diff options
142 files changed, 2185 insertions, 1218 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 500cfa776225..b600df82669d 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1921,6 +1921,28 @@ Format: <bus_id>,<clkrate> + i2c_touchscreen_props= [HW,ACPI,X86] + Set device-properties for ACPI-enumerated I2C-attached + touchscreen, to e.g. fix coordinates of upside-down + mounted touchscreens. If you need this option please + submit a drivers/platform/x86/touchscreen_dmi.c patch + adding a DMI quirk for this. + + Format: + <ACPI_HW_ID>:<prop_name>=<val>[:prop_name=val][:...] + Where <val> is one of: + Omit "=<val>" entirely Set a boolean device-property + Unsigned number Set a u32 device-property + Anything else Set a string device-property + + Examples (split over multiple lines): + i2c_touchscreen_props=GDIX1001:touchscreen-inverted-x: + touchscreen-inverted-y + + i2c_touchscreen_props=MSSL1680:touchscreen-size-x=1920: + touchscreen-size-y=1080:touchscreen-inverted-y: + firmware-name=gsl1680-vendor-model.fw:silead,home-button + i8042.debug [HW] Toggle i8042 debug mode i8042.unmask_kbd_data [HW] Enable printing of interrupt data from the KBD port diff --git a/Documentation/arch/riscv/uabi.rst b/Documentation/arch/riscv/uabi.rst index 54d199dce78b..2b420bab0527 100644 --- a/Documentation/arch/riscv/uabi.rst +++ b/Documentation/arch/riscv/uabi.rst @@ -65,4 +65,6 @@ the extension, or may have deliberately removed it from the listing. Misaligned accesses ------------------- -Misaligned accesses are supported in userspace, but they may perform poorly. +Misaligned scalar accesses are supported in userspace, but they may perform +poorly. Misaligned vector accesses are only supported if the Zicclsm extension +is supported. diff --git a/Documentation/devicetree/bindings/net/pse-pd/microchip,pd692x0.yaml b/Documentation/devicetree/bindings/net/pse-pd/microchip,pd692x0.yaml index 828439398fdf..fd4244fceced 100644 --- a/Documentation/devicetree/bindings/net/pse-pd/microchip,pd692x0.yaml +++ b/Documentation/devicetree/bindings/net/pse-pd/microchip,pd692x0.yaml @@ -24,6 +24,7 @@ properties: managers: type: object + additionalProperties: false description: List of the PD69208T4/PD69204T4/PD69208M PSE managers. Each manager have 4 or 8 physical ports according to the chip version. No need to @@ -47,8 +48,9 @@ properties: - "#size-cells" patternProperties: - "^manager@0[0-9a-b]$": + "^manager@[0-9a-b]$": type: object + additionalProperties: false description: PD69208T4/PD69204T4/PD69208M PSE manager exposing 4 or 8 physical ports. @@ -69,9 +71,14 @@ properties: patternProperties: '^port@[0-7]$': type: object + additionalProperties: false + + properties: + reg: + maxItems: 1 + required: - reg - additionalProperties: false required: - reg diff --git a/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml b/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml index 4147adb11e10..6992d56832bf 100644 --- a/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml +++ b/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml @@ -29,13 +29,31 @@ properties: of the ports conversion matrix that establishes relationship between the logical ports and the physical channels. type: object + additionalProperties: false + + properties: + "#address-cells": + const: 1 + + "#size-cells": + const: 0 patternProperties: '^channel@[0-7]$': type: object + additionalProperties: false + + properties: + reg: + maxItems: 1 + required: - reg + required: + - "#address-cells" + - "#size-cells" + unevaluatedProperties: false required: diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 11a32373365a..959755be4d7f 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -350,6 +350,10 @@ attribute-sets: buffer space, host descriptors etc. type: uint - + name: rx-csum-complete + doc: Number of packets that were marked as CHECKSUM_COMPLETE. + type: uint + - name: rx-csum-unnecessary doc: Number of packets that were marked as CHECKSUM_UNNECESSARY. type: uint diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst index fd96e4a3cef9..5e1fcfad1c4c 100644 --- a/Documentation/process/maintainer-netdev.rst +++ b/Documentation/process/maintainer-netdev.rst @@ -227,7 +227,7 @@ preferably including links to previous postings, for example:: The amount of mooing will depend on packet rate so should match the diurnal cycle quite well. - Signed-of-by: Joe Defarmer <joe@barn.org> + Signed-off-by: Joe Defarmer <joe@barn.org> --- v3: - add a note about time-of-day mooing fluctuation to the commit message diff --git a/MAINTAINERS b/MAINTAINERS index a6a011792167..8754ac2c259d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3854,6 +3854,7 @@ BPF JIT for ARM64 M: Daniel Borkmann <daniel@iogearbox.net> M: Alexei Starovoitov <ast@kernel.org> M: Puranjay Mohan <puranjay@kernel.org> +R: Xu Kuohai <xukuohai@huaweicloud.com> L: bpf@vger.kernel.org S: Supported F: arch/arm64/net/ @@ -21315,7 +21316,7 @@ F: arch/riscv/boot/dts/starfive/ STARFIVE DWMAC GLUE LAYER M: Emil Renner Berthing <kernel@esmil.dk> -M: Samin Guo <samin.guo@starfivetech.com> +M: Minda Chen <minda.chen@starfivetech.com> S: Maintained F: Documentation/devicetree/bindings/net/starfive,jh7110-dwmac.yaml F: drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c diff --git a/arch/arc/net/bpf_jit.h b/arch/arc/net/bpf_jit.h index ec44873c42d1..495f3023e4c1 100644 --- a/arch/arc/net/bpf_jit.h +++ b/arch/arc/net/bpf_jit.h @@ -39,7 +39,7 @@ /************** Functions that the back-end must provide **************/ /* Extension for 32-bit operations. */ -inline u8 zext(u8 *buf, u8 rd); +u8 zext(u8 *buf, u8 rd); /***** Moves *****/ u8 mov_r32(u8 *buf, u8 rd, u8 rs, u8 sign_ext); u8 mov_r32_i32(u8 *buf, u8 reg, s32 imm); diff --git a/arch/arc/net/bpf_jit_arcv2.c b/arch/arc/net/bpf_jit_arcv2.c index 31bfb6e9ce00..4458e409ca0a 100644 --- a/arch/arc/net/bpf_jit_arcv2.c +++ b/arch/arc/net/bpf_jit_arcv2.c @@ -62,7 +62,7 @@ enum { * If/when we decide to add ARCv2 instructions that do use register pairs, * the mapping, hopefully, doesn't need to be revisited. */ -const u8 bpf2arc[][2] = { +static const u8 bpf2arc[][2] = { /* Return value from in-kernel function, and exit value from eBPF */ [BPF_REG_0] = {ARC_R_8, ARC_R_9}, /* Arguments from eBPF program to in-kernel function */ @@ -1302,7 +1302,7 @@ static u8 arc_b(u8 *buf, s32 offset) /************* Packers (Deal with BPF_REGs) **************/ -inline u8 zext(u8 *buf, u8 rd) +u8 zext(u8 *buf, u8 rd) { if (rd != BPF_REG_FP) return arc_movi_r(buf, REG_HI(rd), 0); @@ -2235,6 +2235,7 @@ u8 gen_swap(u8 *buf, u8 rd, u8 size, u8 endian, bool force, bool do_zext) break; default: /* The caller must have handled this. */ + break; } } else { /* @@ -2253,6 +2254,7 @@ u8 gen_swap(u8 *buf, u8 rd, u8 size, u8 endian, bool force, bool do_zext) break; default: /* The caller must have handled this. */ + break; } } @@ -2517,7 +2519,7 @@ u8 arc_epilogue(u8 *buf, u32 usage, u16 frame_size) #define JCC64_NR_OF_JMPS 3 /* Number of jumps in jcc64 template. */ #define JCC64_INSNS_TO_END 3 /* Number of insn. inclusive the 2nd jmp to end. */ #define JCC64_SKIP_JMP 1 /* Index of the "skip" jump to "end". */ -const struct { +static const struct { /* * "jit_off" is common between all "jmp[]" and is coupled with * "cond" of each "jmp[]" instance. e.g.: @@ -2883,7 +2885,7 @@ u8 gen_jmp_64(u8 *buf, u8 rd, u8 rs, u8 cond, u32 curr_off, u32 targ_off) * The "ARC_CC_SET" becomes "CC_unequal" because of the "tst" * instruction that precedes the conditional branch. */ -const u8 arcv2_32_jmps[ARC_CC_LAST] = { +static const u8 arcv2_32_jmps[ARC_CC_LAST] = { [ARC_CC_UGT] = CC_great_u, [ARC_CC_UGE] = CC_great_eq_u, [ARC_CC_ULT] = CC_less_u, diff --git a/arch/arc/net/bpf_jit_core.c b/arch/arc/net/bpf_jit_core.c index 6f6b4ffccf2c..e3628922c24a 100644 --- a/arch/arc/net/bpf_jit_core.c +++ b/arch/arc/net/bpf_jit_core.c @@ -159,7 +159,7 @@ static void jit_dump(const struct jit_context *ctx) /* Initialise the context so there's no garbage. */ static int jit_ctx_init(struct jit_context *ctx, struct