diff options
Diffstat (limited to 'include/linux')
81 files changed, 2420 insertions, 621 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 99f96df83dd8..c749eef1daa1 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -57,6 +57,9 @@ static inline acpi_handle acpi_device_handle(struct acpi_device *adev) acpi_fwnode_handle(adev) : NULL) #define ACPI_HANDLE(dev) acpi_device_handle(ACPI_COMPANION(dev)) + +extern const struct fwnode_operations acpi_fwnode_ops; + static inline struct fwnode_handle *acpi_alloc_fwnode_static(void) { struct fwnode_handle *fwnode; @@ -66,6 +69,7 @@ static inline struct fwnode_handle *acpi_alloc_fwnode_static(void) return NULL; fwnode->type = FWNODE_ACPI_STATIC; + fwnode->ops = &acpi_fwnode_ops; return fwnode; } diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index ace73f96eb1e..854e1bdd0b2a 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -69,34 +69,14 @@ static inline void __add_wb_stat(struct bdi_writeback *wb, percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH); } -static inline void __inc_wb_stat(struct bdi_writeback *wb, - enum wb_stat_item item) -{ - __add_wb_stat(wb, item, 1); -} - static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { - unsigned long flags; - - local_irq_save(flags); - __inc_wb_stat(wb, item); - local_irq_restore(flags); -} - -static inline void __dec_wb_stat(struct bdi_writeback *wb, - enum wb_stat_item item) -{ - __add_wb_stat(wb, item, -1); + __add_wb_stat(wb, item, 1); } static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { - unsigned long flags; - - local_irq_save(flags); - __dec_wb_stat(wb, item); - local_irq_restore(flags); + __add_wb_stat(wb, item, -1); } static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) @@ -104,22 +84,9 @@ static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) return percpu_counter_read_positive(&wb->stat[item]); } -static inline s64 __wb_stat_sum(struct bdi_writeback *wb, - enum wb_stat_item item) -{ - return percpu_counter_sum_positive(&wb->stat[item]); -} - static inline s64 wb_stat_sum(struct bdi_writeback *wb, enum wb_stat_item item) { - s64 sum; - unsigned long flags; - - local_irq_save(flags); - sum = __wb_stat_sum(wb, item); - local_irq_restore(flags); - - return sum; + return percpu_counter_sum_positive(&wb->stat[item]); } extern void wb_writeout_inc(struct bdi_writeback *wb); diff --git a/include/linux/bio.h b/include/linux/bio.h index 664a27da276d..7b1cf4ba0902 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -165,10 +165,27 @@ static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter, { iter->bi_sector += bytes >> 9; - if (bio_no_advance_iter(bio)) + if (bio_no_advance_iter(bio)) { iter->bi_size -= bytes; - else + iter->bi_done += bytes; + } else { bvec_iter_advance(bio->bi_io_vec, iter, bytes); + /* TODO: It is reasonable to complete bio with error here. */ + } +} + +static inline bool bio_rewind_iter(struct bio *bio, struct bvec_iter *iter, + unsigned int bytes) +{ + iter->bi_sector -= bytes >> 9; + + if (bio_no_advance_iter(bio)) { + iter->bi_size += bytes; + iter->bi_done -= bytes; + return true; + } + + return bvec_iter_rewind(bio->bi_io_vec, iter, bytes); } #define __bio_for_each_segment(bvl, bio, iter, start) \ @@ -303,8 +320,6 @@ struct bio_integrity_payload { struct bvec_iter bip_iter; - bio_end_io_t *bip_end_io; /* saved I/O completion fn */ - unsigned short bip_slab; /* slab the bip came from */ unsigned short bip_vcnt; /* # of integrity bio_vecs */ unsigned short bip_max_vcnt; /* integrity bio_vec slots */ @@ -722,13 +737,10 @@ struct biovec_slab { bip_for_each_vec(_bvl, _bio->bi_integrity, _iter) extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int); -extern void bio_integrity_free(struct bio *); extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int); -extern bool bio_integrity_enabled(struct bio *bio); -extern int bio_integrity_prep(struct bio *); -extern void bio_integrity_endio(struct bio *); +extern bool bio_integrity_prep(struct bio *); extern void bio_integrity_advance(struct bio *, unsigned int); -extern void bio_integrity_trim(struct bio *, unsigned int, unsigned int); +extern void bio_integrity_trim(struct bio *); extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t); extern int bioset_integrity_create(struct bio_set *, int); extern void bioset_integrity_free(struct bio_set *); @@ -741,11 +753,6 @@ static inline void *bio_integrity(struct bio *bio) return NULL; } -static inline bool bio_integrity_enabled(struct bio *bio) -{ - return false; -} - static inline int bioset_integrity_create(struct bio_set *bs, int pool_size) { return 0; @@ -756,14 +763,9 @@ static inline void bioset_integrity_free (struct bio_set *bs) return; } -static inline int bio_integrity_prep(struct bio *bio) -{ - return 0; -} - -static inline void bio_integrity_free(struct bio *bio) +static inline bool bio_integrity_prep(struct bio *bio) { - return; + return true; } static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src, @@ -778,8 +780,7 @@ static inline void bio_integrity_advance(struct bio *bio, return; } -static inline void bio_integrity_trim(struct bio *bio, unsigned int offset, - unsigned int sectors) +static inline void bio_integrity_trim(struct bio *bio) { return; } diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 3b77588a9360..5797ca6fdfe2 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -112,9 +112,8 @@ extern int __bitmap_intersects(const unsigned long *bitmap1, extern int __bitmap_subset(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); - -extern void bitmap_set(unsigned long *map, unsigned int start, int len); -extern void bitmap_clear(unsigned long *map, unsigned int start, int len); +extern void __bitmap_set(unsigned long *map, unsigned int start, int len); +extern void __bitmap_clear(unsigned long *map, unsigned int start, int len); extern unsigned long bitmap_find_next_zero_area_off(unsigned long *map, unsigned long size, @@ -267,10 +266,8 @@ static inline int bitmap_equal(const unsigned long *src1, { if (small_const_nbits(nbits)) return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); -#ifdef CONFIG_S390 - if (__builtin_constant_p(nbits) && (nbits % BITS_PER_LONG) == 0) + if (__builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8)) return !memcmp(src1, src2, nbits / 8); -#endif return __bitmap_equal(src1, src2, nbits); } @@ -315,6 +312,30 @@ static __always_inline int bitmap_weight(const unsigned long *src, unsigned int return __bitmap_weight(src, nbits); } +static __always_inline void bitmap_set(unsigned long *map, unsigned int start, + unsigned int nbits) +{ + if (__builtin_constant_p(nbits) && nbits == 1) + __set_bit(start, map); + else if (__builtin_constant_p(start & 7) && IS_ALIGNED(start, 8) && + __builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8)) + memset((char *)map + start / 8, 0xff, nbits / 8); + else + __bitmap_set(map, start, nbits); +} + +static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, + unsigned int nbits) +{ + if (__builtin_constant_p(nbits) && nbits == 1) + __clear_bit(start, map); + else if (__builtin_constant_p(start & 7) && IS_ALIGNED(start, 8) && + __builtin_constant_p(nbits & 7) && IS_ALIGNED(nbits, 8)) + memset((char *)map + start / 8, 0, nbits / 8); + else + __bitmap_clear(map, start, nbits); +} + static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned int shift, int nbits) { diff --git a/include/linux/bug.h b/include/linux/bug.h index 687b557fc5eb..5d5554c874fd 100644 --- a/include/linux/bug.h +++ b/include/linux/bug.h @@ -3,6 +3,7 @@ #include <asm/bug.h> #include <linux/compiler.h> +#include <linux/build_bug.h> enum bug_trap_type { BUG_TRAP_TYPE_NONE = 0, @@ -13,80 +14,9 @@ enum bug_trap_type { struct pt_regs; #ifdef __CHECKER__ -#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) -#define BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) -#define BUILD_BUG_ON_ZERO(e) (0) -#define BUILD_BUG_ON_NULL(e) ((void*)0) -#define BUILD_BUG_ON_INVALID(e) (0) -#define BUILD_BUG_ON_MSG(cond, msg) (0) -#define BUILD_BUG_ON(condition) (0) -#define BUILD_BUG() (0) #define MAYBE_BUILD_BUG_ON(cond) (0) #else /* __CHECKER__ */ -/* Force a compilation error if a constant expression is not a power of 2 */ -#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) \ - BUILD_BUG_ON(((n) & ((n) - 1)) != 0) -#define BUILD_BUG_ON_NOT_POWER_OF_2(n) \ - BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0)) - -/* Force a compilation error if condition is true, but also produce a - result (of value 0 and type size_t), so the expression can be used - e.g. in a structure initializer (or where-ever else comma expressions - aren't permitted). */ -#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); })) -#define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:-!!(e); })) - -/* - * BUILD_BUG_ON_INVALID() permits the compiler to check the validity of the - * expression but avoids the generation of any code, even if that expression - * has side-effects. - */ -#define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e)))) - -/** - * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied - * error message. - * @condition: the condition which the compiler should know is false. - * - * See BUILD_BUG_ON for description. - */ -#define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg) - -/** - * BUILD_BUG_ON - break compile if a condition is true. - * @condition: the condition which the compiler should know is false. - * - * If you have some code which relies on certain constants being equal, or - * some other compile-time-evaluated condition, you should use BUILD_BUG_ON to - * detect if someone changes it. - * - * The implementation uses gcc's reluctance to create a negative array, but gcc - * (as of 4.4) only emits that error for obvious cases (e.g. not arguments to - * inline functions). Luckily, in 4.3 they added the "error" function - * attribute just for this type of case. Thus, we use a negative sized array - * (should always create an error on gcc versions older than 4.4) and then call - * an undefined function with the error attribute (should always create an - * error on gcc 4.3 and later). If for some reason, neither creates a - * compile-time error, we'll still have a link-time error, which is harder to - * track down. - */ -#ifndef __OPTIMIZE__ -#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) -#else -#define BUILD_BUG_ON(condition) \ - BUILD_BUG_ON_MSG(condition, "BUILD_BUG_ON failed: " #condition) -#endif - -/** - * BUILD_BUG - break compile if used. - * - * If you have some code that you expect the compiler to eliminate at - * build time, you should use BUILD_BUG to detect if it is - * unexpectedly used. - */ -#define BUILD_BUG() BUILD_BUG_ON_MSG(1, "BUILD_BUG failed") - #define MAYBE_BUILD_BUG_ON(cond) \ do { \ if (__builtin_constant_p((cond))) \ diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h new file mode 100644 index 000000000000..b7d22d60008a --- /dev/null +++ b/include/linux/build_bug.h @@ -0,0 +1,84 @@ +#ifndef _LINUX_BUILD_BUG_H +#define _LINUX_BUILD_BUG_H + +#include <linux/compiler.h> + +#ifdef __CHECKER__ +#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) +#define BUILD_BUG_ON_NOT_POWER_OF_2(n) (0) +#define BUILD_BUG_ON_ZERO(e) (0) +#define BUILD_BUG_ON_NULL(e) ((void *)0) +#define BUILD_BUG_ON_INVALID(e) (0) +#define BUILD_BUG_ON_MSG(cond, msg) (0) +#define BUILD_BUG_ON(condition) (0) +#define BUILD_BUG() (0) +#else /* __CHECKER__ */ + +/* Force a compilation error if a constant expression is not a power of 2 */ +#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) \ + BUILD_BUG_ON(((n) & ((n) - 1)) != 0) +#define BUILD_BUG_ON_NOT_POWER_OF_2(n) \ + BUILD_BUG_ON((n) == 0 || (((n) & ((n) - 1)) != 0)) + +/* + * Force a compilation error if condition is true, but also produce a + * result (of value 0 and type size_t), so the expression can be used + * e.g. in a structure initializer (or where-ever else comma expressions + * aren't permitted). + */ +#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:(-!!(e)); })) +#define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:(-!!(e)); })) + +/* + * BUILD_BUG_ON_INVALID() permits the compiler to check the validity of the + * expression but avoids the generation of any code, even if that expression + * has side-effects. + */ +#define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e)))) + +/** + * BUILD_BUG_ON_MSG - break compile if a condition is true & emit supplied + * error message. + * @condition: the condition which the compiler should know is false. + * + * See BUILD_BUG_ON for description. + */ +#define BUILD_BUG_ON_MSG(cond, msg) compiletime_assert(!(cond), msg) + +/** + * BUILD_BUG_ON - break compile if a condition is true. + * @condition: the condition which the compiler should know is false. + * + * If you have some code which relies on certain constants being equal, or + * some other compile-time-evaluated condition, you should use BUILD_BUG_ON to + * detect if someone changes it. + * + * The implementation uses gcc's reluctance to create a negative array, but gcc + * (as of 4.4) only emits that error for obvious cases (e.g. not arguments to + * inline functions). Luckily, in 4.3 they added the "error" function + * attribute just for this type of case. Thus, we use a negative sized array + * (should always create an error on gcc versions older than 4.4) and then call + * an undefined function with the error attribute (should always create an + * error on gcc 4.3 and later). If for some reason, neither creates a + * compile-time error, we'll still have a link-time error, which is harder to + * track down. + */ +#ifndef __OPTIMIZE__ +#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) +#else +#define BUILD_BUG_ON(condition) \ + BUILD_BUG_ON_MSG(condition, "BUILD_BUG_ON failed: " #condition) +#endif + +/** + * BUILD_BUG - break compile if used. + * + * If you have some code that you expect the compiler to eliminate at + * build time, you should use BUILD_BUG to detect if it is + * unexpectedly used. + */ +#define BUILD_BUG() BUILD_BUG_ON_MSG(1, "BUILD_BUG failed") + +#endif /* __CHECKER__ */ + +#endif /* _LINUX_BUILD_BUG_H */ diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 89b65b82d98f..ec8a4d7af6bd 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -22,6 +22,7 @@ #include <linux/kernel.h> #include <linux/bug.h> +#include <linux/errno.h> /* * was unsigned short, but we might as well be ready for > 64kB I/O pages @@ -39,6 +40,8 @@ struct bvec_iter { unsigned int bi_idx; /* current index into bvl_vec */ + unsigned int bi_done; /* number of bytes completed */ + unsigned int bi_bvec_done; /* number of bytes completed in current bvec */ }; @@ -66,12 +69,14 @@ struct bvec_iter { .bv_offset = bvec_iter_offset((bvec), (iter)), \ }) -static inline void bvec_iter_advance(const struct bio_vec *bv, - struct bvec_iter *iter, - unsigned bytes) +static inline bool bvec_iter_advance(const struct bio_vec *bv, + struct bvec_iter *iter, unsigned bytes) { - WARN_ONCE(bytes > iter->bi_size, - "Attempted to advance past end of bvec iter\n"); + if (WARN_ONCE(bytes > iter->bi_size, + "Attempted to advance past end of bvec iter\n")) { + iter->bi_size = 0; + return false; + } while (bytes) { unsigned iter_len = bvec_iter_len(bv, *iter); @@ -80,12 +85,38 @@ static inline void bvec_iter_advance(const struct bio_vec *bv, bytes -= len; iter->bi_size -= len; iter->bi_bvec_done += len; + iter->bi_done += len; if (iter->bi_bvec_done == __bvec_iter_bvec(bv, *iter)->bv_len) { iter->bi_bvec_done = 0; iter->bi_idx++; } } + return true; +} + +static inline bool bvec_iter_rewind(const struct bio_vec *bv, + struct bvec_iter *iter, + unsigned int bytes) +{ + while (bytes) { + unsigned len = min(bytes, iter->bi_bvec_done); + + if (iter->bi_bvec_done == 0) { + if (WARN_ONCE(iter->bi_idx == 0, + "Attempted to rewind iter beyond " + "bvec's boundaries\n")) { + return false; + } + iter->bi_idx--; + iter->bi_bvec_done = __bvec_iter_bvec(bv, *iter)->bv_len; + continue; + } + bytes -= len; + iter->bi_size += len; + iter->bi_bvec_done -= len; + } + return true; } #define for_each_bvec(bvl, bio_vec, iter, start) \ diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index fd8b2953c78f..f0f6c537b64c 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -2,103 +2,174 @@ #define __CEPH_FEATURES /* - * feature bits + * Each time we reclaim bits for reuse we need to specify another bit + * that, if present, indicates we have the new incarnation of that + * feature. Base case is 1 (first use). */ -#define CEPH_FEATURE_UID (1ULL<<0) -#define CEPH_FEATURE_NOSRCADDR (1ULL<<1) -#define CEPH_FEATURE_MONCLOCKCHECK (1ULL<<2) -#define CEPH_FEATURE_FLOCK (1ULL<<3) -#define CEPH_FEATURE_SUBSCRIBE2 (1ULL<<4) -#define CEPH_FEATURE_MONNAMES (1ULL<<5) -#define CEPH_FEATURE_RECONNECT_SEQ (1ULL<<6) -#define CEPH_FEATURE_DIRLAYOUTHASH (1ULL<<7) -#define CEPH_FEATURE_OBJECTLOCATOR (1ULL<<8) -#define CEPH_FEATURE_PGID64 (1ULL<<9) -#define CEPH_FEATURE_INCSUBOSDMAP (1ULL<<10) -#define CEPH_FEATURE_PGPOOL3 (1ULL<<11) -#define CEPH_FEATURE_OSDREPLYMUX (1ULL<<12) -#define CEPH_FEATURE_OSDENC (1ULL<<13) -#define CEPH_FEATURE_OMAP (1ULL<<14) -#define CEPH_FEATURE_MONENC (1ULL<<15) -#define CEPH_FEATURE_QUERY_T (1ULL<<16) -#define CEPH_FEATURE_INDEP_PG_MAP (1ULL<<17) -#define CEPH_FEATURE_CRUSH_TUNABLES (1ULL<<18) -#define CEPH_FEATURE_CHUNKY_SCRUB (1ULL<<19) -#define CEPH_FEATURE_MON_NULLROUTE (1ULL<<20) -#define CEPH_FEATURE_MON_GV (1ULL<<21) -#define CEPH_FEATURE_BACKFILL_RESERVATION (1ULL<<22) -#define CEPH_FEATURE_MSG_AUTH (1ULL<<23) -#define CEPH_FEATURE_RECOVERY_RESERVATION (1ULL<<24) -#define CEPH_FEATURE_CRUSH_TUNABLES2 (1ULL<<25) -#define CEPH_FEATURE_CREATEPOOLID (1ULL<<26) -#define CEPH_FEATURE_REPLY_CREATE_INODE (1ULL<<27) -#define CEPH_FEATURE_OSD_HBMSGS (1ULL<<28) -#define CEPH_FEATURE_MDSENC (1ULL<<29) -#define CEPH_FEATURE_OSDHASHPSPOOL (1ULL<<30) -#define CEPH_FEATURE_MON_SINGLE_PAXOS (1ULL<<31) -#define CEPH_FEATURE_OSD_SNAPMAPPER (1ULL<<32) -#define CEPH_FEATURE_MON_SCRUB (1ULL<<33) -#define CEPH_FEATURE_OSD_PACKED_RECOVERY (1ULL<<34) -#define CEPH_FEATURE_OSD_CACHEPOOL (1ULL<<35) -#define CEPH_FEATURE_CRUSH_V2 (1ULL<<36) /* new indep; SET_* steps */ -#define CEPH_FEATURE_EXPORT_PEER (1ULL<<37) -#define CEPH_FEATURE_OSD_ERASURE_CODES (1ULL<<38) -#define CEPH_FEATURE_OSD_TMAP2OMAP (1ULL<<38) /* overlap with EC */ -/* The process supports new-style OSDMap encoding. Monitors also use - this bit to determine if peers support NAK messages. */ -#define CEPH_FEATURE_OSDMAP_ENC (1ULL<<39) -#define CEPH_FEATURE_MDS_INLINE_DATA (1ULL<<40) -#define CEPH_FEATURE_CRUSH_TUNABLES3 (1ULL<<41) -#define CEPH_FEATURE_OSD_PRIMARY_AFFINITY (1ULL<<41) /* overlap w/ tunables3 */ -#define CEPH_FEATURE_MSGR_KEEPALIVE2 (1ULL<<42) -#define CEPH_FEATURE_OSD_POOLRESEND (1ULL<<43) -#define CEPH_FEATURE_ERASURE_CODE_PLUGINS_V2 (1ULL<<44) -#define CEPH_FEATURE_OSD_SET_ALLOC_HINT (1ULL<<45) -#define CEPH_FEATURE_OSD_FADVISE_FLAGS (1ULL<<46) -#define CEPH_FEATURE_OSD_REPOP (1ULL<<46) /* overlap with fadvise */ -#define CEPH_FEATURE_OSD_OBJECT_DIGEST (1ULL<<46) /* overlap with fadvise */ -#define CEPH_FEATURE_OSD_TRANSACTION_MAY_LAYOUT (1ULL<<46) /* overlap w/ fadvise */ -#define CEPH_FEATURE_MDS_QUOTA (1ULL<<47) -#define CEPH_FEATURE_CRUSH_V4 (1ULL<<48) /* straw2 buckets */ -#define CEPH_FEATURE_OSD_MIN_SIZE_RECOVERY (1ULL<<49) -// duplicated since it was introduced at the same time as MIN_SIZE_RECOVERY -#define CEPH_FEATURE_OSD_PROXY_FEATURES (1ULL<<49) /* overlap w/ above */ -#define CEPH_FEATURE_MON_METADATA (1ULL<<50) -#define CEPH_FEATURE_OSD_BITWISE_HOBJ_SORT (1ULL<<51) /* can sort objs bitwise */ -#define CEPH_FEATURE_OSD_PROXY_WRITE_FEATURES (1ULL<<52) -#define CEPH_FEATURE_ERASURE_CODE_PLUGINS_V3 (1ULL<<53) -#define CEPH_FEATURE_OSD_HITSET_GMT (1ULL<<54) -#define CEPH_FEATURE_HAMMER_0_94_4 (1ULL<<55) -#define CEPH_FEATURE_NEW_OSDOP_ENCODING (1ULL<<56) /* New, v7 encoding */ -#define CEPH_FEATURE_MON_STATEFUL_SUB (1ULL<<57) /* stateful mon subscription */ -#define CEPH_FEATURE_MON_ROUTE_OSDMAP (1ULL<<57) /* peon sends osdmaps */ -#define CEPH_FEATURE_CRUSH_TUNABLES5 (1ULL<<58) /* chooseleaf stable mode */ -// duplicated since it was introduced at the same time as CEPH_FEATURE_CRUSH_TUNABLES5 -#define CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING (1ULL<<58) /* New, v7 encoding */ -#define CEPH_FEATURE_FS_FILE_LAYOUT_V2 (1ULL<<58) /* file_layout_t */ +#define CEPH_FEATURE_INCARNATION_1 (0ull) +#define CEPH_FEATURE_INCARNATION_2 (1ull<<57) // CEPH_FEATURE_SERVER_JEWEL + +#define DEFINE_CEPH_FEATURE(bit, incarnation, name) \ + const static uint64_t CEPH_FEATURE_##name = (1ULL<<bit); \ + const static uint64_t CEPH_FEATUREMASK_##name = \ + (1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation); + +/* this bit is ignored but still advertised by release *when* */ +#define DEFINE_CEPH_FEATURE_DEPRECATED(bit, incarnation, name, when) \ + const static uint64_t DEPRECATED_CEPH_FEATURE_##name = (1ULL<<bit); \ + const static uint64_t DEPRECATED_CEPH_FEATUREMASK_##name = \ + (1ULL<<bit | CEPH_FEATURE_INCARNATION_##incarnation); /* - * The introduction of CEPH_FEATURE_OSD_SNAPMAPPER caused the feature - * vector to evaluate to 64 bit ~0. To cope, we designate 1ULL << 63 - * to mean 33 bit ~0, and introduce a helper below to do the - * translation. + * this bit is