diff --git a/Documentation/robust-futexes.txt b/Documentation/robust-futexes.txt index 6c42c75103eb..6361fb01c9c1 100644 --- a/Documentation/robust-futexes.txt +++ b/Documentation/robust-futexes.txt @@ -218,5 +218,4 @@ All other architectures should build just fine too - but they won't have the new syscalls yet. Architectures need to implement the new futex_atomic_cmpxchg_inatomic() -inline function before writing up the syscalls (that function returns --ENOSYS right now). +inline function before writing up the syscalls. diff --git a/Makefile b/Makefile index 275343cf27f7..23b2916ef0ff 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 14 -SUBLEVEL = 131 +SUBLEVEL = 132 EXTRAVERSION = NAME = Petit Gorille diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h index c7e30a6ed56e..232917e9c1d9 100644 --- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -134,7 +134,9 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr, : "memory"); uaccess_disable(); - *uval = val; + if (!ret) + *uval = val; + return ret; } diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 4214c38d016b..e3193fd39d8d 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -271,6 +271,7 @@ __AARCH64_INSN_FUNCS(adrp, 0x9F000000, 0x90000000) __AARCH64_INSN_FUNCS(prfm, 0x3FC00000, 0x39800000) __AARCH64_INSN_FUNCS(prfm_lit, 0xFF000000, 0xD8000000) __AARCH64_INSN_FUNCS(str_reg, 0x3FE0EC00, 0x38206800) +__AARCH64_INSN_FUNCS(ldadd, 0x3F20FC00, 0x38200000) __AARCH64_INSN_FUNCS(ldr_reg, 0x3FE0EC00, 0x38606800) __AARCH64_INSN_FUNCS(ldr_lit, 0xBF000000, 0x18000000) __AARCH64_INSN_FUNCS(ldrsw_lit, 0xFF000000, 0x98000000) @@ -383,6 +384,13 @@ u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg, enum aarch64_insn_register state, enum aarch64_insn_size_type size, enum aarch64_insn_ldst_type type); +u32 aarch64_insn_gen_ldadd(enum aarch64_insn_register result, + enum aarch64_insn_register address, + enum aarch64_insn_register value, + enum aarch64_insn_size_type size); +u32 aarch64_insn_gen_stadd(enum aarch64_insn_register address, + enum aarch64_insn_register value, + enum aarch64_insn_size_type size); u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst, enum aarch64_insn_register src, int imm, enum aarch64_insn_variant variant, diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index 2718a77da165..4381aa7b071d 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -793,6 +793,46 @@ u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg, state); } +u32 aarch64_insn_gen_ldadd(enum aarch64_insn_register result, + enum aarch64_insn_register address, + enum aarch64_insn_register value, + enum aarch64_insn_size_type size) +{ + u32 insn = aarch64_insn_get_ldadd_value(); + + switch (size) { + case AARCH64_INSN_SIZE_32: + case AARCH64_INSN_SIZE_64: + break; + default: + pr_err("%s: unimplemented size encoding %d\n", __func__, size); + return AARCH64_BREAK_FAULT; + } + + insn = aarch64_insn_encode_ldst_size(size, insn); + + insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn, + result); + + insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, + address); + + return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RS, insn, + value); +} + +u32 aarch64_insn_gen_stadd(enum aarch64_insn_register address, + enum aarch64_insn_register value, + enum aarch64_insn_size_type size) +{ + /* + * STADD is simply encoded as an alias for LDADD with XZR as + * the destination register. + */ + return aarch64_insn_gen_ldadd(AARCH64_INSN_REG_ZR, address, + value, size); +} + static u32 aarch64_insn_encode_prfm_imm(enum aarch64_insn_prfm_type type, enum aarch64_insn_prfm_target target, enum aarch64_insn_prfm_policy policy, diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h index 6c881659ee8a..76606e87233f 100644 --- a/arch/arm64/net/bpf_jit.h +++ b/arch/arm64/net/bpf_jit.h @@ -100,6 +100,10 @@ #define A64_STXR(sf, Rt, Rn, Rs) \ A64_LSX(sf, Rt, Rn, Rs, STORE_EX) +/* LSE atomics */ +#define A64_STADD(sf, Rn, Rs) \ + aarch64_insn_gen_stadd(Rn, Rs, A64_SIZE(sf)) + /* Add/subtract (immediate) */ #define A64_ADDSUB_IMM(sf, Rd, Rn, imm12, type) \ aarch64_insn_gen_add_sub_imm(Rd, Rn, imm12, \ diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 6110fe344368..b742171bfef7 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -330,7 +330,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) const int i = insn - ctx->prog->insnsi; const bool is64 = BPF_CLASS(code) == BPF_ALU64; const bool isdw = BPF_SIZE(code) == BPF_DW; - u8 jmp_cond; + u8 jmp_cond, reg; s32 jmp_offset; #define check_imm(bits, imm) do { \ @@ -706,18 +706,28 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) break; } break; + /* STX XADD: lock *(u32 *)(dst + off) += src */ case BPF_STX | BPF_XADD | BPF_W: /* STX XADD: lock *(u64 *)(dst + off) += src */ case BPF_STX | BPF_XADD | BPF_DW: - emit_a64_mov_i(1, tmp, off, ctx); - emit(A64_ADD(1, tmp, tmp, dst), ctx); - emit(A64_LDXR(isdw, tmp2, tmp), ctx); - emit(A64_ADD(isdw, tmp2, tmp2, src), ctx); - emit(A64_STXR(isdw, tmp2, tmp, tmp3), ctx); - jmp_offset = -3; - check_imm19(jmp_offset); - emit(A64_CBNZ(0, tmp3, jmp_offset), ctx); + if (!off) { + reg = dst; + } else { + emit_a64_mov_i(1, tmp, off, ctx); + emit(A64_ADD(1, tmp, tmp, dst), ctx); + reg = tmp; + } + if (cpus_have_cap(ARM64_HAS_LSE_ATOMICS)) { + emit(A64_STADD(isdw, reg, src), ctx); + } else { + emit(A64_LDXR(isdw, tmp2, reg), ctx); + emit(A64_ADD(isdw, tmp2, tmp2, src), ctx); + emit(A64_STXR(isdw, tmp2, reg, tmp3), ctx); + jmp_offset = -3; + check_imm19(jmp_offset); + emit(A64_CBNZ(0, tmp3, jmp_offset), ctx); + } break; /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 2769e0f5c686..3b44d39aca1d 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -820,6 +820,16 