diff options
Diffstat (limited to 'include')
50 files changed, 1494 insertions, 337 deletions
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 1dc8d262035b..459d6981ca96 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -12,7 +12,7 @@ /* Current ACPICA subsystem version in YYYYMMDD format */ -#define ACPI_CA_VERSION 0x20200430 +#define ACPI_CA_VERSION 0x20200528 #include <acpi/acconfig.h> #include <acpi/actypes.h> diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index 4defed58ea33..aa236b9e6f24 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -815,8 +815,9 @@ typedef u8 acpi_adr_space_type; #define ACPI_ADR_SPACE_GPIO (acpi_adr_space_type) 8 #define ACPI_ADR_SPACE_GSBUS (acpi_adr_space_type) 9 #define ACPI_ADR_SPACE_PLATFORM_COMM (acpi_adr_space_type) 10 +#define ACPI_ADR_SPACE_PLATFORM_RT (acpi_adr_space_type) 11 -#define ACPI_NUM_PREDEFINED_REGIONS 11 +#define ACPI_NUM_PREDEFINED_REGIONS 12 /* * Special Address Spaces diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h index 85b28eb80b11..2eacaf7d62f6 100644 --- a/include/asm-generic/barrier.h +++ b/include/asm-generic/barrier.h @@ -128,10 +128,10 @@ do { \ #ifndef __smp_load_acquire #define __smp_load_acquire(p) \ ({ \ - typeof(*p) ___p1 = READ_ONCE(*p); \ + __unqual_scalar_typeof(*p) ___p1 = READ_ONCE(*p); \ compiletime_assert_atomic_type(*p); \ __smp_mb(); \ - ___p1; \ + (typeof(*p))___p1; \ }) #endif @@ -183,10 +183,10 @@ do { \ #ifndef smp_load_acquire #define smp_load_acquire(p) \ ({ \ - typeof(*p) ___p1 = READ_ONCE(*p); \ + __unqual_scalar_typeof(*p) ___p1 = READ_ONCE(*p); \ compiletime_assert_atomic_type(*p); \ barrier(); \ - ___p1; \ + (typeof(*p))___p1; \ }) #endif @@ -229,14 +229,14 @@ do { \ #ifndef smp_cond_load_relaxed #define smp_cond_load_relaxed(ptr, cond_expr) ({ \ typeof(ptr) __PTR = (ptr); \ - typeof(*ptr) VAL; \ + __unqual_scalar_typeof(*ptr) VAL; \ for (;;) { \ VAL = READ_ONCE(*__PTR); \ if (cond_expr) \ break; \ cpu_relax(); \ } \ - VAL; \ + (typeof(*ptr))VAL; \ }) #endif @@ -250,10 +250,10 @@ do { \ */ #ifndef smp_cond_load_acquire #define smp_cond_load_acquire(ptr, cond_expr) ({ \ - typeof(*ptr) _val; \ + __unqual_scalar_typeof(*ptr) _val; \ _val = smp_cond_load_relaxed(ptr, cond_expr); \ smp_acquire__after_ctrl_dep(); \ - _val; \ + (typeof(*ptr))_val; \ }) #endif diff --git a/include/dt-bindings/mailbox/qcom-ipcc.h b/include/dt-bindings/mailbox/qcom-ipcc.h new file mode 100644 index 000000000000..4c23eefed5f3 --- /dev/null +++ b/include/dt-bindings/mailbox/qcom-ipcc.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause */ +/* + * Copyright (c) 2018-2020, The Linux Foundation. All rights reserved. + */ + +#ifndef __DT_BINDINGS_MAILBOX_IPCC_H +#define __DT_BINDINGS_MAILBOX_IPCC_H + +/* Signal IDs for MPROC protocol */ +#define IPCC_MPROC_SIGNAL_GLINK_QMP 0 +#define IPCC_MPROC_SIGNAL_SMP2P 2 +#define IPCC_MPROC_SIGNAL_PING 3 + +/* Client IDs */ +#define IPCC_CLIENT_AOP 0 +#define IPCC_CLIENT_TZ 1 +#define IPCC_CLIENT_MPSS 2 +#define IPCC_CLIENT_LPASS 3 +#define IPCC_CLIENT_SLPI 4 +#define IPCC_CLIENT_SDC 5 +#define IPCC_CLIENT_CDSP 6 +#define IPCC_CLIENT_NPU 7 +#define IPCC_CLIENT_APSS 8 +#define IPCC_CLIENT_GPU 9 +#define IPCC_CLIENT_CVP 10 +#define IPCC_CLIENT_CAM 11 +#define IPCC_CLIENT_VPU 12 +#define IPCC_CLIENT_PCIE0 13 +#define IPCC_CLIENT_PCIE1 14 +#define IPCC_CLIENT_PCIE2 15 +#define IPCC_CLIENT_SPSS 16 + +#endif diff --git a/include/linux/bch.h b/include/linux/bch.h index aa765af85c38..85fdce83d4e2 100644 --- a/include/linux/bch.h +++ b/include/linux/bch.h @@ -33,6 +33,7 @@ * @cache: log-based polynomial representation buffer * @elp: error locator polynomial * @poly_2t: temporary polynomials of degree 2t + * @swap_bits: swap bits within data and syndrome bytes */ struct bch_control { unsigned int m; @@ -51,16 +52,18 @@ struct bch_control { int *cache; struct gf_poly *elp; struct gf_poly *poly_2t[4]; + bool swap_bits; }; -struct bch_control *init_bch(int m, int t, unsigned int prim_poly); +struct bch_control *bch_init(int m, int t, unsigned int prim_poly, + bool swap_bits); -void free_bch(struct bch_control *bch); +void bch_free(struct bch_control *bch); -void encode_bch(struct bch_control *bch, const uint8_t *data, +void bch_encode(struct bch_control *bch, const uint8_t *data, unsigned int len, uint8_t *ecc); -int decode_bch(struct bch_control *bch, const uint8_t *data, unsigned int len, +int bch_decode(struct bch_control *bch, const uint8_t *data, unsigned int len, const uint8_t *recv_ecc, const uint8_t *calc_ecc, const unsigned int *syn, unsigned int *errloc); diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index d7ee4c6bad48..e2f725273261 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -10,7 +10,8 @@ + __GNUC_MINOR__ * 100 \ + __GNUC_PATCHLEVEL__) -#if GCC_VERSION < 40600 +/* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 */ +#if GCC_VERSION < 40800 # error Sorry, your compiler is too old - please upgrade it. #endif @@ -126,9 +127,7 @@ #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) && !defined(__CHECKER__) #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ -#if GCC_VERSION >= 40800 #define __HAVE_BUILTIN_BSWAP16__ -#endif #endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP && !__CHECKER__ */ #if GCC_VERSION >= 70000 diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 6325d64e3c3b..33d3a2e5abab 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -230,60 +230,6 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, # define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __LINE__) #endif -#include <uapi/linux/types.h> - -#define __READ_ONCE_SIZE \ -({ \ - switch (size) { \ - case 1: *(__u8 *)res = *(volatile __u8 *)p; break; \ - case 2: *(__u16 *)res = *(volatile __u16 *)p; break; \ - case 4: *(__u32 *)res = *(volatile __u32 *)p; break; \ - case 8: *(__u64 *)res = *(volatile __u64 *)p; break; \ - default: \ - barrier(); \ - __builtin_memcpy((void *)res, (const void *)p, size); \ - barrier(); \ - } \ -}) - -static __always_inline -void __read_once_size(const volatile void *p, void *res, int size) -{ - __READ_ONCE_SIZE; -} - -#ifdef CONFIG_KASAN -/* - * We can't declare function 'inline' because __no_sanitize_address confilcts - * with inlining. Attempt to inline it may cause a build failure. - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 - * '__maybe_unused' allows us to avoid defined-but-not-used warnings. - */ -# define __no_kasan_or_inline __no_sanitize_address notrace __maybe_unused -#else -# define __no_kasan_or_inline __always_inline -#endif - -static __no_kasan_or_inline -void __read_once_size_nocheck(const volatile void *p, void *res, int size) -{ - __READ_ONCE_SIZE; -} - -static __always_inline void __write_once_size(volatile void *p, void *res, int size) -{ - switch (size) { - case 1: *(volatile __u8 *)p = *(__u8 *)res; break; - case 2: *(volatile __u16 *)p = *(__u16 *)res; break; - case 4: *(volatile __u32 *)p = *(__u32 *)res; break; - case 8: *(volatile __u64 *)p = *(__u64 *)res; break; - default: - barrier(); - __builtin_memcpy((void *)p, (const void *)res, size); - barrier(); - } -} - /* * Prevent the compiler from merging or refetching reads or writes. The * compiler is also forbidden from reordering successive instances of @@ -293,11 +239,7 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s * statements. * * These two macros will also work on aggregate data types like structs or - * unions. If the size of the accessed data type exceeds the word size of - * the machine (e.g., 32 bits or 64 bits) READ_ONCE() and WRITE_ONCE() will - * fall back to memcpy(). There's at least two memcpy()s: one for the - * __builtin_memcpy() and then one for the macro doing the copy of variable - * - '__u' allocated on the stack. + * unions. * * Their two major use cases are: (1) Mediating communication between * process-level code and irq/NMI handlers, all running on the same CPU, @@ -309,23 +251,69 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s #include <asm/barrier.h> #include <linux/kasan-checks.h> -#define __READ_ONCE(x, check) \ +/* + * Use __READ_ONCE() instead of READ_ONCE() if you do not require any + * atomicity or dependency ordering guarantees. Note that this may result + * in tears! + */ +#define __READ_ONCE(x) (*(const volatile __unqual_scalar_typeof(x) *)&(x)) + +#define __READ_ONCE_SCALAR(x) \ ({ \ - union { typeof(x) __val; char __c[1]; } __u; \ - if (check) \ - __read_once_size(&(x), __u.__c, sizeof(x)); \ - else \ - __read_once_size_nocheck(&(x), __u.__c, sizeof(x)); \ - smp_read_barrier_depends(); /* Enforce dependency ordering from x */ \ - __u.__val; \ + __unqual_scalar_typeof(x) __x = __READ_ONCE(x); \ + smp_read_barrier_depends(); \ + (typeof(x))__x; \ }) -#define READ_ONCE(x) __READ_ONCE(x, 1) +#define READ_ONCE(x) \ +({ \ + compiletime_assert_rwonce_type(x); \ + __READ_ONCE_SCALAR(x); \ +}) + +#define __WRITE_ONCE(x, val) \ +do { \ + *(volatile typeof(x) *)&(x) = (val); \ +} while (0) + +#define WRITE_ONCE(x, val) \ +do { \ + compiletime_assert_rwonce_type(x); \ + __WRITE_ONCE(x, val); \ +} while (0) + +#ifdef CONFIG_KASAN /* - * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need - * to hide memory access from KASAN. + * We can't declare function 'inline' because __no_sanitize_address conflicts + * with inlining. Attempt to inline it may cause a build failure. + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 + * '__maybe_unused' allows us to avoid defined-but-not-used warnings. */ -#define READ_ONCE_NOCHECK(x) __READ_ONCE(x, 0) +# define __no_kasan_or_inline __no_sanitize_address notrace __maybe_unused +#else +# define __no_kasan_or_inline __always_inline +#endif + +static __no_kasan_or_inline +unsigned long __read_once_word_nocheck(const void *addr) +{ + return __READ_ONCE(*(unsigned long *)addr); +} + +/* + * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need to load a + * word from memory atomically but without telling KASAN. This is usually + * used by unwinding code when walking the stack of a running process. + */ +#define READ_ONCE_NOCHECK(x) \ +({ \ + unsigned long __x; \ + compiletime_assert(sizeof(x) == sizeof(__x), \ + "Unsupported access size for READ_ONCE_NOCHECK()."); \ + __x = __read_once_word_nocheck(&(x)); \ + smp_read_barrier_depends(); \ + (typeof(x))__x; \ +}) static __no_kasan_or_inline unsigned long read_word_at_a_time(const void *addr) @@ -334,14 +322,6 @@ unsigned long read_word_at_a_time(const void *addr) return *(unsigned long *)addr; } -#define WRITE_ONCE(x, val) \ -({ \ - union { typeof(x) __val; char __c[1]; } __u = \ - { .__val = (__force typeof(x)) (val) }; \ - __write_once_size(&(x), __u.__c, sizeof(x)); \ - __u.