diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index d120201910acffceba89853bcf9e9f8a69e0d328..f8d1933bfe823f2f38a431b988767b0e575a478c 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -1721,7 +1721,10 @@ static inline void decode_cpucfg(struct cpuinfo_mips *c) static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) { + c->cputype = CPU_LOONGSON64; + /* All Loongson processors covered here define ExcCode 16 as GSExc. */ + decode_configs(c); c->options |= MIPS_CPU_GSEXCEX; switch (c->processor_id & PRID_IMP_MASK) { @@ -1731,7 +1734,6 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) case PRID_REV_LOONGSON2K_R1_1: case PRID_REV_LOONGSON2K_R1_2: case PRID_REV_LOONGSON2K_R1_3: - c->cputype = CPU_LOONGSON64; __cpu_name[cpu] = "Loongson-2K"; set_elf_platform(cpu, "gs264e"); set_isa(c, MIPS_CPU_ISA_M64R2); @@ -1744,14 +1746,12 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) switch (c->processor_id & PRID_REV_MASK) { case PRID_REV_LOONGSON3A_R2_0: case PRID_REV_LOONGSON3A_R2_1: - c->cputype = CPU_LOONGSON64; __cpu_name[cpu] = "ICT Loongson-3"; set_elf_platform(cpu, "loongson3a"); set_isa(c, MIPS_CPU_ISA_M64R2); break; case PRID_REV_LOONGSON3A_R3_0: case PRID_REV_LOONGSON3A_R3_1: - c->cputype = CPU_LOONGSON64; __cpu_name[cpu] = "ICT Loongson-3"; set_elf_platform(cpu, "loongson3a"); set_isa(c, MIPS_CPU_ISA_M64R2); @@ -1771,7 +1771,6 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) c->ases &= ~MIPS_ASE_VZ; /* VZ of Loongson-3A2000/3000 is incomplete */ break; case PRID_IMP_LOONGSON_64G: - c->cputype = CPU_LOONGSON64; __cpu_name[cpu] = "ICT Loongson-3"; set_elf_platform(cpu, "loongson3a"); set_isa(c, MIPS_CPU_ISA_M64R2); @@ -1781,8 +1780,6 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) panic("Unknown Loongson Processor ID!"); break; } - - decode_configs(c); } #else static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) { } diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index a3f66ade09b32ac9c6dab237e6fbbd032b7b16fb..912e64ab5f249447f4a6bf53a0b587dbf5cd4031 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -429,3 +429,11 @@ checkbin: echo -n '*** Please use a different binutils version.' ; \ false ; \ fi + @if test "x${CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT}" = "xy" -a \ + "x${CONFIG_LD_IS_BFD}" = "xy" -a \ + "${CONFIG_LD_VERSION}" = "23700" ; then \ + echo -n '*** binutils 2.37 drops unused section symbols, which recordmcount ' ; \ + echo 'is unable to handle.' ; \ + echo '*** Please use a different binutils version.' ; \ + false ; \ + fi diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h index 75c1e9996867585d48a49530607a59fcbdcb7800..ef336fe1600445d8e2ce4c7ad4b8bb7a0eb9eca1 100644 --- a/arch/riscv/net/bpf_jit.h +++ b/arch/riscv/net/bpf_jit.h @@ -69,6 +69,7 @@ struct rv_jit_context { struct bpf_prog *prog; u16 *insns; /* RV insns */ int ninsns; + int prologue_len; int epilogue_offset; int *offset; /* BPF to RV */ unsigned long flags; @@ -214,8 +215,8 @@ static inline int rv_offset(int insn, int off, struct rv_jit_context *ctx) int from, to; off++; /* BPF branch is from PC+1, RV is from PC */ - from = (insn > 0) ? ctx->offset[insn - 1] : 0; - to = (insn + off > 0) ? ctx->offset[insn + off - 1] : 0; + from = (insn > 0) ? ctx->offset[insn - 1] : ctx->prologue_len; + to = (insn + off > 0) ? ctx->offset[insn + off - 1] : ctx->prologue_len; return ninsns_rvoff(to - from); } diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index c113ae818b14ed6932debddf3f70a54af57f7bff..053dc83e323b6ae4af0e17d71ae11f83f84c4d9d 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -1144,16 +1144,3 @@ void bpf_jit_build_epilogue(struct rv_jit_context *ctx) { __build_epilogue(false, ctx); } - -void *bpf_jit_alloc_exec(unsigned long size) -{ - return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START, - BPF_JIT_REGION_END, GFP_KERNEL, - PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, - __builtin_return_address(0)); -} - -void bpf_jit_free_exec(void *addr) -{ - return vfree(addr); -} diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c index cbf7d2414886e4b741c40766787555102ae6e783..ef17bc8055d4c60ac95de79fe33afd92321c3b25 100644 --- a/arch/riscv/net/bpf_jit_core.c +++ b/arch/riscv/net/bpf_jit_core.c @@ -83,6 +83,12 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) prog = orig_prog; goto out_offset; } + + if (build_body(ctx, extra_pass, NULL)) { + prog = orig_prog; + goto out_offset; + } + for (i = 0; i < prog->len; i++) { prev_ninsns += 32; ctx->offset[i] = prev_ninsns; @@ -91,11 +97,15 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) for (i = 0; i < NR_JIT_ITERATIONS; i++) { pass++; ctx->ninsns = 0; + + bpf_jit_build_prologue(ctx); + ctx->prologue_len = ctx->ninsns; + if (build_body(ctx, extra_pass, ctx->offset)) { prog = orig_prog; goto out_offset; } - bpf_jit_build_prologue(ctx); + ctx->epilogue_offset = ctx->ninsns; bpf_jit_build_epilogue(ctx); @@ -153,6 +163,10 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns); if (!prog->is_func || extra_pass) { + bpf_jit_binary_lock_ro(jit_data->header); + for (i = 0; i < prog->len; i++) + ctx->offset[i] = ninsns_rvoff(ctx->offset[i]); + bpf_prog_fill_jited_linfo(prog, ctx->offset); out_offset: kfree(ctx->offset); kfree(jit_data); @@ -165,3 +179,16 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) tmp : orig_prog); return prog; } + +void *bpf_jit_alloc_exec(unsigned long size) +{ + return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START, + BPF_JIT_REGION_END, GFP_KERNEL, + PAGE_KERNEL, 0, NUMA_NO_NODE, + __builtin_return_address(0)); +} + +void bpf_jit_free_exec(void *addr) +{ + return vfree(addr); +} diff --git a/arch/sh/include/asm/pgtable-3level.h b/arch/sh/include/asm/pgtable-3level.h index 56bf35c2f29c2b832170d67468c1a23d5f27383e..cdced80a7ffa3944535eeebb3a1fc49764a6bdd9 100644 --- a/arch/sh/include/asm/pgtable-3level.h +++ b/arch/sh/include/asm/pgtable-3level.h @@ -34,7 +34,7 @@ typedef struct { unsigned long long pmd; } pmd_t; static inline pmd_t *pud_pgtable(pud_t pud) { - return (pmd_t *)pud_val(pud); + return (pmd_t *)(unsigned long)pud_val(pud); } /* only used by the stubbed out hugetlb gup code, should never be called */ diff --git a/block/partitions/amiga.c b/block/partitions/amiga.c index 64f0844468aacd4f57bfacf003856d955f0b848c..a99ec7f1a1749d47ca1df4a27ad4260823eafb02 100644 --- a/block/partitions/amiga.c +++ b/block/partitions/amiga.c @@ -11,10 +11,18 @@ #define pr_fmt(fmt) fmt #include +#include +#include #include #include "check.h" +/* magic offsets in partition DosEnvVec */ +#define NR_HD 3 +#define NR_SECT 5 +#define LO_CYL 9 +#define HI_CYL 10 + static __inline__ u32 checksum_block(__be32 *m, int size) { @@ -31,9 +39,12 @@ int amiga_partition(struct parsed_partitions *state) unsigned char *data; struct RigidDiskBlock *rdb; struct PartitionBlock *pb; - sector_t start_sect, nr_sects; - int blk, part, res = 0; - int blksize = 1; /* Multiplier for disk block size */ + u64 start_sect, nr_sects; + sector_t blk, end_sect; + u32 cylblk; /* rdb_CylBlocks = nr_heads*sect_per_track */ + u32 nr_hd, nr_sect, lo_cyl, hi_cyl; + int part, res = 0; + unsigned int blksize = 1; /* Multiplier for disk block size */ int slot = 1; char b[BDEVNAME_SIZE]; @@ -42,7 +53,7 @@ int amiga_partition(struct parsed_partitions *state) goto rdb_done; data = read_part_sector(state, blk, §); if (!data) { - pr_err("Dev %s: unable to read RDB block %d\n", + pr_err("Dev %s: unable to read RDB block %llu\n", bdevname(state->bdev, b), blk); res = -1; goto rdb_done; @@ -59,12 +70,12 @@ int amiga_partition(struct parsed_partitions *state) *(__be32 *)(data+0xdc) = 0; if (checksum_block((__be32 *)data, be32_to_cpu(rdb->rdb_SummedLongs) & 0x7F)==0) { - pr_err("Trashed word at 0xd0 in block %d ignored in checksum calculation\n", + pr_err("Trashed word at 0xd0 in block %llu ignored in checksum calculation\n", blk); break; } - pr_err("Dev %s: RDB in block %d has bad checksum\n", + pr_err("Dev %s: RDB in block %llu has bad checksum\n", bdevname(state->bdev, b), blk); } @@ -80,11 +91,16 @@ int amiga_partition(struct parsed_partitions *state) } blk = be32_to_cpu(rdb->rdb_PartitionList); put_dev_sector(sect); - for (part = 1; blk>0 && part<=16; part++, put_dev_sector(sect)) { - blk *= blksize; /* Read in terms partition table understands */ + for (part = 1; (s32) blk>0 && part<=16; part++, put_dev_sector(sect)) { + /* Read in terms partition table understands */ + if (check_mul_overflow(blk, (sector_t) blksize, &blk)) { + pr_err("Dev %s: overflow calculating partition block %llu! Skipping partitions %u and beyond\n", + bdevname(state->bdev, b), blk, part); + break; + } data = read_part_sector(state, blk, §); if (!data) { - pr_err("Dev %s: unable to read partition block %d\n", + pr_err("Dev %s: unable to read partition block %llu\n", bdevname(state->bdev, b), blk); res = -1; goto rdb_done; @@ -96,19 +112,70 @@ int amiga_partition(struct parsed_partitions *state) if (checksum_block((__be32 *)pb, be32_to_cpu(pb->pb_SummedLongs) & 0x7F) != 0 ) continue; - /* Tell Kernel about it */ + /* RDB gives us more than enough rope to hang ourselves with, + * many times over (2^128 bytes if all fields max out). + * Some careful checks are in order, so check for potential + * overflows. + * We are multiplying four 32 bit numbers to one sector_t! + */ + + nr_hd = be32_to_cpu(pb->pb_Environment[NR_HD]); + nr_sect = be32_to_cpu(pb->pb_Environment[NR_SECT]); + + /* CylBlocks is total number of blocks per cylinder */ + if (check_mul_overflow(nr_hd, nr_sect, &cylblk)) { + pr_err("Dev %s: heads*sects %u overflows u32, skipping partition!\n", + bdevname(state->bdev, b), cylblk); + continue; + } + + /* check for consistency with RDB defined CylBlocks */ + if (cylblk > be32_to_cpu(rdb->rdb_CylBlocks)) { + pr_warn("Dev %s: cylblk %u > rdb_CylBlocks %u!\n", + bdevname(state->bdev, b), cylblk, + be32_to_cpu(rdb->rdb_CylBlocks)); + } + + /* RDB allows for variable logical block size - + * normalize to 512 byte blocks and check result. + */ + + if (check_mul_overflow(cylblk, blksize, &cylblk)) { + pr_err("Dev %s: partition %u bytes per cyl. overflows u32, skipping partition!\n", + bdevname(state->bdev, b), part); + continue; + } + + /* Calculate partition start and end. Limit of 32 bit on cylblk + * guarantees no overflow occurs if LBD support is enabled. + */ + + lo_cyl = be32_to_cpu(pb->pb_Environment[LO_CYL]); + start_sect = ((u64) lo_cyl * cylblk); + + hi_cyl = be32_to_cpu(pb->pb_Environment[HI_CYL]); + nr_sects = (((u64) hi_cyl - lo_cyl + 1) * cylblk); - nr_sects = ((sector_t)be32_to_cpu(pb->pb_Environment[10]) + 1 - - be32_to_cpu(pb->pb_Environment[9])) * - be32_to_cpu(pb->pb_Environment[3]) * - be32_to_cpu(pb->pb_Environment[5]) * - blksize; if (!nr_sects) continue; - start_sect = (sector_t)be32_to_cpu(pb->pb_Environment[9]) * - be32_to_cpu(pb->pb_Environment[3]) * - be32_to_cpu(pb->pb_Environment[5]) * - blksize; + + /* Warn user if partition end overflows u32 (AmigaDOS limit) */ + + if ((start_sect + nr_sects) > UINT_MAX) { + pr_warn("Dev %s: partition %u (%llu-%llu) needs 64 bit device support!\n", + bdevname(state->bdev, b), part, + start_sect, start_sect + nr_sects); + } + + if (check_add_overflow(start_sect, nr_sects, &end_sect)) { + pr_err("Dev %s: partition %u (%llu-%llu) needs LBD device support, skipping partition!\n", + bdevname(state->bdev, b), part, + start_sect, end_sect); + continue; + } + + /* Tell Kernel about it */ + put_partition(state,slot++,start_sect,nr_sects); { /* Be even more informative to aid mounting */ diff --git a/drivers/char/hw_random/imx-rngc.c b/drivers/char/hw_random/imx-rngc.c index 9b182e5bfa87a7c2740deedf36a03ff2ed1942e8..dbb2da630611acacd92602fe6740df2a2ed415cb 100644 --- a/drivers/char/hw_random/imx-rngc.c +++ b/drivers/char/hw_random/imx-rngc.c @@ -110,7 +110,7 @@ static int imx_rngc_self_test(struct imx_rngc *rngc) cmd = readl(rngc->base + RNGC_COMMAND); writel(cmd | RNGC_CMD_SELF_TEST, rngc->base + RNGC_COMMAND); - ret = wait_for_completion_timeout(&rngc->rng_op_done, RNGC_TIMEOUT); + ret = wait_for_completion_timeout(&rngc->rng_op_done, msecs_to_jiffies(RNGC_TIMEOUT)); imx_rngc_irq_mask_clear(rngc); if (!ret) return -ETIMEDOUT; @@ -187,9 +187,7 @@ static int imx_rngc_init(struct hwrng *rng) cmd = readl(rngc->base + RNGC_COMMAND); writel(cmd | RNGC_CMD_SEED, rngc->base + RNGC_COMMAND); - ret = wait_for_completion_timeout(&rngc->rng_op_done, - RNGC_TIMEOUT); - + ret = wait_for_completion_timeout(&rngc->rng_op_done, msecs_to_jiffies(RNGC_TIMEOUT)); if (!ret) { ret = -ETIMEDOUT; goto err; diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 512c867495ea51f42f738366c8c8b8e935c02206..365761055df3eafbba546ee463e9eae9674d5fb5 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -731,7 +731,9 @@ static irqreturn_t tis_int_handler(int dummy, void *dev_id) wake_up_interruptible(&priv->int_queue); /* Clear interrupts handled with TPM_EOI */ + tpm_tis_request_locality(chip, 0); rc = tpm_tis_write32(priv, TPM_INT_STATUS(priv->locality), interrupt); + tpm_tis_relinquish_locality(chip, 0); if (rc < 0) return IRQ_NONE; diff --git a/drivers/char/tpm/tpm_vtpm_proxy.c b/drivers/char/tpm/tpm_vtpm_proxy.c index 91c772e38bb54b31bbf0f22f000e6ca40d247791..ff2ec71d592ef894d52144430afad4725c7f54a3 100644 --- a/drivers/char/tpm/tpm_vtpm_proxy.c +++ b/drivers/char/tpm/tpm_vtpm_proxy.c @@ -683,37 +683,21 @@ static struct miscdevice vtpmx_miscdev = { .fops = &vtpmx_fops, }; -static int vtpmx_init(void) -{ - return misc_register(&vtpmx_miscdev); -} - -static void vtpmx_cleanup(void) -{ - misc_deregister(&vtpmx_miscdev); -} - static int __init vtpm_module_init(void) { int rc; - rc = vtpmx_init(); - if (rc) { - pr_err("couldn't create vtpmx device\n"); - return rc; - } - workqueue = create_workqueue("tpm-vtpm"); if (!workqueue) { pr_err("couldn't create workqueue\n"); - rc = -ENOMEM; - goto err_vtpmx_cleanup; + return -ENOMEM; } - return 0; - -err_vtpmx_cleanup: - vtpmx_cleanup(); + rc = misc_register(&vtpmx_miscdev); + if (rc) { + pr_err("couldn't create vtpmx device\n"); + destroy_workqueue(workqueue); + } return rc; } @@ -721,7 +705,7 @@ static int __init vtpm_module_init(void) static void __exit vtpm_module_exit(void) { destroy_workqueue(workqueue); - vtpmx_cleanup(); + misc_deregister(&vtpmx_miscdev); } module_init(vtpm_module_init); diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index b0b92f436879a66abe514524ec388b67381330b1..7b69f81444ebd71336acba84e6008e1f7415066b 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -2091,6 +2091,7 @@ static const struct panel_desc innolux_at043tn24 = { .height = 54, }, .bus_format = MEDIA_BUS_FMT_RGB888_1X24, + .connector_type = DRM_MODE_CONNECTOR_DPI, .bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE, }; @@ -3152,6 +3153,7 @@ static const struct drm_display_mode powertip_ph800480t013_idf02_mode = { .vsync_start = 480 + 49, .vsync_end = 480 + 49 + 2, .vtotal = 480 + 49 + 2 + 22, + .flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC, }; static const struct panel_desc powertip_ph800480t013_idf02 = { diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index a20332e755e816f38ca212b84fea60855d0f603a..ee2cfd6c2dfbd2188826995c91e8ac900c8164d6 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -274,6 +274,18 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf) goto abort; } + if (conf->layout == RAID0_ORIG_LAYOUT) { + for (i = 1; i < conf->nr_strip_zones; i++) { + sector_t first_sector = conf->strip_zone[i-1].zone_end; + + sector_div(first_sector, mddev->chunk_sectors); + zone = conf->strip_zone + i; + /* disk_shift is first disk index used in the zone */ + zone->disk_shift = sector_div(first_sector, + zone->nb_dev); + } + } + pr_debug("md/raid0:%s: done.\n", mdname(mddev)); *private_conf = conf; @@ -427,6 +439,20 @@ static void raid0_free(struct mddev *mddev, void *priv) kfree(conf); } +/* + * Convert disk_index to the disk order in which it is read/written. + * For example, if we have 4 disks, they are numbered 0,1,2,3. If we + * write the disks starting at disk 3, then the read/write order would + * be disk 3, then 0, then 1, and then disk 2 and we want map_disk_shift() + * to map the disks as follows 0,1,2,3 => 1,2,3,0. So disk 0 would map + * to 1, 1 to 2, 2 to 3, and 3 to 0. That way we can compare disks in + * that 'output' space to understand the read/write disk ordering. + */ +static int map_disk_shift(int disk_index, int num_disks, int disk_shift) +{ + return ((disk_index + num_disks - disk_shift) % num_disks); +} + static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) { struct r0conf *conf = mddev->private; @@ -440,7 +466,9 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) sector_t end_disk_offset; unsigned int end_disk_index; unsigned int disk; + sector_t orig_start, orig_end; + orig_start = start; zone = find_zone(conf, &start); if (bio_end_sector(bio) > zone->zone_end) { @@ -454,6 +482,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) } else end = bio_end_sector(bio); + orig_end = end; if (zone != conf->strip_zone) end = end - zone[-1].zone_end; @@ -465,13 +494,26 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) last_stripe_index = end; sector_div(last_stripe_index, stripe_size); - start_disk_index = (int)(start - first_stripe_index * stripe_size) / - mddev->chunk_sectors; + /* In the first zone the original and alternate layouts are the same */ + if ((conf->layout == RAID0_ORIG_LAYOUT) && (zone != conf->strip_zone)) { + sector_div(orig_start, mddev->chunk_sectors); + start_disk_index = sector_div(orig_start, zone->nb_dev); + start_disk_index = map_disk_shift(start_disk_index, + zone->nb_dev, + zone->disk_shift); + sector_div(orig_end, mddev->chunk_sectors); + end_disk_index = sector_div(orig_end, zone->nb_dev); + end_disk_index = map_disk_shift(end_disk_index, + zone->nb_dev, zone->disk_shift); + } else { + start_disk_index = (int)(start - first_stripe_index * stripe_size) / + mddev->chunk_sectors; + end_disk_index = (int)(end - last_stripe_index * stripe_size) / + mddev->chunk_sectors; + } start_disk_offset = ((int)(start - first_stripe_index * stripe_size) % mddev->chunk_sectors) + first_stripe_index * mddev->chunk_sectors; - end_disk_index = (int)(end - last_stripe_index * stripe_size) / - mddev->chunk_sectors; end_disk_offset = ((int)(end - last_stripe_index * stripe_size) % mddev->chunk_sectors) + last_stripe_index * mddev->chunk_sectors; @@ -480,18 +522,22 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) sector_t dev_start, dev_end; struct bio *discard_bio = NULL; struct md_rdev *rdev; + int compare_disk; + + compare_disk = map_disk_shift(disk, zone->nb_dev, + zone->disk_shift); - if (disk < start_disk_index) + if (compare_disk < start_disk_index) dev_start = (first_stripe_index + 1) * mddev->chunk_sectors; - else if (disk > start_disk_index) + else if (compare_disk > start_disk_index) dev_start = first_stripe_index * mddev->chunk_sectors; else dev_start = start_disk_offset; - if (disk < end_disk_index) + if (compare_disk < end_disk_index) dev_end = (last_stripe_index + 1) * mddev->chunk_sectors; - else if (disk > end_disk_index) + else if (compare_disk > end_disk_index) dev_end = last_stripe_index * mddev->chunk_sectors; else dev_end = end_disk_offset; diff --git a/drivers/md/raid0.h b/drivers/md/raid0.h index 3816e5477db1e743afeaf707c1971f1dbdce1901..8cc761ca7423002d3d1d1e4c84ac5df9a3dcc70f 100644 --- a/drivers/md/raid0.h +++ b/drivers/md/raid0.h @@ -6,6 +6,7 @@ struct strip_zone { sector_t zone_end; /* Start of the next zone (in sectors) */ sector_t dev_start; /* Zone offset in real dev (in sectors) */ int nb_dev; /* # of devices attached to the zone */ + int disk_shift; /* start disk for the original layout */ }; /* Linux 3.14 (20d0189b101) made an unintended change to diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 2488a9a67d18a7f5008c104bbbbc07affccf50ef..eed047e971e703a38d4106a07591e2fc4ab35834 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -1106,7 +1106,7 @@ static int fastrpc_init_create_process(struct fastrpc_user *fl, sc = FASTRPC_SCALARS(FASTRPC_RMID_INIT_CREATE, 4, 0); if (init.attrs) - sc = FASTRPC_SCALARS(FASTRPC_RMID_INIT_CREATE_ATTR, 6, 0); + sc = FASTRPC_SCALARS(FASTRPC_RMID_INIT_CREATE_ATTR, 4, 0); err = fastrpc_internal_invoke(fl, true, FASTRPC_INIT_HANDLE, sc, args); diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c index 48eec5fe7397bfd3a448c831edbf6175e4b74afc..6c4c85eb714790052dce0e8cdb7a667851b49444 100644 --- a/drivers/misc/pci_endpoint_test.c +++ b/drivers/misc/pci_endpoint_test.c @@ -727,6 +727,10 @@ static long pci_endpoint_test_ioctl(struct file *file, unsigned int cmd, struct pci_dev *pdev = test->pdev; mutex_lock(&test->mutex); + + reinit_completion(&test->irq_raised); + test->last_irq = -ENODATA; + switch (cmd) { case PCITEST_BAR: bar = arg; @@ -935,6 +939,9 @@ static void pci_endpoint_test_remove(struct pci_dev *pdev) if (id < 0) return; + pci_endpoint_test_release_irq(test); + pci_endpoint_test_free_irq_vectors(test); + misc_deregister(&test->miscdev); kfree(misc_device->name); kfree(test->name); @@ -944,9 +951,6 @@ static void pci_endpoint_test_remove(struct pci_dev *pdev) pci_iounmap(pdev, test->bar[bar]); } - pci_endpoint_test_release_irq(test); - pci_endpoint_test_free_irq_vectors(test); - pci_release_regions(pdev); pci_disable_device(pdev); } diff --git a/drivers/mtd/nand/raw/meson_nand.c b/drivers/mtd/nand/raw/meson_nand.c index 228612d82f311d3199e25e8fc7ee78f842eafeba..ee3976b7e197e8a711f226a90733b6fd34e963f1 100644 --- a/drivers/mtd/nand/raw/meson_nand.c +++ b/drivers/mtd/nand/raw/meson_nand.c @@ -72,6 +72,7 @@ #define GENCMDIADDRH(aih, addr) ((aih) | (((addr) >> 16) & 0xffff)) #define DMA_DIR(dir) ((dir) ? NFC_CMD_N2M : NFC_CMD_M2N) +#define DMA_ADDR_ALIGN 8 #define ECC_CHECK_RETURN_FF (-1) @@ -838,6 +839,9 @@ static int meson_nfc_read_oob(struct nand_chip *nand, int page) static bool meson_nfc_is_buffer_dma_safe(const void *buffer) { + if ((uintptr_t)buffer % DMA_ADDR_ALIGN) + return false; + if (virt_addr_valid(buffer) && (!object_is_on_stack(buffer))) return true; return false; diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index bb999e67d7736a02c346d48ff82222876b284bf1..ab8ee933163543030575e7de431fd74c5cf71624 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -1492,8 +1492,6 @@ int bgmac_enet_probe(struct bgmac *bgmac) bgmac->in_init = true; - bgmac_chip_intrs_off(bgmac); - net_dev->irq = bgmac->irq; SET_NETDEV_DEV(net_dev, bgmac->dev); dev_set_drvdata(bgmac->dev, bgmac); @@ -1511,6 +1509,8 @@ int bgmac_enet_probe(struct bgmac *bgmac) */ bgmac_clk_enable(bgmac, 0); + bgmac_chip_intrs_off(bgmac); + /* This seems to be fixing IRQ by assigning OOB #6 to the core */ if (!(bgmac->feature_flags & BGMAC_FEAT_IDM_MASK)) { if (bgmac->feature_flags & BGMAC_FEAT_IRQ_ID_OOB_6) diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 4b875838a6467066546e291fc9cc7d8771d0bb0d..99aba64f03c2f3711a33a7c59ca948a3892960b6 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -624,5 +624,7 @@ void bcmgenet_mii_exit(struct net_device *dev) if (of_phy_is_fixed_link(dn)) of_phy_deregister_fixed_link(dn); of_node_put(priv->phy_dn); + clk_prepare_enable(priv->clk); platform_device_unregister(priv->mii_pdev); + clk_disable_unprepare(priv->clk); } diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index e0449cc24fbdbde3547008193877702a77233d07..cbfd00744935100bda86fca6efb31372aa9f0811 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -516,6 +516,9 @@ static int gve_get_link_ksettings(struct net_device *netdev, err = gve_adminq_report_link_speed(priv); cmd->base.speed = priv->link_speed; + + cmd->base.duplex = DUPLEX_FULL; + return err; } diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index da259cd59adda323585447903d8f89c30f121f2a..d28ac3a025ab10a90b2b55bc2e5399c47d3355f1 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -1673,6 +1673,8 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev, /* twisted pair */ cmd->base.port = PORT_TP; cmd->base.phy_address = hw->phy.addr; + ethtool_link_ksettings_add_link_mode(cmd, supported, TP); + ethtool_link_ksettings_add_link_mode(cmd, advertising, TP); /* advertising link modes */ if (hw->phy.autoneg_advertised & ADVERTISE_10_HALF) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index a15e4b6d7fa40c2a6f8da3f55cccb0496d3e2059..631ce793fb2ecfba0a03c4ecdb1dac7725f6b631 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -600,7 +600,6 @@ static void igc_configure_tx_ring(struct igc_adapter *adapter, /* disable the queue */ wr32(IGC_TXDCTL(reg_idx), 0); wrfl(); - mdelay(10); wr32(IGC_TDLEN(reg_idx), ring->count * sizeof(union igc_adv_tx_desc)); @@ -906,7 +905,7 @@ static __le32 igc_tx_launchtime(struct igc_ring *ring, ktime_t txtime, ktime_t base_time = adapter->base_time; ktime_t now = ktime_get_clocktai(); ktime_t baset_est, end_of_cycle; - u32 launchtime; + s32 launchtime; s64 n; n = div64_s64(ktime_sub_ns(now, base_time), cycle_time); @@ -919,7 +918,7 @@ static __le32 igc_tx_launchtime(struct igc_ring *ring, ktime_t txtime, *first_flag = true; ring->last_ff_cycle = baset_est; - if (ktime_compare(txtime, ring->last_tx_cycle) > 0) + if (ktime_compare(end_of_cycle, ring->last_tx_cycle) > 0) *insert_empty = true; } } diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index f5567d485e91a5e109d1dd320201bf16ffe15ccd..3656a3937eca6aa9363aa9d9753833dfb2c27a89 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1471,7 +1471,7 @@ static void mvneta_defaults_set(struct mvneta_port *pp) */ if (txq_number == 1) txq_map = (cpu == pp->rxq_def) ? - MVNETA_CPU_TXQ_ACCESS(1) : 0; + MVNETA_CPU_TXQ_ACCESS(0) : 0; } else { txq_map = MVNETA_CPU_TXQ_ACCESS_ALL_MASK; @@ -4165,7 +4165,7 @@ static void mvneta_percpu_elect(struct mvneta_port *pp) */ if (txq_number == 1) txq_map = (cpu == elected_cpu) ? - MVNETA_CPU_TXQ_ACCESS(1) : 0; + MVNETA_CPU_TXQ_ACCESS(0) : 0; else txq_map = mvreg_read(pp, MVNETA_CPU_MAP(cpu)) & MVNETA_CPU_TXQ_ACCESS_ALL_MASK; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c index e51f60b55daa4e9b396cd5f23bf03fb081265e43..2da90f6649d177f4df6765e8193d349cbb57c077 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c @@ -194,6 +194,7 @@ static int accel_fs_tcp_create_groups(struct mlx5e_flow_table *ft, in = kvzalloc(inlen, GFP_KERNEL); if (!in || !ft->g) { kfree(ft->g); + ft->g = NULL; kvfree(in); return -ENOMEM; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 16846442717dc08e7f9b3d6027ee6b4a9807f648..c6a81a51530d26b8c87dbac5133c217a817e1907 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1334,7 +1334,8 @@ static void remove_unready_flow(struct mlx5e_tc_flow *flow) uplink_priv = &rpriv->uplink_priv; mutex_lock(&uplink_priv->unready_flows_lock); - unready_flow_del(flow); + if (flow_flag_test(flow, NOT_READY)) + unready_flow_del(flow); mutex_unlock(&uplink_priv->unready_flows_lock); } @@ -1475,8 +1476,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, mlx5e_put_flow_tunnel_id(flow); - if (flow_flag_test(flow, NOT_READY)) - remove_unready_flow(flow); + remove_unready_flow(flow); if (mlx5e_is_offloaded_flow(flow)) { if (flow_flag_test(flow, SLOW)) diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 481f89d193f77657229029edacb6dfb429672db4..50cb1c5251f71071c5e9e2cd8f5e2f262030fd4f 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -83,6 +83,18 @@ static int lan743x_csr_light_reset(struct lan743x_adapter *adapter) !(data & HW_CFG_LRST_), 100000, 10000000); } +static int lan743x_csr_wait_for_bit_atomic(struct lan743x_adapter *adapter, + int offset, u32 bit_mask, + int target_value, int udelay_min, + int udelay_max, int count) +{ + u32 data; + + return readx_poll_timeout_atomic(LAN743X_CSR_READ_OP, offset, data, + target_value == !!(data & bit_mask), + udelay_max, udelay_min * count); +} + static int lan743x_csr_wait_for_bit(struct lan743x_adapter *adapter, int offset, u32 bit_mask, int target_value, int usleep_min, @@ -678,8 +690,8 @@ static int lan743x_dp_write(struct lan743x_adapter *adapter, u32 dp_sel; int i; - if (lan743x_csr_wait_for_bit(adapter, DP_SEL, DP_SEL_DPRDY_, - 1, 40, 100, 100)) + if (lan743x_csr_wait_for_bit_atomic(adapter, DP_SEL, DP_SEL_DPRDY_, + 1, 40, 100, 100)) return -EIO; dp_sel = lan743x_csr_read(adapter, DP_SEL); dp_sel &= ~DP_SEL_MASK_; @@ -690,8 +702,9 @@ static int lan743x_dp_write(struct lan743x_adapter *adapter, lan743x_csr_write(adapter, DP_ADDR, addr + i); lan743x_csr_write(adapter, DP_DATA_0, buf[i]); lan743x_csr_write(adapter, DP_CMD, DP_CMD_WRITE_); - if (lan743x_csr_wait_for_bit(adapter, DP_SEL, DP_SEL_DPRDY_, - 1, 40, 100, 100)) + if (lan743x_csr_wait_for_bit_atomic(adapter, DP_SEL, + DP_SEL_DPRDY_, + 1, 40, 100, 100)) return -EIO; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index fcd4213c99b83bfaecb4d917543479fb857718d9..098772601df8c5cb7041a12ce6df56c96dae5d12 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -433,11 +433,6 @@ static void ionic_qcqs_free(struct ionic_lif *lif) static void ionic_link_qcq_interrupts(struct ionic_qcq *src_qcq, struct ionic_qcq *n_qcq) { - if (WARN_ON(n_qcq->flags & IONIC_QCQ_F_INTR)) { - ionic_intr_free(n_qcq->cq.lif->ionic, n_qcq->intr.index); - n_qcq->flags &= ~IONIC_QCQ_F_INTR; - } - n_qcq->intr.vector = src_qcq->intr.vector; n_qcq->intr.index = src_qcq->intr.index; } diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 9bbecf4d159b45a771b1cd0ecc4aa10bc638ea02..bcf354719745c20fd9891c6054a752df13af7925 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -149,13 +149,10 @@ static ssize_t nsim_dev_trap_fa_cookie_write(struct file *file, cookie_len = (count - 1) / 2; if ((count - 1) % 2) return -EINVAL; - buf = kmalloc(count, GFP_KERNEL | __GFP_NOWARN); - if (!buf) - return -ENOMEM; - ret = simple_write_to_buffer(buf, count, ppos, data, count); - if (ret < 0) - goto free_buf; + buf = memdup_user(data, count); + if (IS_ERR(buf)) + return PTR_ERR(buf); fa_cookie = kmalloc(sizeof(*fa_cookie) + cookie_len, GFP_KERNEL | __GFP_NOWARN); diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c index 5c804bcabfe6be5b87e015b633aaeff57885cb84..f5bc279c9a8c2f4f029572d7ded6621eaacf6535 100644 --- a/drivers/net/wireguard/netlink.c +++ b/drivers/net/wireguard/netlink.c @@ -546,6 +546,7 @@ static int wg_set_device(struct sk_buff *skb, struct genl_info *info) u8 *private_key = nla_data(info->attrs[WGDEVICE_A_PRIVATE_KEY]); u8 public_key[NOISE_PUBLIC_KEY_LEN]; struct wg_peer *peer, *temp; + bool send_staged_packets; if (!crypto_memneq(wg->static_identity.static_private, private_key, NOISE_PUBLIC_KEY_LEN)) @@ -564,14 +565,17 @@ static int wg_set_device(struct sk_buff *skb, struct genl_info *info) } down_write(&wg->static_identity.lock); - wg_noise_set_static_identity_private_key(&wg->static_identity, - private_key); - list_for_each_entry_safe(peer, temp, &wg->peer_list, - peer_list) { + send_staged_packets = !wg->static_identity.has_identity && netif_running(wg->dev); + wg_noise_set_static_identity_private_key(&wg->static_identity, private_key); + send_staged_packets = send_staged_packets && wg->static_identity.has_identity; + + wg_cookie_checker_precompute_device_keys(&wg->cookie_checker); + list_for_each_entry_safe(peer, temp, &wg->peer_list, peer_list) { wg_noise_precompute_static_static(peer); wg_noise_expire_current_peer_keypairs(peer); + if (send_staged_packets) + wg_packet_send_staged_packets(peer); } - wg_cookie_checker_precompute_device_keys(&wg->cookie_checker); up_write(&wg->static_identity.lock); } skip_set_private_key: diff --git a/drivers/net/wireguard/queueing.c b/drivers/net/wireguard/queueing.c index 8084e7408c0ae9065f57bc463921cb985fd68c5e..26d235d152352f8b0b28a61b45d83f72db4f0b5d 100644 --- a/drivers/net/wireguard/queueing.c +++ b/drivers/net/wireguard/queueing.c @@ -28,6 +28,7 @@ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, int ret; memset(queue, 0, sizeof(*queue)); + queue->last_cpu = -1; ret = ptr_ring_init(&queue->ring, len, GFP_KERNEL); if (ret) return ret; diff --git a/drivers/net/wireguard/queueing.h b/drivers/net/wireguard/queueing.h index e2388107f7fdc9c040841adfc164459e0c777d7d..a2e702f8c58268c6da0481a881c1f232ef902103 100644 --- a/drivers/net/wireguard/queueing.h +++ b/drivers/net/wireguard/queueing.h @@ -119,20 +119,17 @@ static inline int wg_cpumask_choose_online(int *stored_cpu, unsigned int id) return cpu; } -/* This function is racy, in the sense that next is unlocked, so it could return - * the same CPU twice. A race-free version of this would be to instead store an - * atomic sequence number, do an increment-and-return, and then iterate through - * every possible CPU until we get to that index -- choose_cpu. However that's - * a bit slower, and it doesn't seem like this potential race actually - * introduces any performance loss, so we live with it. +/* This function is racy, in the sense that it's called while last_cpu is + * unlocked, so it could return the same CPU twice. Adding locking or using + * atomic sequence numbers is slower though, and the consequences of racing are + * harmless, so live with it. */ -static inline int wg_cpumask_next_online(int *next) +static inline int wg_cpumask_next_online(int *last_cpu) { - int cpu = *next; - - while (unlikely(!cpumask_test_cpu(cpu, cpu_online_mask))) - cpu = cpumask_next(cpu, cpu_online_mask) % nr_cpumask_bits; - *next = cpumask_next(cpu, cpu_online_mask) % nr_cpumask_bits; + int cpu = cpumask_next(*last_cpu, cpu_online_mask); + if (cpu >= nr_cpu_ids) + cpu = cpumask_first(cpu_online_mask); + *last_cpu = cpu; return cpu; } @@ -161,7 +158,7 @@ static inline void wg_prev_queue_drop_peeked(struct prev_queue *queue) static inline int wg_queue_enqueue_per_device_and_peer( struct crypt_queue *device_queue, struct prev_queue *peer_queue, - struct sk_buff *skb, struct workqueue_struct *wq, int *next_cpu) + struct sk_buff *skb, struct workqueue_struct *wq) { int cpu; @@ -175,7 +172,7 @@ static inline int wg_queue_enqueue_per_device_and_peer( /* Then we queue it up in the device queue, which consumes the * packet as soon as it can. */ - cpu = wg_cpumask_next_online(next_cpu); + cpu = wg_cpumask_next_online(&device_queue->last_cpu); if (unlikely(ptr_ring_produce_bh(&device_queue->ring, skb))) return -EPIPE; queue_work_on(cpu, wq, &per_cpu_ptr(device_queue->worker, cpu)->work); diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index 7b8df406c7737398f0270361afcb196af4b6a76e..f500aaf678370c85a994ddc256552fd1675c4bb7 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -531,7 +531,7 @@ static void wg_packet_consume_data(struct wg_device *wg, struct sk_buff *skb) goto err; ret = wg_queue_enqueue_per_device_and_peer(&wg->decrypt_queue, &peer->rx_queue, skb, - wg->packet_crypt_wq, &wg->decrypt_queue.last_cpu); + wg->packet_crypt_wq); if (unlikely(ret == -EPIPE)) wg_queue_enqueue_per_peer_rx(skb, PACKET_STATE_DEAD); if (likely(!ret || ret == -EPIPE)) { diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c index 5368f7c35b4bf21706ecc5801ebd1ae68a58d43b..95c853b59e1dae1df8b4e5cbf4e3541e35806b82 100644 --- a/drivers/net/wireguard/send.c +++ b/drivers/net/wireguard/send.c @@ -318,7 +318,7 @@ static void wg_packet_create_data(struct wg_peer *peer, struct sk_buff *first) goto err; ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue, &peer->tx_queue, first, - wg->packet_crypt_wq, &wg->encrypt_queue.last_cpu); + wg->packet_crypt_wq); if (unlikely(ret == -EPIPE)) wg_queue_enqueue_per_peer_tx(first, PACKET_STATE_DEAD); err: diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c index 8c9c6bfbaeee7e5ec053d8cc2825be505e18531f..aa1d12f6f5c3b50ea33cebc83c6c6c01fbd107e0 100644 --- a/drivers/net/wireless/cisco/airo.c +++ b/drivers/net/wireless/cisco/airo.c @@ -6150,8 +6150,11 @@ static int airo_get_rate(struct net_device *dev, { struct airo_info *local = dev->ml_priv; StatusRid status_rid; /* Card status info */ + int ret; - readStatusRid(local, &status_rid, 1); + ret = readStatusRid(local, &status_rid, 1); + if (ret) + return -EBUSY; vwrq->value = le16_to_cpu(status_rid.currentXmitRate) * 500000; /* If more than one rate, set auto */ diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c index 71428d8cbcfc533db4da10cdaeff6b764bde3ad0..ac401ad7884a6b4a56ea300876f63dd5d72eb117 100644 --- a/drivers/ntb/hw/amd/ntb_hw_amd.c +++ b/drivers/ntb/hw/amd/ntb_hw_amd.c @@ -1344,12 +1344,17 @@ static struct pci_driver amd_ntb_pci_driver = { static int __init amd_ntb_pci_driver_init(void) { + int ret; pr_info("%s %s\n", NTB_DESC, NTB_VER); if (debugfs_initialized()) debugfs_dir = debugfs_create_dir(KBUILD_MODNAME, NULL); - return pci_register_driver(&amd_ntb_pci_driver); + ret = pci_register_driver(&amd_ntb_pci_driver); + if (ret) + debugfs_remove_recursive(debugfs_dir); + + return ret; } module_init(amd_ntb_pci_driver_init); diff --git a/drivers/ntb/hw/idt/ntb_hw_idt.c b/drivers/ntb/hw/idt/ntb_hw_idt.c index d54261f50851918407decbb28bf77f39b668b140..99711dd0b6e8e020c705076f7850fc4da6e8cf8b 100644 --- a/drivers/ntb/hw/idt/ntb_hw_idt.c +++ b/drivers/ntb/hw/idt/ntb_hw_idt.c @@ -2902,6 +2902,7 @@ static struct pci_driver idt_pci_driver = { static int __init idt_pci_driver_init(void) { + int ret; pr_info("%s %s\n", NTB_DESC, NTB_VER); /* Create the top DebugFS directory if the FS is initialized */ @@ -2909,7 +2910,11 @@ static int __init idt_pci_driver_init(void) dbgfs_topdir = debugfs_create_dir(KBUILD_MODNAME, NULL); /* Register the NTB hardware driver to handle the PCI device */ - return pci_register_driver(&idt_pci_driver); + ret = pci_register_driver(&idt_pci_driver); + if (ret) + debugfs_remove_recursive(dbgfs_topdir); + + return ret; } module_init(idt_pci_driver_init); diff --git a/drivers/ntb/hw/intel/ntb_hw_gen1.c b/drivers/ntb/hw/intel/ntb_hw_gen1.c index 093dd20057b9274f3f27e7ba6b68e3a517597d15..4f1add57d81dec87ae2b36154b535a54f48e975f 