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) break; } + /* + * If SSBD is controlled by the SPEC_CTRL MSR, then set the proper + * bit in the mask to allow guests to use the mitigation even in the + * case where the host does not enable it. + */ + if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + static_cpu_has(X86_FEATURE_AMD_SSBD)) { + x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; + } + /* * We have three CPU feature flags that are in play here: * - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible. @@ -837,7 +847,6 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) x86_amd_ssb_disable(); } else { x86_spec_ctrl_base |= SPEC_CTRL_SSBD; - x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); } } diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 4a2100ac3423..93c22e7ee424 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -790,13 +790,16 @@ static struct syscore_ops mc_syscore_ops = { .resume = mc_bp_resume, }; -static int mc_cpu_online(unsigned int cpu) +static int mc_cpu_starting(unsigned int cpu) { - struct device *dev; - - dev = get_cpu_device(cpu); microcode_update_cpu(cpu); pr_debug("CPU%d added\n", cpu); + return 0; +} + +static int mc_cpu_online(unsigned int cpu) +{ + struct device *dev = get_cpu_device(cpu); if (sysfs_create_group(&dev->kobj, &mc_attr_group)) pr_err("Failed to create group for CPU%d\n", cpu); @@ -873,7 +876,9 @@ int __init microcode_init(void) goto out_ucode_group; register_syscore_ops(&mc_syscore_ops); - cpuhp_setup_state_nocalls(CPUHP_AP_MICROCODE_LOADER, "x86/microcode:online", + cpuhp_setup_state_nocalls(CPUHP_AP_MICROCODE_LOADER, "x86/microcode:starting", + mc_cpu_starting, NULL); + cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/microcode:online", mc_cpu_online, mc_cpu_down_prep); pr_info("Microcode Update Driver: v%s.", DRIVER_VERSION); diff --git a/block/bio.c b/block/bio.c index d01ab919b313..1384f9790882 100644 --- a/block/bio.c +++ b/block/bio.c @@ -773,7 +773,7 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page return 0; } - if (bio->bi_vcnt >= bio->bi_max_vecs) + if (bio_full(bio)) return 0; /* @@ -821,65 +821,97 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page EXPORT_SYMBOL(bio_add_pc_page); /** - * bio_add_page - attempt to add page to bio - * @bio: destination bio - * @page: page to add - * @len: vec entry length - * @offset: vec entry offset + * __bio_try_merge_page - try appending data to an existing bvec. + * @bio: destination bio + * @page: page to add + * @len: length of the data to add + * @off: offset of the data in @page * - * Attempt to add a page to the bio_vec maplist. This will only fail - * if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio. + * Try to add the data at @page + @off to the last bvec of @bio. This is a + * a useful optimisation for file systems with a block size smaller than the + * page size. + * + * Return %true on success or %false on failure. */ -int bio_add_page(struct bio *bio, struct page *page, - unsigned int len, unsigned int offset) +bool __bio_try_merge_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int off) { - struct bio_vec *bv; - - /* - * cloned bio must not modify vec list - */ if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) - return 0; + return false; - /* - * For filesystems with a blocksize smaller than the pagesize - * we will often be called with the same page as last time and - * a consecutive offset. Optimize this special case. - */ if (bio->bi_vcnt > 0) { - bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; + struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; - if (page == bv->bv_page && - offset == bv->bv_offset + bv->bv_len) { + if (page == bv->bv_page && off == bv->bv_offset + bv->bv_len) { bv->bv_len += len; - goto done; + bio->bi_iter.bi_size += len; + return true; } } + return false; +} +EXPORT_SYMBOL_GPL(__bio_try_merge_page); - if (bio->bi_vcnt >= bio->bi_max_vecs) - return 0; +/** + * __bio_add_page - add page to a bio in a new segment + * @bio: destination bio + * @page: page to add + * @len: length of the data to add + * @off: offset of the data in @page + * + * Add the data at @page + @off to @bio as a new bvec. The caller must ensure + * that @bio has space for another bvec. + */ +void __bio_add_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int off) +{ + struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt]; - bv = &bio->bi_io_vec[bio->bi_vcnt]; - bv->bv_page = page; - bv->bv_len = len; - bv->bv_offset = offset; + WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); + WARN_ON_ONCE(bio_full(bio)); + + bv->bv_page = page; + bv->bv_offset = off; + bv->bv_len = len; - bio->bi_vcnt++; -done: bio->bi_iter.bi_size += len; + bio->bi_vcnt++; +} +EXPORT_SYMBOL_GPL(__bio_add_page); + +/** + * bio_add_page - attempt to add page to bio + * @bio: destination bio + * @page: page to add + * @len: vec entry length + * @offset: vec entry offset + * + * Attempt to add a page to the bio_vec maplist. This will only fail + * if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio. + */ +int bio_add_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int offset) +{ + if (!