__val; \ -}) - #endif /* __KERNEL__ */ /* @@ -406,6 +386,16 @@ static inline void *offset_to_ptr(const int *off) compiletime_assert(__native_word(t), \ "Need native word sized stores/loads for atomicity.") +/* + * Yes, this permits 64-bit accesses on 32-bit architectures. These will + * actually be atomic in some cases (namely Armv7 + LPAE), but for others we + * rely on the access being split into 2x32-bit accesses for a 32-bit quantity + * (e.g. a virtual address) and a strong prevailing wind. + */ +#define compiletime_assert_rwonce_type(t) \ + compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long), \ + "Unsupported access size for {READ,WRITE}_ONCE().") + /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 6fcf73200b67..d4e1956f903f 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -218,6 +218,53 @@ struct ftrace_likely_data { /* Are two types/vars the same type (ignoring qualifiers)? */ #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) +/* + * __unqual_scalar_typeof(x) - Declare an unqualified scalar type, leaving + * non-scalar types unchanged. + */ +#if (defined(CONFIG_CC_IS_GCC) && CONFIG_GCC_VERSION < 40900) || defined(__CHECKER__) +/* + * We build this out of a couple of helper macros in a vain attempt to + * help you keep your lunch down while reading it. + */ +#define __pick_scalar_type(x, type, otherwise) \ + __builtin_choose_expr(__same_type(x, type), (type)0, otherwise) + +/* + * 'char' is not type-compatible with either 'signed char' or 'unsigned char', + * so we include the naked type here as well as the signed/unsigned variants. + */ +#define __pick_integer_type(x, type, otherwise) \ + __pick_scalar_type(x, type, \ + __pick_scalar_type(x, unsigned type, \ + __pick_scalar_type(x, signed type, otherwise))) + +#define __unqual_scalar_typeof(x) typeof( \ + __pick_integer_type(x, char, \ + __pick_integer_type(x, short, \ + __pick_integer_type(x, int, \ + __pick_integer_type(x, long, \ + __pick_integer_type(x, long long, x)))))) +#else +/* + * If supported, prefer C11 _Generic for better compile-times. As above, 'char' + * is not type-compatible with 'signed char', and we define a separate case. + */ +#define __scalar_type_to_expr_cases(type) \ + unsigned type: (unsigned type)0, \ + signed type: (signed type)0 + +#define __unqual_scalar_typeof(x) typeof( \ + _Generic((x), \ + char: (char)0, \ + __scalar_type_to_expr_cases(char), \ + __scalar_type_to_expr_cases(short), \ + __scalar_type_to_expr_cases(int), \ + __scalar_type_to_expr_cases(long), \ + __scalar_type_to_expr_cases(long long), \ + default: (x))) +#endif + /* Is this type a native word size -- useful for atomic operations */ #define __native_word(t) \ (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || \ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 67d5950bd878..3494f6763597 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -367,7 +367,7 @@ struct cpufreq_driver { /* platform specific boost support code */ bool boost_enabled; - int (*set_boost)(int state); + int (*set_boost)(struct cpufreq_policy *policy, int state); }; /* flags */ diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 8377afef8806..191772d4a4d7 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -102,6 +102,7 @@ enum cpuhp_state { CPUHP_AP_IRQ_ARMADA_XP_STARTING, CPUHP_AP_IRQ_BCM2836_STARTING, CPUHP_AP_IRQ_MIPS_GIC_STARTING, + CPUHP_AP_IRQ_RISCV_STARTING, CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING, CPUHP_AP_ARM_MVEBU_COHERENCY, CPUHP_AP_MICROCODE_LOADER, diff --git a/include/linux/fs.h b/include/linux/fs.h index 19ef6c88c152..8e1f8f93108f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1048,6 +1048,7 @@ struct lock_manager_operations { bool (*lm_break)(struct file_lock *); int (*lm_change)(struct file_lock *, int, struct list_head *); void (*lm_setup)(struct file_lock *, void **); + bool (*lm_breaker_owns_lease)(struct file_lock *); }; struct lock_manager { diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index dfbbf7a7208b..e339dac91ee6 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -342,9 +342,8 @@ static inline void arch_ftrace_set_direct_caller(struct pt_regs *regs, extern int stack_tracer_enabled; -int stack_trace_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); +int stack_trace_sysctl(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos); /* DO NOT MODIFY THIS VARIABLE DIRECTLY! */ DECLARE_PER_CPU(int, disable_stack_tracer); diff --git a/include/linux/input/gp2ap002a00f.h b/include/linux/input/gp2ap002a00f.h deleted file mode 100644 index 3614a13a8297..000000000000 --- a/include/linux/input/gp2ap002a00f.h +++ /dev/null @@ -1,23 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _GP2AP002A00F_H_ -#define _GP2AP002A00F_H_ - -#include <linux/i2c.h> - -#define GP2A_I2C_NAME "gp2ap002a00f" - -/** - * struct gp2a_platform_data - Sharp gp2ap002a00f proximity platform data - * @vout_gpio: The gpio connected to the object detected pin (VOUT) - * @wakeup: Set to true if the proximity can wake the device from suspend - * @hw_setup: Callback for setting up hardware such as gpios and vregs - * @hw_shutdown: Callback for properly shutting down hardware - */ -struct gp2a_platform_data { - int vout_gpio; - bool wakeup; - int (*hw_setup)(struct i2c_client *client); - int (*hw_shutdown)(struct i2c_client *client); -}; - -#endif diff --git a/include/linux/input/mt.h b/include/linux/input/mt.h index 9e409bb13642..3b8580bd33c1 100644 --- a/include/linux/input/mt.h +++ b/include/linux/input/mt.h @@ -100,6 +100,11 @@ static inline bool input_is_mt_axis(int axis) bool input_mt_report_slot_state(struct input_dev *dev, unsigned int tool_type, bool active); +static inline void input_mt_report_slot_inactive(struct input_dev *dev) +{ + input_mt_report_slot_state(dev, 0, false); +} + void input_mt_report_finger_count(struct input_dev *dev, int count); void input_mt_report_pointer_emulation(struct input_dev *dev, bool use_count); void input_mt_drop_unused(struct input_dev *dev); diff --git a/include/linux/interconnect.h b/include/linux/interconnect.h index d8c29049f066..3a63d98613fc 100644 --- a/include/linux/interconnect.h +++ b/include/linux/interconnect.h @@ -35,6 +35,7 @@ int icc_enable(struct icc_path *path); int icc_disable(struct icc_path *path); int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw); void icc_set_tag(struct icc_path *path, u32 tag); +const char *icc_get_name(struct icc_path *path); #else @@ -84,6 +85,11 @@ static inline void icc_set_tag(struct icc_path *path, u32 tag) { } +static inline const char *icc_get_name(struct icc_path *path) +{ + return NULL; +} + #endif /* CONFIG_INTERCONNECT */ #endif /* __LINUX_INTERCONNECT_H */ diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 12258ea077cf..65b81e0c494d 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -59,6 +59,7 @@ bool kthread_should_stop(void); bool kthread_should_park(void); bool __kthread_should_park(struct task_struct *k); bool kthread_freezable_should_stop(bool *was_frozen); +void *kthread_func(struct task_struct *k); void *kthread_data(struct task_struct *k); void *kthread_probe_data(struct task_struct *k); int kthread_park(struct task_struct *k); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index fee7fab5d706..375515803cd8 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -318,6 +318,7 @@ extern void try_offline_node(int nid); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern int remove_memory(int nid, u64 start, u64 size); extern void __remove_memory(int nid, u64 start, u64 size); +extern int offline_and_remove_memory(int nid, u64 start, u64 size); #else static inline void try_offline_node(int nid) {} diff --git a/include/linux/mtd/bbm.h b/include/linux/mtd/bbm.h index 886e30441c90..d890805f5494 100644 --- a/include/linux/mtd/bbm.h +++ b/include/linux/mtd/bbm.h @@ -98,7 +98,7 @@ struct nand_bbt_descr { /* * Flag set by nand_create_default_bbt_descr(), marking that the nand_bbt_descr - * was allocated dynamicaly and must be freed in nand_release(). Has no meaning + * was allocated dynamicaly and must be freed in nand_cleanup(). Has no meaning * in nand_chip.bbt_options. */ #define NAND_BBT_DYNAMICSTRUCT 0x80000000 diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index c98a21108688..fd1ecb821106 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -138,7 +138,7 @@ struct cfi_ident { uint16_t InterfaceDesc; uint16_t MaxBufWriteSize; uint8_t NumEraseRegions; - uint32_t EraseRegionInfo[0]; /* Not host ordered */ + uint32_t EraseRegionInfo[]; /* Not host ordered */ } __packed; /* Extended Query Structure for both PRI and ALT */ @@ -165,7 +165,7 @@ struct cfi_pri_intelext { uint16_t ProtRegAddr; uint8_t FactProtRegSize; uint8_t UserProtRegSize; - uint8_t extra[0]; + uint8_t extra[]; } __packed; struct cfi_intelext_otpinfo { @@ -286,7 +286,7 @@ struct cfi_private { map_word sector_erase_cmd; unsigned long chipshift; /* Because they're of the same type */ const char *im_name; /* inter_module name for cmdset_setup */ - struct flchip chips[0]; /* per-chip data structure for each chip */ + struct flchip chips[]; /* per-chip data structure for each chip */ }; uint32_t cfi_build_cmd_addr(uint32_t cmd_ofs, diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 2d1f4a61f4ac..157357ec1441 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -200,6 +200,8 @@ struct mtd_debug_info { * * @node: list node used to add an MTD partition to the parent partition list * @offset: offset of the partition relatively to the parent offset + * @size: partition size. Should be equal to mtd->size unless + * MTD_SLC_ON_MLC_EMULATION is set * @flags: original flags (before the mtdpart logic decided to tweak them based * on flash constraints, like eraseblock/pagesize alignment) * @@ -209,6 +211,7 @@ struct mtd_debug_info { struct mtd_part { struct list_head node; u64 offset; + u64 size; u32 flags; }; @@ -622,7 +625,9 @@ static inline uint32_t mtd_mod_by_ws(uint64_t sz, struct mtd_info *mtd) static inline int mtd_wunit_per_eb(struct mtd_info *mtd) { - return mtd->erasesize / mtd->writesize; + struct mtd_info *master = mtd_get_master(mtd); + + return master->erasesize / mtd->writesize; } static inline int mtd_offset_to_wunit(struct mtd_info *mtd, loff_t offs) diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index e545c050d3e8..b74a539ec581 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -37,6 +37,7 @@ * master MTD flag set for the corresponding MTD partition. * For example, to force a read-only partition, simply adding * MTD_WRITEABLE to the mask_flags will do the trick. + * add_flags: contains flags to add to the parent flags * * Note: writeable partitions require their size and offset be * erasesize aligned (e.g. use MTDPART_OFS_NEXTBLK). @@ -48,6 +49,7 @@ struct mtd_partition { uint64_t size; /* partition size */ uint64_t offset; /* offset within the master MTD space */ uint32_t mask_flags; /* master MTD flags to mask out for this partition */ + uint32_t add_flags; /* flags to add to the partition */ struct device_node *of_node; }; diff --git a/include/linux/mtd/qinfo.h b/include/linux/mtd/qinfo.h index df5b9fddea16..2e3f43788d48 100644 --- a/include/linux/mtd/qinfo.h +++ b/include/linux/mtd/qinfo.h @@ -24,7 +24,7 @@ struct lpddr_private { struct qinfo_chip *qinfo; int numchips; unsigned long chipshift; - struct flchip chips[0]; + struct flchip chips[]; }; /* qinfo_query_info structure contains request information for diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 1e76196f9829..65b1c1c18b41 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -83,14 +83,14 @@ struct nand_chip; /* * Constants for ECC_MODES */ -typedef enum { +enum nand_ecc_mode { + NAND_ECC_INVALID, NAND_ECC_NONE, NAND_ECC_SOFT, NAND_ECC_HW, NAND_ECC_HW_SYNDROME, - NAND_ECC_HW_OOB_FIRST, NAND_ECC_ON_DIE, -} nand_ecc_modes_t; +}; enum nand_ecc_algo { NAND_ECC_UNKNOWN, @@ -119,85 +119,73 @@ enum nand_ecc_algo { #define NAND_ECC_MAXIMIZE BIT(1) /* + * Option constants for bizarre disfunctionality and real + * features. + */ + +/* Buswidth is 16 bit */ +#define NAND_BUSWIDTH_16 BIT(1) + +/* * When using software implementation of Hamming, we can specify which byte * ordering should be used. */ #define NAND_ECC_SOFT_HAMMING_SM_ORDER BIT(2) -/* - * Option constants for bizarre disfunctionality and real - * features. - */ -/* Buswidth is 16 bit */ -#define NAND_BUSWIDTH_16 0x00000002 /* Chip has cache program function */ -#define NAND_CACHEPRG 0x00000008 +#define NAND_CACHEPRG BIT(3) +/* Options valid for Samsung large page devices */ +#define NAND_SAMSUNG_LP_OPTIONS NAND_CACHEPRG + /* * Chip requires ready check on read (for auto-incremented sequential read). * True only for small page devices; large page devices do not support * autoincrement. */ -#define NAND_NEED_READRDY 0x00000100 +#define NAND_NEED_READRDY BIT(8) /* Chip does not allow subpage writes */ -#define NAND_NO_SUBPAGE_WRITE 0x00000200 +#define NAND_NO_SUBPAGE_WRITE BIT(9) /* Device is one of 'new' xD cards that expose fake nand command set */ -#define NAND_BROKEN_XD 0x00000400 +#define NAND_BROKEN_XD BIT(10) /* Device behaves just like nand, but is readonly */ -#define NAND_ROM 0x00000800 +#define NAND_ROM BIT(11) /* Device supports subpage reads */ -#define NAND_SUBPAGE_READ 0x00001000 +#define NAND_SUBPAGE_READ BIT(12) +/* Macros to identify the above */ +#define NAND_HAS_SUBPAGE_READ(chip) ((chip->options & NAND_SUBPAGE_READ)) /* * Some MLC NANDs need data scrambling to limit bitflips caused by repeated * patterns. */ -#define NAND_NEED_SCRAMBLING 0x00002000 +#define NAND_NEED_SCRAMBLING BIT(13) /* Device needs 3rd row address cycle */ -#define NAND_ROW_ADDR_3 0x00004000 - -/* Options valid for Samsung large page devices */ -#define NAND_SAMSUNG_LP_OPTIONS NAND_CACHEPRG - -/* Macros to identify the above */ -#define NAND_HAS_SUBPAGE_READ(chip) ((chip->options & NAND_SUBPAGE_READ)) - -/* - * There are different places where the manufacturer stores the factory bad - * block markers. - * - * Position within the block: Each of these pages needs to be checked for a - * bad block marking pattern. - */ -#define NAND_BBM_FIRSTPAGE 0x01000000 -#define NAND_BBM_SECONDPAGE 0x02000000 -#define NAND_BBM_LASTPAGE 0x04000000 - -/* Position within the OOB data of the page */ -#define NAND_BBM_POS_SMALL 5 -#define NAND_BBM_POS_LARGE 0 +#define NAND_ROW_ADDR_3 BIT(14) /* Non chip related options */ /* This option skips the bbt scan during initialization. */ -#define NAND_SKIP_BBTSCAN 0x00010000 +#define NAND_SKIP_BBTSCAN BIT(16) /* Chip may not exist, so silence any errors in scan */ -#define NAND_SCAN_SILENT_NODEV 0x00040000 +#define NAND_SCAN_SILENT_NODEV BIT(18) + /* * Autodetect nand buswidth with readid/onfi. * This suppose the driver will configure the hardware in 8 bits mode * when calling nand_scan_ident, and update its configuration * before calling nand_scan_tail. */ -#define NAND_BUSWIDTH_AUTO 0x00080000 +#define NAND_BUSWIDTH_AUTO BIT(19) + /* * This option could be defined by controller drivers to protect against * kmap'ed, vmalloc'ed highmem buffers being passed from upper layers */ -#define NAND_USE_BOUNCE_BUFFER 0x00100000 +#define NAND_USES_DMA BIT(20) /* * In case your controller is implementing ->legacy.cmd_ctrl() and is relying @@ -207,26 +195,49 @@ enum nand_ecc_algo { * If your controller already takes care of this delay, you don't need to set * this flag. */ -#define NAND_WAIT_TCCS 0x00200000 +#define NAND_WAIT_TCCS BIT(21) /* * Whether the NAND chip is a boot medium. Drivers might use this information * to select ECC algorithms supported by the boot ROM or similar restrictions. */ -#define NAND_IS_BOOT_MEDIUM 0x00400000 +#define NAND_IS_BOOT_MEDIUM BIT(22) /* * Do not try to tweak the timings at runtime. This is needed when the * controller initializes the timings on itself or when it relies on * configuration done by the bootloader. */ -#define NAND_KEEP_TIMINGS 0x00800000 +#define NAND_KEEP_TIMINGS BIT(23) + +/* + * There are different places where the manufacturer stores the factory bad + * block markers. + * + * Position within the block: Each of these pages needs to be checked for a + * bad block marking pattern. + */ +#define NAND_BBM_FIRSTPAGE BIT(24) +#define NAND_BBM_SECONDPAGE BIT(25) +#define NAND_BBM_LASTPAGE BIT(26) + +/* + * Some controllers with pipelined ECC engines override the BBM marker with + * data or ECC bytes, thus making bad block detection through bad block marker + * impossible. Let's flag those chips so the core knows it shouldn't check the + * BBM and consider all blocks good. + */ +#define NAND_NO_BBM_QUIRK BIT(27) /* Cell info constants */ #define NAND_CI_CHIPNR_MSK 0x03 #define NAND_CI_CELLTYPE_MSK 0x0C #define NAND_CI_CELLTYPE_SHIFT 2 +/* Position within the OOB data of the page */ +#define NAND_BBM_POS_SMALL 5 +#define NAND_BBM_POS_LARGE 0 + /** * struct nand_parameters - NAND generic parameters from the parameter page * @model: Model name @@ -351,7 +362,7 @@ static const struct nand_ecc_caps __name = { \ * @write_oob: function to write chip OOB data */ struct nand_ecc_ctrl { - nand_ecc_modes_t mode; + enum nand_ecc_mode mode; enum nand_ecc_algo algo; int steps; int size; @@ -491,13 +502,17 @@ enum nand_data_interface_type { /** * struct nand_data_interface - NAND interface timing * @type: type of the timing - * @timings: The timing, type according to @type + * @timings: The timing information + * @timings.mode: Timing mode as defined in the specification * @timings.sdr: Use it when @type is %NAND_SDR_IFACE. */ struct nand_data_interface { enum nand_data_interface_type type; - union { - struct nand_sdr_timings sdr; + struct nand_timings { + unsigned int mode; + union { + struct nand_sdr_timings sdr; + }; } timings; }; @@ -694,6 +709,7 @@ struct nand_op_instr { /** * struct nand_subop - a sub operation + * @cs: the CS line to select for this NAND sub-operation * @instrs: array of instructions * @ninstrs: length of the @instrs array * @first_instr_start_off: offset to start from for the first instruction @@ -709,6 +725,7 @@ struct nand_op_instr { * controller driver. */ struct nand_subop { + unsigned int cs; const struct nand_op_instr *instrs; unsigned int ninstrs; unsigned int first_instr_start_off; @@ -1321,13 +1338,17 @@ int nand_read_oob_std(struct nand_chip *chip, int page); int nand_get_set_features_notsupp(struct nand_chip *chip, int addr, u8 *subfeature_param); -/* Default read_page_raw implementation */ +/* read_page_raw implementations */ int nand_read_page_raw(struct nand_chip *chip, uint8_t *buf, int oob_required, int page); +int nand_monolithic_read_page_raw(struct nand_chip *chip, uint8_t *buf, + int oob_required, int page); -/* Default write_page_raw implementation */ +/* write_page_raw implementations */ int nand_write_page_raw(struct nand_chip *chip, const uint8_t *buf, int oob_required, int page); +int nand_monolithic_write_page_raw(struct nand_chip *chip, const uint8_t *buf, + int oob_required, int page); /* Reset and initialize a NAND device */ int nand_reset(struct nand_chip *chip, int chipnr); @@ -1356,7 +1377,7 @@ int nand_change_write_column_op(struct nand_chip *chip, unsigned int offset_in_page, const void *buf, unsigned int len, bool force_8bit); int nand_read_data_op(struct nand_chip *chip, void *buf, unsigned int len, - bool force_8bit); + bool force_8bit, bool check_only); int nand_write_data_op(struct nand_chip *chip, const void *buf, unsigned int len, bool force_8bit); @@ -1377,8 +1398,6 @@ void nand_wait_ready(struct nand_chip *chip); * sucessful nand_scan(). */ void nand_cleanup(struct nand_chip *chip); -/* Unregister the MTD device and calls nand_cleanup() */ -void nand_release(struct nand_chip *chip); /* * External helper for controller drivers that have to implement the WAITRDY @@ -1393,6 +1412,10 @@ int nand_gpio_waitrdy(struct nand_chip *chip, struct gpio_desc *gpiod, void nand_select_target(struct nand_chip *chip, unsigned int cs); void nand_deselect_target(struct nand_chip *chip); +/* Bitops */ +void nand_extract_bits(u8 *dst, unsigned int dst_off, const u8 *src, + unsigned int src_off, unsigned int nbits); + /** * nand_get_data_buf() - Get the internal page buffer * @chip: NAND chip object diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 1e2af0ec1f03..60bac2c0ec45 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -20,6 +20,7 @@ */ /* Flash opcodes. */ +#define SPINOR_OP_WRDI 0x04 /* Write disable */ #define SPINOR_OP_WREN 0x06 /* Write enable */ #define SPINOR_OP_RDSR 0x05 /* Read status register */ #define SPINOR_OP_WRSR 0x01 /* Write status register 1 byte */ @@ -80,7 +81,6 @@ /* Used for SST flashes only. */ #define SPINOR_OP_BP 0x02 /* Byte program */ -#define SPINOR_OP_WRDI 0x04 /* Write disable */ #define SPINOR_OP_AAI_WP 0xad /* Auto address increment word program */ /* Used for S3AN flashes only */ @@ -302,7 +302,7 @@ struct spi_nor; * @read: read data from the SPI NOR. * @write: write data to the SPI NOR. * @erase: erase a sector of the SPI NOR at the offset @offs; if - * not provided by the driver, spi-nor will send the erase + * not provided by the driver, SPI NOR will send the erase * opcode via write_reg(). */ struct spi_nor_controller_ops { @@ -327,16 +327,16 @@ struct spi_nor_manufacturer; struct spi_nor_flash_parameter; /** - * struct spi_nor - Structure for defining a the SPI NOR layer - * @mtd: point to a mtd_info structure + * struct spi_nor - Structure for defining the SPI NOR layer + * @mtd: an mtd_info structure * @lock: the lock for the read/write/erase/lock/unlock operations - * @dev: point to a spi device, or a spi nor controller device. - * @spimem: point to the spi mem device + * @dev: pointer to an SPI device or an SPI NOR controller device + * @spimem: pointer to the SPI memory device * @bouncebuf: bounce buffer used when the buffer passed by the MTD * layer is not DMA-able * @bouncebuf_size: size of the bounce buffer - * @info: spi-nor part JDEC MFR id and other info - * @manufacturer: spi-nor manufacturer + * @info: SPI NOR part JEDEC MFR ID and other info + * @manufacturer: SPI NOR manufacturer * @page_size: the page size of the SPI NOR * @addr_width: number of address bytes * @erase_opcode: the opcode for erasing a sector @@ -344,17 +344,17 @@ struct spi_nor_flash_parameter; * @read_dummy: the dummy needed by the read operation * @program_opcode: the program opcode * @sst_write_second: used by the SST write operation - * @flags: flag options for the current SPI-NOR (SNOR_F_*) + * @flags: flag options for the current SPI NOR (SNOR_F_*) * @read_proto: the SPI protocol for read operations * @write_proto: the SPI protocol for write operations - * @reg_proto the SPI protocol for read_reg/write_reg/erase operations + * @reg_proto: the SPI protocol for read_reg/write_reg/erase operations * @controller_ops: SPI NOR