ignored by release *unused* and not advertised by + * release *unadvertised* + */ +#define DEFINE_CEPH_FEATURE_RETIRED(bit, inc, name, unused, unadvertised) + + +/* + * test for a feature. this test is safer than a typical mask against + * the bit because it ensures that we have the bit AND the marker for the + * bit's incarnation. this must be used in any case where the features + * bits may include an old meaning of the bit. + */ +#define CEPH_HAVE_FEATURE(x, name) \ + (((x) & (CEPH_FEATUREMASK_##name)) == (CEPH_FEATUREMASK_##name)) + + +/* + * Notes on deprecation: + * + * A *major* release is a release through which all upgrades must pass + * (e.g., jewel). For example, no pre-jewel server will ever talk to + * a post-jewel server (mon, osd, etc). + * + * For feature bits used *only* on the server-side: + * + * - In the first phase we indicate that a feature is DEPRECATED as of + * a particular release. This is the first major release X (say, + * jewel) that does not depend on its peers advertising the feature. + * That is, it safely assumes its peers all have the feature. We + * indicate this with the DEPRECATED macro. For example, + * + * DEFINE_CEPH_FEATURE_DEPRECATED( 2, 1, MONCLOCKCHECK, JEWEL) + * + * because 10.2.z (jewel) did not care if its peers advertised this + * feature bit. + * + * - In the second phase we stop advertising the the bit and call it + * RETIRED. This can normally be done in the *next* major release + * following the one in which we marked the feature DEPRECATED. In + * the above example, for 12.0.z (luminous) we can say: + * + * DEFINE_CEPH_FEATURE_RETIRED( 2, 1, MONCLOCKCHECK, JEWEL, LUMINOUS) * - * This was introduced by ceph.git commit - * 9ea02b84104045c2ffd7e7f4e7af512953855ecd v0.58-657-g9ea02b8 - * and fixed by ceph.git commit - * 4255b5c2fb54ae40c53284b3ab700fdfc7e61748 v0.65-263-g4255b5c + * - The bit can be reused in the first post-luminous release, 13.0.z + * (m). + * + * This ensures that no two versions who have different meanings for + * the bit ever speak to each other. */ -#define CEPH_FEATURE_RESERVED (1ULL<<63) - -static inline u64 ceph_sanitize_features(u64 features) -{ - if (features & CEPH_FEATURE_RESERVED) { - /* everything through OSD_SNAPMAPPER */ - return 0x1ffffffffull; - } else { - return features; - } -} + +DEFINE_CEPH_FEATURE( 0, 1, UID) +DEFINE_CEPH_FEATURE( 1, 1, NOSRCADDR) +DEFINE_CEPH_FEATURE_RETIRED( 2, 1, MONCLOCKCHECK, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE( 3, 1, FLOCK) +DEFINE_CEPH_FEATURE( 4, 1, SUBSCRIBE2) +DEFINE_CEPH_FEATURE( 5, 1, MONNAMES) +DEFINE_CEPH_FEATURE( 6, 1, RECONNECT_SEQ) +DEFINE_CEPH_FEATURE( 7, 1, DIRLAYOUTHASH) +DEFINE_CEPH_FEATURE( 8, 1, OBJECTLOCATOR) +DEFINE_CEPH_FEATURE( 9, 1, PGID64) +DEFINE_CEPH_FEATURE(10, 1, INCSUBOSDMAP) +DEFINE_CEPH_FEATURE(11, 1, PGPOOL3) +DEFINE_CEPH_FEATURE(12, 1, OSDREPLYMUX) +DEFINE_CEPH_FEATURE(13, 1, OSDENC) +DEFINE_CEPH_FEATURE_RETIRED(14, 1, OMAP, HAMMER, JEWEL) +DEFINE_CEPH_FEATURE(14, 2, SERVER_KRAKEN) +DEFINE_CEPH_FEATURE(15, 1, MONENC) +DEFINE_CEPH_FEATURE_RETIRED(16, 1, QUERY_T, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE_RETIRED(17, 1, INDEP_PG_MAP, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE(18, 1, CRUSH_TUNABLES) +DEFINE_CEPH_FEATURE_RETIRED(19, 1, CHUNKY_SCRUB, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE_RETIRED(20, 1, MON_NULLROUTE, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE_RETIRED(21, 1, MON_GV, HAMMER, JEWEL) +DEFINE_CEPH_FEATURE(21, 2, SERVER_LUMINOUS) +DEFINE_CEPH_FEATURE(21, 2, RESEND_ON_SPLIT) // overlap +DEFINE_CEPH_FEATURE(21, 2, RADOS_BACKOFF) // overlap +DEFINE_CEPH_FEATURE(21, 2, OSDMAP_PG_UPMAP) // overlap +DEFINE_CEPH_FEATURE(21, 2, CRUSH_CHOOSE_ARGS) // overlap +DEFINE_CEPH_FEATURE_RETIRED(22, 1, BACKFILL_RESERVATION, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE(23, 1, MSG_AUTH) +DEFINE_CEPH_FEATURE_RETIRED(24, 1, RECOVERY_RESERVATION, JEWEL, LUNINOUS) + +DEFINE_CEPH_FEATURE(25, 1, CRUSH_TUNABLES2) +DEFINE_CEPH_FEATURE(26, 1, CREATEPOOLID) +DEFINE_CEPH_FEATURE(27, 1, REPLY_CREATE_INODE) +DEFINE_CEPH_FEATURE_RETIRED(28, 1, OSD_HBMSGS, HAMMER, JEWEL) +DEFINE_CEPH_FEATURE(28, 2, SERVER_M) +DEFINE_CEPH_FEATURE(29, 1, MDSENC) +DEFINE_CEPH_FEATURE(30, 1, OSDHASHPSPOOL) +DEFINE_CEPH_FEATURE(31, 1, MON_SINGLE_PAXOS) // deprecate me +DEFINE_CEPH_FEATURE_RETIRED(32, 1, OSD_SNAPMAPPER, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE_RETIRED(33, 1, MON_SCRUB, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE_RETIRED(34, 1, OSD_PACKED_RECOVERY, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE(35, 1, OSD_CACHEPOOL) +DEFINE_CEPH_FEATURE(36, 1, CRUSH_V2) +DEFINE_CEPH_FEATURE(37, 1, EXPORT_PEER) +DEFINE_CEPH_FEATURE(38, 1, OSD_ERASURE_CODES) +DEFINE_CEPH_FEATURE(38, 1, OSD_OSD_TMAP2OMAP) // overlap +DEFINE_CEPH_FEATURE(39, 1, OSDMAP_ENC) +DEFINE_CEPH_FEATURE(40, 1, MDS_INLINE_DATA) +DEFINE_CEPH_FEATURE(41, 1, CRUSH_TUNABLES3) +DEFINE_CEPH_FEATURE(41, 1, OSD_PRIMARY_AFFINITY) // overlap +DEFINE_CEPH_FEATURE(42, 1, MSGR_KEEPALIVE2) +DEFINE_CEPH_FEATURE(43, 1, OSD_POOLRESEND) +DEFINE_CEPH_FEATURE(44, 1, ERASURE_CODE_PLUGINS_V2) +DEFINE_CEPH_FEATURE_RETIRED(45, 1, OSD_SET_ALLOC_HINT, JEWEL, LUMINOUS) + +DEFINE_CEPH_FEATURE(46, 1, OSD_FADVISE_FLAGS) +DEFINE_CEPH_FEATURE_RETIRED(46, 1, OSD_REPOP, JEWEL, LUMINOUS) // overlap +DEFINE_CEPH_FEATURE_RETIRED(46, 1, OSD_OBJECT_DIGEST, JEWEL, LUMINOUS) // overlap +DEFINE_CEPH_FEATURE_RETIRED(46, 1, OSD_TRANSACTION_MAY_LAYOUT, JEWEL, LUMINOUS) // overlap + +DEFINE_CEPH_FEATURE(47, 1, MDS_QUOTA) +DEFINE_CEPH_FEATURE(48, 1, CRUSH_V4) +DEFINE_CEPH_FEATURE_RETIRED(49, 1, OSD_MIN_SIZE_RECOVERY, JEWEL, LUMINOUS) +DEFINE_CEPH_FEATURE_RETIRED(49, 1, OSD_PROXY_FEATURES, JEWEL, LUMINOUS) // overlap + +DEFINE_CEPH_FEATURE(50, 1, MON_METADATA) +DEFINE_CEPH_FEATURE(51, 1, OSD_BITWISE_HOBJ_SORT) +DEFINE_CEPH_FEATURE(52, 1, OSD_PROXY_WRITE_FEATURES) +DEFINE_CEPH_FEATURE(53, 1, ERASURE_CODE_PLUGINS_V3) +DEFINE_CEPH_FEATURE(54, 1, OSD_HITSET_GMT) +DEFINE_CEPH_FEATURE(55, 1, HAMMER_0_94_4) +DEFINE_CEPH_FEATURE(56, 1, NEW_OSDOP_ENCODING) +DEFINE_CEPH_FEATURE(57, 1, MON_STATEFUL_SUB) +DEFINE_CEPH_FEATURE(57, 1, MON_ROUTE_OSDMAP) // overlap +DEFINE_CEPH_FEATURE(57, 1, OSDSUBOP_NO_SNAPCONTEXT) // overlap +DEFINE_CEPH_FEATURE(57, 1, SERVER_JEWEL) // overlap +DEFINE_CEPH_FEATURE(58, 1, CRUSH_TUNABLES5) +DEFINE_CEPH_FEATURE(58, 1, NEW_OSDOPREPLY_ENCODING) // overlap +DEFINE_CEPH_FEATURE(58, 1, FS_FILE_LAYOUT_V2) // overlap +DEFINE_CEPH_FEATURE(59, 1, FS_BTIME) +DEFINE_CEPH_FEATURE(59, 1, FS_CHANGE_ATTR) // overlap +DEFINE_CEPH_FEATURE(59, 1, MSG_ADDR2) // overlap +DEFINE_CEPH_FEATURE(60, 1, BLKIN_TRACING) // *do not share this bit* + +DEFINE_CEPH_FEATURE(61, 1, RESERVED2) // unused, but slow down! +DEFINE_CEPH_FEATURE(62, 1, RESERVED) // do not use; used as a sentinal +DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facing + /* * Features supported. @@ -113,6 +184,11 @@ static inline u64 ceph_sanitize_features(u64 features) CEPH_FEATURE_PGPOOL3 | \ CEPH_FEATURE_OSDENC | \ CEPH_FEATURE_CRUSH_TUNABLES | \ + CEPH_FEATURE_SERVER_LUMINOUS | \ + CEPH_FEATURE_RESEND_ON_SPLIT | \ + CEPH_FEATURE_RADOS_BACKOFF | \ + CEPH_FEATURE_OSDMAP_PG_UPMAP | \ + CEPH_FEATURE_CRUSH_CHOOSE_ARGS | \ CEPH_FEATURE_MSG_AUTH | \ CEPH_FEATURE_CRUSH_TUNABLES2 | \ CEPH_FEATURE_REPLY_CREATE_INODE | \ @@ -126,7 +202,11 @@ static inline u64 ceph_sanitize_features(u64 features) CEPH_FEATURE_CRUSH_TUNABLES3 | \ CEPH_FEATURE_OSD_PRIMARY_AFFINITY | \ CEPH_FEATURE_MSGR_KEEPALIVE2 | \ + CEPH_FEATURE_OSD_POOLRESEND | \ CEPH_FEATURE_CRUSH_V4 | \ + CEPH_FEATURE_NEW_OSDOP_ENCODING | \ + CEPH_FEATURE_SERVER_JEWEL | \ + CEPH_FEATURE_MON_STATEFUL_SUB | \ CEPH_FEATURE_CRUSH_TUNABLES5 | \ CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING) diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index ad078ebe25d6..edf5b04b918a 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -147,6 +147,7 @@ struct ceph_dir_layout { #define CEPH_MSG_OSD_OP 42 #define CEPH_MSG_OSD_OPREPLY 43 #define CEPH_MSG_WATCH_NOTIFY 44 +#define CEPH_MSG_OSD_BACKOFF 61 /* watch-notify operations */ diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h index f990f2cc907a..14af9b70d301 100644 --- a/include/linux/ceph/decode.h +++ b/include/linux/ceph/decode.h @@ -133,6 +133,66 @@ bad: } /* + * skip helpers + */ +#define ceph_decode_skip_n(p, end, n, bad) \ + do { \ + ceph_decode_need(p, end, n, bad); \ + *p += n; \ + } while (0) + +#define ceph_decode_skip_64(p, end, bad) \ +ceph_decode_skip_n(p, end, sizeof(u64), bad) + +#define ceph_decode_skip_32(p, end, bad) \ +ceph_decode_skip_n(p, end, sizeof(u32), bad) + +#define ceph_decode_skip_16(p, end, bad) \ +ceph_decode_skip_n(p, end, sizeof(u16), bad) + +#define ceph_decode_skip_8(p, end, bad) \ +ceph_decode_skip_n(p, end, sizeof(u8), bad) + +#define ceph_decode_skip_string(p, end, bad) \ + do { \ + u32 len; \ + \ + ceph_decode_32_safe(p, end, len, bad); \ + ceph_decode_skip_n(p, end, len, bad); \ + } while (0) + +#define ceph_decode_skip_set(p, end, type, bad) \ + do { \ + u32 len; \ + \ + ceph_decode_32_safe(p, end, len, bad); \ + while (len--) \ + ceph_decode_skip_##type(p, end, bad); \ + } while (0) + +#define ceph_decode_skip_map(p, end, ktype, vtype, bad) \ + do { \ + u32 len; \ + \ + ceph_decode_32_safe(p, end, len, bad); \ + while (len--) { \ + ceph_decode_skip_##ktype(p, end, bad); \ + ceph_decode_skip_##vtype(p, end, bad); \ + } \ + } while (0) + +#define ceph_decode_skip_map_of_map(p, end, ktype1, ktype2, vtype2, bad) \ + do { \ + u32 len; \ + \ + ceph_decode_32_safe(p, end, len, bad); \ + while (len--) { \ + ceph_decode_skip_##ktype1(p, end, bad); \ + ceph_decode_skip_map(p, end, ktype2, vtype2, bad); \ + } \ + } while (0) + +/* * struct ceph_timespec <-> struct timespec */ static inline void ceph_decode_timespec(struct timespec *ts, diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 3229ae6c7846..8a79587e1317 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -184,10 +184,11 @@ static inline int calc_pages_for(u64 off, u64 len) (off >> PAGE_SHIFT); } -/* - * These are not meant to be generic - an integer key is assumed. - */ -#define DEFINE_RB_INSDEL_FUNCS(name, type, keyfld, nodefld) \ +#define RB_BYVAL(a) (a) +#define RB_BYPTR(a) (&(a)) +#define RB_CMP3WAY(a, b) ((a) < (b) ? -1 : (a) > (b)) + +#define DEFINE_RB_INSDEL_FUNCS2(name, type, keyfld, cmpexp, keyexp, nodefld) \ static void insert_##name(struct rb_root *root, type *t) \ { \ struct rb_node **n = &root->rb_node; \ @@ -197,11 +198,13 @@ static void insert_##name(struct rb_root *root, type *t) \ \ while (*n) { \ type *cur = rb_entry(*n, type, nodefld); \ + int cmp; \ \ parent = *n; \ - if (t->keyfld < cur->keyfld) \ + cmp = cmpexp(keyexp(t->keyfld), keyexp(cur->keyfld)); \ + if (cmp < 0) \ n = &(*n)->rb_left; \ - else if (t->keyfld > cur->keyfld) \ + else if (cmp > 0) \ n = &(*n)->rb_right; \ else \ BUG(); \ @@ -217,19 +220,24 @@ static void erase_##name(struct rb_root *root, type *t) \ RB_CLEAR_NODE(&t->nodefld); \ } -#define DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld) \ -extern type __lookup_##name##_key; \ -static type *lookup_##name(struct rb_root *root, \ - typeof(__lookup_##name##_key.keyfld) key) \ +/* + * @lookup_param_type is a parameter and not constructed from (@type, + * @keyfld) with typeof() because adding const is too unwieldy. + */ +#define DEFINE_RB_LOOKUP_FUNC2(name, type, keyfld, cmpexp, keyexp, \ + lookup_param_type, nodefld) \ +static type *lookup_##name(struct rb_root *root, lookup_param_type key) \ { \ struct rb_node *n = root->rb_node; \ \ while (n) { \ type *cur = rb_entry(n, type, nodefld); \ + int cmp; \ \ - if (key < cur->keyfld) \ + cmp = cmpexp(key, keyexp(cur->keyfld)); \ + if (cmp < 0) \ n = n->rb_left; \ - else if (key > cur->keyfld) \ + else if (cmp > 0) \ n = n->rb_right; \ else \ return cur; \ @@ -238,6 +246,23 @@ static type *lookup_##name(struct rb_root *root, \ return NULL; \ } +#define DEFINE_RB_FUNCS2(name, type, keyfld, cmpexp, keyexp, \ + lookup_param_type, nodefld) \ +DEFINE_RB_INSDEL_FUNCS2(name, type, keyfld, cmpexp, keyexp, nodefld) \ +DEFINE_RB_LOOKUP_FUNC2(name, type, keyfld, cmpexp, keyexp, \ + lookup_param_type, nodefld) + +/* + * Shorthands for integer keys. + */ +#define DEFINE_RB_INSDEL_FUNCS(name, type, keyfld, nodefld) \ +DEFINE_RB_INSDEL_FUNCS2(name, type, keyfld, RB_CMP3WAY, RB_BYVAL, nodefld) + +#define DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld) \ +extern type __lookup_##name##_key; \ +DEFINE_RB_LOOKUP_FUNC2(name, type, keyfld, RB_CMP3WAY, RB_BYVAL, \ + typeof(__lookup_##name##_key.keyfld), nodefld) + #define DEFINE_RB_FUNCS(name, type, keyfld, nodefld) \ DEFINE_RB_INSDEL_FUNCS(name, type, keyfld, nodefld) \ DEFINE_RB_LOOKUP_FUNC(name, type, keyfld, nodefld) diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index c5c4c713e00f..fbd94d9fa5dd 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -44,6 +44,8 @@ struct ceph_connection_operations { struct ceph_msg_header *hdr, int *skip); + void (*reencode_message) (struct ceph_msg *msg); + int (*sign_message) (struct ceph_msg *msg); int (*check_message_signature) (struct ceph_msg *msg); }; diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 85650b415e73..c6d96a5f46fd 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -1,6 +1,7 @@ #ifndef _FS_CEPH_OSD_CLIENT_H #define _FS_CEPH_OSD_CLIENT_H +#include <linux/bitrev.h> #include <linux/completion.h> #include <linux/kref.h> #include <linux/mempool.h> @@ -36,6 +37,8 @@ struct ceph_osd { struct ceph_connection o_con; struct rb_root o_requests; struct rb_root o_linger_requests; + struct rb_root o_backoff_mappings; + struct rb_root o_backoffs_by_id; struct list_head o_osd_lru; struct ceph_auth_handshake o_auth; unsigned long lru_ttl; @@ -136,7 +139,8 @@ struct ceph_osd_request_target { struct ceph_object_id target_oid; struct ceph_object_locator target_oloc; - struct ceph_pg pgid; + struct ceph_pg pgid; /* last raw pg we mapped to */ + struct ceph_spg spgid; /* last actual spg we mapped to */ u32 pg_num; u32 pg_num_mask; struct ceph_osds acting; @@ -148,6 +152,9 @@ struct ceph_osd_request_target { unsigned int flags; /* CEPH_OSD_FLAG_* */ bool paused; + u32 epoch; + u32 last_force_resend; + int osd; }; @@ -193,7 +200,6 @@ struct ceph_osd_request { unsigned long r_stamp; /* jiffies, send or check time */ unsigned long r_start_stamp; /* jiffies */ int r_attempts; - u32 r_last_force_resend; u32 r_map_dne_bound; struct ceph_osd_req_op r_ops[]; @@ -203,6 +209,23 @@ struct ceph_request_redirect { struct ceph_object_locator oloc; }; +/* + * osd request identifier + * + * caller name + incarnation# + tid to unique identify this request + */ +struct ceph_osd_reqid { + struct ceph_entity_name name; + __le64 tid; + __le32 inc; +} __packed; + +struct ceph_blkin_trace_info { + __le64 trace_id; + __le64 span_id; + __le64 parent_span_id; +} __packed; + typedef void (*rados_watchcb2_t)(void *arg, u64 notify_id, u64 cookie, u64 notifier_id, void *data, size_t data_len); typedef void (*rados_watcherrcb_t)(void *arg, u64 cookie, int err); @@ -221,7 +244,6 @@ struct ceph_osd_linger_request { struct list_head pending_lworks; struct ceph_osd_request_target t; - u32 last_force_resend; u32 map_dne_bound; struct timespec mtime; @@ -256,6 +278,48 @@ struct ceph_watch_item { struct ceph_entity_addr addr; }; +struct ceph_spg_mapping { + struct rb_node node; + struct ceph_spg spgid; + + struct rb_root backoffs; +}; + +struct ceph_hobject_id { + void *key; + size_t key_len; + void *oid; + size_t oid_len; + u64 snapid; + u32 hash; + u8 is_max; + void *nspace; + size_t nspace_len; + s64 pool; + + /* cache */ + u32 hash_reverse_bits; +}; + +static inline void ceph_hoid_build_hash_cache(struct ceph_hobject_id *hoid) +{ + hoid->hash_reverse_bits = bitrev32(hoid->hash); +} + +/* + * PG-wide backoff: [begin, end) + * per-object backoff: begin == end + */ +struct ceph_osd_backoff { + struct rb_node spg_node; + struct rb_node id_node; + + struct ceph_spg spgid; + u64 id; + struct ceph_hobject_id *begin; + struct ceph_hobject_id *end; +}; + #define CEPH_LINGER_ID_START 0xffff000000000000ULL struct ceph_osd_client { diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 938656f70807..a0996cb9faed 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -24,7 +24,15 @@ struct ceph_pg { uint32_t seed; }; +#define CEPH_SPG_NOSHARD -1 + +struct ceph_spg { + struct ceph_pg pgid; + s8 shard; +}; + int ceph_pg_compare(const struct ceph_pg *lhs, const struct ceph_pg *rhs); +int ceph_spg_compare(const struct ceph_spg *lhs, const struct ceph_spg *rhs); #define CEPH_POOL_FLAG_HASHPSPOOL (1ULL << 0) /* hash pg seed and pool id together */ @@ -135,10 +143,14 @@ struct ceph_pg_mapping { struct { int len; int osds[]; - } pg_temp; + } pg_temp, pg_upmap; struct { int osd; } primary_temp; + struct { + int len; + int from_to[][2]; + } pg_upmap_items; }; }; @@ -150,13 +162,17 @@ struct ceph_osdmap { u32 flags; /* CEPH_OSDMAP_* */ u32 max_osd; /* size of osd_state, _offload, _addr arrays */ - u8 *osd_state; /* CEPH_OSD_* */ + u32 *osd_state; /* CEPH_OSD_* */ u32 *osd_weight; /* 0 = failed, 0x10000 = 100% normal */ struct ceph_entity_addr *osd_addr; struct rb_root pg_temp; struct rb_root primary_temp; + /* remap (post-CRUSH, pre-up) */ + struct rb_root pg_upmap; /* PG := raw set */ + struct rb_root pg_upmap_items; /* from -> to within raw set */ + u32 *osd_primary_affinity; struct rb_root pg_pools; @@ -187,7 +203,7 @@ static inline bool ceph_osd_is_down(struct ceph_osdmap *map, int osd) return !ceph_osd_is_up(map, osd); } -extern char *ceph_osdmap_state_str(char *str, int len, int state); +char *ceph_osdmap_state_str(char *str, int len, u32 state); extern u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd); static inline struct ceph_entity_addr *ceph_osd_addr(struct ceph_osdmap *map, @@ -198,11 +214,13 @@ static inline struct ceph_entity_addr *ceph_osd_addr(struct ceph_osdmap *map, return &map->osd_addr[osd]; } +#define CEPH_PGID_ENCODING_LEN (1 + 8 + 4 + 4) + static inline int ceph_decode_pgid(void **p, void *end, struct ceph_pg *pgid) { __u8 version; - if (!ceph_has_room(p, end, 1 + 8 + 4 + 4)) { + if (!ceph_has_room(p, end, CEPH_PGID_ENCODING_LEN)) { pr_warn("incomplete pg encoding\n"); return -EINVAL; } @@ -240,6 +258,8 @@ static inline void ceph_osds_init(struct ceph_osds *set) void ceph_osds_copy(struct ceph_osds *dest, const struct ceph_osds *src); +bool ceph_pg_is_split(const struct ceph_pg *pgid, u32 old_pg_num, + u32 new_pg_num); bool ceph_is_new_interval(const struct ceph_osds *old_acting, const struct ceph_osds *new_acting, const struct ceph_osds *old_up, @@ -262,15 +282,24 @@ extern int ceph_calc_file_object_mapping(struct ceph_file_layout *layout, u64 off, u64 len, u64 *bno, u64 *oxoff, u64 *oxlen); +int __ceph_object_locator_to_pg(struct ceph_pg_pool_info *pi, + const struct ceph_object_id *oid, + const struct ceph_object_locator *oloc, + struct ceph_pg *raw_pgid); int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap, - struct ceph_object_id *oid, - struct ceph_object_locator *oloc, + const struct ceph_object_id *oid, + const struct ceph_object_locator *oloc, struct ceph_pg *raw_pgid); void ceph_pg_to_up_acting_osds(struct ceph_osdmap *osdmap, + struct ceph_pg_pool_info *pi, const struct ceph_pg *raw_pgid, struct ceph_osds *up, struct ceph_osds *acting); +bool ceph_pg_to_primary_shard(struct ceph_osdmap *osdmap, + struct ceph_pg_pool_info *pi, + const struct ceph_pg *raw_pgid, + struct ceph_spg *spgid); int ceph_pg_to_acting_primary(struct ceph_osdmap *osdmap, const struct ceph_pg *raw_pgid); diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index 5d0018782d50..385db08bb8b2 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -439,6 +439,12 @@ enum { const char *ceph_osd_watch_op_name(int o); +enum { + CEPH_OSD_BACKOFF_OP_BLOCK = 1, + CEPH_OSD_BACKOFF_OP_ACK_BLOCK = 2, + CEPH_OSD_BACKOFF_OP_UNBLOCK = 3, +}; + /* * an individual object operation. each may be accompanied by some data * payload diff --git a/include/linux/clk.h b/include/linux/clk.h index 91bd464f4c9b..12c96d94d1fa 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -657,6 +657,28 @@ static inline void clk_disable_unprepare(struct clk *clk) clk_unprepare(clk); } +static inline int clk_bulk_prepare_enable(int num_clks, + struct clk_bulk_data *clks) +{ + int ret; + + ret = clk_bulk_prepare(num_clks, clks); + if (ret) + return ret; + ret = clk_bulk_enable(num_clks, clks); + if (ret) + clk_bulk_unprepare(num_clks, clks); + + return ret; +} + +static inline void clk_bulk_disable_unprepare(int num_clks, + struct clk_bulk_data *clks) +{ + clk_bulk_disable(num_clks, clks); + clk_bulk_unprepare(num_clks, clks); +} + #if defined(CONFIG_OF) && defined(CONFIG_COMMON_CLK) struct clk *of_clk_get(struct device_node *np, int index); struct clk *of_clk_get_by_name(struct device_node *np, const char *name); diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h index c156f5082758..d4292ebc5c8b 100644 --- a/include/linux/cpu_cooling.h +++ b/include/linux/cpu_cooling.h @@ -28,47 +28,49 @@ #include <linux/thermal.h> #include <linux/cpumask.h> +struct cpufreq_policy; + typedef int (*get_static_t)(cpumask_t *cpumask, int interval, unsigned long voltage, u32 *power); #ifdef CONFIG_CPU_THERMAL /** * cpufreq_cooling_register - function to create cpufreq cooling device. - * @clip_cpus: cpumask of cpus where the frequency constraints will happen + * @policy: cpufreq policy. */ struct thermal_cooling_device * -cpufreq_cooling_register(const struct cpumask *clip_cpus); +cpufreq_cooling_register(struct cpufreq_policy *policy); struct thermal_cooling_device * -cpufreq_power_cooling_register(const struct cpumask *clip_cpus, +cpufreq_power_cooling_register(struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func); /** * of_cpufreq_cooling_register - create cpufreq cooling device based on DT. * @np: a valid struct device_node to the cooling device device tree node. - * @clip_cpus: cpumask of cpus where the frequency constraints will happen + * @policy: cpufreq policy. */ #ifdef CONFIG_THERMAL_OF struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus); + struct cpufreq_policy *policy); struct thermal_cooling_device * of_cpufreq_power_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus, + struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func); #else static inline struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus) + struct cpufreq_policy *policy) { return ERR_PTR(-ENOSYS); } static inline struct thermal_cooling_device * of_cpufreq_power_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus, + struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { @@ -82,15 +84,14 @@ of_cpufreq_power_cooling_register(struct device_node *np, */ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev); -unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq); #else /* !CONFIG_CPU_THERMAL */ static inline struct thermal_cooling_device * -cpufreq_cooling_register(const struct cpumask *clip_cpus) +cpufreq_cooling_register(struct cpufreq_policy *policy) { return ERR_PTR(-ENOSYS); } static inline struct thermal_cooling_device * -cpufreq_power_cooling_register(const struct cpumask *clip_cpus, +cpufreq_power_cooling_register(struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { return NULL; @@ -98,14 +99,14 @@ cpufreq_power_cooling_register(const struct cpumask *clip_cpus, static inline struct thermal_cooling_device * of_cpufreq_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus) + struct cpufreq_policy *policy) { return ERR_PTR(-ENOSYS); } static inline struct thermal_cooling_device * of_cpufreq_power_cooling_register(struct device_node *np, - const struct cpumask *clip_cpus, + struct cpufreq_policy *policy, u32 capacitance, get_static_t plat_static_func) { @@ -117,11 +118,6 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev) { return; } -static inline -unsigned long cpufreq_cooling_get_level(unsigned int cpu, unsigned int freq) -{ - return THERMAL_CSTATE_INVALID; -} #endif /* CONFIG_CPU_THERMAL */ #endif /* __CPU_COOLING_H__ */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 905117bd5012..f10a9b3761cd 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -862,6 +862,20 @@ static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy, return -EINVAL; } } + +static inline int cpufreq_table_count_valid_entries(const struct cpufreq_policy *policy) +{ + struct cpufreq_frequency_table *pos; + int count = 0; + + if (unlikely(!policy->freq_table)) + return 0; + + cpufreq_for_each_valid_entry(pos, policy->freq_table) + count++; + + return count; +} #else static inline int cpufreq_boost_trigger_state(int state) { diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 4090a42578a8..2df2118fbe13 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -19,7 +19,7 @@ CRASH_CORE_NOTE_NAME_BYTES + \ CRASH_CORE_NOTE_DESC_BYTES) -#define VMCOREINFO_BYTES (4096) +#define VMCOREINFO_BYTES PAGE_SIZE #define VMCOREINFO_NOTE_NAME "VMCOREINFO" #define VMCOREINFO_NOTE_NAME_BYTES ALIGN(sizeof(VMCOREINFO_NOTE_NAME), 4) #define VMCOREINFO_NOTE_SIZE ((CRASH_CORE_NOTE_HEAD_BYTES * 2) + \ @@ -28,6 +28,7 @@ typedef u32 note_buf_t[CRASH_CORE_NOTE_BYTES/4]; +void crash_update_vmcoreinfo_safecopy(void *ptr); void crash_save_vmcoreinfo(void); void arch_crash_save_vmcoreinfo(void); __printf(1, 2) @@ -56,9 +57,7 @@ phys_addr_t paddr_vmcoreinfo_note(void); #define VMCOREINFO_CONFIG(name) \ vmcoreinfo_append_str("CONFIG_%s=y\n", #name) -extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; -extern size_t vmcoreinfo_size; -extern size_t vmcoreinfo_max_size; +extern u32 *vmcoreinfo_note; Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, void *data, size_t data_len); diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index fbecbd089d75..92e165d417a6 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -2,6 +2,7 @@ #define CEPH_CRUSH_CRUSH_H #ifdef __KERNEL__ +# include <linux/rbtree.h> # include <linux/types.h> #else # include "crush_compat.h" @@ -137,6 +138,68 @@ struct crush_bucket { }; +/** @ingroup API + * + * Replacement weights for each item in a bucket. The size of the + * array must be exactly the size of the straw2 bucket, just as the + * item_weights array. + * + */ +struct crush_weight_set { + __u32 *weights; /*!< 16.16 fixed point weights + in the same order as items */ + __u32 size; /*!< size of the __weights__ array */ +}; + +/** @ingroup API + * + * Replacement weights and ids for a given straw2 bucket, for + * placement purposes. + * + * When crush_do_rule() chooses the Nth item from a straw2 bucket, the + * replacement weights found at __weight_set[N]__ are used instead of + * the weights from __item_weights__. If __N__ is greater than + * __weight_set_size__, the weights found at __weight_set_size-1__ are + * used instead. For instance if __weight_set__ is: + * + * [ [ 0x10000, 0x20000 ], // position 0 + * [ 0x20000, 0x40000 ] ] // position 1 + * + * choosing the 0th item will use position 0 weights [ 0x10000, 0x20000 ] + * choosing the 1th item will use position 1 weights [ 0x20000, 0x40000 ] + * choosing the 2th item will use position 1 weights [ 0x20000, 0x40000 ] + * etc. + * + */ +struct crush_choose_arg { + __s32 *ids; /*!< values to use instead of items */ + __u32 ids_size; /*!< size of the __ids__ array */ + struct crush_weight_set *weight_set; /*!< weight replacements for + a given position */ + __u32 weight_set_size; /*!< size of the __weight_set__ array */ +}; + +/** @ingroup API + * + * Replacement weights and ids for each bucket in the crushmap. The + * __size__ of the __args__ array must be exactly the same as the + * __map->max_buckets__. + * + * The __crush_choose_arg__ at index N will be used when choosing + * an item from the bucket __map->buckets[N]__ bucket, provided it + * is a straw2 bucket. + * + */ +struct crush_choose_arg_map { +#ifdef __KERNEL__ + struct rb_node node; + u64 choose_args_index; +#endif + struct crush_choose_arg *args; /*!< replacement for each bucket + in the crushmap */ + __u32 size; /*!< size of the __args__ array */ +}; + struct crush_bucket_uniform { struct crush_bucket h; __u32 item_weight; /* 16-bit fixed point; all items equally weighted */ @@ -236,6 +299,9 @@ struct crush_map { __u32 allowed_bucket_algs; __u32 *choose_tries; +#else + /* CrushWrapper::choose_args */ + struct rb_root choose_args; #endif }; diff --git a/include/linux/crush/mapper.h b/include/linux/crush/mapper.h index c95e19e1ff11..141edabb947e 100644 --- a/include/linux/crush/mapper.h +++ b/include/linux/crush/mapper.h @@ -11,11 +11,10 @@ #include "crush.h" extern int crush_find_rule(const struct crush_map *map, int ruleset, int type, int size); -extern int crush_do_rule(const struct crush_map *map, - int ruleno, - int x, int *result, int result_max, - const __u32 *weights, int weight_max, - void *cwin); +int crush_do_rule(const struct crush_map *map, + int ruleno, int x, int *result, int result_max, + const __u32 *weight, int weight_max, + void *cwin, const struct crush_choose_arg *choose_args); /* * Returns the exact amount of workspace that will need to be used diff --git a/include/linux/dax.h b/include/linux/dax.h index 8f39db7439c3..794811875732 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -154,11 +154,6 @@ static inline unsigned int dax_radix_order(void *entry) #endif int dax_pfn_mkwrite(struct vm_fault *vmf); -static inline bool vma_is_dax(struct vm_area_struct *vma) -{ - return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); -} - static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 025727bf6797..c706eaac692e 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -592,8 +592,8 @@ static inline struct inode *d_real_inode(const struct dentry *dentry) } struct name_snapshot { - const char *name; - char inline_name[DNAME_INLINE_LEN]; + const unsigned char *name; + unsigned char inline_name[DNAME_INLINE_LEN]; }; void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *); void release_dentry_name_snapshot(struct name_snapshot *); diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h index 6daf6d4971f6..2f14ac73d01d 100644 --- a/include/linux/eventpoll.h +++ b/include/linux/eventpoll.h @@ -14,6 +14,7 @@ #define _LINUX_EVENTPOLL_H #include <uapi/linux/eventpoll.h> +#include <uapi/linux/kcmp.h> /* Forward declarations to avoid compiler errors */ @@ -22,6 +23,10 @@ struct file; #ifdef CONFIG_EPOLL +#ifdef CONFIG_CHECKPOINT_RESTORE +struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff); +#endif + /* Used to initialize the epoll bits inside the "struct file" */ static inline void eventpoll_init_file(struct file *file) { diff --git a/include/linux/extable.h b/include/linux/extable.h index 7effea4b257d..28addad0dda7 100644 --- a/include/linux/extable.h +++ b/include/linux/extable.h @@ -2,13 +2,14 @@ #define _LINUX_EXTABLE_H #include <linux/stddef.h> /* for NULL */ +#include <linux/types.h> struct module; struct exception_table_entry; const struct exception_table_entry * -search_extable(const struct exception_table_entry *first, - const struct exception_table_entry *last, +search_extable(const struct exception_table_entry *base, + const size_t num, unsigned long value); void sort_extable(struct exception_table_entry *start, struct exception_table_entry *finish); diff --git a/include/linux/fs.h b/include/linux/fs.h index 0cfa47125d52..976aaa1af82a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -18,6 +18,7 @@ #include <linux/bug.h> #include <linux/mutex.h> #include <linux/rwsem.h> +#include <linux/mm_types.h> #include <linux/capability.h> #include <linux/semaphore.h> #include <linux/fcntl.h> @@ -1954,6 +1955,9 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) * wb stat updates to grab mapping->tree_lock. See * inode_switch_wb_work_fn() for details. * + * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper + * and work dirs among overlayfs mounts. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -1974,6 +1978,7 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) #define __I_DIRTY_TIME_EXPIRED 12 #define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED) #define I_WB_SWITCH (1 << 13) +#define I_OVL_INUSE (1 << 14) #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES) #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) @@ -3127,6 +3132,11 @@ static inline bool io_is_direct(struct file *filp) return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host); } +static inline bool vma_is_dax(struct vm_area_struct *vma) +{ + return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); +} + static inline int iocb_flags(struct file *file) { int res = 0; diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 3dff2398a5f0..9ab375419189 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -12,6 +12,8 @@ #ifndef _LINUX_FWNODE_H_ #define _LINUX_FWNODE_H_ +#include <linux/types.h> + enum fwnode_type { FWNODE_INVALID = 0, FWNODE_OF, @@ -22,9 +24,12 @@ enum fwnode_type { FWNODE_IRQCHIP }; +struct fwnode_operations; + struct fwnode_handle { enum fwnode_type type; struct fwnode_handle *secondary; + const struct fwnode_operations *ops; }; /** @@ -39,4 +44,68 @@ struct fwnode_endpoint { const struct fwnode_handle *local_fwnode; }; +/** + * struct fwnode_operations - Operations for fwnode interface + * @get: Get a reference to an fwnode. + * @put: Put a reference to an fwnode. + * @property_present: Return true if a property is present. + * @property_read_integer_array: Read an array of integer properties. Return + * zero on success, a negative error code + * otherwise. + * @property_read_string_array: Read an array of string properties. Return zero + * on success, a negative error code otherwise. + * @get_parent: Return the parent of an fwnode. + * @get_next_child_node: Return the next child node in an iteration. + * @get_named_child_node: Return a child node with a given name. + * @graph_get_next_endpoint: Return an endpoint node in an iteration. + * @graph_get_remote_endpoint: Return the remote endpoint node of a local + * endpoint node. + * @graph_get_port_parent: Return the parent node of a port node. + * @graph_parse_endpoint: Parse endpoint for port and endpoint id. + */ +struct fwnode_operations { + void (*get)(struct fwnode_handle *fwnode); + void (*put)(struct fwnode_handle *fwnode); + bool (*device_is_available)(struct fwnode_handle *fwnode); + bool (*property_present)(struct fwnode_handle *fwnode, + const char *propname); + int (*property_read_int_array)(struct fwnode_handle *fwnode, + const char *propname, + unsigned int elem_size, void *val, + size_t nval); + int (*property_read_string_array)(struct fwnode_handle *fwnode_handle, + const char *propname, + const char **val, size_t nval); + struct fwnode_handle *(*get_parent)(struct fwnode_handle *fwnode); + struct fwnode_handle * + (*get_next_child_node)(struct fwnode_handle *fwnode, + struct fwnode_handle *child); + struct fwnode_handle * + (*get_named_child_node)(struct fwnode_handle *fwnode, const char *name); + struct fwnode_handle * + (*graph_get_next_endpoint)(struct fwnode_handle *fwnode, + struct fwnode_handle *prev); + struct fwnode_handle * + (*graph_get_remote_endpoint)(struct fwnode_handle *fwnode); + struct fwnode_handle * + (*graph_get_port_parent)(struct fwnode_handle *fwnode); + int (*graph_parse_endpoint)(struct fwnode_handle *fwnode, + struct fwnode_endpoint *endpoint); +}; + +#define fwnode_has_op(fwnode, op) \ + ((fwnode) && (fwnode)->ops && (fwnode)->ops->op) +#define fwnode_call_int_op(fwnode, op, ...) \ + (fwnode ? (fwnode_has_op(fwnode, op) ? \ + (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : -ENXIO) : \ + -EINVAL) +#define fwnode_call_ptr_op(fwnode, op, ...) \ + (fwnode_has_op(fwnode, op) ? \ + (fwnode)->ops->op(fwnode, ## __VA_ARGS__) : NULL) +#define fwnode_call_void_op(fwnode, op, ...) \ + do { \ + if (fwnode_has_op(fwnode, op)) \ + (fwnode)->ops->op(fwnode, ## __VA_ARGS__); \ + } while (false) + #endif diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 4c6656f1fee7..bcfb9f7c46f5 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -25,7 +25,7 @@ struct vm_area_struct; #define ___GFP_FS 0x80u #define ___GFP_COLD 0x100u #define ___GFP_NOWARN 0x200u -#define ___GFP_REPEAT 0x400u +#define ___GFP_RETRY_MAYFAIL 0x400u #define ___GFP_NOFAIL 0x800u #define ___GFP_NORETRY 0x1000u #define ___GFP_MEMALLOC 0x2000u @@ -136,26 +136,56 @@ struct vm_area_struct; * * __GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim. * - * __GFP_REPEAT: Try hard to allocate the memory, but the allocation attempt - * _might_ fail. This depends upon the particular VM implementation. + * The default allocator behavior depends on the request size. We have a concept + * of so called costly allocations (with order > PAGE_ALLOC_COSTLY_ORDER). + * !costly allocations are too essential to fail so they are implicitly + * non-failing by default (with some exceptions like OOM victims might fail so + * the caller still has to check for failures) while costly requests try to be + * not disruptive and back off even without invoking the OOM killer. + * The following three modifiers might be used to override some of these + * implicit rules + * + * __GFP_NORETRY: The VM implementation will try only very lightweight + * memory direct reclaim to get some memory under memory pressure (thus + * it can sleep). It will avoid disruptive actions like OOM killer. The + * caller must handle the failure which is quite likely to happen under + * heavy memory pressure. The flag is suitable when failure can easily be + * handled at small cost, such as reduced throughput + * + * __GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim + * procedures that have previously failed if there is some indication + * that progress has been made else where. It can wait for other + * tasks to attempt high level approaches to freeing memory such as + * compaction (which removes fragmentation) and page-out. + * There is still a definite limit to the number of retries, but it is + * a larger limit than with __GFP_NORETRY. + * Allocations with this flag may fail, but only when there is + * genuinely little unused memory. While these allocations do not + * directly trigger the OOM killer, their failure indicates that + * the system is likely to need to use the OOM killer soon. The + * caller must handle failure, but can reasonably do so by failing + * a higher-level request, or completing it only in a much less + * efficient manner. + * If the allocation does fail, and the caller is in a position to + * free some non-essential memory, doing so could benefit the system + * as a whole. * * __GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller - * cannot handle allocation failures. New users should be evaluated carefully - * (and the flag should be used only when there is no reasonable failure - * policy) but it is definitely preferable to use the flag rather than - * opencode endless loop around allocator. - * - * __GFP_NORETRY: The VM implementation must not retry indefinitely and will - * return NULL when direct reclaim and memory compaction have failed to allow - * the allocation to succeed. The OOM killer is not called with the current - * implementation. + * cannot handle allocation failures. The allocation could block + * indefinitely but will never return with failure. Testing for + * failure is pointless. + * New users should be evaluated carefully (and the flag should be + * used only when there is no reasonable failure policy) but it is + * definitely preferable to use the flag rather than opencode endless + * loop around allocator. + * Using this flag for costly allocations is _highly_ discouraged. */ #define __GFP_IO ((__force gfp_t)___GFP_IO) #define __GFP_FS ((__force gfp_t)___GFP_FS) #define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */ #define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */ #define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM)) -#define __GFP_REPEAT ((__force gfp_t)___GFP_REPEAT) +#define __GFP_RETRY_MAYFAIL ((__force gfp_t)___GFP_RETRY_MAYFAIL) #define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL) #define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index d3b3e8fcc717..ee696347f928 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -1,6 +1,10 @@ #ifndef _LINUX_HUGE_MM_H #define _LINUX_HUGE_MM_H +#include <linux/sched/coredump.h> + +#include <linux/fs.h> /* only for vma_is_dax() */ + extern int do_huge_pmd_anonymous_page(struct vm_fault *vmf); extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, @@ -85,14 +89,32 @@ extern struct kobj_attribute shmem_enabled_attr; extern bool is_vma_temporary_stack(struct vm_area_struct *vma); -#define transparent_hugepage_enabled(__vma) \ - ((transparent_hugepage_flags & \ - (1<<TRANSPARENT_HUGEPAGE_FLAG) || \ - (transparent_hugepage_flags & \ - (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG) && \ - ((__vma)->vm_flags & VM_HUGEPAGE))) && \ - !((__vma)->vm_flags & VM_NOHUGEPAGE) && \ - !is_vma_temporary_stack(__vma)) +extern unsigned long transparent_hugepage_flags; + +static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_NOHUGEPAGE) + return false; + + if (is_vma_temporary_stack(vma)) + return false; + + if (test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + return false; + + if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG)) + return true; + + if (vma_is_dax(vma)) + return true; + + if (transparent_hugepage_flags & + (1 << TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)) + return !!