__bio_try_merge_page(bio, page, len, offset)) { + if (bio_full(bio)) + return 0; + __bio_add_page(bio, page, len, offset); + } return len; } EXPORT_SYMBOL(bio_add_page); /** - * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio + * __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio * @bio: bio to add pages to * @iter: iov iterator describing the region to be mapped * - * Pins as many pages from *iter and appends them to @bio's bvec array. The + * Pins pages from *iter and appends them to @bio's bvec array. The * pages will have to be released using put_page() when done. + * For multi-segment *iter, this function only adds pages from the + * the next non-empty segment of the iov iterator. */ -int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) +static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt, idx; struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt; @@ -916,6 +948,33 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) iov_iter_advance(iter, size); return 0; } + +/** + * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio + * @bio: bio to add pages to + * @iter: iov iterator describing the region to be mapped + * + * Pins pages from *iter and appends them to @bio's bvec array. The + * pages will have to be released using put_page() when done. + * The function tries, but does not guarantee, to pin as many pages as + * fit into the bio, or are requested in *iter, whatever is smaller. + * If MM encounters an error pinning the requested pages, it stops. + * Error is returned only if 0 pages could be pinned. + */ +int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) +{ + unsigned short orig_vcnt = bio->bi_vcnt; + + do { + int ret = __bio_iov_iter_get_pages(bio, iter); + + if (unlikely(ret)) + return bio->bi_vcnt > orig_vcnt ? 0 : ret; + + } while (iov_iter_count(iter) && !bio_full(bio)); + + return 0; +} EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages); struct submit_bio_ret { diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index cbe5ab26d95b..75275f9e363d 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -132,25 +132,22 @@ static int defer_packet_queue( struct hfi1_user_sdma_pkt_q *pq = container_of(wait, struct hfi1_user_sdma_pkt_q, busy); struct hfi1_ibdev *dev = &pq->dd->verbs_dev; - struct user_sdma_txreq *tx = - container_of(txreq, struct user_sdma_txreq, txreq); - if (sdma_progress(sde, seq, txreq)) { - if (tx->busycount++ < MAX_DEFER_RETRY_COUNT) - goto eagain; - } + write_seqlock(&dev->iowait_lock); + if (sdma_progress(sde, seq, txreq)) + goto eagain; /* * We are assuming that if the list is enqueued somewhere, it * is to the dmawait list since that is the only place where * it is supposed to be enqueued. */ xchg(&pq->state, SDMA_PKT_Q_DEFERRED); - write_seqlock(&dev->iowait_lock); if (list_empty(&pq->busy.list)) iowait_queue(pkts_sent, &pq->busy, &sde->dmawait); write_sequnlock(&dev->iowait_lock); return -EBUSY; eagain: + write_sequnlock(&dev->iowait_lock); return -EAGAIN; } @@ -803,7 +800,6 @@ static int user_sdma_send_pkts(struct user_sdma_request *req, unsigned maxpkts) tx->flags = 0; tx->req = req; - tx->busycount = 0; INIT_LIST_HEAD(&tx->list); /* diff --git a/drivers/infiniband/hw/hfi1/user_sdma.h b/drivers/infiniband/hw/hfi1/user_sdma.h index 2b5326d6db53..87b0c567f442 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.h +++ b/drivers/infiniband/hw/hfi1/user_sdma.h @@ -236,7 +236,6 @@ struct user_sdma_txreq { struct list_head list; struct user_sdma_request *req; u16 flags; - unsigned int busycount; u64 seqnum; }; diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 8b80a9ce9ea9..dafedbc28bcc 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -57,6 +57,7 @@ #define WRITE_LOG_VERSION 1ULL #define WRITE_LOG_MAGIC 0x6a736677736872ULL +#define WRITE_LOG_SUPER_SECTOR 0 /* * The disk format for this is braindead simple. @@ -112,6 +113,7 @@ struct log_writes_c { struct list_head logging_blocks; wait_queue_head_t wait; struct task_struct *log_kthread; + struct completion super_done; }; struct pending_block { @@ -177,6 +179,14 @@ static void log_end_io(struct bio *bio) bio_put(bio); } +static void log_end_super(struct bio *bio) +{ + struct log_writes_c *lc = bio->bi_private; + + complete(&lc->super_done); + log_end_io(bio); +} + /* * Meant to be called if there is an error, it will free all the pages * associated with the block. @@ -212,7 +222,8 @@ static int write_metadata(struct log_writes_c *lc, void *entry, bio->bi_iter.bi_size = 0; bio->bi_iter.bi_sector = sector; bio_set_dev(bio, lc->logdev->bdev); - bio->bi_end_io = log_end_io; + bio->bi_end_io = (sector == WRITE_LOG_SUPER_SECTOR) ? + log_end_super : log_end_io; bio->bi_private = lc; bio_set_op_attrs(bio, REQ_OP_WRITE, 0); @@ -334,11 +345,18 @@ static int log_super(struct log_writes_c *lc) super.nr_entries = cpu_to_le64(lc->logged_entries); super.sectorsize = cpu_to_le32(lc->sectorsize); - if (write_metadata(lc, &super, sizeof(super), NULL, 0, 0)) { + if (write_metadata(lc, &super, sizeof(super), NULL, 0, + WRITE_LOG_SUPER_SECTOR)) { DMERR("Couldn't write super"); return -1; } + /* + * Super sector should be writen in-order, otherwise the + * nr_entries could be rewritten incorrectly by an old bio. + */ + wait_for_completion_io(&lc->super_done); + return 0; } @@ -447,6 +465,7 @@ static int log_writes_ctr(struct dm_target *ti, unsigned int argc, char **argv) INIT_LIST_HEAD(&lc->unflushed_blocks); INIT_LIST_HEAD(&lc->logging_blocks); init_waitqueue_head(&lc->wait); + init_completion(&lc->super_done); atomic_set(&lc->io_blocks, 0); atomic_set(&lc->pending_blocks, 0); diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index 59dcd97ee3de..6b58ee2e2a25 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -113,22 +113,6 @@ MODULE_PARM_DESC(write_timeout, "Time (in ms) to try writes (default 25)"); ((1 << AT24_SIZE_FLAGS | (_flags)) \ << AT24_SIZE_BYTELEN | ilog2(_len)) -/* - * Both reads and writes fail if the previous write didn't complete yet. This - * macro loops a few times waiting at least long enough for one entire page - * write to work while making sure that at least one iteration is run before - * checking the break condition. - * - * It takes two parameters: a variable in which the future timeout in jiffies - * will be stored and a temporary variable holding the time