100644 --- a/drivers/ntb/hw/intel/ntb_hw_gen1.c +++ b/drivers/ntb/hw/intel/ntb_hw_gen1.c @@ -2068,12 +2068,17 @@ static struct pci_driver intel_ntb_pci_driver = { static int __init intel_ntb_pci_driver_init(void) { + int ret; pr_info("%s %s\n", NTB_DESC, NTB_VER); if (debugfs_initialized()) debugfs_dir = debugfs_create_dir(KBUILD_MODNAME, NULL); - return pci_register_driver(&intel_ntb_pci_driver); + ret = pci_register_driver(&intel_ntb_pci_driver); + if (ret) + debugfs_remove_recursive(debugfs_dir); + + return ret; } module_init(intel_ntb_pci_driver_init); diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index 4a02561cfb965726c2fe2d73c9934f10adcbfb20..d18cb44765603b7392f3d75ad3beb3e2520de92c 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -412,7 +412,7 @@ int ntb_transport_register_client_dev(char *device_name) rc = device_register(dev); if (rc) { - kfree(client_dev); + put_device(dev); goto err; } diff --git a/drivers/ntb/test/ntb_tool.c b/drivers/ntb/test/ntb_tool.c index 5ee0afa621a9503c34dbcfb32421a990a00abf47..eeeb4b1c97d2c20918ec7ef98bc75ad8bd599c9b 100644 --- a/drivers/ntb/test/ntb_tool.c +++ b/drivers/ntb/test/ntb_tool.c @@ -998,6 +998,8 @@ static int tool_init_mws(struct tool_ctx *tc) tc->peers[pidx].outmws = devm_kcalloc(&tc->ntb->dev, tc->peers[pidx].outmw_cnt, sizeof(*tc->peers[pidx].outmws), GFP_KERNEL); + if (tc->peers[pidx].outmws == NULL) + return -ENOMEM; for (widx = 0; widx < tc->peers[pidx].outmw_cnt; widx++) { tc->peers[pidx].outmws[widx].pidx = pidx; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 5a3d79f92c111005467f415bf27892296ee572a8..679e7878b2e3b0e361063e1fc33df433639cf40b 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -968,7 +968,8 @@ static void nvme_pci_complete_rq(struct request *req) if (blk_integrity_rq(req)) dma_unmap_page(dev->dev, iod->meta_dma, - rq_integrity_vec(req)->bv_len, rq_data_dir(req)); + rq_integrity_vec(req)->bv_len, rq_dma_dir(req)); + if (blk_rq_nr_phys_segments(req)) nvme_unmap_data(dev, req); nvme_complete_rq(req); diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index c68e14271c02c95bfdc561e87a1c90cec4bec6e7..737cc9d6fa6ab47e7d8bc2745a89f7b52f359e50 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -771,6 +771,8 @@ static int qcom_pcie_get_resources_2_4_0(struct qcom_pcie *pcie) return PTR_ERR(res->phy_ahb_reset); } + dw_pcie_dbi_ro_wr_dis(pci); + return 0; } diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c index 379cde59988cfed7582f2ad038ce41a6d0a83766..dba8bdc3fc942aabeb1253f484c5b6408ba76e5e 100644 --- a/drivers/pci/controller/pcie-rockchip-ep.c +++ b/drivers/pci/controller/pcie-rockchip-ep.c @@ -125,6 +125,7 @@ static void rockchip_pcie_prog_ep_ob_atu(struct rockchip_pcie *rockchip, u8 fn, static int rockchip_pcie_ep_write_header(struct pci_epc *epc, u8 fn, struct pci_epf_header *hdr) { + u32 reg; struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); struct rockchip_pcie *rockchip = &ep->rockchip; @@ -137,8 +138,9 @@ static int rockchip_pcie_ep_write_header(struct pci_epc *epc, u8 fn, PCIE_CORE_CONFIG_VENDOR); } - rockchip_pcie_write(rockchip, hdr->deviceid << 16, - ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + PCI_VENDOR_ID); + reg = rockchip_pcie_read(rockchip, PCIE_EP_CONFIG_DID_VID); + reg = (reg & 0xFFFF) | (hdr->deviceid << 16); + rockchip_pcie_write(rockchip, reg, PCIE_EP_CONFIG_DID_VID); rockchip_pcie_write(rockchip, hdr->revid | @@ -312,15 +314,15 @@ static int rockchip_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, { struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); struct rockchip_pcie *rockchip = &ep->rockchip; - u16 flags; + u32 flags; flags = rockchip_pcie_read(rockchip, ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + ROCKCHIP_PCIE_EP_MSI_CTRL_REG); flags &= ~ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_MASK; flags |= - ((multi_msg_cap << 1) << ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_OFFSET) | - PCI_MSI_FLAGS_64BIT; + (multi_msg_cap << ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_OFFSET) | + (PCI_MSI_FLAGS_64BIT << ROCKCHIP_PCIE_EP_MSI_FLAGS_OFFSET); flags &= ~ROCKCHIP_PCIE_EP_MSI_CTRL_MASK_MSI_CAP; rockchip_pcie_write(rockchip, flags, ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + @@ -332,7 +334,7 @@ static int rockchip_pcie_ep_get_msi(struct pci_epc *epc, u8 fn) { struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); struct rockchip_pcie *rockchip = &ep->rockchip; - u16 flags; + u32 flags; flags = rockchip_pcie_read(rockchip, ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + @@ -345,48 +347,25 @@ static int rockchip_pcie_ep_get_msi(struct pci_epc *epc, u8 fn) } static void rockchip_pcie_ep_assert_intx(struct rockchip_pcie_ep *ep, u8 fn, - u8 intx, bool is_asserted) + u8 intx, bool do_assert) { struct rockchip_pcie *rockchip = &ep->rockchip; - u32 r = ep->max_regions - 1; - u32 offset; - u32 status; - u8 msg_code; - - if (unlikely(ep->irq_pci_addr != ROCKCHIP_PCIE_EP_PCI_LEGACY_IRQ_ADDR || - ep->irq_pci_fn != fn)) { - rockchip_pcie_prog_ep_ob_atu(rockchip, fn, r, - AXI_WRAPPER_NOR_MSG, - ep->irq_phys_addr, 0, 0); - ep->irq_pci_addr = ROCKCHIP_PCIE_EP_PCI_LEGACY_IRQ_ADDR; - ep->irq_pci_fn = fn; - } intx &= 3; - if (is_asserted) { + + if (do_assert) { ep->irq_pending |= BIT(intx); - msg_code = ROCKCHIP_PCIE_MSG_CODE_ASSERT_INTA + intx; + rockchip_pcie_write(rockchip, + PCIE_CLIENT_INT_IN_ASSERT | + PCIE_CLIENT_INT_PEND_ST_PEND, + PCIE_CLIENT_LEGACY_INT_CTRL); } else { ep->irq_pending &= ~BIT(intx); - msg_code = ROCKCHIP_PCIE_MSG_CODE_DEASSERT_INTA + intx; + rockchip_pcie_write(rockchip, + PCIE_CLIENT_INT_IN_DEASSERT | + PCIE_CLIENT_INT_PEND_ST_NORMAL, + PCIE_CLIENT_LEGACY_INT_CTRL); } - - status = rockchip_pcie_read(rockchip, - ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + - ROCKCHIP_PCIE_EP_CMD_STATUS); - status &= ROCKCHIP_PCIE_EP_CMD_STATUS_IS; - - if ((status != 0) ^ (ep->irq_pending != 0)) { - status ^= ROCKCHIP_PCIE_EP_CMD_STATUS_IS; - rockchip_pcie_write(rockchip, status, - ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + - ROCKCHIP_PCIE_EP_CMD_STATUS); - } - - offset = - ROCKCHIP_PCIE_MSG_ROUTING(ROCKCHIP_PCIE_MSG_ROUTING_LOCAL_INTX) | - ROCKCHIP_PCIE_MSG_CODE(msg_code) | ROCKCHIP_PCIE_MSG_NO_DATA; - writel(0, ep->irq_cpu_addr + offset); } static int rockchip_pcie_ep_send_legacy_irq(struct rockchip_pcie_ep *ep, u8 fn, @@ -416,7 +395,7 @@ static int rockchip_pcie_ep_send_msi_irq(struct rockchip_pcie_ep *ep, u8 fn, u8 interrupt_num) { struct rockchip_pcie *rockchip = &ep->rockchip; - u16 flags, mme, data, data_mask; + u32 flags, mme, data, data_mask; u8 msi_count; u64 pci_addr, pci_addr_mask = 0xff; @@ -506,6 +485,7 @@ static const struct pci_epc_features rockchip_pcie_epc_features = { .linkup_notifier = false, .msi_capable = true, .msix_capable = false, + .align = 256, }; static const struct pci_epc_features* @@ -631,6 +611,9 @@ static int rockchip_pcie_ep_probe(struct platform_device *pdev) ep->irq_pci_addr = ROCKCHIP_PCIE_EP_DUMMY_IRQ_ADDR; + rockchip_pcie_write(rockchip, PCIE_CLIENT_CONF_ENABLE, + PCIE_CLIENT_CONFIG); + return 0; err_epc_mem_exit: pci_epc_mem_exit(epc); diff --git a/drivers/pci/controller/pcie-rockchip.c b/drivers/pci/controller/pcie-rockchip.c index 990a00e08bc5b6d13f798a93782bd26a6194e75a..1aa84035a8bc7746231bf7d9945e4e91dabc8a79 100644 --- a/drivers/pci/controller/pcie-rockchip.c +++ b/drivers/pci/controller/pcie-rockchip.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -153,6 +154,12 @@ int rockchip_pcie_parse_dt(struct rockchip_pcie *rockchip) } EXPORT_SYMBOL_GPL(rockchip_pcie_parse_dt); +#define rockchip_pcie_read_addr(addr) rockchip_pcie_read(rockchip, addr) +/* 100 ms max wait time for PHY PLLs to lock */ +#define RK_PHY_PLL_LOCK_TIMEOUT_US 100000 +/* Sleep should be less than 20ms */ +#define RK_PHY_PLL_LOCK_SLEEP_US 1000 + int rockchip_pcie_init_port(struct rockchip_pcie *rockchip) { struct device *dev = rockchip->dev; @@ -254,6 +261,16 @@ int rockchip_pcie_init_port(struct rockchip_pcie *rockchip) } } + err = readx_poll_timeout(rockchip_pcie_read_addr, + PCIE_CLIENT_SIDE_BAND_STATUS, + regs, !(regs & PCIE_CLIENT_PHY_ST), + RK_PHY_PLL_LOCK_SLEEP_US, + RK_PHY_PLL_LOCK_TIMEOUT_US); + if (err) { + dev_err(dev, "PHY PLLs could not lock, %d\n", err); + goto err_power_off_phy; + } + /* * Please don't reorder the deassert sequence of the following * four reset pins. diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h index c7d0178fc8c235fa18db011f9353f5b2f0d6fcc8..76a5f96bfd0a7f0cb701c4006be6730223ce9599 100644 --- a/drivers/pci/controller/pcie-rockchip.h +++ b/drivers/pci/controller/pcie-rockchip.h @@ -37,6 +37,13 @@ #define PCIE_CLIENT_MODE_EP HIWORD_UPDATE(0x0040, 0) #define PCIE_CLIENT_GEN_SEL_1 HIWORD_UPDATE(0x0080, 0) #define PCIE_CLIENT_GEN_SEL_2 HIWORD_UPDATE_BIT(0x0080) +#define PCIE_CLIENT_LEGACY_INT_CTRL (PCIE_CLIENT_BASE + 0x0c) +#define PCIE_CLIENT_INT_IN_ASSERT HIWORD_UPDATE_BIT(0x0002) +#define PCIE_CLIENT_INT_IN_DEASSERT HIWORD_UPDATE(0x0002, 0) +#define PCIE_CLIENT_INT_PEND_ST_PEND HIWORD_UPDATE_BIT(0x0001) +#define PCIE_CLIENT_INT_PEND_ST_NORMAL HIWORD_UPDATE(0x0001, 0) +#define PCIE_CLIENT_SIDE_BAND_STATUS (PCIE_CLIENT_BASE + 0x20) +#define PCIE_CLIENT_PHY_ST BIT(12) #define PCIE_CLIENT_DEBUG_OUT_0 (PCIE_CLIENT_BASE + 0x3c) #define PCIE_CLIENT_DEBUG_LTSSM_MASK GENMASK(5, 0) #define PCIE_CLIENT_DEBUG_LTSSM_L1 0x18 @@ -132,6 +139,8 @@ #define PCIE_RC_RP_ATS_BASE 0x400000 #define PCIE_RC_CONFIG_NORMAL_BASE 0x800000 #define PCIE_RC_CONFIG_BASE 0xa00000 +#define PCIE_EP_CONFIG_BASE 0xa00000 +#define PCIE_EP_CONFIG_DID_VID (PCIE_EP_CONFIG_BASE + 0x00) #define PCIE_RC_CONFIG_RID_CCR (PCIE_RC_CONFIG_BASE + 0x08) #define PCIE_RC_CONFIG_SCC_SHIFT 16 #define PCIE_RC_CONFIG_DCR (PCIE_RC_CONFIG_BASE + 0xc4) @@ -223,6 +232,7 @@ #define ROCKCHIP_PCIE_EP_CMD_STATUS 0x4 #define ROCKCHIP_PCIE_EP_CMD_STATUS_IS BIT(19) #define ROCKCHIP_PCIE_EP_MSI_CTRL_REG 0x90 +#define ROCKCHIP_PCIE_EP_MSI_FLAGS_OFFSET 16 #define ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_OFFSET 17 #define ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_MASK GENMASK(19, 17) #define ROCKCHIP_PCIE_EP_MSI_CTRL_MME_OFFSET 20 @@ -230,7 +240,6 @@ #define ROCKCHIP_PCIE_EP_MSI_CTRL_ME BIT(16) #define ROCKCHIP_PCIE_EP_MSI_CTRL_MASK_MSI_CAP BIT(24) #define ROCKCHIP_PCIE_EP_DUMMY_IRQ_ADDR 0x1 -#define ROCKCHIP_PCIE_EP_PCI_LEGACY_IRQ_ADDR 0x3 #define ROCKCHIP_PCIE_EP_FUNC_BASE(fn) (((fn) << 12) & GENMASK(19, 12)) #define ROCKCHIP_PCIE_AT_IB_EP_FUNC_BAR_ADDR0(fn, bar) \ (PCIE_RC_RP_ATS_BASE + 0x0840 + (fn) * 0x0040 + (bar) * 0x0008) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index d37013d007b6eff877def47210edf8fc0401bdc7..1f8106ec709455a02aada5d885df50991c5851b4 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -2830,13 +2830,13 @@ static const struct dmi_system_id bridge_d3_blacklist[] = { { /* * Downstream device is not accessible after putting a root port - * into D3cold and back into D0 on Elo i2. + * into D3cold and back into D0 on Elo Continental Z2 board */ - .ident = "Elo i2", + .ident = "Elo Continental Z2", .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Elo Touch Solutions"), - DMI_MATCH(DMI_PRODUCT_NAME, "Elo i2"), - DMI_MATCH(DMI_PRODUCT_VERSION, "RevB"), + DMI_MATCH(DMI_BOARD_VENDOR, "Elo Touch Solutions"), + DMI_MATCH(DMI_BOARD_NAME, "Geminilake"), + DMI_MATCH(DMI_BOARD_VERSION, "Continental Z2"), }, }, #endif diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index c1ebd5e12b06e51e6177b2805a76a7dbbc901c46..c0d11348119153bc34f5b31a4e6ed37f2e334d01 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -4123,6 +4123,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9220, /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c49 */ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9230, quirk_dma_func1_alias); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9235, + quirk_dma_func1_alias); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TTI, 0x0642, quirk_dma_func1_alias); DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TTI, 0x0645, diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 82b658a3c220a84bc0d1b363d90bf122c8475281..0d71151575eeff0ac4589180a8fceb6b17afdf36 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -126,6 +126,14 @@ static int amd_gpio_set_debounce(struct gpio_chip *gc, unsigned offset, struct amd_gpio *gpio_dev = gpiochip_get_data(gc); raw_spin_lock_irqsave(&gpio_dev->lock, flags); + + /* Use special handling for Pin0 debounce */ + if (offset == 0) { + pin_reg = readl(gpio_dev->base + WAKE_INT_MASTER_REG); + if (pin_reg & INTERNAL_GPIO0_DEBOUNCE) + debounce = 0; + } + pin_reg = readl(gpio_dev->base + offset * 4); if (debounce) { @@ -215,6 +223,7 @@ static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc) char *output_value; char *output_enable; + seq_printf(s, "WAKE_INT_MASTER_REG: 0x%08x\n", readl(gpio_dev->base + WAKE_INT_MASTER_REG)); for (bank = 0; bank < gpio_dev->hwbank_num; bank++) { seq_printf(s, "GPIO bank%d\t", bank); @@ -784,9 +793,9 @@ static void amd_gpio_irq_init(struct amd_gpio *gpio_dev) raw_spin_lock_irqsave(&gpio_dev->lock, flags); - pin_reg = readl(gpio_dev->base + i * 4); + pin_reg = readl(gpio_dev->base + pin * 4); pin_reg &= ~mask; - writel(pin_reg, gpio_dev->base + i * 4); + writel(pin_reg, gpio_dev->base + pin * 4); raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); } diff --git a/drivers/pinctrl/pinctrl-amd.h b/drivers/pinctrl/pinctrl-amd.h index 95e76342404222545efb3a721e60ba7c9ab8666a..9f95ec9e2201a2427c63620d9fe14051dbd58207 100644 --- a/drivers/pinctrl/pinctrl-amd.h +++ b/drivers/pinctrl/pinctrl-amd.h @@ -17,6 +17,7 @@ #define AMD_GPIO_PINS_BANK3 32 #define WAKE_INT_MASTER_REG 0xfc +#define INTERNAL_GPIO0_DEBOUNCE (1 << 15) #define EOI_MASK (1 << 29) #define WAKE_INT_STATUS_REG0 0x2f8 diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index 1f80b2628162822fb2df03ef8c4fd2d9dd00f2ef..567c28705cb1b5471d2aa7d1bcf83ef1c096c041 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -40,7 +40,7 @@ MODULE_LICENSE("GPL"); static LIST_HEAD(wmi_block_list); struct guid_block { - char guid[16]; + guid_t guid; union { char object_id[2]; struct { @@ -121,7 +121,7 @@ static bool find_guid(const char *guid_string, struct wmi_block **out) list_for_each_entry(wblock, &wmi_block_list, list) { block = &wblock->gblock; - if (memcmp(block->guid, &guid_input, 16) == 0) { + if (guid_equal(&block->guid, &guid_input)) { if (out) *out = wblock; return true; @@ -130,11 +130,20 @@ static bool find_guid(const char *guid_string, struct wmi_block **out) return false; } +static bool guid_parse_and_compare(const char *string, const guid_t *guid) +{ + guid_t guid_input; + + if (guid_parse(string, &guid_input)) + return false; + + return guid_equal(&guid_input, guid); +} + static const void *find_guid_context(struct wmi_block *wblock, struct wmi_driver *wdriver) { const struct wmi_device_id *id; - guid_t guid_input; if (wblock == NULL || wdriver == NULL) return NULL; @@ -143,9 +152,7 @@ static const void *find_guid_context(struct wmi_block *wblock, id = wdriver->id_table; while (*id->guid_string) { - if (guid_parse(id->guid_string, &guid_input)) - continue; - if (!memcmp(wblock->gblock.guid, &guid_input, 16)) + if (guid_parse_and_compare(id->guid_string, &wblock->gblock.guid)) return id->context; id++; } @@ -457,7 +464,7 @@ EXPORT_SYMBOL_GPL(wmi_set_block); static void wmi_dump_wdg(const struct guid_block *g) { - pr_info("%pUL:\n", g->guid); + pr_info("%pUL:\n", &g->guid); if (g->flags & ACPI_WMI_EVENT) pr_info("\tnotify_id: 0x%02X\n", g->notify_id); else @@ -539,7 +546,7 @@ wmi_notify_handler handler, void *data) list_for_each_entry(block, &wmi_block_list, list) { acpi_status wmi_status; - if (memcmp(block->gblock.guid, &guid_input, 16) == 0) { + if (guid_equal(&block->gblock.guid, &guid_input)) { if (block->handler && block->handler != wmi_notify_debug) return AE_ALREADY_ACQUIRED; @@ -579,7 +586,7 @@ acpi_status wmi_remove_notify_handler(const char *guid) list_for_each_entry(block, &wmi_block_list, list) { acpi_status wmi_status; - if (memcmp(block->gblock.guid, &guid_input, 16) == 0) { + if (guid_equal(&block->gblock.guid, &guid_input)) { if (!block->handler || block->handler == wmi_notify_debug) return AE_NULL_ENTRY; @@ -615,7 +622,6 @@ acpi_status wmi_get_event_data(u32 event, struct acpi_buffer *out) { struct acpi_object_list input; union acpi_object params[1]; - struct guid_block *gblock; struct wmi_block *wblock; input.count = 1; @@ -624,7 +630,7 @@ acpi_status wmi_get_event_data(u32 event, struct acpi_buffer *out) params[0].integer.value = event; list_for_each_entry(wblock, &wmi_block_list, list) { - gblock = &wblock->gblock; + struct guid_block *gblock = &wblock->gblock; if ((gblock->flags & ACPI_WMI_EVENT) && (gblock->notify_id == event)) @@ -685,7 +691,7 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *attr, { struct wmi_block *wblock = dev_to_wblock(dev); - return sprintf(buf, "wmi:%pUL\n", wblock->gblock.guid); + return sprintf(buf, "wmi:%pUL\n", &wblock->gblock.guid); } static DEVICE_ATTR_RO(modalias); @@ -694,7 +700,7 @@ static ssize_t guid_show(struct device *dev, struct device_attribute *attr, { struct wmi_block *wblock = dev_to_wblock(dev); - return sprintf(buf, "%pUL\n", wblock->gblock.guid); + return sprintf(buf, "%pUL\n", &wblock->gblock.guid); } static DEVICE_ATTR_RO(guid); @@ -777,10 +783,10 @@ static int wmi_dev_uevent(struct device *dev, struct kobj_uevent_env *env) { struct wmi_block *wblock = dev_to_wblock(dev); - if (add_uevent_var(env, "MODALIAS=wmi:%pUL", wblock->gblock.guid)) + if (add_uevent_var(env, "MODALIAS=wmi:%pUL", &wblock->gblock.guid)) return -ENOMEM; - if (add_uevent_var(env, "WMI_GUID=%pUL", wblock->gblock.guid)) + if (add_uevent_var(env, "WMI_GUID=%pUL", &wblock->gblock.guid)) return -ENOMEM; return 0; @@ -804,11 +810,7 @@ static int wmi_dev_match(struct device *dev, struct device_driver *driver) return 0; while (*id->guid_string) { - guid_t driver_guid; - - if (WARN_ON(guid_parse(id->guid_string, &driver_guid))) - continue; - if (!memcmp(&driver_guid, wblock->gblock.guid, 16)) + if (guid_parse_and_compare(id->guid_string, &wblock->gblock.guid)) return 1; id++; @@ -1042,7 +1044,6 @@ static const struct device_type wmi_type_data = { }; static int wmi_create_device(struct device *wmi_bus_dev, - const struct guid_block *gblock, struct wmi_block *wblock, struct acpi_device *device) { @@ -1050,12 +1051,12 @@ static int wmi_create_device(struct device *wmi_bus_dev, char method[5]; int result; - if (gblock->flags & ACPI_WMI_EVENT) { + if (wblock->gblock.flags & ACPI_WMI_EVENT) { wblock->dev.dev.type = &wmi_type_event; goto out_init; } - if (gblock->flags & ACPI_WMI_METHOD) { + if (wblock->gblock.flags & ACPI_WMI_METHOD) { wblock->dev.dev.type = &wmi_type_method; mutex_init(&wblock->char_mutex); goto out_init; @@ -1105,7 +1106,7 @@ static int wmi_create_device(struct