const struct iommu_ops *ops); +int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode); void iommu_fwspec_free(struct device *dev); int iommu_fwspec_add_ids(struct device *dev, const u32 *ids, int num_ids); -const struct iommu_ops *iommu_ops_from_fwnode(const struct fwnode_handle *fwnode); static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev) { @@ -1049,12 +1064,10 @@ int iommu_device_claim_dma_owner(struct device *dev, void *owner); void iommu_device_release_dma_owner(struct device *dev); int iommu_attach_device_pasid(struct iommu_domain *domain, - struct device *dev, ioasid_t pasid); + struct device *dev, ioasid_t pasid, + struct iommu_attach_handle *handle); void iommu_detach_device_pasid(struct iommu_domain *domain, struct device *dev, ioasid_t pasid); -struct iommu_domain * -iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid, - unsigned int type); ioasid_t iommu_alloc_global_pasid(struct device *dev); void iommu_free_global_pasid(ioasid_t pasid); #else /* CONFIG_IOMMU_API */ @@ -1083,6 +1096,11 @@ static inline struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus return NULL; } +static inline struct iommu_domain *iommu_paging_domain_alloc(struct device *dev) +{ + return ERR_PTR(-ENODEV); +} + static inline void iommu_domain_free(struct iommu_domain *domain) { } @@ -1312,8 +1330,7 @@ static inline void iommu_device_unlink(struct device *dev, struct device *link) } static inline int iommu_fwspec_init(struct device *dev, - struct fwnode_handle *iommu_fwnode, - const struct iommu_ops *ops) + struct fwnode_handle *iommu_fwnode) { return -ENODEV; } @@ -1328,12 +1345,6 @@ static inline int iommu_fwspec_add_ids(struct device *dev, u32 *ids, return -ENODEV; } -static inline -const struct iommu_ops *iommu_ops_from_fwnode(const struct fwnode_handle *fwnode) -{ - return NULL; -} - static inline int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat) { @@ -1385,7 +1396,8 @@ static inline int iommu_device_claim_dma_owner(struct device *dev, void *owner) } static inline int iommu_attach_device_pasid(struct iommu_domain *domain, - struct device *dev, ioasid_t pasid) + struct device *dev, ioasid_t pasid, + struct iommu_attach_handle *handle) { return -ENODEV; } @@ -1395,13 +1407,6 @@ static inline void iommu_detach_device_pasid(struct iommu_domain *domain, { } -static inline struct iommu_domain * -iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid, - unsigned int type) -{ - return NULL; -} - static inline ioasid_t iommu_alloc_global_pasid(struct device *dev) { return IOMMU_PASID_INVALID; @@ -1445,9 +1450,6 @@ static inline void iommu_debugfs_setup(void) {} #ifdef CONFIG_IOMMU_DMA #include <linux/msi.h> -/* Setup call for arch DMA mapping code */ -void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit); - int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base); int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr); @@ -1458,10 +1460,6 @@ void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_msg *msg); struct msi_desc; struct msi_msg; -static inline void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit) -{ -} - static inline int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base) { return -ENODEV; @@ -1531,13 +1529,11 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm); void iommu_sva_unbind_device(struct iommu_sva *handle); u32 iommu_sva_get_pasid(struct iommu_sva *handle); -struct iommu_domain *iommu_sva_domain_alloc(struct device *dev, - struct mm_struct *mm); #else static inline struct iommu_sva * iommu_sva_bind_device(struct device *dev, struct mm_struct *mm) { - return NULL; + return ERR_PTR(-ENODEV); } static inline void iommu_sva_unbind_device(struct iommu_sva *handle) @@ -1557,12 +1553,6 @@ static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm) } static inline void mm_pasid_drop(struct mm_struct *mm) {} - -static inline struct iommu_domain * -iommu_sva_domain_alloc(struct device *dev, struct mm_struct *mm) -{ - return NULL; -} #endif /* CONFIG_IOMMU_SVA */ #ifdef CONFIG_IOMMU_IOPF diff --git a/include/linux/ioport.h b/include/linux/ioport.h index db7fe25f3370..6e9fb667a1c5 100644 --- a/include/linux/ioport.h +++ b/include/linux/ioport.h @@ -188,6 +188,42 @@ enum { #define DEFINE_RES_DMA(_dma) \ DEFINE_RES_DMA_NAMED((_dma), NULL) +/** + * typedef resource_alignf - Resource alignment callback + * @data: Private data used by the callback + * @res: Resource candidate range (an empty resource space) + * @size: The minimum size of the empty space + * @align: Alignment from the constraints + * + * Callback allows calculating resource placement and alignment beyond min, + * max, and align fields in the struct resource_constraint. + * + * Return: Start address for the resource. + */ +typedef resource_size_t (*resource_alignf)(void *data, + const struct resource *res, + resource_size_t size, + resource_size_t align); + +/** + * struct resource_constraint - constraints to be met while searching empty + * resource space + * @min: The minimum address for the memory range + * @max: The maximum address for the memory range + * @align: Alignment for the start address of the empty space + * @alignf: Additional alignment constraints callback + * @alignf_data: Data provided for @alignf callback + * + * Contains the range and alignment constraints that have to be met during + * find_resource_space(). @alignf can be NULL indicating no alignment beyond + * @align is necessary. + */ +struct resource_constraint { + resource_size_t min, max, align; + resource_alignf alignf; + void *alignf_data; +}; + /* PC/ISA/whatever - the normal PC address spaces: IO and memory */ extern struct resource ioport_resource; extern struct resource iomem_resource; @@ -207,10 +243,7 @@ extern void arch_remove_reservations(struct resource *avail); extern int allocate_resource(struct resource *root, struct resource *new, resource_size_t size, resource_size_t min, resource_size_t max, resource_size_t align, - resource_size_t (*alignf)(void *, - const struct resource *, - resource_size_t, - resource_size_t), + resource_alignf alignf, void *alignf_data); struct resource *lookup_resource(struct resource *root, resource_size_t start); int adjust_resource(struct resource *res, resource_size_t start, @@ -264,6 +297,9 @@ static inline bool resource_union(const struct resource *r1, const struct resour return true; } +int find_resource_space(struct resource *root, struct resource *new, + resource_size_t size, struct resource_constraint *constraint); + /* Convenience shorthand with allocation */ #define request_region(start,n,name) __request_region(&ioport_resource, (start), (n), (name), 0) #define request_muxed_region(start,n,name) __request_region(&ioport_resource, (start), (n), (name), IORESOURCE_MUXED) diff --git a/include/linux/iova.h b/include/linux/iova.h index 83c00fac2acb..d2c4fd923efa 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -65,6 +65,11 @@ static inline size_t iova_align(struct iova_domain *iovad, size_t size) return ALIGN(size, iovad->granule); } +static inline size_t iova_align_down(struct iova_domain *iovad, size_t size) +{ + return ALIGN_DOWN(size, iovad->granule); +} + static inline dma_addr_t iova_dma_addr(struct iova_domain *iovad, struct iova *iova) { return (dma_addr_t)iova->pfn_lo << iova_shift(iovad); diff --git a/include/linux/irq.h b/include/linux/irq.h index 97baa937ab5b..1f5dbf1f92c9 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -115,7 +115,7 @@ enum { * Return value for chip->irq_set_affinity() * * IRQ_SET_MASK_OK - OK, core updates irq_common_data.affinity - * IRQ_SET_MASK_NOCPY - OK, chip did update irq_common_data.affinity + * IRQ_SET_MASK_NOCOPY - OK, chip did update irq_common_data.affinity * IRQ_SET_MASK_OK_DONE - Same as IRQ_SET_MASK_OK for core. Special code to * support stacked irqchips, which indicates skipping * all descendant irqchips. @@ -1106,6 +1106,7 @@ enum irq_gc_flags { * @irq_flags_to_set: IRQ* flags to set on irq setup * @irq_flags_to_clear: IRQ* flags to clear on irq setup * @gc_flags: Generic chip specific setup flags + * @exit: Function called on each chip when they are destroyed. * @gc: Array of pointers to generic interrupt chips */ struct irq_domain_chip_generic { @@ -1114,9 +1115,37 @@ struct irq_domain_chip_generic { unsigned int irq_flags_to_clear; unsigned int irq_flags_to_set; enum irq_gc_flags gc_flags; + void (*exit)(struct irq_chip_generic *gc); struct irq_chip_generic *gc[]; }; +/** + * struct irq_domain_chip_generic_info - Generic chip information structure + * @name: Name of the generic interrupt chip + * @handler: Interrupt handler used by the generic interrupt chip + * @irqs_per_chip: Number of interrupts each chip handles (max 32) + * @num_ct: Number of irq_chip_type instances associated with each + * chip + * @irq_flags_to_clear: IRQ_* bits to clear in the mapping function + * @irq_flags_to_set: IRQ_* bits to set in the mapping function + * @gc_flags: Generic chip specific setup flags + * @init: Function called on each chip when they are created. + * Allow to do some additional chip initialisation. + * @exit: Function called on each chip when they are destroyed. + * Allow to do some chip cleanup operation. + */ +struct irq_domain_chip_generic_info { + const char *name; + irq_flow_handler_t handler; + unsigned int irqs_per_chip; + unsigned int num_ct; + unsigned int irq_flags_to_clear; + unsigned int irq_flags_to_set; + enum irq_gc_flags gc_flags; + int (*init)(struct irq_chip_generic *gc); + void (*exit)(struct irq_chip_generic *gc); +}; + /* Generic chip callback functions */ void irq_gc_noop(struct irq_data *d); void irq_gc_mask_disable_reg(struct irq_data *d); @@ -1153,6 +1182,20 @@ int devm_irq_setup_generic_chip(struct device *dev, struct irq_chip_generic *gc, struct irq_chip_generic *irq_get_domain_generic_chip(struct irq_domain *d, unsigned int hw_irq); +#ifdef CONFIG_GENERIC_IRQ_CHIP +int irq_domain_alloc_generic_chips(struct irq_domain *d, + const struct irq_domain_chip_generic_info *info); +void irq_domain_remove_generic_chips(struct irq_domain *d); +#else +static inline int +irq_domain_alloc_generic_chips(struct irq_domain *d, + const struct irq_domain_chip_generic_info *info) +{ + return -EINVAL; +} +static inline void irq_domain_remove_generic_chips(struct irq_domain *d) { } +#endif /* CONFIG_GENERIC_IRQ_CHIP */ + int __irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, int num_ct, const char *name, irq_flow_handler_t handler, diff --git a/include/linux/irq_sim.h b/include/linux/irq_sim.h index ab831e5ae748..89b4d8ff274b 100644 --- a/include/linux/irq_sim.h +++ b/include/linux/irq_sim.h @@ -16,11 +16,28 @@ * requested like normal irqs and enqueued from process context. */ +struct irq_sim_ops { + int (*irq_sim_irq_requested)(struct irq_domain *domain, + irq_hw_number_t hwirq, void *data); + void (*irq_sim_irq_released)(struct irq_domain *domain, + irq_hw_number_t hwirq, void *data); +}; + struct irq_domain *irq_domain_create_sim(struct fwnode_handle *fwnode, unsigned int num_irqs); struct irq_domain *devm_irq_domain_create_sim(struct device *dev, struct fwnode_handle *fwnode, unsigned int num_irqs); +struct irq_domain *irq_domain_create_sim_full(struct fwnode_handle *fwnode, + unsigned int num_irqs, + const struct irq_sim_ops *ops, + void *data); +struct irq_domain * +devm_irq_domain_create_sim_full(struct device *dev, + struct fwnode_handle *fwnode, + unsigned int num_irqs, + const struct irq_sim_ops *ops, + void *data); void irq_domain_remove_sim(struct irq_domain *domain); #endif /* _LINUX_IRQ_SIM_H */ diff --git a/include/linux/irqchip/arm-gic-common.h b/include/linux/irqchip/arm-gic-common.h index 1177f3a1aed5..fc0246cc05ac 100644 --- a/include/linux/irqchip/arm-gic-common.h +++ b/include/linux/irqchip/arm-gic-common.h @@ -10,10 +10,6 @@ #include <linux/irqchip/arm-vgic-info.h> #define GICD_INT_DEF_PRI 0xa0 -#define GICD_INT_DEF_PRI_X4 ((GICD_INT_DEF_PRI << 24) |\ - (GICD_INT_DEF_PRI << 16) |\ - (GICD_INT_DEF_PRI << 8) |\ - GICD_INT_DEF_PRI) struct irq_domain; struct fwnode_handle; diff --git a/include/linux/irqchip/arm-gic-v3-prio.h b/include/linux/irqchip/arm-gic-v3-prio.h new file mode 100644 index 000000000000..44157c9abb78 --- /dev/null +++ b/include/linux/irqchip/arm-gic-v3-prio.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __LINUX_IRQCHIP_ARM_GIC_V3_PRIO_H +#define __LINUX_IRQCHIP_ARM_GIC_V3_PRIO_H + +/* + * GIC priorities from the view of the PMR/RPR. + * + * These values are chosen to be valid in either the absolute priority space or + * the NS view of the priority space. The value programmed into the distributor + * and ITS will be chosen at boot time such that these values appear in the + * PMR/RPR. + * + * GICV3_PRIO_UNMASKED is the PMR view of the priority to use to permit both + * IRQs and pseudo-NMIs. + * + * GICV3_PRIO_IRQ is the PMR view of the priority of regular interrupts. This + * can be written to the PMR to mask regular IRQs. + * + * GICV3_PRIO_NMI is the PMR view of the priority of pseudo-NMIs. This can be + * written to the PMR to mask pseudo-NMIs. + * + * On arm64 some code sections either automatically switch back to PSR.I or + * explicitly require to not use priority masking. If bit GICV3_PRIO_PSR_I_SET + * is included in the priority mask, it indicates that PSR.I should be set and + * interrupt disabling temporarily does not rely on IRQ priorities. + */ +#define GICV3_PRIO_UNMASKED 0xe0 +#define GICV3_PRIO_IRQ 0xc0 +#define GICV3_PRIO_NMI 0x80 + +#define GICV3_PRIO_PSR_I_SET (1 << 4) + +#ifndef __ASSEMBLER__ + +#define __gicv3_prio_to_ns(p) (0xff & ((p) << 1)) +#define __gicv3_ns_to_prio(ns) (0x80 | ((ns) >> 1)) + +#define __gicv3_prio_valid_ns(p) \ + (__gicv3_ns_to_prio(__gicv3_prio_to_ns(p)) == (p)) + +static_assert(__gicv3_prio_valid_ns(GICV3_PRIO_NMI)); +static_assert(__gicv3_prio_valid_ns(GICV3_PRIO_IRQ)); + +static_assert(GICV3_PRIO_NMI < GICV3_PRIO_IRQ); +static_assert(GICV3_PRIO_IRQ < GICV3_PRIO_UNMASKED); + +static_assert(GICV3_PRIO_IRQ < (GICV3_PRIO_IRQ | GICV3_PRIO_PSR_I_SET)); + +#endif /* __ASSEMBLER */ + +#endif /* __LINUX_IRQCHIP_ARM_GIC_V3_PRIO_H */ diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 728691365464..70c0948f978e 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -638,7 +638,7 @@ struct fwnode_handle; int __init its_lpi_memreserve_init(void); int its_cpu_init(void); int its_init(struct fwnode_handle *handle, struct rdists *rdists, - struct irq_domain *domain); + struct irq_domain *domain, u8 irq_prio); int mbi_init(struct fwnode_handle *fwnode, struct irq_domain *parent); static inline bool gic_enable_sre(void) diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h index 2c63375bbd43..ecabed6d3307 100644 --- a/include/linux/irqchip/arm-gic-v4.h +++ b/include/linux/irqchip/arm-gic-v4.h @@ -25,6 +25,14 @@ struct its_vm { irq_hw_number_t db_lpi_base; unsigned long *db_bitmap; int nr_db_lpis; + /* + * Ensures mutual exclusion between updates to vlpi_count[] + * and map/unmap when using the ITSList mechanism. + * + * The lock order for any sequence involving the ITSList is + * vmapp_lock -> vpe_lock ->vmovp_lock. + */ + raw_spinlock_t vmapp_lock; u32 vlpi_count[GICv4_ITS_LIST_MAX]; }; diff --git a/include/linux/irqchip/irq-partition-percpu.h b/include/linux/irqchip/irq-partition-percpu.h index 2f6ae7551748..b35ee22c278f 100644 --- a/include/linux/irqchip/irq-partition-percpu.h +++ b/include/linux/irqchip/irq-partition-percpu.h @@ -8,7 +8,7 @@ #define __LINUX_IRQCHIP_IRQ_PARTITION_PERCPU_H #include <linux/fwnode.h> -#include <linux/cpumask.h> +#include <linux/cpumask_types.h> #include <linux/irqdomain.h> struct partition_affinity { diff --git a/include/linux/irqchip/riscv-aplic.h b/include/linux/irqchip/riscv-aplic.h new file mode 100644 index 000000000000..ec8f7df50583 --- /dev/null +++ b/include/linux/irqchip/riscv-aplic.h @@ -0,0 +1,145 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + * Copyright (C) 2022 Ventana Micro Systems Inc. + */ +#ifndef __LINUX_IRQCHIP_RISCV_APLIC_H +#define __LINUX_IRQCHIP_RISCV_APLIC_H + +#include <linux/bitops.h> + +#define APLIC_MAX_IDC BIT(14) +#define APLIC_MAX_SOURCE 1024 + +#define APLIC_DOMAINCFG 0x0000 +#define APLIC_DOMAINCFG_RDONLY 0x80000000 +#define APLIC_DOMAINCFG_IE BIT(8) +#define APLIC_DOMAINCFG_DM BIT(2) +#define APLIC_DOMAINCFG_BE BIT(0) + +#define APLIC_SOURCECFG_BASE 0x0004 +#define APLIC_SOURCECFG_D BIT(10) +#define APLIC_SOURCECFG_CHILDIDX_MASK 0x000003ff +#define APLIC_SOURCECFG_SM_MASK 0x00000007 +#define APLIC_SOURCECFG_SM_INACTIVE 0x0 +#define APLIC_SOURCECFG_SM_DETACH 0x1 +#define APLIC_SOURCECFG_SM_EDGE_RISE 0x4 +#define APLIC_SOURCECFG_SM_EDGE_FALL 0x5 +#define APLIC_SOURCECFG_SM_LEVEL_HIGH 0x6 +#define APLIC_SOURCECFG_SM_LEVEL_LOW 0x7 + +#define APLIC_MMSICFGADDR 0x1bc0 +#define APLIC_MMSICFGADDRH 0x1bc4 +#define APLIC_SMSICFGADDR 0x1bc8 +#define APLIC_SMSICFGADDRH 0x1bcc + +#ifdef CONFIG_RISCV_M_MODE +#define APLIC_xMSICFGADDR APLIC_MMSICFGADDR +#define APLIC_xMSICFGADDRH APLIC_MMSICFGADDRH +#else +#define APLIC_xMSICFGADDR APLIC_SMSICFGADDR +#define APLIC_xMSICFGADDRH APLIC_SMSICFGADDRH +#endif + +#define APLIC_xMSICFGADDRH_L BIT(31) +#define APLIC_xMSICFGADDRH_HHXS_MASK 0x1f +#define APLIC_xMSICFGADDRH_HHXS_SHIFT 24 +#define APLIC_xMSICFGADDRH_HHXS (APLIC_xMSICFGADDRH_HHXS_MASK << \ + APLIC_xMSICFGADDRH_HHXS_SHIFT) +#define APLIC_xMSICFGADDRH_LHXS_MASK 0x7 +#define APLIC_xMSICFGADDRH_LHXS_SHIFT 20 +#define APLIC_xMSICFGADDRH_LHXS (APLIC_xMSICFGADDRH_LHXS_MASK << \ + APLIC_xMSICFGADDRH_LHXS_SHIFT) +#define APLIC_xMSICFGADDRH_HHXW_MASK 0x7 +#define APLIC_xMSICFGADDRH_HHXW_SHIFT 16 +#define APLIC_xMSICFGADDRH_HHXW (APLIC_xMSICFGADDRH_HHXW_MASK << \ + APLIC_xMSICFGADDRH_HHXW_SHIFT) +#define APLIC_xMSICFGADDRH_LHXW_MASK 0xf +#define APLIC_xMSICFGADDRH_LHXW_SHIFT 12 +#define APLIC_xMSICFGADDRH_LHXW (APLIC_xMSICFGADDRH_LHXW_MASK << \ + APLIC_xMSICFGADDRH_LHXW_SHIFT) +#define APLIC_xMSICFGADDRH_BAPPN_MASK 0xfff +#define APLIC_xMSICFGADDRH_BAPPN_SHIFT 0 +#define APLIC_xMSICFGADDRH_BAPPN (APLIC_xMSICFGADDRH_BAPPN_MASK << \ + APLIC_xMSICFGADDRH_BAPPN_SHIFT) + +#define APLIC_xMSICFGADDR_PPN_SHIFT 12 + +#define APLIC_xMSICFGADDR_PPN_HART(__lhxs) \ + (BIT(__lhxs) - 1) + +#define APLIC_xMSICFGADDR_PPN_LHX_MASK(__lhxw) \ + (BIT(__lhxw) - 1) +#define APLIC_xMSICFGADDR_PPN_LHX_SHIFT(__lhxs) \ + ((__lhxs)) +#define APLIC_xMSICFGADDR_PPN_LHX(__lhxw, __lhxs) \ + (APLIC_xMSICFGADDR_PPN_LHX_MASK(__lhxw) << \ + APLIC_xMSICFGADDR_PPN_LHX_SHIFT(__lhxs)) + +#define APLIC_xMSICFGADDR_PPN_HHX_MASK(__hhxw) \ + (BIT(__hhxw) - 1) +#define APLIC_xMSICFGADDR_PPN_HHX_SHIFT(__hhxs) \ + ((__hhxs) + APLIC_xMSICFGADDR_PPN_SHIFT) +#define APLIC_xMSICFGADDR_PPN_HHX(__hhxw, __hhxs) \ + (APLIC_xMSICFGADDR_PPN_HHX_MASK(__hhxw) << \ + APLIC_xMSICFGADDR_PPN_HHX_SHIFT(__hhxs)) + +#define APLIC_IRQBITS_PER_REG 32 + +#define APLIC_SETIP_BASE 0x1c00 +#define APLIC_SETIPNUM 0x1cdc + +#define APLIC_CLRIP_BASE 0x1d00 +#define APLIC_CLRIPNUM 0x1ddc + +#define APLIC_SETIE_BASE 0x1e00 +#define APLIC_SETIENUM 0x1edc + +#define APLIC_CLRIE_BASE 0x1f00 +#define APLIC_CLRIENUM 0x1fdc + +#define APLIC_SETIPNUM_LE 0x2000 +#define APLIC_SETIPNUM_BE 0x2004 + +#define APLIC_GENMSI 0x3000 + +#define APLIC_TARGET_BASE 0x3004 +#define APLIC_TARGET_HART_IDX_SHIFT 18 +#define APLIC_TARGET_HART_IDX_MASK 0x3fff +#define APLIC_TARGET_HART_IDX (APLIC_TARGET_HART_IDX_MASK << \ + APLIC_TARGET_HART_IDX_SHIFT) +#define APLIC_TARGET_GUEST_IDX_SHIFT 12 +#define APLIC_TARGET_GUEST_IDX_MASK 0x3f +#define APLIC_TARGET_GUEST_IDX (APLIC_TARGET_GUEST_IDX_MASK << \ + APLIC_TARGET_GUEST_IDX_SHIFT) +#define APLIC_TARGET_IPRIO_SHIFT 0 +#define APLIC_TARGET_IPRIO_MASK 0xff +#define APLIC_TARGET_IPRIO (APLIC_TARGET_IPRIO_MASK << \ + APLIC_TARGET_IPRIO_SHIFT) +#define APLIC_TARGET_EIID_SHIFT 0 +#define APLIC_TARGET_EIID_MASK 0x7ff +#define APLIC_TARGET_EIID (APLIC_TARGET_EIID_MASK << \ + APLIC_TARGET_EIID_SHIFT) + +#define APLIC_IDC_BASE 0x4000 +#define APLIC_IDC_SIZE 32 + +#define APLIC_IDC_IDELIVERY 0x00 + +#define APLIC_IDC_IFORCE 0x04 + +#define APLIC_IDC_ITHRESHOLD 0x08 + +#define APLIC_IDC_TOPI 0x18 +#define APLIC_IDC_TOPI_ID_SHIFT 16 +#define APLIC_IDC_TOPI_ID_MASK 0x3ff +#define APLIC_IDC_TOPI_ID (APLIC_IDC_TOPI_ID_MASK << \ + APLIC_IDC_TOPI_ID_SHIFT) +#define APLIC_IDC_TOPI_PRIO_SHIFT 0 +#define APLIC_IDC_TOPI_PRIO_MASK 0xff +#define APLIC_IDC_TOPI_PRIO (APLIC_IDC_TOPI_PRIO_MASK << \ + APLIC_IDC_TOPI_PRIO_SHIFT) + +#define APLIC_IDC_CLAIMI 0x1c + +#endif diff --git a/include/linux/irqchip/riscv-imsic.h b/include/linux/irqchip/riscv-imsic.h new file mode 100644 index 000000000000..faf0b800b1b0 --- /dev/null +++ b/include/linux/irqchip/riscv-imsic.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + * Copyright (C) 2022 Ventana Micro Systems Inc. + */ +#ifndef __LINUX_IRQCHIP_RISCV_IMSIC_H +#define __LINUX_IRQCHIP_RISCV_IMSIC_H + +#include <linux/types.h> +#include <linux/bitops.h> +#include <asm/csr.h> + +#define IMSIC_MMIO_PAGE_SHIFT 12 +#define IMSIC_MMIO_PAGE_SZ BIT(IMSIC_MMIO_PAGE_SHIFT) +#define IMSIC_MMIO_PAGE_LE 0x00 +#define IMSIC_MMIO_PAGE_BE 0x04 + +#define IMSIC_MIN_ID 63 +#define IMSIC_MAX_ID 2048 + +#define IMSIC_EIDELIVERY 0x70 + +#define IMSIC_EITHRESHOLD 0x72 + +#define IMSIC_EIP0 0x80 +#define IMSIC_EIP63 0xbf +#define IMSIC_EIPx_BITS 32 + +#define IMSIC_EIE0 0xc0 +#define IMSIC_EIE63 0xff +#define IMSIC_EIEx_BITS 32 + +#define IMSIC_FIRST IMSIC_EIDELIVERY +#define IMSIC_LAST IMSIC_EIE63 + +#define IMSIC_MMIO_SETIPNUM_LE 0x00 +#define IMSIC_MMIO_SETIPNUM_BE 0x04 + +struct imsic_local_config { + phys_addr_t msi_pa; + void __iomem *msi_va; +}; + +struct imsic_global_config { + /* + * MSI Target Address Scheme + * + * XLEN-1 12 0 + * | | | + * ------------------------------------------------------------- + * |xxxxxx|Group Index|xxxxxxxxxxx|HART Index|Guest Index| 0 | + * ------------------------------------------------------------- + */ + + /* Bits representing Guest index, HART index, and Group index */ + u32 guest_index_bits; + u32 hart_index_bits; + u32 group_index_bits; + u32 group_index_shift; + + /* Global base address matching all target MSI addresses */ + phys_addr_t base_addr; + + /* Number of interrupt identities */ + u32 nr_ids; + + /* Number of guest interrupt identities */ + u32 nr_guest_ids; + + /* Per-CPU IMSIC addresses */ + struct imsic_local_config __percpu *local; +}; + +#ifdef CONFIG_RISCV_IMSIC + +const struct imsic_global_config *imsic_get_global_config(void); + +#else + +static inline const struct imsic_global_config *imsic_get_global_config(void) +{ + return NULL; +} + +#endif + +#endif diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index d9451d456a73..fd091c35d572 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -18,6 +18,18 @@ struct irq_domain; struct pt_regs; /** + * struct irqstat - interrupt statistics + * @cnt: real-time interrupt count + * @ref: snapshot of interrupt count + */ +struct irqstat { + unsigned int cnt; +#ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT + unsigned int ref; +#endif +}; + +/** * struct irq_desc - interrupt descriptor * @irq_common_data: per irq and chip data passed down to chip functions * @kstat_irqs: irq stats per cpu @@ -55,7 +67,7 @@ struct pt_regs; struct irq_desc { struct irq_common_data irq_common_data; struct irq_data irq_data; - unsigned int __percpu *kstat_irqs; + struct irqstat __percpu *kstat_irqs; irq_flow_handler_t handle_irq; struct irqaction *action; /* IRQ action list */ unsigned int status_use_accessors; @@ -119,7 +131,7 @@ extern struct irq_desc irq_desc[NR_IRQS]; static inline unsigned int irq_desc_kstat_cpu(struct irq_desc *desc, unsigned int cpu) { - return desc->kstat_irqs ? *per_cpu_ptr(desc->kstat_irqs, cpu) : 0; + return desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, cpu) : 0; } static inline struct irq_desc *irq_data_to_desc(struct irq_data *data) diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 21ecf582a0fe..de6105f68fec 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -74,11 +74,24 @@ void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args, * struct irq_domain_ops - Methods for irq_domain objects * @match: Match an interrupt controller device node to a host, returns * 1 on a match + * @select: Match an interrupt controller fw specification. It is more generic + * than @match as it receives a complete struct irq_fwspec. Therefore, + * @select is preferred if provided. Returns 1 on a match. * @map: Create or update a mapping between a virtual irq number and a hw * irq number. This is called only once for a given mapping. * @unmap: Dispose of such a mapping * @xlate: Given a device tree node and interrupt specifier, decode * the hardware irq number and linux irq type value. + * @alloc: Allocate @nr_irqs interrupts starting from @virq. + * @free: Free @nr_irqs interrupts starting from @virq. + * @activate: Activate one interrupt in HW (@irqd). If @reserve is set, only + * reserve the vector. If unset, assign the vector (called from + * request_irq()). + * @deactivate: Disarm one interrupt (@irqd). + * @translate: Given @fwspec, decode the hardware irq number (@out_hwirq) and + * linux irq type value (@out_type). This is a generalised @xlate + * (over struct irq_fwspec) and is preferred if provided. + * @debug_show: For domains to show specific data for an interrupt in debugfs. * * Functions below are provided by the driver and called whenever a new mapping * is created or an old mapping is disposed. The driver can then proceed to @@ -131,6 +144,9 @@ struct irq_domain_chip_generic; * Optional elements: * @fwnode: Pointer to firmware node associated with the irq_domain. Pretty easy * to swap it for the of_node via the irq_domain_get_of_node accessor + * @bus_token: @fwnode's device_node might be used for several irq domains. But + * in connection with @bus_token, the pair shall be unique in a + * system. * @gc: Pointer to a list of generic chips. There is a helper function for * setting up one or more generic chips for interrupt controllers * drivers using the generic chip library which uses this pointer. @@ -141,9 +157,12 @@ struct irq_domain_chip_generic; * purposes related to the irq domain. * @parent: Pointer to parent irq_domain to support hierarchy irq_domains * @msi_parent_ops: Pointer to MSI parent domain methods for per device domain init + * @exit: Function called when the domain is destroyed * * Revmap data, used internally by the irq domain code: - * @revmap_size: Size of the linear map table @revmap[] + * @hwirq_max: Top limit for the HW irq number. Especially to avoid + * conflicts/failures with reserved HW irqs. Can be ~0. + * @revmap_size: Size of the linear map table @revmap * @revmap_tree: Radix map tree for hwirqs that don't fit in the linear map * @revmap: Linear table of irq_data pointers */ @@ -169,6 +188,7 @@ struct irq_domain { #ifdef CONFIG_GENERIC_MSI_IRQ const struct msi_parent_ops *msi_parent_ops; #endif + void (*exit)(struct irq_domain *d); /* reverse map data. The linear map gets appended to the irq_domain */ irq_hw_number_t hwirq_max; @@ -182,7 +202,7 @@ enum { /* Irq domain is hierarchical */ IRQ_DOMAIN_FLAG_HIERARCHY = (1 << 0), - /* Irq domain name was allocated in __irq_domain_add() */ + /* Irq domain name was allocated internally */ IRQ_DOMAIN_NAME_ALLOCATED = (1 << 1), /* Irq domain is an IPI domain with virq per cpu */ @@ -208,6 +228,9 @@ enum { /* Irq domain is a MSI device domain */ IRQ_DOMAIN_FLAG_MSI_DEVICE = (1 << 9), + /* Irq domain must destroy generic chips when removed */ + IRQ_DOMAIN_FLAG_DESTROY_GC = (1 << 10), + /* * Flags starting from IRQ_DOMAIN_FLAG_NONCORE are reserved * for implementation specific purposes and ignored by the @@ -257,10 +280,51 @@ static inline struct fwnode_handle *irq_domain_alloc_fwnode(phys_addr_t *pa) } void irq_domain_free_fwnode(struct fwnode_handle *fwnode); -struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size, - irq_hw_number_t hwirq_max, int direct_max, - const struct irq_domain_ops *ops, - void *host_data); + +struct irq_domain_chip_generic_info; + +/** + * struct irq_domain_info - Domain information structure + * @fwnode: firmware node for the interrupt controller + * @domain_flags: Additional flags to add to the domain flags + * @size: Size of linear map; 0 for radix mapping only + * @hwirq_max: Maximum number of interrupts supported by controller + * @direct_max: Maximum value of direct maps; + * Use ~0 for no limit; 0 for no direct mapping + * @bus_token: Domain bus token + * @ops: Domain operation callbacks + * @host_data: Controller private data pointer + * @dgc_info: Geneneric chip information structure pointer used to + * create generic chips for the domain if not NULL. + * @init: Function called when the domain is created. + * Allow to do some additional domain initialisation. + * @exit: Function called when the domain is destroyed. + * Allow to do some additional cleanup operation. + */ +struct irq_domain_info { + struct fwnode_handle *fwnode; + unsigned int domain_flags; + unsigned int size; + irq_hw_number_t hwirq_max; + int direct_max; + enum irq_domain_bus_token bus_token; + const struct irq_domain_ops *ops; + void *host_data; +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + /** + * @parent: Pointer to the parent irq domain used in a hierarchy domain + */ + struct irq_domain *parent; +#endif + struct irq_domain_chip_generic_info *dgc_info; + int (*init)(struct irq_domain *d); + void (*exit)(struct irq_domain *d); +}; + +struct irq_domain *irq_domain_instantiate(const struct irq_domain_info *info); +struct irq_domain *devm_irq_domain_instantiate(struct device *dev, + const struct irq_domain_info *info); + struct irq_domain *irq_domain_create_simple(struct fwnode_handle *fwnode, unsigned int size, unsigned int first_irq, @@ -293,7 +357,7 @@ static inline struct fwnode_handle *of_node_to_fwnode(struct device_node *node) extern const struct fwnode_operations irqchip_fwnode_ops; -static inline bool is_fwnode_irqchip(struct fwnode_handle *fwnode) +static inline bool is_fwnode_irqchip(const struct fwnode_handle *fwnode) { return fwnode && fwnode->ops == &irqchip_fwnode_ops; } @@ -350,7 +414,17 @@ static inline struct irq_domain *irq_domain_add_linear(struct device_node *of_no const struct irq_domain_ops *ops, void *host_data) { - return __irq_domain_add(of_node_to_fwnode(of_node), size, size, 0, ops, host_data); + struct irq_domain_info info = { + .fwnode = of_node_to_fwnode(of_node), + .size = size, + .hwirq_max = size, + .ops = ops, + .host_data = host_data, + }; + struct irq_domain *d; + + d = irq_domain_instantiate(&info); + return IS_ERR(d) ? NULL : d; } #ifdef CONFIG_IRQ_DOMAIN_NOMAP @@ -359,7 +433,17 @@ static inline struct irq_domain *irq_domain_add_nomap(struct device_node *of_nod const struct irq_domain_ops *ops, void *host_data) { - return __irq_domain_add(of_node_to_fwnode(of_node), 0, max_irq, max_irq, ops, host_data); + struct irq_domain_info info = { + .fwnode = of_node_to_fwnode(of_node), + .hwirq_max = max_irq, + .direct_max = max_irq, + .ops = ops, + .host_data = host_data, + }; + struct irq_domain *d; + + d = irq_domain_instantiate(&info); + return IS_ERR(d) ? NULL : d; } extern unsigned int irq_create_direct_mapping(struct irq_domain *host); @@ -369,7 +453,16 @@ static inline struct irq_domain *irq_domain_add_tree(struct device_node *of_node const struct irq_domain_ops *ops, void *host_data) { - return __irq_domain_add(of_node_to_fwnode(of_node), 0, ~0, 0, ops, host_data); + struct irq_domain_info info = { + .fwnode = of_node_to_fwnode(of_node), + .hwirq_max = ~0U, + .ops = ops, + .host_data = host_data, + }; + struct irq_domain *d; + + d = irq_domain_instantiate(&info); + return IS_ERR(d) ? NULL : d; } static inline struct irq_domain *irq_domain_create_linear(struct fwnode_handle *fwnode, @@ -377,14 +470,33 @@ static inline struct irq_domain *irq_domain_create_linear(struct fwnode_handle * const struct irq_domain_ops *ops, void *host_data) { - return __irq_domain_add(fwnode, size, size, 0, ops, host_data); + struct irq_domain_info info = { + .fwnode = fwnode, + .size = size, + .hwirq_max = size, + .ops = ops, + .host_data = host_data, + }; + struct irq_domain *d; + + d = irq_domain_instantiate(&info); + return IS_ERR(d) ? NULL : d; } static inline struct irq_domain *irq_domain_create_tree(struct fwnode_handle *fwnode, const struct irq_domain_ops *ops, void *host_data) { - return __irq_domain_add(fwnode, 0, ~0, 0, ops, host_data); + struct irq_domain_info info = { + .fwnode = fwnode, + .hwirq_max = ~0, + .ops = ops, + .host_data = host_data, + }; + struct irq_domain *d; + + d = irq_domain_instantiate(&info); + return IS_ERR(d) ? NULL : d; } extern void irq_domain_remove(struct irq_domain *host); diff --git a/include/linux/irqdomain_defs.h b/include/linux/irqdomain_defs.h index 5c1fe6f1fcde..36653e2ee1c9 100644 --- a/include/linux/irqdomain_defs.h +++ b/include/linux/irqdomain_defs.h @@ -25,7 +25,6 @@ enum irq_domain_bus_token { DOMAIN_BUS_PCI_DEVICE_MSIX, DOMAIN_BUS_DMAR, DOMAIN_BUS_AMDVI, - DOMAIN_BUS_PCI_DEVICE_IMS, DOMAIN_BUS_DEVICE_MSI, DOMAIN_BUS_WIRED_TO_MSI, }; diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 971f3e826e15..5157d92b6f23 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1086,6 +1086,13 @@ struct journal_s int j_revoke_records_per_block; /** + * @j_transaction_overhead: + * + * Number of blocks each transaction needs for its own bookkeeping + */ + int j_transaction_overhead_buffers; + + /** * @j_commit_interval: * * What is the maximum transaction lifetime before we begin a commit? @@ -1434,7 +1441,9 @@ void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); extern void jbd2_journal_commit_transaction(journal_t *); /* Checkpoint list management */ -void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy); +enum jbd2_shrink_type {JBD2_SHRINK_DESTROY, JBD2_SHRINK_BUSY_STOP, JBD2_SHRINK_BUSY_SKIP}; + +void __jbd2_journal_clean_checkpoint_list(journal_t *journal, enum jbd2_shrink_type type); unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan); int __jbd2_journal_remove_checkpoint(struct journal_head *); int jbd2_journal_try_remove_checkpoint(struct journal_head *jh); @@ -1586,10 +1595,13 @@ void jbd2_journal_put_journal_head(struct journal_head *jh); */ extern struct kmem_cache *jbd2_handle_cache; -static inline handle_t *jbd2_alloc_handle(gfp_t gfp_flags) -{ - return kmem_cache_zalloc(jbd2_handle_cache, gfp_flags); -} +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). The typecast is + * intentional to enforce typesafety. + */ +#define jbd2_alloc_handle(_gfp_flags) \ + ((handle_t *)kmem_cache_zalloc(jbd2_handle_cache, _gfp_flags)) static inline void jbd2_free_handle(handle_t *handle) { @@ -1602,10 +1614,13 @@ static inline void jbd2_free_handle(handle_t *handle) */ extern struct kmem_cache *jbd2_inode_cache; -static inline struct jbd2_inode *jbd2_alloc_inode(gfp_t gfp_flags) -{ - return kmem_cache_alloc(jbd2_inode_cache, gfp_flags); -} +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). The typecast is + * intentional to enforce typesafety. + */ +#define jbd2_alloc_inode(_gfp_flags) \ + ((struct jbd2_inode *)kmem_cache_alloc(jbd2_inode_cache, _gfp_flags)) static inline void jbd2_free_inode(struct jbd2_inode *jinode) { @@ -1662,11 +1677,6 @@ int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode); int jbd2_fc_wait_bufs(journal_t *journal, int num_blks); int jbd2_fc_release_bufs(journal_t *journal); -static inline int jbd2_journal_get_max_txn_bufs(journal_t *journal) -{ - return (journal->j_total_len - journal->j_fc_wbufsize) / 4; -} - /* * is_journal_abort * @@ -1696,7 +1706,7 @@ static inline void jbd2_journal_abort_handle(handle_t *handle) static inline void jbd2_init_fs_dev_write_error(journal_t *journal) { - struct address_space *mapping = journal->j_fs_dev->bd_inode->i_mapping; + struct address_space *mapping = journal->j_fs_dev->bd_mapping; /* * Save the original wb_err value of client fs's bdev mapping which @@ -1707,7 +1717,7 @@ static inline void jbd2_init_fs_dev_write_error(journal_t *journal) static inline int jbd2_check_fs_dev_write_error(journal_t *journal) { - struct address_space *mapping = journal->j_fs_dev->bd_inode->i_mapping; + struct address_space *mapping = journal->j_fs_dev->bd_mapping; return errseq_check(&mapping->wb_err, READ_ONCE(journal->j_fs_dev_wb_err)); diff --git a/include/linux/jhash.h b/include/linux/jhash.h index ab7f8c152b89..fa26a2dd3b52 100644 --- a/include/linux/jhash.h +++ b/include/linux/jhash.h @@ -31,7 +31,7 @@ /* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */ #define jhash_mask(n) (jhash_size(n)-1) -/* __jhash_mix -- mix 3 32-bit values reversibly. */ +/* __jhash_mix - mix 3 32-bit values reversibly. */ #define __jhash_mix(a, b, c) \ { \ a -= c; a ^= rol32(c, 4); c += b; \ @@ -60,7 +60,7 @@ /* jhash - hash an arbitrary key * @k: sequence of bytes as key * @length: the length of the key - * @initval: the previous hash, or an arbitray value + * @initval: the previous hash, or an arbitrary value * * The generic version, hashes an arbitrary sequence of bytes. * No alignment or length assumptions are made about the input key. @@ -110,7 +110,7 @@ static inline u32 jhash(const void *key, u32 length, u32 initval) /* jhash2 - hash an array of u32's * @k: the key which must be an array of u32's * @length: the number of u32's in the key - * @initval: the previous hash, or an arbitray value + * @initval: the previous hash, or an arbitrary value * * Returns the hash value of the key. */ diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index f0a949b7c973..f5a2727ca4a9 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -216,6 +216,7 @@ extern struct jump_entry __start___jump_table[]; extern struct jump_entry __stop___jump_table[]; extern void jump_label_init(void); +extern void jump_label_init_ro(void); extern void jump_label_lock(void); extern void jump_label_unlock(void); extern void arch_jump_label_transform(struct jump_entry *entry, @@ -265,6 +266,8 @@ static __always_inline void jump_label_init(void) static_key_initialized = true; } +static __always_inline void jump_label_init_ro(void) { } + static __always_inline bool static_key_false(struct static_key *key) { if (unlikely_notrace(static_key_count(key) > 0)) diff --git a/include/linux/kcov.h b/include/linux/kcov.h index b851ba415e03..75a2fb8b16c3 100644 --- a/include/linux/kcov.h +++ b/include/linux/kcov.h @@ -21,6 +21,8 @@ enum kcov_mode { KCOV_MODE_TRACE_PC = 2, /* Collecting comparison operands mode. */ KCOV_MODE_TRACE_CMP = 3, + /* The process owns a KCOV remote reference. */ + KCOV_MODE_REMOTE = 4, }; #define KCOV_IN_CTXSW (1 << 30) @@ -55,21 +57,47 @@ static inline void kcov_remote_start_usb(u64 id) /* * The softirq flavor of kcov_remote_*() functions is introduced as a temporary - * work around for kcov's lack of nested remote coverage sections support in - * task context. Adding support for nested sections is tracked in: - * https://bugzilla.kernel.org/show_bug.cgi?id=210337 + * workaround for KCOV's lack of nested remote coverage sections support. + * + * Adding support is tracked in https://bugzilla.kernel.org/show_bug.cgi?id=210337. + * + * kcov_remote_start_usb_softirq(): + * + * 1. Only collects coverage when called in the softirq context. This allows + * avoiding nested remote coverage collection sections in the task context. + * For example, USB/IP calls usb_hcd_giveback_urb() in the task context + * within an existing remote coverage collection section. Thus, KCOV should + * not attempt to start collecting coverage within the coverage collection + * section in __usb_hcd_giveback_urb() in this case. + * + * 2. Disables interrupts for the duration of the coverage collection section. + * This allows avoiding nested remote coverage collection sections in the + * softirq context (a softirq might occur during the execution of a work in + * the BH workqueue, which runs with in_serving_softirq() > 0). + * For example, usb_giveback_urb_bh() runs in the BH workqueue with + * interrupts enabled, so __usb_hcd_giveback_urb() might be interrupted in + * the middle of its remote coverage collection section, and the interrupt + * handler might invoke __usb_hcd_giveback_urb() again. */ -static inline void kcov_remote_start_usb_softirq(u64 id) +static inline unsigned long kcov_remote_start_usb_softirq(u64 id) { - if (in_serving_softirq()) + unsigned long flags = 0; + + if (in_serving_softirq()) { + local_irq_save(flags); kcov_remote_start_usb(id); + } + + return flags; } -static inline void kcov_remote_stop_softirq(void) +static inline void kcov_remote_stop_softirq(unsigned long flags) { - if (in_serving_softirq()) + if (in_serving_softirq()) { kcov_remote_stop(); + local_irq_restore(flags); + } } #ifdef CONFIG_64BIT @@ -103,8 +131,11 @@ static inline u64 kcov_common_handle(void) } static inline void kcov_remote_start_common(u64 id) {} static inline void kcov_remote_start_usb(u64 id) {} -static inline void kcov_remote_start_usb_softirq(u64 id) {} -static inline void kcov_remote_stop_softirq(void) {} +static inline unsigned long kcov_remote_start_usb_softirq(u64 id) +{ + return 0; +} +static inline void kcov_remote_stop_softirq(unsigned long flags) {} #endif /* CONFIG_KCOV */ #endif /* _LINUX_KCOV_H */ diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 9935f7ecbfb9..b97ce2df376f 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -5,7 +5,6 @@ #include <linux/smp.h> #include <linux/threads.h> #include <linux/percpu.h> -#include <linux/cpumask.h> #include <linux/interrupt.h> #include <linux/sched.h> #include <linux/vtime.h> @@ -79,6 +78,14 @@ static inline unsigned int kstat_cpu_softirqs_sum(int cpu) return sum; } +#ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT +extern void kstat_snapshot_irqs(void); +extern unsigned int kstat_get_irq_since_snapshot(unsigned int irq); +#else +static inline void kstat_snapshot_irqs(void) { } +static inline unsigned int kstat_get_irq_since_snapshot(unsigned int irq) { return 0; } +#endif + /* * Number of interrupts per specific IRQ source, since bootup */ diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 060835bb82d5..f0e9f8eda7a3 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -319,8 +319,10 @@ struct kimage { /* If set, we are using file mode kexec syscall */ unsigned int file_mode:1; #ifdef CONFIG_CRASH_HOTPLUG - /* If set, allow changes to elfcorehdr of kexec_load'd image */ - unsigned int update_elfcorehdr:1; + /* If set, it is safe to update kexec segments that are + * excluded from SHA calculation. + */ + unsigned int hotplug_support:1; #endif #ifdef ARCH_HAS_KIMAGE_ARCH @@ -391,9 +393,10 @@ bool kexec_load_permitted(int kexec_image_type); /* List of defined/legal kexec flags */ #ifndef CONFIG_KEXEC_JUMP -#define KEXEC_FLAGS (KEXEC_ON_CRASH | KEXEC_UPDATE_ELFCOREHDR) +#define KEXEC_FLAGS (KEXEC_ON_CRASH | KEXEC_UPDATE_ELFCOREHDR | KEXEC_CRASH_HOTPLUG_SUPPORT) #else -#define KEXEC_FLAGS (KEXEC_ON_CRASH | KEXEC_PRESERVE_CONTEXT | KEXEC_UPDATE_ELFCOREHDR) +#define KEXEC_FLAGS (KEXEC_ON_CRASH | KEXEC_PRESERVE_CONTEXT | KEXEC_UPDATE_ELFCOREHDR | \ + KEXEC_CRASH_HOTPLUG_SUPPORT) #endif /* List of defined/legal kexec file flags */ @@ -461,10 +464,8 @@ static inline void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages) { extern bool kexec_file_dbg_print; -#define kexec_dprintk(fmt, ...) \ - printk("%s" fmt, \ - kexec_file_dbg_print ? KERN_INFO : KERN_DEBUG, \ - ##__VA_ARGS__) +#define kexec_dprintk(fmt, arg...) \ + do { if (kexec_file_dbg_print) pr_info(fmt, ##arg); } while (0) #else /* !CONFIG_KEXEC_CORE */ struct pt_regs; diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index 0b35a41440ff..564868bdce89 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -36,10 +36,16 @@ * to lock the reader. */ -#include <linux/kernel.h> +#include <linux/array_size.h> +#include <linux/dma-mapping.h> #include <linux/spinlock.h> #include <linux/stddef.h> -#include <linux/scatterlist.h> +#include <linux/types.h> + +#include <asm/barrier.h> +#include <asm/errno.h> + +struct scatterlist; struct __kfifo { unsigned int in; @@ -304,19 +310,25 @@ __kfifo_uint_must_check_helper( \ ) /** - * kfifo_skip - skip output data + * kfifo_skip_count - skip output data * @fifo: address of the fifo to be used + * @count: count of data to skip */ -#define kfifo_skip(fifo) \ -(void)({ \ +#define kfifo_skip_count(fifo, count) do { \ typeof((fifo) + 1) __tmp = (fifo); \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ if (__recsize) \ __kfifo_skip_r(__kfifo, __recsize); \ else \ - __kfifo->out++; \ -}) + __kfifo->out += (count); \ +} while(0) + +/** + * kfifo_skip - skip output data + * @fifo: address of the fifo to be used + */ +#define kfifo_skip(fifo) kfifo_skip_count(fifo, 1) /** * kfifo_peek_len - gets the size of the next fifo record @@ -578,7 +590,7 @@ __kfifo_uint_must_check_helper( \ * @buf: pointer to the storage buffer * @n: max. number of elements to get * - * This macro get some data from the fifo and return the numbers of elements + * This macro gets some data from the fifo and returns the numbers of elements * copied. * * Note that with only one concurrent reader and one concurrent @@ -605,7 +617,7 @@ __kfifo_uint_must_check_helper( \ * @n: max. number of elements to get * @lock: pointer to the spinlock to use for locking * - * This macro get the data from the fifo and return the numbers of elements + * This macro gets the data from the fifo and returns the numbers of elements * copied. */ #define kfifo_out_spinlocked(fifo, buf, n, lock) \ @@ -703,11 +715,12 @@ __kfifo_int_must_check_helper( \ ) /** - * kfifo_dma_in_prepare - setup a scatterlist for DMA input + * kfifo_dma_in_prepare_mapped - setup a scatterlist for DMA input * @fifo: address of the fifo to be used * @sgl: pointer to the scatterlist array * @nents: number of entries in the scatterlist array * @len: number of elements to transfer + * @dma: mapped dma address to fill into @sgl * * This macro fills a scatterlist for DMA input. * It returns the number entries in the scatterlist array. @@ -715,7 +728,7 @@ __kfifo_int_must_check_helper( \ * Note that with only one concurrent reader and one concurrent * writer, you don't need extra locking to use these macros. */ -#define kfifo_dma_in_prepare(fifo, sgl, nents, len) \ +#define kfifo_dma_in_prepare_mapped(fifo, sgl, nents, len, dma) \ ({ \ typeof((fifo) + 1) __tmp = (fifo); \ struct scatterlist *__sgl = (sgl); \ @@ -724,16 +737,20 @@ __kfifo_int_must_check_helper( \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ (__recsize) ? \ - __kfifo_dma_in_prepare_r(__kfifo, __sgl, __nents, __len, __recsize) : \ - __kfifo_dma_in_prepare(__kfifo, __sgl, __nents, __len); \ + __kfifo_dma_in_prepare_r(__kfifo, __sgl, __nents, __len, __recsize, \ + dma) : \ + __kfifo_dma_in_prepare(__kfifo, __sgl, __nents, __len, dma); \ }) +#define kfifo_dma_in_prepare(fifo, sgl, nents, len) \ + kfifo_dma_in_prepare_mapped(fifo, sgl, nents, len, DMA_MAPPING_ERROR) + /** * kfifo_dma_in_finish - finish a DMA IN operation * @fifo: address of the fifo to be used * @len: number of bytes to received * - * This macro finish a DMA IN operation. The in counter will be updated by + * This macro finishes a DMA IN operation. The in counter will be updated by * the len parameter. No error checking will be done. * * Note that with only one concurrent reader and one concurrent @@ -752,11 +769,12 @@ __kfifo_int_must_check_helper( \ }) /** - * kfifo_dma_out_prepare - setup a scatterlist for DMA output + * kfifo_dma_out_prepare_mapped - setup a scatterlist for DMA output * @fifo: address of the fifo to be used * @sgl: pointer to the scatterlist array * @nents: number of entries in the scatterlist array * @len: number of elements to transfer + * @dma: mapped dma address to fill into @sgl * * This macro fills a scatterlist for DMA output which at most @len bytes * to transfer. @@ -766,7 +784,7 @@ __kfifo_int_must_check_helper( \ * Note that with only one concurrent reader and one concurrent * writer, you don't need extra locking to use these macros. */ -#define kfifo_dma_out_prepare(fifo, sgl, nents, len) \ +#define kfifo_dma_out_prepare_mapped(fifo, sgl, nents, len, dma) \ ({ \ typeof((fifo) + 1) __tmp = (fifo); \ struct scatterlist *__sgl = (sgl); \ @@ -775,32 +793,29 @@ __kfifo_int_must_check_helper( \ const size_t __recsize = sizeof(*__tmp->rectype); \ struct __kfifo *__kfifo = &__tmp->kfifo; \ (__recsize) ? \ - __kfifo_dma_out_prepare_r(__kfifo, __sgl, __nents, __len, __recsize) : \ - __kfifo_dma_out_prepare(__kfifo, __sgl, __nents, __len); \ + __kfifo_dma_out_prepare_r(__kfifo, __sgl, __nents, __len, __recsize, \ + dma) : \ + __kfifo_dma_out_prepare(__kfifo, __sgl, __nents, __len, dma); \ }) +#define kfifo_dma_out_prepare(fifo, sgl, nents, len) \ + kfifo_dma_out_prepare_mapped(fifo, sgl, nents, len, DMA_MAPPING_ERROR) + /** * kfifo_dma_out_finish - finish a DMA OUT operation * @fifo: address of the fifo to be used * @len: number of bytes transferred * - * This macro finish a DMA OUT operation. The out counter will be updated by + * This macro finishes a DMA OUT operation. The out counter will be updated by * the len parameter. No error checking will be done. * * Note that with only one concurrent reader and one concurrent * writer, you don't need extra locking to use these macros. */ -#define kfifo_dma_out_finish(fifo, len) \ -(void)({ \ - typeof((fifo) + 1) __tmp = (fifo); \ - unsigned int __len = (len); \ - const size_t __recsize = sizeof(*__tmp->rectype); \ - struct __kfifo *__kfifo = &__tmp->kfifo; \ - if (__recsize) \ - __kfifo_dma_out_finish_r(__kfifo, __recsize); \ - else \ - __kfifo->out += __len / sizeof(*__tmp->type); \ -}) +#define kfifo_dma_out_finish(fifo, len) do { \ + typeof((fifo) + 1) ___tmp = (fifo); \ + kfifo_skip_count(___tmp, (len) / sizeof(*___tmp->type)); \ +} while (0) /** * kfifo_out_peek - gets some data from the fifo @@ -808,7 +823,7 @@ __kfifo_int_must_check_helper( \ * @buf: pointer to the storage buffer * @n: max. number of elements to get * - * This macro get the data from the fifo and return the numbers of elements + * This macro gets the data from the fifo and returns the numbers of elements * copied. The data is not removed from the fifo. * * Note that with only one concurrent reader and one concurrent @@ -828,6 +843,63 @@ __kfifo_uint_must_check_helper( \ }) \ ) +/** + * kfifo_out_linear - gets a tail of/offset to available data + * @fifo: address of the fifo to be used + * @tail: pointer to an unsigned int to store the value of tail + * @n: max. number of elements to point at + * + * This macro obtains the offset (tail) to the available data in the fifo + * buffer and returns the + * numbers of elements available. It returns the available count till the end + * of data or till the end of the buffer. So that it can be used for linear + * data processing (like memcpy() of (@fifo->data + @tail) with count + * returned). + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_out_linear(fifo, tail, n) \ +__kfifo_uint_must_check_helper( \ +({ \ + typeof((fifo) + 1) __tmp = (fifo); \ + unsigned int *__tail = (tail); \ + unsigned long __n = (n); \ + const size_t __recsize = sizeof(*__tmp->rectype); \ + struct __kfifo *__kfifo = &__tmp->kfifo; \ + (__recsize) ? \ + __kfifo_out_linear_r(__kfifo, __tail, __n, __recsize) : \ + __kfifo_out_linear(__kfifo, __tail, __n); \ +}) \ +) + +/** + * kfifo_out_linear_ptr - gets a pointer to the available data + * @fifo: address of the fifo to be used + * @ptr: pointer to data to store the pointer to tail + * @n: max. number of elements to point at + * + * Similarly to kfifo_out_linear(), this macro obtains the pointer to the + * available data in the fifo buffer and returns the numbers of elements + * available. It returns the available count till the end of available data or + * till the end of the buffer. So that it can be used for linear data + * processing (like memcpy() of @ptr with count returned). + * + * Note that with only one concurrent reader and one concurrent + * writer, you don't need extra locking to use these macro. + */ +#define kfifo_out_linear_ptr(fifo, ptr, n) \ +__kfifo_uint_must_check_helper( \ +({ \ + typeof((fifo) + 1) ___tmp = (fifo); \ + unsigned int ___tail; \ + unsigned int ___n = kfifo_out_linear(___tmp, &___tail, (n)); \ + *(ptr) = ___tmp->kfifo.data + ___tail * kfifo_esize(___tmp); \ + ___n; \ +}) \ +) + + extern int __kfifo_alloc(struct __kfifo *fifo, unsigned int size, size_t esize, gfp_t gfp_mask); @@ -849,14 +921,17 @@ extern int __kfifo_to_user(struct __kfifo *fifo, void __user *to, unsigned long len, unsigned int *copied); extern unsigned int __kfifo_dma_in_prepare(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len); + struct scatterlist *sgl, int nents, unsigned int len, dma_addr_t dma); extern unsigned int __kfifo_dma_out_prepare(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len); + struct scatterlist *sgl, int nents, unsigned int len, dma_addr_t dma); extern unsigned int __kfifo_out_peek(struct __kfifo *fifo, void *buf, unsigned int len); +extern unsigned int __kfifo_out_linear(struct __kfifo *fifo, + unsigned int *tail, unsigned int n); + extern unsigned int __kfifo_in_r(struct __kfifo *fifo, const void *buf, unsigned int len, size_t recsize); @@ -871,15 +946,15 @@ extern int __kfifo_to_user_r(struct __kfifo *fifo, void __user *to, unsigned long len, unsigned int *copied, size_t recsize); extern unsigned int __kfifo_dma_in_prepare_r(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len, size_t recsize); + struct scatterlist *sgl, int nents, unsigned int len, size_t recsize, + dma_addr_t dma); extern void __kfifo_dma_in_finish_r(struct __kfifo *fifo, unsigned int len, size_t recsize); extern unsigned int __kfifo_dma_out_prepare_r(struct __kfifo *fifo, - struct scatterlist *sgl, int nents, unsigned int len, size_t recsize); - -extern void __kfifo_dma_out_finish_r(struct __kfifo *fifo, size_t recsize); + struct scatterlist *sgl, int nents, unsigned int len, size_t recsize, + dma_addr_t dma); extern unsigned int __kfifo_len_r(struct __kfifo *fifo, size_t recsize); @@ -888,6 +963,9 @@ extern void __kfifo_skip_r(struct __kfifo *fifo, size_t recsize); extern unsigned int __kfifo_out_peek_r(struct __kfifo *fifo, void *buf, unsigned int len, size_t recsize); +extern unsigned int __kfifo_out_linear_r(struct __kfifo *fifo, + unsigned int *tail, unsigned int n, size_t recsize); + extern unsigned int __kfifo_max_r(unsigned int len, size_t recsize); #endif diff --git a/include/linux/kmsan-checks.h b/include/linux/kmsan-checks.h index c4cae333deec..e1082dc40abc 100644 --- a/include/linux/kmsan-checks.h +++ b/include/linux/kmsan-checks.h @@ -61,6 +61,17 @@ void kmsan_check_memory(const void *address, size_t size); void kmsan_copy_to_user(void __user *to, const void *from, size_t to_copy, size_t left); +/** + * kmsan_memmove() - Notify KMSAN about a data copy within kernel. + * @to: destination address in the kernel. + * @from: source address in the kernel. + * @size: number of bytes to copy. + * + * Invoked after non-instrumented version (e.g. implemented using assembly + * code) of memmove()/memcpy() is called, in order to copy KMSAN's metadata. + */ +void kmsan_memmove(void *to, const void *from, size_t to_copy); + #else static inline void kmsan_poison_memory(const void *address, size_t size, @@ -78,6 +89,10 @@ static inline void kmsan_copy_to_user(void __user *to, const void *from, { } +static inline void kmsan_memmove(void *to, const void *from, size_t to_copy) +{ +} + #endif #endif /* _LINUX_KMSAN_CHECKS_H */ diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h index e0c23a32cdf0..2b1432cc16d5 100644 --- a/include/linux/kmsan.h +++ b/include/linux/kmsan.h @@ -230,6 +230,67 @@ void kmsan_handle_urb(const struct urb *urb, bool is_out); */ void kmsan_unpoison_entry_regs(const struct pt_regs *regs); +/** + * kmsan_get_metadata() - Return a pointer to KMSAN shadow or origins. + * @addr: kernel address. + * @is_origin: whether to return origins or shadow. + * + * Return NULL if metadata cannot be found. + */ +void *kmsan_get_metadata(void *addr, bool is_origin); + +/** + * kmsan_enable_current(): Enable KMSAN for the current task. + * + * Each kmsan_enable_current() current call must be preceded by a + * kmsan_disable_current() call. These call pairs may be nested. + */ +void kmsan_enable_current(void); + +/** + * kmsan_disable_current(): Disable KMSAN for the current task. + * + * Each kmsan_disable_current() current call must be followed by a + * kmsan_enable_current() call. These call pairs may be nested. + */ +void kmsan_disable_current(void); + +/** + * memset_no_sanitize_memory(): Fill memory without KMSAN instrumentation. + * @s: address of kernel memory to fill. + * @c: constant byte to fill the memory with. + * @n: number of bytes to fill. + * + * This is like memset(), but without KMSAN instrumentation. + */ +static inline void *memset_no_sanitize_memory(void *s, int c, size_t n) +{ + return __memset(s, c, n); +} + +extern bool kmsan_enabled; +extern int panic_on_kmsan; + +/* + * KMSAN performs a lot of consistency checks that are currently enabled by + * default. BUG_ON is normally discouraged in the kernel, unless used for + * debugging, but KMSAN itself is a debugging tool, so it makes little sense to + * recover if something goes wrong. + */ +#define KMSAN_WARN_ON(cond) \ + ({ \ + const bool __cond = WARN_ON(cond); \ + if (unlikely(__cond)) { \ + WRITE_ONCE(kmsan_enabled, false); \ + if (panic_on_kmsan) { \ + /* Can't call panic() here because */ \ + /* of uaccess checks. */ \ + BUG(); \ + } \ + } \ + __cond; \ + }) + #else static inline void kmsan_init_shadow(void) @@ -329,6 +390,21 @@ static inline void kmsan_unpoison_entry_regs(const struct pt_regs *regs) { } +static inline void kmsan_enable_current(void) +{ +} + +static inline void kmsan_disable_current(void) +{ +} + +static inline void *memset_no_sanitize_memory(void *s, int c, size_t n) +{ + return memset(s, c, n); +} + +#define KMSAN_WARN_ON WARN_ON + #endif #endif /* _LINUX_KMSAN_H */ diff --git a/include/linux/kmsan_types.h b/include/linux/kmsan_types.h index 929287981afe..dfc59918b3c0 100644 --- a/include/linux/kmsan_types.h +++ b/include/linux/kmsan_types.h @@ -31,7 +31,7 @@ struct kmsan_context_state { struct kmsan_ctx { struct kmsan_context_state cstate; int kmsan_in_runtime; - bool allow_reporting; + unsigned int depth; }; #endif /* _LINUX_KMSAN_TYPES_H */ diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 0ff44d6633e3..5fcbc254d186 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -378,11 +378,15 @@ static inline void wait_for_kprobe_optimizer(void) { } extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct ftrace_regs *fregs); extern int arch_prepare_kprobe_ftrace(struct kprobe *p); +/* Set when ftrace has been killed: kprobes on ftrace must be disabled for safety */ +extern bool kprobe_ftrace_disabled __read_mostly; +extern void kprobe_ftrace_kill(void); #else static inline int arch_prepare_kprobe_ftrace(struct kprobe *p) { return -EINVAL; } +static inline void kprobe_ftrace_kill(void) {} #endif /* CONFIG_KPROBES_ON_FTRACE */ /* Get the kprobe at this addr (if any) - called with preemption disabled */ @@ -495,6 +499,9 @@ static inline void kprobe_flush_task(struct task_struct *tk) static inline void kprobe_free_init_mem(void) { } +static inline void kprobe_ftrace_kill(void) +{ +} static inline int disable_kprobe(struct kprobe *kp) { return -EOPNOTSUPP; diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 401348e9f92b..11690dacd986 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -33,28 +33,39 @@ void __ksm_exit(struct mm_struct *mm); */ #define is_ksm_zero_pte(pte) (is_zero_pfn(pte_pfn(pte)) && pte_dirty(pte)) -extern unsigned long ksm_zero_pages; +extern atomic_long_t ksm_zero_pages; + +static inline void ksm_map_zero_page(struct mm_struct *mm) +{ + atomic_long_inc(&ksm_zero_pages); + atomic_long_inc(&mm->ksm_zero_pages); +} static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { if (is_ksm_zero_pte(pte)) { - ksm_zero_pages--; - mm->ksm_zero_pages--; + atomic_long_dec(&ksm_zero_pages); + atomic_long_dec(&mm->ksm_zero_pages); } } +static inline long mm_ksm_zero_pages(struct mm_struct *mm) +{ + return atomic_long_read(&mm->ksm_zero_pages); +} + static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { - int ret; + if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) + return __ksm_enter(mm); - if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) { - ret = __ksm_enter(mm); - if (ret) - return ret; - } + return 0; +} - if (test_bit(MMF_VM_MERGE_ANY, &oldmm->flags)) - set_bit(MMF_VM_MERGE_ANY, &mm->flags); +static inline int ksm_execve(struct mm_struct *mm) +{ + if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) + return __ksm_enter(mm); return 0; } @@ -81,15 +92,9 @@ struct folio *ksm_might_need_to_copy(struct folio *folio, 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 +void collect_procs_ksm(struct folio *folio, struct page *page, + struct list_head *to_kill, int force_early); long ksm_process_profit(struct mm_struct *); -#endif /* CONFIG_PROC_FS */ #else /* !CONFIG_KSM */ @@ -107,6 +112,11 @@ static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) return 0; } +static inline int ksm_execve(struct mm_struct *mm) +{ + return 0; +} + static inline void ksm_exit(struct mm_struct *mm) { } @@ -115,12 +125,10 @@ static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { } -#ifdef CONFIG_MEMORY_FAILURE -static inline void collect_procs_ksm(struct page *page, +static inline void collect_procs_ksm(struct folio *folio, 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, diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 48f31dcd318a..b23c6d48392f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -193,8 +193,6 @@ static inline bool is_error_page(struct page *page) bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, unsigned long *vcpu_bitmap); bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); -bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req, - struct kvm_vcpu *except); #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 @@ -259,7 +257,6 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER union kvm_mmu_notifier_arg { - pte_t pte; unsigned long attributes; }; @@ -273,7 +270,6 @@ struct kvm_gfn_range { bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); -bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range); #endif enum { @@ -382,8 +378,10 @@ struct kvm_vcpu { bool dy_eligible; } spin_loop; #endif + bool wants_to_run; bool preempted; bool ready; + bool scheduled_out; struct kvm_vcpu_arch arch; struct kvm_vcpu_stat stat; char stats_id[KVM_STATS_NAME_SIZE]; @@ -717,6 +715,13 @@ static inline bool kvm_arch_has_private_mem(struct kvm *kvm) } #endif +#ifndef kvm_arch_has_readonly_mem +static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm) +{ + return IS_ENABLED(CONFIG_HAVE_KVM_READONLY_MEM); +} +#endif + struct kvm_memslots { u64 generation; atomic_long_t last_used_slot; @@ -1498,8 +1503,6 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg); int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu); -void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu); - void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu); void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id); @@ -1959,8 +1962,6 @@ struct _kvm_stats_desc { HALT_POLL_HIST_COUNT), \ STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking) -extern struct dentry *kvm_debugfs_dir; - ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header, const struct _kvm_stats_desc *desc, void *stats, size_t size_stats, @@ -2100,6 +2101,7 @@ int kvm_set_irq_routing(struct kvm *kvm, const struct kvm_irq_routing_entry *entries, unsigned nr, unsigned flags); +int kvm_init_irq_routing(struct kvm *kvm); int kvm_set_routing_entry(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue); @@ -2109,6 +2111,11 @@ void kvm_free_irq_routing(struct kvm *kvm); static inline void kvm_free_irq_routing(struct kvm *kvm) {} +static inline int kvm_init_irq_routing(struct kvm *kvm) +{ + return 0; +} + #endif int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi); @@ -2414,7 +2421,7 @@ static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn } bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, - unsigned long attrs); + unsigned long mask, unsigned long attrs); bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, @@ -2445,4 +2452,46 @@ static inline int kvm_gmem_get_pfn(struct kvm *kvm, } #endif /* CONFIG_KVM_PRIVATE_MEM */ +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE +int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order); +#endif + +#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM +/** + * kvm_gmem_populate() - Populate/prepare a GPA range with guest data + * + * @kvm: KVM instance + * @gfn: starting GFN to be populated + * @src: userspace-provided buffer containing data to copy into GFN range + * (passed to @post_populate, and incremented on each iteration + * if not NULL) + * @npages: number of pages to copy from userspace-buffer + * @post_populate: callback to issue for each gmem page that backs the GPA + * range + * @opaque: opaque data to pass to @post_populate callback + * + * This is primarily intended for cases where a gmem-backed GPA range needs + * to be initialized with userspace-provided data prior to being mapped into + * the guest as a private page. This should be called with the slots->lock + * held so that caller-enforced invariants regarding the expected memory + * attributes of the GPA range do not race with KVM_SET_MEMORY_ATTRIBUTES. + * + * Returns the number of pages that were populated. + */ +typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, + void __user *src, int order, void *opaque); + +long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages, + kvm_gmem_populate_cb post_populate, void *opaque); +#endif + +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE +void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end); +#endif + +#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY +long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, + struct kvm_pre_fault_memory *range); +#endif + #endif diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index d93f6522b2c3..827ecc0b7e10 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -86,6 +86,7 @@ struct gfn_to_pfn_cache { struct kvm_mmu_memory_cache { gfp_t gfp_zero; gfp_t gfp_custom; + u64 init_value; struct kmem_cache *kmem_cache; int capacity; int nobjs; diff --git a/include/linux/lcd.h b/include/linux/lcd.h index 238fb1dfed98..68703a51dc53 100644 --- a/include/linux/lcd.h +++ b/include/linux/lcd.h @@ -61,7 +61,7 @@ struct lcd_device { points to something in the body of that driver, it is also invalid. */ struct mutex ops_lock; /* If this is NULL, the backing module is unloaded */ - struct lcd_ops *ops; + const struct lcd_ops *ops; /* Serialise access to set_power method */ struct mutex update_lock; /* The framebuffer notifier block */ @@ -102,10 +102,10 @@ static inline void lcd_set_power(struct lcd_device *ld, int power) } extern struct lcd_device *lcd_device_register(const char *name, - struct device *parent, void *devdata, struct lcd_ops *ops); + struct device *parent, void *devdata, const struct lcd_ops *ops); extern struct lcd_device *devm_lcd_device_register(struct device *dev, const char *name, struct device *parent, - void *devdata, struct lcd_ops *ops); + void *devdata, const struct lcd_ops *ops); extern void lcd_device_unregister(struct lcd_device *ld); extern void devm_lcd_device_unregister(struct device *dev, struct lcd_device *ld); diff --git a/include/linux/leds.h b/include/linux/leds.h index db6b114bb3d9..6885603f211b 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -107,6 +107,8 @@ struct led_classdev { #define LED_BRIGHT_HW_CHANGED BIT(21) #define LED_RETAIN_AT_SHUTDOWN BIT(22) #define LED_INIT_DEFAULT_TRIGGER BIT(23) +#define LED_REJECT_NAME_CONFLICT BIT(24) +#define LED_MULTI_COLOR BIT(25) /* set_brightness_work / blink_timer flags, atomic, private. */ unsigned long work_flags; @@ -374,6 +376,25 @@ void led_set_brightness(struct led_classdev *led_cdev, unsigned int brightness); int led_set_brightness_sync(struct led_classdev *led_cdev, unsigned int value); /** + * led_mc_set_brightness - set mc LED color intensity values and brightness + * @led_cdev: the LED to set + * @intensity_value: array of per color intensity values to set + * @num_colors: amount of entries in intensity_value array + * @brightness: the brightness to set the LED to + * + * Set a multi-color LED's per color intensity values and brightness. + * If necessary, this cancels the software blink timer. This function is + * guaranteed not to sleep. + * + * Calling this function on a non multi-color led_classdev or with the wrong + * num_colors value is an error. In this case an error will be logged once + * and the call will do nothing. + */ +void led_mc_set_brightness(struct led_classdev *led_cdev, + unsigned int *intensity_value, unsigned int num_colors, + unsigned int brightness); + +/** * led_update_brightness - update LED brightness * @led_cdev: the LED to query * @@ -428,6 +449,16 @@ int led_compose_name(struct device *dev, struct led_init_data *init_data, char *led_classdev_name); /** + * led_get_color_name - get string representation of color ID + * @color_id: The LED_COLOR_ID_* constant + * + * Get the string name of a LED_COLOR_ID_* constant. + * + * Returns: A string constant or NULL on an invalid ID. + */ +const char *led_get_color_name(u8 color_id); + +/** * led_sysfs_is_disabled - check if LED sysfs interface is disabled * @led_cdev: the LED to query * @@ -455,6 +486,9 @@ struct led_trigger { int (*activate)(struct led_classdev *led_cdev); void (*deactivate)(struct led_classdev *led_cdev); + /* Brightness set by led_trigger_event */ + enum led_brightness brightness; + /* LED-private triggers have this set */ struct led_hw_trigger_type *trigger_type; @@ -487,6 +521,9 @@ void led_trigger_register_simple(const char *name, struct led_trigger **trigger); void led_trigger_unregister_simple(struct led_trigger *trigger); void led_trigger_event(struct led_trigger *trigger, enum led_brightness event); +void led_mc_trigger_event(struct led_trigger *trig, + unsigned int *intensity_value, unsigned int num_colors, + enum led_brightness brightness); void led_trigger_blink(struct led_trigger *trigger, unsigned long delay_on, unsigned long delay_off); void led_trigger_blink_oneshot(struct led_trigger *trigger, @@ -508,6 +545,12 @@ static inline void *led_get_trigger_data(struct led_classdev *led_cdev) return led_cdev->trigger_data; } +static inline enum led_brightness +led_trigger_get_brightness(const struct led_trigger *trigger) +{ + return trigger ? trigger->brightness : LED_OFF; +} + #define module_led_trigger(__led_trigger) \ module_driver(__led_trigger, led_trigger_register, \ led_trigger_unregister) @@ -523,6 +566,9 @@ static inline void led_trigger_register_simple(const char *name, static inline void led_trigger_unregister_simple(struct led_trigger *trigger) {} static inline void led_trigger_event(struct led_trigger *trigger, enum led_brightness event) {} +static inline void led_mc_trigger_event(struct led_trigger *trig, + unsigned int *intensity_value, unsigned int num_colors, + enum led_brightness brightness) {} static inline void led_trigger_blink(struct led_trigger *trigger, unsigned long delay_on, unsigned long delay_off) {} @@ -544,6 +590,12 @@ static inline void *led_get_trigger_data(struct led_classdev *led_cdev) return NULL; } +static inline enum led_brightness +led_trigger_get_brightness(const struct led_trigger *trigger) +{ + return LED_OFF; +} + #endif /* CONFIG_LEDS_TRIGGERS */ /* Trigger specific enum */ @@ -690,18 +742,4 @@ enum led_audio { NUM_AUDIO_LEDS }; -#if IS_ENABLED(CONFIG_LEDS_TRIGGER_AUDIO) -enum led_brightness ledtrig_audio_get(enum led_audio type); -void ledtrig_audio_set(enum led_audio type, enum led_brightness state); -#else -static inline enum led_brightness ledtrig_audio_get(enum led_audio type) -{ - return LED_OFF; -} -static inline void ledtrig_audio_set(enum led_audio type, - enum led_brightness state) -{ -} -#endif - #endif /* __LINUX_LEDS_H_INCLUDED */ diff --git a/include/linux/libata.h b/include/linux/libata.h index 324d792e7c78..17394098bee9 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -814,7 +814,6 @@ struct ata_port { /* Flags that change dynamically, protected by ap->lock */ unsigned int pflags; /* ATA_PFLAG_xxx */ unsigned int print_id; /* user visible unique port ID */ - unsigned int local_port_no; /* host local port num */ unsigned int port_no; /* 0 based port no. inside the host */ #ifdef CONFIG_ATA_SFF @@ -1069,7 +1068,7 @@ extern int sata_std_hardreset(struct ata_link *link, unsigned int *class, unsigned long deadline); extern void ata_std_postreset(struct ata_link *link, unsigned int *classes); -extern struct ata_host *ata_host_alloc(struct device *dev, int max_ports); +extern struct ata_host *ata_host_alloc(struct device *dev, int n_ports); extern struct ata_host *ata_host_alloc_pinfo(struct device *dev, const struct ata_port_info * const * ppi, int n_ports); extern void ata_host_get(struct ata_host *host); @@ -1082,7 +1081,6 @@ extern int ata_host_activate(struct ata_host *host, int irq, const struct scsi_host_template *sht); extern void ata_host_detach(struct ata_host *host); extern void ata_host_init(struct ata_host *, struct device *, struct ata_port_operations *); -extern int ata_scsi_detect(struct scsi_host_template *sht); extern int ata_scsi_ioctl(struct scsi_device *dev, unsigned int cmd, void __user *arg); #ifdef CONFIG_COMPAT @@ -1152,12 +1150,19 @@ extern int ata_std_bios_param(struct scsi_device *sdev, sector_t capacity, int geom[]); extern void ata_scsi_unlock_native_capacity(struct scsi_device *sdev); extern int ata_scsi_slave_alloc(struct scsi_device *sdev); -extern int ata_scsi_slave_config(struct scsi_device *sdev); +int ata_scsi_device_configure(struct scsi_device *sdev, + struct queue_limits *lim); extern void ata_scsi_slave_destroy(struct scsi_device *sdev); extern int ata_scsi_change_queue_depth(struct scsi_device *sdev, int queue_depth); extern int ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev, int queue_depth); +extern int ata_ncq_prio_supported(struct ata_port *ap, struct scsi_device *sdev, + bool *supported); +extern int ata_ncq_prio_enabled(struct ata_port *ap, struct scsi_device *sdev, + bool *enabled); +extern int ata_ncq_prio_enable(struct ata_port *ap, struct scsi_device *sdev, + bool enable); extern struct ata_device *ata_dev_pair(struct ata_device *adev); extern int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev); extern void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap); @@ -1239,12 +1244,13 @@ extern int sata_link_debounce(struct ata_link *link, extern int sata_link_scr_lpm(struct ata_link *link, enum ata_lpm_policy policy, bool spm_wakeup); extern int ata_slave_link_init(struct ata_port *ap); -extern struct ata_port *ata_sas_port_alloc(struct ata_host *, - struct ata_port_info *, struct Scsi_Host *); extern void ata_port_probe(struct ata_port *ap); -extern int ata_sas_tport_add(struct device *parent, struct ata_port *ap); -extern void ata_sas_tport_delete(struct ata_port *ap); -extern int ata_sas_slave_configure(struct scsi_device *, struct ata_port *); +extern struct ata_port *ata_port_alloc(struct ata_host *host); +extern void ata_port_free(struct ata_port *ap); +extern int ata_tport_add(struct device *parent, struct ata_port *ap); +extern void ata_tport_delete(struct ata_port *ap); +int ata_sas_device_configure(struct scsi_device *sdev, struct queue_limits *lim, + struct ata_port *ap); extern int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap); extern void ata_tf_to_fis(const struct ata_taskfile *tf, u8 pmp, int is_cmd, u8 *fis); @@ -1410,13 +1416,13 @@ extern const struct attribute_group *ata_common_sdev_groups[]; __ATA_BASE_SHT(drv_name), \ .can_queue = ATA_DEF_QUEUE, \ .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ - .slave_configure = ata_scsi_slave_config + .device_configure = ata_scsi_device_configure #define ATA_SUBBASE_SHT_QD(drv_name, drv_qd) \ __ATA_BASE_SHT(drv_name), \ .can_queue = drv_qd, \ .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ - .slave_configure = ata_scsi_slave_config + .device_configure = ata_scsi_device_configure #define ATA_BASE_SHT(drv_name) \ ATA_SUBBASE_SHT(drv_name), \ diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index 287f590ed56b..d94bfd9ac8cc 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -43,29 +43,10 @@ static inline int linkmode_andnot(unsigned long *dst, const unsigned long *src1, return bitmap_andnot(dst, src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static inline void linkmode_set_bit(int nr, volatile unsigned long *addr) -{ - __set_bit(nr, addr); -} - -static inline void linkmode_clear_bit(int nr, volatile unsigned long *addr) -{ - __clear_bit(nr, addr); -} - -static inline void linkmode_mod_bit(int nr, volatile unsigned long *addr, - int set) -{ - if (set) - linkmode_set_bit(nr, addr); - else - linkmode_clear_bit(nr, addr); -} - -static inline int linkmode_test_bit(int nr, const volatile unsigned long *addr) -{ - return test_bit(nr, addr); -} +#define linkmode_test_bit test_bit +#define linkmode_set_bit __set_bit +#define linkmode_clear_bit __clear_bit +#define linkmode_mod_bit __assign_bit static inline void linkmode_set_bit_array(const int *array, int array_size, unsigned long *addr) diff --git a/include/linux/linux_logo.h b/include/linux/linux_logo.h index d4d5b93efe84..e37699b7e839 100644 --- a/include/linux/linux_logo.h +++ b/include/linux/linux_logo.h @@ -10,9 +10,6 @@ * Copyright (C) 2001 Greg Banks <gnb@alphalink.com.au> * Copyright (C) 2001 Jan-Benedict Glaw <jbglaw@lug-owl.de> * Copyright (C) 2003 Geert Uytterhoeven <geert@linux-m68k.org> - * - * Serial_console ascii image can be any size, - * but should contain %s to display the version */ #include <linux/init.h> diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 792b67ceb631..5099a8ccd5f4 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -50,7 +50,7 @@ struct list_lru_node { struct list_lru { struct list_lru_node *node; -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG struct list_head list; int shrinker_id; bool memcg_aware; diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 9b9b38e89563..51a258c24ff5 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -18,9 +18,9 @@ #if IS_ENABLED(CONFIG_LIVEPATCH) /* task patch states */ -#define KLP_UNDEFINED -1 -#define KLP_UNPATCHED 0 -#define KLP_PATCHED 1 +#define KLP_TRANSITION_IDLE -1 +#define KLP_TRANSITION_UNPATCHED 0 +#define KLP_TRANSITION_PATCHED 1 /** * struct klp_func - function structure for live patching diff --git a/include/linux/local_lock.h b/include/linux/local_lock.h index e55010fa7329..091dc0b6bdfb 100644 --- a/include/linux/local_lock.h +++ b/include/linux/local_lock.h @@ -51,4 +51,25 @@ #define local_unlock_irqrestore(lock, flags) \ __local_unlock_irqrestore(lock, flags) +DEFINE_GUARD(local_lock, local_lock_t __percpu*, + local_lock(_T), + local_unlock(_T)) +DEFINE_GUARD(local_lock_irq, local_lock_t __percpu*, + local_lock_irq(_T), + local_unlock_irq(_T)) +DEFINE_LOCK_GUARD_1(local_lock_irqsave, local_lock_t __percpu, + local_lock_irqsave(_T->lock, _T->flags), + local_unlock_irqrestore(_T->lock, _T->flags), + unsigned long flags) + +#define local_lock_nested_bh(_lock) \ + __local_lock_nested_bh(_lock) + +#define local_unlock_nested_bh(_lock) \ + __local_unlock_nested_bh(_lock) + +DEFINE_GUARD(local_lock_nested_bh, local_lock_t __percpu*, + local_lock_nested_bh(_T), + local_unlock_nested_bh(_T)) + #endif diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index 975e33b793a7..8dd71fbbb6d2 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -62,6 +62,17 @@ do { \ local_lock_debug_init(lock); \ } while (0) +#define __spinlock_nested_bh_init(lock) \ +do { \ + static struct lock_class_key __key; \ + \ + debug_check_no_locks_freed((void *)lock, sizeof(*lock));\ + lockdep_init_map_type(&(lock)->dep_map, #lock, &__key, \ + 0, LD_WAIT_CONFIG, LD_WAIT_INV, \ + LD_LOCK_NORMAL); \ + local_lock_debug_init(lock); \ +} while (0) + #define __local_lock(lock) \ do { \ preempt_disable(); \ @@ -98,6 +109,15 @@ do { \ local_irq_restore(flags); \ } while (0) +#define __local_lock_nested_bh(lock) \ + do { \ + lockdep_assert_in_softirq(); \ + local_lock_acquire(this_cpu_ptr(lock)); \ + } while (0) + +#define __local_unlock_nested_bh(lock) \ + local_lock_release(this_cpu_ptr(lock)) + #else /* !CONFIG_PREEMPT_RT */ /* @@ -138,4 +158,15 @@ typedef spinlock_t local_lock_t; #define __local_unlock_irqrestore(lock, flags) __local_unlock(lock) +#define __local_lock_nested_bh(lock) \ +do { \ + lockdep_assert_in_softirq_func(); \ + spin_lock(this_cpu_ptr(lock)); \ +} while (0) + +#define __local_unlock_nested_bh(lock) \ +do { \ + spin_unlock(this_cpu_ptr((lock))); \ +} while (0) + #endif /* CONFIG_PREEMPT_RT */ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 08b0d1d9d78b..217f7abf2cbf 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -178,9 +178,27 @@ static inline void lockdep_init_map(struct lockdep_map *lock, const char *name, (lock)->dep_map.wait_type_outer, \ (lock)->dep_map.lock_type) +/** + * lockdep_set_novalidate_class: disable checking of lock ordering on a given + * lock + * @lock: Lock to mark + * + * Lockdep will still record that this lock has been taken, and print held + * instances when dumping locks + */ #define lockdep_set_novalidate_class(lock) \ lockdep_set_class_and_name(lock, &__lockdep_no_validate__, #lock) +/** + * lockdep_set_notrack_class: disable lockdep tracking of a given lock entirely + * @lock: Lock to mark + * + * Bigger hammer than lockdep_set_novalidate_class: so far just for bcachefs, + * which takes more locks than lockdep is able to track (48). + */ +#define lockdep_set_notrack_class(lock) \ + lockdep_set_class_and_name(lock, &__lockdep_no_track__, #lock) + /* * Compare locking classes */ @@ -338,6 +356,7 @@ static inline void lockdep_set_selftest_task(struct task_struct *task) #define lockdep_set_subclass(lock, sub) do { } while (0) #define lockdep_set_novalidate_class(lock) do { } while (0) +#define lockdep_set_notrack_class(lock) do { } while (0) /* * We don't define lockdep_match_class() and lockdep_match_key() for !LOCKDEP @@ -600,6 +619,8 @@ do { \ (!in_softirq() || in_irq() || in_nmi())); \ } while (0) +extern void lockdep_assert_in_softirq_func(void); + #else # define might_lock(lock) do { } while (0) # define might_lock_read(lock) do { } while (0) @@ -613,6 +634,7 @@ do { \ # define lockdep_assert_preemption_enabled() do { } while (0) # define lockdep_assert_preemption_disabled() do { } while (0) # define lockdep_assert_in_softirq() do { } while (0) +# define lockdep_assert_in_softirq_func() do { } while (0) #endif #ifdef CONFIG_PROVE_RAW_LOCK_NESTING diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h index 70d30d40ea4a..9f361d3ab9d9 100644 --- a/include/linux/lockdep_types.h +++ b/include/linux/lockdep_types.h @@ -80,6 +80,7 @@ struct lock_class_key { }; extern struct lock_class_key __lockdep_no_validate__; +extern struct lock_class_key __lockdep_no_track__; struct lock_trace; diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 334e00efbde4..855db460e08b 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -144,6 +144,7 @@ LSM_HOOK(int, 0, inode_setattr, struct mnt_idmap *idmap, struct dentry *dentry, LSM_HOOK(void, LSM_RET_VOID, inode_post_setattr, struct mnt_idmap *idmap, struct dentry *dentry, int ia_valid) LSM_HOOK(int, 0, inode_getattr, const struct path *path) +LSM_HOOK(int, 0, inode_xattr_skipcap, const char *name) LSM_HOOK(int, 0, inode_setxattr, struct mnt_idmap *idmap, struct dentry *dentry, const char *name, const void *value, size_t size, int flags) @@ -176,7 +177,8 @@ LSM_HOOK(int, 0, inode_listsecurity, struct inode *inode, char *buffer, size_t buffer_size) LSM_HOOK(void, LSM_RET_VOID, inode_getsecid, struct inode *inode, u32 *secid) LSM_HOOK(int, 0, inode_copy_up, struct dentry *src, struct cred **new) -LSM_HOOK(int, -EOPNOTSUPP, inode_copy_up_xattr, const char *name) +LSM_HOOK(int, -EOPNOTSUPP, inode_copy_up_xattr, struct dentry *src, + const char *name) LSM_HOOK(int, 0, kernfs_init_security, struct kernfs_node *kn_dir, struct kernfs_node *kn) LSM_HOOK(int, 0, file_permission, struct file *file, int mask) @@ -412,7 +414,7 @@ LSM_HOOK(void, LSM_RET_VOID, key_post_create_or_update, struct key *keyring, #ifdef CONFIG_AUDIT LSM_HOOK(int, 0, audit_rule_init, u32 field, u32 op, char *rulestr, - void **lsmrule) + void **lsmrule, gfp_t gfp) LSM_HOOK(int, 0, audit_rule_known, struct audit_krule *krule) LSM_HOOK(int, 0, audit_rule_match, u32 secid, u32 field, u32 op, void *lsmrule) LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule) diff --git a/include/linux/maple.h b/include/linux/maple.h index 9aae44efcfd4..3be4e567473c 100644 --- a/include/linux/maple.h +++ b/include/linux/maple.h @@ -97,7 +97,7 @@ int maple_add_packet(struct maple_device *mdev, u32 function, void maple_clear_dev(struct maple_device *mdev); #define to_maple_dev(n) container_of(n, struct maple_device, dev) -#define to_maple_driver(n) container_of(n, struct maple_driver, drv) +#define to_maple_driver(n) container_of_const(n, struct maple_driver, drv) #define maple_get_drvdata(d) dev_get_drvdata(&(d)->dev) #define maple_set_drvdata(d,p) dev_set_drvdata(&(d)->dev, (p)) diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index 693eba9869e4..b1fbe4118414 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -7,6 +7,7 @@ /* Known PHY IDs */ #define MARVELL_PHY_ID_88E1101 0x01410c60 +#define MARVELL_PHY_ID_88E3082 0x01410c80 #define MARVELL_PHY_ID_88E1112 0x01410c90 #define MARVELL_PHY_ID_88E1111 0x01410cc0 #define MARVELL_PHY_ID_88E1118 0x01410e10 @@ -31,6 +32,8 @@ /* Marvel 88E1111 in Finisar SFP module with modified PHY ID */ #define MARVELL_PHY_ID_88E1111_FINISAR 0x01ff0cc0 +/* ID from 88E6020, assumed to be the same for the whole 6250 family */ +#define MARVELL_PHY_ID_88E6250_FAMILY 0x01410db0 /* These Ethernet switch families contain embedded PHYs, but they do * not have a model ID. So the switch driver traps reads to the ID2 * register and returns the switch family ID diff --git a/include/linux/math.h b/include/linux/math.h index dd4152711de7..f5f18dc3616b 100644 --- a/include/linux/math.h +++ b/include/linux/math.h @@ -112,6 +112,8 @@ struct type##_fract { \ __##type numerator; \ __##type denominator; \ }; +__STRUCT_FRACT(s8) +__STRUCT_FRACT(u8) __STRUCT_FRACT(s16) __STRUCT_FRACT(u16) __STRUCT_FRACT(s32) diff --git a/include/linux/math64.h b/include/linux/math64.h index bf74478926d4..6aaccc1626ab 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -4,8 +4,8 @@ #include <linux/types.h> #include <linux/math.h> -#include <vdso/math64.h> #include <asm/div64.h> +#include <vdso/math64.h> #if BITS_PER_LONG == 64 @@ -179,16 +179,12 @@ static __always_inline u64 mul_u64_u64_shr(u64 a, u64 mul, unsigned int shift) #ifndef mul_u64_u32_shr static __always_inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift) { - u32 ah, al; + u32 ah = a >> 32, al = a; u64 ret; - al = a; - ah = a >> 32; - ret = mul_u32_u32(al, mul) >> shift; if (ah) ret += mul_u32_u32(ah, mul) << (32 - shift); - return ret; } #endif /* mul_u64_u32_shr */ @@ -302,6 +298,19 @@ u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div); ({ u64 _tmp = (d); div64_u64((ll) + _tmp - 1, _tmp); }) /** + * DIV_U64_ROUND_UP - unsigned 64bit divide with 32bit divisor rounded up + * @ll: unsigned 64bit dividend + * @d: unsigned 32bit divisor + * + * Divide unsigned 64bit dividend by unsigned 32bit divisor + * and round up. + * + * Return: dividend / divisor rounded up + */ +#define DIV_U64_ROUND_UP(ll, d) \ + ({ u32 _tmp = (d); div_u64((ll) + _tmp - 1, _tmp); }) + +/** * DIV64_U64_ROUND_CLOSEST - unsigned 64bit divide with 64bit divisor rounded to nearest integer * @dividend: unsigned 64bit dividend * @divisor: unsigned 64bit divisor @@ -346,4 +355,19 @@ u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div); div_s64((__x - (__d / 2)), __d); \ } \ ) + +/** + * roundup_u64 - Round up a 64bit value to the next specified 32bit multiple + * @x: the value to up + * @y: 32bit multiple to round up to + * + * Rounds @x to the next multiple of @y. For 32bit @x values, see roundup and + * the faster round_up() for powers of 2. + * + * Return: rounded up value. + */ +static inline u64 roundup_u64(u64 x, u32 y) +{ + return DIV_U64_ROUND_UP(x, y) * y; +} #endif /* _LINUX_MATH64_H */ diff --git a/include/linux/mcb.h b/include/linux/mcb.h index 0b971b24a804..4ab2691f51a6 100644 --- a/include/linux/mcb.h +++ b/include/linux/mcb.h @@ -94,10 +94,7 @@ struct mcb_driver { void (*shutdown)(struct mcb_device *mdev); }; -static inline struct mcb_driver *to_mcb_driver(struct device_driver *drv) -{ - return container_of(drv, struct mcb_driver, driver); -} +#define to_mcb_driver(__drv) container_of_const(__drv, struct mcb_driver, driver) static inline void *mcb_get_drvdata(struct mcb_device *dev) { diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 68f8d2e970d4..efeca5bd7600 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -31,7 +31,7 @@ struct mdio_device { struct mii_bus *bus; char modalias[MDIO_NAME_SIZE]; - int (*bus_match)(struct device *dev, struct device_driver *drv); + int (*bus_match)(struct device *dev, const struct device_driver *drv); void (*device_free)(struct mdio_device *mdiodev); void (*device_remove)(struct mdio_device *mdiodev); @@ -57,11 +57,8 @@ struct mdio_driver_common { }; #define MDIO_DEVICE_FLAG_PHY 1 -static inline struct mdio_driver_common * -to_mdio_common_driver(const struct device_driver *driver) -{ - return container_of(driver, struct mdio_driver_common, driver); -} +#define to_mdio_common_driver(__drv_c) container_of_const(__drv_c, struct mdio_driver_common, \ + driver) /* struct mdio_driver: Generic MDIO driver */ struct mdio_driver { @@ -80,12 +77,8 @@ struct mdio_driver { void (*shutdown)(struct mdio_device *mdiodev); }; -static inline struct mdio_driver * -to_mdio_driver(const struct device_driver *driver) -{ - return container_of(to_mdio_common_driver(driver), struct mdio_driver, - mdiodrv); -} +#define to_mdio_driver(__drv_m) container_of_const(to_mdio_common_driver(__drv_m), \ + struct mdio_driver, mdiodrv) /* device driver data */ static inline void mdiodev_set_drvdata(struct mdio_device *mdio, void *data) @@ -105,7 +98,7 @@ void mdio_device_remove(struct mdio_device *mdiodev); void mdio_device_reset(struct mdio_device *mdiodev, int value); int mdio_driver_register(struct mdio_driver *drv); void mdio_driver_unregister(struct mdio_driver *drv); -int mdio_device_bus_match(struct device *dev, struct device_driver *drv); +int mdio_device_bus_match(struct device *dev, const struct device_driver *drv); static inline void mdio_device_get(struct mdio_device *mdiodev) { diff --git a/include/linux/memblock.h b/include/linux/memblock.h index e2082240586d..fc4d75c6cec3 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -299,25 +299,6 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, unsigned long *out_spfn, unsigned long *out_epfn); -/** - * for_each_free_mem_pfn_range_in_zone - iterate through zone specific free - * memblock areas - * @i: u64 used as loop variable - * @zone: zone in which all of the memory blocks reside - * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL - * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL - * - * Walks over free (memory && !reserved) areas of memblock in a specific - * zone. Available once memblock and an empty zone is initialized. The main - * assumption is that the zone start, end, and pgdat have been associated. - * This way we can use the zone to determine NUMA node, and if a given part - * of the memblock is valid for the zone. - */ -#define for_each_free_mem_pfn_range_in_zone(i, zone, p_start, p_end) \ - for (i = 0, \ - __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end); \ - i != U64_MAX; \ - __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end)) /** * for_each_free_mem_pfn_range_in_zone_from - iterate through zone specific @@ -335,8 +316,6 @@ void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, for (; i != U64_MAX; \ __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end)) -int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask); - #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */ /** @@ -565,7 +544,7 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo } /** - * for_each_mem_region - itereate over memory regions + * for_each_mem_region - iterate over memory regions * @region: loop variable */ #define for_each_mem_region(region) \ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 394fd0a887ae..0e5bf25d324f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -69,20 +69,10 @@ struct mem_cgroup_id { refcount_t ref; }; -/* - * Per memcg event counter is incremented at every pagein/pageout. With THP, - * it will be incremented by the number of pages. This counter is used - * to trigger some periodic events. This is straightforward and better - * than using jiffies etc. to handle periodic memcg event. - */ -enum mem_cgroup_events_target { - MEM_CGROUP_TARGET_THRESH, - MEM_CGROUP_TARGET_SOFTLIMIT, - MEM_CGROUP_NTARGETS, -}; - struct memcg_vmstats_percpu; struct memcg_vmstats; +struct lruvec_stats_percpu; +struct lruvec_stats; struct mem_cgroup_reclaim_iter { struct mem_cgroup *position; @@ -90,46 +80,38 @@ struct mem_cgroup_reclaim_iter { unsigned int generation; }; -struct lruvec_stats_percpu { - /* Local (CPU and cgroup) state */ - long state[NR_VM_NODE_STAT_ITEMS]; - - /* Delta calculation for lockless upward propagation */ - long state_prev[NR_VM_NODE_STAT_ITEMS]; -}; - -struct lruvec_stats { - /* Aggregated (CPU and subtree) state */ - long state[NR_VM_NODE_STAT_ITEMS]; - - /* Non-hierarchical (CPU aggregated) state */ - long state_local[NR_VM_NODE_STAT_ITEMS]; - - /* Pending child counts during tree propagation */ - long state_pending[NR_VM_NODE_STAT_ITEMS]; -}; - /* * per-node information in memory controller. */ struct mem_cgroup_per_node { - struct lruvec lruvec; + /* Keep the read-only fields at the start */ + struct mem_cgroup *memcg; /* Back pointer, we cannot */ + /* use container_of */ struct lruvec_stats_percpu __percpu *lruvec_stats_percpu; - struct lruvec_stats lruvec_stats; - - unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; - - struct mem_cgroup_reclaim_iter iter; - + struct lruvec_stats *lruvec_stats; struct shrinker_info __rcu *shrinker_info; +#ifdef CONFIG_MEMCG_V1 + /* + * Memcg-v1 only stuff in middle as buffer between read mostly fields + * and update often fields to avoid false sharing. If v1 stuff is + * not present, an explicit padding is needed. + */ + struct rb_node tree_node; /* RB tree node */ unsigned long usage_in_excess;/* Set to the value by which */ /* the soft limit is exceeded*/ bool on_tree; - struct mem_cgroup *memcg; /* Back pointer, we cannot */ - /* use container_of */ +#else + CACHELINE_PADDING(_pad1_); +#endif + + /* Fields which get updated often at the end. */ + struct lruvec lruvec; + CACHELINE_PADDING(_pad2_); + unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; + struct mem_cgroup_reclaim_iter iter; }; struct mem_cgroup_threshold { @@ -211,14 +193,10 @@ struct mem_cgroup { struct page_counter memsw; /* v1 only */ }; - /* Legacy consumer-oriented counters */ - struct page_counter kmem; /* v1 only */ - struct page_counter tcpmem; /* v1 only */ - /* Range enforcement for interrupt charges */ struct work_struct high_work; -#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) +#ifdef CONFIG_ZSWAP unsigned long zswap_max; /* @@ -228,8 +206,6 @@ struct mem_cgroup { bool zswap_writeback; #endif - unsigned long soft_limit; - /* vmpressure notifications */ struct vmpressure vmpressure; @@ -238,13 +214,7 @@ struct mem_cgroup { */ bool oom_group; - /* protected by memcg_oom_lock */ - bool oom_lock; - int under_oom; - - int swappiness; - /* OOM-Killer disable */ - int oom_kill_disable; + int swappiness; /* memory.events and memory.events.local */ struct cgroup_file events_file; @@ -253,29 +223,6 @@ struct mem_cgroup { /* handle for "memory.swap.events" */ struct cgroup_file swap_events_file; - /* protect arrays of thresholds */ - struct mutex thresholds_lock; - - /* thresholds for memory usage. RCU-protected */ - struct mem_cgroup_thresholds thresholds; - - /* thresholds for mem+swap usage. RCU-protected */ - struct mem_cgroup_thresholds memsw_thresholds; - - /* For oom notifier event fd */ - struct list_head oom_notify; - - /* - * Should we move charges of a task when a task is moved into this - * mem_cgroup ? And what type of charges should we move ? - */ - unsigned long move_charge_at_immigrate; - /* taken only while moving_account > 0 */ - spinlock_t move_lock; - unsigned long move_lock_flags; - - CACHELINE_PADDING(_pad1_); - /* memory.stat */ struct memcg_vmstats *vmstats; @@ -290,11 +237,6 @@ struct mem_cgroup { */ unsigned long socket_pressure; - /* Legacy tcp memory accounting */ - bool tcpmem_active; - int tcpmem_pressure; - -#ifdef CONFIG_MEMCG_KMEM int kmemcg_id; /* * memcg->objcg is wiped out as a part of the objcg repaprenting @@ -305,15 +247,6 @@ struct mem_cgroup { struct obj_cgroup *orig_objcg; /* list of inherited objcgs, protected by objcg_lock */ struct list_head objcg_list; -#endif - - CACHELINE_PADDING(_pad2_); - - /* - * set > 0 if pages under this cgroup are moving to other cgroup. - */ - atomic_t moving_account; - struct task_struct *move_lock_task; struct memcg_vmstats_percpu __percpu *vmstats_percpu; @@ -323,10 +256,6 @@ struct mem_cgroup { struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT]; #endif - /* List of events which userspace want to receive */ - struct list_head event_list; - spinlock_t event_list_lock; - #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split deferred_split_queue; #endif @@ -336,6 +265,56 @@ struct mem_cgroup { struct lru_gen_mm_list mm_list; #endif +#ifdef CONFIG_MEMCG_V1 + /* Legacy consumer-oriented counters */ + struct page_counter kmem; /* v1 only */ + struct page_counter tcpmem; /* v1 only */ + + unsigned long soft_limit; + + /* protected by memcg_oom_lock */ + bool oom_lock; + int under_oom; + + /* OOM-Killer disable */ + int oom_kill_disable; + + /* protect arrays of thresholds */ + struct mutex thresholds_lock; + + /* thresholds for memory usage. RCU-protected */ + struct mem_cgroup_thresholds thresholds; + + /* thresholds for mem+swap usage. RCU-protected */ + struct mem_cgroup_thresholds memsw_thresholds; + + /* For oom notifier event fd */ + struct list_head oom_notify; + + /* + * Should we move charges of a task when a task is moved into this + * mem_cgroup ? And what type of charges should we move ? + */ + unsigned long move_charge_at_immigrate; + /* taken only while moving_account > 0 */ + spinlock_t move_lock; + unsigned long move_lock_flags; + + /* Legacy tcp memory accounting */ + bool tcpmem_active; + int tcpmem_pressure; + + /* + * set > 0 if pages under this cgroup are moving to other cgroup. + */ + atomic_t moving_account; + struct task_struct *move_lock_task; + + /* List of events which userspace want to receive */ + struct list_head event_list; + spinlock_t event_list_lock; +#endif /* CONFIG_MEMCG_V1 */ + struct mem_cgroup_per_node *nodeinfo[]; }; @@ -349,15 +328,32 @@ struct mem_cgroup { extern struct mem_cgroup *root_mem_cgroup; enum page_memcg_data_flags { - /* page->memcg_data is a pointer to an objcgs vector */ - MEMCG_DATA_OBJCGS = (1UL << 0), + /* page->memcg_data is a pointer to an slabobj_ext vector */ + MEMCG_DATA_OBJEXTS = (1UL << 0), /* page has been accounted as a non-slab kernel page */ MEMCG_DATA_KMEM = (1UL << 1), /* the next bit after the last actual flag */ __NR_MEMCG_DATA_FLAGS = (1UL << 2), }; -#define MEMCG_DATA_FLAGS_MASK (__NR_MEMCG_DATA_FLAGS - 1) +#define __FIRST_OBJEXT_FLAG __NR_MEMCG_DATA_FLAGS + +#else /* CONFIG_MEMCG */ + +#define __FIRST_OBJEXT_FLAG (1UL << 0) + +#endif /* CONFIG_MEMCG */ + +enum objext_flags { + /* slabobj_ext vector failed to allocate */ + OBJEXTS_ALLOC_FAIL = __FIRST_OBJEXT_FLAG, + /* the next bit after the last actual flag */ + __NR_OBJEXTS_FLAGS = (__FIRST_OBJEXT_FLAG << 1), +}; + +#define OBJEXTS_FLAGS_MASK (__NR_OBJEXTS_FLAGS - 1) + +#ifdef CONFIG_MEMCG static inline bool folio_memcg_kmem(struct folio *folio); @@ -388,10 +384,10 @@ static inline struct mem_cgroup *__folio_memcg(struct folio *folio) unsigned long memcg_data = folio->memcg_data; VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); - VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio); + VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJEXTS, folio); VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_KMEM, folio); - return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } /* @@ -409,10 +405,10 @@ static inline struct obj_cgroup *__folio_objcg(struct folio *folio) unsigned long memcg_data = folio->memcg_data; VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); - VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio); + VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJEXTS, folio); VM_BUG_ON_FOLIO(!