controller driver specific operations. - * @params: [FLASH-SPECIFIC] SPI-NOR flash parameters and settings. + * @params: [FLASH-SPECIFIC] SPI NOR flash parameters and settings. * The structure includes legacy flash parameters and * settings that can be overwritten by the spi_nor_fixups * hooks, or dynamically when parsing the SFDP tables. * @dirmap: pointers to struct spi_mem_dirmap_desc for reads/writes. - * @priv: the private data + * @priv: pointer to the private data */ struct spi_nor { struct mtd_info mtd; diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 82d8fb422092..4dba3c948932 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -38,7 +38,7 @@ struct nfs4_ace { struct nfs4_acl { uint32_t naces; - struct nfs4_ace aces[0]; + struct nfs4_ace aces[]; }; #define NFS4_MAXLABELLEN 2048 @@ -295,7 +295,7 @@ static inline bool seqid_mutating_err(u32 err) case NFS4ERR_NOFILEHANDLE: case NFS4ERR_MOVED: return false; - }; + } return true; } diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 73eda45f1cfd..6ee9119acc5d 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -230,6 +230,7 @@ struct nfs4_copy_state { #define NFS_INO_INVALID_OTHER BIT(12) /* other attrs are invalid */ #define NFS_INO_DATA_INVAL_DEFER \ BIT(13) /* Deferred cache invalidation */ +#define NFS_INO_INVALID_BLOCKS BIT(14) /* cached blocks are invalid */ #define NFS_INO_INVALID_ATTR (NFS_INO_INVALID_CHANGE \ | NFS_INO_INVALID_CTIME \ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index e5f3e7d8d3d5..5fd0a9ef425f 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1227,7 +1227,7 @@ struct nfs4_secinfo4 { struct nfs4_secinfo_flavors { unsigned int num_flavors; - struct nfs4_secinfo4 flavors[0]; + struct nfs4_secinfo4 flavors[]; }; struct nfs4_secinfo_arg { diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 222f6f7b2bb3..6be1aa559b1e 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -777,6 +777,16 @@ PAGE_TYPE_OPS(Buddy, buddy) * not onlined when onlining the section). * The content of these pages is effectively stale. Such pages should not * be touched (read/write/dump/save) except by their owner. + * + * 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 + * 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. */ PAGE_TYPE_OPS(Offline, offline) diff --git a/include/linux/platform_data/mtd-davinci.h b/include/linux/platform_data/mtd-davinci.h index 08e639e047e5..03e92c71b3fa 100644 --- a/include/linux/platform_data/mtd-davinci.h +++ b/include/linux/platform_data/mtd-davinci.h @@ -68,7 +68,7 @@ struct davinci_nand_pdata { /* platform_data */ * Newer ones also support 4-bit ECC, but are awkward * using it with large page chips. */ - nand_ecc_modes_t ecc_mode; + enum nand_ecc_mode ecc_mode; u8 ecc_bits; /* e.g. NAND_BUSWIDTH_16 */ diff --git a/include/linux/platform_data/mtd-nand-s3c2410.h b/include/linux/platform_data/mtd-nand-s3c2410.h index deb849bcf0ec..08675b16f9e1 100644 --- a/include/linux/platform_data/mtd-nand-s3c2410.h +++ b/include/linux/platform_data/mtd-nand-s3c2410.h @@ -49,7 +49,7 @@ struct s3c2410_platform_nand { unsigned int ignore_unset_ecc:1; - nand_ecc_modes_t ecc_mode; + enum nand_ecc_mode ecc_mode; int nr_sets; struct s3c2410_nand_set *sets; diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 747861816f4f..d5c4a329321d 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -42,6 +42,18 @@ struct dev_pm_opp_supply { }; /** + * struct dev_pm_opp_icc_bw - Interconnect bandwidth values + * @avg: Average bandwidth corresponding to this OPP (in icc units) + * @peak: Peak bandwidth corresponding to this OPP (in icc units) + * + * This structure stores the bandwidth values for a single interconnect path. + */ +struct dev_pm_opp_icc_bw { + u32 avg; + u32 peak; +}; + +/** * struct dev_pm_opp_info - OPP freq/voltage/current values * @rate: Target clk rate in hz * @supplies: Array of voltage/current values for all power supplies @@ -360,6 +372,7 @@ 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); +int dev_pm_opp_of_find_icc_paths(struct device *dev, struct opp_table *opp_table); void dev_pm_opp_of_register_em(struct cpumask *cpus); #else static inline int dev_pm_opp_of_add_table(struct device *dev) @@ -408,6 +421,11 @@ static inline int of_get_required_opp_performance_state(struct device_node *np, { return -ENOTSUPP; } + +static inline int dev_pm_opp_of_find_icc_paths(struct device *dev, struct opp_table *opp_table) +{ + return -ENOTSUPP; +} #endif #endif /* __LINUX_OPP_H__ */ diff --git a/include/linux/regset.h b/include/linux/regset.h index bf0243779738..46d6ae68c455 100644 --- a/include/linux/regset.h +++ b/include/linux/regset.h @@ -320,7 +320,7 @@ static inline int user_regset_copyout_zero(unsigned int *pos, if (*kbuf) { memset(*kbuf, 0, copy); *kbuf += copy; - } else if (__clear_user(*ubuf, copy)) + } else if (clear_user(*ubuf, copy)) return -EFAULT; else *ubuf += copy; diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index 4f6b28487f28..98da816b5fc2 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -76,7 +76,7 @@ struct rpc_auth { unsigned int au_verfsize; /* size of reply verifier */ unsigned int au_ralign; /* words before UL header */ - unsigned int au_flags; + unsigned long au_flags; const struct rpc_authops *au_ops; rpc_authflavor_t au_flavor; /* pseudoflavor (note may * differ from the flavor in @@ -89,7 +89,8 @@ struct rpc_auth { }; /* rpc_auth au_flags */ -#define RPCAUTH_AUTH_DATATOUCH 0x00000002 +#define RPCAUTH_AUTH_DATATOUCH (1) +#define RPCAUTH_AUTH_UPDATE_SLACK (2) struct rpc_auth_create_args { rpc_authflavor_t pseudoflavor; diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index bc07e51f20d1..bf4ac8a0268c 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -84,6 +84,7 @@ struct pf_desc { u32 service; char *name; char *auth_domain_name; + struct auth_domain *domain; bool datatouch; }; diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index fd390894a584..386628b36bc7 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -254,6 +254,7 @@ struct svc_rqst { struct page * *rq_page_end; /* one past the last page */ struct kvec rq_vec[RPCSVC_MAXPAGES]; /* generally useful.. */ + struct bio_vec rq_bvec[RPCSVC_MAXPAGES]; __be32 rq_xid; /* transmission id */ u32 rq_prog; /* program number */ @@ -299,6 +300,7 @@ struct svc_rqst { struct net *rq_bc_net; /* pointer to backchannel's * net namespace */ + void ** rq_lease_breaker; /* The v4 client breaking a lease */ }; #define SVC_NET(rqst) (rqst->rq_xprt ? rqst->rq_xprt->xpt_net : rqst->rq_bc_net) diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index cbcfbd0521e3..7ed82625dc0b 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -48,7 +48,6 @@ #include <linux/sunrpc/rpc_rdma.h> #include <rdma/ib_verbs.h> #include <rdma/rdma_cm.h> -#define SVCRDMA_DEBUG /* Default and maximum inline threshold sizes */ enum { @@ -160,9 +159,8 @@ struct svc_rdma_send_ctxt { }; /* svc_rdma_backchannel.c */ -extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, - __be32 *rdma_resp, - struct xdr_buf *rcvbuf); +extern void svc_rdma_handle_bc_reply(struct svc_rqst *rqstp, + struct svc_rdma_recv_ctxt *rctxt); /* svc_rdma_recvfrom.c */ extern void svc_rdma_recv_ctxts_destroy(struct svcxprt_rdma *rdma); diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 9e1e046de176..aca35ab5cff2 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -117,6 +117,12 @@ static inline int register_xpt_user(struct svc_xprt *xpt, struct svc_xpt_user *u return 0; } +static inline bool svc_xprt_is_dead(const struct svc_xprt *xprt) +{ + return (test_bit(XPT_DEAD, &xprt->xpt_flags) != 0) || + (test_bit(XPT_CLOSE, &xprt->xpt_flags) != 0); +} + 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 *, diff --git a/include/linux/sunrpc/svcauth_gss.h b/include/linux/sunrpc/svcauth_gss.h index ca39a388dc22..f09c82b0a7ae 100644 --- a/include/linux/sunrpc/svcauth_gss.h +++ b/include/linux/sunrpc/svcauth_gss.h @@ -20,7 +20,8 @@ int gss_svc_init(void); void gss_svc_shutdown(void); int gss_svc_init_net(struct net *net); void gss_svc_shutdown_net(struct net *net); -int svcauth_gss_register_pseudoflavor(u32 pseudoflavor, char * name); +struct auth_domain *svcauth_gss_register_pseudoflavor(u32 pseudoflavor, + char *name); u32 svcauth_gss_flavor(struct auth_domain *dom); #endif /* _LINUX_SUNRPC_SVCAUTH_GSS_H */ diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index 771baadaee9d..b7ac7fe68306 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -28,7 +28,7 @@ struct svc_sock { /* private TCP part */ /* On-the-wire fragment header: */ - __be32 sk_reclen; + __be32 sk_marker; /* As we receive a record, this includes the length received so * far (including the fragment header): */ u32 sk_tcplen; @@ -41,12 +41,12 @@ struct svc_sock { static inline u32 svc_sock_reclen(struct svc_sock *svsk) { - return ntohl(svsk->sk_reclen) & RPC_FRAGMENT_SIZE_MASK; + return be32_to_cpu(svsk->sk_marker) & RPC_FRAGMENT_SIZE_MASK; } static inline u32 svc_sock_final_rec(struct svc_sock *svsk) { - return ntohl(svsk->sk_reclen) & RPC_LAST_STREAM_FRAGMENT; + return be32_to_cpu(svsk->sk_marker) & RPC_LAST_STREAM_FRAGMENT; } /* diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 5453af87a33e..239db794357c 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -18,6 +18,16 @@ struct vdpa_callback { }; /** + * vDPA notification area + * @addr: base address of the notification area + * @size: size of the notification area + */ +struct vdpa_notification_area { + resource_size_t addr; + resource_size_t size; +}; + +/** * vDPA device - representation of a vDPA device * @dev: underlying device * @dma_dev: the actual device that is performing DMA @@ -73,6 +83,10 @@ struct vdpa_device { * @vdev: vdpa device * @idx: virtqueue index * Returns virtqueue state (last_avail_idx) + * @get_vq_notification: Get the notification area for a virtqueue + * @vdev: vdpa device + * @idx: virtqueue index + * Returns the notifcation area * @get_vq_align: Get the virtqueue align requirement * for the device * @vdev: vdpa device @@ -162,6 +176,8 @@ struct vdpa_config_ops { bool (*get_vq_ready)(struct vdpa_device *vdev, u16 idx); int (*set_vq_state)(struct vdpa_device *vdev, u16 idx, u64 state); u64 (*get_vq_state)(struct vdpa_device *vdev, u16 idx); + struct vdpa_notification_area + (*get_vq_notification)(struct vdpa_device *vdev, u16 idx); /* Device ops */ u32 (*get_vq_align)(struct vdpa_device *vdev); diff --git a/include/linux/vringh.h b/include/linux/vringh.h index 9e2763d7c159..59bd50f99291 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -105,9 +105,9 @@ struct vringh_kiov { /* Helpers for userspace vrings. */ int vringh_init_user(struct vringh *vrh, u64 features, unsigned int num, bool weak_barriers, - struct vring_desc __user *desc, - struct vring_avail __user *avail, - struct vring_used __user *used); + vring_desc_t __user *desc, + vring_avail_t __user *avail, + vring_used_t __user *used); static inline void vringh_iov_init(struct vringh_iov *iov, struct iovec *iovec, unsigned num) diff --git a/include/net/neighbour.h b/include/net/neighbour.h index e1476775769c..81ee17594c32 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -392,13 +392,12 @@ void *neigh_seq_next(struct seq_file *, void *, loff_t *); void neigh_seq_stop(struct seq_file *, void *); int neigh_proc_dointvec(struct ctl_table *ctl, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write, - void __user *buffer, + void *buffer, size_t *lenp, loff_t *ppos); int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos); + void *buffer, size_t *lenp, loff_t *ppos); int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, proc_handler *proc_handler); diff --git a/include/trace/events/rpcgss.h b/include/trace/events/rpcgss.h index 32d88c4fb063..b9b51a4b1db1 100644 --- a/include/trace/events/rpcgss.h +++ b/include/trace/events/rpcgss.h @@ -17,6 +17,16 @@ ** GSS-API related trace events **/ +TRACE_DEFINE_ENUM(RPC_GSS_SVC_NONE); +TRACE_DEFINE_ENUM(RPC_GSS_SVC_INTEGRITY); +TRACE_DEFINE_ENUM(RPC_GSS_SVC_PRIVACY); + +#define show_gss_service(x) \ + __print_symbolic(x, \ + { RPC_GSS_SVC_NONE, "none" }, \ + { RPC_GSS_SVC_INTEGRITY, "integrity" }, \ + { RPC_GSS_SVC_PRIVACY, "privacy" }) + TRACE_DEFINE_ENUM(GSS_S_BAD_MECH); TRACE_DEFINE_ENUM(GSS_S_BAD_NAME); TRACE_DEFINE_ENUM(GSS_S_BAD_NAMETYPE); @@ -126,6 +136,40 @@ DEFINE_GSSAPI_EVENT(verify_mic); DEFINE_GSSAPI_EVENT(wrap); DEFINE_GSSAPI_EVENT(unwrap); +DECLARE_EVENT_CLASS(rpcgss_ctx_class, + TP_PROTO( + const struct gss_cred *gc + ), + + TP_ARGS(gc), + + TP_STRUCT__entry( + __field(const void *, cred) + __field(unsigned long, service) + __string(principal, gc->gc_principal) + ), + + TP_fast_assign( + __entry->cred = gc; + __entry->service = gc->gc_service; + __assign_str(principal, gc->gc_principal) + ), + + TP_printk("cred=%p service=%s principal='%s'", + __entry->cred, show_gss_service(__entry->service), + __get_str(principal)) +); + +#define DEFINE_CTX_EVENT(name) \ + DEFINE_EVENT(rpcgss_ctx_class, rpcgss_ctx_##name, \ + TP_PROTO( \ + const struct gss_cred *gc \ + ), \ + TP_ARGS(gc)) + +DEFINE_CTX_EVENT(init); +DEFINE_CTX_EVENT(destroy); + TRACE_EVENT(rpcgss_svc_accept_upcall, TP_PROTO( __be32 xid, @@ -291,6 +335,40 @@ TRACE_EVENT(rpcgss_need_reencode, __entry->ret ? "" : "un") ); +TRACE_EVENT(rpcgss_update_slack, + TP_PROTO( + const struct rpc_task *task, + const struct rpc_auth *auth + ), + + TP_ARGS(task, auth), + + TP_STRUCT__entry( + __field(unsigned int, task_id) + __field(unsigned int, client_id) + __field(u32, xid) + __field(const void *, auth) + __field(unsigned int, rslack) + __field(unsigned int, ralign) + __field(unsigned int, verfsize) + ), + + TP_fast_assign( + __entry->task_id = task->tk_pid; + __entry->client_id = task->tk_client->cl_clid; + __entry->xid = be32_to_cpu(task->tk_rqstp->rq_xid); + __entry->auth = auth; + __entry->rslack = auth->au_rslack; + __entry->ralign = auth->au_ralign; + __entry->verfsize = auth->au_verfsize; + ), + + TP_printk("task:%u@%u xid=0x%08x auth=%p rslack=%u ralign=%u verfsize=%u\n", + __entry->task_id, __entry->client_id, __entry->xid, + __entry->auth, __entry->rslack, __entry->ralign, + __entry->verfsize) +); + DECLARE_EVENT_CLASS(rpcgss_svc_seqno_class, TP_PROTO( __be32 xid, @@ -371,6 +449,7 @@ TRACE_EVENT(rpcgss_upcall_result, TRACE_EVENT(rpcgss_context, TP_PROTO( + u32 window_size, unsigned long expiry, unsigned long now, unsigned int timeout, @@ -378,12 +457,13 @@ TRACE_EVENT(rpcgss_context, const u8 *data ), - TP_ARGS(expiry, now, timeout, len, data), + TP_ARGS(window_size, expiry, now, timeout, len, data), TP_STRUCT__entry( __field(unsigned long, expiry) __field(unsigned long, now) __field(unsigned int, timeout) + __field(u32, window_size) __field(int, len) __string(acceptor, data) ), @@ -392,13 +472,14 @@ TRACE_EVENT(rpcgss_context, __entry->expiry = expiry; __entry->now = now; __entry->timeout = timeout; + __entry->window_size = window_size; __entry->len = len; strncpy(__get_str(acceptor), data, len); ), - TP_printk("gc_expiry=%lu now=%lu timeout=%u acceptor=%.*s", - __entry->expiry, __entry->now, __entry->timeout, - __entry->len, __get_str(acceptor)) + TP_printk("win_size=%u expiry=%lu now=%lu timeout=%u acceptor=%.*s", + __entry->window_size, __entry->expiry, __entry->now, + __entry->timeout, __entry->len, __get_str(acceptor)) ); diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 132c3c778a43..0f05a6e2b9cb 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -380,12 +380,8 @@ TRACE_EVENT(xprtrdma_inline_thresh, DEFINE_CONN_EVENT(connect); DEFINE_CONN_EVENT(disconnect); -DEFINE_CONN_EVENT(flush_dct); -DEFINE_RXPRT_EVENT(xprtrdma_create); -DEFINE_RXPRT_EVENT(xprtrdma_op_destroy); DEFINE_RXPRT_EVENT(xprtrdma_op_inject_dsc); -DEFINE_RXPRT_EVENT(xprtrdma_op_close); DEFINE_RXPRT_EVENT(xprtrdma_op_setport); TRACE_EVENT(xprtrdma_op_connect, @@ -1279,38 +1275,42 @@ TRACE_EVENT(xprtrdma_leaked_rep, ** Server-side RPC/RDMA events **/ -DECLARE_EVENT_CLASS(svcrdma_xprt_event, +DECLARE_EVENT_CLASS(svcrdma_accept_class, TP_PROTO( - const struct svc_xprt *xprt + const struct svcxprt_rdma *rdma, + long status ), - TP_ARGS(xprt), + TP_ARGS(rdma, status), TP_STRUCT__entry( - __field(const void *, xprt) - __string(addr, xprt->xpt_remotebuf) + __field(long, status) + __string(addr, rdma->sc_xprt.xpt_remotebuf) ), TP_fast_assign( - __entry->xprt = xprt; - __assign_str(addr, xprt->xpt_remotebuf); + __entry->status = status; + __assign_str(addr, rdma->sc_xprt.xpt_remotebuf); ), - TP_printk("xprt=%p addr=%s", - __entry->xprt, __get_str(addr) + TP_printk("addr=%s status=%ld", + __get_str(addr), __entry->status ) ); -#define DEFINE_XPRT_EVENT(name) \ - DEFINE_EVENT(svcrdma_xprt_event, svcrdma_xprt_##name, \ - TP_PROTO( \ - const struct svc_xprt *xprt \ - ), \ - TP_ARGS(xprt)) +#define DEFINE_ACCEPT_EVENT(name) \ + DEFINE_EVENT(svcrdma_accept_class, svcrdma_##name##_err, \ + TP_PROTO( \ + const struct svcxprt_rdma *rdma, \ + long status \ + ), \ + TP_ARGS(rdma, status)) -DEFINE_XPRT_EVENT(accept); -DEFINE_XPRT_EVENT(fail); -DEFINE_XPRT_EVENT(free); +DEFINE_ACCEPT_EVENT(pd); +DEFINE_ACCEPT_EVENT(qp); +DEFINE_ACCEPT_EVENT(fabric); +DEFINE_ACCEPT_EVENT(initdepth); +DEFINE_ACCEPT_EVENT(accept); TRACE_DEFINE_ENUM(RDMA_MSG); TRACE_DEFINE_ENUM(RDMA_NOMSG); @@ -1355,7 +1355,7 @@ TRACE_EVENT(svcrdma_decode_rqst, show_rpcrdma_proc(__entry->proc), __entry->hdrlen) ); -TRACE_EVENT(svcrdma_decode_short, +TRACE_EVENT(svcrdma_decode_short_err, TP_PROTO( unsigned int hdrlen ), @@ -1399,7 +1399,8 @@ DECLARE_EVENT_CLASS(svcrdma_badreq_event, ); #define DEFINE_BADREQ_EVENT(name) \ - DEFINE_EVENT(svcrdma_badreq_event, svcrdma_decode_##name,\ + DEFINE_EVENT(svcrdma_badreq_event, \ + svcrdma_decode_##name##_err, \ TP_PROTO( \ __be32 *p \ ), \ @@ -1583,28 +1584,117 @@ DECLARE_EVENT_CLASS(svcrdma_dma_map_class, DEFINE_SVC_DMA_EVENT(dma_map_page); DEFINE_SVC_DMA_EVENT(dma_unmap_page); -TRACE_EVENT(svcrdma_dma_map_rwctx, +TRACE_EVENT(svcrdma_dma_map_rw_err, TP_PROTO( const struct svcxprt_rdma *rdma, + unsigned int nents, int status ), - TP_ARGS(rdma, status), + TP_ARGS(rdma, nents, status), TP_STRUCT__entry( __field(int, status) + __field(unsigned int, nents) __string(device, rdma->sc_cm_id->device->name) __string(addr, rdma->sc_xprt.xpt_remotebuf) ), TP_fast_assign( __entry->status = status; + __entry->nents = nents; + __assign_str(device, rdma->sc_cm_id->device->name); + __assign_str(addr, rdma->sc_xprt.xpt_remotebuf); + ), + + TP_printk("addr=%s device=%s nents=%u status=%d", + __get_str(addr), __get_str(device), __entry->nents, + __entry->status + ) +); + +TRACE_EVENT(svcrdma_no_rwctx_err, + TP_PROTO( + const struct svcxprt_rdma *rdma, + unsigned int num_sges + ), + + TP_ARGS(rdma, num_sges), + + TP_STRUCT__entry( + __field(unsigned int, num_sges) + __string(device, rdma->sc_cm_id->device->name) + __string(addr, rdma->sc_xprt.xpt_remotebuf) + ), + + TP_fast_assign( + __entry->num_sges = num_sges; + __assign_str(device, rdma->sc_cm_id->device->name); + __assign_str(addr, rdma->sc_xprt.xpt_remotebuf); + ), + + TP_printk("addr=%s device=%s num_sges=%d", + __get_str(addr), __get_str(device), __entry->num_sges + ) +); + +TRACE_EVENT(svcrdma_page_overrun_err, + TP_PROTO( + const struct svcxprt_rdma *rdma, + const struct svc_rqst *rqst, + unsigned int pageno + ), + + TP_ARGS(rdma, rqst, pageno), + + TP_STRUCT__entry( + __field(unsigned int, pageno) + __field(u32, xid) + __string(device, rdma->sc_cm_id->device->name) + __string(addr, rdma->sc_xprt.xpt_remotebuf) + ), + + TP_fast_assign( + __entry->pageno = pageno; + __entry->xid = __be32_to_cpu(rqst->rq_xid); + __assign_str(device, rdma->sc_cm_id->device->name); + __assign_str(addr, rdma->sc_xprt.xpt_remotebuf); + ), + + TP_printk("addr=%s device=%s xid=0x%08x pageno=%u", __get_str(addr), + __get_str(device), __entry->xid, __entry->pageno + ) +); + +TRACE_EVENT(svcrdma_small_wrch_err, + TP_PROTO( + const struct svcxprt_rdma *rdma, + unsigned int remaining, + unsigned int seg_no, + unsigned int num_segs + ), + + TP_ARGS(rdma, remaining, seg_no, num_segs), + + TP_STRUCT__entry( + __field(unsigned int, remaining) + __field(unsigned int, seg_no) + __field(unsigned int, num_segs) + __string(device, rdma->sc_cm_id->device->name) + __string(addr, rdma->sc_xprt.xpt_remotebuf) + ), + + TP_fast_assign( + __entry->remaining = remaining; + __entry->seg_no = seg_no; + __entry->num_segs = num_segs; __assign_str(device, rdma->sc_cm_id->device->name); __assign_str(addr, rdma->sc_xprt.xpt_remotebuf); ), - TP_printk("addr=%s device=%s status=%d", - __get_str(addr), __get_str(device), __entry->status + TP_printk("addr=%s device=%s remaining=%u seg_no=%u num_segs=%u", + __get_str(addr), __get_str(device), __entry->remaining, + __entry->seg_no, __entry->num_segs ) ); diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index ffd2215950dc..6a12935b8b14 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -14,14 +14,50 @@ #include <linux/net.h> #include <linux/tracepoint.h> -DECLARE_EVENT_CLASS(xdr_buf_class, +TRACE_DEFINE_ENUM(SOCK_STREAM); +TRACE_DEFINE_ENUM(SOCK_DGRAM); +TRACE_DEFINE_ENUM(SOCK_RAW); +TRACE_DEFINE_ENUM(SOCK_RDM); +TRACE_DEFINE_ENUM(SOCK_SEQPACKET); +TRACE_DEFINE_ENUM(SOCK_DCCP); +TRACE_DEFINE_ENUM(SOCK_PACKET); + +#define show_socket_type(type) \ + __print_symbolic(type, \ + { SOCK_STREAM, "STREAM" }, \ + { SOCK_DGRAM, "DGRAM" }, \ + { SOCK_RAW, "RAW" }, \ + { SOCK_RDM, "RDM" }, \ + { SOCK_SEQPACKET, "SEQPACKET" }, \ + { SOCK_DCCP, "DCCP" }, \ + { SOCK_PACKET, "PACKET" }) + +/* This list is known to be incomplete, add new enums as needed. */ +TRACE_DEFINE_ENUM(AF_UNSPEC); +TRACE_DEFINE_ENUM(AF_UNIX); +TRACE_DEFINE_ENUM(AF_LOCAL); +TRACE_DEFINE_ENUM(AF_INET); +TRACE_DEFINE_ENUM(AF_INET6); + +#define rpc_show_address_family(family) \ + __print_symbolic(family, \ + { AF_UNSPEC, "AF_UNSPEC" }, \ + { AF_UNIX, "AF_UNIX" }, \ + { AF_LOCAL, "AF_LOCAL" }, \ + { AF_INET, "AF_INET" }, \ + { AF_INET6, "AF_INET6" }) + +DECLARE_EVENT_CLASS(rpc_xdr_buf_class, TP_PROTO( + const struct rpc_task *task, const struct xdr_buf *xdr ), - TP_ARGS(xdr), + TP_ARGS(task, xdr), TP_STRUCT__entry( + __field(unsigned int, task_id) + __field(unsigned int, client_id) __field(const void *, head_base) __field(size_t, head_len) __field(const void *, tail_base) @@ -31,6 +67,8 @@ DECLARE_EVENT_CLASS(xdr_buf_class, ), TP_fast_assign( + __entry->task_id = task->tk_pid; + __entry->client_id = task->tk_client->cl_clid; __entry->head_base = xdr->head[0].iov_base; __entry->head_len = xdr->head[0].iov_len; __entry->tail_base = xdr->tail[0].iov_base; @@ -39,23 +77,137 @@ DECLARE_EVENT_CLASS(xdr_buf_class, __entry->msg_len = xdr->len; ), - TP_printk("head=[%p,%zu] page=%u tail=[%p,%zu] len=%u", + TP_printk("task:%u@%u head=[%p,%zu] page=%u tail=[%p,%zu] len=%u", + __entry->task_id, __entry->client_id, __entry->head_base, __entry->head_len, __entry->page_len, __entry->tail_base, __entry->tail_len, __entry->msg_len ) ); -#define DEFINE_XDRBUF_EVENT(name) \ - DEFINE_EVENT(xdr_buf_class, name, \ +#define DEFINE_RPCXDRBUF_EVENT(name) \ + DEFINE_EVENT(rpc_xdr_buf_class, \ + rpc_xdr_##name, \ TP_PROTO( \ + const struct rpc_task *task, \ const struct xdr_buf *xdr \ ), \ - TP_ARGS(xdr)) + TP_ARGS(task, xdr)) + +DEFINE_RPCXDRBUF_EVENT(sendto); +DEFINE_RPCXDRBUF_EVENT(recvfrom); +DEFINE_RPCXDRBUF_EVENT(reply_pages); + + +DECLARE_EVENT_CLASS(rpc_clnt_class, + TP_PROTO( + const struct rpc_clnt *clnt + ), + + TP_ARGS(clnt), + + TP_STRUCT__entry( + __field(unsigned int, client_id) + ), + + TP_fast_assign( + __entry->client_id = clnt->cl_clid; + ), + + TP_printk("clid=%u", __entry->client_id) +); + +#define DEFINE_RPC_CLNT_EVENT(name) \ + DEFINE_EVENT(rpc_clnt_class, \ + rpc_clnt_##name, \ + TP_PROTO( \ + const struct rpc_clnt *clnt \ + ), \ + TP_ARGS(clnt)) + +DEFINE_RPC_CLNT_EVENT(free); +DEFINE_RPC_CLNT_EVENT(killall); +DEFINE_RPC_CLNT_EVENT(shutdown); +DEFINE_RPC_CLNT_EVENT(release); +DEFINE_RPC_CLNT_EVENT(replace_xprt); +DEFINE_RPC_CLNT_EVENT(replace_xprt_err); + +TRACE_EVENT(rpc_clnt_new, + TP_PROTO( + const struct rpc_clnt *clnt, + const struct rpc_xprt *xprt, + const char *program, + const char *server + ), + + TP_ARGS(clnt, xprt, program, server), + + TP_STRUCT__entry( + __field(unsigned int, client_id) + __string(addr, xprt->address_strings[RPC_DISPLAY_ADDR]) + __string(port, xprt->address_strings[RPC_DISPLAY_PORT]) + __string(program, program) + __string(server, server) + ), + + TP_fast_assign( + __entry->client_id = clnt->cl_clid; + __assign_str(addr, xprt->address_strings[RPC_DISPLAY_ADDR]); + __assign_str(port, xprt->address_strings[RPC_DISPLAY_PORT]); + __assign_str(program, program) + __assign_str(server, server) + ), + + TP_printk("client=%u peer=[%s]:%s program=%s server=%s", + __entry->client_id, __get_str(addr), __get_str(port), + __get_str(program), __get_str(server)) +); + +TRACE_EVENT(rpc_clnt_new_err, + TP_PROTO( + const char *program, + const char *server, + int error + ), + + TP_ARGS(program, server, error), + + TP_STRUCT__entry( + __field(int, error) + __string(program, program) + __string(server, server) + ), + + TP_fast_assign( + __entry->error = error; + __assign_str(program, program) + __assign_str(server, server) + ), + + TP_printk("program=%s server=%s error=%d", + __get_str(program), __get_str(server), __entry->error) +); + +TRACE_EVENT(rpc_clnt_clone_err, + TP_PROTO( + const struct rpc_clnt *clnt, + int error + ), + + TP_ARGS(clnt, error), + + TP_STRUCT__entry( + __field(unsigned int, client_id) + __field(int, error) + ), + + TP_fast_assign( + __entry->client_id = clnt->cl_clid; + __entry->error = error; + ), + + TP_printk("client=%u error=%d", __entry->client_id, __entry->error) +); -DEFINE_XDRBUF_EVENT(xprt_sendto); -DEFINE_XDRBUF_EVENT(xprt_recvfrom); -DEFINE_XDRBUF_EVENT(svc_recvfrom); -DEFINE_XDRBUF_EVENT(svc_sendto); TRACE_DEFINE_ENUM(RPC_AUTH_OK); TRACE_DEFINE_ENUM(RPC_AUTH_BADCRED); @@ -142,29 +294,35 @@ TRACE_EVENT(rpc_request, TRACE_DEFINE_ENUM(RPC_TASK_ASYNC); TRACE_DEFINE_ENUM(RPC_TASK_SWAPPER); +TRACE_DEFINE_ENUM(RPC_TASK_NULLCREDS); TRACE_DEFINE_ENUM(RPC_CALL_MAJORSEEN); TRACE_DEFINE_ENUM(RPC_TASK_ROOTCREDS); TRACE_DEFINE_ENUM(RPC_TASK_DYNAMIC); +TRACE_DEFINE_ENUM(RPC_TASK_NO_ROUND_ROBIN); TRACE_DEFINE_ENUM(RPC_TASK_SOFT); TRACE_DEFINE_ENUM(RPC_TASK_SOFTCONN); TRACE_DEFINE_ENUM(RPC_TASK_SENT); TRACE_DEFINE_ENUM(RPC_TASK_TIMEOUT); TRACE_DEFINE_ENUM(RPC_TASK_NOCONNECT); TRACE_DEFINE_ENUM(RPC_TASK_NO_RETRANS_TIMEOUT); +TRACE_DEFINE_ENUM(RPC_TASK_CRED_NOREF); #define rpc_show_task_flags(flags) \ __print_flags(flags, "|", \ { RPC_TASK_ASYNC, "ASYNC" }, \ { RPC_TASK_SWAPPER, "SWAPPER" }, \ + { RPC_TASK_NULLCREDS, "NULLCREDS" }, \ { RPC_CALL_MAJORSEEN, "MAJORSEEN" }, \ { RPC_TASK_ROOTCREDS, "ROOTCREDS" }, \ { RPC_TASK_DYNAMIC, "DYNAMIC" }, \ + { RPC_TASK_NO_ROUND_ROBIN, "NO_ROUND_ROBIN" }, \ { RPC_TASK_SOFT, "SOFT" }, \ { RPC_TASK_SOFTCONN, "SOFTCONN" }, \ { RPC_TASK_SENT, "SENT" }, \ { RPC_TASK_TIMEOUT, "TIMEOUT" }, \ { RPC_TASK_NOCONNECT, "NOCONNECT" }, \ - { RPC_TASK_NO_RETRANS_TIMEOUT, "NORTO" }) + { RPC_TASK_NO_RETRANS_TIMEOUT, "NORTO" }, \ + { RPC_TASK_CRED_NOREF, "CRED_NOREF" }) TRACE_DEFINE_ENUM(RPC_TASK_RUNNING); TRACE_DEFINE_ENUM(RPC_TASK_QUEUED); @@ -359,6 +517,34 @@ DEFINE_RPC_REPLY_EVENT(stale_creds); DEFINE_RPC_REPLY_EVENT(bad_creds); DEFINE_RPC_REPLY_EVENT(auth_tooweak); +TRACE_EVENT(rpc_call_rpcerror, + TP_PROTO( + const struct rpc_task *task, + int tk_status, + int rpc_status + ), + + TP_ARGS(task, tk_status, rpc_status), + + TP_STRUCT__entry( + __field(unsigned int, task_id) + __field(unsigned int, client_id) + __field(int, tk_status) + __field(int, rpc_status) + ), + + TP_fast_assign( + __entry->client_id = task->tk_client->cl_clid; + __entry->task_id = task->tk_pid; + __entry->tk_status = tk_status; + __entry->rpc_status = rpc_status; + ), + + TP_printk("task:%u@%u tk_status=%d rpc_status=%d", + __entry->task_id, __entry->client_id, + __entry->tk_status, __entry->rpc_status) +); + TRACE_EVENT(rpc_stats_latency, TP_PROTO( @@ -526,43 +712,6 @@ TRACE_EVENT(rpc_xdr_alignment, ) ); -TRACE_EVENT(rpc_reply_pages, - TP_PROTO( - const struct rpc_rqst *req - ), - - TP_ARGS(req), - - TP_STRUCT__entry( - __field(unsigned int, task_id) - __field(unsigned int, client_id) - __field(const void *, head_base) - __field(size_t, head_len) - __field(const void *, tail_base) - __field(size_t, tail_len) - __field(unsigned int, page_len) - ), - - TP_fast_assign( - __entry->task_id = req->rq_task->tk_pid; - __entry->client_id = req->rq_task->tk_client->cl_clid; - - __entry->head_base = req->rq_rcv_buf.head[0].iov_base; - __entry->head_len = req->rq_rcv_buf.head[0].iov_len; - __entry->page_len = req->rq_rcv_buf.page_len; - __entry->tail_base = req->rq_rcv_buf.tail[0].iov_base; - __entry->tail_len = req->rq_rcv_buf.tail[0].iov_len; - ), - - TP_printk( - "task:%u@%u xdr=[%p,%zu]/%u/[%p,%zu]\n", - __entry->task_id, __entry->client_id, - __entry->head_base, __entry->head_len, - __entry->page_len, - __entry->tail_base, __entry->tail_len - ) -); - /* * First define the enums in the below macros to be exported to userspace * via TRACE_DEFINE_ENUM(). @@ -575,9 +724,9 @@ TRACE_EVENT(rpc_reply_pages, #define RPC_SHOW_SOCKET \ EM( SS_FREE, "FREE" ) \ EM( SS_UNCONNECTED, "UNCONNECTED" ) \ - EM( SS_CONNECTING, "CONNECTING," ) \ - EM( SS_CONNECTED, "CONNECTED," ) \ - EMe(SS_DISCONNECTING, "DISCONNECTING" ) + EM( SS_CONNECTING, "CONNECTING" ) \ + EM( SS_CONNECTED, "CONNECTED" ) \ + EMe( SS_DISCONNECTING, "DISCONNECTING" ) #define rpc_show_socket_state(state) \ __print_symbolic(state, RPC_SHOW_SOCKET) @@ -719,6 +868,69 @@ DEFINE_RPC_SOCKET_EVENT_DONE(rpc_socket_reset_connection); DEFINE_RPC_SOCKET_EVENT(rpc_socket_close); DEFINE_RPC_SOCKET_EVENT(rpc_socket_shutdown); +TRACE_DEFINE_ENUM(XPRT_LOCKED); +TRACE_DEFINE_ENUM(XPRT_CONNECTED); +TRACE_DEFINE_ENUM(XPRT_CONNECTING); +TRACE_DEFINE_ENUM(XPRT_CLOSE_WAIT); +TRACE_DEFINE_ENUM(XPRT_BOUND); +TRACE_DEFINE_ENUM(XPRT_BINDING); +TRACE_DEFINE_ENUM(XPRT_CLOSING); +TRACE_DEFINE_ENUM(XPRT_CONGESTED); +TRACE_DEFINE_ENUM(XPRT_CWND_WAIT); +TRACE_DEFINE_ENUM(XPRT_WRITE_SPACE); + +#define rpc_show_xprt_state(x) \ + __print_flags(x, "|", \ + { (1UL << XPRT_LOCKED), "LOCKED"}, \ + { (1UL << XPRT_CONNECTED), "CONNECTED"}, \ + { (1UL << XPRT_CONNECTING), "CONNECTING"}, \ + { (1UL << XPRT_CLOSE_WAIT), "CLOSE_WAIT"}, \ + { (1UL << XPRT_BOUND), "BOUND"}, \ + { (1UL << XPRT_BINDING), "BINDING"}, \ + { (1UL << XPRT_CLOSING), "CLOSING"}, \ + { (1UL << XPRT_CONGESTED), "CONGESTED"}, \ + { (1UL << XPRT_CWND_WAIT), "CWND_WAIT"}, \ + { (1UL << XPRT_WRITE_SPACE), "WRITE_SPACE"}) + +DECLARE_EVENT_CLASS(rpc_xprt_lifetime_class, + TP_PROTO( + const struct rpc_xprt *xprt + ), + + TP_ARGS(xprt), + + TP_STRUCT__entry( + __field(unsigned long, state) + __string(addr, xprt->address_strings[RPC_DISPLAY_ADDR]) + __string(port, xprt->address_strings[RPC_DISPLAY_PORT]) + ), + + TP_fast_assign( + __entry->state = xprt->state; + __assign_str(addr, xprt->address_strings[RPC_DISPLAY_ADDR]); + __assign_str(port, xprt->address_strings[RPC_DISPLAY_PORT]); + ), + + TP_printk("peer=[%s]:%s state=%s", + __get_str(addr), __get_str(port), + rpc_show_xprt_state(__entry->state)) +); + +#define DEFINE_RPC_XPRT_LIFETIME_EVENT(name) \ + DEFINE_EVENT(rpc_xprt_lifetime_class, \ + xprt_##name, \ + TP_PROTO( \ + const struct rpc_xprt *xprt \ + ), \ + TP_ARGS(xprt)) + +DEFINE_RPC_XPRT_LIFETIME_EVENT(create); +DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_auto); +DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_done); +DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_force); +DEFINE_RPC_XPRT_LIFETIME_EVENT(disconnect_cleanup); +DEFINE_RPC_XPRT_LIFETIME_EVENT(destroy); + DECLARE_EVENT_CLASS(rpc_xprt_event, TP_PROTO( const struct rpc_xprt *xprt, @@ -990,6 +1202,54 @@ TRACE_EVENT(xs_stream_read_request, __entry->copied, __entry->reclen, __entry->offset) ); + +DECLARE_EVENT_CLASS(svc_xdr_buf_class, + TP_PROTO( + const struct svc_rqst *rqst, + const struct xdr_buf *xdr + ), + + TP_ARGS(rqst, xdr), + + TP_STRUCT__entry( + __field(u32, xid) + __field(const void *, head_base) + __field(size_t, head_len) + __field(const void *, tail_base) + __field(size_t, tail_len) + __field(unsigned int, page_len) + __field(unsigned int, msg_len) + ), + + TP_fast_assign( + __entry->xid = be32_to_cpu(rqst->rq_xid); + __entry->head_base = xdr->head[0].iov_base; + __entry->head_len = xdr->head[0].iov_len; + __entry->tail_base = xdr->tail[0].iov_base; + __entry->tail_len = xdr->tail[0].iov_len; + __entry->page_len = xdr->page_len; + __entry->msg_len = xdr->len; + ), + + TP_printk("xid=0x%08x head=[%p,%zu] page=%u tail=[%p,%zu] len=%u", + __entry->xid, + __entry->head_base, __entry->head_len, __entry->page_len, + __entry->tail_base, __entry->tail_len, __entry->msg_len + ) +); + +#define DEFINE_SVCXDRBUF_EVENT(name) \ + DEFINE_EVENT(svc_xdr_buf_class, \ + svc_xdr_##name, \ + TP_PROTO( \ + const struct svc_rqst *rqst, \ + const struct xdr_buf *xdr \ + ), \ + TP_ARGS(rqst, xdr)) + +DEFINE_SVCXDRBUF_EVENT(recvfrom); +DEFINE_SVCXDRBUF_EVENT(sendto); + #define show_rqstp_flags(flags) \ __print_flags(flags, "|", \ { (1UL << RQ_SECURE), "RQ_SECURE"}, \ @@ -1024,6 +1284,17 @@ TRACE_EVENT(svc_recv, show_rqstp_flags(__entry->flags)) ); +TRACE_DEFINE_ENUM(SVC_GARBAGE); +TRACE_DEFINE_ENUM(SVC_SYSERR); +TRACE_DEFINE_ENUM(SVC_VALID); +TRACE_DEFINE_ENUM(SVC_NEGATIVE); +TRACE_DEFINE_ENUM(SVC_OK); +TRACE_DEFINE_ENUM(SVC_DROP); +TRACE_DEFINE_ENUM(SVC_CLOSE); +TRACE_DEFINE_ENUM(SVC_DENIED); +TRACE_DEFINE_ENUM(SVC_PENDING); +TRACE_DEFINE_ENUM(SVC_COMPLETE); + #define