bpf_prog *prog) { - memset(ctx, 0, sizeof(ctx)); + memset(ctx, 0, sizeof(*ctx)); ctx->orig_prog = prog; @@ -167,7 +167,7 @@ static int jit_ctx_init(struct jit_context *ctx, struct bpf_prog *prog) ctx->prog = bpf_jit_blind_constants(prog); if (IS_ERR(ctx->prog)) return PTR_ERR(ctx->prog); - ctx->blinded = (ctx->prog == ctx->orig_prog ? false : true); + ctx->blinded = (ctx->prog != ctx->orig_prog); /* If the verifier doesn't zero-extend, then we have to do it. */ ctx->do_zext = !ctx->prog->aux->verifier_zext; @@ -1182,12 +1182,12 @@ static int jit_prepare(struct jit_context *ctx) } /* - * All the "handle_*()" functions have been called before by the - * "jit_prepare()". If there was an error, we would know by now. - * Therefore, no extra error checking at this point, other than - * a sanity check at the end that expects the calculated length - * (jit.len) to be equal to the length of generated instructions - * (jit.index). + * jit_compile() is the real compilation phase. jit_prepare() is + * invoked before jit_compile() as a dry-run to make sure everything + * will go OK and allocate the necessary memory. + * + * In the end, jit_compile() checks if it has produced the same number + * of instructions as jit_prepare() would. */ static int jit_compile(struct jit_context *ctx) { @@ -1407,9 +1407,9 @@ static struct bpf_prog *do_extra_pass(struct bpf_prog *prog) /* * This function may be invoked twice for the same stream of BPF - * instructions. The "extra pass" happens, when there are "call"s - * involved that their addresses are not known during the first - * invocation. + * instructions. The "extra pass" happens, when there are + * (re)locations involved that their addresses are not known + * during the first run. */ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) { diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index b94176e25be1..0525ee2d63c7 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -106,7 +106,7 @@ config RISCV select HAS_IOPORT if MMU select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_HUGE_VMALLOC if HAVE_ARCH_HUGE_VMAP - select HAVE_ARCH_HUGE_VMAP if MMU && 64BIT && !XIP_KERNEL + select HAVE_ARCH_HUGE_VMAP if MMU && 64BIT select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL select HAVE_ARCH_KASAN if MMU && 64BIT diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h index ddb002ed89de..808b4c78462e 100644 --- a/arch/riscv/include/asm/cmpxchg.h +++ b/arch/riscv/include/asm/cmpxchg.h @@ -10,7 +10,7 @@ #include <asm/fence.h> -#define __arch_xchg_masked(prepend, append, r, p, n) \ +#define __arch_xchg_masked(sc_sfx, prepend, append, r, p, n) \ ({ \ u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3); \ ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE; \ @@ -25,7 +25,7 @@ "0: lr.w %0, %2\n" \ " and %1, %0, %z4\n" \ " or %1, %1, %z3\n" \ - " sc.w %1, %1, %2\n" \ + " sc.w" sc_sfx " %1, %1, %2\n" \ " bnez %1, 0b\n" \ append \ : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b)) \ @@ -46,7 +46,8 @@ : "memory"); \ }) -#define _arch_xchg(ptr, new, sfx, prepend, append) \ +#define _arch_xchg(ptr, new, sc_sfx, swap_sfx, prepend, \ + sc_append, swap_append) \ ({ \ __typeof__(ptr) __ptr = (ptr); \ __typeof__(*(__ptr)) __new = (new); \ @@ -55,15 +56,15 @@ switch (sizeof(*__ptr)) { \ case 1: \ case 2: \ - __arch_xchg_masked(prepend, append, \ + __arch_xchg_masked(sc_sfx, prepend, sc_append, \ __ret, __ptr, __new); \ break; \ case 4: \ - __arch_xchg(".w" sfx, prepend, append, \ + __arch_xchg(".w" swap_sfx, prepend, swap_append, \ __ret, __ptr, __new); \ break; \ case 8: \ - __arch_xchg(".d" sfx, prepend, append, \ + __arch_xchg(".d" swap_sfx, prepend, swap_append, \ __ret, __ptr, __new); \ break; \ default: \ @@ -73,16 +74,17 @@ }) #define arch_xchg_relaxed(ptr, x) \ - _arch_xchg(ptr, x, "", "", "") + _arch_xchg(ptr, x, "", "", "", "", "") #define arch_xchg_acquire(ptr, x) \ - _arch_xchg(ptr, x, "", "", RISCV_ACQUIRE_BARRIER) + _arch_xchg(ptr, x, "", "", "", \ + RISCV_ACQUIRE_BARRIER, RISCV_ACQUIRE_BARRIER) #define arch_xchg_release(ptr, x) \ - _arch_xchg(ptr, x, "", RISCV_RELEASE_BARRIER, "") + _arch_xchg(ptr, x, "", "", RISCV_RELEASE_BARRIER, "", "") #define arch_xchg(ptr, x) \ - _arch_xchg(ptr, x, ".aqrl", "", "") + _arch_xchg(ptr, x, ".rl", ".aqrl", "", RISCV_FULL_BARRIER, "") #define xchg32(ptr, x) \ ({ \ diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c index 1cc7df740edd..e6fbaaf54956 100644 --- a/arch/riscv/kernel/cpu_ops_sbi.c +++ b/arch/riscv/kernel/cpu_ops_sbi.c @@ -72,7 +72,7 @@ static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle) /* Make sure tidle is updated */ smp_mb(); bdata->task_ptr = tidle; - bdata->stack_ptr = task_stack_page(tidle) + THREAD_SIZE; + bdata->stack_ptr = task_pt_regs(tidle); /* Make sure boot data is updated */ smp_mb(); hsm_data = __pa(bdata); diff --git a/arch/riscv/kernel/cpu_ops_spinwait.c b/arch/riscv/kernel/cpu_ops_spinwait.c index 613872b0a21a..24869eb88908 100644 --- a/arch/riscv/kernel/cpu_ops_spinwait.c +++ b/arch/riscv/kernel/cpu_ops_spinwait.c @@ -34,8 +34,7 @@ static void cpu_update_secondary_bootdata(unsigned int cpuid, /* Make sure tidle is updated */ smp_mb(); - WRITE_ONCE(__cpu_spinwait_stack_pointer[hartid], - task_stack_page(tidle) + THREAD_SIZE); + WRITE_ONCE(__cpu_spinwait_stack_pointer[hartid], task_pt_regs(tidle)); WRITE_ONCE(__cpu_spinwait_task_pointer[hartid], tidle); } diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c index f5c71a617a99..4084df65c9fa 100644 --- a/drivers/char/hw_random/core.c +++ b/drivers/char/hw_random/core.c @@ -64,19 +64,6 @@ static size_t rng_buffer_size(void) return RNG_BUFFER_SIZE; } -static void add_early_randomness(struct hwrng *rng) -{ - int bytes_read; - - mutex_lock(&reading_mutex); - bytes_read = rng_get_data(rng, rng_fillbuf, 32, 0); - mutex_unlock(&reading_mutex); - if (bytes_read > 0) { - size_t entropy = bytes_read * 8 * rng->quality / 1024; - add_hwgenerator_randomness(rng_fillbuf, bytes_read, entropy, false); - } -} - static inline void cleanup_rng(struct kref *kref) { struct hwrng *rng = container_of(kref, struct hwrng, ref); @@ -340,13 +327,12 @@ static ssize_t rng_current_store(struct device *dev, const char *buf, size_t len) { int err; - struct hwrng *rng, *old_rng, *new_rng; + struct hwrng *rng, *new_rng; err = mutex_lock_interruptible(&rng_mutex); if (err) return -ERESTARTSYS; - old_rng = current_rng; if (sysfs_streq(buf, "")) { err = enable_best_rng(); } else { @@ -362,11 +348,8 @@ static ssize_t rng_current_store(struct device *dev, new_rng = get_current_rng_nolock(); mutex_unlock(&rng_mutex); - if (new_rng) { - if (new_rng != old_rng) - add_early_randomness(new_rng); + if (new_rng) put_rng(new_rng); - } return err ? : len; } @@ -544,7 +527,6 @@ int hwrng_register(struct hwrng *rng) { int err = -EINVAL; struct hwrng *tmp; - bool is_new_current = false; if (!rng->name || (!rng->data_read && !rng->read)) goto out; @@ -573,25 +555,8 @@ int hwrng_register(struct hwrng *rng) err = set_current_rng(rng); if (err) goto out_unlock; - /* to use current_rng in add_early_randomness() we need - * to take a ref - */ - is_new_current = true; - kref_get(&rng->ref); } mutex_unlock(&rng_mutex); - if (is_new_current || !rng->init) { - /* - * Use a new device's input to add some randomness to - * the system. If this rng device isn't going to be - * used right away, its init function hasn't been - * called yet by set_current_rng(); so only use the - * randomness from devices that don't need an init callback - */ - add_early_randomness(rng); - } - if (is_new_current) - put_rng(rng); return 0; out_unlock: mutex_unlock(&rng_mutex); @@ -602,12 +567,11 @@ EXPORT_SYMBOL_GPL(hwrng_register); void hwrng_unregister(struct hwrng *rng) { - struct hwrng *old_rng, *new_rng; + struct hwrng *new_rng; int err; mutex_lock(&rng_mutex); - old_rng = current_rng; list_del(&rng->list); complete_all(&rng->dying); if (current_rng == rng) { @@ -626,11 +590,8 @@ void hwrng_unregister(struct hwrng *rng) } else mutex_unlock(&rng_mutex); - if (new_rng) { - if (old_rng != new_rng) - add_early_randomness(new_rng); + if (new_rng) put_rng(new_rng); - } wait_for_completion(&rng->cleanup_done); } diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig index e63a6a17793c..cf0be8a7939d 100644 --- a/drivers/char/tpm/Kconfig +++ b/drivers/char/tpm/Kconfig @@ -29,7 +29,7 @@ if TCG_TPM config TCG_TPM2_HMAC bool "Use HMAC and encrypted transactions on the TPM bus" - default y + default X86_64 select CRYPTO_ECDH select CRYPTO_LIB_AESCFB select CRYPTO_LIB_SHA256 diff --git a/drivers/char/tpm/tpm-buf.c b/drivers/char/tpm/tpm-buf.c index 647c6ca92ac3..cad0048bcc3c 100644 --- a/drivers/char/tpm/tpm-buf.c +++ b/drivers/char/tpm/tpm-buf.c @@ -223,30 +223,4 @@ u32 tpm_buf_read_u32(struct tpm_buf *buf, off_t *offset) } EXPORT_SYMBOL_GPL(tpm_buf_read_u32); -static u16 tpm_buf_tag(struct tpm_buf *buf) -{ - struct tpm_header *head = (struct tpm_header *)buf->data; - - return be16_to_cpu(head->tag); -} - -/** - * tpm_buf_parameters - return the TPM response parameters area of the tpm_buf - * @buf: tpm_buf to use - * - * Where the parameters are located depends on the tag of a TPM - * command (it's immediately after the header for TPM_ST_NO_SESSIONS - * or 4 bytes after for TPM_ST_SESSIONS). Evaluate this and return a - * pointer to the first byte of the parameters area. - * - * @return: pointer to parameters area - */ -u8 *tpm_buf_parameters(struct tpm_buf *buf) -{ - int offset = TPM_HEADER_SIZE; - - if (tpm_buf_tag(buf) == TPM2_ST_SESSIONS) - offset += 4; - return &buf->data[offset]; -} diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index 0cdf892ec2a7..1e856259219e 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -281,6 +281,7 @@ struct tpm2_get_random_out { int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max) { struct tpm2_get_random_out *out; + struct tpm_header *head; struct tpm_buf buf; u32 recd; u32 num_bytes = max; @@ -288,6 +289,7 @@ int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max) int total = 0; int retries = 5; u8 *dest_ptr = dest; + off_t offset; if (!num_bytes || max > TPM_MAX_RNG_DATA) return -EINVAL; @@ -320,7 +322,13 @@ int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max) goto out; } - out = (struct tpm2_get_random_out *)tpm_buf_parameters(&buf); + head = (struct tpm_header *)buf.data; + offset = TPM_HEADER_SIZE; + /* Skip the parameter size field: */ + if (be16_to_cpu(head->tag) == TPM2_ST_SESSIONS) + offset += 4; + + out = (struct tpm2_get_random_out *)&buf.data[offset]; recd = min_t(u32, be16_to_cpu(out->size), num_bytes); if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c index ea8860661876..907ac9956a78 100644 --- a/drivers/char/tpm/tpm2-sessions.c +++ b/drivers/char/tpm/tpm2-sessions.c @@ -80,6 +80,9 @@ /* maximum number of names the TPM must remember for authorization */ #define AUTH_MAX_NAMES 3 +#define AES_KEY_BYTES AES_KEYSIZE_128 +#define AES_KEY_BITS (AES_KEY_BYTES*8) + static int tpm2_create_primary(struct tpm_chip *chip, u32 hierarchy, u32 *handle, u8 *name); @@ -954,6 +957,20 @@ int tpm2_start_auth_session(struct tpm_chip *chip) } EXPORT_SYMBOL(tpm2_start_auth_session); +/* + * A mask containing the object attributes for the kernel held null primary key + * used in HMAC encryption. For more information on specific attributes look up + * to "8.3 TPMA_OBJECT (Object Attributes)". + */ +#define TPM2_OA_NULL_KEY ( \ + TPM2_OA_NO_DA | \ + TPM2_OA_FIXED_TPM | \ + TPM2_OA_FIXED_PARENT | \ + TPM2_OA_SENSITIVE_DATA_ORIGIN | \ + TPM2_OA_USER_WITH_AUTH | \ + TPM2_OA_DECRYPT | \ + TPM2_OA_RESTRICTED) + /** * tpm2_parse_create_primary() - parse the data returned from TPM_CC_CREATE_PRIMARY * @@ -1018,7 +1035,7 @@ static int tpm2_parse_create_primary(struct tpm_chip *chip, struct tpm_buf *buf, val = tpm_buf_read_u32(buf, &offset_t); /* object properties */ - if (val != TPM2_OA_TMPL) + if (val != TPM2_OA_NULL_KEY) return -EINVAL; /* auth policy (empty) */ @@ -1178,7 +1195,7 @@ static int tpm2_create_primary(struct tpm_chip *chip, u32 hierarchy, tpm_buf_append_u16(&template, TPM_ALG_SHA256); /* object properties */ - tpm_buf_append_u32(&template, TPM2_OA_TMPL); + tpm_buf_append_u32(&template, TPM2_OA_NULL_KEY); /* sauth policy (empty) */ tpm_buf_append_u16(&template, 0); diff --git a/drivers/char/tpm/tpm_tis_spi_main.c b/drivers/char/tpm/tpm_tis_spi_main.c index 3f9eaf27b41b..c9eca24bbad4 100644 --- a/drivers/char/tpm/tpm_tis_spi_main.c +++ b/drivers/char/tpm/tpm_tis_spi_main.c @@ -37,6 +37,7 @@ #include "tpm_tis_spi.h" #define MAX_SPI_FRAMESIZE 64 +#define SPI_HDRSIZE 4 /* * TCG SPI flow control is documented in section 6.4 of the spec[1]. In short, @@ -247,7 +248,7 @@ static int tpm_tis_spi_write_bytes(struct tpm_tis_data *data, u32 addr, int tpm_tis_spi_init(struct spi_device *spi, struct tpm_tis_spi_phy *phy, int irq, const struct tpm_tis_phy_ops *phy_ops) { - phy->iobuf = devm_kmalloc(&spi->dev, MAX_SPI_FRAMESIZE, GFP_KERNEL); + phy->iobuf = devm_kmalloc(&spi->dev, SPI_HDRSIZE + MAX_SPI_FRAMESIZE, GFP_KERNEL); if (!phy->iobuf) return -ENOMEM; diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 1e0085cd9a9a..2818e24e2a51 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -3142,7 +3142,7 @@ phy_interface_t ksz_get_xmii(struct ksz_device *dev, int port, bool gbit) else interface = PHY_INTERFACE_MODE_MII; } else if (val == bitval[P_RMII_SEL]) { - interface = PHY_INTERFACE_MODE_RGMII; + interface = PHY_INTERFACE_MODE_RMII; } else { interface = PHY_INTERFACE_MODE_RGMII; if (data8 & P_RGMII_ID_EG_ENABLE) diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 2d8a66ea82fa..713a595370bf 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -312,7 +312,6 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev, struct ena_com_io_sq *io_sq) { size_t size; - int dev_node = 0; memset(&io_sq->desc_addr, 0x0, sizeof(io_sq->desc_addr)); @@ -325,12 +324,9 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev, size = io_sq->desc_entry_size * io_sq->q_depth; if (io_sq->mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_HOST) { - dev_node = dev_to_node(ena_dev->dmadev); - set_dev_node(ena_dev->dmadev, ctx->numa_node); io_sq->desc_addr.virt_addr = dma_alloc_coherent(ena_dev->dmadev, size, &io_sq->desc_addr.phys_addr, GFP_KERNEL); - set_dev_node(ena_dev->dmadev, dev_node); if (!io_sq->desc_addr.virt_addr) { io_sq->desc_addr.virt_addr = dma_alloc_coherent(ena_dev->dmadev, size, @@ -354,10 +350,7 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev, size = (size_t)io_sq->bounce_buf_ctrl.buffer_size * io_sq->bounce_buf_ctrl.buffers_num; - dev_node = dev_to_node(ena_dev->dmadev); - set_dev_node(ena_dev->dmadev, ctx->numa_node); io_sq->bounce_buf_ctrl.base_buffer = devm_kzalloc(ena_dev->dmadev, size, GFP_KERNEL); - set_dev_node(ena_dev->dmadev, dev_node); if (!io_sq->bounce_buf_ctrl.base_buffer) io_sq->bounce_buf_ctrl.base_buffer = devm_kzalloc(ena_dev->dmadev, size, GFP_KERNEL); @@ -397,7 +390,6 @@ static int ena_com_init_io_cq(struct ena_com_dev *ena_dev, struct ena_com_io_cq *io_cq) { size_t size; - int prev_node = 0; memset(&io_cq->cdesc_addr, 0x0, sizeof(io_cq->cdesc_addr)); @@ -409,11 +401,8 @@ static int ena_com_init_io_cq(struct ena_com_dev *ena_dev, size = io_cq->cdesc_entry_size_in_bytes * io_cq->q_depth; - prev_node = dev_to_node(ena_dev->dmadev); - set_dev_node(ena_dev->dmadev, ctx->numa_node); io_cq->cdesc_addr.virt_addr = dma_alloc_coherent(ena_dev->dmadev, size, &io_cq->cdesc_addr.phys_addr, GFP_KERNEL); - set_dev_node(ena_dev->dmadev, prev_node); if (!io_cq->cdesc_addr.virt_addr) { io_cq->cdesc_addr.virt_addr = dma_alloc_coherent(ena_dev->dmadev, size, &io_cq->cdesc_addr.phys_addr, diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index f604119efc80..5f26fc3ad655 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -1117,18 +1117,30 @@ static int enic_set_vf_port(struct net_device *netdev, int vf, pp->request = nla_get_u8(port[IFLA_PORT_REQUEST]); if (port[IFLA_PORT_PROFILE]) { + if (nla_len(port[IFLA_PORT_PROFILE]) != PORT_PROFILE_MAX) { + memcpy(pp, &prev_pp, sizeof(*pp)); + return -EINVAL; + } pp->set |= ENIC_SET_NAME; memcpy(pp->name, nla_data(port[IFLA_PORT_PROFILE]), PORT_PROFILE_MAX); } if (port[IFLA_PORT_INSTANCE_UUID]) { + if (nla_len(port[IFLA_PORT_INSTANCE_UUID]) != PORT_UUID_MAX) { + memcpy(pp, &prev_pp, sizeof(*pp)); + return -EINVAL; + } pp->set |= ENIC_SET_INSTANCE; memcpy(pp->instance_uuid, nla_data(port[IFLA_PORT_INSTANCE_UUID]), PORT_UUID_MAX); } if (port[IFLA_PORT_HOST_UUID]) { + if (nla_len(port[IFLA_PORT_HOST_UUID]) != PORT_UUID_MAX) { + memcpy(pp, &prev_pp, sizeof(*pp)); + return -EINVAL; + } pp->set |= ENIC_SET_HOST; memcpy(pp->host_uuid, nla_data(port[IFLA_PORT_HOST_UUID]), PORT_UUID_MAX); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index a72d8a2eb0b3..881ece735dcf 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -4130,6 +4130,14 @@ free_queue_mem: return ret; } +static void fec_enet_deinit(struct net_device *ndev) +{ + struct fec_enet_private *fep = netdev_priv(ndev); + + netif_napi_del(&fep->napi); + fec_enet_free_queue(ndev); +} + #ifdef CONFIG_OF static int fec_reset_phy(struct platform_device *pdev) { @@ -4524,6 +4532,7 @@ failed_register: fec_enet_mii_remove(fep); failed_mii_init: failed_irq: + fec_enet_deinit(ndev); failed_init: fec_ptp_stop(pdev); failed_reset: @@ -4587,6 +4596,7 @@ fec_drv_remove(struct platform_device *pdev) pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); + fec_enet_deinit(ndev); free_netdev(ndev); } diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index f9e94be36e97..2e98a2a0bead 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1225,6 +1225,28 @@ s32 e1000_enable_ulp_lpt_lp(struct e1000_hw *hw, bool to_sx) } release: + /* Switching PHY interface always returns MDI error + * so disable retry mechanism to avoid wasting time + */ + e1000e_disable_phy_retry(hw); + + /* Force SMBus mode in PHY */ + ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &phy_reg); + if (ret_val) { + e1000e_enable_phy_retry(hw); + hw->phy.ops.release(hw); + goto out; + } + phy_reg |= CV_SMB_CTRL_FORCE_SMBUS; + e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, phy_reg); + + e1000e_enable_phy_retry(hw); + + /* Force SMBus mode in MAC */ + mac_reg = er32(CTRL_EXT); + mac_reg |= E1000_CTRL_EXT_FORCE_SMBUS; + ew32(CTRL_EXT, mac_reg); + hw->phy.ops.release(hw); out: if (ret_val) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 220d62fca55d..da5c59daf8ba 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6623,7 +6623,6 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) struct e1000_hw *hw = &adapter->hw; u32 ctrl, ctrl_ext, rctl, status, wufc; int retval = 0; - u16 smb_ctrl; /* Runtime suspend should only enable wakeup for link changes */ if (runtime) @@ -6697,23 +6696,6 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) if (retval) return retval; } - - /* Force SMBUS to allow WOL */ - /* Switching PHY interface always returns MDI error - * so disable retry mechanism to avoid wasting time - */ - e1000e_disable_phy_retry(hw); - - e1e_rphy(hw, CV_SMB_CTRL, &smb_ctrl); - smb_ctrl |= CV_SMB_CTRL_FORCE_SMBUS; - e1e_wphy(hw, CV_SMB_CTRL, smb_ctrl); - - e1000e_enable_phy_retry(hw); - - /* Force SMBus mode in MAC */ - ctrl_ext = er32(CTRL_EXT); - ctrl_ext |= E1000_CTRL_EXT_FORCE_SMBUS; - ew32(CTRL_EXT, ctrl_ext); } /* Ensure that the appropriate bits are set in LPI_CTRL diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 1f188c052828..284c3fad5a6e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -11171,6 +11171,8 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit, ret = i40e_reset(pf); if (!ret) i40e_rebuild(pf, reinit, lock_acquired); + else + dev_err(&pf->pdev->dev, "%s: i40e_reset() FAILED", __func__); } /** @@ -16335,6 +16337,139 @@ unmap: } /** + * i40e_enable_mc_magic_wake - enable multicast magic packet wake up + * using the mac_address_write admin q function + * @pf: pointer to i40e_pf struct + **/ +static void i40e_enable_mc_magic_wake(struct i40e_pf *pf) +{ + struct i40e_vsi *main_vsi = i40e_pf_get_main_vsi(pf); + struct i40e_hw *hw = &pf->hw; + u8 mac_addr[6]; + u16 flags = 0; + int ret; + + /* Get current MAC address in case it's an LAA */ + if (main_vsi && main_vsi->netdev) { + ether_addr_copy(mac_addr, main_vsi->netdev->dev_addr); + } else { + dev_err(&pf->pdev->dev, + "Failed to retrieve MAC address; using default\n"); + ether_addr_copy(mac_addr, hw->mac.addr); + } + + /* The FW expects the mac address write cmd to first be called with + * one of these flags before calling it again with the multicast + * enable flags. + */ + flags = I40E_AQC_WRITE_TYPE_LAA_WOL; + + if (hw->func_caps.flex10_enable && hw->partition_id != 1) + flags = I40E_AQC_WRITE_TYPE_LAA_ONLY; + + ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL); + if (ret) { + dev_err(&pf->pdev->dev, + "Failed to update MAC address registers; cannot enable Multicast Magic packet wake up"); + return; + } + + flags = I40E_AQC_MC_MAG_EN + | I40E_AQC_WOL_PRESERVE_ON_PFR + | I40E_AQC_WRITE_TYPE_UPDATE_MC_MAG; + ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL); + if (ret) + dev_err(&pf->pdev->dev, + "Failed to enable Multicast Magic Packet wake up\n"); +} + +/** + * i40e_io_suspend - suspend all IO operations + * @pf: pointer to i40e_pf struct + * + **/ +static int i40e_io_suspend(struct i40e_pf *pf) +{ + struct i40e_hw *hw = &pf->hw; + + set_bit(__I40E_DOWN, pf->state); + + /* Ensure service task will not be running */ + del_timer_sync(&pf->service_timer); + cancel_work_sync(&pf->service_task); + + /* Client close must be called explicitly here because the timer + * has been stopped. + */ + i40e_notify_client_of_netdev_close(pf, false); + + if (test_bit(I40E_HW_CAP_WOL_MC_MAGIC_PKT_WAKE, pf->hw.caps) && + pf->wol_en) + i40e_enable_mc_magic_wake(pf); + + /* Since we're going to destroy queues during the + * i40e_clear_interrupt_scheme() we should hold the RTNL lock for this + * whole section + */ + rtnl_lock(); + + i40e_prep_for_reset(pf); + + wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0)); + wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0)); + + /* Clear the interrupt scheme and release our IRQs so that the system + * can safely hibernate even when there are a large number of CPUs. + * Otherwise hibernation might fail when mapping all the vectors back + * to CPU0. + */ + i40e_clear_interrupt_scheme(pf); + + rtnl_unlock(); + + return 0; +} + +/** + * i40e_io_resume - resume IO operations + * @pf: pointer to i40e_pf struct + * + **/ +static int i40e_io_resume(struct i40e_pf *pf) +{ + struct device *dev = &pf->pdev->dev; + int err; + + /* We need to hold the RTNL lock prior to restoring interrupt schemes, + * since we're going to be restoring queues + */ + rtnl_lock(); + + /* We cleared the interrupt scheme when we suspended, so we need to + * restore it now to resume device functionality. + */ + err = i40e_restore_interrupt_scheme(pf); + if (err) { + dev_err(dev, "Cannot restore interrupt scheme: %d\n", + err); + } + + clear_bit(__I40E_DOWN, pf->state); + i40e_reset_and_rebuild(pf, false, true); + + rtnl_unlock(); + + /* Clear suspended state last after everything is recovered */ + clear_bit(__I40E_SUSPENDED, pf->state); + + /* Restart the service task */ + mod_timer(&pf->service_timer, + round_jiffies(jiffies + pf->service_timer_period)); + + return 0; +} + +/** * i40e_pci_error_detected - warning that something funky happened in PCI land * @pdev: PCI device information struct * @error: the type of PCI error @@ -16358,7 +16493,7 @@ static pci_ers_result_t i40e_pci_error_detected(struct pci_dev *pdev, /* shutdown all operations */ if (!test_bit(__I40E_SUSPENDED, pf->state)) - i40e_prep_for_reset(pf); + i40e_io_suspend(pf); /* Request a slot reset */ return PCI_ERS_RESULT_NEED_RESET; @@ -16380,7 +16515,8 @@ static pci_ers_result_t i40e_pci_error_slot_reset(struct pci_dev *pdev) u32 reg; dev_dbg(&pdev->dev, "%s\n", __func__); - if (pci_enable_device_mem(pdev)) { + /* enable I/O and memory of the device */ + if (pci_enable_device(pdev)) { dev_info(&pdev->dev, "Cannot re-enable PCI device after reset.