(memcg_data & MEMCG_DATA_KMEM), folio); - return (struct obj_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + return (struct obj_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } /* @@ -443,11 +439,6 @@ static inline struct mem_cgroup *folio_memcg(struct folio *folio) return __folio_memcg(folio); } -static inline struct mem_cgroup *page_memcg(struct page *page) -{ - return folio_memcg(page_folio(page)); -} - /** * folio_memcg_rcu - Locklessly get the memory cgroup associated with a folio. * @folio: Pointer to the folio. @@ -469,11 +460,11 @@ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) if (memcg_data & MEMCG_DATA_KMEM) { struct obj_cgroup *objcg; - objcg = (void *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + objcg = (void *)(memcg_data & ~OBJEXTS_FLAGS_MASK); return obj_cgroup_memcg(objcg); } - return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } /* @@ -506,17 +497,17 @@ static inline struct mem_cgroup *folio_memcg_check(struct folio *folio) */ unsigned long memcg_data = READ_ONCE(folio->memcg_data); - if (memcg_data & MEMCG_DATA_OBJCGS) + if (memcg_data & MEMCG_DATA_OBJEXTS) return NULL; if (memcg_data & MEMCG_DATA_KMEM) { struct obj_cgroup *objcg; - objcg = (void *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + objcg = (void *)(memcg_data & ~OBJEXTS_FLAGS_MASK); return obj_cgroup_memcg(objcg); } - return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); + return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } static inline struct mem_cgroup *page_memcg_check(struct page *page) @@ -540,7 +531,6 @@ retry: return memcg; } -#ifdef CONFIG_MEMCG_KMEM /* * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set. * @folio: Pointer to the folio. @@ -552,19 +542,10 @@ retry: static inline bool folio_memcg_kmem(struct folio *folio) { VM_BUG_ON_PGFLAGS(PageTail(&folio->page), &folio->page); - VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJCGS, folio); + VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJEXTS, folio); return folio->memcg_data & MEMCG_DATA_KMEM; } - -#else -static inline bool folio_memcg_kmem(struct folio *folio) -{ - return false; -} - -#endif - static inline bool PageMemcgKmem(struct page *page) { return folio_memcg_kmem(page_folio(page)); @@ -818,7 +799,8 @@ static inline void obj_cgroup_get_many(struct obj_cgroup *objcg, static inline void obj_cgroup_put(struct obj_cgroup *objcg) { - percpu_ref_put(&objcg->refcnt); + if (objcg) + percpu_ref_put(&objcg->refcnt); } static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg) @@ -948,53 +930,16 @@ void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg); -static inline void mem_cgroup_enter_user_fault(void) -{ - WARN_ON(current->in_user_fault); - current->in_user_fault = 1; -} - -static inline void mem_cgroup_exit_user_fault(void) -{ - WARN_ON(!current->in_user_fault); - current->in_user_fault = 0; -} - -static inline bool task_in_memcg_oom(struct task_struct *p) -{ - return p->memcg_in_oom; -} - -bool mem_cgroup_oom_synchronize(bool wait); struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, struct mem_cgroup *oom_domain); void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); -void folio_memcg_lock(struct folio *folio); -void folio_memcg_unlock(struct folio *folio); - -void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val); - -/* try to stablize folio_memcg() for all the pages in a memcg */ -static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) -{ - rcu_read_lock(); - - if (mem_cgroup_disabled() || !atomic_read(&memcg->moving_account)) - return true; - - rcu_read_unlock(); - return false; -} - -static inline void mem_cgroup_unlock_pages(void) -{ - rcu_read_unlock(); -} +void __mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, + int val); /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void mod_memcg_state(struct mem_cgroup *memcg, - int idx, int val) + enum memcg_stat_item idx, int val) { unsigned long flags; @@ -1004,7 +949,7 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, } static inline void mod_memcg_page_state(struct page *page, - int idx, int val) + enum memcg_stat_item idx, int val) { struct mem_cgroup *memcg; @@ -1012,55 +957,20 @@ static inline void mod_memcg_page_state(struct page *page, return; rcu_read_lock(); - memcg = page_memcg(page); + memcg = folio_memcg(page_folio(page)); if (memcg) mod_memcg_state(memcg, idx, val); rcu_read_unlock(); } unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx); - -static inline unsigned long lruvec_page_state(struct lruvec *lruvec, - enum node_stat_item idx) -{ - struct mem_cgroup_per_node *pn; - long x; - - if (mem_cgroup_disabled()) - return node_page_state(lruvec_pgdat(lruvec), idx); - - pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - x = READ_ONCE(pn->lruvec_stats.state[idx]); -#ifdef CONFIG_SMP - if (x < 0) - x = 0; -#endif - return x; -} - -static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, - enum node_stat_item idx) -{ - struct mem_cgroup_per_node *pn; - long x = 0; - - if (mem_cgroup_disabled()) - return node_page_state(lruvec_pgdat(lruvec), idx); - - pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - x = READ_ONCE(pn->lruvec_stats.state_local[idx]); -#ifdef CONFIG_SMP - if (x < 0) - x = 0; -#endif - return x; -} +unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx); +unsigned long lruvec_page_state_local(struct lruvec *lruvec, + enum node_stat_item idx); void mem_cgroup_flush_stats(struct mem_cgroup *memcg); void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg); -void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, - int val); void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val); static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, @@ -1073,16 +983,6 @@ static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, local_irq_restore(flags); } -static inline void mod_memcg_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx, int val) -{ - unsigned long flags; - - local_irq_save(flags); - __mod_memcg_lruvec_state(lruvec, idx, val); - local_irq_restore(flags); -} - void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count); @@ -1163,10 +1063,6 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm, void split_page_memcg(struct page *head, int old_order, int new_order); -unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, - gfp_t gfp_mask, - unsigned long *total_scanned); - #else /* CONFIG_MEMCG */ #define MEM_CGROUP_ID_SHIFT 0 @@ -1176,11 +1072,6 @@ static inline struct mem_cgroup *folio_memcg(struct folio *folio) return NULL; } -static inline struct mem_cgroup *page_memcg(struct page *page) -{ - return NULL; -} - static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) { WARN_ON_ONCE(!rcu_read_lock_held()); @@ -1482,48 +1373,10 @@ mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) { } -static inline void folio_memcg_lock(struct folio *folio) -{ -} - -static inline void folio_memcg_unlock(struct folio *folio) -{ -} - -static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) -{ - /* to match folio_memcg_rcu() */ - rcu_read_lock(); - return true; -} - -static inline void mem_cgroup_unlock_pages(void) -{ - rcu_read_unlock(); -} - static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask) { } -static inline void mem_cgroup_enter_user_fault(void) -{ -} - -static inline void mem_cgroup_exit_user_fault(void) -{ -} - -static inline bool task_in_memcg_oom(struct task_struct *p) -{ - return false; -} - -static inline bool mem_cgroup_oom_synchronize(bool wait) -{ - return false; -} - static inline struct mem_cgroup *mem_cgroup_get_oom_group( struct task_struct *victim, struct mem_cgroup *oom_domain) { @@ -1535,19 +1388,19 @@ static inline void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) } static inline void __mod_memcg_state(struct mem_cgroup *memcg, - int idx, + enum memcg_stat_item idx, int nr) { } static inline void mod_memcg_state(struct mem_cgroup *memcg, - int idx, + enum memcg_stat_item idx, int nr) { } static inline void mod_memcg_page_state(struct page *page, - int idx, int val) + enum memcg_stat_item idx, int val) { } @@ -1576,11 +1429,6 @@ static inline void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg) { } -static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx, int val) -{ -} - static inline void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) { @@ -1622,16 +1470,21 @@ void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) static inline void split_page_memcg(struct page *head, int old_order, int new_order) { } - -static inline -unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, - gfp_t gfp_mask, - unsigned long *total_scanned) -{ - return 0; -} #endif /* CONFIG_MEMCG */ +/* + * Extended information for slab objects stored as an array in page->memcg_data + * if MEMCG_DATA_OBJEXTS is set. + */ +struct slabobj_ext { +#ifdef CONFIG_MEMCG + struct obj_cgroup *objcg; +#endif +#ifdef CONFIG_MEM_ALLOC_PROFILING + union codetag_ref ref; +#endif +} __aligned(8); + static inline void __inc_lruvec_kmem_state(void *p, enum node_stat_item idx) { __mod_lruvec_kmem_state(p, idx, 1); @@ -1671,7 +1524,7 @@ static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec, spin_unlock_irqrestore(&lruvec->lru_lock, flags); } -/* Test requires a stable page->memcg binding, see page_memcg() */ +/* Test requires a stable folio->memcg binding, see folio_memcg() */ static inline bool folio_matches_lruvec(struct folio *folio, struct lruvec *lruvec) { @@ -1769,8 +1622,10 @@ void mem_cgroup_sk_alloc(struct sock *sk); void mem_cgroup_sk_free(struct sock *sk); static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { +#ifdef CONFIG_MEMCG_V1 if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) return !!memcg->tcpmem_pressure; +#endif /* CONFIG_MEMCG_V1 */ do { if (time_before(jiffies, READ_ONCE(memcg->socket_pressure))) return true; @@ -1797,7 +1652,7 @@ static inline void set_shrinker_bit(struct mem_cgroup *memcg, } #endif -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG bool mem_cgroup_kmem_disabled(void); int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); @@ -1940,9 +1795,9 @@ static inline void count_objcg_event(struct obj_cgroup *objcg, { } -#endif /* CONFIG_MEMCG_KMEM */ +#endif /* CONFIG_MEMCG */ -#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) +#if defined(CONFIG_MEMCG) && defined(CONFIG_ZSWAP) bool obj_cgroup_may_zswap(struct obj_cgroup *objcg); void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size); void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size); @@ -1967,4 +1822,100 @@ static inline bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg) } #endif + +/* Cgroup v1-related declarations */ + +#ifdef CONFIG_MEMCG_V1 +unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order, + gfp_t gfp_mask, + unsigned long *total_scanned); + +bool mem_cgroup_oom_synchronize(bool wait); + +static inline bool task_in_memcg_oom(struct task_struct *p) +{ + return p->memcg_in_oom; +} + +void folio_memcg_lock(struct folio *folio); +void folio_memcg_unlock(struct folio *folio); + +/* try to stablize folio_memcg() for all the pages in a memcg */ +static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) +{ + rcu_read_lock(); + + if (mem_cgroup_disabled() || !atomic_read(&memcg->moving_account)) + return true; + + rcu_read_unlock(); + return false; +} + +static inline void mem_cgroup_unlock_pages(void) +{ + rcu_read_unlock(); +} + +static inline void mem_cgroup_enter_user_fault(void) +{ + WARN_ON(current->in_user_fault); + current->in_user_fault = 1; +} + +static inline void mem_cgroup_exit_user_fault(void) +{ + WARN_ON(!current->in_user_fault); + current->in_user_fault = 0; +} + +#else /* CONFIG_MEMCG_V1 */ +static inline +unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order, + gfp_t gfp_mask, + unsigned long *total_scanned) +{ + return 0; +} + +static inline void folio_memcg_lock(struct folio *folio) +{ +} + +static inline void folio_memcg_unlock(struct folio *folio) +{ +} + +static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg) +{ + /* to match folio_memcg_rcu() */ + rcu_read_lock(); + return true; +} + +static inline void mem_cgroup_unlock_pages(void) +{ + rcu_read_unlock(); +} + +static inline bool task_in_memcg_oom(struct task_struct *p) +{ + return false; +} + +static inline bool mem_cgroup_oom_synchronize(bool wait) +{ + return false; +} + +static inline void mem_cgroup_enter_user_fault(void) +{ +} + +static inline void mem_cgroup_exit_user_fault(void) +{ +} + +#endif /* CONFIG_MEMCG_V1 */ + #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/linux/memfd.h b/include/linux/memfd.h index e7abf6fa4c52..3f2cf339ceaf 100644 --- a/include/linux/memfd.h +++ b/include/linux/memfd.h @@ -6,11 +6,16 @@ #ifdef CONFIG_MEMFD_CREATE extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg); +struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx); #else static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a) { return -EINVAL; } +static inline struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx) +{ + return ERR_PTR(-EINVAL); +} #endif #endif /* __LINUX_MEMFD_H */ diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index 69e781900082..0dc0cf2863e2 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -38,6 +38,7 @@ struct access_coordinate; #ifdef CONFIG_NUMA extern bool numa_demotion_enabled; extern struct memory_dev_type *default_dram_type; +extern nodemask_t default_dram_nodes; struct memory_dev_type *alloc_memory_type(int adistance); void put_memory_type(struct memory_dev_type *memtype); void init_node_memory_type(int node, struct memory_dev_type *default_type); @@ -48,6 +49,9 @@ int mt_calc_adistance(int node, int *adist); int mt_set_default_dram_perf(int nid, struct access_coordinate *perf, const char *source); int mt_perf_to_adistance(struct access_coordinate *perf, int *adist); +struct memory_dev_type *mt_find_alloc_memory_type(int adist, + struct list_head *memory_types); +void mt_put_memory_types(struct list_head *memory_types); #ifdef CONFIG_MIGRATION int next_demotion_node(int node); void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets); @@ -73,6 +77,7 @@ static inline bool node_is_toptier(int node) #define numa_demotion_enabled false #define default_dram_type NULL +#define default_dram_nodes NODE_MASK_NONE /* * CONFIG_NUMA implementation returns non NULL error. */ @@ -136,5 +141,15 @@ static inline int mt_perf_to_adistance(struct access_coordinate *perf, int *adis { return -EIO; } + +static inline struct memory_dev_type *mt_find_alloc_memory_type(int adist, + struct list_head *memory_types) +{ + return NULL; +} + +static inline void mt_put_memory_types(struct list_head *memory_types) +{ +} #endif /* CONFIG_NUMA */ #endif /* _LINUX_MEMORY_TIERS_H */ diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 7a9ff464608d..ebe876930e78 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -175,8 +175,8 @@ extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages); extern int online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group); -extern void __offline_isolated_pages(unsigned long start_pfn, - unsigned long end_pfn); +extern unsigned long __offline_isolated_pages(unsigned long start_pfn, + unsigned long end_pfn); typedef void (*online_page_callback_t)(struct page *page, unsigned int order); diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 931b118336f4..1add16f21612 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -167,7 +167,8 @@ extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol); /* Check if a vma is migratable */ extern bool vma_migratable(struct vm_area_struct *vma); -int mpol_misplaced(struct folio *, struct vm_area_struct *, unsigned long); +int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, + unsigned long addr); extern void mpol_put_task_policy(struct task_struct *); static inline bool mpol_is_preferred_many(struct mempolicy *pol) @@ -282,7 +283,7 @@ static inline int mpol_parse_str(char *str, struct mempolicy **mpol) #endif static inline int mpol_misplaced(struct folio *folio, - struct vm_area_struct *vma, + struct vm_fault *vmf, unsigned long address) { return -1; /* no node preference */ diff --git a/include/linux/mempool.h b/include/linux/mempool.h index 16c5cc807ff6..7b151441341b 100644 --- a/include/linux/mempool.h +++ b/include/linux/mempool.h @@ -5,6 +5,8 @@ #ifndef _LINUX_MEMPOOL_H #define _LINUX_MEMPOOL_H +#include <linux/sched.h> +#include <linux/alloc_tag.h> #include <linux/wait.h> #include <linux/compiler.h> @@ -39,18 +41,32 @@ void mempool_exit(mempool_t *pool); int mempool_init_node(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data, gfp_t gfp_mask, int node_id); -int mempool_init(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, + +int mempool_init_noprof(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data); +#define mempool_init(...) \ + alloc_hooks(mempool_init_noprof(__VA_ARGS__)) extern mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data); -extern mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn, + +extern mempool_t *mempool_create_node_noprof(int min_nr, mempool_alloc_t *alloc_fn, mempool_free_t *free_fn, void *pool_data, gfp_t gfp_mask, int nid); +#define mempool_create_node(...) \ + alloc_hooks(mempool_create_node_noprof(__VA_ARGS__)) + +#define mempool_create(_min_nr, _alloc_fn, _free_fn, _pool_data) \ + mempool_create_node(_min_nr, _alloc_fn, _free_fn, _pool_data, \ + GFP_KERNEL, NUMA_NO_NODE) extern int mempool_resize(mempool_t *pool, int new_min_nr); extern void mempool_destroy(mempool_t *pool); -extern void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask) __malloc; + +extern void *mempool_alloc_noprof(mempool_t *pool, gfp_t gfp_mask) __malloc; +#define mempool_alloc(...) \ + alloc_hooks(mempool_alloc_noprof(__VA_ARGS__)) + extern void *mempool_alloc_preallocated(mempool_t *pool) __malloc; extern void mempool_free(void *element, mempool_t *pool); @@ -62,19 +78,10 @@ extern void mempool_free(void *element, mempool_t *pool); void *mempool_alloc_slab(gfp_t gfp_mask, void *pool_data); void mempool_free_slab(void *element, void *pool_data); -static inline int -mempool_init_slab_pool(mempool_t *pool, int min_nr, struct kmem_cache *kc) -{ - return mempool_init(pool, min_nr, mempool_alloc_slab, - mempool_free_slab, (void *) kc); -} - -static inline mempool_t * -mempool_create_slab_pool(int min_nr, struct kmem_cache *kc) -{ - return mempool_create(min_nr, mempool_alloc_slab, mempool_free_slab, - (void *) kc); -} +#define mempool_init_slab_pool(_pool, _min_nr, _kc) \ + mempool_init(_pool, (_min_nr), mempool_alloc_slab, mempool_free_slab, (void *)(_kc)) +#define mempool_create_slab_pool(_min_nr, _kc) \ + mempool_create((_min_nr), mempool_alloc_slab, mempool_free_slab, (void *)(_kc)) /* * a mempool_alloc_t and a mempool_free_t to kmalloc and kfree the @@ -83,17 +90,12 @@ mempool_create_slab_pool(int min_nr, struct kmem_cache *kc) void *mempool_kmalloc(gfp_t gfp_mask, void *pool_data); void mempool_kfree(void *element, void *pool_data); -static inline int mempool_init_kmalloc_pool(mempool_t *pool, int min_nr, size_t size) -{ - return mempool_init(pool, min_nr, mempool_kmalloc, - mempool_kfree, (void *) size); -} - -static inline mempool_t *mempool_create_kmalloc_pool(int min_nr, size_t size) -{ - return mempool_create(min_nr, mempool_kmalloc, mempool_kfree, - (void *) size); -} +#define mempool_init_kmalloc_pool(_pool, _min_nr, _size) \ + mempool_init(_pool, (_min_nr), mempool_kmalloc, mempool_kfree, \ + (void *)(unsigned long)(_size)) +#define mempool_create_kmalloc_pool(_min_nr, _size) \ + mempool_create((_min_nr), mempool_kmalloc, mempool_kfree, \ + (void *)(unsigned long)(_size)) void *mempool_kvmalloc(gfp_t gfp_mask, void *pool_data); void mempool_kvfree(void *element, void *pool_data); @@ -115,16 +117,11 @@ static inline mempool_t *mempool_create_kvmalloc_pool(int min_nr, size_t size) void *mempool_alloc_pages(gfp_t gfp_mask, void *pool_data); void mempool_free_pages(void *element, void *pool_data); -static inline int mempool_init_page_pool(mempool_t *pool, int min_nr, int order) -{ - return mempool_init(pool, min_nr, mempool_alloc_pages, - mempool_free_pages, (void *)(long)order); -} - -static inline mempool_t *mempool_create_page_pool(int min_nr, int order) -{ - return mempool_create(min_nr, mempool_alloc_pages, mempool_free_pages, - (void *)(long)order); -} +#define mempool_init_page_pool(_pool, _min_nr, _order) \ + mempool_init(_pool, (_min_nr), mempool_alloc_pages, \ + mempool_free_pages, (void *)(long)(_order)) +#define mempool_create_page_pool(_min_nr, _order) \ + mempool_create((_min_nr), mempool_alloc_pages, \ + mempool_free_pages, (void *)(long)(_order)) #endif /* _LINUX_MEMPOOL_H */ diff --git a/include/linux/mfd/88pm886.h b/include/linux/mfd/88pm886.h new file mode 100644 index 000000000000..133aa302e492 --- /dev/null +++ b/include/linux/mfd/88pm886.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __MFD_88PM886_H +#define __MFD_88PM886_H + +#include <linux/i2c.h> +#include <linux/regmap.h> + +#define PM886_A1_CHIP_ID 0xa1 + +#define PM886_IRQ_ONKEY 0 + +#define PM886_PAGE_OFFSET_REGULATORS 1 + +#define PM886_REG_ID 0x00 + +#define PM886_REG_STATUS1 0x01 +#define PM886_ONKEY_STS1 BIT(0) + +#define PM886_REG_INT_STATUS1 0x05 + +#define PM886_REG_INT_ENA_1 0x0a +#define PM886_INT_ENA1_ONKEY BIT(0) + +#define PM886_REG_MISC_CONFIG1 0x14 +#define PM886_SW_PDOWN BIT(5) + +#define PM886_REG_MISC_CONFIG2 0x15 +#define PM886_INT_INV BIT(0) +#define PM886_INT_CLEAR BIT(1) +#define PM886_INT_RC 0x00 +#define PM886_INT_WC BIT(1) +#define PM886_INT_MASK_MODE BIT(2) + +#define PM886_REG_RTC_SPARE6 0xef + +#define PM886_REG_BUCK_EN 0x08 +#define PM886_REG_LDO_EN1 0x09 +#define PM886_REG_LDO_EN2 0x0a +#define PM886_REG_LDO1_VOUT 0x20 +#define PM886_REG_LDO2_VOUT 0x26 +#define PM886_REG_LDO3_VOUT 0x2c +#define PM886_REG_LDO4_VOUT 0x32 +#define PM886_REG_LDO5_VOUT 0x38 +#define PM886_REG_LDO6_VOUT 0x3e +#define PM886_REG_LDO7_VOUT 0x44 +#define PM886_REG_LDO8_VOUT 0x4a +#define PM886_REG_LDO9_VOUT 0x50 +#define PM886_REG_LDO10_VOUT 0x56 +#define PM886_REG_LDO11_VOUT 0x5c +#define PM886_REG_LDO12_VOUT 0x62 +#define PM886_REG_LDO13_VOUT 0x68 +#define PM886_REG_LDO14_VOUT 0x6e +#define PM886_REG_LDO15_VOUT 0x74 +#define PM886_REG_LDO16_VOUT 0x7a +#define PM886_REG_BUCK1_VOUT 0xa5 +#define PM886_REG_BUCK2_VOUT 0xb3 +#define PM886_REG_BUCK3_VOUT 0xc1 +#define PM886_REG_BUCK4_VOUT 0xcf +#define PM886_REG_BUCK5_VOUT 0xdd + +#define PM886_LDO_VSEL_MASK 0x0f +#define PM886_BUCK_VSEL_MASK 0x7f + +struct pm886_chip { + struct i2c_client *client; + unsigned int chip_id; + struct regmap *regmap; +}; +#endif /* __MFD_88PM886_H */ diff --git a/include/linux/mfd/atmel-hlcdc.h b/include/linux/mfd/atmel-hlcdc.h index a186119a49b5..80d675a03b39 100644 --- a/include/linux/mfd/atmel-hlcdc.h +++ b/include/linux/mfd/atmel-hlcdc.h @@ -22,6 +22,8 @@ #define ATMEL_HLCDC_DITHER BIT(6) #define ATMEL_HLCDC_DISPDLY BIT(7) #define ATMEL_HLCDC_MODE_MASK GENMASK(9, 8) +#define ATMEL_XLCDC_MODE_MASK GENMASK(10, 8) +#define ATMEL_XLCDC_DPI BIT(11) #define ATMEL_HLCDC_PP BIT(10) #define ATMEL_HLCDC_VSPSU BIT(12) #define ATMEL_HLCDC_VSPHO BIT(13) @@ -34,6 +36,12 @@ #define ATMEL_HLCDC_IDR 0x30 #define ATMEL_HLCDC_IMR 0x34 #define ATMEL_HLCDC_ISR 0x38 +#define ATMEL_XLCDC_ATTRE 0x3c + +#define ATMEL_XLCDC_BASE_UPDATE BIT(0) +#define ATMEL_XLCDC_OVR1_UPDATE BIT(1) +#define ATMEL_XLCDC_OVR3_UPDATE BIT(2) +#define ATMEL_XLCDC_HEO_UPDATE BIT(3) #define ATMEL_HLCDC_CLKPOL BIT(0) #define ATMEL_HLCDC_CLKSEL BIT(2) @@ -48,6 +56,8 @@ #define ATMEL_HLCDC_DISP BIT(2) #define ATMEL_HLCDC_PWM BIT(3) #define ATMEL_HLCDC_SIP BIT(4) +#define ATMEL_XLCDC_SD BIT(5) +#define ATMEL_XLCDC_CM BIT(6) #define ATMEL_HLCDC_SOF BIT(0) #define ATMEL_HLCDC_SYNCDIS BIT(1) diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h index f1755163dd9f..8c0a33a2e9ce 100644 --- a/include/linux/mfd/axp20x.h +++ b/include/linux/mfd/axp20x.h @@ -19,6 +19,7 @@ enum axp20x_variants { AXP223_ID, AXP288_ID, AXP313A_ID, + AXP717_ID, AXP803_ID, AXP806_ID, AXP809_ID, @@ -104,15 +105,47 @@ enum axp20x_variants { #define AXP313A_ON_INDICATE 0x00 #define AXP313A_OUTPUT_CONTROL 0x10 -#define AXP313A_DCDC1_CONRTOL 0x13 -#define AXP313A_DCDC2_CONRTOL 0x14 -#define AXP313A_DCDC3_CONRTOL 0x15 -#define AXP313A_ALDO1_CONRTOL 0x16 -#define AXP313A_DLDO1_CONRTOL 0x17 +#define AXP313A_DCDC1_CONTROL 0x13 +#define AXP313A_DCDC2_CONTROL 0x14 +#define AXP313A_DCDC3_CONTROL 0x15 +#define AXP313A_ALDO1_CONTROL 0x16 +#define AXP313A_DLDO1_CONTROL 0x17 #define AXP313A_SHUTDOWN_CTRL 0x1a #define AXP313A_IRQ_EN 0x20 #define AXP313A_IRQ_STATE 0x21 +#define AXP717_ON_INDICATE 0x00 +#define AXP717_IRQ0_EN 0x40 +#define AXP717_IRQ1_EN 0x41 +#define AXP717_IRQ2_EN 0x42 +#define AXP717_IRQ3_EN 0x43 +#define AXP717_IRQ4_EN 0x44 +#define AXP717_IRQ0_STATE 0x48 +#define AXP717_IRQ1_STATE 0x49 +#define AXP717_IRQ2_STATE 0x4a +#define AXP717_IRQ3_STATE 0x4b +#define AXP717_IRQ4_STATE 0x4c +#define AXP717_DCDC_OUTPUT_CONTROL 0x80 +#define AXP717_DCDC1_CONTROL 0x83 +#define AXP717_DCDC2_CONTROL 0x84 +#define AXP717_DCDC3_CONTROL 0x85 +#define AXP717_DCDC4_CONTROL 0x86 +#define AXP717_LDO0_OUTPUT_CONTROL 0x90 +#define AXP717_LDO1_OUTPUT_CONTROL 0x91 +#define AXP717_ALDO1_CONTROL 0x93 +#define AXP717_ALDO2_CONTROL 0x94 +#define AXP717_ALDO3_CONTROL 0x95 +#define AXP717_ALDO4_CONTROL 0x96 +#define AXP717_BLDO1_CONTROL 0x97 +#define AXP717_BLDO2_CONTROL 0x98 +#define AXP717_BLDO3_CONTROL 0x99 +#define AXP717_BLDO4_CONTROL 0x9a +#define AXP717_CLDO1_CONTROL 0x9b +#define AXP717_CLDO2_CONTROL 0x9c +#define AXP717_CLDO3_CONTROL 0x9d +#define AXP717_CLDO4_CONTROL 0x9e +#define AXP717_CPUSLDO_CONTROL 0x9f + #define AXP806_STARTUP_SRC 0x00 #define AXP806_CHIP_ID 0x03 #define AXP806_PWR_OUT_CTRL1 0x10 @@ -434,6 +467,27 @@ enum { }; enum { + AXP717_DCDC1 = 0, + AXP717_DCDC2, + AXP717_DCDC3, + AXP717_DCDC4, + AXP717_ALDO1, + AXP717_ALDO2, + AXP717_ALDO3, + AXP717_ALDO4, + AXP717_BLDO1, + AXP717_BLDO2, + AXP717_BLDO3, + AXP717_BLDO4, + AXP717_CLDO1, + AXP717_CLDO2, + AXP717_CLDO3, + AXP717_CLDO4, + AXP717_CPUSLDO, + AXP717_REG_ID_MAX, +}; + +enum { AXP806_DCDCA = 0, AXP806_DCDCB, AXP806_DCDCC, @@ -732,6 +786,40 @@ enum axp313a_irqs { AXP313A_IRQ_PEK_RIS_EDGE, }; +enum axp717_irqs { + AXP717_IRQ_VBUS_FAULT, + AXP717_IRQ_VBUS_OVER_V, + AXP717_IRQ_BOOST_OVER_V, + AXP717_IRQ_GAUGE_NEW_SOC = 4, + AXP717_IRQ_SOC_DROP_LVL1 = 6, + AXP717_IRQ_SOC_DROP_LVL2, + AXP717_IRQ_PEK_RIS_EDGE, + AXP717_IRQ_PEK_FAL_EDGE, + AXP717_IRQ_PEK_LONG, + AXP717_IRQ_PEK_SHORT, + AXP717_IRQ_BATT_REMOVAL, + AXP717_IRQ_BATT_PLUGIN, + AXP717_IRQ_VBUS_REMOVAL, + AXP717_IRQ_VBUS_PLUGIN, + AXP717_IRQ_BATT_OVER_V, + AXP717_IRQ_CHARG_TIMER, + AXP717_IRQ_DIE_TEMP_HIGH, + AXP717_IRQ_CHARG, + AXP717_IRQ_CHARG_DONE, + AXP717_IRQ_BATT_OVER_CURR, + AXP717_IRQ_LDO_OVER_CURR, + AXP717_IRQ_WDOG_EXPIRE, + AXP717_IRQ_BATT_ACT_TEMP_LOW, + AXP717_IRQ_BATT_ACT_TEMP_HIGH, + AXP717_IRQ_BATT_CHG_TEMP_LOW, + AXP717_IRQ_BATT_CHG_TEMP_HIGH, + AXP717_IRQ_BATT_QUIT_TEMP_HIGH, + AXP717_IRQ_BC_USB_CHNG = 30, + AXP717_IRQ_BC_USB_DONE, + AXP717_IRQ_TYPEC_PLUGIN = 37, + AXP717_IRQ_TYPEC_REMOVE, +}; + enum axp803_irqs { AXP803_IRQ_ACIN_OVER_V = 1, AXP803_IRQ_ACIN_PLUGIN, diff --git a/include/linux/mfd/cs40l50.h b/include/linux/mfd/cs40l50.h new file mode 100644 index 000000000000..e5dc49860944 --- /dev/null +++ b/include/linux/mfd/cs40l50.h @@ -0,0 +1,137 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * CS40L50 Advanced Haptic Driver with waveform memory, + * integrated DSP, and closed-loop algorithms + * + * Copyright 2024 Cirrus Logic, Inc. + * + * Author: James Ogletree <james.ogletree@cirrus.com> + */ + +#ifndef __MFD_CS40L50_H__ +#define __MFD_CS40L50_H__ + +#include <linux/firmware/cirrus/cs_dsp.h> +#include <linux/gpio/consumer.h> +#include <linux/pm.h> +#include <linux/regmap.h> + +/* Power Supply Configuration */ +#define CS40L50_BLOCK_ENABLES2 0x201C +#define CS40L50_ERR_RLS 0x2034 +#define CS40L50_BST_LPMODE_SEL 0x3810 +#define CS40L50_DCM_LOW_POWER 0x1 +#define CS40L50_OVERTEMP_WARN 0x4000010 + +/* Interrupts */ +#define CS40L50_IRQ1_INT_1 0xE010 +#define CS40L50_IRQ1_BASE CS40L50_IRQ1_INT_1 +#define CS40L50_IRQ1_INT_2 0xE014 +#define CS40L50_IRQ1_INT_8 0xE02C +#define CS40L50_IRQ1_INT_9 0xE030 +#define CS40L50_IRQ1_INT_10 0xE034 +#define CS40L50_IRQ1_INT_18 0xE054 +#define CS40L50_IRQ1_MASK_1 0xE090 +#define CS40L50_IRQ1_MASK_2 0xE094 +#define CS40L50_IRQ1_MASK_20 0xE0DC +#define CS40L50_IRQ1_INT_1_OFFSET (CS40L50_IRQ1_INT_1 - CS40L50_IRQ1_BASE) +#define CS40L50_IRQ1_INT_2_OFFSET (CS40L50_IRQ1_INT_2 - CS40L50_IRQ1_BASE) +#define CS40L50_IRQ1_INT_8_OFFSET (CS40L50_IRQ1_INT_8 - CS40L50_IRQ1_BASE) +#define CS40L50_IRQ1_INT_9_OFFSET (CS40L50_IRQ1_INT_9 - CS40L50_IRQ1_BASE) +#define CS40L50_IRQ1_INT_10_OFFSET (CS40L50_IRQ1_INT_10 - CS40L50_IRQ1_BASE) +#define CS40L50_IRQ1_INT_18_OFFSET (CS40L50_IRQ1_INT_18 - CS40L50_IRQ1_BASE) +#define CS40L50_IRQ_MASK_2_OVERRIDE 0xFFDF7FFF +#define CS40L50_IRQ_MASK_20_OVERRIDE 0x15C01000 +#define CS40L50_AMP_SHORT_MASK BIT(31) +#define CS40L50_DSP_QUEUE_MASK BIT(21) +#define CS40L50_TEMP_ERR_MASK BIT(31) +#define CS40L50_BST_UVP_MASK BIT(6) +#define CS40L50_BST_SHORT_MASK BIT(7) +#define CS40L50_BST_ILIMIT_MASK BIT(18) +#define CS40L50_UVLO_VDDBATT_MASK BIT(16) +#define CS40L50_GLOBAL_ERROR_MASK BIT(15) + +enum cs40l50_irq_list { + CS40L50_DSP_QUEUE_IRQ, + CS40L50_GLOBAL_ERROR_IRQ, + CS40L50_UVLO_VDDBATT_IRQ, + CS40L50_BST_ILIMIT_IRQ, + CS40L50_BST_SHORT_IRQ, + CS40L50_BST_UVP_IRQ, + CS40L50_TEMP_ERR_IRQ, + CS40L50_AMP_SHORT_IRQ, +}; + +/* DSP */ +#define CS40L50_XMEM_PACKED_0 0x2000000 +#define CS40L50_XMEM_UNPACKED24_0 0x2800000 +#define CS40L50_SYS_INFO_ID 0x25E0000 +#define CS40L50_DSP_QUEUE_WT 0x28042C8 +#define CS40L50_DSP_QUEUE_RD 0x28042CC +#define CS40L50_NUM_WAVES 0x2805C18 +#define CS40L50_CORE_BASE 0x2B80000 +#define CS40L50_YMEM_PACKED_0 0x2C00000 +#define CS40L50_YMEM_UNPACKED24_0 0x3400000 +#define CS40L50_PMEM_0 0x3800000 +#define CS40L50_DSP_POLL_US 1000 +#define CS40L50_DSP_TIMEOUT_COUNT 100 +#define CS40L50_RESET_PULSE_US 2200 +#define CS40L50_CP_READY_US 3100 +#define CS40L50_AUTOSUSPEND_MS 2000 +#define CS40L50_PM_ALGO 0x9F206 +#define CS40L50_GLOBAL_ERR_RLS_SET BIT(11) +#define CS40L50_GLOBAL_ERR_RLS_CLEAR 0 + +enum cs40l50_wseqs { + CS40L50_PWR_ON, + CS40L50_STANDBY, + CS40L50_ACTIVE, + CS40L50_NUM_WSEQS, +}; + +/* DSP Queue */ +#define CS40L50_DSP_QUEUE_BASE 0x11004 +#define CS40L50_DSP_QUEUE_END 0x1101C +#define CS40L50_DSP_QUEUE 0x11020 +#define CS40L50_PREVENT_HIBER 0x2000003 +#define CS40L50_ALLOW_HIBER 0x2000004 +#define CS40L50_SHUTDOWN 0x2000005 +#define CS40L50_SYSTEM_RESET 0x2000007 +#define CS40L50_START_I2S 0x3000002 +#define CS40L50_OWT_PUSH 0x3000008 +#define CS40L50_STOP_PLAYBACK 0x5000000 +#define CS40L50_OWT_DELETE 0xD000000 + +/* Firmware files */ +#define CS40L50_FW "cs40l50.wmfw" +#define CS40L50_WT "cs40l50.bin" + +/* Device */ +#define CS40L50_DEVID 0x0 +#define CS40L50_REVID 0x4 +#define CS40L50_DEVID_A 0x40A50 +#define CS40L50_REVID_B0 0xB0 + +struct cs40l50 { + struct device *dev; + struct regmap *regmap; + struct mutex lock; + struct cs_dsp dsp; + struct gpio_desc *reset_gpio; + struct regmap_irq_chip_data *irq_data; + const struct firmware *fw; + const struct firmware *bin; + struct cs_dsp_wseq wseqs[CS40L50_NUM_WSEQS]; + int irq; + u32 devid; + u32 revid; +}; + +int cs40l50_dsp_write(struct device *dev, struct regmap *regmap, u32 val); +int cs40l50_probe(struct cs40l50 *cs40l50); +int cs40l50_remove(struct cs40l50 *cs40l50); + +extern const struct regmap_config cs40l50_regmap; +extern const struct dev_pm_ops cs40l50_pm_ops; + +#endif /* __MFD_CS40L50_H__ */ diff --git a/include/linux/mfd/idt8a340_reg.h b/include/linux/mfd/idt8a340_reg.h index 0c706085c205..53a222605526 100644 --- a/include/linux/mfd/idt8a340_reg.h +++ b/include/linux/mfd/idt8a340_reg.h @@ -61,7 +61,7 @@ #define HW_Q8_CTRL_SPARE (0xa7d4) #define HW_Q11_CTRL_SPARE (0xa7ec) -/** +/* * Select FOD5 as sync_trigger for Q8 divider. * Transition from logic zero to one * sets trigger to sync Q8 divider. @@ -70,7 +70,7 @@ */ #define Q9_TO_Q8_SYNC_TRIG BIT(1) -/** +/* * Enable FOD5 as driver for clock and sync for Q8 divider. * Enable fanout buffer for FOD5. * @@ -78,7 +78,7 @@ */ #define Q9_TO_Q8_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK (BIT(0) | BIT(2)) -/** +/* * Select FOD6 as sync_trigger for Q11 divider. * Transition from logic zero to one * sets trigger to sync Q11 divider. @@ -87,7 +87,7 @@ */ #define Q10_TO_Q11_SYNC_TRIG BIT(1) -/** +/* * Enable FOD6 as driver for clock and sync for Q11 divider. * Enable fanout buffer for FOD6. * diff --git a/include/linux/mfd/intel-m10-bmc.h b/include/linux/mfd/intel-m10-bmc.h index ee66c9751003..988f1cd90032 100644 --- a/include/linux/mfd/intel-m10-bmc.h +++ b/include/linux/mfd/intel-m10-bmc.h @@ -205,6 +205,7 @@ struct m10bmc_csr_map { unsigned int pr_reh_addr; unsigned int pr_magic; unsigned int rsu_update_counter; + unsigned int staging_size; }; /** diff --git a/include/linux/mfd/lm3533.h b/include/linux/mfd/lm3533.h index 77092f6363ad..69059a7a2ce5 100644 --- a/include/linux/mfd/lm3533.h +++ b/include/linux/mfd/lm3533.h @@ -16,6 +16,7 @@ DEVICE_ATTR(_name, S_IRUGO | S_IWUSR , show_##_name, store_##_name) struct device; +struct gpio_desc; struct regmap; struct lm3533 { @@ -23,7 +24,7 @@ struct lm3533 { struct regmap *regmap; - int gpio_hwen; + struct gpio_desc *hwen; int irq; unsigned have_als:1; @@ -69,8 +70,6 @@ enum lm3533_boost_ovp { }; struct lm3533_platform_data { - int gpio_hwen; - enum lm3533_boost_ovp boost_ovp; enum lm3533_boost_freq boost_freq; diff --git a/include/linux/mfd/lp8788.h b/include/linux/mfd/lp8788.h index 51b47966a04d..fd17bec2a33e 100644 --- a/include/linux/mfd/lp8788.h +++ b/include/linux/mfd/lp8788.h @@ -11,7 +11,6 @@ #define __MFD_LP8788_H__ #include <linux/irqdomain.h> -#include <linux/pwm.h> #include <linux/regmap.h> #define LP8788_DEV_BUCK "lp8788-buck" @@ -87,12 +86,6 @@ enum lp8788_charger_event { CHARGER_DETECTED, }; -enum lp8788_bl_ctrl_mode { - LP8788_BL_REGISTER_ONLY, - LP8788_BL_COMB_PWM_BASED, /* PWM + I2C, changed by PWM input */ - LP8788_BL_COMB_REGISTER_BASED, /* PWM + I2C, changed by I2C */ -}; - enum lp8788_bl_dim_mode { LP8788_DIM_EXPONENTIAL, LP8788_DIM_LINEAR, @@ -202,31 +195,6 @@ struct lp8788_charger_platform_data { }; /* - * struct lp8788_backlight_platform_data - * @name : backlight driver name. (default: "lcd-backlight") - * @initial_brightness : initial value of backlight brightness - * @bl_mode : brightness control by pwm or lp8788 register - * @dim_mode : dimming mode selection - * @full_scale : full scale current setting - * @rise_time : brightness ramp up step time - * @fall_time : brightness ramp down step time - * @pwm_pol : pwm polarity setting when bl_mode is pwm based - * @period_ns : platform specific pwm period value. unit is nano. - Only valid when bl_mode is LP8788_BL_COMB_PWM_BASED - */ -struct lp8788_backlight_platform_data { - char *name; - int initial_brightness; - enum lp8788_bl_ctrl_mode bl_mode; - enum lp8788_bl_dim_mode dim_mode; - enum lp8788_bl_full_scale_current full_scale; - enum lp8788_bl_ramp_step rise_time; - enum lp8788_bl_ramp_step fall_time; - enum pwm_polarity pwm_pol; - unsigned int period_ns; -}; - -/* * struct lp8788_led_platform_data * @name : led driver name. (default: "keyboard-backlight") * @scale : current scale @@ -267,7 +235,6 @@ struct lp8788_vib_platform_data { * @buck2_dvs : configurations for buck2 dvs * @chg_pdata : platform data for charger driver * @alarm_sel : rtc alarm selection (1 or 2) - * @bl_pdata : configurable data for backlight driver * @led_pdata : configurable data for led driver * @vib_pdata : configurable data for vibrator driver * @adc_pdata : iio map data for adc driver @@ -289,9 +256,6 @@ struct lp8788_platform_data { /* rtc alarm */ enum lp8788_alarm_sel alarm_sel; - /* backlight */ - struct lp8788_backlight_platform_data *bl_pdata; - /* current sinks */ struct lp8788_led_platform_data *led_pdata; struct lp8788_vib_platform_data *vib_pdata; diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h index 78e167a92483..69cbea78b430 100644 --- a/include/linux/mfd/rk808.h +++ b/include/linux/mfd/rk808.h @@ -113,6 +113,148 @@ enum rk808_reg { #define RK808_INT_STS_MSK_REG2 0x4f #define RK808_IO_POL_REG 0x50 +/* RK816 */ +enum rk816_reg { + RK816_ID_DCDC1, + RK816_ID_DCDC2, + RK816_ID_DCDC3, + RK816_ID_DCDC4, + RK816_ID_LDO1, + RK816_ID_LDO2, + RK816_ID_LDO3, + RK816_ID_LDO4, + RK816_ID_LDO5, + RK816_ID_LDO6, + RK816_ID_BOOST, + RK816_ID_OTG_SW, +}; + +enum rk816_irqs { + /* INT_STS_REG1 */ + RK816_IRQ_PWRON_FALL, + RK816_IRQ_PWRON_RISE, + + /* INT_STS_REG2 */ + RK816_IRQ_VB_LOW, + RK816_IRQ_PWRON, + RK816_IRQ_PWRON_LP, + RK816_IRQ_HOTDIE, + RK816_IRQ_RTC_ALARM, + RK816_IRQ_RTC_PERIOD, + RK816_IRQ_USB_OV, + + /* INT_STS_REG3 */ + RK816_IRQ_PLUG_IN, + RK816_IRQ_PLUG_OUT, + RK816_IRQ_CHG_OK, + RK816_IRQ_CHG_TE, + RK816_IRQ_CHG_TS, + RK816_IRQ_CHG_CVTLIM, + RK816_IRQ_DISCHG_ILIM, +}; + +/* power channel registers */ +#define RK816_DCDC_EN_REG1 0x23 + +#define RK816_DCDC_EN_REG2 0x24 +#define RK816_BOOST_EN BIT(1) +#define RK816_OTG_EN BIT(2) +#define RK816_BOOST_EN_MSK BIT(5) +#define RK816_OTG_EN_MSK BIT(6) +#define RK816_BUCK_DVS_CONFIRM BIT(7) + +#define RK816_LDO_EN_REG1 0x27 + +#define RK816_LDO_EN_REG2 0x28 + +/* interrupt registers and irq definitions */ +#define RK816_INT_STS_REG1 0x49 +#define RK816_INT_STS_MSK_REG1 0x4a +#define RK816_INT_STS_PWRON_FALL BIT(5) +#define RK816_INT_STS_PWRON_RISE BIT(6) + +#define RK816_INT_STS_REG2 0x4c +#define RK816_INT_STS_MSK_REG2 0x4d +#define RK816_INT_STS_VB_LOW BIT(1) +#define RK816_INT_STS_PWRON BIT(2) +#define RK816_INT_STS_PWRON_LP BIT(3) +#define RK816_INT_STS_HOTDIE BIT(4) +#define RK816_INT_STS_RTC_ALARM BIT(5) +#define RK816_INT_STS_RTC_PERIOD BIT(6) +#define RK816_INT_STS_USB_OV BIT(7) + +#define RK816_INT_STS_REG3 0x4e +#define RK816_INT_STS_MSK_REG3 0x4f +#define RK816_INT_STS_PLUG_IN BIT(0) +#define RK816_INT_STS_PLUG_OUT BIT(1) +#define RK816_INT_STS_CHG_OK BIT(2) +#define RK816_INT_STS_CHG_TE BIT(3) +#define RK816_INT_STS_CHG_TS BIT(4) +#define RK816_INT_STS_CHG_CVTLIM BIT(6) +#define RK816_INT_STS_DISCHG_ILIM BIT(7) + +#define RK816_IRQ_STS_OFFSET(x) ((x) - RK816_INT_STS_REG1) +#define RK816_IRQ_MSK_OFFSET(x) ((x) - RK816_INT_STS_MSK_REG1) + +/* charger, boost and OTG registers */ +#define RK816_OTG_BUCK_LDO_CONFIG_REG 0x2a +#define RK816_CHRG_CONFIG_REG 0x2b +#define RK816_BOOST_ON_VESL_REG 0x54 +#define RK816_BOOST_SLP_VSEL_REG 0x55 +#define RK816_CHRG_BOOST_CONFIG_REG 0x9a +#define RK816_SUP_STS_REG 0xa0 +#define RK816_USB_CTRL_REG 0xa1 +#define RK816_CHRG_CTRL(x) (0xa3 + (x)) +#define RK816_BAT_CTRL_REG 0xa6 +#define RK816_BAT_HTS_TS_REG 0xa8 +#define RK816_BAT_LTS_TS_REG 0xa9 + +/* adc and fuel gauge registers */ +#define RK816_TS_CTRL_REG 0xac +#define RK816_ADC_CTRL_REG 0xad +#define RK816_GGCON_REG 0xb0 +#define RK816_GGSTS_REG 0xb1 +#define RK816_ZERO_CUR_ADC_REGH 0xb2 +#define RK816_ZERO_CUR_ADC_REGL 0xb3 +#define RK816_GASCNT_CAL_REG(x) (0xb7 - (x)) +#define RK816_GASCNT_REG(x) (0xbb - (x)) +#define RK816_BAT_CUR_AVG_REGH 0xbc +#define RK816_BAT_CUR_AVG_REGL 0xbd +#define RK816_TS_ADC_REGH 0xbe +#define RK816_TS_ADC_REGL 0xbf +#define RK816_USB_ADC_REGH 0xc0 +#define RK816_USB_ADC_REGL 0xc1 +#define RK816_BAT_OCV_REGH 0xc2 +#define RK816_BAT_OCV_REGL 0xc3 +#define RK816_BAT_VOL_REGH 0xc4 +#define RK816_BAT_VOL_REGL 0xc5 +#define RK816_RELAX_ENTRY_THRES_REGH 0xc6 +#define RK816_RELAX_ENTRY_THRES_REGL 0xc7 +#define RK816_RELAX_EXIT_THRES_REGH 0xc8 +#define RK816_RELAX_EXIT_THRES_REGL 0xc9 +#define RK816_RELAX_VOL1_REGH 0xca +#define RK816_RELAX_VOL1_REGL 0xcb +#define RK816_RELAX_VOL2_REGH 0xcc +#define RK816_RELAX_VOL2_REGL 0xcd +#define RK816_RELAX_CUR1_REGH 0xce +#define RK816_RELAX_CUR1_REGL 0xcf +#define RK816_RELAX_CUR2_REGH 0xd0 +#define RK816_RELAX_CUR2_REGL 0xd1 +#define RK816_CAL_OFFSET_REGH 0xd2 +#define RK816_CAL_OFFSET_REGL 0xd3 +#define RK816_NON_ACT_TIMER_CNT_REG 0xd4 +#define RK816_VCALIB0_REGH 0xd5 +#define RK816_VCALIB0_REGL 0xd6 +#define RK816_VCALIB1_REGH 0xd7 +#define RK816_VCALIB1_REGL 0xd8 +#define RK816_FCC_GASCNT_REG(x) (0xdc - (x)) +#define RK816_IOFFSET_REGH 0xdd +#define RK816_IOFFSET_REGL 0xde +#define RK816_SLEEP_CON_SAMP_CUR_REG 0xdf + +/* general purpose data registers 0xe0 ~ 0xf2 */ +#define RK816_DATA_REG(x) (0xe0 + (x)) + /* RK818 */ #define RK818_DCDC1 0 #define RK818_LDO1 4 @@ -791,6 +933,7 @@ enum rk806_dvs_mode { #define VOUT_LO_INT BIT(0) #define CLK32KOUT2_EN BIT(0) +#define TEMP105C 0x08 #define TEMP115C 0x0c #define TEMP_HOTDIE_MSK 0x0c #define SLP_SD_MSK (0x3 << 2) @@ -1191,6 +1334,7 @@ enum { RK806_ID = 0x8060, RK808_ID = 0x0000, RK809_ID = 0x8090, + RK816_ID = 0x8160, RK817_ID = 0x8170, RK818_ID = 0x8180, }; diff --git a/include/linux/mfd/rohm-bd71828.h b/include/linux/mfd/rohm-bd71828.h index 3b5f3a7db4bd..ce786c96404a 100644 --- a/include/linux/mfd/rohm-bd71828.h +++ b/include/linux/mfd/rohm-bd71828.h @@ -4,6 +4,7 @@ #ifndef __LINUX_MFD_BD71828_H__ #define __LINUX_MFD_BD71828_H__ +#include <linux/bits.h> #include <linux/mfd/rohm-generic.h> #include <linux/mfd/rohm-shared.h> @@ -41,7 +42,8 @@ enum { #define BD71828_REG_PS_CTRL_2 0x05 #define BD71828_REG_PS_CTRL_3 0x06 -//#define BD71828_REG_SWRESET 0x06 +#define BD71828_MASK_STATE_HBNT BIT(1) + #define BD71828_MASK_RUN_LVL_CTRL 0x30 /* Regulator control masks */ @@ -133,7 +135,6 @@ enum { #define BD71828_REG_LDO5_VOLT 0x43 #define BD71828_REG_LDO5_VOLT_OPT 0x42 #define BD71828_REG_LDO6_EN 0x44 -//#define BD71828_REG_LDO6_VOLT 0x4 #define BD71828_REG_LDO7_EN 0x45 #define BD71828_REG_LDO7_VOLT 0x46 diff --git a/include/linux/mfd/rohm-bd96801.h b/include/linux/mfd/rohm-bd96801.h new file mode 100644 index 000000000000..e2d9e10b6364 --- /dev/null +++ b/include/linux/mfd/rohm-bd96801.h @@ -0,0 +1,215 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright (C) 2024 ROHM Semiconductors */ + +#ifndef __MFD_BD96801_H__ +#define __MFD_BD96801_H__ + +#define BD96801_REG_SSCG_CTRL 0x09 +#define BD96801_REG_SHD_INTB 0x20 +#define BD96801_LDO5_VOL_LVL_REG 0x2c +#define BD96801_LDO6_VOL_LVL_REG 0x2d +#define BD96801_LDO7_VOL_LVL_REG 0x2e +#define BD96801_REG_BUCK_OVP 0x30 +#define BD96801_REG_BUCK_OVD 0x35 +#define BD96801_REG_LDO_OVP 0x31 +#define BD96801_REG_LDO_OVD 0x36 +#define BD96801_REG_BOOT_OVERTIME 0x3a +#define BD96801_REG_WD_TMO 0x40 +#define BD96801_REG_WD_CONF 0x41 +#define BD96801_REG_WD_FEED 0x42 +#define BD96801_REG_WD_FAILCOUNT 0x43 +#define BD96801_REG_WD_ASK 0x46 +#define BD96801_REG_WD_STATUS 0x4a +#define BD96801_REG_PMIC_STATE 0x4f +#define BD96801_REG_EXT_STATE 0x50 + +#define BD96801_STATE_STBY 0x09 + +#define BD96801_LOCK_REG 0x04 +#define BD96801_UNLOCK 0x9d +#define BD96801_LOCK 0x00 + +/* IRQ register area */ +#define BD96801_REG_INT_MAIN 0x51 + +/* + * The BD96801 has two physical IRQ lines, INTB and ERRB. + * + * The 'main status register' is located at 0x51. + * The ERRB status registers are located at 0x52 ... 0x5B + * INTB status registers are at range 0x5c ... 0x63 + */ +#define BD96801_REG_INT_SYS_ERRB1 0x52 +#define BD96801_REG_INT_SYS_INTB 0x5c +#define BD96801_REG_INT_LDO7_INTB 0x63 + +/* MASK registers */ +#define BD96801_REG_MASK_SYS_INTB 0x73 +#define BD96801_REG_MASK_SYS_ERRB 0x69 + +#define BD96801_MAX_REGISTER 0x7a + +#define BD96801_OTP_ERR_MASK BIT(0) +#define BD96801_DBIST_ERR_MASK BIT(1) +#define BD96801_EEP_ERR_MASK BIT(2) +#define BD96801_ABIST_ERR_MASK BIT(3) +#define BD96801_PRSTB_ERR_MASK BIT(4) +#define BD96801_DRMOS1_ERR_MASK BIT(5) +#define BD96801_DRMOS2_ERR_MASK BIT(6) +#define BD96801_SLAVE_ERR_MASK BIT(7) +#define BD96801_VREF_ERR_MASK BIT(0) +#define BD96801_TSD_ERR_MASK BIT(1) +#define BD96801_UVLO_ERR_MASK BIT(2) +#define BD96801_OVLO_ERR_MASK BIT(3) +#define BD96801_OSC_ERR_MASK BIT(4) +#define BD96801_PON_ERR_MASK BIT(5) +#define BD96801_POFF_ERR_MASK BIT(6) +#define BD96801_CMD_SHDN_ERR_MASK BIT(7) +#define BD96801_INT_PRSTB_WDT_ERR_MASK BIT(0) +#define BD96801_INT_CHIP_IF_ERR_MASK BIT(3) +#define BD96801_INT_SHDN_ERR_MASK BIT(7) +#define BD96801_OUT_PVIN_ERR_MASK BIT(0) +#define BD96801_OUT_OVP_ERR_MASK BIT(1) +#define BD96801_OUT_UVP_ERR_MASK BIT(2) +#define BD96801_OUT_SHDN_ERR_MASK BIT(7) + +/* ERRB IRQs */ +enum { + /* Reg 0x52, 0x53, 0x54 - ERRB system IRQs */ + BD96801_OTP_ERR_STAT, + BD96801_DBIST_ERR_STAT, + BD96801_EEP_ERR_STAT, + BD96801_ABIST_ERR_STAT, + BD96801_PRSTB_ERR_STAT, + BD96801_DRMOS1_ERR_STAT, + BD96801_DRMOS2_ERR_STAT, + BD96801_SLAVE_ERR_STAT, + BD96801_VREF_ERR_STAT, + BD96801_TSD_ERR_STAT, + BD96801_UVLO_ERR_STAT, + BD96801_OVLO_ERR_STAT, + BD96801_OSC_ERR_STAT, + BD96801_PON_ERR_STAT, + BD96801_POFF_ERR_STAT, + BD96801_CMD_SHDN_ERR_STAT, + BD96801_INT_PRSTB_WDT_ERR, + BD96801_INT_CHIP_IF_ERR, + BD96801_INT_SHDN_ERR_STAT, + + /* Reg 0x55 BUCK1 ERR IRQs */ + BD96801_BUCK1_PVIN_ERR_STAT, + BD96801_BUCK1_OVP_ERR_STAT, + BD96801_BUCK1_UVP_ERR_STAT, + BD96801_BUCK1_SHDN_ERR_STAT, + + /* Reg 0x56 BUCK2 ERR IRQs */ + BD96801_BUCK2_PVIN_ERR_STAT, + BD96801_BUCK2_OVP_ERR_STAT, + BD96801_BUCK2_UVP_ERR_STAT, + BD96801_BUCK2_SHDN_ERR_STAT, + + /* Reg 0x57 BUCK3 ERR IRQs */ + BD96801_BUCK3_PVIN_ERR_STAT, + BD96801_BUCK3_OVP_ERR_STAT, + BD96801_BUCK3_UVP_ERR_STAT, + BD96801_BUCK3_SHDN_ERR_STAT, + + /* Reg 0x58 BUCK4 ERR IRQs */ + BD96801_BUCK4_PVIN_ERR_STAT, + BD96801_BUCK4_OVP_ERR_STAT, + BD96801_BUCK4_UVP_ERR_STAT, + BD96801_BUCK4_SHDN_ERR_STAT, + + /* Reg 0x59 LDO5 ERR IRQs */ + BD96801_LDO5_PVIN_ERR_STAT, + BD96801_LDO5_OVP_ERR_STAT, + BD96801_LDO5_UVP_ERR_STAT, + BD96801_LDO5_SHDN_ERR_STAT, + + /* Reg 0x5a LDO6 ERR IRQs */ + BD96801_LDO6_PVIN_ERR_STAT, + BD96801_LDO6_OVP_ERR_STAT, + BD96801_LDO6_UVP_ERR_STAT, + BD96801_LDO6_SHDN_ERR_STAT, + + /* Reg 0x5b LDO7 ERR IRQs */ + BD96801_LDO7_PVIN_ERR_STAT, + BD96801_LDO7_OVP_ERR_STAT, + BD96801_LDO7_UVP_ERR_STAT, + BD96801_LDO7_SHDN_ERR_STAT, +}; + +/* INTB IRQs */ +enum { + /* Reg 0x5c (System INTB) */ + BD96801_TW_STAT, + BD96801_WDT_ERR_STAT, + BD96801_I2C_ERR_STAT, + BD96801_CHIP_IF_ERR_STAT, + + /* Reg 0x5d (BUCK1 INTB) */ + BD96801_BUCK1_OCPH_STAT, + BD96801_BUCK1_OCPL_STAT, + BD96801_BUCK1_OCPN_STAT, + BD96801_BUCK1_OVD_STAT, + BD96801_BUCK1_UVD_STAT, + BD96801_BUCK1_TW_CH_STAT, + + /* Reg 0x5e (BUCK2 INTB) */ + BD96801_BUCK2_OCPH_STAT, + BD96801_BUCK2_OCPL_STAT, + BD96801_BUCK2_OCPN_STAT, + BD96801_BUCK2_OVD_STAT, + BD96801_BUCK2_UVD_STAT, + BD96801_BUCK2_TW_CH_STAT, + + /* Reg 0x5f (BUCK3 INTB)*/ + BD96801_BUCK3_OCPH_STAT, + BD96801_BUCK3_OCPL_STAT, + BD96801_BUCK3_OCPN_STAT, + BD96801_BUCK3_OVD_STAT, + BD96801_BUCK3_UVD_STAT, + BD96801_BUCK3_TW_CH_STAT, + + /* Reg 0x60 (BUCK4 INTB)*/ + BD96801_BUCK4_OCPH_STAT, + BD96801_BUCK4_OCPL_STAT, + BD96801_BUCK4_OCPN_STAT, + BD96801_BUCK4_OVD_STAT, + BD96801_BUCK4_UVD_STAT, + BD96801_BUCK4_TW_CH_STAT, + + /* Reg 0x61 (LDO5 INTB) */ + BD96801_LDO5_OCPH_STAT, /* bit [0] */ + BD96801_LDO5_OVD_STAT, /* bit [3] */ + BD96801_LDO5_UVD_STAT, /* bit [4] */ + + /* Reg 0x62 (LDO6 INTB) */ + BD96801_LDO6_OCPH_STAT, /* bit [0] */ + BD96801_LDO6_OVD_STAT, /* bit [3] */ + BD96801_LDO6_UVD_STAT, /* bit [4] */ + + /* Reg 0x63 (LDO7 INTB) */ + BD96801_LDO7_OCPH_STAT, /* bit [0] */ + BD96801_LDO7_OVD_STAT, /* bit [3] */ + BD96801_LDO7_UVD_STAT, /* bit [4] */ +}; + +/* IRQ MASKs */ +#define BD96801_TW_STAT_MASK BIT(0) +#define BD96801_WDT_ERR_STAT_MASK BIT(1) +#define BD96801_I2C_ERR_STAT_MASK BIT(2) +#define BD96801_CHIP_IF_ERR_STAT_MASK BIT(3) + +#define BD96801_BUCK_OCPH_STAT_MASK BIT(0) +#define BD96801_BUCK_OCPL_STAT_MASK BIT(1) +#define BD96801_BUCK_OCPN_STAT_MASK BIT(2) +#define BD96801_BUCK_OVD_STAT_MASK BIT(3) +#define BD96801_BUCK_UVD_STAT_MASK BIT(4) +#define BD96801_BUCK_TW_CH_STAT_MASK BIT(5) + +#define BD96801_LDO_OCPH_STAT_MASK BIT(0) +#define BD96801_LDO_OVD_STAT_MASK BIT(3) +#define BD96801_LDO_UVD_STAT_MASK BIT(4) + +#endif diff --git a/include/linux/mfd/rohm-generic.h b/include/linux/mfd/rohm-generic.h index 4eeb22876bad..e7d4e6afe388 100644 --- a/include/linux/mfd/rohm-generic.h +++ b/include/linux/mfd/rohm-generic.h @@ -16,6 +16,7 @@ enum rohm_chip_type { ROHM_CHIP_TYPE_BD71828, ROHM_CHIP_TYPE_BD71837, ROHM_CHIP_TYPE_BD71847, + ROHM_CHIP_TYPE_BD96801, ROHM_CHIP_TYPE_AMOUNT }; diff --git a/include/linux/mfd/stm32-timers.h b/include/linux/mfd/stm32-timers.h index ca35af30745f..f09ba598c97a 100644 --- a/include/linux/mfd/stm32-timers.h +++ b/include/linux/mfd/stm32-timers.h @@ -12,84 +12,106 @@ #include <linux/dma-mapping.h> #include <linux/regmap.h> -#define TIM_CR1 0x00 /* Control Register 1 */ -#define TIM_CR2 0x04 /* Control Register 2 */ -#define TIM_SMCR 0x08 /* Slave mode control reg */ -#define TIM_DIER 0x0C /* DMA/interrupt register */ -#define TIM_SR 0x10 /* Status register */ -#define TIM_EGR 0x14 /* Event Generation Reg */ -#define TIM_CCMR1 0x18 /* Capt/Comp 1 Mode Reg */ -#define TIM_CCMR2 0x1C /* Capt/Comp 2 Mode Reg */ -#define TIM_CCER 0x20 /* Capt/Comp Enable Reg */ -#define TIM_CNT 0x24 /* Counter */ -#define TIM_PSC 0x28 /* Prescaler */ -#define TIM_ARR 0x2c /* Auto-Reload Register */ -#define TIM_CCR1 0x34 /* Capt/Comp Register 1 */ -#define TIM_CCR2 0x38 /* Capt/Comp Register 2 */ -#define TIM_CCR3 0x3C /* Capt/Comp Register 3 */ -#define TIM_CCR4 0x40 /* Capt/Comp Register 4 */ -#define TIM_BDTR 0x44 /* Break and Dead-Time Reg */ -#define TIM_DCR 0x48 /* DMA control register */ -#define TIM_DMAR 0x4C /* DMA register for transfer */ -#define TIM_TISEL 0x68 /* Input Selection */ +#define TIM_CR1 0x00 /* Control Register 1 */ +#define TIM_CR2 0x04 /* Control Register 2 */ +#define TIM_SMCR 0x08 /* Slave mode control reg */ +#define TIM_DIER 0x0C /* DMA/interrupt register */ +#define TIM_SR 0x10 /* Status register */ +#define TIM_EGR 0x14 /* Event Generation Reg */ +#define TIM_CCMR1 0x18 /* Capt/Comp 1 Mode Reg */ +#define TIM_CCMR2 0x1C /* Capt/Comp 2 Mode Reg */ +#define TIM_CCER 0x20 /* Capt/Comp Enable Reg */ +#define TIM_CNT 0x24 /* Counter */ +#define TIM_PSC 0x28 /* Prescaler */ +#define TIM_ARR 0x2c /* Auto-Reload Register */ +#define TIM_CCRx(x) (0x34 + 4 * ((x) - 1)) /* Capt/Comp Register x (x ∈ {1, .. 4}) */ +#define TIM_CCR1 TIM_CCRx(1) /* Capt/Comp Register 1 */ +#define TIM_CCR2 TIM_CCRx(2) /* Capt/Comp Register 2 */ +#define TIM_CCR3 TIM_CCRx(3) /* Capt/Comp Register 3 */ +#define TIM_CCR4 TIM_CCRx(4) /* Capt/Comp Register 4 */ +#define TIM_BDTR 0x44 /* Break and Dead-Time Reg */ +#define TIM_DCR 0x48 /* DMA control register */ +#define TIM_DMAR 0x4C /* DMA register for transfer */ +#define TIM_TISEL 0x68 /* Input Selection */ -#define TIM_CR1_CEN BIT(0) /* Counter Enable */ -#define TIM_CR1_DIR BIT(4) /* Counter Direction */ -#define TIM_CR1_ARPE BIT(7) /* Auto-reload Preload Ena */ -#define TIM_CR2_MMS (BIT(4) | BIT(5) | BIT(6)) /* Master mode selection */ -#define TIM_CR2_MMS2 GENMASK(23, 20) /* Master mode selection 2 */ -#define TIM_SMCR_SMS (BIT(0) | BIT(1) | BIT(2)) /* Slave mode selection */ -#define TIM_SMCR_TS (BIT(4) | BIT(5) | BIT(6)) /* Trigger selection */ -#define TIM_DIER_UIE BIT(0) /* Update interrupt */ -#define TIM_DIER_UDE BIT(8) /* Update DMA request Enable */ -#define TIM_DIER_CC1DE BIT(9) /* CC1 DMA request Enable */ -#define TIM_DIER_CC2DE BIT(10) /* CC2 DMA request Enable */ -#define TIM_DIER_CC3DE BIT(11) /* CC3 DMA request Enable */ -#define TIM_DIER_CC4DE BIT(12) /* CC4 DMA request Enable */ -#define TIM_DIER_COMDE BIT(13) /* COM DMA request Enable */ -#define TIM_DIER_TDE BIT(14) /* Trigger DMA request Enable */ -#define TIM_SR_UIF BIT(0) /* Update interrupt flag */ -#define TIM_EGR_UG BIT(0) /* Update Generation */ -#define TIM_CCMR_PE BIT(3) /* Channel Preload Enable */ -#define TIM_CCMR_M1 (BIT(6) | BIT(5)) /* Channel PWM Mode 1 */ -#define TIM_CCMR_CC1S (BIT(0) | BIT(1)) /* Capture/compare 1 sel */ -#define TIM_CCMR_IC1PSC GENMASK(3, 2) /* Input capture 1 prescaler */ -#define TIM_CCMR_CC2S (BIT(8) | BIT(9)) /* Capture/compare 2 sel */ -#define TIM_CCMR_IC2PSC GENMASK(11, 10) /* Input capture 2 prescaler */ -#define TIM_CCMR_CC1S_TI1 BIT(0) /* IC1/IC3 selects TI1/TI3 */ -#define TIM_CCMR_CC1S_TI2 BIT(1) /* IC1/IC3 selects TI2/TI4 */ -#define TIM_CCMR_CC2S_TI2 BIT(8) /* IC2/IC4 selects TI2/TI4 */ -#define TIM_CCMR_CC2S_TI1 BIT(9) /* IC2/IC4 selects TI1/TI3 */ -#define TIM_CCER_CC1E BIT(0) /* Capt/Comp 1 out Ena */ -#define TIM_CCER_CC1P BIT(1) /* Capt/Comp 1 Polarity */ -#define TIM_CCER_CC1NE BIT(2) /* Capt/Comp 1N out Ena */ -#define TIM_CCER_CC1NP BIT(3) /* Capt/Comp 1N Polarity */ -#define TIM_CCER_CC2E BIT(4) /* Capt/Comp 2 out Ena */ -#define TIM_CCER_CC2P BIT(5) /* Capt/Comp 2 Polarity */ -#define TIM_CCER_CC3E BIT(8) /* Capt/Comp 3 out Ena */ -#define TIM_CCER_CC3P BIT(9) /* Capt/Comp 3 Polarity */ -#define TIM_CCER_CC4E BIT(12) /* Capt/Comp 4 out Ena */ -#define TIM_CCER_CC4P BIT(13) /* Capt/Comp 4 Polarity */ -#define TIM_CCER_CCXE (BIT(0) | BIT(4) | BIT(8) | BIT(12)) -#define TIM_BDTR_BKE(x) BIT(12 + (x) * 12) /* Break input enable */ -#define TIM_BDTR_BKP(x) BIT(13 + (x) * 12) /* Break input polarity */ -#define TIM_BDTR_AOE BIT(14) /* Automatic Output Enable */ -#define TIM_BDTR_MOE BIT(15) /* Main Output Enable */ -#define TIM_BDTR_BKF(x) (0xf << (16 + (x) * 4)) -#define TIM_DCR_DBA GENMASK(4, 0) /* DMA base addr */ -#define TIM_DCR_DBL GENMASK(12, 8) /* DMA burst len */ +#define TIM_CR1_CEN BIT(0) /* Counter Enable */ +#define TIM_CR1_DIR BIT(4) /* Counter Direction */ +#define TIM_CR1_ARPE BIT(7) /* Auto-reload Preload Ena */ +#define TIM_CR2_MMS (BIT(4) | BIT(5) | BIT(6)) /* Master mode selection */ +#define TIM_CR2_MMS2 GENMASK(23, 20) /* Master mode selection 2 */ +#define TIM_SMCR_SMS (BIT(0) | BIT(1) | BIT(2)) /* Slave mode selection */ +#define TIM_SMCR_TS (BIT(4) | BIT(5) | BIT(6)) /* Trigger selection */ +#define TIM_DIER_UIE BIT(0) /* Update interrupt */ +#define TIM_DIER_CCxIE(x) BIT(1 + ((x) - 1)) /* CCx Interrupt Enable (x ∈ {1, .. 4}) */ +#define TIM_DIER_CC1IE TIM_DIER_CCxIE(1) /* CC1 Interrupt Enable */ +#define TIM_DIER_CC2IE TIM_DIER_CCxIE(2) /* CC2 Interrupt Enable */ +#define TIM_DIER_CC3IE TIM_DIER_CCxIE(3) /* CC3 Interrupt Enable */ +#define TIM_DIER_CC4IE TIM_DIER_CCxIE(4) /* CC4 Interrupt Enable */ +#define TIM_DIER_UDE BIT(8) /* Update DMA request Enable */ +#define TIM_DIER_CCxDE(x) BIT(9 + ((x) - 1)) /* CCx DMA request Enable (x ∈ {1, .. 4}) */ +#define TIM_DIER_CC1DE TIM_DIER_CCxDE(1) /* CC1 DMA request Enable */ +#define TIM_DIER_CC2DE TIM_DIER_CCxDE(2) /* CC2 DMA request Enable */ +#define TIM_DIER_CC3DE TIM_DIER_CCxDE(3) /* CC3 DMA request Enable */ +#define TIM_DIER_CC4DE TIM_DIER_CCxDE(4) /* CC4 DMA request Enable */ +#define TIM_DIER_COMDE BIT(13) /* COM DMA request Enable */ +#define TIM_DIER_TDE BIT(14) /* Trigger DMA request Enable */ +#define TIM_SR_UIF BIT(0) /* Update interrupt flag */ +#define TIM_SR_CC_IF(x) BIT((x) + 1) /* CC1, CC2, CC3, CC4 interrupt flag */ +#define TIM_EGR_UG BIT(0) /* Update Generation */ +#define TIM_CCMR_PE BIT(3) /* Channel Preload Enable */ +#define TIM_CCMR_M1 (BIT(6) | BIT(5)) /* Channel PWM Mode 1 */ +#define TIM_CCMR_CC1S (BIT(0) | BIT(1)) /* Capture/compare 1 sel */ +#define TIM_CCMR_IC1PSC GENMASK(3, 2) /* Input capture 1 prescaler */ +#define TIM_CCMR_CC2S (BIT(8) | BIT(9)) /* Capture/compare 2 sel */ +#define TIM_CCMR_IC2PSC GENMASK(11, 10) /* Input capture 2 prescaler */ +#define TIM_CCMR_CC1S_TI1 BIT(0) /* IC1/IC3 selects TI1/TI3 */ +#define TIM_CCMR_CC1S_TI2 BIT(1) /* IC1/IC3 selects TI2/TI4 */ +#define TIM_CCMR_CC2S_TI2 BIT(8) /* IC2/IC4 selects TI2/TI4 */ +#define TIM_CCMR_CC2S_TI1 BIT(9) /* IC2/IC4 selects TI1/TI3 */ +#define TIM_CCMR_CC3S (BIT(0) | BIT(1)) /* Capture/compare 3 sel */ +#define TIM_CCMR_CC4S (BIT(8) | BIT(9)) /* Capture/compare 4 sel */ +#define TIM_CCMR_CC3S_TI3 BIT(0) /* IC3 selects TI3 */ +#define TIM_CCMR_CC4S_TI4 BIT(8) /* IC4 selects TI4 */ +#define TIM_CCER_CCxE(x) BIT(0 + 4 * ((x) - 1)) /* Capt/Comp x out Ena (x ∈ {1, .. 4}) */ +#define TIM_CCER_CCxP(x) BIT(1 + 4 * ((x) - 1)) /* Capt/Comp x Polarity (x ∈ {1, .. 4}) */ +#define TIM_CCER_CCxNE(x) BIT(2 + 4 * ((x) - 1)) /* Capt/Comp xN out Ena (x ∈ {1, .. 4}) */ +#define TIM_CCER_CCxNP(x) BIT(3 + 4 * ((x) - 1)) /* Capt/Comp xN Polarity (x ∈ {1, .. 4}) */ +#define TIM_CCER_CC1E TIM_CCER_CCxE(1) /* Capt/Comp 1 out Ena */ +#define TIM_CCER_CC1P TIM_CCER_CCxP(1) /* Capt/Comp 1 Polarity */ +#define TIM_CCER_CC1NE TIM_CCER_CCxNE(1) /* Capt/Comp 1N out Ena */ +#define TIM_CCER_CC1NP TIM_CCER_CCxNP(1) /* Capt/Comp 1N Polarity */ +#define TIM_CCER_CC2E TIM_CCER_CCxE(2) /* Capt/Comp 2 out Ena */ +#define TIM_CCER_CC2P TIM_CCER_CCxP(2) /* Capt/Comp 2 Polarity */ +#define TIM_CCER_CC2NE TIM_CCER_CCxNE(2) /* Capt/Comp 2N out Ena */ +#define TIM_CCER_CC2NP TIM_CCER_CCxNP(2) /* Capt/Comp 2N Polarity */ +#define TIM_CCER_CC3E TIM_CCER_CCxE(3) /* Capt/Comp 3 out Ena */ +#define TIM_CCER_CC3P TIM_CCER_CCxP(3) /* Capt/Comp 3 Polarity */ +#define TIM_CCER_CC3NE TIM_CCER_CCxNE(3) /* Capt/Comp 3N out Ena */ +#define TIM_CCER_CC3NP TIM_CCER_CCxNP(3) /* Capt/Comp 3N Polarity */ +#define TIM_CCER_CC4E TIM_CCER_CCxE(4) /* Capt/Comp 4 out Ena */ +#define TIM_CCER_CC4P TIM_CCER_CCxP(4) /* Capt/Comp 4 Polarity */ +#define TIM_CCER_CC4NE TIM_CCER_CCxNE(4) /* Capt/Comp 4N out Ena */ +#define TIM_CCER_CC4NP TIM_CCER_CCxNP(4) /* Capt/Comp 4N Polarity */ +#define TIM_CCER_CCXE (BIT(0) | BIT(4) | BIT(8) | BIT(12)) +#define TIM_BDTR_BKE(x) BIT(12 + (x) * 12) /* Break input enable */ +#define TIM_BDTR_BKP(x) BIT(13 + (x) * 12) /* Break input polarity */ +#define TIM_BDTR_AOE BIT(14) /* Automatic Output Enable */ +#define TIM_BDTR_MOE BIT(15) /* Main Output Enable */ +#define TIM_BDTR_BKF(x) (0xf << (16 + (x) * 4)) +#define TIM_DCR_DBA GENMASK(4, 0) /* DMA base addr */ +#define TIM_DCR_DBL GENMASK(12, 8) /* DMA burst len */ -#define MAX_TIM_PSC 0xFFFF -#define MAX_TIM_ICPSC 0x3 -#define TIM_CR2_MMS_SHIFT 4 -#define TIM_CR2_MMS2_SHIFT 20 +#define MAX_TIM_PSC 0xFFFF +#define MAX_TIM_ICPSC 0x3 +#define TIM_CR2_MMS_SHIFT 4 +#define TIM_CR2_MMS2_SHIFT 20 #define TIM_SMCR_SMS_SLAVE_MODE_DISABLED 0 /* counts on internal clock when CEN=1 */ #define TIM_SMCR_SMS_ENCODER_MODE_1 1 /* counts TI1FP1 edges, depending on TI2FP2 level */ #define TIM_SMCR_SMS_ENCODER_MODE_2 2 /* counts TI2FP2 edges, depending on TI1FP1 level */ #define TIM_SMCR_SMS_ENCODER_MODE_3 3 /* counts on both TI1FP1 and TI2FP2 edges */ -#define TIM_SMCR_TS_SHIFT 4 -#define TIM_BDTR_BKF_MASK 0xF -#define TIM_BDTR_BKF_SHIFT(x) (16 + (x) * 4) +#define TIM_SMCR_TS_SHIFT 4 +#define TIM_BDTR_BKF_MASK 0xF +#define TIM_BDTR_BKF_SHIFT(x) (16 + (x) * 4) enum stm32_timers_dmas { STM32_TIMERS_DMA_CH1, diff --git a/include/linux/mfd/syscon.h b/include/linux/mfd/syscon.h index c315903f6dab..aad9c6b50463 100644 --- a/include/linux/mfd/syscon.h +++ b/include/linux/mfd/syscon.h @@ -28,6 +28,8 @@ struct regmap *syscon_regmap_lookup_by_phandle_args(struct device_node *np, unsigned int *out_args); struct regmap *syscon_regmap_lookup_by_phandle_optional(struct device_node *np, const char *property); +int of_syscon_register_regmap(struct device_node *np, + struct regmap *regmap); #else static inline struct regmap *device_node_to_regmap(struct device_node *np) { @@ -67,6 +69,12 @@ static inline struct regmap *syscon_regmap_lookup_by_phandle_optional( return NULL; } +static inline int of_syscon_register_regmap(struct device_node *np, + struct regmap *regmap) +{ + return -EOPNOTSUPP; +} + #endif #endif /* __LINUX_MFD_SYSCON_H__ */ diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h deleted file mode 100644 index eace8ea6cda0..000000000000 --- a/include/linux/mfd/tmio.h +++ /dev/null @@ -1,133 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef MFD_TMIO_H -#define MFD_TMIO_H - -#include <linux/device.h> -#include <linux/fb.h> -#include <linux/io.h> -#include <linux/jiffies.h> -#include <linux/mmc/card.h> -#include <linux/platform_device.h> -#include <linux/pm_runtime.h> - -#define tmio_ioread8(addr) readb(addr) -#define tmio_ioread16(addr) readw(addr) -#define tmio_ioread16_rep(r, b, l) readsw(r, b, l) -#define tmio_ioread32(addr) \ - (((u32)readw((addr))) | (((u32)readw((addr) + 2)) << 16)) - -#define tmio_iowrite8(val, addr) writeb((val), (addr)) -#define tmio_iowrite16(val, addr) writew((val), (addr)) -#define tmio_iowrite16_rep(r, b, l) writesw(r, b, l) -#define tmio_iowrite32(val, addr) \ - do { \ - writew((val), (addr)); \ - writew((val) >> 16, (addr) + 2); \ - } while (0) - -#define sd_config_write8(base, shift, reg, val) \ - tmio_iowrite8((val), (base) + ((reg) << (shift))) -#define sd_config_write16(base, shift, reg, val) \ - tmio_iowrite16((val), (base) + ((reg) << (shift))) -#define sd_config_write32(base, shift, reg, val) \ - do { \ - tmio_iowrite16((val), (base) + ((reg) << (shift))); \ - tmio_iowrite16((val) >> 16, (base) + ((reg + 2) << (shift))); \ - } while (0) - -/* tmio MMC platform flags */ -/* - * Some controllers can support a 2-byte block size when the bus width - * is configured in 4-bit mode. - */ -#define TMIO_MMC_BLKSZ_2BYTES BIT(1) -/* - * Some controllers can support SDIO IRQ signalling. - */ -#define TMIO_MMC_SDIO_IRQ BIT(2) - -/* Some features are only available or tested on R-Car Gen2 or later */ -#define TMIO_MMC_MIN_RCAR2 BIT(3) - -/* - * Some controllers require waiting for the SD bus to become - * idle before writing to some registers. - */ -#define TMIO_MMC_HAS_IDLE_WAIT BIT(4) - -/* - * Use the busy timeout feature. Probably all TMIO versions support it. Yet, - * we don't have documentation for old variants, so we enable only known good - * variants with this flag. Can be removed once all variants are known good. - */ -#define TMIO_MMC_USE_BUSY_TIMEOUT BIT(5) - -/* - * Some controllers have CMD12 automatically - * issue/non-issue register - */ -#define TMIO_MMC_HAVE_CMD12_CTRL BIT(7) - -/* Controller has some SDIO status bits which must be 1 */ -#define TMIO_MMC_SDIO_STATUS_SETBITS BIT(8) - -/* - * Some controllers have a 32-bit wide data port register - */ -#define TMIO_MMC_32BIT_DATA_PORT BIT(9) - -/* - * Some controllers allows to set SDx actual clock - */ -#define TMIO_MMC_CLK_ACTUAL BIT(10) - -/* Some controllers have a CBSY bit */ -#define TMIO_MMC_HAVE_CBSY BIT(11) - -struct dma_chan; - -/* - * data for the MMC controller - */ -struct tmio_mmc_data { - void *chan_priv_tx; - void *chan_priv_rx; - unsigned int hclk; - unsigned long capabilities; - unsigned long capabilities2; - unsigned long flags; - u32 ocr_mask; /* available voltages */ - dma_addr_t dma_rx_offset; - unsigned int max_blk_count; - unsigned short max_segs; - void (*set_pwr)(struct platform_device *host, int state); - void (*set_clk_div)(struct platform_device *host, int state); -}; - -/* - * data for the NAND controller - */ -struct tmio_nand_data { - struct nand_bbt_descr *badblock_pattern; - struct mtd_partition *partition; - unsigned int num_partitions; - const char *const *part_parsers; -}; - -#define FBIO_TMIO_ACC_WRITE 0x7C639300 -#define FBIO_TMIO_ACC_SYNC 0x7C639301 - -struct tmio_fb_data { - int (*lcd_set_power)(struct platform_device *fb_dev, - bool on); - int (*lcd_mode)(struct platform_device *fb_dev, - const struct fb_videomode *mode); - int num_modes; - struct fb_videomode *modes; - - /* in mm: size of screen */ - int height; - int width; -}; - -#endif diff --git a/include/linux/mfd/tps65912.h b/include/linux/mfd/tps65912.h index 860ec0a16c96..e5373c302722 100644 --- a/include/linux/mfd/tps65912.h +++ b/include/linux/mfd/tps65912.h @@ -314,6 +314,5 @@ struct tps65912 { extern const struct regmap_config tps65912_regmap_config; int tps65912_device_init(struct tps65912 *tps); -void tps65912_device_exit(struct tps65912 *tps); #endif /* __LINUX_MFD_TPS65912_H */ diff --git a/include/linux/mfd/tps6594.h b/include/linux/mfd/tps6594.h index 3f7c5e23cd4c..16543fd4d83e 100644 --- a/include/linux/mfd/tps6594.h +++ b/include/linux/mfd/tps6594.h @@ -18,12 +18,13 @@ enum pmic_id { TPS6594, TPS6593, LP8764, + TPS65224, }; /* Macro to get page index from register address */ #define TPS6594_REG_TO_PAGE(reg) ((reg) >> 8) -/* Registers for page 0 of TPS6594 */ +/* Registers for page 0 */ #define TPS6594_REG_DEV_REV 0x01 #define TPS6594_REG_NVM_CODE_1 0x02 @@ -56,9 +57,6 @@ enum pmic_id { #define TPS6594_REG_GPIOX_OUT(gpio_inst) (TPS6594_REG_GPIO_OUT_1 + (gpio_inst) / 8) #define TPS6594_REG_GPIOX_IN(gpio_inst) (TPS6594_REG_GPIO_IN_1 + (gpio_inst) / 8) -#define TPS6594_REG_GPIO_IN_1 0x3f -#define TPS6594_REG_GPIO_IN_2 0x40 - #define TPS6594_REG_RAIL_SEL_1 0x41 #define TPS6594_REG_RAIL_SEL_2 0x42 #define TPS6594_REG_RAIL_SEL_3 0x43 @@ -70,13 +68,15 @@ enum pmic_id { #define TPS6594_REG_FSM_TRIG_MASK_3 0x48 #define TPS6594_REG_MASK_BUCK1_2 0x49 +#define TPS65224_REG_MASK_BUCKS 0x49 #define TPS6594_REG_MASK_BUCK3_4 0x4a #define TPS6594_REG_MASK_BUCK5 0x4b #define TPS6594_REG_MASK_LDO1_2 0x4c +#define TPS65224_REG_MASK_LDOS 0x4c #define TPS6594_REG_MASK_LDO3_4 0x4d #define TPS6594_REG_MASK_VMON 0x4e -#define TPS6594_REG_MASK_GPIO1_8_FALL 0x4f -#define TPS6594_REG_MASK_GPIO1_8_RISE 0x50 +#define TPS6594_REG_MASK_GPIO_FALL 0x4f +#define TPS6594_REG_MASK_GPIO_RISE 0x50 #define TPS6594_REG_MASK_GPIO9_11 0x51 #define TPS6594_REG_MASK_STARTUP 0x52 #define TPS6594_REG_MASK_MISC 0x53 @@ -174,6 +174,10 @@ enum pmic_id { #define TPS6594_REG_REGISTER_LOCK 0xa1 +#define TPS65224_REG_SRAM_ACCESS_1 0xa2 +#define TPS65224_REG_SRAM_ACCESS_2 0xa3 +#define TPS65224_REG_SRAM_ADDR_CTRL 0xa4 +#define TPS65224_REG_RECOV_CNT_PFSM_INCR 0xa5 #define TPS6594_REG_MANUFACTURING_VER 0xa6 #define TPS6594_REG_CUSTOMER_NVM_ID_REG 0xa7 @@ -182,6 +186,9 @@ enum pmic_id { #define TPS6594_REG_SOFT_REBOOT_REG 0xab +#define TPS65224_REG_ADC_CTRL 0xac +#define TPS65224_REG_ADC_RESULT_REG_1 0xad +#define TPS65224_REG_ADC_RESULT_REG_2 0xae #define TPS6594_REG_RTC_SECONDS 0xb5 #define TPS6594_REG_RTC_MINUTES 0xb6 #define TPS6594_REG_RTC_HOURS 0xb7 @@ -199,6 +206,7 @@ enum pmic_id { #define TPS6594_REG_RTC_CTRL_1 0xc2 #define TPS6594_REG_RTC_CTRL_2 0xc3 +#define TPS65224_REG_STARTUP_CTRL 0xc3 #define TPS6594_REG_RTC_STATUS 0xc4 #define TPS6594_REG_RTC_INTERRUPTS 0xc5 #define TPS6594_REG_RTC_COMP_LSB 0xc6 @@ -214,13 +222,17 @@ enum pmic_id { #define TPS6594_REG_PFSM_DELAY_REG_2 0xce #define TPS6594_REG_PFSM_DELAY_REG_3 0xcf #define TPS6594_REG_PFSM_DELAY_REG_4 0xd0 +#define TPS65224_REG_ADC_GAIN_COMP_REG 0xd0 +#define TPS65224_REG_CRC_CALC_CONTROL 0xef +#define TPS65224_REG_REGMAP_USER_CRC_LOW 0xf0 +#define TPS65224_REG_REGMAP_USER_CRC_HIGH 0xf1 -/* Registers for page 1 of TPS6594 */ +/* Registers for page 1 */ #define TPS6594_REG_SERIAL_IF_CONFIG 0x11a #define TPS6594_REG_I2C1_ID 0x122 #define TPS6594_REG_I2C2_ID 0x123 -/* Registers for page 4 of TPS6594 */ +/* Registers for page 4 */ #define TPS6594_REG_WD_ANSWER_REG 0x401 #define TPS6594_REG_WD_QUESTION_ANSW_CNT 0x402 #define TPS6594_REG_WD_WIN1_CFG 0x403 @@ -241,16 +253,26 @@ enum pmic_id { #define TPS6594_BIT_BUCK_PLDN BIT(5) #define TPS6594_BIT_BUCK_RV_SEL BIT(7) -/* BUCKX_CONF register field definition */ +/* TPS6594 BUCKX_CONF register field definition */ #define TPS6594_MASK_BUCK_SLEW_RATE GENMASK(2, 0) #define TPS6594_MASK_BUCK_ILIM GENMASK(5, 3) -/* BUCKX_PG_WINDOW register field definition */ +/* TPS65224 BUCKX_CONF register field definition */ +#define TPS65224_MASK_BUCK_SLEW_RATE GENMASK(1, 0) + +/* TPS6594 BUCKX_PG_WINDOW register field definition */ #define TPS6594_MASK_BUCK_OV_THR GENMASK(2, 0) #define TPS6594_MASK_BUCK_UV_THR GENMASK(5, 3) -/* BUCKX VSET */ -#define TPS6594_MASK_BUCKS_VSET GENMASK(7, 0) +/* TPS65224 BUCKX_PG_WINDOW register field definition */ +#define TPS65224_MASK_BUCK_VMON_THR GENMASK(1, 0) + +/* TPS6594 BUCKX_VOUT register field definition */ +#define TPS6594_MASK_BUCKS_VSET GENMASK(7, 0) + +/* TPS65224 BUCKX_VOUT register field definition */ +#define TPS65224_MASK_BUCK1_VSET GENMASK(7, 0) +#define TPS65224_MASK_BUCKS_VSET GENMASK(6, 0) /* LDOX_CTRL register field definition */ #define TPS6594_BIT_LDO_EN BIT(0) @@ -258,6 +280,7 @@ enum pmic_id { #define TPS6594_BIT_LDO_VMON_EN BIT(4) #define TPS6594_MASK_LDO_PLDN GENMASK(6, 5) #define TPS6594_BIT_LDO_RV_SEL BIT(7) +#define TPS65224_BIT_LDO_DISCHARGE_EN BIT(5) /* LDORTC_CTRL register field definition */ #define TPS6594_BIT_LDORTC_DIS BIT(0) @@ -271,6 +294,9 @@ enum pmic_id { #define TPS6594_MASK_LDO_OV_THR GENMASK(2, 0) #define TPS6594_MASK_LDO_UV_THR GENMASK(5, 3) +/* LDOX_PG_WINDOW register field definition */ +#define TPS65224_MASK_LDO_VMON_THR GENMASK(1, 0) + /* VCCA_VMON_CTRL register field definition */ #define TPS6594_BIT_VMON_EN BIT(0) #define TPS6594_BIT_VMON1_EN BIT(1) @@ -278,10 +304,12 @@ enum pmic_id { #define TPS6594_BIT_VMON2_EN BIT(3) #define TPS6594_BIT_VMON2_RV_SEL BIT(4) #define TPS6594_BIT_VMON_DEGLITCH_SEL BIT(5) +#define TPS65224_BIT_VMON_DEGLITCH_SEL GENMASK(7, 5) /* VCCA_PG_WINDOW register field definition */ #define TPS6594_MASK_VCCA_OV_THR GENMASK(2, 0) #define TPS6594_MASK_VCCA_UV_THR GENMASK(5, 3) +#define TPS65224_MASK_VCCA_VMON_THR GENMASK(1, 0) #define TPS6594_BIT_VCCA_PG_SET BIT(6) /* VMONX_PG_WINDOW register field definition */ @@ -289,6 +317,9 @@ enum pmic_id { #define TPS6594_MASK_VMONX_UV_THR GENMASK(5, 3) #define TPS6594_BIT_VMONX_RANGE BIT(6) +/* VMONX_PG_WINDOW register field definition */ +#define TPS65224_MASK_VMONX_THR GENMASK(1, 0) + /* GPIOX_CONF register field definition */ #define TPS6594_BIT_GPIO_DIR BIT(0) #define TPS6594_BIT_GPIO_OD BIT(1) @@ -296,6 +327,8 @@ enum pmic_id { #define TPS6594_BIT_GPIO_PU_PD_EN BIT(3) #define TPS6594_BIT_GPIO_DEGLITCH_EN BIT(4) #define TPS6594_MASK_GPIO_SEL GENMASK(7, 5) +#define TPS65224_MASK_GPIO_SEL GENMASK(6, 5) +#define TPS65224_MASK_GPIO_SEL_GPIO6 GENMASK(7, 5) /* NPWRON_CONF register field definition */ #define TPS6594_BIT_NRSTOUT_OD BIT(0) @@ -305,6 +338,12 @@ enum pmic_id { #define TPS6594_BIT_ENABLE_POL BIT(5) #define TPS6594_MASK_NPWRON_SEL GENMASK(7, 6) +/* POWER_ON_CONFIG register field definition */ +#define TPS65224_BIT_NINT_ENDRV_PU_SEL BIT(0) +#define TPS65224_BIT_NINT_ENDRV_SEL BIT(1) +#define TPS65224_BIT_EN_PB_DEGL BIT(5) +#define TPS65224_MASK_EN_PB_VSENSE_CONFIG GENMASK(7, 6) + /* GPIO_OUT_X register field definition */ #define TPS6594_BIT_GPIOX_OUT(gpio_inst) BIT((gpio_inst) % 8) @@ -312,6 +351,12 @@ enum pmic_id { #define TPS6594_BIT_GPIOX_IN(gpio_inst) BIT((gpio_inst) % 8) #define TPS6594_BIT_NPWRON_IN BIT(3) +/* GPIO_OUT_X register field definition */ +#define TPS65224_BIT_GPIOX_OUT(gpio_inst) BIT((gpio_inst)) + +/* GPIO_IN_X register field definition */ +#define TPS65224_BIT_GPIOX_IN(gpio_inst) BIT((gpio_inst)) + /* RAIL_SEL_1 register field definition */ #define TPS6594_MASK_BUCK1_GRP_SEL GENMASK(1, 0) #define TPS6594_MASK_BUCK2_GRP_SEL GENMASK(3, 2) @@ -343,6 +388,9 @@ enum pmic_id { #define TPS6594_BIT_GPIOX_FSM_MASK(gpio_inst) BIT(((gpio_inst) << 1) % 8) #define TPS6594_BIT_GPIOX_FSM_MASK_POL(gpio_inst) BIT(((gpio_inst) << 1) % 8 + 1) +#define TPS65224_BIT_GPIOX_FSM_MASK(gpio_inst) BIT(((gpio_inst) << 1) % 6) +#define TPS65224_BIT_GPIOX_FSM_MASK_POL(gpio_inst) BIT(((gpio_inst) << 1) % 6 + 1) + /* MASK_BUCKX register field definition */ #define TPS6594_BIT_BUCKX_OV_MASK(buck_inst) BIT(((buck_inst) << 2) % 8) #define TPS6594_BIT_BUCKX_UV_MASK(buck_inst) BIT(((buck_inst) << 2) % 8 + 1) @@ -361,22 +409,46 @@ enum pmic_id { #define TPS6594_BIT_VMON2_OV_MASK BIT(5) #define TPS6594_BIT_VMON2_UV_MASK BIT(6) +/* MASK_BUCK Register field definition */ +#define TPS65224_BIT_BUCK1_UVOV_MASK BIT(0) +#define TPS65224_BIT_BUCK2_UVOV_MASK BIT(1) +#define TPS65224_BIT_BUCK3_UVOV_MASK BIT(2) +#define TPS65224_BIT_BUCK4_UVOV_MASK BIT(4) + +/* MASK_LDO_VMON register field definition */ +#define TPS65224_BIT_LDO1_UVOV_MASK BIT(0) +#define TPS65224_BIT_LDO2_UVOV_MASK BIT(1) +#define TPS65224_BIT_LDO3_UVOV_MASK BIT(2) +#define TPS65224_BIT_VCCA_UVOV_MASK BIT(4) +#define TPS65224_BIT_VMON1_UVOV_MASK BIT(5) +#define TPS65224_BIT_VMON2_UVOV_MASK BIT(6) + /* MASK_GPIOX register field definition */ #define TPS6594_BIT_GPIOX_FALL_MASK(gpio_inst) BIT((gpio_inst) < 8 ? \ (gpio_inst) : (gpio_inst) % 8) #define TPS6594_BIT_GPIOX_RISE_MASK(gpio_inst) BIT((gpio_inst) < 8 ? \ (gpio_inst) : (gpio_inst) % 8 + 3) +/* MASK_GPIOX register field definition */ +#define TPS65224_BIT_GPIOX_FALL_MASK(gpio_inst) BIT((gpio_inst)) +#define TPS65224_BIT_GPIOX_RISE_MASK(gpio_inst) BIT((gpio_inst)) /* MASK_STARTUP register field definition */ #define TPS6594_BIT_NPWRON_START_MASK BIT(0) #define TPS6594_BIT_ENABLE_MASK BIT(1) #define TPS6594_BIT_FSD_MASK BIT(4) #define TPS6594_BIT_SOFT_REBOOT_MASK BIT(5) +#define TPS65224_BIT_VSENSE_MASK BIT(0) +#define TPS65224_BIT_PB_SHORT_MASK BIT(2) /* MASK_MISC register field definition */ #define TPS6594_BIT_BIST_PASS_MASK BIT(0) #define TPS6594_BIT_EXT_CLK_MASK BIT(1) +#define TPS65224_BIT_REG_UNLOCK_MASK BIT(2) #define TPS6594_BIT_TWARN_MASK BIT(3) +#define TPS65224_BIT_PB_LONG_MASK BIT(4) +#define TPS65224_BIT_PB_FALL_MASK BIT(5) +#define TPS65224_BIT_PB_RISE_MASK BIT(6) +#define TPS65224_BIT_ADC_CONV_READY_MASK BIT(7) /* MASK_MODERATE_ERR register field definition */ #define TPS6594_BIT_BIST_FAIL_MASK BIT(1) @@ -391,6 +463,8 @@ enum pmic_id { #define TPS6594_BIT_ORD_SHUTDOWN_MASK BIT(1) #define TPS6594_BIT_MCU_PWR_ERR_MASK BIT(2) #define TPS6594_BIT_SOC_PWR_ERR_MASK BIT(3) +#define TPS65224_BIT_COMM_ERR_MASK BIT(4) +#define TPS65224_BIT_I2C2_ERR_MASK BIT(5) /* MASK_COMM_ERR register field definition */ #define TPS6594_BIT_COMM_FRM_ERR_MASK BIT(0) @@ -426,6 +500,12 @@ enum pmic_id { #define TPS6594_BIT_BUCK3_4_INT BIT(1) #define TPS6594_BIT_BUCK5_INT BIT(2) +/* INT_BUCK register field definition */ +#define TPS65224_BIT_BUCK1_UVOV_INT BIT(0) +#define TPS65224_BIT_BUCK2_UVOV_INT BIT(1) +#define TPS65224_BIT_BUCK3_UVOV_INT BIT(2) +#define TPS65224_BIT_BUCK4_UVOV_INT BIT(3) + /* INT_BUCKX register field definition */ #define TPS6594_BIT_BUCKX_OV_INT(buck_inst) BIT(((buck_inst) << 2) % 8) #define TPS6594_BIT_BUCKX_UV_INT(buck_inst) BIT(((buck_inst) << 2) % 8 + 1) @@ -437,6 +517,14 @@ enum pmic_id { #define TPS6594_BIT_LDO3_4_INT BIT(1) #define TPS6594_BIT_VCCA_INT BIT(4) +/* INT_LDO_VMON register field definition */ +#define TPS65224_BIT_LDO1_UVOV_INT BIT(0) +#define TPS65224_BIT_LDO2_UVOV_INT BIT(1) +#define TPS65224_BIT_LDO3_UVOV_INT BIT(2) +#define TPS65224_BIT_VCCA_UVOV_INT BIT(4) +#define TPS65224_BIT_VMON1_UVOV_INT BIT(5) +#define TPS65224_BIT_VMON2_UVOV_INT BIT(6) + /* INT_LDOX register field definition */ #define TPS6594_BIT_LDOX_OV_INT(ldo_inst) BIT(((ldo_inst) << 2) % 8) #define TPS6594_BIT_LDOX_UV_INT(ldo_inst) BIT(((ldo_inst) << 2) % 8 + 1) @@ -462,17 +550,32 @@ enum pmic_id { /* INT_GPIOX register field definition */ #define TPS6594_BIT_GPIOX_INT(gpio_inst) BIT(gpio_inst) +/* INT_GPIO register field definition */ +#define TPS65224_BIT_GPIO1_INT BIT(0) +#define TPS65224_BIT_GPIO2_INT BIT(1) +#define TPS65224_BIT_GPIO3_INT BIT(2) +#define TPS65224_BIT_GPIO4_INT BIT(3) +#define TPS65224_BIT_GPIO5_INT BIT(4) +#define TPS65224_BIT_GPIO6_INT BIT(5) + /* INT_STARTUP register field definition */ #define TPS6594_BIT_NPWRON_START_INT BIT(0) +#define TPS65224_BIT_VSENSE_INT BIT(0) #define TPS6594_BIT_ENABLE_INT BIT(1) #define TPS6594_BIT_RTC_INT BIT(2) +#define TPS65224_BIT_PB_SHORT_INT BIT(2) #define TPS6594_BIT_FSD_INT BIT(4) #define TPS6594_BIT_SOFT_REBOOT_INT BIT(5) /* INT_MISC register field definition */ #define TPS6594_BIT_BIST_PASS_INT BIT(0) #define TPS6594_BIT_EXT_CLK_INT BIT(1) +#define TPS65224_BIT_REG_UNLOCK_INT BIT(2) #define TPS6594_BIT_TWARN_INT BIT(3) +#define TPS65224_BIT_PB_LONG_INT BIT(4) +#define TPS65224_BIT_PB_FALL_INT BIT(5) +#define TPS65224_BIT_PB_RISE_INT BIT(6) +#define TPS65224_BIT_ADC_CONV_READY_INT BIT(7) /* INT_MODERATE_ERR register field definition */ #define TPS6594_BIT_TSD_ORD_INT BIT(0) @@ -488,6 +591,7 @@ enum pmic_id { #define TPS6594_BIT_TSD_IMM_INT BIT(0) #define TPS6594_BIT_VCCA_OVP_INT BIT(1) #define TPS6594_BIT_PFSM_ERR_INT BIT(2) +#define TPS65224_BIT_BG_XMON_INT BIT(3) /* INT_FSM_ERR register field definition */ #define TPS6594_BIT_IMM_SHUTDOWN_INT BIT(0) @@ -496,6 +600,7 @@ enum pmic_id { #define TPS6594_BIT_SOC_PWR_ERR_INT BIT(3) #define TPS6594_BIT_COMM_ERR_INT BIT(4) #define TPS6594_BIT_READBACK_ERR_INT BIT(5) +#define TPS65224_BIT_I2C2_ERR_INT BIT(5) #define TPS6594_BIT_ESM_INT BIT(6) #define TPS6594_BIT_WD_INT BIT(7) @@ -536,8 +641,18 @@ enum pmic_id { #define TPS6594_BIT_VMON2_OV_STAT BIT(5) #define TPS6594_BIT_VMON2_UV_STAT BIT(6) +/* STAT_LDO_VMON register field definition */ +#define TPS65224_BIT_LDO1_UVOV_STAT BIT(0) +#define TPS65224_BIT_LDO2_UVOV_STAT BIT(1) +#define TPS65224_BIT_LDO3_UVOV_STAT BIT(2) +#define TPS65224_BIT_VCCA_UVOV_STAT BIT(4) +#define TPS65224_BIT_VMON1_UVOV_STAT BIT(5) +#define TPS65224_BIT_VMON2_UVOV_STAT BIT(6) + /* STAT_STARTUP register field definition */ +#define TPS65224_BIT_VSENSE_STAT BIT(0) #define TPS6594_BIT_ENABLE_STAT BIT(1) +#define TPS65224_BIT_PB_LEVEL_STAT BIT(2) /* STAT_MISC register field definition */ #define TPS6594_BIT_EXT_CLK_STAT BIT(1) @@ -549,6 +664,7 @@ enum pmic_id { /* STAT_SEVERE_ERR register field definition */ #define TPS6594_BIT_TSD_IMM_STAT BIT(0) #define TPS6594_BIT_VCCA_OVP_STAT BIT(1) +#define TPS65224_BIT_BG_XMON_STAT BIT(3) /* STAT_READBACK_ERR register field definition */ #define TPS6594_BIT_EN_DRV_READBACK_STAT BIT(0) @@ -597,6 +713,8 @@ enum pmic_id { #define TPS6594_BIT_BB_CHARGER_EN BIT(0) #define TPS6594_BIT_BB_ICHR BIT(1) #define TPS6594_MASK_BB_VEOC GENMASK(3, 2) +#define TPS65224_BIT_I2C1_SPI_CRC_EN BIT(4) +#define TPS65224_BIT_I2C2_CRC_EN BIT(5) #define TPS6594_BB_EOC_RDY BIT(7) /* ENABLE_DRV_REG register field definition */ @@ -617,6 +735,7 @@ enum pmic_id { #define TPS6594_BIT_NRSTOUT_SOC_IN BIT(2) #define TPS6594_BIT_FORCE_EN_DRV_LOW BIT(3) #define TPS6594_BIT_SPMI_LPM_EN BIT(4) +#define TPS65224_BIT_TSD_DISABLE BIT(5) /* RECOV_CNT_REG_1 register field definition */ #define TPS6594_MASK_RECOV_CNT GENMASK(3, 0) @@ -671,15 +790,27 @@ enum pmic_id { /* ESM_SOC_START_REG register field definition */ #define TPS6594_BIT_ESM_SOC_START BIT(0) +/* ESM_MCU_START_REG register field definition */ +#define TPS65224_BIT_ESM_MCU_START BIT(0) + /* ESM_SOC_MODE_CFG register field definition */ #define TPS6594_MASK_ESM_SOC_ERR_CNT_TH GENMASK(3, 0) #define TPS6594_BIT_ESM_SOC_ENDRV BIT(5) #define TPS6594_BIT_ESM_SOC_EN BIT(6) #define TPS6594_BIT_ESM_SOC_MODE BIT(7) +/* ESM_MCU_MODE_CFG register field definition */ +#define TPS65224_MASK_ESM_MCU_ERR_CNT_TH GENMASK(3, 0) +#define TPS65224_BIT_ESM_MCU_ENDRV BIT(5) +#define TPS65224_BIT_ESM_MCU_EN BIT(6) +#define TPS65224_BIT_ESM_MCU_MODE BIT(7) + /* ESM_SOC_ERR_CNT_REG register field definition */ #define TPS6594_MASK_ESM_SOC_ERR_CNT GENMASK(4, 0) +/* ESM_MCU_ERR_CNT_REG register field definition */ +#define TPS6594_MASK_ESM_MCU_ERR_CNT GENMASK(4, 0) + /* REGISTER_LOCK register field definition */ #define TPS6594_BIT_REGISTER_LOCK_STATUS BIT(0) @@ -687,6 +818,29 @@ enum pmic_id { #define TPS6594_MASK_VMON1_SLEW_RATE GENMASK(2, 0) #define TPS6594_MASK_VMON2_SLEW_RATE GENMASK(5, 3) +/* SRAM_ACCESS_1 Register field definition */ +#define TPS65224_MASk_SRAM_UNLOCK_SEQ GENMASK(7, 0) + +/* SRAM_ACCESS_2 Register field definition */ +#define TPS65224_BIT_SRAM_WRITE_MODE BIT(0) +#define TPS65224_BIT_OTP_PROG_USER BIT(1) +#define TPS65224_BIT_OTP_PROG_PFSM BIT(2) +#define TPS65224_BIT_OTP_PROG_STATUS BIT(3) +#define TPS65224_BIT_SRAM_UNLOCKED BIT(6) +#define TPS65224_USER_PROG_ALLOWED BIT(7) + +/* SRAM_ADDR_CTRL Register field definition */ +#define TPS65224_MASk_SRAM_SEL GENMASK(1, 0) + +/* RECOV_CNT_PFSM_INCR Register field definition */ +#define TPS65224_BIT_INCREMENT_RECOV_CNT BIT(0) + +/* MANUFACTURING_VER Register field definition */ +#define TPS65224_MASK_SILICON_REV GENMASK(7, 0) + +/* CUSTOMER_NVM_ID_REG Register field definition */ +#define TPS65224_MASK_CUSTOMER_NVM_ID GENMASK(7, 0) + /* SOFT_REBOOT_REG register field definition */ #define TPS6594_BIT_SOFT_REBOOT BIT(0) @@ -755,14 +909,83 @@ enum pmic_id { #define TPS6594_BIT_I2C2_CRC_EN BIT(2) #define TPS6594_MASK_T_CRC GENMASK(7, 3) +/* ADC_CTRL Register field definition */ +#define TPS65224_BIT_ADC_START BIT(0) +#define TPS65224_BIT_ADC_CONT_CONV BIT(1) +#define TPS65224_BIT_ADC_THERMAL_SEL BIT(2) +#define TPS65224_BIT_ADC_RDIV_EN BIT(3) +#define TPS65224_BIT_ADC_STATUS BIT(7) + +/* ADC_RESULT_REG_1 Register field definition */ +#define TPS65224_MASK_ADC_RESULT_11_4 GENMASK(7, 0) + +/* ADC_RESULT_REG_2 Register field definition */ +#define TPS65224_MASK_ADC_RESULT_3_0 GENMASK(7, 4) + +/* STARTUP_CTRL Register field definition */ +#define TPS65224_MASK_STARTUP_DEST GENMASK(6, 5) +#define TPS65224_BIT_FIRST_STARTUP_DONE BIT(7) + +/* SCRATCH_PAD_REG_1 Register field definition */ +#define TPS6594_MASK_SCRATCH_PAD_1 GENMASK(7, 0) + +/* SCRATCH_PAD_REG_2 Register field definition */ +#define TPS6594_MASK_SCRATCH_PAD_2 GENMASK(7, 0) + +/* SCRATCH_PAD_REG_3 Register field definition */ +#define TPS6594_MASK_SCRATCH_PAD_3 GENMASK(7, 0) + +/* SCRATCH_PAD_REG_4 Register field definition */ +#define TPS6594_MASK_SCRATCH_PAD_4 GENMASK(7, 0) + +/* PFSM_DELAY_REG_1 Register field definition */ +#define TPS6594_MASK_PFSM_DELAY1 GENMASK(7, 0) + +/* PFSM_DELAY_REG_2 Register field definition */ +#define TPS6594_MASK_PFSM_DELAY2 GENMASK(7, 0) + +/* PFSM_DELAY_REG_3 Register field definition */ +#define TPS6594_MASK_PFSM_DELAY3 GENMASK(7, 0) + +/* PFSM_DELAY_REG_4 Register field definition */ +#define TPS6594_MASK_PFSM_DELAY4 GENMASK(7, 0) + +/* CRC_CALC_CONTROL Register field definition */ +#define TPS65224_BIT_RUN_CRC_BIST BIT(0) +#define TPS65224_BIT_RUN_CRC_UPDATE BIT(1) + +/* ADC_GAIN_COMP_REG Register field definition */ +#define TPS65224_MASK_ADC_GAIN_COMP GENMASK(7, 0) + +/* REGMAP_USER_CRC_LOW Register field definition */ +#define TPS65224_MASK_REGMAP_USER_CRC16_LOW GENMASK(7, 0) + +/* REGMAP_USER_CRC_HIGH Register field definition */ +#define TPS65224_MASK_REGMAP_USER_CRC16_HIGH GENMASK(7, 0) + +/* WD_ANSWER_REG Register field definition */ +#define TPS6594_MASK_WD_ANSWER GENMASK(7, 0) + /* WD_QUESTION_ANSW_CNT register field definition */ #define TPS6594_MASK_WD_QUESTION GENMASK(3, 0) #define TPS6594_MASK_WD_ANSW_CNT GENMASK(5, 4) +#define TPS65224_BIT_INT_TOP_STATUS BIT(7) + +/* WD WIN1_CFG register field definition */ +#define TPS6594_MASK_WD_WIN1_CFG GENMASK(6, 0) + +/* WD WIN2_CFG register field definition */ +#define TPS6594_MASK_WD_WIN2_CFG GENMASK(6, 0) + +/* WD LongWin register field definition */ +#define TPS6594_MASK_WD_LONGWIN_CFG GENMASK(7, 0) /* WD_MODE_REG register field definition */ #define TPS6594_BIT_WD_RETURN_LONGWIN BIT(0) #define TPS6594_BIT_WD_MODE_SELECT BIT(1) #define TPS6594_BIT_WD_PWRHOLD BIT(2) +#define TPS65224_BIT_WD_ENDRV_SEL BIT(6) +#define TPS65224_BIT_WD_CNT_SEL BIT(7) /* WD_QA_CFG register field definition */ #define TPS6594_MASK_WD_QUESTION_SEED GENMASK(3, 0) @@ -993,6 +1216,106 @@ enum tps6594_irqs { #define TPS6594_IRQ_NAME_ALARM "alarm" #define TPS6594_IRQ_NAME_POWERUP "powerup" +/* IRQs */ +enum tps65224_irqs { + /* INT_BUCK register */ + TPS65224_IRQ_BUCK1_UVOV, + TPS65224_IRQ_BUCK2_UVOV, + TPS65224_IRQ_BUCK3_UVOV, + TPS65224_IRQ_BUCK4_UVOV, + /* INT_LDO_VMON register */ + TPS65224_IRQ_LDO1_UVOV, + TPS65224_IRQ_LDO2_UVOV, + TPS65224_IRQ_LDO3_UVOV, + TPS65224_IRQ_VCCA_UVOV, + TPS65224_IRQ_VMON1_UVOV, + TPS65224_IRQ_VMON2_UVOV, + /* INT_GPIO register */ + TPS65224_IRQ_GPIO1, + TPS65224_IRQ_GPIO2, + TPS65224_IRQ_GPIO3, + TPS65224_IRQ_GPIO4, + TPS65224_IRQ_GPIO5, + TPS65224_IRQ_GPIO6, + /* INT_STARTUP register */ + TPS65224_IRQ_VSENSE, + TPS65224_IRQ_ENABLE, + TPS65224_IRQ_PB_SHORT, + TPS65224_IRQ_FSD, + TPS65224_IRQ_SOFT_REBOOT, + /* INT_MISC register */ + TPS65224_IRQ_BIST_PASS, + TPS65224_IRQ_EXT_CLK, + TPS65224_IRQ_REG_UNLOCK, + TPS65224_IRQ_TWARN, + TPS65224_IRQ_PB_LONG, + TPS65224_IRQ_PB_FALL, + TPS65224_IRQ_PB_RISE, + TPS65224_IRQ_ADC_CONV_READY, + /* INT_MODERATE_ERR register */ + TPS65224_IRQ_TSD_ORD, + TPS65224_IRQ_BIST_FAIL, + TPS65224_IRQ_REG_CRC_ERR, + TPS65224_IRQ_RECOV_CNT, + /* INT_SEVERE_ERR register */ + TPS65224_IRQ_TSD_IMM, + TPS65224_IRQ_VCCA_OVP, + TPS65224_IRQ_PFSM_ERR, + TPS65224_IRQ_BG_XMON, + /* INT_FSM_ERR register */ + TPS65224_IRQ_IMM_SHUTDOWN, + TPS65224_IRQ_ORD_SHUTDOWN, + TPS65224_IRQ_MCU_PWR_ERR, + TPS65224_IRQ_SOC_PWR_ERR, + TPS65224_IRQ_COMM_ERR, + TPS65224_IRQ_I2C2_ERR, +}; + +#define TPS65224_IRQ_NAME_BUCK1_UVOV "buck1_uvov" +#define TPS65224_IRQ_NAME_BUCK2_UVOV "buck2_uvov" +#define TPS65224_IRQ_NAME_BUCK3_UVOV "buck3_uvov" +#define TPS65224_IRQ_NAME_BUCK4_UVOV "buck4_uvov" +#define TPS65224_IRQ_NAME_LDO1_UVOV "ldo1_uvov" +#define TPS65224_IRQ_NAME_LDO2_UVOV "ldo2_uvov" +#define TPS65224_IRQ_NAME_LDO3_UVOV "ldo3_uvov" +#define TPS65224_IRQ_NAME_VCCA_UVOV "vcca_uvov" +#define TPS65224_IRQ_NAME_VMON1_UVOV "vmon1_uvov" +#define TPS65224_IRQ_NAME_VMON2_UVOV "vmon2_uvov" +#define TPS65224_IRQ_NAME_GPIO1 "gpio1" +#define TPS65224_IRQ_NAME_GPIO2 "gpio2" +#define TPS65224_IRQ_NAME_GPIO3 "gpio3" +#define TPS65224_IRQ_NAME_GPIO4 "gpio4" +#define TPS65224_IRQ_NAME_GPIO5 "gpio5" +#define TPS65224_IRQ_NAME_GPIO6 "gpio6" +#define TPS65224_IRQ_NAME_VSENSE "vsense" +#define TPS65224_IRQ_NAME_ENABLE "enable" +#define TPS65224_IRQ_NAME_PB_SHORT "pb_short" +#define TPS65224_IRQ_NAME_FSD "fsd" +#define TPS65224_IRQ_NAME_SOFT_REBOOT "soft_reboot" +#define TPS65224_IRQ_NAME_BIST_PASS "bist_pass" +#define TPS65224_IRQ_NAME_EXT_CLK "ext_clk" +#define TPS65224_IRQ_NAME_REG_UNLOCK "reg_unlock" +#define TPS65224_IRQ_NAME_TWARN "twarn" +#define TPS65224_IRQ_NAME_PB_LONG "pb_long" +#define TPS65224_IRQ_NAME_PB_FALL "pb_fall" +#define TPS65224_IRQ_NAME_PB_RISE "pb_rise" +#define TPS65224_IRQ_NAME_ADC_CONV_READY "adc_conv_ready" +#define TPS65224_IRQ_NAME_TSD_ORD "tsd_ord" +#define TPS65224_IRQ_NAME_BIST_FAIL "bist_fail" +#define TPS65224_IRQ_NAME_REG_CRC_ERR "reg_crc_err" +#define TPS65224_IRQ_NAME_RECOV_CNT "recov_cnt" +#define TPS65224_IRQ_NAME_TSD_IMM "tsd_imm" +#define TPS65224_IRQ_NAME_VCCA_OVP "vcca_ovp" +#define TPS65224_IRQ_NAME_PFSM_ERR "pfsm_err" +#define TPS65224_IRQ_NAME_BG_XMON "bg_xmon" +#define TPS65224_IRQ_NAME_IMM_SHUTDOWN "imm_shutdown" +#define TPS65224_IRQ_NAME_ORD_SHUTDOWN "ord_shutdown" +#define TPS65224_IRQ_NAME_MCU_PWR_ERR "mcu_pwr_err" +#define TPS65224_IRQ_NAME_SOC_PWR_ERR "soc_pwr_err" +#define TPS65224_IRQ_NAME_COMM_ERR "comm_err" +#define TPS65224_IRQ_NAME_I2C2_ERR "i2c2_err" +#define TPS65224_IRQ_NAME_POWERUP "powerup" + /** * struct tps6594 - device private data structure * @@ -1014,7 +1337,9 @@ struct tps6594 { struct regmap_irq_chip_data *irq_data; }; -bool tps6594_is_volatile_reg(struct device *dev, unsigned int reg); +extern const struct regmap_access_table tps6594_volatile_table; +extern const struct regmap_access_table tps65224_volatile_table; + int tps6594_device_init(struct tps6594 *tps, bool enable_crc); #endif /* __LINUX_MFD_TPS6594_H */ diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 77b8c0a26674..059dc94d20bb 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -290,6 +290,7 @@ struct mhi_controller_config { /** * struct mhi_controller - Master MHI controller structure + * @name: Device name of the MHI controller * @cntrl_dev: Pointer to the struct device of physical bus acting as the MHI * controller (required) * @mhi_dev: MHI device instance for the controller @@ -353,6 +354,7 @@ struct mhi_controller_config { * @read_reg: Read a MHI register via the physical link (required) * @write_reg: Write a MHI register via the physical link (required) * @reset: Controller specific reset function (optional) + * @edl_trigger: CB function to trigger EDL mode (optional) * @buffer_len: Bounce buffer length * @index: Index of the MHI controller instance * @bounce_buf: Use of bounce buffer @@ -366,6 +368,7 @@ struct mhi_controller_config { * they can be populated depending on the usecase. */ struct mhi_controller { + const char *name; struct device *cntrl_dev; struct mhi_device *mhi_dev; struct dentry *debugfs_dentry; @@ -435,6 +438,7 @@ struct mhi_controller { void (*write_reg)(struct mhi_controller *mhi_cntrl, void __iomem *addr, u32 val); void (*reset)(struct mhi_controller *mhi_cntrl); + int (*edl_trigger)(struct mhi_controller *mhi_cntrl); size_t buffer_len; int index; @@ -524,7 +528,7 @@ struct mhi_driver { struct device_driver driver; }; -#define to_mhi_driver(drv) container_of(drv, struct mhi_driver, driver) +#define to_mhi_driver(drv) container_of_const(drv, struct mhi_driver, driver) #define to_mhi_device(dev) container_of(dev, struct mhi_device, dev) /** @@ -630,13 +634,29 @@ int mhi_async_power_up(struct mhi_controller *mhi_cntrl); int mhi_sync_power_up(struct mhi_controller *mhi_cntrl); /** - * mhi_power_down - Start MHI power down sequence + * mhi_power_down - Power down the MHI device and also destroy the + * 'struct device' for the channels associated with it. + * See also mhi_power_down_keep_dev() which is a variant + * of this API that keeps the 'struct device' for channels + * (useful during suspend/hibernation). * @mhi_cntrl: MHI controller * @graceful: Link is still accessible, so do a graceful shutdown process */ void mhi_power_down(struct mhi_controller *mhi_cntrl, bool graceful); /** + * mhi_power_down_keep_dev - Power down the MHI device but keep the 'struct + * device' for the channels associated with it. + * This is a variant of 'mhi_power_down()' and + * useful in scenarios such as suspend/hibernation + * where destroying of the 'struct device' is not + * needed. + * @mhi_cntrl: MHI controller + * @graceful: Link is still accessible, so do a graceful shutdown process + */ +void mhi_power_down_keep_dev(struct mhi_controller *mhi_cntrl, bool graceful); + +/** * mhi_unprepare_after_power_down - Free any allocated memory after power down * @mhi_cntrl: MHI controller */ @@ -798,4 +818,13 @@ int mhi_queue_skb(struct mhi_device *mhi_dev, enum dma_data_direction dir, */ bool mhi_queue_is_full(struct mhi_device *mhi_dev, enum dma_data_direction dir); +/** + * mhi_get_channel_doorbell_offset - Get the channel doorbell offset + * @mhi_cntrl: MHI controller + * @chdb_offset: Read channel doorbell offset + * + * Return: 0 if the read succeeds, a negative error code otherwise + */ +int mhi_get_channel_doorbell_offset(struct mhi_controller *mhi_cntrl, u32 *chdb_offset); + #endif /* _MHI_H_ */ diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h index 11bf3212f782..7b40fc8cbe77 100644 --- a/include/linux/mhi_ep.h +++ b/include/linux/mhi_ep.h @@ -221,7 +221,7 @@ struct mhi_ep_driver { }; #define to_mhi_ep_device(dev) container_of(dev, struct mhi_ep_device, dev) -#define to_mhi_ep_driver(drv) container_of(drv, struct mhi_ep_driver, driver) +#define to_mhi_ep_driver(drv) container_of_const(drv, struct mhi_ep_driver, driver) /* * module_mhi_ep_driver() - Helper macro for drivers that don't do diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 2ce13e8a309b..644be30b69c8 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -63,8 +63,6 @@ extern const char *migrate_reason_names[MR_TYPES]; #ifdef CONFIG_MIGRATION void putback_movable_pages(struct list_head *l); -int migrate_folio_extra(struct address_space *mapping, struct folio *dst, - struct folio *src, enum migrate_mode mode, int extra_count); int migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode); int migrate_pages(struct list_head *l, new_folio_t new, free_folio_t free, @@ -78,7 +76,6 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, void migration_entry_wait_on_locked(swp_entry_t entry, spinlock_t *ptl) __releases(ptl); void folio_migrate_flags(struct folio *newfolio, struct folio *folio); -void folio_migrate_copy(struct folio *newfolio, struct folio *folio); int folio_migrate_mapping(struct address_space *mapping, struct folio *newfolio, struct folio *folio, int extra_count); @@ -142,9 +139,16 @@ const struct movable_operations *page_movable_ops(struct page *page) } #ifdef CONFIG_NUMA_BALANCING +int migrate_misplaced_folio_prepare(struct folio *folio, + struct vm_area_struct *vma, int node); int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma, int node); #else +static inline int migrate_misplaced_folio_prepare(struct folio *folio, + struct vm_area_struct *vma, int node) +{ + return -EAGAIN; /* can't migrate now */ +} static inline int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma, int node) { diff --git a/include/linux/migrate_mode.h b/include/linux/migrate_mode.h index f37cc03f9369..265c4328b36a 100644 --- a/include/linux/migrate_mode.h +++ b/include/linux/migrate_mode.h @@ -7,16 +7,11 @@ * on most operations but not ->writepage as the potential stall time * is too significant * MIGRATE_SYNC will block when migrating pages - * MIGRATE_SYNC_NO_COPY will block when migrating pages but will not copy pages - * with the CPU. Instead, page copy happens outside the migratepage() - * callback and is likely using a DMA engine. See migrate_vma() and HMM - * (mm/hmm.c) for users of this mode. */ enum migrate_mode { MIGRATE_ASYNC, MIGRATE_SYNC_LIGHT, MIGRATE_SYNC, - MIGRATE_SYNC_NO_COPY, }; enum migrate_reason { @@ -29,6 +24,7 @@ enum migrate_reason { MR_CONTIG_RANGE, MR_LONGTERM_PIN, MR_DEMOTION, + MR_DAMON, MR_TYPES }; diff --git a/include/linux/mii_timestamper.h b/include/linux/mii_timestamper.h index 26b04f73f214..995db62570f9 100644 --- a/include/linux/mii_timestamper.h +++ b/include/linux/mii_timestamper.h @@ -59,7 +59,7 @@ struct mii_timestamper { struct phy_device *phydev); int (*ts_info)(struct mii_timestamper *mii_ts, - struct ethtool_ts_info *ts_info); + struct kernel_ethtool_ts_info *ts_info); struct device *device; }; diff --git a/include/linux/min_heap.h b/include/linux/min_heap.h index d52daf45861b..43a7b9dcf15e 100644 --- a/include/linux/min_heap.h +++ b/include/linux/min_heap.h @@ -7,46 +7,89 @@ #include <linux/types.h> /** - * struct min_heap - Data structure to hold a min-heap. - * @data: Start of array holding the heap elements. + * Data structure to hold a min-heap. * @nr: Number of elements currently in the heap. * @size: Maximum number of elements that can be held in current storage. + * @data: Pointer to the start of array holding the heap elements. + * @preallocated: Start of the static preallocated array holding the heap elements. */ -struct min_heap { - void *data; - int nr; - int size; -}; +#define MIN_HEAP_PREALLOCATED(_type, _name, _nr) \ +struct _name { \ + int nr; \ + int size; \ + _type *data; \ + _type preallocated[_nr]; \ +} + +#define DEFINE_MIN_HEAP(_type, _name) MIN_HEAP_PREALLOCATED(_type, _name, 0) + +typedef DEFINE_MIN_HEAP(char, min_heap_char) min_heap_char; + +#define __minheap_cast(_heap) (typeof((_heap)->data[0]) *) +#define __minheap_obj_size(_heap) sizeof((_heap)->data[0]) /** * struct min_heap_callbacks - Data/functions to customise the min_heap. - * @elem_size: The nr of each element in bytes. * @less: Partial order function for this heap. * @swp: Swap elements function. */ struct min_heap_callbacks { - int elem_size; - bool (*less)(const void *lhs, const void *rhs); - void (*swp)(void *lhs, void *rhs); + bool (*less)(const void *lhs, const void *rhs, void *args); + void (*swp)(void *lhs, void *rhs, void *args); }; +/* Initialize a min-heap. */ +static __always_inline +void __min_heap_init(min_heap_char *heap, void *data, int size) +{ + heap->nr = 0; + heap->size = size; + if (data) + heap->data = data; + else + heap->data = heap->preallocated; +} + +#define min_heap_init(_heap, _data, _size) \ + __min_heap_init((min_heap_char *)_heap, _data, _size) + +/* Get the minimum element from the heap. */ +static __always_inline +void *__min_heap_peek(struct min_heap_char *heap) +{ + return heap->nr ? heap->data : NULL; +} + +#define min_heap_peek(_heap) \ + (__minheap_cast(_heap) __min_heap_peek((min_heap_char *)_heap)) + +/* Check if the heap is full. */ +static __always_inline +bool __min_heap_full(min_heap_char *heap) +{ + return heap->nr == heap->size; +} + +#define min_heap_full(_heap) \ + __min_heap_full((min_heap_char *)_heap) + /* Sift the element at pos down the heap. */ static __always_inline -void min_heapify(struct min_heap *heap, int pos, - const struct min_heap_callbacks *func) +void __min_heap_sift_down(min_heap_char *heap, int pos, size_t elem_size, + const struct min_heap_callbacks *func, void *args) { void *left, *right; void *data = heap->data; - void *root = data + pos * func->elem_size; + void *root = data + pos * elem_size; int i = pos, j; /* Find the sift-down path all the way to the leaves. */ for (;;) { if (i * 2 + 2 >= heap->nr) break; - left = data + (i * 2 + 1) * func->elem_size; - right = data + (i * 2 + 2) * func->elem_size; - i = func->less(left, right) ? i * 2 + 1 : i * 2 + 2; + left = data + (i * 2 + 1) * elem_size; + right = data + (i * 2 + 2) * elem_size; + i = func->less(left, right, args) ? i * 2 + 1 : i * 2 + 2; } /* Special case for the last leaf with no sibling. */ @@ -54,83 +97,140 @@ void min_heapify(struct min_heap *heap, int pos, i = i * 2 + 1; /* Backtrack to the correct location. */ - while (i != pos && func->less(root, data + i * func->elem_size)) + while (i != pos && func->less(root, data + i * elem_size, args)) i = (i - 1) / 2; /* Shift the element into its correct place. */ j = i; while (i != pos) { i = (i - 1) / 2; - func->swp(data + i * func->elem_size, data + j * func->elem_size); + func->swp(data + i * elem_size, data + j * elem_size, args); + } +} + +#define min_heap_sift_down(_heap, _pos, _func, _args) \ + __min_heap_sift_down((min_heap_char *)_heap, _pos, __minheap_obj_size(_heap), _func, _args) + +/* Sift up ith element from the heap, O(log2(nr)). */ +static __always_inline +void __min_heap_sift_up(min_heap_char *heap, size_t elem_size, size_t idx, + const struct min_heap_callbacks *func, void *args) +{ + void *data = heap->data; + size_t parent; + + while (idx) { + parent = (idx - 1) / 2; + if (func->less(data + parent * elem_size, data + idx * elem_size, args)) + break; + func->swp(data + parent * elem_size, data + idx * elem_size, args); + idx = parent; } } +#define min_heap_sift_up(_heap, _idx, _func, _args) \ + __min_heap_sift_up((min_heap_char *)_heap, __minheap_obj_size(_heap), _idx, _func, _args) + /* Floyd's approach to heapification that is O(nr). */ static __always_inline -void min_heapify_all(struct min_heap *heap, - const struct min_heap_callbacks *func) +void __min_heapify_all(min_heap_char *heap, size_t elem_size, + const struct min_heap_callbacks *func, void *args) { int i; for (i = heap->nr / 2 - 1; i >= 0; i--) - min_heapify(heap, i, func); + __min_heap_sift_down(heap, i, elem_size, func, args); } +#define min_heapify_all(_heap, _func, _args) \ + __min_heapify_all((min_heap_char *)_heap, __minheap_obj_size(_heap), _func, _args) + /* Remove minimum element from the heap, O(log2(nr)). */ static __always_inline -void min_heap_pop(struct min_heap *heap, - const struct min_heap_callbacks *func) +bool __min_heap_pop(min_heap_char *heap, size_t elem_size, + const struct min_heap_callbacks *func, void *args) { void *data = heap->data; if (WARN_ONCE(heap->nr <= 0, "Popping an empty heap")) - return; + return false; /* Place last element at the root (position 0) and then sift down. */ heap->nr--; - memcpy(data, data + (heap->nr * func->elem_size), func->elem_size); - min_heapify(heap, 0, func); + memcpy(data, data + (heap->nr * elem_size), elem_size); + __min_heap_sift_down(heap, 0, elem_size, func, args); + + return true; } +#define min_heap_pop(_heap, _func, _args) \ + __min_heap_pop((min_heap_char *)_heap, __minheap_obj_size(_heap), _func, _args) + /* * Remove the minimum element and then push the given element. The * implementation performs 1 sift (O(log2(nr))) and is therefore more * efficient than a pop followed by a push that does 2. */ static __always_inline -void min_heap_pop_push(struct min_heap *heap, - const void *element, - const struct min_heap_callbacks *func) +void __min_heap_pop_push(min_heap_char *heap, + const void *element, size_t elem_size, + const struct min_heap_callbacks *func, + void *args) { - memcpy(heap->data, element, func->elem_size); - min_heapify(heap, 0, func); + memcpy(heap->data, element, elem_size); + __min_heap_sift_down(heap, 0, elem_size, func, args); } +#define min_heap_pop_push(_heap, _element, _func, _args) \ + __min_heap_pop_push((min_heap_char *)_heap, _element, __minheap_obj_size(_heap), _func, _args) + /* Push an element on to the heap, O(log2(nr)). */ static __always_inline -void min_heap_push(struct min_heap *heap, const void *element, - const struct min_heap_callbacks *func) +bool __min_heap_push(min_heap_char *heap, const void *element, size_t elem_size, + const struct min_heap_callbacks *func, void *args) { void *data = heap->data; - void *child, *parent; int pos; if (WARN_ONCE(heap->nr >= heap->size, "Pushing on a full heap")) - return; + return false; /* Place at the end of data. */ pos = heap->nr; - memcpy(data + (pos * func->elem_size), element, func->elem_size); + memcpy(data + (pos * elem_size), element, elem_size); heap->nr++; /* Sift child at pos up. */ - for (; pos > 0; pos = (pos - 1) / 2) { - child = data + (pos * func->elem_size); - parent = data + ((pos - 1) / 2) * func->elem_size; - if (func->less(parent, child)) - break; - func->swp(parent, child); - } + __min_heap_sift_up(heap, elem_size, pos, func, args); + + return true; } +#define min_heap_push(_heap, _element, _func, _args) \ + __min_heap_push((min_heap_char *)_heap, _element, __minheap_obj_size(_heap), _func, _args) + +/* Remove ith element from the heap, O(log2(nr)). */ +static __always_inline +bool __min_heap_del(min_heap_char *heap, size_t elem_size, size_t idx, + const struct min_heap_callbacks *func, void *args) +{ + void *data = heap->data; + + if (WARN_ONCE(heap->nr <= 0, "Popping an empty heap")) + return false; + + /* Place last element at the root (position 0) and then sift down. */ + heap->nr--; + if (idx == heap->nr) + return true; + func->swp(data + (idx * elem_size), data + (heap->nr * elem_size), args); + __min_heap_sift_up(heap, elem_size, idx, func, args); + __min_heap_sift_down(heap, idx, elem_size, func, args); + + return true; +} + +#define min_heap_del(_heap, _idx, _func, _args) \ + __min_heap_del((min_heap_char *)_heap, __minheap_obj_size(_heap), _idx, _func, _args) + #endif /* _LINUX_MIN_HEAP_H */ diff --git a/include/linux/minmax.h b/include/linux/minmax.h index 2ec559284a9f..98008dd92153 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -26,56 +26,100 @@ #define __typecheck(x, y) \ (!!