(vma->vm_flags & VM_HUGEPAGE); + + return false; +} + #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) @@ -104,8 +126,6 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma); #define transparent_hugepage_debug_cow() 0 #endif /* CONFIG_DEBUG_VM */ -extern unsigned long transparent_hugepage_flags; - extern unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); @@ -224,7 +244,10 @@ void mm_put_huge_zero_page(struct mm_struct *mm); #define hpage_nr_pages(x) 1 -#define transparent_hugepage_enabled(__vma) 0 +static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) +{ + return false; +} static inline void prep_transhuge_page(struct page *page) {} diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 46bfb702e7d6..8d9fe131a240 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -116,7 +116,6 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to, vm_flags_t vm_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); -int dequeue_hwpoisoned_huge_page(struct page *page); bool isolate_huge_page(struct page *page, struct list_head *list); void putback_active_hugepage(struct page *page); void free_huge_page(struct page *page); @@ -192,10 +191,6 @@ static inline void hugetlb_show_meminfo(void) #define hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \ src_addr, pagep) ({ BUG(); 0; }) #define huge_pte_offset(mm, address, sz) 0 -static inline int dequeue_hwpoisoned_huge_page(struct page *page) -{ - return 0; -} static inline bool isolate_huge_page(struct page *page, struct list_head *list) { @@ -354,6 +349,8 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, struct page *alloc_huge_page_node(struct hstate *h, int nid); struct page *alloc_huge_page_noerr(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); +struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid, + nodemask_t *nmask); int huge_add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t idx); @@ -472,6 +469,7 @@ static inline pgoff_t basepage_index(struct page *page) return __basepage_index(page); } +extern int dissolve_free_huge_page(struct page *page); extern int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn); static inline bool hugepage_migration_supported(struct hstate *h) @@ -528,6 +526,7 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr struct hstate {}; #define alloc_huge_page(v, a, r) NULL #define alloc_huge_page_node(h, nid) NULL +#define alloc_huge_page_nodemask(h, preferred_nid, nmask) NULL #define alloc_huge_page_noerr(v, a, r) NULL #define alloc_bootmem_huge_page(h) NULL #define hstate_file(f) NULL @@ -550,15 +549,37 @@ static inline unsigned int pages_per_huge_page(struct hstate *h) { return 1; } -#define hstate_index_to_shift(index) 0 -#define hstate_index(h) 0 + +static inline unsigned hstate_index_to_shift(unsigned index) +{ + return 0; +} + +static inline int hstate_index(struct hstate *h) +{ + return 0; +} static inline pgoff_t basepage_index(struct page *page) { return page->index; } -#define dissolve_free_huge_pages(s, e) 0 -#define hugepage_migration_supported(h) false + +static inline int dissolve_free_huge_page(struct page *page) +{ + return 0; +} + +static inline int dissolve_free_huge_pages(unsigned long start_pfn, + unsigned long end_pfn) +{ + return 0; +} + +static inline bool hugepage_migration_supported(struct hstate *h) +{ + return false; +} static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 72d0ece70ed3..00ca5b86a753 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -295,6 +295,8 @@ static inline int i2c_slave_event(struct i2c_client *client, { return client->slave_cb(client, event, val); } +#else +static inline bool i2c_detect_slave_mode(struct device *dev) { return false; } #endif /** diff --git a/include/linux/i2c/i2c-sh_mobile.h b/include/linux/i2c/i2c-sh_mobile.h deleted file mode 100644 index 06e3089795fb..000000000000 --- a/include/linux/i2c/i2c-sh_mobile.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef __I2C_SH_MOBILE_H__ -#define __I2C_SH_MOBILE_H__ - -#include <linux/platform_device.h> - -struct i2c_sh_mobile_platform_data { - unsigned long bus_speed; - unsigned int clks_per_count; -}; - -#endif /* __I2C_SH_MOBILE_H__ */ diff --git a/include/linux/initrd.h b/include/linux/initrd.h index 55289d261b4f..bc67b767f9ce 100644 --- a/include/linux/initrd.h +++ b/include/linux/initrd.h @@ -10,6 +10,9 @@ extern int rd_prompt; /* starting block # of image */ extern int rd_image_start; +/* size of a single RAM disk */ +extern unsigned long rd_size; + /* 1 if it is not an error if initrd_start < memory_start */ extern int initrd_below_start_ok; diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index 3c25794042f9..99bc5b3ae26e 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -102,6 +102,21 @@ extern int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, */ extern int intel_svm_unbind_mm(struct device *dev, int pasid); +/** + * intel_svm_is_pasid_valid() - check if pasid is valid + * @dev: Device for which PASID was allocated + * @pasid: PASID value to be checked + * + * This function checks if the specified pasid is still valid. A + * valid pasid means the backing mm is still having a valid user. + * For kernel callers init_mm is always valid. for other mm, if mm->mm_users + * is non-zero, it is valid. + * + * returns -EINVAL if invalid pasid, 0 if pasid ref count is invalid + * 1 if pasid is valid. + */ +extern int intel_svm_is_pasid_valid(struct device *dev, int pasid); + #else /* CONFIG_INTEL_IOMMU_SVM */ static inline int intel_svm_bind_mm(struct device *dev, int *pasid, @@ -114,6 +129,11 @@ static inline int intel_svm_unbind_mm(struct device *dev, int pasid) { BUG(); } + +static int intel_svm_is_pasid_valid(struct device *dev, int pasid) +{ + return -EINVAL; +} #endif /* CONFIG_INTEL_IOMMU_SVM */ #define intel_svm_available(dev) (!intel_svm_bind_mm((dev), NULL, 0, NULL)) diff --git a/include/linux/ipc.h b/include/linux/ipc.h index 71fd92d81b26..5591f055e13f 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -20,6 +20,9 @@ struct kern_ipc_perm { umode_t mode; unsigned long seq; void *security; + + struct rcu_head rcu; + atomic_t refcount; } ____cacheline_aligned_in_smp; #endif /* _LINUX_IPC_H */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 1c91f26e2996..bd6d96cf80b1 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -11,6 +11,7 @@ #include <linux/log2.h> #include <linux/typecheck.h> #include <linux/printk.h> +#include <linux/build_bug.h> #include <asm/byteorder.h> #include <uapi/linux/kernel.h> @@ -854,9 +855,12 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * @member: the name of the member within the struct. * */ -#define container_of(ptr, type, member) ({ \ - const typeof( ((type *)0)->member ) *__mptr = (ptr); \ - (type *)( (char *)__mptr - offsetof(type,member) );}) +#define container_of(ptr, type, member) ({ \ + void *__mptr = (void *)(ptr); \ + BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ + !__same_type(*(ptr), void), \ + "pointer type mismatch in container_of()"); \ + ((type *)(__mptr - offsetof(type, member))); }) /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */ #ifdef CONFIG_FTRACE_MCOUNT_RECORD diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 65888418fb69..dd056fab9e35 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -172,6 +172,7 @@ struct kimage { unsigned long start; struct page *control_code_page; struct page *swap_page; + void *vmcoreinfo_data_copy; /* locates in the crash memory */ unsigned long nr_segments; struct kexec_segment segment[KEXEC_SEGMENT_MAX]; @@ -241,6 +242,7 @@ extern void crash_kexec(struct pt_regs *); int kexec_should_crash(struct task_struct *); int kexec_crash_loaded(void); void crash_save_cpu(struct pt_regs *regs, int cpu); +extern int kimage_crash_copy_vmcoreinfo(struct kimage *image); extern struct kimage *kexec_image; extern struct kimage *kexec_crash_image; diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h index 5d9a400af509..f0d7335336cd 100644 --- a/include/linux/khugepaged.h +++ b/include/linux/khugepaged.h @@ -48,7 +48,8 @@ static inline int khugepaged_enter(struct vm_area_struct *vma, if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags)) if ((khugepaged_always() || (khugepaged_req_madv() && (vm_flags & VM_HUGEPAGE))) && - !(vm_flags & VM_NOHUGEPAGE)) + !(vm_flags & VM_NOHUGEPAGE) && + !test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) if (__khugepaged_enter(vma->vm_mm)) return -ENOMEM; return 0; diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index cb0ba9f2a9a2..fa7fd03cb5f9 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -44,6 +44,7 @@ struct list_lru_node { /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */ struct list_lru_memcg *memcg_lrus; #endif + long nr_items; } ____cacheline_aligned_in_smp; struct list_lru { diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index 41f7b6a04d69..3eca67728366 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -192,9 +192,9 @@ struct nlm_block { * Global variables */ extern const struct rpc_program nlm_program; -extern struct svc_procedure nlmsvc_procedures[]; +extern const struct svc_procedure nlmsvc_procedures[]; #ifdef CONFIG_LOCKD_V4 -extern struct svc_procedure nlmsvc_procedures4[]; +extern const struct svc_procedure nlmsvc_procedures4[]; #endif extern int nlmsvc_grace_period; extern unsigned long nlmsvc_timeout; diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index d39ed1cc5fbf..7acbecc21a40 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -95,19 +95,19 @@ struct nlm_reboot { */ #define NLMSVC_XDRSIZE sizeof(struct nlm_args) -int nlmsvc_decode_testargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlmsvc_decode_res(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlmsvc_encode_void(struct svc_rqst *, __be32 *, void *); -int nlmsvc_decode_void(struct svc_rqst *, __be32 *, void *); -int nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlmsvc_decode_notify(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlmsvc_decode_reboot(struct svc_rqst *, __be32 *, struct nlm_reboot *); +int nlmsvc_decode_testargs(struct svc_rqst *, __be32 *); +int nlmsvc_encode_testres(struct svc_rqst *, __be32 *); +int nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *); +int nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *); +int nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *); +int nlmsvc_encode_res(struct svc_rqst *, __be32 *); +int nlmsvc_decode_res(struct svc_rqst *, __be32 *); +int nlmsvc_encode_void(struct svc_rqst *, __be32 *); +int nlmsvc_decode_void(struct svc_rqst *, __be32 *); +int nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *); +int nlmsvc_encode_shareres(struct svc_rqst *, __be32 *); +int nlmsvc_decode_notify(struct svc_rqst *, __be32 *); +int nlmsvc_decode_reboot(struct svc_rqst *, __be32 *); /* int nlmclt_encode_testargs(struct rpc_rqst *, u32 *, struct nlm_args *); int nlmclt_encode_lockargs(struct rpc_rqst *, u32 *, struct nlm_args *); diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index e58c88b52ce1..bf1645609225 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -23,19 +23,19 @@ -int nlm4svc_decode_testargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_encode_testres(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_encode_res(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlm4svc_decode_res(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlm4svc_encode_void(struct svc_rqst *, __be32 *, void *); -int nlm4svc_decode_void(struct svc_rqst *, __be32 *, void *); -int nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_encode_shareres(struct svc_rqst *, __be32 *, struct nlm_res *); -int nlm4svc_decode_notify(struct svc_rqst *, __be32 *, struct nlm_args *); -int nlm4svc_decode_reboot(struct svc_rqst *, __be32 *, struct nlm_reboot *); +int nlm4svc_decode_testargs(struct svc_rqst *, __be32 *); +int nlm4svc_encode_testres(struct svc_rqst *, __be32 *); +int nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *); +int nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *); +int nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *); +int nlm4svc_encode_res(struct svc_rqst *, __be32 *); +int nlm4svc_decode_res(struct svc_rqst *, __be32 *); +int nlm4svc_encode_void(struct svc_rqst *, __be32 *); +int nlm4svc_decode_void(struct svc_rqst *, __be32 *); +int nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *); +int nlm4svc_encode_shareres(struct svc_rqst *, __be32 *); +int nlm4svc_decode_notify(struct svc_rqst *, __be32 *); +int nlm4svc_decode_reboot(struct svc_rqst *, __be32 *); /* int nlmclt_encode_testargs(struct rpc_rqst *, u32 *, struct nlm_args *); int nlmclt_encode_lockargs(struct rpc_rqst *, u32 *, struct nlm_args *); diff --git a/include/linux/mfd/cros_ec.h b/include/linux/mfd/cros_ec.h index 28baee63eaf6..4e887ba22635 100644 --- a/include/linux/mfd/cros_ec.h +++ b/include/linux/mfd/cros_ec.h @@ -149,6 +149,7 @@ struct cros_ec_device { struct ec_response_get_next_event event_data; int event_size; + u32 host_event_wake_mask; }; /** @@ -172,6 +173,8 @@ struct cros_ec_platform { u16 cmd_offset; }; +struct cros_ec_debugfs; + /* * struct cros_ec_dev - ChromeOS EC device entry point * @@ -179,6 +182,7 @@ struct cros_ec_platform { * @cdev: Character device structure in /dev * @ec_dev: cros_ec_device structure to talk to the physical device * @dev: pointer to the platform device + * @debug_info: cros_ec_debugfs structure for debugging information * @cmd_offset: offset to apply for each command. */ struct cros_ec_dev { @@ -186,6 +190,7 @@ struct cros_ec_dev { struct cdev cdev; struct cros_ec_device *ec_dev; struct device *dev; + struct cros_ec_debugfs *debug_info; u16 cmd_offset; u32 features[2]; }; @@ -295,10 +300,22 @@ int cros_ec_query_all(struct cros_ec_device *ec_dev); * cros_ec_get_next_event - Fetch next event from the ChromeOS EC * * @ec_dev: Device to fetch event from + * @wake_event: Pointer to a bool set to true upon return if the event might be + * treated as a wake event. Ignored if null. * * Returns: 0 on success, Linux error number on failure */ -int cros_ec_get_next_event(struct cros_ec_device *ec_dev); +int cros_ec_get_next_event(struct cros_ec_device *ec_dev, bool *wake_event); + +/** + * cros_ec_get_host_event - Return a mask of event set by the EC. + * + * When MKBP is supported, when the EC raises an interrupt, + * We collect the events raised and call the functions in the ec notifier. + * + * This function is a helper to know which events are raised. + */ +u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); /* sysfs stuff */ extern struct attribute_group cros_ec_attr_group; diff --git a/include/linux/mfd/cros_ec_commands.h b/include/linux/mfd/cros_ec_commands.h index c93e7e0300ef..190c8f4afa02 100644 --- a/include/linux/mfd/cros_ec_commands.h +++ b/include/linux/mfd/cros_ec_commands.h @@ -625,6 +625,10 @@ struct ec_params_get_cmd_versions { uint8_t cmd; /* Command to check */ } __packed; +struct ec_params_get_cmd_versions_v1 { + uint16_t cmd; /* Command to check */ +} __packed; + struct ec_response_get_cmd_versions { /* * Mask of supported versions; use EC_VER_MASK() to compare with a @@ -1158,13 +1162,20 @@ struct lightbar_params_v1 { struct rgb_s color[8]; /* 0-3 are Google colors */ } __packed; +/* Lightbar program */ +#define EC_LB_PROG_LEN 192 +struct lightbar_program { + uint8_t size; + uint8_t data[EC_LB_PROG_LEN]; +}; + struct ec_params_lightbar { uint8_t cmd; /* Command (see enum lightbar_command) */ union { struct { /* no args */ } dump, off, on, init, get_seq, get_params_v0, get_params_v1, - version, get_brightness, get_demo; + version, get_brightness, get_demo, suspend, resume; struct { uint8_t num; @@ -1182,8 +1193,13 @@ struct ec_params_lightbar { uint8_t led; } get_rgb; + struct { + uint8_t enable; + } manual_suspend_ctrl; + struct lightbar_params_v0 set_params_v0; struct lightbar_params_v1 set_params_v1; + struct lightbar_program set_program; }; } __packed; @@ -1216,7 +1232,8 @@ struct ec_response_lightbar { struct { /* no return params */ } off, on, init, set_brightness, seq, reg, set_rgb, - demo, set_params_v0, set_params_v1; + demo, set_params_v0, set_params_v1, + set_program, manual_suspend_ctrl, suspend, resume; }; } __packed; @@ -1240,6 +1257,10 @@ enum lightbar_command { LIGHTBAR_CMD_GET_DEMO = 15, LIGHTBAR_CMD_GET_PARAMS_V1 = 16, LIGHTBAR_CMD_SET_PARAMS_V1 = 17, + LIGHTBAR_CMD_SET_PROGRAM = 18, + LIGHTBAR_CMD_MANUAL_SUSPEND_CTRL = 19, + LIGHTBAR_CMD_SUSPEND = 20, + LIGHTBAR_CMD_RESUME = 21, LIGHTBAR_NUM_CMDS }; @@ -2285,13 +2306,28 @@ struct ec_params_charge_control { #define EC_CMD_CONSOLE_SNAPSHOT 0x97 /* - * Read next chunk of data from saved snapshot. + * Read data from the saved snapshot. If the subcmd parameter is + * CONSOLE_READ_NEXT, this will return data starting from the beginning of + * the latest snapshot. If it is CONSOLE_READ_RECENT, it will start from the + * end of the previous snapshot. + * + * The params are only looked at in version >= 1 of this command. Prior + * versions will just default to CONSOLE_READ_NEXT behavior. * * Response is null-terminated string. Empty string, if there is no more * remaining output. */ #define EC_CMD_CONSOLE_READ 0x98 +enum ec_console_read_subcmd { + CONSOLE_READ_NEXT = 0, + CONSOLE_READ_RECENT +}; + +struct ec_params_console_read_v1 { + uint8_t subcmd; /* enum ec_console_read_subcmd */ +} __packed; + /*****************************************************************************/ /* diff --git a/include/linux/mfd/cros_ec_lpc_mec.h b/include/linux/mfd/cros_ec_lpc_mec.h new file mode 100644 index 000000000000..176496ddc66c --- /dev/null +++ b/include/linux/mfd/cros_ec_lpc_mec.h @@ -0,0 +1,90 @@ +/* + * cros_ec_lpc_mec - LPC variant I/O for Microchip EC + * + * Copyright (C) 2016 Google, Inc + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * This driver uses the Chrome OS EC byte-level message-based protocol for + * communicating the keyboard state (which keys are pressed) from a keyboard EC + * to the AP over some bus (such as i2c, lpc, spi). The EC does debouncing, + * but everything else (including deghosting) is done here. The main + * motivation for this is to keep the EC firmware as simple as possible, since + * it cannot be easily upgraded and EC flash/IRAM space is relatively + * expensive. + */ + +#ifndef __LINUX_MFD_CROS_EC_MEC_H +#define __LINUX_MFD_CROS_EC_MEC_H + +#include <linux/mfd/cros_ec_commands.h> + +enum cros_ec_lpc_mec_emi_access_mode { + /* 8-bit access */ + ACCESS_TYPE_BYTE = 0x0, + /* 16-bit access */ + ACCESS_TYPE_WORD = 0x1, + /* 32-bit access */ + ACCESS_TYPE_LONG = 0x2, + /* + * 32-bit access, read or write of MEC_EMI_EC_DATA_B3 causes the + * EC data register to be incremented. + */ + ACCESS_TYPE_LONG_AUTO_INCREMENT = 0x3, +}; + +enum cros_ec_lpc_mec_io_type { + MEC_IO_READ, + MEC_IO_WRITE, +}; + +/* Access IO ranges 0x800 thru 0x9ff using EMI interface instead of LPC */ +#define MEC_EMI_RANGE_START EC_HOST_CMD_REGION0 +#define MEC_EMI_RANGE_END (EC_LPC_ADDR_MEMMAP + EC_MEMMAP_SIZE) + +/* EMI registers are relative to base */ +#define MEC_EMI_BASE 0x800 +#define MEC_EMI_HOST_TO_EC (MEC_EMI_BASE + 0) +#define MEC_EMI_EC_TO_HOST (MEC_EMI_BASE + 1) +#define MEC_EMI_EC_ADDRESS_B0 (MEC_EMI_BASE + 2) +#define MEC_EMI_EC_ADDRESS_B1 (MEC_EMI_BASE + 3) +#define MEC_EMI_EC_DATA_B0 (MEC_EMI_BASE + 4) +#define MEC_EMI_EC_DATA_B1 (MEC_EMI_BASE + 5) +#define MEC_EMI_EC_DATA_B2 (MEC_EMI_BASE + 6) +#define MEC_EMI_EC_DATA_B3 (MEC_EMI_BASE + 7) + +/* + * cros_ec_lpc_mec_init + * + * Initialize MEC I/O. + */ +void cros_ec_lpc_mec_init(void); + +/* + * cros_ec_lpc_mec_destroy + * + * Cleanup MEC I/O. + */ +void cros_ec_lpc_mec_destroy(void); + +/** + * cros_ec_lpc_io_bytes_mec - Read / write bytes to MEC EMI port + * + * @io_type: MEC_IO_READ or MEC_IO_WRITE, depending on request + * @offset: Base read / write address + * @length: Number of bytes to read / write + * @buf: Destination / source buffer + * + * @return 8-bit checksum of all bytes read / written + */ +u8 cros_ec_lpc_io_bytes_mec(enum cros_ec_lpc_mec_io_type io_type, + unsigned int offset, unsigned int length, u8 *buf); + +#endif /* __LINUX_MFD_CROS_EC_MEC_H */ diff --git a/include/linux/mfd/cros_ec_lpc_reg.h b/include/linux/mfd/cros_ec_lpc_reg.h new file mode 100644 index 000000000000..5560bef63c2b --- /dev/null +++ b/include/linux/mfd/cros_ec_lpc_reg.h @@ -0,0 +1,61 @@ +/* + * cros_ec_lpc_reg - LPC access to the Chrome OS Embedded Controller + * + * Copyright (C) 2016 Google, Inc + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * This driver uses the Chrome OS EC byte-level message-based protocol for + * communicating the keyboard state (which keys are pressed) from a keyboard EC + * to the AP over some bus (such as i2c, lpc, spi). The EC does debouncing, + * but everything else (including deghosting) is done here. The main + * motivation for this is to keep the EC firmware as simple as possible, since + * it cannot be easily upgraded and EC flash/IRAM space is relatively + * expensive. + */ + +#ifndef __LINUX_MFD_CROS_EC_REG_H +#define __LINUX_MFD_CROS_EC_REG_H + +/** + * cros_ec_lpc_read_bytes - Read bytes from a given LPC-mapped address. + * Returns 8-bit checksum of all bytes read. + * + * @offset: Base read address + * @length: Number of bytes to read + * @dest: Destination buffer + */ +u8 cros_ec_lpc_read_bytes(unsigned int offset, unsigned int length, u8 *dest); + +/** + * cros_ec_lpc_write_bytes - Write bytes to a given LPC-mapped address. + * Returns 8-bit checksum of all bytes written. + * + * @offset: Base write address + * @length: Number of bytes to write + * @msg: Write data buffer + */ +u8 cros_ec_lpc_write_bytes(unsigned int offset, unsigned int length, u8 *msg); + +/** + * cros_ec_lpc_reg_init + * + * Initialize register I/O. + */ +void cros_ec_lpc_reg_init(void); + +/** + * cros_ec_lpc_reg_destroy + * + * Cleanup reg I/O. + */ +void cros_ec_lpc_reg_destroy(void); + +#endif /* __LINUX_MFD_CROS_EC_REG_H */ diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 48e24844b3c5..3e0d405dc842 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -4,6 +4,7 @@ #include <linux/mm.h> #include <linux/mempolicy.h> #include <linux/migrate_mode.h> +#include <linux/hugetlb.h> typedef struct page *new_page_t(struct page *page, unsigned long private, int **reason); @@ -30,6 +31,21 @@ enum migrate_reason { /* In mm/debug.c; also keep sync with include/trace/events/migrate.h */ extern char *migrate_reason_names[MR_TYPES]; +static inline struct page *new_page_nodemask(struct page *page, + int preferred_nid, nodemask_t *nodemask) +{ + gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL; + + if (PageHuge(page)) + return alloc_huge_page_nodemask(page_hstate(compound_head(page)), + preferred_nid, nodemask); + + if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE)) + gfp_mask |= __GFP_HIGHMEM; + + return __alloc_pages_nodemask(gfp_mask, 0, preferred_nid, nodemask); +} + #ifdef CONFIG_MIGRATION extern void putback_movable_pages(struct list_head *l); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7e8f100cb56d..fc14b8b3f6ce 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -603,12 +603,9 @@ extern struct page *mem_map; #endif /* - * The pg_data_t structure is used in machines with CONFIG_DISCONTIGMEM - * (mostly NUMA machines?) to denote a higher-level memory zone than the - * zone denotes. - * * On NUMA machines, each NUMA node would have a pg_data_t to describe - * it's memory layout. + * it's memory layout. On UMA machines there is a single pglist_data which + * describes the whole memory. * * Memory statistics and page replacement data structures are maintained on a * per-zone basis. @@ -1058,6 +1055,7 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) static inline unsigned long early_pfn_to_nid(unsigned long pfn) { + BUILD_BUG_ON(IS_ENABLED(CONFIG_NUMA)); return 0; } #endif diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index de0d889e4fe1..892148c448cc 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -107,6 +107,8 @@ int nand_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len); #define NAND_STATUS_READY 0x40 #define NAND_STATUS_WP 0x80 +#define NAND_DATA_IFACE_CHECK_ONLY -1 + /* * Constants for ECC_MODES */ @@ -116,6 +118,7 @@ typedef enum { NAND_ECC_HW, NAND_ECC_HW_SYNDROME, NAND_ECC_HW_OOB_FIRST, + NAND_ECC_ON_DIE, } nand_ecc_modes_t; enum nand_ecc_algo { @@ -257,6 +260,8 @@ struct nand_chip; /* Vendor-specific feature address (Micron) */ #define ONFI_FEATURE_ADDR_READ_RETRY 0x89 +#define ONFI_FEATURE_ON_DIE_ECC 0x90 +#define ONFI_FEATURE_ON_DIE_ECC_EN BIT(3) /* ONFI subfeature parameters length */ #define ONFI_SUBFEATURE_PARAM_LEN 4 @@ -477,6 +482,44 @@ static inline void nand_hw_control_init(struct nand_hw_control *nfc) } /** + * struct nand_ecc_step_info - ECC step information of ECC engine + * @stepsize: data bytes per ECC step + * @strengths: array of supported strengths + * @nstrengths: number of supported strengths + */ +struct nand_ecc_step_info { + int stepsize; + const int *strengths; + int nstrengths; +}; + +/** + * struct nand_ecc_caps - capability of ECC engine + * @stepinfos: array of ECC step information + * @nstepinfos: number of ECC step information + * @calc_ecc_bytes: driver's hook to calculate ECC bytes per step + */ +struct nand_ecc_caps { + const struct nand_ecc_step_info *stepinfos; + int nstepinfos; + int (*calc_ecc_bytes)(int step_size, int strength); +}; + +/* a shorthand to generate struct nand_ecc_caps with only one ECC stepsize */ +#define NAND_ECC_CAPS_SINGLE(__name, __calc, __step, ...) \ +static const int __name##_strengths[] = { __VA_ARGS__ }; \ +static const struct nand_ecc_step_info __name##_stepinfo = { \ + .stepsize = __step, \ + .strengths = __name##_strengths, \ + .nstrengths = ARRAY_SIZE(__name##_strengths), \ +}; \ +static const struct nand_ecc_caps __name = { \ + .stepinfos = &__name##_stepinfo, \ + .nstepinfos = 1, \ + .calc_ecc_bytes = __calc, \ +} + +/** * struct nand_ecc_ctrl - Control structure for ECC * @mode: ECC mode * @algo: ECC algorithm @@ -815,7 +858,10 @@ struct nand_manufacturer_ops { * @read_retries: [INTERN] the number of read retry modes supported * @onfi_set_features: [REPLACEABLE] set the features for ONFI nand * @onfi_get_features: [REPLACEABLE] get the features for ONFI nand - * @setup_data_interface: [OPTIONAL] setup the data interface and timing + * @setup_data_interface: [OPTIONAL] setup the data interface and timing. If + * chipnr is set to %NAND_DATA_IFACE_CHECK_ONLY this + * means the configuration should not be applied but + * only checked. * @bbt: [INTERN] bad block table pointer * @bbt_td: [REPLACEABLE] bad block table descriptor for flash * lookup. @@ -826,9 +872,6 @@ struct nand_manufacturer_ops { * structure which is shared among multiple independent * devices. * @priv: [OPTIONAL] pointer to private chip data - * @errstat: [OPTIONAL] hardware specific function to perform - * additional error status checks (determine if errors are - * correctable). * @manufacturer: [INTERN] Contains manufacturer information */ @@ -852,16 +895,13 @@ struct nand_chip { int(*waitfunc)(struct mtd_info *mtd, struct nand_chip *this); int (*erase)(struct mtd_info *mtd, int page); int (*scan_bbt)(struct mtd_info *mtd); - int (*errstat)(struct mtd_info *mtd, struct nand_chip *this, int state, - int status, int page); int (*onfi_set_features)(struct mtd_info *mtd, struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); int (*onfi_get_features)(struct mtd_info *mtd, struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); int (*setup_read_retry)(struct mtd_info *mtd, int retry_mode); - int (*setup_data_interface)(struct mtd_info *mtd, - const struct nand_data_interface *conf, - bool check_only); + int (*setup_data_interface)(struct mtd_info *mtd, int chipnr, + const struct nand_data_interface *conf); int chip_delay; @@ -1244,6 +1284,15 @@ int nand_check_erased_ecc_chunk(void *data, int datalen, void *extraoob, int extraooblen, int threshold); +int nand_check_ecc_caps(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail); + +int nand_match_ecc_req(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail); + +int nand_maximize_ecc(struct nand_chip *chip, + const struct nand_ecc_caps *caps, int oobavail); + /* Default write_oob implementation */ int nand_write_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page); @@ -1258,6 +1307,19 @@ int nand_read_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page); int nand_read_oob_syndrome(struct mtd_info *mtd, struct nand_chip *chip, int page); +/* Stub used by drivers that do not support GET/SET FEATURES operations */ +int nand_onfi_get_set_features_notsupp(struct mtd_info *mtd, + struct nand_chip *chip, int addr, + u8 *subfeature_param); + +/* Default read_page_raw implementation */ +int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip, + uint8_t *buf, int oob_required, int page); + +/* Default write_page_raw implementation */ +int nand_write_page_raw(struct mtd_info *mtd, 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); diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index 06df1e06b6e0..c4beb70dacbd 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -20,6 +20,12 @@ * * For each partition, these fields are available: * name: string that will be used to label the partition's MTD device. + * types: some partitions can be containers using specific format to describe + * embedded subpartitions / volumes. E.g. many home routers use "firmware" + * partition that contains at least kernel and rootfs. In such case an + * extra parser is needed that will detect these dynamic partitions and + * report them to the MTD subsystem. If set this property stores an array + * of parser names to use when looking for subpartitions. * size: the partition size; if defined as MTDPART_SIZ_FULL, the partition * will extend to the end of the master MTD device. * offset: absolute starting position within the master MTD device; if @@ -38,6 +44,7 @@ struct mtd_partition { const char *name; /* identifier string */ + const char *const *types; /* names of parsers to use if any */ 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 */ diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index f2a718030476..55faa2f07cca 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -73,6 +73,15 @@ #define SPINOR_OP_BE_32K_4B 0x5c /* Erase 32KiB block */ #define SPINOR_OP_SE_4B 0xdc /* Sector erase (usually 64KiB) */ +/* Double Transfer Rate opcodes - defined in JEDEC JESD216B. */ +#define SPINOR_OP_READ_1_1_1_DTR 0x0d +#define SPINOR_OP_READ_1_2_2_DTR 0xbd +#define SPINOR_OP_READ_1_4_4_DTR 0xed + +#define SPINOR_OP_READ_1_1_1_DTR_4B 0x0e +#define SPINOR_OP_READ_1_2_2_DTR_4B 0xbe +#define SPINOR_OP_READ_1_4_4_DTR_4B 0xee + /* Used for SST flashes only. */ #define SPINOR_OP_BP 0x02 /* Byte program */ #define SPINOR_OP_WRDI 0x04 /* Write disable */ @@ -119,13 +128,81 @@ /* Configuration Register bits. */ #define CR_QUAD_EN_SPAN BIT(1) /* Spansion Quad I/O */ -enum read_mode { - SPI_NOR_NORMAL = 0, - SPI_NOR_FAST, - SPI_NOR_DUAL, - SPI_NOR_QUAD, +/* Supported SPI protocols */ +#define SNOR_PROTO_INST_MASK GENMASK(23, 16) +#define SNOR_PROTO_INST_SHIFT 16 +#define SNOR_PROTO_INST(_nbits) \ + ((((unsigned long)(_nbits)) << SNOR_PROTO_INST_SHIFT) & \ + SNOR_PROTO_INST_MASK) + +#define SNOR_PROTO_ADDR_MASK GENMASK(15, 8) +#define SNOR_PROTO_ADDR_SHIFT 8 +#define SNOR_PROTO_ADDR(_nbits) \ + ((((unsigned long)(_nbits)) << SNOR_PROTO_ADDR_SHIFT) & \ + SNOR_PROTO_ADDR_MASK) + +#define SNOR_PROTO_DATA_MASK GENMASK(7, 0) +#define SNOR_PROTO_DATA_SHIFT 0 +#define SNOR_PROTO_DATA(_nbits) \ + ((((unsigned long)(_nbits)) << SNOR_PROTO_DATA_SHIFT) & \ + SNOR_PROTO_DATA_MASK) + +#define SNOR_PROTO_IS_DTR BIT(24) /* Double Transfer Rate */ + +#define SNOR_PROTO_STR(_inst_nbits, _addr_nbits, _data_nbits) \ + (SNOR_PROTO_INST(_inst_nbits) | \ + SNOR_PROTO_ADDR(_addr_nbits) | \ + SNOR_PROTO_DATA(_data_nbits)) +#define SNOR_PROTO_DTR(_inst_nbits, _addr_nbits, _data_nbits) \ + (SNOR_PROTO_IS_DTR | \ + SNOR_PROTO_STR(_inst_nbits, _addr_nbits, _data_nbits)) + +enum spi_nor_protocol { + SNOR_PROTO_1_1_1 = SNOR_PROTO_STR(1, 1, 1), + SNOR_PROTO_1_1_2 = SNOR_PROTO_STR(1, 1, 2), + SNOR_PROTO_1_1_4 = SNOR_PROTO_STR(1, 1, 4), + SNOR_PROTO_1_1_8 = SNOR_PROTO_STR(1, 1, 8), + SNOR_PROTO_1_2_2 = SNOR_PROTO_STR(1, 2, 2), + SNOR_PROTO_1_4_4 = SNOR_PROTO_STR(1, 4, 4), + SNOR_PROTO_1_8_8 = SNOR_PROTO_STR(1, 8, 8), + SNOR_PROTO_2_2_2 = SNOR_PROTO_STR(2, 2, 2), + SNOR_PROTO_4_4_4 = SNOR_PROTO_STR(4, 4, 4), + SNOR_PROTO_8_8_8 = SNOR_PROTO_STR(8, 8, 8), + + SNOR_PROTO_1_1_1_DTR = SNOR_PROTO_DTR(1, 1, 1), + SNOR_PROTO_1_2_2_DTR = SNOR_PROTO_DTR(1, 2, 2), + SNOR_PROTO_1_4_4_DTR = SNOR_PROTO_DTR(1, 4, 4), + SNOR_PROTO_1_8_8_DTR = SNOR_PROTO_DTR(1, 8, 8), }; +static inline bool spi_nor_protocol_is_dtr(enum spi_nor_protocol proto) +{ + return !!(proto & SNOR_PROTO_IS_DTR); +} + +static inline u8 spi_nor_get_protocol_inst_nbits(enum spi_nor_protocol proto) +{ + return ((unsigned long)(proto & SNOR_PROTO_INST_MASK)) >> + SNOR_PROTO_INST_SHIFT; +} + +static inline u8 spi_nor_get_protocol_addr_nbits(enum spi_nor_protocol proto) +{ + return ((unsigned long)(proto & SNOR_PROTO_ADDR_MASK)) >> + SNOR_PROTO_ADDR_SHIFT; +} + +static inline u8 spi_nor_get_protocol_data_nbits(enum spi_nor_protocol proto) +{ + return ((unsigned long)(proto & SNOR_PROTO_DATA_MASK)) >> + SNOR_PROTO_DATA_SHIFT; +} + +static inline u8 spi_nor_get_protocol_width(enum spi_nor_protocol proto) +{ + return spi_nor_get_protocol_data_nbits(proto); +} + #define SPI_NOR_MAX_CMD_SIZE 8 enum spi_nor_ops { SPI_NOR_OPS_READ = 0, @@ -154,9 +231,11 @@ enum spi_nor_option_flags { * @read_opcode: the read opcode * @read_dummy: the dummy needed by the read operation * @program_opcode: the program opcode - * @flash_read: the mode of the read * @sst_write_second: used by the SST write operation * @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 * @cmd_buf: used by the write_reg * @prepare: [OPTIONAL] do some preparations for the * read/write/erase/lock/unlock operations @@ -185,7 +264,9 @@ struct spi_nor { u8 read_opcode; u8 read_dummy; u8 program_opcode; - enum read_mode flash_read; + enum spi_nor_protocol read_proto; + enum spi_nor_protocol write_proto; + enum spi_nor_protocol reg_proto; bool sst_write_second; u32 flags; u8 cmd_buf[SPI_NOR_MAX_CMD_SIZE]; @@ -220,10 +301,71 @@ static inline struct device_node *spi_nor_get_flash_node(struct spi_nor *nor) } /** + * struct spi_nor_hwcaps - Structure for describing the hardware capabilies + * supported by the SPI controller (bus master). + * @mask: the bitmask listing all the supported hw capabilies + */ +struct spi_nor_hwcaps { + u32 mask; +}; + +/* + *(Fast) Read capabilities. + * MUST be ordered by priority: the higher bit position, the higher priority. + * As a matter of performances, it is relevant to use Octo SPI protocols first, + * then Quad SPI protocols before Dual SPI protocols, Fast Read and lastly + * (Slow) Read. + */ +#define SNOR_HWCAPS_READ_MASK GENMASK(14, 0) +#define SNOR_HWCAPS_READ BIT(0) +#define SNOR_HWCAPS_READ_FAST BIT(1) +#define SNOR_HWCAPS_READ_1_1_1_DTR BIT(2) + +#define SNOR_HWCAPS_READ_DUAL GENMASK(6, 3) +#define SNOR_HWCAPS_READ_1_1_2 BIT(3) +#define SNOR_HWCAPS_READ_1_2_2 BIT(4) +#define SNOR_HWCAPS_READ_2_2_2 BIT(5) +#define SNOR_HWCAPS_READ_1_2_2_DTR BIT(6) + +#define SNOR_HWCAPS_READ_QUAD GENMASK(10, 7) +#define SNOR_HWCAPS_READ_1_1_4 BIT(7) +#define SNOR_HWCAPS_READ_1_4_4 BIT(8) +#define SNOR_HWCAPS_READ_4_4_4 BIT(9) +#define SNOR_HWCAPS_READ_1_4_4_DTR BIT(10) + +#define SNOR_HWCPAS_READ_OCTO GENMASK(14, 11) +#define SNOR_HWCAPS_READ_1_1_8 BIT(11) +#define SNOR_HWCAPS_READ_1_8_8 BIT(12) +#define SNOR_HWCAPS_READ_8_8_8 BIT(13) +#define SNOR_HWCAPS_READ_1_8_8_DTR BIT(14) + +/* + * Page Program capabilities. + * MUST be ordered by priority: the higher bit position, the higher priority. + * Like (Fast) Read capabilities, Octo/Quad SPI protocols are preferred to the + * legacy SPI 1-1-1 protocol. + * Note that Dual Page Programs are not supported because there is no existing + * JEDEC/SFDP standard to define them. Also at this moment no SPI flash memory + * implements such commands. + */ +#define SNOR_HWCAPS_PP_MASK GENMASK(22, 16) +#define SNOR_HWCAPS_PP BIT(16) + +#define SNOR_HWCAPS_PP_QUAD GENMASK(19, 17) +#define SNOR_HWCAPS_PP_1_1_4 BIT(17) +#define SNOR_HWCAPS_PP_1_4_4 BIT(18) +#define SNOR_HWCAPS_PP_4_4_4 BIT(19) + +#define SNOR_HWCAPS_PP_OCTO GENMASK(22, 20) +#define SNOR_HWCAPS_PP_1_1_8 BIT(20) +#define SNOR_HWCAPS_PP_1_8_8 BIT(21) +#define SNOR_HWCAPS_PP_8_8_8 BIT(22) + +/** * spi_nor_scan() - scan the SPI NOR * @nor: the spi_nor structure * @name: the chip type name - * @mode: the read mode supported by the driver + * @hwcaps: the hardware capabilities supported by the controller driver * * The drivers can use this fuction to scan the SPI NOR. * In the scanning, it will try to get all the necessary information to @@ -233,6 +375,7 @@ static inline struct device_node *spi_nor_get_flash_node(struct spi_nor *nor) * * Return: 0 for success, others for failure. */ -int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode); +int spi_nor_scan(struct spi_nor *nor, const char *name, + const struct spi_nor_hwcaps *hwcaps); #endif diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 1b1ca04820a3..47239c336688 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -479,6 +479,7 @@ enum { NFSPROC4_CLNT_ACCESS, NFSPROC4_CLNT_GETATTR, NFSPROC4_CLNT_LOOKUP, + NFSPROC4_CLNT_LOOKUPP, NFSPROC4_CLNT_LOOKUP_ROOT, NFSPROC4_CLNT_REMOVE, NFSPROC4_CLNT_RENAME, diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index bb0eb2c9acca..e52cc55ac300 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -332,6 +332,7 @@ extern void nfs_zap_caches(struct inode *); extern void nfs_invalidate_atime(struct inode *); extern struct inode *nfs_fhget(struct super_block *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *); +struct inode *nfs_ilookup(struct super_block *sb, struct nfs_fattr *, struct nfs_fh *); extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fattr); diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index e418a1096662..74c44665e6d3 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -42,6 +42,7 @@ struct nfs_client { #define NFS_CS_MIGRATION 2 /* - transparent state migr */ #define NFS_CS_INFINITE_SLOTS 3 /* - don't limit TCP slots */ #define NFS_CS_NO_RETRANS_TIMEOUT 4 /* - Disable retransmit timeouts */ +#define NFS_CS_TSM_POSSIBLE 5 /* - Maybe state migration */ struct sockaddr_storage cl_addr; /* server identifier */ size_t cl_addrlen; char * cl_hostname; /* hostname of server */ @@ -210,6 +211,7 @@ struct nfs_server { unsigned long mig_status; #define NFS_MIG_IN_TRANSITION (1) #define NFS_MIG_FAILED (2) +#define NFS_MIG_TSM_POSSIBLE (3) void (*destroy)(struct nfs_server *); diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 247cc3d3498f..d67b67ae6c8b 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -33,6 +33,8 @@ enum { PG_UPTODATE, /* page group sync bit in read path */ PG_WB_END, /* page group sync bit in write path */ PG_REMOVE, /* page group sync bit in write path */ + PG_CONTENDED1, /* Is someone waiting for a lock? */ + PG_CONTENDED2, /* Is someone waiting for a lock? */ }; struct nfs_inode; @@ -93,8 +95,8 @@ struct nfs_pageio_descriptor { const struct rpc_call_ops *pg_rpc_callops; const struct nfs_pgio_completion_ops *pg_completion_ops; struct pnfs_layout_segment *pg_lseg; + struct nfs_io_completion *pg_io_completion; struct nfs_direct_req *pg_dreq; - void *pg_layout_private; unsigned int pg_bsize; /* default bsize for mirrors */ u32 pg_mirror_count; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index b28c83475ee8..ca3bcc4ed4e5 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -878,7 +878,7 @@ struct nfs3_readdirargs { struct nfs_fh * fh; __u64 cookie; __be32 verf[2]; - int plus; + bool plus; unsigned int count; struct page ** pages; }; @@ -909,7 +909,7 @@ struct nfs3_linkres { struct nfs3_readdirres { struct nfs_fattr * dir_attr; __be32 * verf; - int plus; + bool plus; }; struct nfs3_getaclres { @@ -1012,7 +1012,6 @@ struct nfs4_link_res { struct nfs_fattr * dir_attr; }; - struct nfs4_lookup_arg { struct nfs4_sequence_args seq_args; const struct nfs_fh * dir_fh; @@ -1028,6 +1027,20 @@ struct nfs4_lookup_res { struct nfs4_label *label; }; +struct nfs4_lookupp_arg { + struct nfs4_sequence_args seq_args; + const struct nfs_fh *fh; + const u32 *bitmask; +}; + +struct nfs4_lookupp_res { + struct nfs4_sequence_res seq_res; + const struct nfs_server *server; + struct nfs_fattr *fattr; + struct nfs_fh *fh; + struct nfs4_label *label; +}; + struct nfs4_lookup_root_arg { struct nfs4_sequence_args seq_args; const u32 * bitmask; @@ -1053,7 +1066,7 @@ struct nfs4_readdir_arg { struct page ** pages; /* zero-copy data */ unsigned int pgbase; /* zero-copy data */ const u32 * bitmask; - int plus; + bool plus; }; struct nfs4_readdir_res { @@ -1422,6 +1435,7 @@ enum { NFS_IOHDR_STAT, }; +struct nfs_io_completion; struct nfs_pgio_header { struct inode *inode; struct rpc_cred *cred; @@ -1435,8 +1449,8 @@ struct nfs_pgio_header { void (*release) (struct nfs_pgio_header *hdr); const struct nfs_pgio_completion_ops *completion_ops; const struct nfs_rw_ops *rw_ops; + struct nfs_io_completion *io_completion; struct nfs_direct_req *dreq; - void *layout_private; spinlock_t lock; /* fields protected by lock */ int pnfs_error; @@ -1533,6 +1547,7 @@ struct nfs_renamedata { struct nfs_fattr new_fattr; void (*complete)(struct rpc_task *, struct nfs_renamedata *); long timeout; + bool cancelled; }; struct nfs_access_entry; @@ -1567,6 +1582,8 @@ struct nfs_rpc_ops { int (*lookup) (struct inode *, const struct qstr *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *); + int (*lookupp) (struct inode *, struct nfs_fh *, + struct nfs_fattr *, struct nfs4_label *); int (*access) (struct inode *, struct nfs_access_entry *); int (*readlink)(struct inode *, struct page *, unsigned int, unsigned int); @@ -1585,7 +1602,7 @@ struct nfs_rpc_ops { int (*mkdir) (struct inode *, struct dentry *, struct iattr *); int (*rmdir) (struct inode *, const struct qstr *); int (*readdir) (struct dentry *, struct rpc_cred *, - u64, struct page **, unsigned int, int); + u64, struct page **, unsigned int, bool); int (*mknod) (struct inode *, struct dentry *, struct iattr *, dev_t); int (*statfs) (struct nfs_server *, struct nfs_fh *, @@ -1595,7 +1612,7 @@ struct nfs_rpc_ops { int (*pathconf) (struct nfs_server *, struct nfs_fh *, struct nfs_pathconf *); int (*set_capabilities)(struct nfs_server *, struct nfs_fh *); - int (*decode_dirent)(struct xdr_stream *, struct nfs_entry *, int); + int (*decode_dirent)(struct xdr_stream *, struct nfs_entry *, bool); int (*pgio_rpc_prepare)(struct rpc_task *, struct nfs_pgio_header *); void (*read_setup)(struct nfs_pgio_header *, struct rpc_message *); diff --git a/include/linux/nmi.h b/include/linux/nmi.h index aa3cd0878270..8aa01fd859fb 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -6,18 +6,26 @@ #include <linux/sched.h> #include <asm/irq.h> +#if defined(CONFIG_HAVE_NMI_WATCHDOG) +#include <asm/nmi.h> +#endif #ifdef CONFIG_LOCKUP_DETECTOR +void lockup_detector_init(void); +#else +static inline void lockup_detector_init(void) +{ +} +#endif + +#ifdef CONFIG_SOFTLOCKUP_DETECTOR extern void touch_softlockup_watchdog_sched(void); extern void touch_softlockup_watchdog(void); extern void touch_softlockup_watchdog_sync(void); extern void touch_all_softlockup_watchdogs(void); -extern int proc_dowatchdog_thresh(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos); extern unsigned int softlockup_panic; -extern unsigned int hardlockup_panic; -void lockup_detector_init(void); +extern int soft_watchdog_enabled; +extern atomic_t watchdog_park_in_progress; #else static inline void touch_softlockup_watchdog_sched(void) { @@ -31,9 +39,6 @@ static inline void touch_softlockup_watchdog_sync(void) static inline void