\n"); result = PCI_ERS_RESULT_DISCONNECT; @@ -16443,54 +16579,7 @@ static void i40e_pci_error_resume(struct pci_dev *pdev) if (test_bit(__I40E_SUSPENDED, pf->state)) return; - i40e_handle_reset_warning(pf, false); -} - -/** - * i40e_enable_mc_magic_wake - enable multicast magic packet wake up - * using the mac_address_write admin q function - * @pf: pointer to i40e_pf struct - **/ -static void i40e_enable_mc_magic_wake(struct i40e_pf *pf) -{ - struct i40e_vsi *main_vsi = i40e_pf_get_main_vsi(pf); - struct i40e_hw *hw = &pf->hw; - u8 mac_addr[6]; - u16 flags = 0; - int ret; - - /* Get current MAC address in case it's an LAA */ - if (main_vsi && main_vsi->netdev) { - ether_addr_copy(mac_addr, main_vsi->netdev->dev_addr); - } else { - dev_err(&pf->pdev->dev, - "Failed to retrieve MAC address; using default\n"); - ether_addr_copy(mac_addr, hw->mac.addr); - } - - /* The FW expects the mac address write cmd to first be called with - * one of these flags before calling it again with the multicast - * enable flags. - */ - flags = I40E_AQC_WRITE_TYPE_LAA_WOL; - - if (hw->func_caps.flex10_enable && hw->partition_id != 1) - flags = I40E_AQC_WRITE_TYPE_LAA_ONLY; - - ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL); - if (ret) { - dev_err(&pf->pdev->dev, - "Failed to update MAC address registers; cannot enable Multicast Magic packet wake up"); - return; - } - - flags = I40E_AQC_MC_MAG_EN - | I40E_AQC_WOL_PRESERVE_ON_PFR - | I40E_AQC_WRITE_TYPE_UPDATE_MC_MAG; - ret = i40e_aq_mac_address_write(hw, flags, mac_addr, NULL); - if (ret) - dev_err(&pf->pdev->dev, - "Failed to enable Multicast Magic Packet wake up\n"); + i40e_io_resume(pf); } /** @@ -16552,48 +16641,11 @@ static void i40e_shutdown(struct pci_dev *pdev) static int i40e_suspend(struct device *dev) { struct i40e_pf *pf = dev_get_drvdata(dev); - struct i40e_hw *hw = &pf->hw; /* If we're already suspended, then there is nothing to do */ if (test_and_set_bit(__I40E_SUSPENDED, pf->state)) return 0; - - set_bit(__I40E_DOWN, pf->state); - - /* Ensure service task will not be running */ - del_timer_sync(&pf->service_timer); - cancel_work_sync(&pf->service_task); - - /* Client close must be called explicitly here because the timer - * has been stopped. - */ - i40e_notify_client_of_netdev_close(pf, false); - - if (test_bit(I40E_HW_CAP_WOL_MC_MAGIC_PKT_WAKE, pf->hw.caps) && - pf->wol_en) - i40e_enable_mc_magic_wake(pf); - - /* Since we're going to destroy queues during the - * i40e_clear_interrupt_scheme() we should hold the RTNL lock for this - * whole section - */ - rtnl_lock(); - - i40e_prep_for_reset(pf); - - wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0)); - wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0)); - - /* Clear the interrupt scheme and release our IRQs so that the system - * can safely hibernate even when there are a large number of CPUs. - * Otherwise hibernation might fail when mapping all the vectors back - * to CPU0. - */ - i40e_clear_interrupt_scheme(pf); - - rtnl_unlock(); - - return 0; + return i40e_io_suspend(pf); } /** @@ -16603,39 +16655,11 @@ static int i40e_suspend(struct device *dev) static int i40e_resume(struct device *dev) { struct i40e_pf *pf = dev_get_drvdata(dev); - int err; /* If we're not suspended, then there is nothing to do */ if (!test_bit(__I40E_SUSPENDED, pf->state)) return 0; - - /* We need to hold the RTNL lock prior to restoring interrupt schemes, - * since we're going to be restoring queues - */ - rtnl_lock(); - - /* We cleared the interrupt scheme when we suspended, so we need to - * restore it now to resume device functionality. - */ - err = i40e_restore_interrupt_scheme(pf); - if (err) { - dev_err(dev, "Cannot restore interrupt scheme: %d\n", - err); - } - - clear_bit(__I40E_DOWN, pf->state); - i40e_reset_and_rebuild(pf, false, true); - - rtnl_unlock(); - - /* Clear suspended state last after everything is recovered */ - clear_bit(__I40E_SUSPENDED, pf->state); - - /* Restart the service task */ - mod_timer(&pf->service_timer, - round_jiffies(jiffies + pf->service_timer_period)); - - return 0; + return i40e_io_resume(pf); } static const struct pci_error_handlers i40e_err_handler = { diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index c4b69655cdf5..704e9ad5144e 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -1388,7 +1388,7 @@ enum ice_param_id { ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS, }; -static const struct devlink_param ice_devlink_params[] = { +static const struct devlink_param ice_dvl_rdma_params[] = { DEVLINK_PARAM_GENERIC(ENABLE_ROCE, BIT(DEVLINK_PARAM_CMODE_RUNTIME), ice_devlink_enable_roce_get, ice_devlink_enable_roce_set, @@ -1397,6 +1397,9 @@ static const struct devlink_param ice_devlink_params[] = { ice_devlink_enable_iw_get, ice_devlink_enable_iw_set, ice_devlink_enable_iw_validate), +}; + +static const struct devlink_param ice_dvl_sched_params[] = { DEVLINK_PARAM_DRIVER(ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS, "tx_scheduling_layers", DEVLINK_PARAM_TYPE_U8, @@ -1464,21 +1467,31 @@ int ice_devlink_register_params(struct ice_pf *pf) { struct devlink *devlink = priv_to_devlink(pf); struct ice_hw *hw = &pf->hw; - size_t params_size; + int status; - params_size = ARRAY_SIZE(ice_devlink_params); + status = devl_params_register(devlink, ice_dvl_rdma_params, + ARRAY_SIZE(ice_dvl_rdma_params)); + if (status) + return status; - if (!hw->func_caps.common_cap.tx_sched_topo_comp_mode_en) - params_size--; + if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en) + status = devl_params_register(devlink, ice_dvl_sched_params, + ARRAY_SIZE(ice_dvl_sched_params)); - return devl_params_register(devlink, ice_devlink_params, - params_size); + return status; } void ice_devlink_unregister_params(struct ice_pf *pf) { - devl_params_unregister(priv_to_devlink(pf), ice_devlink_params, - ARRAY_SIZE(ice_devlink_params)); + struct devlink *devlink = priv_to_devlink(pf); + struct ice_hw *hw = &pf->hw; + + devl_params_unregister(devlink, ice_dvl_rdma_params, + ARRAY_SIZE(ice_dvl_rdma_params)); + + if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en) + devl_params_unregister(devlink, ice_dvl_sched_params, + ARRAY_SIZE(ice_dvl_sched_params)); } #define ICE_DEVLINK_READ_BLK_SIZE (1024 * 1024) diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 5649b257e631..24716a3b494c 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -3148,6 +3148,16 @@ ice_get_link_speed_based_on_phy_type(u64 phy_type_low, u64 phy_type_high) case ICE_PHY_TYPE_HIGH_100G_AUI2: speed_phy_type_high = ICE_AQ_LINK_SPEED_100GB; break; + case ICE_PHY_TYPE_HIGH_200G_CR4_PAM4: + case ICE_PHY_TYPE_HIGH_200G_SR4: + case ICE_PHY_TYPE_HIGH_200G_FR4: + case ICE_PHY_TYPE_HIGH_200G_LR4: + case ICE_PHY_TYPE_HIGH_200G_DR4: + case ICE_PHY_TYPE_HIGH_200G_KR4_PAM4: + case ICE_PHY_TYPE_HIGH_200G_AUI4_AOC_ACC: + case ICE_PHY_TYPE_HIGH_200G_AUI4: + speed_phy_type_high = ICE_AQ_LINK_SPEED_200GB; + break; default: speed_phy_type_high = ICE_AQ_LINK_SPEED_UNKNOWN; break; diff --git a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c index 2e9ad27cb9d1..6e8f2aab6080 100644 --- a/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vsi_vlan_lib.c @@ -45,14 +45,15 @@ int ice_vsi_add_vlan(struct ice_vsi *vsi, struct ice_vlan *vlan) return -EINVAL; err = ice_fltr_add_vlan(vsi, vlan); - if (err && err != -EEXIST) { + if (!err) + vsi->num_vlan++; + else if (err == -EEXIST) + err = 0; + else dev_err(ice_pf_to_dev(vsi->back), "Failure Adding VLAN %d on VSI %i, status %d\n", vlan->vid, vsi->vsi_num, err); - return err; - } - vsi->num_vlan++; - return 0; + return err; } /** diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index 52ceda6306a3..f1ee5584e8fa 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -1394,6 +1394,7 @@ static int idpf_vport_open(struct idpf_vport *vport, bool alloc_res) } idpf_rx_init_buf_tail(vport); + idpf_vport_intr_ena(vport); err = idpf_send_config_queues_msg(vport); if (err) { diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 285da2177ee4..b023704bbbda 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -3746,9 +3746,9 @@ static void idpf_vport_intr_ena_irq_all(struct idpf_vport *vport) */ void idpf_vport_intr_deinit(struct idpf_vport *vport) { + idpf_vport_intr_dis_irq_all(vport); idpf_vport_intr_napi_dis_all(vport); idpf_vport_intr_napi_del_all(vport); - idpf_vport_intr_dis_irq_all(vport); idpf_vport_intr_rel_irq(vport); } @@ -4179,7 +4179,6 @@ int idpf_vport_intr_init(struct idpf_vport *vport) idpf_vport_intr_map_vector_to_qs(vport); idpf_vport_intr_napi_add_all(vport); - idpf_vport_intr_napi_ena_all(vport); err = vport->adapter->dev_ops.reg_ops.intr_reg_init(vport); if (err) @@ -4193,17 +4192,20 @@ int idpf_vport_intr_init(struct idpf_vport *vport) if (err) goto unroll_vectors_alloc; - idpf_vport_intr_ena_irq_all(vport); - return 0; unroll_vectors_alloc: - idpf_vport_intr_napi_dis_all(vport); idpf_vport_intr_napi_del_all(vport); return err; } +void idpf_vport_intr_ena(struct idpf_vport *vport) +{ + idpf_vport_intr_napi_ena_all(vport); + idpf_vport_intr_ena_irq_all(vport); +} + /** * idpf_config_rss - Send virtchnl messages to configure RSS * @vport: virtual port diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h index 3d046b81e507..551391e20464 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h @@ -990,6 +990,7 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport); void idpf_vport_intr_update_itr_ena_irq(struct idpf_q_vector *q_vector); void idpf_vport_intr_deinit(struct idpf_vport *vport); int idpf_vport_intr_init(struct idpf_vport *vport); +void idpf_vport_intr_ena(struct idpf_vport *vport); enum pkt_hash_types idpf_ptype_to_htype(const struct idpf_rx_ptype_decoded *decoded); int idpf_config_rss(struct idpf_vport *vport); int idpf_init_rss(struct idpf_vport *vport); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c index 070711df612e..edac008099c0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c @@ -1422,7 +1422,10 @@ static int otx2_qos_leaf_to_inner(struct otx2_nic *pfvf, u16 classid, otx2_qos_read_txschq_cfg(pfvf, node, old_cfg); /* delete the txschq nodes allocated for this node */ + otx2_qos_disable_sq(pfvf, qid); + otx2_qos_free_hw_node_schq(pfvf, node); otx2_qos_free_sw_node_schq(pfvf, node); + pfvf->qos.qid_to_sqmap[qid] = OTX2_QOS_INVALID_SQ; /* mark this node as htb inner node */ WRITE_ONCE(node->qid, OTX2_QOS_QID_INNER); @@ -1632,6 +1635,7 @@ static int otx2_qos_leaf_del_last(struct otx2_nic *pfvf, u16 classid, bool force dwrr_del_node = true; /* destroy the leaf node */ + otx2_qos_disable_sq(pfvf, qid); otx2_qos_destroy_node(pfvf, node); pfvf->qos.qid_to_sqmap[qid] = OTX2_QOS_INVALID_SQ; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h index caa34b9c161e..33e32584b07f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h @@ -102,8 +102,14 @@ static inline void mlx5e_udp_gso_handle_tx_skb(struct sk_buff *skb) { int payload_len = skb_shinfo(skb)->gso_size + sizeof(struct udphdr); + struct udphdr *udphdr; - udp_hdr(skb)->len = htons(payload_len); + if (skb->encapsulation) + udphdr = (struct udphdr *)skb_inner_transport_header(skb); + else + udphdr = udp_hdr(skb); + + udphdr->len = htons(payload_len); } struct mlx5e_accel_tx_state { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index 41a2543a52cd..e51b03d4c717 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -750,8 +750,7 @@ err_fs: err_fs_ft: if (rx->allow_tunnel_mode) mlx5_eswitch_unblock_encap(mdev); - mlx5_del_flow_rules(rx->status.rule); - mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr); + mlx5_ipsec_rx_status_destroy(ipsec, rx); err_add: mlx5_destroy_flow_table(rx->ft.status); err_fs_ft_status: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h index 82064614846f..359050f0b54d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h @@ -97,18 +97,11 @@ mlx5e_ipsec_feature_check(struct sk_buff *skb, netdev_features_t features) if (!x || !x->xso.offload_handle) goto out_disable; - if (xo->inner_ipproto) { - /* Cannot support tunnel packet over IPsec tunnel mode - * because we cannot offload three IP header csum - */ - if (x->props.mode == XFRM_MODE_TUNNEL) - goto out_disable; - - /* Only support UDP or TCP L4 checksum */ - if (xo->inner_ipproto != IPPROTO_UDP && - xo->inner_ipproto != IPPROTO_TCP) - goto out_disable; - } + /* Only support UDP or TCP L4 checksum */ + if (xo->inner_ipproto && + xo->inner_ipproto != IPPROTO_UDP && + xo->inner_ipproto != IPPROTO_TCP) + goto out_disable; return features; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b758bc72ac36..c53c99dde558 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3886,7 +3886,7 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) mlx5e_fold_sw_stats64(priv, stats); } - stats->rx_dropped = priv->stats.qcnt.rx_out_of_buffer; + stats->rx_missed_errors = priv->stats.qcnt.rx_out_of_buffer; stats->rx_length_errors = PPORT_802_3_GET(pstats, a_in_range_length_errors) + diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index e211c41cec06..e1ed214e8651 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -1186,6 +1186,9 @@ void mlx5e_stats_ts_get(struct mlx5e_priv *priv, ts_stats->err = 0; ts_stats->lost = 0; + if (!ptp) + goto out; + /* Aggregate stats across all TCs */ for (i = 0; i < ptp->num_tc; i++) { struct mlx5e_ptp_cq_stats *stats = @@ -1214,6 +1217,7 @@ void mlx5e_stats_ts_get(struct mlx5e_priv *priv, } } +out: mutex_unlock(&priv->state_lock); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 099bf1078889..b09e9abd39f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -153,7 +153,11 @@ mlx5e_tx_get_gso_ihs(struct mlx5e_txqsq *sq, struct sk_buff *skb, int *hopbyhop) *hopbyhop = 0; if (skb->encapsulation) { - ihs = skb_inner_tcp_all_headers(skb); + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) + ihs = skb_inner_transport_offset(skb) + + sizeof(struct udphdr); + else + ihs = skb_inner_tcp_all_headers(skb); stats->tso_inner_packets++; stats->tso_inner_bytes += skb->len - ihs; } else { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index f7f0476a4a58..d0871c46b8c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -719,6 +719,7 @@ bool mlx5_lag_check_prereq(struct mlx5_lag *ldev) struct mlx5_core_dev *dev; u8 mode; #endif + bool roce_support; int i; for (i = 0; i < ldev->ports; i++) @@ -743,6 +744,11 @@ bool mlx5_lag_check_prereq(struct mlx5_lag *ldev) if (mlx5_sriov_is_enabled(ldev->pf[i].dev)) return false; #endif + roce_support = mlx5_get_roce_state(ldev->pf[MLX5_LAG_P1].dev); + for (i = 1; i < ldev->ports; i++) + if (mlx5_get_roce_state(ldev->pf[i].dev) != roce_support) + return false; + return true; } @@ -910,8 +916,10 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) } else if (roce_lag) { dev0->priv.flags &= ~MLX5_PRIV_FLAGS_DISABLE_IB_ADEV; mlx5_rescan_drivers_locked(dev0); - for (i = 1; i < ldev->ports; i++) - mlx5_nic_vport_enable_roce(ldev->pf[i].dev); + for (i = 1; i < ldev->ports; i++) { + if (mlx5_get_roce_state(ldev->pf[i].dev)) + mlx5_nic_vport_enable_roce(ldev->pf[i].dev); + } } else if (shared_fdb) { int i; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c index dd5d186dc614..f6deb5a3f820 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c @@ -100,10 +100,6 @@ static bool ft_create_alias_supported(struct mlx5_core_dev *dev) static bool mlx5_sd_is_supported(struct mlx5_core_dev *dev, u8 host_buses) { - /* Feature is currently implemented for PFs only */ - if (!mlx5_core_is_pf(dev)) - return false; - /* Honor the SW implementation limit */ if (host_buses > MLX5_SD_MAX_GROUP_SZ) return false; @@ -162,6 +158,14 @@ static int sd_init(struct mlx5_core_dev *dev) bool sdm; int err; + /* Feature is currently implemented for PFs only */ + if (!mlx5_core_is_pf(dev)) + return 0; + + /* Block on embedded CPU PFs */ + if (mlx5_core_is_ecpf(dev)) + return 0; + if (!MLX5_CAP_MCAM_REG(dev, mpir)) return 0; diff --git a/drivers/net/ethernet/ti/icssg/icssg_classifier.c b/drivers/net/ethernet/ti/icssg/icssg_classifier.c index 79ba47bb3602..f7d21da1a0fb 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_classifier.c +++ b/drivers/net/ethernet/ti/icssg/icssg_classifier.c @@ -455,7 +455,7 @@ void icssg_ft1_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac_addr) { const u8 mask_addr[] = { 0, 0, 0, 0, 0, 0, }; - rx_class_ft1_set_start_len(miig_rt, slice, 0, 6); + rx_class_ft1_set_start_len(miig_rt, slice, ETH_ALEN, ETH_ALEN); rx_class_ft1_set_da(miig_rt, slice, 0, mac_addr); rx_class_ft1_set_da_mask(miig_rt, slice, 0, mask_addr); rx_class_ft1_cfg_set_type(miig_rt, slice, 0, FT1_CFG_TYPE_EQ); diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 2d5b021b4ea6..fef4eff7753a 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -439,7 +439,7 @@ static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb) memset(IPCB(skb), 0, sizeof(*IPCB(skb))); - err = ip_local_out(net, skb->sk, skb); + err = ip_local_out(net, NULL, skb); if (unlikely(net_xmit_eval(err))) DEV_STATS_INC(dev, tx_errors); else @@ -494,7 +494,7 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb) memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); - err = ip6_local_out(dev_net(dev), skb->sk, skb); + err = ip6_local_out(dev_net(dev), NULL, skb); if (unlikely(net_xmit_eval(err))) DEV_STATS_INC(dev, tx_errors); else diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index a4d2e76a8d58..16789cd446e9 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -55,6 +55,7 @@ static void netkit_prep_forward(struct sk_buff *skb, bool xnet) skb_scrub_packet(skb, xnet); skb->priority = 0; nf_skip_egress(skb, true); + skb_reset_mac_header(skb); } static struct netkit *netkit_priv(const struct net_device *dev) @@ -78,6 +79,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) skb_orphan_frags(skb, GFP_ATOMIC))) goto drop; netkit_prep_forward(skb, !net_eq(dev_net(dev), dev_net(peer))); + eth_skb_pkt_type(skb, peer); skb->dev = peer; entry = rcu_dereference(nk->active); if (entry) @@ -85,7 +87,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) switch (ret) { case NETKIT_NEXT: case NETKIT_PASS: - skb->protocol = eth_type_trans(skb, skb->dev); + eth_skb_pull_mac(skb); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) { dev_sw_netstats_tx_add(dev, 1, len); @@ -155,6 +157,16 @@ static void netkit_set_multicast(struct net_device *dev) /* Nothing to do, we receive whatever gets pushed to us! */ } +static int netkit_set_macaddr(struct net_device *dev, void *sa) +{ + struct netkit *nk = netkit_priv(dev); + + if (nk->mode != NETKIT_L2) + return -EOPNOTSUPP; + + return eth_mac_addr(dev, sa); +} + static void netkit_set_headroom(struct net_device *dev, int headroom) { struct netkit *nk = netkit_priv(dev), *nk2; @@ -198,6 +210,7 @@ static const struct net_device_ops netkit_netdev_ops = { .ndo_start_xmit = netkit_xmit, .ndo_set_rx_mode = netkit_set_multicast, .ndo_set_rx_headroom = netkit_set_headroom, + .ndo_set_mac_address = netkit_set_macaddr, .ndo_get_iflink = netkit_get_iflink, .ndo_get_peer_dev = netkit_peer_dev, .ndo_get_stats64 = netkit_get_stats, @@ -300,9 +313,11 @@ static int netkit_validate(struct nlattr *tb[], struct nlattr *data[], if (!attr) return 0; - NL_SET_ERR_MSG_ATTR(extack, attr, - "Setting Ethernet address is not supported"); - return -EOPNOTSUPP; + if (nla_len(attr) != ETH_ALEN) + return -EINVAL; + if (!is_valid_ether_addr(nla_data(attr))) + return -EADDRNOTAVAIL; + return 0; } static struct rtnl_link_ops netkit_link_ops; @@ -365,6 +380,9 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev, strscpy(ifname, "nk%d", IFNAMSIZ); ifname_assign_type = NET_NAME_ENUM; } + if (mode != NETKIT_L2 && + (tb[IFLA_ADDRESS] || tbp[IFLA_ADDRESS])) + return -EOPNOTSUPP; net = rtnl_link_get_net(src_net, tbp); if (IS_ERR(net)) @@ -379,7 +397,7 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev, netif_inherit_tso_max(peer, dev); - if (mode == NETKIT_L2) + if (mode == NETKIT_L2 && !(ifmp && tbp[IFLA_ADDRESS])) eth_hw_addr_random(peer); if (ifmp && dev->ifindex) peer->ifindex = ifmp->ifi_index; @@ -402,7 +420,7 @@ static int netkit_new_link(struct net *src_net, struct net_device *dev, if (err < 0) goto err_configure_peer; - if (mode == NETKIT_L2) + if (mode == NETKIT_L2 && !tb[IFLA_ADDRESS]) eth_hw_addr_random(dev); if (tb[IFLA_IFNAME]) nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ); diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 13e30ea7eec5..2b8f8b7f1517 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -4029,7 +4029,7 @@ static int lan8841_config_intr(struct phy_device *phydev) if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { err = phy_read(phydev, LAN8814_INTS); - if (err) + if (err < 0) return err; /* Enable / disable interrupts. It is OK to enable PTP interrupt @@ -4045,6 +4045,14 @@ static int lan8841_config_intr(struct phy_device *phydev) return err; err = phy_read(phydev, LAN8814_INTS); + if (err < 0) + return err; + + /* Getting a positive value doesn't mean that is an error, it + * just indicates what was the status. Therefore make sure to + * clear the value and say that there is no error. + */ + err = 0; } return err; @@ -5327,6 +5335,7 @@ static struct phy_driver ksphy_driver[] = { /* PHY_BASIC_FEATURES */ .probe = kszphy_probe, .config_init = ksz8061_config_init, + .soft_reset = genphy_soft_reset, .config_intr = kszphy_config_intr, .handle_interrupt = kszphy_handle_interrupt, .suspend = kszphy_suspend, diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index cbea24666479..8e82184be5e7 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -879,7 +879,7 @@ static int smsc95xx_start_rx_path(struct usbnet *dev) static int smsc95xx_reset(struct usbnet *dev) { struct smsc95xx_priv *pdata = dev->driver_priv; - u32 read_buf, write_buf, burst_cap; + u32 read_buf, burst_cap; int ret = 0, timeout; netif_dbg(dev, ifup, dev->net, "entering smsc95xx_reset\n"); @@ -1003,10 +1003,13 @@ static int smsc95xx_reset(struct usbnet *dev) return ret; netif_dbg(dev, ifup, dev->net, "ID_REV = 0x%08x\n", read_buf); + ret = smsc95xx_read_reg(dev, LED_GPIO_CFG, &read_buf); + if (ret < 0) + return ret; /* Configure GPIO pins as LED outputs */ - write_buf = LED_GPIO_CFG_SPD_LED | LED_GPIO_CFG_LNK_LED | - LED_GPIO_CFG_FDX_LED; - ret = smsc95xx_write_reg(dev, LED_GPIO_CFG, write_buf); + read_buf |= LED_GPIO_CFG_SPD_LED | LED_GPIO_CFG_LNK_LED | + LED_GPIO_CFG_FDX_LED; + ret = smsc95xx_write_reg(dev, LED_GPIO_CFG, read_buf); if (ret < 0) return ret; diff --git a/drivers/nfc/virtual_ncidev.c b/drivers/nfc/virtual_ncidev.c index 590b038e449e..6b89d596ba9a 100644 --- a/drivers/nfc/virtual_ncidev.c +++ b/drivers/nfc/virtual_ncidev.c @@ -125,6 +125,10 @@ static ssize_t virtual_ncidev_write(struct file *file, kfree_skb(skb); return -EFAULT; } + if (strnlen(skb->data, count) != count) { + kfree_skb(skb); + return -EINVAL; + } nci_recv_frame(vdev->ndev, skb); return count; diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 0ec952b5d03e..1953317541ea 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -515,6 +515,7 @@ config THINKPAD_ACPI select NVRAM select NEW_LEDS select LEDS_CLASS + select INPUT_SPARSEKMAP help This is a driver for the IBM and Lenovo ThinkPad laptops. It adds support for Fn-Fx key combinations, Bluetooth control, video diff --git a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c index 7bac7841ff0a..7fa360073f6e 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c @@ -1610,8 +1610,8 @@ void tpmi_sst_dev_remove(struct auxiliary_device *auxdev) tpmi_sst->partition_mask_current &= ~BIT(plat_info->partition); /* Free the package instance when the all partitions are removed */ if (!tpmi_sst->partition_mask_current) { - kfree(tpmi_sst); isst_common.sst_inst[tpmi_sst->package_id] = NULL; + kfree(tpmi_sst); } mutex_unlock(&isst_tpmi_dev_lock); } diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index c6a10ec2c83f..2d9ca2292ea1 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -9,10 +9,13 @@ */ #include <linux/acpi.h> +#include <linux/ctype.h> #include <linux/device.h> #include <linux/dmi.h> #include <linux/efi_embedded_fw.h> #include <linux/i2c.h> +#include <linux/init.h> +#include <linux/kstrtox.h> #include <linux/notifier.h> #include <linux/property.h> #include <linux/string.h> @@ -897,6 +900,22 @@ static const struct ts_dmi_data schneider_sct101ctm_data = { .properties = schneider_sct101ctm_props, }; +static const struct property_entry globalspace_solt_ivw116_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 7), + PROPERTY_ENTRY_U32("touchscreen-min-y", 22), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1723), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1077), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-globalspace-solt-ivw116.