(sizeof((typeof(x) *)1 == (typeof(y) *)1))) -/* is_signed_type() isn't a constexpr for pointer types */ -#define __is_signed(x) \ - __builtin_choose_expr(__is_constexpr(is_signed_type(typeof(x))), \ - is_signed_type(typeof(x)), 0) +/* + * __sign_use for integer expressions: + * bit #0 set if ok for unsigned comparisons + * bit #1 set if ok for signed comparisons + * + * In particular, statically non-negative signed integer + * expressions are ok for both. + * + * NOTE! Unsigned types smaller than 'int' are implicitly + * converted to 'int' in expressions, and are accepted for + * signed conversions for now. This is debatable. + * + * Note that 'x' is the original expression, and 'ux' is + * the unique variable that contains the value. + * + * We use 'ux' for pure type checking, and 'x' for when + * we need to look at the value (but without evaluating + * it for side effects! Careful to only ever evaluate it + * with sizeof() or __builtin_constant_p() etc). + * + * Pointers end up being checked by the normal C type + * rules at the actual comparison, and these expressions + * only need to be careful to not cause warnings for + * pointer use. + */ +#define __signed_type_use(x,ux) (2+__is_nonneg(x,ux)) +#define __unsigned_type_use(x,ux) (1+2*(sizeof(ux)<4)) +#define __sign_use(x,ux) (is_signed_type(typeof(ux))? \ + __signed_type_use(x,ux):__unsigned_type_use(x,ux)) -/* True for a non-negative signed int constant */ -#define __is_noneg_int(x) \ - (__builtin_choose_expr(__is_constexpr(x) && __is_signed(x), x, -1) >= 0) +/* + * To avoid warnings about casting pointers to integers + * of different sizes, we need that special sign type. + * + * On 64-bit we can just always use 'long', since any + * integer or pointer type can just be cast to that. + * + * This does not work for 128-bit signed integers since + * the cast would truncate them, but we do not use s128 + * types in the kernel (we do use 'u128', but they will + * be handled by the !is_signed_type() case). + * + * NOTE! The cast is there only to avoid any warnings + * from when values that aren't signed integer types. + */ +#ifdef CONFIG_64BIT + #define __signed_type(ux) long +#else + #define __signed_type(ux) typeof(__builtin_choose_expr(sizeof(ux)>4,1LL,1L)) +#endif +#define __is_nonneg(x,ux) statically_true((__signed_type(ux))(x)>=0) + +#define __types_ok(x,y,ux,uy) \ + (__sign_use(x,ux) & __sign_use(y,uy)) -#define __types_ok(x, y) \ - (__is_signed(x) == __is_signed(y) || \ - __is_signed((x) + 0) == __is_signed((y) + 0) || \ - __is_noneg_int(x) || __is_noneg_int(y)) +#define __types_ok3(x,y,z,ux,uy,uz) \ + (__sign_use(x,ux) & __sign_use(y,uy) & __sign_use(z,uz)) #define __cmp_op_min < #define __cmp_op_max > #define __cmp(op, x, y) ((x) __cmp_op_##op (y) ? (x) : (y)) -#define __cmp_once(op, x, y, unique_x, unique_y) ({ \ - typeof(x) unique_x = (x); \ - typeof(y) unique_y = (y); \ - static_assert(__types_ok(x, y), \ - #op "(" #x ", " #y ") signedness error, fix types or consider u" #op "() before " #op "_t()"); \ - __cmp(op, unique_x, unique_y); }) +#define __cmp_once_unique(op, type, x, y, ux, uy) \ + ({ type ux = (x); type uy = (y); __cmp(op, ux, uy); }) + +#define __cmp_once(op, type, x, y) \ + __cmp_once_unique(op, type, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_)) + +#define __careful_cmp_once(op, x, y, ux, uy) ({ \ + __auto_type ux = (x); __auto_type uy = (y); \ + BUILD_BUG_ON_MSG(!__types_ok(x,y,ux,uy), \ + #op"("#x", "#y") signedness error"); \ + __cmp(op, ux, uy); }) -#define __careful_cmp(op, x, y) \ - __builtin_choose_expr(__is_constexpr((x) - (y)), \ - __cmp(op, x, y), \ - __cmp_once(op, x, y, __UNIQUE_ID(__x), __UNIQUE_ID(__y))) +#define __careful_cmp(op, x, y) \ + __careful_cmp_once(op, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_)) #define __clamp(val, lo, hi) \ ((val) >= (hi) ? (hi) : ((val) <= (lo) ? (lo) : (val))) -#define __clamp_once(val, lo, hi, unique_val, unique_lo, unique_hi) ({ \ - typeof(val) unique_val = (val); \ - typeof(lo) unique_lo = (lo); \ - typeof(hi) unique_hi = (hi); \ +#define __clamp_once(val, lo, hi, uval, ulo, uhi) ({ \ + __auto_type uval = (val); \ + __auto_type ulo = (lo); \ + __auto_type uhi = (hi); \ static_assert(__builtin_choose_expr(__is_constexpr((lo) > (hi)), \ (lo) <= (hi), true), \ "clamp() low limit " #lo " greater than high limit " #hi); \ - static_assert(__types_ok(val, lo), "clamp() 'lo' signedness error"); \ - static_assert(__types_ok(val, hi), "clamp() 'hi' signedness error"); \ - __clamp(unique_val, unique_lo, unique_hi); }) + BUILD_BUG_ON_MSG(!__types_ok3(val,lo,hi,uval,ulo,uhi), \ + "clamp("#val", "#lo", "#hi") signedness error"); \ + __clamp(uval, ulo, uhi); }) -#define __careful_clamp(val, lo, hi) ({ \ - __builtin_choose_expr(__is_constexpr((val) - (lo) + (hi)), \ - __clamp(val, lo, hi), \ - __clamp_once(val, lo, hi, __UNIQUE_ID(__val), \ - __UNIQUE_ID(__lo), __UNIQUE_ID(__hi))); }) +#define __careful_clamp(val, lo, hi) \ + __clamp_once(val, lo, hi, __UNIQUE_ID(v_), __UNIQUE_ID(l_), __UNIQUE_ID(h_)) /** * min - return minimum of two values of the same or compatible types @@ -108,13 +152,20 @@ #define umax(x, y) \ __careful_cmp(max, (x) + 0u + 0ul + 0ull, (y) + 0u + 0ul + 0ull) +#define __careful_op3(op, x, y, z, ux, uy, uz) ({ \ + __auto_type ux = (x); __auto_type uy = (y);__auto_type uz = (z);\ + BUILD_BUG_ON_MSG(!__types_ok3(x,y,z,ux,uy,uz), \ + #op"3("#x", "#y", "#z") signedness error"); \ + __cmp(op, ux, __cmp(op, uy, uz)); }) + /** * min3 - return minimum of three values * @x: first value * @y: second value * @z: third value */ -#define min3(x, y, z) min((typeof(x))min(x, y), z) +#define min3(x, y, z) \ + __careful_op3(min, x, y, z, __UNIQUE_ID(x_), __UNIQUE_ID(y_), __UNIQUE_ID(z_)) /** * max3 - return maximum of three values @@ -122,7 +173,8 @@ * @y: second value * @z: third value */ -#define max3(x, y, z) max((typeof(x))max(x, y), z) +#define max3(x, y, z) \ + __careful_op3(max, x, y, z, __UNIQUE_ID(x_), __UNIQUE_ID(y_), __UNIQUE_ID(z_)) /** * min_not_zero - return the minimum that is _not_ zero, unless both are zero @@ -158,7 +210,7 @@ * @x: first value * @y: second value */ -#define min_t(type, x, y) __careful_cmp(min, (type)(x), (type)(y)) +#define min_t(type, x, y) __cmp_once(min, type, x, y) /** * max_t - return maximum of two values, using the specified type @@ -166,7 +218,7 @@ * @x: first value * @y: second value */ -#define max_t(type, x, y) __careful_cmp(max, (type)(x), (type)(y)) +#define max_t(type, x, y) __cmp_once(max, type, x, y) /* * Do not check the array parameter using __must_be_array(). @@ -270,4 +322,13 @@ static inline bool in_range32(u32 val, u32 start, u32 len) #define swap(a, b) \ do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) +/* + * Use these carefully: no type checking, and uses the arguments + * multiple times. Use for obvious constants only. + */ +#define MIN(a,b) __cmp(min,a,b) +#define MAX(a,b) __cmp(max,a,b) +#define MIN_T(type,a,b) __cmp(min,(type)(a),(type)(b)) +#define MAX_T(type,a,b) __cmp(max,(type)(a),(type)(b)) + #endif /* _LINUX_MINMAX_H */ diff --git a/include/linux/misc/keba.h b/include/linux/misc/keba.h new file mode 100644 index 000000000000..323b31a847c5 --- /dev/null +++ b/include/linux/misc/keba.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2024, KEBA Industrial Automation Gmbh */ + +#ifndef _LINUX_MISC_KEBA_H +#define _LINUX_MISC_KEBA_H + +#include <linux/auxiliary_bus.h> + +struct i2c_board_info; + +/** + * struct keba_i2c_auxdev - KEBA I2C auxiliary device + * @auxdev: auxiliary device object + * @io: address range of I2C controller IO memory + * @info_size: number of I2C devices to be probed + * @info: I2C devices to be probed + */ +struct keba_i2c_auxdev { + struct auxiliary_device auxdev; + struct resource io; + int info_size; + struct i2c_board_info *info; +}; + +#endif /* _LINUX_MISC_KEBA_H */ diff --git a/include/linux/misc_cgroup.h b/include/linux/misc_cgroup.h index e799b1f8d05b..49eef10c8e59 100644 --- a/include/linux/misc_cgroup.h +++ b/include/linux/misc_cgroup.h @@ -9,15 +9,16 @@ #define _MISC_CGROUP_H_ /** - * Types of misc cgroup entries supported by the host. + * enum misc_res_type - Types of misc cgroup entries supported by the host. */ enum misc_res_type { #ifdef CONFIG_KVM_AMD_SEV - /* AMD SEV ASIDs resource */ + /** @MISC_CG_RES_SEV: AMD SEV ASIDs resource */ MISC_CG_RES_SEV, - /* AMD SEV-ES ASIDs resource */ + /** @MISC_CG_RES_SEV_ES: AMD SEV-ES ASIDs resource */ MISC_CG_RES_SEV_ES, #endif + /** @MISC_CG_RES_TYPES: count of enum misc_res_type constants */ MISC_CG_RES_TYPES }; @@ -30,13 +31,16 @@ struct misc_cg; /** * struct misc_res: Per cgroup per misc type resource * @max: Maximum limit on the resource. + * @watermark: Historical maximum usage of the resource. * @usage: Current usage of the resource. * @events: Number of times, the resource limit exceeded. */ struct misc_res { u64 max; + atomic64_t watermark; atomic64_t usage; atomic64_t events; + atomic64_t events_local; }; /** @@ -50,6 +54,8 @@ struct misc_cg { /* misc.events */ struct cgroup_file events_file; + /* misc.events.local */ + struct cgroup_file events_local_file; struct misc_res res[MISC_CG_RES_TYPES]; }; diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index cb15308b5cb0..991526039ccb 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -95,9 +95,10 @@ enum { }; enum { - MLX5_CQ_MODIFY_PERIOD = 1 << 0, - MLX5_CQ_MODIFY_COUNT = 1 << 1, - MLX5_CQ_MODIFY_OVERRUN = 1 << 2, + MLX5_CQ_MODIFY_PERIOD = BIT(0), + MLX5_CQ_MODIFY_COUNT = BIT(1), + MLX5_CQ_MODIFY_OVERRUN = BIT(2), + MLX5_CQ_MODIFY_PERIOD_MODE = BIT(4), }; enum { diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 01275c6e8468..ba875a619b97 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -68,7 +68,7 @@ #define MLX5_UN_SZ_BYTES(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 8) #define MLX5_UN_SZ_DW(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 32) #define MLX5_BYTE_OFF(typ, fld) (__mlx5_bit_off(typ, fld) / 8) -#define MLX5_ADDR_OF(typ, p, fld) ((void *)((uint8_t *)(p) + MLX5_BYTE_OFF(typ, fld))) +#define MLX5_ADDR_OF(typ, p, fld) ((void *)((u8 *)(p) + MLX5_BYTE_OFF(typ, fld))) /* insert a value to a struct */ #define MLX5_SET(typ, p, fld, v) do { \ @@ -294,6 +294,7 @@ enum { #define MLX5_UMR_FLEX_ALIGNMENT 0x40 #define MLX5_UMR_MTT_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_mtt)) #define MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_klm)) +#define MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_ksm)) #define MLX5_USER_INDEX_LEN (MLX5_FLD_SZ_BYTES(qpc, user_index) * 8) @@ -1336,6 +1337,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_ESW_FT_FIELD_SUPPORT_2(mdev, cap) \ MLX5_CAP_ESW_FLOWTABLE(mdev, ft_field_support_2_esw_fdb.cap) +#define MLX5_CAP_NIC_RX_FT_FIELD_SUPPORT_2(mdev, cap) \ + MLX5_CAP_FLOWTABLE(mdev, ft_field_support_2_nic_receive.cap) + #define MLX5_CAP_ESW(mdev, cap) \ MLX5_GET(e_switch_cap, \ mdev->caps.hca[MLX5_CAP_ESWITCH]->cur, cap) @@ -1359,6 +1363,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) \ MLX5_CAP_PORT_SELECTION(mdev, flow_table_properties_port_selection.cap) +#define MLX5_CAP_PORT_SELECTION_FT_FIELD_SUPPORT_2(mdev, cap) \ + MLX5_CAP_PORT_SELECTION(mdev, ft_field_support_2_port_selection.cap) + #define MLX5_CAP_ODP(mdev, cap)\ MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, cap) @@ -1460,6 +1467,7 @@ enum { MLX5_PER_TRAFFIC_CLASS_CONGESTION_GROUP = 0x13, MLX5_PHYSICAL_LAYER_STATISTICAL_GROUP = 0x16, MLX5_INFINIBAND_PORT_COUNTERS_GROUP = 0x20, + MLX5_INFINIBAND_EXTENDED_PORT_COUNTERS_GROUP = 0x21, }; enum { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index bf9324a31ae9..a96438ded15f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -85,7 +85,7 @@ enum mlx5_sqp_t { }; enum { - MLX5_MAX_PORTS = 4, + MLX5_MAX_PORTS = 8, }; enum { @@ -766,6 +766,12 @@ struct mlx5_hca_cap { u32 max[MLX5_UN_SZ_DW(hca_cap_union)]; }; +enum mlx5_wc_state { + MLX5_WC_STATE_UNINITIALIZED, + MLX5_WC_STATE_UNSUPPORTED, + MLX5_WC_STATE_SUPPORTED, +}; + struct mlx5_core_dev { struct device *device; enum mlx5_coredev_type coredev_type; @@ -824,6 +830,9 @@ struct mlx5_core_dev { #endif u64 num_ipsec_offloads; struct mlx5_sd *sd; + enum mlx5_wc_state wc_state; + /* sync write combining state */ + struct mutex wc_state_lock; }; struct mlx5_db { @@ -862,6 +871,7 @@ struct mlx5_cmd_work_ent { void *context; int idx; struct completion handling; + struct completion slotted; struct completion done; struct mlx5_cmd *cmd; struct work_struct work; @@ -907,6 +917,7 @@ struct mlx5_hca_vport_context { u16 qkey_violation_counter; u16 pkey_violation_counter; bool grh_required; + u8 num_plane; }; #define STRUCT_FIELD(header, field) \ @@ -1375,10 +1386,5 @@ enum { MLX5_OCTWORD = 16, }; -struct msi_map mlx5_msix_alloc(struct mlx5_core_dev *dev, - irqreturn_t (*handler)(int, void *), - const struct irq_affinity_desc *affdesc, - const char *name); -void mlx5_msix_free(struct mlx5_core_dev *dev, struct msi_map map); - +bool mlx5_wc_support_get(struct mlx5_core_dev *mdev); #endif /* MLX5_DRIVER_H */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c940b329a475..cab228cf51c6 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -416,7 +416,10 @@ struct mlx5_ifc_flow_table_fields_supported_bits { /* Table 2170 - Flow Table Fields Supported 2 Format */ struct mlx5_ifc_flow_table_fields_supported_2_bits { - u8 reserved_at_0[0xe]; + u8 reserved_at_0[0x2]; + u8 inner_l4_type[0x1]; + u8 outer_l4_type[0x1]; + u8 reserved_at_4[0xa]; u8 bth_opcode[0x1]; u8 reserved_at_f[0x1]; u8 tunnel_header_0_1[0x1]; @@ -525,6 +528,12 @@ union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits { u8 reserved_at_0[0x80]; }; +enum { + MLX5_PACKET_L4_TYPE_NONE, + MLX5_PACKET_L4_TYPE_TCP, + MLX5_PACKET_L4_TYPE_UDP, +}; + struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 smac_47_16[0x20]; @@ -550,7 +559,8 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 tcp_sport[0x10]; u8 tcp_dport[0x10]; - u8 reserved_at_c0[0x10]; + u8 l4_type[0x2]; + u8 reserved_at_c2[0xe]; u8 ipv4_ihl[0x4]; u8 reserved_at_c4[0x4]; @@ -783,7 +793,7 @@ struct mlx5_ifc_ads_bits { u8 reserved_at_2[0xe]; u8 pkey_index[0x10]; - u8 reserved_at_20[0x8]; + u8 plane_index[0x8]; u8 grh[0x1]; u8 mlid[0x7]; u8 rlid[0x10]; @@ -846,7 +856,11 @@ struct mlx5_ifc_flow_table_nic_cap_bits { struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit_sniffer; - u8 reserved_at_e00[0x700]; + u8 reserved_at_e00[0x600]; + + struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_nic_receive; + + u8 reserved_at_1480[0x80]; struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_nic_receive_rdma; @@ -876,7 +890,9 @@ struct mlx5_ifc_port_selection_cap_bits { struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_port_selection; - u8 reserved_at_400[0x7c00]; + struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_port_selection; + + u8 reserved_at_480[0x7b80]; }; enum { @@ -1077,7 +1093,8 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 tunnel_stateless_ip_over_ip_tx[0x1]; u8 reserved_at_2e[0x2]; u8 max_vxlan_udp_ports[0x8]; - u8 reserved_at_38[0x6]; + u8 swp_csum_l4_partial[0x1]; + u8 reserved_at_39[0x5]; u8 max_geneve_opt_len[0x1]; u8 tunnel_stateless_geneve_rx[0x1]; @@ -1469,7 +1486,9 @@ enum { }; struct mlx5_ifc_cmd_hca_cap_bits { - u8 reserved_at_0[0x10]; + u8 reserved_at_0[0x6]; + u8 page_request_disable[0x1]; + u8 reserved_at_7[0x9]; u8 shared_object_to_user_object_allowed[0x1]; u8 reserved_at_13[0xe]; u8 vhca_resource_manager[0x1]; @@ -1508,8 +1527,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 ts_cqe_to_dest_cqn[0x1]; u8 reserved_at_b3[0x6]; u8 go_back_n[0x1]; - u8 shampo[0x1]; - u8 reserved_at_bb[0x5]; + u8 reserved_at_ba[0x6]; u8 max_sgl_for_optimized_performance[0x8]; u8 log_max_cq_sz[0x8]; @@ -1668,7 +1686,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 cq_oi[0x1]; u8 cq_resize[0x1]; u8 cq_moderation[0x1]; - u8 reserved_at_223[0x3]; + u8 cq_period_mode_modify[0x1]; + u8 reserved_at_224[0x2]; u8 cq_eq_remap[0x1]; u8 pg[0x1]; u8 block_lb_mc[0x1]; @@ -1725,7 +1744,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_280[0x10]; u8 max_wqe_sz_sq[0x10]; - u8 reserved_at_2a0[0x10]; + u8 reserved_at_2a0[0xb]; + u8 shampo[0x1]; + u8 reserved_at_2ac[0x4]; u8 max_wqe_sz_rq[0x10]; u8 max_flow_counter_31_16[0x10]; @@ -1971,9 +1992,12 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_c0[0x8]; u8 migration_multi_load[0x1]; u8 migration_tracking_state[0x1]; - u8 reserved_at_ca[0x6]; + u8 multiplane_qp_ud[0x1]; + u8 reserved_at_cb[0x5]; u8 migration_in_chunks[0x1]; - u8 reserved_at_d1[0xf]; + u8 reserved_at_d1[0x1]; + u8 sf_eq_usage[0x1]; + u8 reserved_at_d3[0xd]; u8 cross_vhca_object_to_object_supported[0x20]; @@ -1998,13 +2022,28 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_250[0x10]; u8 reserved_at_260[0x120]; - u8 reserved_at_380[0x10]; + u8 reserved_at_380[0xb]; + u8 min_mkey_log_entity_size_fixed_buffer[0x5]; u8 ec_vf_vport_base[0x10]; u8 reserved_at_3a0[0x10]; u8 max_rqt_vhca_id[0x10]; - u8 reserved_at_3c0[0x440]; + u8 reserved_at_3c0[0x20]; + + u8 reserved_at_3e0[0x10]; + u8 pcc_ifa2[0x1]; + u8 reserved_at_3f1[0xf]; + + u8 reserved_at_400[0x1]; + u8 min_mkey_log_entity_size_fixed_buffer_valid[0x1]; + u8 reserved_at_402[0x1e]; + + u8 reserved_at_420[0x20]; + + u8 reserved_at_440[0x8]; + u8 max_num_eqs_24b[0x18]; + u8 reserved_at_460[0x3a0]; }; enum mlx5_ifc_flow_destination_type { @@ -2625,6 +2664,46 @@ struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits { u8 port_xmit_wait[0x20]; }; +struct mlx5_ifc_ib_ext_port_cntrs_grp_data_layout_bits { + u8 reserved_at_0[0x300]; + + u8 port_xmit_data_high[0x20]; + + u8 port_xmit_data_low[0x20]; + + u8 port_rcv_data_high[0x20]; + + u8 port_rcv_data_low[0x20]; + + u8 port_xmit_pkts_high[0x20]; + + u8 port_xmit_pkts_low[0x20]; + + u8 port_rcv_pkts_high[0x20]; + + u8 port_rcv_pkts_low[0x20]; + + u8 reserved_at_400[0x80]; + + u8 port_unicast_xmit_pkts_high[0x20]; + + u8 port_unicast_xmit_pkts_low[0x20]; + + u8 port_multicast_xmit_pkts_high[0x20]; + + u8 port_multicast_xmit_pkts_low[0x20]; + + u8 port_unicast_rcv_pkts_high[0x20]; + + u8 port_unicast_rcv_pkts_low[0x20]; + + u8 port_multicast_rcv_pkts_high[0x20]; + + u8 port_multicast_rcv_pkts_low[0x20]; + + u8 reserved_at_580[0x240]; +}; + struct mlx5_ifc_eth_per_tc_prio_grp_data_layout_bits { u8 transmit_queue_high[0x20]; @@ -3883,7 +3962,7 @@ enum { }; enum { - ELEMENT_TYPE_CAP_MASK_TASR = 1 << 0, + ELEMENT_TYPE_CAP_MASK_TSAR = 1 << 0, ELEMENT_TYPE_CAP_MASK_VPORT = 1 << 1, ELEMENT_TYPE_CAP_MASK_VPORT_TC = 1 << 2, ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC = 1 << 3, @@ -4147,7 +4226,8 @@ struct mlx5_ifc_hca_vport_context_bits { u8 has_smi[0x1]; u8 has_raw[0x1]; u8 grh_required[0x1]; - u8 reserved_at_104[0xc]; + u8 reserved_at_104[0x4]; + u8 num_port_plane[0x8]; u8 port_physical_state[0x4]; u8 vport_state_policy[0x4]; u8 port_state[0x4]; @@ -4361,10 +4441,10 @@ enum { MLX5_CQC_ST_FIRED = 0xa, }; -enum { +enum mlx5_cq_period_mode { MLX5_CQ_PERIOD_MODE_START_FROM_EQE = 0x0, MLX5_CQ_PERIOD_MODE_START_FROM_CQE = 0x1, - MLX5_CQ_PERIOD_NUM_MODES + MLX5_CQ_PERIOD_NUM_MODES, }; struct mlx5_ifc_cqc_bits { @@ -4516,6 +4596,7 @@ union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits { struct mlx5_ifc_eth_per_tc_prio_grp_data_layout_bits eth_per_tc_prio_grp_data_layout; struct mlx5_ifc_eth_per_tc_congest_prio_grp_data_layout_bits eth_per_tc_congest_prio_grp_data_layout; struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits ib_port_cntrs_grp_data_layout; + struct mlx5_ifc_ib_ext_port_cntrs_grp_data_layout_bits ib_ext_port_cntrs_grp_data_layout; struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs; struct mlx5_ifc_phys_layer_statistical_cntrs_bits phys_layer_statistical_cntrs; u8 reserved_at_0[0x7c0]; @@ -5604,7 +5685,11 @@ struct mlx5_ifc_query_q_counter_out_bits { u8 local_ack_timeout_err[0x20]; - u8 reserved_at_320[0xa0]; + u8 reserved_at_320[0x60]; + + u8 req_rnr_retries_exceeded[0x20]; + + u8 reserved_at_3a0[0x20]; u8 resp_local_length_error[0x20]; @@ -7663,7 +7748,7 @@ struct mlx5_ifc_mad_ifc_in_bits { u8 op_mod[0x10]; u8 remote_lid[0x10]; - u8 reserved_at_50[0x8]; + u8 plane_index[0x8]; u8 port[0x8]; u8 reserved_at_60[0x20]; @@ -9592,7 +9677,9 @@ struct mlx5_ifc_ptys_reg_bits { u8 an_disable_cap[0x1]; u8 reserved_at_3[0x5]; u8 local_port[0x8]; - u8 reserved_at_10[0xd]; + u8 reserved_at_10[0x8]; + u8 plane_ind[0x4]; + u8 reserved_at_1c[0x1]; u8 proto_mask[0x3]; u8 an_status[0x4]; @@ -9793,7 +9880,21 @@ struct mlx5_ifc_pplm_reg_bits { u8 fec_override_admin_100g_2x[0x10]; u8 fec_override_admin_50g_1x[0x10]; - u8 reserved_at_140[0x140]; + u8 fec_override_cap_800g_8x[0x10]; + u8 fec_override_cap_400g_4x[0x10]; + + u8 fec_override_cap_200g_2x[0x10]; + u8 fec_override_cap_100g_1x[0x10]; + + u8 reserved_at_180[0xa0]; + + u8 fec_override_admin_800g_8x[0x10]; + u8 fec_override_admin_400g_4x[0x10]; + + u8 fec_override_admin_200g_2x[0x10]; + u8 fec_override_admin_100g_1x[0x10]; + + u8 reserved_at_260[0x20]; }; struct mlx5_ifc_ppcnt_reg_bits { @@ -9804,8 +9905,10 @@ struct mlx5_ifc_ppcnt_reg_bits { u8 grp[0x6]; u8 clr[0x1]; - u8 reserved_at_21[0x1c]; - u8 prio_tc[0x3]; + u8 reserved_at_21[0x13]; + u8 plane_ind[0x4]; + u8 reserved_at_38[0x3]; + u8 prio_tc[0x5]; union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set; }; @@ -10165,7 +10268,9 @@ struct mlx5_ifc_mtutc_reg_bits { }; struct mlx5_ifc_pcam_enhanced_features_bits { - u8 reserved_at_0[0x68]; + u8 reserved_at_0[0x48]; + u8 fec_100G_per_lane_in_pplm[0x1]; + u8 reserved_at_49[0x1f]; u8 fec_50G_per_lane_in_pplm[0x1]; u8 reserved_at_69[0x4]; u8 rx_icrc_encapsulated_counter[0x1]; @@ -10267,9 +10372,9 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 mfrl[0x1]; u8 regs_39_to_32[0x8]; - u8 regs_31_to_10[0x16]; + u8 regs_31_to_11[0x15]; u8 mtmp[0x1]; - u8 regs_8_to_0[0x9]; + u8 regs_9_to_0[0xa]; }; struct mlx5_ifc_mcam_access_reg_bits1 { diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h index 40371c916cf9..58dfa2ee7c83 100644 --- a/include/linux/mlx5/mlx5_ifc_vdpa.h +++ b/include/linux/mlx5/mlx5_ifc_vdpa.h @@ -148,7 +148,9 @@ enum { MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_ADDRS = (u64)1 << 6, MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_AVAIL_IDX = (u64)1 << 7, MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX = (u64)1 << 8, + MLX5_VIRTQ_MODIFY_MASK_QUEUE_VIRTIO_VERSION = (u64)1 << 10, MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY = (u64)1 << 11, + MLX5_VIRTQ_MODIFY_MASK_QUEUE_FEATURES = (u64)1 << 12, MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY = (u64)1 << 14, }; diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 26092c78a985..e68d42b8ce65 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -155,10 +155,11 @@ struct mlx5_port_eth_proto { int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps); int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, - int ptys_size, int proto_mask, u8 local_port); + int ptys_size, int proto_mask, + u8 local_port, u8 plane_index); int mlx5_query_ib_port_oper(struct mlx5_core_dev *dev, u16 *link_width_oper, - u16 *proto_oper, u8 local_port); + u16 *proto_oper, u8 local_port, u8 plane_index); void mlx5_toggle_port_link(struct mlx5_core_dev *dev); int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, enum mlx5_port_status status); diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index f0e55bf3ec8b..ad1ce650146c 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -576,9 +576,12 @@ static inline const char *mlx5_qp_state_str(int state) static inline int mlx5_get_qp_default_ts(struct mlx5_core_dev *dev) { - return !MLX5_CAP_ROCE(dev, qp_ts_format) ? - MLX5_TIMESTAMP_FORMAT_FREE_RUNNING : - MLX5_TIMESTAMP_FORMAT_DEFAULT; + u8 supported_ts_cap = mlx5_get_roce_state(dev) ? + MLX5_CAP_ROCE(dev, qp_ts_format) : + MLX5_CAP_GEN(dev, sq_ts_format); + + return supported_ts_cap ? MLX5_TIMESTAMP_FORMAT_DEFAULT : + MLX5_TIMESTAMP_FORMAT_FREE_RUNNING; } #endif /* MLX5_QP_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index b6bdaa18b9e9..6549d0979b28 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -5,6 +5,7 @@ #include <linux/errno.h> #include <linux/mmdebug.h> #include <linux/gfp.h> +#include <linux/pgalloc_tag.h> #include <linux/bug.h> #include <linux/list.h> #include <linux/mmzone.h> @@ -203,11 +204,11 @@ extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern unsigned long sysctl_overcommit_kbytes; -int overcommit_ratio_handler(struct ctl_table *, int, void *, size_t *, +int overcommit_ratio_handler(const struct ctl_table *, int, void *, size_t *, loff_t *); -int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *, +int overcommit_kbytes_handler(const struct ctl_table *, int, void *, size_t *, loff_t *); -int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, +int overcommit_policy_handler(const struct ctl_table *, int, void *, size_t *, loff_t *); #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) @@ -405,6 +406,18 @@ extern unsigned int kobjsize(const void *objp); #define VM_ALLOW_ANY_UNCACHED VM_NONE #endif +#ifdef CONFIG_64BIT +#define VM_DROPPABLE_BIT 40 +#define VM_DROPPABLE BIT(VM_DROPPABLE_BIT) +#else +#define VM_DROPPABLE VM_NONE +#endif + +#ifdef CONFIG_64BIT +/* VM is sealed, in vm_flags */ +#define VM_SEALED _BITUL(63) +#endif + /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY) @@ -1104,7 +1117,7 @@ static inline unsigned int compound_order(struct page *page) * * Return: The order of the folio. */ -static inline unsigned int folio_order(struct folio *folio) +static inline unsigned int folio_order(const struct folio *folio) { if (!folio_test_large(folio)) return 0; @@ -1196,77 +1209,52 @@ static inline int is_vmalloc_or_module_addr(const void *x) /* * How many times the entire folio is mapped as a single unit (eg by a * PMD or PUD entry). This is probably not what you want, except for - * debugging purposes - it does not include PTE-mapped sub-pages; look - * at folio_mapcount() or page_mapcount() instead. + * debugging purposes or implementation of other core folio_*() primitives. */ -static inline int folio_entire_mapcount(struct folio *folio) +static inline int folio_entire_mapcount(const struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); return atomic_read(&folio->_entire_mapcount) + 1; } -/* - * The atomic page->_mapcount, starts from -1: so that transitions - * both from it and to it can be tracked, using atomic_inc_and_test - * and atomic_add_negative(-1). - */ -static inline void page_mapcount_reset(struct page *page) +static inline int folio_large_mapcount(const struct folio *folio) { - atomic_set(&(page)->_mapcount, -1); + VM_WARN_ON_FOLIO(!folio_test_large(folio), folio); + return atomic_read(&folio->_large_mapcount) + 1; } /** - * page_mapcount() - Number of times this precise page is mapped. - * @page: The page. + * folio_mapcount() - Number of mappings of this folio. + * @folio: The folio. * - * The number of times this page is mapped. If this page is part of - * a large folio, it includes the number of times this page is mapped - * as part of that folio. + * The folio mapcount corresponds to the number of present user page table + * entries that reference any part of a folio. Each such present user page + * table entry must be paired with exactly on folio reference. * - * Will report 0 for pages which cannot be mapped into userspace, eg - * slab, page tables and similar. - */ -static inline int page_mapcount(struct page *page) -{ - int mapcount = atomic_read(&page->_mapcount) + 1; - - /* Handle page_has_type() pages */ - if (mapcount < 0) - mapcount = 0; - if (unlikely(PageCompound(page))) - mapcount += folio_entire_mapcount(page_folio(page)); - - return mapcount; -} - -int folio_total_mapcount(struct folio *folio); - -/** - * folio_mapcount() - Calculate the number of mappings of this folio. - * @folio: The folio. + * For ordindary folios, each user page table entry (PTE/PMD/PUD/...) counts + * exactly once. * - * A large folio tracks both how many times the entire folio is mapped, - * and how many times each individual page in the folio is mapped. - * This function calculates the total number of times the folio is - * mapped. + * For hugetlb folios, each abstracted "hugetlb" user page table entry that + * references the entire folio counts exactly once, even when such special + * page table entries are comprised of multiple ordinary page table entries. + * + * Will report 0 for pages which cannot be mapped into userspace, such as + * slab, page tables and similar. * * Return: The number of times this folio is mapped. */ -static inline int folio_mapcount(struct folio *folio) +static inline int folio_mapcount(const struct folio *folio) { - if (likely(!folio_test_large(folio))) - return atomic_read(&folio->_mapcount) + 1; - return folio_total_mapcount(folio); -} + int mapcount; -static inline bool folio_large_is_mapped(struct folio *folio) -{ - /* - * Reading _entire_mapcount below could be omitted if hugetlb - * participated in incrementing nr_pages_mapped when compound mapped. - */ - return atomic_read(&folio->_nr_pages_mapped) > 0 || - atomic_read(&folio->_entire_mapcount) >= 0; + if (likely(!folio_test_large(folio))) { + mapcount = atomic_read(&folio->_mapcount) + 1; + /* Handle page_has_type() pages */ + if (mapcount < PAGE_MAPCOUNT_RESERVE + 1) + mapcount = 0; + return mapcount; + } + return folio_large_mapcount(folio); } /** @@ -1275,11 +1263,9 @@ static inline bool folio_large_is_mapped(struct folio *folio) * * Return: True if any page in this folio is referenced by user page tables. */ -static inline bool folio_mapped(struct folio *folio) +static inline bool folio_mapped(const struct folio *folio) { - if (likely(!folio_test_large(folio))) - return atomic_read(&folio->_mapcount) >= 0; - return folio_large_is_mapped(folio); + return folio_mapcount(folio) >= 1; } /* @@ -1287,11 +1273,9 @@ static inline bool folio_mapped(struct folio *folio) * For compound page it returns true if any sub-page of compound page is mapped, * even if this particular sub-page is not itself mapped by any PTE or PMD. */ -static inline bool page_mapped(struct page *page) +static inline bool page_mapped(const struct page *page) { - if (likely(!PageCompound(page))) - return atomic_read(&page->_mapcount) >= 0; - return folio_large_is_mapped(page_folio(page)); + return folio_mapped(page_folio(page)); } static inline struct page *virt_to_head_page(const void *x) @@ -1314,11 +1298,10 @@ void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); void folio_copy(struct folio *dst, struct folio *src); +int folio_mc_copy(struct folio *dst, struct folio *src); unsigned long nr_free_buffer_pages(void); -void destroy_large_folio(struct folio *folio); - /* Returns the number of bytes in this potentially compound page. */ static inline unsigned long page_size(struct page *page) { @@ -1436,27 +1419,22 @@ vm_fault_t finish_fault(struct vm_fault *vmf); #if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX) DECLARE_STATIC_KEY_FALSE(devmap_managed_key); -bool __put_devmap_managed_page_refs(struct page *page, int refs); -static inline bool put_devmap_managed_page_refs(struct page *page, int refs) +bool __put_devmap_managed_folio_refs(struct folio *folio, int refs); +static inline bool put_devmap_managed_folio_refs(struct folio *folio, int refs) { if (!static_branch_unlikely(&devmap_managed_key)) return false; - if (!is_zone_device_page(page)) + if (!folio_is_zone_device(folio)) return false; - return __put_devmap_managed_page_refs(page, refs); + return __put_devmap_managed_folio_refs(folio, refs); } #else /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ -static inline bool put_devmap_managed_page_refs(struct page *page, int refs) +static inline bool put_devmap_managed_folio_refs(struct folio *folio, int refs) { return false; } #endif /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */ -static inline bool put_devmap_managed_page(struct page *page) -{ - return put_devmap_managed_page_refs(page, 1); -} - /* 127: arbitrary random number, small enough to assemble well */ #define folio_ref_zero_or_close_to_overflow(folio) \ ((unsigned int) folio_ref_count(folio) + 127u <= 127u) @@ -1575,7 +1553,7 @@ static inline void put_page(struct page *page) * For some devmap managed pages we need to catch refcount transition * from 2 to 1: */ - if (put_devmap_managed_page(&folio->page)) + if (put_devmap_managed_folio_refs(folio, 1)) return; folio_put(folio); } @@ -1607,17 +1585,19 @@ static inline void put_page(struct page *page) * issue. * * Locking: the lockless algorithm described in folio_try_get_rcu() - * provides safe operation for get_user_pages(), page_mkclean() and + * provides safe operation for get_user_pages(), folio_mkclean() and * other calls that race to set up page table entries. */ #define GUP_PIN_COUNTING_BIAS (1U << 10) void unpin_user_page(struct page *page); +void unpin_folio(struct folio *folio); void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, bool make_dirty); void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, bool make_dirty); void unpin_user_pages(struct page **pages, unsigned long npages); +void unpin_folios(struct folio **folios, unsigned long nfolios); static inline bool is_cow_mapping(vm_flags_t flags) { @@ -1948,8 +1928,8 @@ static inline struct folio *pfn_folio(unsigned long pfn) * * For more information, please see Documentation/core-api/pin_user_pages.rst. * - * Return: True, if it is likely that the page has been "dma-pinned". - * False, if the page is definitely not dma-pinned. + * Return: True, if it is likely that the folio has been "dma-pinned". + * False, if the folio is definitely not dma-pinned. */ static inline bool folio_maybe_dma_pinned(struct folio *folio) { @@ -1968,11 +1948,6 @@ static inline bool folio_maybe_dma_pinned(struct folio *folio) GUP_PIN_COUNTING_BIAS; } -static inline bool page_maybe_dma_pinned(struct page *page) -{ - return folio_maybe_dma_pinned(page_folio(page)); -} - /* * This should most likely only be called during fork() to see whether we * should break the cow immediately for an anon page on the src mm. @@ -2069,7 +2044,7 @@ static inline void set_page_links(struct page *page, enum zone_type zone, * * Return: A positive power of two. */ -static inline long folio_nr_pages(struct folio *folio) +static inline long folio_nr_pages(const struct folio *folio) { if (!folio_test_large(folio)) return 1; @@ -2145,7 +2120,7 @@ static inline struct folio *folio_next(struct folio *folio) * it from being split. It is not necessary for the folio to be locked. * Return: The base-2 logarithm of the size of this folio. */ -static inline unsigned int folio_shift(struct folio *folio) +static inline unsigned int folio_shift(const struct folio *folio) { return PAGE_SHIFT + folio_order(folio); } @@ -2158,27 +2133,70 @@ static inline unsigned int folio_shift(struct folio *folio) * it from being split. It is not necessary for the folio to be locked. * Return: The number of bytes in this folio. */ -static inline size_t folio_size(struct folio *folio) +static inline size_t folio_size(const struct folio *folio) { return PAGE_SIZE << folio_order(folio); } /** - * folio_estimated_sharers - Estimate the number of sharers of a folio. + * folio_likely_mapped_shared - Estimate if the folio is mapped into the page + * tables of more than one MM * @folio: The folio. * - * folio_estimated_sharers() aims to serve as a function to efficiently - * estimate the number of processes sharing a folio. This is done by - * looking at the precise mapcount of the first subpage in the folio, and - * assuming the other subpages are the same. This may not be true for large - * folios. If you want exact mapcounts for exact calculations, look at - * page_mapcount() or folio_total_mapcount(). + * This function checks if the folio is currently mapped into more than one + * MM ("mapped shared"), or if the folio is only mapped into a single MM + * ("mapped exclusively"). * - * Return: The estimated number of processes sharing a folio. + * As precise information is not easily available for all folios, this function + * estimates the number of MMs ("sharers") that are currently mapping a folio + * using the number of times the first page of the folio is currently mapped + * into page tables. + * + * For small anonymous folios (except KSM folios) and anonymous hugetlb folios, + * the return value will be exactly correct, because they can only be mapped + * at most once into an MM, and they cannot be partially mapped. + * + * For other folios, the result can be fuzzy: + * #. For partially-mappable large folios (THP), the return value can wrongly + * indicate "mapped exclusively" (false negative) when the folio is + * only partially mapped into at least one MM. + * #. For pagecache folios (including hugetlb), the return value can wrongly + * indicate "mapped shared" (false positive) when two VMAs in the same MM + * cover the same file range. + * #. For (small) KSM folios, the return value can wrongly indicate "mapped + * shared" (false positive), when the folio is mapped multiple times into + * the same MM. + * + * Further, this function only considers current page table mappings that + * are tracked using the folio mapcount(s). + * + * This function does not consider: + * #. If the folio might get mapped in the (near) future (e.g., swapcache, + * pagecache, temporary unmapping for migration). + * #. If the folio is mapped differently (VM_PFNMAP). + * #. If hugetlb page table sharing applies. Callers might want to check + * hugetlb_pmd_shared(). + * + * Return: Whether the folio is estimated to be mapped into more than one MM. */ -static inline int folio_estimated_sharers(struct folio *folio) +static inline bool folio_likely_mapped_shared(struct folio *folio) { - return page_mapcount(folio_page(folio, 0)); + int mapcount = folio_mapcount(folio); + + /* Only partially-mappable folios require more care. */ + if (!folio_test_large(folio) || unlikely(folio_test_hugetlb(folio))) + return mapcount > 1; + + /* A single mapping implies "mapped exclusively". */ + if (mapcount <= 1) + return false; + + /* If any page is mapped more than once we treat it "mapped shared". */ + if (folio_entire_mapcount(folio) || mapcount > folio_nr_pages(folio)) + return true; + + /* Let's guess based on the first subpage. */ + return atomic_read(&folio->_mapcount) > 0; } #ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE @@ -2247,19 +2265,6 @@ static inline void *folio_address(const struct folio *folio) return page_address(&folio->page); } -extern pgoff_t __page_file_index(struct page *page); - -/* - * Return the pagecache index of the passed page. Regular pagecache pages - * use ->index whereas swapcache pages use swp_offset(->private) - */ -static inline pgoff_t page_index(struct page *page) -{ - if (unlikely(PageSwapCache(page))) - return __page_file_index(page); - return page->index; -} - /* * Return true only if the page has been allocated with * ALLOC_NO_WATERMARKS and the low watermark was not @@ -2393,12 +2398,8 @@ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); -int follow_pte(struct mm_struct *mm, unsigned long address, +int follow_pte(struct vm_area_struct *vma, unsigned long address, pte_t **ptepp, spinlock_t **ptlp); -int follow_pfn(struct vm_area_struct *vma, unsigned long address, - unsigned long *pfn); -int follow_phys(struct vm_area_struct *vma, unsigned long address, - unsigned int flags, unsigned long *prot, resource_size_t *phys); int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); @@ -2506,6 +2507,9 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); +long memfd_pin_folios(struct file *memfd, loff_t start, loff_t end, + struct folio **folios, unsigned int max_folios, + pgoff_t *offset); int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); @@ -2552,7 +2556,7 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma, MM_CP_UFFD_WP_RESOLVE) bool vma_needs_dirty_tracking(struct vm_area_struct *vma); -int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); +bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma) { /* @@ -2859,12 +2863,13 @@ static inline bool pagetable_is_reserved(struct ptdesc *pt) * * Return: The ptdesc describing the allocated page tables. */ -static inline struct ptdesc *pagetable_alloc(gfp_t gfp, unsigned int order) +static inline struct ptdesc *pagetable_alloc_noprof(gfp_t gfp, unsigned int order) { - struct page *page = alloc_pages(gfp | __GFP_COMP, order); + struct page *page = alloc_pages_noprof(gfp | __GFP_COMP, order); return page_ptdesc(page); } +#define pagetable_alloc(...) alloc_hooks(pagetable_alloc_noprof(__VA_ARGS__)) /** * pagetable_free - Free pagetables @@ -2915,6 +2920,13 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) return ptlock_ptr(page_ptdesc(pmd_page(*pmd))); } +static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) +{ + BUILD_BUG_ON(IS_ENABLED(CONFIG_HIGHPTE)); + BUILD_BUG_ON(MAX_PTRS_PER_PTE * sizeof(pte_t) > PAGE_SIZE); + return ptlock_ptr(virt_to_ptdesc(pte)); +} + static inline bool ptlock_init(struct ptdesc *ptdesc) { /* @@ -2939,6 +2951,10 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { return &mm->page_table_lock; } +static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte) +{ + return &mm->page_table_lock; +} static inline void ptlock_cache_init(void) {} static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; } static inline void ptlock_free(struct ptdesc *ptdesc) {} @@ -3132,13 +3148,7 @@ extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end, int nid); /* Free the reserved page into the buddy system, so it gets managed. */ -static inline void free_reserved_page(struct page *page) -{ - ClearPageReserved(page); - init_page_count(page); - __free_page(page); - adjust_managed_page_count(page, 1); -} +void free_reserved_page(struct page *page); #define free_highmem_page(page) free_reserved_page(page) static inline void mark_page_reserved(struct page *page) @@ -3195,8 +3205,6 @@ static inline unsigned long get_num_physpages(void) */ void free_area_init(unsigned long *max_zone_pfn); unsigned long node_map_pfn_alignment(void); -unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn, - unsigned long end_pfn); extern unsigned long absent_pages_in_range(unsigned long start_pfn, unsigned long end_pfn); extern void get_pfn_range_for_nid(unsigned int nid, @@ -3212,7 +3220,6 @@ static inline int early_pfn_to_nid(unsigned long pfn) extern int __meminit early_pfn_to_nid(unsigned long pfn); #endif -extern void set_dma_reserve(unsigned long new_dma_reserve); extern void mem_init(void); extern void __init mmap_init(void); @@ -3224,9 +3231,6 @@ static inline void show_mem(void) extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); -#ifdef __HAVE_ARCH_RESERVED_KERNEL_PAGES -extern unsigned long arch_reserved_kernel_pages(void); -#endif extern __printf(3, 4) void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...); @@ -3385,7 +3389,16 @@ extern int install_special_mapping(struct mm_struct *mm, unsigned long randomize_stack_top(unsigned long stack_top); unsigned long randomize_page(unsigned long start, unsigned long range); -extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); +unsigned long +__get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags); + +static inline unsigned long +get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + return __get_unmapped_area(file, addr, len, pgoff, flags, 0); +} extern unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, @@ -3431,6 +3444,7 @@ struct vm_unmapped_area_info { unsigned long high_limit; unsigned long align_mask; unsigned long align_offset; + unsigned long start_gap; }; extern unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info); @@ -3787,24 +3801,22 @@ static inline bool page_is_guard(struct page *page) return PageGuard(page); } -bool __set_page_guard(struct zone *zone, struct page *page, unsigned int order, - int migratetype); +bool __set_page_guard(struct zone *zone, struct page *page, unsigned int order); static inline bool set_page_guard(struct zone *zone, struct page *page, - unsigned int order, int migratetype) + unsigned int order) { if (!debug_guardpage_enabled()) return false; - return __set_page_guard(zone, page, order, migratetype); + return __set_page_guard(zone, page, order); } -void __clear_page_guard(struct zone *zone, struct page *page, unsigned int order, - int migratetype); +void __clear_page_guard(struct zone *zone, struct page *page, unsigned int order); static inline void clear_page_guard(struct zone *zone, struct page *page, - unsigned int order, int migratetype) + unsigned int order) { if (!debug_guardpage_enabled()) return; - __clear_page_guard(zone, page, order, migratetype); + __clear_page_guard(zone, page, order); } #else /* CONFIG_DEBUG_PAGEALLOC */ @@ -3814,9 +3826,9 @@ static inline unsigned int debug_guardpage_minorder(void) { return 0; } static inline bool debug_guardpage_enabled(void) { return false; } static inline bool page_is_guard(struct page *page) { return false; } static inline bool set_page_guard(struct zone *zone, struct page *page, - unsigned int order, int migratetype) { return false; } + unsigned int order) { return false; } static inline void clear_page_guard(struct zone *zone, struct page *page, - unsigned int order, int migratetype) {} + unsigned int order) {} #endif /* CONFIG_DEBUG_PAGEALLOC */ #ifdef __HAVE_ARCH_GATE_AREA @@ -3839,7 +3851,7 @@ extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm); #ifdef CONFIG_SYSCTL extern int sysctl_drop_caches; -int drop_caches_sysctl_handler(struct ctl_table *, int, void *, size_t *, +int drop_caches_sysctl_handler(const struct ctl_table *, int, void *, size_t *, loff_t *); #endif @@ -3971,7 +3983,6 @@ 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 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); #ifdef CONFIG_MEMORY_FAILURE @@ -3984,7 +3995,6 @@ 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) { @@ -4005,12 +4015,6 @@ 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); @@ -4051,10 +4055,10 @@ enum mf_result { enum mf_action_page_type { MF_MSG_KERNEL, MF_MSG_KERNEL_HIGH_ORDER, - MF_MSG_SLAB, MF_MSG_DIFFERENT_COMPOUND, MF_MSG_HUGE, MF_MSG_FREE_HUGE, + MF_MSG_GET_HWPOISON, MF_MSG_UNMAP_FAILED, MF_MSG_DIRTY_SWAPCACHE, MF_MSG_CLEAN_SWAPCACHE, @@ -4068,13 +4072,12 @@ enum mf_action_page_type { MF_MSG_BUDDY, MF_MSG_DAX, MF_MSG_UNSPLIT_THP, + MF_MSG_ALREADY_POISONED, MF_MSG_UNKNOWN, }; #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) -extern void clear_huge_page(struct page *page, - unsigned long addr_hint, - unsigned int pages_per_huge_page); +void folio_zero_user(struct folio *folio, unsigned long addr_hint); int copy_user_large_folio(struct folio *dst, struct folio *src, unsigned long addr_hint, struct vm_area_struct *vma); @@ -4204,4 +4207,9 @@ static inline bool pfn_is_unaccepted_memory(unsigned long pfn) return range_contains_unaccepted_memory(paddr, paddr + PAGE_SIZE); } +void vma_pgtable_walk_begin(struct vm_area_struct *vma); +void vma_pgtable_walk_end(struct vm_area_struct *vma); + +int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size); + #endif /* _LINUX_MM_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5240bd7bca33..485424979254 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -46,9 +46,7 @@ struct mem_cgroup; * which is guaranteed to be aligned. If you use the same storage as * page->mapping, you must restore it to NULL before freeing the page. * - * If your page will not be mapped to userspace, you can also use the four - * bytes in the mapcount union, but you must call page_mapcount_reset() - * before freeing it. + * The mapcount field must not be used for own purposes. * * If you want to use the refcount field, it must be used in such a way * that other CPUs temporarily incrementing and then decrementing the @@ -152,18 +150,31 @@ struct page { union { /* This union is 4 bytes in size. */ /* - * If the page can be mapped to userspace, encodes the number - * of times this page is referenced by a page table. + * For head pages of typed folios, the value stored here + * allows for determining what this page is used for. The + * tail pages of typed folios will not store a type + * (page_type == _mapcount == -1). + * + * See page-flags.h for a list of page types which are currently + * stored here. + * + * Owners of typed folios may reuse the lower 16 bit of the + * head page page_type field after setting the page type, + * but must reset these 16 bit to -1 before clearing the + * page type. */ - atomic_t _mapcount; + unsigned int page_type; /* - * If the page is neither PageSlab nor mappable to userspace, - * the value stored here may help determine what this page - * is used for. See page-flags.h for a list of page types - * which are currently stored here. + * For pages that are part of non-typed folios for which mappings + * are tracked via the RMAP, encodes the number of times this page + * is directly referenced by a page table. + * + * Note that the mapcount is always initialized to -1, so that + * transitions both from it and to it can be tracked, using + * atomic_inc_and_test() and atomic_add_negative(-1). */ - unsigned int page_type; + atomic_t _mapcount; }; /* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */ @@ -171,6 +182,8 @@ struct page { #ifdef CONFIG_MEMCG unsigned long memcg_data; +#elif defined(CONFIG_SLAB_OBJ_EXT) + unsigned long _unused_slab_obj_exts; #endif /* @@ -289,7 +302,8 @@ typedef struct { * @virtual: Virtual address in the kernel direct map. * @_last_cpupid: IDs of last CPU and last process that accessed the folio. * @_entire_mapcount: Do not use directly, call folio_entire_mapcount(). - * @_nr_pages_mapped: Do not use directly, call folio_mapcount(). + * @_large_mapcount: Do not use directly, call folio_mapcount(). + * @_nr_pages_mapped: Do not use outside of rmap and debug code. * @_pincount: Do not use directly, call folio_maybe_dma_pinned(). * @_folio_nr_pages: Do not use directly, call folio_nr_pages(). * @_hugetlb_subpool: Do not use directly, use accessor in hugetlb.h. @@ -297,6 +311,7 @@ typedef struct { * @_hugetlb_cgroup_rsvd: Do not use directly, use accessor in hugetlb_cgroup.h. * @_hugetlb_hwpoison: Do not use directly, call raw_hwp_list_head(). * @_deferred_list: Folios to be split under memory pressure. + * @_unused_slab_obj_exts: Placeholder to match obj_exts in struct slab. * * A folio is a physically, virtually and logically contiguous set * of bytes. It is a power-of-two in size, and it is aligned to that @@ -333,6 +348,8 @@ struct folio { atomic_t _refcount; #ifdef CONFIG_MEMCG unsigned long memcg_data; +#elif defined(CONFIG_SLAB_OBJ_EXT) + unsigned long _unused_slab_obj_exts; #endif #if defined(WANT_PAGE_VIRTUAL) void *virtual; @@ -348,8 +365,8 @@ struct folio { struct { unsigned long _flags_1; unsigned long _head_1; - unsigned long _folio_avail; /* public: */ + atomic_t _large_mapcount; atomic_t _entire_mapcount; atomic_t _nr_pages_mapped; atomic_t _pincount; @@ -671,6 +688,9 @@ struct vm_area_struct { }; #ifdef CONFIG_PER_VMA_LOCK + /* Flag to indicate areas detached from the mm->mm_mt tree */ + bool detached; + /* * Can only be written (using WRITE_ONCE()) while holding both: * - mmap_lock (in write mode) @@ -687,9 +707,6 @@ struct vm_area_struct { */ int vm_lock_seq; struct vma_lock *vm_lock; - - /* Flag to indicate areas detached from the mm->mm_mt tree */ - bool detached; #endif /* @@ -777,11 +794,7 @@ struct mm_struct { } ____cacheline_aligned_in_smp; struct maple_tree mm_mt; -#ifdef CONFIG_MMU - unsigned long (*get_unmapped_area) (struct file *filp, - unsigned long addr, unsigned long len, - unsigned long pgoff, unsigned long flags); -#endif + unsigned long mmap_base; /* base of mmap area */ unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */ #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES @@ -988,7 +1001,7 @@ struct mm_struct { * Represent how many empty pages are merged with kernel zero * pages when enabling KSM use_zero_pages. */ - unsigned long ksm_zero_pages; + atomic_long_t ksm_zero_pages; #endif /* CONFIG_KSM */ #ifdef CONFIG_LRU_GEN_WALKS_MMU struct { @@ -1170,14 +1183,15 @@ static inline void mm_init_cid(struct mm_struct *mm) cpumask_clear(mm_cidmask(mm)); } -static inline int mm_alloc_cid(struct mm_struct *mm) +static inline int mm_alloc_cid_noprof(struct mm_struct *mm) { - mm->pcpu_cid = alloc_percpu(struct mm_cid); + mm->pcpu_cid = alloc_percpu_noprof(struct mm_cid); if (!mm->pcpu_cid) return -ENOMEM; mm_init_cid(mm); return 0; } +#define mm_alloc_cid(...) alloc_hooks(mm_alloc_cid_noprof(__VA_ARGS__)) static inline void mm_destroy_cid(struct mm_struct *mm) { @@ -1370,6 +1384,15 @@ enum fault_flag { typedef unsigned int __bitwise zap_flags_t; +/* Flags for clear_young_dirty_ptes(). */ +typedef int __bitwise cydp_t; + +/* Clear the access bit */ +#define CYDP_CLEAR_YOUNG ((__force cydp_t)BIT(0)) + +/* Clear the dirty bit */ +#define CYDP_CLEAR_DIRTY ((__force cydp_t)BIT(1)) + /* * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each * other. Here is what they mean, and how to use them: diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h index 8d38dcb6d044..de9dc20b01ba 100644 --- a/include/linux/mmap_lock.h +++ b/include/linux/mmap_lock.h @@ -60,16 +60,14 @@ 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) +static inline void mmap_assert_locked(const struct mm_struct *mm) { - lockdep_assert_held(&mm->mmap_lock); - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); + rwsem_assert_held(&mm->mmap_lock); } -static inline void mmap_assert_write_locked(struct mm_struct *mm) +static inline void mmap_assert_write_locked(const struct mm_struct *mm) { - lockdep_assert_held_write(&mm->mmap_lock); - VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm); + rwsem_assert_held_write(&mm->mmap_lock); } #ifdef CONFIG_PER_VMA_LOCK diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 5894bf912f7b..88c6a76042ee 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -433,8 +433,8 @@ struct mmc_host { mmc_pm_flag_t pm_caps; /* supported pm features */ /* host specific block data */ - unsigned int max_seg_size; /* see blk_queue_max_segment_size */ - unsigned short max_segs; /* see blk_queue_max_segments */ + unsigned int max_seg_size; /* lim->max_segment_size */ + unsigned short max_segs; /* lim->max_segments */ unsigned short unused; unsigned int max_req_size; /* maximum number of bytes in one req */ unsigned int max_blk_size; /* maximum size of one mmc block */ diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h index 478855b8e406..fed1f5f4a8d3 100644 --- a/include/linux/mmc/sdio_func.h +++ b/include/linux/mmc/sdio_func.h @@ -106,7 +106,10 @@ struct sdio_driver { .class = (dev_class), \ .vendor = SDIO_ANY_ID, .device = SDIO_ANY_ID -extern int sdio_register_driver(struct sdio_driver *); +/* use a macro to avoid include chaining to get THIS_MODULE */ +#define sdio_register_driver(drv) \ + __sdio_register_driver(drv, THIS_MODULE) +extern int __sdio_register_driver(struct sdio_driver *, struct module *); extern void sdio_unregister_driver(struct sdio_driver *); /** diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index 7fada7a714fe..7cddfdac2f57 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -124,6 +124,7 @@ #define SDIO_DEVICE_ID_REALTEK_RTW8723DS_2ANT 0xd723 #define SDIO_DEVICE_ID_REALTEK_RTW8723DS_1ANT 0xd724 #define SDIO_DEVICE_ID_REALTEK_RTW8821DS 0xd821 +#define SDIO_DEVICE_ID_REALTEK_RTW8723CS 0xb703 #define SDIO_VENDOR_ID_SIANO 0x039a #define SDIO_DEVICE_ID_SIANO_NOVA_B0 0x0201 diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h index 5d3d15e97868..274a2767ea49 100644 --- a/include/linux/mmc/slot-gpio.h +++ b/include/linux/mmc/slot-gpio.h @@ -8,8 +8,8 @@ #ifndef MMC_SLOT_GPIO_H #define MMC_SLOT_GPIO_H +#include <linux/interrupt.h> #include <linux/types.h> -#include <linux/irqreturn.h> struct mmc_host; @@ -21,8 +21,8 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id, unsigned int debounce); int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id, unsigned int idx, unsigned int debounce); -void mmc_gpio_set_cd_isr(struct mmc_host *host, - irqreturn_t (*isr)(int irq, void *dev_id)); +int mmc_gpiod_set_cd_config(struct mmc_host *host, unsigned long config); +void mmc_gpio_set_cd_isr(struct mmc_host *host, irq_handler_t isr); int mmc_gpio_set_cd_wake(struct mmc_host *host, bool on); void mmc_gpiod_request_cd_irq(struct mmc_host *host); bool mmc_can_gpio_cd(struct mmc_host *host); diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index f349e08a9dfe..d39ebb10caeb 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -123,15 +123,6 @@ struct mmu_notifier_ops { unsigned long address); /* - * change_pte is called in cases that pte mapping to page is changed: - * for example, when ksm remaps pte to point to a new shared page. - */ - void (*change_pte)(struct mmu_notifier *subscription, - struct mm_struct *mm, - unsigned long address, - pte_t pte); - - /* * invalidate_range_start() and invalidate_range_end() must be * paired and are called only when the mmap_lock and/or the * locks protecting the reverse maps are held. If the subsystem @@ -392,8 +383,6 @@ extern int __mmu_notifier_clear_young(struct mm_struct *mm, unsigned long end); extern int __mmu_notifier_test_young(struct mm_struct *mm, unsigned long address); -extern void __mmu_notifier_change_pte(struct mm_struct *mm, - unsigned long address, pte_t pte); extern int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *r); extern void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *r); extern void __mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm, @@ -439,13 +428,6 @@ static inline int mmu_notifier_test_young(struct mm_struct *mm, return 0; } -static inline void mmu_notifier_change_pte(struct mm_struct *mm, - unsigned long address, pte_t pte) -{ - if (mm_has_notifiers(mm)) - __mmu_notifier_change_pte(mm, address, pte); -} - static inline void mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) { @@ -581,26 +563,6 @@ static inline void mmu_notifier_range_init_owner( __young; \ }) -/* - * set_pte_at_notify() sets the pte _after_ running the notifier. - * This is safe to start by updating the secondary MMUs, because the primary MMU - * pte invalidate must have already happened with a ptep_clear_flush() before - * set_pte_at_notify() has been invoked. Updating the secondary MMUs first is - * required when we change both the protection of the mapping from read-only to - * read-write and the pfn (like during copy on write page faults). Otherwise the - * old page would remain mapped readonly in the secondary MMUs after the new - * page is already writable by some CPU through the primary MMU. - */ -#define set_pte_at_notify(__mm, __address, __ptep, __pte) \ -({ \ - struct mm_struct *___mm = __mm; \ - unsigned long ___address = __address; \ - pte_t ___pte = __pte; \ - \ - mmu_notifier_change_pte(___mm, ___address, ___pte); \ - set_pte_at(___mm, ___address, __ptep, ___pte); \ -}) - #else /* CONFIG_MMU_NOTIFIER */ struct mmu_notifier_range { @@ -650,11 +612,6 @@ static inline int mmu_notifier_test_young(struct mm_struct *mm, return 0; } -static inline void mmu_notifier_change_pte(struct mm_struct *mm, - unsigned long address, pte_t pte) -{ -} - static inline void mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) { @@ -693,7 +650,6 @@ static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm) #define ptep_clear_flush_notify ptep_clear_flush #define pmdp_huge_clear_flush_notify pmdp_huge_clear_flush #define pudp_huge_clear_flush_notify pudp_huge_clear_flush -#define set_pte_at_notify set_pte_at static inline void mmu_notifier_synchronize(void) { diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index c11b7cde81ef..1dc6248feb83 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -205,7 +205,10 @@ enum node_stat_item { NR_KERNEL_SCS_KB, /* measured in KiB */ #endif NR_PAGETABLE, /* used for pagetables */ - NR_SECONDARY_PAGETABLE, /* secondary pagetables, e.g. KVM pagetables */ + NR_SECONDARY_PAGETABLE, /* secondary pagetables, KVM & IOMMU */ +#ifdef CONFIG_IOMMU_SUPPORT + NR_IOMMU_PAGES, /* # of pages allocated by IOMMU */ +#endif #ifdef CONFIG_SWAP NR_SWAPCACHE, #endif @@ -651,13 +654,12 @@ enum zone_watermarks { }; /* - * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. One additional list - * for THP which will usually be GFP_MOVABLE. Even if it is another type, - * it should not contribute to serious fragmentation causing THP allocation - * failures. + * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. Two additional lists + * are added for THP. One PCP list is used by GPF_MOVABLE, and the other PCP list + * is used by GFP_UNMOVABLE and GFP_RECLAIMABLE. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define NR_PCP_THP 1 +#define NR_PCP_THP 2 #else #define NR_PCP_THP 0 #endif @@ -1977,8 +1979,9 @@ static inline int subsection_map_index(unsigned long pfn) static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { int idx = subsection_map_index(pfn); + struct mem_section_usage *usage = READ_ONCE(ms->usage); - return test_bit(idx, READ_ONCE(ms->usage)->subsection_map); + return usage ? test_bit(idx, usage->subsection_map) : 0; } #else static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 7a9a07ea451b..4338b1b4ac44 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -690,6 +690,8 @@ struct x86_cpu_id { __u16 model; __u16 steppings; __u16 feature; /* bit index */ + /* Solely for kernel-internal use: DO NOT EXPORT to userspace! */ + __u16 flags; kernel_ulong_t driver_data; }; diff --git a/include/linux/module.h b/include/linux/module.h index 1153b0d99a80..88ecc5e9f523 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -174,6 +174,12 @@ extern void cleanup_module(void); #define MODULE_SOFTDEP(_softdep) MODULE_INFO(softdep, _softdep) /* + * Weak module dependencies. See man modprobe.d for details. + * Example: MODULE_WEAKDEP("module-foo") + */ +#define MODULE_WEAKDEP(_weakdep) MODULE_INFO(weakdep, _weakdep) + +/* * MODULE_FILE is used for generating modules.builtin * So, make it no-op when this is being built as a module */ @@ -509,7 +515,9 @@ struct module { #endif #ifdef CONFIG_DEBUG_INFO_BTF_MODULES unsigned int btf_data_size; + unsigned int btf_base_data_size; void *btf_data; + void *btf_base_data; #endif #ifdef CONFIG_JUMP_LABEL struct jump_entry *jump_entries; @@ -605,6 +613,11 @@ static inline bool module_is_live(struct module *mod) return mod->state != MODULE_STATE_GOING; } +static inline bool module_is_coming(struct module *mod) +{ + return mod->state == MODULE_STATE_COMING; +} + struct module *__module_text_address(unsigned long addr); struct module *__module_address(unsigned long addr); bool is_module_address(unsigned long addr); @@ -857,6 +870,10 @@ void *dereference_module_function_descriptor(struct module *mod, void *ptr) return ptr; } +static inline bool module_is_coming(struct module *mod) +{ + return false; +} #endif /* CONFIG_MODULES */ #ifdef CONFIG_SYSFS @@ -922,11 +939,11 @@ int module_kallsyms_on_each_symbol(const char *modname, * least KSYM_NAME_LEN long: a pointer to namebuf is returned if * found, otherwise NULL. */ -const char *module_address_lookup(unsigned long addr, - unsigned long *symbolsize, - unsigned long *offset, - char **modname, const unsigned char **modbuildid, - char *namebuf); +int module_address_lookup(unsigned long addr, + unsigned long *symbolsize, + unsigned long *offset, + char **modname, const unsigned char **modbuildid, + char *namebuf); int lookup_module_symbol_name(unsigned long addr, char *symname); int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, @@ -955,14 +972,14 @@ static inline int module_kallsyms_on_each_symbol(const char *modname, } /* For kallsyms to ask for address resolution. NULL means not found. */ -static inline const char *module_address_lookup(unsigned long addr, +static inline int module_address_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, const unsigned char **modbuildid, char *namebuf) { - return NULL; + return 0; } static inline int lookup_module_symbol_name(unsigned long addr, char *symname) diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h index 89b1e0ed9811..e395461d59e5 100644 --- a/include/linux/moduleloader.h +++ b/include/linux/moduleloader.h @@ -25,13 +25,6 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, /* Additional bytes needed by arch in front of individual sections */ unsigned int arch_mod_section_prepend(struct module *mod, unsigned int section); -/* Allocator used for allocating struct module, core sections and init - sections. Returns NULL on failure. */ -void *module_alloc(unsigned long size); - -/* Free memory returned from module_alloc. */ -void module_memfree(void *module_region); - /* Determines if the section name is an init section (that is only used during * module loading). */ @@ -129,12 +122,4 @@ void module_arch_cleanup(struct module *mod); /* Any cleanup before freeing mod->module_init */ void module_arch_freeing_init(struct module *mod); -#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ - !defined(CONFIG_KASAN_VMALLOC) -#include <linux/kasan.h> -#define MODULE_ALIGN (PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT) -#else -#define MODULE_ALIGN PAGE_SIZE -#endif - #endif diff --git a/include/linux/moxtet.h b/include/linux/moxtet.h index ac577699edfd..dfa4800306ee 100644 --- a/include/linux/moxtet.h +++ b/include/linux/moxtet.h @@ -61,13 +61,8 @@ struct moxtet_driver { struct device_driver driver; }; -static inline struct moxtet_driver * -to_moxtet_driver(struct device_driver *drv) -{ - if (!drv) - return NULL; - return container_of(drv, struct moxtet_driver, driver); -} +#define to_moxtet_driver(__drv) \ + ( __drv ? container_of_const(__drv, struct moxtet_driver, driver) : NULL ) extern int __moxtet_register_driver(struct module *owner, struct moxtet_driver *mdrv); diff --git a/include/linux/msi.h b/include/linux/msi.h index 26d07e23052e..944979763825 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -19,13 +19,9 @@ */ #include <linux/irqdomain_defs.h> -#include <linux/cpumask.h> +#include <linux/cpumask_types.h> #include <linux/msi_api.h> -#include <linux/xarray.h> -#include <linux/mutex.h> -#include <linux/list.h> #include <linux/irq.h> -#include <linux/bits.h> #include <asm/msi.h> @@ -81,7 +77,6 @@ extern int pci_msi_ignore_mask; /* Helper functions */ struct msi_desc; struct pci_dev; -struct platform_msi_priv_data; struct device_attribute; struct irq_domain; struct irq_affinity_desc; @@ -228,22 +223,6 @@ struct msi_dev_domain { struct irq_domain *domain; }; -/** - * msi_device_data - MSI per device data - * @properties: MSI properties which are interesting to drivers - * @platform_data: Platform-MSI specific data - * @mutex: Mutex protecting the MSI descriptor store - * @__domains: Internal data for per device MSI domains - * @__iter_idx: Index to search the next entry for iterators - */ -struct msi_device_data { - unsigned long properties; - struct platform_msi_priv_data *platform_data; - struct mutex mutex; - struct msi_dev_domain __domains[MSI_MAX_DEVICE_IRQDOMAINS]; - unsigned long __iter_idx; -}; - int msi_setup_device_data(struct device *dev); void msi_lock_descs(struct device *dev); @@ -556,6 +535,8 @@ enum { MSI_FLAG_USE_DEV_FWNODE = (1 << 7), /* Set parent->dev into domain->pm_dev on device domain creation */ MSI_FLAG_PARENT_PM_DEV = (1 << 8), + /* Support for parent mask/unmask */ + MSI_FLAG_PCI_MSI_MASK_PARENT = (1 << 9), /* Mask for the generic functionality */ MSI_GENERIC_FLAGS_MASK = GENMASK(15, 0), @@ -573,8 +554,6 @@ enum { MSI_FLAG_MSIX_CONTIGUOUS = (1 << 19), /* PCI/MSI-X vectors can be dynamically allocated/freed post MSI-X enable */ MSI_FLAG_PCI_MSIX_ALLOC_DYN = (1 << 20), - /* Support for PCI/IMS */ - MSI_FLAG_PCI_IMS = (1 << 21), }; /** @@ -641,41 +620,18 @@ void msi_domain_free_irqs_all(struct device *dev, unsigned int domid); struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain); -struct irq_domain *platform_msi_create_irq_domain(struct fwnode_handle *fwnode, - struct msi_domain_info *info, - struct irq_domain *parent); - -/* When an MSI domain is used as an intermediate domain */ -int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev, - int nvec, msi_alloc_info_t *args); -int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev, - int virq, int nvec, msi_alloc_info_t *args); -void msi_domain_depopulate_descs(struct device *dev, int virq, int nvec); - -struct irq_domain * -__platform_msi_create_device_domain(struct device *dev, - unsigned int nvec, - bool is_tree, - irq_write_msi_msg_t write_msi_msg, - const struct irq_domain_ops *ops, - void *host_data); - -#define platform_msi_create_device_domain(dev, nvec, write, ops, data) \ - __platform_msi_create_device_domain(dev, nvec, false, write, ops, data) -#define platform_msi_create_device_tree_domain(dev, nvec, write, ops, data) \ - __platform_msi_create_device_domain(dev, nvec, true, write, ops, data) - -int platform_msi_device_domain_alloc(struct irq_domain *domain, unsigned int virq, - unsigned int nr_irqs); -void platform_msi_device_domain_free(struct irq_domain *domain, unsigned int virq, - unsigned int nvec); -void *platform_msi_get_host_data(struct irq_domain *domain); /* Per device platform MSI */ int platform_device_msi_init_and_alloc_irqs(struct device *dev, unsigned int nvec, irq_write_msi_msg_t write_msi_msg); void platform_device_msi_free_irqs_all(struct device *dev); bool msi_device_has_isolated_msi(struct device *dev); + +static inline int msi_domain_alloc_irqs(struct device *dev, unsigned int domid, int nirqs) +{ + return msi_domain_alloc_irqs_range(dev, domid, 0, nirqs - 1); +} + #else /* CONFIG_GENERIC_MSI_IRQ */ static inline bool msi_device_has_isolated_msi(struct device *dev) { diff --git a/include/linux/msi_api.h b/include/linux/msi_api.h index 391087ad99b1..5ae72d1912c4 100644 --- a/include/linux/msi_api.h +++ b/include/linux/msi_api.h @@ -15,7 +15,6 @@ struct device; */ enum msi_domain_ids { MSI_DEFAULT_DOMAIN, - MSI_SECONDARY_DOMAIN, MSI_MAX_DEVICE_IRQDOMAINS, }; diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index 947410faf9e2..35ca19ae21ae 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -308,32 +308,32 @@ static inline uint8_t cfi_read_query(struct map_info *map, uint32_t addr) { map_word val = map_read(map, addr); - if (map_bankwidth_is_1(map)) { + if (map_bankwidth_is_1(map)) return val.x[0]; - } else if (map_bankwidth_is_2(map)) { + if (map_bankwidth_is_2(map)) return cfi16_to_cpu(map, val.x[0]); - } else { - /* No point in a 64-bit byteswap since that would just be - swapping the responses from different chips, and we are - only interested in one chip (a representative sample) */ - return cfi32_to_cpu(map, val.x[0]); - } + /* + * No point in a 64-bit byteswap since that would just be + * swapping the responses from different chips, and we are + * only interested in one chip (a representative sample) + */ + return cfi32_to_cpu(map, val.x[0]); } static inline uint16_t cfi_read_query16(struct map_info *map, uint32_t addr) { map_word val = map_read(map, addr); - if (map_bankwidth_is_1(map)) { + if (map_bankwidth_is_1(map)) return val.x[0] & 0xff; - } else if (map_bankwidth_is_2(map)) { + if (map_bankwidth_is_2(map)) return cfi16_to_cpu(map, val.x[0]); - } else { - /* No point in a 64-bit byteswap since that would just be - swapping the responses from different chips, and we are - only interested in one chip (a representative sample) */ - return cfi32_to_cpu(map, val.x[0]); - } + /* + * No point in a 64-bit byteswap since that would just be + * swapping the responses from different chips, and we are + * only interested in one chip (a representative sample) + */ + return cfi32_to_cpu(map, val.x[0]); } void cfi_udelay(int us); diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 67edc4ca2bee..a561c629d89f 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -22,6 +22,8 @@ #include <linux/cleanup.h> #include <linux/mutex_types.h> +struct device; + #ifdef CONFIG_DEBUG_LOCK_ALLOC # define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ , .dep_map = { \ @@ -117,6 +119,31 @@ do { \ } while (0) #endif /* CONFIG_PREEMPT_RT */ +#ifdef CONFIG_DEBUG_MUTEXES + +int __devm_mutex_init(struct device *dev, struct mutex *lock); + +#else + +static inline int __devm_mutex_init(struct device *dev, struct mutex *lock) +{ + /* + * When CONFIG_DEBUG_MUTEXES is off mutex_destroy() is just a nop so + * no really need to register it in the devm subsystem. + */ + return 0; +} + +#endif + +#define devm_mutex_init(dev, mutex) \ +({ \ + typeof(mutex) mutex_ = (mutex); \ + \ + mutex_init(mutex_); \ + __devm_mutex_init(dev, mutex_); \ +}) + /* * See kernel/locking/mutex.c for detailed documentation of these APIs. * Also see Documentation/locking/mutex-design.rst. diff --git a/include/linux/namei.h b/include/linux/namei.h index 74e0cc14ebf8..8ec8fed3bce8 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -44,18 +44,13 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; #define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ #define LOOKUP_IN_ROOT 0x100000 /* Treat dirfd as fs root. */ #define LOOKUP_CACHED 0x200000 /* Only do cached lookup */ +#define LOOKUP_LINKAT_EMPTY 0x400000 /* Linkat request with empty path. */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) extern int path_pts(struct path *path); -extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty); - -static inline int user_path_at(int dfd, const char __user *name, unsigned flags, - struct path *path) -{ - return user_path_at_empty(dfd, name, flags, path, NULL); -} +extern int user_path_at(int, const char __user *, unsigned, struct path *); struct dentry *lookup_one_qstr_excl(const struct qstr *name, struct dentry *base, diff --git a/include/linux/nd.h b/include/linux/nd.h index b9771ba1ef87..fa099e295f78 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -84,11 +84,7 @@ struct nd_device_driver { void (*notify)(struct device *dev, enum nvdimm_event event); }; -static inline struct nd_device_driver *to_nd_device_driver( - struct device_driver *drv) -{ - return container_of(drv, struct nd_device_driver, drv); -}; +#define to_nd_device_driver(__drv) container_of_const(__drv, struct nd_device_driver, drv) /** * struct nd_namespace_common - core infrastructure of a namespace diff --git a/include/linux/net.h b/include/linux/net.h index 15df6d5f27a7..688320b79fcc 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -153,6 +153,7 @@ struct sockaddr; struct msghdr; struct module; struct sk_buff; +struct proto_accept_arg; typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, unsigned int, size_t); typedef int (*skb_read_actor_t)(struct sock *, struct sk_buff *); @@ -171,7 +172,8 @@ struct proto_ops { int (*socketpair)(struct socket *sock1, struct socket *sock2); int (*accept) (struct socket *sock, - struct socket *newsock, int flags, bool kern); + struct socket *newsock, + struct proto_accept_arg *arg); int (*getname) (struct socket *sock, struct sockaddr *addr, int peer); diff --git a/include/linux/net/intel/libie/rx.h b/include/linux/net/intel/libie/rx.h new file mode 100644 index 000000000000..8e97775f1d66 --- /dev/null +++ b/include/linux/net/intel/libie/rx.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (C) 2024 Intel Corporation */ + +#ifndef __LIBIE_RX_H +#define __LIBIE_RX_H + +#include <net/libeth/rx.h> + +/* Rx buffer management */ + +/* The largest size for a single descriptor as per HW */ +#define LIBIE_MAX_RX_BUF_LEN 9728U +/* "True" HW-writeable space: minimum from SW and HW values */ +#define LIBIE_RX_BUF_LEN(hr) min_t(u32, LIBETH_RX_PAGE_LEN(hr), \ + LIBIE_MAX_RX_BUF_LEN) + +/* The maximum frame size as per HW (S/G) */ +#define __LIBIE_MAX_RX_FRM_LEN 16382U +/* ATST, HW can chain up to 5 Rx descriptors */ +#define LIBIE_MAX_RX_FRM_LEN(hr) \ + min_t(u32, __LIBIE_MAX_RX_FRM_LEN, LIBIE_RX_BUF_LEN(hr) * 5) +/* Maximum frame size minus LL overhead */ +#define LIBIE_MAX_MTU \ + (LIBIE_MAX_RX_FRM_LEN(LIBETH_MAX_HEADROOM) - LIBETH_RX_LL_LEN) + +/* O(1) converting i40e/ice/iavf's 8/10-bit hardware packet type to a parsed + * bitfield struct. + */ + +#define LIBIE_RX_PT_NUM 154 + +extern const struct libeth_rx_pt libie_rx_pt_lut[LIBIE_RX_PT_NUM]; + +/** + * libie_rx_pt_parse - convert HW packet type to software bitfield structure + * @pt: 10-bit hardware packet type value from the descriptor + * + * ```libie_rx_pt_lut``` must be accessed only using this wrapper. + * + * Return: parsed bitfield struct corresponding to the provided ptype. + */ +static inline struct libeth_rx_pt libie_rx_pt_parse(u32 pt) +{ + if (unlikely(pt >= LIBIE_RX_PT_NUM)) + pt = 0; + + return libie_rx_pt_lut[pt]; +} + +#endif /* __LIBIE_RX_H */ diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h index eb01c37e71e0..662074b08c94 100644 --- a/include/linux/net_tstamp.h +++ b/include/linux/net_tstamp.h @@ -5,7 +5,16 @@ #include <uapi/linux/net_tstamp.h> +#define SOF_TIMESTAMPING_SOFTWARE_MASK (SOF_TIMESTAMPING_RX_SOFTWARE | \ + SOF_TIMESTAMPING_TX_SOFTWARE | \ + SOF_TIMESTAMPING_SOFTWARE) + +#define SOF_TIMESTAMPING_HARDWARE_MASK (SOF_TIMESTAMPING_RX_HARDWARE | \ + SOF_TIMESTAMPING_TX_HARDWARE | \ + SOF_TIMESTAMPING_RAW_HARDWARE) + enum hwtstamp_source { + HWTSTAMP_SOURCE_UNSPEC, HWTSTAMP_SOURCE_NETDEV, HWTSTAMP_SOURCE_PHYLIB, }; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cb37817d6382..607009150b5f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -43,6 +43,7 @@ #include <linux/netdev_features.h> #include <linux/neighbour.h> +#include <linux/netdevice_xmit.h> #include <uapi/linux/netdevice.h> #include <uapi/linux/if_bonding.h> #include <uapi/linux/pkt_cls.h> @@ -59,7 +60,7 @@ struct ethtool_ops; struct kernel_hwtstamp_config; struct phy_device; struct dsa_port; -struct ip_tunnel_parm; +struct ip_tunnel_parm_kern; struct macsec_context; struct macsec_ops; struct netdev_name_node; @@ -79,6 +80,7 @@ struct xdp_buff; struct xdp_frame; struct xdp_metadata_ops; struct xdp_md; +struct ethtool_netdev_state; typedef u32 xdp_features_t; @@ -1327,7 +1329,7 @@ struct netdev_net_notifier { * queue id bound to an AF_XDP socket. The flags field specifies if * only RX, only Tx, or both should be woken up using the flags * XDP_WAKEUP_RX and XDP_WAKEUP_TX. - * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p, + * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm_kern *p, * int cmd); * Add, change, delete or get information on an IPv4 tunnel. * struct net_device *(*ndo_get_peer_dev)(struct net_device *dev); @@ -1583,7 +1585,8 @@ struct net_device_ops { int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); int (*ndo_tunnel_ctl)(struct net_device *dev, - struct ip_tunnel_parm *p, int cmd); + struct ip_tunnel_parm_kern *p, + int cmd); struct net_device * (*ndo_get_peer_dev)(struct net_device *dev); int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path); @@ -1816,7 +1819,8 @@ enum netdev_reg_state { * @priv_flags: Like 'flags' but invisible to userspace, * see if.h for the definitions * @gflags: Global flags ( kept as legacy ) - * @padded: How much padding added by alloc_netdev() + * @priv_len: Size of the ->priv flexible array + * @priv: Flexible array containing private data * @operstate: RFC2863 operstate * @link_mode: Mapping policy to operstate * @if_port: Selectable AUI, TP, ... @@ -1956,6 +1960,7 @@ enum netdev_reg_state { * @sysfs_rx_queue_group: Space for optional per-rx queue attributes * @rtnl_link_ops: Rtnl_link_ops * @stat_ops: Optional ops for queue-aware statistics + * @queue_mgmt_ops: Optional ops for queue management * * @gso_max_size: Maximum size of generic segmentation offload * @tso_max_size: Device (as in HW) limit on the max TSO request size @@ -1983,8 +1988,6 @@ enum netdev_reg_state { * switch driver and used to set the phys state of the * switch port. * - * @wol_enabled: Wake-on-LAN is enabled - * * @threaded: napi threaded mode is enabled * * @net_notifier_list: List of per-net netdev notifier block @@ -1996,6 +1999,7 @@ enum netdev_reg_state { * @udp_tunnel_nic_info: static structure describing the UDP tunnel * offload capabilities of the device * @udp_tunnel_nic: UDP tunnel offload state + * @ethtool: ethtool related state * @xdp_state: stores info on attached XDP BPF programs * * @nested_level: Used as a parameter of spin_lock_nested() of @@ -2196,10 +2200,10 @@ struct net_device { unsigned short neigh_priv_len; unsigned short dev_id; unsigned short dev_port; - unsigned short padded; + int irq; + u32 priv_len; spinlock_t addr_list_lock; - int irq; struct netdev_hw_addr_list uc; struct netdev_hw_addr_list mc; @@ -2338,6 +2342,8 @@ struct net_device { const struct netdev_stat_ops *stat_ops; + const struct netdev_queue_mgmt_ops *queue_mgmt_ops; + /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SEGS 65535u #define GSO_LEGACY_MAX_SIZE 65536u @@ -2367,8 +2373,7 @@ struct net_device { struct sfp_bus *sfp_bus; struct lock_class_key *qdisc_tx_busylock; bool proto_down; - unsigned wol_enabled:1; - unsigned threaded:1; + bool threaded; struct list_head net_notifier_list; @@ -2379,6 +2384,8 @@ struct net_device { const struct udp_tunnel_nic_info *udp_tunnel_nic_info; struct udp_tunnel_nic *udp_tunnel_nic; + struct ethtool_netdev_state *ethtool; + /* protected by rtnl_lock */ struct bpf_xdp_entity xdp_state[__MAX_XDP_MODE]; @@ -2397,7 +2404,13 @@ struct net_device { /** @page_pools: page pools created for this netdevice */ struct hlist_head page_pools; #endif -}; + + /** @irq_moder: dim parameters used if IS_ENABLED(CONFIG_DIMLIB). */ + struct dim_irq_moder *irq_moder; + + u8 priv[] ____cacheline_aligned + __counted_by(priv_len); +} ____cacheline_aligned; #define to_net_dev(d) container_of(d, struct net_device, dev) /* @@ -2587,7 +2600,7 @@ void dev_net_set(struct net_device *dev, struct net *net) */ static inline void *netdev_priv(const struct net_device *dev) { - return (char *)dev + ALIGN(sizeof(struct net_device), NETDEV_ALIGN); + return (void *)dev->priv; } /* Set the sysfs physical device reference for the network logical device @@ -2727,12 +2740,12 @@ struct pcpu_sw_netstats { } __aligned(4 * sizeof(u64)); struct pcpu_dstats { - u64 rx_packets; - u64 rx_bytes; - u64 rx_drops; - u64 tx_packets; - u64 tx_bytes; - u64 tx_drops; + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t rx_drops; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; + u64_stats_t tx_drops; struct u64_stats_sync syncp; } __aligned(8 * sizeof(u64)); @@ -3017,7 +3030,8 @@ int call_netdevice_notifiers_info(unsigned long val, #define net_device_entry(lh) list_entry(lh, struct net_device, dev_list) #define for_each_netdev_dump(net, d, ifindex) \ - xa_for_each_start(&(net)->dev_by_index, (ifindex), (d), (ifindex)) + for (; (d = xa_find(&(net)->dev_by_index, &ifindex, \ + ULONG_MAX, XA_PRESENT)); ifindex++) static inline struct net_device *next_net_device(struct net_device *dev) { @@ -3117,7 +3131,6 @@ static inline void unregister_netdevice(struct net_device *dev) int netdev_refcnt_read(const struct net_device *dev); void free_netdev(struct net_device *dev); -void netdev_freemem(struct net_device *dev); void init_dummy_netdev(struct net_device *dev); struct net_device *netdev_get_xmit_slave(struct net_device *dev, @@ -3133,6 +3146,7 @@ struct net_device *netdev_get_by_name(struct net *net, const char *name, netdevice_tracker *tracker, gfp_t gfp); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); struct net_device *dev_get_by_napi_id(unsigned int napi_id); +void netdev_copy_name(struct net_device *dev, char *name); static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, @@ -3195,6 +3209,7 @@ static inline bool dev_has_header(const struct net_device *dev) struct softnet_data { struct list_head poll_list; struct sk_buff_head process_queue; + local_lock_t process_queue_bh_lock; /* stats */ unsigned int processed; @@ -3203,6 +3218,7 @@ struct softnet_data { struct softnet_data *rps_ipi_list; #endif + unsigned int received_rps; bool in_net_rx_action; bool in_napi_threaded_poll; @@ -3216,13 +3232,7 @@ struct softnet_data { struct sk_buff_head xfrm_backlog; #endif /* written and read only by owning cpu: */ - struct { - u16 recursion; - u8 more; -#ifdef CONFIG_NET_EGRESS - u8 skip_txqueue; -#endif - } xmit; + struct netdev_xmit xmit; #ifdef CONFIG_RPS /* input_queue_head should be written by cpu owning this struct, * and only read by other cpus. Worth using a cache line. @@ -3235,11 +3245,11 @@ struct softnet_data { unsigned int cpu; unsigned int input_queue_tail; #endif - unsigned int received_rps; - unsigned int dropped; struct sk_buff_head input_pkt_queue; struct napi_struct backlog; + atomic_t dropped ____cacheline_aligned_in_smp; + /* Another possibly contended cache line */ spinlock_t defer_lock ____cacheline_aligned_in_smp; int defer_count; @@ -3248,44 +3258,20 @@ struct softnet_data { call_single_data_t defer_csd; }; -static inline void input_queue_head_incr(struct softnet_data *sd) -{ -#ifdef CONFIG_RPS - sd->input_queue_head++; -#endif -} - -static inline void input_queue_tail_incr_save(struct softnet_data *sd, - unsigned int *qtail) -{ -#ifdef CONFIG_RPS - *qtail = ++sd->input_queue_tail; -#endif -} - DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); +#ifndef CONFIG_PREEMPT_RT static inline int dev_recursion_level(void) { return this_cpu_read(softnet_data.xmit.recursion); } - -#define XMIT_RECURSION_LIMIT 8 -static inline bool dev_xmit_recursion(void) -{ - return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > - XMIT_RECURSION_LIMIT); -} - -static inline void dev_xmit_recursion_inc(void) +#else +static inline int dev_recursion_level(void) { - __this_cpu_inc(softnet_data.xmit.recursion); + return current->net_xmit.recursion; } -static inline void dev_xmit_recursion_dec(void) -{ - __this_cpu_dec(softnet_data.xmit.recursion); -} +#endif void __netif_schedule(struct Qdisc *q); void netif_schedule_queue(struct netdev_queue *txq); @@ -3929,9 +3915,6 @@ int generic_hwtstamp_get_lower(struct net_device *dev, int generic_hwtstamp_set_lower(struct net_device *dev, struct kernel_hwtstamp_config *kernel_cfg, struct netlink_ext_ack *extack); -int dev_set_hwtstamp_phylib(struct net_device *dev, - struct kernel_hwtstamp_config *cfg, - struct netlink_ext_ack *extack); int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata); unsigned int dev_get_flags(const struct net_device *); int __dev_change_flags(struct net_device *dev, unsigned int flags, @@ -4127,6 +4110,8 @@ static inline void dev_put(struct net_device *dev) netdev_put(dev, NULL); } +DEFINE_FREE(dev_put, struct net_device *, if (_T) dev_put(_T)) + static inline void netdev_ref_replace(struct net_device *odev, struct net_device *ndev, netdevice_tracker *tracker, @@ -4545,6 +4530,9 @@ static inline void netif_addr_unlock_bh(struct net_device *dev) void ether_setup(struct net_device *dev); +/* Allocate dummy net_device */ +struct net_device *alloc_netdev_dummy(int sizeof_priv); + /* Support for loadable net-drivers */ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned char name_assign_type, @@ -4895,18 +4883,35 @@ static inline ktime_t netdev_get_tstamp(struct net_device *dev, return hwtstamps->hwtstamp; } -static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, - struct sk_buff *skb, struct net_device *dev, - bool more) +#ifndef CONFIG_PREEMPT_RT +static inline void netdev_xmit_set_more(bool more) { __this_cpu_write(softnet_data.xmit.more, more); - return ops->ndo_start_xmit(skb, dev); } static inline bool netdev_xmit_more(void) { return __this_cpu_read(softnet_data.xmit.more); } +#else +static inline void netdev_xmit_set_more(bool more) +{ + current->net_xmit.more = more; +} + +static inline bool netdev_xmit_more(void) +{ + return current->net_xmit.more; +} +#endif + +static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, + struct sk_buff *skb, struct net_device *dev, + bool more) +{ + netdev_xmit_set_more(more); + return ops->ndo_start_xmit(skb, dev); +} static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, bool more) diff --git a/include/linux/netdevice_xmit.h b/include/linux/netdevice_xmit.h new file mode 100644 index 000000000000..38325e070296 --- /dev/null +++ b/include/linux/netdevice_xmit.