of the last - * iteration of processing the request. Both should be unsigned integers - * holding at least 32 bits. - */ -#define loop_until_timeout(tout, op_time) \ - for (tout = jiffies + msecs_to_jiffies(write_timeout), op_time = 0; \ - op_time ? time_before(op_time, tout) : true; \ - usleep_range(1000, 1500), op_time = jiffies) - static const struct i2c_device_id at24_ids[] = { /* needs 8 addresses as A0-A2 are ignored */ { "24c00", AT24_DEVICE_MAGIC(128 / 8, AT24_FLAG_TAKE8ADDR) }, @@ -234,7 +218,14 @@ static ssize_t at24_eeprom_read_smbus(struct at24_data *at24, char *buf, if (count > I2C_SMBUS_BLOCK_MAX) count = I2C_SMBUS_BLOCK_MAX; - loop_until_timeout(timeout, read_time) { + timeout = jiffies + msecs_to_jiffies(write_timeout); + do { + /* + * The timestamp shall be taken before the actual operation + * to avoid a premature timeout in case of high CPU load. + */ + read_time = jiffies; + status = i2c_smbus_read_i2c_block_data_or_emulated(client, offset, count, buf); @@ -244,7 +235,9 @@ static ssize_t at24_eeprom_read_smbus(struct at24_data *at24, char *buf, if (status == count) return count; - } + + usleep_range(1000, 1500); + } while (time_before(read_time, timeout)); return -ETIMEDOUT; } @@ -284,7 +277,14 @@ static ssize_t at24_eeprom_read_i2c(struct at24_data *at24, char *buf, msg[1].buf = buf; msg[1].len = count; - loop_until_timeout(timeout, read_time) { + timeout = jiffies + msecs_to_jiffies(write_timeout); + do { + /* + * The timestamp shall be taken before the actual operation + * to avoid a premature timeout in case of high CPU load. + */ + read_time = jiffies; + status = i2c_transfer(client->adapter, msg, 2); if (status == 2) status = count; @@ -294,7 +294,9 @@ static ssize_t at24_eeprom_read_i2c(struct at24_data *at24, char *buf, if (status == count) return count; - } + + usleep_range(1000, 1500); + } while (time_before(read_time, timeout)); return -ETIMEDOUT; } @@ -343,11 +345,20 @@ static ssize_t at24_eeprom_read_serial(struct at24_data *at24, char *buf, msg[1].buf = buf; msg[1].len = count; - loop_until_timeout(timeout, read_time) { + timeout = jiffies + msecs_to_jiffies(write_timeout); + do { + /* + * The timestamp shall be taken before the actual operation + * to avoid a premature timeout in case of high CPU load. + */ + read_time = jiffies; + status = i2c_transfer(client->adapter, msg, 2); if (status == 2) return count; - } + + usleep_range(1000, 1500); + } while (time_before(read_time, timeout)); return -ETIMEDOUT; } @@ -374,11 +385,20 @@ static ssize_t at24_eeprom_read_mac(struct at24_data *at24, char *buf, msg[1].buf = buf; msg[1].len = count; - loop_until_timeout(timeout, read_time) { + timeout = jiffies + msecs_to_jiffies(write_timeout); + do { + /* + * The timestamp shall be taken before the actual operation + * to avoid a premature timeout in case of high CPU load. + */ + read_time = jiffies; + status = i2c_transfer(client->adapter, msg, 2); if (status == 2) return count; - } + + usleep_range(1000, 1500); + } while (time_before(read_time, timeout)); return -ETIMEDOUT; } @@ -420,7 +440,14 @@ static ssize_t at24_eeprom_write_smbus_block(struct at24_data *at24, client = at24_translate_offset(at24, &offset); count = at24_adjust_write_count(at24, offset, count); - loop_until_timeout(timeout, write_time) { + timeout = jiffies + msecs_to_jiffies(write_timeout); + do { + /* + * The timestamp shall be taken before the actual operation + * to avoid a premature timeout in case of high CPU load. + */ + write_time = jiffies; + status = i2c_smbus_write_i2c_block_data(client, offset, count, buf); if (status == 0) @@ -431,7 +458,9 @@ static ssize_t at24_eeprom_write_smbus_block(struct at24_data *at24, if (status == count) return count; - } + + usleep_range(1000, 1500); + } while (time_before(write_time, timeout)); return -ETIMEDOUT; } @@ -446,7 +475,14 @@ static ssize_t at24_eeprom_write_smbus_byte(struct at24_data *at24, client = at24_translate_offset(at24, &offset); - loop_until_timeout(timeout, write_time) { + timeout = jiffies + msecs_to_jiffies(write_timeout); + do { + /* + * The timestamp shall be taken before the actual operation + * to avoid a premature timeout in case of high CPU load. + */ + write_time = jiffies; + status = i2c_smbus_write_byte_data(client, offset, buf[0]); if (status == 0) status = count; @@ -456,7 +492,9 @@ static ssize_t at24_eeprom_write_smbus_byte(struct at24_data *at24, if (status == count) return count; - } + + usleep_range(1000, 1500); + } while (time_before(write_time, timeout)); return -ETIMEDOUT; } @@ -485,7 +523,14 @@ static ssize_t at24_eeprom_write_i2c(struct at24_data *at24, const char *buf, memcpy(&msg.buf[i], buf, count); msg.len = i + count; - loop_until_timeout(timeout, write_time) { + timeout = jiffies + msecs_to_jiffies(write_timeout); + do { + /* + * The timestamp shall be taken before the actual operation + * to avoid a premature timeout in case of high CPU load. + */ + write_time = jiffies; + status = i2c_transfer(client->adapter, &msg, 1); if (status == 1) status = count; @@ -495,7 +540,9 @@ static ssize_t at24_eeprom_write_i2c(struct at24_data *at24, const char *buf, if (status == count) return count; - } + + usleep_range(1000, 1500); + } while (time_before(write_time, timeout)); return -ETIMEDOUT; } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 1edd4ff5382c..8536a75f32e3 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4263,12 +4263,12 @@ void bond_setup(struct net_device *bond_dev) bond_dev->features |= NETIF_F_NETNS_LOCAL; bond_dev->hw_features = BOND_VLAN_FEATURES | - NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER; bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; bond_dev->features |= bond_dev->hw_features; + bond_dev->features |= NETIF_F_HW_VLAN_CTAG_TX; } /* Destroy a bonding device. diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index 08c19ebd5306..41d528fbebb4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -121,7 +121,7 @@ static int stmmac_adjust_systime(void __iomem *ioaddr, u32 sec, u32 nsec, * programmed with (2^32 – <new_sec_value>) */ if (gmac4) - sec = (100000000ULL - sec); + sec = -sec; value = readl(ioaddr + PTP_TCR); if (value & PTP_TCR_TSCTRLSSR) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index e9a92ed5a308..f3e3e568311a 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2131,12 +2131,12 @@ static void team_setup(struct net_device *dev) dev->features |= NETIF_F_NETNS_LOCAL; dev->hw_features = TEAM_VLAN_FEATURES | - NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER; dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; dev->features |= dev->hw_features; + dev->features |= NETIF_F_HW_VLAN_CTAG_TX; } static int team_newlink(struct net *src_net, struct net_device *dev, diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 3b13d9e4030a..84a33c81b9b7 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -831,18 +831,8 @@ static void tun_net_uninit(struct net_device *dev) /* Net device open. */ static int tun_net_open(struct net_device *dev) { - struct tun_struct *tun = netdev_priv(dev); - int i; - netif_tx_start_all_queues(dev); - for (i = 0; i < tun->numqueues; i++) { - struct tun_file *tfile; - - tfile = rtnl_dereference(tun->tfiles[i]); - tfile->socket.sk->sk_write_space(tfile->socket.sk); - } - return 0; } @@ -2826,6 +2816,7 @@ static int tun_device_event(struct notifier_block *unused, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct tun_struct *tun = netdev_priv(dev); + int i; if (dev->rtnl_link_ops != &tun_link_ops) return NOTIFY_DONE; @@ -2835,6 +2826,14 @@ static int tun_device_event(struct notifier_block *unused, if (tun_queue_resize(tun)) return NOTIFY_BAD; break; + case NETDEV_UP: + for (i = 0; i < tun->numqueues; i++) { + struct tun_file *tfile; + + tfile = rtnl_dereference(tun->tfiles[i]); + tfile->socket.sk->sk_write_space(tfile->socket.sk); + } + break; default: break; } diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index c2d6c501dd85..063daa3435e4 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1395,14 +1395,14 @@ static int qmi_wwan_probe(struct usb_interface *intf, return -ENODEV; } - info = (void *)&id->driver_info; - /* Several Quectel modems supports dynamic interface configuration, so * we need to match on class/subclass/protocol. These values are * identical for the diagnostic- and QMI-interface, but bNumEndpoints is * different. Ignore the current interface if the number of endpoints * equals the number for the diag interface (two). */ + info = (void *)id->driver_info; + if (info->data & QMI_WWAN_QUIRK_QUECTEL_DYNCFG) { if (desc->bNumEndpoints == 2) return -ENODEV; diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c index 890b8aaf95e1..64eb8ffb2ddf 100644 --- a/drivers/scsi/vmw_pvscsi.c +++ b/drivers/scsi/vmw_pvscsi.c @@ -763,6 +763,7 @@ static int pvscsi_queue_lck(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd struct pvscsi_adapter *adapter = shost_priv(host); struct pvscsi_ctx *ctx; unsigned long flags; + unsigned char op; spin_lock_irqsave(&adapter->hw_lock, flags); @@ -775,13 +776,14 @@ static int pvscsi_queue_lck(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd } cmd->scsi_done = done; + op = cmd->cmnd[0]; dev_dbg(&cmd->device->sdev_gendev, - "queued cmd %p, ctx %p, op=%x\n", cmd, ctx, cmd->cmnd[0]); + "queued cmd %p, ctx %p, op=%x\n", cmd, ctx, op); spin_unlock_irqrestore(&adapter->hw_lock, flags); - pvscsi_kick_io(adapter, cmd->cmnd[0]); + pvscsi_kick_io(adapter, op); return 0; } diff --git a/fs/9p/acl.c b/fs/9p/acl.c index 082d227fa56b..6261719f6f2a 100644 --- a/fs/9p/acl.c +++ b/fs/9p/acl.c @@ -276,7 +276,7 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler, switch (handler->flags) { case ACL_TYPE_ACCESS: if (acl) { - struct iattr iattr; + struct iattr iattr = { 0 }; struct posix_acl *old_acl = acl; retval = posix_acl_update_mode(inode, &iattr.ia_mode, &acl); diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 5d6b94475f27..78b5bac82559 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -856,9 +856,14 @@ static int load_flat_file(struct linux_binprm *bprm, static int load_flat_shared_library(int id, struct lib_info *libs) { + /* + * This is a fake bprm struct; only the members "buf", "file" and + * "filename" are actually used. + */ struct linux_binprm bprm; int res; char buf[16]; + loff_t pos = 0; memset(&bprm, 0, sizeof(bprm)); @@ -872,25 +877,11 @@ static int load_flat_shared_library(int id, struct lib_info *libs) if (IS_ERR(bprm.file)) return res; - bprm.cred = prepare_exec_creds(); - res = -ENOMEM; - if (!bprm.cred) - goto out; - - /* We don't really care about recalculating credentials at this point - * as we're past the point of no return and are dealing with shared - * libraries. - */ - bprm.called_set_creds = 1; + res = kernel_read(bprm.file, bprm.buf, BINPRM_BUF_SIZE, &pos); - res = prepare_binprm(&bprm); - - if (!res) + if (res >= 0) res = load_flat_file(&bprm, libs, id, NULL); - abort_creds(bprm.cred); - -out: allow_write_access(bprm.file); fput(bprm.file); diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index 9f69e83810ca..2de6e87e5ee5 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -18,7 +18,7 @@ #define NFSDBG_FACILITY NFSDBG_PNFS_LD -static unsigned int dataserver_timeo = NFS_DEF_TCP_RETRANS; +static unsigned int dataserver_timeo = NFS_DEF_TCP_TIMEO; static unsigned int dataserver_retrans; static bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg); diff --git a/fs/proc/array.c b/fs/proc/array.c index 