touch_all_softlockup_watchdogs(void) { } -static inline void lockup_detector_init(void) -{ -} #endif #ifdef CONFIG_DETECT_HUNG_TASK @@ -61,6 +66,21 @@ static inline void reset_hung_task_detector(void) #define NMI_WATCHDOG_ENABLED (1 << NMI_WATCHDOG_ENABLED_BIT) #define SOFT_WATCHDOG_ENABLED (1 << SOFT_WATCHDOG_ENABLED_BIT) +#if defined(CONFIG_HARDLOCKUP_DETECTOR) +extern void hardlockup_detector_disable(void); +extern unsigned int hardlockup_panic; +#else +static inline void hardlockup_detector_disable(void) {} +#endif + +#if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF) +extern void arch_touch_nmi_watchdog(void); +#else +#if !defined(CONFIG_HAVE_NMI_WATCHDOG) +static inline void arch_touch_nmi_watchdog(void) {} +#endif +#endif + /** * touch_nmi_watchdog - restart NMI watchdog timeout. * @@ -68,21 +88,11 @@ static inline void reset_hung_task_detector(void) * may be used to reset the timeout - for code which intentionally * disables interrupts for a long time. This call is stateless. */ -#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) -#include <asm/nmi.h> -extern void touch_nmi_watchdog(void); -#else static inline void touch_nmi_watchdog(void) { + arch_touch_nmi_watchdog(); touch_softlockup_watchdog(); } -#endif - -#if defined(CONFIG_HARDLOCKUP_DETECTOR) -extern void hardlockup_detector_disable(void); -#else -static inline void hardlockup_detector_disable(void) {} -#endif /* * Create trigger_all_cpu_backtrace() out of the arch-provided @@ -139,15 +149,18 @@ static inline bool trigger_single_cpu_backtrace(int cpu) } #endif -#ifdef CONFIG_LOCKUP_DETECTOR +#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF u64 hw_nmi_get_sample_period(int watchdog_thresh); +#endif + +#ifdef CONFIG_LOCKUP_DETECTOR extern int nmi_watchdog_enabled; -extern int soft_watchdog_enabled; extern int watchdog_user_enabled; extern int watchdog_thresh; extern unsigned long watchdog_enabled; +extern struct cpumask watchdog_cpumask; extern unsigned long *watchdog_cpumask_bits; -extern atomic_t watchdog_park_in_progress; +extern int __read_mostly watchdog_suspended; #ifdef CONFIG_SMP extern int sysctl_softlockup_all_cpu_backtrace; extern int sysctl_hardlockup_all_cpu_backtrace; diff --git a/include/linux/ntb.h b/include/linux/ntb.h index de87ceac110e..609e232c00da 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -5,6 +5,7 @@ * GPL LICENSE SUMMARY * * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -18,6 +19,7 @@ * BSD LICENSE * * Copyright (C) 2015 EMC Corporation. All Rights Reserved. + * Copyright (C) 2016 T-Platforms. All Rights Reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions @@ -106,6 +108,7 @@ static inline char *ntb_topo_string(enum ntb_topo topo) * @NTB_SPEED_GEN1: Link is trained to gen1 speed. * @NTB_SPEED_GEN2: Link is trained to gen2 speed. * @NTB_SPEED_GEN3: Link is trained to gen3 speed. + * @NTB_SPEED_GEN4: Link is trained to gen4 speed. */ enum ntb_speed { NTB_SPEED_AUTO = -1, @@ -113,6 +116,7 @@ enum ntb_speed { NTB_SPEED_GEN1 = 1, NTB_SPEED_GEN2 = 2, NTB_SPEED_GEN3 = 3, + NTB_SPEED_GEN4 = 4 }; /** @@ -140,6 +144,20 @@ enum ntb_width { }; /** + * enum ntb_default_port - NTB default port number + * @NTB_PORT_PRI_USD: Default port of the NTB_TOPO_PRI/NTB_TOPO_B2B_USD + * topologies + * @NTB_PORT_SEC_DSD: Default port of the NTB_TOPO_SEC/NTB_TOPO_B2B_DSD + * topologies + */ +enum ntb_default_port { + NTB_PORT_PRI_USD, + NTB_PORT_SEC_DSD +}; +#define NTB_DEF_PEER_CNT (1) +#define NTB_DEF_PEER_IDX (0) + +/** * struct ntb_client_ops - ntb client operations * @probe: Notify client of a new device. * @remove: Notify client to remove a device. @@ -162,10 +180,12 @@ static inline int ntb_client_ops_is_valid(const struct ntb_client_ops *ops) * struct ntb_ctx_ops - ntb driver context operations * @link_event: See ntb_link_event(). * @db_event: See ntb_db_event(). + * @msg_event: See ntb_msg_event(). */ struct ntb_ctx_ops { void (*link_event)(void *ctx); void (*db_event)(void *ctx, int db_vector); + void (*msg_event)(void *ctx); }; static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) @@ -174,18 +194,27 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) return /* ops->link_event && */ /* ops->db_event && */ + /* ops->msg_event && */ 1; } /** * struct ntb_ctx_ops - ntb device operations - * @mw_count: See ntb_mw_count(). - * @mw_get_range: See ntb_mw_get_range(). - * @mw_set_trans: See ntb_mw_set_trans(). - * @mw_clear_trans: See ntb_mw_clear_trans(). + * @port_number: See ntb_port_number(). + * @peer_port_count: See ntb_peer_port_count(). + * @peer_port_number: See ntb_peer_port_number(). + * @peer_port_idx: See ntb_peer_port_idx(). * @link_is_up: See ntb_link_is_up(). * @link_enable: See ntb_link_enable(). * @link_disable: See ntb_link_disable(). + * @mw_count: See ntb_mw_count(). + * @mw_get_align: See ntb_mw_get_align(). + * @mw_set_trans: See ntb_mw_set_trans(). + * @mw_clear_trans: See ntb_mw_clear_trans(). + * @peer_mw_count: See ntb_peer_mw_count(). + * @peer_mw_get_addr: See ntb_peer_mw_get_addr(). + * @peer_mw_set_trans: See ntb_peer_mw_set_trans(). + * @peer_mw_clear_trans:See ntb_peer_mw_clear_trans(). * @db_is_unsafe: See ntb_db_is_unsafe(). * @db_valid_mask: See ntb_db_valid_mask(). * @db_vector_count: See ntb_db_vector_count(). @@ -210,22 +239,43 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) * @peer_spad_addr: See ntb_peer_spad_addr(). * @peer_spad_read: See ntb_peer_spad_read(). * @peer_spad_write: See ntb_peer_spad_write(). + * @msg_count: See ntb_msg_count(). + * @msg_inbits: See ntb_msg_inbits(). + * @msg_outbits: See ntb_msg_outbits(). + * @msg_read_sts: See ntb_msg_read_sts(). + * @msg_clear_sts: See ntb_msg_clear_sts(). + * @msg_set_mask: See ntb_msg_set_mask(). + * @msg_clear_mask: See ntb_msg_clear_mask(). + * @msg_read: See ntb_msg_read(). + * @msg_write: See ntb_msg_write(). */ struct ntb_dev_ops { - int (*mw_count)(struct ntb_dev *ntb); - int (*mw_get_range)(struct ntb_dev *ntb, int idx, - phys_addr_t *base, resource_size_t *size, - resource_size_t *align, resource_size_t *align_size); - int (*mw_set_trans)(struct ntb_dev *ntb, int idx, - dma_addr_t addr, resource_size_t size); - int (*mw_clear_trans)(struct ntb_dev *ntb, int idx); + int (*port_number)(struct ntb_dev *ntb); + int (*peer_port_count)(struct ntb_dev *ntb); + int (*peer_port_number)(struct ntb_dev *ntb, int pidx); + int (*peer_port_idx)(struct ntb_dev *ntb, int port); - int (*link_is_up)(struct ntb_dev *ntb, + u64 (*link_is_up)(struct ntb_dev *ntb, enum ntb_speed *speed, enum ntb_width *width); int (*link_enable)(struct ntb_dev *ntb, enum ntb_speed max_speed, enum ntb_width max_width); int (*link_disable)(struct ntb_dev *ntb); + int (*mw_count)(struct ntb_dev *ntb, int pidx); + int (*mw_get_align)(struct ntb_dev *ntb, int pidx, int widx, + resource_size_t *addr_align, + resource_size_t *size_align, + resource_size_t *size_max); + int (*mw_set_trans)(struct ntb_dev *ntb, int pidx, int widx, + dma_addr_t addr, resource_size_t size); + int (*mw_clear_trans)(struct ntb_dev *ntb, int pidx, int widx); + int (*peer_mw_count)(struct ntb_dev *ntb); + int (*peer_mw_get_addr)(struct ntb_dev *ntb, int widx, + phys_addr_t *base, resource_size_t *size); + int (*peer_mw_set_trans)(struct ntb_dev *ntb, int pidx, int widx, + u64 addr, resource_size_t size); + int (*peer_mw_clear_trans)(struct ntb_dev *ntb, int pidx, int widx); + int (*db_is_unsafe)(struct ntb_dev *ntb); u64 (*db_valid_mask)(struct ntb_dev *ntb); int (*db_vector_count)(struct ntb_dev *ntb); @@ -252,32 +302,55 @@ struct ntb_dev_ops { int (*spad_is_unsafe)(struct ntb_dev *ntb); int (*spad_count)(struct ntb_dev *ntb); - u32 (*spad_read)(struct ntb_dev *ntb, int idx); - int (*spad_write)(struct ntb_dev *ntb, int idx, u32 val); + u32 (*spad_read)(struct ntb_dev *ntb, int sidx); + int (*spad_write)(struct ntb_dev *ntb, int sidx, u32 val); - int (*peer_spad_addr)(struct ntb_dev *ntb, int idx, + int (*peer_spad_addr)(struct ntb_dev *ntb, int pidx, int sidx, phys_addr_t *spad_addr); - u32 (*peer_spad_read)(struct ntb_dev *ntb, int idx); - int (*peer_spad_write)(struct ntb_dev *ntb, int idx, u32 val); + u32 (*peer_spad_read)(struct ntb_dev *ntb, int pidx, int sidx); + int (*peer_spad_write)(struct ntb_dev *ntb, int pidx, int sidx, + u32 val); + + int (*msg_count)(struct ntb_dev *ntb); + u64 (*msg_inbits)(struct ntb_dev *ntb); + u64 (*msg_outbits)(struct ntb_dev *ntb); + u64 (*msg_read_sts)(struct ntb_dev *ntb); + int (*msg_clear_sts)(struct ntb_dev *ntb, u64 sts_bits); + int (*msg_set_mask)(struct ntb_dev *ntb, u64 mask_bits); + int (*msg_clear_mask)(struct ntb_dev *ntb, u64 mask_bits); + int (*msg_read)(struct ntb_dev *ntb, int midx, int *pidx, u32 *msg); + int (*msg_write)(struct ntb_dev *ntb, int midx, int pidx, u32 msg); }; static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) { /* commented callbacks are not required: */ return - ops->mw_count && - ops->mw_get_range && - ops->mw_set_trans && - /* ops->mw_clear_trans && */ + /* Port operations are required for multiport devices */ + !ops->peer_port_count == !ops->port_number && + !ops->peer_port_number == !ops->port_number && + !ops->peer_port_idx == !ops->port_number && + + /* Link operations are required */ ops->link_is_up && ops->link_enable && ops->link_disable && + + /* One or both MW interfaces should be developed */ + ops->mw_count && + ops->mw_get_align && + (ops->mw_set_trans || + ops->peer_mw_set_trans) && + /* ops->mw_clear_trans && */ + ops->peer_mw_count && + ops->peer_mw_get_addr && + /* ops->peer_mw_clear_trans && */ + + /* Doorbell operations are mostly required */ /* ops->db_is_unsafe && */ ops->db_valid_mask && - /* both set, or both unset */ - (!ops->db_vector_count == !ops->db_vector_mask) && - + (!ops->db_vector_count == !ops->db_vector_mask) && ops->db_read && /* ops->db_set && */ ops->db_clear && @@ -291,13 +364,24 @@ static inline int ntb_dev_ops_is_valid(const struct ntb_dev_ops *ops) /* ops->peer_db_read_mask && */ /* ops->peer_db_set_mask && */ /* ops->peer_db_clear_mask && */ - /* ops->spad_is_unsafe && */ - ops->spad_count && - ops->spad_read && - ops->spad_write && - /* ops->peer_spad_addr && */ - /* ops->peer_spad_read && */ - ops->peer_spad_write && + + /* Scrachpads interface is optional */ + /* !ops->spad_is_unsafe == !ops->spad_count && */ + !ops->spad_read == !ops->spad_count && + !ops->spad_write == !ops->spad_count && + /* !ops->peer_spad_addr == !ops->spad_count && */ + /* !ops->peer_spad_read == !ops->spad_count && */ + !ops->peer_spad_write == !ops->spad_count && + + /* Messaging interface is optional */ + !ops->msg_inbits == !ops->msg_count && + !ops->msg_outbits == !ops->msg_count && + !ops->msg_read_sts == !ops->msg_count && + !ops->msg_clear_sts == !ops->msg_count && + /* !ops->msg_set_mask == !ops->msg_count && */ + /* !ops->msg_clear_mask == !ops->msg_count && */ + !ops->msg_read == !ops->msg_count && + !ops->msg_write == !ops->msg_count && 1; } @@ -310,13 +394,12 @@ struct ntb_client { struct device_driver drv; const struct ntb_client_ops ops; }; - #define drv_ntb_client(__drv) container_of((__drv), struct ntb_client, drv) /** * struct ntb_device - ntb device * @dev: Linux device object. - * @pdev: Pci device entry of the ntb. + * @pdev: PCI device entry of the ntb. * @topo: Detected topology of the ntb. * @ops: See &ntb_dev_ops. * @ctx: See &ntb_ctx_ops. @@ -337,7 +420,6 @@ struct ntb_dev { /* block unregister until device is fully released */ struct completion released; }; - #define dev_ntb(__dev) container_of((__dev), struct ntb_dev, dev) /** @@ -434,86 +516,152 @@ void ntb_link_event(struct ntb_dev *ntb); * multiple interrupt vectors for doorbells, the vector number indicates which * vector received the interrupt. The vector number is relative to the first * vector used for doorbells, starting at zero, and must be less than - ** ntb_db_vector_count(). The driver may call ntb_db_read() to check which + * ntb_db_vector_count(). The driver may call ntb_db_read() to check which * doorbell bits need service, and ntb_db_vector_mask() to determine which of * those bits are associated with the vector number. */ void ntb_db_event(struct ntb_dev *ntb, int vector); /** - * ntb_mw_count() - get the number of memory windows + * ntb_msg_event() - notify driver context of a message event * @ntb: NTB device context. * - * Hardware and topology may support a different number of memory windows. + * Notify the driver context of a message event. If hardware supports + * message registers, this event indicates, that a new message arrived in + * some incoming message register or last sent message couldn't be delivered. + * The events can be masked/unmasked by the methods ntb_msg_set_mask() and + * ntb_msg_clear_mask(). + */ +void ntb_msg_event(struct ntb_dev *ntb); + +/** + * ntb_default_port_number() - get the default local port number + * @ntb: NTB device context. * - * Return: the number of memory windows. + * If hardware driver doesn't specify port_number() callback method, the NTB + * is considered with just two ports. So this method returns default local + * port number in compliance with topology. + * + * NOTE Don't call this method directly. The ntb_port_number() function should + * be used instead. + * + * Return: the default local port number + */ +int ntb_default_port_number(struct ntb_dev *ntb); + +/** + * ntb_default_port_count() - get the default number of peer device ports + * @ntb: NTB device context. + * + * By default hardware driver supports just one peer device. + * + * NOTE Don't call this method directly. The ntb_peer_port_count() function + * should be used instead. + * + * Return: the default number of peer ports + */ +int ntb_default_peer_port_count(struct ntb_dev *ntb); + +/** + * ntb_default_peer_port_number() - get the default peer port by given index + * @ntb: NTB device context. + * @idx: Peer port index (should not differ from zero). + * + * By default hardware driver supports just one peer device, so this method + * shall return the corresponding value from enum ntb_default_port. + * + * NOTE Don't call this method directly. The ntb_peer_port_number() function + * should be used instead. + * + * Return: the peer device port or negative value indicating an error + */ +int ntb_default_peer_port_number(struct ntb_dev *ntb, int pidx); + +/** + * ntb_default_peer_port_idx() - get the default peer device port index by + * given port number + * @ntb: NTB device context. + * @port: Peer port number (should be one of enum ntb_default_port). + * + * By default hardware driver supports just one peer device, so while + * specified port-argument indicates peer port from enum ntb_default_port, + * the return value shall be zero. + * + * NOTE Don't call this method directly. The ntb_peer_port_idx() function + * should be used instead. + * + * Return: the peer port index or negative value indicating an error + */ +int ntb_default_peer_port_idx(struct ntb_dev *ntb, int port); + +/** + * ntb_port_number() - get the local port number + * @ntb: NTB device context. + * + * Hardware must support at least simple two-ports ntb connection + * + * Return: the local port number */ -static inline int ntb_mw_count(struct ntb_dev *ntb) +static inline int ntb_port_number(struct ntb_dev *ntb) { - return ntb->ops->mw_count(ntb); + if (!ntb->ops->port_number) + return ntb_default_port_number(ntb); + + return ntb->ops->port_number(ntb); } /** - * ntb_mw_get_range() - get the range of a memory window + * ntb_peer_port_count() - get the number of peer device ports * @ntb: NTB device context. - * @idx: Memory window number. - * @base: OUT - the base address for mapping the memory window - * @size: OUT - the size for mapping the memory window - * @align: OUT - the base alignment for translating the memory window - * @align_size: OUT - the size alignment for translating the memory window * - * Get the range of a memory window. NULL may be given for any output - * parameter if the value is not needed. The base and size may be used for - * mapping the memory window, to access the peer memory. The alignment and - * size may be used for translating the memory window, for the peer to access - * memory on the local system. + * Hardware may support an access to memory of several remote domains + * over multi-port NTB devices. This method returns the number of peers, + * local device can have shared memory with. * - * Return: Zero on success, otherwise an error number. + * Return: the number of peer ports */ -static inline int ntb_mw_get_range(struct ntb_dev *ntb, int idx, - phys_addr_t *base, resource_size_t *size, - resource_size_t *align, resource_size_t *align_size) +static inline int ntb_peer_port_count(struct ntb_dev *ntb) { - return ntb->ops->mw_get_range(ntb, idx, base, size, - align, align_size); + if (!ntb->ops->peer_port_count) + return ntb_default_peer_port_count(ntb); + + return ntb->ops->peer_port_count(ntb); } /** - * ntb_mw_set_trans() - set the translation of a memory window + * ntb_peer_port_number() - get the peer port by given index * @ntb: NTB device context. - * @idx: Memory window number. - * @addr: The dma address local memory to expose to the peer. - * @size: The size of the local memory to expose to the peer. + * @pidx: Peer port index. * - * Set the translation of a memory window. The peer may access local memory - * through the window starting at the address, up to the size. The address - * must be aligned to the alignment specified by ntb_mw_get_range(). The size - * must be aligned to the size alignment specified by ntb_mw_get_range(). + * Peer ports are continuously enumerated by NTB API logic, so this method + * lets to retrieve port real number by its index. * - * Return: Zero on success, otherwise an error number. + * Return: the peer device port or negative value indicating an error */ -static inline int ntb_mw_set_trans(struct ntb_dev *ntb, int idx, - dma_addr_t addr, resource_size_t size) +static inline int ntb_peer_port_number(struct ntb_dev *ntb, int pidx) { - return ntb->ops->mw_set_trans(ntb, idx, addr, size); + if (!ntb->ops->peer_port_number) + return ntb_default_peer_port_number(ntb, pidx); + + return ntb->ops->peer_port_number(ntb, pidx); } /** - * ntb_mw_clear_trans() - clear the translation of a memory window + * ntb_peer_port_idx() - get the peer device port index by given port number * @ntb: NTB device context. - * @idx: Memory window number. + * @port: Peer port number. * - * Clear the translation of a memory window. The peer may no longer access - * local memory through the window. + * Inverse operation of ntb_peer_port_number(), so one can get port index + * by specified port number. * - * Return: Zero on success, otherwise an error number. + * Return: the peer port index or negative value indicating an error */ -static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int idx) +static inline int ntb_peer_port_idx(struct ntb_dev *ntb, int port) { - if (!ntb->ops->mw_clear_trans) - return ntb->ops->mw_set_trans(ntb, idx, 0, 0); + if (!ntb->ops->peer_port_idx) + return ntb_default_peer_port_idx(ntb, port); - return ntb->ops->mw_clear_trans(ntb, idx); + return ntb->ops->peer_port_idx(ntb, port); } /** @@ -526,25 +674,26 @@ static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int idx) * state once after every link event. It is safe to query the link state in * the context of the link event callback. * - * Return: One if the link is up, zero if the link is down, otherwise a - * negative value indicating the error number. + * Return: bitfield of indexed ports link state: bit is set/cleared if the + * link is up/down respectively. */ -static inline int ntb_link_is_up(struct ntb_dev *ntb, +static inline u64 ntb_link_is_up(struct ntb_dev *ntb, enum ntb_speed *speed, enum ntb_width *width) { return ntb->ops->link_is_up(ntb, speed, width); } /** - * ntb_link_enable() - enable the link on the secondary side of the ntb + * ntb_link_enable() - enable the local port ntb connection * @ntb: NTB device context. * @max_speed: The maximum link speed expressed as PCIe generation number. * @max_width: The maximum link width expressed as the number of PCIe lanes. * - * Enable the link on the secondary side of the ntb. This can only be done - * from the primary side of the ntb in primary or b2b topology. The ntb device - * should train the link to its maximum speed and width, or the requested speed - * and width, whichever is smaller, if supported. + * Enable the NTB/PCIe link on the local or remote (for bridge-to-bridge + * topology) side of the bridge. If it's supported the ntb device should train + * the link to its maximum speed and width, or the requested speed and width, + * whichever is smaller. Some hardware doesn't support PCIe link training, so + * the last two arguments will be ignored then. * * Return: Zero on success, otherwise an error number. */ @@ -556,14 +705,14 @@ static inline int ntb_link_enable(struct ntb_dev *ntb, } /** - * ntb_link_disable() - disable the link on the secondary side of the ntb + * ntb_link_disable() - disable the local port ntb connection * @ntb: NTB device context. * - * Disable the link on the secondary side of the ntb. This can only be - * done from the primary side of the ntb in primary or b2b topology. The ntb - * device should disable the link. Returning from this call must indicate that - * a barrier has passed, though with no more writes may pass in either - * direction across the link, except if this call returns an error number. + * Disable the link on the local or remote (for b2b topology) of the ntb. + * The ntb device should disable the link. Returning from this call must + * indicate that a barrier has passed, though with no more writes may pass in + * either direction across the link, except if this call returns an error + * number. * * Return: Zero on success, otherwise an error number. */ @@ -573,6 +722,183 @@ static inline int ntb_link_disable(struct ntb_dev *ntb) } /** + * ntb_mw_count() - get the number of inbound memory windows, which could + * be created for a specified peer device + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * + * Hardware and topology may support a different number of memory windows. + * Moreover different peer devices can support different number of memory + * windows. Simply speaking this method returns the number of possible inbound + * memory windows to share with specified peer device. + * + * Return: the number of memory windows. + */ +static inline int ntb_mw_count(struct ntb_dev *ntb, int pidx) +{ + return ntb->ops->mw_count(ntb, pidx); +} + +/** + * ntb_mw_get_align() - get the restriction parameters of inbound memory window + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * @addr_align: OUT - the base alignment for translating the memory window + * @size_align: OUT - the size alignment for translating the memory window + * @size_max: OUT - the maximum size of the memory window + * + * Get the alignments of an inbound memory window with specified index. + * NULL may be given for any output parameter if the value is not needed. + * The alignment and size parameters may be used for allocation of proper + * shared memory. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_mw_get_align(struct ntb_dev *ntb, int pidx, int widx, + resource_size_t *addr_align, + resource_size_t *size_align, + resource_size_t *size_max) +{ + return ntb->ops->mw_get_align(ntb, pidx, widx, addr_align, size_align, + size_max); +} + +/** + * ntb_mw_set_trans() - set the translation of an inbound memory window + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * @addr: The dma address of local memory to expose to the peer. + * @size: The size of the local memory to expose to the peer. + * + * Set the translation of a memory window. The peer may access local memory + * through the window starting at the address, up to the size. The address + * and size must be aligned in compliance with restrictions of + * ntb_mw_get_align(). The region size should not exceed the size_max parameter + * of that method. + * + * This method may not be implemented due to the hardware specific memory + * windows interface. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx, + dma_addr_t addr, resource_size_t size) +{ + if (!ntb->ops->mw_set_trans) + return 0; + + return ntb->ops->mw_set_trans(ntb, pidx, widx, addr, size); +} + +/** + * ntb_mw_clear_trans() - clear the translation address of an inbound memory + * window + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * + * Clear the translation of an inbound memory window. The peer may no longer + * access local memory through the window. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int pidx, int widx) +{ + if (!ntb->ops->mw_clear_trans) + return ntb_mw_set_trans(ntb, pidx, widx, 0, 0); + + return ntb->ops->mw_clear_trans(ntb, pidx, widx); +} + +/** + * ntb_peer_mw_count() - get the number of outbound memory windows, which could + * be mapped to access a shared memory + * @ntb: NTB device context. + * + * Hardware and topology may support a different number of memory windows. + * This method returns the number of outbound memory windows supported by + * local device. + * + * Return: the number of memory windows. + */ +static inline int ntb_peer_mw_count(struct ntb_dev *ntb) +{ + return ntb->ops->peer_mw_count(ntb); +} + +/** + * ntb_peer_mw_get_addr() - get map address of an outbound memory window + * @ntb: NTB device context. + * @widx: Memory window index (within ntb_peer_mw_count() return value). + * @base: OUT - the base address of mapping region. + * @size: OUT - the size of mapping region. + * + * Get base and size of memory region to map. NULL may be given for any output + * parameter if the value is not needed. The base and size may be used for + * mapping the memory window, to access the peer memory. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_peer_mw_get_addr(struct ntb_dev *ntb, int widx, + phys_addr_t *base, resource_size_t *size) +{ + return ntb->ops->peer_mw_get_addr(ntb, widx, base, size); +} + +/** + * ntb_peer_mw_set_trans() - set a translation address of a memory window + * retrieved from a peer device + * @ntb: NTB device context. + * @pidx: Port index of peer device the translation address received from. + * @widx: Memory window index. + * @addr: The dma address of the shared memory to access. + * @size: The size of the shared memory to access. + * + * Set the translation of an outbound memory window. The local device may + * access shared memory allocated by a peer device sent the address. + * + * This method may not be implemented due to the hardware specific memory + * windows interface, so a translation address can be only set on the side, + * where shared memory (inbound memory windows) is allocated. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx, + u64 addr, resource_size_t size) +{ + if (!ntb->ops->peer_mw_set_trans) + return 0; + + return ntb->ops->peer_mw_set_trans(ntb, pidx, widx, addr, size); +} + +/** + * ntb_peer_mw_clear_trans() - clear the translation address of an outbound + * memory window + * @ntb: NTB device context. + * @pidx: Port index of peer device. + * @widx: Memory window index. + * + * Clear the translation of a outbound memory window. The local device may no + * longer access a shared memory through the window. + * + * This method may not be implemented due to the hardware specific memory + * windows interface. + * + * Return: Zero on success, otherwise an error number. + */ +static inline int ntb_peer_mw_clear_trans(struct ntb_dev *ntb, int pidx, + int widx) +{ + if (!ntb->ops->peer_mw_clear_trans) + return ntb_peer_mw_set_trans(ntb, pidx, widx, 0, 0); + + return ntb->ops->peer_mw_clear_trans(ntb, pidx, widx); +} + +/** * ntb_db_is_unsafe() - check if it is safe to use hardware doorbell * @ntb: NTB device context. * @@ -900,47 +1226,58 @@ static inline int ntb_spad_is_unsafe(struct ntb_dev *ntb) * @ntb: NTB device context. * * Hardware and topology may support a different number of scratchpads. + * Although it must be the same for all ports per NTB device. * * Return: the number of scratchpads. */ static inline int ntb_spad_count(struct ntb_dev *ntb) { + if (!ntb->ops->spad_count) + return 0; + return ntb->ops->spad_count(ntb); } /** * ntb_spad_read() - read the local scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @sidx: Scratchpad index. * * Read the local scratchpad register, and return the value. * * Return: The value of the local scratchpad register. */ -static inline u32 ntb_spad_read(struct ntb_dev *ntb, int idx) +static inline u32 ntb_spad_read(struct ntb_dev *ntb, int sidx) { - return ntb->ops->spad_read(ntb, idx); + if (!ntb->ops->spad_read) + return ~(u32)0; + + return ntb->ops->spad_read(ntb, sidx); } /** * ntb_spad_write() - write the local scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @sidx: Scratchpad index. * @val: Scratchpad value. * * Write the value to the local scratchpad register. * * Return: Zero on success, otherwise an error number. */ -static inline int ntb_spad_write(struct ntb_dev *ntb, int idx, u32 val) +static inline int ntb_spad_write(struct ntb_dev *ntb, int sidx, u32 val) { - return ntb->ops->spad_write(ntb, idx, val); + if (!ntb->ops->spad_write) + return -EINVAL; + + return ntb->ops->spad_write(ntb, sidx, val); } /** * ntb_peer_spad_addr() - address of the peer scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @pidx: Port index of peer device. + * @sidx: Scratchpad index. * @spad_addr: OUT - The address of the peer scratchpad register. * * Return the address of the peer doorbell register. This may be used, for @@ -948,45 +1285,213 @@ static inline int ntb_spad_write(struct ntb_dev *ntb, int idx, u32 val) * * Return: Zero on success, otherwise an error number. */ -static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int idx, +static inline int ntb_peer_spad_addr(struct ntb_dev *ntb, int pidx, int sidx, phys_addr_t *spad_addr) { if (!ntb->ops->peer_spad_addr) return -EINVAL; - return ntb->ops->peer_spad_addr(ntb, idx, spad_addr); + return ntb->ops->peer_spad_addr(ntb, pidx, sidx, spad_addr); } /** * ntb_peer_spad_read() - read the peer scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @pidx: Port index of peer device. + * @sidx: Scratchpad index. * * Read the peer scratchpad register, and return the value. * * Return: The value of the local scratchpad register. */ -static inline u32 ntb_peer_spad_read(struct ntb_dev *ntb, int idx) +static inline u32 ntb_peer_spad_read(struct ntb_dev *ntb, int pidx, int sidx) { if (!ntb->ops->peer_spad_read) - return 0; + return ~(u32)0; - return ntb->ops->peer_spad_read(ntb, idx); + return ntb->ops->peer_spad_read(ntb, pidx, sidx); } /** * ntb_peer_spad_write() - write the peer scratchpad register * @ntb: NTB device context. - * @idx: Scratchpad index. + * @pidx: Port index of peer device. + * @sidx: Scratchpad index. * @val: Scratchpad value. * * Write the value to the peer scratchpad register. * * Return: Zero on success, otherwise an error number. */ -static inline int ntb_peer_spad_write(struct ntb_dev *ntb, int idx, u32 val) +static inline int ntb_peer_spad_write(struct ntb_dev *ntb, int pidx, int sidx, + u32 val) +{ + if (!ntb->ops->peer_spad_write) + return -EINVAL; + + return ntb->ops->peer_spad_write(ntb, pidx, sidx, val); +} + +/** + * ntb_msg_count() - get the number of message registers + * @ntb: NTB device context. + * + * Hardware may support a different number of message registers. + * + * Return: the number of message registers. + */ +static inline int ntb_msg_count(struct ntb_dev *ntb) +{ + if (!ntb->ops->msg_count) + return 0; + + return ntb->ops->msg_count(ntb); +} + +/** + * ntb_msg_inbits() - get a bitfield of inbound message registers status + * @ntb: NTB device context. + * + * The method returns the bitfield of status and mask registers, which related + * to inbound message registers. + * + * Return: bitfield of inbound message registers. + */ +static inline u64 ntb_msg_inbits(struct ntb_dev *ntb) { - return ntb->ops->peer_spad_write(ntb, idx, val); + if (!ntb->ops->msg_inbits) + return 0; + + return ntb->ops->msg_inbits(ntb); +} + +/** + * ntb_msg_outbits() - get a bitfield of outbound message registers status + * @ntb: NTB device context. + * + * The method returns the bitfield of status and mask registers, which related + * to outbound message registers. + * + * Return: bitfield of outbound message registers. + */ +static inline u64 ntb_msg_outbits(struct ntb_dev *ntb) +{ + if (!ntb->ops->msg_outbits) + return 0; + + return ntb->ops->msg_outbits(ntb); +} + +/** + * ntb_msg_read_sts() - read the message registers status + * @ntb: NTB device context. + * + * Read the status of message register. Inbound and outbound message registers + * related bits can be filtered by masks retrieved from ntb_msg_inbits() and + * ntb_msg_outbits(). + * + * Return: status bits of message registers + */ +static inline u64 ntb_msg_read_sts(struct ntb_dev *ntb) +{ + if (!ntb->ops->msg_read_sts) + return 0; + + return ntb->ops->msg_read_sts(ntb); +} + +/** + * ntb_msg_clear_sts() - clear status bits of message registers + * @ntb: NTB device context. + * @sts_bits: Status bits to clear. + * + * Clear bits in the status register. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_clear_sts(struct ntb_dev *ntb, u64 sts_bits) +{ + if (!ntb->ops->msg_clear_sts) + return -EINVAL; + + return ntb->ops->msg_clear_sts(ntb, sts_bits); +} + +/** + * ntb_msg_set_mask() - set mask of message register status bits + * @ntb: NTB device context. + * @mask_bits: Mask bits. + * + * Mask the message registers status bits from raising the message event. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_set_mask(struct ntb_dev *ntb, u64 mask_bits) +{ + if (!ntb->ops->msg_set_mask) + return -EINVAL; + + return ntb->ops->msg_set_mask(ntb, mask_bits); +} + +/** + * ntb_msg_clear_mask() - clear message registers mask + * @ntb: NTB device context. + * @mask_bits: Mask bits to clear. + * + * Clear bits in the message events mask register. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_clear_mask(struct ntb_dev *ntb, u64 mask_bits) +{ + if (!ntb->ops->msg_clear_mask) + return -EINVAL; + + return ntb->ops->msg_clear_mask(ntb, mask_bits); +} + +/** + * ntb_msg_read() - read message register with specified index + * @ntb: NTB device context. + * @midx: Message register index + * @pidx: OUT - Port index of peer device a message retrieved from + * @msg: OUT - Data + * + * Read data from the specified message register. Source port index of a + * message is retrieved as well. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_read(struct ntb_dev *ntb, int midx, int *pidx, + u32 *msg) +{ + if (!ntb->ops->msg_read) + return -EINVAL; + + return ntb->ops->msg_read(ntb, midx, pidx, msg); +} + +/** + * ntb_msg_write() - write data to the specified message register + * @ntb: NTB device context. + * @midx: Message register index + * @pidx: Port index of peer device a message being sent to + * @msg: Data to send + * + * Send data to a specified peer device using the defined message register. + * Message event can be raised if the midx registers isn't empty while + * calling this method and the corresponding interrupt isn't masked. + * + * Return: Zero on success, otherwise a negative error number. + */ +static inline int ntb_msg_write(struct ntb_dev *ntb, int midx, int pidx, + u32 msg) +{ + if (!ntb->ops->msg_write) + return -EINVAL; + + return ntb->ops->msg_write(ntb, midx, pidx, msg); } #endif diff --git a/include/linux/nvme-fc.h b/include/linux/nvme-fc.h index bc711a10be05..21c37e39e41a 100644 --- a/include/linux/nvme-fc.h +++ b/include/linux/nvme-fc.h @@ -17,6 +17,7 @@ /* * This file contains definitions relative to FC-NVME r1.14 (16-020vB). + * The fcnvme_lsdesc_cr_assoc_cmd struct reflects expected r1.16 content. */ #ifndef _NVME_FC_H @@ -193,9 +194,21 @@ struct fcnvme_lsdesc_cr_assoc_cmd { uuid_t hostid; u8 hostnqn[FCNVME_ASSOC_HOSTNQN_LEN]; u8 subnqn[FCNVME_ASSOC_SUBNQN_LEN]; - u8 rsvd632[384]; + __be32 rsvd584[108]; /* pad to 1016 bytes, + * which makes overall LS rqst + * payload 1024 bytes + */ }; +#define FCNVME_LSDESC_CRA_CMD_DESC_MINLEN \ + offsetof(struct fcnvme_lsdesc_cr_assoc_cmd, rsvd584) + +#define FCNVME_LSDESC_CRA_CMD_DESC_MIN_DESCLEN \ + (FCNVME_LSDESC_CRA_CMD_DESC_MINLEN - \ + offsetof(struct fcnvme_lsdesc_cr_assoc_cmd, ersp_ratio)) + + + /* FCNVME_LSDESC_CREATE_CONN_CMD */ struct fcnvme_lsdesc_cr_conn_cmd { __be32 desc_tag; /* FCNVME_LSDESC_xxx */ @@ -273,6 +286,14 @@ struct fcnvme_ls_cr_assoc_rqst { struct fcnvme_lsdesc_cr_assoc_cmd assoc_cmd; }; +#define FCNVME_LSDESC_CRA_RQST_MINLEN \ + (offsetof(struct fcnvme_ls_cr_assoc_rqst, assoc_cmd) + \ + FCNVME_LSDESC_CRA_CMD_DESC_MINLEN) + +#define FCNVME_LSDESC_CRA_RQST_MIN_LISTLEN \ + FCNVME_LSDESC_CRA_CMD_DESC_MINLEN + + struct fcnvme_ls_cr_assoc_acc { struct fcnvme_ls_acc_hdr hdr; struct fcnvme_lsdesc_assoc_id associd; diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index cd93416d762e..497706f5adca 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -12,6 +12,9 @@ #ifndef _LINUX_NVMEM_PROVIDER_H #define _LINUX_NVMEM_PROVIDER_H +#include <linux/err.h> +#include <linux/errno.h> + struct nvmem_device; struct nvmem_cell_info; typedef int (*nvmem_reg_read_t)(void *priv, unsigned int offset, diff --git a/include/linux/of.h b/include/linux/of.h index fa089a2789a0..4a8a70916237 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -100,10 +100,12 @@ struct of_reconfig_data { /* initialize a node */ extern struct kobj_type of_node_ktype; +extern const struct fwnode_operations of_fwnode_ops; static inline void of_node_init(struct device_node *node) { kobject_init(&node->kobj, &of_node_ktype); node->fwnode.type = FWNODE_OF; + node->fwnode.ops = &of_fwnode_ops; } /* true when node is initialized */ diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index 610e13271918..1fd71733aa68 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -174,6 +174,7 @@ static inline void page_ref_unfreeze(struct page *page, int count) VM_BUG_ON_PAGE(page_count(page) != 0, page); VM_BUG_ON(count == 0); + smp_mb(); atomic_set(&page->_refcount, count); if (page_ref_tracepoint_active(__tracepoint_page_ref_unfreeze)) __page_ref_unfreeze(page, count); diff --git a/include/linux/platform_data/usb-ohci-s3c2410.h b/include/linux/platform_data/usb-ohci-s3c2410.h index 7fa1fbefc3f2..cc7554ae6e8b 100644 --- a/include/linux/platform_data/usb-ohci-s3c2410.h +++ b/include/linux/platform_data/usb-ohci-s3c2410.h @@ -31,7 +31,7 @@ struct s3c2410_hcd_info { void (*report_oc)(struct s3c2410_hcd_info *, int ports); }; -static void inline s3c2410_usb_report_oc(struct s3c2410_hcd_info *info, int ports) +static inline void s3c2410_usb_report_oc(struct s3c2410_hcd_info *info, int ports) { if (info->report_oc != NULL) { (info->report_oc)(info, ports); diff --git a/include/linux/property.h b/include/linux/property.h index 2f482616a2f2..7e77039e6b81 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -51,6 +51,7 @@ int device_property_read_string(struct device *dev, const char *propname, int device_property_match_string(struct device *dev, const char *propname, const char *string); +bool fwnode_device_is_available(struct fwnode_handle *fwnode); bool fwnode_property_present(struct fwnode_handle *fwnode, const char *propname); int fwnode_property_read_u8_array(struct fwnode_handle *fwnode, const char *propname, u8 *val, @@ -274,12 +275,16 @@ void *device_get_mac_address(struct device *dev, char *addr, int alen); struct fwnode_handle *fwnode_graph_get_next_endpoint( struct fwnode_handle *fwnode, struct fwnode_handle *prev); +struct fwnode_handle * +fwnode_graph_get_port_parent(struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_graph_get_remote_port_parent( struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_graph_get_remote_port( struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_graph_get_remote_endpoint( struct fwnode_handle *fwnode); +struct fwnode_handle *fwnode_graph_get_remote_node(struct fwnode_handle *fwnode, + u32 port, u32 endpoint); int fwnode_graph_parse_endpoint(struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint); diff --git a/include/linux/random.h b/include/linux/random.h index ed5c3838780d..1fa0dc880bd7 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -57,6 +57,27 @@ static inline unsigned long get_random_long(void) #endif } +/* + * On 64-bit architectures, protect against non-terminated C string overflows + * by zeroing out the first byte of the canary; this leaves 56 bits of entropy. + */ +#ifdef CONFIG_64BIT +# ifdef __LITTLE_ENDIAN +# define CANARY_MASK 0xffffffffffffff00UL +# else /* big endian, 64 bits: */ +# define CANARY_MASK 0x00ffffffffffffffUL +# endif +#else /* 32 bits: */ +# define CANARY_MASK 0xffffffffUL +#endif + +static inline unsigned long get_random_canary(void) +{ + unsigned long val = get_random_long(); + + return val & CANARY_MASK; +} + unsigned long randomize_page(unsigned long start, unsigned long range); u32 prandom_u32(void); diff --git a/include/linux/rtc.h b/include/linux/rtc.h index b693adac853b..0a0f0d14a5fb 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -14,6 +14,7 @@ #include <linux/types.h> #include <linux/interrupt.h> +#include <linux/nvmem-provider.h> #include <uapi/linux/rtc.h> extern int rtc_month_days(unsigned int month, unsigned int year); @@ -32,17 +33,11 @@ static inline time64_t rtc_tm_sub(struct rtc_time *lhs, struct rtc_time *rhs) return rtc_tm_to_time64(lhs) - rtc_tm_to_time64(rhs); } -/** - * Deprecated. Use rtc_time64_to_tm(). - */ static inline void rtc_time_to_tm(unsigned long time, struct rtc_time *tm) { rtc_time64_to_tm(time, tm); } -/** - * Deprecated. Use rtc_tm_to_time64(). - */ static inline int rtc_tm_to_time(struct rtc_time *tm, unsigned long *time) { *time = rtc_tm_to_time64(tm); @@ -116,7 +111,6 @@ struct rtc_device { struct module *owner; int id; - char name[RTC_DEVICE_NAME_SIZE]; const struct rtc_class_ops *ops; struct mutex ops_lock; @@ -143,6 +137,14 @@ struct rtc_device { /* Some hardware can't support UIE mode */ int uie_unsupported; + bool registered; + + struct nvmem_config *nvmem_config; + struct nvmem_device *nvmem; + /* Old ABI support */ + bool nvram_old_abi; + struct bin_attribute *nvram; + #ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL struct work_struct uie_task; struct timer_list uie_timer; @@ -164,6 +166,8 @@ extern struct rtc_device *devm_rtc_device_register(struct device *dev, const char *name, const struct rtc_class_ops *ops, struct module *owner); +struct rtc_device *devm_rtc_allocate_device(struct device *dev); +int __rtc_register_device(struct module *owner, struct rtc_device *rtc); extern void rtc_device_unregister(struct rtc_device *rtc); extern void devm_rtc_device_unregister(struct device *dev, struct rtc_device *rtc); @@ -219,6 +223,9 @@ static inline bool is_leap_year(unsigned int year) return (!