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_NETDEVICE_XMIT_H +#define _LINUX_NETDEVICE_XMIT_H + +struct netdev_xmit { + u16 recursion; + u8 more; +#ifdef CONFIG_NET_EGRESS + u8 skip_txqueue; +#endif +}; + +#endif diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 100cbb261269..983816608f15 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -20,95 +20,24 @@ #include <linux/uio.h> enum netfs_sreq_ref_trace; - -/* - * Overload PG_private_2 to give us PG_fscache - this is used to indicate that - * a page is currently backed by a local disk cache - */ -#define folio_test_fscache(folio) folio_test_private_2(folio) -#define PageFsCache(page) PagePrivate2((page)) -#define SetPageFsCache(page) SetPagePrivate2((page)) -#define ClearPageFsCache(page) ClearPagePrivate2((page)) -#define TestSetPageFsCache(page) TestSetPagePrivate2((page)) -#define TestClearPageFsCache(page) TestClearPagePrivate2((page)) +typedef struct mempool_s mempool_t; /** - * folio_start_fscache - Start an fscache write on a folio. + * folio_start_private_2 - Start an fscache write on a folio. [DEPRECATED] * @folio: The folio. * * Call this function before writing a folio to a local cache. Starting a * second write before the first one finishes is not allowed. + * + * Note that this should no longer be used. */ -static inline void folio_start_fscache(struct folio *folio) +static inline void folio_start_private_2(struct folio *folio) { VM_BUG_ON_FOLIO(folio_test_private_2(folio), folio); folio_get(folio); folio_set_private_2(folio); } -/** - * folio_end_fscache - End an fscache write on a folio. - * @folio: The folio. - * - * Call this function after the folio has been written to the local cache. - * This will wake any sleepers waiting on this folio. - */ -static inline void folio_end_fscache(struct folio *folio) -{ - folio_end_private_2(folio); -} - -/** - * folio_wait_fscache - Wait for an fscache write on this folio to end. - * @folio: The folio. - * - * If this folio is currently being written to a local cache, wait for - * the write to finish. Another write may start after this one finishes, - * unless the caller holds the folio lock. - */ -static inline void folio_wait_fscache(struct folio *folio) -{ - folio_wait_private_2(folio); -} - -/** - * folio_wait_fscache_killable - Wait for an fscache write on this folio to end. - * @folio: The folio. - * - * If this folio is currently being written to a local cache, wait - * for the write to finish or for a fatal signal to be received. - * Another write may start after this one finishes, unless the caller - * holds the folio lock. - * - * Return: - * - 0 if successful. - * - -EINTR if a fatal signal was encountered. - */ -static inline int folio_wait_fscache_killable(struct folio *folio) -{ - return folio_wait_private_2_killable(folio); -} - -static inline void set_page_fscache(struct page *page) -{ - folio_start_fscache(page_folio(page)); -} - -static inline void end_page_fscache(struct page *page) -{ - folio_end_private_2(page_folio(page)); -} - -static inline void wait_on_page_fscache(struct page *page) -{ - folio_wait_private_2(page_folio(page)); -} - -static inline int wait_on_page_fscache_killable(struct page *page) -{ - return folio_wait_private_2_killable(page_folio(page)); -} - /* Marks used on xarray-based buffers */ #define NETFS_BUF_PUT_MARK XA_MARK_0 /* - Page needs putting */ #define NETFS_BUF_PAGECACHE_MARK XA_MARK_1 /* - Page needs wb/dirty flag wrangling */ @@ -135,14 +64,15 @@ struct netfs_inode { #if IS_ENABLED(CONFIG_FSCACHE) struct fscache_cookie *cache; #endif + struct mutex wb_lock; /* Writeback serialisation */ loff_t remote_i_size; /* Size of the remote file */ loff_t zero_point; /* Size after which we assume there's no data * on the server */ + atomic_t io_count; /* Number of outstanding reqs */ unsigned long flags; #define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ #define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ #define NETFS_ICTX_WRITETHROUGH 2 /* Write-through caching */ -#define NETFS_ICTX_NO_WRITE_STREAMING 3 /* Don't engage in write-streaming */ }; /* @@ -165,16 +95,25 @@ struct netfs_folio { unsigned int dirty_len; /* Write-streaming dirty data length */ }; #define NETFS_FOLIO_INFO 0x1UL /* OR'd with folio->private. */ +#define NETFS_FOLIO_COPY_TO_CACHE ((struct netfs_group *)0x356UL) /* Write to the cache only */ -static inline struct netfs_folio *netfs_folio_info(struct folio *folio) +static inline bool netfs_is_folio_info(const void *priv) { - void *priv = folio_get_private(folio); + return (unsigned long)priv & NETFS_FOLIO_INFO; +} - if ((unsigned long)priv & NETFS_FOLIO_INFO) +static inline struct netfs_folio *__netfs_folio_info(const void *priv) +{ + if (netfs_is_folio_info(priv)) return (struct netfs_folio *)((unsigned long)priv & ~NETFS_FOLIO_INFO); return NULL; } +static inline struct netfs_folio *netfs_folio_info(struct folio *folio) +{ + return __netfs_folio_info(folio_get_private(folio)); +} + static inline struct netfs_group *netfs_folio_group(struct folio *folio) { struct netfs_folio *finfo; @@ -187,6 +126,33 @@ static inline struct netfs_group *netfs_folio_group(struct folio *folio) } /* + * Stream of I/O subrequests going to a particular destination, such as the + * server or the local cache. This is mainly intended for writing where we may + * have to write to multiple destinations concurrently. + */ +struct netfs_io_stream { + /* Submission tracking */ + struct netfs_io_subrequest *construct; /* Op being constructed */ + unsigned int submit_off; /* Folio offset we're submitting from */ + unsigned int submit_len; /* Amount of data left to submit */ + unsigned int submit_max_len; /* Amount I/O can be rounded up to */ + void (*prepare_write)(struct netfs_io_subrequest *subreq); + void (*issue_write)(struct netfs_io_subrequest *subreq); + /* Collection tracking */ + struct list_head subrequests; /* Contributory I/O operations */ + struct netfs_io_subrequest *front; /* Op being collected */ + unsigned long long collected_to; /* Position we've collected results to */ + size_t transferred; /* The amount transferred from this stream */ + enum netfs_io_source source; /* Where to read from/write to */ + unsigned short error; /* Aggregate error for the stream */ + unsigned char stream_nr; /* Index of stream in parent table */ + bool avail; /* T if stream is available */ + bool active; /* T if stream is active */ + bool need_retry; /* T if this stream needs retrying */ + bool failed; /* T if this stream failed */ +}; + +/* * Resources required to do operations on a cache. */ struct netfs_cache_resources { @@ -209,14 +175,17 @@ struct netfs_io_subrequest { struct work_struct work; struct list_head rreq_link; /* Link in rreq->subrequests */ struct iov_iter io_iter; /* Iterator for this subrequest */ - loff_t start; /* Where to start the I/O */ + unsigned long long start; /* Where to start the I/O */ + size_t max_len; /* Maximum size of the I/O */ size_t len; /* Size of the I/O */ size_t transferred; /* Amount of data transferred */ refcount_t ref; short error; /* 0 or error that occurred */ unsigned short debug_index; /* Index in list (for debugging output) */ + unsigned int nr_segs; /* Number of segs in io_iter */ unsigned int max_nr_segs; /* 0 or max number of segments in an iterator */ enum netfs_io_source source; /* Where to read from/write to */ + unsigned char stream_nr; /* I/O stream this belongs to */ unsigned long flags; #define NETFS_SREQ_COPY_TO_CACHE 0 /* Set if should copy the data to the cache */ #define NETFS_SREQ_CLEAR_TAIL 1 /* Set if the rest of the read should be cleared */ @@ -224,15 +193,20 @@ struct netfs_io_subrequest { #define NETFS_SREQ_SEEK_DATA_READ 3 /* Set if ->read() should SEEK_DATA first */ #define NETFS_SREQ_NO_PROGRESS 4 /* Set if we didn't manage to read any data */ #define NETFS_SREQ_ONDEMAND 5 /* Set if it's from on-demand read mode */ +#define NETFS_SREQ_BOUNDARY 6 /* Set if ends on hard boundary (eg. ceph object) */ +#define NETFS_SREQ_IN_PROGRESS 8 /* Unlocked when the subrequest completes */ +#define NETFS_SREQ_NEED_RETRY 9 /* Set if the filesystem requests a retry */ +#define NETFS_SREQ_RETRYING 10 /* Set if we're retrying */ +#define NETFS_SREQ_FAILED 11 /* Set if the subreq failed unretryably */ }; enum netfs_io_origin { NETFS_READAHEAD, /* This read was triggered by readahead */ NETFS_READPAGE, /* This read is a synchronous read */ NETFS_READ_FOR_WRITE, /* This read is to prepare a write */ + NETFS_COPY_TO_CACHE, /* This write is to copy a read to the cache */ NETFS_WRITEBACK, /* This write was triggered by writepages */ NETFS_WRITETHROUGH, /* This write was made by netfs_perform_write() */ - NETFS_LAUNDER_WRITE, /* This is triggered by ->launder_folio() */ NETFS_UNBUFFERED_WRITE, /* This is an unbuffered write */ NETFS_DIO_READ, /* This is a direct I/O read */ NETFS_DIO_WRITE, /* This is a direct I/O write */ @@ -254,26 +228,36 @@ struct netfs_io_request { struct netfs_cache_resources cache_resources; struct list_head proc_link; /* Link in netfs_iorequests */ struct list_head subrequests; /* Contributory I/O operations */ + struct netfs_io_stream io_streams[2]; /* Streams of parallel I/O operations */ +#define NR_IO_STREAMS 2 //wreq->nr_io_streams + struct netfs_group *group; /* Writeback group being written back */ struct iov_iter iter; /* Unencrypted-side iterator */ struct iov_iter io_iter; /* I/O (Encrypted-side) iterator */ void *netfs_priv; /* Private data for the netfs */ + void *netfs_priv2; /* Private data for the netfs */ struct bio_vec *direct_bv; /* DIO buffer list (when handling iovec-iter) */ unsigned int direct_bv_count; /* Number of elements in direct_bv[] */ unsigned int debug_id; unsigned int rsize; /* Maximum read size (0 for none) */ unsigned int wsize; /* Maximum write size (0 for none) */ - unsigned int subreq_counter; /* Next subreq->debug_index */ + atomic_t subreq_counter; /* Next subreq->debug_index */ + unsigned int nr_group_rel; /* Number of refs to release on ->group */ + spinlock_t lock; /* Lock for queuing subreqs */ atomic_t nr_outstanding; /* Number of ops in progress */ atomic_t nr_copy_ops; /* Number of copy-to-cache ops in progress */ - size_t submitted; /* Amount submitted for I/O so far */ - size_t len; /* Length of the request */ size_t upper_len; /* Length can be extended to here */ + unsigned long long submitted; /* Amount submitted for I/O so far */ + unsigned long long len; /* Length of the request */ size_t transferred; /* Amount to be indicated as transferred */ short error; /* 0 or error that occurred */ enum netfs_io_origin origin; /* Origin of the request */ bool direct_bv_unpin; /* T if direct_bv[] must be unpinned */ - loff_t i_size; /* Size of the file */ - loff_t start; /* Start position */ + unsigned long long i_size; /* Size of the file */ + unsigned long long start; /* Start position */ + atomic64_t issued_to; /* Write issuer folio cursor */ + unsigned long long contiguity; /* Tracking for gaps in the writeback sequence */ + unsigned long long collected_to; /* Point we've collected to */ + unsigned long long cleaned_to; /* Position we've cleaned folios to */ pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ refcount_t ref; unsigned long flags; @@ -283,10 +267,14 @@ struct netfs_io_request { #define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ #define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */ -#define NETFS_RREQ_WRITE_TO_CACHE 7 /* Need to write to the cache */ #define NETFS_RREQ_UPLOAD_TO_SERVER 8 /* Need to write to the server */ #define NETFS_RREQ_NONBLOCK 9 /* Don't block if possible (O_NONBLOCK) */ #define NETFS_RREQ_BLOCKED 10 /* We blocked */ +#define NETFS_RREQ_PAUSE 11 /* Pause subrequest generation */ +#define NETFS_RREQ_USE_IO_ITER 12 /* Use ->io_iter rather than ->i_pages */ +#define NETFS_RREQ_ALL_QUEUED 13 /* All subreqs are now queued */ +#define NETFS_RREQ_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark + * write to cache on read */ const struct netfs_request_ops *netfs_ops; void (*cleanup)(struct netfs_io_request *req); }; @@ -295,8 +283,8 @@ struct netfs_io_request { * Operations the network filesystem can/must provide to the helpers. */ struct netfs_request_ops { - unsigned int io_request_size; /* Alloc size for netfs_io_request struct */ - unsigned int io_subrequest_size; /* Alloc size for netfs_io_subrequest struct */ + mempool_t *request_pool; + mempool_t *subrequest_pool; int (*init_request)(struct netfs_io_request *rreq, struct file *file); void (*free_request)(struct netfs_io_request *rreq); void (*free_subrequest)(struct netfs_io_subrequest *rreq); @@ -312,10 +300,13 @@ struct netfs_request_ops { /* Modification handling */ void (*update_i_size)(struct inode *inode, loff_t i_size); + void (*post_modify)(struct inode *inode); /* Write request handling */ - void (*create_write_requests)(struct netfs_io_request *wreq, - loff_t start, size_t len); + void (*begin_writeback)(struct netfs_io_request *wreq); + void (*prepare_write)(struct netfs_io_subrequest *subreq); + void (*issue_write)(struct netfs_io_subrequest *subreq); + void (*retry_request)(struct netfs_io_request *wreq, struct netfs_io_stream *stream); void (*invalidate_cache)(struct netfs_io_request *wreq); }; @@ -350,15 +341,27 @@ struct netfs_cache_ops { netfs_io_terminated_t term_func, void *term_func_priv); + /* Write data to the cache from a netfs subrequest. */ + void (*issue_write)(struct netfs_io_subrequest *subreq); + /* Expand readahead request */ void (*expand_readahead)(struct netfs_cache_resources *cres, - loff_t *_start, size_t *_len, loff_t i_size); + unsigned long long *_start, + unsigned long long *_len, + unsigned long long i_size); /* Prepare a read operation, shortening it to a cached/uncached * boundary as appropriate. */ enum netfs_io_source (*prepare_read)(struct netfs_io_subrequest *subreq, - loff_t i_size); + unsigned long long i_size); + + /* Prepare a write subrequest, working out if we're allowed to do it + * and finding out the maximum amount of data to gather before + * attempting to submit. If we're not permitted to do it, the + * subrequest should be marked failed. + */ + void (*prepare_write_subreq)(struct netfs_io_subrequest *subreq); /* Prepare a write operation, working out what part of the write we can * actually do. @@ -384,6 +387,7 @@ struct netfs_cache_ops { }; /* High-level read API. */ +ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *iter); ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter); ssize_t netfs_buffered_read_iter(struct kiocb *iocb, struct iov_iter *iter); ssize_t netfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter); @@ -394,6 +398,8 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, ssize_t netfs_buffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *from, struct netfs_group *netfs_group); ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from); +ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *iter, + struct netfs_group *netfs_group); ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from); /* Address operations API */ @@ -410,7 +416,6 @@ int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc); void netfs_clear_inode_writeback(struct inode *inode, const void *aux); void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length); bool netfs_release_folio(struct folio *folio, gfp_t gfp); -int netfs_launder_folio(struct folio *folio); /* VMA operations API. */ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group); @@ -426,9 +431,7 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, iov_iter_extraction_t extraction_flags); size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset, size_t max_size, size_t max_segs); -struct netfs_io_subrequest *netfs_create_write_request( - struct netfs_io_request *wreq, enum netfs_io_source dest, - loff_t start, size_t len, work_func_t worker); +void netfs_prepare_write_failed(struct netfs_io_subrequest *subreq); void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error, bool was_async); void netfs_queue_write_request(struct netfs_io_subrequest *subreq); @@ -469,9 +472,11 @@ static inline void netfs_inode_init(struct netfs_inode *ctx, ctx->remote_i_size = i_size_read(&ctx->inode); ctx->zero_point = LLONG_MAX; ctx->flags = 0; + atomic_set(&ctx->io_count, 0); #if IS_ENABLED(CONFIG_FSCACHE) ctx->cache = NULL; #endif + mutex_init(&ctx->wb_lock); /* ->releasepage() drives zero_point */ if (use_zero_point) { ctx->zero_point = ctx->remote_i_size; @@ -511,4 +516,20 @@ static inline struct fscache_cookie *netfs_i_cookie(struct netfs_inode *ctx) #endif } +/** + * netfs_wait_for_outstanding_io - Wait for outstanding I/O to complete + * @inode: The netfs inode to wait on + * + * Wait for outstanding I/O requests of any type to complete. This is intended + * to be called from inode eviction routines. This makes sure that any + * resources held by those requests are cleaned up before we let the inode get + * cleaned up. + */ +static inline void netfs_wait_for_outstanding_io(struct inode *inode) +{ + struct netfs_inode *ictx = netfs_inode(inode); + + wait_var_event(&ictx->io_count, atomic_read(&ictx->io_count) == 0); +} + #endif /* _LINUX_NETFS_H */ diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 5df7340d4dab..b332c2048c75 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -47,7 +47,6 @@ struct netlink_kernel_cfg { unsigned int groups; unsigned int flags; void (*input)(struct sk_buff *skb); - struct mutex *cb_mutex; int (*bind)(struct net *net, int group); void (*unbind)(struct net *net, int group); void (*release) (struct sock *sk, unsigned long *groups); diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index ef8d2d618d5b..f9df88091c6d 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -367,6 +367,8 @@ enum open_delegation_type4 { NFS4_OPEN_DELEGATE_READ = 1, NFS4_OPEN_DELEGATE_WRITE = 2, NFS4_OPEN_DELEGATE_NONE_EXT = 3, /* 4.1 */ + NFS4_OPEN_DELEGATE_READ_ATTRS_DELEG = 4, + NFS4_OPEN_DELEGATE_WRITE_ATTRS_DELEG = 5, }; enum why_no_delegation4 { /* new to v4.1 */ @@ -507,6 +509,12 @@ enum { FATTR4_XATTR_SUPPORT = 82, }; +enum { + FATTR4_TIME_DELEG_ACCESS = 84, + FATTR4_TIME_DELEG_MODIFY = 85, + FATTR4_OPEN_ARGUMENTS = 86, +}; + /* * The following internal definitions enable processing the above * attribute bits within 32-bit word boundaries. @@ -586,6 +594,9 @@ enum { #define FATTR4_WORD2_SECURITY_LABEL BIT(FATTR4_SEC_LABEL - 64) #define FATTR4_WORD2_MODE_UMASK BIT(FATTR4_MODE_UMASK - 64) #define FATTR4_WORD2_XATTR_SUPPORT BIT(FATTR4_XATTR_SUPPORT - 64) +#define FATTR4_WORD2_TIME_DELEG_ACCESS BIT(FATTR4_TIME_DELEG_ACCESS - 64) +#define FATTR4_WORD2_TIME_DELEG_MODIFY BIT(FATTR4_TIME_DELEG_MODIFY - 64) +#define FATTR4_WORD2_OPEN_ARGUMENTS BIT(FATTR4_OPEN_ARGUMENTS - 64) /* MDS threshold bitmap bits */ #define THRESHOLD_RD (1UL << 0) @@ -701,6 +712,12 @@ enum state_protect_how4 { SP4_SSV = 2 }; +/* GET_DIR_DELEGATION non-fatal status codes */ +enum gddrnf4_status { + GDD4_OK = 0, + GDD4_UNAVAIL = 1 +}; + enum pnfs_layouttype { LAYOUT_NFSV4_1_FILES = 1, LAYOUT_OSD2_OBJECTS = 2, diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index d59116ac8209..039898d70954 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -561,6 +561,9 @@ extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openfl extern void nfs_access_zap_cache(struct inode *inode); extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, u32 *mask, bool may_block); +extern int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry, + struct file *file, unsigned int open_flags, + umode_t mode); /* * linux/fs/nfs/symlink.c diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 92de074e63b9..1df86ab98c77 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -140,6 +140,7 @@ struct nfs_server { struct rpc_clnt * client_acl; /* ACL RPC client handle */ struct nlm_host *nlm_host; /* NLM client handle */ struct nfs_iostats __percpu *io_stats; /* I/O statistics */ + wait_queue_head_t write_congestion_wait; /* wait until write congestion eases */ atomic_long_t writeback; /* number of writeback pages */ unsigned int write_congested;/* flag set when writeback gets too high */ unsigned int flags; /* various flags */ @@ -278,6 +279,9 @@ struct nfs_server { #define NFS_CAP_LGOPEN (1U << 5) #define NFS_CAP_CASE_INSENSITIVE (1U << 6) #define NFS_CAP_CASE_PRESERVING (1U << 7) +#define NFS_CAP_REBOOT_LAYOUTRETURN (1U << 8) +#define NFS_CAP_OPEN_XOR (1U << 12) +#define NFS_CAP_DELEGTIME (1U << 13) #define NFS_CAP_POSIX_LOCK (1U << 14) #define NFS_CAP_UIDGID_NOMAP (1U << 15) #define NFS_CAP_STATEID_NFSV41 (1U << 16) diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 1c315f854ea8..169b4ae30ff4 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -152,11 +152,8 @@ extern void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *, pgoff_t); extern size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, struct nfs_page *prev, struct nfs_page *req); -extern int nfs_wait_on_request(struct nfs_page *); extern void nfs_unlock_request(struct nfs_page *req); extern void nfs_unlock_and_release_request(struct nfs_page *); -extern struct nfs_page *nfs_page_group_lock_head(struct nfs_page *req); -extern int nfs_page_group_lock_subrequests(struct nfs_page *head); extern void nfs_join_page_group(struct nfs_page *head, struct nfs_commit_info *cinfo, struct inode *inode); @@ -208,8 +205,8 @@ static inline struct inode *nfs_page_to_inode(const struct nfs_page *req) struct folio *folio = nfs_page_to_folio(req); if (folio == NULL) - return page_file_mapping(req->wb_page)->host; - return folio_file_mapping(folio)->host; + return req->wb_page->mapping->host; + return folio->mapping->host; } /** diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index d09b9773b20c..45623af3e7b8 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -449,6 +449,22 @@ struct stateowner_id { __u32 uniquifier; }; +struct nfs4_open_delegation { + __u32 open_delegation_type; + union { + struct { + fmode_t type; + __u32 do_recall; + nfs4_stateid stateid; + unsigned long pagemod_limit; + }; + struct { + __u32 why_no_delegation; + __u32 will_notify; + }; + }; +}; + /* * Arguments to the open call. */ @@ -468,7 +484,7 @@ struct nfs_openargs { nfs4_verifier verifier; /* EXCLUSIVE */ }; nfs4_stateid delegation; /* CLAIM_DELEGATE_CUR */ - fmode_t delegation_type; /* CLAIM_PREVIOUS */ + __u32 delegation_type; /* CLAIM_PREVIOUS */ } u; const struct qstr * name; const struct nfs_server *server; /* Needed for ID mapping */ @@ -490,13 +506,10 @@ struct nfs_openres { struct nfs_fattr * f_attr; struct nfs_seqid * seqid; const struct nfs_server *server; - fmode_t delegation_type; - nfs4_stateid delegation; - unsigned long pagemod_limit; - __u32 do_recall; __u32 attrset[NFS4_BITMAP_SIZE]; struct nfs4_string *owner; struct nfs4_string *group_owner; + struct nfs4_open_delegation delegation; __u32 access_request; __u32 access_supported; __u32 access_result; @@ -609,6 +622,13 @@ struct nfs_release_lockowner_res { struct nfs4_sequence_res seq_res; }; +struct nfs4_delegattr { + struct timespec64 atime; + struct timespec64 mtime; + bool atime_set; + bool mtime_set; +}; + struct nfs4_delegreturnargs { struct nfs4_sequence_args seq_args; const struct nfs_fh *fhandle; @@ -616,6 +636,7 @@ struct nfs4_delegreturnargs { const u32 *bitmask; u32 bitmask_store[NFS_BITMASK_SZ]; struct nfs4_layoutreturn_args *lr_args; + struct nfs4_delegattr *sattr_args; }; struct nfs4_delegreturnres { @@ -624,6 +645,8 @@ struct nfs4_delegreturnres { struct nfs_server *server; struct nfs4_layoutreturn_res *lr_res; int lr_ret; + bool sattr_res; + int sattr_ret; }; /* @@ -1190,6 +1213,14 @@ struct nfs4_statfs_res { struct nfs_fsstat *fsstat; }; +struct nfs4_open_caps { + u32 oa_share_access[1]; + u32 oa_share_deny[1]; + u32 oa_share_access_want[1]; + u32 oa_open_claim[1]; + u32 oa_createmode[1]; +}; + struct nfs4_server_caps_arg { struct nfs4_sequence_args seq_args; struct nfs_fh *fhandle; @@ -1206,6 +1237,7 @@ struct nfs4_server_caps_res { u32 fh_expire_type; u32 case_insensitive; u32 case_preserving; + struct nfs4_open_caps open_caps; }; #define NFS4_PATHNAME_MAXCOMPONENTS 512 @@ -1406,7 +1438,7 @@ struct nfs41_secinfo_no_name_args { struct nfs41_test_stateid_args { struct nfs4_sequence_args seq_args; - nfs4_stateid *stateid; + nfs4_stateid stateid; }; struct nfs41_test_stateid_res { @@ -1807,7 +1839,8 @@ struct nfs_rpc_ops { int open_flags, struct iattr *iattr, int *); - int (*have_delegation)(struct inode *, fmode_t); + int (*have_delegation)(struct inode *, fmode_t, int); + int (*return_delegation)(struct inode *); struct nfs_client *(*alloc_client) (const struct nfs_client_initdata *); struct nfs_client *(*init_client) (struct nfs_client *, const struct nfs_client_initdata *); diff --git a/include/linux/nmi.h b/include/linux/nmi.h index f53438eae815..a8dfb38c9bb6 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -105,10 +105,12 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs); extern void hardlockup_detector_perf_stop(void); extern void hardlockup_detector_perf_restart(void); extern void hardlockup_detector_perf_cleanup(void); +extern void hardlockup_config_perf_event(const char *str); #else static inline void hardlockup_detector_perf_stop(void) { } static inline void hardlockup_detector_perf_restart(void) { } static inline void hardlockup_detector_perf_cleanup(void) { } +static inline void hardlockup_config_perf_event(const char *str) { } #endif void watchdog_hardlockup_stop(void); diff --git a/include/linux/node.h b/include/linux/node.h index dfc004e4bee7..9a881c2208b3 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -16,7 +16,6 @@ #define _LINUX_NODE_H_ #include <linux/device.h> -#include <linux/cpumask.h> #include <linux/list.h> /** diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index 5601d14e2886..dab6a1734a22 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -42,6 +42,17 @@ struct nsproxy { }; extern struct nsproxy init_nsproxy; +#define to_ns_common(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: &(__ns->ns), \ + struct ipc_namespace *: &(__ns->ns), \ + struct net *: &(__ns->ns), \ + struct pid_namespace *: &(__ns->ns), \ + struct mnt_namespace *: &(__ns->ns), \ + struct time_namespace *: &(__ns->ns), \ + struct user_namespace *: &(__ns->ns), \ + struct uts_namespace *: &(__ns->ns)) + /* * A structure to encompass all bits needed to install * a partial or complete new set of namespaces. @@ -112,4 +123,6 @@ static inline void get_nsproxy(struct nsproxy *ns) refcount_inc(&ns->count); } +DEFINE_FREE(put_nsproxy, struct nsproxy *, if (_T) put_nsproxy(_T)) + #endif diff --git a/include/linux/numa.h b/include/linux/numa.h index 915033a75731..eb19503604fe 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -15,6 +15,11 @@ #define NUMA_NO_NODE (-1) #define NUMA_NO_MEMBLK (-1) +static inline bool numa_valid_node(int nid) +{ + return nid >= 0 && nid < MAX_NUMNODES; +} + /* optionally keep NUMA memory info available post init */ #ifdef CONFIG_NUMA_KEEP_MEMINFO #define __initdata_or_meminfo @@ -36,12 +41,7 @@ int memory_add_physaddr_to_nid(u64 start); int phys_to_target_node(u64 start); #endif -#ifndef numa_fill_memblks -static inline int __init numa_fill_memblks(u64 start, u64 end) -{ - return NUMA_NO_MEMBLK; -} -#endif +int numa_fill_memblks(u64 start, u64 end); #else /* !CONFIG_NUMA */ static inline int numa_nearest_node(int node, unsigned int state) diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 4109f1bd6128..9f6acadfe0c8 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -620,7 +620,7 @@ enum { * * Structure used between LLDD and nvmet-fc layer to represent the exchange * context for a FC-NVME FCP I/O operation (e.g. a nvme sqe, the sqe-related - * memory transfers, and its assocated cqe transfer). + * memory transfers, and its associated cqe transfer). * * The structure is allocated by the LLDD whenever a FCP CMD IU is received * from the FC link. The address of the structure is passed to the nvmet-fc @@ -920,6 +920,9 @@ struct nvmet_fc_target_port { * further references to hosthandle. * Entrypoint is Mandatory if the lldd calls nvmet_fc_invalidate_host(). * + * @host_traddr: called by the transport to retrieve the node name and + * port name of the host port address. + * * @max_hw_queues: indicates the maximum number of hw queues the LLDD * supports for cpu affinitization. * Value is Mandatory. Must be at least 1. @@ -975,6 +978,7 @@ struct nvmet_fc_target_template { void (*ls_abort)(struct nvmet_fc_target_port *targetport, void *hosthandle, struct nvmefc_ls_req *lsreq); void (*host_release)(void *hosthandle); + int (*host_traddr)(void *hosthandle, u64 *wwnn, u64 *wwpn); u32 max_hw_queues; u16 max_sgl_segments; diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 425573202295..7b2ae2e43544 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -25,6 +25,9 @@ #define NVME_NSID_ALL 0xffffffff +/* Special NSSR value, 'NVMe' */ +#define NVME_SUBSYS_RESET 0x4E564D65 + enum nvme_subsys_type { /* Referral to another discovery type target subsystem */ NVME_NQN_DISC = 1, @@ -85,10 +88,11 @@ enum { enum { NVMF_RDMA_QPTYPE_CONNECTED = 1, /* Reliable Connected */ NVMF_RDMA_QPTYPE_DATAGRAM = 2, /* Reliable Datagram */ + NVMF_RDMA_QPTYPE_INVALID = 0xff, }; -/* RDMA QP Service Type codes for Discovery Log Page entry TSAS - * RDMA_QPTYPE field +/* RDMA Provider Type codes for Discovery Log Page entry TSAS + * RDMA_PRTYPE field */ enum { NVMF_RDMA_PRTYPE_NOT_SPECIFIED = 1, /* No Provider Specified */ @@ -110,6 +114,7 @@ enum { NVMF_TCP_SECTYPE_NONE = 0, /* No Security */ NVMF_TCP_SECTYPE_TLS12 = 1, /* TLSv1.2, NVMe-oF 1.1 and NVMe-TCP 3.6.1.1 */ NVMF_TCP_SECTYPE_TLS13 = 2, /* TLSv1.3, NVMe-oF 1.1 and NVMe-TCP 3.6.1.1 */ + NVMF_TCP_SECTYPE_INVALID = 0xff, }; #define NVME_AQ_DEPTH 32 @@ -480,6 +485,9 @@ enum { NVME_ID_NS_NVM_STS_MASK = 0x7f, NVME_ID_NS_NVM_GUARD_SHIFT = 7, NVME_ID_NS_NVM_GUARD_MASK = 0x3, + NVME_ID_NS_NVM_QPIF_SHIFT = 9, + NVME_ID_NS_NVM_QPIF_MASK = 0xf, + NVME_ID_NS_NVM_QPIFS = 1 << 3, }; static inline __u8 nvme_elbaf_sts(__u32 elbaf) @@ -492,6 +500,11 @@ static inline __u8 nvme_elbaf_guard_type(__u32 elbaf) return (elbaf >> NVME_ID_NS_NVM_GUARD_SHIFT) & NVME_ID_NS_NVM_GUARD_MASK; } +static inline __u8 nvme_elbaf_qualified_guard_type(__u32 elbaf) +{ + return (elbaf >> NVME_ID_NS_NVM_QPIF_SHIFT) & NVME_ID_NS_NVM_QPIF_MASK; +} + struct nvme_id_ctrl_nvm { __u8 vsl; __u8 wzsl; @@ -571,6 +584,7 @@ enum { NVME_NVM_NS_16B_GUARD = 0, NVME_NVM_NS_32B_GUARD = 1, NVME_NVM_NS_64B_GUARD = 2, + NVME_NVM_NS_QTYPE_GUARD = 3, }; static inline __u8 nvme_lbaf_index(__u8 flbas) @@ -1846,6 +1860,7 @@ enum { /* * Generic Command Status: */ + NVME_SCT_GENERIC = 0x0, NVME_SC_SUCCESS = 0x0, NVME_SC_INVALID_OPCODE = 0x1, NVME_SC_INVALID_FIELD = 0x2, @@ -1893,6 +1908,7 @@ enum { /* * Command Specific Status: */ + NVME_SCT_COMMAND_SPECIFIC = 0x100, NVME_SC_CQ_INVALID = 0x100, NVME_SC_QID_INVALID = 0x101, NVME_SC_QUEUE_SIZE = 0x102, @@ -1966,6 +1982,7 @@ enum { /* * Media and Data Integrity Errors: */ + NVME_SCT_MEDIA_ERROR = 0x200, NVME_SC_WRITE_FAULT = 0x280, NVME_SC_READ_ERROR = 0x281, NVME_SC_GUARD_CHECK = 0x282, @@ -1978,6 +1995,7 @@ enum { /* * Path-related Errors: */ + NVME_SCT_PATH = 0x300, NVME_SC_INTERNAL_PATH_ERROR = 0x300, NVME_SC_ANA_PERSISTENT_LOSS = 0x301, NVME_SC_ANA_INACCESSIBLE = 0x302, @@ -1986,11 +2004,17 @@ enum { NVME_SC_HOST_PATH_ERROR = 0x370, NVME_SC_HOST_ABORTED_CMD = 0x371, - NVME_SC_CRD = 0x1800, - NVME_SC_MORE = 0x2000, - NVME_SC_DNR = 0x4000, + NVME_SC_MASK = 0x00ff, /* Status Code */ + NVME_SCT_MASK = 0x0700, /* Status Code Type */ + NVME_SCT_SC_MASK = NVME_SCT_MASK | NVME_SC_MASK, + + NVME_STATUS_CRD = 0x1800, /* Command Retry Delayed */ + NVME_STATUS_MORE = 0x2000, + NVME_STATUS_DNR = 0x4000, /* Do Not Retry */ }; +#define NVME_SCT(status) ((status) >> 8 & 7) + struct nvme_completion { /* * Used by Admin and Fabrics commands to return data: diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index f0ba0e03218f..3ebeaa0ded00 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -199,7 +199,10 @@ int nvmem_add_one_cell(struct nvmem_device *nvmem, int nvmem_layout_register(struct nvmem_layout *layout); void nvmem_layout_unregister(struct nvmem_layout *layout); -int nvmem_layout_driver_register(struct nvmem_layout_driver *drv); +#define nvmem_layout_driver_register(drv) \ + __nvmem_layout_driver_register(drv, THIS_MODULE) +int __nvmem_layout_driver_register(struct nvmem_layout_driver *drv, + struct module *owner); void nvmem_layout_driver_unregister(struct nvmem_layout_driver *drv); #define module_nvmem_layout_driver(__nvmem_layout_driver) \ module_driver(__nvmem_layout_driver, nvmem_layout_driver_register, \ diff --git a/include/linux/objagg.h b/include/linux/objagg.h index 78021777df46..6df5b887dc54 100644 --- a/include/linux/objagg.h +++ b/include/linux/objagg.h @@ -8,7 +8,6 @@ struct objagg_ops { size_t obj_size; bool (*delta_check)(void *priv, const void *parent_obj, const void *obj); - int (*hints_obj_cmp)(const void *obj1, const void *obj2); void * (*delta_create)(void *priv, void *parent_obj, void *obj); void (*delta_destroy)(void *priv, void *delta_priv); void * (*root_create)(void *priv, void *obj, unsigned int root_id); diff --git a/include/linux/objpool.h b/include/linux/objpool.h index 15aff4a17f0c..cb1758eaa2d3 100644 --- a/include/linux/objpool.h +++ b/include/linux/objpool.h @@ -5,6 +5,10 @@ #include <linux/types.h> #include <linux/refcount.h> +#include <linux/atomic.h> +#include <linux/cpumask.h> +#include <linux/irqflags.h> +#include <linux/smp.h> /* * objpool: ring-array based lockless MPMC queue @@ -69,7 +73,7 @@ typedef int (*objpool_fini_cb)(struct objpool_head *head, void *context); * struct objpool_head - object pooling metadata * @obj_size: object size, aligned to sizeof(void *) * @nr_objs: total objs (to be pre-allocated with objpool) - * @nr_cpus: local copy of nr_cpu_ids + * @nr_possible_cpus: cached value of num_possible_cpus() * @capacity: max objs can be managed by one objpool_slot * @gfp: gfp flags for kmalloc & vmalloc * @ref: refcount of objpool @@ -81,7 +85,7 @@ typedef int (*objpool_fini_cb)(struct objpool_head *head, void *context); struct objpool_head { int obj_size; int nr_objs; - int nr_cpus; + int nr_possible_cpus; int capacity; gfp_t gfp; refcount_t ref; @@ -118,13 +122,94 @@ int objpool_init(struct objpool_head *pool, int nr_objs, int object_size, gfp_t gfp, void *context, objpool_init_obj_cb objinit, objpool_fini_cb release); +/* try to retrieve object from slot */ +static inline void *__objpool_try_get_slot(struct objpool_head *pool, int cpu) +{ + struct objpool_slot *slot = pool->cpu_slots[cpu]; + /* load head snapshot, other cpus may change it */ + uint32_t head = smp_load_acquire(&slot->head); + + while (head != READ_ONCE(slot->last)) { + void *obj; + + /* + * data visibility of 'last' and 'head' could be out of + * order since memory updating of 'last' and 'head' are + * performed in push() and pop() independently + * + * before any retrieving attempts, pop() must guarantee + * 'last' is behind 'head', that is to say, there must + * be available objects in slot, which could be ensured + * by condition 'last != head && last - head <= nr_objs' + * that is equivalent to 'last - head - 1 < nr_objs' as + * 'last' and 'head' are both unsigned int32 + */ + if (READ_ONCE(slot->last) - head - 1 >= pool->nr_objs) { + head = READ_ONCE(slot->head); + continue; + } + + /* obj must be retrieved before moving forward head */ + obj = READ_ONCE(slot->entries[head & slot->mask]); + + /* move head forward to mark it's consumption */ + if (try_cmpxchg_release(&slot->head, &head, head + 1)) + return obj; + } + + return NULL; +} + /** * objpool_pop() - allocate an object from objpool * @pool: object pool * * return value: object ptr or NULL if failed */ -void *objpool_pop(struct objpool_head *pool); +static inline void *objpool_pop(struct objpool_head *pool) +{ + void *obj = NULL; + unsigned long flags; + int i, cpu; + + /* disable local irq to avoid preemption & interruption */ + raw_local_irq_save(flags); + + cpu = raw_smp_processor_id(); + for (i = 0; i < pool->nr_possible_cpus; i++) { + obj = __objpool_try_get_slot(pool, cpu); + if (obj) + break; + cpu = cpumask_next_wrap(cpu, cpu_possible_mask, -1, 1); + } + raw_local_irq_restore(flags); + + return obj; +} + +/* adding object to slot, abort if the slot was already full */ +static inline int +__objpool_try_add_slot(void *obj, struct objpool_head *pool, int cpu) +{ + struct objpool_slot *slot = pool->cpu_slots[cpu]; + uint32_t head, tail; + + /* loading tail and head as a local snapshot, tail first */ + tail = READ_ONCE(slot->tail); + + do { + head = READ_ONCE(slot->head); + /* fault caught: something must be wrong */ + WARN_ON_ONCE(tail - head > pool->nr_objs); + } while (!try_cmpxchg_acquire(&slot->tail, &tail, tail + 1)); + + /* now the tail position is reserved for the given obj */ + WRITE_ONCE(slot->entries[tail & slot->mask], obj); + /* update sequence to make this obj available for pop() */ + smp_store_release(&slot->last, tail + 1); + + return 0; +} /** * objpool_push() - reclaim the object and return back to objpool @@ -134,7 +219,19 @@ void *objpool_pop(struct objpool_head *pool); * return: 0 or error code (it fails only when user tries to push * the same object multiple times or wrong "objects" into objpool) */ -int objpool_push(void *obj, struct objpool_head *pool); +static inline int objpool_push(void *obj, struct objpool_head *pool) +{ + unsigned long flags; + int rc; + + /* disable local irq to avoid preemption & interruption */ + raw_local_irq_save(flags); + rc = __objpool_try_add_slot(obj, pool, raw_smp_processor_id()); + raw_local_irq_restore(flags); + + return rc; +} + /** * objpool_drop() - discard the object and deref objpool diff --git a/include/linux/of.h b/include/linux/of.h index a0bedd038a05..85b60ac9eec5 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -430,11 +430,9 @@ extern int of_detach_node(struct device_node *); #define of_match_ptr(_ptr) (_ptr) /* - * struct property *prop; - * const __be32 *p; * u32 u; * - * of_property_for_each_u32(np, "propname", prop, p, u) + * of_property_for_each_u32(np, "propname", u) * printk("U32 value: %x\n", u); */ const __be32 *of_prop_next_u32(struct property *prop, const __be32 *cur, @@ -1431,11 +1429,12 @@ static inline int of_property_read_s32(const struct device_node *np, err == 0; \ err = of_phandle_iterator_next(it)) -#define of_property_for_each_u32(np, propname, prop, p, u) \ - for (prop = of_find_property(np, propname, NULL), \ - p = of_prop_next_u32(prop, NULL, &u); \ - p; \ - p = of_prop_next_u32(prop, p, &u)) +#define of_property_for_each_u32(np, propname, u) \ + for (struct {struct property *prop; const __be32 *item; } _it = \ + {of_find_property(np, propname, NULL), \ + of_prop_next_u32(_it.prop, NULL, &u)}; \ + _it.item; \ + _it.item = of_prop_next_u32(_it.prop, _it.item, &u)) #define of_property_for_each_string(np, propname, prop, s) \ for (prop = of_find_property(np, propname, NULL), \ @@ -1639,7 +1638,7 @@ int of_changeset_add_prop_string(struct of_changeset *ocs, int of_changeset_add_prop_string_array(struct of_changeset *ocs, struct device_node *np, const char *prop_name, - const char **str_array, size_t sz); + const char * const *str_array, size_t sz); int of_changeset_add_prop_u32_array(struct of_changeset *ocs, struct device_node *np, const char *prop_name, @@ -1652,6 +1651,9 @@ static inline int of_changeset_add_prop_u32(struct of_changeset *ocs, return of_changeset_add_prop_u32_array(ocs, np, prop_name, &val, 1); } +int of_changeset_add_prop_bool(struct of_changeset *ocs, struct device_node *np, + const char *prop_name); + #else /* CONFIG_OF_DYNAMIC */ static inline int of_reconfig_notifier_register(struct notifier_block *nb) { diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h index 4de2a24cadc9..e338282da652 100644 --- a/include/linux/of_reserved_mem.h +++ b/include/linux/of_reserved_mem.h @@ -11,7 +11,6 @@ struct reserved_mem_ops; struct reserved_mem { const char *name; unsigned long fdt_node; - unsigned long phandle; const struct reserved_mem_ops *ops; phys_addr_t base; phys_addr_t size; diff --git a/include/linux/oid_registry.h b/include/linux/oid_registry.h index 51421fdbb0ba..6f9242259edc 100644 --- a/include/linux/oid_registry.h +++ b/include/linux/oid_registry.h @@ -69,6 +69,7 @@ enum OID { OID_certAuthInfoAccess, /* 1.3.6.1.5.5.7.1.1 */ OID_sha1, /* 1.3.14.3.2.26 */ OID_id_ansip384r1, /* 1.3.132.0.34 */ + OID_id_ansip521r1, /* 1.3.132.0.35 */ OID_sha256, /* 2.16.840.1.101.3.4.2.1 */ OID_sha384, /* 2.16.840.1.101.3.4.2.2 */ OID_sha512, /* 2.16.840.1.101.3.4.2.3 */ diff --git a/include/linux/omap-mailbox.h b/include/linux/omap-mailbox.h index 8aa984ec1f38..3cc5c4ed7f5a 100644 --- a/include/linux/omap-mailbox.h +++ b/include/linux/omap-mailbox.h @@ -10,17 +10,4 @@ typedef uintptr_t mbox_msg_t; #define omap_mbox_message(data) (u32)(mbox_msg_t)(data) -typedef int __bitwise omap_mbox_irq_t; -#define IRQ_TX ((__force omap_mbox_irq_t) 1) -#define IRQ_RX ((__force omap_mbox_irq_t) 2) - -struct mbox_chan; -struct mbox_client; - -struct mbox_chan *omap_mbox_request_channel(struct mbox_client *cl, - const char *chan_name); - -void omap_mbox_enable_irq(struct mbox_chan *chan, omap_mbox_irq_t irq); -void omap_mbox_disable_irq(struct mbox_chan *chan, omap_mbox_irq_t irq); - #endif /* OMAP_MAILBOX_H */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 4bf1c25fd1dc..5769fe6e4950 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -30,16 +30,11 @@ * - Pages falling into physical memory gaps - not IORESOURCE_SYSRAM. Trying * to read/write these pages might end badly. Don't touch! * - The zero page(s) - * - Pages not added to the page allocator when onlining a section because - * they were excluded via the online_page_callback() or because they are - * PG_hwpoison. * - Pages allocated in the context of kexec/kdump (loaded kernel image, * control pages, vmcoreinfo) * - MMIO/DMA pages. Some architectures don't allow to ioremap pages that are * not marked PG_reserved (as they might be in use by somebody else who does * not respect the caching strategy). - * - Pages part of an offline section (struct pages of offline sections should - * not be trusted as they will be initialized when first onlined). * - MCA pages on ia64 * - Pages holding CPU notes for POWER Firmware Assisted Dump * - Device memory (e.g. PMEM, DAX, HMM) @@ -109,7 +104,6 @@ enum pageflags { PG_active, PG_workingset, PG_error, - PG_slab, PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/ PG_arch_1, PG_reserved, @@ -513,9 +507,9 @@ static inline int TestClearPage##uname(struct page *page) { return 0; } __PAGEFLAG(Locked, locked, PF_NO_TAIL) FOLIO_FLAG(waiters, FOLIO_HEAD_PAGE) PAGEFLAG(Error, error, PF_NO_TAIL) TESTCLEARFLAG(Error, error, PF_NO_TAIL) -PAGEFLAG(Referenced, referenced, PF_HEAD) - TESTCLEARFLAG(Referenced, referenced, PF_HEAD) - __SETPAGEFLAG(Referenced, referenced, PF_HEAD) +FOLIO_FLAG(referenced, FOLIO_HEAD_PAGE) + FOLIO_TEST_CLEAR_FLAG(referenced, FOLIO_HEAD_PAGE) + __FOLIO_SET_FLAG(referenced, FOLIO_HEAD_PAGE) PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) __CLEARPAGEFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) @@ -524,7 +518,6 @@ PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) TESTCLEARFLAG(Active, active, PF_HEAD) PAGEFLAG(Workingset, workingset, PF_HEAD) TESTCLEARFLAG(Workingset, workingset, PF_HEAD) -__PAGEFLAG(Slab, slab, PF_NO_TAIL) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ /* Xen */ @@ -618,22 +611,24 @@ PAGEFLAG_FALSE(Uncached, uncached) PAGEFLAG(HWPoison, hwpoison, PF_ANY) TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) -#define MAGIC_HWPOISON 0x48575053U /* HWPS */ -extern void SetPageHWPoisonTakenOff(struct page *page); -extern void ClearPageHWPoisonTakenOff(struct page *page); -extern bool take_page_off_buddy(struct page *page); -extern bool put_page_back_buddy(struct page *page); #else PAGEFLAG_FALSE(HWPoison, hwpoison) #define __PG_HWPOISON 0 #endif -#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT) +#ifdef CONFIG_PAGE_IDLE_FLAG +#ifdef CONFIG_64BIT FOLIO_TEST_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_SET_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_TEST_CLEAR_FLAG(young, FOLIO_HEAD_PAGE) FOLIO_FLAG(idle, FOLIO_HEAD_PAGE) #endif +/* See page_idle.h for !64BIT workaround */ +#else /* !CONFIG_PAGE_IDLE_FLAG */ +FOLIO_FLAG_FALSE(young) +FOLIO_TEST_CLEAR_FLAG_FALSE(young) +FOLIO_FLAG_FALSE(idle) +#endif /* * PageReported() is used to track reported free pages within the Buddy @@ -650,27 +645,28 @@ PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted) #endif /* - * On an anonymous page mapped into a user virtual memory area, - * page->mapping points to its anon_vma, not to a struct address_space; + * On an anonymous folio mapped into a user virtual memory area, + * folio->mapping points to its anon_vma, not to a struct address_space; * with the PAGE_MAPPING_ANON bit set to distinguish it. See rmap.h. * * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled, * the PAGE_MAPPING_MOVABLE bit may be set along with the PAGE_MAPPING_ANON - * bit; and then page->mapping points, not to an anon_vma, but to a private + * bit; and then folio->mapping points, not to an anon_vma, but to a private * structure which KSM associates with that merged page. See ksm.h. * * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is used for non-lru movable - * page and then page->mapping points to a struct movable_operations. + * page and then folio->mapping points to a struct movable_operations. * - * Please note that, confusingly, "page_mapping" refers to the inode - * address_space which maps the page from disk; whereas "page_mapped" - * refers to user virtual address space into which the page is mapped. + * Please note that, confusingly, "folio_mapping" refers to the inode + * address_space which maps the folio from disk; whereas "folio_mapped" + * refers to user virtual address space into which the folio is mapped. * * For slab pages, since slab reuses the bits in struct page to store its - * internal states, the page->mapping does not exist as such, nor do these - * flags below. So in order to avoid testing non-existent bits, please - * make sure that PageSlab(page) actually evaluates to false before calling - * the following functions (e.g., PageAnon). See mm/slab.h. + * internal states, the folio->mapping does not exist as such, nor do + * these flags below. So in order to avoid testing non-existent bits, + * please make sure that folio_test_slab(folio) actually evaluates to + * false before calling the following functions (e.g., folio_test_anon). + * See mm/slab.h. */ #define PAGE_MAPPING_ANON 0x1 #define PAGE_MAPPING_MOVABLE 0x2 @@ -688,7 +684,7 @@ static __always_inline bool folio_mapping_flags(const struct folio *folio) return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) != 0; } -static __always_inline int PageMappingFlags(const struct page *page) +static __always_inline bool PageMappingFlags(const struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0; } @@ -709,7 +705,7 @@ static __always_inline bool __folio_test_movable(const struct folio *folio) PAGE_MAPPING_MOVABLE; } -static __always_inline int __PageMovable(const struct page *page) +static __always_inline bool __PageMovable(const struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_MOVABLE; @@ -736,7 +732,7 @@ static __always_inline bool PageKsm(const struct page *page) TESTPAGEFLAG_FALSE(Ksm, ksm) #endif -u64 stable_page_flags(struct page *page); +u64 stable_page_flags(const struct page *page); /** * folio_xor_flags_has_waiters - Change some folio flags. @@ -784,7 +780,7 @@ static inline bool folio_test_uptodate(const struct folio *folio) return ret; } -static inline int PageUptodate(const struct page *page) +static inline bool PageUptodate(const struct page *page) { return folio_test_uptodate(page_folio(page)); } @@ -868,9 +864,9 @@ static inline void ClearPageCompound(struct page *page) BUG_ON(!PageHead(page)); ClearPageHead(page); } -PAGEFLAG(LargeRmappable, large_rmappable, PF_SECOND) +FOLIO_FLAG(large_rmappable, FOLIO_SECOND_PAGE) #else -TESTPAGEFLAG_FALSE(LargeRmappable, large_rmappable) +FOLIO_FLAG_FALSE(large_rmappable) #endif #define PG_head_mask ((1UL << PG_head)) @@ -931,7 +927,7 @@ PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) #endif /* - * For pages that are never mapped to userspace (and aren't PageSlab), + * For pages that are never mapped to userspace, * page_type may be used. Because it is initialised to -1, we invert the * sense of the bit, so __SetPageFoo *clears* the bit used for PageFoo, and * __ClearPageFoo *sets* the bit used for PageFoo. We reserve a few high and @@ -939,19 +935,29 @@ PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) * mistaken for a page type value. */ -#define PAGE_TYPE_BASE 0xf0000000 -/* Reserve 0x0000007f to catch underflows of _mapcount */ -#define PAGE_MAPCOUNT_RESERVE -128 -#define PG_buddy 0x00000080 -#define PG_offline 0x00000100 -#define PG_table 0x00000200 -#define PG_guard 0x00000400 -#define PG_hugetlb 0x00000800 +enum pagetype { + PG_buddy = 0x40000000, + PG_offline = 0x20000000, + PG_table = 0x10000000, + PG_guard = 0x08000000, + PG_hugetlb = 0x04000000, + PG_slab = 0x02000000, + PG_zsmalloc = 0x01000000, + + PAGE_TYPE_BASE = 0x80000000, + + /* + * Reserve 0xffff0000 - 0xfffffffe to catch _mapcount underflows and + * allow owners that set a type to reuse the lower 16 bit for their own + * purposes. + */ + PAGE_MAPCOUNT_RESERVE = ~0x0000ffff, +}; #define PageType(page, flag) \ - ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) + ((READ_ONCE(page->page_type) & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) #define folio_test_type(folio, flag) \ - ((folio->page.page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) + ((READ_ONCE(folio->page.page_type) & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) static inline int page_type_has_type(unsigned int page_type) { @@ -960,7 +966,7 @@ static inline int page_type_has_type(unsigned int page_type) static inline int page_has_type(const struct page *page) { - return page_type_has_type(page->page_type); + return page_type_has_type(READ_ONCE(page->page_type)); } #define FOLIO_TYPE_OPS(lname, fname) \ @@ -1009,15 +1015,22 @@ PAGE_TYPE_OPS(Buddy, buddy, buddy) * The content of these pages is effectively stale. Such pages should not * be touched (read/write/dump/save) except by their owner. * + * When a memory block gets onlined, all pages are initialized with a + * refcount of 1 and PageOffline(). generic_online_page() will + * take care of clearing PageOffline(). + * * If a driver wants to allow to offline unmovable PageOffline() pages without * putting them back to the buddy, it can do so via the memory notifier by * decrementing the reference count in MEM_GOING_OFFLINE and incrementing the * reference count in MEM_CANCEL_OFFLINE. When offlining, the PageOffline() - * pages (now with a reference count of zero) are treated like free pages, - * allowing the containing memory block to get offlined. A driver that + * pages (now with a reference count of zero) are treated like free (unmanaged) + * pages, allowing the containing memory block to get offlined. A driver that * relies on this feature is aware that re-onlining the memory block will - * require to re-set the pages PageOffline() and not giving them to the - * buddy via online_page_callback_t. + * require not giving them to the buddy via generic_online_page(). + * + * Memory offlining code will not adjust the managed page count for any + * PageOffline() pages, treating them like they were never exposed to the + * buddy using generic_online_page(). * * There are drivers that mark a page PageOffline() and expect there won't be * any further access to page content. PFN walkers that read content of random @@ -1041,12 +1054,28 @@ PAGE_TYPE_OPS(Table, table, pgtable) */ PAGE_TYPE_OPS(Guard, guard, guard) +FOLIO_TYPE_OPS(slab, slab) + +/** + * PageSlab - Determine if the page belongs to the slab allocator + * @page: The page to test. + * + * Context: Any context. + * Return: True for slab pages, false for any other kind of page. + */ +static inline bool PageSlab(const struct page *page) +{ + return folio_test_slab(page_folio(page)); +} + #ifdef CONFIG_HUGETLB_PAGE FOLIO_TYPE_OPS(hugetlb, hugetlb) #else FOLIO_TEST_FLAG_FALSE(hugetlb) #endif +PAGE_TYPE_OPS(Zsmalloc, zsmalloc, zsmalloc) + /** * PageHuge - Determine if the page belongs to hugetlbfs * @page: The page to test. @@ -1065,21 +1094,29 @@ static inline bool PageHuge(const struct page *page) * best effort only and inherently racy: there is no way to synchronize with * failing hardware. */ -static inline bool is_page_hwpoison(struct page *page) +static inline bool is_page_hwpoison(const struct page *page) { + const struct folio *folio; + if (PageHWPoison(page)) return true; - return PageHuge(page) && PageHWPoison(compound_head(page)); + folio = page_folio(page); + return folio_test_hugetlb(folio) && PageHWPoison(&folio->page); } -extern bool is_free_buddy_page(struct page *page); +bool is_free_buddy_page(const struct page *page); PAGEFLAG(Isolated, isolated, PF_ANY); static __always_inline int PageAnonExclusive(const struct page *page) { VM_BUG_ON_PGFLAGS(!PageAnon(page), page); - VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page); + /* + * HugeTLB stores this information on the head page; THP keeps it per + * page + */ + if (PageHuge(page)) + page = compound_head(page); return test_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags); } @@ -1118,7 +1155,7 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) (1UL << PG_lru | 1UL << PG_locked | \ 1UL << PG_private | 1UL << PG_private_2 | \ 1UL << PG_writeback | 1UL << PG_reserved | \ - 1UL << PG_slab | 1UL << PG_active | \ + 1UL << PG_active | \ 1UL << PG_unevictable | __PG_MLOCKED | LRU_GEN_MASK) /* diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 4ac34392823a..c16db0067090 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -34,8 +34,9 @@ static inline bool is_migrate_isolate(int migratetype) #define REPORT_FAILURE 0x2 void set_pageblock_migratetype(struct page *page, int migratetype); -int move_freepages_block(struct zone *zone, struct page *page, - int migratetype, int *num_movable); + +bool move_freepages_block_isolate(struct zone *zone, struct page *page, + int migratetype); int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, int migratetype, int flags, gfp_t gfp_flags); diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h index 8cd858d912c4..904c52f97284 100644 --- a/include/linux/page_counter.h +++ b/include/linux/page_counter.h @@ -81,4 +81,8 @@ static inline void page_counter_reset_watermark(struct page_counter *counter) counter->watermark = page_counter_read(counter); } +void page_counter_calculate_protection(struct page_counter *root, + struct page_counter *counter, + bool recursive_protection); + #endif /* _LINUX_PAGE_COUNTER_H */ diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index be98564191e6..e4b48a0dda24 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -4,7 +4,6 @@ #include <linux/types.h> #include <linux/stacktrace.h> -#include <linux/stackdepot.h> struct pglist_data; @@ -78,7 +77,7 @@ static inline void page_ext_init(void) } #endif -extern struct page_ext *page_ext_get(struct page *page); +extern struct page_ext *page_ext_get(const struct page *page); extern void page_ext_put(struct page_ext *page_ext); static inline void *page_ext_data(struct page_ext *page_ext, @@ -118,7 +117,7 @@ static inline void page_ext_init_flatmem(void) { } -static inline struct page_ext *page_ext_get(struct page *page) +static inline struct page_ext *page_ext_get(const struct page *page) { return NULL; } diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h index d8f344840643..89ca0d5dc1e7 100644 --- a/include/linux/page_idle.h +++ b/include/linux/page_idle.h @@ -6,14 +6,12 @@ #include <linux/page-flags.h> #include <linux/page_ext.h> -#ifdef CONFIG_PAGE_IDLE_FLAG - -#ifndef CONFIG_64BIT +#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) /* * If there is not enough space to store Idle and Young bits in page flags, use * page ext flags instead. */ -static inline bool folio_test_young(struct folio *folio) +static inline bool folio_test_young(const struct folio *folio) { struct page_ext *page_ext = page_ext_get(&folio->page); bool page_young; @@ -52,7 +50,7 @@ static inline bool folio_test_clear_young(struct folio *folio) return page_young; } -static inline bool folio_test_idle(struct folio *folio) +static inline bool folio_test_idle(const struct folio *folio) { struct page_ext *page_ext = page_ext_get(&folio->page); bool page_idle; @@ -60,7 +58,7 @@ static inline bool folio_test_idle(struct folio *folio) if (unlikely(!page_ext)) return false; - page_idle = test_bit(PAGE_EXT_IDLE, &page_ext->flags); + page_idle = test_bit(PAGE_EXT_IDLE, &page_ext->flags); page_ext_put(page_ext); return page_idle; @@ -87,61 +85,5 @@ static inline void folio_clear_idle(struct folio *folio) clear_bit(PAGE_EXT_IDLE, &page_ext->flags); page_ext_put(page_ext); } -#endif /* !CONFIG_64BIT */ - -#else /* !CONFIG_PAGE_IDLE_FLAG */ - -static inline bool folio_test_young(struct folio *folio) -{ - return false; -} - -static inline void folio_set_young(struct folio *folio) -{ -} - -static inline bool folio_test_clear_young(struct folio *folio) -{ - return false; -} - -static inline bool folio_test_idle(struct folio *folio) -{ - return false; -} - -static inline void folio_set_idle(struct folio *folio) -{ -} - -static inline void folio_clear_idle(struct folio *folio) -{ -} - -#endif /* CONFIG_PAGE_IDLE_FLAG */ - -static inline bool page_is_young(struct page *page) -{ - return folio_test_young(page_folio(page)); -} - -static inline void set_page_young(struct page *page) -{ - folio_set_young(page_folio(page)); -} - -static inline bool test_and_clear_page_young(struct page *page) -{ - return folio_test_clear_young(page_folio(page)); -} - -static inline bool page_is_idle(struct page *page) -{ - return folio_test_idle(page_folio(page)); -} - -static inline void set_page_idle(struct page *page) -{ - folio_set_idle(page_folio(page)); -} +#endif /* CONFIG_PAGE_IDLE_FLAG && !64BIT */ #endif /* _LINUX_MM_PAGE_IDLE_H */ diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index d7c2d33baa7f..8c236c651d1d 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -139,20 +139,15 @@ static inline void folio_ref_sub(struct folio *folio, int nr) page_ref_sub(&folio->page, nr); } -static inline int page_ref_sub_return(struct page *page, int nr) +static inline int folio_ref_sub_return(struct folio *folio, int nr) { - int ret = atomic_sub_return(nr, &page->_refcount); + int ret = atomic_sub_return(nr, &folio->_refcount); if (page_ref_tracepoint_active(page_ref_mod_and_return)) - __page_ref_mod_and_return(page, -nr, ret); + __page_ref_mod_and_return(&folio->page, -nr, ret); return ret; } -static inline int folio_ref_sub_return(struct folio *folio, int nr) -{ - return page_ref_sub_return(&folio->page, nr); -} - static inline void page_ref_inc(struct page *page) { atomic_inc(&page->_refcount); @@ -235,7 +230,13 @@ static inline int folio_ref_dec_return(struct folio *folio) static inline bool page_ref_add_unless(struct page *page, int nr, int u) { - bool ret = atomic_add_unless(&page->_refcount, nr, u); + bool ret = false; + + rcu_read_lock(); + /* avoid writing to the vmemmap area being remapped */ + if (!page_is_fake_head(page) && page_ref_count(page) != u) + ret = atomic_add_unless(&page->_refcount, nr, u); + rcu_read_unlock(); if (page_ref_tracepoint_active(page_ref_mod_unless)) __page_ref_mod_unless(page, nr, ret); @@ -263,54 +264,9 @@ static inline bool folio_try_get(struct folio *folio) return folio_ref_add_unless(folio, 1, 0); } -static inline bool folio_ref_try_add_rcu(struct folio *folio, int count) -{ -#ifdef CONFIG_TINY_RCU - /* - * The caller guarantees the folio will not be freed from interrupt - * context, so (on !SMP) we only need preemption to be disabled - * and TINY_RCU does that for us. - */ -# ifdef CONFIG_PREEMPT_COUNT - VM_BUG_ON(!in_atomic() && !irqs_disabled()); -# endif - VM_BUG_ON_FOLIO(folio_ref_count(folio) == 0, folio); - folio_ref_add(folio, count); -#else - if (unlikely(!folio_ref_add_unless(folio, count, 0))) { - /* Either the folio has been freed, or will be freed. */ - return false; - } -#endif - return true; -} - -/** - * folio_try_get_rcu - Attempt to increase the refcount on a folio. - * @folio: The folio. - * - * This is a version of folio_try_get() optimised for non-SMP kernels. - * If you are still holding the rcu_read_lock() after looking up the - * page and know that the page cannot have its refcount decreased to - * zero in interrupt context, you can use this instead of folio_try_get(). - * - * Example users include get_user_pages_fast() (as pages are not unmapped - * from interrupt context) and the page cache lookups (as pages are not - * truncated from interrupt context). We also know that pages are not - * frozen in interrupt context for the purposes of splitting or migration. - * - * You can also use this function if you're holding a lock that prevents - * pages being frozen & removed; eg the i_pages lock for the page cache - * or the mmap_lock or page table lock for page tables. In this case, - * it will always succeed, and you could have used a plain folio_get(), - * but it's sometimes more convenient to have a common function called - * from both locked and RCU-protected contexts. - * - * Return: True if the reference count was successfully incremented. - */ -static inline bool folio_try_get_rcu(struct folio *folio) +static inline bool folio_ref_try_add(struct folio *folio, int count) { - return folio_ref_try_add_rcu(folio, 1); + return folio_ref_add_unless(folio, count, 0); } static inline int page_ref_freeze(struct page *page, int count) diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h index 3f2409b968ec..fc6b9c87cb0a 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -28,7 +28,7 @@ enum pageblock_bits { NR_PAGEBLOCK_BITS }; -#ifdef CONFIG_HUGETLB_PAGE +#if defined(CONFIG_HUGETLB_PAGE) #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE @@ -41,11 +41,15 @@ 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_PAGE_ORDER) +#define pageblock_order MIN_T(unsigned int, HUGETLB_PAGE_ORDER, MAX_PAGE_ORDER) #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */ -#else /* CONFIG_HUGETLB_PAGE */ +#elif defined(CONFIG_TRANSPARENT_HUGEPAGE) + +#define pageblock_order MIN_T(unsigned int, HPAGE_PMD_ORDER, MAX_PAGE_ORDER) + +#else /* CONFIG_TRANSPARENT_HUGEPAGE */ /* If huge pages are not used, group by MAX_ORDER_NR_PAGES */ #define pageblock_order MAX_PAGE_ORDER diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 2df35e65557d..d9c7edb6422b 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -40,6 +40,8 @@ int filemap_fdatawait_keep_errors(struct address_space *mapping); int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte); +int filemap_invalidate_inode(struct inode *inode, bool flush, + loff_t start, loff_t end); static inline int filemap_fdatawait(struct address_space *mapping) { @@ -206,7 +208,8 @@ enum mapping_flags { AS_RELEASE_ALWAYS, /* Call ->release_folio(), even if no private data */ AS_STABLE_WRITES, /* must wait for writeback before modifying folio contents */ - AS_UNMOVABLE, /* The mapping cannot be moved, ever */ + AS_INACCESSIBLE, /* Do not attempt direct R/W access to the mapping, + including to move the mapping */ }; /** @@ -307,20 +310,20 @@ static inline void mapping_clear_stable_writes(struct address_space *mapping) clear_bit(AS_STABLE_WRITES, &mapping->flags); } -static inline void mapping_set_unmovable(struct address_space *mapping) +static inline void mapping_set_inaccessible(struct address_space *mapping) { /* - * It's expected unmovable mappings are also unevictable. Compaction + * It's expected inaccessible mappings are also unevictable. Compaction * migrate scanner (isolate_migratepages_block()) relies on this to * reduce page locking. */ set_bit(AS_UNEVICTABLE, &mapping->flags); - set_bit(AS_UNMOVABLE, &mapping->flags); + set_bit(AS_INACCESSIBLE, &mapping->flags); } -static inline bool mapping_unmovable(struct address_space *mapping) +static inline bool mapping_inaccessible(struct address_space *mapping) { - return test_bit(AS_UNMOVABLE, &mapping->flags); + return test_bit(AS_INACCESSIBLE, &mapping->flags); } static inline gfp_t mapping_gfp_mask(struct address_space * mapping) @@ -344,6 +347,26 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) m->gfp_mask = mask; } +/* + * There are some parts of the kernel which assume that PMD entries + * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then, + * limit the maximum allocation order to PMD size. I'm not aware of any + * assumptions about maximum order if THP are disabled, but 8 seems like + * a good order (that's 1MB if you're using 4kB pages) + */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define PREFERRED_MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER +#else +#define PREFERRED_MAX_PAGECACHE_ORDER 8 +#endif + +/* + * xas_split_alloc() does not support arbitrary orders. This implies no + * 512MB THP on ARM64 with 64KB base page size. + */ +#define MAX_XAS_ORDER (XA_CHUNK_SHIFT * 2 - 1) +#define MAX_PAGECACHE_ORDER min(MAX_XAS_ORDER, PREFERRED_MAX_PAGECACHE_ORDER) + /** * mapping_set_large_folios() - Indicate the file supports large folios. * @mapping: The file. @@ -366,10 +389,22 @@ static inline void mapping_set_large_folios(struct address_space *mapping) */ static inline bool mapping_large_folio_support(struct address_space *mapping) { + /* AS_LARGE_FOLIO_SUPPORT is only reasonable for pagecache folios */ + VM_WARN_ONCE((unsigned long)mapping & PAGE_MAPPING_ANON, + "Anonymous mapping always supports large folio"); + return IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } +/* Return the maximum folio size for this pagecache mapping, in bytes. */ +static inline size_t mapping_max_folio_size(struct address_space *mapping) +{ + if (mapping_large_folio_support(mapping)) + return PAGE_SIZE << MAX_PAGECACHE_ORDER; + return PAGE_SIZE; +} + static inline int filemap_nr_thps(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS @@ -399,7 +434,6 @@ static inline void filemap_nr_thps_dec(struct address_space *mapping) #endif } -struct address_space *page_mapping(struct page *); struct address_space *folio_mapping(struct folio *); struct address_space *swapcache_mapping(struct folio *); @@ -528,38 +562,23 @@ static inline void *detach_page_private(struct page *page) return folio_detach_private(page_folio(page)); } -/* - * There are some parts of the kernel which assume that PMD entries - * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then, - * limit the maximum allocation order to PMD size. I'm not aware of any - * assumptions about maximum order if THP are disabled, but 8 seems like - * a good order (that's 1MB if you're using 4kB pages) - */ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER -#else -#define MAX_PAGECACHE_ORDER 8 -#endif - #ifdef CONFIG_NUMA -struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order); +struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order); #else -static inline struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order) +static inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order) { - return folio_alloc(gfp, order); + return folio_alloc_noprof(gfp, order); } #endif +#define filemap_alloc_folio(...) \ + alloc_hooks(filemap_alloc_folio_noprof(__VA_ARGS__)) + static inline struct page *__page_cache_alloc(gfp_t gfp) { return &filemap_alloc_folio(gfp, 0)->page; } -static inline struct page *page_cache_alloc(struct address_space *x) -{ - return __page_cache_alloc(mapping_gfp_mask(x)); -} - static inline gfp_t readahead_gfp_mask(struct address_space *x) { return mapping_gfp_mask(x) | __GFP_NORETRY | __GFP_NOWARN; @@ -780,7 +799,7 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, mapping_gfp_mask(mapping)); } -#define swapcache_index(folio) __page_file_index(&(folio)->page) +extern pgoff_t __folio_swap_cache_index(struct folio *folio); /** * folio_index - File index of a folio. @@ -795,9 +814,9 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, */ static inline pgoff_t folio_index(struct folio *folio) { - if (unlikely(folio_test_swapcache(folio))) - return swapcache_index(folio); - return folio->index; + if (unlikely(folio_test_swapcache(folio))) + return __folio_swap_cache_index(folio); + return folio->index; } /** @@ -920,11 +939,6 @@ static inline loff_t page_offset(struct page *page) return ((loff_t)page->index) << PAGE_SHIFT; } -static inline loff_t page_file_offset(struct page *page) -{ - return ((loff_t)page_index(page)) << PAGE_SHIFT; -} - /** * folio_pos - Returns the byte position of this folio in its file. * @folio: The folio. @@ -934,18 +948,6 @@ static inline loff_t folio_pos(struct folio *folio) return page_offset(&folio->page); } -/** - * folio_file_pos - Returns the byte position of this folio in its file. - * @folio: The folio. - * - * This differs from folio_pos() for folios which belong to a swap file. - * NFS is the only filesystem today which needs to use folio_file_pos(). - */ -static inline loff_t folio_file_pos(struct folio *folio) -{ - return page_file_offset(&folio->page); -} - /* * Get the offset in PAGE_SIZE (even for hugetlb folios). */ @@ -1014,7 +1016,7 @@ static inline bool folio_trylock(struct folio *folio) /* * Return true if the page was successfully locked */ -static inline int trylock_page(struct page *page) +static inline bool trylock_page(struct page *page) { return folio_trylock(page_folio(page)); } @@ -1144,11 +1146,6 @@ void folio_end_writeback(struct folio *folio); void wait_for_stable_page(struct page *page); void folio_wait_stable(struct folio *folio); void __folio_mark_dirty(struct folio *folio, struct address_space *, int warn); -static inline void __set_page_dirty(struct page *page, - struct address_space *mapping, int warn) -{ - __folio_mark_dirty(page_folio(page), mapping, warn); -} void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb); void __folio_cancel_dirty(struct folio *folio); static inline void folio_cancel_dirty(struct folio *folio) @@ -1160,7 +1157,6 @@ static inline void folio_cancel_dirty(struct folio *folio) bool folio_clear_dirty_for_io(struct folio *folio); bool clear_page_dirty_for_io(struct page *page); void folio_invalidate(struct folio *folio, size_t offset, size_t length); -int __set_page_dirty_nobuffers(struct page *page); bool noop_dirty_folio(struct address_space *mapping, struct folio *folio); #ifdef CONFIG_MIGRATION @@ -1305,8 +1301,7 @@ void page_cache_sync_readahead(struct address_space *mapping, * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @file: Used by the filesystem for authentication. - * @folio: The folio at @index which triggered the readahead call. - * @index: Index of first page to be read. + * @folio: The folio which triggered the readahead call. * @req_count: Total number of pages being read by the caller. * * page_cache_async_readahead() should be called when a page is used which @@ -1317,9 +1312,9 @@ void page_cache_sync_readahead(struct address_space *mapping, static inline void page_cache_async_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, - struct folio *folio, pgoff_t index, unsigned long req_count) + struct folio *folio, unsigned long req_count) { - DEFINE_READAHEAD(ractl, file, ra, mapping, index); + DEFINE_READAHEAD(ractl, file, ra, mapping, folio->index); page_cache_async_ra(&ractl, folio, req_count); } @@ -1542,10 +1537,4 @@ unsigned int i_blocks_per_folio(struct inode *inode, struct folio *folio) { return folio_size(folio) >> inode->i_blkbits; } - -static inline -unsigned int i_blocks_per_page(struct inode *inode, struct page *page) -{ - return i_blocks_per_folio(inode, page_folio(page)); -} #endif /* _LINUX_PAGEMAP_H */ diff --git a/include/linux/panic.h b/include/linux/panic.h index 6717b15e798c..3130e0b5116b 100644 --- a/include/linux/panic.h +++ b/include/linux/panic.h @@ -77,9 +77,10 @@ static inline void set_arch_panic_timeout(int timeout, int arch_default_timeout) #define TAINT_FLAGS_MAX ((1UL << TAINT_FLAGS_COUNT) - 1) struct taint_flag { - char c_true; /* character printed when tainted */ - char c_false; /* character printed when not tainted */ - bool module; /* also show as a per-module taint flag */ + char c_true; /* character printed when tainted */ + char c_false; /* character printed when not tainted */ + bool module; /* also show as a per-module taint flag */ + const char *desc; /* verbose description of the set taint flag */ }; extern const struct taint_flag taint_flags[TAINT_FLAGS_COUNT]; @@ -90,6 +91,7 @@ enum lockdep_ok { }; extern const char *print_tainted(void); +extern const char *print_tainted_verbose(void); extern void add_taint(unsigned flag, enum lockdep_ok); extern int test_taint(unsigned flag); extern unsigned long get_taint(void); diff --git a/include/linux/papr_scm.h b/include/linux/papr_scm.h new file mode 100644 index 000000000000..eb36453813db --- /dev/null +++ b/include/linux/papr_scm.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __LINUX_PAPR_SCM_H +#define __LINUX_PAPR_SCM_H + +/* DIMM health bitmap indicators */ +/* SCM device is unable to persist memory contents */ +#define PAPR_PMEM_UNARMED (1ULL << (63 - 0)) +/* SCM device failed to persist memory contents */ +#define PAPR_PMEM_SHUTDOWN_DIRTY (1ULL << (63 - 1)) +/* SCM device contents are persisted from previous IPL */ +#define PAPR_PMEM_SHUTDOWN_CLEAN (1ULL << (63 - 2)) +/* SCM device contents are not persisted from previous IPL */ +#define PAPR_PMEM_EMPTY (1ULL << (63 - 3)) +/* SCM device memory life remaining is critically low */ +#define PAPR_PMEM_HEALTH_CRITICAL (1ULL << (63 - 4)) +/* SCM device will be garded off next IPL due to failure */ +#define PAPR_PMEM_HEALTH_FATAL (1ULL << (63 - 5)) +/* SCM contents cannot persist due to current platform health status */ +#define PAPR_PMEM_HEALTH_UNHEALTHY (1ULL << (63 - 6)) +/* SCM device is unable to persist memory contents in certain conditions */ +#define PAPR_PMEM_HEALTH_NON_CRITICAL (1ULL << (63 - 7)) +/* SCM device is encrypted */ +#define PAPR_PMEM_ENCRYPTED (1ULL << (63 - 8)) +/* SCM device has been scrubbed and locked */ +#define PAPR_PMEM_SCRUBBED_AND_LOCKED (1ULL << (63 - 9)) + +#define PAPR_PMEM_SAVE_FAILED (1ULL << (63 - 10)) + +/* Bits status indicators for health bitmap indicating unarmed dimm */ +#define PAPR_PMEM_UNARMED_MASK (PAPR_PMEM_UNARMED | \ + PAPR_PMEM_HEALTH_UNHEALTHY) + +/* Bits status indicators for health bitmap indicating unflushed dimm */ +#define PAPR_PMEM_BAD_SHUTDOWN_MASK (PAPR_PMEM_SHUTDOWN_DIRTY) + +/* Bits status indicators for health bitmap indicating unrestored dimm */ +#define PAPR_PMEM_BAD_RESTORE_MASK (PAPR_PMEM_EMPTY) + +/* Bit status indicators for smart event notification */ +#define PAPR_PMEM_SMART_EVENT_MASK (PAPR_PMEM_HEALTH_CRITICAL | \ + PAPR_PMEM_HEALTH_FATAL | \ + PAPR_PMEM_HEALTH_UNHEALTHY) + +#define PAPR_PMEM_SAVE_MASK (PAPR_PMEM_SAVE_FAILED) + +#define PAPR_SCM_PERF_STATS_EYECATCHER __stringify(SCMSTATS) +#define PAPR_SCM_PERF_STATS_VERSION 0x1 + +#endif /* __LINUX_PAPR_SCM_H */ diff --git a/include/linux/parport.h b/include/linux/parport.h index fff39bc30629..464c2ad28039 100644 --- a/include/linux/parport.h +++ b/include/linux/parport.h @@ -252,13 +252,10 @@ struct parport { struct parport_driver { const char *name; - void (*attach) (struct parport *); void (*detach) (struct parport *); void (*match_port)(struct parport *); int (*probe)(struct pardevice *); struct device_driver driver; - bool devmodel; - struct list_head list; }; #define to_parport_driver(n) container_of(n, struct parport_driver, driver) @@ -301,9 +298,6 @@ int __must_check __parport_register_driver(struct parport_driver *, * to receive notifications about ports being found in the * system, as well as ports no longer available. * - * If devmodel is true then the new device model is used - * for registration. - * * The @driver structure is allocated by the caller and must not be * deallocated until after calling parport_unregister_driver(). * diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index abeba356bc3f..ac8c44dd8237 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -59,7 +59,7 @@ static inline void part_stat_set_all(struct block_device *part, int value) #define part_stat_add(part, field, addnd) do { \ __part_stat_add((part), field, addnd); \ - if ((part)->bd_partno) \ + if (bdev_is_partition(part)) \ __part_stat_add(bdev_whole(part), field, addnd); \ } while (0) diff --git a/include/linux/path.h b/include/linux/path.h index 475225a03d0d..ca073e70decd 100644 --- a/include/linux/path.h +++ b/include/linux/path.h @@ -24,4 +24,13 @@ static inline void path_put_init(struct path *path) *path = (struct path) { }; } +/* + * Cleanup macro for use with __free(path_put). Avoids dereference and + * copying @path unlike DEFINE_FREE(). path_put() will handle the empty + * path correctly just ensure @path is initialized: + * + * struct path path __free(path_put) = {}; + */ +#define __free_path_put path_put + #endif /* _LINUX_PATH_H */ diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h index cc2f70d061c8..85bdf2adb760 100644 --- a/include/linux/pci-epc.h +++ b/include/linux/pci-epc.h @@ -128,6 +128,8 @@ struct pci_epc_mem { * @group: configfs group representing the PCI EPC device * @lock: mutex to protect pci_epc ops * @function_num_map: bitmap to manage physical function number + * @init_complete: flag to indicate whether the EPC initialization is complete + * or not */ struct pci_epc { struct device dev; @@ -143,6 +145,7 @@ struct pci_epc { /* mutex to protect against concurrent access of EP controller */ struct mutex lock; unsigned long function_num_map; + bool init_complete; }; /** @@ -179,8 +182,6 @@ struct pci_epc_bar_desc { /** * struct pci_epc_features - features supported by a EPC device per function * @linkup_notifier: indicate if the EPC device can notify EPF driver on link up - * @core_init_notifier: indicate cores that can notify about their availability - * for initialization * @msi_capable: indicate if the endpoint function has MSI capability * @msix_capable: indicate if the endpoint function has MSI-X capability * @bar: array specifying the hardware description for each BAR @@ -188,7 +189,6 @@ struct pci_epc_bar_desc { */ struct pci_epc_features { unsigned int linkup_notifier : 1; - unsigned int core_init_notifier : 1; unsigned int msi_capable : 1; unsigned int msix_capable : 1; struct pci_epc_bar_desc bar[PCI_STD_NUM_BARS]; @@ -197,6 +197,8 @@ struct pci_epc_features { #define to_pci_epc(device) container_of((device), struct pci_epc, dev) +#ifdef CONFIG_PCI_ENDPOINT + #define pci_epc_create(dev, ops) \ __pci_epc_create((dev), (ops), THIS_MODULE) #define devm_pci_epc_create(dev, ops) \ @@ -225,7 +227,9 @@ int pci_epc_add_epf(struct pci_epc *epc, struct pci_epf *epf, void pci_epc_linkup(struct pci_epc *epc); void pci_epc_linkdown(struct pci_epc *epc); void pci_epc_init_notify(struct pci_epc *epc); -void pci_epc_bme_notify(struct pci_epc *epc); +void pci_epc_notify_pending_init(struct pci_epc *epc, struct pci_epf *epf); +void pci_epc_deinit_notify(struct pci_epc *epc); +void pci_epc_bus_master_enable_notify(struct pci_epc *epc); void pci_epc_remove_epf(struct pci_epc *epc, struct pci_epf *epf, enum pci_epc_interface_type type); int pci_epc_write_header(struct pci_epc *epc, u8 func_no, u8 vfunc_no, @@ -271,4 +275,14 @@ void __iomem *pci_epc_mem_alloc_addr(struct pci_epc *epc, phys_addr_t *phys_addr, size_t size); void pci_epc_mem_free_addr(struct pci_epc *epc, phys_addr_t phys_addr, void __iomem *virt_addr, size_t size); + +#else +static inline void pci_epc_init_notify(struct pci_epc *epc) +{ +} + +static inline void pci_epc_deinit_notify(struct pci_epc *epc) +{ +} +#endif /* CONFIG_PCI_ENDPOINT */ #endif /* __LINUX_PCI_EPC_H */ diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h index adee6a1b35db..18a3aeb62ae4 100644 --- a/include/linux/pci-epf.h +++ b/include/linux/pci-epf.h @@ -70,16 +70,18 @@ struct pci_epf_ops { /** * struct pci_epc_event_ops - Callbacks for capturing the EPC events - * @core_init: Callback for the EPC initialization complete event + * @epc_init: Callback for the EPC initialization complete event + * @epc_deinit: Callback for the EPC deinitialization event * @link_up: Callback for the EPC link up event * @link_down: Callback for the EPC link down event - * @bme: Callback for the EPC BME (Bus Master Enable) event + * @bus_master_enable: Callback for the EPC Bus Master Enable event */ struct pci_epc_event_ops { - int (*core_init)(struct pci_epf *epf); + int (*epc_init)(struct pci_epf *epf); + void (*epc_deinit)(struct pci_epf *epf); int (*link_up)(struct pci_epf *epf); int (*link_down)(struct pci_epf *epf); - int (*bme)(struct pci_epf *epf); + int (*bus_master_enable)(struct pci_epf *epf); }; /** @@ -105,8 +107,7 @@ struct pci_epf_driver { const struct pci_epf_device_id *id_table; }; -#define to_pci_epf_driver(drv) (container_of((drv), struct pci_epf_driver, \ - driver)) +#define to_pci_epf_driver(drv) container_of_const((drv), struct pci_epf_driver, driver) /** * struct pci_epf_bar - represents the BAR of EPF device diff --git a/include/linux/pci-pwrctl.h b/include/linux/pci-pwrctl.h new file mode 100644 index 000000000000..45e9cfe740e4 --- /dev/null +++ b/include/linux/pci-pwrctl.