4ac811e1a26c..37c7ed0dc820 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -448,7 +448,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, * a program is not able to use ptrace(2) in that case. It is * safe because the task has stopped executing permanently. */ - if (permitted && (task->flags & PF_DUMPCORE)) { + if (permitted && (task->flags & (PF_EXITING|PF_DUMPCORE))) { if (try_get_task_stack(task)) { eip = KSTK_EIP(task); esp = KSTK_ESP(task); diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h index fcb61b4659b3..8666fe7f35d7 100644 --- a/include/asm-generic/futex.h +++ b/include/asm-generic/futex.h @@ -23,7 +23,9 @@ * * Return: * 0 - On success - * <0 - On error + * -EFAULT - User access resulted in a page fault + * -EAGAIN - Atomic operation was unable to complete due to contention + * -ENOSYS - Operation not supported */ static inline int arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr) @@ -85,7 +87,9 @@ arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr) * * Return: * 0 - On success - * <0 - On error + * -EFAULT - User access resulted in a page fault + * -EAGAIN - Atomic operation was unable to complete due to contention + * -ENOSYS - Function not implemented (only if !HAVE_FUTEX_CMPXCHG) */ static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, diff --git a/include/linux/bio.h b/include/linux/bio.h index d4b39caf081d..e260f000b9ac 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -123,6 +123,11 @@ static inline void *bio_data(struct bio *bio) return NULL; } +static inline bool bio_full(struct bio *bio) +{ + return bio->bi_vcnt >= bio->bi_max_vecs; +} + /* * will die */ @@ -459,6 +464,10 @@ void bio_chain(struct bio *, struct bio *); extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); +bool __bio_try_merge_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int off); +void __bio_add_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int off); int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter); struct rq_map_data; extern struct bio *bio_map_user_iov(struct request_queue *, diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 67c3934fb9ed..a704d032713b 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -119,10 +119,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, # define ASM_UNREACHABLE #endif #ifndef unreachable -# define unreachable() do { \ - annotate_unreachable(); \ - __builtin_unreachable(); \ -} while (0) +# define unreachable() do { annotate_reachable(); do { } while (1); } while (0) #endif /* diff --git a/kernel/cpu.c b/kernel/cpu.c index 127a69b8b192..f370a0f43005 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2308,6 +2308,9 @@ static int __init mitigations_parse_cmdline(char *arg) cpu_mitigations = CPU_MITIGATIONS_AUTO; else if (!strcmp(arg, "auto,nosmt")) cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT; + else + pr_crit("Unsupported mitigations=%s, system may still be vulnerable\n", + arg); return 0; } diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index 3ea65cdff30d..4ad967453b6f 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -205,8 +205,6 @@ void trace_likely_condition(struct ftrace_likely_data *f, int val, int expect) void ftrace_likely_update(struct ftrace_likely_data *f, int val, int expect, int is_constant) { - unsigned long flags = user_access_save(); - /* A constant is always correct */ if (is_constant) { f->constant++; @@ -225,8 +223,6 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, f->data.correct++; else f->data.incorrect++; - - user_access_restore(flags); } EXPORT_SYMBOL(ftrace_likely_update); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 6ca0225335eb..a37cfa88669e 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -305,7 +305,7 @@ static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) else { nodes_remap(tmp, pol->v.nodes,pol->w.cpuset_mems_allowed, *nodes); - pol->w.cpuset_mems_allowed = tmp; + pol->w.cpuset_mems_allowed = *nodes; } if (nodes_empty(tmp)) diff --git a/mm/page_idle.c b/mm/page_idle.c index e412a63b2b74..504684181827 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -136,7 +136,7 @@ static ssize_t page_idle_bitmap_read(struct file *file, struct kobject *kobj, end_pfn = pfn + count * BITS_PER_BYTE; if (end_pfn > max_pfn) - end_pfn = ALIGN(max_pfn, BITMAP_CHUNK_BITS); + end_pfn = max_pfn; for (; pfn < end_pfn; pfn++) { bit = pfn % BITMAP_CHUNK_BITS; @@ -181,7 +181,7 @@ static ssize_t page_idle_bitmap_write(struct file *file, struct kobject *kobj, end_pfn = pfn + count * BITS_PER_BYTE; if (end_pfn > max_pfn) - end_pfn = ALIGN(max_pfn, BITMAP_CHUNK_BITS); + end_pfn = max_pfn; for (; pfn < end_pfn; pfn++) { bit = pfn % BITMAP_CHUNK_BITS; diff --git a/net/9p/protocol.c b/net/9p/protocol.c index 766d1ef4640a..1885403c9a3e 100644 --- a/net/9p/protocol.c +++ b/net/9p/protocol.c @@ -622,13 +622,19 @@ int p9dirent_read(struct p9_client *clnt, char *buf, int len, if (ret) { p9_debug(P9_DEBUG_9P, "<<< p9dirent_read failed: %d\n", ret); trace_9p_protocol_dump(clnt, &fake_pdu); - goto out; + return ret; } - strcpy(dirent->d_name, nameptr); + ret = strscpy(dirent->d_name, nameptr, sizeof(dirent->d_name)); + if (ret < 0) { + p9_debug(P9_DEBUG_ERROR, + "On the wire dirent name too long: %s\n", + nameptr); + kfree(nameptr); + return ret; + } kfree(nameptr); -out: return fake_pdu.offset; } EXPORT_SYMBOL(p9dirent_read); diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c index 38aa6345bdfa..9c0c894b56f8 100644 --- a/net/9p/trans_common.c +++ b/net/9p/trans_common.c @@ -14,6 +14,7 @@ #include <linux/mm.h> #include <linux/module.h> +#include "trans_common.h" /** * p9_release_req_pages - Release pages after the transaction. diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index