device *wmi_bus_dev, wblock->dev.dev.bus = &wmi_bus_type; wblock->dev.dev.parent = wmi_bus_dev; - dev_set_name(&wblock->dev.dev, "%pUL", gblock->guid); + dev_set_name(&wblock->dev.dev, "%pUL", &wblock->gblock.guid); device_initialize(&wblock->dev.dev); @@ -1125,12 +1126,12 @@ static void wmi_free_devices(struct acpi_device *device) } } -static bool guid_already_parsed(struct acpi_device *device, const u8 *guid) +static bool guid_already_parsed(struct acpi_device *device, const guid_t *guid) { struct wmi_block *wblock; list_for_each_entry(wblock, &wmi_block_list, list) { - if (memcmp(wblock->gblock.guid, guid, 16) == 0) { + if (guid_equal(&wblock->gblock.guid, guid)) { /* * Because we historically didn't track the relationship * between GUIDs and ACPI nodes, we don't know whether @@ -1185,7 +1186,7 @@ static int parse_wdg(struct device *wmi_bus_dev, struct acpi_device *device) * case yet, so for now, we'll just ignore the duplicate * for device creation. */ - if (guid_already_parsed(device, gblock[i].guid)) + if (guid_already_parsed(device, &gblock[i].guid)) continue; wblock = kzalloc(sizeof(struct wmi_block), GFP_KERNEL); @@ -1197,7 +1198,7 @@ static int parse_wdg(struct device *wmi_bus_dev, struct acpi_device *device) wblock->acpi_device = device; wblock->gblock = gblock[i]; - retval = wmi_create_device(wmi_bus_dev, &gblock[i], wblock, device); + retval = wmi_create_device(wmi_bus_dev, wblock, device); if (retval) { kfree(wblock); continue; @@ -1222,7 +1223,7 @@ static int parse_wdg(struct device *wmi_bus_dev, struct acpi_device *device) retval = device_add(&wblock->dev.dev); if (retval) { dev_err(wmi_bus_dev, "failed to register %pUL\n", - wblock->gblock.guid); + &wblock->gblock.guid); if (debug_event) wmi_method_enable(wblock, 0); list_del(&wblock->list); @@ -1282,12 +1283,11 @@ acpi_wmi_ec_space_handler(u32 function, acpi_physical_address address, static void acpi_wmi_notify_handler(acpi_handle handle, u32 event, void *context) { - struct guid_block *block; struct wmi_block *wblock; bool found_it = false; list_for_each_entry(wblock, &wmi_block_list, list) { - block = &wblock->gblock; + struct guid_block *block = &wblock->gblock; if (wblock->acpi_device->handle == handle && (block->flags & ACPI_WMI_EVENT) && @@ -1336,7 +1336,7 @@ static void acpi_wmi_notify_handler(acpi_handle handle, u32 event, } if (debug_event) - pr_info("DEBUG Event GUID: %pUL\n", wblock->gblock.guid); + pr_info("DEBUG Event GUID: %pUL\n", &wblock->gblock.guid); acpi_bus_generate_netlink_event( wblock->acpi_device->pnp.device_class, diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index e54cc2a761dd46ee110c2149b79d327ed0218d2f..f0af76c3de7e30b59d829bc534a1236c39d19bfd 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -3713,7 +3713,7 @@ qla2x00_start_sp(srb_t *sp) spin_lock_irqsave(qp->qp_lock_ptr, flags); pkt = __qla2x00_alloc_iocbs(sp->qpair, sp); if (!pkt) { - rval = EAGAIN; + rval = -EAGAIN; ql_log(ql_log_warn, vha, 0x700c, "qla2x00_alloc_iocbs failed.\n"); goto done; diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c index ca22a1125821777daf9f2be0bf55d8cbed4bd3ce..a4cf00756681a9923ffa267808f674737d3230c7 100644 --- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -2589,6 +2589,7 @@ OF_EARLYCON_DECLARE(lpuart, "fsl,vf610-lpuart", lpuart_early_console_setup); OF_EARLYCON_DECLARE(lpuart32, "fsl,ls1021a-lpuart", lpuart32_early_console_setup); OF_EARLYCON_DECLARE(lpuart32, "fsl,ls1028a-lpuart", ls1028a_early_console_setup); OF_EARLYCON_DECLARE(lpuart32, "fsl,imx7ulp-lpuart", lpuart32_imx_early_console_setup); +OF_EARLYCON_DECLARE(lpuart32, "fsl,imx8ulp-lpuart", lpuart32_imx_early_console_setup); OF_EARLYCON_DECLARE(lpuart32, "fsl,imx8qxp-lpuart", lpuart32_imx_early_console_setup); EARLYCON_DECLARE(lpuart, lpuart_early_console_setup); EARLYCON_DECLARE(lpuart32, lpuart32_early_console_setup); diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 8cb2cf612e49b816b10f9979d1952b5a868fd8e7..9cff927382599bba53289d1f8cbe6efd26fbaed2 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -629,7 +629,7 @@ static int z_erofs_do_read_page(struct z_erofs_decompress_frontend *fe, tight &= (clt->mode >= COLLECT_PRIMARY_HOOKED && clt->mode != COLLECT_PRIMARY_FOLLOWED_NOINPLACE); - cur = end - min_t(unsigned int, offset + end - map->m_la, end); + cur = end - min_t(erofs_off_t, offset + end - map->m_la, end); if (!(map->m_flags & EROFS_MAP_MAPPED)) { zero_user_segment(page, cur, end); goto next_part; diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index f18194fd8d770d29a863911979d9a689c829a520..a5537a9f8f36789d1d799ff50841009967bdd98b 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -215,7 +215,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, int i; u8 *in, type; - if (1 << amortizedshift == 4) + if (1 << amortizedshift == 4 && lclusterbits <= 14) vcnt = 2; else if (1 << amortizedshift == 2 && lclusterbits == 12) vcnt = 16; @@ -273,7 +273,6 @@ static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m, { struct inode *const inode = m->inode; struct erofs_inode *const vi = EROFS_I(inode); - const unsigned int lclusterbits = vi->z_logical_clusterbits; const erofs_off_t ebase = ALIGN(iloc(EROFS_I_SB(inode), vi->nid) + vi->inode_isize + vi->xattr_isize, 8) + sizeof(struct z_erofs_map_header); @@ -283,9 +282,6 @@ static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m, erofs_off_t pos; int err; - if (lclusterbits != 12) - return -EOPNOTSUPP; - if (lcn >= totalidx) return -EINVAL; diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 237983cd8cdc26ea4ea9ca8b29924c68944934c8..c2bb2ff3fbb6bf3eca97af757ddf8711c6abd59a 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -649,6 +649,14 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, ext4_update_inode_fsync_trans(handle, inode, 1); count = ar.len; + + /* + * Update reserved blocks/metadata blocks after successful block + * allocation which had been deferred till now. + */ + if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) + ext4_da_update_reserve_space(inode, count, 1); + got_it: map->m_flags |= EXT4_MAP_MAPPED; map->m_pblk = le32_to_cpu(chain[depth-1].key); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index be08d20b300da93fc351315ae9503517fdbf0a4c..c14918c71993094a531c4954e737aaab06f65453 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -654,16 +654,6 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode, */ ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE); } - - /* - * Update reserved blocks/metadata blocks after successful - * block allocation which had been deferred till now. We don't - * support fallocate for non extent files. So we can update - * reserve space here. - */ - if ((retval > 0) && - (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)) - ext4_da_update_reserve_space(inode, retval, 1); } if (retval > 0) { diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index a954ad5944ded60795f2164bd78e76567c3ae75f..0d3247045e1ecfbed3d6265635377e2a5488cd0a 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5569,8 +5569,8 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode, * them with group lock_held */ if (test_opt(sb, DISCARD)) { - err = ext4_issue_discard(sb, block_group, bit, count, - NULL); + err = ext4_issue_discard(sb, block_group, bit, + count_clusters, NULL); if (err && err != -EOPNOTSUPP) ext4_msg(sb, KERN_WARNING, "discard request in" " group:%u block:%d count:%lu failed" @@ -5654,12 +5654,6 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, sbi = EXT4_SB(sb); - if (sbi->s_mount_state & EXT4_FC_REPLAY) { - ext4_free_blocks_simple(inode, block, count); - return; - } - - might_sleep(); if (bh) { if (block) BUG_ON(block != bh->b_blocknr); @@ -5667,6 +5661,13 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, block = bh->b_blocknr; } + if (sbi->s_mount_state & EXT4_FC_REPLAY) { + ext4_free_blocks_simple(inode, block, EXT4_NUM_B2C(sbi, count)); + return; + } + + might_sleep(); + if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks not in datazone - " diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a58dded6ce6302cf998f918038a971ce0a92f13d..e1948d5a4c4754c12f98e3088fff29f2c6f5cdb2 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1098,6 +1098,12 @@ static void ext4_blkdev_remove(struct ext4_sb_info *sbi) struct block_device *bdev; bdev = sbi->s_journal_bdev; if (bdev) { + /* + * Invalidate the journal device's buffers. We don't want them + * floating about in memory - the physical journal device may + * hotswapped, and it breaks the `ro-after' testing code. + */ + invalidate_bdev(bdev); ext4_blkdev_put(bdev); sbi->s_journal_bdev = NULL; } @@ -1237,13 +1243,7 @@ static void ext4_put_super(struct super_block *sb) sync_blockdev(sb->s_bdev); invalidate_bdev(sb->s_bdev); if (sbi->s_journal_bdev && sbi->s_journal_bdev != sb->s_bdev) { - /* - * Invalidate the journal device's buffers. We don't want them - * floating about in memory - the physical journal device may - * hotswapped, and it breaks the `ro-after' testing code. - */ sync_blockdev(sbi->s_journal_bdev); - invalidate_bdev(sbi->s_journal_bdev); ext4_blkdev_remove(sbi); } @@ -5204,6 +5204,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) brelse(bh); ext4_blkdev_remove(sbi); out_fail: + invalidate_bdev(sb->s_bdev); sb->s_fs_info = NULL; kfree(sbi->s_blockgroup_lock); out_free_base: diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 501263355ef48bcd562a5760d0805736e3fee4aa..bd9af2be352fc0cd8a7daac0a6b85bf234f4ef58 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -178,7 +178,13 @@ int dbMount(struct inode *ipbmap) dbmp_le = (struct dbmap_disk *) mp->data; bmp->db_mapsize = le64_to_cpu(dbmp_le->dn_mapsize); bmp->db_nfree = le64_to_cpu(dbmp_le->dn_nfree); + bmp->db_l2nbperpage = le32_to_cpu(dbmp_le->dn_l2nbperpage); + if (bmp->db_l2nbperpage > L2PSIZE - L2MINBLOCKSIZE) { + err = -EINVAL; + goto err_release_metapage; + } + bmp->db_numag = le32_to_cpu(dbmp_le->dn_numag); if (!bmp->db_numag) { err = -EINVAL; diff --git a/fs/jfs/jfs_filsys.h b/fs/jfs/jfs_filsys.h index b5d702df7111a919a79f903ffe5462845deb4bd3..33ef13a0b110826b9c484f5d33cfa23c4a83ded2 100644 --- a/fs/jfs/jfs_filsys.h +++ b/fs/jfs/jfs_filsys.h @@ -122,7 +122,9 @@ #define NUM_INODE_PER_IAG INOSPERIAG #define MINBLOCKSIZE 512 +#define L2MINBLOCKSIZE 9 #define MAXBLOCKSIZE 4096 +#define L2MAXBLOCKSIZE 12 #define MAXFILESIZE ((s64)1 << 52) #define JFS_LINK_MAX 0xffffffff diff --git a/fs/namei.c b/fs/namei.c index 0fa9bff6e4372b9b4b1ce8b5e1e4404141bd948e..6af2bd9f814186f299f6e077784d22d24a2f0f9d 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -4400,8 +4400,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, d_exchange(old_dentry, new_dentry); } out: - if (source) - inode_unlock(source); + inode_unlock(source); if (target) inode_unlock(target); dput(new_dentry); diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 18e014fa06480eae000d20fe7c16226b24b116a0..84de9f97bbc092f8c4b183e43ddaf59f5c3fb47a 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1090,8 +1090,11 @@ static int fanotify_test_fid(struct path *path, __kernel_fsid_t *fsid) return 0; } -static int fanotify_events_supported(struct path *path, __u64 mask) +static int fanotify_events_supported(struct path *path, __u64 mask, + unsigned int flags) { + unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS; + /* * Some filesystems such as 'proc' acquire unusual locks when opening * files. For them fanotify permission events have high chances of @@ -1103,6 +1106,21 @@ static int fanotify_events_supported(struct path *path, __u64 mask) if (mask & FANOTIFY_PERM_EVENTS && path->mnt->mnt_sb->s_type->fs_flags & FS_DISALLOW_NOTIFY_PERM) return -EINVAL; + + /* + * mount and sb marks are not allowed on kernel internal pseudo fs, + * like pipe_mnt, because that would subscribe to events on all the + * anonynous pipes in the system. + * + * SB_NOUSER covers all of the internal pseudo fs whose objects are not + * exposed to user's mount namespace, but there are other SB_KERNMOUNT + * fs, like nsfs, debugfs, for which the value of allowing sb and mount + * mark is questionable. For now we leave them alone. + */ + if (mark_type != FAN_MARK_INODE && + path->mnt->mnt_sb->s_flags & SB_NOUSER) + return -EINVAL; + return 0; } @@ -1218,7 +1236,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, goto fput_and_out; if (flags & FAN_MARK_ADD) { - ret = fanotify_events_supported(&path, mask); + ret = fanotify_events_supported(&path, mask, flags); if (ret) goto path_put_and_out; } diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 2fa9b311e56632b8f6718d030b3bcc75f0ab9d13..460c58fa011aee8e0474c38ea9d010e2515975c7 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -73,7 +73,6 @@ enum { WORK_OFFQ_FLAG_BASE = WORK_STRUCT_COLOR_SHIFT, __WORK_OFFQ_CANCELING = WORK_OFFQ_FLAG_BASE, - WORK_OFFQ_CANCELING = (1 << __WORK_OFFQ_CANCELING), /* * When a work item is off queue, its high bits point to the last @@ -84,12 +83,6 @@ enum { WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_FLAG_BASE + WORK_OFFQ_FLAG_BITS, WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31, - WORK_OFFQ_POOL_NONE = (1LU << WORK_OFFQ_POOL_BITS) - 1, - - /* convenience constants */ - WORK_STRUCT_FLAG_MASK = (1UL << WORK_STRUCT_FLAG_BITS) - 1, - WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK, - WORK_STRUCT_NO_POOL = (unsigned long)WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT, /* bit mask for work_busy() return values */ WORK_BUSY_PENDING = 1 << 0, @@ -99,6 +92,14 @@ enum { WORKER_DESC_LEN = 24, }; +/* Convenience constants - of type 'unsigned long', not 'enum'! */ +#define WORK_OFFQ_CANCELING (1ul << __WORK_OFFQ_CANCELING) +#define WORK_OFFQ_POOL_NONE ((1ul << WORK_OFFQ_POOL_BITS) - 1) +#define WORK_STRUCT_NO_POOL (WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT) + +#define WORK_STRUCT_FLAG_MASK ((1ul << WORK_STRUCT_FLAG_BITS) - 1) +#define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK) + struct work_struct { atomic_long_t data; struct list_head entry; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 030237f3d82a6627fab3e64d6e69b07d15b92f2e..fb3c5f6907506b04d160054731818aa69f5736bf 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -382,7 +382,8 @@ struct nft_set_ops { int (*init)(const struct nft_set *set, const struct nft_set_desc *desc, const struct nlattr * const nla[]); - void (*destroy)(const struct nft_set *set); + void (*destroy)(const struct nft_ctx *ctx, + const struct nft_set *set); void (*gc_init)(const struct nft_set *set); unsigned int elemsize; @@ -686,6 +687,8 @@ void *nft_set_elem_init(const struct nft_set *set, u64 timeout, u64 expiration, gfp_t gfp); void nft_set_elem_destroy(const struct nft_set *set, void *elem, bool destroy_expr); +void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, + const struct nft_set *set, void *elem); /** * struct nft_set_gc_batch_head - nf_tables set garbage collection batch @@ -777,6 +780,7 @@ struct nft_expr_type { enum nft_trans_phase { NFT_TRANS_PREPARE, + NFT_TRANS_PREPARE_ERROR, NFT_TRANS_ABORT, NFT_TRANS_COMMIT, NFT_TRANS_RELEASE @@ -907,7 +911,10 @@ static inline struct nft_userdata *nft_userdata(const struct nft_rule *rule) return (void *)&rule->data[rule->dlen]; } -void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule); +void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_rule *rule); +void nft_rule_expr_deactivate(const struct nft_ctx *ctx, struct nft_rule *rule, + enum nft_trans_phase phase); +void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule); static inline void nft_set_elem_update_expr(const struct nft_set_ext *ext, struct nft_regs *regs, @@ -966,6 +973,8 @@ struct nft_chain { }; int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain); +int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); +void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); enum nft_chain_types { NFT_CHAIN_T_DEFAULT = 0, @@ -1002,11 +1011,17 @@ int nft_chain_validate_dependency(const struct nft_chain *chain, int nft_chain_validate_hooks(const struct nft_chain *chain, unsigned int hook_flags); +static inline bool nft_chain_binding(const struct nft_chain *chain) +{ + return chain->flags & NFT_CHAIN_BINDING; +} + static inline bool nft_chain_is_bound(struct nft_chain *chain) { return (chain->flags & NFT_CHAIN_BINDING) && chain->bound; } +int nft_chain_add(struct nft_table *table, struct nft_chain *chain); void nft_chain_del(struct nft_chain *chain); void nf_tables_chain_destroy(struct nft_ctx *ctx); @@ -1414,6 +1429,7 @@ static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext) * struct nft_trans - nf_tables object update in transaction * * @list: used internally + * @binding_list: list of objects with possible bindings * @msg_type: message type * @put_net: ctx->net needs to be put * @ctx: transaction context @@ -1421,6 +1437,7 @@ static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext) */ struct nft_trans { struct list_head list; + struct list_head binding_list; int msg_type; bool put_net; struct nft_ctx ctx; @@ -1431,6 +1448,7 @@ struct nft_trans_rule { struct nft_rule *rule; struct nft_flow_rule *flow; u32 rule_id; + bool bound; }; #define nft_trans_rule(trans) \ @@ -1439,6 +1457,8 @@ struct nft_trans_rule { (((struct nft_trans_rule *)trans->data)->flow) #define nft_trans_rule_id(trans) \ (((struct nft_trans_rule *)trans->data)->rule_id) +#define nft_trans_rule_bound(trans) \ + (((struct nft_trans_rule *)trans->data)->bound) struct nft_trans_set { struct nft_set *set; @@ -1454,13 +1474,17 @@ struct nft_trans_set { (((struct nft_trans_set *)trans->data)->bound) struct nft_trans_chain { + struct nft_chain *chain; bool update; char *name; struct nft_stats __percpu *stats; u8 policy; + bool bound; u32 chain_id; }; +#define nft_trans_chain(trans) \ + (((struct nft_trans_chain *)trans->data)->chain) #define nft_trans_chain_update(trans) \ (((struct nft_trans_chain *)trans->data)->update) #define nft_trans_chain_name(trans) \ @@ -1469,6 +1493,8 @@ struct nft_trans_chain { (((struct nft_trans_chain *)trans->data)->stats) #define nft_trans_chain_policy(trans) \ (((struct nft_trans_chain *)trans->data)->policy) +#define nft_trans_chain_bound(trans) \ + (((struct nft_trans_chain *)trans->data)->bound) #define nft_trans_chain_id(trans) \ (((struct nft_trans_chain *)trans->data)->chain_id) @@ -1535,4 +1561,15 @@ void nf_tables_trans_destroy_flush_work(void); int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result); __be64 nf_jiffies64_to_msecs(u64 input); +struct nftables_pernet { + struct list_head tables; + struct list_head commit_list; + struct list_head binding_list; + struct list_head module_list; + struct list_head notify_list; + struct mutex commit_mutex; + unsigned int base_seq; + u8 validate_state; +}; + #endif /* _NET_NF_TABLES_H */ diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h index 