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2024 Linaro Ltd. + */ + +#ifndef __PCI_PWRCTL_H__ +#define __PCI_PWRCTL_H__ + +#include <linux/notifier.h> + +struct device; +struct device_link; + +/* + * This is a simple framework for solving the issue of PCI devices that require + * certain resources (regulators, GPIOs, clocks) to be enabled before the + * device can actually be detected on the PCI bus. + * + * The idea is to reuse the platform bus to populate OF nodes describing the + * PCI device and its resources, let these platform devices probe and enable + * relevant resources and then trigger a rescan of the PCI bus allowing for the + * same device (with a second associated struct device) to be registered with + * the PCI subsystem. + * + * To preserve a correct hierarchy for PCI power management and device reset, + * we create a device link between the power control platform device (parent) + * and the supplied PCI device (child). + */ + +/** + * struct pci_pwrctl - PCI device power control context. + * @dev: Address of the power controlling device. + * + * An object of this type must be allocated by the PCI power control device and + * passed to the pwrctl subsystem to trigger a bus rescan and setup a device + * link with the device once it's up. + */ +struct pci_pwrctl { + struct device *dev; + + /* Private: don't use. */ + struct notifier_block nb; + struct device_link *link; +}; + +int pci_pwrctl_device_set_ready(struct pci_pwrctl *pwrctl); +void pci_pwrctl_device_unset_ready(struct pci_pwrctl *pwrctl); +int devm_pci_pwrctl_device_set_ready(struct device *dev, + struct pci_pwrctl *pwrctl); + +#endif /* __PCI_PWRCTL_H__ */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 16493426a04f..4cf89a4b4cbc 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -51,7 +51,7 @@ PCI_STATUS_PARITY) /* Number of reset methods used in pci_reset_fn_methods array in pci.c */ -#define PCI_NUM_RESET_METHODS 7 +#define PCI_NUM_RESET_METHODS 8 #define PCI_RESET_PROBE true #define PCI_RESET_DO_RESET false @@ -367,10 +367,11 @@ struct pci_dev { this is D0-D3, D0 being fully functional, and D3 being off. */ u8 pm_cap; /* PM capability offset */ - unsigned int imm_ready:1; /* Supports Immediate Readiness */ unsigned int pme_support:5; /* Bitmask of states from which PME# can be generated */ unsigned int pme_poll:1; /* Poll device's PME status bit */ + unsigned int pinned:1; /* Whether this dev is pinned */ + unsigned int imm_ready:1; /* Supports Immediate Readiness */ unsigned int d1_support:1; /* Low power state D1 is supported */ unsigned int d2_support:1; /* Low power state D2 is supported */ unsigned int no_d1d2:1; /* D1 and D2 are forbidden */ @@ -958,10 +959,8 @@ struct pci_driver { bool driver_managed_dma; }; -static inline struct pci_driver *to_pci_driver(struct device_driver *drv) -{ - return drv ? container_of(drv, struct pci_driver, driver) : NULL; -} +#define to_pci_driver(__drv) \ + ( __drv ? container_of_const(__drv, struct pci_driver, driver) : NULL ) /** * PCI_DEVICE - macro used to describe a specific PCI device @@ -1077,8 +1076,6 @@ enum { #define PCI_IRQ_MSIX (1 << 2) /* Allow MSI-X interrupts */ #define PCI_IRQ_AFFINITY (1 << 3) /* Auto-assign affinity */ -#define PCI_IRQ_LEGACY PCI_IRQ_INTX /* Deprecated! Use PCI_IRQ_INTX */ - /* These external functions are only available when PCI support is enabled */ #ifdef CONFIG_PCI @@ -1315,7 +1312,6 @@ int pci_user_write_config_word(struct pci_dev *dev, int where, u16 val); int pci_user_write_config_dword(struct pci_dev *dev, int where, u32 val); int __must_check pci_enable_device(struct pci_dev *dev); -int __must_check pci_enable_device_io(struct pci_dev *dev); int __must_check pci_enable_device_mem(struct pci_dev *dev); int __must_check pci_reenable_device(struct pci_dev *); int __must_check pcim_enable_device(struct pci_dev *pdev); @@ -1552,10 +1548,7 @@ int __must_check pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res, resource_size_t size, resource_size_t align, resource_size_t min, unsigned long type_mask, - resource_size_t (*alignf)(void *, - const struct resource *, - resource_size_t, - resource_size_t), + resource_alignf alignf, void *alignf_data); @@ -1648,8 +1641,7 @@ int pci_set_vga_state(struct pci_dev *pdev, bool decode, */ #define PCI_IRQ_VIRTUAL (1 << 4) -#define PCI_IRQ_ALL_TYPES \ - (PCI_IRQ_LEGACY | PCI_IRQ_MSI | PCI_IRQ_MSIX) +#define PCI_IRQ_ALL_TYPES (PCI_IRQ_INTX | PCI_IRQ_MSI | PCI_IRQ_MSIX) #include <linux/dmapool.h> @@ -1658,8 +1650,6 @@ struct msix_entry { u16 entry; /* Driver uses to specify entry, OS writes */ }; -struct msi_domain_template; - #ifdef CONFIG_PCI_MSI int pci_msi_vec_count(struct pci_dev *dev); void pci_disable_msi(struct pci_dev *dev); @@ -1692,11 +1682,6 @@ void pci_msix_free_irq(struct pci_dev *pdev, struct msi_map map); void pci_free_irq_vectors(struct pci_dev *dev); int pci_irq_vector(struct pci_dev *dev, unsigned int nr); const struct cpumask *pci_irq_get_affinity(struct pci_dev *pdev, int vec); -bool pci_create_ims_domain(struct pci_dev *pdev, const struct msi_domain_template *template, - unsigned int hwsize, void *data); -struct msi_map pci_ims_alloc_irq(struct pci_dev *pdev, union msi_instance_cookie *icookie, - const struct irq_affinity_desc *affdesc); -void pci_ims_free_irq(struct pci_dev *pdev, struct msi_map map); #else static inline int pci_msi_vec_count(struct pci_dev *dev) { return -ENOSYS; } @@ -1719,7 +1704,7 @@ pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, unsigned int max_vecs, unsigned int flags, struct irq_affinity *aff_desc) { - if ((flags & PCI_IRQ_LEGACY) && min_vecs == 1 && dev->irq) + if ((flags & PCI_IRQ_INTX) && min_vecs == 1 && dev->irq) return 1; return -ENOSPC; } @@ -1760,25 +1745,6 @@ static inline const struct cpumask *pci_irq_get_affinity(struct pci_dev *pdev, { return cpu_possible_mask; } - -static inline bool pci_create_ims_domain(struct pci_dev *pdev, - const struct msi_domain_template *template, - unsigned int hwsize, void *data) -{ return false; } - -static inline struct msi_map pci_ims_alloc_irq(struct pci_dev *pdev, - union msi_instance_cookie *icookie, - const struct irq_affinity_desc *affdesc) -{ - struct msi_map map = { .index = -ENOSYS, }; - - return map; -} - -static inline void pci_ims_free_irq(struct pci_dev *pdev, struct msi_map map) -{ -} - #endif /** @@ -1821,17 +1787,21 @@ extern bool pcie_ports_native; #define pcie_ports_native false #endif -#define PCIE_LINK_STATE_L0S BIT(0) -#define PCIE_LINK_STATE_L1 BIT(1) -#define PCIE_LINK_STATE_CLKPM BIT(2) -#define PCIE_LINK_STATE_L1_1 BIT(3) -#define PCIE_LINK_STATE_L1_2 BIT(4) -#define PCIE_LINK_STATE_L1_1_PCIPM BIT(5) -#define PCIE_LINK_STATE_L1_2_PCIPM BIT(6) -#define PCIE_LINK_STATE_ALL (PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1 |\ - PCIE_LINK_STATE_CLKPM | PCIE_LINK_STATE_L1_1 |\ - PCIE_LINK_STATE_L1_2 | PCIE_LINK_STATE_L1_1_PCIPM |\ +#define PCIE_LINK_STATE_L0S (BIT(0) | BIT(1)) /* Upstr/dwnstr L0s */ +#define PCIE_LINK_STATE_L1 BIT(2) /* L1 state */ +#define PCIE_LINK_STATE_L1_1 BIT(3) /* ASPM L1.1 state */ +#define PCIE_LINK_STATE_L1_2 BIT(4) /* ASPM L1.2 state */ +#define PCIE_LINK_STATE_L1_1_PCIPM BIT(5) /* PCI-PM L1.1 state */ +#define PCIE_LINK_STATE_L1_2_PCIPM BIT(6) /* PCI-PM L1.2 state */ +#define PCIE_LINK_STATE_ASPM_ALL (PCIE_LINK_STATE_L0S |\ + PCIE_LINK_STATE_L1 |\ + PCIE_LINK_STATE_L1_1 |\ + PCIE_LINK_STATE_L1_2 |\ + PCIE_LINK_STATE_L1_1_PCIPM |\ PCIE_LINK_STATE_L1_2_PCIPM) +#define PCIE_LINK_STATE_CLKPM BIT(7) +#define PCIE_LINK_STATE_ALL (PCIE_LINK_STATE_ASPM_ALL |\ + PCIE_LINK_STATE_CLKPM) #ifdef CONFIG_PCIEASPM int pci_disable_link_state(struct pci_dev *pdev, int state); @@ -2014,10 +1984,9 @@ static inline int pci_register_driver(struct pci_driver *drv) static inline void pci_unregister_driver(struct pci_driver *drv) { } static inline u8 pci_find_capability(struct pci_dev *dev, int cap) { return 0; } -static inline int pci_find_next_capability(struct pci_dev *dev, u8 post, - int cap) +static inline u8 pci_find_next_capability(struct pci_dev *dev, u8 post, int cap) { return 0; } -static inline int pci_find_ext_capability(struct pci_dev *dev, int cap) +static inline u16 pci_find_ext_capability(struct pci_dev *dev, int cap) { return 0; } static inline u64 pci_get_dsn(struct pci_dev *dev) @@ -2327,6 +2296,8 @@ int pcim_iomap_regions(struct pci_dev *pdev, int mask, const char *name); int pcim_iomap_regions_request_all(struct pci_dev *pdev, int mask, const char *name); void pcim_iounmap_regions(struct pci_dev *pdev, int mask); +void __iomem *pcim_iomap_range(struct pci_dev *pdev, int bar, + unsigned long offset, unsigned long len); extern int pci_pci_problems; #define PCIPCI_FAIL 1 /* No PCI PCI DMA */ @@ -2519,7 +2490,12 @@ static inline struct pci_dev *pcie_find_root_port(struct pci_dev *dev) static inline bool pci_dev_is_disconnected(const struct pci_dev *dev) { - return dev->error_state == pci_channel_io_perm_failure; + /* + * error_state is set in pci_dev_set_io_state() using xchg/cmpxchg() + * and read w/o common lock. READ_ONCE() ensures compiler cannot cache + * the value (e.g. inside the loop in pci_dev_wait()). + */ + return READ_ONCE(dev->error_state) == pci_channel_io_perm_failure; } void pci_request_acs(void); diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index a0c75e467df3..e388c8b1cbc2 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -580,6 +580,7 @@ #define PCI_DEVICE_ID_AMD_19H_M78H_DF_F3 0x12fb #define PCI_DEVICE_ID_AMD_1AH_M00H_DF_F3 0x12c3 #define PCI_DEVICE_ID_AMD_1AH_M20H_DF_F3 0x16fb +#define PCI_DEVICE_ID_AMD_1AH_M70H_DF_F3 0x12bb #define PCI_DEVICE_ID_AMD_MI200_DF_F3 0x14d3 #define PCI_DEVICE_ID_AMD_MI300_DF_F3 0x152b #define PCI_DEVICE_ID_AMD_VANGOGH_USB 0x163a @@ -2125,6 +2126,8 @@ #define PCI_VENDOR_ID_CHELSIO 0x1425 +#define PCI_VENDOR_ID_EDIMAX 0x1432 + #define PCI_VENDOR_ID_ADLINK 0x144a #define PCI_VENDOR_ID_SAMSUNG 0x144d @@ -2598,6 +2601,8 @@ #define PCI_VENDOR_ID_HYGON 0x1d94 +#define PCI_VENDOR_ID_META 0x1d9b + #define PCI_VENDOR_ID_FUNGIBLE 0x1dad #define PCI_VENDOR_ID_HXT 0x1dbf @@ -2607,6 +2612,8 @@ #define PCI_VENDOR_ID_ALIBABA 0x1ded +#define PCI_VENDOR_ID_CXL 0x1e98 + #define PCI_VENDOR_ID_TEHUTI 0x1fc9 #define PCI_DEVICE_ID_TEHUTI_3009 0x3009 #define PCI_DEVICE_ID_TEHUTI_3010 0x3010 @@ -2686,8 +2693,10 @@ #define PCI_DEVICE_ID_INTEL_I960 0x0960 #define PCI_DEVICE_ID_INTEL_I960RM 0x0962 #define PCI_DEVICE_ID_INTEL_HDA_HSW_0 0x0a0c +#define PCI_DEVICE_ID_INTEL_DSA_SPR0 0x0b25 #define PCI_DEVICE_ID_INTEL_HDA_HSW_2 0x0c0c #define PCI_DEVICE_ID_INTEL_CENTERTON_ILB 0x0c60 +#define PCI_DEVICE_ID_INTEL_IAX_SPR0 0x0cfe #define PCI_DEVICE_ID_INTEL_HDA_HSW_3 0x0d0c #define PCI_DEVICE_ID_INTEL_HDA_BYT 0x0f04 #define PCI_DEVICE_ID_INTEL_SST_BYT 0x0f28 @@ -3106,6 +3115,8 @@ #define PCI_DEVICE_ID_INTEL_HDA_CML_S 0xa3f0 #define PCI_DEVICE_ID_INTEL_HDA_LNL_P 0xa828 #define PCI_DEVICE_ID_INTEL_S21152BB 0xb152 +#define PCI_DEVICE_ID_INTEL_HDA_BMG 0xe2f7 +#define PCI_DEVICE_ID_INTEL_HDA_PTL 0xe428 #define PCI_DEVICE_ID_INTEL_HDA_CML_R 0xf0c8 #define PCI_DEVICE_ID_INTEL_HDA_RKL_S 0xf1c8 diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index da3a6c30f6d2..b4a4eb6c8866 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -7,11 +7,12 @@ #ifndef __LINUX_PCS_XPCS_H #define __LINUX_PCS_XPCS_H +#include <linux/clk.h> +#include <linux/fwnode.h> +#include <linux/mdio.h> #include <linux/phy.h> #include <linux/phylink.h> - -#define NXP_SJA1105_XPCS_ID 0x00000010 -#define NXP_SJA1110_XPCS_ID 0x00000020 +#include <linux/types.h> /* AN mode */ #define DW_AN_C73 1 @@ -20,20 +21,46 @@ #define DW_AN_C37_1000BASEX 4 #define DW_10GBASER 5 -/* device vendor OUI */ -#define DW_OUI_WX 0x0018fc80 +struct dw_xpcs_desc; + +enum dw_xpcs_pcs_id { + DW_XPCS_ID_NATIVE = 0, + NXP_SJA1105_XPCS_ID = 0x00000010, + NXP_SJA1110_XPCS_ID = 0x00000020, + DW_XPCS_ID = 0x7996ced0, + DW_XPCS_ID_MASK = 0xffffffff, +}; -/* dev_flag */ -#define DW_DEV_TXGBE BIT(0) +enum dw_xpcs_pma_id { + DW_XPCS_PMA_ID_NATIVE = 0, + DW_XPCS_PMA_GEN1_3G_ID, + DW_XPCS_PMA_GEN2_3G_ID, + DW_XPCS_PMA_GEN2_6G_ID, + DW_XPCS_PMA_GEN4_3G_ID, + DW_XPCS_PMA_GEN4_6G_ID, + DW_XPCS_PMA_GEN5_10G_ID, + DW_XPCS_PMA_GEN5_12G_ID, + WX_TXGBE_XPCS_PMA_10G_ID = 0x0018fc80, +}; -struct xpcs_id; +struct dw_xpcs_info { + u32 pcs; + u32 pma; +}; + +enum dw_xpcs_clock { + DW_XPCS_CORE_CLK, + DW_XPCS_PAD_CLK, + DW_XPCS_NUM_CLKS, +}; struct dw_xpcs { + struct dw_xpcs_info info; + const struct dw_xpcs_desc *desc; struct mdio_device *mdiodev; - const struct xpcs_id *id; + struct clk_bulk_data clks[DW_XPCS_NUM_CLKS]; struct phylink_pcs pcs; phy_interface_t interface; - int dev_flag; }; int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface); @@ -46,6 +73,8 @@ int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable); struct dw_xpcs *xpcs_create_mdiodev(struct mii_bus *bus, int addr, phy_interface_t interface); +struct dw_xpcs *xpcs_create_fwnode(struct fwnode_handle *fwnode, + phy_interface_t interface); void xpcs_destroy(struct dw_xpcs *xpcs); #endif /* __LINUX_PCS_XPCS_H */ diff --git a/include/linux/pds/pds_common.h b/include/linux/pds/pds_common.h index 30581e2e04cc..5802e1deef24 100644 --- a/include/linux/pds/pds_common.h +++ b/include/linux/pds/pds_common.h @@ -4,6 +4,8 @@ #ifndef _PDS_COMMON_H_ #define _PDS_COMMON_H_ +#include <linux/notifier.h> + #define PDS_CORE_DRV_NAME "pds_core" /* the device's internal addressing uses up to 52 bits */ diff --git a/include/linux/peci-cpu.h b/include/linux/peci-cpu.h index ff8ae9c26c80..601cdd086bf6 100644 --- a/include/linux/peci-cpu.h +++ b/include/linux/peci-cpu.h @@ -6,6 +6,30 @@ #include <linux/types.h> +/* Copied from x86 <asm/processor.h> */ +#define X86_VENDOR_INTEL 0 + +/* Copied from x86 <asm/cpu_device_id.h> */ +#define VFM_MODEL_BIT 0 +#define VFM_FAMILY_BIT 8 +#define VFM_VENDOR_BIT 16 +#define VFM_RSVD_BIT 24 + +#define VFM_MODEL_MASK GENMASK(VFM_FAMILY_BIT - 1, VFM_MODEL_BIT) +#define VFM_FAMILY_MASK GENMASK(VFM_VENDOR_BIT - 1, VFM_FAMILY_BIT) +#define VFM_VENDOR_MASK GENMASK(VFM_RSVD_BIT - 1, VFM_VENDOR_BIT) + +#define VFM_MODEL(vfm) (((vfm) & VFM_MODEL_MASK) >> VFM_MODEL_BIT) +#define VFM_FAMILY(vfm) (((vfm) & VFM_FAMILY_MASK) >> VFM_FAMILY_BIT) +#define VFM_VENDOR(vfm) (((vfm) & VFM_VENDOR_MASK) >> VFM_VENDOR_BIT) + +#define VFM_MAKE(_vendor, _family, _model) ( \ + ((_model) << VFM_MODEL_BIT) | \ + ((_family) << VFM_FAMILY_BIT) | \ + ((_vendor) << VFM_VENDOR_BIT) \ +) +/* End of copied code */ + #include "../../arch/x86/include/asm/intel-family.h" #define PECI_PCS_PKG_ID 0 /* Package Identifier Read */ diff --git a/include/linux/peci.h b/include/linux/peci.h index 90e241458ef6..3e0bc37591d6 100644 --- a/include/linux/peci.h +++ b/include/linux/peci.h @@ -59,8 +59,7 @@ static inline struct peci_controller *to_peci_controller(void *d) * struct peci_device - PECI device * @dev: device object to register PECI device to the device model * @info: PECI device characteristics - * @info.family: device family - * @info.model: device model + * @info.x86_vfm: device vendor-family-model * @info.peci_revision: PECI revision supported by the PECI device * @info.socket_id: the socket ID represented by the PECI device * @addr: address used on the PECI bus connected to the parent controller @@ -73,8 +72,7 @@ static inline struct peci_controller *to_peci_controller(void *d) struct peci_device { struct device dev; struct { - u16 family; - u8 model; + u32 x86_vfm; u8 peci_revision; u8 socket_id; } info; diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index ec3573119923..8efce7414fad 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -475,6 +475,12 @@ do { \ raw_cpu_cmpxchg(pcp, oval, nval); \ }) +#define __this_cpu_try_cmpxchg(pcp, ovalp, nval) \ +({ \ + __this_cpu_preempt_check("try_cmpxchg"); \ + raw_cpu_try_cmpxchg(pcp, ovalp, nval); \ +}) + #define __this_cpu_sub(pcp, val) __this_cpu_add(pcp, -(typeof(pcp))(val)) #define __this_cpu_inc(pcp) __this_cpu_add(pcp, 1) #define __this_cpu_dec(pcp) __this_cpu_sub(pcp, 1) diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 8c677f185901..4b2047b78b67 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -2,19 +2,24 @@ #ifndef __LINUX_PERCPU_H #define __LINUX_PERCPU_H +#include <linux/alloc_tag.h> #include <linux/mmdebug.h> #include <linux/preempt.h> #include <linux/smp.h> -#include <linux/cpumask.h> #include <linux/pfn.h> #include <linux/init.h> #include <linux/cleanup.h> +#include <linux/sched.h> #include <asm/percpu.h> /* enough to cover all DEFINE_PER_CPUs in modules */ #ifdef CONFIG_MODULES +#ifdef CONFIG_MEM_ALLOC_PROFILING +#define PERCPU_MODULE_RESERVE (8 << 13) +#else #define PERCPU_MODULE_RESERVE (8 << 10) +#endif #else #define PERCPU_MODULE_RESERVE 0 #endif @@ -121,7 +126,6 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn); #endif -extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align) __alloc_size(1); extern bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr); extern bool is_kernel_percpu_address(unsigned long addr); @@ -129,14 +133,16 @@ extern bool is_kernel_percpu_address(unsigned long addr); extern void __init setup_per_cpu_areas(void); #endif -extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp) __alloc_size(1); -extern void __percpu *__alloc_percpu(size_t size, size_t align) __alloc_size(1); -extern void free_percpu(void __percpu *__pdata); +extern void __percpu *pcpu_alloc_noprof(size_t size, size_t align, bool reserved, + gfp_t gfp) __alloc_size(1); extern size_t pcpu_alloc_size(void __percpu *__pdata); -DEFINE_FREE(free_percpu, void __percpu *, free_percpu(_T)) - -extern phys_addr_t per_cpu_ptr_to_phys(void *addr); +#define __alloc_percpu_gfp(_size, _align, _gfp) \ + alloc_hooks(pcpu_alloc_noprof(_size, _align, false, _gfp)) +#define __alloc_percpu(_size, _align) \ + alloc_hooks(pcpu_alloc_noprof(_size, _align, false, GFP_KERNEL)) +#define __alloc_reserved_percpu(_size, _align) \ + alloc_hooks(pcpu_alloc_noprof(_size, _align, true, GFP_KERNEL)) #define alloc_percpu_gfp(type, gfp) \ (typeof(type) __percpu *)__alloc_percpu_gfp(sizeof(type), \ @@ -144,6 +150,15 @@ extern phys_addr_t per_cpu_ptr_to_phys(void *addr); #define alloc_percpu(type) \ (typeof(type) __percpu *)__alloc_percpu(sizeof(type), \ __alignof__(type)) +#define alloc_percpu_noprof(type) \ + ((typeof(type) __percpu *)pcpu_alloc_noprof(sizeof(type), \ + __alignof__(type), false, GFP_KERNEL)) + +extern void free_percpu(void __percpu *__pdata); + +DEFINE_FREE(free_percpu, void __percpu *, free_percpu(_T)) + +extern phys_addr_t per_cpu_ptr_to_phys(void *addr); extern unsigned long pcpu_nr_pages(void); diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h index 46377e134d67..7867db04ec98 100644 --- a/include/linux/perf/arm_pmuv3.h +++ b/include/linux/perf/arm_pmuv3.h @@ -309,4 +309,6 @@ } \ } while (0) +#include <asm/arm_pmuv3.h> + #endif diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h index 43282e22ebe1..701974639ff2 100644 --- a/include/linux/perf/riscv_pmu.h +++ b/include/linux/perf/riscv_pmu.h @@ -39,6 +39,14 @@ struct cpu_hw_events { DECLARE_BITMAP(used_hw_ctrs, RISCV_MAX_COUNTERS); /* currently enabled firmware counters */ DECLARE_BITMAP(used_fw_ctrs, RISCV_MAX_COUNTERS); + /* The virtual address of the shared memory where counter snapshot will be taken */ + void *snapshot_addr; + /* The physical address of the shared memory where counter snapshot will be taken */ + phys_addr_t snapshot_addr_phys; + /* Boolean flag to indicate setup is already done */ + bool snapshot_set_done; + /* A shadow copy of the counter values to avoid clobbering during multiple SBI calls */ + u64 snapshot_cval_shcopy[RISCV_MAX_COUNTERS]; }; struct riscv_pmu { diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index d2a15c0c6f8a..1a8942277dda 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -781,11 +781,12 @@ struct perf_event { unsigned int pending_wakeup; unsigned int pending_kill; unsigned int pending_disable; - unsigned int pending_sigtrap; unsigned long pending_addr; /* SIGTRAP */ struct irq_work pending_irq; + struct irq_work pending_disable_irq; struct callback_head pending_task; unsigned int pending_work; + struct rcuwait pending_work_wait; atomic_t event_limit; @@ -809,11 +810,8 @@ struct perf_event { u64 (*clock)(void); perf_overflow_handler_t overflow_handler; void *overflow_handler_context; -#ifdef CONFIG_BPF_SYSCALL - perf_overflow_handler_t orig_overflow_handler; struct bpf_prog *prog; u64 bpf_cookie; -#endif #ifdef CONFIG_EVENT_TRACING struct trace_event_call *tp_event; @@ -883,6 +881,7 @@ struct perf_event_pmu_context { unsigned int nr_events; unsigned int nr_cgroups; + unsigned int nr_freq; atomic_t refcount; /* event <-> epc */ struct rcu_head rcu_head; @@ -897,6 +896,11 @@ struct perf_event_pmu_context { int rotate_necessary; }; +static inline bool perf_pmu_ctx_is_active(struct perf_event_pmu_context *epc) +{ + return !list_empty(&epc->flexible_active) || !list_empty(&epc->pinned_active); +} + struct perf_event_groups { struct rb_root tree; u64 index; @@ -959,7 +963,7 @@ struct perf_event_context { struct rcu_head rcu_head; /* - * Sum (event->pending_sigtrap + event->pending_work) + * Sum (event->pending_work + event->pending_work) * * The SIGTRAP is targeted at ctx->task, as such it won't do changing * that until the signal is delivered. @@ -967,12 +971,6 @@ struct perf_event_context { local_t nr_pending; }; -/* - * Number of contexts where an event can trigger: - * task, softirq, hardirq, nmi. - */ -#define PERF_NR_CONTEXTS 4 - struct perf_cpu_pmu_context { struct perf_event_pmu_context epc; struct perf_event_pmu_context *task_epc; @@ -1342,8 +1340,10 @@ extern int perf_event_output(struct perf_event *event, struct pt_regs *regs); static inline bool -__is_default_overflow_handler(perf_overflow_handler_t overflow_handler) +is_default_overflow_handler(struct perf_event *event) { + perf_overflow_handler_t overflow_handler = event->overflow_handler; + if (likely(overflow_handler == perf_event_output_forward)) return true; if (unlikely(overflow_handler == perf_event_output_backward)) @@ -1351,22 +1351,6 @@ __is_default_overflow_handler(perf_overflow_handler_t overflow_handler) return false; } -#define is_default_overflow_handler(event) \ - __is_default_overflow_handler((event)->overflow_handler) - -#ifdef CONFIG_BPF_SYSCALL -static inline bool uses_default_overflow_handler(struct perf_event *event) -{ - if (likely(is_default_overflow_handler(event))) - return true; - - return __is_default_overflow_handler(event->orig_overflow_handler); -} -#else -#define uses_default_overflow_handler(event) \ - is_default_overflow_handler(event) -#endif - extern void perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, @@ -1598,11 +1582,11 @@ extern int sysctl_perf_cpu_time_max_percent; extern void perf_sample_event_took(u64 sample_len_ns); -int perf_event_max_sample_rate_handler(struct ctl_table *table, int write, +int perf_event_max_sample_rate_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write, +int perf_cpu_time_max_percent_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int perf_event_max_stack_handler(struct ctl_table *table, int write, +int perf_event_max_stack_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); /* Access to perf_event_open(2) syscall. */ @@ -1697,6 +1681,14 @@ perf_event_addr_filters(struct perf_event *event) return ifh; } +static inline struct fasync_struct **perf_event_fasync(struct perf_event *event) +{ + /* Only the parent has fasync state */ + if (event->parent) + event = event->parent; + return &event->fasync; +} + extern void perf_event_addr_filters_sync(struct perf_event *event); extern void perf_report_aux_output_id(struct perf_event *event, u64 hw_id); diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h new file mode 100644 index 000000000000..207f0c83c8e9 --- /dev/null +++ b/include/linux/pgalloc_tag.h @@ -0,0 +1,151 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * page allocation tagging + */ +#ifndef _LINUX_PGALLOC_TAG_H +#define _LINUX_PGALLOC_TAG_H + +#include <linux/alloc_tag.h> + +#ifdef CONFIG_MEM_ALLOC_PROFILING + +#include <linux/page_ext.h> + +extern struct page_ext_operations page_alloc_tagging_ops; + +static inline union codetag_ref *codetag_ref_from_page_ext(struct page_ext *page_ext) +{ + return (union codetag_ref *)page_ext_data(page_ext, &page_alloc_tagging_ops); +} + +static inline struct page_ext *page_ext_from_codetag_ref(union codetag_ref *ref) +{ + return (void *)ref - page_alloc_tagging_ops.offset; +} + +/* Should be called only if mem_alloc_profiling_enabled() */ +static inline union codetag_ref *get_page_tag_ref(struct page *page) +{ + if (page) { + struct page_ext *page_ext = page_ext_get(page); + + if (page_ext) + return codetag_ref_from_page_ext(page_ext); + } + return NULL; +} + +static inline void put_page_tag_ref(union codetag_ref *ref) +{ + if (WARN_ON(!ref)) + return; + + page_ext_put(page_ext_from_codetag_ref(ref)); +} + +static inline void clear_page_tag_ref(struct page *page) +{ + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + set_codetag_empty(ref); + put_page_tag_ref(ref); + } + } +} + +static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, + unsigned int nr) +{ + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + alloc_tag_add(ref, task->alloc_tag, PAGE_SIZE * nr); + put_page_tag_ref(ref); + } + } +} + +static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) +{ + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + if (ref) { + alloc_tag_sub(ref, PAGE_SIZE * nr); + put_page_tag_ref(ref); + } + } +} + +static inline void pgalloc_tag_split(struct page *page, unsigned int nr) +{ + int i; + struct page_ext *first_page_ext; + struct page_ext *page_ext; + union codetag_ref *ref; + struct alloc_tag *tag; + + if (!mem_alloc_profiling_enabled()) + return; + + first_page_ext = page_ext = page_ext_get(page); + if (unlikely(!page_ext)) + return; + + ref = codetag_ref_from_page_ext(page_ext); + if (!ref->ct) + goto out; + + tag = ct_to_alloc_tag(ref->ct); + page_ext = page_ext_next(page_ext); + for (i = 1; i < nr; i++) { + /* Set new reference to point to the original tag */ + alloc_tag_ref_set(codetag_ref_from_page_ext(page_ext), tag); + page_ext = page_ext_next(page_ext); + } +out: + page_ext_put(first_page_ext); +} + +static inline struct alloc_tag *pgalloc_tag_get(struct page *page) +{ + struct alloc_tag *tag = NULL; + + if (mem_alloc_profiling_enabled()) { + union codetag_ref *ref = get_page_tag_ref(page); + + alloc_tag_sub_check(ref); + if (ref) { + if (ref->ct) + tag = ct_to_alloc_tag(ref->ct); + put_page_tag_ref(ref); + } + } + + return tag; +} + +static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) +{ + if (mem_alloc_profiling_enabled() && tag) + this_cpu_sub(tag->counters->bytes, PAGE_SIZE * nr); +} + +#else /* CONFIG_MEM_ALLOC_PROFILING */ + +static inline union codetag_ref *get_page_tag_ref(struct page *page) { return NULL; } +static inline void put_page_tag_ref(union codetag_ref *ref) {} +static inline void clear_page_tag_ref(struct page *page) {} +static inline void pgalloc_tag_add(struct page *page, struct task_struct *task, + unsigned int nr) {} +static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {} +static inline void pgalloc_tag_split(struct page *page, unsigned int nr) {} +static inline struct alloc_tag *pgalloc_tag_get(struct page *page) { return NULL; } +static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr) {} + +#endif /* CONFIG_MEM_ALLOC_PROFILING */ + +#endif /* _LINUX_PGALLOC_TAG_H */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 85fc7554cd52..2a6a3cccfc36 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -50,6 +50,8 @@ #define pmd_pgtable(pmd) pmd_page(pmd) #endif +#define pmd_folio(pmd) page_folio(pmd_page(pmd)) + /* * A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD] * @@ -149,9 +151,7 @@ static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address) * a shortcut which implies the use of the kernel's pgd, instead * of a process's */ -#ifndef pgd_offset_k #define pgd_offset_k(address) pgd_offset(&init_mm, (address)) -#endif /* * In many cases it is known that a virtual address is mapped at PMD or PTE @@ -459,6 +459,50 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, } #endif +#ifndef clear_young_dirty_ptes +/** + * clear_young_dirty_ptes - Mark PTEs that map consecutive pages of the + * same folio as old/clean. + * @mm: Address space the pages are mapped into. + * @addr: Address the first page is mapped at. + * @ptep: Page table pointer for the first entry. + * @nr: Number of entries to mark old/clean. + * @flags: Flags to modify the PTE batch semantics. + * + * May be overridden by the architecture; otherwise, implemented by + * get_and_clear/modify/set for each pte in the range. + * + * Note that PTE bits in the PTE range besides the PFN can differ. For example, + * some PTEs might be write-protected. + * + * Context: The caller holds the page table lock. The PTEs map consecutive + * pages that belong to the same folio. The PTEs are all in the same PMD. + */ +static inline void clear_young_dirty_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr, cydp_t flags) +{ + pte_t pte; + + for (;;) { + if (flags == CYDP_CLEAR_YOUNG) + ptep_test_and_clear_young(vma, addr, ptep); + else { + pte = ptep_get_and_clear(vma->vm_mm, addr, ptep); + if (flags & CYDP_CLEAR_YOUNG) + pte = pte_mkold(pte); + if (flags & CYDP_CLEAR_DIRTY) + pte = pte_mkclean(pte); + set_pte_at(vma->vm_mm, addr, ptep, pte); + } + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } +} +#endif + static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { @@ -685,13 +729,18 @@ static inline void clear_full_ptes(struct mm_struct *mm, unsigned long addr, * fault. This function updates TLB only, do nothing with cache or others. * It is the difference with function update_mmu_cache. */ -#ifndef __HAVE_ARCH_UPDATE_MMU_TLB +#ifndef update_mmu_tlb_range +static inline void update_mmu_tlb_range(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, unsigned int nr) +{ +} +#endif + static inline void update_mmu_tlb(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { + update_mmu_tlb_range(vma, address, ptep, 1); } -#define __HAVE_ARCH_UPDATE_MMU_TLB -#endif /* * Some architectures may be able to avoid expensive synchronization @@ -708,6 +757,35 @@ static inline void pte_clear_not_present_full(struct mm_struct *mm, } #endif +#ifndef clear_not_present_full_ptes +/** + * clear_not_present_full_ptes - Clear multiple not present PTEs which are + * consecutive in the pgtable. + * @mm: Address space the ptes represent. + * @addr: Address of the first pte. + * @ptep: Page table pointer for the first entry. + * @nr: Number of entries to clear. + * @full: Whether we are clearing a full mm. + * + * May be overridden by the architecture; otherwise, implemented as a simple + * loop over pte_clear_not_present_full(). + * + * Context: The caller holds the page table lock. The PTEs are all not present. + * The PTEs are all in the same PMD. + */ +static inline void clear_not_present_full_ptes(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, unsigned int nr, int full) +{ + for (;;) { + pte_clear_not_present_full(mm, addr, ptep, full); + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } +} +#endif + #ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH extern pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address, @@ -1011,6 +1089,15 @@ static inline int pgd_same(pgd_t pgd_a, pgd_t pgd_b) }) #ifndef __HAVE_ARCH_DO_SWAP_PAGE +static inline void arch_do_swap_page_nr(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long addr, + pte_t pte, pte_t oldpte, + int nr) +{ + +} +#else /* * Some architectures support metadata associated with a page. When a * page is being swapped out, this metadata must be saved so it can be @@ -1019,12 +1106,17 @@ static inline int pgd_same(pgd_t pgd_a, pgd_t pgd_b) * page as metadata for the page. arch_do_swap_page() can restore this * metadata when a page is swapped back in. */ -static inline void arch_do_swap_page(struct mm_struct *mm, - struct vm_area_struct *vma, - unsigned long addr, - pte_t pte, pte_t oldpte) -{ - +static inline void arch_do_swap_page_nr(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long addr, + pte_t pte, pte_t oldpte, + int nr) +{ + for (int i = 0; i < nr; i++) { + arch_do_swap_page(vma->vm_mm, vma, addr + i * PAGE_SIZE, + pte_advance_pfn(pte, i), + pte_advance_pfn(oldpte, i)); + } } #endif @@ -1052,7 +1144,7 @@ static inline int arch_unmap_one(struct mm_struct *mm, * prototypes must be defined in the arch-specific asm/pgtable.h file. */ #ifndef __HAVE_ARCH_PREPARE_TO_SWAP -static inline int arch_prepare_to_swap(struct page *page) +static inline int arch_prepare_to_swap(struct folio *folio) { return 0; } @@ -1079,7 +1171,7 @@ static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) #endif #ifndef __HAVE_ARCH_MOVE_PTE -#define move_pte(pte, prot, old_addr, new_addr) (pte) +#define move_pte(pte, old_addr, new_addr) (pte) #endif #ifndef pte_accessible @@ -1770,11 +1862,25 @@ typedef unsigned int pgtbl_mod_mask; #endif /* - * p?d_leaf() - true if this entry is a final mapping to a physical address. - * This differs from p?d_huge() by the fact that they are always available (if - * the architecture supports large pages at the appropriate level) even - * if CONFIG_HUGETLB_PAGE is not defined. - * Only meaningful when called on a valid entry. + * pXd_leaf() is the API to check whether a pgtable entry is a huge page + * mapping. It should work globally across all archs, without any + * dependency on CONFIG_* options. For architectures that do not support + * huge mappings on specific levels, below fallbacks will be used. + * + * A leaf pgtable entry should always imply the following: + * + * - It is a "present" entry. IOW, before using this API, please check it + * with pXd_present() first. NOTE: it may not always mean the "present + * bit" is set. For example, PROT_NONE entries are always "present". + * + * - It should _never_ be a swap entry of any type. Above "present" check + * should have guarded this, but let's be crystal clear on this. + * + * - It should contain a huge PFN, which points to a huge page larger than + * PAGE_SIZE of the platform. The PFN format isn't important here. + * + * - It should cover all kinds of huge mappings (e.g., pXd_trans_huge(), + * pXd_devmap(), or hugetlb mappings). */ #ifndef pgd_leaf #define pgd_leaf(x) false @@ -1801,9 +1907,26 @@ typedef unsigned int pgtbl_mod_mask; #ifndef pmd_leaf_size #define pmd_leaf_size(x) PMD_SIZE #endif +#ifndef __pte_leaf_size #ifndef pte_leaf_size #define pte_leaf_size(x) PAGE_SIZE #endif +#define __pte_leaf_size(x,y) pte_leaf_size(y) +#endif + +/* + * We always define pmd_pfn for all archs as it's used in lots of generic + * code. Now it happens too for pud_pfn (and can happen for larger + * mappings too in the future; we're not there yet). Instead of defining + * it for all archs (like pmd_pfn), provide a fallback. + * + * Note that returning 0 here means any arch that didn't define this can + * get severely wrong when it hits a real pud leaf. It's arch's + * responsibility to properly define it when a huge pud is possible. + */ +#ifndef pud_pfn +#define pud_pfn(x) 0 +#endif /* * Some architectures have MMUs that are configurable or selectable at boot diff --git a/include/linux/phy.h b/include/linux/phy.h index 3f68b8239bb1..6b7d40d49129 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -128,6 +128,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_10GKR: 10GBASE-KR - with Clause 73 AN * @PHY_INTERFACE_MODE_QUSGMII: Quad Universal SGMII * @PHY_INTERFACE_MODE_1000BASEKX: 1000Base-KX - with Clause 73 AN + * @PHY_INTERFACE_MODE_10G_QXGMII: 10G-QXGMII - 4 ports over 10G USXGMII * @PHY_INTERFACE_MODE_MAX: Book keeping * * Describes the interface between the MAC and PHY. @@ -168,6 +169,7 @@ typedef enum { PHY_INTERFACE_MODE_10GKR, PHY_INTERFACE_MODE_QUSGMII, PHY_INTERFACE_MODE_1000BASEKX, + PHY_INTERFACE_MODE_10G_QXGMII, PHY_INTERFACE_MODE_MAX, } phy_interface_t; @@ -289,6 +291,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "100base-x"; case PHY_INTERFACE_MODE_QUSGMII: return "qusgmii"; + case PHY_INTERFACE_MODE_10G_QXGMII: + return "10g-qxgmii"; default: return "unknown"; } @@ -612,6 +616,8 @@ struct macsec_ops; * handling shall be postponed until PHY has resumed * @irq_rerun: Flag indicating interrupts occurred while PHY was suspended, * requiring a rerun of the interrupt handler after resume + * @default_timestamp: Flag indicating whether we are using the phy + * timestamp as the default one * @interface: enum phy_interface_t value * @possible_interfaces: bitmap if interface modes that the attached PHY * will switch between depending on media speed. @@ -677,6 +683,8 @@ struct phy_device { unsigned irq_suspended:1; unsigned irq_rerun:1; + unsigned default_timestamp:1; + int rate_matching; enum phy_state state; @@ -778,6 +786,7 @@ struct phy_device { /* Generic phy_device::dev_flags */ #define PHY_F_NO_IRQ 0x80000000 +#define PHY_F_RXC_ALWAYS_ON 0x40000000 static inline struct phy_device *to_phy_device(const struct device *dev) { @@ -1121,7 +1130,7 @@ struct phy_driver { u8 index, enum led_brightness value); /** - * @led_blink_set: Set a PHY LED brightness. Index indicates + * @led_blink_set: Set a PHY LED blinking. Index indicates * which of the PHYs led should be configured to blink. Delays * are in milliseconds and if both are zero then a sensible * default should be chosen. The call should adjust the @@ -1178,7 +1187,7 @@ struct phy_driver { int (*led_polarity_set)(struct phy_device *dev, int index, unsigned long modes); }; -#define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ +#define to_phy_driver(d) container_of_const(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) #define PHY_ANY_ID "MATCH ANY PHY" @@ -1609,7 +1618,7 @@ static inline bool phy_rxtstamp(struct phy_device *phydev, struct sk_buff *skb, } static inline int phy_ts_info(struct phy_device *phydev, - struct ethtool_ts_info *tsinfo) + struct kernel_ethtool_ts_info *tsinfo) { return phydev->mii_ts->ts_info(phydev->mii_ts, tsinfo); } @@ -1621,6 +1630,21 @@ static inline void phy_txtstamp(struct phy_device *phydev, struct sk_buff *skb, } /** + * phy_is_default_hwtstamp - Is the PHY hwtstamp the default timestamp + * @phydev: Pointer to phy_device + * + * This is used to get default timestamping device taking into account + * the new API choice, which is selecting the timestamping from MAC by + * default if the phydev does not have default_timestamp flag enabled. + * + * Return: True if phy is the default hw timestamp, false otherwise. + */ +static inline bool phy_is_default_hwtstamp(struct phy_device *phydev) +{ + return phy_has_hwtstamp(phydev) && phydev->default_timestamp; +} + +/** * phy_is_internal - Convenience function for testing if a PHY is internal * @phydev: the phy_device struct */ diff --git a/include/linux/phy/phy-dp.h b/include/linux/phy/phy-dp.h index 18cad23642cd..9cce5766bc0b 100644 --- a/include/linux/phy/phy-dp.h +++ b/include/linux/phy/phy-dp.h @@ -8,6 +8,9 @@ #include <linux/types.h> +#define PHY_SUBMODE_DP 0 +#define PHY_SUBMODE_EDP 1 + /** * struct phy_configure_opts_dp - DisplayPort PHY configuration set * diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 9a57deefcb07..2381e07429a2 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -138,7 +138,11 @@ enum phylink_op_type { * @poll_fixed_state: if true, starts link_poll, * if MAC link is at %MLO_AN_FIXED mode. * @mac_managed_pm: if true, indicate the MAC driver is responsible for PHY PM. - * @ovr_an_inband: if true, override PCS to MLO_AN_INBAND + * @mac_requires_rxc: if true, the MAC always requires a receive clock from PHY. + * The PHY driver should start the clock signal as soon as + * possible and avoid stopping it during suspend events. + * @default_an_inband: if true, defaults to MLO_AN_INBAND rather than + * MLO_AN_PHY. A fixed-link specification will override. * @get_fixed_state: callback to execute to determine the fixed link state, * if MAC link is at %MLO_AN_FIXED mode. * @supported_interfaces: bitmap describing which PHY_INTERFACE_MODE_xxx @@ -150,7 +154,8 @@ struct phylink_config { enum phylink_op_type type; bool poll_fixed_state; bool mac_managed_pm; - bool ovr_an_inband; + bool mac_requires_rxc; + bool default_an_inband; void (*get_fixed_state)(struct phylink_config *config, struct phylink_link_state *state); DECLARE_PHY_INTERFACE_MASK(supported_interfaces); @@ -392,6 +397,10 @@ struct phylink_pcs_ops; * @phylink: pointer to &struct phylink_config * @neg_mode: provide PCS neg mode via "mode" argument * @poll: poll the PCS for link changes + * @rxc_always_on: The MAC driver requires the reference clock + * to always be on. Standalone PCS drivers which + * do not have access to a PHY device can check + * this instead of PHY_F_RXC_ALWAYS_ON. * * This structure is designed to be embedded within the PCS private data, * and will be passed between phylink and the PCS. @@ -404,6 +413,7 @@ struct phylink_pcs { struct phylink *phylink; bool neg_mode; bool poll; + bool rxc_always_on; }; /** @@ -418,6 +428,8 @@ struct phylink_pcs { * @pcs_an_restart: restart 802.3z BaseX autonegotiation. * @pcs_link_up: program the PCS for the resolved link configuration * (where necessary). + * @pcs_pre_init: configure PCS components necessary for MAC hardware + * initialization e.g. RX clock for stmmac. */ struct phylink_pcs_ops { int (*pcs_validate)(struct phylink_pcs *pcs, unsigned long *supported, @@ -437,6 +449,7 @@ struct phylink_pcs_ops { void (*pcs_an_restart)(struct phylink_pcs *pcs); void (*pcs_link_up)(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, int speed, int duplex); + int (*pcs_pre_init)(struct phylink_pcs *pcs); }; #if 0 /* For kernel-doc purposes only. */ @@ -542,6 +555,34 @@ void pcs_an_restart(struct phylink_pcs *pcs); */ void pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, int speed, int duplex); + +/** + * pcs_pre_init() - Configure PCS components necessary for MAC initialization + * @pcs: a pointer to a &struct phylink_pcs. + * + * This function can be called by MAC drivers through the + * phylink_pcs_pre_init() wrapper, before their hardware is initialized. It + * should not be called after the link is brought up, as reconfiguring the PCS + * at this point could break the link. + * + * Some MAC devices require specific hardware initialization to be performed by + * their associated PCS device before they can properly initialize their own + * hardware. An example of this is the initialization of stmmac controllers, + * which requires an active REF_CLK signal to be provided by the PHY/PCS. + * + * By calling phylink_pcs_pre_init(), MAC drivers can ensure that the PCS is + * setup in a way that allows for successful hardware initialization. + * + * The specific configuration performed by pcs_pre_init() is dependent on the + * model of PCS and the requirements of the MAC device attached to it. PCS + * driver authors should consider whether their target device is to be used in + * conjunction with a MAC device whose driver calls phylink_pcs_pre_init(). MAC + * driver authors should document their requirements for the PCS + * pre-initialization. + * + */ +int pcs_pre_init(struct phylink_pcs *pcs); + #endif struct phylink *phylink_create(struct phylink_config *, @@ -561,6 +602,8 @@ void phylink_disconnect_phy(struct phylink *); void phylink_mac_change(struct phylink *, bool up); void phylink_pcs_change(struct phylink_pcs *, bool up); +int phylink_pcs_pre_init(struct phylink *pl, struct phylink_pcs *pcs); + void phylink_start(struct phylink *); void phylink_stop(struct phylink *); @@ -611,6 +654,7 @@ static inline int phylink_get_link_timer_ns(phy_interface_t interface) case PHY_INTERFACE_MODE_SGMII: case PHY_INTERFACE_MODE_QSGMII: case PHY_INTERFACE_MODE_USXGMII: + case PHY_INTERFACE_MODE_10G_QXGMII: return 1600000; case PHY_INTERFACE_MODE_1000BASEX: diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h index ecc47d5fe239..e574b790be6f 100644 --- a/include/linux/platform_data/cros_ec_commands.h +++ b/include/linux/platform_data/cros_ec_commands.h @@ -3463,6 +3463,34 @@ union __ec_align_offset1 ec_response_get_next_data_v1 { }; BUILD_ASSERT(sizeof(union ec_response_get_next_data_v1) == 16); +union __ec_align_offset1 ec_response_get_next_data_v3 { + uint8_t key_matrix[18]; + + /* Unaligned */ + uint32_t host_event; + uint64_t host_event64; + + struct __ec_todo_unpacked { + /* For aligning the fifo_info */ + uint8_t reserved[3]; + struct ec_response_motion_sense_fifo_info info; + } sensor_fifo; + + uint32_t buttons; + + uint32_t switches; + + uint32_t fp_events; + + uint32_t sysrq; + + /* CEC events from enum mkbp_cec_event */ + uint32_t cec_events; + + uint8_t cec_message[16]; +}; +BUILD_ASSERT(sizeof(union ec_response_get_next_data_v3) == 18); + struct ec_response_get_next_event { uint8_t event_type; /* Followed by event data if any */ @@ -3475,6 +3503,12 @@ struct ec_response_get_next_event_v1 { union ec_response_get_next_data_v1 data; } __ec_align1; +struct ec_response_get_next_event_v3 { + uint8_t event_type; + /* Followed by event data if any */ + union ec_response_get_next_data_v3 data; +} __ec_align1; + /* Bit indices for buttons and switches.*/ /* Buttons */ #define EC_MKBP_POWER_BUTTON 0 @@ -3809,16 +3843,61 @@ struct ec_params_i2c_write { * discharge the battery. */ #define EC_CMD_CHARGE_CONTROL 0x0096 -#define EC_VER_CHARGE_CONTROL 1 +#define EC_VER_CHARGE_CONTROL 3 enum ec_charge_control_mode { CHARGE_CONTROL_NORMAL = 0, CHARGE_CONTROL_IDLE, CHARGE_CONTROL_DISCHARGE, + /* Add no more entry below. */ + CHARGE_CONTROL_COUNT, +}; + +#define EC_CHARGE_MODE_TEXT \ + { \ + [CHARGE_CONTROL_NORMAL] = "NORMAL", \ + [CHARGE_CONTROL_IDLE] = "IDLE", \ + [CHARGE_CONTROL_DISCHARGE] = "DISCHARGE", \ + } + +enum ec_charge_control_cmd { + EC_CHARGE_CONTROL_CMD_SET = 0, + EC_CHARGE_CONTROL_CMD_GET, +}; + +enum ec_charge_control_flag { + EC_CHARGE_CONTROL_FLAG_NO_IDLE = BIT(0), }; struct ec_params_charge_control { - uint32_t mode; /* enum charge_control_mode */ + uint32_t mode; /* enum charge_control_mode */ + + /* Below are the fields added in V2. */ + uint8_t cmd; /* enum ec_charge_control_cmd. */ + uint8_t flags; /* enum ec_charge_control_flag (v3+) */ + /* + * Lower and upper thresholds for battery sustainer. This struct isn't + * named to avoid tainting foreign projects' name spaces. + * + * If charge mode is explicitly set (e.g. DISCHARGE), battery sustainer + * will be disabled. To disable battery sustainer, set mode=NORMAL, + * lower=-1, upper=-1. + */ + struct { + int8_t lower; /* Display SoC in percentage. */ + int8_t upper; /* Display SoC in percentage. */ + } sustain_soc; +} __ec_align4; + +/* Added in v2 */ +struct ec_response_charge_control { + uint32_t mode; /* enum charge_control_mode */ + struct { /* Battery sustainer thresholds */ + int8_t lower; + int8_t upper; + } sustain_soc; + uint8_t flags; /* enum ec_charge_control_flag (v3+) */ + uint8_t reserved; } __ec_align4; /*****************************************************************************/ diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 8865e350c12a..b34ed0cc1f8d 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -185,7 +185,7 @@ struct cros_ec_device { bool host_sleep_v1; struct blocking_notifier_head event_notifier; - struct ec_response_get_next_event_v1 event_data; + struct ec_response_get_next_event_v3 event_data; int event_size; u32 host_event_wake_mask; u32 last_resume_result; @@ -261,6 +261,10 @@ int cros_ec_get_sensor_count(struct cros_ec_dev *ec); int cros_ec_cmd(struct cros_ec_device *ec_dev, unsigned int version, int command, const void *outdata, size_t outsize, void *indata, size_t insize); +int cros_ec_cmd_readmem(struct cros_ec_device *ec_dev, u8 offset, u8 size, void *dest); + +int cros_ec_get_cmd_versions(struct cros_ec_device *ec_dev, u16 cmd); + /** * cros_ec_get_time_ns() - Return time in ns. * diff --git a/include/linux/platform_data/davinci_asp.h b/include/linux/platform_data/davinci_asp.h index c8645b2ed3c0..b9c8520b4bd3 100644 --- a/include/linux/platform_data/davinci_asp.h +++ b/include/linux/platform_data/davinci_asp.h @@ -26,16 +26,6 @@ struct davinci_mcasp_pdata { struct gen_pool *sram_pool; /* - * If McBSP peripheral gets the clock from an external pin, - * there are three chooses, that are MCBSP_CLKX, MCBSP_CLKR - * and MCBSP_CLKS. - * Depending on different hardware connections it is possible - * to use this setting to change the behaviour of McBSP - * driver. - */ - int clk_input_pin; - - /* * This flag works when both clock and FS are outputs for the cpu * and makes clock more accurate (FS is not symmetrical and the * clock is very fast. @@ -91,11 +81,6 @@ enum { MCASP_VERSION_OMAP, /* OMAP4/5 */ }; -enum mcbsp_clk_input_pin { - MCBSP_CLKR = 0, /* as in DM365 */ - MCBSP_CLKS, -}; - #define INACTIVE_MODE 0 #define TX_MODE 1 #define RX_MODE 2 diff --git a/include/linux/platform_data/i2c-mux-gpio.h b/include/linux/platform_data/i2c-mux-gpio.h index 5e4c2c272a73..96843aab4d1e 100644 --- a/include/linux/platform_data/i2c-mux-gpio.h +++ b/include/linux/platform_data/i2c-mux-gpio.h @@ -18,16 +18,16 @@ * @values: Array of bitmasks of GPIO settings (low/high) for each * position * @n_values: Number of multiplexer positions (busses to instantiate) - * @classes: Optional I2C auto-detection classes * @idle: Bitmask to write to MUX when idle or GPIO_I2CMUX_NO_IDLE if not used + * @settle_time: Delay to wait when a new bus is selected */ struct i2c_mux_gpio_platform_data { int parent; int base_nr; const unsigned *values; int n_values; - const unsigned *classes; unsigned idle; + u32 settle_time; }; #endif /* _LINUX_I2C_MUX_GPIO_H */ diff --git a/include/linux/platform_data/lenovo-yoga-c630.h b/include/linux/platform_data/lenovo-yoga-c630.h new file mode 100644 index 000000000000..5d1f9fb33cfc --- /dev/null +++ b/include/linux/platform_data/lenovo-yoga-c630.h @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022-2024, Linaro Ltd + * Authors: + * Bjorn Andersson + * Dmitry Baryshkov + */ + +#ifndef _LENOVO_YOGA_C630_DATA_H +#define _LENOVO_YOGA_C630_DATA_H + +struct yoga_c630_ec; +struct notifier_block; + +#define YOGA_C630_MOD_NAME "lenovo_yoga_c630" + +#define YOGA_C630_DEV_UCSI "ucsi" +#define YOGA_C630_DEV_PSY "psy" + +int yoga_c630_ec_read8(struct yoga_c630_ec *ec, u8 addr); +int yoga_c630_ec_read16(struct yoga_c630_ec *ec, u8 addr); + +int yoga_c630_ec_register_notify(struct yoga_c630_ec *ec, struct notifier_block *nb); +void yoga_c630_ec_unregister_notify(struct yoga_c630_ec *ec, struct notifier_block *nb); + +#define YOGA_C630_UCSI_WRITE_SIZE 8 +#define YOGA_C630_UCSI_CCI_SIZE 4 +#define YOGA_C630_UCSI_DATA_SIZE 16 +#define YOGA_C630_UCSI_READ_SIZE (YOGA_C630_UCSI_CCI_SIZE + YOGA_C630_UCSI_DATA_SIZE) + +u16 yoga_c630_ec_ucsi_get_version(struct yoga_c630_ec *ec); +int yoga_c630_ec_ucsi_write(struct yoga_c630_ec *ec, + const u8 req[YOGA_C630_UCSI_WRITE_SIZE]); +int yoga_c630_ec_ucsi_read(struct yoga_c630_ec *ec, + u8 resp[YOGA_C630_UCSI_READ_SIZE]); + +#define LENOVO_EC_EVENT_USB 0x20 +#define LENOVO_EC_EVENT_UCSI 0x21 +#define LENOVO_EC_EVENT_HPD 0x22 +#define LENOVO_EC_EVENT_BAT_STATUS 0x24 +#define LENOVO_EC_EVENT_BAT_INFO 0x25 +#define LENOVO_EC_EVENT_BAT_ADPT_STATUS 0x37 + +#endif diff --git a/include/linux/platform_data/mmc-pxamci.h b/include/linux/platform_data/mmc-pxamci.h index 7e44e84e7150..652f323b5ecc 100644 --- a/include/linux/platform_data/mmc-pxamci.h +++ b/include/linux/platform_data/mmc-pxamci.h @@ -7,6 +7,7 @@ struct device; struct mmc_host; +struct property_entry; struct pxamci_platform_data { unsigned int ocr_mask; /* available voltages */ @@ -18,7 +19,8 @@ struct pxamci_platform_data { bool gpio_card_ro_invert; /* gpio ro is inverted */ }; -extern void pxa_set_mci_info(struct pxamci_platform_data *info); +extern void pxa_set_mci_info(const struct pxamci_platform_data *info, + const struct property_entry *props); extern void pxa3xx_set_mci2_info(struct pxamci_platform_data *info); extern void pxa3xx_set_mci3_info(struct pxamci_platform_data *info); diff --git a/include/linux/platform_data/omap1_bl.h b/include/linux/platform_data/omap1_bl.h index 5e8b17d77a5f..3d0bab31a0a9 100644 --- a/include/linux/platform_data/omap1_bl.h +++ b/include/linux/platform_data/omap1_bl.h @@ -6,7 +6,6 @@ struct omap_backlight_config { int default_intensity; - int (*set_power)(struct device *dev, int state); }; #endif diff --git a/include/linux/platform_data/spi-omap2-mcspi.h b/include/linux/platform_data/spi-omap2-mcspi.h index 3b400b1919a9..9e3c15b4ac91 100644 --- a/include/linux/platform_data/spi-omap2-mcspi.h +++ b/include/linux/platform_data/spi-omap2-mcspi.h @@ -16,9 +16,6 @@ struct omap2_mcspi_platform_config { struct omap2_mcspi_device_config { unsigned turbo_mode:1; - - /* toggle chip select after every word */ - unsigned cs_per_word:1; }; #endif diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index eb556f988d57..d8f15770a522 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -71,7 +71,6 @@ struct sysc_regbits { #define SYSC_QUIRK_SWSUP_SIDLE_ACT BIT(12) #define SYSC_QUIRK_SWSUP_SIDLE BIT(11) #define SYSC_QUIRK_EXT_OPT_CLOCK BIT(10) -#define SYSC_QUIRK_LEGACY_IDLE BIT(9) #define SYSC_QUIRK_RESET_STATUS BIT(8) #define SYSC_QUIRK_NO_IDLE BIT(7) #define SYSC_QUIRK_NO_IDLE_ON_INIT BIT(6) diff --git a/include/linux/platform_data/tmio.h b/include/linux/platform_data/tmio.h new file mode 100644 index 000000000000..b060124ba1ae --- /dev/null +++ b/include/linux/platform_data/tmio.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef MFD_TMIO_H +#define MFD_TMIO_H + +#include <linux/platform_device.h> +#include <linux/types.h> + +/* TMIO MMC platform flags */ + +/* + * Some controllers can support a 2-byte block size when the bus width is + * configured in 4-bit mode. + */ +#define TMIO_MMC_BLKSZ_2BYTES BIT(1) + +/* Some controllers can support SDIO IRQ signalling */ +#define TMIO_MMC_SDIO_IRQ BIT(2) + +/* Some features are only available or tested on R-Car Gen2 or later */ +#define TMIO_MMC_MIN_RCAR2 BIT(3) + +/* + * Some controllers require waiting for the SD bus to become idle before + * writing to some registers. + */ +#define TMIO_MMC_HAS_IDLE_WAIT BIT(4) + +/* + * Use the busy timeout feature. Probably all TMIO versions support it. Yet, + * we don't have documentation for old variants, so we enable only known good + * variants with this flag. Can be removed once all variants are known good. + */ +#define TMIO_MMC_USE_BUSY_TIMEOUT BIT(5) + +/* Some controllers have CMD12 automatically issue/non-issue register */ +#define TMIO_MMC_HAVE_CMD12_CTRL BIT(7) + +/* Controller has some SDIO status bits which must be 1 */ +#define TMIO_MMC_SDIO_STATUS_SETBITS BIT(8) + +/* Some controllers have a 32-bit wide data port register */ +#define TMIO_MMC_32BIT_DATA_PORT BIT(9) + +/* Some controllers allows to set SDx actual clock */ +#define TMIO_MMC_CLK_ACTUAL BIT(10) + +/* Some controllers have a CBSY bit */ +#define TMIO_MMC_HAVE_CBSY BIT(11) + +struct tmio_mmc_data { + void *chan_priv_tx; + void *chan_priv_rx; + unsigned int hclk; + unsigned long capabilities; + unsigned long capabilities2; + unsigned long flags; + u32 ocr_mask; /* available voltages */ + dma_addr_t dma_rx_offset; + unsigned int max_blk_count; + unsigned short max_segs; +}; +#endif diff --git a/include/linux/platform_data/uio_pruss.h b/include/linux/platform_data/uio_pruss.h deleted file mode 100644 index f76fa393b802..000000000000 --- a/include/linux/platform_data/uio_pruss.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * include/linux/platform_data/uio_pruss.h - * - * Platform data for uio_pruss driver - * - * Copyright (C) 2010-11 Texas Instruments Incorporated - https://www.ti.com/ - */ - -#ifndef _UIO_PRUSS_H_ -#define _UIO_PRUSS_H_ - -/* To configure the PRUSS INTC base offset for UIO driver */ -struct uio_pruss_pdata { - u32 pintc_base; - struct gen_pool *sram_pool; -}; -#endif /* _UIO_PRUSS_H_ */ diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index ab1c7deff118..0aeeae1c1943 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -51,6 +51,10 @@ #define ASUS_WMI_DEVID_LED6 0x00020016 #define ASUS_WMI_DEVID_MICMUTE_LED 0x00040017 +/* Disable Camera LED */ +#define ASUS_WMI_DEVID_CAMERA_LED_NEG 0x00060078 /* 0 = on (unused) */ +#define ASUS_WMI_DEVID_CAMERA_LED 0x00060079 /* 1 = on */ + /* Backlight and Brightness */ #define ASUS_WMI_DEVID_ALS_ENABLE 0x00050001 /* Ambient Light Sensor */ #define ASUS_WMI_DEVID_BACKLIGHT 0x00050011 @@ -71,6 +75,7 @@ #define ASUS_WMI_DEVID_LID_FLIP 0x00060062 #define ASUS_WMI_DEVID_LID_FLIP_ROG 0x00060077 #define ASUS_WMI_DEVID_MINI_LED_MODE 0x0005001E +#define ASUS_WMI_DEVID_MINI_LED_MODE2 0x0005002E /* Storage */ #define ASUS_WMI_DEVID_CARDREADER 0x00080013 @@ -127,13 +132,18 @@ /* gpu mux switch, 0 = dGPU, 1 = Optimus */ #define ASUS_WMI_DEVID_GPU_MUX 0x00090016 +#define ASUS_WMI_DEVID_GPU_MUX_VIVO 0x00090026 /* TUF laptop RGB modes/colours */ #define ASUS_WMI_DEVID_TUF_RGB_MODE 0x00100056 +#define ASUS_WMI_DEVID_TUF_RGB_MODE2 0x0010005A /* TUF laptop RGB power/state */ #define ASUS_WMI_DEVID_TUF_RGB_STATE 0x00100057 +/* Bootup sound control */ +#define ASUS_WMI_DEVID_BOOT_SOUND 0x00130022 + /* DSTS masks */ #define ASUS_WMI_DSTS_STATUS_BIT 0x00000001 #define ASUS_WMI_DSTS_UNKNOWN_BIT 0x00000002 diff --git a/include/linux/platform_data/x86/soc.h b/include/linux/platform_data/x86/soc.h index a5705189e2ac..f981907a5cb0 100644 --- a/include/linux/platform_data/x86/soc.h +++ b/include/linux/platform_data/x86/soc.h @@ -20,7 +20,7 @@ static inline bool soc_intel_is_##soc(void) \ { \ static const struct x86_cpu_id soc##_cpu_ids[] = { \ - X86_MATCH_INTEL_FAM6_MODEL(type, NULL), \ + X86_MATCH_VFM(type, NULL), \ {} \ }; \ const struct x86_cpu_id *id; \ @@ -31,11 +31,11 @@ static inline bool soc_intel_is_##soc(void) \ return false; \ } -SOC_INTEL_IS_CPU(byt, ATOM_SILVERMONT); -SOC_INTEL_IS_CPU(cht, ATOM_AIRMONT); -SOC_INTEL_IS_CPU(apl, ATOM_GOLDMONT); -SOC_INTEL_IS_CPU(glk, ATOM_GOLDMONT_PLUS); -SOC_INTEL_IS_CPU(cml, KABYLAKE_L); +SOC_INTEL_IS_CPU(byt, INTEL_ATOM_SILVERMONT); +SOC_INTEL_IS_CPU(cht, INTEL_ATOM_AIRMONT); +SOC_INTEL_IS_CPU(apl, INTEL_ATOM_GOLDMONT); +SOC_INTEL_IS_CPU(glk, INTEL_ATOM_GOLDMONT_PLUS); +SOC_INTEL_IS_CPU(cml, INTEL_KABYLAKE_L); #undef SOC_INTEL_IS_CPU diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 7a41c72c1959..d422db6eec63 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -237,15 +237,14 @@ struct platform_driver { int (*probe)(struct platform_device *); /* - * Traditionally the remove callback returned an int which however is - * ignored by the driver core. This led to wrong expectations by driver - * authors who thought returning an error code was a valid error - * handling strategy. To convert to a callback returning void, new - * drivers should implement .remove_new() until the conversion it done - * that eventually makes .remove() return void. + * .remove_new() is a relic from a prototype conversion of .remove(). + * New drivers are supposed to implement .remove(). Once all drivers are + * converted to not use .remove_new any more, it will be dropped. */ - int (*remove)(struct platform_device *); - void (*remove_new)(struct platform_device *); + union { + void (*remove)(struct platform_device *); + void (*remove_new)(struct platform_device *); + }; void (*shutdown)(struct platform_device *); int (*suspend)(struct platform_device *, pm_message_t state); diff --git a/include/linux/platform_profile.h b/include/linux/platform_profile.h index e5cbb6841f3a..f5492ed413f3 100644 --- a/include/linux/platform_profile.h +++ b/include/linux/platform_profile.h @@ -36,6 +36,7 @@ struct platform_profile_handler { int platform_profile_register(struct platform_profile_handler *pprof); int platform_profile_remove(void); +int platform_profile_cycle(void); void platform_profile_notify(void); #endif /*_PLATFORM_PROFILE_H_*/ diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 772d3280d35f..858c8e7851fb 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -16,7 +16,7 @@ #include <linux/of.h> #include <linux/notifier.h> #include <linux/spinlock.h> -#include <linux/cpumask.h> +#include <linux/cpumask_types.h> #include <linux/time64.h> /* @@ -175,6 +175,10 @@ struct generic_pm_domain { int (*set_performance_state)(struct generic_pm_domain *genpd, unsigned int state); struct gpd_dev_ops dev_ops; + int (*set_hwmode_dev)(struct generic_pm_domain *domain, + struct device *dev, bool enable); + bool (*get_hwmode_dev)(struct generic_pm_domain *domain, + struct device *dev); int (*attach_dev)(struct generic_pm_domain *domain, struct device *dev); void (*detach_dev)(struct generic_pm_domain *domain, @@ -237,6 +241,7 @@ struct generic_pm_domain_data { unsigned int performance_state; unsigned int default_pstate; unsigned int rpm_pstate; + bool hw_mode; void *data; }; @@ -260,12 +265,15 @@ int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, int pm_genpd_init(struct generic_pm_domain *genpd, struct dev_power_governor *gov, bool is_off); int pm_genpd_remove(struct generic_pm_domain *genpd); +struct device *dev_to_genpd_dev(struct device *dev); int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state); int dev_pm_genpd_add_notifier(struct device *dev, struct notifier_block *nb); int dev_pm_genpd_remove_notifier(struct device *dev); void dev_pm_genpd_set_next_wakeup(struct device *dev, ktime_t next); ktime_t dev_pm_genpd_get_next_hrtimer(struct device *dev); void dev_pm_genpd_synced_poweroff(struct device *dev); +int dev_pm_genpd_set_hwmode(struct device *dev, bool enable); +bool dev_pm_genpd_get_hwmode(struct device *dev); extern struct dev_power_governor simple_qos_governor; extern struct dev_power_governor pm_domain_always_on_gov; @@ -307,6 +315,11 @@ static inline int pm_genpd_remove(struct generic_pm_domain *genpd) return -EOPNOTSUPP; } +static inline struct device *dev_to_genpd_dev(struct device *dev) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state) { @@ -334,6 +347,16 @@ static inline ktime_t dev_pm_genpd_get_next_hrtimer(struct device *dev) static inline void dev_pm_genpd_synced_poweroff(struct device *dev) { } +static inline int dev_pm_genpd_set_hwmode(struct device *dev, bool enable) +{ + return -EOPNOTSUPP; +} + +static inline bool dev_pm_genpd_get_hwmode(struct device *dev) +{ + return false; +} + #define simple_qos_governor (*(struct dev_power_governor *)(NULL)) #define pm_domain_always_on_gov (*(struct dev_power_governor *)(NULL)) #endif diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 065a47382302..6424692c30b7 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -474,8 +474,11 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpuma struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev); struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp); int of_get_required_opp_performance_state(struct device_node *np, int index); +bool dev_pm_opp_of_has_required_opp(struct device *dev); int dev_pm_opp_of_find_icc_paths(struct device *dev, struct opp_table *opp_table); int dev_pm_opp_of_register_em(struct device *dev, struct cpumask *cpus); +int dev_pm_opp_calc_power(struct device *dev, unsigned long *uW, + unsigned long *kHz); static inline void dev_pm_opp_of_unregister_em(struct device *dev) { em_dev_unregister_perf_domain(dev); @@ -539,11 +542,22 @@ static inline void dev_pm_opp_of_unregister_em(struct device *dev) { } +static inline int dev_pm_opp_calc_power(struct device *dev, unsigned long *uW, + unsigned long *kHz) +{ + return -EOPNOTSUPP; +} + static inline int of_get_required_opp_performance_state(struct device_node *np, int index) { return -EOPNOTSUPP; } +static inline bool dev_pm_opp_of_has_required_opp(struct device *dev) +{ + return false; +} + static inline int dev_pm_opp_of_find_icc_paths(struct device *dev, struct opp_table *opp_table) { return -EOPNOTSUPP; diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h index 6eb9adaef52b..76cd1f9f1365 100644 --- a/include/linux/pm_wakeup.h +++ b/include/linux/pm_wakeup.h @@ -107,7 +107,7 @@ extern void wakeup_sources_read_unlock(int idx); extern struct wakeup_source *wakeup_sources_walk_start(void); extern struct wakeup_source *wakeup_sources_walk_next(struct wakeup_source *ws); extern int device_wakeup_enable(struct device *dev); -extern int device_wakeup_disable(struct device *dev); +extern void device_wakeup_disable(struct device *dev); extern void device_set_wakeup_capable(struct device *dev, bool capable); extern int device_set_wakeup_enable(struct device *dev, bool enable); extern void __pm_stay_awake(struct wakeup_source *ws); @@ -154,10 +154,9 @@ static inline int device_wakeup_enable(struct device *dev) return 0; } -static inline int device_wakeup_disable(struct device *dev) +static inline void device_wakeup_disable(struct device *dev) { dev->power.should_wakeup = false; - return 0; } static inline int device_set_wakeup_enable(struct device *dev, bool enable) @@ -235,11 +234,10 @@ static inline int device_init_wakeup(struct device *dev, bool enable) if (enable) { device_set_wakeup_capable(dev, true); return device_wakeup_enable(dev); - } else { - device_wakeup_disable(dev); - device_set_wakeup_capable(dev, false); - return 0; } + device_wakeup_disable(dev); + device_set_wakeup_capable(dev, false); + return 0; } #endif /* _LINUX_PM_WAKEUP_H */ diff --git a/include/linux/pnp.h b/include/linux/pnp.h index ddbe7c3ca4ce..b7a7158aaf65 100644 --- a/include/linux/pnp.h +++ b/include/linux/pnp.h @@ -383,7 +383,7 @@ struct pnp_driver { struct device_driver driver; }; -#define to_pnp_driver(drv) container_of(drv, struct pnp_driver, driver) +#define to_pnp_driver(drv) container_of_const(drv, struct pnp_driver, driver) struct pnp_card_driver { struct list_head global_list; @@ -435,8 +435,6 @@ struct pnp_protocol { #define protocol_for_each_dev(protocol, dev) \ list_for_each_entry(dev, &(protocol)->devices, protocol_list) -extern const struct bus_type pnp_bus_type; - #if defined(CONFIG_PNP) /* device management */ @@ -469,6 +467,8 @@ int compare_pnp_id(struct pnp_id *pos, const char *id); int pnp_register_driver(struct pnp_driver *drv); void pnp_unregister_driver(struct pnp_driver *drv); +bool dev_is_pnp(const struct device *dev); + #else /* device management */ @@ -500,6 +500,8 @@ static inline int compare_pnp_id(struct pnp_id *pos, const char *id) { return -E static inline int pnp_register_driver(struct pnp_driver *drv) { return -ENODEV; } static inline void pnp_unregister_driver(struct pnp_driver *drv) { } +static inline bool dev_is_pnp(const struct device *dev) { return false; } + #endif /* CONFIG_PNP */ /** diff --git a/include/linux/poison.h b/include/linux/poison.h index 1f0ee2459f2a..331a9a996fa8 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -38,11 +38,8 @@ * Magic nums for obj red zoning. * Placed in the first word before and the first word after an obj. */ -#define RED_INACTIVE 0x09F911029D74E35BULL /* when obj is inactive */ -#define RED_ACTIVE 0xD84156C5635688C0ULL /* when obj is active */ - -#define SLUB_RED_INACTIVE 0xbb -#define SLUB_RED_ACTIVE 0xcc +#define SLUB_RED_INACTIVE 0xbb /* when obj is inactive */ +#define SLUB_RED_ACTIVE 0xcc /* when obj is active */ /* ...and for poisoning */ #define POISON_INUSE 0x5a /* for use-uninitialised poisoning */ @@ -52,12 +49,6 @@ /********** arch/$ARCH/mm/init.c **********/ #define POISON_FREE_INITMEM 0xcc -/********** arch/ia64/hp/common/sba_iommu.c **********/ -/* - * arch/ia64/hp/common/sba_iommu.c uses a 16-byte poison string with a - * value of "SBAIOMMU POISON\0" for spill-over poisoning. - */ - /********** fs/jbd/journal.c **********/ #define JBD_POISON_FREE 0x5b #define JBD2_POISON_FREE 0x5c diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index b9e5bd2b42d3..5180dc9f1706 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -47,16 +47,8 @@ struct bq27xxx_access_methods { }; struct bq27xxx_reg_cache { - int temperature; - int time_to_empty; - int time_to_empty_avg; - int time_to_full; - int charge_full; - int cycle_count; int capacity; - int energy; int flags; - int health; }; struct bq27xxx_device_info { diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 8e5705a56b85..72dc7e45c90c 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -309,16 +309,11 @@ struct power_supply { #endif #ifdef CONFIG_LEDS_TRIGGERS - struct led_trigger *charging_full_trig; - char *charging_full_trig_name; + struct led_trigger *trig; struct led_trigger *charging_trig; - char *charging_trig_name; struct led_trigger *full_trig; - char *full_trig_name; - struct led_trigger *online_trig; - char *online_trig_name; struct led_trigger *charging_blink_full_solid_trig; - char *charging_blink_full_solid_trig_name; + struct led_trigger *charging_orange_full_green_trig; #endif }; @@ -741,7 +736,7 @@ struct power_supply_battery_info { int overvoltage_limit_uv; int constant_charge_current_max_ua; int constant_charge_voltage_max_uv; - struct power_supply_maintenance_charge_table *maintenance_charge; + const struct power_supply_maintenance_charge_table *maintenance_charge; int maintenance_charge_size; int alert_low_temp_charge_current_ua; int alert_low_temp_charge_voltage_uv; @@ -760,9 +755,9 @@ struct power_supply_battery_info { int ocv_table_size[POWER_SUPPLY_OCV_TEMP_MAX]; struct power_supply_resistance_temp_table *resist_table; int resist_table_size; - struct power_supply_vbat_ri_table *vbat2ri_discharging; + const struct power_supply_vbat_ri_table *vbat2ri_discharging; int vbat2ri_discharging_size; - struct power_supply_vbat_ri_table *vbat2ri_charging; + const struct power_supply_vbat_ri_table *vbat2ri_charging; int vbat2ri_charging_size; int bti_resistance_ohm; int bti_resistance_tolerance; @@ -815,7 +810,7 @@ power_supply_temp2resist_simple(struct power_supply_resistance_temp_table *table int table_len, int temp); extern int power_supply_vbat2ri(struct power_supply_battery_info *info, int vbat_uv, bool charging); -extern struct power_supply_maintenance_charge_table * +extern const struct power_supply_maintenance_charge_table * power_supply_get_maintenance_charging_setting(struct power_supply_battery_info *info, int index); extern bool power_supply_battery_bti_in_range(struct power_supply_battery_info *info, int resistance); @@ -829,7 +824,7 @@ extern int power_supply_set_battery_charged(struct power_supply *psy); static inline bool power_supply_supports_maintenance_charging(struct power_supply_battery_info *info) { - struct power_supply_maintenance_charge_table *mt; + const struct power_supply_maintenance_charge_table *mt; mt = power_supply_get_maintenance_charging_setting(info, 0); diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 7233e9cf1bab..ce76f1a45722 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -481,4 +481,45 @@ DEFINE_LOCK_GUARD_0(preempt, preempt_disable(), preempt_enable()) DEFINE_LOCK_GUARD_0(preempt_notrace, preempt_disable_notrace(), preempt_enable_notrace()) DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable()) +#ifdef CONFIG_PREEMPT_DYNAMIC + +extern bool preempt_model_none(void); +extern bool preempt_model_voluntary(void); +extern bool preempt_model_full(void); + +#else + +static inline bool preempt_model_none(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_NONE); +} +static inline bool preempt_model_voluntary(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY); +} +static inline bool preempt_model_full(void) +{ + return IS_ENABLED(CONFIG_PREEMPT); +} + +#endif + +static inline bool preempt_model_rt(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_RT); +} + +/* + * Does the preemption model allow non-cooperative preemption? + * + * For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with + * CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the + * kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the + * PREEMPT_NONE model. + */ +static inline bool preempt_model_preemptible(void) +{ + return preempt_model_full() || preempt_model_rt(); +} + #endif /* __LINUX_PREEMPT_H */ diff --git a/include/linux/printk.h b/include/linux/printk.h index 955e31860095..b937cefcb31c 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -60,6 +60,10 @@ static inline const char *printk_skip_headers(const char *buffer) #define CONSOLE_LOGLEVEL_DEFAULT CONFIG_CONSOLE_LOGLEVEL_DEFAULT #define CONSOLE_LOGLEVEL_QUIET CONFIG_CONSOLE_LOGLEVEL_QUIET +int match_devname_and_update_preferred_console(const char *match, + const char *name, + const short idx); + extern int console_printk[]; #define console_loglevel (console_printk[0]) @@ -71,7 +75,7 @@ extern void console_verbose(void); /* strlen("ratelimit") + 1 */ #define DEVKMSG_STR_MAX_SIZE 10 -extern char devkmsg_log_str[]; +extern char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE]; struct ctl_table; extern int suppress_printk; @@ -126,7 +130,7 @@ struct va_format { #define no_printk(fmt, ...) \ ({ \ if (0) \ - printk(fmt, ##__VA_ARGS__); \ + _printk(fmt, ##__VA_ARGS__); \ 0; \ }) @@ -192,6 +196,7 @@ void show_regs_print_info(const char *log_lvl); extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold; extern asmlinkage void dump_stack(void) __cold; void printk_trigger_flush(void); +void console_try_replay_all(void); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) @@ -271,6 +276,9 @@ static inline void dump_stack(void) static inline void printk_trigger_flush(void) { } +static inline void console_try_replay_all(void) +{ +} #endif bool this_cpu_in_panic(void); diff --git a/include/linux/profile.h b/include/linux/profile.h index 04ae5ebcb637..3f53cdb0c27c 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -4,14 +4,12 @@ #include <linux/kernel.h> #include <linux/init.h> -#include <linux/cpumask.h> #include <linux/cache.h> #include <asm/errno.h> #define CPU_PROFILING 1 #define SCHED_PROFILING 2 -#define SLEEP_PROFILING 3 #define KVM_PROFILING 4 struct proc_dir_entry; diff --git a/include/linux/property.h b/include/linux/property.h index 3a1045eb786c..61fc20e5f81f 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -13,6 +13,7 @@ #include <linux/args.h> #include <linux/array_size.h> #include <linux/bits.h> +#include <linux/cleanup.h> #include <linux/fwnode.h> #include <linux/stddef.h> #include <linux/types.h> @@ -174,13 +175,32 @@ struct fwnode_handle *device_get_next_child_node(const struct device *dev, for (child = device_get_next_child_node(dev, NULL); child; \ child = device_get_next_child_node(dev, child)) +#define device_for_each_child_node_scoped(dev, child) \ + for (struct fwnode_handle *child __free(fwnode_handle) = \ + device_get_next_child_node(dev, NULL); \ + child; child = device_get_next_child_node(dev, child)) + struct fwnode_handle *fwnode_get_named_child_node(const struct fwnode_handle *fwnode, const char *childname); struct fwnode_handle *device_get_named_child_node(const struct device *dev, const char *childname); struct fwnode_handle *fwnode_handle_get(struct fwnode_handle *fwnode); -void fwnode_handle_put(struct fwnode_handle *fwnode); + +/** + * fwnode_handle_put - Drop reference to a device node + * @fwnode: Pointer to the device node to drop the reference to. + * + * This has to be used when terminating device_for_each_child_node() iteration + * with break or return to prevent stale device node references from being left + * behind. + */ +static inline void fwnode_handle_put(struct fwnode_handle *fwnode) +{ + fwnode_call_void_op(fwnode, put); +} + +DEFINE_FREE(fwnode_handle, struct fwnode_handle *, fwnode_handle_put(_T)) int fwnode_irq_get(const struct fwnode_handle *fwnode, unsigned int index); int fwnode_irq_get_byname(const struct fwnode_handle *fwnode, const char *name); diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h index fb724c65c77b..591a53e082e6 100644 --- a/include/linux/pse-pd/pse.h +++ b/include/linux/pse-pd/pse.h @@ -9,17 +9,23 @@ #include <linux/list.h> #include <uapi/linux/ethtool.h> +/* Maximum current in uA according to IEEE 802.3-2022 Table 145-1 */ +#define MAX_PI_CURRENT 1920000 + struct phy_device; struct pse_controller_dev; /** * struct pse_control_config - PSE control/channel configuration. * - * @admin_cotrol: set PoDL PSE admin control as described in + * @podl_admin_control: set PoDL PSE admin control as described in * IEEE 802.3-2018 30.15.1.2.1 acPoDLPSEAdminControl + * @c33_admin_control: set PSE admin control as described in + * IEEE 802.3-2022 30.9.1.2.1 acPSEAdminControl */ struct pse_control_config { - enum ethtool_podl_pse_admin_state admin_cotrol; + enum ethtool_podl_pse_admin_state podl_admin_control; + enum ethtool_c33_pse_admin_state c33_admin_control; }; /** @@ -29,25 +35,66 @@ struct pse_control_config { * functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState * @podl_pw_status: power detection status of the PoDL PSE. * IEEE 802.3-2018 30.15.1.1.3 aPoDLPSEPowerDetectionStatus: + * @c33_admin_state: operational state of the PSE + * functions. IEEE 802.3-2022 30.9.1.1.2 aPSEAdminState + * @c33_pw_status: power detection status of the PSE. + * IEEE 802.3-2022 30.9.1.1.5 aPSEPowerDetectionStatus: + * @c33_pw_class: detected class of a powered PD + * IEEE 802.3-2022 30.9.1.1.8 aPSEPowerClassification + * @c33_actual_pw: power currently delivered by the PSE in mW + * IEEE 802.3-2022 30.9.1.1.23 aPSEActualPower + * @c33_ext_state_info: extended state information of the PSE + * @c33_avail_pw_limit: available power limit of the PSE in mW + * IEEE 802.3-2022 145.2.5.4 pse_avail_pwr + * @c33_pw_limit_ranges: supported power limit configuration range. The driver + * is in charge of the memory allocation. + * @c33_pw_limit_nb_ranges: number of supported power limit configuration + * ranges */ struct pse_control_status { enum ethtool_podl_pse_admin_state podl_admin_state; enum ethtool_podl_pse_pw_d_status podl_pw_status; + enum ethtool_c33_pse_admin_state c33_admin_state; + enum ethtool_c33_pse_pw_d_status c33_pw_status; + u32 c33_pw_class; + u32 c33_actual_pw; + struct ethtool_c33_pse_ext_state_info c33_ext_state_info; + u32 c33_avail_pw_limit; + struct ethtool_c33_pse_pw_limit_range *c33_pw_limit_ranges; + u32 c33_pw_limit_nb_ranges; }; /** * struct pse_controller_ops - PSE controller driver callbacks * * @ethtool_get_status: get PSE control status for ethtool interface - * @ethtool_set_config: set PSE control configuration over ethtool interface + * @setup_pi_matrix: setup PI matrix of the PSE controller + * @pi_is_enabled: Return 1 if the PSE PI is enabled, 0 if not. + * May also return negative errno. + * @pi_enable: Configure the PSE PI as enabled. + * @pi_disable: Configure the PSE PI as disabled. + * @pi_get_voltage: Return voltage similarly to get_voltage regulator + * callback. + * @pi_get_current_limit: Get the configured current limit similarly to + * get_current_limit regulator callback. + * @pi_set_current_limit: Configure the current limit similarly to + * set_current_limit regulator callback. + * Should not return an error in case of MAX_PI_CURRENT + * current value set. */ struct pse_controller_ops { int (*ethtool_get_status)(struct pse_controller_dev *pcdev, unsigned long id, struct netlink_ext_ack *extack, struct pse_control_status *status); - int (*ethtool_set_config)(struct pse_controller_dev *pcdev, - unsigned long id, struct netlink_ext_ack *extack, - const struct pse_control_config *config); + int (*setup_pi_matrix)(struct pse_controller_dev *pcdev); + int (*pi_is_enabled)(struct pse_controller_dev *pcdev, int id); + int (*pi_enable)(struct pse_controller_dev *pcdev, int id); + int (*pi_disable)(struct pse_controller_dev *pcdev, int id); + int (*pi_get_voltage)(struct pse_controller_dev *pcdev, int id); + int (*pi_get_current_limit)(struct pse_controller_dev *pcdev, + int id); + int (*pi_set_current_limit)(struct pse_controller_dev *pcdev, + int id, int max_uA); }; struct module; @@ -55,6 +102,40 @@ struct device_node; struct of_phandle_args; struct pse_control; +/* PSE PI pairset pinout can either be Alternative A or Alternative B */ +enum pse_pi_pairset_pinout { + ALTERNATIVE_A, + ALTERNATIVE_B, +}; + +/** + * struct pse_pi_pairset - PSE PI pairset entity describing the pinout + * alternative ant its phandle + * + * @pinout: description of the pinout alternative + * @np: device node pointer describing the pairset phandle + */ +struct pse_pi_pairset { + enum pse_pi_pairset_pinout pinout; + struct device_node *np; +}; + +/** + * struct pse_pi - PSE PI (Power Interface) entity as described in + * IEEE 802.3-2022 145.2.4 + * + * @pairset: table of the PSE PI pinout alternative for the two pairset + * @np: device node pointer of the PSE PI node + * @rdev: regulator represented by the PSE PI + * @admin_state_enabled: PI enabled state + */ +struct pse_pi { + struct pse_pi_pairset pairset[2]; + struct device_node *np; + struct regulator_dev *rdev; + bool admin_state_enabled; +}; + /** * struct pse_controller_dev - PSE controller entity that might * provide multiple PSE controls @@ -64,10 +145,11 @@ struct pse_control; * @pse_control_head: head of internal list of requested PSE controls * @dev: corresponding driver model device struct * @of_pse_n_cells: number of cells in PSE line specifiers - * @of_xlate: translation function to translate from specifier as found in the - * device tree to id as given to the PSE control ops * @nr_lines: number of PSE controls in this controller device * @lock: Mutex for serialization access to the PSE controller + * @types: types of the PSE controller + * @pi: table of PSE PIs described in this controller device + * @no_of_pse_pi: flag set if the pse_pis devicetree node is not used */ struct pse_controller_dev { const struct pse_controller_ops *ops; @@ -76,10 +158,11 @@ struct pse_controller_dev { struct list_head pse_control_head; struct device *dev; int of_pse_n_cells; - int (*of_xlate)(struct pse_controller_dev *pcdev, - const struct of_phandle_args *pse_spec); unsigned int nr_lines; struct mutex lock; + enum ethtool_pse_types types; + struct pse_pi *pi; + bool no_of_pse_pi; }; #if IS_ENABLED(CONFIG_PSE_CONTROLLER) @@ -98,6 +181,14 @@ int pse_ethtool_get_status(struct pse_control *psec, int pse_ethtool_set_config(struct pse_control *psec, struct netlink_ext_ack *extack, const struct pse_control_config *config); +int pse_ethtool_set_pw_limit(struct pse_control *psec, + struct netlink_ext_ack *extack, + const unsigned int pw_limit); +int pse_ethtool_get_pw_limit(struct pse_control *psec, + struct netlink_ext_ack *extack); + +bool pse_has_podl(struct pse_control *psec); +bool pse_has_c33(struct pse_control *psec); #else @@ -114,14 +205,37 @@ static inline int pse_ethtool_get_status(struct pse_control *psec, struct netlink_ext_ack *extack, struct pse_control_status *status) { - return -ENOTSUPP; + return -EOPNOTSUPP; } static inline int pse_ethtool_set_config(struct pse_control *psec, struct netlink_ext_ack *extack, const struct pse_control_config *config) { - return -ENOTSUPP; + return -EOPNOTSUPP; +} + +static inline int pse_ethtool_set_pw_limit(struct pse_control *psec, + struct netlink_ext_ack *extack, + const unsigned int pw_limit) +{ + return -EOPNOTSUPP; +} + +static inline int pse_ethtool_get_pw_limit(struct pse_control *psec, + struct netlink_ext_ack *extack) +{ + return -EOPNOTSUPP; +} + +static inline bool pse_has_podl(struct pse_control *psec) +{ + return false; +} + +static inline bool pse_has_c33(struct pse_control *psec) +{ + return false; } #endif diff --git a/include/linux/psp-platform-access.h b/include/linux/psp-platform-access.h index c1dc87fc536b..1504fb012c05 100644 --- a/include/linux/psp-platform-access.h +++ b/include/linux/psp-platform-access.h @@ -6,8 +6,9 @@ #include <linux/psp.h> enum psp_platform_access_msg { - PSP_CMD_NONE = 0x0, - PSP_I2C_REQ_BUS_CMD = 0x64, + PSP_CMD_NONE = 0x0, + PSP_CMD_HSTI_QUERY = 0x14, + PSP_I2C_REQ_BUS_CMD = 0x64, PSP_DYNAMIC_BOOST_GET_NONCE, PSP_DYNAMIC_BOOST_SET_UID, PSP_DYNAMIC_BOOST_GET_PARAMETER, diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 3705c2044fc0..903ddfea8585 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -658,6 +658,7 @@ struct sev_data_snp_launch_update { * @id_auth_paddr: system physical address of ID block authentication structure * @id_block_en: indicates whether ID block is present * @auth_key_en: indicates whether author key is present in authentication structure + * @vcek_disabled: indicates whether use of VCEK is allowed for attestation reports * @rsvd: reserved * @host_data: host-supplied data for guest, not interpreted by firmware */ @@ -667,7 +668,8 @@ struct sev_data_snp_launch_finish { u64 id_auth_paddr; u8 id_block_en:1; u8 auth_key_en:1; - u64 rsvd:62; + u8 vcek_disabled:1; + u64 rsvd:61; u8 host_data[32]; } __packed; diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index 808f9d3ee546..fd037c127bb0 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -464,11 +464,11 @@ static inline int ptr_ring_consume_batched_bh(struct ptr_ring *r, /* Not all gfp_t flags (besides GFP_KERNEL) are allowed. See * documentation for vmalloc for which of them are legal. */ -static inline void **__ptr_ring_init_queue_alloc(unsigned int size, gfp_t gfp) +static inline void **__ptr_ring_init_queue_alloc_noprof(unsigned int size, gfp_t gfp) { if (size > KMALLOC_MAX_SIZE / sizeof(void *)) return NULL; - return kvmalloc_array(size, sizeof(void *), gfp | __GFP_ZERO); + return kvmalloc_array_noprof(size, sizeof(void *), gfp | __GFP_ZERO); } static inline void __ptr_ring_set_size(struct ptr_ring *r, int size) @@ -484,9 +484,9 @@ static inline void __ptr_ring_set_size(struct ptr_ring *r, int size) r->batch = 1; } -static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp) +static inline int ptr_ring_init_noprof(struct ptr_ring *r, int size, gfp_t gfp) { - r->queue = __ptr_ring_init_queue_alloc(size, gfp); + r->queue = __ptr_ring_init_queue_alloc_noprof(size, gfp); if (!r->queue) return -ENOMEM; @@ -497,6 +497,7 @@ static inline int ptr_ring_init(struct ptr_ring *r, int size, gfp_t gfp) return 0; } +#define ptr_ring_init(...) alloc_hooks(ptr_ring_init_noprof(__VA_ARGS__)) /* * Return entries into ring. Destroy entries that don't fit. @@ -587,11 +588,11 @@ static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue, * In particular if you consume ring in interrupt or BH context, you must * disable interrupts/BH when doing so. */ -static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, +static inline int ptr_ring_resize_noprof(struct ptr_ring *r, int size, gfp_t gfp, void (*destroy)(void *)) { unsigned long flags; - void **queue = __ptr_ring_init_queue_alloc(size, gfp); + void **queue = __ptr_ring_init_queue_alloc_noprof(size, gfp); void **old; if (!queue) @@ -609,6 +610,7 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, return 0; } +#define ptr_ring_resize(...) alloc_hooks(ptr_ring_resize_noprof(__VA_ARGS__)) /* * Note: producer lock is nested within consumer lock, so if you @@ -616,21 +618,21 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, * In particular if you consume ring in interrupt or BH context, you must * disable interrupts/BH when doing so. */ -static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, - unsigned int nrings, - int size, - gfp_t gfp, void (*destroy)(void *)) +static inline int ptr_ring_resize_multiple_noprof(struct ptr_ring **rings, + unsigned int nrings, + int size, + gfp_t gfp, void (*destroy)(void *)) { unsigned long flags; void ***queues; int i; - queues = kmalloc_array(nrings, sizeof(*queues), gfp); + queues = kmalloc_array_noprof(nrings, sizeof(*queues), gfp); if (!queues) goto noqueues; for (i = 0; i < nrings; ++i) { - queues[i] = __ptr_ring_init_queue_alloc(size, gfp); + queues[i] = __ptr_ring_init_queue_alloc_noprof(size, gfp); if (!queues[i]) goto nomem; } @@ -660,6 +662,8 @@ nomem: noqueues: return -ENOMEM; } +#define ptr_ring_resize_multiple(...) \ + alloc_hooks(ptr_ring_resize_multiple_noprof(__VA_ARGS__)) static inline void ptr_ring_cleanup(struct ptr_ring *r, void (*destroy)(void *)) { diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 4a6568dfdf3f..f8c2dc12dbd3 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -2,10 +2,14 @@ #ifndef __LINUX_PWM_H #define __LINUX_PWM_H +#include <linux/device.h> #include <linux/err.h> +#include <linux/module.h> #include <linux/mutex.h> #include <linux/of.h> +MODULE_IMPORT_NS(PWM); + struct pwm_chip; /** @@ -248,9 +252,7 @@ struct pwm_capture { * @free: optional hook for freeing a PWM * @capture: capture and report PWM signal * @apply: atomically apply a new PWM config - * @get_state: get the current PWM state. This function is only - * called once per PWM device when the PWM chip is - * registered. + * @get_state: get the current PWM state. */ struct pwm_ops { int (*request)(struct pwm_chip *chip, struct pwm_device *pwm); @@ -272,11 +274,11 @@ struct pwm_ops { * @npwm: number of PWMs controlled by this chip * @of_xlate: request a PWM device given a device tree PWM specifier * @atomic: can the driver's ->apply() be called in atomic context - * @driver_data: Private pointer for driver specific info + * @uses_pwmchip_alloc: signals if pwmchip_allow was used to allocate this chip * @pwms: array of PWM devices allocated by the framework */ struct pwm_chip { - struct device *dev; + struct device dev; const struct pwm_ops *ops; struct module *owner; unsigned int id; @@ -287,31 +289,23 @@ struct pwm_chip { bool atomic; /* only used internally by the PWM framework */ - void *driver_data; - struct pwm_device *pwms; + bool uses_pwmchip_alloc; + struct pwm_device pwms[] __counted_by(npwm); }; static inline struct device *pwmchip_parent(const struct pwm_chip *chip) { - return chip->dev; + return chip->dev.parent; } static inline void *pwmchip_get_drvdata(struct pwm_chip *chip) { - /* - * After pwm_chip got a dedicated struct device, this can be replaced by - * dev_get_drvdata(&chip->dev); - */ - return chip->driver_data; + return dev_get_drvdata(&chip->dev); } static inline void pwmchip_set_drvdata(struct pwm_chip *chip, void *data) { - /* - * After pwm_chip got a dedicated struct device, this can be replaced by - * dev_set_drvdata(&chip->dev, data); - */ - chip->driver_data = data; + dev_set_drvdata(&chip->dev, data); } #if IS_ENABLED(CONFIG_PWM) @@ -414,10 +408,6 @@ void pwmchip_remove(struct pwm_chip *chip); int __devm_pwmchip_add(struct device *dev, struct pwm_chip *chip, struct module *owner); #define devm_pwmchip_add(dev, chip) __devm_pwmchip_add(dev, chip, THIS_MODULE) -struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip, - unsigned int index, - const char *label); - struct pwm_device *of_pwm_xlate_with_flags(struct pwm_chip *chip, const struct of_phandle_args *args); struct pwm_device *of_pwm_single_xlate(struct pwm_chip *chip, @@ -512,14 +502,6 @@ static inline int devm_pwmchip_add(struct device *dev, struct pwm_chip *chip) return -EINVAL; } -static inline struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip, - unsigned int index, - const char *label) -{ - might_sleep(); - return ERR_PTR(-ENODEV); -} - static inline struct pwm_device *pwm_get(struct device *dev, const char *consumer) { @@ -581,13 +563,6 @@ static inline void pwm_apply_args(struct pwm_device *pwm) pwm_apply_might_sleep(pwm, &state); } -/* only for backwards-compatibility, new code should not use this */ -static inline int pwm_apply_state(struct pwm_device *pwm, - const struct pwm_state *state) -{ - return pwm_apply_might_sleep(pwm, state); -} - struct pwm_lookup { struct list_head list; const char *provider; @@ -628,17 +603,4 @@ static inline void pwm_remove_table(struct pwm_lookup *table, size_t num) } #endif -#ifdef CONFIG_PWM_SYSFS -void pwmchip_sysfs_export(struct pwm_chip *chip); -void pwmchip_sysfs_unexport(struct pwm_chip *chip); -#else -static inline void pwmchip_sysfs_export(struct pwm_chip *chip) -{ -} - -static inline void pwmchip_sysfs_unexport(struct pwm_chip *chip) -{ -} -#endif /* CONFIG_PWM_SYSFS */ - #endif /* __LINUX_PWM_H */ diff --git a/include/linux/pwm_backlight.h b/include/linux/pwm_backlight.h index cdd2ac366bc7..0bf80e98d5b4 100644 --- a/include/linux/pwm_backlight.h +++ b/include/linux/pwm_backlight.h @@ -19,7 +19,6 @@ struct platform_pwm_backlight_data { int (*notify)(struct device *dev, int brightness); void (*notify_after)(struct device *dev, int brightness); void (*exit)(struct device *dev); - int (*check_fb)(struct device *dev, struct fb_info *info); }; #endif diff --git a/include/linux/pwrseq/consumer.h b/include/linux/pwrseq/consumer.h new file mode 100644 index 000000000000..7d583b4f266e --- /dev/null +++ b/include/linux/pwrseq/consumer.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2024 Linaro Ltd. + */ + +#ifndef __POWER_SEQUENCING_CONSUMER_H__ +#define __POWER_SEQUENCING_CONSUMER_H__ + +#include <linux/err.h> + +struct device; +struct pwrseq_desc; + +#if IS_ENABLED(CONFIG_POWER_SEQUENCING) + +struct pwrseq_desc * __must_check +pwrseq_get(struct device *dev, const char *target); +void pwrseq_put(struct pwrseq_desc *desc); + +struct pwrseq_desc * __must_check +devm_pwrseq_get(struct device *dev, const char *target); + +int pwrseq_power_on(struct pwrseq_desc *desc); +int pwrseq_power_off(struct pwrseq_desc *desc); + +#else /* CONFIG_POWER_SEQUENCING */ + +static inline struct pwrseq_desc * __must_check +pwrseq_get(struct device *dev, const char *target) +{ + return ERR_PTR(-ENOSYS); +} + +static inline void pwrseq_put(struct pwrseq_desc *desc) +{ +} + +static inline struct pwrseq_desc * __must_check +devm_pwrseq_get(struct device *dev, const char *target) +{ + return ERR_PTR(-ENOSYS); +} + +static inline int pwrseq_power_on(struct pwrseq_desc *desc) +{ + return -ENOSYS; +} + +static inline int pwrseq_power_off(struct pwrseq_desc *desc) +{ + return -ENOSYS; +} + +#endif /* CONFIG_POWER_SEQUENCING */ + +#endif /* __POWER_SEQUENCING_CONSUMER_H__ */ diff --git a/include/linux/pwrseq/provider.h b/include/linux/pwrseq/provider.h new file mode 100644 index 000000000000..cbc3607cbfcf --- /dev/null +++ b/include/linux/pwrseq/provider.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2024 Linaro Ltd. + */ + +#ifndef __POWER_SEQUENCING_PROVIDER_H__ +#define __POWER_SEQUENCING_PROVIDER_H__ + +struct device; +struct module; +struct pwrseq_device; + +typedef int (*pwrseq_power_state_func)(struct pwrseq_device *); +typedef int (*pwrseq_match_func)(struct pwrseq_device *, struct device *); + +/** + * struct pwrseq_unit_data - Configuration of a single power sequencing + * unit. + * @name: Name of the unit. + * @deps: Units that must be enabled before this one and disabled after it + * in the order they come in this array. Must be NULL-terminated. + * @enable: Callback running the part of the power-on sequence provided by + * this unit. + * @disable: Callback running the part of the power-off sequence provided + * by this unit. + */ +struct pwrseq_unit_data { + const char *name; + const struct pwrseq_unit_data **deps; + pwrseq_power_state_func enable; + pwrseq_power_state_func disable; +}; + +/** + * struct pwrseq_target_data - Configuration of a power sequencing target. + * @name: Name of the target. + * @unit: Final unit that this target must reach in order to be considered + * enabled. + * @post_enable: Callback run after the target unit has been enabled, *after* + * the state lock has been released. It's useful for implementing + * boot-up delays without blocking other users from powering up + * using the same power sequencer. + */ +struct pwrseq_target_data { + const char *name; + const struct pwrseq_unit_data *unit; + pwrseq_power_state_func post_enable; +}; + +/** + * struct pwrseq_config - Configuration used for registering a new provider. + * @parent: Parent device for the sequencer. Must be set. + * @owner: Module providing this device. + * @drvdata: Private driver data. + * @match: Provider callback used to match the consumer device to the sequencer. + * @targets: Array of targets for this power sequencer. Must be NULL-terminated. + */ +struct pwrseq_config { + struct device *parent; + struct module *owner; + void *drvdata; + pwrseq_match_func match; + const struct pwrseq_target_data **targets; +}; + +struct pwrseq_device * +pwrseq_device_register(const struct pwrseq_config *config); +void pwrseq_device_unregister(struct pwrseq_device *pwrseq); +struct pwrseq_device * +devm_pwrseq_device_register(struct device *dev, + const struct pwrseq_config *config); + +void *pwrseq_device_get_drvdata(struct pwrseq_device *pwrseq); + +#endif /* __POWER_SEQUENCING_PROVIDER_H__ */ diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index cd1973e6ac4b..844a2743ca94 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -217,9 +217,9 @@ enum pxa_ssp_type { PXA27x_SSP, PXA3xx_SSP, PXA168_SSP, - MMP2_SSP, PXA910_SSP, CE4100_SSP, + MMP2_SSP, MRFLD_SSP, QUARK_X1000_SSP, /* Keep LPSS types sorted with lpss_platforms[] */ diff --git a/include/linux/qat/qat_mig_dev.h b/include/linux/qat/qat_mig_dev.h new file mode 100644 index 000000000000..dbbb6a063dd2 --- /dev/null +++ b/include/linux/qat/qat_mig_dev.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright(c) 2024 Intel Corporation */ +#ifndef QAT_MIG_DEV_H_ +#define QAT_MIG_DEV_H_ + +struct pci_dev; + +struct qat_mig_dev { + void *parent_accel_dev; + u8 *state; + u32 setup_size; + u32 remote_setup_size; + u32 state_size; + s32 vf_id; +}; + +struct qat_mig_dev *qat_vfmig_create(struct pci_dev *pdev, int vf_id); +int qat_vfmig_init(struct qat_mig_dev *mdev); +void qat_vfmig_cleanup(struct qat_mig_dev *mdev); +void qat_vfmig_reset(struct qat_mig_dev *mdev); +int qat_vfmig_open(struct qat_mig_dev *mdev); +void qat_vfmig_close(struct qat_mig_dev *mdev); +int qat_vfmig_suspend(struct qat_mig_dev *mdev); +int qat_vfmig_resume(struct qat_mig_dev *mdev); +int qat_vfmig_save_state(struct qat_mig_dev *mdev); +int qat_vfmig_save_setup(struct qat_mig_dev *mdev); +int qat_vfmig_load_state(struct qat_mig_dev *mdev); +int qat_vfmig_load_setup(struct qat_mig_dev *mdev, int size); +void qat_vfmig_destroy(struct qat_mig_dev *mdev); + +#endif /*QAT_MIG_DEV_H_*/ diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h index 6d92b68efbf6..1d982dbdd0d0 100644 --- a/include/linux/randomize_kstack.h +++ b/include/linux/randomize_kstack.h @@ -32,13 +32,19 @@ DECLARE_PER_CPU(u32, kstack_offset); #endif /* - * Use, at most, 10 bits of entropy. We explicitly cap this to keep the - * "VLA" from being unbounded (see above). 