(year % 4) && (year % 100)) || !(year % 400); } +#define rtc_register_device(device) \ + __rtc_register_device(THIS_MODULE, device) + #ifdef CONFIG_RTC_HCTOSYS_DEVICE extern int rtc_hctosys_ret; #else diff --git a/include/linux/sched.h b/include/linux/sched.h index 20814b7d7d70..2ba9ec93423f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -974,6 +974,7 @@ struct task_struct { #ifdef CONFIG_FAULT_INJECTION int make_it_fail; + unsigned int fail_nth; #endif /* * When (nr_dirtied >= nr_dirtied_pause), it's time to call diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index 69eedcef8f03..98ae0d05aa32 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -68,7 +68,10 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_OOM_SKIP 21 /* mm is of no interest for the OOM killer */ #define MMF_UNSTABLE 22 /* mm is unstable for copy_from_user */ #define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ +#define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ +#define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) -#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK) +#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ + MMF_DISABLE_THP_MASK) #endif /* _LINUX_SCHED_COREDUMP_H */ diff --git a/include/linux/sem.h b/include/linux/sem.h index 9edec926e9d9..be5cf2ea14ad 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -8,11 +8,29 @@ struct task_struct; +/* One semaphore structure for each semaphore in the system. */ +struct sem { + int semval; /* current value */ + /* + * PID of the process that last modified the semaphore. For + * Linux, specifically these are: + * - semop + * - semctl, via SETVAL and SETALL. + * - at task exit when performing undo adjustments (see exit_sem). + */ + int sempid; + spinlock_t lock; /* spinlock for fine-grained semtimedop */ + struct list_head pending_alter; /* pending single-sop operations */ + /* that alter the semaphore */ + struct list_head pending_const; /* pending single-sop operations */ + /* that do not alter the semaphore*/ + time_t sem_otime; /* candidate for sem_otime */ +} ____cacheline_aligned_in_smp; + /* One sem_array data structure for each set of semaphores in the system. */ struct sem_array { struct kern_ipc_perm sem_perm; /* permissions .. see ipc.h */ - time_t sem_ctime; /* last change time */ - struct sem *sem_base; /* ptr to first semaphore in array */ + time_t sem_ctime; /* create/last semctl() time */ struct list_head pending_alter; /* pending operations */ /* that alter the array */ struct list_head pending_const; /* pending complex operations */ @@ -21,6 +39,8 @@ struct sem_array { int sem_nsems; /* no. of semaphores in array */ int complex_count; /* pending complex operations */ unsigned int use_global_lock;/* >0: global lock required */ + + struct sem sems[]; }; #ifdef CONFIG_SYSVIPC diff --git a/include/linux/slab.h b/include/linux/slab.h index 04a7f7993e67..41473df6dfb0 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -471,7 +471,8 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) * * %__GFP_NOWARN - If allocation fails, don't issue any warnings. * - * %__GFP_REPEAT - If allocation fails initially, try once more before failing. + * %__GFP_RETRY_MAYFAIL - Try really hard to succeed the allocation but fail + * eventually. * * There are other flags available as well, but these are not intended * for general use, and so are not documented here. For a full list of diff --git a/include/linux/string.h b/include/linux/string.h index 7439d83eaa33..049866760e8b 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -193,4 +193,205 @@ static inline const char *kbasename(const char *path) return tail ? tail + 1 : path; } +#define __FORTIFY_INLINE extern __always_inline __attribute__((gnu_inline)) +#define __RENAME(x) __asm__(#x) + +void fortify_panic(const char *name) __noreturn __cold; +void __read_overflow(void) __compiletime_error("detected read beyond size of object passed as 1st parameter"); +void __read_overflow2(void) __compiletime_error("detected read beyond size of object passed as 2nd parameter"); +void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter"); + +#if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) +__FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __write_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __builtin_strncpy(p, q, size); +} + +__FORTIFY_INLINE char *strcat(char *p, const char *q) +{ + size_t p_size = __builtin_object_size(p, 0); + if (p_size == (size_t)-1) + return __builtin_strcat(p, q); + if (strlcat(p, q, p_size) >= p_size) + fortify_panic(__func__); + return p; +} + +__FORTIFY_INLINE __kernel_size_t strlen(const char *p) +{ + __kernel_size_t ret; + size_t p_size = __builtin_object_size(p, 0); + if (p_size == (size_t)-1) + return __builtin_strlen(p); + ret = strnlen(p, p_size); + if (p_size <= ret) + fortify_panic(__func__); + return ret; +} + +extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); +__FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) +{ + size_t p_size = __builtin_object_size(p, 0); + __kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); + if (p_size <= ret && maxlen != ret) + fortify_panic(__func__); + return ret; +} + +/* defined after fortified strlen to reuse it */ +extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); +__FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) +{ + size_t ret; + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __real_strlcpy(p, q, size); + ret = strlen(q); + if (size) { + size_t len = (ret >= size) ? size - 1 : ret; + if (__builtin_constant_p(len) && len >= p_size) + __write_overflow(); + if (len >= p_size) + fortify_panic(__func__); + __builtin_memcpy(p, q, len); + p[len] = '\0'; + } + return ret; +} + +/* defined after fortified strlen and strnlen to reuse them */ +__FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) +{ + size_t p_len, copy_len; + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __builtin_strncat(p, q, count); + p_len = strlen(p); + copy_len = strnlen(q, count); + if (p_size < p_len + copy_len + 1) + fortify_panic(__func__); + __builtin_memcpy(p + p_len, q, copy_len); + p[p_len + copy_len] = '\0'; + return p; +} + +__FORTIFY_INLINE void *memset(void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __write_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __builtin_memset(p, c, size); +} + +__FORTIFY_INLINE void *memcpy(void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (__builtin_constant_p(size)) { + if (p_size < size) + __write_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __builtin_memcpy(p, q, size); +} + +__FORTIFY_INLINE void *memmove(void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (__builtin_constant_p(size)) { + if (p_size < size) + __write_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __builtin_memmove(p, q, size); +} + +extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan); +__FORTIFY_INLINE void *memscan(void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_memscan(p, c, size); +} + +__FORTIFY_INLINE int memcmp(const void *p, const void *q, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (__builtin_constant_p(size)) { + if (p_size < size) + __read_overflow(); + if (q_size < size) + __read_overflow2(); + } + if (p_size < size || q_size < size) + fortify_panic(__func__); + return __builtin_memcmp(p, q, size); +} + +__FORTIFY_INLINE void *memchr(const void *p, int c, __kernel_size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __builtin_memchr(p, c, size); +} + +void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv); +__FORTIFY_INLINE void *memchr_inv(const void *p, int c, size_t size) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_memchr_inv(p, c, size); +} + +extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup); +__FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) +{ + size_t p_size = __builtin_object_size(p, 0); + if (__builtin_constant_p(size) && p_size < size) + __read_overflow(); + if (p_size < size) + fortify_panic(__func__); + return __real_kmemdup(p, size, gfp); +} + +/* defined after fortified strlen and memcpy to reuse them */ +__FORTIFY_INLINE char *strcpy(char *p, const char *q) +{ + size_t p_size = __builtin_object_size(p, 0); + size_t q_size = __builtin_object_size(q, 0); + if (p_size == (size_t)-1 && q_size == (size_t)-1) + return __builtin_strcpy(p, q); + memcpy(p, q, strlen(q) + 1); + return p; +} + +#endif + #endif /* _LINUX_STRING_H_ */ diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 6095ecba0dde..55ef67bea06b 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -39,7 +39,7 @@ struct rpc_clnt { struct list_head cl_tasks; /* List of tasks */ spinlock_t cl_lock; /* spinlock */ struct rpc_xprt __rcu * cl_xprt; /* transport */ - struct rpc_procinfo * cl_procinfo; /* procedure info */ + const struct rpc_procinfo *cl_procinfo; /* procedure info */ u32 cl_prog, /* RPC program number */ cl_vers, /* RPC version number */ cl_maxproc; /* max procedure number */ @@ -87,7 +87,8 @@ struct rpc_program { struct rpc_version { u32 number; /* version number */ unsigned int nrprocs; /* number of procs */ - struct rpc_procinfo * procs; /* procedure array */ + const struct rpc_procinfo *procs; /* procedure array */ + unsigned int *counts; /* call counts */ }; /* @@ -99,7 +100,6 @@ struct rpc_procinfo { kxdrdproc_t p_decode; /* XDR decode function */ unsigned int p_arglen; /* argument hdr length (u32) */ unsigned int p_replen; /* reply hdr length (u32) */ - unsigned int p_count; /* call count */ unsigned int p_timer; /* Which RTT timer to use */ u32 p_statidx; /* Which procedure to account */ const char * p_name; /* name of procedure */ diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 9d7529ffc4ce..50a99a117da7 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -22,7 +22,7 @@ */ struct rpc_procinfo; struct rpc_message { - struct rpc_procinfo * rpc_proc; /* Procedure information */ + const struct rpc_procinfo *rpc_proc; /* Procedure information */ void * rpc_argp; /* Arguments */ void * rpc_resp; /* Result */ struct rpc_cred * rpc_cred; /* Credentials */ diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 11cef5a7bc87..a3f8af9bd543 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -237,7 +237,7 @@ struct svc_rqst { struct svc_serv * rq_server; /* RPC service definition */ struct svc_pool * rq_pool; /* thread pool */ - struct svc_procedure * rq_procinfo; /* procedure info */ + const struct svc_procedure *rq_procinfo;/* procedure info */ struct auth_ops * rq_authop; /* authentication flavour */ struct svc_cred rq_cred; /* auth info */ void * rq_xprt_ctxt; /* transport specific context ptr */ @@ -246,7 +246,7 @@ struct svc_rqst { size_t rq_xprt_hlen; /* xprt header len */ struct xdr_buf rq_arg; struct xdr_buf rq_res; - struct page * rq_pages[RPCSVC_MAXPAGES]; + struct page *rq_pages[RPCSVC_MAXPAGES + 1]; struct page * *rq_respages; /* points into rq_pages */ struct page * *rq_next_page; /* next reply page to use */ struct page * *rq_page_end; /* one past the last page */ @@ -384,7 +384,7 @@ struct svc_program { unsigned int pg_lovers; /* lowest version */ unsigned int pg_hivers; /* highest version */ unsigned int pg_nvers; /* number of versions */ - struct svc_version ** pg_vers; /* version array */ + const struct svc_version **pg_vers; /* version array */ char * pg_name; /* service name */ char * pg_class; /* class name: services sharing authentication */ struct svc_stat * pg_stats; /* rpc statistics */ @@ -397,7 +397,8 @@ struct svc_program { struct svc_version { u32 vs_vers; /* version number */ u32 vs_nproc; /* number of procedures */ - struct svc_procedure * vs_proc; /* per-procedure info */ + const struct svc_procedure *vs_proc; /* per-procedure info */ + unsigned int *vs_count; /* call counts */ u32 vs_xdrsize; /* xdrsize needed for this version */ /* Don't register with rpcbind */ @@ -419,15 +420,17 @@ struct svc_version { /* * RPC procedure info */ -typedef __be32 (*svc_procfunc)(struct svc_rqst *, void *argp, void *resp); struct svc_procedure { - svc_procfunc pc_func; /* process the request */ - kxdrproc_t pc_decode; /* XDR decode args */ - kxdrproc_t pc_encode; /* XDR encode result */ - kxdrproc_t pc_release; /* XDR free result */ + /* process the request: */ + __be32 (*pc_func)(struct svc_rqst *); + /* XDR decode args: */ + int (*pc_decode)(struct svc_rqst *, __be32 *data); + /* XDR encode result: */ + int (*pc_encode)(struct svc_rqst *, __be32 *data); + /* XDR free result: */ + void (*pc_release)(struct svc_rqst *); unsigned int pc_argsize; /* argument struct size */ unsigned int pc_ressize; /* result struct size */ - unsigned int pc_count; /* call count */ unsigned int pc_cachetype; /* cache info (NFS) */ unsigned int pc_xdrressize; /* maximum size of XDR reply */ }; diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index f3787d800ba4..995c6fe9ee90 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -77,46 +77,25 @@ extern atomic_t rdma_stat_sq_prod; */ struct svc_rdma_op_ctxt { struct list_head list; - struct svc_rdma_op_ctxt *read_hdr; - struct svc_rdma_fastreg_mr *frmr; - int hdr_count; struct xdr_buf arg; struct ib_cqe cqe; - struct ib_cqe reg_cqe; - struct ib_cqe inv_cqe; u32 byte_len; - u32 position; struct svcxprt_rdma *xprt; - unsigned long flags; enum dma_data_direction direction; int count; unsigned int mapped_sges; + int hdr_count; struct ib_send_wr send_wr; struct ib_sge sge[1 + RPCRDMA_MAX_INLINE_THRESH / PAGE_SIZE]; struct page *pages[RPCSVC_MAXPAGES]; }; -struct svc_rdma_fastreg_mr { - struct ib_mr *mr; - struct scatterlist *sg; - int sg_nents; - unsigned long access_flags; - enum dma_data_direction direction; - struct list_head frmr_list; -}; - -#define RDMACTXT_F_LAST_CTXT 2 - -#define SVCRDMA_DEVCAP_FAST_REG 1 /* fast mr registration */ -#define SVCRDMA_DEVCAP_READ_W_INV 2 /* read w/ invalidate */ - struct svcxprt_rdma { struct svc_xprt sc_xprt; /* SVC transport structure */ struct rdma_cm_id *sc_cm_id; /* RDMA connection id */ struct list_head sc_accept_q; /* Conn. waiting accept */ int sc_ord; /* RDMA read limit */ int sc_max_sge; - int sc_max_sge_rd; /* max sge for read target */ bool sc_snd_w_inv; /* OK to use Send With Invalidate */ atomic_t sc_sq_avail; /* SQEs ready to be consumed */ @@ -141,14 +120,6 @@ struct svcxprt_rdma { struct ib_qp *sc_qp; struct ib_cq *sc_rq_cq; struct ib_cq *sc_sq_cq; - int (*sc_reader)(struct svcxprt_rdma *, - struct svc_rqst *, - struct svc_rdma_op_ctxt *, - int *, u32 *, u32, u32, u64, bool); - u32 sc_dev_caps; /* distilled device caps */ - unsigned int sc_frmr_pg_list_len; - struct list_head sc_frmr_q; - spinlock_t sc_frmr_q_lock; spinlock_t sc_lock; /* transport lock */ @@ -185,20 +156,14 @@ extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp, struct xdr_buf *rcvbuf); -/* svc_rdma_marshal.c */ -extern int svc_rdma_xdr_decode_req(struct xdr_buf *); - /* svc_rdma_recvfrom.c */ extern int svc_rdma_recvfrom(struct svc_rqst *); -extern int rdma_read_chunk_lcl(struct svcxprt_rdma *, struct svc_rqst *, - struct svc_rdma_op_ctxt *, int *, u32 *, - u32, u32, u64, bool); -extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *, - struct svc_rdma_op_ctxt *, int *, u32 *, - u32, u32, u64, bool); /* svc_rdma_rw.c */ extern void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma); +extern int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, + struct svc_rqst *rqstp, + struct svc_rdma_op_ctxt *head, __be32 *p); extern int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch, struct xdr_buf *xdr); extern int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma, @@ -226,9 +191,6 @@ extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *); extern struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *); extern void svc_rdma_put_context(struct svc_rdma_op_ctxt *, int); extern void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt); -extern struct svc_rdma_fastreg_mr *svc_rdma_get_frmr(struct svcxprt_rdma *); -extern void svc_rdma_put_frmr(struct svcxprt_rdma *, - struct svc_rdma_fastreg_mr *); extern void svc_sq_reap(struct svcxprt_rdma *); extern void svc_rq_reap(struct svcxprt_rdma *); extern void svc_rdma_prep_reply_hdr(struct svc_rqst *); diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 054c8cde18f3..261b48a2701d 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -17,6 +17,8 @@ #include <asm/unaligned.h> #include <linux/scatterlist.h> +struct rpc_rqst; + /* * Buffer adjustment */ @@ -33,13 +35,6 @@ struct xdr_netobj { }; /* - * This is the legacy generic XDR function. rqstp is either a rpc_rqst - * (client side) or svc_rqst pointer (server side). - * Encode functions always assume there's enough room in the buffer. - */ -typedef int (*kxdrproc_t)(void *rqstp, __be32 *data, void *obj); - -/* * Basic structure for transmission/reception of a client XDR message. * Features a header (for a linear buffer containing RPC headers * and the data payload for short messages), and then an array of @@ -222,8 +217,10 @@ struct xdr_stream { /* * These are the xdr_stream style generic XDR encode and decode functions. */ -typedef void (*kxdreproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj); -typedef int (*kxdrdproc_t)(void *rqstp, struct xdr_stream *xdr, void *obj); +typedef void (*kxdreproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + const void *obj); +typedef int (*kxdrdproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + void *obj); extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p); extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); diff --git a/include/linux/swap.h b/include/linux/swap.h index 5ab1c98c7d27..d83d28e53e62 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -277,6 +277,7 @@ extern void mark_page_accessed(struct page *); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_all(void); +extern void lru_add_drain_all_cpuslocked(void); extern void rotate_reclaimable_page(struct page *page); extern void deactivate_file_page(struct page *page); extern void mark_page_lazyfree(struct page *page); @@ -331,7 +332,7 @@ extern void kswapd_stop(int nid); #include <linux/blk_types.h> /* for bio_end_io_t */ /* linux/mm/page_io.c */ -extern int swap_readpage(struct page *); +extern int swap_readpage(struct page *page, bool do_poll); extern int swap_writepage(struct page *page, struct writeback_control *wbc); extern void end_swap_bio_write(struct bio *bio); extern int __swap_writepage(struct page *page, struct writeback_control *wbc, @@ -362,7 +363,8 @@ extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); extern struct page *lookup_swap_cache(swp_entry_t); extern struct page *read_swap_cache_async(swp_entry_t, gfp_t, - struct vm_area_struct *vma, unsigned long addr); + struct vm_area_struct *vma, unsigned long addr, + bool do_poll); extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr, bool *new_page_allocated); diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 5c3a5f3e7eec..c5ff7b217ee6 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -196,15 +196,6 @@ static inline void num_poisoned_pages_dec(void) atomic_long_dec(&num_poisoned_pages); } -static inline void num_poisoned_pages_add(long num) -{ - atomic_long_add(num, &num_poisoned_pages); -} - -static inline void num_poisoned_pages_sub(long num) -{ - atomic_long_sub(num, &num_poisoned_pages); -} #else static inline swp_entry_t make_hwpoison_entry(struct page *page) diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 80d07816def0..3a89b9ff4cdc 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -47,6 +47,9 @@ extern int proc_douintvec(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec_minmax(struct ctl_table *, int, void __user *, size_t *, loff_t *); +extern int proc_douintvec_minmax(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); extern int proc_dointvec_jiffies(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec_userhz_jiffies(struct ctl_table *, int, @@ -143,7 +146,7 @@ struct ctl_table_header struct ctl_table_set *set; struct ctl_dir *parent; struct ctl_node *node; - struct list_head inodes; /* head for proc_inode->sysctl_inodes */ + struct hlist_head inodes; /* head for proc_inode->sysctl_inodes */ }; struct ctl_dir { diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index 9375d23a24e7..635a3c5706bd 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -33,6 +33,8 @@ struct t10_pi_tuple { __be32 ref_tag; /* Target LBA or indirect LBA */ }; +#define T10_PI_APP_ESCAPE cpu_to_be16(0xffff) +#define T10_PI_REF_ESCAPE cpu_to_be32(0xffffffff) extern const struct blk_integrity_profile t10_pi_type1_crc; extern const struct blk_integrity_profile t10_pi_type1_ip; diff --git a/include/linux/vfio.h b/include/linux/vfio.h index f57076b958b7..586809abb273 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -97,6 +97,8 @@ extern void vfio_unregister_iommu_driver( */ extern struct vfio_group *vfio_group_get_external_user(struct file *filep); extern void vfio_group_put_external_user(struct vfio_group *group); +extern bool vfio_external_group_match_file(struct vfio_group *group, + struct file *filep); extern int vfio_external_user_iommu_id(struct vfio_group *group); extern long vfio_external_check_extension(struct vfio_group *group, unsigned long arg); |