6c0806bd8d1e636579a92796965936b872bc8dbc..8c77832d024041c02ee2c38e0c7951d5c56eefda 100644 --- a/include/net/netns/nftables.h +++ b/include/net/netns/nftables.h @@ -5,14 +5,7 @@ #include struct netns_nftables { - struct list_head tables; - struct list_head commit_list; - struct list_head module_list; - struct list_head notify_list; - struct mutex commit_mutex; - unsigned int base_seq; u8 gencursor; - u8 validate_state; }; #endif diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index ba781e0aaf5667c00ddeb9a0f99f07083a353d89..e186b2bd8c86037b319c5fe379e0cb1852bd4d19 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -136,7 +136,7 @@ extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; */ static inline unsigned int psched_mtu(const struct net_device *dev) { - return dev->mtu + dev->hard_header_len; + return READ_ONCE(dev->mtu) + dev->hard_header_len; } static inline struct net *qdisc_net(struct Qdisc *q) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 0831ff6ba09fd57fbb2bbd9b7e40bddf333d10e2..d226eeaef44c407d659bcba5b6f0249072941180 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2214,9 +2214,12 @@ static void tctx_task_work(struct callback_head *cb) } req->io_task_work.func(req, &locked); node = next; + if (unlikely(need_resched())) { + ctx_flush_and_put(ctx, &locked); + ctx = NULL; + cond_resched(); + } } while (node); - - cond_resched(); } ctx_flush_and_put(ctx, &locked); @@ -7624,7 +7627,7 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, struct io_wait_queue *iowq, ktime_t *timeout) { - int ret; + int token, ret; /* make sure we run task_work before checking for signals */ ret = io_run_task_work_sig(); @@ -7634,9 +7637,17 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, if (test_bit(0, &ctx->check_cq_overflow)) return 1; + /* + * Use io_schedule_prepare/finish, so cpufreq can take into account + * that the task is waiting for IO - turns out to be important for low + * QD IO. + */ + token = io_schedule_prepare(); + ret = 1; if (!schedule_hrtimeout(timeout, HRTIMER_MODE_ABS)) - return -ETIME; - return 1; + ret = -ETIME; + io_schedule_finish(token); + return ret; } /* diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index c66d47685b28e40fca40c2e38fc83aa765fcebec..23101ebbbe1efe44ee7111adc8d3f294669e4c9b 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -801,7 +801,7 @@ static DEFINE_IRQ_WORK(rcu_tasks_trace_iw, rcu_read_unlock_iw); /* If we are the last reader, wake up the grace-period kthread. */ void rcu_read_unlock_trace_special(struct task_struct *t, int nesting) { - int nq = t->trc_reader_special.b.need_qs; + int nq = READ_ONCE(t->trc_reader_special.b.need_qs); if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) && t->trc_reader_special.b.need_mb) @@ -841,33 +841,25 @@ static void trc_read_check_handler(void *t_in) // If the task is no longer running on this CPU, leave. if (unlikely(texp != t)) { - if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end))) - wake_up(&trc_wait); goto reset_ipi; // Already on holdout list, so will check later. } // If the task is not in a read-side critical section, and // if this is the last reader, awaken the grace-period kthread. - if (likely(!t->trc_reader_nesting)) { - if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end))) - wake_up(&trc_wait); - // Mark as checked after decrement to avoid false - // positives on the above WARN_ON_ONCE(). + if (likely(!READ_ONCE(t->trc_reader_nesting))) { WRITE_ONCE(t->trc_reader_checked, true); goto reset_ipi; } // If we are racing with an rcu_read_unlock_trace(), try again later. - if (unlikely(t->trc_reader_nesting < 0)) { - if (WARN_ON_ONCE(atomic_dec_and_test(&trc_n_readers_need_end))) - wake_up(&trc_wait); + if (unlikely(READ_ONCE(t->trc_reader_nesting) < 0)) goto reset_ipi; - } WRITE_ONCE(t->trc_reader_checked, true); // Get here if the task is in a read-side critical section. Set // its state so that it will awaken the grace-period kthread upon // exit from that critical section. - WARN_ON_ONCE(t->trc_reader_special.b.need_qs); + atomic_inc(&trc_n_readers_need_end); // One more to wait on. + WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs)); WRITE_ONCE(t->trc_reader_special.b.need_qs, true); reset_ipi: @@ -904,6 +896,7 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg) n_heavy_reader_ofl_updates++; in_qs = true; } else { + // The task is not running, so C-language access is safe. in_qs = likely(!t->trc_reader_nesting); } @@ -918,7 +911,7 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg) // state so that it will awaken the grace-period kthread upon exit // from that critical section. atomic_inc(&trc_n_readers_need_end); // One more to wait on. - WARN_ON_ONCE(t->trc_reader_special.b.need_qs); + WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs)); WRITE_ONCE(t->trc_reader_special.b.need_qs, true); return true; } @@ -936,7 +929,7 @@ static void trc_wait_for_one_reader(struct task_struct *t, // The current task had better be in a quiescent state. if (t == current) { t->trc_reader_checked = true; - WARN_ON_ONCE(t->trc_reader_nesting); + WARN_ON_ONCE(READ_ONCE(t->trc_reader_nesting)); return; } @@ -959,21 +952,15 @@ static void trc_wait_for_one_reader(struct task_struct *t, if (per_cpu(trc_ipi_to_cpu, cpu) || t->trc_ipi_to_cpu >= 0) return; - atomic_inc(&trc_n_readers_need_end); per_cpu(trc_ipi_to_cpu, cpu) = true; t->trc_ipi_to_cpu = cpu; rcu_tasks_trace.n_ipis++; - if (smp_call_function_single(cpu, - trc_read_check_handler, t, 0)) { + if (smp_call_function_single(cpu, trc_read_check_handler, t, 0)) { // Just in case there is some other reason for // failure than the target CPU being offline. rcu_tasks_trace.n_ipis_fails++; per_cpu(trc_ipi_to_cpu, cpu) = false; t->trc_ipi_to_cpu = cpu; - if (atomic_dec_and_test(&trc_n_readers_need_end)) { - WARN_ON_ONCE(1); - wake_up(&trc_wait); - } } } } @@ -1046,8 +1033,8 @@ static void show_stalled_task_trace(struct task_struct *t, bool *firstreport) ".I"[READ_ONCE(t->trc_ipi_to_cpu) > 0], ".i"[is_idle_task(t)], ".N"[cpu > 0 && tick_nohz_full_cpu(cpu)], - t->trc_reader_nesting, - " N"[!!t->trc_reader_special.b.need_qs], + READ_ONCE(t->trc_reader_nesting), + " N"[!!READ_ONCE(t->trc_reader_special.b.need_qs)], cpu); sched_show_task(t); } @@ -1141,7 +1128,7 @@ static void rcu_tasks_trace_postgp(struct rcu_tasks *rtp) static void exit_tasks_rcu_finish_trace(struct task_struct *t) { WRITE_ONCE(t->trc_reader_checked, true); - WARN_ON_ONCE(t->trc_reader_nesting); + WARN_ON_ONCE(READ_ONCE(t->trc_reader_nesting)); WRITE_ONCE(t->trc_reader_nesting, 0); if (WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs))) rcu_read_unlock_trace_special(t, 0); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 2f2eeaf51d4110a2ae68b92a03797edec96e5d47..23b59b0d3143768509e4323b92b47ef5165ed22a 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -679,12 +679,17 @@ static void clear_work_data(struct work_struct *work) set_work_data(work, WORK_STRUCT_NO_POOL, 0); } +static inline struct pool_workqueue *work_struct_pwq(unsigned long data) +{ + return (struct pool_workqueue *)(data & WORK_STRUCT_WQ_DATA_MASK); +} + static struct pool_workqueue *get_work_pwq(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); if (data & WORK_STRUCT_PWQ) - return (void *)(data & WORK_STRUCT_WQ_DATA_MASK); + return work_struct_pwq(data); else return NULL; } @@ -712,8 +717,7 @@ static struct worker_pool *get_work_pool(struct work_struct *work) assert_rcu_or_pool_mutex(); if (data & WORK_STRUCT_PWQ) - return ((struct pool_workqueue *) - (data & WORK_STRUCT_WQ_DATA_MASK))->pool; + return work_struct_pwq(data)->pool; pool_id = data >> WORK_OFFQ_POOL_SHIFT; if (pool_id == WORK_OFFQ_POOL_NONE) @@ -734,8 +738,7 @@ static int get_work_pool_id(struct work_struct *work) unsigned long data = atomic_long_read(&work->data); if (data & WORK_STRUCT_PWQ) - return ((struct pool_workqueue *) - (data & WORK_STRUCT_WQ_DATA_MASK))->pool->id; + return work_struct_pwq(data)->pool->id; return data >> WORK_OFFQ_POOL_SHIFT; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d189e3c7a5f598c9c91a747ac409ee7e90771f25..9cb3f1d1b29d3a26c4d15006a44b4740cf018e47 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3685,6 +3685,11 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, skb_push(skb, -skb_network_offset(skb) + offset); + /* Ensure the head is writeable before touching the shared info */ + err = skb_unclone(skb, GFP_ATOMIC); + if (err) + goto err_linearize; + skb_shinfo(skb)->frag_list = NULL; while (list_skb) { diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ed1e5bfc97b3124476f8feb8b8072022526c6920..d5d10496b4aef14873c259522261e61c2419de60 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -314,9 +314,8 @@ static void addrconf_del_dad_work(struct inet6_ifaddr *ifp) static void addrconf_mod_rs_timer(struct inet6_dev *idev, unsigned long when) { - if (!timer_pending(&idev->rs_timer)) + if (!mod_timer(&idev->rs_timer, jiffies + when)) in6_dev_hold(idev); - mod_timer(&idev->rs_timer, jiffies + when); } static void addrconf_mod_dad_work(struct inet6_ifaddr *ifp, diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index fd1f896115c1e0ca7769c752e510f7f3af7f6411..d01165bb6a32bd9b1fdaa25c7b2da9f9091cb38c 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -429,7 +429,10 @@ static struct net_device *icmp6_dev(const struct sk_buff *skb) if (unlikely(dev->ifindex == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) { const struct rt6_info *rt6 = skb_rt6_info(skb); - if (rt6) + /* The destination could be an external IP in Ext Hdr (SRv6, RPL, etc.), + * and ip6_null_entry could be set to skb if no route is found. + */ + if (rt6 && rt6->rt6i_idev) dev = rt6->rt6i_idev->dev; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 19c0721399d9e1a3c1df5ab5af6c70770e56afca..788bb19f32e99e13bd4451349af5b8551a3b32d7 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -87,7 +87,7 @@ static u32 udp6_ehashfn(const struct net *net, fhash = __ipv6_addr_jhash(faddr, udp_ipv6_hash_secret); return __inet6_ehashfn(lhash, lport, fhash, fport, - udp_ipv6_hash_secret + net_hash_mix(net)); + udp6_ehash_secret + net_hash_mix(net)); } int udp_v6_get_port(struct sock *sk, unsigned short snum) diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 118f415928aefe26d7771379b98a2156e6b6b227..32cc91f5ba99fc21f773a0e9663d4c8bd774da92 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -404,6 +404,9 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me) BUG_ON(me->expect_class_max >= NF_CT_MAX_EXPECT_CLASSES); BUG_ON(strlen(me->name) > NF_CT_HELPER_NAME_LEN - 1); + if (!nf_ct_helper_hash) + return -ENOENT; + if (me->expect_policy->max_expected > NF_CT_EXPECT_MAX_CNT) return -EINVAL; @@ -587,4 +590,5 @@ void nf_conntrack_helper_fini(void) { nf_ct_extend_unregister(&helper_extend); kvfree(nf_ct_helper_hash); + nf_ct_helper_hash = NULL; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index efd714ae4fdb0140ea68b52d2349a8c609e7f4bd..571e697ed5430f0633374d5ba4e2c2e3cf90df03 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -21,10 +21,13 @@ #include #include #include +#include #include #define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-")) +unsigned int nf_tables_net_id __read_mostly; + static LIST_HEAD(nf_tables_expressions); static LIST_HEAD(nf_tables_objects); static LIST_HEAD(nf_tables_flowtables); @@ -103,7 +106,9 @@ static const u8 nft2audit_op[NFT_MSG_MAX] = { // enum nf_tables_msg_types static void nft_validate_state_update(struct net *net, u8 new_validate_state) { - switch (net->nft.validate_state) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + + switch (nft_net->validate_state) { case NFT_VALIDATE_SKIP: WARN_ON_ONCE(new_validate_state == NFT_VALIDATE_DO); break; @@ -114,7 +119,7 @@ static void nft_validate_state_update(struct net *net, u8 new_validate_state) return; } - net->nft.validate_state = new_validate_state; + nft_net->validate_state = new_validate_state; } static void nf_tables_trans_destroy_work(struct work_struct *w); static DECLARE_WORK(trans_destroy_work, nf_tables_trans_destroy_work); @@ -150,6 +155,7 @@ static struct nft_trans *nft_trans_alloc_gfp(const struct nft_ctx *ctx, return NULL; INIT_LIST_HEAD(&trans->list); + INIT_LIST_HEAD(&trans->binding_list); trans->msg_type = msg_type; trans->ctx = *ctx; @@ -162,34 +168,107 @@ static struct nft_trans *nft_trans_alloc(const struct nft_ctx *ctx, return nft_trans_alloc_gfp(ctx, msg_type, size, GFP_KERNEL); } -static void nft_trans_destroy(struct nft_trans *trans) +static void nft_trans_list_del(struct nft_trans *trans) { list_del(&trans->list); + list_del(&trans->binding_list); +} + +static void nft_trans_destroy(struct nft_trans *trans) +{ + nft_trans_list_del(trans); kfree(trans); } -static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) +static void __nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set, + bool bind) { + struct nftables_pernet *nft_net; struct net *net = ctx->net; struct nft_trans *trans; if (!nft_set_is_anonymous(set)) return; - list_for_each_entry_reverse(trans, &net->nft.commit_list, list) { + nft_net = net_generic(net, nf_tables_net_id); + list_for_each_entry_reverse(trans, &nft_net->commit_list, list) { switch (trans->msg_type) { case NFT_MSG_NEWSET: if (nft_trans_set(trans) == set) - nft_trans_set_bound(trans) = true; + nft_trans_set_bound(trans) = bind; break; case NFT_MSG_NEWSETELEM: if (nft_trans_elem_set(trans) == set) - nft_trans_elem_set_bound(trans) = true; + nft_trans_elem_set_bound(trans) = bind; + break; + } + } +} + +static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) +{ + return __nft_set_trans_bind(ctx, set, true); +} + +static void nft_set_trans_unbind(const struct nft_ctx *ctx, struct nft_set *set) +{ + return __nft_set_trans_bind(ctx, set, false); +} + +static void __nft_chain_trans_bind(const struct nft_ctx *ctx, + struct nft_chain *chain, bool bind) +{ + struct nftables_pernet *nft_net; + struct net *net = ctx->net; + struct nft_trans *trans; + + if (!nft_chain_binding(chain)) + return; + + nft_net = net_generic(net, nf_tables_net_id); + list_for_each_entry_reverse(trans, &nft_net->commit_list, list) { + switch (trans->msg_type) { + case NFT_MSG_NEWCHAIN: + if (nft_trans_chain(trans) == chain) + nft_trans_chain_bound(trans) = bind; + break; + case NFT_MSG_NEWRULE: + if (trans->ctx.chain == chain) + nft_trans_rule_bound(trans) = bind; break; } } } +static void nft_chain_trans_bind(const struct nft_ctx *ctx, + struct nft_chain *chain) +{ + __nft_chain_trans_bind(ctx, chain, true); +} + +int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain) +{ + if (!nft_chain_binding(chain)) + return 0; + + if (nft_chain_binding(ctx->chain)) + return -EOPNOTSUPP; + + if (chain->bound) + return -EBUSY; + + chain->bound = true; + chain->use++; + nft_chain_trans_bind(ctx, chain); + + return 0; +} + +void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain) +{ + __nft_chain_trans_bind(ctx, chain, false); +} + static int nft_netdev_register_hooks(struct net *net, struct list_head *hook_list) { @@ -270,6 +349,27 @@ static void nf_tables_unregister_hook(struct net *net, nf_unregister_net_hook(net, &basechain->ops); } +static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *trans) +{ + struct nftables_pernet *nft_net; + + nft_net = net_generic(net, nf_tables_net_id); + + switch (trans->msg_type) { + case NFT_MSG_NEWSET: + if (nft_set_is_anonymous(nft_trans_set(trans))) + list_add_tail(&trans->binding_list, &nft_net->binding_list); + break; + case NFT_MSG_NEWCHAIN: + if (!nft_trans_chain_update(trans) && + nft_chain_binding(nft_trans_chain(trans))) + list_add_tail(&trans->binding_list, &nft_net->binding_list); + break; + } + + list_add_tail(&trans->list, &nft_net->commit_list); +} + static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type) { struct nft_trans *trans; @@ -281,7 +381,7 @@ static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type) if (msg_type == NFT_MSG_NEWTABLE) nft_activate_next(ctx->net, ctx->table); - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } @@ -313,8 +413,9 @@ static struct nft_trans *nft_trans_chain_add(struct nft_ctx *ctx, int msg_type) ntohl(nla_get_be32(ctx->nla[NFTA_CHAIN_ID])); } } + nft_trans_chain(trans) = ctx->chain; + nft_trans_commit_list_add_tail(ctx->net, trans); - list_add_tail(&trans->list, &ctx->net->nft.commit_list); return trans; } @@ -332,8 +433,7 @@ static int nft_delchain(struct nft_ctx *ctx) return 0; } -static void nft_rule_expr_activate(const struct nft_ctx *ctx, - struct nft_rule *rule) +void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_rule *rule) { struct nft_expr *expr; @@ -346,9 +446,8 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx, } } -static void nft_rule_expr_deactivate(const struct nft_ctx *ctx, - struct nft_rule *rule, - enum nft_trans_phase phase) +void nft_rule_expr_deactivate(const struct nft_ctx *ctx, struct nft_rule *rule, + enum nft_trans_phase phase) { struct nft_expr *expr; @@ -387,7 +486,7 @@ static struct nft_trans *nft_trans_rule_add(struct nft_ctx *ctx, int msg_type, ntohl(nla_get_be32(ctx->nla[NFTA_RULE_ID])); } nft_trans_rule(trans) = rule; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return trans; } @@ -453,11 +552,36 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, nft_activate_next(ctx->net, set); } nft_trans_set(trans) = set; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } +static void nft_setelem_data_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem); + +static int nft_mapelem_deactivate(const struct nft_ctx *ctx, + struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem) +{ + nft_setelem_data_deactivate(ctx->net, set, elem); + + return 0; +} + +static void nft_map_deactivate(const struct nft_ctx *ctx, struct nft_set *set) +{ + struct nft_set_iter iter = { + .genmask = nft_genmask_next(ctx->net), + .fn = nft_mapelem_deactivate, + }; + + set->ops->walk(ctx, set, &iter); + WARN_ON_ONCE(iter.err); +} + static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set) { int err; @@ -466,6 +590,9 @@ static int nft_delset(const struct nft_ctx *ctx, struct nft_set *set) if (err < 0) return err; + if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_deactivate(ctx, set); + nft_deactivate_next(ctx->net, set); ctx->table->use--; @@ -485,7 +612,7 @@ static int nft_trans_obj_add(struct nft_ctx *ctx, int msg_type, nft_activate_next(ctx->net, obj); nft_trans_obj(trans) = obj; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } @@ -519,7 +646,7 @@ static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); nft_trans_flowtable(trans) = flowtable; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; } @@ -547,13 +674,15 @@ static struct nft_table *nft_table_lookup(const struct net *net, const struct nlattr *nla, u8 family, u8 genmask) { + struct nftables_pernet *nft_net; struct nft_table *table; if (nla == NULL) return