10 bits leaves enough room for - * per-arch offset masks to reduce entropy (by removing higher bits, since - * high entropy may overly constrain usable stack space), and for - * compiler/arch-specific stack alignment to remove the lower bits. + * Use, at most, 6 bits of entropy (on 64-bit; 8 on 32-bit). This cap is + * to keep the "VLA" from being unbounded (see above). Additionally clear + * the bottom 4 bits (on 64-bit systems, 2 for 32-bit), since stack + * alignment will always be at least word size. This makes the compiler + * code gen better when it is applying the actual per-arch alignment to + * the final offset. The resulting randomness is reasonable without overly + * constraining usable stack space. */ -#define KSTACK_OFFSET_MAX(x) ((x) & 0x3FF) +#ifdef CONFIG_64BIT +#define KSTACK_OFFSET_MAX(x) ((x) & 0b1111110000) +#else +#define KSTACK_OFFSET_MAX(x) ((x) & 0b1111111100) +#endif /** * add_random_kstack_offset - Increase stack utilization by previously diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h index 659d13a7ddaa..ba95c06675e1 100644 --- a/include/linux/rcu_segcblist.h +++ b/include/linux/rcu_segcblist.h @@ -80,36 +80,35 @@ struct rcu_cblist { * | SEGCBLIST_RCU_CORE | SEGCBLIST_LOCKING | SEGCBLIST_OFFLOADED | * | | * | Callbacks processed by rcu_core() from softirqs or local | - * | rcuc kthread, while holding nocb_lock. Waking up CB and GP kthreads, | - * | allowing nocb_timer to be armed. | + * | rcuc kthread, while holding nocb_lock. Waking up CB and GP kthreads. | * ---------------------------------------------------------------------------- * | * v - * ----------------------------------- - * | | - * v v - * --------------------------------------- ----------------------------------| - * | SEGCBLIST_RCU_CORE | | | SEGCBLIST_RCU_CORE | | - * | SEGCBLIST_LOCKING | | | SEGCBLIST_LOCKING | | - * | SEGCBLIST_OFFLOADED | | | SEGCBLIST_OFFLOADED | | - * | SEGCBLIST_KTHREAD_CB | | SEGCBLIST_KTHREAD_GP | - * | | | | - * | | | | - * | CB kthread woke up and | | GP kthread woke up and | - * | acknowledged SEGCBLIST_OFFLOADED. | | acknowledged SEGCBLIST_OFFLOADED| - * | Processes callbacks concurrently | | | - * | with rcu_core(), holding | | | - * | nocb_lock. | | | - * --------------------------------------- ----------------------------------- - * | | - * ----------------------------------- + * ---------------------------------------------------------------------------- + * | SEGCBLIST_RCU_CORE | SEGCBLIST_LOCKING | SEGCBLIST_OFFLOADED | + * | + unparked CB kthread | + * | | + * | CB kthread got unparked and processes callbacks concurrently with | + * | rcu_core(), holding nocb_lock. | + * --------------------------------------------------------------------------- + * | + * v + * ---------------------------------------------------------------------------| + * | SEGCBLIST_RCU_CORE | | + * | SEGCBLIST_LOCKING | | + * | SEGCBLIST_OFFLOADED | | + * | SEGCBLIST_KTHREAD_GP | + * | + unparked CB kthread | + * | | + * | GP kthread woke up and acknowledged nocb_lock. | + * ---------------------------------------- ----------------------------------- * | * v * |--------------------------------------------------------------------------| - * | SEGCBLIST_LOCKING | | - * | SEGCBLIST_OFFLOADED | | + * | SEGCBLIST_LOCKING | | + * | SEGCBLIST_OFFLOADED | | * | SEGCBLIST_KTHREAD_GP | | - * | SEGCBLIST_KTHREAD_CB | + * | + unparked CB kthread | * | | * | Kthreads handle callbacks holding nocb_lock, local rcu_core() stops | * | handling callbacks. Enable bypass queueing. | @@ -125,8 +124,8 @@ struct rcu_cblist { * |--------------------------------------------------------------------------| * | SEGCBLIST_LOCKING | | * | SEGCBLIST_OFFLOADED | | - * | SEGCBLIST_KTHREAD_CB | | * | SEGCBLIST_KTHREAD_GP | + * | + unparked CB kthread | * | | * | CB/GP kthreads handle callbacks holding nocb_lock, local rcu_core() | * | ignores callbacks. Bypass enqueue is enabled. | @@ -137,11 +136,11 @@ struct rcu_cblist { * | SEGCBLIST_RCU_CORE | | * | SEGCBLIST_LOCKING | | * | SEGCBLIST_OFFLOADED | | - * | SEGCBLIST_KTHREAD_CB | | * | SEGCBLIST_KTHREAD_GP | + * | + unparked CB kthread | * | | * | CB/GP kthreads handle callbacks holding nocb_lock, local rcu_core() | - * | handles callbacks concurrently. Bypass enqueue is enabled. | + * | handles callbacks concurrently. Bypass enqueue is disabled. | * | Invoke RCU core so we make sure not to preempt it in the middle with | * | leaving some urgent work unattended within a jiffy. | * ---------------------------------------------------------------------------- @@ -150,42 +149,31 @@ struct rcu_cblist { * |--------------------------------------------------------------------------| * | SEGCBLIST_RCU_CORE | | * | SEGCBLIST_LOCKING | | - * | SEGCBLIST_KTHREAD_CB | | * | SEGCBLIST_KTHREAD_GP | + * | + unparked CB kthread | * | | * | CB/GP kthreads and local rcu_core() handle callbacks concurrently | - * | holding nocb_lock. Wake up CB and GP kthreads if necessary. Disable | - * | bypass enqueue. | + * | holding nocb_lock. Wake up GP kthread if necessary. | * ---------------------------------------------------------------------------- * | * v - * ----------------------------------- - * | | - * v v - * ---------------------------------------------------------------------------| - * | | | - * | SEGCBLIST_RCU_CORE | | SEGCBLIST_RCU_CORE | | - * | SEGCBLIST_LOCKING | | SEGCBLIST_LOCKING | | - * | SEGCBLIST_KTHREAD_CB | SEGCBLIST_KTHREAD_GP | - * | | | - * | GP kthread woke up and | CB kthread woke up and | - * | acknowledged the fact that | acknowledged the fact that | - * | SEGCBLIST_OFFLOADED got cleared. | SEGCBLIST_OFFLOADED got cleared. | - * | | The CB kthread goes to sleep | - * | The callbacks from the target CPU | until it ever gets re-offloaded. | - * | will be ignored from the GP kthread | | - * | loop. | | + * |--------------------------------------------------------------------------| + * | SEGCBLIST_RCU_CORE | | + * | SEGCBLIST_LOCKING | | + * | + unparked CB kthread | + * | | + * | GP kthread woke up and acknowledged the fact that SEGCBLIST_OFFLOADED | + * | got cleared. The callbacks from the target CPU will be ignored from the| + * | GP kthread loop. | * ---------------------------------------------------------------------------- - * | | - * ----------------------------------- * | * v * ---------------------------------------------------------------------------- * | SEGCBLIST_RCU_CORE | SEGCBLIST_LOCKING | + * | + parked CB kthread | * | | - * | Callbacks processed by rcu_core() from softirqs or local | - * | rcuc kthread, while holding nocb_lock. Forbid nocb_timer to be armed. | - * | Flush pending nocb_timer. Flush nocb bypass callbacks. | + * | CB kthread is parked. Callbacks processed by rcu_core() from softirqs or | + * | local rcuc kthread, while holding nocb_lock. | * ---------------------------------------------------------------------------- * | * v diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 17d7ed5f3ae6..13f6f00aecf9 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -29,7 +29,6 @@ #include <linux/lockdep.h> #include <linux/cleanup.h> #include <asm/processor.h> -#include <linux/cpumask.h> #include <linux/context_tracking_irq.h> #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) @@ -209,7 +208,6 @@ void synchronize_rcu_tasks_rude(void); #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false) void exit_tasks_rcu_start(void); -void exit_tasks_rcu_stop(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ #define rcu_tasks_classic_qs(t, preempt) do { } while (0) @@ -218,7 +216,6 @@ void exit_tasks_rcu_finish(void); #define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu static inline void exit_tasks_rcu_start(void) { } -static inline void exit_tasks_rcu_stop(void) { } static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ @@ -401,15 +398,15 @@ static inline int debug_lockdep_rcu_enabled(void) } \ } while (0) -#if defined(CONFIG_PROVE_RCU) && !defined(CONFIG_PREEMPT_RCU) +#ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map), "Illegal context switch in RCU read-side critical section"); } -#else /* #ifdef CONFIG_PROVE_RCU */ +#else // #ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { } -#endif /* #else #ifdef CONFIG_PROVE_RCU */ +#endif // #else // #ifndef CONFIG_PREEMPT_RCU #define rcu_sleep_check() \ do { \ @@ -421,11 +418,71 @@ static inline void rcu_preempt_sleep_check(void) { } "Illegal context switch in RCU-sched read-side critical section"); \ } while (0) +// See RCU_LOCKDEP_WARN() for an explanation of the double call to +// debug_lockdep_rcu_enabled(). +static inline bool lockdep_assert_rcu_helper(bool c) +{ + return debug_lockdep_rcu_enabled() && + (c || !rcu_is_watching() || !rcu_lockdep_current_cpu_online()) && + debug_lockdep_rcu_enabled(); +} + +/** + * lockdep_assert_in_rcu_read_lock - WARN if not protected by rcu_read_lock() + * + * Splats if lockdep is enabled and there is no rcu_read_lock() in effect. + */ +#define lockdep_assert_in_rcu_read_lock() \ + WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_lock_map))) + +/** + * lockdep_assert_in_rcu_read_lock_bh - WARN if not protected by rcu_read_lock_bh() + * + * Splats if lockdep is enabled and there is no rcu_read_lock_bh() in effect. + * Note that local_bh_disable() and friends do not suffice here, instead an + * actual rcu_read_lock_bh() is required. + */ +#define lockdep_assert_in_rcu_read_lock_bh() \ + WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_bh_lock_map))) + +/** + * lockdep_assert_in_rcu_read_lock_sched - WARN if not protected by rcu_read_lock_sched() + * + * Splats if lockdep is enabled and there is no rcu_read_lock_sched() + * in effect. Note that preempt_disable() and friends do not suffice here, + * instead an actual rcu_read_lock_sched() is required. + */ +#define lockdep_assert_in_rcu_read_lock_sched() \ + WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_sched_lock_map))) + +/** + * lockdep_assert_in_rcu_reader - WARN if not within some type of RCU reader + * + * Splats if lockdep is enabled and there is no RCU reader of any + * type in effect. Note that regions of code protected by things like + * preempt_disable, local_bh_disable(), and local_irq_disable() all qualify + * as RCU readers. + * + * Note that this will never trigger in PREEMPT_NONE or PREEMPT_VOLUNTARY + * kernels that are not also built with PREEMPT_COUNT. But if you have + * lockdep enabled, you might as well also enable PREEMPT_COUNT. + */ +#define lockdep_assert_in_rcu_reader() \ + WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_lock_map) && \ + !lock_is_held(&rcu_bh_lock_map) && \ + !lock_is_held(&rcu_sched_lock_map) && \ + preemptible())) + #else /* #ifdef CONFIG_PROVE_RCU */ #define RCU_LOCKDEP_WARN(c, s) do { } while (0 && (c)) #define rcu_sleep_check() do { } while (0) +#define lockdep_assert_in_rcu_read_lock() do { } while (0) +#define lockdep_assert_in_rcu_read_lock_bh() do { } while (0) +#define lockdep_assert_in_rcu_read_lock_sched() do { } while (0) +#define lockdep_assert_in_rcu_reader() do { } while (0) + #endif /* #else #ifdef CONFIG_PROVE_RCU */ /* @@ -809,9 +866,9 @@ static inline void rcu_read_unlock(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock() used illegally while idle"); + rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ __release(RCU); __rcu_read_unlock(); - rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ } /** @@ -1090,6 +1147,18 @@ rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) extern int rcu_expedited; extern int rcu_normal; -DEFINE_LOCK_GUARD_0(rcu, rcu_read_lock(), rcu_read_unlock()) +DEFINE_LOCK_GUARD_0(rcu, + do { + rcu_read_lock(); + /* + * sparse doesn't call the cleanup function, + * so just release immediately and don't track + * the context. We don't need to anyway, since + * the whole point of the guard is to not need + * the explicit unlock. + */ + __release(RCU); + } while (0), + rcu_read_unlock()) #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h index d07f0848802e..303ab9bee155 100644 --- a/include/linux/rcupdate_wait.h +++ b/include/linux/rcupdate_wait.h @@ -19,18 +19,18 @@ struct rcu_synchronize { }; void wakeme_after_rcu(struct rcu_head *head); -void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, +void __wait_rcu_gp(bool checktiny, unsigned int state, int n, call_rcu_func_t *crcu_array, struct rcu_synchronize *rs_array); -#define _wait_rcu_gp(checktiny, ...) \ -do { \ - call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \ - struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)]; \ - __wait_rcu_gp(checktiny, ARRAY_SIZE(__crcu_array), \ - __crcu_array, __rs_array); \ +#define _wait_rcu_gp(checktiny, state, ...) \ +do { \ + call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \ + struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)]; \ + __wait_rcu_gp(checktiny, state, ARRAY_SIZE(__crcu_array), __crcu_array, __rs_array); \ } while (0) -#define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__) +#define wait_rcu_gp(...) _wait_rcu_gp(false, TASK_UNINTERRUPTIBLE, __VA_ARGS__) +#define wait_rcu_gp_state(state, ...) _wait_rcu_gp(false, state, __VA_ARGS__) /** * synchronize_rcu_mult - Wait concurrently for multiple grace periods @@ -54,7 +54,7 @@ do { \ * grace period. */ #define synchronize_rcu_mult(...) \ - _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__) + _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), TASK_UNINTERRUPTIBLE, __VA_ARGS__) static inline void cond_resched_rcu(void) { diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 59b3b752394d..35f039ecb272 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -266,12 +266,12 @@ bool __refcount_sub_and_test(int i, refcount_t *r, int *oldp) if (oldp) *oldp = old; - if (old == i) { + if (old > 0 && old == i) { smp_acquire__after_ctrl_dep(); return true; } - if (unlikely(old < 0 || old - i < 0)) + if (unlikely(old <= 0 || old - i < 0)) refcount_warn_saturate(r, REFCOUNT_SUB_UAF); return false; diff --git a/include/linux/regmap.h b/include/linux/regmap.h index d470303b1bbb..122e38161acb 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -297,15 +297,6 @@ typedef void (*regmap_unlock)(void *); * performed on such table (a register is no increment * readable if it belongs to one of the ranges specified * by rd_noinc_table). - * @disable_locking: This regmap is either protected by external means or - * is guaranteed not to be accessed from multiple threads. - * Don't use any locking mechanisms. - * @lock: Optional lock callback (overrides regmap's default lock - * function, based on spinlock or mutex). - * @unlock: As above for unlocking. - * @lock_arg: this field is passed as the only argument of lock/unlock - * functions (ignored in case regular lock/unlock functions - * are not overridden). * @reg_read: Optional callback that if filled will be used to perform * all the reads from the registers. Should only be provided for * devices whose read operation cannot be represented as a simple @@ -323,6 +314,7 @@ typedef void (*regmap_unlock)(void *); * @write: Same as above for writing. * @max_raw_read: Max raw read size that can be used on the device. * @max_raw_write: Max raw write size that can be used on the device. + * @can_sleep: Optional, specifies whether regmap operations can sleep. * @fast_io: Register IO is fast. Use a spinlock instead of a mutex * to perform locking. This field is ignored if custom lock/unlock * functions are used (see fields lock/unlock of struct regmap_config). @@ -331,6 +323,15 @@ typedef void (*regmap_unlock)(void *); * Use it only for "no-bus" cases. * @io_port: Support IO port accessors. Makes sense only when MMIO vs. IO port * access can be distinguished. + * @disable_locking: This regmap is either protected by external means or + * is guaranteed not to be accessed from multiple threads. + * Don't use any locking mechanisms. + * @lock: Optional lock callback (overrides regmap's default lock + * function, based on spinlock or mutex). + * @unlock: As above for unlocking. + * @lock_arg: This field is passed as the only argument of lock/unlock + * functions (ignored in case regular lock/unlock functions + * are not overridden). * @max_register: Optional, specifies the maximum valid register address. * @max_register_is_0: Optional, specifies that zero value in @max_register * should be taken into account. This is a workaround to @@ -373,21 +374,20 @@ typedef void (*regmap_unlock)(void *); * @reg_defaults_raw: Power on reset values for registers (for use with * register cache support). * @num_reg_defaults_raw: Number of elements in reg_defaults_raw. - * @reg_format_endian: Endianness for formatted register addresses. If this is - * DEFAULT, the @reg_format_endian_default value from the - * regmap bus is used. - * @val_format_endian: Endianness for formatted register values. If this is - * DEFAULT, the @reg_format_endian_default value from the - * regmap bus is used. - * - * @ranges: Array of configuration entries for virtual address ranges. - * @num_ranges: Number of range configuration entries. * @use_hwlock: Indicate if a hardware spinlock should be used. * @use_raw_spinlock: Indicate if a raw spinlock should be used. * @hwlock_id: Specify the hardware spinlock id. * @hwlock_mode: The hardware spinlock mode, should be HWLOCK_IRQSTATE, * HWLOCK_IRQ or 0. - * @can_sleep: Optional, specifies whether regmap operations can sleep. + * @reg_format_endian: Endianness for formatted register addresses. If this is + * DEFAULT, the @reg_format_endian_default value from the + * regmap bus is used. + * @val_format_endian: Endianness for formatted register values. If this is + * DEFAULT, the @reg_format_endian_default value from the + * regmap bus is used. + * + * @ranges: Array of configuration entries for virtual address ranges. + * @num_ranges: Number of range configuration entries. */ struct regmap_config { const char *name; @@ -406,11 +406,6 @@ struct regmap_config { bool (*writeable_noinc_reg)(struct device *dev, unsigned int reg); bool (*readable_noinc_reg)(struct device *dev, unsigned int reg); - bool disable_locking; - regmap_lock lock; - regmap_unlock unlock; - void *lock_arg; - int (*reg_read)(void *context, unsigned int reg, unsigned int *val); int (*reg_write)(void *context, unsigned int reg, unsigned int val); int (*reg_update_bits)(void *context, unsigned int reg, @@ -422,9 +417,16 @@ struct regmap_config { size_t max_raw_read; size_t max_raw_write; + bool can_sleep; + bool fast_io; bool io_port; + bool disable_locking; + regmap_lock lock; + regmap_unlock unlock; + void *lock_arg; + unsigned int max_register; bool max_register_is_0; const struct regmap_access_table *wr_table; @@ -448,18 +450,16 @@ struct regmap_config { bool use_relaxed_mmio; bool can_multi_write; - enum regmap_endian reg_format_endian; - enum regmap_endian val_format_endian; - - const struct regmap_range_cfg *ranges; - unsigned int num_ranges; - bool use_hwlock; bool use_raw_spinlock; unsigned int hwlock_id; unsigned int hwlock_mode; - bool can_sleep; + enum regmap_endian reg_format_endian; + enum regmap_endian val_format_endian; + + const struct regmap_range_cfg *ranges; + unsigned int num_ranges; }; /** @@ -1237,6 +1237,8 @@ int regmap_noinc_read(struct regmap *map, unsigned int reg, void *val, size_t val_len); int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val, size_t val_count); +int regmap_multi_reg_read(struct regmap *map, unsigned int *reg, void *val, + size_t val_count); int regmap_update_bits_base(struct regmap *map, unsigned int reg, unsigned int mask, unsigned int val, bool *change, bool async, bool force); @@ -1607,7 +1609,7 @@ struct regmap_irq_chip { unsigned int main_status; unsigned int num_main_status_bits; - struct regmap_irq_sub_irq_map *sub_reg_offsets; + const struct regmap_irq_sub_irq_map *sub_reg_offsets; int num_main_regs; unsigned int status_base; diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index ed180ca419da..d986ec13092e 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -128,11 +128,11 @@ struct regulator; * * @supply: The name of the supply. Initialised by the user before * using the bulk regulator APIs. + * @consumer: The regulator consumer for the supply. This will be managed + * by the bulk API. * @init_load_uA: After getting the regulator, regulator_set_load() will be * called with this load. Initialised by the user before * using the bulk regulator APIs. - * @consumer: The regulator consumer for the supply. This will be managed - * by the bulk API. * * The regulator APIs provide a series of regulator_bulk_() API calls as * a convenience to consumers which require multiple supplies. This @@ -140,8 +140,8 @@ struct regulator; */ struct regulator_bulk_data { const char *supply; - int init_load_uA; struct regulator *consumer; + int init_load_uA; /* private: Internal use */ int ret; @@ -164,6 +164,7 @@ struct regulator *__must_check devm_regulator_get_optional(struct device *dev, const char *id); int devm_regulator_get_enable(struct device *dev, const char *id); int devm_regulator_get_enable_optional(struct device *dev, const char *id); +int devm_regulator_get_enable_read_voltage(struct device *dev, const char *id); void regulator_put(struct regulator *regulator); void devm_regulator_put(struct regulator *regulator); @@ -249,6 +250,7 @@ int regulator_get_hardware_vsel_register(struct regulator *regulator, unsigned *vsel_mask); int regulator_list_hardware_vsel(struct regulator *regulator, unsigned selector); +int regulator_hardware_enable(struct regulator *regulator, bool enable); /* regulator notifier block */ int regulator_register_notifier(struct regulator *regulator, @@ -329,6 +331,12 @@ static inline int devm_regulator_get_enable_optional(struct device *dev, return 0; } +static inline int devm_regulator_get_enable_read_voltage(struct device *dev, + const char *id) +{ + return -ENODEV; +} + static inline struct regulator *__must_check regulator_get_optional(struct device *dev, const char *id) { @@ -564,6 +572,12 @@ static inline int regulator_list_hardware_vsel(struct regulator *regulator, return -EOPNOTSUPP; } +static inline int regulator_hardware_enable(struct regulator *regulator, + bool enable) +{ + return -EOPNOTSUPP; +} + static inline int regulator_register_notifier(struct regulator *regulator, struct notifier_block *nb) { diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 22a07c0900a4..f230a472ccd3 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -299,6 +299,8 @@ enum regulator_type { * @vsel_range_reg: Register for range selector when using pickable ranges * and ``regulator_map_*_voltage_*_pickable`` functions. * @vsel_range_mask: Mask for register bitfield used for range selector + * @range_applied_by_vsel: A flag to indicate that changes to vsel_range_reg + * are only effective after vsel_reg is written * @vsel_reg: Register for selector when using ``regulator_map_*_voltage_*`` * @vsel_mask: Mask for register bitfield used for selector * @vsel_step: Specify the resolution of selector stepping when setting @@ -389,6 +391,7 @@ struct regulator_desc { unsigned int vsel_range_reg; unsigned int vsel_range_mask; + bool range_applied_by_vsel; unsigned int vsel_reg; unsigned int vsel_mask; unsigned int vsel_step; diff --git a/include/linux/regulator/pca9450.h b/include/linux/regulator/pca9450.h index 505c908dbb81..243633c8dceb 100644 --- a/include/linux/regulator/pca9450.h +++ b/include/linux/regulator/pca9450.h @@ -9,6 +9,7 @@ enum pca9450_chip_type { PCA9450_TYPE_PCA9450A = 0, PCA9450_TYPE_PCA9450BC, + PCA9450_TYPE_PCA9451A, PCA9450_TYPE_AMOUNT, }; diff --git a/include/linux/remoteproc/mtk_scp.h b/include/linux/remoteproc/mtk_scp.h index 7c2b7cc9fe6c..344ff41c22c7 100644 --- a/include/linux/remoteproc/mtk_scp.h +++ b/include/linux/remoteproc/mtk_scp.h @@ -43,6 +43,7 @@ enum scp_ipi_id { SCP_IPI_CROS_HOST_CMD, SCP_IPI_VDEC_LAT, SCP_IPI_VDEC_CORE, + SCP_IPI_IMGSYS_CMD, SCP_IPI_NS_SERVICE = 0xFF, SCP_IPI_MAX = 0x100, }; diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index a365f67131ec..b0875b99e811 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -2,6 +2,7 @@ #ifndef _RESCTRL_H #define _RESCTRL_H +#include <linux/cacheinfo.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/pid.h> @@ -58,11 +59,45 @@ struct resctrl_staged_config { bool have_new_ctrl; }; +enum resctrl_domain_type { + RESCTRL_CTRL_DOMAIN, + RESCTRL_MON_DOMAIN, +}; + /** - * struct rdt_domain - group of CPUs sharing a resctrl resource + * struct rdt_domain_hdr - common header for different domain types * @list: all instances of this resource * @id: unique id for this instance + * @type: type of this instance * @cpu_mask: which CPUs share this resource + */ +struct rdt_domain_hdr { + struct list_head list; + int id; + enum resctrl_domain_type type; + struct cpumask cpu_mask; +}; + +/** + * struct rdt_ctrl_domain - group of CPUs sharing a resctrl control resource + * @hdr: common header for different domain types + * @plr: pseudo-locked region (if any) associated with domain + * @staged_config: parsed configuration to be applied + * @mbps_val: When mba_sc is enabled, this holds the array of user + * specified control values for mba_sc in MBps, indexed + * by closid + */ +struct rdt_ctrl_domain { + struct rdt_domain_hdr hdr; + struct pseudo_lock_region *plr; + struct resctrl_staged_config staged_config[CDP_NUM_TYPES]; + u32 *mbps_val; +}; + +/** + * struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource + * @hdr: common header for different domain types + * @ci: cache info for this domain * @rmid_busy_llc: bitmap of which limbo RMIDs are above threshold * @mbm_total: saved state for MBM total bandwidth * @mbm_local: saved state for MBM local bandwidth @@ -70,16 +105,10 @@ struct resctrl_staged_config { * @cqm_limbo: worker to periodically read CQM h/w counters * @mbm_work_cpu: worker CPU for MBM h/w counters * @cqm_work_cpu: worker CPU for CQM h/w counters - * @plr: pseudo-locked region (if any) associated with domain - * @staged_config: parsed configuration to be applied - * @mbps_val: When mba_sc is enabled, this holds the array of user - * specified control values for mba_sc in MBps, indexed - * by closid */ -struct rdt_domain { - struct list_head list; - int id; - struct cpumask cpu_mask; +struct rdt_mon_domain { + struct rdt_domain_hdr hdr; + struct cacheinfo *ci; unsigned long *rmid_busy_llc; struct mbm_state *mbm_total; struct mbm_state *mbm_local; @@ -87,9 +116,6 @@ struct rdt_domain { struct delayed_work cqm_limbo; int mbm_work_cpu; int cqm_work_cpu; - struct pseudo_lock_region *plr; - struct resctrl_staged_config staged_config[CDP_NUM_TYPES]; - u32 *mbps_val; }; /** @@ -150,16 +176,24 @@ struct resctrl_membw { struct rdt_parse_data; struct resctrl_schema; +enum resctrl_scope { + RESCTRL_L2_CACHE = 2, + RESCTRL_L3_CACHE = 3, + RESCTRL_L3_NODE, +}; + /** * struct rdt_resource - attributes of a resctrl resource * @rid: The index of the resource * @alloc_capable: Is allocation available on this machine * @mon_capable: Is monitor feature available on this machine * @num_rmid: Number of RMIDs available - * @cache_level: Which cache level defines scope of this resource + * @ctrl_scope: Scope of this resource for control functions + * @mon_scope: Scope of this resource for monitor functions * @cache: Cache allocation related data * @membw: If the component has bandwidth controls, their properties. - * @domains: RCU list of all domains for this resource + * @ctrl_domains: RCU list of all control domains for this resource + * @mon_domains: RCU list of all monitor domains for this resource * @name: Name to use in "schemata" file. * @data_width: Character width of data when displaying * @default_ctrl: Specifies default cache cbm or memory B/W percent. @@ -174,17 +208,19 @@ struct rdt_resource { bool alloc_capable; bool mon_capable; int num_rmid; - int cache_level; + enum resctrl_scope ctrl_scope; + enum resctrl_scope mon_scope; struct resctrl_cache cache; struct resctrl_membw membw; - struct list_head domains; + struct list_head ctrl_domains; + struct list_head mon_domains; char *name; int data_width; u32 default_ctrl; const char *format_str; int (*parse_ctrlval)(struct rdt_parse_data *data, struct resctrl_schema *s, - struct rdt_domain *d); + struct rdt_ctrl_domain *d); struct list_head evt_list; unsigned long fflags; bool cdp_capable; @@ -218,13 +254,15 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid); * Update the ctrl_val and apply this config right now. * Must be called on one of the domain's CPUs. */ -int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_domain *d, +int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_ctrl_domain *d, u32 closid, enum resctrl_conf_type t, u32 cfg_val); -u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d, +u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_ctrl_domain *d, u32 closid, enum resctrl_conf_type type); -int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d); -void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d); +int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d); +int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d); +void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d); +void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d); void resctrl_online_cpu(unsigned int cpu); void resctrl_offline_cpu(unsigned int cpu); @@ -253,7 +291,7 @@ void resctrl_offline_cpu(unsigned int cpu); * Return: * 0 on success, or -EIO, -EINVAL etc on error. */ -int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, +int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d, u32 closid, u32 rmid, enum resctrl_event_id eventid, u64 *val, void *arch_mon_ctx); @@ -286,7 +324,7 @@ static inline void resctrl_arch_rmid_read_context_check(void) * * This can be called from any CPU. */ -void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, +void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d, u32 closid, u32 rmid, enum resctrl_event_id eventid); @@ -299,7 +337,7 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, * * This can be called from any CPU. */ -void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_domain *d); +void resctrl_arch_reset_rmid_all(struct rdt_resource *r, struct rdt_mon_domain *d); extern unsigned int resctrl_rmid_realloc_threshold; extern unsigned int resctrl_rmid_realloc_limit; diff --git a/include/linux/rhashtable-types.h b/include/linux/rhashtable-types.h index b6f3797277ff..015c8298bebc 100644 --- a/include/linux/rhashtable-types.h +++ b/include/linux/rhashtable-types.h @@ -9,6 +9,7 @@ #ifndef _LINUX_RHASHTABLE_TYPES_H #define _LINUX_RHASHTABLE_TYPES_H +#include <linux/alloc_tag.h> #include <linux/atomic.h> #include <linux/compiler.h> #include <linux/mutex.h> @@ -88,6 +89,9 @@ struct rhashtable { struct mutex mutex; spinlock_t lock; atomic_t nelems; +#ifdef CONFIG_MEM_ALLOC_PROFILING + struct alloc_tag *alloc_tag; +#endif }; /** @@ -127,9 +131,12 @@ struct rhashtable_iter { bool end_of_table; }; -int rhashtable_init(struct rhashtable *ht, +int rhashtable_init_noprof(struct rhashtable *ht, const struct rhashtable_params *params); -int rhltable_init(struct rhltable *hlt, +#define rhashtable_init(...) alloc_hooks(rhashtable_init_noprof(__VA_ARGS__)) + +int rhltable_init_noprof(struct rhltable *hlt, const struct rhashtable_params *params); +#define rhltable_init(...) alloc_hooks(rhltable_init_noprof(__VA_ARGS__)) #endif /* _LINUX_RHASHTABLE_TYPES_H */ diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 5b5357c0bd8c..8463a128e2f4 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -633,7 +633,7 @@ restart: * @params: hash table parameters * * Computes the hash value for the key and traverses the bucket chain looking - * for a entry with an identical key. The first matching entry is returned. + * for an entry with an identical key. The first matching entry is returned. * * This must only be called under the RCU read lock. * @@ -655,7 +655,7 @@ static inline void *rhashtable_lookup( * @params: hash table parameters * * Computes the hash value for the key and traverses the bucket chain looking - * for a entry with an identical key. The first matching entry is returned. + * for an entry with an identical key. The first matching entry is returned. * * Only use this function when you have other mechanisms guaranteeing * that the object won't go away after the RCU read lock is released. @@ -682,7 +682,7 @@ static inline void *rhashtable_lookup_fast( * @params: hash table parameters * * Computes the hash value for the key and traverses the bucket chain looking - * for a entry with an identical key. All matching entries are returned + * for an entry with an identical key. All matching entries are returned * in a list. * * This must only be called under the RCU read lock. @@ -699,7 +699,7 @@ static inline struct rhlist_head *rhltable_lookup( } /* Internal function, please use rhashtable_insert_fast() instead. This - * function returns the existing element already in hashes in there is a clash, + * function returns the existing element already in hashes if there is a clash, * otherwise it returns an error via ERR_PTR(). */ static inline void *__rhashtable_insert_fast( @@ -1130,7 +1130,7 @@ static inline int rhashtable_remove_fast( * * Since the hash chain is single linked, the removal operation needs to * walk the bucket chain upon removal. The removal operation is thus - * considerable slow if the hash table is not correctly sized. + * considerably slower if the hash table is not correctly sized. * * Will automatically shrink the table if permitted when residency drops * below 30% diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index dc5ae4e96aee..fd35d4ec12e1 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -6,6 +6,8 @@ #include <linux/seq_file.h> #include <linux/poll.h> +#include <uapi/linux/trace_mmap.h> + struct trace_buffer; struct ring_buffer_iter; @@ -191,7 +193,6 @@ void ring_buffer_set_clock(struct trace_buffer *buffer, void ring_buffer_set_time_stamp_abs(struct trace_buffer *buffer, bool abs); bool ring_buffer_time_stamp_abs(struct trace_buffer *buffer); -size_t ring_buffer_nr_pages(struct trace_buffer *buffer, int cpu); size_t ring_buffer_nr_dirty_pages(struct trace_buffer *buffer, int cpu); struct buffer_data_read_page; @@ -223,4 +224,8 @@ int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node); #define trace_rb_cpu_prepare NULL #endif +int ring_buffer_map(struct trace_buffer *buffer, int cpu, + struct vm_area_struct *vma); +int ring_buffer_unmap(struct trace_buffer *buffer, int cpu); +int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu); #endif /* _LINUX_RING_BUFFER_H */ diff --git a/include/linux/rio.h b/include/linux/rio.h index 2cd637268b4f..3c29f40f3c94 100644 --- a/include/linux/rio.h +++ b/include/linux/rio.h @@ -465,7 +465,7 @@ struct rio_driver { struct device_driver driver; }; -#define to_rio_driver(drv) container_of(drv,struct rio_driver, driver) +#define to_rio_driver(drv) container_of_const(drv,struct rio_driver, driver) union rio_pw_msg { struct { diff --git a/include/linux/rmap.h b/include/linux/rmap.h index b7944a833668..0978c64f49d8 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -200,6 +200,9 @@ static inline void __folio_rmap_sanity_checks(struct folio *folio, /* hugetlb folios are handled separately. */ VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); + /* When (un)mapping zeropages, we should never touch ref+mapcount. */ + VM_WARN_ON_FOLIO(is_zero_folio(folio), folio); + /* * TODO: we get driver-allocated folios that have nothing to do with * the rmap using vm_insert_page(); therefore, we cannot assume that @@ -241,7 +244,7 @@ void folio_add_anon_rmap_ptes(struct folio *, struct page *, int nr_pages, void folio_add_anon_rmap_pmd(struct folio *, struct page *, struct vm_area_struct *, unsigned long address, rmap_t flags); void folio_add_new_anon_rmap(struct folio *, struct vm_area_struct *, - unsigned long address); + unsigned long address, rmap_t flags); void folio_add_file_rmap_ptes(struct folio *, struct page *, int nr_pages, struct vm_area_struct *); #define folio_add_file_rmap_pte(folio, page, vma) \ @@ -273,6 +276,7 @@ static inline int hugetlb_try_dup_anon_rmap(struct folio *folio, ClearPageAnonExclusive(&folio->page); } atomic_inc(&folio->_entire_mapcount); + atomic_inc(&folio->_large_mapcount); return 0; } @@ -284,7 +288,7 @@ static inline int hugetlb_try_share_anon_rmap(struct folio *folio) VM_WARN_ON_FOLIO(!PageAnonExclusive(&folio->page), folio); /* Paired with the memory barrier in try_grab_folio(). */ - if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_mb(); if (unlikely(folio_maybe_dma_pinned(folio))) @@ -295,7 +299,7 @@ static inline int hugetlb_try_share_anon_rmap(struct folio *folio) * This is conceptually a smp_wmb() paired with the smp_rmb() in * gup_must_unshare(). */ - if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_mb__after_atomic(); return 0; } @@ -306,6 +310,7 @@ static inline void hugetlb_add_file_rmap(struct folio *folio) VM_WARN_ON_FOLIO(folio_test_anon(folio), folio); atomic_inc(&folio->_entire_mapcount); + atomic_inc(&folio->_large_mapcount); } static inline void hugetlb_remove_rmap(struct folio *folio) @@ -313,21 +318,31 @@ static inline void hugetlb_remove_rmap(struct folio *folio) VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); atomic_dec(&folio->_entire_mapcount); + atomic_dec(&folio->_large_mapcount); } static __always_inline void __folio_dup_file_rmap(struct folio *folio, struct page *page, int nr_pages, enum rmap_level level) { + const int orig_nr_pages = nr_pages; + __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case RMAP_LEVEL_PTE: + if (!folio_test_large(folio)) { + atomic_inc(&page->_mapcount); + break; + } + do { atomic_inc(&page->_mapcount); } while (page++, --nr_pages > 0); + atomic_add(orig_nr_pages, &folio->_large_mapcount); break; case RMAP_LEVEL_PMD: atomic_inc(&folio->_entire_mapcount); + atomic_inc(&folio->_large_mapcount); break; } } @@ -347,8 +362,12 @@ static inline void folio_dup_file_rmap_ptes(struct folio *folio, { __folio_dup_file_rmap(folio, page, nr_pages, RMAP_LEVEL_PTE); } -#define folio_dup_file_rmap_pte(folio, page) \ - folio_dup_file_rmap_ptes(folio, page, 1) + +static __always_inline void folio_dup_file_rmap_pte(struct folio *folio, + struct page *page) +{ + __folio_dup_file_rmap(folio, page, 1, RMAP_LEVEL_PTE); +} /** * folio_dup_file_rmap_pmd - duplicate a PMD mapping of a page range of a folio @@ -373,6 +392,7 @@ static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *src_vma, enum rmap_level level) { + const int orig_nr_pages = nr_pages; bool maybe_pinned; int i; @@ -401,11 +421,20 @@ static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, if (PageAnonExclusive(page + i)) return -EBUSY; } + + if (!folio_test_large(folio)) { + if (PageAnonExclusive(page)) + ClearPageAnonExclusive(page); + atomic_inc(&page->_mapcount); + break; + } + do { if (PageAnonExclusive(page)) ClearPageAnonExclusive(page); atomic_inc(&page->_mapcount); } while (page++, --nr_pages > 0); + atomic_add(orig_nr_pages, &folio->_large_mapcount); break; case RMAP_LEVEL_PMD: if (PageAnonExclusive(page)) { @@ -414,6 +443,7 @@ static __always_inline int __folio_try_dup_anon_rmap(struct folio *folio, ClearPageAnonExclusive(page); } atomic_inc(&folio->_entire_mapcount); + atomic_inc(&folio->_large_mapcount); break; } return 0; @@ -448,8 +478,13 @@ static inline int folio_try_dup_anon_rmap_ptes(struct folio *folio, return __folio_try_dup_anon_rmap(folio, page, nr_pages, src_vma, RMAP_LEVEL_PTE); } -#define folio_try_dup_anon_rmap_pte(folio, page, vma) \ - folio_try_dup_anon_rmap_ptes(folio, page, 1, vma) + +static __always_inline int folio_try_dup_anon_rmap_pte(struct folio *folio, + struct page *page, struct vm_area_struct *src_vma) +{ + return __folio_try_dup_anon_rmap(folio, page, 1, src_vma, + RMAP_LEVEL_PTE); +} /** * folio_try_dup_anon_rmap_pmd - try duplicating a PMD mapping of a page range @@ -541,7 +576,7 @@ static __always_inline int __folio_try_share_anon_rmap(struct folio *folio, */ /* Paired with the memory barrier in try_grab_folio(). */ - if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_mb(); if (unlikely(folio_maybe_dma_pinned(folio))) @@ -552,7 +587,7 @@ static __always_inline int __folio_try_share_anon_rmap(struct folio *folio, * This is conceptually a smp_wmb() paired with the smp_rmb() in * gup_must_unshare(). */ - if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + if (IS_ENABLED(CONFIG_HAVE_GUP_FAST)) smp_mb__after_atomic(); return 0; } @@ -649,16 +684,6 @@ struct page_vma_mapped_walk { unsigned int flags; }; -#define DEFINE_PAGE_VMA_WALK(name, _page, _vma, _address, _flags) \ - struct page_vma_mapped_walk name = { \ - .pfn = page_to_pfn(_page), \ - .nr_pages = compound_nr(_page), \ - .pgoff = page_to_pgoff(_page), \ - .vma = _vma, \ - .address = _address, \ - .flags = _flags, \ - } - #define DEFINE_FOLIO_VMA_WALK(name, _folio, _vma, _address, _flags) \ struct page_vma_mapped_walk name = { \ .pfn = folio_pfn(_folio), \ @@ -678,6 +703,30 @@ static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw) spin_unlock(pvmw->ptl); } +/** + * page_vma_mapped_walk_restart - Restart the page table walk. + * @pvmw: Pointer to struct page_vma_mapped_walk. + * + * It restarts the page table walk when changes occur in the page + * table, such as splitting a PMD. Ensures that the PTL held during + * the previous walk is released and resets the state to allow for + * a new walk starting at the current address stored in pvmw->address. + */ +static inline void +page_vma_mapped_walk_restart(struct page_vma_mapped_walk *pvmw) +{ + WARN_ON_ONCE(!pvmw->pmd && !pvmw->pte); + + if (likely(pvmw->ptl)) + spin_unlock(pvmw->ptl); + else + WARN_ON_ONCE(1); + + pvmw->ptl = NULL; + pvmw->pmd = NULL; + pvmw->pte = NULL; +} + bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw); /* @@ -698,8 +747,6 @@ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked); -int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma); - /* * rmap_walk_control: To control rmap traversing for specific needs * @@ -755,8 +802,4 @@ static inline int folio_mkclean(struct folio *folio) } #endif /* CONFIG_MMU */ -static inline int page_mkclean(struct page *page) -{ - return folio_mkclean(page_folio(page)); -} #endif /* _LINUX_RMAP_H */ diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index cdfc897f1e3c..a7da7dfc06a2 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -7,6 +7,7 @@ #include <linux/netdevice.h> #include <linux/wait.h> #include <linux/refcount.h> +#include <linux/cleanup.h> #include <uapi/linux/rtnetlink.h> extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo); @@ -46,6 +47,8 @@ extern int rtnl_is_locked(void); extern int rtnl_lock_killable(void); extern bool refcount_dec_and_rtnl_lock(refcount_t *r); +DEFINE_LOCK_GUARD_0(rtnl, rtnl_lock(), rtnl_unlock()) + extern wait_queue_head_t netdev_unregistering_wq; extern atomic_t dev_unreg_count; extern struct rw_semaphore pernet_ops_rwsem; diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index d662cf136021..c09cdcc99471 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -36,6 +36,11 @@ struct sbitmap_word { * @cleared: word holding cleared bits */ unsigned long cleared ____cacheline_aligned_in_smp; + + /** + * @swap_lock: serializes simultaneous updates of ->word and ->cleared + */ + spinlock_t swap_lock; } ____cacheline_aligned_in_smp; /** diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 77df3d7b18a6..e61d164622db 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -332,7 +332,7 @@ static inline void sg_dma_unmark_bus_address(struct scatterlist *sg) * Description: * Returns true if the scatterlist was marked for SWIOTLB bouncing. Not all * elements may have been bounced, so the caller would have to check - * individual SG entries with is_swiotlb_buffer(). + * individual SG entries with swiotlb_find_pool(). */ static inline bool sg_dma_is_swiotlb(struct scatterlist *sg) { diff --git a/include/linux/sched.h b/include/linux/sched.h index 3c2abbc587b4..f8d150343d42 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -13,7 +13,7 @@ #include <asm/processor.h> #include <linux/thread_info.h> #include <linux/preempt.h> -#include <linux/cpumask.h> +#include <linux/cpumask_types.h> #include <linux/cache.h> #include <linux/irqflags_types.h> @@ -36,6 +36,7 @@ #include <linux/signal_types.h> #include <linux/syscall_user_dispatch_types.h> #include <linux/mm_types_task.h> +#include <linux/netdevice_xmit.h> #include <linux/task_io_accounting.h> #include <linux/posix-timers_types.h> #include <linux/restart_block.h> @@ -53,6 +54,7 @@ struct bio_list; struct blk_plug; struct bpf_local_storage; struct bpf_run_ctx; +struct bpf_net_context; struct capture_control; struct cfs_rq; struct fs_struct; @@ -301,7 +303,7 @@ enum { TASK_COMM_LEN = 16, }; -extern void scheduler_tick(void); +extern void sched_tick(void); #define MAX_SCHEDULE_TIMEOUT LONG_MAX @@ -734,6 +736,12 @@ enum perf_event_task_context { perf_nr_task_contexts, }; +/* + * Number of contexts where an event can trigger: + * task, softirq, hardirq, nmi. + */ +#define PERF_NR_CONTEXTS 4 + struct wake_q_node { struct wake_q_node *next; }; @@ -770,6 +778,10 @@ struct task_struct { unsigned int flags; unsigned int ptrace; +#ifdef CONFIG_MEM_ALLOC_PROFILING + struct alloc_tag *alloc_tag; +#endif + #ifdef CONFIG_SMP int on_cpu; struct __call_single_node wake_entry; @@ -810,6 +822,7 @@ struct task_struct { struct task_group *sched_task_group; #endif + #ifdef CONFIG_UCLAMP_TASK /* * Clamp values requested for a scheduling entity. @@ -835,6 +848,7 @@ struct task_struct { #endif unsigned int policy; + unsigned long max_allowed_capacity; int nr_cpus_allowed; const cpumask_t *cpus_ptr; cpumask_t *user_cpus_ptr; @@ -928,7 +942,7 @@ struct task_struct { #ifndef TIF_RESTORE_SIGMASK unsigned restore_sigmask:1; #endif -#ifdef CONFIG_MEMCG +#ifdef CONFIG_MEMCG_V1 unsigned in_user_fault:1; #endif #ifdef CONFIG_LRU_GEN @@ -969,7 +983,9 @@ struct task_struct { /* delay due to memory thrashing */ unsigned in_thrashing:1; #endif - +#ifdef CONFIG_PREEMPT_RT + struct netdev_xmit net_xmit; +#endif unsigned long atomic_flags; /* Flags requiring atomic access. */ struct restart_block restart_block; @@ -1250,6 +1266,7 @@ struct task_struct { unsigned int futex_state; #endif #ifdef CONFIG_PERF_EVENTS + u8 perf_recursion[PERF_NR_CONTEXTS]; struct perf_event_context *perf_event_ctxp; struct mutex perf_event_mutex; struct list_head perf_event_list; @@ -1396,7 +1413,7 @@ struct task_struct { int curr_ret_depth; /* Stack of return addresses for return function tracing: */ - struct ftrace_ret_stack *ret_stack; + unsigned long *ret_stack; /* Timestamp for last schedule: */ unsigned long long ftrace_timestamp; @@ -1441,19 +1458,18 @@ struct task_struct { unsigned int kcov_softirq; #endif -#ifdef CONFIG_MEMCG +#ifdef CONFIG_MEMCG_V1 struct mem_cgroup *memcg_in_oom; - gfp_t memcg_oom_gfp_mask; - int memcg_oom_order; +#endif +#ifdef CONFIG_MEMCG /* Number of pages to reclaim on returning to userland: */ unsigned int memcg_nr_pages_over_high; /* Used by memcontrol for targeted memcg charge: */ struct mem_cgroup *active_memcg; -#endif -#ifdef CONFIG_MEMCG_KMEM + /* Cache for current->cgroups->memcg->objcg lookups: */ struct obj_cgroup *objcg; #endif @@ -1502,6 +1518,8 @@ struct task_struct { /* Used for BPF run context */ struct bpf_run_ctx *bpf_ctx; #endif + /* Used by BPF for per-TASK xdp storage */ + struct bpf_net_context *bpf_net_context; #ifdef CONFIG_GCC_PLUGIN_STACKLEAK unsigned long lowest_stack; @@ -1600,7 +1618,7 @@ static inline char task_index_to_char(unsigned int state) { static const char state_char[] = "RSDTtXZPI"; - BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != sizeof(state_char) - 1); + BUILD_BUG_ON(TASK_REPORT_MAX * 2 != 1 << (sizeof(state_char) - 1)); return state_char[state]; } @@ -1774,7 +1792,8 @@ static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpuma } static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) { - if (!cpumask_test_cpu(0, new_mask)) + /* Opencoded cpumask_test_cpu(0, new_mask) to avoid dependency on cpumask.h */ + if ((*cpumask_bits(new_mask) & 1) == 0) return -EINVAL; return 0; } @@ -2060,47 +2079,6 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock); __cond_resched_rwlock_write(lock); \ }) -#ifdef CONFIG_PREEMPT_DYNAMIC - -extern bool preempt_model_none(void); -extern bool preempt_model_voluntary(void); -extern bool preempt_model_full(void); - -#else - -static inline bool preempt_model_none(void) -{ - return IS_ENABLED(CONFIG_PREEMPT_NONE); -} -static inline bool preempt_model_voluntary(void) -{ - return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY); -} -static inline bool preempt_model_full(void) -{ - return IS_ENABLED(CONFIG_PREEMPT); -} - -#endif - -static inline bool preempt_model_rt(void) -{ - return IS_ENABLED(CONFIG_PREEMPT_RT); -} - -/* - * Does the preemption model allow non-cooperative preemption? - * - * For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with - * CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the - * kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the - * PREEMPT_NONE model. - */ -static inline bool preempt_model_preemptible(void) -{ - return preempt_model_full() || preempt_model_rt(); -} - static __always_inline bool need_resched(void) { return unlikely(tif_need_resched()); @@ -2187,4 +2165,23 @@ static inline int sched_core_idle_cpu(int cpu) { return idle_cpu(cpu); } extern void sched_set_stop_task(int cpu, struct task_struct *stop); +#ifdef CONFIG_MEM_ALLOC_PROFILING +static __always_inline struct alloc_tag *alloc_tag_save(struct alloc_tag *tag) +{ + swap(current->alloc_tag, tag); + return tag; +} + +static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct alloc_tag *old) +{ +#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG + WARN(current->alloc_tag != tag, "current->alloc_tag was changed:\n"); +#endif + current->alloc_tag = old; +} +#else +#define alloc_tag_save(_tag) NULL +#define alloc_tag_restore(_tag, _old) do {} while (0) +#endif + #endif diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 02f5090ffea2..e62ff805cfc9 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -92,9 +92,12 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_VM_MERGE_ANY 30 #define MMF_VM_MERGE_ANY_MASK (1 << MMF_VM_MERGE_ANY) +#define MMF_TOPDOWN 31 /* mm searches top down by default */ +#define MMF_TOPDOWN_MASK (1 << MMF_TOPDOWN) + #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK |\ - MMF_VM_MERGE_ANY_MASK) + MMF_VM_MERGE_ANY_MASK | MMF_TOPDOWN_MASK) static inline unsigned long mmf_init_flags(unsigned long flags) { diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h index 478084f9105e..e670ac282333 100644 --- a/include/linux/sched/idle.h +++ b/include/linux/sched/idle.h @@ -5,8 +5,8 @@ #include <linux/sched.h> enum cpu_idle_type { + __CPU_NOT_IDLE = 0, CPU_IDLE, - CPU_NOT_IDLE, CPU_NEWLY_IDLE, CPU_MAX_IDLE_TYPES }; diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index b6543f9d78d6..91546493c43d 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -8,6 +8,7 @@ #include <linux/mm_types.h> #include <linux/gfp.h> #include <linux/sync_core.h> +#include <linux/sched/coredump.h> /* * Routines for handling mm_structs @@ -186,6 +187,27 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); +unsigned long mm_get_unmapped_area(struct mm_struct *mm, struct file *filp, + unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags); + +unsigned long +arch_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags, vm_flags_t vm_flags); +unsigned long +arch_get_unmapped_area_topdown_vmflags(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags, vm_flags_t); + +unsigned long mm_get_unmapped_area_vmflags(struct mm_struct *mm, + struct file *filp, + unsigned long addr, + unsigned long len, + unsigned long pgoff, + unsigned long flags, + vm_flags_t vm_flags); + unsigned long generic_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 18572c9ea724..4237daa5ac7a 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -110,7 +110,7 @@ struct sched_domain { unsigned long last_decay_max_lb_cost; #ifdef CONFIG_SCHEDSTATS - /* load_balance() stats */ + /* sched_balance_rq() stats */ unsigned int lb_count[CPU_MAX_IDLE_TYPES]; unsigned int lb_failed[CPU_MAX_IDLE_TYPES]; unsigned int lb_balanced[CPU_MAX_IDLE_TYPES]; @@ -270,17 +270,17 @@ unsigned long arch_scale_cpu_capacity(int cpu) } #endif -#ifndef arch_scale_thermal_pressure +#ifndef arch_scale_hw_pressure static __always_inline -unsigned long arch_scale_thermal_pressure(int cpu) +unsigned long arch_scale_hw_pressure(int cpu) { return 0; } #endif -#ifndef arch_update_thermal_pressure +#ifndef arch_update_hw_pressure static __always_inline -void arch_update_thermal_pressure(const struct cpumask *cpus, +void arch_update_hw_pressure(const struct cpumask *cpus, unsigned long capped_frequency) { } #endif diff --git a/include/linux/sched/vhost_task.h b/include/linux/sched/vhost_task.h index bc60243d43b3..25446c5d3508 100644 --- a/include/linux/sched/vhost_task.h +++ b/include/linux/sched/vhost_task.h @@ -4,7 +4,8 @@ struct vhost_task; -struct vhost_task *vhost_task_create(bool (*fn)(void *), void *arg, +struct vhost_task *vhost_task_create(bool (*fn)(void *), + void (*handle_kill)(void *), void *arg, const char *name); void vhost_task_start(struct vhost_task *vtsk); void vhost_task_stop(struct vhost_task *vtsk); diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index b807141acc14..688466a0e816 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -737,6 +737,89 @@ struct scmi_powercap_proto_ops { u32 *power_thresh_high); }; +enum scmi_pinctrl_selector_type { + PIN_TYPE = 0, + GROUP_TYPE, + FUNCTION_TYPE, +}; + +enum scmi_pinctrl_conf_type { + SCMI_PIN_DEFAULT = 0, + SCMI_PIN_BIAS_BUS_HOLD = 1, + SCMI_PIN_BIAS_DISABLE = 2, + SCMI_PIN_BIAS_HIGH_IMPEDANCE = 3, + SCMI_PIN_BIAS_PULL_UP = 4, + SCMI_PIN_BIAS_PULL_DEFAULT = 5, + SCMI_PIN_BIAS_PULL_DOWN = 6, + SCMI_PIN_DRIVE_OPEN_DRAIN = 7, + SCMI_PIN_DRIVE_OPEN_SOURCE = 8, + SCMI_PIN_DRIVE_PUSH_PULL = 9, + SCMI_PIN_DRIVE_STRENGTH = 10, + SCMI_PIN_INPUT_DEBOUNCE = 11, + SCMI_PIN_INPUT_MODE = 12, + SCMI_PIN_PULL_MODE = 13, + SCMI_PIN_INPUT_VALUE = 14, + SCMI_PIN_INPUT_SCHMITT = 15, + SCMI_PIN_LOW_POWER_MODE = 16, + SCMI_PIN_OUTPUT_MODE = 17, + SCMI_PIN_OUTPUT_VALUE = 18, + SCMI_PIN_POWER_SOURCE = 19, + SCMI_PIN_SLEW_RATE = 20, + SCMI_PIN_OEM_START = 192, + SCMI_PIN_OEM_END = 255, +}; + +/** + * struct scmi_pinctrl_proto_ops - represents the various operations provided + * by SCMI Pinctrl Protocol + * + * @count_get: returns count of the registered elements in given type + * @name_get: returns name by index of given type + * @group_pins_get: returns the set of pins, assigned to the specified group + * @function_groups_get: returns the set of groups, assigned to the specified + * function + * @mux_set: set muxing function for groups of pins + * @settings_get_one: returns one configuration parameter for pin or group + * specified by config_type + * @settings_get_all: returns all configuration parameters for pin or group + * @settings_conf: sets the configuration parameter for pin or group + * @pin_request: aquire pin before selecting mux setting + * @pin_free: frees pin, acquired by request_pin call + */ +struct scmi_pinctrl_proto_ops { + int (*count_get)(const struct scmi_protocol_handle *ph, + enum scmi_pinctrl_selector_type type); + int (*name_get)(const struct scmi_protocol_handle *ph, u32 selector, + enum scmi_pinctrl_selector_type type, + const char **name); + int (*group_pins_get)(const struct scmi_protocol_handle *ph, + u32 selector, const unsigned int **pins, + unsigned int *nr_pins); + int (*function_groups_get)(const struct scmi_protocol_handle *ph, + u32 selector, unsigned int *nr_groups, + const unsigned int **groups); + int (*mux_set)(const struct scmi_protocol_handle *ph, u32 selector, + u32 group); + int (*settings_get_one)(const struct scmi_protocol_handle *ph, + u32 selector, + enum scmi_pinctrl_selector_type type, + enum scmi_pinctrl_conf_type config_type, + u32 *config_value); + int (*settings_get_all)(const struct scmi_protocol_handle *ph, + u32 selector, + enum scmi_pinctrl_selector_type type, + unsigned int *nr_configs, + enum scmi_pinctrl_conf_type *config_types, + u32 *config_values); + int (*settings_conf)(const struct scmi_protocol_handle *ph, + u32 selector, enum scmi_pinctrl_selector_type type, + unsigned int nr_configs, + enum scmi_pinctrl_conf_type *config_type, + u32 *config_value); + int (*pin_request)(const struct scmi_protocol_handle *ph, u32 pin); + int (*pin_free)(const struct scmi_protocol_handle *ph, u32 pin); +}; + /** * struct scmi_notify_ops - represents notifications' operations provided by * SCMI core @@ -783,8 +866,6 @@ struct scmi_notify_ops { const u32 *src_id, struct notifier_block *nb); int (*devm_event_notifier_unregister)(struct scmi_device *sdev, - u8 proto_id, u8 evt_id, - const u32 *src_id, struct notifier_block *nb); int (*event_notifier_register)(const struct scmi_handle *handle, u8 proto_id, u8 evt_id, @@ -844,6 +925,7 @@ enum scmi_std_protocol { SCMI_PROTOCOL_RESET = 0x16, SCMI_PROTOCOL_VOLTAGE = 0x17, SCMI_PROTOCOL_POWERCAP = 0x18, + SCMI_PROTOCOL_PINCTRL = 0x19, }; enum scmi_system_events { @@ -863,7 +945,7 @@ struct scmi_device { struct scmi_handle *handle; }; -#define to_scmi_dev(d) container_of(d, struct scmi_device, dev) +#define to_scmi_dev(d) container_of_const(d, struct scmi_device, dev) struct scmi_device_id { u8 protocol_id; diff --git a/include/linux/screen_info.h b/include/linux/screen_info.h index 75303c126285..6a4a3cec4638 100644 --- a/include/linux/screen_info.h +++ b/include/linux/screen_info.h @@ -49,6 +49,16 @@ static inline u64 __screen_info_lfb_size(const struct screen_info *si, unsigned return lfb_size; } +static inline bool __screen_info_vbe_mode_nonvga(const struct screen_info *si) +{ + /* + * VESA modes typically run on VGA hardware. Set bit 5 signals that this + * is not the case. Drivers can then not make use of VGA resources. See + * Sec 4.4 of the VBE 2.0 spec. + */ + return si->vesa_attributes & BIT(5); +} + static inline unsigned int __screen_info_video_type(unsigned int type) { switch (type) { diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h index acf7e1a3f3de..e918f96881f5 100644 --- a/include/linux/secretmem.h +++ b/include/linux/secretmem.h @@ -6,25 +6,8 @@ extern const struct address_space_operations secretmem_aops; -static inline bool folio_is_secretmem(struct folio *folio) +static inline bool secretmem_mapping(struct address_space *mapping) { - struct address_space *mapping; - - /* - * Using folio_mapping() is quite slow because of the actual call - * instruction. - * We know that secretmem pages are not compound, so we can - * save a couple of cycles here. - */ - if (folio_test_large(folio)) - return false; - - mapping = (struct address_space *) - ((unsigned long)folio->mapping & ~PAGE_MAPPING_FLAGS); - - if (!mapping || mapping != folio->mapping) - return false; - return mapping->a_ops == &secretmem_aops; } @@ -38,7 +21,7 @@ static inline bool vma_is_secretmem(struct vm_area_struct *vma) return false; } -static inline bool folio_is_secretmem(struct folio *folio) +static inline bool secretmem_mapping(struct address_space *mapping) { return false; } diff --git a/include/linux/security.h b/include/linux/security.h index 41a8f667bdfa..1390f1efb4f0 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -228,7 +228,7 @@ struct request_sock; #define LSM_UNSAFE_NO_NEW_PRIVS 4 #ifdef CONFIG_MMU -extern int mmap_min_addr_handler(struct ctl_table *table, int write, +extern int mmap_min_addr_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); #endif @@ -398,7 +398,7 @@ int security_inode_setsecurity(struct inode *inode, const char *name, const void int security_inode_listsecurity(struct inode *inode, char *buffer, size_t buffer_size); void security_inode_getsecid(struct inode *inode, u32 *secid); int security_inode_copy_up(struct dentry *src, struct cred **new); -int security_inode_copy_up_xattr(const char *name); +int security_inode_copy_up_xattr(struct dentry *src, const char *name); int security_kernfs_init_security(struct kernfs_node *kn_dir, struct kernfs_node *kn); int security_file_permission(struct file *file, int mask); @@ -1016,7 +1016,7 @@ static inline int security_kernfs_init_security(struct kernfs_node *kn_dir, return 0; } -static inline int security_inode_copy_up_xattr(const char *name) +static inline int security_inode_copy_up_xattr(struct dentry *src, const char *name) { return -EOPNOTSUPP; } @@ -2048,7 +2048,8 @@ static inline void security_key_post_create_or_update(struct key *keyring, #ifdef CONFIG_AUDIT #ifdef CONFIG_SECURITY -int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule); +int security_audit_rule_init(u32 field, u32 op, char *rulestr, void **lsmrule, + gfp_t gfp); int security_audit_rule_known(struct audit_krule *krule); int security_audit_rule_match(u32 secid, u32 field, u32 op, void *lsmrule); void security_audit_rule_free(void *lsmrule); @@ -2056,7 +2057,7 @@ void security_audit_rule_free(void *lsmrule); #else static inline int security_audit_rule_init(u32 field, u32 op, char *rulestr, - void **lsmrule) + void **lsmrule, gfp_t gfp) { return 0; } diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 234bcdb1fba4..2fb266ea69fa 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -7,7 +7,6 @@ #include <linux/string_helpers.h> #include <linux/bug.h> #include <linux/mutex.h> -#include <linux/cpumask.h> #include <linux/nodemask.h> #include <linux/fs.h> #include <linux/cred.h> @@ -118,7 +117,18 @@ void seq_vprintf(struct seq_file *m, const char *fmt, va_list args); __printf(2, 3) void seq_printf(struct seq_file *m, const char *fmt, ...); void seq_putc(struct seq_file *m, char c); -void seq_puts(struct seq_file *m, const char *s); +void __seq_puts(struct seq_file *m, const char *s); + +static __always_inline void seq_puts(struct seq_file *m, const char *s) +{ + if (!__builtin_constant_p(*s)) + __seq_puts(m, s); + else if (s[0] && !s[1]) + seq_putc(m, s[0]); + else + seq_write(m, s, __builtin_strlen(s)); +} + void seq_put_decimal_ull_width(struct seq_file *m, const char *delimiter, unsigned long long num, unsigned int width); void seq_put_decimal_ull(struct seq_file *m, const char *delimiter, diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 0a0f6e21d40e..aea25eef9a1a 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -11,7 +11,6 @@ #include <linux/compiler.h> #include <linux/console.h> #include <linux/interrupt.h> -#include <linux/circ_buf.h> #include <linux/spinlock.h> #include <linux/sched.h> #include <linux/tty.h> @@ -699,7 +698,6 @@ struct uart_state { struct tty_port port; enum uart_pm_state pm_state; - struct circ_buf xmit; atomic_t refcount; wait_queue_head_t remove_wait; @@ -723,12 +721,35 @@ struct uart_state { */ static inline void uart_xmit_advance(struct uart_port *up, unsigned int chars) { - struct circ_buf *xmit = &up->state->xmit; + struct tty_port *tport = &up->state->port; - xmit->tail = (xmit->tail + chars) & (UART_XMIT_SIZE - 1); + kfifo_skip_count(&tport->xmit_fifo, chars); up->icount.tx += chars; } +static inline unsigned int uart_fifo_out(struct uart_port *up, + unsigned char *buf, unsigned int chars) +{ + struct tty_port *tport = &up->state->port; + + chars = kfifo_out(&tport->xmit_fifo, buf, chars); + up->icount.tx += chars; + + return chars; +} + +static inline unsigned int uart_fifo_get(struct uart_port *up, + unsigned char *ch) +{ + struct tty_port *tport = &up->state->port; + unsigned int chars; + + chars = kfifo_get(&tport->xmit_fifo, ch); + up->icount.tx += chars; + + return chars; +} + struct module; struct tty_driver; @@ -764,7 +785,7 @@ enum UART_TX_FLAGS { for_test, for_post) \ ({ \ struct uart_port *__port = (uport); \ - struct circ_buf *xmit = &__port->state->xmit; \ + struct tty_port *__tport = &__port->state->port; \ unsigned int pending; \ \ for (; (for_test) && (tx_ready); (for_post), __port->icount.tx++) { \ @@ -775,22 +796,22 @@ enum UART_TX_FLAGS { continue; \ } \ \ - if (uart_circ_empty(xmit) || uart_tx_stopped(__port)) \ + if (uart_tx_stopped(__port)) \ + break; \ + \ + if (!kfifo_get(&__tport->xmit_fifo, &(ch))) \ break; \ \ - (ch) = xmit->buf[xmit->tail]; \ (put_char); \ - xmit->tail = (xmit->tail + 1) % UART_XMIT_SIZE; \ } \ \ (tx_done); \ \ - pending = uart_circ_chars_pending(xmit); \ + pending = kfifo_len(&__tport->xmit_fifo); \ if (pending < WAKEUP_CHARS) { \ uart_write_wakeup(__port); \ \ - if (!((flags) & UART_TX_NOSTOP) && pending == 0 && \ - __port->ops->tx_empty(__port)) \ + if (!((flags) & UART_TX_NOSTOP) && pending == 0) \ __port->ops->stop_tx(__port); \ } \ \ @@ -830,6 +851,24 @@ enum UART_TX_FLAGS { }) /** + * uart_port_tx_limited_flags -- transmit helper for uart_port with count limiting with flags + * @port: uart port + * @ch: variable to store a character to be written to the HW + * @flags: %UART_TX_NOSTOP or similar + * @count: a limit of characters to send + * @tx_ready: can HW accept more data function + * @put_char: function to write a character + * @tx_done: function to call after the loop is done + * + * See uart_port_tx_limited() for more details. + */ +#define uart_port_tx_limited_flags(port, ch, flags, count, tx_ready, put_char, tx_done) ({ \ + unsigned int __count = (count); \ + __uart_port_tx(port, ch, flags, tx_ready, put_char, tx_done, __count, \ + __count--); \ +}) + +/** * uart_port_tx -- transmit helper for uart_port * @port: uart port * @ch: variable to store a character to be written to the HW @@ -974,15 +1013,6 @@ bool uart_match_port(const struct uart_port *port1, int uart_suspend_port(struct uart_driver *reg, struct uart_port *port); int uart_resume_port(struct uart_driver *reg, struct uart_port *port); -#define uart_circ_empty(circ) ((circ)->head == (circ)->tail) -#define uart_circ_clear(circ) ((circ)->head = (circ)->tail = 0) - -#define uart_circ_chars_pending(circ) \ - (CIRC_CNT((circ)->head, (circ)->tail, UART_XMIT_SIZE)) - -#define uart_circ_chars_free(circ) \ - (CIRC_SPACE((circ)->head, (circ)->tail, UART_XMIT_SIZE)) - static inline int uart_tx_stopped(struct uart_port *port) { struct tty_struct *tty = port->state->port.tty; diff --git a/include/linux/serial_max3100.h b/include/linux/serial_max3100.h deleted file mode 100644 index befd55c08a7c..000000000000 --- a/include/linux/serial_max3100.h +++ /dev/null @@ -1,48 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * - * Copyright (C) 2007 Christian Pellegrin - */ - - -#ifndef _LINUX_SERIAL_MAX3100_H -#define _LINUX_SERIAL_MAX3100_H 1 - - -/** - * struct plat_max3100 - MAX3100 SPI UART platform data - * @loopback: force MAX3100 in loopback - * @crystal: 1 for 3.6864 Mhz, 0 for 1.8432 - * @max3100_hw_suspend: MAX3100 has a shutdown pin. This is a hook - * called on suspend and resume to activate it. - * @poll_time: poll time for CTS signal in ms, 0 disables (so no hw - * flow ctrl is possible but you have less CPU usage) - * - * You should use this structure in your machine description to specify - * how the MAX3100 is connected. Example: - * - * static struct plat_max3100 max3100_plat_data = { - * .loopback = 0, - * .crystal = 0, - * .poll_time = 100, - * }; - * - * static struct spi_board_info spi_board_info[] = { - * { - * .modalias = "max3100", - * .platform_data = &max3100_plat_data, - * .irq = IRQ_EINT12, - * .max_speed_hz = 5*1000*1000, - * .chip_select = 0, - * }, - * }; - * - **/ -struct plat_max3100 { - int loopback; - int crystal; - void (*max3100_hw_suspend) (int suspend); - int poll_time; -}; - -#endif diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h index 1c89611e0e06..0f2f50b8d28e 100644 --- a/include/linux/serial_sci.h +++ b/include/linux/serial_sci.h @@ -37,6 +37,7 @@ enum { SCIx_SH7705_SCIF_REGTYPE, SCIx_HSCIF_REGTYPE, SCIx_RZ_SCIFA_REGTYPE, + SCIx_RZV2H_SCIF_REGTYPE, SCIx_NR_REGTYPES, }; diff --git a/include/linux/serio.h b/include/linux/serio.h index 7ca41af93b37..bf2191f25350 100644 --- a/include/linux/serio.h +++ b/include/linux/serio.h @@ -80,7 +80,7 @@ struct serio_driver { struct device_driver driver; }; -#define to_serio_driver(d) container_of(d, struct serio_driver, driver) +#define to_serio_driver(d) container_of_const(d, struct serio_driver, driver) int serio_open(struct serio *serio, struct serio_driver *drv); void serio_close(struct serio *serio); diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 9346cd44814d..b14be59550e3 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -284,6 +284,12 @@ enum { SFF8024_ID_QSFP_8438 = 0x0c, SFF8024_ID_QSFP_8436_8636 = 0x0d, SFF8024_ID_QSFP28_8636 = 0x11, + SFF8024_ID_QSFP_DD = 0x18, + SFF8024_ID_OSFP = 0x19, + SFF8024_ID_DSFP = 0x1B, + SFF8024_ID_QSFP_PLUS_CMIS = 0x1E, + SFF8024_ID_SFP_DD_CMIS = 0x1F, + SFF8024_ID_SFP_PLUS_CMIS = 0x20, SFF8024_ENCODING_UNSPEC = 0x00, SFF8024_ENCODING_8B10B = 0x01, @@ -554,7 +560,7 @@ bool sfp_may_have_phy(struct sfp_bus *bus, const struct sfp_eeprom_id *id); void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, unsigned long *support, unsigned long *interfaces); phy_interface_t sfp_select_interface(struct sfp_bus *bus, - unsigned long *link_modes); + const unsigned long *link_modes); int sfp_get_module_info(struct sfp_bus *bus, struct ethtool_modinfo *modinfo); int sfp_get_module_eeprom(struct sfp_bus *bus, struct ethtool_eeprom *ee, @@ -592,7 +598,7 @@ static inline void sfp_parse_support(struct sfp_bus *bus, } static inline phy_interface_t sfp_select_interface(struct sfp_bus *bus, - unsigned long *link_modes) + const unsigned long *link_modes) { return PHY_INTERFACE_MODE_NA; } diff --git a/include/linux/shm.h b/include/linux/shm.h index c55bef0538e5..1d3d3ae958fb 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -16,7 +16,6 @@ struct sysv_shm { long do_shmat(int shmid, char __user *shmaddr, int shmflg, unsigned long *addr, unsigned long shmlba); -bool is_file_shm_hugepages(struct file *file); void exit_shm(struct task_struct *task); #define shm_init_task(task) INIT_LIST_HEAD(&(task)->sysvshm.shm_clist) #else @@ -30,10 +29,6 @@ static inline long do_shmat(int shmid, char __user *shmaddr, { return -ENOSYS; } -static inline bool is_file_shm_hugepages(struct file *file) -{ - return false; -} static inline void exit_shm(struct task_struct *task) { } diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 3fb18f7eb73e..1d06b1e5408a 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -113,12 +113,21 @@ int shmem_unuse(unsigned int type); #ifdef CONFIG_TRANSPARENT_HUGEPAGE extern bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, struct mm_struct *mm, unsigned long vm_flags); +unsigned long shmem_allowable_huge_orders(struct inode *inode, + struct vm_area_struct *vma, pgoff_t index, + bool global_huge); #else static __always_inline bool shmem_is_huge(struct inode *inode, pgoff_t index, bool shmem_huge_force, struct mm_struct *mm, unsigned long vm_flags) { return false; } +static inline unsigned long shmem_allowable_huge_orders(struct inode *inode, + struct vm_area_struct *vma, pgoff_t index, + bool global_huge) +{ + return 0; +} #endif #ifdef CONFIG_SHMEM diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h index e2d45b7cb619..926496c9cc9c 100644 --- a/include/linux/skb_array.h +++ b/include/linux/skb_array.h @@ -177,10 +177,11 @@ static inline int skb_array_peek_len_any(struct skb_array *a) return PTR_RING_PEEK_CALL_ANY(&a->ring, __skb_array_len_with_tag); } -static inline int skb_array_init(struct skb_array *a, int size, gfp_t gfp) +static inline int skb_array_init_noprof(struct skb_array *a, int size, gfp_t gfp) { - return ptr_ring_init(&a->ring, size, gfp); + return ptr_ring_init_noprof(&a->ring, size, gfp); } +#define skb_array_init(...) alloc_hooks(skb_array_init_noprof(__VA_ARGS__)) static void __skb_array_destroy_skb(void *ptr) { @@ -198,15 +199,17 @@ static inline int skb_array_resize(struct skb_array *a, int size, gfp_t gfp) return ptr_ring_resize(&a->ring, size, gfp, __skb_array_destroy_skb); } -static inline int skb_array_resize_multiple(struct skb_array **rings, - int nrings, unsigned int size, - gfp_t gfp) +static inline int skb_array_resize_multiple_noprof(struct skb_array **rings, + int nrings, unsigned int size, + gfp_t gfp) { BUILD_BUG_ON(offsetof(struct skb_array, ring)); - return ptr_ring_resize_multiple((struct ptr_ring **)rings, - nrings, size, gfp, - __skb_array_destroy_skb); + return ptr_ring_resize_multiple_noprof((struct ptr_ring **)rings, + nrings, size, gfp, + __skb_array_destroy_skb); } +#define skb_array_resize_multiple(...) \ + alloc_hooks(skb_array_resize_multiple_noprof(__VA_ARGS__)) static inline void skb_array_cleanup(struct skb_array *a) { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9d24aec064e8..29c3ea5b6e93 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -353,8 +353,6 @@ struct sk_buff; #define MAX_SKB_FRAGS CONFIG_MAX_SKB_FRAGS -extern int sysctl_max_skb_frags; - /* Set skb_shinfo(skb)->gso_size to this in case you want skb_segment to * segment using its current segmentation instead. */ @@ -527,6 +525,13 @@ enum { #define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \ SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS) +struct ubuf_info_ops { + void (*complete)(struct sk_buff *, struct ubuf_info *, + bool zerocopy_success); + /* has to be compatible with skb_zcopy_set() */ + int (*link_skb)(struct sk_buff *skb, struct ubuf_info *uarg); +}; + /* * The callback notifies userspace to release buffers when skb DMA is done in * lower device, the skb last reference should be 0 when calling this. @@ -536,8 +541,7 @@ enum { * The desc field is used to track userspace buffer index. */ struct ubuf_info { - void (*callback)(struct sk_buff *, struct ubuf_info *, - bool zerocopy_success); + const struct ubuf_info_ops *ops; refcount_t refcnt; u8 flags; }; @@ -702,6 +706,13 @@ typedef unsigned int sk_buff_data_t; typedef unsigned char *sk_buff_data_t; #endif +enum skb_tstamp_type { + SKB_CLOCK_REALTIME, + SKB_CLOCK_MONOTONIC, + SKB_CLOCK_TAI, + __SKB_CLOCK_MAX = SKB_CLOCK_TAI, +}; + /** * DOC: Basic sk_buff geometry * @@ -819,10 +830,8 @@ typedef unsigned char *sk_buff_data_t; * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @slow_gro: state present at GRO time, slower prepare step required - * @mono_delivery_time: When set, skb->tstamp has the - * delivery_time in mono clock base (i.e. EDT). Otherwise, the - * skb->tstamp has the (rcv) timestamp at ingress and - * delivery_time at egress. + * @tstamp_type: When set, skb->tstamp has the + * delivery_time clock base of skb->tstamp. * @napi_id: id of the NAPI struct this skb came from * @sender_cpu: (aka @napi_id) source CPU in XPS * @alloc_cpu: CPU which did the skb allocation. @@ -950,7 +959,7 @@ struct sk_buff { /* private: */ __u8 __mono_tc_offset[0]; /* public: */ - __u8 mono_delivery_time:1; /* See SKB_MONO_DELIVERY_TIME_MASK */ + __u8 tstamp_type:2; /* See skb_tstamp_type */ #ifdef CONFIG_NET_XGRESS __u8 tc_at_ingress:1; /* See TC_AT_INGRESS_MASK */ __u8 tc_skip_classify:1; @@ -992,7 +1001,7 @@ struct sk_buff { #ifdef CONFIG_NETFILTER_SKIP_EGRESS __u8 nf_skip_egress:1; #endif -#ifdef CONFIG_TLS_DEVICE +#ifdef CONFIG_SKB_DECRYPTED __u8 decrypted:1; #endif __u8 slow_gro:1; @@ -1080,15 +1089,16 @@ struct sk_buff { #endif #define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset) -/* if you move tc_at_ingress or mono_delivery_time +/* if you move tc_at_ingress or tstamp_type * around, you also must adapt these constants. */ #ifdef __BIG_ENDIAN_BITFIELD -#define SKB_MONO_DELIVERY_TIME_MASK (1 << 7) -#define TC_AT_INGRESS_MASK (1 << 6) +#define SKB_TSTAMP_TYPE_MASK (3 << 6) +#define SKB_TSTAMP_TYPE_RSHIFT (6) +#define TC_AT_INGRESS_MASK (1 << 5) #else -#define SKB_MONO_DELIVERY_TIME_MASK (1 << 0) -#define TC_AT_INGRESS_MASK (1 << 1) +#define SKB_TSTAMP_TYPE_MASK (3) +#define TC_AT_INGRESS_MASK (1 << 2) #endif #define SKB_BF_MONO_TC_OFFSET offsetof(struct sk_buff, __mono_tc_offset) @@ -1174,15 +1184,6 @@ static inline bool skb_dst_is_noref(const struct sk_buff *skb) return (skb->_skb_refdst & SKB_DST_NOREF) && skb_dst(skb); } -/** - * skb_rtable - Returns the skb &rtable - * @skb: buffer - */ -static inline struct rtable *skb_rtable(const struct sk_buff *skb) -{ - return (struct rtable *)skb_dst(skb); -} - /* For mangling skb->pkt_type from user space side from applications * such as nft, tc, etc, we only allow a conservative subset of * possible pkt_types to be set. @@ -1250,8 +1251,14 @@ static inline bool skb_data_unref(const struct sk_buff *skb, return true; } -void __fix_address -kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason); +void __fix_address sk_skb_reason_drop(struct sock *sk, struct sk_buff *skb, + enum skb_drop_reason reason); + +static inline void +kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) +{ + sk_skb_reason_drop(NULL, skb, reason); +} /** * kfree_skb - free an sk_buff with 'NOT_SPECIFIED' reason @@ -1497,8 +1504,14 @@ __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4) __skb_set_hash(skb, hash, true, is_l4); } -void __skb_get_hash(struct sk_buff *skb); -u32 __skb_get_hash_symmetric(const struct sk_buff *skb); +u32 __skb_get_hash_symmetric_net(const struct net *net, const struct sk_buff *skb); + +static inline u32 __skb_get_hash_symmetric(const struct sk_buff *skb) +{ + return __skb_get_hash_symmetric_net(NULL, skb); +} + +void __skb_get_hash_net(const struct net *net, struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, const void *data, const struct flow_keys_basic *keys, int hlen); @@ -1577,10 +1590,18 @@ void skb_flow_dissect_hash(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container); +static inline __u32 skb_get_hash_net(const struct net *net, struct sk_buff *skb) +{ + if (!skb->l4_hash && !skb->sw_hash) + __skb_get_hash_net(net, skb); + + return skb->hash; +} + static inline __u32 skb_get_hash(struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) - __skb_get_hash(skb); + __skb_get_hash_net(NULL, skb); return skb->hash; } @@ -1615,17 +1636,26 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from) static inline int skb_cmp_decrypted(const struct sk_buff *skb1, const struct sk_buff *skb2) { -#ifdef CONFIG_TLS_DEVICE +#ifdef CONFIG_SKB_DECRYPTED return skb2->decrypted - skb1->decrypted; #else return 0; #endif } +static inline bool skb_is_decrypted(const struct sk_buff *skb) +{ +#ifdef CONFIG_SKB_DECRYPTED + return skb->decrypted; +#else + return false; +#endif +} + static inline void skb_copy_decrypted(struct sk_buff *to, const struct sk_buff *from) { -#ifdef CONFIG_TLS_DEVICE +#ifdef CONFIG_SKB_DECRYPTED to->decrypted = from->decrypted; #endif } @@ -1662,18 +1692,20 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) } #endif +extern const struct ubuf_info_ops msg_zerocopy_ubuf_ops; + struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); -void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, - bool success); - int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, struct iov_iter *from, size_t length); +int zerocopy_fill_skb_from_iter(struct sk_buff *skb, + struct iov_iter *from, size_t length); + static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb, struct msghdr *msg, int len) { @@ -1757,13 +1789,13 @@ static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) static inline void net_zcopy_put(struct ubuf_info *uarg) { if (uarg) - uarg->callback(NULL, uarg, true); + uarg->ops->complete(NULL, uarg, true); } static inline void net_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) { if (uarg) { - if (uarg->callback == msg_zerocopy_callback) + if (uarg->ops == &msg_zerocopy_ubuf_ops) msg_zerocopy_put_abort(uarg, have_uref); else if (have_uref) net_zcopy_put(uarg); @@ -1777,7 +1809,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) if (uarg) { if (!skb_zcopy_is_nouarg(skb)) - uarg->callback(skb, uarg, zerocopy_success); + uarg->ops->complete(skb, uarg, zerocopy_success); skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY; } @@ -3031,6 +3063,21 @@ static inline void skb_mac_header_rebuild(struct sk_buff *skb) } } +/* Move the full mac header up to current network_header. + * Leaves skb->data pointing at offset skb->mac_len into the mac_header. + * Must be provided the complete mac header length. + */ +static inline void skb_mac_header_rebuild_full(struct sk_buff *skb, u32 full_mac_len) +{ + if (skb_mac_header_was_set(skb)) { + const unsigned char *old_mac = skb_mac_header(skb); + + skb_set_mac_header(skb, -full_mac_len); + memmove(skb_mac_header(skb), old_mac, full_mac_len); + __skb_push(skb, full_mac_len - skb->mac_len); + } +} + static inline int skb_checksum_start_offset(const struct sk_buff *skb) { return skb->csum_start - skb_headroom(skb); @@ -3350,13 +3397,7 @@ static inline void *napi_alloc_frag_align(unsigned int fragsz, return __napi_alloc_frag_align(fragsz, -align); } -struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, - unsigned int length, gfp_t gfp_mask); -static inline struct sk_buff *napi_alloc_skb(struct napi_struct *napi, - unsigned int length) -{ - return __napi_alloc_skb(napi, length, GFP_ATOMIC); -} +struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int length); void napi_consume_skb(struct sk_buff *skb, int budget); void napi_skb_free_stolen_head(struct sk_buff *skb); @@ -3371,7 +3412,7 @@ void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason); * * %NULL is returned if there is no free memory. */ -static inline struct page *__dev_alloc_pages(gfp_t gfp_mask, +static inline struct page *__dev_alloc_pages_noprof(gfp_t gfp_mask, unsigned int order) { /* This piece of code contains several assumptions. @@ -3384,13 +3425,15 @@ static inline struct page *__dev_alloc_pages(gfp_t gfp_mask, */ gfp_mask |= __GFP_COMP | __GFP_MEMALLOC; - return alloc_pages_node(NUMA_NO_NODE, gfp_mask, order); + return alloc_pages_node_noprof(NUMA_NO_NODE, gfp_mask, order); } +#define __dev_alloc_pages(...) alloc_hooks(__dev_alloc_pages_noprof(__VA_ARGS__)) -static inline struct page *dev_alloc_pages(unsigned int order) -{ - return __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, order); -} +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). + */ +#define dev_alloc_pages(_order) __dev_alloc_pages(GFP_ATOMIC | __GFP_NOWARN, _order) /** * __dev_alloc_page - allocate a page for network Rx @@ -3400,15 +3443,17 @@ static inline struct page *dev_alloc_pages(unsigned int order) * * %NULL is returned if there is no free memory. */ -static inline struct page *__dev_alloc_page(gfp_t gfp_mask) +static inline struct page *__dev_alloc_page_noprof(gfp_t gfp_mask) { - return __dev_alloc_pages(gfp_mask, 0); + return __dev_alloc_pages_noprof(gfp_mask, 0); } +#define __dev_alloc_page(...) alloc_hooks(__dev_alloc_page_noprof(__VA_ARGS__)) -static inline struct page *dev_alloc_page(void) -{ - return dev_alloc_pages(0); -} +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). + */ +#define dev_alloc_page() dev_alloc_pages(0) /** * dev_page_is_reusable - check whether a page can be reused for network Rx @@ -3489,85 +3534,10 @@ static inline struct page *skb_frag_page(const skb_frag_t *frag) return netmem_to_page(frag->netmem); } -/** - * __skb_frag_ref - take an addition reference on a paged fragment. - * @frag: the paged fragment - * - * Takes an additional reference on the paged fragment @frag. - */ -static inline void __skb_frag_ref(skb_frag_t *frag) -{ - get_page(skb_frag_page(frag)); -} - -/** - * skb_frag_ref - take an addition reference on a paged fragment of an skb. - * @skb: the buffer - * @f: the fragment offset. - * - * Takes an additional reference on the @f'th paged fragment of @skb. - */ -static inline void skb_frag_ref(struct sk_buff *skb, int f) -{ - __skb_frag_ref(&skb_shinfo(skb)->frags[f]); -} - int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb, unsigned int headroom); int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb, struct bpf_prog *prog); -bool napi_pp_put_page(struct page *page, bool napi_safe); - -static inline void -skb_page_unref(const struct sk_buff *skb, struct page *page, bool napi_safe) -{ -#ifdef CONFIG_PAGE_POOL - if (skb->pp_recycle && napi_pp_put_page(page, napi_safe)) - return; -#endif - put_page(page); -} - -static inline void -napi_frag_unref(skb_frag_t *frag, bool recycle, bool napi_safe) -{ - struct page *page = skb_frag_page(frag); - -#ifdef CONFIG_PAGE_POOL - if (recycle && napi_pp_put_page(page, napi_safe)) - return; -#endif - put_page(page); -} - -/** - * __skb_frag_unref - release a reference on a paged fragment. - * @frag: the paged fragment - * @recycle: recycle the page if allocated via page_pool - * - * Releases a reference on the paged fragment @frag - * or recycles the page via the page_pool API. - */ -static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) -{ - napi_frag_unref(frag, recycle, false); -} - -/** - * skb_frag_unref - release a reference on a paged fragment of an skb. - * @skb: the buffer - * @f: the fragment offset - * - * Releases a reference on the @f'th paged fragment of @skb. - */ -static inline void skb_frag_unref(struct sk_buff *skb, int f) -{ - struct skb_shared_info *shinfo = skb_shinfo(skb); - - if (!skb_zcopy_managed(skb)) - __skb_frag_unref(&shinfo->frags[f], skb->pp_recycle); -} - /** * skb_frag_address - gets the address of the data contained in a paged fragment * @frag: the paged fragment buffer @@ -4058,12 +4028,6 @@ int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, struct iov_iter *from, int len); int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm); void skb_free_datagram(struct sock *sk, struct sk_buff *skb); -void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len); -static inline void skb_free_datagram_locked(struct sock *sk, - struct sk_buff *skb) -{ - __skb_free_datagram_locked(sk, skb, 0); -} int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags); int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len); int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len); @@ -4252,7 +4216,7 @@ static inline void skb_get_new_timestampns(const struct sk_buff *skb, static inline void __net_timestamp(struct sk_buff *skb) { skb->tstamp = ktime_get_real(); - skb->mono_delivery_time = 0; + skb->tstamp_type = SKB_CLOCK_REALTIME; } static inline ktime_t net_timedelta(ktime_t t) @@ -4261,10 +4225,36 @@ static inline ktime_t net_timedelta(ktime_t t) } static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt, - bool mono) + u8 tstamp_type) { skb->tstamp = kt; - skb->mono_delivery_time = kt && mono; + + if (kt) + skb->tstamp_type = tstamp_type; + else + skb->tstamp_type = SKB_CLOCK_REALTIME; +} + +static inline void skb_set_delivery_type_by_clockid(struct sk_buff *skb, + ktime_t kt, clockid_t clockid) +{ + u8 tstamp_type = SKB_CLOCK_REALTIME; + + switch (clockid) { + case CLOCK_REALTIME: + break; + case CLOCK_MONOTONIC: + tstamp_type = SKB_CLOCK_MONOTONIC; + break; + case CLOCK_TAI: + tstamp_type = SKB_CLOCK_TAI; + break; + default: + WARN_ON_ONCE(1); + kt = 0; + } + + skb_set_delivery_time(skb, kt, tstamp_type); } DECLARE_STATIC_KEY_FALSE(netstamp_needed_key); @@ -4274,8 +4264,8 @@ DECLARE_STATIC_KEY_FALSE(netstamp_needed_key); */ static inline void skb_clear_delivery_time(struct sk_buff *skb) { - if (skb->mono_delivery_time) { - skb->mono_delivery_time = 0; + if (skb->tstamp_type) { + skb->tstamp_type = SKB_CLOCK_REALTIME; if (static_branch_unlikely(&netstamp_needed_key)) skb->tstamp = ktime_get_real(); else @@ -4285,7 +4275,7 @@ static inline void skb_clear_delivery_time(struct sk_buff *skb) static inline void skb_clear_tstamp(struct sk_buff *skb) { - if (skb->mono_delivery_time) + if (skb->tstamp_type) return; skb->tstamp = 0; @@ -4293,7 +4283,7 @@ static inline void skb_clear_tstamp(struct sk_buff *skb) static inline ktime_t skb_tstamp(const struct sk_buff *skb) { - if (skb->mono_delivery_time) + if (skb->tstamp_type) return 0; return skb->tstamp; @@ -4301,7 +4291,7 @@ static inline ktime_t skb_tstamp(const struct sk_buff *skb) static inline ktime_t skb_tstamp_cond(const struct sk_buff *skb, bool cond) { - if (!skb->mono_delivery_time && skb->tstamp) + if (skb->tstamp_type != SKB_CLOCK_MONOTONIC && skb->tstamp) return skb->tstamp; if (static_branch_unlikely(&netstamp_needed_key) || cond) diff --git a/include/linux/skbuff_ref.h b/include/linux/skbuff_ref.h new file mode 100644 index 000000000000..16c241a23472 --- /dev/null +++ b/include/linux/skbuff_ref.