f58467a49090..16a4a31f16e0 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -276,8 +276,7 @@ p9_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) case RDMA_CM_EVENT_DISCONNECTED: if (rdma) rdma->state = P9_RDMA_CLOSED; - if (c) - c->status = Disconnected; + c->status = Disconnected; break; case RDMA_CM_EVENT_TIMEWAIT_EXIT: @@ -476,7 +475,7 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) err = post_recv(client, rpl_context); if (err) { - p9_debug(P9_DEBUG_FCALL, "POST RECV failed\n"); + p9_debug(P9_DEBUG_ERROR, "POST RECV failed: %d\n", err); goto recv_error; } /* remove posted receive buffer from request structure */ @@ -545,7 +544,7 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req) recv_error: kfree(rpl_context); spin_lock_irqsave(&rdma->req_lock, flags); - if (rdma->state < P9_RDMA_CLOSING) { + if (err != -EINTR && rdma->state < P9_RDMA_CLOSING) { rdma->state = P9_RDMA_CLOSING; spin_unlock_irqrestore(&rdma->req_lock, flags); rdma_disconnect(rdma->cm_id); diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index c10bdf63eae7..389eb635ec2c 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -392,8 +392,8 @@ static int xen_9pfs_front_probe(struct xenbus_device *dev, unsigned int max_rings, max_ring_order, len = 0; versions = xenbus_read(XBT_NIL, dev->otherend, "versions", &len); - if (!len) - return -EINVAL; + if (IS_ERR(versions)) + return PTR_ERR(versions); if (strcmp(versions, "1")) { kfree(versions); return -EINVAL; diff --git a/net/core/sock.c b/net/core/sock.c index a88579589946..c8d39092e8bf 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1358,9 +1358,6 @@ int sock_getsockopt(struct socket *sock, int level, int optname, { u32 meminfo[SK_MEMINFO_VARS]; - if (get_user(len, optlen)) - return -EFAULT; - sk_get_meminfo(sk, meminfo); len = min_t(unsigned int, len, sizeof(meminfo)); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 115d9fd413e2..53a11894f9e4 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -202,7 +202,7 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash) } sk = __raw_v4_lookup(net, sk_next(sk), iph->protocol, iph->saddr, iph->daddr, - skb->dev->ifindex, sdif); + dif, sdif); } out: read_unlock(&raw_v4_hashinfo.lock); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index b89920c0f226..54343dc29cb4 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -563,7 +563,11 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, struct sock *udp4_lib_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport) { - return __udp4_lib_lookup_skb(skb, sport, dport, &udp_table); + const struct iphdr *iph = ip_hdr(skb); + + return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport, + iph->daddr, dport, inet_iif(skb), + inet_sdif(skb), &udp_table, NULL); } EXPORT_SYMBOL_GPL(udp4_lib_lookup_skb); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 8d185a0fc5af..9f7bfeb90fb0 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -308,7 +308,7 @@ struct sock *udp6_lib_lookup_skb(struct sk_buff *skb, return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport, &iph->daddr, dport, inet6_iif(skb), - inet6_sdif(skb), &udp_table, skb); + inet6_sdif(skb), &udp_table, NULL); } EXPORT_SYMBOL_GPL(udp6_lib_lookup_skb); @@ -506,7 +506,7 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, struct net *net = dev_net(skb->dev); sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, - inet6_iif(skb), 0, udptable, skb); + inet6_iif(skb), 0, udptable, NULL); if (!sk) { __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a968e81d4c81..047ee7ff7038 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2438,6 +2438,9 @@ static void tpacket_destruct_skb(struct sk_buff *skb) ts = __packet_set_timestamp(po, ph, skb); __packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts); + + if (!packet_read_pending(&po->tx_ring)) + complete(&po->skb_completion); } sock_wfree(skb); @@ -2632,7 +2635,7 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame, static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) { - struct sk_buff *skb; + struct sk_buff *skb = NULL; struct net_device *dev; struct virtio_net_hdr *vnet_hdr = NULL; struct sockcm_cookie sockc; @@ -2647,6 +2650,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) int len_sum = 0; int status = TP_STATUS_AVAILABLE; int hlen, tlen, copylen = 0; + long timeo = 0; mutex_lock(&po->pg_vec_lock); @@ -2693,12 +2697,21 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) if ((size_max > dev->mtu + reserve + VLAN_HLEN) && !po->has_vnet_hdr) size_max = dev->mtu + reserve + VLAN_HLEN; + reinit_completion(&po->skb_completion); + do { ph = packet_current_frame(po, &po->tx_ring, TP_STATUS_SEND_REQUEST); if (unlikely(ph == NULL)) { - if (need_wait && need_resched()) - schedule(); + if (need_wait && skb) { + timeo = sock_sndtimeo(&po->sk, msg->msg_flags & MSG_DONTWAIT); + timeo = wait_for_completion_interruptible_timeout(&po->skb_completion, timeo); + if (timeo <= 0) { + err = !timeo ? -ETIMEDOUT : -ERESTARTSYS; + goto out_put; + } + } + /* check for additional frames */ continue; } @@ -3252,6 +3265,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, sock_init_data(sock, sk); po = pkt_sk(sk); + init_completion(&po->skb_completion); sk->sk_family = PF_PACKET; po->num = proto; po->xmit = dev_queue_xmit; @@ -4340,7 +4354,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, req3->tp_sizeof_priv || req3->tp_feature_req_word) { err = -EINVAL; - goto out; + goto out_free_pg_vec; } } break; @@ -4404,6 +4418,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, prb_shutdown_retire_blk_timer(po, rb_queue); } +out_free_pg_vec: if (pg_vec) free_pg_vec(pg_vec, order, req->tp_block_nr); out: diff --git a/net/packet/internal.h b/net/packet/internal.h index 