svc_show_status(status) \ __print_symbolic(status, \ { SVC_GARBAGE, "SVC_GARBAGE" }, \ @@ -1167,28 +1438,54 @@ DEFINE_EVENT(svc_rqst_status, svc_send, { (1UL << XPT_KILL_TEMP), "XPT_KILL_TEMP"}, \ { (1UL << XPT_CONG_CTRL), "XPT_CONG_CTRL"}) +TRACE_EVENT(svc_xprt_create_err, + TP_PROTO( + const char *program, + const char *protocol, + struct sockaddr *sap, + const struct svc_xprt *xprt + ), + + TP_ARGS(program, protocol, sap, xprt), + + TP_STRUCT__entry( + __field(long, error) + __string(program, program) + __string(protocol, protocol) + __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + ), + + TP_fast_assign( + __entry->error = PTR_ERR(xprt); + __assign_str(program, program); + __assign_str(protocol, protocol); + memcpy(__entry->addr, sap, sizeof(__entry->addr)); + ), + + TP_printk("addr=%pISpc program=%s protocol=%s error=%ld", + __entry->addr, __get_str(program), __get_str(protocol), + __entry->error) +); + TRACE_EVENT(svc_xprt_do_enqueue, TP_PROTO(struct svc_xprt *xprt, struct svc_rqst *rqst), TP_ARGS(xprt, rqst), TP_STRUCT__entry( - __field(struct svc_xprt *, xprt) __field(int, pid) __field(unsigned long, flags) __string(addr, xprt->xpt_remotebuf) ), TP_fast_assign( - __entry->xprt = xprt; __entry->pid = rqst? rqst->rq_task->pid : 0; __entry->flags = xprt->xpt_flags; __assign_str(addr, xprt->xpt_remotebuf); ), - TP_printk("xprt=%p addr=%s pid=%d flags=%s", - __entry->xprt, __get_str(addr), - __entry->pid, show_svc_xprt_flags(__entry->flags)) + TP_printk("addr=%s pid=%d flags=%s", __get_str(addr), + __entry->pid, show_svc_xprt_flags(__entry->flags)) ); DECLARE_EVENT_CLASS(svc_xprt_event, @@ -1197,25 +1494,55 @@ DECLARE_EVENT_CLASS(svc_xprt_event, TP_ARGS(xprt), TP_STRUCT__entry( - __field(struct svc_xprt *, xprt) __field(unsigned long, flags) __string(addr, xprt->xpt_remotebuf) ), TP_fast_assign( - __entry->xprt = xprt; __entry->flags = xprt->xpt_flags; __assign_str(addr, xprt->xpt_remotebuf); ), - TP_printk("xprt=%p addr=%s flags=%s", - __entry->xprt, __get_str(addr), - show_svc_xprt_flags(__entry->flags)) + TP_printk("addr=%s flags=%s", __get_str(addr), + show_svc_xprt_flags(__entry->flags)) ); -DEFINE_EVENT(svc_xprt_event, svc_xprt_no_write_space, - TP_PROTO(struct svc_xprt *xprt), - TP_ARGS(xprt)); +#define DEFINE_SVC_XPRT_EVENT(name) \ + DEFINE_EVENT(svc_xprt_event, svc_xprt_##name, \ + TP_PROTO( \ + struct svc_xprt *xprt \ + ), \ + TP_ARGS(xprt)) + +DEFINE_SVC_XPRT_EVENT(no_write_space); +DEFINE_SVC_XPRT_EVENT(close); +DEFINE_SVC_XPRT_EVENT(detach); +DEFINE_SVC_XPRT_EVENT(free); + +TRACE_EVENT(svc_xprt_accept, + TP_PROTO( + const struct svc_xprt *xprt, + const char *service + ), + + TP_ARGS(xprt, service), + + TP_STRUCT__entry( + __string(addr, xprt->xpt_remotebuf) + __string(protocol, xprt->xpt_class->xcl_name) + __string(service, service) + ), + + TP_fast_assign( + __assign_str(addr, xprt->xpt_remotebuf); + __assign_str(protocol, xprt->xpt_class->xcl_name) + __assign_str(service, service); + ), + + TP_printk("addr=%s protocol=%s service=%s", + __get_str(addr), __get_str(protocol), __get_str(service) + ) +); TRACE_EVENT(svc_xprt_dequeue, TP_PROTO(struct svc_rqst *rqst), @@ -1223,24 +1550,20 @@ TRACE_EVENT(svc_xprt_dequeue, TP_ARGS(rqst), TP_STRUCT__entry( - __field(struct svc_xprt *, xprt) __field(unsigned long, flags) __field(unsigned long, wakeup) __string(addr, rqst->rq_xprt->xpt_remotebuf) ), TP_fast_assign( - __entry->xprt = rqst->rq_xprt; __entry->flags = rqst->rq_xprt->xpt_flags; __entry->wakeup = ktime_to_us(ktime_sub(ktime_get(), rqst->rq_qtime)); __assign_str(addr, rqst->rq_xprt->xpt_remotebuf); ), - TP_printk("xprt=%p addr=%s flags=%s wakeup-us=%lu", - __entry->xprt, __get_str(addr), - show_svc_xprt_flags(__entry->flags), - __entry->wakeup) + TP_printk("addr=%s flags=%s wakeup-us=%lu", __get_str(addr), + show_svc_xprt_flags(__entry->flags), __entry->wakeup) ); TRACE_EVENT(svc_wake_up, @@ -1265,21 +1588,18 @@ TRACE_EVENT(svc_handle_xprt, TP_ARGS(xprt, len), TP_STRUCT__entry( - __field(struct svc_xprt *, xprt) __field(int, len) __field(unsigned long, flags) __string(addr, xprt->xpt_remotebuf) ), TP_fast_assign( - __entry->xprt = xprt; __entry->len = len; __entry->flags = xprt->xpt_flags; __assign_str(addr, xprt->xpt_remotebuf); ), - TP_printk("xprt=%p addr=%s len=%d flags=%s", - __entry->xprt, __get_str(addr), + TP_printk("addr=%s len=%d flags=%s", __get_str(addr), __entry->len, show_svc_xprt_flags(__entry->flags)) ); @@ -1313,27 +1633,221 @@ DECLARE_EVENT_CLASS(svc_deferred_event, TP_ARGS(dr), TP_STRUCT__entry( + __field(const void *, dr) __field(u32, xid) __string(addr, dr->xprt->xpt_remotebuf) ), TP_fast_assign( + __entry->dr = dr; __entry->xid = be32_to_cpu(*(__be32 *)(dr->args + (dr->xprt_hlen>>2))); __assign_str(addr, dr->xprt->xpt_remotebuf); ), - TP_printk("addr=%s xid=0x%08x", __get_str(addr), __entry->xid) + TP_printk("addr=%s dr=%p xid=0x%08x", __get_str(addr), __entry->dr, + __entry->xid) ); + #define DEFINE_SVC_DEFERRED_EVENT(name) \ - DEFINE_EVENT(svc_deferred_event, svc_##name##_deferred, \ + DEFINE_EVENT(svc_deferred_event, svc_defer_##name, \ TP_PROTO( \ const struct svc_deferred_req *dr \ ), \ TP_ARGS(dr)) DEFINE_SVC_DEFERRED_EVENT(drop); -DEFINE_SVC_DEFERRED_EVENT(revisit); +DEFINE_SVC_DEFERRED_EVENT(queue); +DEFINE_SVC_DEFERRED_EVENT(recv); + +TRACE_EVENT(svcsock_new_socket, + TP_PROTO( + const struct socket *socket + ), + + TP_ARGS(socket), + + TP_STRUCT__entry( + __field(unsigned long, type) + __field(unsigned long, family) + __field(bool, listener) + ), + + TP_fast_assign( + __entry->type = socket->type; + __entry->family = socket->sk->sk_family; + __entry->listener = (socket->sk->sk_state == TCP_LISTEN); + ), + + TP_printk("type=%s family=%s%s", + show_socket_type(__entry->type), + rpc_show_address_family(__entry->family), + __entry->listener ? " (listener)" : "" + ) +); + +TRACE_EVENT(svcsock_marker, + TP_PROTO( + const struct svc_xprt *xprt, + __be32 marker + ), + + TP_ARGS(xprt, marker), + + TP_STRUCT__entry( + __field(unsigned int, length) + __field(bool, last) + __string(addr, xprt->xpt_remotebuf) + ), + + TP_fast_assign( + __entry->length = be32_to_cpu(marker) & RPC_FRAGMENT_SIZE_MASK; + __entry->last = be32_to_cpu(marker) & RPC_LAST_STREAM_FRAGMENT; + __assign_str(addr, xprt->xpt_remotebuf); + ), + + TP_printk("addr=%s length=%u%s", __get_str(addr), + __entry->length, __entry->last ? " (last)" : "") +); + +DECLARE_EVENT_CLASS(svcsock_class, + TP_PROTO( + const struct svc_xprt *xprt, + ssize_t result + ), + + TP_ARGS(xprt, result), + + TP_STRUCT__entry( + __field(ssize_t, result) + __field(unsigned long, flags) + __string(addr, xprt->xpt_remotebuf) + ), + + TP_fast_assign( + __entry->result = result; + __entry->flags = xprt->xpt_flags; + __assign_str(addr, xprt->xpt_remotebuf); + ), + + TP_printk("addr=%s result=%zd flags=%s", __get_str(addr), + __entry->result, show_svc_xprt_flags(__entry->flags) + ) +); + +#define DEFINE_SVCSOCK_EVENT(name) \ + DEFINE_EVENT(svcsock_class, svcsock_##name, \ + TP_PROTO( \ + const struct svc_xprt *xprt, \ + ssize_t result \ + ), \ + TP_ARGS(xprt, result)) + +DEFINE_SVCSOCK_EVENT(udp_send); +DEFINE_SVCSOCK_EVENT(udp_recv); +DEFINE_SVCSOCK_EVENT(udp_recv_err); +DEFINE_SVCSOCK_EVENT(tcp_send); +DEFINE_SVCSOCK_EVENT(tcp_recv); +DEFINE_SVCSOCK_EVENT(tcp_recv_eagain); +DEFINE_SVCSOCK_EVENT(tcp_recv_err); +DEFINE_SVCSOCK_EVENT(data_ready); +DEFINE_SVCSOCK_EVENT(write_space); + +TRACE_EVENT(svcsock_tcp_recv_short, + TP_PROTO( + const struct svc_xprt *xprt, + u32 expected, + u32 received + ), + + TP_ARGS(xprt, expected, received), + + TP_STRUCT__entry( + __field(u32, expected) + __field(u32, received) + __field(unsigned long, flags) + __string(addr, xprt->xpt_remotebuf) + ), + + TP_fast_assign( + __entry->expected = expected; + __entry->received = received; + __entry->flags = xprt->xpt_flags; + __assign_str(addr, xprt->xpt_remotebuf); + ), + + TP_printk("addr=%s flags=%s expected=%u received=%u", + __get_str(addr), show_svc_xprt_flags(__entry->flags), + __entry->expected, __entry->received + ) +); + +TRACE_EVENT(svcsock_tcp_state, + TP_PROTO( + const struct svc_xprt *xprt, + const struct socket *socket + ), + + TP_ARGS(xprt, socket), + + TP_STRUCT__entry( + __field(unsigned long, socket_state) + __field(unsigned long, sock_state) + __field(unsigned long, flags) + __string(addr, xprt->xpt_remotebuf) + ), + + TP_fast_assign( + __entry->socket_state = socket->state; + __entry->sock_state = socket->sk->sk_state; + __entry->flags = xprt->xpt_flags; + __assign_str(addr, xprt->xpt_remotebuf); + ), + + TP_printk("addr=%s state=%s sk_state=%s flags=%s", __get_str(addr), + rpc_show_socket_state(__entry->socket_state), + rpc_show_sock_state(__entry->sock_state), + show_svc_xprt_flags(__entry->flags) + ) +); + +DECLARE_EVENT_CLASS(svcsock_accept_class, + TP_PROTO( + const struct svc_xprt *xprt, + const char *service, + long status + ), + + TP_ARGS(xprt, service, status), + + TP_STRUCT__entry( + __field(long, status) + __string(service, service) + __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + ), + + TP_fast_assign( + __entry->status = status; + __assign_str(service, service); + memcpy(__entry->addr, &xprt->xpt_local, sizeof(__entry->addr)); + ), + + TP_printk("listener=%pISpc service=%s status=%ld", + __entry->addr, __get_str(service), __entry->status + ) +); + +#define DEFINE_ACCEPT_EVENT(name) \ + DEFINE_EVENT(svcsock_accept_class, svcsock_##name##_err, \ + TP_PROTO( \ + const struct svc_xprt *xprt, \ + const char *service, \ + long status \ + ), \ + TP_ARGS(xprt, service, status)) + +DEFINE_ACCEPT_EVENT(accept); +DEFINE_ACCEPT_EVENT(getpeername); DECLARE_EVENT_CLASS(cache_event, TP_PROTO( @@ -1368,6 +1882,86 @@ DEFINE_CACHE_EVENT(cache_entry_update); DEFINE_CACHE_EVENT(cache_entry_make_negative); DEFINE_CACHE_EVENT(cache_entry_no_listener); +DECLARE_EVENT_CLASS(register_class, + TP_PROTO( + const char *program, + const u32 version, + const int family, + const unsigned short protocol, + const unsigned short port, + int error + ), + + TP_ARGS(program, version, family, protocol, port, error), + + TP_STRUCT__entry( + __field(u32, version) + __field(unsigned long, family) + __field(unsigned short, protocol) + __field(unsigned short, port) + __field(int, error) + __string(program, program) + ), + + TP_fast_assign( + __entry->version = version; + __entry->family = family; + __entry->protocol = protocol; + __entry->port = port; + __entry->error = error; + __assign_str(program, program); + ), + + TP_printk("program=%sv%u proto=%s port=%u family=%s error=%d", + __get_str(program), __entry->version, + __entry->protocol == IPPROTO_UDP ? "udp" : "tcp", + __entry->port, rpc_show_address_family(__entry->family), + __entry->error + ) +); + +#define DEFINE_REGISTER_EVENT(name) \ + DEFINE_EVENT(register_class, svc_##name, \ + TP_PROTO( \ + const char *program, \ + const u32 version, \ + const int family, \ + const unsigned short protocol, \ + const unsigned short port, \ + int error \ + ), \ + TP_ARGS(program, version, family, protocol, \ + port, error)) + +DEFINE_REGISTER_EVENT(register); +DEFINE_REGISTER_EVENT(noregister); + +TRACE_EVENT(svc_unregister, + TP_PROTO( + const