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Skb ref helpers. + * + */ + +#ifndef _LINUX_SKBUFF_REF_H +#define _LINUX_SKBUFF_REF_H + +#include <linux/skbuff.h> + +/** + * __skb_frag_ref - take an addition reference on a paged fragment. + * @frag: the paged fragment + * + * Takes an additional reference on the paged fragment @frag. + */ +static inline void __skb_frag_ref(skb_frag_t *frag) +{ + get_page(skb_frag_page(frag)); +} + +/** + * skb_frag_ref - take an addition reference on a paged fragment of an skb. + * @skb: the buffer + * @f: the fragment offset. + * + * Takes an additional reference on the @f'th paged fragment of @skb. + */ +static inline void skb_frag_ref(struct sk_buff *skb, int f) +{ + __skb_frag_ref(&skb_shinfo(skb)->frags[f]); +} + +bool napi_pp_put_page(netmem_ref netmem); + +static inline void +skb_page_unref(struct page *page, bool recycle) +{ +#ifdef CONFIG_PAGE_POOL + if (recycle && napi_pp_put_page(page_to_netmem(page))) + return; +#endif + put_page(page); +} + +/** + * __skb_frag_unref - release a reference on a paged fragment. + * @frag: the paged fragment + * @recycle: recycle the page if allocated via page_pool + * + * Releases a reference on the paged fragment @frag + * or recycles the page via the page_pool API. + */ +static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) +{ + skb_page_unref(skb_frag_page(frag), recycle); +} + +/** + * skb_frag_unref - release a reference on a paged fragment of an skb. + * @skb: the buffer + * @f: the fragment offset + * + * Releases a reference on the @f'th paged fragment of @skb. + */ +static inline void skb_frag_unref(struct sk_buff *skb, int f) +{ + struct skb_shared_info *shinfo = skb_shinfo(skb); + + if (!skb_zcopy_managed(skb)) + __skb_frag_unref(&shinfo->frags[f], skb->pp_recycle); +} + +#endif /* _LINUX_SKBUFF_REF_H */ diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index a509caf823d6..d9b03e0746e7 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -58,6 +58,10 @@ struct sk_psock_progs { struct bpf_prog *stream_parser; struct bpf_prog *stream_verdict; struct bpf_prog *skb_verdict; + struct bpf_link *msg_parser_link; + struct bpf_link *stream_parser_link; + struct bpf_link *stream_verdict_link; + struct bpf_link *skb_verdict_link; }; enum sk_psock_state_bits { @@ -410,11 +414,14 @@ void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock); int sk_psock_msg_verdict(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg); -static inline struct sk_psock_link *sk_psock_init_link(void) -{ - return kzalloc(sizeof(struct sk_psock_link), - GFP_ATOMIC | __GFP_NOWARN); -} +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). The typecast is + * intentional to enforce typesafety. + */ +#define sk_psock_init_link() \ + ((struct sk_psock_link *)kzalloc(sizeof(struct sk_psock_link), \ + GFP_ATOMIC | __GFP_NOWARN)) static inline void sk_psock_free_link(struct sk_psock_link *link) { diff --git a/include/linux/slab.h b/include/linux/slab.h index 739b21262507..eb2bf4629157 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -41,7 +41,7 @@ enum _slab_flag_bits { #ifdef CONFIG_FAILSLAB _SLAB_FAILSLAB, #endif -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG _SLAB_ACCOUNT, #endif #ifdef CONFIG_KASAN_GENERIC @@ -56,6 +56,9 @@ enum _slab_flag_bits { #endif _SLAB_OBJECT_POISON, _SLAB_CMPXCHG_DOUBLE, +#ifdef CONFIG_SLAB_OBJ_EXT + _SLAB_NO_OBJ_EXT, +#endif _SLAB_FLAGS_LAST_BIT }; @@ -168,7 +171,7 @@ enum _slab_flag_bits { # define SLAB_FAILSLAB __SLAB_FLAG_UNUSED #endif /* Account to memcg */ -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG # define SLAB_ACCOUNT __SLAB_FLAG_BIT(_SLAB_ACCOUNT) #else # define SLAB_ACCOUNT __SLAB_FLAG_UNUSED @@ -202,6 +205,13 @@ enum _slab_flag_bits { #endif #define SLAB_TEMPORARY SLAB_RECLAIM_ACCOUNT /* Objects are short-lived */ +/* Slab created using create_boot_cache */ +#ifdef CONFIG_SLAB_OBJ_EXT +#define SLAB_NO_OBJ_EXT __SLAB_FLAG_BIT(_SLAB_NO_OBJ_EXT) +#else +#define SLAB_NO_OBJ_EXT __SLAB_FLAG_UNUSED +#endif + /* * ZERO_SIZE_PTR will be returned for zero sized kmalloc requests. * @@ -261,7 +271,10 @@ int kmem_cache_shrink(struct kmem_cache *s); /* * Common kmalloc functions provided by all allocators */ -void * __must_check krealloc(const void *objp, size_t new_size, gfp_t flags) __realloc_size(2); +void * __must_check krealloc_noprof(const void *objp, size_t new_size, + gfp_t flags) __realloc_size(2); +#define krealloc(...) alloc_hooks(krealloc_noprof(__VA_ARGS__)) + void kfree(const void *objp); void kfree_sensitive(const void *objp); size_t __ksize(const void *objp); @@ -394,7 +407,7 @@ enum kmalloc_cache_type { #ifndef CONFIG_ZONE_DMA KMALLOC_DMA = KMALLOC_NORMAL, #endif -#ifndef CONFIG_MEMCG_KMEM +#ifndef CONFIG_MEMCG KMALLOC_CGROUP = KMALLOC_NORMAL, #endif KMALLOC_RANDOM_START = KMALLOC_NORMAL, @@ -407,14 +420,15 @@ enum kmalloc_cache_type { #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, #endif -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG KMALLOC_CGROUP, #endif NR_KMALLOC_TYPES }; -extern struct kmem_cache * -kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; +typedef struct kmem_cache * kmem_buckets[KMALLOC_SHIFT_HIGH + 1]; + +extern kmem_buckets kmalloc_caches[NR_KMALLOC_TYPES]; /* * Define gfp bits that should not be set for KMALLOC_NORMAL. @@ -422,7 +436,7 @@ kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; #define KMALLOC_NOT_NORMAL_BITS \ (__GFP_RECLAIMABLE | \ (IS_ENABLED(CONFIG_ZONE_DMA) ? __GFP_DMA : 0) | \ - (IS_ENABLED(CONFIG_MEMCG_KMEM) ? __GFP_ACCOUNT : 0)) + (IS_ENABLED(CONFIG_MEMCG) ? __GFP_ACCOUNT : 0)) extern unsigned long random_kmalloc_seed; @@ -450,7 +464,7 @@ static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags, unsigne */ if (IS_ENABLED(CONFIG_ZONE_DMA) && (flags & __GFP_DMA)) return KMALLOC_DMA; - if (!IS_ENABLED(CONFIG_MEMCG_KMEM) || (flags & __GFP_RECLAIMABLE)) + if (!IS_ENABLED(CONFIG_MEMCG) || (flags & __GFP_RECLAIMABLE)) return KMALLOC_RECLAIM; else return KMALLOC_CGROUP; @@ -513,7 +527,7 @@ static __always_inline unsigned int __kmalloc_index(size_t size, static_assert(PAGE_SHIFT <= 20); #define kmalloc_index(s) __kmalloc_index(s, true) -void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1); +#include <linux/alloc_tag.h> /** * kmem_cache_alloc - Allocate an object @@ -525,11 +539,20 @@ void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_siz * * Return: pointer to the new object or %NULL in case of error */ -void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) __assume_slab_alignment __malloc; -void *kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru, - gfp_t gfpflags) __assume_slab_alignment __malloc; +void *kmem_cache_alloc_noprof(struct kmem_cache *cachep, + gfp_t flags) __assume_slab_alignment __malloc; +#define kmem_cache_alloc(...) alloc_hooks(kmem_cache_alloc_noprof(__VA_ARGS__)) + +void *kmem_cache_alloc_lru_noprof(struct kmem_cache *s, struct list_lru *lru, + gfp_t gfpflags) __assume_slab_alignment __malloc; +#define kmem_cache_alloc_lru(...) alloc_hooks(kmem_cache_alloc_lru_noprof(__VA_ARGS__)) + void kmem_cache_free(struct kmem_cache *s, void *objp); +kmem_buckets *kmem_buckets_create(const char *name, slab_flags_t flags, + unsigned int useroffset, unsigned int usersize, + void (*ctor)(void *)); + /* * Bulk allocation and freeing operations. These are accelerated in an * allocator specific way to avoid taking locks repeatedly or building @@ -538,29 +561,58 @@ void kmem_cache_free(struct kmem_cache *s, void *objp); * Note that interrupts must be enabled when calling these functions. */ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p); -int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void **p); + +int kmem_cache_alloc_bulk_noprof(struct kmem_cache *s, gfp_t flags, size_t size, void **p); +#define kmem_cache_alloc_bulk(...) alloc_hooks(kmem_cache_alloc_bulk_noprof(__VA_ARGS__)) static __always_inline void kfree_bulk(size_t size, void **p) { kmem_cache_free_bulk(NULL, size, p); } -void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment - __alloc_size(1); -void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment - __malloc; +void *kmem_cache_alloc_node_noprof(struct kmem_cache *s, gfp_t flags, + int node) __assume_slab_alignment __malloc; +#define kmem_cache_alloc_node(...) alloc_hooks(kmem_cache_alloc_node_noprof(__VA_ARGS__)) -void *kmalloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) - __assume_kmalloc_alignment __alloc_size(3); +/* + * These macros allow declaring a kmem_buckets * parameter alongside size, which + * can be compiled out with CONFIG_SLAB_BUCKETS=n so that a large number of call + * sites don't have to pass NULL. + */ +#ifdef CONFIG_SLAB_BUCKETS +#define DECL_BUCKET_PARAMS(_size, _b) size_t (_size), kmem_buckets *(_b) +#define PASS_BUCKET_PARAMS(_size, _b) (_size), (_b) +#define PASS_BUCKET_PARAM(_b) (_b) +#else +#define DECL_BUCKET_PARAMS(_size, _b) size_t (_size) +#define PASS_BUCKET_PARAMS(_size, _b) (_size) +#define PASS_BUCKET_PARAM(_b) NULL +#endif + +/* + * The following functions are not to be used directly and are intended only + * for internal use from kmalloc() and kmalloc_node() + * with the exception of kunit tests + */ + +void *__kmalloc_noprof(size_t size, gfp_t flags) + __assume_kmalloc_alignment __alloc_size(1); + +void *__kmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node) + __assume_kmalloc_alignment __alloc_size(1); -void *kmalloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node, size_t size) __assume_kmalloc_alignment - __alloc_size(4); -void *kmalloc_large(size_t size, gfp_t flags) __assume_page_alignment - __alloc_size(1); +void *__kmalloc_cache_noprof(struct kmem_cache *s, gfp_t flags, size_t size) + __assume_kmalloc_alignment __alloc_size(3); -void *kmalloc_large_node(size_t size, gfp_t flags, int node) __assume_page_alignment - __alloc_size(1); +void *__kmalloc_cache_node_noprof(struct kmem_cache *s, gfp_t gfpflags, + int node, size_t size) + __assume_kmalloc_alignment __alloc_size(4); + +void *__kmalloc_large_noprof(size_t size, gfp_t flags) + __assume_page_alignment __alloc_size(1); + +void *__kmalloc_large_node_noprof(size_t size, gfp_t flags, int node) + __assume_page_alignment __alloc_size(1); /** * kmalloc - allocate kernel memory @@ -572,7 +624,8 @@ void *kmalloc_large_node(size_t size, gfp_t flags, int node) __assume_page_align * * The allocated object address is aligned to at least ARCH_KMALLOC_MINALIGN * bytes. For @size of power of two bytes, the alignment is also guaranteed - * to be at least to the size. + * to be at least to the size. For other sizes, the alignment is guaranteed to + * be at least the largest power-of-two divisor of @size. * * The @flags argument may be one of the GFP flags defined at * include/linux/gfp_types.h and described at @@ -616,37 +669,45 @@ void *kmalloc_large_node(size_t size, gfp_t flags, int node) __assume_page_align * Try really hard to succeed the allocation but fail * eventually. */ -static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags) +static __always_inline __alloc_size(1) void *kmalloc_noprof(size_t size, gfp_t flags) { if (__builtin_constant_p(size) && size) { unsigned int index; if (size > KMALLOC_MAX_CACHE_SIZE) - return kmalloc_large(size, flags); + return __kmalloc_large_noprof(size, flags); index = kmalloc_index(size); - return kmalloc_trace( + return __kmalloc_cache_noprof( kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index], flags, size); } - return __kmalloc(size, flags); + return __kmalloc_noprof(size, flags); } +#define kmalloc(...) alloc_hooks(kmalloc_noprof(__VA_ARGS__)) + +#define kmem_buckets_alloc(_b, _size, _flags) \ + alloc_hooks(__kmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE)) -static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t flags, int node) +#define kmem_buckets_alloc_track_caller(_b, _size, _flags) \ + alloc_hooks(__kmalloc_node_track_caller_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE, _RET_IP_)) + +static __always_inline __alloc_size(1) void *kmalloc_node_noprof(size_t size, gfp_t flags, int node) { if (__builtin_constant_p(size) && size) { unsigned int index; if (size > KMALLOC_MAX_CACHE_SIZE) - return kmalloc_large_node(size, flags, node); + return __kmalloc_large_node_noprof(size, flags, node); index = kmalloc_index(size); - return kmalloc_node_trace( + return __kmalloc_cache_node_noprof( kmalloc_caches[kmalloc_type(flags, _RET_IP_)][index], flags, node, size); } - return __kmalloc_node(size, flags, node); + return __kmalloc_node_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node); } +#define kmalloc_node(...) alloc_hooks(kmalloc_node_noprof(__VA_ARGS__)) /** * kmalloc_array - allocate memory for an array. @@ -654,16 +715,17 @@ static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t fla * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ -static inline __alloc_size(1, 2) void *kmalloc_array(size_t n, size_t size, gfp_t flags) +static inline __alloc_size(1, 2) void *kmalloc_array_noprof(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) - return kmalloc(bytes, flags); - return __kmalloc(bytes, flags); + return kmalloc_noprof(bytes, flags); + return kmalloc_noprof(bytes, flags); } +#define kmalloc_array(...) alloc_hooks(kmalloc_array_noprof(__VA_ARGS__)) /** * krealloc_array - reallocate memory for an array. @@ -672,18 +734,19 @@ static inline __alloc_size(1, 2) void *kmalloc_array(size_t n, size_t size, gfp_ * @new_size: new size of a single member of the array * @flags: the type of memory to allocate (see kmalloc) */ -static inline __realloc_size(2, 3) void * __must_check krealloc_array(void *p, - size_t new_n, - size_t new_size, - gfp_t flags) +static inline __realloc_size(2, 3) void * __must_check krealloc_array_noprof(void *p, + size_t new_n, + size_t new_size, + gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(new_n, new_size, &bytes))) return NULL; - return krealloc(p, bytes, flags); + return krealloc_noprof(p, bytes, flags); } +#define krealloc_array(...) alloc_hooks(krealloc_array_noprof(__VA_ARGS__)) /** * kcalloc - allocate memory for an array. The memory is set to zero. @@ -691,16 +754,14 @@ static inline __realloc_size(2, 3) void * __must_check krealloc_array(void *p, * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ -static inline __alloc_size(1, 2) void *kcalloc(size_t n, size_t size, gfp_t flags) -{ - return kmalloc_array(n, size, flags | __GFP_ZERO); -} +#define kcalloc(n, size, flags) kmalloc_array(n, size, (flags) | __GFP_ZERO) -void *__kmalloc_node_track_caller(size_t size, gfp_t flags, int node, - unsigned long caller) __alloc_size(1); -#define kmalloc_node_track_caller(size, flags, node) \ - __kmalloc_node_track_caller(size, flags, node, \ - _RET_IP_) +void *__kmalloc_node_track_caller_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node, + unsigned long caller) __alloc_size(1); +#define kmalloc_node_track_caller_noprof(size, flags, node, caller) \ + __kmalloc_node_track_caller_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node, caller) +#define kmalloc_node_track_caller(...) \ + alloc_hooks(kmalloc_node_track_caller_noprof(__VA_ARGS__, _RET_IP_)) /* * kmalloc_track_caller is a special version of kmalloc that records the @@ -710,11 +771,12 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t flags, int node, * allocator where we care about the real place the memory allocation * request comes from. */ -#define kmalloc_track_caller(size, flags) \ - __kmalloc_node_track_caller(size, flags, \ - NUMA_NO_NODE, _RET_IP_) +#define kmalloc_track_caller(...) kmalloc_node_track_caller(__VA_ARGS__, NUMA_NO_NODE) + +#define kmalloc_track_caller_noprof(...) \ + kmalloc_node_track_caller_noprof(__VA_ARGS__, NUMA_NO_NODE, _RET_IP_) -static inline __alloc_size(1, 2) void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, +static inline __alloc_size(1, 2) void *kmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; @@ -722,75 +784,67 @@ static inline __alloc_size(1, 2) void *kmalloc_array_node(size_t n, size_t size, if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; if (__builtin_constant_p(n) && __builtin_constant_p(size)) - return kmalloc_node(bytes, flags, node); - return __kmalloc_node(bytes, flags, node); + return kmalloc_node_noprof(bytes, flags, node); + return __kmalloc_node_noprof(PASS_BUCKET_PARAMS(bytes, NULL), flags, node); } +#define kmalloc_array_node(...) alloc_hooks(kmalloc_array_node_noprof(__VA_ARGS__)) -static inline __alloc_size(1, 2) void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) -{ - return kmalloc_array_node(n, size, flags | __GFP_ZERO, node); -} +#define kcalloc_node(_n, _size, _flags, _node) \ + kmalloc_array_node(_n, _size, (_flags) | __GFP_ZERO, _node) /* * Shortcuts */ -static inline void *kmem_cache_zalloc(struct kmem_cache *k, gfp_t flags) -{ - return kmem_cache_alloc(k, flags | __GFP_ZERO); -} +#define kmem_cache_zalloc(_k, _flags) kmem_cache_alloc(_k, (_flags)|__GFP_ZERO) /** * kzalloc - allocate memory. The memory is set to zero. * @size: how many bytes of memory are required. * @flags: the type of memory to allocate (see kmalloc). */ -static inline __alloc_size(1) void *kzalloc(size_t size, gfp_t flags) +static inline __alloc_size(1) void *kzalloc_noprof(size_t size, gfp_t flags) { - return kmalloc(size, flags | __GFP_ZERO); + return kmalloc_noprof(size, flags | __GFP_ZERO); } +#define kzalloc(...) alloc_hooks(kzalloc_noprof(__VA_ARGS__)) +#define kzalloc_node(_size, _flags, _node) kmalloc_node(_size, (_flags)|__GFP_ZERO, _node) -/** - * kzalloc_node - allocate zeroed memory from a particular memory node. - * @size: how many bytes of memory are required. - * @flags: the type of memory to allocate (see kmalloc). - * @node: memory node from which to allocate - */ -static inline __alloc_size(1) void *kzalloc_node(size_t size, gfp_t flags, int node) -{ - return kmalloc_node(size, flags | __GFP_ZERO, node); -} +void *__kvmalloc_node_noprof(DECL_BUCKET_PARAMS(size, b), gfp_t flags, int node) __alloc_size(1); +#define kvmalloc_node_noprof(size, flags, node) \ + __kvmalloc_node_noprof(PASS_BUCKET_PARAMS(size, NULL), flags, node) +#define kvmalloc_node(...) alloc_hooks(kvmalloc_node_noprof(__VA_ARGS__)) -extern void *kvmalloc_node(size_t size, gfp_t flags, int node) __alloc_size(1); -static inline __alloc_size(1) void *kvmalloc(size_t size, gfp_t flags) -{ - return kvmalloc_node(size, flags, NUMA_NO_NODE); -} -static inline __alloc_size(1) void *kvzalloc_node(size_t size, gfp_t flags, int node) -{ - return kvmalloc_node(size, flags | __GFP_ZERO, node); -} -static inline __alloc_size(1) void *kvzalloc(size_t size, gfp_t flags) -{ - return kvmalloc(size, flags | __GFP_ZERO); -} +#define kvmalloc(_size, _flags) kvmalloc_node(_size, _flags, NUMA_NO_NODE) +#define kvmalloc_noprof(_size, _flags) kvmalloc_node_noprof(_size, _flags, NUMA_NO_NODE) +#define kvzalloc(_size, _flags) kvmalloc(_size, (_flags)|__GFP_ZERO) -static inline __alloc_size(1, 2) void *kvmalloc_array(size_t n, size_t size, gfp_t flags) +#define kvzalloc_node(_size, _flags, _node) kvmalloc_node(_size, (_flags)|__GFP_ZERO, _node) +#define kmem_buckets_valloc(_b, _size, _flags) \ + alloc_hooks(__kvmalloc_node_noprof(PASS_BUCKET_PARAMS(_size, _b), _flags, NUMA_NO_NODE)) + +static inline __alloc_size(1, 2) void * +kvmalloc_array_node_noprof(size_t n, size_t size, gfp_t flags, int node) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; - return kvmalloc(bytes, flags); + return kvmalloc_node_noprof(bytes, flags, node); } -static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t flags) -{ - return kvmalloc_array(n, size, flags | __GFP_ZERO); -} +#define kvmalloc_array_noprof(...) kvmalloc_array_node_noprof(__VA_ARGS__, NUMA_NO_NODE) +#define kvcalloc_node_noprof(_n,_s,_f,_node) kvmalloc_array_node_noprof(_n,_s,(_f)|__GFP_ZERO,_node) +#define kvcalloc_noprof(...) kvcalloc_node_noprof(__VA_ARGS__, NUMA_NO_NODE) -extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags) +#define kvmalloc_array(...) alloc_hooks(kvmalloc_array_noprof(__VA_ARGS__)) +#define kvcalloc_node(...) alloc_hooks(kvcalloc_node_noprof(__VA_ARGS__)) +#define kvcalloc(...) alloc_hooks(kvcalloc_noprof(__VA_ARGS__)) + +extern void *kvrealloc_noprof(const void *p, size_t oldsize, size_t newsize, gfp_t flags) __realloc_size(3); +#define kvrealloc(...) alloc_hooks(kvrealloc_noprof(__VA_ARGS__)) + extern void kvfree(const void *addr); DEFINE_FREE(kvfree, void *, if (!IS_ERR_OR_NULL(_T)) kvfree(_T)) diff --git a/include/linux/slimbus.h b/include/linux/slimbus.h index 3042385b7b40..a4608d9a9684 100644 --- a/include/linux/slimbus.h +++ b/include/linux/slimbus.h @@ -91,7 +91,7 @@ struct slim_driver { struct device_driver driver; const struct slim_device_id *id_table; }; -#define to_slim_driver(d) container_of(d, struct slim_driver, driver) +#define to_slim_driver(d) container_of_const(d, struct slim_driver, driver) /** * struct slim_val_inf - Slimbus value or information element diff --git a/include/linux/soc/apple/rtkit.h b/include/linux/soc/apple/rtkit.h index 8c9ca857ccf6..c06d17599ae7 100644 --- a/include/linux/soc/apple/rtkit.h +++ b/include/linux/soc/apple/rtkit.h @@ -69,7 +69,7 @@ struct apple_rtkit; * Initializes the internal state required to handle RTKit. This * should usually be called within _probe. * - * @dev: Pointer to the device node this coprocessor is assocated with + * @dev: Pointer to the device node this coprocessor is associated with * @cookie: opaque cookie passed to all functions defined in rtkit_ops * @mbox_name: mailbox name used to communicate with the co-processor * @mbox_idx: mailbox index to be used if mbox_name is NULL @@ -83,7 +83,7 @@ struct apple_rtkit *devm_apple_rtkit_init(struct device *dev, void *cookie, * Non-devm version of devm_apple_rtkit_init. Must be freed with * apple_rtkit_free. * - * @dev: Pointer to the device node this coprocessor is assocated with + * @dev: Pointer to the device node this coprocessor is associated with * @cookie: opaque cookie passed to all functions defined in rtkit_ops * @mbox_name: mailbox name used to communicate with the co-processor * @mbox_idx: mailbox index to be used if mbox_name is NULL diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index 649955d2cf5c..5bee6f7fc400 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -14,8 +14,42 @@ #define CMDQ_ADDR_HIGH(addr) ((u32)(((addr) >> 16) & GENMASK(31, 0))) #define CMDQ_ADDR_LOW(addr) ((u16)(addr) | BIT(1)) +/* + * Every cmdq thread has its own SPRs (Specific Purpose Registers), + * so there are 4 * N (threads) SPRs in GCE that shares the same indexes below. + */ +#define CMDQ_THR_SPR_IDX0 (0) +#define CMDQ_THR_SPR_IDX1 (1) +#define CMDQ_THR_SPR_IDX2 (2) +#define CMDQ_THR_SPR_IDX3 (3) + struct cmdq_pkt; +enum cmdq_logic_op { + CMDQ_LOGIC_ASSIGN = 0, + CMDQ_LOGIC_ADD = 1, + CMDQ_LOGIC_SUBTRACT = 2, + CMDQ_LOGIC_MULTIPLY = 3, + CMDQ_LOGIC_XOR = 8, + CMDQ_LOGIC_NOT = 9, + CMDQ_LOGIC_OR = 10, + CMDQ_LOGIC_AND = 11, + CMDQ_LOGIC_LEFT_SHIFT = 12, + CMDQ_LOGIC_RIGHT_SHIFT = 13, + CMDQ_LOGIC_MAX, +}; + +struct cmdq_operand { + /* register type */ + bool reg; + union { + /* index */ + u16 idx; + /* value */ + u16 value; + }; +}; + struct cmdq_client_reg { u8 subsys; u16 offset; @@ -62,17 +96,19 @@ void cmdq_mbox_destroy(struct cmdq_client *client); /** * cmdq_pkt_create() - create a CMDQ packet * @client: the CMDQ mailbox client + * @pkt: the CMDQ packet * @size: required CMDQ buffer size * - * Return: CMDQ packet pointer + * Return: 0 for success; else the error code is returned */ -struct cmdq_pkt *cmdq_pkt_create(struct cmdq_client *client, size_t size); +int cmdq_pkt_create(struct cmdq_client *client, struct cmdq_pkt *pkt, size_t size); /** * cmdq_pkt_destroy() - destroy the CMDQ packet + * @client: the CMDQ mailbox client * @pkt: the CMDQ packet */ -void cmdq_pkt_destroy(struct cmdq_pkt *pkt); +void cmdq_pkt_destroy(struct cmdq_client *client, struct cmdq_pkt *pkt); /** * cmdq_pkt_write() - append write command to the CMDQ packet @@ -174,6 +210,18 @@ int cmdq_pkt_write_s_mask_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx, u16 addr_low, u32 value, u32 mask); /** + * cmdq_pkt_mem_move() - append memory move command to the CMDQ packet + * @pkt: the CMDQ packet + * @src_addr: source address + * @dst_addr: destination address + * + * Appends a CMDQ command to copy the value found in `src_addr` to `dst_addr`. + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_mem_move(struct cmdq_pkt *pkt, dma_addr_t src_addr, dma_addr_t dst_addr); + +/** * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet * @pkt: the CMDQ packet * @event: the desired event type to wait @@ -184,6 +232,21 @@ int cmdq_pkt_write_s_mask_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx, int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event, bool clear); /** + * cmdq_pkt_acquire_event() - append acquire event command to the CMDQ packet + * @pkt: the CMDQ packet + * @event: the desired event to be acquired + * + * User can use cmdq_pkt_acquire_event() as `mutex_lock` and cmdq_pkt_clear_event() + * as `mutex_unlock` to protect some `critical section` instructions between them. + * cmdq_pkt_acquire_event() would wait for event to be cleared. + * After event is cleared by cmdq_pkt_clear_event in other GCE threads, + * cmdq_pkt_acquire_event() would set event and keep executing next instruction. + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_acquire_event(struct cmdq_pkt *pkt, u16 event); + +/** * cmdq_pkt_clear_event() - append clear event command to the CMDQ packet * @pkt: the CMDQ packet * @event: the desired event to be cleared @@ -235,6 +298,23 @@ int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys, u16 offset, u32 value, u32 mask); /** + * cmdq_pkt_logic_command() - Append logic command to the CMDQ packet, ask GCE to + * execute an instruction that store the result of logic operation + * with left and right operand into result_reg_idx. + * @pkt: the CMDQ packet + * @result_reg_idx: SPR index that store operation result of left_operand and right_operand + * @left_operand: left operand + * @s_op: the logic operator enum + * @right_operand: right operand + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_logic_command(struct cmdq_pkt *pkt, u16 result_reg_idx, + struct cmdq_operand *left_operand, + enum cmdq_logic_op s_op, + struct cmdq_operand *right_operand); + +/** * cmdq_pkt_assign() - Append logic assign command to the CMDQ packet, ask GCE * to execute an instruction that set a constant value into * internal register and use as value, mask or address in @@ -248,36 +328,76 @@ int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys, int cmdq_pkt_assign(struct cmdq_pkt *pkt, u16 reg_idx, u32 value); /** - * cmdq_pkt_jump() - Append jump command to the CMDQ packet, ask GCE - * to execute an instruction that change current thread PC to - * a physical address which should contains more instruction. + * cmdq_pkt_poll_addr() - Append blocking POLL command to CMDQ packet + * @pkt: the CMDQ packet + * @addr: the hardware register address + * @value: the specified target register value + * @mask: the specified target register mask + * + * Appends a polling (POLL) command to the CMDQ packet and asks the GCE + * to execute an instruction that checks for the specified `value` (with + * or without `mask`) to appear in the specified hardware register `addr`. + * All GCE threads will be blocked by this instruction. + * + * Return: 0 for success or negative error code + */ +int cmdq_pkt_poll_addr(struct cmdq_pkt *pkt, dma_addr_t addr, u32 value, u32 mask); + +/** + * cmdq_pkt_jump_abs() - Append jump command to the CMDQ packet, ask GCE + * to execute an instruction that change current thread + * PC to a absolute physical address which should + * contains more instruction. * @pkt: the CMDQ packet - * @addr: physical address of target instruction buffer + * @addr: absolute physical address of target instruction buffer + * @shift_pa: shift bits of physical address in CMDQ instruction. This value + * is got by cmdq_get_shift_pa(). * * Return: 0 for success; else the error code is returned */ -int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr); +int cmdq_pkt_jump_abs(struct cmdq_pkt *pkt, dma_addr_t addr, u8 shift_pa); + +/* This wrapper has to be removed after all users migrated to jump_abs */ +static inline int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr, u8 shift_pa) +{ + return cmdq_pkt_jump_abs(pkt, addr, shift_pa); +} /** - * cmdq_pkt_finalize() - Append EOC and jump command to pkt. + * cmdq_pkt_jump_rel() - Append jump command to the CMDQ packet, ask GCE + * to execute an instruction that change current thread + * PC to a physical address with relative offset. The + * target address should contains more instruction. * @pkt: the CMDQ packet + * @offset: relative offset of target instruction buffer from current PC. + * @shift_pa: shift bits of physical address in CMDQ instruction. This value + * is got by cmdq_get_shift_pa(). * * Return: 0 for success; else the error code is returned */ -int cmdq_pkt_finalize(struct cmdq_pkt *pkt); +int cmdq_pkt_jump_rel(struct cmdq_pkt *pkt, s32 offset, u8 shift_pa); /** - * cmdq_pkt_flush_async() - trigger CMDQ to asynchronously execute the CMDQ - * packet and call back at the end of done packet + * cmdq_pkt_eoc() - Append EOC and ask GCE to generate an IRQ at end of execution + * @pkt: The CMDQ packet + * + * Appends an End Of Code (EOC) command to the CMDQ packet and asks the GCE + * to generate an interrupt at the end of the execution of all commands in + * the pipeline. + * The EOC command is usually appended to the end of the pipeline to notify + * that all commands are done. + * + * Return: 0 for success or negative error number + */ +int cmdq_pkt_eoc(struct cmdq_pkt *pkt); + +/** + * cmdq_pkt_finalize() - Append EOC and jump command to pkt. * @pkt: the CMDQ packet * * Return: 0 for success; else the error code is returned - * - * Trigger CMDQ to asynchronously execute the CMDQ packet and call back - * at the end of done packet. Note that this is an ASYNC function. When the - * function returned, it may or may not be finished. */ -int cmdq_pkt_flush_async(struct cmdq_pkt *pkt); +int cmdq_pkt_finalize(struct cmdq_pkt *pkt); #else /* IS_ENABLED(CONFIG_MTK_CMDQ) */ @@ -294,12 +414,12 @@ static inline struct cmdq_client *cmdq_mbox_create(struct device *dev, int index static inline void cmdq_mbox_destroy(struct cmdq_client *client) { } -static inline struct cmdq_pkt *cmdq_pkt_create(struct cmdq_client *client, size_t size) +static inline int cmdq_pkt_create(struct cmdq_client *client, struct cmdq_pkt *pkt, size_t size) { - return ERR_PTR(-EINVAL); + return -EINVAL; } -static inline void cmdq_pkt_destroy(struct cmdq_pkt *pkt) { } +static inline void cmdq_pkt_destroy(struct cmdq_client *client, struct cmdq_pkt *pkt) { } static inline int cmdq_pkt_write(struct cmdq_pkt *pkt, u8 subsys, u16 offset, u32 value) { @@ -374,17 +494,32 @@ static inline int cmdq_pkt_assign(struct cmdq_pkt *pkt, u16 reg_idx, u32 value) return -EINVAL; } -static inline int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr) +static inline int cmdq_pkt_poll_addr(struct cmdq_pkt *pkt, dma_addr_t addr, u32 value, u32 mask) { return -EINVAL; } -static inline int cmdq_pkt_finalize(struct cmdq_pkt *pkt) +static inline int cmdq_pkt_jump_abs(struct cmdq_pkt *pkt, dma_addr_t addr, u8 shift_pa) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr, u8 shift_pa) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_jump_rel(struct cmdq_pkt *pkt, s32 offset, u8 shift_pa) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_eoc(struct cmdq_pkt *pkt) { return -EINVAL; } -static inline int cmdq_pkt_flush_async(struct cmdq_pkt *pkt) +static inline int cmdq_pkt_finalize(struct cmdq_pkt *pkt) { return -EINVAL; } diff --git a/include/linux/soc/qcom/apr.h b/include/linux/soc/qcom/apr.h index 7161a3183eda..a532d1e4b1f4 100644 --- a/include/linux/soc/qcom/apr.h +++ b/include/linux/soc/qcom/apr.h @@ -162,7 +162,7 @@ struct apr_driver { }; typedef struct apr_driver gpr_driver_t; -#define to_apr_driver(d) container_of(d, struct apr_driver, driver) +#define to_apr_driver(d) container_of_const(d, struct apr_driver, driver) /* * use a macro to avoid include chaining to get THIS_MODULE diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index 1a886666bbb6..9e9f528b1370 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -115,7 +115,8 @@ struct llcc_edac_reg_offset { /** * struct llcc_drv_data - Data associated with the llcc driver * @regmaps: regmaps associated with the llcc device - * @bcast_regmap: regmap associated with llcc broadcast offset + * @bcast_regmap: regmap associated with llcc broadcast OR offset + * @bcast_and_regmap: regmap associated with llcc broadcast AND offset * @cfg: pointer to the data structure for slice configuration * @edac_reg_offset: Offset of the LLCC EDAC registers * @lock: mutex associated with each slice @@ -129,6 +130,7 @@ struct llcc_edac_reg_offset { struct llcc_drv_data { struct regmap **regmaps; struct regmap *bcast_regmap; + struct regmap *bcast_and_regmap; const struct llcc_slice_config *cfg; const struct llcc_edac_reg_offset *edac_reg_offset; struct mutex lock; diff --git a/include/linux/soc/qcom/smem.h b/include/linux/soc/qcom/smem.h index a36a3b9d4929..f946e3beca21 100644 --- a/include/linux/soc/qcom/smem.h +++ b/include/linux/soc/qcom/smem.h @@ -13,5 +13,8 @@ int qcom_smem_get_free_space(unsigned host); phys_addr_t qcom_smem_virt_to_phys(void *p); int qcom_smem_get_soc_id(u32 *id); +int qcom_smem_get_feature_code(u32 *code); + +int qcom_smem_bust_hwspin_lock_by_host(unsigned int host); #endif diff --git a/include/linux/soc/qcom/socinfo.h b/include/linux/soc/qcom/socinfo.h index e78777bb0f4a..608950443eee 100644 --- a/include/linux/soc/qcom/socinfo.h +++ b/include/linux/soc/qcom/socinfo.h @@ -3,6 +3,8 @@ #ifndef __QCOM_SOCINFO_H__ #define __QCOM_SOCINFO_H__ +#include <linux/types.h> + /* * SMEM item id, used to acquire handles to respective * SMEM region. @@ -12,6 +14,14 @@ #define SMEM_SOCINFO_BUILD_ID_LENGTH 32 #define SMEM_SOCINFO_CHIP_ID_LENGTH 32 +/* + * SoC version type with major number in the upper 16 bits and minor + * number in the lower 16 bits. + */ +#define SOCINFO_MAJOR(ver) (((ver) >> 16) & 0xffff) +#define SOCINFO_MINOR(ver) ((ver) & 0xffff) +#define SOCINFO_VERSION(maj, min) ((((maj) & 0xffff) << 16)|((min) & 0xffff)) + /* Socinfo SMEM item structure */ struct socinfo { __le32 fmt; @@ -74,4 +84,28 @@ struct socinfo { __le32 boot_core; }; +/* Internal feature codes */ +enum qcom_socinfo_feature_code { + /* External feature codes */ + SOCINFO_FC_UNKNOWN = 0x0, + SOCINFO_FC_AA, + SOCINFO_FC_AB, + SOCINFO_FC_AC, + SOCINFO_FC_AD, + SOCINFO_FC_AE, + SOCINFO_FC_AF, + SOCINFO_FC_AG, + SOCINFO_FC_AH, +}; + +/* Internal feature codes */ +/* Valid values: 0 <= n <= 0xf */ +#define SOCINFO_FC_Yn(n) (0xf1 + (n)) +#define SOCINFO_FC_INT_MAX SOCINFO_FC_Yn(0xf) + +/* Product codes */ +#define SOCINFO_PC_UNKNOWN 0 +#define SOCINFO_PCn(n) ((n) + 1) +#define SOCINFO_PC_RESERVE (BIT(31) - 1) + #endif diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h index aa840ed043e1..ce1a3790d6fb 100644 --- a/include/linux/soc/samsung/exynos-regs-pmu.h +++ b/include/linux/soc/samsung/exynos-regs-pmu.h @@ -657,4 +657,10 @@ #define EXYNOS5433_PAD_RETENTION_UFS_OPTION (0x3268) #define EXYNOS5433_PAD_RETENTION_FSYSGENIO_OPTION (0x32A8) +/* For Tensor GS101 */ +#define GS101_SYSIP_DAT0 (0x810) +#define GS101_SYSTEM_CONFIGURATION (0x3A00) +#define GS101_PHY_CTRL_USB20 (0x3EB0) +#define GS101_PHY_CTRL_USBDP (0x3EB4) + #endif /* __LINUX_SOC_EXYNOS_REGS_PMU_H */ diff --git a/include/linux/socket.h b/include/linux/socket.h index 139c330ccf2c..df9cdb8bbfb8 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -16,6 +16,7 @@ struct cred; struct socket; struct sock; struct sk_buff; +struct proto_accept_arg; #define __sockaddr_check_size(size) \ BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage))) @@ -75,7 +76,7 @@ struct msghdr { __kernel_size_t msg_controllen; /* ancillary data buffer length */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ struct ubuf_info *msg_ubuf; - int (*sg_from_iter)(struct sock *sk, struct sk_buff *skb, + int (*sg_from_iter)(struct sk_buff *skb, struct iov_iter *from, size_t length); }; @@ -433,7 +434,7 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, extern int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr __user *addr, int addr_len); -extern struct file *do_accept(struct file *file, unsigned file_flags, +extern struct file *do_accept(struct file *file, struct proto_accept_arg *arg, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, @@ -441,11 +442,14 @@ extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, extern int __sys_socket(int family, int type, int protocol); extern struct file *__sys_socket_file(int family, int type, int protocol); extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen); +extern int __sys_bind_socket(struct socket *sock, struct sockaddr_storage *address, + int addrlen); extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr, int addrlen, int file_flags); extern int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen); extern int __sys_listen(int fd, int backlog); +extern int __sys_listen_socket(struct socket *sock, int backlog); extern int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len); extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr, diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index 317200cd3a60..fc5a206c4043 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -117,9 +117,9 @@ static inline int copy_to_sockptr(sockptr_t dst, const void *src, size_t size) return copy_to_sockptr_offset(dst, 0, src, size); } -static inline void *memdup_sockptr(sockptr_t src, size_t len) +static inline void *memdup_sockptr_noprof(sockptr_t src, size_t len) { - void *p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN); + void *p = kmalloc_track_caller_noprof(len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); @@ -129,10 +129,11 @@ static inline void *memdup_sockptr(sockptr_t src, size_t len) } return p; } +#define memdup_sockptr(...) alloc_hooks(memdup_sockptr_noprof(__VA_ARGS__)) -static inline void *memdup_sockptr_nul(sockptr_t src, size_t len) +static inline void *memdup_sockptr_nul_noprof(sockptr_t src, size_t len) { - char *p = kmalloc_track_caller(len + 1, GFP_KERNEL); + char *p = kmalloc_track_caller_noprof(len + 1, GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); @@ -143,6 +144,7 @@ static inline void *memdup_sockptr_nul(sockptr_t src, size_t len) p[len] = '\0'; return p; } +#define memdup_sockptr_nul(...) alloc_hooks(memdup_sockptr_nul_noprof(__VA_ARGS__)) static inline long strncpy_from_sockptr(char *dst, sockptr_t src, size_t count) { diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 66f814b63a43..94fc1b57c57b 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -235,6 +235,7 @@ enum sdw_clk_stop_mode { * @BRA_flow_controlled: Slave implementation results in an OK_NotReady * response * @simple_ch_prep_sm: If channel prepare sequence is required + * @ch_prep_timeout: Port-specific timeout value, in milliseconds * @imp_def_interrupts: If set, each bit corresponds to support for * implementation-defined interrupts * @@ -249,6 +250,7 @@ struct sdw_dp0_prop { u32 *words; bool BRA_flow_controlled; bool simple_ch_prep_sm; + u32 ch_prep_timeout; bool imp_def_interrupts; }; @@ -543,21 +545,6 @@ enum sdw_reg_bank { }; /** - * struct sdw_bus_conf: Bus configuration - * - * @clk_freq: Clock frequency, in Hz - * @num_rows: Number of rows in frame - * @num_cols: Number of columns in frame - * @bank: Next register bank - */ -struct sdw_bus_conf { - unsigned int clk_freq; - unsigned int num_rows; - unsigned int num_cols; - unsigned int bank; -}; - -/** * struct sdw_prepare_ch: Prepare/De-prepare Data Port channel * * @num: Port number @@ -899,6 +886,7 @@ struct sdw_master_ops { * @port_ops: Master port callback ops * @params: Current bus parameters * @prop: Master properties + * @vendor_specific_prop: pointer to non-standard properties * @m_rt_list: List of Master instance of all stream(s) running on Bus. This * is used to compute and program bus bandwidth, clock, frame shape, * transport and port parameters @@ -915,6 +903,7 @@ struct sdw_master_ops { * meaningful if multi_link is set. If set to 1, hardware-based * synchronization will be used even if a stream only uses a single * SoundWire segment. + * @stream_refcount: number of streams currently using this bus */ struct sdw_bus { struct device *dev; @@ -933,6 +922,7 @@ struct sdw_bus { const struct sdw_master_port_ops *port_ops; struct sdw_bus_params params; struct sdw_master_prop prop; + void *vendor_specific_prop; struct list_head m_rt_list; #ifdef CONFIG_DEBUG_FS struct dentry *debugfs; @@ -944,6 +934,7 @@ struct sdw_bus { u32 bank_switch_timeout; bool multi_link; int hw_sync_min_links; + int stream_refcount; }; int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent, diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 00bb22d96ae5..d537587b4499 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -22,6 +22,7 @@ /* LCAP */ #define SDW_SHIM_LCAP 0x0 #define SDW_SHIM_LCAP_LCOUNT_MASK GENMASK(2, 0) +#define SDW_SHIM_LCAP_MLCS_MASK BIT(8) /* LCTL */ #define SDW_SHIM_LCTL 0x4 @@ -30,12 +31,18 @@ #define SDW_SHIM_LCTL_SPA_MASK GENMASK(3, 0) #define SDW_SHIM_LCTL_CPA BIT(8) #define SDW_SHIM_LCTL_CPA_MASK GENMASK(11, 8) +#define SDW_SHIM_LCTL_MLCS_MASK GENMASK(29, 27) +#define SDW_SHIM_MLCS_XTAL_CLK 0x0 +#define SDW_SHIM_MLCS_CARDINAL_CLK 0x1 +#define SDW_SHIM_MLCS_AUDIO_PLL_CLK 0x2 /* SYNC */ #define SDW_SHIM_SYNC 0xC -#define SDW_SHIM_SYNC_SYNCPRD_VAL_24 (24000 / SDW_CADENCE_GSYNC_KHZ - 1) -#define SDW_SHIM_SYNC_SYNCPRD_VAL_38_4 (38400 / SDW_CADENCE_GSYNC_KHZ - 1) +#define SDW_SHIM_SYNC_SYNCPRD_VAL_24 (24000 / SDW_CADENCE_GSYNC_KHZ - 1) +#define SDW_SHIM_SYNC_SYNCPRD_VAL_24_576 (24576 / SDW_CADENCE_GSYNC_KHZ - 1) +#define SDW_SHIM_SYNC_SYNCPRD_VAL_38_4 (38400 / SDW_CADENCE_GSYNC_KHZ - 1) +#define SDW_SHIM_SYNC_SYNCPRD_VAL_96 (96000 / SDW_CADENCE_GSYNC_KHZ - 1) #define SDW_SHIM_SYNC_SYNCPRD GENMASK(14, 0) #define SDW_SHIM_SYNC_SYNCCPU BIT(15) #define SDW_SHIM_SYNC_CMDSYNC_MASK GENMASK(19, 16) @@ -175,6 +182,11 @@ #define SDW_SHIM2_INTEL_VS_ACTMCTL_DODSE BIT(2) #define SDW_SHIM2_INTEL_VS_ACTMCTL_DOAIS GENMASK(4, 3) #define SDW_SHIM2_INTEL_VS_ACTMCTL_DOAISE BIT(5) +#define SDW_SHIM3_INTEL_VS_ACTMCTL_CLSS BIT(6) +#define SDW_SHIM3_INTEL_VS_ACTMCTL_CLDS GENMASK(11, 7) +#define SDW_SHIM3_INTEL_VS_ACTMCTL_DODSE2 GENMASK(13, 12) +#define SDW_SHIM3_INTEL_VS_ACTMCTL_DOAISE2 BIT(14) +#define SDW_SHIM3_INTEL_VS_ACTMCTL_CLDE BIT(15) /** * struct sdw_intel_stream_params_data: configuration passed during diff --git a/include/linux/soundwire/sdw_registers.h b/include/linux/soundwire/sdw_registers.h index 138bec908c40..658b10fa5b20 100644 --- a/include/linux/soundwire/sdw_registers.h +++ b/include/linux/soundwire/sdw_registers.h @@ -13,7 +13,7 @@ #define SDW_REG_NO_PAGE 0x00008000 #define SDW_REG_OPTIONAL_PAGE 0x00010000 -#define SDW_REG_MAX 0x80000000 +#define SDW_REG_MAX 0x48000000 #define SDW_DPN_SIZE 0x100 #define SDW_BANK1_OFFSET 0x10 diff --git a/include/linux/soundwire/sdw_type.h b/include/linux/soundwire/sdw_type.h index 693320b4f5c2..d405935a45fe 100644 --- a/include/linux/soundwire/sdw_type.h +++ b/include/linux/soundwire/sdw_type.h @@ -13,7 +13,7 @@ static inline int is_sdw_slave(const struct device *dev) return dev->type == &sdw_slave_type; } -#define drv_to_sdw_driver(_drv) container_of(_drv, struct sdw_driver, driver) +#define drv_to_sdw_driver(_drv) container_of_const(_drv, struct sdw_driver, driver) #define sdw_register_driver(drv) \ __sdw_register_driver(drv, THIS_MODULE) diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h deleted file mode 100644 index ca2cd4e30ead..000000000000 --- a/include/linux/spi/pxa2xx_spi.h +++ /dev/null @@ -1,56 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Copyright (C) 2005 Stephen Street / StreetFire Sound Labs - */ -#ifndef __LINUX_SPI_PXA2XX_SPI_H -#define __LINUX_SPI_PXA2XX_SPI_H - -#include <linux/dmaengine.h> -#include <linux/types.h> - -#include <linux/pxa2xx_ssp.h> - -struct dma_chan; - -/* - * The platform data for SSP controller devices - * (resides in device.platform_data). - */ -struct pxa2xx_spi_controller { - u16 num_chipselect; - u8 enable_dma; - u8 dma_burst_size; - bool is_target; - - /* DMA engine specific config */ - dma_filter_fn dma_filter; - void *tx_param; - void *rx_param; - - /* For non-PXA arches */ - struct ssp_device ssp; -}; - -/* - * The controller specific data for SPI target devices - * (resides in spi_board_info.controller_data), - * copied to spi_device.platform_data ... mostly for - * DMA tuning. - */ -struct pxa2xx_spi_chip { - u8 tx_threshold; - u8 tx_hi_threshold; - u8 rx_threshold; - u8 dma_burst_size; - u32 timeout; -}; - -#if defined(CONFIG_ARCH_PXA) || defined(CONFIG_ARCH_MMP) - -#include <linux/clk.h> - -extern void pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_controller *info); - -#endif - -#endif /* __LINUX_SPI_PXA2XX_SPI_H */ diff --git a/include/linux/spi/rspi.h b/include/linux/spi/rspi.h deleted file mode 100644 index dbdfcc7a3db2..000000000000 --- a/include/linux/spi/rspi.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Renesas SPI driver - * - * Copyright (C) 2012 Renesas Solutions Corp. - */ - -#ifndef __LINUX_SPI_RENESAS_SPI_H__ -#define __LINUX_SPI_RENESAS_SPI_H__ - -struct rspi_plat_data { - unsigned int dma_tx_id; - unsigned int dma_rx_id; - - u16 num_chipselect; -}; - -#endif diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index c459809efee4..d47d5f14ff99 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -351,10 +351,8 @@ struct spi_driver { struct device_driver driver; }; -static inline struct spi_driver *to_spi_driver(struct device_driver *drv) -{ - return drv ? container_of(drv, struct spi_driver, driver) : NULL; -} +#define to_spi_driver(__drv) \ + ( __drv ? container_of_const(__drv, struct spi_driver, driver) : NULL ) extern int __spi_register_driver(struct module *owner, struct spi_driver *sdrv); @@ -447,12 +445,12 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @cur_msg_need_completion: Flag used internally to opportunistically skip * the @cur_msg_completion. This flag is used to signal the context that * is running spi_finalize_current_message() that it needs to complete() - * @cur_msg_mapped: message has been mapped for DMA * @fallback: fallback to PIO if DMA transfer return failure with * SPI_TRANS_FAIL_NO_START. * @last_cs_mode_high: was (mode & SPI_CS_HIGH) true on the last call to set_cs. * @last_cs: the last chip_select that is recorded by set_cs, -1 on non chip * selected + * @last_cs_index_mask: bit mask the last chip selects that were used * @xfer_completion: used by core transfer_one_message() * @busy: message pump is busy * @running: message pump is running @@ -532,6 +530,9 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch * @queue_empty: signal green light for opportunistically skipping the queue * for spi_sync transfers. * @must_async: disable all fast paths in the core + * @defer_optimize_message: set to true if controller cannot pre-optimize messages + * and needs to defer the optimization step until the message is actually + * being transferred * * Each SPI controller can communicate with one or more @spi_device * children. These make a small bus, sharing MOSI, MISO and SCK signals @@ -707,7 +708,6 @@ struct spi_controller { bool running; bool rt; bool auto_runtime_pm; - bool cur_msg_mapped; bool fallback; bool last_cs_mode_high; s8 last_cs[SPI_CS_CNT_MAX]; @@ -775,6 +775,7 @@ struct spi_controller { /* Flag for enabling opportunistic skipping of the queue in spi_sync */ bool queue_empty; bool must_async; + bool defer_optimize_message; }; static inline void *spi_controller_get_devdata(struct spi_controller *ctlr) @@ -901,12 +902,29 @@ extern int devm_spi_register_controller(struct device *dev, struct spi_controller *ctlr); extern void spi_unregister_controller(struct spi_controller *ctlr); -#if IS_ENABLED(CONFIG_ACPI) +#if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_SPI_MASTER) extern struct spi_controller *acpi_spi_find_controller_by_adev(struct acpi_device *adev); extern struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr, struct acpi_device *adev, int index); int acpi_spi_count_resources(struct acpi_device *adev); +#else +static inline struct spi_controller *acpi_spi_find_controller_by_adev(struct acpi_device *adev) +{ + return NULL; +} + +static inline struct spi_device *acpi_spi_device_alloc(struct spi_controller *ctlr, + struct acpi_device *adev, + int index) +{ + return ERR_PTR(-ENODEV); +} + +static inline int acpi_spi_count_resources(struct acpi_device *adev) +{ + return 0; +} #endif /* @@ -955,8 +973,8 @@ struct spi_res { * struct spi_transfer - a read/write buffer pair * @tx_buf: data to be written (DMA-safe memory), or NULL * @rx_buf: data to be read (DMA-safe memory), or NULL - * @tx_dma: DMA address of tx_buf, if @spi_message.is_dma_mapped - * @rx_dma: DMA address of rx_buf, if @spi_message.is_dma_mapped + * @tx_dma: DMA address of tx_buf, currently not for client use + * @rx_dma: DMA address of rx_buf, currently not for client use * @tx_nbits: number of bits used for writing. If 0 the default * (SPI_NBITS_SINGLE) is used. * @rx_nbits: number of bits used for reading. If 0 the default @@ -980,6 +998,8 @@ struct spi_res { * transfer this transfer. Set to 0 if the SPI bus driver does * not support it. * @transfer_list: transfers are sequenced through @spi_message.transfers + * @tx_sg_mapped: If true, the @tx_sg is mapped for DMA + * @rx_sg_mapped: If true, the @rx_sg is mapped for DMA * @tx_sg: Scatterlist for transmit, currently not for client use * @rx_sg: Scatterlist for receive, currently not for client use * @ptp_sts_word_pre: The word (subject to bits_per_word semantics) offset @@ -1066,8 +1086,7 @@ struct spi_transfer { /* * It's okay if tx_buf == rx_buf (right?). * For MicroWire, one buffer must be NULL. - * Buffers must work with dma_*map_single() calls, unless - * spi_message.is_dma_mapped reports a pre-existing mapping. + * Buffers must work with dma_*map_single() calls. */ const void *tx_buf; void *rx_buf; @@ -1077,20 +1096,24 @@ struct spi_transfer { #define SPI_TRANS_FAIL_IO BIT(1) u16 error; - dma_addr_t tx_dma; - dma_addr_t rx_dma; + bool tx_sg_mapped; + bool rx_sg_mapped; + struct sg_table tx_sg; struct sg_table rx_sg; + dma_addr_t tx_dma; + dma_addr_t rx_dma; unsigned dummy_data:1; unsigned cs_off:1; unsigned cs_change:1; - unsigned tx_nbits:3; - unsigned rx_nbits:3; + unsigned tx_nbits:4; + unsigned rx_nbits:4; unsigned timestamped:1; #define SPI_NBITS_SINGLE 0x01 /* 1-bit transfer */ #define SPI_NBITS_DUAL 0x02 /* 2-bit transfer */ #define SPI_NBITS_QUAD 0x04 /* 4-bit transfer */ +#define SPI_NBITS_OCTAL 0x08 /* 8-bit transfer */ u8 bits_per_word; struct spi_delay delay; struct spi_delay cs_change_delay; @@ -1111,8 +1134,6 @@ struct spi_transfer { * struct spi_message - one multi-segment SPI transaction * @transfers: list of transfer segments in this transaction * @spi: SPI device to which the transaction is queued - * @is_dma_mapped: if true, the caller provided both DMA and CPU virtual - * addresses for each transfer buffer * @pre_optimized: peripheral driver pre-optimized the message * @optimized: the message is in the optimized state * @prepared: spi_prepare_message was called for the this message @@ -1146,8 +1167,6 @@ struct spi_message { struct spi_device *spi; - unsigned is_dma_mapped:1; - /* spi_optimize_message() was called for this message */ bool pre_optimized; /* __spi_optimize_message() was called for this message */ @@ -1272,6 +1291,8 @@ static inline void spi_message_free(struct spi_message *m) extern int spi_optimize_message(struct spi_device *spi, struct spi_message *msg); extern void spi_unoptimize_message(struct spi_message *msg); +extern int devm_spi_optimize_message(struct device *dev, struct spi_device *spi, + struct spi_message *msg); extern int spi_setup(struct spi_device *spi); extern int spi_async(struct spi_device *spi, struct spi_message *message); diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h index b930eca2ef7b..d4cb83195f7a 100644 --- a/include/linux/spi/spi_bitbang.h +++ b/include/linux/spi/spi_bitbang.h @@ -4,6 +4,8 @@ #include <linux/workqueue.h> +typedef u32 (*spi_bb_txrx_word_fn)(struct spi_device *, unsigned int, u32, u8, unsigned int); + struct spi_bitbang { struct mutex lock; u8 busy; @@ -28,9 +30,8 @@ struct spi_bitbang { int (*txrx_bufs)(struct spi_device *spi, struct spi_transfer *t); /* txrx_word[SPI_MODE_*]() just looks like a shift register */ - u32 (*txrx_word[4])(struct spi_device *spi, - unsigned nsecs, - u32 word, u8 bits, unsigned flags); + spi_bb_txrx_word_fn txrx_word[SPI_MODE_X_MASK + 1]; + int (*set_line_direction)(struct spi_device *spi, bool output); }; diff --git a/include/linux/spi/xilinx_spi.h b/include/linux/spi/xilinx_spi.h index 3934ce789d87..1b8d984668b6 100644 --- a/include/linux/spi/xilinx_spi.h +++ b/include/linux/spi/xilinx_spi.h @@ -2,19 +2,23 @@ #ifndef __LINUX_SPI_XILINX_SPI_H #define __LINUX_SPI_XILINX_SPI_H +#include <linux/types.h> + +struct spi_board_info; + /** * struct xspi_platform_data - Platform data of the Xilinx SPI driver - * @num_chipselect: Number of chip select by the IP. - * @little_endian: If registers should be accessed little endian or not. - * @bits_per_word: Number of bits per word. * @devices: Devices to add when the driver is probed. * @num_devices: Number of devices in the devices array. + * @num_chipselect: Number of chip select by the IP. + * @bits_per_word: Number of bits per word. + * @force_irq: If set, forces QSPI transaction requirements. */ struct xspi_platform_data { - u16 num_chipselect; - u8 bits_per_word; struct spi_board_info *devices; u8 num_devices; + u8 num_chipselect; + u8 bits_per_word; bool force_irq; }; diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 3fcd20de6ca8..63dd8cf3c3c2 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -462,11 +462,10 @@ static __always_inline int spin_is_contended(spinlock_t *lock) */ static inline int spin_needbreak(spinlock_t *lock) { -#ifdef CONFIG_PREEMPTION + if (!preempt_model_preemptible()) + return 0; + return spin_is_contended(lock); -#else - return 0; -#endif } /* @@ -479,11 +478,10 @@ static inline int spin_needbreak(spinlock_t *lock) */ static inline int rwlock_needbreak(rwlock_t *lock) { -#ifdef CONFIG_PREEMPTION + if (!preempt_model_preemptible()) + return 0; + return rwlock_is_contended(lock); -#else - return 0; -#endif } /* diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 236610e4a8fa..835bbb2d1f88 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -57,10 +57,45 @@ void cleanup_srcu_struct(struct srcu_struct *ssp); int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp); void synchronize_srcu(struct srcu_struct *ssp); + +#define SRCU_GET_STATE_COMPLETED 0x1 + +/** + * get_completed_synchronize_srcu - Return a pre-completed polled state cookie + * + * Returns a value that poll_state_synchronize_srcu() will always treat + * as a cookie whose grace period has already completed. + */ +static inline unsigned long get_completed_synchronize_srcu(void) +{ + return SRCU_GET_STATE_COMPLETED; +} + unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp); unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp); bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie); +// Maximum number of unsigned long values corresponding to +// not-yet-completed SRCU grace periods. +#define NUM_ACTIVE_SRCU_POLL_OLDSTATE 2 + +/** + * same_state_synchronize_srcu - Are two old-state values identical? + * @oldstate1: First old-state value. + * @oldstate2: Second old-state value. + * + * The two old-state values must have been obtained from either + * get_state_synchronize_srcu(), start_poll_synchronize_srcu(), or + * get_completed_synchronize_srcu(). Returns @true if the two values are + * identical and @false otherwise. This allows structures whose lifetimes + * are tracked by old-state values to push these values to a list header, + * allowing those structures to be slightly smaller. + */ +static inline bool same_state_synchronize_srcu(unsigned long oldstate1, unsigned long oldstate2) +{ + return oldstate1 == oldstate2; +} + #ifdef CONFIG_NEED_SRCU_NMI_SAFE int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases(ssp); @@ -343,6 +378,20 @@ static inline void smp_mb__after_srcu_read_unlock(void) /* __srcu_read_unlock has smp_mb() internally so nothing to do here. */ } +/** + * smp_mb__after_srcu_read_lock - ensure full ordering after srcu_read_lock + * + * Converts the preceding srcu_read_lock into a two-way memory barrier. + * + * Call this after srcu_read_lock, to guarantee that all memory operations + * that occur after smp_mb__after_srcu_read_lock will appear to happen after + * the preceding srcu_read_lock. + */ +static inline void smp_mb__after_srcu_read_lock(void) +{ + /* __srcu_read_lock has smp_mb() internally so nothing to do here. */ +} + DEFINE_LOCK_GUARD_1(srcu, struct srcu_struct, _T->idx = srcu_read_lock(_T->lock), srcu_read_unlock(_T->lock, _T->idx), diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index 447133171d95..4d96bbdb45f0 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -64,8 +64,10 @@ static inline int __srcu_read_lock(struct srcu_struct *ssp) { int idx; + preempt_disable(); // Needed for PREEMPT_AUTO idx = ((READ_ONCE(ssp->srcu_idx) + 1) & 0x2) >> 1; WRITE_ONCE(ssp->srcu_lock_nesting[idx], READ_ONCE(ssp->srcu_lock_nesting[idx]) + 1); + preempt_enable(); return idx; } diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index 1f326da289d3..e1fb11e0f12c 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -325,7 +325,7 @@ struct ssb_driver { struct device_driver drv; }; -#define drv_to_ssb_drv(_drv) container_of(_drv, struct ssb_driver, drv) +#define drv_to_ssb_drv(_drv) container_of_const(_drv, struct ssb_driver, drv) extern int __ssb_driver_register(struct ssb_driver *drv, struct module *owner); #define ssb_driver_register(drv) \ @@ -621,14 +621,6 @@ extern u32 ssb_dma_translation(struct ssb_device *dev); #define SSB_DMA_TRANSLATION_MASK 0xC0000000 #define SSB_DMA_TRANSLATION_SHIFT 30 -static inline void __cold __ssb_dma_not_implemented(struct ssb_device *dev) -{ -#ifdef CONFIG_SSB_DEBUG - printk(KERN_ERR "SSB: BUG! Calling DMA API for " - "unsupported bustype %d\n", dev->bus->bustype); -#endif /* DEBUG */ -} - #ifdef CONFIG_SSB_PCIHOST /* PCI-host wrapper driver */ extern int ssb_pcihost_register(struct pci_driver *driver); diff --git a/include/linux/stat.h b/include/linux/stat.h index 52150570d37a..3d900c86981c 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -53,6 +53,10 @@ struct kstat { u32 dio_mem_align; u32 dio_offset_align; u64 change_cookie; + u64 subvol; + u32 atomic_write_unit_min; + u32 atomic_write_unit_max; + u32 atomic_write_segments_max; }; /* These definitions are internal to the kernel for now. Mainly used by nfsd. */ diff --git a/include/linux/stm.h b/include/linux/stm.h index 3b22689512be..2fcbef9608f6 100644 --- a/include/linux/stm.h +++ b/include/linux/stm.h @@ -30,6 +30,16 @@ enum stp_packet_flags { STP_PACKET_TIMESTAMPED = 0x2, }; +/** + * enum stm_source_type - STM source driver + * @STM_USER: any STM trace source + * @STM_FTRACE: ftrace STM source + */ +enum stm_source_type { + STM_USER, + STM_FTRACE, +}; + struct stp_policy; struct stm_device; @@ -106,6 +116,7 @@ struct stm_source_device; * @name: device name, will be used for policy lookup * @src: internal structure, only used by stm class code * @nr_chans: number of channels to allocate + * @type: type of STM source driver represented by stm_source_type * @link: called when this source gets linked to an STM device * @unlink: called when this source is about to get unlinked from its STM * @@ -117,6 +128,7 @@ struct stm_source_data { struct stm_source_device *src; unsigned int percpu; unsigned int nr_chans; + unsigned int type; int (*link)(struct stm_source_data *data); void (*unlink)(struct stm_source_data *data); }; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index dfa1828cd756..84e13bd5df28 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -13,7 +13,7 @@ #define __STMMAC_PLATFORM_DATA #include <linux/platform_device.h> -#include <linux/phy.h> +#include <linux/phylink.h> #define MTL_MAX_RX_QUEUES 8 #define MTL_MAX_TX_QUEUES 8 @@ -82,8 +82,8 @@ struct stmmac_priv; struct stmmac_mdio_bus_data { unsigned int phy_mask; - unsigned int has_xpcs; - unsigned int xpcs_an_inband; + unsigned int pcs_mask; + unsigned int default_an_inband; int *irqs; int probed_phy_irq; bool needs_reset; @@ -115,21 +115,6 @@ struct stmmac_axi { bool axi_rb; }; -#define EST_GCL 1024 -struct stmmac_est { - struct mutex lock; - int enable; - u32 btr_reserve[2]; - u32 btr_offset[2]; - u32 btr[2]; - u32 ctr[2]; - u32 ter; - u32 gcl_unaligned[EST_GCL]; - u32 gcl[EST_GCL]; - u32 gcl_size; - u32 max_sdu[MTL_MAX_TX_QUEUES]; -}; - struct stmmac_rxq_cfg { u8 mode_to_use; u32 chan; @@ -246,7 +231,6 @@ struct plat_stmmacenet_data { struct fwnode_handle *port_node; struct device_node *mdio_node; struct stmmac_dma_cfg *dma_cfg; - struct stmmac_est *est; struct stmmac_fpe_cfg *fpe_cfg; struct stmmac_safety_feature_cfg *safety_feat_cfg; int clk_csr; @@ -285,6 +269,10 @@ struct plat_stmmacenet_data { int (*crosststamp)(ktime_t *device, struct system_counterval_t *system, void *ctx); void (*dump_debug_regs)(void *priv); + int (*pcs_init)(struct stmmac_priv *priv); + void (*pcs_exit)(struct stmmac_priv *priv); + struct phylink_pcs *(*select_pcs)(struct stmmac_priv *priv, + phy_interface_t interface); void *bsp_priv; struct clk *stmmac_clk; struct clk *pclk; diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index ea7a74ea7389..3132262a404d 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -3,7 +3,7 @@ #define _LINUX_STOP_MACHINE #include <linux/cpu.h> -#include <linux/cpumask.h> +#include <linux/cpumask_types.h> #include <linux/smp.h> #include <linux/list.h> diff --git a/include/linux/string.h b/include/linux/string.h index 9ba8b4597009..9edace076ddb 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -14,8 +14,8 @@ #include <uapi/linux/string.h> extern char *strndup_user(const char __user *, long); -extern void *memdup_user(const void __user *, size_t); -extern void *vmemdup_user(const void __user *, size_t); +extern void *memdup_user(const void __user *, size_t) __realloc_size(2); +extern void *vmemdup_user(const void __user *, size_t) __realloc_size(2); extern void *memdup_user_nul(const void __user *, size_t); /** @@ -27,7 +27,8 @@ extern void *memdup_user_nul(const void __user *, size_t); * Return: an ERR_PTR() on failure. Result is physically * contiguous, to be freed by kfree(). */ -static inline void *memdup_array_user(const void __user *src, size_t n, size_t size) +static inline __realloc_size(2, 3) +void *memdup_array_user(const void __user *src, size_t n, size_t size) { size_t nbytes; @@ -46,7 +47,8 @@ static inline void *memdup_array_user(const void __user *src, size_t n, size_t s * Return: an ERR_PTR() on failure. Result may be not * physically contiguous. Use kvfree() to free. */ -static inline void *vmemdup_array_user(const void __user *src, size_t n, size_t size) +static inline __realloc_size(2, 3) +void *vmemdup_array_user(const void __user *src, size_t n, size_t size) { size_t nbytes; @@ -282,10 +284,13 @@ extern void kfree_const(const void *x); extern char *kstrdup(const char *s, gfp_t gfp) __malloc; extern const char *kstrdup_const(const char *s, gfp_t gfp); extern char *kstrndup(const char *s, size_t len, gfp_t gfp); -extern void *kmemdup(const void *src, size_t len, gfp_t gfp) __realloc_size(2); +extern void *kmemdup_noprof(const void *src, size_t len, gfp_t gfp) __realloc_size(2); +#define kmemdup(...) alloc_hooks(kmemdup_noprof(__VA_ARGS__)) + extern void *kvmemdup(const void *src, size_t len, gfp_t gfp) __realloc_size(2); extern char *kmemdup_nul(const char *s, size_t len, gfp_t gfp); -extern void *kmemdup_array(const void *src, size_t element_size, size_t count, gfp_t gfp); +extern void *kmemdup_array(const void *src, size_t count, size_t element_size, gfp_t gfp) + __realloc_size(2, 3); /* lib/argv_split.c */ extern char **argv_split(gfp_t gfp, const char *str, int *argcp); @@ -423,6 +428,55 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, } while (0) /** + * memtostr - Copy a possibly non-NUL-term string to a NUL-term string + * @dest: Pointer to destination NUL-terminates string + * @src: Pointer to character array (likely marked as __nonstring) + * + * This is a replacement for strncpy() uses where the source is not + * a NUL-terminated string. + * + * Note that sizes of @dest and @src must be known at compile-time. + */ +#define memtostr(dest, src) do { \ + const size_t _dest_len = __builtin_object_size(dest, 1); \ + const size_t _src_len = __builtin_object_size(src, 1); \ + const size_t _src_chars = strnlen(src, _src_len); \ + const size_t _copy_len = min(_dest_len - 1, _src_chars); \ + \ + BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ + !__builtin_constant_p(_src_len) || \ + _dest_len == 0 || _dest_len == (size_t)-1 || \ + _src_len == 0 || _src_len == (size_t)-1); \ + memcpy(dest, src, _copy_len); \ + dest[_copy_len] = '\0'; \ +} while (0) + +/** + * memtostr_pad - Copy a possibly non-NUL-term string to a NUL-term string + * with NUL padding in the destination + * @dest: Pointer to destination NUL-terminates string + * @src: Pointer to character array (likely marked as __nonstring) + * + * This is a replacement for strncpy() uses where the source is not + * a NUL-terminated string. + * + * Note that sizes of @dest and @src must be known at compile-time. + */ +#define memtostr_pad(dest, src) do { \ + const size_t _dest_len = __builtin_object_size(dest, 1); \ + const size_t _src_len = __builtin_object_size(src, 1); \ + const size_t _src_chars = strnlen(src, _src_len); \ + const size_t _copy_len = min(_dest_len - 1, _src_chars); \ + \ + BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ + !__builtin_constant_p(_src_len) || \ + _dest_len == 0 || _dest_len == (size_t)-1 || \ + _src_len == 0 || _src_len == (size_t)-1); \ + memcpy(dest, src, _copy_len); \ + memset(&dest[_copy_len], 0, _dest_len - _copy_len); \ +} while (0) + +/** * memset_after - Set a value after a struct member to the end of a struct * * @obj: Address of target struct instance diff --git a/include/linux/sunrpc/rdma_rn.h b/include/linux/sunrpc/rdma_rn.h new file mode 100644 index 000000000000..7d032ca057af --- /dev/null +++ b/include/linux/sunrpc/rdma_rn.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * * Copyright (c) 2024, Oracle and/or its affiliates. + */ + +#ifndef _LINUX_SUNRPC_RDMA_RN_H +#define _LINUX_SUNRPC_RDMA_RN_H + +#include <rdma/ib_verbs.h> + +/** + * rpcrdma_notification - request removal notification + */ +struct rpcrdma_notification { + void (*rn_done)(struct rpcrdma_notification *rn); + u32 rn_index; +}; + +int rpcrdma_rn_register(struct ib_device *device, + struct rpcrdma_notification *rn, + void (*done)(struct rpcrdma_notification *rn)); +void rpcrdma_rn_unregister(struct ib_device *device, + struct rpcrdma_notification *rn); +int rpcrdma_ib_client_register(void); +void rpcrdma_ib_client_unregister(void); + +#endif /* _LINUX_SUNRPC_RDMA_RN_H */ diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 23617da0e565..a7d0406b9ef5 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -85,6 +85,7 @@ struct svc_serv { char * sv_name; /* service name */ unsigned int sv_nrpools; /* number of thread pools */ + bool sv_is_pooled; /* is this a pooled service? */ struct svc_pool * sv_pools; /* array of thread pools */ int (*sv_threadfn)(void *data); @@ -398,6 +399,8 @@ struct svc_procedure { /* * Function prototypes. */ +int sunrpc_set_pool_mode(const char *val); +int sunrpc_get_pool_mode(char *val, size_t size); int svc_rpcb_setup(struct svc_serv *serv, struct net *net); void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net); int svc_bind(struct svc_serv *serv, struct net *net); diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 8e20cd60e2e7..0981e35a9fed 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -135,6 +135,9 @@ int svc_reg_xprt_class(struct svc_xprt_class *); void svc_unreg_xprt_class(struct svc_xprt_class *); void svc_xprt_init(struct net *, struct svc_xprt_class *, struct svc_xprt *, struct svc_serv *); +int svc_xprt_create_from_sa(struct svc_serv *serv, const char *xprt_name, + struct net *net, struct sockaddr *sap, + int flags, const struct cred *cred); int svc_xprt_create(struct svc_serv *serv, const char *xprt_name, struct net *net, const int family, const unsigned short port, int flags, @@ -147,6 +150,8 @@ void svc_xprt_copy_addrs(struct svc_rqst *rqstp, struct svc_xprt *xprt); void svc_xprt_close(struct svc_xprt *xprt); int svc_port_is_privileged(struct sockaddr *sin); int svc_print_xprts(char *buf, int maxlen); +struct svc_xprt *svc_find_listener(struct svc_serv *serv, const char *xcl_name, + struct net *net, const struct sockaddr *sa); struct svc_xprt *svc_find_xprt(struct svc_serv *serv, const char *xcl_name, struct net *net, const sa_family_t af, const unsigned short port); diff --git a/include/linux/swap.h b/include/linux/swap.h index f53d608daa01..ba7ea95d1c57 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -259,7 +259,20 @@ struct swap_cluster_info { }; #define CLUSTER_FLAG_FREE 1 /* This cluster is free */ #define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */ -#define CLUSTER_FLAG_HUGE 4 /* This cluster is backing a transparent huge page */ + +/* + * The first page in the swap file is the swap header, which is always marked + * bad to prevent it from being allocated as an entry. This also prevents the + * cluster to which it belongs being marked free. Therefore 0 is safe to use as + * a sentinel to indicate next is not valid in percpu_cluster. + */ +#define SWAP_NEXT_INVALID 0 + +#ifdef CONFIG_THP_SWAP +#define SWAP_NR_ORDERS (PMD_ORDER + 1) +#else +#define SWAP_NR_ORDERS 1 +#endif /* * We assign a cluster to each CPU, so each CPU can allocate swap entry from @@ -267,8 +280,7 @@ struct swap_cluster_info { * throughput. */ struct percpu_cluster { - struct swap_cluster_info index; /* Current cluster index */ - unsigned int next; /* Likely next allocation offset */ + unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */ }; struct swap_cluster_list { @@ -298,10 +310,8 @@ struct swap_info_struct { unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */ struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */ struct rb_root swap_extent_root;/* root of the swap extent rbtree */ - struct file *bdev_file; /* open handle of the bdev */ struct block_device *bdev; /* swap device or bdev of swap file */ struct file *swap_file; /* seldom referenced */ - unsigned int old_block_size; /* seldom referenced */ struct completion comp; /* seldom referenced */ spinlock_t lock; /* * protect map scan related fields like @@ -344,7 +354,8 @@ static inline swp_entry_t page_swap_entry(struct page *page) } /* linux/mm/workingset.c */ -bool workingset_test_recent(void *shadow, bool file, bool *workingset); +bool workingset_test_recent(void *shadow, bool file, bool *workingset, + bool flush); void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg); void workingset_refault(struct folio *folio, void *shadow); @@ -394,10 +405,13 @@ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, #define MEMCG_RECLAIM_MAY_SWAP (1 << 1) #define MEMCG_RECLAIM_PROACTIVE (1 << 2) +#define MIN_SWAPPINESS 0 +#define MAX_SWAPPINESS 200 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, - unsigned int reclaim_options); + unsigned int reclaim_options, + int *swappiness); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, @@ -462,14 +476,14 @@ swp_entry_t folio_alloc_swap(struct folio *folio); bool folio_free_swap(struct folio *folio); void put_swap_folio(struct folio *folio, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); -extern int get_swap_pages(int n, swp_entry_t swp_entries[], int entry_size); +extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order); extern int add_swap_count_continuation(swp_entry_t, gfp_t); extern void swap_shmem_alloc(swp_entry_t); extern int swap_duplicate(swp_entry_t); extern int swapcache_prepare(swp_entry_t); -extern void swap_free(swp_entry_t); +extern void swap_free_nr(swp_entry_t entry, int nr_pages); extern void swapcache_free_entries(swp_entry_t *entries, int n); -extern int free_swap_and_cache(swp_entry_t); +extern void free_swap_and_cache_nr(swp_entry_t entry, int nr); int swap_type_of(dev_t device, sector_t offset); int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); @@ -518,8 +532,9 @@ static inline void put_swap_device(struct swap_info_struct *si) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr)); -/* used to sanity check ptes in zap_pte_range when CONFIG_SWAP=0 */ -#define free_swap_and_cache(e) is_pfn_swap_entry(e) +static inline void free_swap_and_cache_nr(swp_entry_t entry, int nr) +{ +} static inline void free_swap_cache(struct folio *folio) { @@ -544,7 +559,7 @@ static inline int swapcache_prepare(swp_entry_t swp) return 0; } -static inline void swap_free(swp_entry_t swp) +static inline void swap_free_nr(swp_entry_t entry, int nr_pages) { } @@ -587,14 +602,15 @@ static inline int add_swap_extent(struct swap_info_struct *sis, } #endif /* CONFIG_SWAP */ -#ifdef CONFIG_THP_SWAP -extern int split_swap_cluster(swp_entry_t entry); -#else -static inline int split_swap_cluster(swp_entry_t entry) +static inline void free_swap_and_cache(swp_entry_t entry) { - return 0; + free_swap_and_cache_nr(entry, 1); +} + +static inline void swap_free(swp_entry_t entry) +{ + swap_free_nr(entry, 1); } -#endif #ifdef CONFIG_MEMCG static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) diff --git a/include/linux/swapops.h b/include/linux/swapops.h index a5c560a2f8c2..cb468e418ea1 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -334,7 +334,7 @@ static inline bool is_migration_entry_dirty(swp_entry_t entry) extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address); -extern void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte); +extern void migration_entry_wait_huge(struct vm_area_struct *vma, unsigned long addr, pte_t *pte); #else /* CONFIG_MIGRATION */ static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { @@ -359,7 +359,7 @@ static inline int is_migration_entry(swp_entry_t swp) static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, - pte_t *pte) { } + unsigned long addr, pte_t *pte) { } static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index ea23097e351f..3dae0f592063 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -42,24 +42,6 @@ int swiotlb_init_late(size_t size, gfp_t gfp_mask, int (*remap)(void *tlb, unsigned long nslabs)); extern void __init swiotlb_update_mem_attributes(void); -phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, - size_t mapping_size, size_t alloc_size, - unsigned int alloc_aligned_mask, enum dma_data_direction dir, - unsigned long attrs); - -extern void swiotlb_tbl_unmap_single(struct device *hwdev, - phys_addr_t tlb_addr, - size_t mapping_size, - enum dma_data_direction dir, - unsigned long attrs); - -void swiotlb_sync_single_for_device(struct device *dev, phys_addr_t tlb_addr, - size_t size, enum dma_data_direction dir); -void swiotlb_sync_single_for_cpu(struct device *dev, phys_addr_t tlb_addr, - size_t size, enum dma_data_direction dir); -dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys, - size_t size, enum dma_data_direction dir, unsigned long attrs); - #ifdef CONFIG_SWIOTLB /** @@ -143,37 +125,27 @@ struct io_tlb_mem { #endif }; -#ifdef CONFIG_SWIOTLB_DYNAMIC - -struct io_tlb_pool *swiotlb_find_pool(struct device *dev, phys_addr_t paddr); - -#else - -static inline struct io_tlb_pool *swiotlb_find_pool(struct device *dev, - phys_addr_t paddr) -{ - return &dev->dma_io_tlb_mem->defpool; -} - -#endif +struct io_tlb_pool *__swiotlb_find_pool(struct device *dev, phys_addr_t paddr); /** - * is_swiotlb_buffer() - check if a physical address belongs to a swiotlb + * swiotlb_find_pool() - find swiotlb pool to which a physical address belongs * @dev: Device which has mapped the buffer. * @paddr: Physical address within the DMA buffer. * - * Check if @paddr points into a bounce buffer. + * Find the swiotlb pool that @paddr points into. * * Return: - * * %true if @paddr points into a bounce buffer - * * %false otherwise + * * pool address if @paddr points into a bounce buffer + * * NULL if @paddr does not point into a bounce buffer. As such, this function + * can be used to determine if @paddr denotes a swiotlb bounce buffer. */ -static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) +static inline struct io_tlb_pool *swiotlb_find_pool(struct device *dev, + phys_addr_t paddr) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; if (!mem) - return false; + return NULL; #ifdef CONFIG_SWIOTLB_DYNAMIC /* @@ -182,16 +154,19 @@ static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) * If a SWIOTLB address is checked on another CPU, then it was * presumably loaded by the device driver from an unspecified private * data structure. Make sure that this load is ordered before reading - * dev->dma_uses_io_tlb here and mem->pools in swiotlb_find_pool(). + * dev->dma_uses_io_tlb here and mem->pools in __swiotlb_find_pool(). * * This barrier pairs with smp_mb() in swiotlb_find_slots(). */ smp_rmb(); - return READ_ONCE(dev->dma_uses_io_tlb) && - swiotlb_find_pool(dev, paddr); + if (READ_ONCE(dev->dma_uses_io_tlb)) + return __swiotlb_find_pool(dev, paddr); #else - return paddr >= mem->defpool.start && paddr < mem->defpool.end; + if (paddr >= mem->defpool.start && paddr < mem->defpool.end) + return &mem->defpool; #endif + + return NULL; } static inline bool is_swiotlb_force_bounce(struct device *dev) @@ -219,9 +194,10 @@ static inline void swiotlb_dev_init(struct device *dev) { } -static inline bool is_swiotlb_buffer(struct device *dev, phys_addr_t paddr) +static inline struct io_tlb_pool *swiotlb_find_pool(struct device *dev, + phys_addr_t paddr) { - return false; + return NULL; } static inline bool is_swiotlb_force_bounce(struct device *dev) { @@ -260,6 +236,49 @@ static inline phys_addr_t default_swiotlb_limit(void) } #endif /* CONFIG_SWIOTLB */ +phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, + size_t mapping_size, unsigned int alloc_aligned_mask, + enum dma_data_direction dir, unsigned long attrs); +dma_addr_t swiotlb_map(struct device *dev, phys_addr_t phys, + size_t size, enum dma_data_direction dir, unsigned long attrs); + +void __swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, + size_t mapping_size, enum dma_data_direction dir, + unsigned long attrs, struct io_tlb_pool *pool); +static inline void swiotlb_tbl_unmap_single(struct device *dev, + phys_addr_t addr, size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + struct io_tlb_pool *pool = swiotlb_find_pool(dev, addr); + + if (unlikely(pool)) + __swiotlb_tbl_unmap_single(dev, addr, size, dir, attrs, pool); +} + +void __swiotlb_sync_single_for_device(struct device *dev, phys_addr_t tlb_addr, + size_t size, enum dma_data_direction dir, + struct io_tlb_pool *pool); +static inline void swiotlb_sync_single_for_device(struct device *dev, + phys_addr_t addr, size_t size, enum dma_data_direction dir) +{ + struct io_tlb_pool *pool = swiotlb_find_pool(dev, addr); + + if (unlikely(pool)) + __swiotlb_sync_single_for_device(dev, addr, size, dir, pool); +} + +void __swiotlb_sync_single_for_cpu(struct device *dev, phys_addr_t tlb_addr, + size_t size, enum dma_data_direction dir, + struct io_tlb_pool *pool); +static inline void swiotlb_sync_single_for_cpu(struct device *dev, + phys_addr_t addr, size_t size, enum dma_data_direction dir) +{ + struct io_tlb_pool *pool = swiotlb_find_pool(dev, addr); + + if (unlikely(pool)) + __swiotlb_sync_single_for_cpu(dev, addr, size, dir, pool); +} + extern void swiotlb_print_info(void); #ifdef CONFIG_DMA_RESTRICTED_POOL diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index 8d8fac1626bd..cdb58d61c152 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -521,6 +521,6 @@ static inline struct switchtec_dev *to_stdev(struct device *dev) return container_of(dev, struct switchtec_dev, dev); } -extern struct class *switchtec_class; +extern const struct class switchtec_class; #endif diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index e619ac10cd23..4bcf6754738d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -322,13 +322,13 @@ asmlinkage long sys_io_pgetevents(aio_context_t ctx_id, long nr, struct io_event __user *events, struct __kernel_timespec __user *timeout, - const struct __aio_sigset *sig); + const struct __aio_sigset __user *sig); asmlinkage long sys_io_pgetevents_time32(aio_context_t ctx_id, long min_nr, long nr, struct io_event __user *events, struct old_timespec32 __user *timeout, - const struct __aio_sigset *sig); + const struct __aio_sigset __user *sig); asmlinkage long sys_io_uring_setup(u32 entries, struct io_uring_params __user *p); asmlinkage long sys_io_uring_enter(unsigned int fd, u32 to_submit, @@ -418,7 +418,7 @@ asmlinkage long sys_listmount(const struct mnt_id_req __user *req, u64 __user *mnt_ids, size_t nr_mnt_ids, unsigned int flags); asmlinkage long sys_truncate(const char __user *path, long length); -asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length); +asmlinkage long sys_ftruncate(unsigned int fd, off_t length); #if BITS_PER_LONG == 32 asmlinkage long sys_truncate64(const char __user *path, loff_t length); asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length); @@ -441,7 +441,7 @@ asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group); asmlinkage long sys_openat(int dfd, const char __user *filename, int flags, umode_t mode); asmlinkage long sys_openat2(int dfd, const char __user *filename, - struct open_how *how, size_t size); + struct open_how __user *how, size_t size); asmlinkage long sys_close(unsigned int fd); asmlinkage long sys_close_range(unsigned int fd, unsigned int max_fd, unsigned int flags); @@ -555,7 +555,7 @@ asmlinkage long sys_get_robust_list(int pid, asmlinkage long sys_set_robust_list(struct robust_list_head __user *head, size_t len); -asmlinkage long sys_futex_waitv(struct futex_waitv *waiters, +asmlinkage long sys_futex_waitv(struct futex_waitv __user *waiters, unsigned int nr_futexes, unsigned int flags, struct __kernel_timespec __user *timeout, clockid_t clockid); @@ -821,6 +821,7 @@ asmlinkage long sys_process_mrelease(int pidfd, unsigned int flags); asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size, unsigned long prot, unsigned long pgoff, unsigned long flags); +asmlinkage long sys_mseal(unsigned long start, size_t len, unsigned long flags); asmlinkage long sys_mbind(unsigned long start, unsigned long len, unsigned long mode, const unsigned long __user *nmask, @@ -858,9 +859,15 @@ asmlinkage long sys_prlimit64(pid_t pid, unsigned int resource, const struct rlimit64 __user *new_rlim, struct rlimit64 __user *old_rlim); asmlinkage long sys_fanotify_init(unsigned int flags, unsigned int event_f_flags); +#if defined(CONFIG_ARCH_SPLIT_ARG64) +asmlinkage long sys_fanotify_mark(int fanotify_fd, unsigned int flags, + unsigned int mask_1, unsigned int mask_2, + int dfd, const char __user * pathname); +#else asmlinkage long sys_fanotify_mark(int fanotify_fd, unsigned int flags, u64 mask, int fd, const char __user *pathname); +#endif asmlinkage long sys_name_to_handle_at(int dfd, const char __user *name, struct file_handle __user *handle, int __user *mnt_id, int flag); @@ -906,7 +913,7 @@ asmlinkage long sys_seccomp(unsigned int op, unsigned int flags, asmlinkage long sys_getrandom(char __user *buf, size_t count, unsigned int flags); asmlinkage long sys_memfd_create(const char __user *uname_ptr, unsigned int flags); -asmlinkage long sys_bpf(int cmd, union bpf_attr *attr, unsigned int size); +asmlinkage long sys_bpf(int cmd, union bpf_attr __user *attr, unsigned int size); asmlinkage long sys_execveat(int dfd, const char __user *filename, const char __user *const __user *argv, const char __user *const __user *envp, int flags); @@ -959,11 +966,11 @@ asmlinkage long sys_cachestat(unsigned int fd, struct cachestat_range __user *cstat_range, struct cachestat __user *cstat, unsigned int flags); asmlinkage long sys_map_shadow_stack(unsigned long addr, unsigned long size, unsigned int flags); -asmlinkage long sys_lsm_get_self_attr(unsigned int attr, struct lsm_ctx *ctx, - u32 *size, u32 flags); -asmlinkage long sys_lsm_set_self_attr(unsigned int attr, struct lsm_ctx *ctx, +asmlinkage long sys_lsm_get_self_attr(unsigned int attr, struct lsm_ctx __user *ctx, + u32 __user *size, u32 flags); +asmlinkage long sys_lsm_set_self_attr(unsigned int attr, struct lsm_ctx __user *ctx, u32 size, u32 flags); -asmlinkage long sys_lsm_list_modules(u64 *ids, u32 *size, u32 flags); +asmlinkage long sys_lsm_list_modules(u64 __user *ids, u32 __user *size, u32 flags); /* * Architecture-specific system calls @@ -972,6 +979,8 @@ asmlinkage long sys_lsm_list_modules(u64 *ids, u32 *size, u32 flags); /* x86 */ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int on); +asmlinkage long sys_uretprobe(void); + /* pciconfig: alpha, arm, arm64, ia64, sparc */ asmlinkage long sys_pciconfig_read(unsigned long bus, unsigned long dfn, unsigned long off, unsigned long len, diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index ee7d33b89e9e..aa4c6d44aaa0 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -61,31 +61,31 @@ extern const int sysctl_vals[]; extern const unsigned long sysctl_long_vals[]; -typedef int proc_handler(struct ctl_table *ctl, int write, void *buffer, +typedef int proc_handler(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); -int proc_dostring(struct ctl_table *, int, void *, size_t *, loff_t *); -int proc_dobool(struct ctl_table *table, int write, void *buffer, +int proc_dostring(const struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_dobool(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int proc_dointvec(struct ctl_table *, int, void *, size_t *, loff_t *); -int proc_douintvec(struct ctl_table *, int, void *, size_t *, loff_t *); -int proc_dointvec_minmax(struct ctl_table *, int, void *, size_t *, loff_t *); -int proc_douintvec_minmax(struct ctl_table *table, int write, void *buffer, +int proc_dointvec(const struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_douintvec(const struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_dointvec_minmax(const struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_douintvec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int proc_dou8vec_minmax(struct ctl_table *table, int write, void *buffer, +int proc_dou8vec_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int proc_dointvec_jiffies(struct ctl_table *, int, void *, size_t *, loff_t *); -int proc_dointvec_ms_jiffies_minmax(struct ctl_table *table, int write, +int proc_dointvec_jiffies(const struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_dointvec_ms_jiffies_minmax(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int proc_dointvec_userhz_jiffies(struct ctl_table *, int, void *, size_t *, +int proc_dointvec_userhz_jiffies(const struct ctl_table *, int, void *, size_t *, loff_t *); -int proc_dointvec_ms_jiffies(struct ctl_table *, int, void *, size_t *, +int proc_dointvec_ms_jiffies(const struct ctl_table *, int, void *, size_t *, loff_t *); -int proc_doulongvec_minmax(struct ctl_table *, int, void *, size_t *, loff_t *); -int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int, void *, +int proc_doulongvec_minmax(const struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_doulongvec_ms_jiffies_minmax(const struct ctl_table *table, int, void *, size_t *, loff_t *); -int proc_do_large_bitmap(struct ctl_table *, int, void *, size_t *, loff_t *); -int proc_do_static_key(struct ctl_table *table, int write, void *buffer, +int proc_do_large_bitmap(const struct ctl_table *, int, void *, size_t *, loff_t *); +int proc_do_static_key(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); /* @@ -137,17 +137,6 @@ struct ctl_table { void *data; int maxlen; umode_t mode; - /** - * enum type - Enumeration to differentiate between ctl target types - * @SYSCTL_TABLE_TYPE_DEFAULT: ctl target with no special considerations - * @SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY: Used to identify a permanently - * empty directory target to serve - * as mount point. - */ - enum { - SYSCTL_TABLE_TYPE_DEFAULT, - SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY - } type; proc_handler *proc_handler; /* Callback for text formatting */ struct ctl_table_poll *poll; void *extra1; @@ -182,12 +171,23 @@ struct ctl_table_header { struct rcu_head rcu; }; struct completion *unregistering; - struct ctl_table *ctl_table_arg; + const struct ctl_table *ctl_table_arg; struct ctl_table_root *root; struct ctl_table_set *set; struct ctl_dir *parent; struct ctl_node *node; struct hlist_head inodes; /* head for proc_inode->sysctl_inodes */ + /** + * enum type - Enumeration to differentiate between ctl target types + * @SYSCTL_TABLE_TYPE_DEFAULT: ctl target with no special considerations + * @SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY: Used to identify a permanently + * empty directory target to serve + * as mount point. + */ + enum { + SYSCTL_TABLE_TYPE_DEFAULT, + SYSCTL_TABLE_TYPE_PERMANENTLY_EMPTY, + } type; }; struct ctl_dir { @@ -205,9 +205,8 @@ struct ctl_table_root { struct ctl_table_set default_set; struct ctl_table_set *(*lookup)(struct ctl_table_root *root); void (*set_ownership)(struct ctl_table_header *head, - struct ctl_table *table, kuid_t *uid, kgid_t *gid); - int (*permissions)(struct ctl_table_header *head, struct ctl_table *table); + int (*permissions)(struct ctl_table_header *head, const struct ctl_table *table); }; #define register_sysctl(path, table) \ @@ -238,7 +237,7 @@ extern struct ctl_table_header *register_sysctl_mount_point(const char *path); void do_sysctl_args(void); bool sysctl_is_alias(char *param); -int do_proc_douintvec(struct ctl_table *table, int write, +int do_proc_douintvec(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos, int (*conv)(unsigned long *lvalp, unsigned int *valp, @@ -288,7 +287,7 @@ static inline bool sysctl_is_alias(char *param) } #endif /* CONFIG_SYSCTL */ -int sysctl_max_threads(struct ctl_table *table, int write, void *buffer, +int sysctl_max_threads(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); #endif /* _LINUX_SYSCTL_H */ diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 326341c62385..c4e64dc11206 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -371,6 +371,17 @@ struct bin_attribute bin_attr_##_name = __BIN_ATTR_ADMIN_RO(_name, _size) #define BIN_ATTR_ADMIN_RW(_name, _size) \ struct bin_attribute bin_attr_##_name = __BIN_ATTR_ADMIN_RW(_name, _size) +#define __BIN_ATTR_SIMPLE_RO(_name, _mode) { \ + .attr = { .name = __stringify(_name), .mode = _mode }, \ + .read = sysfs_bin_attr_simple_read, \ +} + +#define BIN_ATTR_SIMPLE_RO(_name) \ +struct bin_attribute bin_attr_##_name = __BIN_ATTR_SIMPLE_RO(_name, 0444) + +#define BIN_ATTR_SIMPLE_ADMIN_RO(_name) \ +struct bin_attribute bin_attr_##_name = __BIN_ATTR_SIMPLE_RO(_name, 0400) + struct sysfs_ops { ssize_t (*show)(struct kobject *, struct attribute *, char *); ssize_t (*store)(struct kobject *, struct attribute *, const char *, size_t); @@ -478,6 +489,10 @@ int sysfs_emit(char *buf, const char *fmt, ...); __printf(3, 4) int sysfs_emit_at(char *buf, int at, const char *fmt, ...); +ssize_t sysfs_bin_attr_simple_read(struct file *file, struct kobject *kobj, + struct bin_attribute *attr, char *buf, + loff_t off, size_t count); + #else /* CONFIG_SYSFS */ static inline int sysfs_create_dir_ns(struct kobject *kobj, const void *ns) @@ -735,6 +750,15 @@ static inline int sysfs_emit_at(char *buf, int at, const char *fmt, ...) { return 0; } + +static inline ssize_t sysfs_bin_attr_simple_read(struct file *file, + struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t off, + size_t count) +{ + return 0; +} #endif /* CONFIG_SYSFS */ static inline int __must_check sysfs_create_file(struct kobject *kobj, diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index 248f4ac95642..2c59fe3efcd4 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -41,18 +41,12 @@ static inline u32 t10_pi_ref_tag(struct request *rq) { unsigned int shift = ilog2(queue_logical_block_size(rq->q)); -#ifdef CONFIG_BLK_DEV_INTEGRITY - if (rq->q->integrity.interval_exp) - shift = rq->q->integrity.interval_exp; -#endif + if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) && + rq->q->limits.integrity.interval_exp) + shift = rq->q->limits.integrity.interval_exp; return blk_rq_pos(rq) >> (shift - SECTOR_SHIFT) & 0xffffffff; } -extern const struct blk_integrity_profile t10_pi_type1_crc; -extern const struct blk_integrity_profile t10_pi_type1_ip; -extern const struct blk_integrity_profile t10_pi_type3_crc; -extern const struct blk_integrity_profile t10_pi_type3_ip; - struct crc64_pi_tuple { __be64 guard_tag; __be16 app_tag; @@ -72,14 +66,10 @@ static inline u64 ext_pi_ref_tag(struct request *rq) { unsigned int shift = ilog2(queue_logical_block_size(rq->q)); -#ifdef CONFIG_BLK_DEV_INTEGRITY - if (rq->q->integrity.interval_exp) - shift = rq->q->integrity.interval_exp; -#endif + if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) && + rq->q->limits.integrity.interval_exp) + shift = rq->q->limits.integrity.interval_exp; return lower_48_bits(blk_rq_pos(rq) >> (shift - SECTOR_SHIFT)); } -extern const struct blk_integrity_profile ext_pi_type1_crc64; -extern const struct blk_integrity_profile ext_pi_type3_crc64; - #endif diff --git a/include/linux/task_work.h b/include/linux/task_work.h index 795ef5a68429..cf5e7e891a77 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -18,6 +18,7 @@ enum task_work_notify_mode { TWA_RESUME, TWA_SIGNAL, TWA_SIGNAL_NO_IPI, + TWA_NMI_CURRENT, }; static inline bool task_work_pending(struct task_struct *task) @@ -30,7 +31,8 @@ int task_work_add(struct task_struct *task, struct callback_head *twork, struct callback_head *task_work_cancel_match(struct task_struct *task, bool (*match)(struct callback_head *, void *data), void *data); -struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t); +struct callback_head *task_work_cancel_func(struct task_struct *, task_work_func_t); +bool task_work_cancel(struct task_struct *task, struct callback_head *cb); void task_work_run(void); static inline void exit_task_work(struct task_struct *task) diff --git a/include/linux/tc.h b/include/linux/tc.h index 1638660abf5e..8416bae9b126 100644 --- a/include/linux/tc.h +++ b/include/linux/tc.h @@ -108,7 +108,7 @@ struct tc_driver { struct device_driver driver; }; -#define to_tc_driver(drv) container_of(drv, struct tc_driver, driver) +#define to_tc_driver(drv) container_of_const(drv, struct tc_driver, driver) /* * Return TURBOchannel clock frequency in Hz. diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 55399ee2a57e..6a5e08b937b3 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -244,6 +244,7 @@ struct tcp_sock { /* OOO segments go in this rbtree. Socket lock must be held. */ struct rb_root out_of_order_queue; u32 snd_ssthresh; /* Slow start size threshold */ + u8 recvmsg_inq : 1;/* Indicate # of bytes in queue upon recvmsg */ __cacheline_group_end(tcp_sock_read_rx); /* TX read-write hotpath cache lines */ @@ -266,8 +267,6 @@ struct tcp_sock { u32 mdev_us; /* medium deviation */ u32 rtt_seq; /* sequence number to update rttvar */ u64 tcp_wstamp_ns; /* departure time for next sent data packet */ - u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */ - u64 tcp_mstamp; /* most recent packet received/sent */ struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */ struct sk_buff *highest_sack; /* skb just after the highest * skb with SACKed bit set @@ -284,6 +283,8 @@ struct tcp_sock { * 0x5?10 << 16 + snd_wnd in net byte order */ __be32 pred_flags; + u64 tcp_clock_cache; /* cache last tcp_clock_ns() (see tcp_mstamp_refresh()) */ + u64 tcp_mstamp; /* most recent packet received/sent */ u32 rcv_nxt; /* What we want to receive next */ u32 snd_nxt; /* Next sequence we send */ u32 snd_una; /* First byte we want an ack for */ @@ -370,7 +371,6 @@ struct tcp_sock { tlp_retrans:1, /* TLP is a retransmission */ unused:5; u8 thin_lto : 1,/* Use linear timeouts for thin streams */ - recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */ fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */ fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */ fastopen_client_fail:2, /* reason why fastopen failed */ diff --git a/include/linux/tee_core.h b/include/linux/tee_core.h new file mode 100644 index 000000000000..efd16ed52315 --- /dev/null +++ b/include/linux/tee_core.h @@ -0,0 +1,306 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2024 Linaro Limited + */ + +#ifndef __TEE_CORE_H +#define __TEE_CORE_H + +#include <linux/cdev.h> +#include <linux/device.h> +#include <linux/idr.h> +#include <linux/kref.h> +#include <linux/list.h> +#include <linux/tee.h> +#include <linux/tee_drv.h> +#include <linux/types.h> +#include <linux/uuid.h> + +/* + * The file describes the API provided by the generic TEE driver to the + * specific TEE driver. + */ + +#define TEE_SHM_DYNAMIC BIT(0) /* Dynamic shared memory registered */ + /* in secure world */ +#define TEE_SHM_USER_MAPPED BIT(1) /* Memory mapped in user space */ +#define TEE_SHM_POOL BIT(2) /* Memory allocated from pool */ +#define TEE_SHM_PRIV BIT(3) /* Memory private to TEE driver */ + +#define TEE_DEVICE_FLAG_REGISTERED 0x1 +#define TEE_MAX_DEV_NAME_LEN 32 + +/** + * struct tee_device - TEE Device representation + * @name: name of device + * @desc: description of device + * @id: unique id of device + * @flags: represented by TEE_DEVICE_FLAG_REGISTERED above + * @dev: embedded basic device structure + * @cdev: embedded cdev + * @num_users: number of active users of this device + * @c_no_user: completion used when unregistering the device + * @mutex: mutex protecting @num_users and @idr + * @idr: register of user space shared memory objects allocated or + * registered on this device + * @pool: shared memory pool + */ +struct tee_device { + char name[TEE_MAX_DEV_NAME_LEN]; + const struct tee_desc *desc; + int id; + unsigned int flags; + + struct device dev; + struct cdev cdev; + + size_t num_users; + struct completion c_no_users; + struct mutex mutex; /* protects num_users and idr */ + + struct idr idr; + struct tee_shm_pool *pool; +}; + +/** + * struct tee_driver_ops - driver operations vtable + * @get_version: returns version of driver + * @open: called when the device file is opened + * @release: release this open file + * @open_session: open a new session + * @close_session: close a session + * @system_session: declare session as a system session + * @invoke_func: invoke a trusted function + * @cancel_req: request cancel of an ongoing invoke or open + * @supp_recv: called for supplicant to get a command + * @supp_send: called for supplicant to send a response + * @shm_register: register shared memory buffer in TEE + * @shm_unregister: unregister shared memory buffer in TEE + */ +struct tee_driver_ops { + void (*get_version)(struct tee_device *teedev, + struct tee_ioctl_version_data *vers); + int (*open)(struct tee_context *ctx); + void (*release)(struct tee_context *ctx); + int (*open_session)(struct tee_context *ctx, + struct tee_ioctl_open_session_arg *arg, + struct tee_param *param); + int (*close_session)(struct tee_context *ctx, u32 session); + int (*system_session)(struct tee_context *ctx, u32 session); + int (*invoke_func)(struct tee_context *ctx, + struct tee_ioctl_invoke_arg *arg, + struct tee_param *param); + int (*cancel_req)(struct tee_context *ctx, u32 cancel_id, u32 session); + int (*supp_recv)(struct tee_context *ctx, u32 *func, u32 *num_params, + struct tee_param *param); + int (*supp_send)(struct tee_context *ctx, u32 ret, u32 num_params, + struct tee_param *param); + int (*shm_register)(struct tee_context *ctx, struct tee_shm *shm, + struct page **pages, size_t num_pages, + unsigned long start); + int (*shm_unregister)(struct tee_context *ctx, struct tee_shm *shm); +}; + +/** + * struct tee_desc - Describes the TEE driver to the subsystem + * @name: name of driver + * @ops: driver operations vtable + * @owner: module providing the driver + * @flags: Extra properties of driver, defined by TEE_DESC_* below + */ +#define TEE_DESC_PRIVILEGED 0x1 +struct tee_desc { + const char *name; + const struct tee_driver_ops *ops; + struct module *owner; + u32 flags; +}; + +/** + * tee_device_alloc() - Allocate a new struct tee_device instance + * @teedesc: Descriptor for this driver + * @dev: Parent device for this device + * @pool: Shared memory pool, NULL if not used + * @driver_data: Private driver data for this device + * + * Allocates a new struct tee_device instance. The device is + * removed by tee_device_unregister(). + * + * @returns a pointer to a 'struct tee_device' or an ERR_PTR on failure + */ +struct tee_device *tee_device_alloc(const struct tee_desc *teedesc, + struct device *dev, + struct tee_shm_pool *pool, + void *driver_data); + +/** + * tee_device_register() - Registers a TEE device + * @teedev: Device to register + * + * tee_device_unregister() need to be called to remove the @teedev if + * this function fails. + * + * @returns < 0 on failure + */ +int tee_device_register(struct tee_device *teedev); + +/** + * tee_device_unregister() - Removes a TEE device + * @teedev: Device to unregister + * + * This function should be called to remove the @teedev even if + * tee_device_register() hasn't been called yet. Does nothing if + * @teedev is NULL. + */ +void tee_device_unregister(struct tee_device *teedev); + +/** + * tee_session_calc_client_uuid() - Calculates client UUID for session + * @uuid: Resulting UUID + * @connection_method: Connection method for session (TEE_IOCTL_LOGIN_*) + * @connectuon_data: Connection data for opening session + * + * Based on connection method calculates UUIDv5 based client UUID. + * + * For group based logins verifies that calling process has specified + * credentials. + * + * @return < 0 on failure + */ +int tee_session_calc_client_uuid(uuid_t *uuid, u32 connection_method, + const u8 connection_data[TEE_IOCTL_UUID_LEN]); + +/** + * struct tee_shm_pool - shared memory pool + * @ops: operations + * @private_data: private data for the shared memory manager + */ +struct tee_shm_pool { + const struct tee_shm_pool_ops *ops; + void *private_data; +}; + +/** + * struct tee_shm_pool_ops - shared memory pool operations + * @alloc: called when allocating shared memory + * @free: called when freeing shared memory + * @destroy_pool: called when destroying the pool + */ +struct tee_shm_pool_ops { + int (*alloc)(struct tee_shm_pool *pool, struct tee_shm *shm, + size_t size, size_t align); + void (*free)(struct tee_shm_pool *pool, struct tee_shm *shm); + void (*destroy_pool)(struct tee_shm_pool *pool); +}; + +/* + * tee_shm_pool_alloc_res_mem() - Create a shm manager for reserved memory + * @vaddr: Virtual address of start of pool + * @paddr: Physical address of start of pool + * @size: Size in bytes of the pool + * + * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure. + */ +struct tee_shm_pool *tee_shm_pool_alloc_res_mem(unsigned long vaddr, + phys_addr_t paddr, size_t size, + int min_alloc_order); + +/** + * tee_shm_pool_free() - Free a shared memory pool + * @pool: The shared memory pool to free + * + * The must be no remaining shared memory allocated from this pool when + * this function is called. + */ +static inline void tee_shm_pool_free(struct tee_shm_pool *pool) +{ + pool->ops->destroy_pool(pool); +} + +/** + * tee_get_drvdata() - Return driver_data pointer + * @returns the driver_data pointer supplied to tee_register(). + */ +void *tee_get_drvdata(struct tee_device *teedev); + +/** + * tee_shm_alloc_priv_buf() - Allocate shared memory for private use by specific + * TEE driver + * @ctx: The TEE context for shared memory allocation + * @size: Shared memory allocation size + * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure + */ +struct tee_shm *tee_shm_alloc_priv_buf(struct tee_context *ctx, size_t size); + +int tee_dyn_shm_alloc_helper(struct tee_shm *shm, size_t size, size_t align, + int (*shm_register)(struct tee_context *ctx, + struct tee_shm *shm, + struct page **pages, + size_t num_pages, + unsigned long start)); +void tee_dyn_shm_free_helper(struct tee_shm *shm, + int (*shm_unregister)(struct tee_context *ctx, + struct tee_shm *shm)); + +/** + * tee_shm_is_dynamic() - Check if shared memory object is of the dynamic kind + * @shm: Shared memory handle + * @returns true if object is dynamic shared memory + */ +static inline bool tee_shm_is_dynamic(struct tee_shm *shm) +{ + return shm && (shm->flags & TEE_SHM_DYNAMIC); +} + +/** + * tee_shm_put() - Decrease reference count on a shared memory handle + * @shm: Shared memory handle + */ +void tee_shm_put(struct tee_shm *shm); + +/** + * tee_shm_get_id() - Get id of a shared memory object + * @shm: Shared memory handle + * @returns id + */ +static inline int tee_shm_get_id(struct tee_shm *shm) +{ + return shm->id; +} + +/** + * tee_shm_get_from_id() - Find shared memory object and increase reference + * count + * @ctx: Context owning the shared memory + * @id: Id of shared memory object + * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure + */ +struct tee_shm *tee_shm_get_from_id(struct tee_context *ctx, int id); + +static inline bool tee_param_is_memref(struct tee_param *param) +{ + switch (param->attr & TEE_IOCTL_PARAM_ATTR_TYPE_MASK) { + case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT: + case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT: + case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT: + return true; + default: + return false; + } +} + +/** + * teedev_open() - Open a struct tee_device + * @teedev: Device to open + * + * @return a pointer to struct tee_context on success or an ERR_PTR on failure. + */ +struct tee_context *teedev_open(struct tee_device *teedev); + +/** + * teedev_close_context() - closes a struct tee_context + * @ctx: The struct tee_context to close + */ +void teedev_close_context(struct tee_context *ctx); + +#endif /*__TEE_CORE_H*/ diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 71632e3c5f18..a54c203000ed 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -1,40 +1,28 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2015-2022 Linaro Limited + * Copyright (c) 2015-2024 Linaro Limited */ #ifndef __TEE_DRV_H #define __TEE_DRV_H #include <linux/device.h> -#include <linux/idr.