ERR_PTR(-EINVAL); - list_for_each_entry_rcu(table, &net->nft.tables, list, - lockdep_is_held(&net->nft.commit_mutex)) { + nft_net = net_generic(net, nf_tables_net_id); + list_for_each_entry_rcu(table, &nft_net->tables, list, + lockdep_is_held(&nft_net->commit_mutex)) { if (!nla_strcmp(nla, table->name) && table->family == family && nft_active_genmask(table, genmask)) @@ -567,9 +696,11 @@ static struct nft_table *nft_table_lookup_byhandle(const struct net *net, const struct nlattr *nla, u8 genmask) { + struct nftables_pernet *nft_net; struct nft_table *table; - list_for_each_entry(table, &net->nft.tables, list) { + nft_net = net_generic(net, nf_tables_net_id); + list_for_each_entry(table, &nft_net->tables, list) { if (be64_to_cpu(nla_get_be64(nla)) == table->handle && nft_active_genmask(table, genmask)) return table; @@ -621,6 +752,7 @@ struct nft_module_request { static int nft_request_module(struct net *net, const char *fmt, ...) { char module_name[MODULE_NAME_LEN]; + struct nftables_pernet *nft_net; struct nft_module_request *req; va_list args; int ret; @@ -631,7 +763,8 @@ static int nft_request_module(struct net *net, const char *fmt, ...) if (ret >= MODULE_NAME_LEN) return 0; - list_for_each_entry(req, &net->nft.module_list, list) { + nft_net = net_generic(net, nf_tables_net_id); + list_for_each_entry(req, &nft_net->module_list, list) { if (!strcmp(req->module, module_name)) { if (req->done) return 0; @@ -647,7 +780,7 @@ static int nft_request_module(struct net *net, const char *fmt, ...) req->done = false; strlcpy(req->module, module_name, MODULE_NAME_LEN); - list_add_tail(&req->list, &net->nft.module_list); + list_add_tail(&req->list, &nft_net->module_list); return -EAGAIN; } @@ -685,7 +818,9 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla, static __be16 nft_base_seq(const struct net *net) { - return htons(net->nft.base_seq & 0xffff); + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + + return htons(nft_net->base_seq & 0xffff); } static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = { @@ -743,6 +878,7 @@ static void nft_notify_enqueue(struct sk_buff *skb, bool report, static void nf_tables_table_notify(const struct nft_ctx *ctx, int event) { + struct nftables_pernet *nft_net; struct sk_buff *skb; int err; @@ -761,7 +897,8 @@ static void nf_tables_table_notify(const struct nft_ctx *ctx, int event) goto err; } - nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); + nft_net = net_generic(ctx->net, nf_tables_net_id); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -771,15 +908,17 @@ static int nf_tables_dump_tables(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); + struct nftables_pernet *nft_net; const struct nft_table *table; unsigned int idx = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = net_generic(net, nf_tables_net_id); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -954,7 +1093,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx) goto err; nft_trans_table_update(trans) = true; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err: nft_trans_destroy(trans); @@ -1041,6 +1180,7 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, const struct nlattr * const nla[], struct netlink_ext_ack *extack) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; @@ -1053,7 +1193,7 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, if (!nft_supported_family(family)) return -EOPNOTSUPP; - lockdep_assert_held(&net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); attr = nla[NFTA_TABLE_NAME]; table = nft_table_lookup(net, attr, family, genmask); if (IS_ERR(table)) { @@ -1111,7 +1251,7 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, if (err < 0) goto err_trans; - list_add_tail_rcu(&table->list, &net->nft.tables); + list_add_tail_rcu(&table->list, &nft_net->tables); return 0; err_trans: rhltable_destroy(&table->chains_ht); @@ -1199,11 +1339,12 @@ static int nft_flush_table(struct nft_ctx *ctx) static int nft_flush(struct nft_ctx *ctx, int family) { + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); struct nft_table *table, *nt; const struct nlattr * const *nla = ctx->nla; int err = 0; - list_for_each_entry_safe(table, nt, &ctx->net->nft.tables, list) { + list_for_each_entry_safe(table, nt, &nft_net->tables, list) { if (family != AF_UNSPEC && table->family != family) continue; @@ -1318,7 +1459,9 @@ nft_chain_lookup_byhandle(const struct nft_table *table, u64 handle, u8 genmask) static bool lockdep_commit_lock_is_held(const struct net *net) { #ifdef CONFIG_PROVE_LOCKING - return lockdep_is_held(&net->nft.commit_mutex); + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + + return lockdep_is_held(&nft_net->commit_mutex); #else return true; #endif @@ -1521,6 +1664,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event) { + struct nftables_pernet *nft_net; struct sk_buff *skb; int err; @@ -1540,7 +1684,8 @@ static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event) goto err; } - nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); + nft_net = net_generic(ctx->net, nf_tables_net_id); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -1555,11 +1700,13 @@ static int nf_tables_dump_chains(struct sk_buff *skb, unsigned int idx = 0, s_idx = cb->args[0]; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + struct nftables_pernet *nft_net; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = net_generic(net, nf_tables_net_id); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -1874,11 +2021,12 @@ static int nft_chain_parse_hook(struct net *net, struct nft_chain_hook *hook, u8 family, bool autoload) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nlattr *ha[NFTA_HOOK_MAX + 1]; const struct nft_chain_type *type; int err; - lockdep_assert_held(&net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); lockdep_nfnl_nft_mutex_not_held(); err = nla_parse_nested_deprecated(ha, NFTA_HOOK_MAX, @@ -2008,7 +2156,7 @@ static int nft_basechain_init(struct nft_base_chain *basechain, u8 family, return 0; } -static int nft_chain_add(struct nft_table *table, struct nft_chain *chain) +int nft_chain_add(struct nft_table *table, struct nft_chain *chain) { int err; @@ -2271,6 +2419,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, if (nla[NFTA_CHAIN_HANDLE] && nla[NFTA_CHAIN_NAME]) { + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); struct nft_trans *tmp; char *name; @@ -2280,7 +2429,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, goto err; err = -EEXIST; - list_for_each_entry(tmp, &ctx->net->nft.commit_list, list) { + list_for_each_entry(tmp, &nft_net->commit_list, list) { if (tmp->msg_type == NFT_MSG_NEWCHAIN && tmp->ctx.table == table && nft_trans_chain_update(tmp) && @@ -2294,7 +2443,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, nft_trans_chain_name(trans) = name; } - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err: @@ -2307,10 +2456,11 @@ static struct nft_chain *nft_chain_lookup_byid(const struct net *net, const struct nft_table *table, const struct nlattr *nla, u8 genmask) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); u32 id = ntohl(nla_get_be32(nla)); struct nft_trans *trans; - list_for_each_entry(trans, &net->nft.commit_list, list) { + list_for_each_entry(trans, &nft_net->commit_list, list) { struct nft_chain *chain = trans->ctx.chain; if (trans->msg_type == NFT_MSG_NEWCHAIN && @@ -2327,6 +2477,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, const struct nlattr * const nla[], struct netlink_ext_ack *extack) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; @@ -2338,7 +2489,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, u64 handle = 0; u32 flags = 0; - lockdep_assert_held(&net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask); if (IS_ERR(table)) { @@ -2876,6 +3027,7 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, static void nf_tables_rule_notify(const struct nft_ctx *ctx, const struct nft_rule *rule, int event) { + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); struct sk_buff *skb; int err; @@ -2895,7 +3047,7 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx, goto err; } - nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -2953,11 +3105,13 @@ static int nf_tables_dump_rules(struct sk_buff *skb, unsigned int idx = 0; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + struct nftables_pernet *nft_net; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = net_generic(net, nf_tables_net_id); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -3104,8 +3258,7 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, return err; } -static void nf_tables_rule_destroy(const struct nft_ctx *ctx, - struct nft_rule *rule) +void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule) { struct nft_expr *expr, *next; @@ -3122,7 +3275,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, kfree(rule); } -void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) +static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) { nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE); nf_tables_rule_destroy(ctx, rule); @@ -3150,6 +3303,8 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) if (err < 0) return err; } + + cond_resched(); } return 0; @@ -3189,6 +3344,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, const struct nlattr * const nla[], struct netlink_ext_ack *extack) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); struct nft_expr_info *info = NULL; @@ -3206,7 +3362,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, int err, rem; u64 handle, pos_handle; - lockdep_assert_held(&net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask); if (IS_ERR(table)) { @@ -3381,7 +3537,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, kvfree(info); chain->use++; - if (net->nft.validate_state == NFT_VALIDATE_DO) + if (nft_net->validate_state == NFT_VALIDATE_DO) return nft_table_validate(net, table); if (chain->flags & NFT_CHAIN_HW_OFFLOAD) { @@ -3394,7 +3550,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, return 0; err2: - nft_rule_expr_deactivate(&ctx, rule, NFT_TRANS_PREPARE); + nft_rule_expr_deactivate(&ctx, rule, NFT_TRANS_PREPARE_ERROR); nf_tables_rule_destroy(&ctx, rule); err1: for (i = 0; i < n; i++) { @@ -3412,10 +3568,11 @@ static struct nft_rule *nft_rule_lookup_byid(const struct net *net, const struct nft_chain *chain, const struct nlattr *nla) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); u32 id = ntohl(nla_get_be32(nla)); struct nft_trans *trans; - list_for_each_entry(trans, &net->nft.commit_list, list) { + list_for_each_entry(trans, &nft_net->commit_list, list) { struct nft_rule *rule = nft_trans_rule(trans); if (trans->msg_type == NFT_MSG_NEWRULE && @@ -3530,13 +3687,14 @@ nft_select_set_ops(const struct nft_ctx *ctx, const struct nft_set_desc *desc, enum nft_set_policies policy) { + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); const struct nft_set_ops *ops, *bops; struct nft_set_estimate est, best; const struct nft_set_type *type; u32 flags = 0; int i; - lockdep_assert_held(&ctx->net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); lockdep_nfnl_nft_mutex_not_held(); if (nla[NFTA_SET_FLAGS] != NULL) @@ -3674,10 +3832,11 @@ static struct nft_set *nft_set_lookup_byid(const struct net *net, const struct nft_table *table, const struct nlattr *nla, u8 genmask) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_trans *trans; u32 id = ntohl(nla_get_be32(nla)); - list_for_each_entry(trans, &net->nft.commit_list, list) { + list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->msg_type == NFT_MSG_NEWSET) { struct nft_set *set = nft_trans_set(trans); @@ -3900,6 +4059,7 @@ static void nf_tables_set_notify(const struct nft_ctx *ctx, const struct nft_set *set, int event, gfp_t gfp_flags) { + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); struct sk_buff *skb; u32 portid = ctx->portid; int err; @@ -3918,7 +4078,7 @@ static void nf_tables_set_notify(const struct nft_ctx *ctx, goto err; } - nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -3931,14 +4091,16 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb) struct nft_table *table, *cur_table = (struct nft_table *)cb->args[2]; struct net *net = sock_net(skb->sk); struct nft_ctx *ctx = cb->data, ctx_set; + struct nftables_pernet *nft_net; if (cb->args[1]) return skb->len; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = net_generic(net, nf_tables_net_id); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (ctx->family != NFPROTO_UNSPEC && ctx->family != table->family) continue; @@ -4372,7 +4534,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (set->expr) nft_expr_destroy(&ctx, set->expr); - ops->destroy(set); + ops->destroy(&ctx, set); err_set_init: kfree(set->name); err_set_name: @@ -4388,7 +4550,7 @@ static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set) if (set->expr) nft_expr_destroy(ctx, set->expr); - set->ops->destroy(set); + set->ops->destroy(ctx, set); kfree(set->name); kvfree(set); } @@ -4512,10 +4674,39 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, } } +static void nft_setelem_data_activate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem); + +static int nft_mapelem_activate(const struct nft_ctx *ctx, + struct nft_set *set, + const struct nft_set_iter *iter, + struct nft_set_elem *elem) +{ + nft_setelem_data_activate(ctx->net, set, elem); + + return 0; +} + +static void nft_map_activate(const struct nft_ctx *ctx, struct nft_set *set) +{ + struct nft_set_iter iter = { + .genmask = nft_genmask_next(ctx->net), + .fn = nft_mapelem_activate, + }; + + set->ops->walk(ctx, set, &iter); + WARN_ON_ONCE(iter.err); +} + void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set) { - if (nft_set_is_anonymous(set)) + if (nft_set_is_anonymous(set)) { + if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_activate(ctx, set); + nft_clear(ctx->net, set); + } set->use++; } @@ -4526,14 +4717,30 @@ void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set, enum nft_trans_phase phase) { switch (phase) { - case NFT_TRANS_PREPARE: + case NFT_TRANS_PREPARE_ERROR: + nft_set_trans_unbind(ctx, set); if (nft_set_is_anonymous(set)) nft_deactivate_next(ctx->net, set); + else + list_del_rcu(&binding->list); + set->use--; + break; + case NFT_TRANS_PREPARE: + if (nft_set_is_anonymous(set)) { + if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_deactivate(ctx, set); + + nft_deactivate_next(ctx->net, set); + } set->use--; return; case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: + if (nft_set_is_anonymous(set) && + set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_deactivate(ctx, set); + set->use--; fallthrough; default: @@ -4739,6 +4946,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) { struct nft_set_dump_ctx *dump_ctx = cb->data; struct net *net = sock_net(skb->sk); + struct nftables_pernet *nft_net; struct nft_table *table; struct nft_set *set; struct nft_set_dump_args args; @@ -4749,7 +4957,8 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) int event; rcu_read_lock(); - list_for_each_entry_rcu(table, &net->nft.tables, list) { + nft_net = net_generic(net, nf_tables_net_id); + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (dump_ctx->ctx.family != NFPROTO_UNSPEC && dump_ctx->ctx.family != table->family) continue; @@ -5028,6 +5237,7 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx, const struct nft_set_elem *elem, int event, u16 flags) { + struct nftables_pernet *nft_net; struct net *net = ctx->net; u32 portid = ctx->portid; struct sk_buff *skb; @@ -5047,7 +5257,8 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx, goto err; } - nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); + nft_net = net_generic(net, nf_tables_net_id); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -5136,6 +5347,7 @@ static void nft_set_elem_expr_destroy(const struct nft_ctx *ctx, } } +/* Drop references and destroy. Called from gc, dynset and abort path. */ void nft_set_elem_destroy(const struct nft_set *set, void *elem, bool destroy_expr) { @@ -5157,11 +5369,11 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, } EXPORT_SYMBOL_GPL(nft_set_elem_destroy); -/* Only called from commit path, nft_set_elem_deactivate() already deals with - * the refcounting from the preparation phase. +/* Destroy element. References have been already dropped in the preparation + * path via nft_setelem_data_deactivate(). */ -static void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, - const struct nft_set *set, void *elem) +void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, + const struct nft_set *set, void *elem) { struct nft_set_ext *ext = nft_set_elem_ext(set, elem); @@ -5443,7 +5655,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, } nft_trans_elem(trans) = elem; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err_set_full: @@ -5474,6 +5686,7 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, const struct nlattr * const nla[], struct netlink_ext_ack *extack) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); u8 genmask = nft_genmask_next(net); const struct nlattr *attr; struct nft_set *set; @@ -5503,7 +5716,7 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, return err; } - if (net->nft.validate_state == NFT_VALIDATE_DO) + if (nft_net->validate_state == NFT_VALIDATE_DO) return nft_table_validate(net, ctx.table); return 0; @@ -5523,7 +5736,6 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, void nft_data_hold(const struct nft_data *data, enum nft_data_types type) { struct nft_chain *chain; - struct nft_rule *rule; if (type == NFT_DATA_VERDICT) { switch (data->verdict.code) { @@ -5531,23 +5743,14 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) case NFT_GOTO: chain = data->verdict.chain; chain->use++; - - if (!nft_chain_is_bound(chain)) - break; - - chain->table->use++; - list_for_each_entry(rule, &chain->rules, list) - chain->use++; - - nft_chain_add(chain->table, chain); break; } } } -static void nft_set_elem_activate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem) +static void nft_setelem_data_activate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); @@ -5557,9 +5760,9 @@ static void nft_set_elem_activate(const struct net *net, (*nft_set_ext_obj(ext))->use++; } -static void nft_set_elem_deactivate(const struct net *net, - const struct nft_set *set, - struct nft_set_elem *elem) +static void nft_setelem_data_deactivate(const struct net *net, + const struct nft_set *set, + struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); @@ -5636,10 +5839,10 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, kfree(elem.priv); elem.priv = priv; - nft_set_elem_deactivate(ctx->net, set, &elem); + nft_setelem_data_deactivate(ctx->net, set, &elem); nft_trans_elem(trans) = elem; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; fail_ops: @@ -5670,10 +5873,10 @@ static int nft_flush_set(const struct nft_ctx *ctx, } set->ndeact++; - nft_set_elem_deactivate(ctx->net, set, elem); + nft_setelem_data_deactivate(ctx->net, set, elem); nft_trans_elem_set(trans) = set; nft_trans_elem(trans) = *elem; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err1: @@ -5972,7 +6175,7 @@ static int nf_tables_updobj(const struct nft_ctx *ctx, nft_trans_obj(trans) = obj; nft_trans_obj_update(trans) = true; nft_trans_obj_newobj(trans) = newobj; - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; @@ -6135,6 +6338,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) struct nft_obj_filter *filter = cb->data; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; + struct nftables_pernet *nft_net; struct nft_object *obj; bool reset = false; @@ -6142,9 +6346,10 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) reset = true; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = net_generic(net, nf_tables_net_id); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -6167,7 +6372,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) char *buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, - net->nft.base_seq); + nft_net->base_seq); audit_log_nfcfg(buf, family, @@ -6288,8 +6493,11 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, reset = true; if (reset) { - char *buf = kasprintf(GFP_ATOMIC, "%s:%u", - table->name, net->nft.base_seq); + const struct nftables_pernet *nft_net; + char *buf; + + nft_net = net_generic(net, nf_tables_net_id); + buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, nft_net->base_seq); audit_log_nfcfg(buf, family, @@ -6374,10 +6582,11 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, int event, int family, int report, gfp_t gfp) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct sk_buff *skb; int err; char *buf = kasprintf(gfp, "%s:%u", - table->name, net->nft.base_seq); + table->name, nft_net->base_seq); audit_log_nfcfg(buf, family, @@ -6403,7 +6612,7 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, goto err; } - nft_notify_enqueue(skb, report, &net->nft.notify_list); + nft_notify_enqueue(skb, report, &nft_net->notify_list); return; err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -6465,6 +6674,7 @@ void nf_tables_deactivate_flowtable(const struct nft_ctx *ctx, enum nft_trans_phase phase) { switch (phase) { + case NFT_TRANS_PREPARE_ERROR: case NFT_TRANS_PREPARE: case NFT_TRANS_ABORT: case NFT_TRANS_RELEASE: @@ -6739,7 +6949,7 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); list_splice(&flowtable_hook.list, &nft_trans_flowtable_hooks(trans)); - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; @@ -6929,7 +7139,7 @@ static int nft_delflowtable_hook(struct nft_ctx *ctx, list_splice(&flowtable_del_list, &nft_trans_flowtable_hooks(trans)); nft_flowtable_hook_release(&flowtable_hook); - list_add_tail(&trans->list, &ctx->net->nft.commit_list); + nft_trans_commit_list_add_tail(ctx->net, trans); return 0; @@ -7055,12 +7265,14 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb, struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nft_flowtable *flowtable; + struct nftables_pernet *nft_net; const struct nft_table *table; rcu_read_lock(); - cb->seq = net->nft.base_seq; + nft_net = net_generic(net, nf_tables_net_id); + cb->seq = nft_net->base_seq; - list_for_each_entry_rcu(table, &net->nft.tables, list) { + list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) continue; @@ -7195,6 +7407,7 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, struct list_head *hook_list, int event) { + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); struct sk_buff *skb; int err; @@ -7214,7 +7427,7 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, goto err; } - nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); + nft_notify_enqueue(skb, ctx->report, &nft_net->notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -7239,6 +7452,7 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nlmsghdr *nlh; char buf[TASK_COMM_LEN]; int event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_NEWGEN); @@ -7248,7 +7462,7 @@ static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, if (!nlh) goto nla_put_failure; - if (nla_put_be32(skb, NFTA_GEN_ID, htonl(net->nft.base_seq)) || + if (nla_put_be32(skb, NFTA_GEN_ID, htonl(nft_net->base_seq)) || nla_put_be32(skb, NFTA_GEN_PROC_PID, htonl(task_pid_nr(current))) || nla_put_string(skb, NFTA_GEN_PROC_NAME, get_task_comm(buf, current))) goto nla_put_failure; @@ -7283,6 +7497,7 @@ static int nf_tables_flowtable_event(struct notifier_block *this, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct nft_flowtable *flowtable; + struct nftables_pernet *nft_net; struct nft_table *table; struct net *net; @@ -7290,13 +7505,14 @@ static int nf_tables_flowtable_event(struct notifier_block *this, return 0; net = dev_net(dev); - mutex_lock(&net->nft.commit_mutex); - list_for_each_entry(table, &net->nft.tables, list) { + nft_net = net_generic(net, nf_tables_net_id); + mutex_lock(&nft_net->commit_mutex); + list_for_each_entry(table, &nft_net->tables, list) { list_for_each_entry(flowtable, &table->flowtables, list) { nft_flowtable_event(event, dev, flowtable); } } - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } @@ -7477,16 +7693,17 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { static int nf_tables_validate(struct net *net) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_table *table; - switch (net->nft.validate_state) { + switch (nft_net->validate_state) { case NFT_VALIDATE_SKIP: break; case NFT_VALIDATE_NEED: nft_validate_state_update(net, NFT_VALIDATE_DO); fallthrough; case NFT_VALIDATE_DO: - list_for_each_entry(table, &net->nft.tables, list) { + list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_validate(net, table) < 0) return -EAGAIN; } @@ -7619,7 +7836,7 @@ static void nf_tables_trans_destroy_work(struct work_struct *w) synchronize_rcu(); list_for_each_entry_safe(trans, next, &head, list) { - list_del(&trans->list); + nft_trans_list_del(trans); nft_commit_release(trans); } } @@ -7663,9 +7880,10 @@ static int nf_tables_commit_chain_prepare(struct net *net, struct nft_chain *cha static void nf_tables_commit_chain_prepare_cancel(struct net *net) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_trans *trans, *next; - list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { struct nft_chain *chain = trans->ctx.chain; if (trans->msg_type == NFT_MSG_NEWRULE || @@ -7763,10 +7981,11 @@ void nft_chain_del(struct nft_chain *chain) static void nf_tables_module_autoload_cleanup(struct net *net) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_module_request *req, *next; - WARN_ON_ONCE(!list_empty(&net->nft.commit_list)); - list_for_each_entry_safe(req, next, &net->nft.module_list, list) { + WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); + list_for_each_entry_safe(req, next, &nft_net->module_list, list) { WARN_ON_ONCE(!req->done); list_del(&req->list); kfree(req); @@ -7775,6 +7994,7 @@ static void nf_tables_module_autoload_cleanup(struct net *net) static void nf_tables_commit_release(struct net *net) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_trans *trans; /* all side effects have to be made visible. @@ -7784,35 +8004,36 @@ static void nf_tables_commit_release(struct net *net) * Memory reclaim happens asynchronously from work queue * to prevent expensive synchronize_rcu() in commit phase. */ - if (list_empty(&net->nft.commit_list)) { + if (list_empty(&nft_net->commit_list)) { nf_tables_module_autoload_cleanup(net); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return; } - trans = list_last_entry(&net->nft.commit_list, + trans = list_last_entry(&nft_net->commit_list, struct nft_trans, list); get_net(trans->ctx.net); WARN_ON_ONCE(trans->put_net); trans->put_net = true; spin_lock(&nf_tables_destroy_list_lock); - list_splice_tail_init(&net->nft.commit_list, &nf_tables_destroy_list); + list_splice_tail_init(&nft_net->commit_list, &nf_tables_destroy_list); spin_unlock(&nf_tables_destroy_list_lock); nf_tables_module_autoload_cleanup(net); schedule_work(&trans_destroy_work); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); } static void nft_commit_notify(struct net *net, u32 portid) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct sk_buff *batch_skb = NULL, *nskb, *skb; unsigned char *data; int len; - list_for_each_entry_safe(skb, nskb, &net->nft.notify_list, list) { + list_for_each_entry_safe(skb, nskb, &nft_net->notify_list, list) { if (!batch_skb) { new_batch: batch_skb = skb; @@ -7838,7 +8059,7 @@ static void nft_commit_notify(struct net *net, u32 portid) NFT_CB(batch_skb).report, GFP_KERNEL); } - WARN_ON_ONCE(!list_empty(&net->nft.notify_list)); + WARN_ON_ONCE(!list_empty(&nft_net->notify_list)); } static int nf_tables_commit_audit_alloc(struct list_head *adl, @@ -7904,6 +8125,7 @@ static void nf_tables_commit_audit_log(struct list_head *adl, u32 generation) static int nf_tables_commit(struct net *net, struct sk_buff *skb) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_trans *trans, *next; struct nft_trans_elem *te; struct nft_chain *chain; @@ -7911,11 +8133,31 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) LIST_HEAD(adl); int err; - if (list_empty(&net->nft.commit_list)) { - mutex_unlock(&net->nft.commit_mutex); + if (list_empty(&nft_net->commit_list)) { + mutex_unlock(&nft_net->commit_mutex); return 0; } + list_for_each_entry(trans, &nft_net->binding_list, binding_list) { + switch (trans->msg_type) { + case NFT_MSG_NEWSET: + if (nft_set_is_anonymous(nft_trans_set(trans)) && + !nft_trans_set_bound(trans)) { + pr_warn_once("nftables ruleset with unbound set\n"); + return -EINVAL; + } + break; + case NFT_MSG_NEWCHAIN: + if (!nft_trans_chain_update(trans) && + nft_chain_binding(nft_trans_chain(trans)) && + !nft_trans_chain_bound(trans)) { + pr_warn_once("nftables ruleset with unbound chain\n"); + return -EINVAL; + } + break; + } + } + /* 0. Validate ruleset, otherwise roll back for error reporting. */ if (nf_tables_validate(net) < 0) return -EAGAIN; @@ -7925,7 +8167,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) return err; /* 1. Allocate space for next generation rules_gen_X[] */ - list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { int ret; ret = nf_tables_commit_audit_alloc(&adl, trans->ctx.table); @@ -7948,7 +8190,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) } /* step 2. Make rules_gen_X visible to packet path */ - list_for_each_entry(table, &net->nft.tables, list) { + list_for_each_entry(table, &nft_net->tables, list) { list_for_each_entry(chain, &table->chains, list) nf_tables_commit_chain(net, chain); } @@ -7957,12 +8199,13 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) * Bump generation counter, invalidate any dump in progress. * Cannot fail after this point. */ - while (++net->nft.base_seq == 0); + while (++nft_net->base_seq == 0) + ; /* step 3. Start new generation, rules_gen_X now in use. */ net->nft.gencursor = nft_gencursor_next(net); - list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) { + list_for_each_entry_safe(trans, next, &nft_net->commit_list, list) { nf_tables_commit_audit_collect(&adl, trans->ctx.table, trans->msg_type); switch (trans->msg_type) { @@ -8122,7 +8365,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_commit_notify(net, NETLINK_CB(skb).portid); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); - nf_tables_commit_audit_log(&adl, net->nft.base_seq); + nf_tables_commit_audit_log(&adl, nft_net->base_seq); nf_tables_commit_release(net); return 0; @@ -8130,17 +8373,18 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) static void nf_tables_module_autoload(struct net *net) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_module_request *req, *next; LIST_HEAD(module_list); - list_splice_init(&net->nft.module_list, &module_list); - mutex_unlock(&net->nft.commit_mutex); + list_splice_init(&nft_net->module_list, &module_list); + mutex_unlock(&nft_net->commit_mutex); list_for_each_entry_safe(req, next, &module_list, list) { request_module("%s", req->module); req->done = true; } - mutex_lock(&net->nft.commit_mutex); - list_splice(&module_list, &net->nft.module_list); + mutex_lock(&nft_net->commit_mutex); + list_splice(&module_list, &nft_net->module_list); } static void nf_tables_abort_release(struct nft_trans *trans) @@ -8177,6 +8421,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_trans *trans, *next; struct nft_trans_elem *te; @@ -8184,7 +8429,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nf_tables_validate(net) < 0) return -EAGAIN; - list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list, + list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list, list) { switch (trans->msg_type) { case NFT_MSG_NEWTABLE: @@ -8209,7 +8454,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) kfree(nft_trans_chain_name(trans)); nft_trans_destroy(trans); } else { - if (nft_chain_is_bound(trans->ctx.chain)) { + if (nft_trans_chain_bound(trans)) { nft_trans_destroy(trans); break; } @@ -8226,6 +8471,10 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nft_trans_destroy(trans); break; case NFT_MSG_NEWRULE: + if (nft_trans_rule_bound(trans)) { + nft_trans_destroy(trans); + break; + } trans->ctx.chain->use--; list_del_rcu(&nft_trans_rule(trans)->list); nft_rule_expr_deactivate(&trans->ctx, @@ -8249,6 +8498,9 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) case NFT_MSG_DELSET: trans->ctx.table->use++; nft_clear(trans->ctx.net, nft_trans_set(trans)); + if (nft_trans_set(trans)->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_activate(&trans->ctx, nft_trans_set(trans)); + nft_trans_destroy(trans); break; case NFT_MSG_NEWSETELEM: @@ -8263,7 +8515,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) case NFT_MSG_DELSETELEM: te = (struct nft_trans_elem *)trans->data; - nft_set_elem_activate(net, te->set, &te->elem); + nft_setelem_data_activate(net, te->set, &te->elem); te->set->ops->activate(net, te->set, &te->elem); te->set->ndeact--; @@ -8310,8 +8562,8 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) synchronize_rcu(); list_for_each_entry_safe_reverse(trans, next, - &net->nft.commit_list, list) { - list_del(&trans->list); + &nft_net->commit_list, list) { + nft_trans_list_del(trans); nf_tables_abort_release(trans); } @@ -8326,22 +8578,24 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) static int nf_tables_abort(struct net *net, struct sk_buff *skb, enum nfnl_abort_action action) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); int ret = __nf_tables_abort(net, action); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return ret; } static bool nf_tables_valid_genid(struct net *net, u32 genid) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); bool genid_ok; - mutex_lock(&net->nft.commit_mutex); + mutex_lock(&nft_net->commit_mutex); - genid_ok = genid == 0 || net->nft.base_seq == genid; + genid_ok = genid == 0 || nft_net->base_seq == genid; if (!genid_ok) - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); /* else, commit mutex has to be released by commit or abort function */ return genid_ok; @@ -8742,22 +8996,12 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, static void nft_verdict_uninit(const struct nft_data *data) { struct nft_chain *chain; - struct nft_rule *rule; switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: chain = data->verdict.chain; chain->use--; - - if (!nft_chain_is_bound(chain)) - break; - - chain->table->use--; - list_for_each_entry(rule, &chain->rules, list) - chain->use--; - - nft_chain_del(chain); break; } } @@ -8939,19 +9183,19 @@ EXPORT_SYMBOL_GPL(__nft_release_basechain); static void __nft_release_hooks(struct net *net) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_table *table; struct nft_chain *chain; - list_for_each_entry(table, &net->nft.tables, list) { + list_for_each_entry(table, &nft_net->tables, list) { list_for_each_entry(chain, &table->chains, list) nf_tables_unregister_hook(net, table, chain); } } -static void __nft_release_tables(struct net *net) +static void __nft_release_table(struct net *net, struct nft_table *table) { struct nft_flowtable *flowtable, *nf; - struct nft_table *table, *nt; struct nft_chain *chain, *nc; struct nft_object *obj, *ne; struct nft_rule *rule, *nr; @@ -8961,79 +9205,98 @@ static void __nft_release_tables(struct net *net) .family = NFPROTO_NETDEV, }; - list_for_each_entry_safe(table, nt, &net->nft.tables, list) { - ctx.family = table->family; - ctx.table = table; - list_for_each_entry(chain, &table->chains, list) { - ctx.chain = chain; - list_for_each_entry_safe(rule, nr, &chain->rules, list) { - list_del(&rule->list); - chain->use--; - nf_tables_rule_release(&ctx, rule); - } - } - list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) { - list_del(&flowtable->list); - table->use--; - nf_tables_flowtable_destroy(flowtable); - } - list_for_each_entry_safe(set, ns, &table->sets, list) { - list_del(&set->list); - table->use--; - nft_set_destroy(&ctx, set); - } - list_for_each_entry_safe(obj, ne, &table->objects, list) { - nft_obj_del(obj); - table->use--; - nft_obj_destroy(&ctx, obj); - } - list_for_each_entry_safe(chain, nc, &table->chains, list) { - ctx.chain = chain; - nft_chain_del(chain); - table->use--; - nf_tables_chain_destroy(&ctx); + ctx.family = table->family; + ctx.table = table; + list_for_each_entry(chain, &table->chains, list) { + ctx.chain = chain; + list_for_each_entry_safe(rule, nr, &chain->rules, list) { + list_del(&rule->list); + chain->use--; + nf_tables_rule_release(&ctx, rule); } - list_del(&table->list); - nf_tables_table_destroy(&ctx); } + list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) { + list_del(&flowtable->list); + table->use--; + nf_tables_flowtable_destroy(flowtable); + } + list_for_each_entry_safe(set, ns, &table->sets, list) { + list_del(&set->list); + table->use--; + if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT)) + nft_map_deactivate(&ctx, set); + + nft_set_destroy(&ctx, set); + } + list_for_each_entry_safe(obj, ne, &table->objects, list) { + nft_obj_del(obj); + table->use--; + nft_obj_destroy(&ctx, obj); + } + list_for_each_entry_safe(chain, nc, &table->chains, list) { + ctx.chain = chain; + nft_chain_del(chain); + table->use--; + nf_tables_chain_destroy(&ctx); + } + list_del(&table->list); + nf_tables_table_destroy(&ctx); +} + +static void __nft_release_tables(struct net *net) +{ + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + struct nft_table *table, *nt; + + list_for_each_entry_safe(table, nt, &nft_net->tables, list) + __nft_release_table(net, table); } static int __net_init nf_tables_init_net(struct net *net) { - INIT_LIST_HEAD(&net->nft.tables); - INIT_LIST_HEAD(&net->nft.commit_list); - INIT_LIST_HEAD(&net->nft.module_list); - INIT_LIST_HEAD(&net->nft.notify_list); - mutex_init(&net->nft.commit_mutex); - net->nft.base_seq = 1; - net->nft.validate_state = NFT_VALIDATE_SKIP; + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + + INIT_LIST_HEAD(&nft_net->tables); + INIT_LIST_HEAD(&nft_net->commit_list); + INIT_LIST_HEAD(&nft_net->binding_list); + INIT_LIST_HEAD(&nft_net->module_list); + INIT_LIST_HEAD(&nft_net->notify_list); + mutex_init(&nft_net->commit_mutex); + nft_net->base_seq = 1; + nft_net->validate_state = NFT_VALIDATE_SKIP; return 0; } static void __net_exit nf_tables_pre_exit_net(struct net *net) { - mutex_lock(&net->nft.commit_mutex); + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + + mutex_lock(&nft_net->commit_mutex); __nft_release_hooks(net); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); } static void __net_exit nf_tables_exit_net(struct net *net) { - mutex_lock(&net->nft.commit_mutex); - if (!list_empty(&net->nft.commit_list)) + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); + + mutex_lock(&nft_net->commit_mutex); + if (!list_empty(&nft_net->commit_list)) __nf_tables_abort(net, NFNL_ABORT_NONE); __nft_release_tables(net); - mutex_unlock(&net->nft.commit_mutex); - WARN_ON_ONCE(!list_empty(&net->nft.tables)); - WARN_ON_ONCE(!list_empty(&net->nft.module_list)); - WARN_ON_ONCE(!list_empty(&net->nft.notify_list)); + mutex_unlock(&nft_net->commit_mutex); + WARN_ON_ONCE(!list_empty(&nft_net->tables)); + WARN_ON_ONCE(!list_empty(&nft_net->module_list)); + WARN_ON_ONCE(!list_empty(&nft_net->notify_list)); } static struct pernet_operations nf_tables_net_ops = { .init = nf_tables_init_net, .pre_exit = nf_tables_pre_exit_net, .exit = nf_tables_exit_net, + .id = &nf_tables_net_id, + .size = sizeof(struct nftables_pernet), }; static int __init nf_tables_module_init(void) diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 4e99b1731b3f9c2488f0293933fa12f88b49cd94..5cfbb29d8a34a684c68a3bbc0f35320ff6f3b31d 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -7,6 +7,8 @@ #include #include +extern unsigned int nf_tables_net_id; + static struct nft_flow_rule *nft_flow_rule_alloc(int num_actions) { struct nft_flow_rule *flow; @@ -371,16 +373,18 @@ static void nft_indr_block_cleanup(struct flow_block_cb *block_cb) struct nft_base_chain *basechain = block_cb->indr.data; struct net_device *dev = block_cb->indr.dev; struct netlink_ext_ack extack = {}; + struct nftables_pernet *nft_net; struct net *net = dev_net(dev); struct flow_block_offload bo; nft_flow_block_offload_init(&bo, dev_net(dev), FLOW_BLOCK_UNBIND, basechain, &extack); - mutex_lock(&net->nft.commit_mutex); + nft_net = net_generic(net, nf_tables_net_id); + mutex_lock(&nft_net->commit_mutex); list_del(&block_cb->driver_list); list_move(&block_cb->list, &bo.cb_list); nft_flow_offload_unbind(&bo, basechain); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); } static int nft_indr_block_offload_cmd(struct nft_base_chain *basechain, @@ -476,9 +480,10 @@ static int nft_flow_offload_chain(struct nft_chain *chain, u8 *ppolicy, static void nft_flow_rule_offload_abort(struct net *net, struct nft_trans *trans) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); int err = 0; - list_for_each_entry_continue_reverse(trans, &net->nft.commit_list, list) { + list_for_each_entry_continue_reverse(trans, &nft_net->commit_list, list) { if (trans->ctx.family != NFPROTO_NETDEV) continue; @@ -524,11 +529,12 @@ static void nft_flow_rule_offload_abort(struct net *net, int nft_flow_rule_offload_commit(struct net *net) { + struct nftables_pernet *nft_net = net_generic(net, nf_tables_net_id); struct nft_trans *trans; int err = 0; u8 policy; - list_for_each_entry(trans, &net->nft.commit_list, list) { + list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->ctx.family != NFPROTO_NETDEV) continue; @@ -580,7 +586,7 @@ int nft_flow_rule_offload_commit(struct net *net) } } - list_for_each_entry(trans, &net->nft.commit_list, list) { + list_for_each_entry(trans, &nft_net->commit_list, list) { if (trans->ctx.family != NFPROTO_NETDEV) continue; @@ -600,15 +606,15 @@ int nft_flow_rule_offload_commit(struct net *net) return err; } -static struct nft_chain *__nft_offload_get_chain(struct net_device *dev) +static struct nft_chain *__nft_offload_get_chain(const struct nftables_pernet *nft_net, + struct net_device *dev) { struct nft_base_chain *basechain; - struct net *net = dev_net(dev); struct nft_hook *hook, *found; const struct nft_table *table; struct nft_chain *chain; - list_for_each_entry(table, &net->nft.tables, list) { + list_for_each_entry(table, &nft_net->tables, list) { if (table->family != NFPROTO_NETDEV) continue; @@ -640,19 +646,21 @@ static int nft_offload_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct nftables_pernet *nft_net; struct net *net = dev_net(dev); struct nft_chain *chain; if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; - mutex_lock(&net->nft.commit_mutex); - chain = __nft_offload_get_chain(dev); + nft_net = net_generic(net, nf_tables_net_id); + mutex_lock(&nft_net->commit_mutex); + chain = __nft_offload_get_chain(nft_net, dev); if (chain) nft_flow_block_chain(nft_base_chain(chain), dev, FLOW_BLOCK_UNBIND); - mutex_unlock(&net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index ff8528ad3dc6364c76f71a8fba56a1bfe278f19c..7a9aa57b195bf798ecb46e3f07e1050846464ea6 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -2,6 +2,7 @@ #include #include #include +#include #include #include #include @@ -10,6 +11,8 @@ #include #include +extern unsigned int nf_tables_net_id; + #ifdef CONFIG_NF_TABLES_IPV4 static unsigned int nft_do_chain_ipv4(void *priv, struct sk_buff *skb, @@ -355,6 +358,7 @@ static int nf_tables_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct nftables_pernet *nft_net; struct nft_table *table; struct nft_chain *chain, *nr; struct nft_ctx ctx = { @@ -365,8 +369,9 @@ static int nf_tables_netdev_event(struct notifier_block *this, event != NETDEV_CHANGENAME) return NOTIFY_DONE; - mutex_lock(&ctx.net->nft.commit_mutex); - list_for_each_entry(table, &ctx.net->nft.tables, list) { + nft_net = net_generic(ctx.net, nf_tables_net_id); + mutex_lock(&nft_net->commit_mutex); + list_for_each_entry(table, &nft_net->tables, list) { if (table->family != NFPROTO_NETDEV) continue; @@ -380,7 +385,7 @@ static int nf_tables_netdev_event(struct notifier_block *this, nft_netdev_event(event, dev, &ctx); } } - mutex_unlock(&ctx.net->nft.commit_mutex); + mutex_unlock(&nft_net->commit_mutex); return NOTIFY_DONE; } diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 038588d4d80e112f01df1513c38b91f4a852c582..8d47782b778f12a3cba6844511a1ab0f1096c735 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -11,6 +11,9 @@ #include #include #include +#include + +extern unsigned int nf_tables_net_id; struct nft_dynset { struct nft_set *set; @@ -106,13 +109,14 @@ static int nft_dynset_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); struct nft_dynset *priv = nft_expr_priv(expr); u8 genmask = nft_genmask_next(ctx->net); struct nft_set *set; u64 timeout; int err; - lockdep_assert_held(&ctx->net->nft.commit_mutex); + lockdep_assert_held(&nft_net->commit_mutex); if (tb[NFTA_DYNSET_SET_NAME] == NULL || tb[NFTA_DYNSET_OP] == NULL || diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index fcdbc5ed3f3679835c0aa734438d22fd10d03006..6b0efab4fad09fd53210b41f4cc7fe64c876065f 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -76,11 +76,9 @@ static int nft_immediate_init(const struct nft_ctx *ctx, switch (priv->data.verdict.code) { case NFT_JUMP: case NFT_GOTO: - if (nft_chain_is_bound(chain)) { - err = -EBUSY; - goto err1; - } - chain->bound = true; + err = nf_tables_bind_chain(ctx, chain); + if (err < 0) + return err; break; default: break; @@ -98,6 +96,31 @@ static void nft_immediate_activate(const struct nft_ctx *ctx, const struct nft_expr *expr) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); + const struct nft_data *data = &priv->data; + struct nft_ctx chain_ctx; + struct nft_chain *chain; + struct nft_rule *rule; + + if (priv->dreg == NFT_REG_VERDICT) { + switch (data->verdict.code) { + case NFT_JUMP: + case NFT_GOTO: + chain = data->verdict.chain; + if (!nft_chain_binding(chain)) + break; + + chain_ctx = *ctx; + chain_ctx.chain = chain; + + list_for_each_entry(rule, &chain->rules, list) + nft_rule_expr_activate(&chain_ctx, rule); + + nft_clear(ctx->net, chain); + break; + default: + break; + } + } return nft_data_hold(&priv->data, nft_dreg_to_type(priv->dreg)); } @@ -107,6 +130,43 @@ static void nft_immediate_deactivate(const struct nft_ctx *ctx, enum nft_trans_phase phase) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); + const struct nft_data *data = &priv->data; + struct nft_ctx chain_ctx; + struct nft_chain *chain; + struct nft_rule *rule; + + if (priv->dreg == NFT_REG_VERDICT) { + switch (data->verdict.code) { + case NFT_JUMP: + case NFT_GOTO: + chain = data->verdict.chain; + if (!nft_chain_binding(chain)) + break; + + chain_ctx = *ctx; + chain_ctx.chain = chain; + + list_for_each_entry(rule, &chain->rules, list) + nft_rule_expr_deactivate(&chain_ctx, rule, phase); + + switch (phase) { + case NFT_TRANS_PREPARE_ERROR: + nf_tables_unbind_chain(ctx, chain); + fallthrough; + case NFT_TRANS_PREPARE: + nft_deactivate_next(ctx->net, chain); + break; + default: + nft_chain_del(chain); + chain->bound = false; + chain->table->use--; + break; + } + break; + default: + break; + } + } if (phase == NFT_TRANS_COMMIT) return; @@ -131,15 +191,27 @@ static void nft_immediate_destroy(const struct nft_ctx *ctx, case NFT_GOTO: chain = data->verdict.chain; - if (!nft_chain_is_bound(chain)) + if (!nft_chain_binding(chain)) + break; + + /* Rule construction failed, but chain is already bound: + * let the transaction records release this chain and its rules. + */ + if (chain->bound) { + chain->use--; break; + } + /* Rule has been deleted, release chain and its rules. */ chain_ctx = *ctx; chain_ctx.chain = chain; - list_for_each_entry_safe(rule, n, &chain->rules, list) - nf_tables_rule_release(&chain_ctx, rule); - + chain->use--; + list_for_each_entry_safe(rule, n, &chain->rules, list) { + chain->use--; + list_del(&rule->list); + nf_tables_rule_destroy(&chain_ctx, rule); + } nf_tables_chain_destroy(&chain_ctx); break; default: diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 2a81ea4218193aac5ae82a38d770572509c6d14e..3c63f8acebd8a944a9714746ed73357b5191227a 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -270,13 +270,14 @@ static int nft_bitmap_init(const struct nft_set *set, return 0; } -static void nft_bitmap_destroy(const struct nft_set *set) +static void nft_bitmap_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_bitmap *priv = nft_set_priv(set); struct nft_bitmap_elem *be, *n; list_for_each_entry_safe(be, n, &priv->list, head) - nft_set_elem_destroy(set, be, true); + nf_tables_set_elem_destroy(ctx, set, be); } static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features, diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index a5cfb321ae23ab9cf1cf93b246d73270a789e77d..51d3e6f0934a9361c8ff32a4a29a4e1f4d9ca014 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -380,19 +380,31 @@ static int nft_rhash_init(const struct nft_set *set, return 0; } +struct nft_rhash_ctx { + const struct nft_ctx ctx; + const struct nft_set *set; +}; + static void nft_rhash_elem_destroy(void *ptr, void *arg) { - nft_set_elem_destroy(arg, ptr, true); + struct nft_rhash_ctx *rhash_ctx = arg; + + nf_tables_set_elem_destroy(&rhash_ctx->ctx, rhash_ctx->set, ptr); } -static void nft_rhash_destroy(const struct nft_set *set) +static void nft_rhash_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_rhash *priv = nft_set_priv(set); + struct nft_rhash_ctx rhash_ctx = { + .ctx = *ctx, + .set = set, + }; cancel_delayed_work_sync(&priv->gc_work); rcu_barrier(); rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy, - (void *)set); + (void *)&rhash_ctx); } /* Number of buckets is stored in u32, so cap our result to 1U<<31 */ @@ -621,7 +633,8 @@ static int nft_hash_init(const struct nft_set *set, return 0; } -static void nft_hash_destroy(const struct nft_set *set) +static void nft_hash_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_hash *priv = nft_set_priv(set); struct nft_hash_elem *he; @@ -631,7 +644,7 @@ static void nft_hash_destroy(const struct nft_set *set) for (i = 0; i < priv->buckets; i++) { hlist_for_each_entry_safe(he, next, &priv->table[i], node) { hlist_del_rcu(&he->node); - nft_set_elem_destroy(set, he, true); + nf_tables_set_elem_destroy(ctx, set, he); } } } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index edb9458f53c79d3e165a5282f2877adda0f37783..ff4a76a77f0bc8aeae29568757207f2390748cf2 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -2131,10 +2131,12 @@ static int nft_pipapo_init(const struct nft_set *set, /** * nft_set_pipapo_match_destroy() - Destroy elements from key mapping array + * @ctx: context * @set: nftables API set representation * @m: matching data pointing to key mapping array */ -static void nft_set_pipapo_match_destroy(const struct nft_set *set, +static void nft_set_pipapo_match_destroy(const struct nft_ctx *ctx, + const struct nft_set *set, struct nft_pipapo_match *m) { struct nft_pipapo_field *f; @@ -2151,15 +2153,17 @@ static void nft_set_pipapo_match_destroy(const struct nft_set *set, e = f->mt[r].e; - nft_set_elem_destroy(set, e, true); + nf_tables_set_elem_destroy(ctx, set, e); } } /** * nft_pipapo_destroy() - Free private data for set and all committed elements + * @ctx: context * @set: nftables API set representation */ -static void nft_pipapo_destroy(const struct nft_set *set) +static void nft_pipapo_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m; @@ -2169,7 +2173,7 @@ static void nft_pipapo_destroy(const struct nft_set *set) if (m) { rcu_barrier(); - nft_set_pipapo_match_destroy(set, m); + nft_set_pipapo_match_destroy(ctx, set, m); #ifdef NFT_PIPAPO_ALIGN free_percpu(m->scratch_aligned); @@ -2186,7 +2190,7 @@ static void nft_pipapo_destroy(const struct nft_set *set) m = priv->clone; if (priv->dirty) - nft_set_pipapo_match_destroy(set, m); + nft_set_pipapo_match_destroy(ctx, set, m); #ifdef NFT_PIPAPO_ALIGN free_percpu(priv->clone->scratch_aligned); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 1ffb24f4c74ca2c4aa02d311242692e3da55a5f0..172b994790a06c870d032b2244a229728c95ebff 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -657,7 +657,8 @@ static int nft_rbtree_init(const struct nft_set *set, return 0; } -static void nft_rbtree_destroy(const struct nft_set *set) +static void nft_rbtree_destroy(const struct nft_ctx *ctx, + const struct nft_set *set) { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe; @@ -668,7 +669,7 @@ static void nft_rbtree_destroy(const struct nft_set *set) while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); - nft_set_elem_destroy(set, rbe, true); + nf_tables_set_elem_destroy(ctx, set, rbe); } } diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index caf1a05bfbde4e5999c2c0eb7ea0da4fcb8c2c92..dcf21d99f132c550a8b05c382781f1ddd5c20887 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -778,6 +778,16 @@ static int fl_set_key_port_range(struct nlattr **tb, struct fl_flow_key *key, TCA_FLOWER_KEY_PORT_SRC_MAX, &mask->tp_range.tp_max.src, TCA_FLOWER_UNSPEC, sizeof(key->tp_range.tp_max.src)); + if (mask->tp_range.tp_min.dst != mask->tp_range.tp_max.dst) { + NL_SET_ERR_MSG(extack, + "Both min and max destination ports must be specified"); + return -EINVAL; + } + if (mask->tp_range.tp_min.src != mask->tp_range.tp_max.src) { + NL_SET_ERR_MSG(extack, + "Both min and max source ports must be specified"); + return -EINVAL; + } if (mask->tp_range.tp_min.dst && mask->tp_range.tp_max.dst && ntohs(key->tp_range.tp_max.dst) <= ntohs(key->tp_range.tp_min.dst)) { diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 46393f52e56182ccf504d66e373bd2612cb12b59..10688d8ffd109c3afe38b8446fd219a15a07a428 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -113,6 +113,7 @@ #define QFQ_MTU_SHIFT 16 /* to support TSO/GSO */ #define QFQ_MIN_LMAX 512 /* see qfq_slot_insert */ +#define QFQ_MAX_LMAX (1UL << QFQ_MTU_SHIFT) #define QFQ_MAX_AGG_CLASSES 8 /* max num classes per aggregate allowed */ @@ -214,9 +215,14 @@ static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid) return container_of(clc, struct qfq_class, common); } +static struct netlink_range_validation lmax_range = { + .min = QFQ_MIN_LMAX, + .max = QFQ_MAX_LMAX, +}; + static const struct nla_policy qfq_policy[TCA_QFQ_MAX + 1] = { - [TCA_QFQ_WEIGHT] = { .type = NLA_U32 }, - [TCA_QFQ_LMAX] = { .type = NLA_U32 }, + [TCA_QFQ_WEIGHT] = NLA_POLICY_RANGE(NLA_U32, 1, QFQ_MAX_WEIGHT), + [TCA_QFQ_LMAX] = NLA_POLICY_FULL_RANGE(NLA_U32, &lmax_range), }; /* @@ -413,17 +419,13 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, } err = nla_parse_nested_deprecated(tb, TCA_QFQ_MAX, tca[TCA_OPTIONS], - qfq_policy, NULL); + qfq_policy, extack); if (err < 0) return err; - if (tb[TCA_QFQ_WEIGHT]) { + if (tb[TCA_QFQ_WEIGHT]) weight = nla_get_u32(tb[TCA_QFQ_WEIGHT]); - if (!weight || weight > (1UL << QFQ_MAX_WSHIFT)) { - pr_notice("qfq: invalid weight %u\n", weight); - return -EINVAL; - } - } else + else weight = 1; if (tb[TCA_QFQ_LMAX]) @@ -431,11 +433,6 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, else lmax = psched_mtu(qdisc_dev(sch)); - if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) { - pr_notice("qfq: invalid max length %u\n", lmax); - return -EINVAL; - } - inv_w = ONE_FP / weight; weight = ONE_FP / inv_w; diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 8a9461aa0878a0b6ea74fc9ec48f370846e39397..93e44410f170e9451b4a327576b03f74d87439a6 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -502,10 +502,32 @@ n2 bash -c 'printf 0 > /proc/sys/net/ipv4/conf/all/rp_filter' n1 ping -W 1 -c 1 192.168.241.2 [[ $(n2 wg show wg0 endpoints) == "$pub1 10.0.0.3:1" ]] -ip1 link del veth1 -ip1 link del veth3 -ip1 link del wg0 -ip2 link del wg0 +ip1 link del dev veth3 +ip1 link del dev wg0 +ip2 link del dev wg0 + +# Make sure persistent keep alives are sent when an adapter comes up +ip1 link add dev wg0 type wireguard +n1 wg set wg0 private-key <(echo "$key1") peer "$pub2" endpoint 10.0.0.1:1 persistent-keepalive 1 +read _ _ tx_bytes < <(n1 wg show wg0 transfer) +[[ $tx_bytes -eq 0 ]] +ip1 link set dev wg0 up +read _ _ tx_bytes < <(n1 wg show wg0 transfer) +[[ $tx_bytes -gt 0 ]] +ip1 link del dev wg0 +# This should also happen even if the private key is set later +ip1 link add dev wg0 type wireguard +n1 wg set wg0 peer "$pub2" endpoint 10.0.0.1:1 persistent-keepalive 1 +read _ _ tx_bytes < <(n1 wg show wg0 transfer) +[[ $tx_bytes -eq 0 ]] +ip1 link set dev wg0 up +read _ _ tx_bytes < <(n1 wg show wg0 transfer) +[[ $tx_bytes -eq 0 ]] +n1 wg set wg0 private-key <(echo "$key1") +read _ _ tx_bytes < <(n1 wg show wg0 transfer) +[[ $tx_bytes -gt 0 ]] +ip1 link del dev veth1 +ip1 link del dev wg0 # We test that Netlink/IPC is working properly by doing things that usually cause split responses ip0 link add dev wg0 type wireguard