char *program, + const u32 version, + int error + ), + + TP_ARGS(program, version, error), + + TP_STRUCT__entry( + __field(u32, version) + __field(int, error) + __string(program, program) + ), + + TP_fast_assign( + __entry->version = version; + __entry->error = error; + __assign_str(program, program); + ), + + TP_printk("program=%sv%u error=%d", + __get_str(program), __entry->version, __entry->error + ) +); + #endif /* _TRACE_SUNRPC_H */ #include <trace/define_trace.h> diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 9fe72e4b1373..0c2349612e77 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -15,6 +15,8 @@ #include <linux/types.h> #include <linux/ioctl.h> +#define VHOST_FILE_UNBIND -1 + /* ioctls */ #define VHOST_VIRTIO 0xAF @@ -140,4 +142,6 @@ /* Get the max ring size. */ #define VHOST_VDPA_GET_VRING_NUM _IOR(VHOST_VIRTIO, 0x76, __u16) +/* Set event fd for config interrupt*/ +#define VHOST_VDPA_SET_CONFIG_CALL _IOW(VHOST_VIRTIO, 0x77, int) #endif diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h index ecc27a17401a..b052355ac7a3 100644 --- a/include/uapi/linux/virtio_ids.h +++ b/include/uapi/linux/virtio_ids.h @@ -44,6 +44,7 @@ #define VIRTIO_ID_VSOCK 19 /* virtio vsock transport */ #define VIRTIO_ID_CRYPTO 20 /* virtio crypto */ #define VIRTIO_ID_IOMMU 23 /* virtio IOMMU */ +#define VIRTIO_ID_MEM 24 /* virtio mem */ #define VIRTIO_ID_FS 26 /* virtio filesystem */ #define VIRTIO_ID_PMEM 27 /* virtio pmem */ #define VIRTIO_ID_MAC80211_HWSIM 29 /* virtio mac80211-hwsim */ diff --git a/include/uapi/linux/virtio_mem.h b/include/uapi/linux/virtio_mem.h new file mode 100644 index 000000000000..a9ffe041843c --- /dev/null +++ b/include/uapi/linux/virtio_mem.h @@ -0,0 +1,211 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ +/* + * Virtio Mem Device + * + * Copyright Red Hat, Inc. 2020 + * + * Authors: + * David Hildenbrand <david@redhat.com> + * + * This header is BSD licensed so anyone can use the definitions + * to implement compatible drivers/servers: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of IBM nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL IBM OR + * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF + * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, + * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT + * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#ifndef _LINUX_VIRTIO_MEM_H +#define _LINUX_VIRTIO_MEM_H + +#include <linux/types.h> +#include <linux/virtio_types.h> +#include <linux/virtio_ids.h> +#include <linux/virtio_config.h> + +/* + * Each virtio-mem device manages a dedicated region in physical address + * space. Each device can belong to a single NUMA node, multiple devices + * for a single NUMA node are possible. A virtio-mem device is like a + * "resizable DIMM" consisting of small memory blocks that can be plugged + * or unplugged. The device driver is responsible for (un)plugging memory + * blocks on demand. + * + * Virtio-mem devices can only operate on their assigned memory region in + * order to (un)plug memory. A device cannot (un)plug memory belonging to + * other devices. + * + * The "region_size" corresponds to the maximum amount of memory that can + * be provided by a device. The "size" corresponds to the amount of memory + * that is currently plugged. "requested_size" corresponds to a request + * from the device to the device driver to (un)plug blocks. The + * device driver should try to (un)plug blocks in order to reach the + * "requested_size". It is impossible to plug more memory than requested. + * + * The "usable_region_size" represents the memory region that can actually + * be used to (un)plug memory. It is always at least as big as the + * "requested_size" and will grow dynamically. It will only shrink when + * explicitly triggered (VIRTIO_MEM_REQ_UNPLUG). + * + * There are no guarantees what will happen if unplugged memory is + * read/written. Such memory should, in general, not be touched. E.g., + * even writing might succeed, but the values will simply be discarded at + * random points in time. + * + * It can happen that the device cannot process a request, because it is + * busy. The device driver has to retry later. + * + * Usually, during system resets all memory will get unplugged, so the + * device driver can start with a clean state. However, in specific + * scenarios (if the device is busy) it can happen that the device still + * has memory plugged. The device driver can request to unplug all memory + * (VIRTIO_MEM_REQ_UNPLUG) - which might take a while to succeed if the + * device is busy. + */ + +/* --- virtio-mem: feature bits --- */ + +/* node_id is an ACPI PXM and is valid */ +#define VIRTIO_MEM_F_ACPI_PXM 0 + + +/* --- virtio-mem: guest -> host requests --- */ + +/* request to plug memory blocks */ +#define VIRTIO_MEM_REQ_PLUG 0 +/* request to unplug memory blocks */ +#define VIRTIO_MEM_REQ_UNPLUG 1 +/* request to unplug all blocks and shrink the usable size */ +#define VIRTIO_MEM_REQ_UNPLUG_ALL 2 +/* request information about the plugged state of memory blocks */ +#define VIRTIO_MEM_REQ_STATE 3 + +struct virtio_mem_req_plug { + __virtio64 addr; + __virtio16 nb_blocks; + __virtio16 padding[3]; +}; + +struct virtio_mem_req_unplug { + __virtio64 addr; + __virtio16 nb_blocks; + __virtio16 padding[3]; +}; + +struct virtio_mem_req_state { + __virtio64 addr; + __virtio16 nb_blocks; + __virtio16 padding[3]; +}; + +struct virtio_mem_req { + __virtio16 type; + __virtio16 padding[3]; + + union { + struct virtio_mem_req_plug plug; + struct virtio_mem_req_unplug unplug; + struct virtio_mem_req_state state; + } u; +}; + + +/* --- virtio-mem: host -> guest response --- */ + +/* + * Request processed successfully, applicable for + * - VIRTIO_MEM_REQ_PLUG + * - VIRTIO_MEM_REQ_UNPLUG + * - VIRTIO_MEM_REQ_UNPLUG_ALL + * - VIRTIO_MEM_REQ_STATE + */ +#define VIRTIO_MEM_RESP_ACK 0 +/* + * Request denied - e.g. trying to plug more than requested, applicable for + * - VIRTIO_MEM_REQ_PLUG + */ +#define VIRTIO_MEM_RESP_NACK 1 +/* + * Request cannot be processed right now, try again later, applicable for + * - VIRTIO_MEM_REQ_PLUG + * - VIRTIO_MEM_REQ_UNPLUG + * - VIRTIO_MEM_REQ_UNPLUG_ALL + */ +#define VIRTIO_MEM_RESP_BUSY 2 +/* + * Error in request (e.g. addresses/alignment), applicable for + * - VIRTIO_MEM_REQ_PLUG + * - VIRTIO_MEM_REQ_UNPLUG + * - VIRTIO_MEM_REQ_STATE + */ +#define VIRTIO_MEM_RESP_ERROR 3 + + +/* State of memory blocks is "plugged" */ +#define VIRTIO_MEM_STATE_PLUGGED 0 +/* State of memory blocks is "unplugged" */ +#define VIRTIO_MEM_STATE_UNPLUGGED 1 +/* State of memory blocks is "mixed" */ +#define VIRTIO_MEM_STATE_MIXED 2 + +struct virtio_mem_resp_state { + __virtio16 state; +}; + +struct virtio_mem_resp { + __virtio16 type; + __virtio16 padding[3]; + + union { + struct virtio_mem_resp_state state; + } u; +}; + +/* --- virtio-mem: configuration --- */ + +struct virtio_mem_config { + /* Block size and alignment. Cannot change. */ + __u64 block_size; + /* Valid with VIRTIO_MEM_F_ACPI_PXM. Cannot change. */ + __u16 node_id; + __u8 padding[6]; + /* Start address of the memory region. Cannot change. */ + __u64 addr; + /* Region size (maximum). Cannot change. */ + __u64 region_size; + /* + * Currently usable region size. Can grow up to region_size. Can + * shrink due to VIRTIO_MEM_REQ_UNPLUG_ALL (in which case no config + * update will be sent). + */ + __u64 usable_region_size; + /* + * Currently used size. Changes due to plug/unplug requests, but no + * config updates will be sent. + */ + __u64 plugged_size; + /* Requested size. New plug requests cannot exceed it. Can change. */ + __u64 requested_size; +}; + +#endif /* _LINUX_VIRTIO_MEM_H */ diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h index 559f42e73315..476d3e5c0fe7 100644 --- a/include/uapi/linux/virtio_ring.h +++ b/include/uapi/linux/virtio_ring.h @@ -86,6 +86,13 @@ * at the end of the used ring. Guest should ignore the used->flags field. */ #define VIRTIO_RING_F_EVENT_IDX 29 +/* Alignment requirements for vring elements. + * When using pre-virtio 1.0 layout, these fall out naturally. + */ +#define VRING_AVAIL_ALIGN_SIZE 2 +#define VRING_USED_ALIGN_SIZE 4 +#define VRING_DESC_ALIGN_SIZE 16 + /* Virtio ring descriptors: 16 bytes. These can chain together via "next". */ struct vring_desc { /* Address (guest-physical). */ @@ -112,28 +119,47 @@ struct vring_used_elem { __virtio32 len; }; +typedef struct vring_used_elem __attribute__((aligned(VRING_USED_ALIGN_SIZE))) + vring_used_elem_t; + struct vring_used { __virtio16 flags; __virtio16 idx; - struct vring_used_elem ring[]; + vring_used_elem_t ring[]; }; +/* + * The ring element addresses are passed between components with different + * alignments assumptions. Thus, we might need to decrease the compiler-selected + * alignment, and so must use a typedef to make sure the aligned attribute + * actually takes hold: + * + * https://gcc.gnu.org/onlinedocs//gcc/Common-Type-Attributes.html#Common-Type-Attributes + * + * When used on a struct, or struct member, the aligned attribute can only + * increase the alignment; in order to decrease it, the packed attribute must + * be specified as well. When used as part of a typedef, the aligned attribute + * can both increase and decrease alignment, and specifying the packed + * attribute generates a warning. + */ +typedef struct vring_desc __attribute__((aligned(VRING_DESC_ALIGN_SIZE))) + vring_desc_t; +typedef struct vring_avail __attribute__((aligned(VRING_AVAIL_ALIGN_SIZE))) + vring_avail_t; +typedef struct vring_used __attribute__((aligned(VRING_USED_ALIGN_SIZE))) + vring_used_t; + struct vring { unsigned int num; - struct vring_desc *desc; + vring_desc_t *desc; - struct vring_avail *avail; + vring_avail_t *avail; - struct vring_used *used; + vring_used_t *used; }; -/* Alignment requirements for vring elements. - * When using pre-virtio 1.0 layout, these fall out naturally. - */ -#define VRING_AVAIL_ALIGN_SIZE 2 -#define VRING_USED_ALIGN_SIZE 4 -#define VRING_DESC_ALIGN_SIZE 16 +#ifndef VIRTIO_RING_NO_LEGACY /* The standard layout for the ring is a continuous chunk of memory which looks * like this. We assume num is a power of 2. @@ -181,6 +207,8 @@ static inline unsigned vring_size(unsigned int num, unsigned long align) + sizeof(__virtio16) * 3 + sizeof(struct vring_used_elem) * num; } +#endif /* VIRTIO_RING_NO_LEGACY */ + /* The following is used with USED_EVENT_IDX and AVAIL_EVENT_IDX */ /* Assuming a given event_idx value from the other side, if * we have just incremented index from old to new_idx, diff --git a/include/uapi/mtd/mtd-abi.h b/include/uapi/mtd/mtd-abi.h index 47ffe3208c27..4b48fbf7d343 100644 --- a/include/uapi/mtd/mtd-abi.h +++ b/include/uapi/mtd/mtd-abi.h @@ -104,6 +104,7 @@ struct mtd_write_req { #define MTD_BIT_WRITEABLE 0x800 /* Single bits can be flipped */ #define MTD_NO_ERASE 0x1000 /* No erase necessary */ #define MTD_POWERUP_LOCK 0x2000 /* Always locked after reset */ +#define MTD_SLC_ON_MLC_EMULATION 0x4000 /* Emulate SLC behavior on MLC NANDs */ /* Some common devices / combinations of capabilities */ #define MTD_CAP_ROM 0 |