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/mod_devicetable.h> #include <linux/tee.h> #include <linux/types.h> -#include <linux/uuid.h> /* - * The file describes the API provided by the generic TEE driver to the - * specific TEE driver. + * The file describes the API provided by the TEE subsystem to the + * TEE client drivers. */ -#define TEE_SHM_DYNAMIC BIT(0) /* Dynamic shared memory registered */ - /* in secure world */ -#define TEE_SHM_USER_MAPPED BIT(1) /* Memory mapped in user space */ -#define TEE_SHM_POOL BIT(2) /* Memory allocated from pool */ -#define TEE_SHM_PRIV BIT(3) /* Memory private to TEE driver */ - -struct device; struct tee_device; -struct tee_shm; -struct tee_shm_pool; /** * struct tee_context - driver specific context on file pointer data * @teedev: pointer to this drivers struct tee_device - * @list_shm: List of shared memory object owned by this context * @data: driver specific context data, managed by the driver * @refcount: reference counter for this structure * @releasing: flag that indicates if context is being released right now. @@ -57,134 +45,6 @@ struct tee_context { bool cap_memref_null; }; -struct tee_param_memref { - size_t shm_offs; - size_t size; - struct tee_shm *shm; -}; - -struct tee_param_value { - u64 a; - u64 b; - u64 c; -}; - -struct tee_param { - u64 attr; - union { - struct tee_param_memref memref; - struct tee_param_value value; - } u; -}; - -/** - * struct tee_driver_ops - driver operations vtable - * @get_version: returns version of driver - * @open: called when the device file is opened - * @release: release this open file - * @open_session: open a new session - * @close_session: close a session - * @system_session: declare session as a system session - * @invoke_func: invoke a trusted function - * @cancel_req: request cancel of an ongoing invoke or open - * @supp_recv: called for supplicant to get a command - * @supp_send: called for supplicant to send a response - * @shm_register: register shared memory buffer in TEE - * @shm_unregister: unregister shared memory buffer in TEE - */ -struct tee_driver_ops { - void (*get_version)(struct tee_device *teedev, - struct tee_ioctl_version_data *vers); - int (*open)(struct tee_context *ctx); - void (*release)(struct tee_context *ctx); - int (*open_session)(struct tee_context *ctx, - struct tee_ioctl_open_session_arg *arg, - struct tee_param *param); - int (*close_session)(struct tee_context *ctx, u32 session); - int (*system_session)(struct tee_context *ctx, u32 session); - int (*invoke_func)(struct tee_context *ctx, - struct tee_ioctl_invoke_arg *arg, - struct tee_param *param); - int (*cancel_req)(struct tee_context *ctx, u32 cancel_id, u32 session); - int (*supp_recv)(struct tee_context *ctx, u32 *func, u32 *num_params, - struct tee_param *param); - int (*supp_send)(struct tee_context *ctx, u32 ret, u32 num_params, - struct tee_param *param); - int (*shm_register)(struct tee_context *ctx, struct tee_shm *shm, - struct page **pages, size_t num_pages, - unsigned long start); - int (*shm_unregister)(struct tee_context *ctx, struct tee_shm *shm); -}; - -/** - * struct tee_desc - Describes the TEE driver to the subsystem - * @name: name of driver - * @ops: driver operations vtable - * @owner: module providing the driver - * @flags: Extra properties of driver, defined by TEE_DESC_* below - */ -#define TEE_DESC_PRIVILEGED 0x1 -struct tee_desc { - const char *name; - const struct tee_driver_ops *ops; - struct module *owner; - u32 flags; -}; - -/** - * tee_device_alloc() - Allocate a new struct tee_device instance - * @teedesc: Descriptor for this driver - * @dev: Parent device for this device - * @pool: Shared memory pool, NULL if not used - * @driver_data: Private driver data for this device - * - * Allocates a new struct tee_device instance. The device is - * removed by tee_device_unregister(). - * - * @returns a pointer to a 'struct tee_device' or an ERR_PTR on failure - */ -struct tee_device *tee_device_alloc(const struct tee_desc *teedesc, - struct device *dev, - struct tee_shm_pool *pool, - void *driver_data); - -/** - * tee_device_register() - Registers a TEE device - * @teedev: Device to register - * - * tee_device_unregister() need to be called to remove the @teedev if - * this function fails. - * - * @returns < 0 on failure - */ -int tee_device_register(struct tee_device *teedev); - -/** - * tee_device_unregister() - Removes a TEE device - * @teedev: Device to unregister - * - * This function should be called to remove the @teedev even if - * tee_device_register() hasn't been called yet. Does nothing if - * @teedev is NULL. - */ -void tee_device_unregister(struct tee_device *teedev); - -/** - * tee_session_calc_client_uuid() - Calculates client UUID for session - * @uuid: Resulting UUID - * @connection_method: Connection method for session (TEE_IOCTL_LOGIN_*) - * @connectuon_data: Connection data for opening session - * - * Based on connection method calculates UUIDv5 based client UUID. - * - * For group based logins verifies that calling process has specified - * credentials. - * - * @return < 0 on failure - */ -int tee_session_calc_client_uuid(uuid_t *uuid, u32 connection_method, - const u8 connection_data[TEE_IOCTL_UUID_LEN]); - /** * struct tee_shm - shared memory object * @ctx: context using the object @@ -195,15 +55,12 @@ int tee_session_calc_client_uuid(uuid_t *uuid, u32 connection_method, * @pages: locked pages from userspace * @num_pages: number of locked pages * @refcount: reference counter - * @flags: defined by TEE_SHM_* in tee_drv.h + * @flags: defined by TEE_SHM_* in tee_core.h * @id: unique id of a shared memory object on this device, shared * with user space * @sec_world_id: * secure world assigned id of this shared memory object, not * used by all drivers - * - * This pool is only supposed to be accessed directly from the TEE - * subsystem and from drivers that implements their own shm pool manager. */ struct tee_shm { struct tee_context *ctx; @@ -219,88 +76,53 @@ struct tee_shm { u64 sec_world_id; }; -/** - * struct tee_shm_pool - shared memory pool - * @ops: operations - * @private_data: private data for the shared memory manager - */ -struct tee_shm_pool { - const struct tee_shm_pool_ops *ops; - void *private_data; +struct tee_param_memref { + size_t shm_offs; + size_t size; + struct tee_shm *shm; }; -/** - * struct tee_shm_pool_ops - shared memory pool operations - * @alloc: called when allocating shared memory - * @free: called when freeing shared memory - * @destroy_pool: called when destroying the pool - */ -struct tee_shm_pool_ops { - int (*alloc)(struct tee_shm_pool *pool, struct tee_shm *shm, - size_t size, size_t align); - void (*free)(struct tee_shm_pool *pool, struct tee_shm *shm); - void (*destroy_pool)(struct tee_shm_pool *pool); +struct tee_param_value { + u64 a; + u64 b; + u64 c; }; -/* - * tee_shm_pool_alloc_res_mem() - Create a shm manager for reserved memory - * @vaddr: Virtual address of start of pool - * @paddr: Physical address of start of pool - * @size: Size in bytes of the pool - * - * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure. - */ -struct tee_shm_pool *tee_shm_pool_alloc_res_mem(unsigned long vaddr, - phys_addr_t paddr, size_t size, - int min_alloc_order); +struct tee_param { + u64 attr; + union { + struct tee_param_memref memref; + struct tee_param_value value; + } u; +}; /** - * tee_shm_pool_free() - Free a shared memory pool - * @pool: The shared memory pool to free - * - * The must be no remaining shared memory allocated from this pool when - * this function is called. + * tee_shm_alloc_kernel_buf() - Allocate kernel shared memory for a + * particular TEE client driver + * @ctx: The TEE context for shared memory allocation + * @size: Shared memory allocation size + * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure */ -static inline void tee_shm_pool_free(struct tee_shm_pool *pool) -{ - pool->ops->destroy_pool(pool); -} +struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size); /** - * tee_get_drvdata() - Return driver_data pointer - * @returns the driver_data pointer supplied to tee_register(). + * tee_shm_register_kernel_buf() - Register kernel shared memory for a + * particular TEE client driver + * @ctx: The TEE context for shared memory registration + * @addr: Kernel buffer address + * @length: Kernel buffer length + * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure */ -void *tee_get_drvdata(struct tee_device *teedev); - -struct tee_shm *tee_shm_alloc_priv_buf(struct tee_context *ctx, size_t size); -struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size); - struct tee_shm *tee_shm_register_kernel_buf(struct tee_context *ctx, void *addr, size_t length); /** - * tee_shm_is_dynamic() - Check if shared memory object is of the dynamic kind - * @shm: Shared memory handle - * @returns true if object is dynamic shared memory - */ -static inline bool tee_shm_is_dynamic(struct tee_shm *shm) -{ - return shm && (shm->flags & TEE_SHM_DYNAMIC); -} - -/** * tee_shm_free() - Free shared memory * @shm: Handle to shared memory to free */ void tee_shm_free(struct tee_shm *shm); /** - * tee_shm_put() - Decrease reference count on a shared memory handle - * @shm: Shared memory handle - */ -void tee_shm_put(struct tee_shm *shm); - -/** * tee_shm_get_va() - Get virtual address of a shared memory plus an offset * @shm: Shared memory handle * @offs: Offset from start of this shared memory @@ -353,25 +175,6 @@ static inline size_t tee_shm_get_page_offset(struct tee_shm *shm) } /** - * tee_shm_get_id() - Get id of a shared memory object - * @shm: Shared memory handle - * @returns id - */ -static inline int tee_shm_get_id(struct tee_shm *shm) -{ - return shm->id; -} - -/** - * tee_shm_get_from_id() - Find shared memory object and increase reference - * count - * @ctx: Context owning the shared memory - * @id: Id of shared memory object - * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure - */ -struct tee_shm *tee_shm_get_from_id(struct tee_context *ctx, int id); - -/** * tee_client_open_context() - Open a TEE context * @start: if not NULL, continue search after this context * @match: function to check TEE device @@ -470,18 +273,6 @@ int tee_client_invoke_func(struct tee_context *ctx, int tee_client_cancel_req(struct tee_context *ctx, struct tee_ioctl_cancel_arg *arg); -static inline bool tee_param_is_memref(struct tee_param *param) -{ - switch (param->attr & TEE_IOCTL_PARAM_ATTR_TYPE_MASK) { - case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT: - case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT: - case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT: - return true; - default: - return false; - } -} - extern const struct bus_type tee_bus_type; /** @@ -507,20 +298,6 @@ struct tee_client_driver { }; #define to_tee_client_driver(d) \ - container_of(d, struct tee_client_driver, driver) - -/** - * teedev_open() - Open a struct tee_device - * @teedev: Device to open - * - * @return a pointer to struct tee_context on success or an ERR_PTR on failure. - */ -struct tee_context *teedev_open(struct tee_device *teedev); - -/** - * teedev_close_context() - closes a struct tee_context - * @ctx: The struct tee_context to close - */ -void teedev_close_context(struct tee_context *ctx); + container_of_const(d, struct tee_client_driver, driver) #endif /*__TEE_DRV_H*/ diff --git a/include/linux/thermal.h b/include/linux/thermal.h index c33f50177f51..b86ddca46b9e 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -55,13 +55,13 @@ enum thermal_notify_event { THERMAL_TZ_BIND_CDEV, /* Cooling dev is bind to the thermal zone */ THERMAL_TZ_UNBIND_CDEV, /* Cooling dev is unbind from the thermal zone */ THERMAL_INSTANCE_WEIGHT_CHANGED, /* Thermal instance weight changed */ + THERMAL_TZ_RESUME, /* Thermal zone is resuming after system sleep */ }; /** * struct thermal_trip - representation of a point in temperature domain * @temperature: temperature value in miliCelsius * @hysteresis: relative hysteresis in miliCelsius - * @threshold: trip crossing notification threshold miliCelsius * @type: trip point type * @priv: pointer to driver data associated with this trip * @flags: flags representing binary properties of the trip @@ -69,7 +69,6 @@ enum thermal_notify_event { struct thermal_trip { int temperature; int hysteresis; - int threshold; enum thermal_trip_type type; u8 flags; void *priv; @@ -81,6 +80,11 @@ struct thermal_trip { #define THERMAL_TRIP_FLAG_RW (THERMAL_TRIP_FLAG_RW_TEMP | \ THERMAL_TRIP_FLAG_RW_HYST) +#define THERMAL_TRIP_PRIV_TO_INT(_val_) (uintptr_t)(_val_) +#define THERMAL_INT_TO_TRIP_PRIV(_val_) (void *)(uintptr_t)(_val_) + +struct thermal_zone_device; + struct thermal_zone_device_ops { int (*bind) (struct thermal_zone_device *, struct thermal_cooling_device *); @@ -90,7 +94,8 @@ struct thermal_zone_device_ops { int (*set_trips) (struct thermal_zone_device *, int, int); int (*change_mode) (struct thermal_zone_device *, enum thermal_device_mode); - int (*set_trip_temp) (struct thermal_zone_device *, int, int); + int (*set_trip_temp) (struct thermal_zone_device *, + const struct thermal_trip *, int); int (*get_crit_temp) (struct thermal_zone_device *, int *); int (*set_emul_temp) (struct thermal_zone_device *, int); int (*get_trend) (struct thermal_zone_device *, @@ -126,111 +131,6 @@ struct thermal_cooling_device { #endif }; -/** - * struct thermal_zone_device - structure for a thermal zone - * @id: unique id number for each thermal zone - * @type: the thermal zone device type - * @device: &struct device for this thermal zone - * @removal: removal completion - * @trip_temp_attrs: attributes for trip points for sysfs: trip temperature - * @trip_type_attrs: attributes for trip points for sysfs: trip type - * @trip_hyst_attrs: attributes for trip points for sysfs: trip hysteresis - * @mode: current mode of this thermal zone - * @devdata: private pointer for device private data - * @num_trips: number of trip points the thermal zone supports - * @passive_delay_jiffies: number of jiffies to wait between polls when - * performing passive cooling. - * @polling_delay_jiffies: number of jiffies to wait between polls when - * checking whether trip points have been crossed (0 for - * interrupt driven systems) - * @temperature: current temperature. This is only for core code, - * drivers should use thermal_zone_get_temp() to get the - * current temperature - * @last_temperature: previous temperature read - * @emul_temperature: emulated temperature when using CONFIG_THERMAL_EMULATION - * @passive: 1 if you've crossed a passive trip point, 0 otherwise. - * @prev_low_trip: the low current temperature if you've crossed a passive - trip point. - * @prev_high_trip: the above current temperature if you've crossed a - passive trip point. - * @need_update: if equals 1, thermal_zone_device_update needs to be invoked. - * @ops: operations this &thermal_zone_device supports - * @tzp: thermal zone parameters - * @governor: pointer to the governor for this thermal zone - * @governor_data: private pointer for governor data - * @thermal_instances: list of &struct thermal_instance of this thermal zone - * @ida: &struct ida to generate unique id for this zone's cooling - * devices - * @lock: lock to protect thermal_instances list - * @node: node in thermal_tz_list (in thermal_core.c) - * @poll_queue: delayed work for polling - * @notify_event: Last notification event - * @suspended: thermal zone suspend indicator - * @trips: array of struct thermal_trip objects - */ -struct thermal_zone_device { - int id; - char type[THERMAL_NAME_LENGTH]; - struct device device; - struct completion removal; - struct attribute_group trips_attribute_group; - struct thermal_attr *trip_temp_attrs; - struct thermal_attr *trip_type_attrs; - struct thermal_attr *trip_hyst_attrs; - enum thermal_device_mode mode; - void *devdata; - int num_trips; - unsigned long passive_delay_jiffies; - unsigned long polling_delay_jiffies; - int temperature; - int last_temperature; - int emul_temperature; - int passive; - int prev_low_trip; - int prev_high_trip; - atomic_t need_update; - struct thermal_zone_device_ops ops; - struct thermal_zone_params *tzp; - struct thermal_governor *governor; - void *governor_data; - struct list_head thermal_instances; - struct ida ida; - struct mutex lock; - struct list_head node; - struct delayed_work poll_queue; - enum thermal_notify_event notify_event; - bool suspended; -#ifdef CONFIG_THERMAL_DEBUGFS - struct thermal_debugfs *debugfs; -#endif - struct thermal_trip trips[] __counted_by(num_trips); -}; - -/** - * struct thermal_governor - structure that holds thermal governor information - * @name: name of the governor - * @bind_to_tz: callback called when binding to a thermal zone. If it - * returns 0, the governor is bound to the thermal zone, - * otherwise it fails. - * @unbind_from_tz: callback called when a governor is unbound from a - * thermal zone. - * @throttle: callback called for every trip point even if temperature is - * below the trip point temperature - * @update_tz: callback called when thermal zone internals have changed, e.g. - * thermal cooling instance was added/removed - * @governor_list: node in thermal_governor_list (in thermal_core.c) - */ -struct thermal_governor { - const char *name; - int (*bind_to_tz)(struct thermal_zone_device *tz); - void (*unbind_from_tz)(struct thermal_zone_device *tz); - int (*throttle)(struct thermal_zone_device *tz, - const struct thermal_trip *trip); - void (*update_tz)(struct thermal_zone_device *tz, - enum thermal_notify_event reason); - struct list_head governor_list; -}; - /* Structure to define Thermal Zone parameters */ struct thermal_zone_params { const char *governor_name; @@ -303,8 +203,6 @@ static inline void devm_thermal_of_zone_unregister(struct device *dev, } #endif -int __thermal_zone_get_trip(struct thermal_zone_device *tz, int trip_id, - struct thermal_trip *trip); int thermal_zone_get_trip(struct thermal_zone_device *tz, int trip_id, struct thermal_trip *trip); int for_each_thermal_trip(struct thermal_zone_device *tz, @@ -326,7 +224,8 @@ struct thermal_zone_device *thermal_zone_device_register_with_trips( int num_trips, void *devdata, const struct thermal_zone_device_ops *ops, const struct thermal_zone_params *tzp, - int passive_delay, int polling_delay); + unsigned int passive_delay, + unsigned int polling_delay); struct thermal_zone_device *thermal_tripless_zone_device_register( const char *type, @@ -366,7 +265,7 @@ thermal_of_cooling_device_register(struct device_node *np, const char *, void *, struct thermal_cooling_device * devm_thermal_of_cooling_device_register(struct device *dev, struct device_node *np, - char *type, void *devdata, + const char *type, void *devdata, const struct thermal_cooling_device_ops *ops); void thermal_cooling_device_update(struct thermal_cooling_device *); void thermal_cooling_device_unregister(struct thermal_cooling_device *); @@ -374,6 +273,9 @@ struct thermal_zone_device *thermal_zone_get_zone_by_name(const char *name); int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp); int thermal_zone_get_slope(struct thermal_zone_device *tz); int thermal_zone_get_offset(struct thermal_zone_device *tz); +bool thermal_trip_is_bound_to_cdev(struct thermal_zone_device *tz, + const struct thermal_trip *trip, + struct thermal_cooling_device *cdev); int thermal_zone_device_enable(struct thermal_zone_device *tz); int thermal_zone_device_disable(struct thermal_zone_device *tz); @@ -410,7 +312,7 @@ thermal_of_cooling_device_register(struct device_node *np, static inline struct thermal_cooling_device * devm_thermal_of_cooling_device_register(struct device *dev, struct device_node *np, - char *type, void *devdata, + const char *type, void *devdata, const struct thermal_cooling_device_ops *ops) { return ERR_PTR(-ENODEV); diff --git a/include/linux/threads.h b/include/linux/threads.h index c34173e6c5f1..1674a471b0b4 100644 --- a/include/linux/threads.h +++ b/include/linux/threads.h @@ -25,13 +25,13 @@ /* * This controls the default maximum pid allocated to a process */ -#define PID_MAX_DEFAULT (CONFIG_BASE_SMALL ? 0x1000 : 0x8000) +#define PID_MAX_DEFAULT (IS_ENABLED(CONFIG_BASE_SMALL) ? 0x1000 : 0x8000) /* * A maximum of 4 million PIDs should be enough for a while. * [NOTE: PID/TIDs are limited to 2^30 ~= 1 billion, see FUTEX_TID_MASK.] */ -#define PID_MAX_LIMIT (CONFIG_BASE_SMALL ? PAGE_SIZE * 8 : \ +#define PID_MAX_LIMIT (IS_ENABLED(CONFIG_BASE_SMALL) ? PAGE_SIZE * 8 : \ (sizeof(long) > 4 ? 4 * 1024 * 1024 : PID_MAX_DEFAULT)) /* diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index 4338ea9ac4fd..7d902d8c054b 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -33,7 +33,6 @@ enum tb_cfg_pkg_type { TB_CFG_PKG_ICM_EVENT = 10, TB_CFG_PKG_ICM_CMD = 11, TB_CFG_PKG_ICM_RESP = 12, - TB_CFG_PKG_PREPARE_TO_SLEEP = 13, }; /** diff --git a/include/linux/tick.h b/include/linux/tick.h index 4924a33700b7..72744638c5b0 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -139,7 +139,6 @@ extern void tick_nohz_irq_exit(void); extern bool tick_nohz_idle_got_tick(void); extern ktime_t tick_nohz_get_next_hrtimer(void); extern ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next); -extern unsigned long tick_nohz_get_idle_calls(void); extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu); extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 0ea7823b7f31..fc12a9ba2c88 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -310,12 +310,18 @@ struct system_device_crosststamp { * timekeeping code to verify comparability of two cycle values. * The default ID, CSID_GENERIC, does not identify a specific * clocksource. + * @use_nsecs: @cycles is in nanoseconds. */ struct system_counterval_t { u64 cycles; enum clocksource_ids cs_id; + bool use_nsecs; }; +extern bool ktime_real_to_base_clock(ktime_t treal, + enum clocksource_ids base_id, u64 *cycles); +extern bool timekeeping_clocksource_has_base(enum clocksource_ids id); + /* * Get cross timestamp between system clock and device clock */ diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h index 62973f7d4610..d306d9dd2207 100644 --- a/include/linux/timerqueue.h +++ b/include/linux/timerqueue.h @@ -37,11 +37,6 @@ static inline bool timerqueue_node_queued(struct timerqueue_node *node) return !RB_EMPTY_NODE(&node->node); } -static inline bool timerqueue_node_expires(struct timerqueue_node *node) -{ - return node->expires; -} - static inline void timerqueue_init_head(struct timerqueue_head *head) { head->rb_root = RB_ROOT_CACHED; diff --git a/include/linux/torture.h b/include/linux/torture.h index 1541454da03e..c2e979f82f8d 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -14,7 +14,7 @@ #include <linux/cache.h> #include <linux/spinlock.h> #include <linux/threads.h> -#include <linux/cpumask.h> +#include <linux/cpumask_types.h> #include <linux/seqlock.h> #include <linux/lockdep.h> #include <linux/completion.h> diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 4ee9d13749ad..e93ee8d936a9 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -23,6 +23,7 @@ #include <linux/fs.h> #include <linux/highmem.h> #include <crypto/hash_info.h> +#include <crypto/aes.h> #define TPM_DIGEST_SIZE 20 /* Max TPM v1.2 PCR size */ #define TPM_MAX_DIGEST_SIZE SHA512_DIGEST_SIZE @@ -30,17 +31,28 @@ struct tpm_chip; struct trusted_key_payload; struct trusted_key_options; +/* opaque structure, holds auth session parameters like the session key */ +struct tpm2_auth; + +enum tpm2_session_types { + TPM2_SE_HMAC = 0x00, + TPM2_SE_POLICY = 0x01, + TPM2_SE_TRIAL = 0x02, +}; /* if you add a new hash to this, increment TPM_MAX_HASHES below */ enum tpm_algorithms { TPM_ALG_ERROR = 0x0000, TPM_ALG_SHA1 = 0x0004, + TPM_ALG_AES = 0x0006, TPM_ALG_KEYEDHASH = 0x0008, TPM_ALG_SHA256 = 0x000B, TPM_ALG_SHA384 = 0x000C, TPM_ALG_SHA512 = 0x000D, TPM_ALG_NULL = 0x0010, TPM_ALG_SM3_256 = 0x0012, + TPM_ALG_ECC = 0x0023, + TPM_ALG_CFB = 0x0043, }; /* @@ -49,6 +61,11 @@ enum tpm_algorithms { */ #define TPM_MAX_HASHES 5 +enum tpm2_curves { + TPM2_ECC_NONE = 0x0000, + TPM2_ECC_NIST_P256 = 0x0003, +}; + struct tpm_digest { u16 alg_id; u8 digest[TPM_MAX_DIGEST_SIZE]; @@ -116,6 +133,20 @@ struct tpm_chip_seqops { const struct seq_operations *seqops; }; +/* fixed define for the curve we use which is NIST_P256 */ +#define EC_PT_SZ 32 + +/* + * fixed define for the size of a name. This is actually HASHALG size + * plus 2, so 32 for SHA256 + */ +#define TPM2_NAME_SIZE 34 + +/* + * The maximum size for an object context + */ +#define TPM2_MAX_CONTEXT_SIZE 4096 + struct tpm_chip { struct device dev; struct device devs; @@ -170,6 +201,18 @@ struct tpm_chip { /* active locality */ int locality; + +#ifdef CONFIG_TCG_TPM2_HMAC + /* details for communication security via sessions */ + + /* saved context for NULL seed */ + u8 null_key_context[TPM2_MAX_CONTEXT_SIZE]; + /* name of NULL seed */ + u8 null_key_name[TPM2_NAME_SIZE]; + u8 null_ec_key_x[EC_PT_SZ]; + u8 null_ec_key_y[EC_PT_SZ]; + struct tpm2_auth *auth; +#endif }; #define TPM_HEADER_SIZE 10 @@ -194,6 +237,7 @@ enum tpm2_timeouts { enum tpm2_structures { TPM2_ST_NO_SESSIONS = 0x8001, TPM2_ST_SESSIONS = 0x8002, + TPM2_ST_CREATION = 0x8021, }; /* Indicates from what layer of the software stack the error comes from */ @@ -204,6 +248,7 @@ enum tpm2_return_codes { TPM2_RC_SUCCESS = 0x0000, TPM2_RC_HASH = 0x0083, /* RC_FMT1 */ TPM2_RC_HANDLE = 0x008B, + TPM2_RC_INTEGRITY = 0x009F, TPM2_RC_INITIALIZE = 0x0100, /* RC_VER1 */ TPM2_RC_FAILURE = 0x0101, TPM2_RC_DISABLED = 0x0120, @@ -231,6 +276,8 @@ enum tpm2_command_codes { TPM2_CC_CONTEXT_LOAD = 0x0161, TPM2_CC_CONTEXT_SAVE = 0x0162, TPM2_CC_FLUSH_CONTEXT = 0x0165, + TPM2_CC_READ_PUBLIC = 0x0173, + TPM2_CC_START_AUTH_SESS = 0x0176, TPM2_CC_VERIFY_SIGNATURE = 0x0177, TPM2_CC_GET_CAPABILITY = 0x017A, TPM2_CC_GET_RANDOM = 0x017B, @@ -243,9 +290,25 @@ enum tpm2_command_codes { }; enum tpm2_permanent_handles { + TPM2_RH_NULL = 0x40000007, TPM2_RS_PW = 0x40000009, }; +/* Most Significant Octet for key types */ +enum tpm2_mso_type { + TPM2_MSO_NVRAM = 0x01, + TPM2_MSO_SESSION = 0x02, + TPM2_MSO_POLICY = 0x03, + TPM2_MSO_PERMANENT = 0x40, + TPM2_MSO_VOLATILE = 0x80, + TPM2_MSO_PERSISTENT = 0x81, +}; + +static inline enum tpm2_mso_type tpm2_handle_mso(u32 handle) +{ + return handle >> 24; +} + enum tpm2_capabilities { TPM2_CAP_HANDLES = 1, TPM2_CAP_COMMANDS = 2, @@ -284,6 +347,7 @@ enum tpm_chip_flags { TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), TPM_CHIP_FLAG_SUSPENDED = BIT(8), TPM_CHIP_FLAG_HWRNG_DISABLED = BIT(9), + TPM_CHIP_FLAG_DISABLE = BIT(10), }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) @@ -297,28 +361,46 @@ struct tpm_header { }; } __packed; -/* A string buffer type for constructing TPM commands. This is based on the - * ideas of string buffer code in security/keys/trusted.h but is heap based - * in order to keep the stack usage minimal. - */ - enum tpm_buf_flags { + /* the capacity exceeded: */ TPM_BUF_OVERFLOW = BIT(0), + /* TPM2B format: */ + TPM_BUF_TPM2B = BIT(1), + /* read out of boundary: */ + TPM_BUF_BOUNDARY_ERROR = BIT(2), }; +/* + * A string buffer type for constructing TPM commands. + */ struct tpm_buf { - unsigned int flags; + u32 flags; + u32 length; u8 *data; + u8 handles; }; enum tpm2_object_attributes { TPM2_OA_FIXED_TPM = BIT(1), + TPM2_OA_ST_CLEAR = BIT(2), TPM2_OA_FIXED_PARENT = BIT(4), + TPM2_OA_SENSITIVE_DATA_ORIGIN = BIT(5), TPM2_OA_USER_WITH_AUTH = BIT(6), + TPM2_OA_ADMIN_WITH_POLICY = BIT(7), + TPM2_OA_NO_DA = BIT(10), + TPM2_OA_ENCRYPTED_DUPLICATION = BIT(11), + TPM2_OA_RESTRICTED = BIT(16), + TPM2_OA_DECRYPT = BIT(17), + TPM2_OA_SIGN = BIT(18), }; enum tpm2_session_attributes { TPM2_SA_CONTINUE_SESSION = BIT(0), + TPM2_SA_AUDIT_EXCLUSIVE = BIT(1), + TPM2_SA_AUDIT_RESET = BIT(3), + TPM2_SA_DECRYPT = BIT(5), + TPM2_SA_ENCRYPT = BIT(6), + TPM2_SA_AUDIT = BIT(7), }; struct tpm2_hash { @@ -326,84 +408,19 @@ struct tpm2_hash { unsigned int tpm_id; }; -static inline void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - head->tag = cpu_to_be16(tag); - head->length = cpu_to_be32(sizeof(*head)); - head->ordinal = cpu_to_be32(ordinal); -} - -static inline int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal) -{ - buf->data = (u8 *)__get_free_page(GFP_KERNEL); - if (!buf->data) - return -ENOMEM; - - buf->flags = 0; - tpm_buf_reset(buf, tag, ordinal); - return 0; -} - -static inline void tpm_buf_destroy(struct tpm_buf *buf) -{ - free_page((unsigned long)buf->data); -} - -static inline u32 tpm_buf_length(struct tpm_buf *buf) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - return be32_to_cpu(head->length); -} - -static inline u16 tpm_buf_tag(struct tpm_buf *buf) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - return be16_to_cpu(head->tag); -} - -static inline void tpm_buf_append(struct tpm_buf *buf, - const unsigned char *new_data, - unsigned int new_len) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - u32 len = tpm_buf_length(buf); - - /* Return silently if overflow has already happened. */ - if (buf->flags & TPM_BUF_OVERFLOW) - return; - - if ((len + new_len) > PAGE_SIZE) { - WARN(1, "tpm_buf: overflow\n"); - buf->flags |= TPM_BUF_OVERFLOW; - return; - } - - memcpy(&buf->data[len], new_data, new_len); - head->length = cpu_to_be32(len + new_len); -} - -static inline void tpm_buf_append_u8(struct tpm_buf *buf, const u8 value) -{ - tpm_buf_append(buf, &value, 1); -} - -static inline void tpm_buf_append_u16(struct tpm_buf *buf, const u16 value) -{ - __be16 value2 = cpu_to_be16(value); - - tpm_buf_append(buf, (u8 *) &value2, 2); -} - -static inline void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value) -{ - __be32 value2 = cpu_to_be32(value); - - tpm_buf_append(buf, (u8 *) &value2, 4); -} +int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal); +void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal); +int tpm_buf_init_sized(struct tpm_buf *buf); +void tpm_buf_reset_sized(struct tpm_buf *buf); +void tpm_buf_destroy(struct tpm_buf *buf); +u32 tpm_buf_length(struct tpm_buf *buf); +void tpm_buf_append(struct tpm_buf *buf, const u8 *new_data, u16 new_length); +void tpm_buf_append_u8(struct tpm_buf *buf, const u8 value); +void tpm_buf_append_u16(struct tpm_buf *buf, const u16 value); +void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value); +u8 tpm_buf_read_u8(struct tpm_buf *buf, off_t *offset); +u16 tpm_buf_read_u16(struct tpm_buf *buf, off_t *offset); +u32 tpm_buf_read_u32(struct tpm_buf *buf, off_t *offset); /* * Check if TPM device is in the firmware upgrade mode. @@ -415,7 +432,7 @@ static inline bool tpm_is_firmware_upgrade(struct tpm_chip *chip) static inline u32 tpm2_rc_value(u32 rc) { - return (rc & BIT(7)) ? rc & 0xff : rc; + return (rc & BIT(7)) ? rc & 0xbf : rc; } #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE) @@ -429,10 +446,19 @@ extern int tpm_pcr_read(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digest); extern int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digests); -extern int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen); extern int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max); extern struct tpm_chip *tpm_default_chip(void); void tpm2_flush_context(struct tpm_chip *chip, u32 handle); + +static inline void tpm_buf_append_empty_auth(struct tpm_buf *buf, u32 handle) +{ + /* simple authorization for empty auth */ + tpm_buf_append_u32(buf, 9); /* total length of auth */ + tpm_buf_append_u32(buf, handle); + tpm_buf_append_u16(buf, 0); /* nonce len */ + tpm_buf_append_u8(buf, 0); /* attributes */ + tpm_buf_append_u16(buf, 0); /* hmac len */ +} #else static inline int tpm_is_tpm2(struct tpm_chip *chip) { @@ -450,10 +476,6 @@ static inline int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, return -ENODEV; } -static inline int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen) -{ - return -ENODEV; -} static inline int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max) { return -ENODEV; @@ -463,5 +485,77 @@ static inline struct tpm_chip *tpm_default_chip(void) { return NULL; } + +static inline void tpm_buf_append_empty_auth(struct tpm_buf *buf, u32 handle) +{ +} #endif + +static inline struct tpm2_auth *tpm2_chip_auth(struct tpm_chip *chip) +{ +#ifdef CONFIG_TCG_TPM2_HMAC + return chip->auth; +#else + return NULL; +#endif +} + +void tpm_buf_append_name(struct tpm_chip *chip, struct tpm_buf *buf, + u32 handle, u8 *name); +void tpm_buf_append_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf, + u8 attributes, u8 *passphrase, + int passphraselen); +static inline void tpm_buf_append_hmac_session_opt(struct tpm_chip *chip, + struct tpm_buf *buf, + u8 attributes, + u8 *passphrase, + int passphraselen) +{ + struct tpm_header *head; + int offset; + + if (tpm2_chip_auth(chip)) { + tpm_buf_append_hmac_session(chip, buf, attributes, passphrase, passphraselen); + } else { + offset = buf->handles * 4 + TPM_HEADER_SIZE; + head = (struct tpm_header *)buf->data; + + /* + * If the only sessions are optional, the command tag must change to + * TPM2_ST_NO_SESSIONS. + */ + if (tpm_buf_length(buf) == offset) + head->tag = cpu_to_be16(TPM2_ST_NO_SESSIONS); + } +} + +#ifdef CONFIG_TCG_TPM2_HMAC + +int tpm2_start_auth_session(struct tpm_chip *chip); +void tpm_buf_fill_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf); +int tpm_buf_check_hmac_response(struct tpm_chip *chip, struct tpm_buf *buf, + int rc); +void tpm2_end_auth_session(struct tpm_chip *chip); +#else +#include <asm/unaligned.h> + +static inline int tpm2_start_auth_session(struct tpm_chip *chip) +{ + return 0; +} +static inline void tpm2_end_auth_session(struct tpm_chip *chip) +{ +} +static inline void tpm_buf_fill_hmac_session(struct tpm_chip *chip, + struct tpm_buf *buf) +{ +} +static inline int tpm_buf_check_hmac_response(struct tpm_chip *chip, + struct tpm_buf *buf, + int rc) +{ + return rc; +} +#endif /* CONFIG_TCG_TPM2_HMAC */ + #endif diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 6f9bdfb09d1d..42bedcddd511 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -680,7 +680,7 @@ struct trace_event_file { * caching and such. Which is mostly OK ;-) */ unsigned long flags; - atomic_t ref; /* ref count for opened files */ + refcount_t ref; /* ref count for opened files */ atomic_t sm_ref; /* soft-mode reference counter */ atomic_t tm_ref; /* trigger-mode reference counter */ }; @@ -765,8 +765,11 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx); int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie); void perf_event_detach_bpf_prog(struct perf_event *event); int perf_event_query_prog_array(struct perf_event *event, void __user *info); -int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog); -int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog); + +struct bpf_raw_tp_link; +int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link); +int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link); + struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name); void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp); int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, @@ -794,11 +797,12 @@ perf_event_query_prog_array(struct perf_event *event, void __user *info) { return -EOPNOTSUPP; } -static inline int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *p) +struct bpf_raw_tp_link; +static inline int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { return -EOPNOTSUPP; } -static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *p) +static inline int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_raw_tp_link *link) { return -EOPNOTSUPP; } @@ -876,7 +880,6 @@ do { \ struct perf_event; DECLARE_PER_CPU(struct pt_regs, perf_trace_regs); -DECLARE_PER_CPU(int, bpf_kprobe_override); extern int perf_trace_init(struct perf_event *event); extern void perf_trace_destroy(struct perf_event *event); @@ -909,31 +912,31 @@ void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp); int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog, u64 bpf_cookie); void perf_event_free_bpf_prog(struct perf_event *event); -void bpf_trace_run1(struct bpf_prog *prog, u64 arg1); -void bpf_trace_run2(struct bpf_prog *prog, u64 arg1, u64 arg2); -void bpf_trace_run3(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run1(struct bpf_raw_tp_link *link, u64 arg1); +void bpf_trace_run2(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2); +void bpf_trace_run3(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3); -void bpf_trace_run4(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run4(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4); -void bpf_trace_run5(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run5(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5); -void bpf_trace_run6(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run6(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6); -void bpf_trace_run7(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run7(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7); -void bpf_trace_run8(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run8(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8); -void bpf_trace_run9(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run9(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9); -void bpf_trace_run10(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run10(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10); -void bpf_trace_run11(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run11(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10, u64 arg11); -void bpf_trace_run12(struct bpf_prog *prog, u64 arg1, u64 arg2, +void bpf_trace_run12(struct bpf_raw_tp_link *link, u64 arg1, u64 arg2, u64 arg3, u64 arg4, u64 arg5, u64 arg6, u64 arg7, u64 arg8, u64 arg9, u64 arg10, u64 arg11, u64 arg12); void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx, diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h index d48cd92d2364..ae04054a1be3 100644 --- a/include/linux/trace_recursion.h +++ b/include/linux/trace_recursion.h @@ -44,35 +44,6 @@ enum { */ TRACE_IRQ_BIT, - /* Set if the function is in the set_graph_function file */ - TRACE_GRAPH_BIT, - - /* - * In the very unlikely case that an interrupt came in - * at a start of graph tracing, and we want to trace - * the function in that interrupt, the depth can be greater - * than zero, because of the preempted start of a previous - * trace. In an even more unlikely case, depth could be 2 - * if a softirq interrupted the start of graph tracing, - * followed by an interrupt preempting a start of graph - * tracing in the softirq, and depth can even be 3 - * if an NMI came in at the start of an interrupt function - * that preempted a softirq start of a function that - * preempted normal context!!!! Luckily, it can't be - * greater than 3, so the next two bits are a mask - * of what the depth is when we set TRACE_GRAPH_BIT - */ - - TRACE_GRAPH_DEPTH_START_BIT, - TRACE_GRAPH_DEPTH_END_BIT, - - /* - * To implement set_graph_notrace, if this bit is set, we ignore - * function graph tracing of called functions, until the return - * function is called to clear it. - */ - TRACE_GRAPH_NOTRACE_BIT, - /* Used to prevent recursion recording from recursing. */ TRACE_RECORD_RECURSION_BIT, }; @@ -81,16 +52,6 @@ enum { #define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(1<<(bit)); } while (0) #define trace_recursion_test(bit) ((current)->trace_recursion & (1<<(bit))) -#define trace_recursion_depth() \ - (((current)->trace_recursion >> TRACE_GRAPH_DEPTH_START_BIT) & 3) -#define trace_recursion_set_depth(depth) \ - do { \ - current->trace_recursion &= \ - ~(3 << TRACE_GRAPH_DEPTH_START_BIT); \ - current->trace_recursion |= \ - ((depth) & 3) << TRACE_GRAPH_DEPTH_START_BIT; \ - } while (0) - #define TRACE_CONTEXT_BITS 4 #define TRACE_FTRACE_START TRACE_FTRACE_BIT @@ -135,7 +96,7 @@ extern void ftrace_record_recursion(unsigned long ip, unsigned long parent_ip); # define do_ftrace_record_recursion(ip, pip) do { } while (0) #endif -#ifdef CONFIG_ARCH_WANTS_NO_INSTR +#ifdef CONFIG_FTRACE_VALIDATE_RCU_IS_WATCHING # define trace_warn_on_no_rcu(ip) \ ({ \ bool __ret = !rcu_is_watching(); \ diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 689b6d71590e..6be396bb4297 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -16,7 +16,6 @@ #include <linux/srcu.h> #include <linux/errno.h> #include <linux/types.h> -#include <linux/cpumask.h> #include <linux/rcupdate.h> #include <linux/tracepoint-defs.h> #include <linux/static_call.h> diff --git a/include/linux/tsm.h b/include/linux/tsm.h index de8324a2223c..11b0c525be30 100644 --- a/include/linux/tsm.h +++ b/include/linux/tsm.h @@ -4,6 +4,7 @@ #include <linux/sizes.h> #include <linux/types.h> +#include <linux/uuid.h> #define TSM_INBLOB_MAX 64 #define TSM_OUTBLOB_MAX SZ_32K @@ -19,11 +20,17 @@ * @privlevel: optional privilege level to associate with @outblob * @inblob_len: sizeof @inblob * @inblob: arbitrary input data + * @service_provider: optional name of where to obtain the tsm report blob + * @service_guid: optional service-provider service guid to attest + * @service_manifest_version: optional service-provider service manifest version requested */ struct tsm_desc { unsigned int privlevel; size_t inblob_len; u8 inblob[TSM_INBLOB_MAX]; + char *service_provider; + guid_t service_guid; + unsigned int service_manifest_version; }; /** @@ -33,6 +40,8 @@ struct tsm_desc { * @outblob: generated evidence to provider to the attestation agent * @auxblob_len: sizeof(@auxblob) * @auxblob: (optional) auxiliary data to the report (e.g. certificate data) + * @manifestblob_len: sizeof(@manifestblob) + * @manifestblob: (optional) manifest data associated with the report */ struct tsm_report { struct tsm_desc desc; @@ -40,6 +49,42 @@ struct tsm_report { u8 *outblob; size_t auxblob_len; u8 *auxblob; + size_t manifestblob_len; + u8 *manifestblob; +}; + +/** + * enum tsm_attr_index - index used to reference report attributes + * @TSM_REPORT_GENERATION: index of the report generation number attribute + * @TSM_REPORT_PROVIDER: index of the provider name attribute + * @TSM_REPORT_PRIVLEVEL: index of the desired privilege level attribute + * @TSM_REPORT_PRIVLEVEL_FLOOR: index of the minimum allowed privileg level attribute + * @TSM_REPORT_SERVICE_PROVIDER: index of the service provider identifier attribute + * @TSM_REPORT_SERVICE_GUID: index of the service GUID attribute + * @TSM_REPORT_SERVICE_MANIFEST_VER: index of the service manifest version attribute + */ +enum tsm_attr_index { + TSM_REPORT_GENERATION, + TSM_REPORT_PROVIDER, + TSM_REPORT_PRIVLEVEL, + TSM_REPORT_PRIVLEVEL_FLOOR, + TSM_REPORT_SERVICE_PROVIDER, + TSM_REPORT_SERVICE_GUID, + TSM_REPORT_SERVICE_MANIFEST_VER, +}; + +/** + * enum tsm_bin_attr_index - index used to reference binary report attributes + * @TSM_REPORT_INBLOB: index of the binary report input attribute + * @TSM_REPORT_OUTBLOB: index of the binary report output attribute + * @TSM_REPORT_AUXBLOB: index of the binary auxiliary data attribute + * @TSM_REPORT_MANIFESTBLOB: index of the binary manifest data attribute + */ +enum tsm_bin_attr_index { + TSM_REPORT_INBLOB, + TSM_REPORT_OUTBLOB, + TSM_REPORT_AUXBLOB, + TSM_REPORT_MANIFESTBLOB, }; /** @@ -48,22 +93,20 @@ struct tsm_report { * @privlevel_floor: convey base privlevel for nested scenarios * @report_new: Populate @report with the report blob and auxblob * (optional), return 0 on successful population, or -errno otherwise + * @report_attr_visible: show or hide a report attribute entry + * @report_bin_attr_visible: show or hide a report binary attribute entry * * Implementation specific ops, only one is expected to be registered at * a time i.e. only one of "sev-guest", "tdx-guest", etc. */ struct tsm_ops { const char *name; - const unsigned int privlevel_floor; + unsigned int privlevel_floor; int (*report_new)(struct tsm_report *report, void *data); + bool (*report_attr_visible)(int n); + bool (*report_bin_attr_visible)(int n); }; -extern const struct config_item_type tsm_report_default_type; - -/* publish @privlevel, @privlevel_floor, and @auxblob attributes */ -extern const struct config_item_type tsm_report_extra_type; - -int tsm_register(const struct tsm_ops *ops, void *priv, - const struct config_item_type *type); +int tsm_register(const struct tsm_ops *ops, void *priv); int tsm_unregister(const struct tsm_ops *ops); #endif /* __TSM_H */ diff --git a/include/linux/tty.h b/include/linux/tty.h index 2b2e6f0a54d6..2372f9357240 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -145,15 +145,12 @@ struct tty_operations; * @count: count of open processes, reaching zero cancels all the work for * this tty and drops a @kref too (but does not free this tty) * @winsize: size of the terminal "window" (cf. @winsize_mutex) - * @flow: flow settings grouped together, see also @flow.unused + * @flow: flow settings grouped together * @flow.lock: lock for @flow members * @flow.stopped: tty stopped/started by stop_tty()/start_tty() * @flow.tco_stopped: tty stopped/started by %TCOOFF/%TCOON ioctls (it has * precedence over @flow.stopped) - * @flow.unused: alignment for Alpha, so that no members other than @flow.* are - * modified by the same 64b word store. The @flow's __aligned is - * there for the very same reason. - * @ctrl: control settings grouped together, see also @ctrl.unused + * @ctrl: control settings grouped together * @ctrl.lock: lock for @ctrl members * @ctrl.pgrp: process group of this tty (setpgrp(2)) * @ctrl.session: session of this tty (setsid(2)). Writes are protected by both @@ -161,7 +158,6 @@ struct tty_operations; * them. * @ctrl.pktstatus: packet mode status (bitwise OR of %TIOCPKT_ constants) * @ctrl.packet: packet mode enabled - * @ctrl.unused: alignment for Alpha, see @flow.unused for explanation * @hw_stopped: not controlled by the tty layer, under @driver's control for CTS * handling * @receive_room: bytes permitted to feed to @ldisc without any being lost @@ -216,8 +212,7 @@ struct tty_struct { spinlock_t lock; bool stopped; bool tco_stopped; - unsigned long unused[0]; - } __aligned(sizeof(unsigned long)) flow; + } flow; struct { struct pid *pgrp; @@ -225,8 +220,7 @@ struct tty_struct { spinlock_t lock; unsigned char pktstatus; bool packet; - unsigned long unused[0]; - } __aligned(sizeof(unsigned long)) ctrl; + } ctrl; bool hw_stopped; bool closing; diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 7372124fbf90..dd4b31ce6d5d 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -154,6 +154,13 @@ struct serial_struct; * * Optional. Called under the @tty->termios_rwsem. May sleep. * + * @ldisc_ok: ``int ()(struct tty_struct *tty, int ldisc)`` + * + * This routine allows the @tty driver to decide if it can deal + * with a particular @ldisc. + * + * Optional. Called under the @tty->ldisc_sem and @tty->termios_rwsem. + * * @set_ldisc: ``void ()(struct tty_struct *tty)`` * * This routine allows the @tty driver to be notified when the device's @@ -372,6 +379,7 @@ struct tty_operations { void (*hangup)(struct tty_struct *tty); int (*break_ctl)(struct tty_struct *tty, int state); void (*flush_buffer)(struct tty_struct *tty); + int (*ldisc_ok)(struct tty_struct *tty, int ldisc); void (*set_ldisc)(struct tty_struct *tty); void (*wait_until_sent)(struct tty_struct *tty, int timeout); void (*send_xchar)(struct tty_struct *tty, u8 ch); diff --git a/include/linux/turris-omnia-mcu-interface.h b/include/linux/turris-omnia-mcu-interface.h new file mode 100644 index 000000000000..2da8cbeb158a --- /dev/null +++ b/include/linux/turris-omnia-mcu-interface.h @@ -0,0 +1,249 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * CZ.NIC's Turris Omnia MCU I2C interface commands definitions + * + * 2024 by Marek Behún <kabel@kernel.org> + */ + +#ifndef __TURRIS_OMNIA_MCU_INTERFACE_H +#define __TURRIS_OMNIA_MCU_INTERFACE_H + +#include <linux/bitfield.h> +#include <linux/bits.h> + +enum omnia_commands_e { + OMNIA_CMD_GET_STATUS_WORD = 0x01, /* slave sends status word back */ + OMNIA_CMD_GENERAL_CONTROL = 0x02, + OMNIA_CMD_LED_MODE = 0x03, /* default/user */ + OMNIA_CMD_LED_STATE = 0x04, /* LED on/off */ + OMNIA_CMD_LED_COLOR = 0x05, /* LED number + RED + GREEN + BLUE */ + OMNIA_CMD_USER_VOLTAGE = 0x06, + OMNIA_CMD_SET_BRIGHTNESS = 0x07, + OMNIA_CMD_GET_BRIGHTNESS = 0x08, + OMNIA_CMD_GET_RESET = 0x09, + OMNIA_CMD_GET_FW_VERSION_APP = 0x0A, /* 20B git hash number */ + OMNIA_CMD_SET_WATCHDOG_STATE = 0x0B, /* 0 - disable + * 1 - enable / ping + * after boot watchdog is started + * with 2 minutes timeout + */ + + /* OMNIA_CMD_WATCHDOG_STATUS = 0x0C, not implemented anymore */ + + OMNIA_CMD_GET_WATCHDOG_STATE = 0x0D, + OMNIA_CMD_GET_FW_VERSION_BOOT = 0x0E, /* 20B Git hash number */ + OMNIA_CMD_GET_FW_CHECKSUM = 0x0F, /* 4B length, 4B checksum */ + + /* available if FEATURES_SUPPORTED bit set in status word */ + OMNIA_CMD_GET_FEATURES = 0x10, + + /* available if EXT_CMD bit set in features */ + OMNIA_CMD_GET_EXT_STATUS_DWORD = 0x11, + OMNIA_CMD_EXT_CONTROL = 0x12, + OMNIA_CMD_GET_EXT_CONTROL_STATUS = 0x13, + + /* available if NEW_INT_API bit set in features */ + OMNIA_CMD_GET_INT_AND_CLEAR = 0x14, + OMNIA_CMD_GET_INT_MASK = 0x15, + OMNIA_CMD_SET_INT_MASK = 0x16, + + /* available if FLASHING bit set in features */ + OMNIA_CMD_FLASH = 0x19, + + /* available if WDT_PING bit set in features */ + OMNIA_CMD_SET_WDT_TIMEOUT = 0x20, + OMNIA_CMD_GET_WDT_TIMELEFT = 0x21, + + /* available if POWEROFF_WAKEUP bit set in features */ + OMNIA_CMD_SET_WAKEUP = 0x22, + OMNIA_CMD_GET_UPTIME_AND_WAKEUP = 0x23, + OMNIA_CMD_POWER_OFF = 0x24, + + /* available if USB_OVC_PROT_SETTING bit set in features */ + OMNIA_CMD_SET_USB_OVC_PROT = 0x25, + OMNIA_CMD_GET_USB_OVC_PROT = 0x26, + + /* available if TRNG bit set in features */ + OMNIA_CMD_TRNG_COLLECT_ENTROPY = 0x28, + + /* available if CRYPTO bit set in features */ + OMNIA_CMD_CRYPTO_GET_PUBLIC_KEY = 0x29, + OMNIA_CMD_CRYPTO_SIGN_MESSAGE = 0x2A, + OMNIA_CMD_CRYPTO_COLLECT_SIGNATURE = 0x2B, + + /* available if BOARD_INFO it set in features */ + OMNIA_CMD_BOARD_INFO_GET = 0x2C, + OMNIA_CMD_BOARD_INFO_BURN = 0x2D, + + /* available only at address 0x2b (LED-controller) */ + /* available only if LED_GAMMA_CORRECTION bit set in features */ + OMNIA_CMD_SET_GAMMA_CORRECTION = 0x30, + OMNIA_CMD_GET_GAMMA_CORRECTION = 0x31, + + /* available only at address 0x2b (LED-controller) */ + /* available only if PER_LED_CORRECTION bit set in features */ + /* available only if FROM_BIT_16_INVALID bit NOT set in features */ + OMNIA_CMD_SET_LED_CORRECTIONS = 0x32, + OMNIA_CMD_GET_LED_CORRECTIONS = 0x33, +}; + +enum omnia_flashing_commands_e { + OMNIA_FLASH_CMD_UNLOCK = 0x01, + OMNIA_FLASH_CMD_SIZE_AND_CSUM = 0x02, + OMNIA_FLASH_CMD_PROGRAM = 0x03, + OMNIA_FLASH_CMD_RESET = 0x04, +}; + +enum omnia_sts_word_e { + OMNIA_STS_MCU_TYPE_MASK = GENMASK(1, 0), + OMNIA_STS_MCU_TYPE_STM32 = FIELD_PREP_CONST(OMNIA_STS_MCU_TYPE_MASK, 0), + OMNIA_STS_MCU_TYPE_GD32 = FIELD_PREP_CONST(OMNIA_STS_MCU_TYPE_MASK, 1), + OMNIA_STS_MCU_TYPE_MKL = FIELD_PREP_CONST(OMNIA_STS_MCU_TYPE_MASK, 2), + OMNIA_STS_FEATURES_SUPPORTED = BIT(2), + OMNIA_STS_USER_REGULATOR_NOT_SUPPORTED = BIT(3), + OMNIA_STS_CARD_DET = BIT(4), + OMNIA_STS_MSATA_IND = BIT(5), + OMNIA_STS_USB30_OVC = BIT(6), + OMNIA_STS_USB31_OVC = BIT(7), + OMNIA_STS_USB30_PWRON = BIT(8), + OMNIA_STS_USB31_PWRON = BIT(9), + OMNIA_STS_ENABLE_4V5 = BIT(10), + OMNIA_STS_BUTTON_MODE = BIT(11), + OMNIA_STS_BUTTON_PRESSED = BIT(12), + OMNIA_STS_BUTTON_COUNTER_MASK = GENMASK(15, 13), +}; + +enum omnia_ctl_byte_e { + OMNIA_CTL_LIGHT_RST = BIT(0), + OMNIA_CTL_HARD_RST = BIT(1), + /* BIT(2) is currently reserved */ + OMNIA_CTL_USB30_PWRON = BIT(3), + OMNIA_CTL_USB31_PWRON = BIT(4), + OMNIA_CTL_ENABLE_4V5 = BIT(5), + OMNIA_CTL_BUTTON_MODE = BIT(6), + OMNIA_CTL_BOOTLOADER = BIT(7), +}; + +enum omnia_features_e { + OMNIA_FEAT_PERIPH_MCU = BIT(0), + OMNIA_FEAT_EXT_CMDS = BIT(1), + OMNIA_FEAT_WDT_PING = BIT(2), + OMNIA_FEAT_LED_STATE_EXT_MASK = GENMASK(4, 3), + OMNIA_FEAT_LED_STATE_EXT = FIELD_PREP_CONST(OMNIA_FEAT_LED_STATE_EXT_MASK, 1), + OMNIA_FEAT_LED_STATE_EXT_V32 = FIELD_PREP_CONST(OMNIA_FEAT_LED_STATE_EXT_MASK, 2), + OMNIA_FEAT_LED_GAMMA_CORRECTION = BIT(5), + OMNIA_FEAT_NEW_INT_API = BIT(6), + OMNIA_FEAT_BOOTLOADER = BIT(7), + OMNIA_FEAT_FLASHING = BIT(8), + OMNIA_FEAT_NEW_MESSAGE_API = BIT(9), + OMNIA_FEAT_BRIGHTNESS_INT = BIT(10), + OMNIA_FEAT_POWEROFF_WAKEUP = BIT(11), + OMNIA_FEAT_CAN_OLD_MESSAGE_API = BIT(12), + OMNIA_FEAT_TRNG = BIT(13), + OMNIA_FEAT_CRYPTO = BIT(14), + OMNIA_FEAT_BOARD_INFO = BIT(15), + + /* + * Orginally the features command replied only 16 bits. If more were + * read, either the I2C transaction failed or 0xff bytes were sent. + * Therefore to consider bits 16 - 31 valid, one bit (20) was reserved + * to be zero. + */ + + /* Bits 16 - 19 correspond to bits 0 - 3 of status word */ + OMNIA_FEAT_MCU_TYPE_MASK = GENMASK(17, 16), + OMNIA_FEAT_MCU_TYPE_STM32 = FIELD_PREP_CONST(OMNIA_FEAT_MCU_TYPE_MASK, 0), + OMNIA_FEAT_MCU_TYPE_GD32 = FIELD_PREP_CONST(OMNIA_FEAT_MCU_TYPE_MASK, 1), + OMNIA_FEAT_MCU_TYPE_MKL = FIELD_PREP_CONST(OMNIA_FEAT_MCU_TYPE_MASK, 2), + OMNIA_FEAT_FEATURES_SUPPORTED = BIT(18), + OMNIA_FEAT_USER_REGULATOR_NOT_SUPPORTED = BIT(19), + + /* must not be set */ + OMNIA_FEAT_FROM_BIT_16_INVALID = BIT(20), + + OMNIA_FEAT_PER_LED_CORRECTION = BIT(21), + OMNIA_FEAT_USB_OVC_PROT_SETTING = BIT(22), +}; + +enum omnia_ext_sts_dword_e { + OMNIA_EXT_STS_SFP_nDET = BIT(0), + OMNIA_EXT_STS_LED_STATES_MASK = GENMASK(31, 12), + OMNIA_EXT_STS_WLAN0_MSATA_LED = BIT(12), + OMNIA_EXT_STS_WLAN1_LED = BIT(13), + OMNIA_EXT_STS_WLAN2_LED = BIT(14), + OMNIA_EXT_STS_WPAN0_LED = BIT(15), + OMNIA_EXT_STS_WPAN1_LED = BIT(16), + OMNIA_EXT_STS_WPAN2_LED = BIT(17), + OMNIA_EXT_STS_WAN_LED0 = BIT(18), + OMNIA_EXT_STS_WAN_LED1 = BIT(19), + OMNIA_EXT_STS_LAN0_LED0 = BIT(20), + OMNIA_EXT_STS_LAN0_LED1 = BIT(21), + OMNIA_EXT_STS_LAN1_LED0 = BIT(22), + OMNIA_EXT_STS_LAN1_LED1 = BIT(23), + OMNIA_EXT_STS_LAN2_LED0 = BIT(24), + OMNIA_EXT_STS_LAN2_LED1 = BIT(25), + OMNIA_EXT_STS_LAN3_LED0 = BIT(26), + OMNIA_EXT_STS_LAN3_LED1 = BIT(27), + OMNIA_EXT_STS_LAN4_LED0 = BIT(28), + OMNIA_EXT_STS_LAN4_LED1 = BIT(29), + OMNIA_EXT_STS_LAN5_LED0 = BIT(30), + OMNIA_EXT_STS_LAN5_LED1 = BIT(31), +}; + +enum omnia_ext_ctl_e { + OMNIA_EXT_CTL_nRES_MMC = BIT(0), + OMNIA_EXT_CTL_nRES_LAN = BIT(1), + OMNIA_EXT_CTL_nRES_PHY = BIT(2), + OMNIA_EXT_CTL_nPERST0 = BIT(3), + OMNIA_EXT_CTL_nPERST1 = BIT(4), + OMNIA_EXT_CTL_nPERST2 = BIT(5), + OMNIA_EXT_CTL_PHY_SFP = BIT(6), + OMNIA_EXT_CTL_PHY_SFP_AUTO = BIT(7), + OMNIA_EXT_CTL_nVHV_CTRL = BIT(8), +}; + +enum omnia_int_e { + OMNIA_INT_CARD_DET = BIT(0), + OMNIA_INT_MSATA_IND = BIT(1), + OMNIA_INT_USB30_OVC = BIT(2), + OMNIA_INT_USB31_OVC = BIT(3), + OMNIA_INT_BUTTON_PRESSED = BIT(4), + OMNIA_INT_SFP_nDET = BIT(5), + OMNIA_INT_BRIGHTNESS_CHANGED = BIT(6), + OMNIA_INT_TRNG = BIT(7), + OMNIA_INT_MESSAGE_SIGNED = BIT(8), + + OMNIA_INT_LED_STATES_MASK = GENMASK(31, 12), + OMNIA_INT_WLAN0_MSATA_LED = BIT(12), + OMNIA_INT_WLAN1_LED = BIT(13), + OMNIA_INT_WLAN2_LED = BIT(14), + OMNIA_INT_WPAN0_LED = BIT(15), + OMNIA_INT_WPAN1_LED = BIT(16), + OMNIA_INT_WPAN2_LED = BIT(17), + OMNIA_INT_WAN_LED0 = BIT(18), + OMNIA_INT_WAN_LED1 = BIT(19), + OMNIA_INT_LAN0_LED0 = BIT(20), + OMNIA_INT_LAN0_LED1 = BIT(21), + OMNIA_INT_LAN1_LED0 = BIT(22), + OMNIA_INT_LAN1_LED1 = BIT(23), + OMNIA_INT_LAN2_LED0 = BIT(24), + OMNIA_INT_LAN2_LED1 = BIT(25), + OMNIA_INT_LAN3_LED0 = BIT(26), + OMNIA_INT_LAN3_LED1 = BIT(27), + OMNIA_INT_LAN4_LED0 = BIT(28), + OMNIA_INT_LAN4_LED1 = BIT(29), + OMNIA_INT_LAN5_LED0 = BIT(30), + OMNIA_INT_LAN5_LED1 = BIT(31), +}; + +enum omnia_cmd_poweroff_e { + OMNIA_CMD_POWER_OFF_POWERON_BUTTON = BIT(0), + OMNIA_CMD_POWER_OFF_MAGIC = 0xdead, +}; + +enum omnia_cmd_usb_ovc_prot_e { + OMNIA_CMD_xET_USB_OVC_PROT_PORT_MASK = GENMASK(3, 0), + OMNIA_CMD_xET_USB_OVC_PROT_ENABLE = BIT(4), +}; + +#endif /* __TURRIS_OMNIA_MCU_INTERFACE_H */ diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 3064314f4832..d8e4105a2f21 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -5,6 +5,7 @@ #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/minmax.h> +#include <linux/nospec.h> #include <linux/sched.h> #include <linux/thread_info.h> @@ -138,13 +139,26 @@ __copy_to_user(void __user *to, const void *from, unsigned long n) return raw_copy_to_user(to, from, n); } -#ifdef INLINE_COPY_FROM_USER +/* + * Architectures that #define INLINE_COPY_TO_USER use this function + * directly in the normal copy_to/from_user(), the other ones go + * through an extern _copy_to/from_user(), which expands the same code + * here. + * + * Rust code always uses the extern definition. + */ static inline __must_check unsigned long -_copy_from_user(void *to, const void __user *from, unsigned long n) +_inline_copy_from_user(void *to, const void __user *from, unsigned long n) { unsigned long res = n; might_fault(); if (!should_fail_usercopy() && likely(access_ok(from, n))) { + /* + * Ensure that bad access_ok() speculation will not + * lead to nasty side effects *after* the copy is + * finished: + */ + barrier_nospec(); instrument_copy_from_user_before(to, from, n); res = raw_copy_from_user(to, from, n); instrument_copy_from_user_after(to, from, n, res); @@ -153,14 +167,11 @@ _copy_from_user(void *to, const void __user *from, unsigned long n) memset(to + (n - res), 0, res); return res; } -#else extern __must_check unsigned long _copy_from_user(void *, const void __user *, unsigned long); -#endif -#ifdef INLINE_COPY_TO_USER static inline __must_check unsigned long -_copy_to_user(void __user *to, const void *from, unsigned long n) +_inline_copy_to_user(void __user *to, const void *from, unsigned long n) { might_fault(); if (should_fail_usercopy()) @@ -171,25 +182,32 @@ _copy_to_user(void __user *to, const void *from, unsigned long n) } return n; } -#else extern __must_check unsigned long _copy_to_user(void __user *, const void *, unsigned long); -#endif static __always_inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { - if (check_copy_size(to, n, false)) - n = _copy_from_user(to, from, n); - return n; + if (!check_copy_size(to, n, false)) + return n; +#ifdef INLINE_COPY_FROM_USER + return _inline_copy_from_user(to, from, n); +#else + return _copy_from_user(to, from, n); +#endif } static __always_inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { - if (check_copy_size(from, n, true)) - n = _copy_to_user(to, from, n); - return n; + if (!check_copy_size(from, n, true)) + return n; + +#ifdef INLINE_COPY_TO_USER + return _inline_copy_to_user(to, from, n); +#else + return _copy_to_user(to, from, n); +#endif } #ifndef copy_mc_to_kernel diff --git a/include/linux/udp.h b/include/linux/udp.h index e398e1dbd2d3..3eb3f2b9a2a0 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -24,7 +24,7 @@ static inline struct udphdr *udp_hdr(const struct sk_buff *skb) } #define UDP_HTABLE_SIZE_MIN_PERNET 128 -#define UDP_HTABLE_SIZE_MIN (CONFIG_BASE_SMALL ? 128 : 256) +#define UDP_HTABLE_SIZE_MIN (IS_ENABLED(CONFIG_BASE_SMALL) ? 128 : 256) #define UDP_HTABLE_SIZE_MAX 65536 static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask) diff --git a/include/linux/uio.h b/include/linux/uio.h index 00cebe2b70de..7020adedfa08 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -206,6 +206,16 @@ size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) } static __always_inline __must_check +bool copy_to_iter_full(const void *addr, size_t bytes, struct iov_iter *i) +{ + size_t copied = copy_to_iter(addr, bytes, i); + if (likely(copied == bytes)) + return true; + iov_iter_revert(i, copied); + return false; +} + +static __always_inline __must_check bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) { size_t copied = copy_from_iter(addr, bytes, i); diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index f46e0ca0169c..b503fafb7fb3 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -138,6 +138,9 @@ extern bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check c extern bool arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs); extern void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, void *src, unsigned long len); +extern void uprobe_handle_trampoline(struct pt_regs *regs); +extern void *arch_uprobe_trampoline(unsigned long *psize); +extern unsigned long uprobe_get_trampoline_vaddr(void); #else /* !CONFIG_UPROBES */ struct uprobes_state { }; diff --git a/include/linux/usb.h b/include/linux/usb.h index 9e52179872a5..832997a9da0a 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -440,11 +440,6 @@ int __usb_get_extra_descriptor(char *buffer, unsigned size, /* ----------------------------------------------------------------------- */ -/* USB device number allocation bitmap */ -struct usb_devmap { - unsigned long devicemap[128 / (8*sizeof(unsigned long))]; -}; - /* * Allocated per bus (tree of devices) we have: */ @@ -472,7 +467,7 @@ struct usb_bus { * round-robin allocation */ struct mutex devnum_next_mutex; /* devnum_next mutex */ - struct usb_devmap devmap; /* device address allocation map */ + DECLARE_BITMAP(devmap, 128); /* USB device number allocation bitmap */ struct usb_device *root_hub; /* Root hub */ struct usb_bus *hs_companion; /* Companion EHCI bus, if any */ @@ -1176,6 +1171,7 @@ extern ssize_t usb_show_dynids(struct usb_dynids *dynids, char *buf); * post_reset method is called. * @post_reset: Called by usb_reset_device() after the device * has been reset + * @shutdown: Called at shut-down time to quiesce the device. * @id_table: USB drivers use ID table to support hotplugging. * Export this with MODULE_DEVICE_TABLE(usb,...). This must be set * or your driver's probe function will never get called. @@ -1227,6 +1223,8 @@ struct usb_driver { int (*pre_reset)(struct usb_interface *intf); int (*post_reset)(struct usb_interface *intf); + void (*shutdown)(struct usb_interface *intf); + const struct usb_device_id *id_table; const struct attribute_group **dev_groups; diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 56dda8e1562d..df33333650a0 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -229,18 +229,18 @@ struct usb_ep { const char *name; const struct usb_ep_ops *ops; + const struct usb_endpoint_descriptor *desc; + const struct usb_ss_ep_comp_descriptor *comp_desc; struct list_head ep_list; struct usb_ep_caps caps; bool claimed; bool enabled; - unsigned maxpacket:16; - unsigned maxpacket_limit:16; - unsigned max_streams:16; unsigned mult:2; unsigned maxburst:5; u8 address; - const struct usb_endpoint_descriptor *desc; - const struct usb_ss_ep_comp_descriptor *comp_desc; + u16 maxpacket; + u16 maxpacket_limit; + u16 max_streams; }; /*-------------------------------------------------------------------------*/ diff --git a/include/linux/usb/onboard_dev.h b/include/linux/usb/onboard_dev.h new file mode 100644 index 000000000000..b79db6d193c8 --- /dev/null +++ b/include/linux/usb/onboard_dev.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __LINUX_USB_ONBOARD_DEV_H +#define __LINUX_USB_ONBOARD_DEV_H + +struct usb_device; +struct list_head; + +#if IS_ENABLED(CONFIG_USB_ONBOARD_DEV) +void onboard_dev_create_pdevs(struct usb_device *parent_dev, struct list_head *pdev_list); +void onboard_dev_destroy_pdevs(struct list_head *pdev_list); +#else +static inline void onboard_dev_create_pdevs(struct usb_device *parent_dev, + struct list_head *pdev_list) {} +static inline void onboard_dev_destroy_pdevs(struct list_head *pdev_list) {} +#endif + +#endif /* __LINUX_USB_ONBOARD_DEV_H */ diff --git a/include/linux/usb/onboard_hub.h b/include/linux/usb/onboard_hub.h deleted file mode 100644 index d9373230556e..000000000000 --- a/include/linux/usb/onboard_hub.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -#ifndef __LINUX_USB_ONBOARD_HUB_H -#define __LINUX_USB_ONBOARD_HUB_H - -struct usb_device; -struct list_head; - -#if IS_ENABLED(CONFIG_USB_ONBOARD_HUB) -void onboard_hub_create_pdevs(struct usb_device *parent_hub, struct list_head *pdev_list); -void onboard_hub_destroy_pdevs(struct list_head *pdev_list); -#else -static inline void onboard_hub_create_pdevs(struct usb_device *parent_hub, - struct list_head *pdev_list) {} -static inline void onboard_hub_destroy_pdevs(struct list_head *pdev_list) {} -#endif - -#endif /* __LINUX_USB_ONBOARD_HUB_H */ diff --git a/include/linux/usb/renesas_usbhs.h b/include/linux/usb/renesas_usbhs.h index 372898d9eeb0..67bfcda6c7d2 100644 --- a/include/linux/usb/renesas_usbhs.h +++ b/include/linux/usb/renesas_usbhs.h @@ -194,9 +194,4 @@ struct renesas_usbhs_platform_info { struct renesas_usbhs_driver_param driver_param; }; -/* - * macro for platform - */ -#define renesas_usbhs_get_info(pdev)\ - ((struct renesas_usbhs_platform_info *)(pdev)->dev.platform_data) #endif /* RENESAS_USB_H */ diff --git a/include/linux/usb/tcpci.h b/include/linux/usb/tcpci.h index 47a86b8a4a50..0ab39b6ea205 100644 --- a/include/linux/usb/tcpci.h +++ b/include/linux/usb/tcpci.h @@ -47,6 +47,9 @@ #define TCPC_SINK_FAST_ROLE_SWAP BIT(0) #define TCPC_CONFIG_STD_OUTPUT 0x18 +#define TCPC_CONFIG_STD_OUTPUT_ORIENTATION_MASK BIT(0) +#define TCPC_CONFIG_STD_OUTPUT_ORIENTATION_NORMAL 0 +#define TCPC_CONFIG_STD_OUTPUT_ORIENTATION_FLIPPED 1 #define TCPC_TCPC_CTRL 0x19 #define TCPC_TCPC_CTRL_ORIENTATION BIT(0) @@ -127,6 +130,7 @@ #define TCPC_DEV_CAP_2 0x26 #define TCPC_STD_INPUT_CAP 0x28 #define TCPC_STD_OUTPUT_CAP 0x29 +#define TCPC_STD_OUTPUT_CAP_ORIENTATION BIT(0) #define TCPC_MSG_HDR_INFO 0x2e #define TCPC_MSG_HDR_INFO_DATA_ROLE BIT(3) @@ -209,6 +213,9 @@ struct tcpci; * swap following Discover Identity on SOP' occurs. * Return true when the TCPM is allowed to request a Vconn swap * after Discovery Identity on SOP. + * @set_orientation: + * Optional; Enable setting the connector orientation + * CONFIG_STANDARD_OUTPUT (0x18) bit0. */ struct tcpci_data { struct regmap *regmap; @@ -216,6 +223,7 @@ struct tcpci_data { unsigned char auto_discharge_disconnect:1; unsigned char vbus_vsafe0v:1; unsigned char cable_comm_capable:1; + unsigned char set_orientation:1; int (*init)(struct tcpci *tcpci, struct tcpci_data *data); int (*set_vconn)(struct tcpci *tcpci, struct tcpci_data *data, diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index 46e73584b6e6..e6c14f2b1f9b 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -7,11 +7,12 @@ #define __TEGRA_USB_PHY_H #include <linux/clk.h> -#include <linux/gpio.h> #include <linux/regmap.h> #include <linux/reset.h> #include <linux/usb/otg.h> +struct gpio_desc; + /* * utmi_pll_config_in_car_module: true if the UTMI PLL configuration registers * should be set up by clk-tegra, false if by the PHY code diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index b35b427561ab..549275f8ac1b 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -167,6 +167,9 @@ struct typec_port *typec_altmode2port(struct typec_altmode *alt); void typec_altmode_update_active(struct typec_altmode *alt, bool active); +void typec_altmode_set_ops(struct typec_altmode *alt, + const struct typec_altmode_ops *ops); + enum typec_plug_index { TYPEC_PLUG_SOP_P, TYPEC_PLUG_SOP_PP, diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 05d59f74fc88..a12bcf042551 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -218,6 +218,9 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma, { vm_flags &= __VM_UFFD_FLAGS; + if (vm_flags & VM_DROPPABLE) + return false; + if ((vm_flags & VM_UFFD_MINOR) && (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma))) return false; diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 8b1a29820409..000a6cab2d31 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -64,6 +64,7 @@ struct vfio_device { struct completion comp; struct iommufd_access *iommufd_access; void (*put_kvm)(struct kvm *kvm); + struct inode *inode; #if IS_ENABLED(CONFIG_IOMMUFD) struct iommufd_device *iommufd_device; u8 iommufd_attached:1; diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index a2c8b8bba711..fbb472dd99b3 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -93,8 +93,6 @@ struct vfio_pci_core_device { struct list_head sriov_pfs_item; struct vfio_pci_core_device *sriov_pf_core_dev; struct notifier_block nb; - struct mutex vma_lock; - struct list_head vma_list; struct rw_semaphore memory_lock; }; @@ -139,23 +137,26 @@ bool vfio_pci_core_range_intersect_range(loff_t buf_start, size_t buf_cnt, loff_t *buf_offset, size_t *intersect_count, size_t *register_offset); -#define VFIO_IOWRITE_DECLATION(size) \ +#define VFIO_IOWRITE_DECLARATION(size) \ int vfio_pci_core_iowrite##size(struct vfio_pci_core_device *vdev, \ bool test_mem, u##size val, void __iomem *io); -VFIO_IOWRITE_DECLATION(8) -VFIO_IOWRITE_DECLATION(16) -VFIO_IOWRITE_DECLATION(32) +VFIO_IOWRITE_DECLARATION(8) +VFIO_IOWRITE_DECLARATION(16) +VFIO_IOWRITE_DECLARATION(32) #ifdef iowrite64 -VFIO_IOWRITE_DECLATION(64) +VFIO_IOWRITE_DECLARATION(64) #endif -#define VFIO_IOREAD_DECLATION(size) \ +#define VFIO_IOREAD_DECLARATION(size) \ int vfio_pci_core_ioread##size(struct vfio_pci_core_device *vdev, \ bool test_mem, u##size *val, void __iomem *io); -VFIO_IOREAD_DECLATION(8) -VFIO_IOREAD_DECLATION(16) -VFIO_IOREAD_DECLATION(32) +VFIO_IOREAD_DECLARATION(8) +VFIO_IOREAD_DECLARATION(16) +VFIO_IOREAD_DECLARATION(32) +#ifdef ioread64 +VFIO_IOREAD_DECLARATION(64) +#endif #endif /* VFIO_PCI_CORE_H */ diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 26c4325aa373..4b16844c6bc2 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -10,6 +10,7 @@ #include <linux/mod_devicetable.h> #include <linux/gfp.h> #include <linux/dma-mapping.h> +#include <linux/completion.h> /** * struct virtqueue - a queue to register buffers for sending or receiving. @@ -109,6 +110,8 @@ struct virtio_admin_cmd { __le64 group_member_id; struct scatterlist *data_sg; struct scatterlist *result_sg; + struct completion completion; + int ret; }; /** @@ -126,6 +129,8 @@ struct virtio_admin_cmd { * @vqs: the list of virtqueues for this device. * @features: the features supported by both driver and device. * @priv: private pointer for the driver's use. + * @debugfs_dir: debugfs directory entry. + * @debugfs_filter_features: features to be filtered set by debugfs. */ struct virtio_device { int index; @@ -141,6 +146,10 @@ struct virtio_device { struct list_head vqs; u64 features; void *priv; +#ifdef CONFIG_VIRTIO_DEBUG + struct dentry *debugfs_dir; + u64 debugfs_filter_features; +#endif }; #define dev_to_virtio(_dev) container_of_const(_dev, struct virtio_device, dev) @@ -203,10 +212,7 @@ struct virtio_driver { int (*restore)(struct virtio_device *dev); }; -static inline struct virtio_driver *drv_to_virtio(struct device_driver *drv) -{ - return container_of(drv, struct virtio_driver, driver); -} +#define drv_to_virtio(__drv) container_of_const(__drv, struct virtio_driver, driver) /* use a macro to avoid include chaining to get THIS_MODULE */ #define register_virtio_driver(drv) \ @@ -237,4 +243,33 @@ void virtqueue_dma_sync_single_range_for_cpu(struct virtqueue *_vq, dma_addr_t a void virtqueue_dma_sync_single_range_for_device(struct virtqueue *_vq, dma_addr_t addr, unsigned long offset, size_t size, enum dma_data_direction dir); + +#ifdef CONFIG_VIRTIO_DEBUG +void virtio_debug_device_init(struct virtio_device *dev); +void virtio_debug_device_exit(struct virtio_device *dev); +void virtio_debug_device_filter_features(struct virtio_device *dev); +void virtio_debug_init(void); +void virtio_debug_exit(void); +#else +static inline void virtio_debug_device_init(struct virtio_device *dev) +{ +} + +static inline void virtio_debug_device_exit(struct virtio_device *dev) +{ +} + +static inline void virtio_debug_device_filter_features(struct virtio_device *dev) +{ +} + +static inline void virtio_debug_init(void) +{ +} + +static inline void virtio_debug_exit(void) +{ +} +#endif + #endif /* _LINUX_VIRTIO_H */ diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index da9b271b54db..169c7d367fac 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -19,6 +19,20 @@ struct virtio_shm_region { typedef void vq_callback_t(struct virtqueue *); /** + * struct virtqueue_info - Info for a virtqueue passed to find_vqs(). + * @name: virtqueue description. Used mainly for debugging, NULL for + * a virtqueue unused by the driver. + * @callback: A callback to invoke on a used buffer notification. + * NULL for a virtqueue that does not need a callback. + * @ctx: A flag to indicate to maintain an extra context per virtqueue. + */ +struct virtqueue_info { + const char *name; + vq_callback_t *callback; + bool ctx; +}; + +/** * struct virtio_config_ops - operations for configuring a virtio device * Note: Do not assume that a transport implements all of the operations * getting/setting a value as a simple read/write! Generally speaking, @@ -53,10 +67,7 @@ typedef void vq_callback_t(struct virtqueue *); * vdev: the virtio_device * nvqs: the number of virtqueues to find * vqs: on success, includes new virtqueues - * callbacks: array of callbacks, for each virtqueue - * include a NULL entry for vqs that do not need a callback - * names: array of virtqueue names (mainly for debugging) - * include a NULL entry for vqs unused by driver + * vqs_info: array of virtqueue info structures * Returns 0 on success or error status * @del_vqs: free virtqueues found by find_vqs(). * @synchronize_cbs: synchronize with the virtqueue callbacks (optional) @@ -93,8 +104,6 @@ typedef void vq_callback_t(struct virtqueue *); * Returns 0 on success or error status * If disable_vq_and_reset is set, then enable_vq_after_reset must also be * set. - * @create_avq: create admin virtqueue resource. - * @destroy_avq: destroy admin virtqueue resource. */ struct virtio_config_ops { void (*get)(struct virtio_device *vdev, unsigned offset, @@ -105,9 +114,9 @@ struct virtio_config_ops { u8 (*get_status)(struct virtio_device *vdev); void (*set_status)(struct virtio_device *vdev, u8 status); void (*reset)(struct virtio_device *vdev); - int (*find_vqs)(struct virtio_device *, unsigned nvqs, - struct virtqueue *vqs[], vq_callback_t *callbacks[], - const char * const names[], const bool *ctx, + int (*find_vqs)(struct virtio_device *vdev, unsigned int nvqs, + struct virtqueue *vqs[], + struct virtqueue_info vqs_info[], struct irq_affinity *desc); void (*del_vqs)(struct virtio_device *); void (*synchronize_cbs)(struct virtio_device *); @@ -117,13 +126,11 @@ struct virtio_config_ops { int (*set_vq_affinity)(struct virtqueue *vq, const struct cpumask *cpu_mask); const struct cpumask *(*get_vq_affinity)(struct virtio_device *vdev, - int index); + int index); bool (*get_shm_region)(struct virtio_device *vdev, struct virtio_shm_region *region, u8 id); int (*disable_vq_and_reset)(struct virtqueue *vq); int (*enable_vq_after_reset)(struct virtqueue *vq); - int (*create_avq)(struct virtio_device *vdev); - void (*destroy_avq)(struct virtio_device *vdev); }; /* If driver didn't advertise the feature, it will never appear. */ @@ -211,38 +218,29 @@ static inline bool virtio_has_dma_quirk(const struct virtio_device *vdev) } static inline +int virtio_find_vqs(struct virtio_device *vdev, unsigned int nvqs, + struct virtqueue *vqs[], + struct virtqueue_info vqs_info[], + struct irq_affinity *desc) +{ + return vdev->config->find_vqs(vdev, nvqs, vqs, vqs_info, desc); +} + +static inline struct virtqueue *virtio_find_single_vq(struct virtio_device *vdev, vq_callback_t *c, const char *n) { - vq_callback_t *callbacks[] = { c }; - const char *names[] = { n }; + struct virtqueue_info vqs_info[] = { + { n, c }, + }; struct virtqueue *vq; - int err = vdev->config->find_vqs(vdev, 1, &vq, callbacks, names, NULL, - NULL); + int err = virtio_find_vqs(vdev, 1, &vq, vqs_info, NULL); + if (err < 0) return ERR_PTR(err); return vq; } -static inline -int virtio_find_vqs(struct virtio_device *vdev, unsigned nvqs, - struct virtqueue *vqs[], vq_callback_t *callbacks[], - const char * const names[], - struct irq_affinity *desc) -{ - return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, NULL, desc); -} - -static inline -int virtio_find_vqs_ctx(struct virtio_device *vdev, unsigned nvqs, - struct virtqueue *vqs[], vq_callback_t *callbacks[], - const char * const names[], const bool *ctx, - struct irq_affinity *desc) -{ - return vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names, ctx, - desc); -} - /** * virtio_synchronize_cbs - synchronize with virtqueue callbacks * @dev: the virtio device diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 4dfa9b69ca8d..6c395a2600e8 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -171,6 +171,11 @@ retry: if (gso_type != SKB_GSO_UDP_L4) return -EINVAL; break; + case SKB_GSO_TCPV4: + case SKB_GSO_TCPV6: + if (skb->csum_offset != offsetof(struct tcphdr, check)) + return -EINVAL; + break; } /* Kernel has a special handling for GSO_BY_FRAGS. */ diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 98ea90e90439..e4a631ec430b 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -2,6 +2,8 @@ #ifndef _LINUX_VMALLOC_H #define _LINUX_VMALLOC_H +#include <linux/alloc_tag.h> +#include <linux/sched.h> #include <linux/spinlock.h> #include <linux/init.h> #include <linux/list.h> @@ -138,26 +140,54 @@ extern unsigned long vmalloc_nr_pages(void); static inline unsigned long vmalloc_nr_pages(void) { return 0; } #endif -extern void *vmalloc(unsigned long size) __alloc_size(1); -extern void *vzalloc(unsigned long size) __alloc_size(1); -extern void *vmalloc_user(unsigned long size) __alloc_size(1); -extern void *vmalloc_node(unsigned long size, int node) __alloc_size(1); -extern void *vzalloc_node(unsigned long size, int node) __alloc_size(1); -extern void *vmalloc_32(unsigned long size) __alloc_size(1); -extern void *vmalloc_32_user(unsigned long size) __alloc_size(1); -extern void *__vmalloc(unsigned long size, gfp_t gfp_mask) __alloc_size(1); -extern void *__vmalloc_node_range(unsigned long size, unsigned long align, +extern void *vmalloc_noprof(unsigned long size) __alloc_size(1); +#define vmalloc(...) alloc_hooks(vmalloc_noprof(__VA_ARGS__)) + +extern void *vzalloc_noprof(unsigned long size) __alloc_size(1); +#define vzalloc(...) alloc_hooks(vzalloc_noprof(__VA_ARGS__)) + +extern void *vmalloc_user_noprof(unsigned long size) __alloc_size(1); +#define vmalloc_user(...) alloc_hooks(vmalloc_user_noprof(__VA_ARGS__)) + +extern void *vmalloc_node_noprof(unsigned long size, int node) __alloc_size(1); +#define vmalloc_node(...) alloc_hooks(vmalloc_node_noprof(__VA_ARGS__)) + +extern void *vzalloc_node_noprof(unsigned long size, int node) __alloc_size(1); +#define vzalloc_node(...) alloc_hooks(vzalloc_node_noprof(__VA_ARGS__)) + +extern void *vmalloc_32_noprof(unsigned long size) __alloc_size(1); +#define vmalloc_32(...) alloc_hooks(vmalloc_32_noprof(__VA_ARGS__)) + +extern void *vmalloc_32_user_noprof(unsigned long size) __alloc_size(1); +#define vmalloc_32_user(...) alloc_hooks(vmalloc_32_user_noprof(__VA_ARGS__)) + +extern void *__vmalloc_noprof(unsigned long size, gfp_t gfp_mask) __alloc_size(1); +#define __vmalloc(...) alloc_hooks(__vmalloc_noprof(__VA_ARGS__)) + +extern void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller) __alloc_size(1); -void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, +#define __vmalloc_node_range(...) alloc_hooks(__vmalloc_node_range_noprof(__VA_ARGS__)) + +void *__vmalloc_node_noprof(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) __alloc_size(1); -void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) __alloc_size(1); +#define __vmalloc_node(...) alloc_hooks(__vmalloc_node_noprof(__VA_ARGS__)) + +void *vmalloc_huge_noprof(unsigned long size, gfp_t gfp_mask) __alloc_size(1); +#define vmalloc_huge(...) alloc_hooks(vmalloc_huge_noprof(__VA_ARGS__)) + +extern void *__vmalloc_array_noprof(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); +#define __vmalloc_array(...) alloc_hooks(__vmalloc_array_noprof(__VA_ARGS__)) + +extern void *vmalloc_array_noprof(size_t n, size_t size) __alloc_size(1, 2); +#define vmalloc_array(...) alloc_hooks(vmalloc_array_noprof(__VA_ARGS__)) + +extern void *__vcalloc_noprof(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); +#define __vcalloc(...) alloc_hooks(__vcalloc_noprof(__VA_ARGS__)) -extern void *__vmalloc_array(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); -extern void *vmalloc_array(size_t n, size_t size) __alloc_size(1, 2); -extern void *__vcalloc(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); -extern void *vcalloc(size_t n, size_t size) __alloc_size(1, 2); +extern void *vcalloc_noprof(size_t n, size_t size) __alloc_size(1, 2); +#define vcalloc(...) alloc_hooks(vcalloc_noprof(__VA_ARGS__)) extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 343906a98d6e..9eb77c9007e6 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -17,7 +17,7 @@ extern int sysctl_stat_interval; #define DISABLE_NUMA_STAT 0 extern int sysctl_vm_numa_stat; DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key); -int sysctl_vm_numa_stat_handler(struct ctl_table *table, int write, +int sysctl_vm_numa_stat_handler(const struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); #endif @@ -34,10 +34,13 @@ struct reclaim_stat { unsigned nr_lazyfree_fail; }; -enum writeback_stat_item { +/* Stat data for system wide items */ +enum vm_stat_item { NR_DIRTY_THRESHOLD, NR_DIRTY_BG_THRESHOLD, - NR_VM_WRITEBACK_STAT_ITEMS, + NR_MEMMAP_PAGES, /* page metadata allocated through buddy allocator */ + NR_MEMMAP_BOOT_PAGES, /* page metadata allocated through boot allocator */ + NR_VM_STAT_ITEMS, }; #ifdef CONFIG_VM_EVENT_COUNTERS @@ -301,7 +304,7 @@ void cpu_vm_stats_fold(int cpu); void refresh_zone_stat_thresholds(void); struct ctl_table; -int vmstat_refresh(struct ctl_table *, int write, void *buffer, size_t *lenp, +int vmstat_refresh(const struct ctl_table *, int write, void *buffer, size_t *lenp, loff_t *ppos); void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *); @@ -487,14 +490,6 @@ static inline void node_stat_sub_folio(struct folio *folio, mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio)); } -static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages, - int migratetype) -{ - __mod_zone_page_state(zone, NR_FREE_PAGES, nr_pages); - if (is_migrate_cma(migratetype)) - __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages); -} - extern const char * const vmstat_text[]; static inline const char *zone_stat_name(enum zone_stat_item item) @@ -522,21 +517,13 @@ static inline const char *lru_list_name(enum lru_list lru) return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" } -static inline const char *writeback_stat_name(enum writeback_stat_item item) -{ - return vmstat_text[NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_EVENT_ITEMS + - NR_VM_NODE_STAT_ITEMS + - item]; -} - #if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) static inline const char *vm_event_name(enum vm_event_item item) { return vmstat_text[NR_VM_ZONE_STAT_ITEMS + NR_VM_NUMA_EVENT_ITEMS + NR_VM_NODE_STAT_ITEMS + - NR_VM_WRITEBACK_STAT_ITEMS + + NR_VM_STAT_ITEMS + item]; } #endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ @@ -632,4 +619,7 @@ static inline void lruvec_stat_sub_folio(struct folio *folio, { lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); } + +void memmap_boot_pages_add(long delta); +void memmap_pages_add(long delta); #endif /* _LINUX_VMSTAT_H */ diff --git a/include/linux/vtime.h b/include/linux/vtime.h index 3684487d01e1..29dd5b91dd7d 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -5,10 +5,6 @@ #include <linux/context_tracking_state.h> #include <linux/sched.h> -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -#include <asm/vtime.h> -#endif - /* * Common vtime APIs */ @@ -18,7 +14,6 @@ extern void vtime_account_idle(struct task_struct *tsk); #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -extern void arch_vtime_task_switch(struct task_struct *tsk); extern void vtime_user_enter(struct task_struct *tsk); extern void vtime_user_exit(struct task_struct *tsk); extern void vtime_guest_enter(struct task_struct *tsk); diff --git a/include/linux/w1.h b/include/linux/w1.h index 9a2a0ef39018..064805bfae3f 100644 --- a/include/linux/w1.h +++ b/include/linux/w1.h @@ -85,7 +85,8 @@ typedef void (*w1_slave_found_callback)(struct w1_master *, u64); * * @data: the first parameter in all the functions below * - * @read_bit: Sample the line level @return the level read (0 or 1) + * @read_bit: Sample the line level + * @return the level read (0 or 1) * * @write_bit: Sets the line level * @@ -95,7 +96,7 @@ typedef void (*w1_slave_found_callback)(struct w1_master *, u64); * touch_bit(1) = write-1 / read cycle * @return the bit read (0 or 1) * - * @read_byte: Reads a bytes. Same as 8 touch_bit(1) calls. + * @read_byte: Reads a byte. Same as 8 touch_bit(1) calls. * @return the byte read * * @write_byte: Writes a byte. Same as 8 touch_bit(x) calls. @@ -114,7 +115,7 @@ typedef void (*w1_slave_found_callback)(struct w1_master *, u64); * @set_pullup: Put out a strong pull-up pulse of the specified duration. * @return -1=Error, 0=completed * - * @search: Really nice hardware can handles the different types of ROM search + * @search: Really nice hardware can handle the different types of ROM search * w1_master* is passed to the slave found callback. * u8 is search_type, W1_SEARCH or W1_ALARM_SEARCH * diff --git a/include/linux/wmi.h b/include/linux/wmi.h index 63cca3b58d6d..3275470b5531 100644 --- a/include/linux/wmi.h +++ b/include/linux/wmi.h @@ -16,12 +16,16 @@ * struct wmi_device - WMI device structure * @dev: Device associated with this WMI device * @setable: True for devices implementing the Set Control Method + * @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. * * This represents WMI devices discovered by the WMI driver core. */ struct wmi_device { struct device dev; bool setable; + const char *driver_override; }; /** diff --git a/include/linux/wordpart.h b/include/linux/wordpart.h index f6f8f83b15b0..5a7b97bb7c95 100644 --- a/include/linux/wordpart.h +++ b/include/linux/wordpart.h @@ -39,4 +39,19 @@ */ #define REPEAT_BYTE(x) ((~0ul / 0xff) * (x)) +/** + * REPEAT_BYTE_U32 - repeat the value @x multiple times as a u32 value + * @x: value to repeat + * + * NOTE: @x is not checked for > 0xff; larger values produce odd results. + */ +#define REPEAT_BYTE_U32(x) lower_32_bits(REPEAT_BYTE(x)) + +/* Set bits in the first 'n' bytes when loaded from memory */ +#ifdef __LITTLE_ENDIAN +# define aligned_byte_mask(n) ((1UL << 8*(n))-1) +#else +# define aligned_byte_mask(n) (~0xffUL << (BITS_PER_LONG - 8 - 8*(n))) +#endif + #endif // _LINUX_WORDPART_H diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 158784dd189a..4eb8f9563136 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -12,7 +12,7 @@ #include <linux/lockdep.h> #include <linux/threads.h> #include <linux/atomic.h> -#include <linux/cpumask.h> +#include <linux/cpumask_types.h> #include <linux/rcupdate.h> #include <linux/workqueue_types.h> @@ -51,20 +51,23 @@ enum work_bits { * data contains off-queue information when !WORK_STRUCT_PWQ. * * MSB - * [ pool ID ] [ OFFQ flags ] [ STRUCT flags ] - * 1 bit 4 or 5 bits + * [ pool ID ] [ disable depth ] [ OFFQ flags ] [ STRUCT flags ] + * 16 bits 1 bit 4 or 5 bits */ WORK_OFFQ_FLAG_SHIFT = WORK_STRUCT_FLAG_BITS, - WORK_OFFQ_CANCELING_BIT = WORK_OFFQ_FLAG_SHIFT, + WORK_OFFQ_BH_BIT = WORK_OFFQ_FLAG_SHIFT, WORK_OFFQ_FLAG_END, WORK_OFFQ_FLAG_BITS = WORK_OFFQ_FLAG_END - WORK_OFFQ_FLAG_SHIFT, + WORK_OFFQ_DISABLE_SHIFT = WORK_OFFQ_FLAG_SHIFT + WORK_OFFQ_FLAG_BITS, + WORK_OFFQ_DISABLE_BITS = 16, + /* * When a work item is off queue, the high bits encode off-queue flags * and the last pool it was on. Cap pool ID to 31 bits and use the * highest number to indicate that no pool is associated. */ - WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_FLAG_SHIFT + WORK_OFFQ_FLAG_BITS, + WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_DISABLE_SHIFT + WORK_OFFQ_DISABLE_BITS, WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31, }; @@ -92,11 +95,13 @@ enum wq_misc_consts { WORK_BUSY_RUNNING = 1 << 1, /* maximum string length for set_worker_desc() */ - WORKER_DESC_LEN = 24, + WORKER_DESC_LEN = 32, }; /* Convenience constants - of type 'unsigned long', not 'enum'! */ -#define WORK_OFFQ_CANCELING (1ul << WORK_OFFQ_CANCELING_BIT) +#define WORK_OFFQ_BH (1ul << WORK_OFFQ_BH_BIT) +#define WORK_OFFQ_FLAG_MASK (((1ul << WORK_OFFQ_FLAG_BITS) - 1) << WORK_OFFQ_FLAG_SHIFT) +#define WORK_OFFQ_DISABLE_MASK (((1ul << WORK_OFFQ_DISABLE_BITS) - 1) << WORK_OFFQ_DISABLE_SHIFT) #define WORK_OFFQ_POOL_NONE ((1ul << WORK_OFFQ_POOL_BITS) - 1) #define WORK_STRUCT_NO_POOL (WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT) #define WORK_STRUCT_PWQ_MASK (~((1ul << WORK_STRUCT_PWQ_SHIFT) - 1)) @@ -180,6 +185,9 @@ struct workqueue_attrs { * Below fields aren't properties of a worker_pool. They only modify how * :c:func:`apply_workqueue_attrs` select pools and thus don't * participate in pool hash calculations or equality comparisons. + * + * If @affn_strict is set, @cpumask isn't a property of a worker_pool + * either. */ /** @@ -465,7 +473,7 @@ void workqueue_softirq_dead(unsigned int cpu); * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags * @max_active: max in-flight work items, 0 for default - * remaining args: args for @fmt + * @...: args for @fmt * * For a per-cpu workqueue, @max_active limits the number of in-flight work * items for each CPU. e.g. @max_active of 1 indicates that each CPU can be @@ -559,6 +567,14 @@ extern bool flush_delayed_work(struct delayed_work *dwork); extern bool cancel_delayed_work(struct delayed_work *dwork); extern bool cancel_delayed_work_sync(struct delayed_work *dwork); +extern bool disable_work(struct work_struct *work); +extern bool disable_work_sync(struct work_struct *work); +extern bool enable_work(struct work_struct *work); + +extern bool disable_delayed_work(struct delayed_work *dwork); +extern bool disable_delayed_work_sync(struct delayed_work *dwork); +extern bool enable_delayed_work(struct delayed_work *dwork); + extern bool flush_rcu_work(struct rcu_work *rwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, @@ -666,6 +682,32 @@ static inline bool schedule_work(struct work_struct *work) return queue_work(system_wq, work); } +/** + * enable_and_queue_work - Enable and queue a work item on a specific workqueue + * @wq: The target workqueue + * @work: The work item to be enabled and queued + * + * This function combines the operations of enable_work() and queue_work(), + * providing a convenient way to enable and queue a work item in a single call. + * It invokes enable_work() on @work and then queues it if the disable depth + * reached 0. Returns %true if the disable depth reached 0 and @work is queued, + * and %false otherwise. + * + * Note that @work is always queued when disable depth reaches zero. If the + * desired behavior is queueing only if certain events took place while @work is + * disabled, the user should implement the necessary state tracking and perform + * explicit conditional queueing after enable_work(). + */ +static inline bool enable_and_queue_work(struct workqueue_struct *wq, + struct work_struct *work) +{ + if (enable_work(work)) { + queue_work(wq, work); + return true; + } + return false; +} + /* * Detect attempt to flush system-wide workqueues at compile time when possible. * Warn attempt to flush system-wide workqueues at runtime. diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 9845cb62e40b..1a54676d843a 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -350,11 +350,12 @@ extern unsigned int dirty_expire_interval; extern unsigned int dirtytime_expire_interval; extern int laptop_mode; -int dirtytime_interval_handler(struct ctl_table *table, int write, +int dirtytime_interval_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); +unsigned long cgwb_calc_thresh(struct bdi_writeback *wb); void wb_update_bandwidth(struct bdi_writeback *wb); diff --git a/include/linux/xarray.h b/include/linux/xarray.h index cb571dfcf4b1..0b618ec04115 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -12,14 +12,18 @@ #include <linux/bitmap.h> #include <linux/bug.h> #include <linux/compiler.h> +#include <linux/err.h> #include <linux/gfp.h> #include <linux/kconfig.h> -#include <linux/kernel.h> +#include <linux/limits.h> +#include <linux/lockdep.h> #include <linux/rcupdate.h> #include <linux/sched/mm.h> #include <linux/spinlock.h> #include <linux/types.h> +struct list_lru; + /* * The bottom two bits of the entry determine how the XArray interprets * the contents: @@ -1141,12 +1145,12 @@ static inline void xa_release(struct xarray *xa, unsigned long index) * doubled the number of slots per node, we'd get only 3 nodes per 4kB page. */ #ifndef XA_CHUNK_SHIFT -#define XA_CHUNK_SHIFT (CONFIG_BASE_SMALL ? 4 : 6) +#define XA_CHUNK_SHIFT (IS_ENABLED(CONFIG_BASE_SMALL) ? 4 : 6) #endif #define XA_CHUNK_SIZE (1UL << XA_CHUNK_SHIFT) #define XA_CHUNK_MASK (XA_CHUNK_SIZE - 1) #define XA_MAX_MARKS 3 -#define XA_MARK_LONGS DIV_ROUND_UP(XA_CHUNK_SIZE, BITS_PER_LONG) +#define XA_MARK_LONGS BITS_TO_LONGS(XA_CHUNK_SIZE) /* * @count is the count of every non-NULL element in the ->slots array @@ -1548,6 +1552,7 @@ void xas_create_range(struct xa_state *); #ifdef CONFIG_XARRAY_MULTI int xa_get_order(struct xarray *, unsigned long index); +int xas_get_order(struct xa_state *xas); void xas_split(struct xa_state *, void *entry, unsigned int order); void xas_split_alloc(struct xa_state *, void *entry, unsigned int order, gfp_t); #else @@ -1556,6 +1561,11 @@ static inline int xa_get_order(struct xarray *xa, unsigned long index) return 0; } +static inline int xas_get_order(struct xa_state *xas) +{ + return 0; +} + static inline void xas_split(struct xa_state *xas, void *entry, unsigned int order) { diff --git a/include/linux/zorro.h b/include/linux/zorro.h index db7416ed6057..f36c8d39553d 100644 --- a/include/linux/zorro.h +++ b/include/linux/zorro.h @@ -52,7 +52,7 @@ struct zorro_driver { struct device_driver driver; }; -#define to_zorro_driver(drv) container_of(drv, struct zorro_driver, driver) +#define to_zorro_driver(drv) container_of_const(drv, struct zorro_driver, driver) #define zorro_for_each_dev(dev) \ diff --git a/include/linux/zpool.h b/include/linux/zpool.h index 3296438eec06..a67d62b79698 100644 --- a/include/linux/zpool.h +++ b/include/linux/zpool.h @@ -53,7 +53,7 @@ void *zpool_map_handle(struct zpool *pool, unsigned long handle, void zpool_unmap_handle(struct zpool *pool, unsigned long handle); -u64 zpool_get_total_size(struct zpool *pool); +u64 zpool_get_total_pages(struct zpool *pool); /** @@ -91,7 +91,7 @@ struct zpool_driver { enum zpool_mapmode mm); void (*unmap)(void *pool, unsigned long handle); - u64 (*total_size)(void *pool); + u64 (*total_pages)(void *pool); }; void zpool_register_driver(struct zpool_driver *driver); diff --git a/include/linux/zswap.h b/include/linux/zswap.h index 341aea490070..6cecb4a4f68b 100644 --- a/include/linux/zswap.h +++ b/include/linux/zswap.h @@ -7,7 +7,6 @@ struct lruvec; -extern u64 zswap_pool_total_size; extern atomic_t zswap_stored_pages; #ifdef CONFIG_ZSWAP @@ -27,6 +26,7 @@ struct zswap_lruvec_state { atomic_long_t nr_zswap_protected; }; +unsigned long zswap_total_pages(void); bool zswap_store(struct folio *folio); bool zswap_load(struct folio *folio); void zswap_invalidate(swp_entry_t swp); @@ -35,7 +35,8 @@ void zswap_swapoff(int type); void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg); void zswap_lruvec_state_init(struct lruvec *lruvec); void zswap_folio_swapin(struct folio *folio); -bool is_zswap_enabled(void); +bool zswap_is_enabled(void); +bool zswap_never_enabled(void); #else struct zswap_lruvec_state {}; @@ -60,11 +61,16 @@ static inline void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) {} static inline void zswap_lruvec_state_init(struct lruvec *lruvec) {} static inline void zswap_folio_swapin(struct folio *folio) {} -static inline bool is_zswap_enabled(void) +static inline bool zswap_is_enabled(void) { return false; } +static inline bool zswap_never_enabled(void) +{ + return true; +} + #endif #endif /* _LINUX_ZSWAP_H */ |