3bb7c5fb3bff..c70a2794456f 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -128,6 +128,7 @@ struct packet_sock { unsigned int tp_hdrlen; unsigned int tp_reserve; unsigned int tp_tstamp; + struct completion skb_completion; struct net_device __rcu *cached_dev; int (*xmit)(struct sk_buff *skb); struct packet_type prot_hook ____cacheline_aligned_in_smp; diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index ee1e601a0b11..5d4079ef3de6 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -126,10 +126,6 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, /* Initialize the bind addr area */ sctp_bind_addr_init(&ep->base.bind_addr, 0); - /* Remember who we are attached to. */ - ep->base.sk = sk; - sock_hold(ep->base.sk); - /* Create the lists of associations. */ INIT_LIST_HEAD(&ep->asocs); @@ -167,6 +163,10 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, ep->prsctp_enable = net->sctp.prsctp_enable; ep->reconf_enable = net->sctp.reconf_enable; + /* Remember who we are attached to. */ + ep->base.sk = sk; + sock_hold(ep->base.sk); + return ep; nomem_hmacs: diff --git a/net/tipc/core.c b/net/tipc/core.c index 7561e64c220e..67ac10434ba2 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -128,7 +128,7 @@ static int __init tipc_init(void) if (err) goto out_sysctl; - err = register_pernet_subsys(&tipc_net_ops); + err = register_pernet_device(&tipc_net_ops); if (err) goto out_pernet; @@ -136,7 +136,7 @@ static int __init tipc_init(void) if (err) goto out_socket; - err = register_pernet_subsys(&tipc_topsrv_net_ops); + err = register_pernet_device(&tipc_topsrv_net_ops); if (err) goto out_pernet_topsrv; @@ -147,11 +147,11 @@ static int __init tipc_init(void) pr_info("Started in single node mode\n"); return 0; out_bearer: - unregister_pernet_subsys(&tipc_topsrv_net_ops); + unregister_pernet_device(&tipc_topsrv_net_ops); out_pernet_topsrv: tipc_socket_stop(); out_socket: - unregister_pernet_subsys(&tipc_net_ops); + unregister_pernet_device(&tipc_net_ops); out_pernet: tipc_unregister_sysctl(); out_sysctl: @@ -166,9 +166,9 @@ static int __init tipc_init(void) static void __exit tipc_exit(void) { tipc_bearer_cleanup(); - unregister_pernet_subsys(&tipc_topsrv_net_ops); + unregister_pernet_device(&tipc_topsrv_net_ops); tipc_socket_stop(); - unregister_pernet_subsys(&tipc_net_ops); + unregister_pernet_device(&tipc_net_ops); tipc_netlink_stop(); tipc_netlink_compat_stop(); tipc_unregister_sysctl(); diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index aa75bc8b158f..41954ed7ff51 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -436,7 +436,11 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd, if (!bearer) return -EMSGSIZE; - len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_BEARER_NAME); + len = TLV_GET_DATA_LEN(msg->req); + if (len <= 0) + return -EINVAL; + + len = min_t(int, len, TIPC_MAX_BEARER_NAME); if (!string_is_valid(name, len)) return -EINVAL; @@ -528,7 +532,11 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg, name = (char *)TLV_DATA(msg->req); - len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME); + len = TLV_GET_DATA_LEN(msg->req); + if (len <= 0) + return -EINVAL; + + len = min_t(int, len, TIPC_MAX_BEARER_NAME); if (!string_is_valid(name, len)) return -EINVAL; @@ -806,7 +814,11 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd, if (!link) return -EMSGSIZE; - len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME); + len = TLV_GET_DATA_LEN(msg->req); + if (len <= 0) + return -EINVAL; + + len = min_t(int, len, TIPC_MAX_BEARER_NAME); if (!string_is_valid(name, len)) return -EINVAL; diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index e3cff9d6c092..de011fdd7964 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -174,7 +174,6 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb, goto tx_error; } - skb->dev = rt->dst.dev; ttl = ip4_dst_hoplimit(&rt->dst); udp_tunnel_xmit_skb(rt, ub->ubsock->sk, skb, src->ipv4.s_addr, dst->ipv4.s_addr, 0, ttl, 0, src->port, @@ -193,10 +192,9 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb, if (err) goto tx_error; ttl = ip6_dst_hoplimit(ndst); - err = udp_tunnel6_xmit_skb(ndst, ub->ubsock->sk, skb, - ndst->dev, &src->ipv6, - &dst->ipv6, 0, ttl, 0, src->port, - dst->port, false); + err = udp_tunnel6_xmit_skb(ndst, ub->ubsock->sk, skb, NULL, + &src->ipv6, &dst->ipv6, 0, ttl, 0, + src->port, dst->port, false); #endif } return err; diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c index a0f7ed2b869b..3c364798093b 100644 --- a/tools/perf/builtin-help.c +++ b/tools/perf/builtin-help.c @@ -189,7 +189,7 @@ static void add_man_viewer(const char *name) while (*p) p = &((*p)->next); *p = zalloc(sizeof(**p) + len + 1); - strncpy((*p)->name, name, len); + strcpy((*p)->name, name); } static int supported_man_viewer(const char *name, size_t len) diff --git a/tools/perf/ui/tui/helpline.c b/tools/perf/ui/tui/helpline.c index 4ca799aadb4e..93d6b7240285 100644 --- a/tools/perf/ui/tui/helpline.c +++ b/tools/perf/ui/tui/helpline.c @@ -24,7 +24,7 @@ static void tui_helpline__push(const char *msg) SLsmg_set_color(0); SLsmg_write_nstring((char *)msg, SLtt_Screen_Cols); SLsmg_refresh(); - strncpy(ui_helpline__current, msg, sz)[sz - 1] = '\0'; + strlcpy(ui_helpline__current, msg, sz); } static int tui_helpline__show(const char *format, va_list ap) diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index 696f2654826b..f11cead6a151 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -3171,7 +3171,7 @@ perf_event__synthesize_event_update_name(struct perf_tool *tool, if (ev == NULL) return -ENOMEM; - strncpy(ev->data, evsel->name, len); + strlcpy(ev->data, evsel->name, len + 1); err = process(tool, (union perf_event*) ev, NULL, NULL); free(ev); return err;