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + PROPERTY_ENTRY_BOOL("silead,home-button"), + { } +}; + +static const struct ts_dmi_data globalspace_solt_ivw116_data = { + .acpi_name = "MSSL1680:00", + .properties = globalspace_solt_ivw116_props, +}; + static const struct property_entry techbite_arc_11_6_props[] = { PROPERTY_ENTRY_U32("touchscreen-min-x", 5), PROPERTY_ENTRY_U32("touchscreen-min-y", 7), @@ -1386,6 +1405,17 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* Jumper EZpad 6s Pro */ + .driver_data = (void *)&jumper_ezpad_6_pro_b_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Jumper"), + DMI_MATCH(DMI_PRODUCT_NAME, "Ezpad"), + /* Above matches are too generic, add bios match */ + DMI_MATCH(DMI_BIOS_VERSION, "E.WSA116_8.E1.042.bin"), + DMI_MATCH(DMI_BIOS_DATE, "01/08/2020"), + }, + }, + { /* Jumper EZpad 6 m4 */ .driver_data = (void *)&jumper_ezpad_6_m4_data, .matches = { @@ -1625,6 +1655,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* GlobalSpace SoLT IVW 11.6" */ + .driver_data = (void *)&globalspace_solt_ivw116_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Globalspace Tech Pvt Ltd"), + DMI_MATCH(DMI_PRODUCT_NAME, "SolTIVW"), + DMI_MATCH(DMI_PRODUCT_SKU, "PN20170413488"), + }, + }, + { /* Techbite Arc 11.6 */ .driver_data = (void *)&techbite_arc_11_6_data, .matches = { @@ -1817,7 +1856,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = { { } }; -static const struct ts_dmi_data *ts_data; +static struct ts_dmi_data *ts_data; static void ts_dmi_add_props(struct i2c_client *client) { @@ -1852,6 +1891,64 @@ static int ts_dmi_notifier_call(struct notifier_block *nb, return 0; } +#define MAX_CMDLINE_PROPS 16 + +static struct property_entry ts_cmdline_props[MAX_CMDLINE_PROPS + 1]; + +static struct ts_dmi_data ts_cmdline_data = { + .properties = ts_cmdline_props, +}; + +static int __init ts_parse_props(char *str) +{ + /* Save the original str to show it on syntax errors */ + char orig_str[256]; + char *name, *value; + u32 u32val; + int i, ret; + + strscpy(orig_str, str, sizeof(orig_str)); + + /* + * str is part of the static_command_line from init/main.c and poking + * holes in that by writing 0 to it is allowed, as is taking long + * lasting references to it. + */ + ts_cmdline_data.acpi_name = strsep(&str, ":"); + + for (i = 0; i < MAX_CMDLINE_PROPS; i++) { + name = strsep(&str, ":"); + if (!name || !name[0]) + break; + + /* Replace '=' with 0 and make value point past '=' or NULL */ + value = name; + strsep(&value, "="); + if (!value) { + ts_cmdline_props[i] = PROPERTY_ENTRY_BOOL(name); + } else if (isdigit(value[0])) { + ret = kstrtou32(value, 0, &u32val); + if (ret) + goto syntax_error; + + ts_cmdline_props[i] = PROPERTY_ENTRY_U32(name, u32val); + } else { + ts_cmdline_props[i] = PROPERTY_ENTRY_STRING(name, value); + } + } + + if (!i || str) + goto syntax_error; + + ts_data = &ts_cmdline_data; + return 1; + +syntax_error: + pr_err("Invalid '%s' value for 'i2c_touchscreen_props='\n", orig_str); + return 1; /* "i2c_touchscreen_props=" is still a known parameter */ +} +__setup("i2c_touchscreen_props=", ts_parse_props); + static struct notifier_block ts_dmi_notifier = { .notifier_call = ts_dmi_notifier_call, }; @@ -1859,13 +1956,25 @@ static struct notifier_block ts_dmi_notifier = { static int __init ts_dmi_init(void) { const struct dmi_system_id *dmi_id; + struct ts_dmi_data *ts_data_dmi; int error; dmi_id = dmi_first_match(touchscreen_dmi_table); - if (!dmi_id) + ts_data_dmi = dmi_id ? dmi_id->driver_data : NULL; + + if (ts_data) { + /* + * Kernel cmdline provided data takes precedence, copy over + * DMI efi_embedded_fw info if available. + */ + if (ts_data_dmi) + ts_data->embedded_fw = ts_data_dmi->embedded_fw; + } else if (ts_data_dmi) { + ts_data = ts_data_dmi; + } else { return 0; /* Not an error */ + } - ts_data = dmi_id->driver_data; /* Some dmi table entries only provide an efi_embedded_fw_desc */ if (!ts_data->properties) return 0; diff --git a/drivers/platform/x86/x86-android-tablets/Kconfig b/drivers/platform/x86/x86-android-tablets/Kconfig index 6603461d4273..b591419de80c 100644 --- a/drivers/platform/x86/x86-android-tablets/Kconfig +++ b/drivers/platform/x86/x86-android-tablets/Kconfig @@ -6,6 +6,8 @@ config X86_ANDROID_TABLETS tristate "X86 Android tablet support" depends on I2C && SPI && SERIAL_DEV_BUS && ACPI && EFI && GPIOLIB && PMIC_OPREGION + select NEW_LEDS + select LEDS_CLASS help X86 tablets which ship with Android as (part of) the factory image typically have various problems with their DSDTs. The factory kernels diff --git a/drivers/pmdomain/imx/gpcv2.c b/drivers/pmdomain/imx/gpcv2.c index 4b828d74a606..856eaac0ec14 100644 --- a/drivers/pmdomain/imx/gpcv2.c +++ b/drivers/pmdomain/imx/gpcv2.c @@ -393,6 +393,17 @@ static int imx_pgc_power_up(struct generic_pm_domain *genpd) * automatically there. Just add a delay and suppose the handshake finish * after that. */ + + /* + * For some BLK-CTL module (eg. AudioMix on i.MX8MP) doesn't have BUS + * clk-en bit, it is better to add delay here, as the BLK-CTL module + * doesn't need to care about how it is powered up. + * + * regmap_read_bypassed() is to make sure the above write IO transaction + * already reaches target before udelay() + */ + regmap_read_bypassed(domain->regmap, domain->regs->hsk, ®_val); + udelay(5); } /* Disable reset clocks for all devices in the domain */ diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c index f16f73581634..01338d4c2d9e 100644 --- a/fs/9p/vfs_dentry.c +++ b/fs/9p/vfs_dentry.c @@ -48,12 +48,17 @@ static int v9fs_cached_dentry_delete(const struct dentry *dentry) static void v9fs_dentry_release(struct dentry *dentry) { struct hlist_node *p, *n; + struct hlist_head head; p9_debug(P9_DEBUG_VFS, " dentry: %pd (%p)\n", dentry, dentry); - hlist_for_each_safe(p, n, (struct hlist_head *)&dentry->d_fsdata) + + spin_lock(&dentry->d_lock); + hlist_move_list((struct hlist_head *)&dentry->d_fsdata, &head); + spin_unlock(&dentry->d_lock); + + hlist_for_each_safe(p, n, &head) p9_fid_put(hlist_entry(p, struct p9_fid, dlist)); - dentry->d_fsdata = NULL; } static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 7a3308d77606..fd72fc38c8f5 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -348,6 +348,7 @@ void v9fs_evict_inode(struct inode *inode) __le32 __maybe_unused version; if (!is_bad_inode(inode)) { + netfs_wait_for_outstanding_io(inode); truncate_inode_pages_final(&inode->i_data); version = cpu_to_le32(v9inode->qid.version); diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 94fc049aff58..15bb7989c387 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -648,6 +648,7 @@ void afs_evict_inode(struct inode *inode) ASSERTCMP(inode->i_ino, ==, vnode->fid.vnode); + netfs_wait_for_outstanding_io(inode); truncate_inode_pages_final(&inode->i_data); afs_set_cache_aux(vnode, &aux); diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index 97f50e9fd9eb..297487ee8323 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -140,6 +140,11 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt) put_page(page); if (ret < 0) return ret; + + /* Don't cross a backup volume mountpoint from a backup volume */ + if (src_as->volume && src_as->volume->type == AFSVL_BACKVOL && + ctx->type == AFSVL_BACKVOL) + return -ENODEV; } return 0; diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c index 692b1c7d5018..4321f9fb73bd 100644 --- a/fs/bcachefs/backpointers.c +++ b/fs/bcachefs/backpointers.c @@ -690,7 +690,7 @@ static int check_extent_to_backpointers(struct btree_trans *trans, ptrs = bch2_bkey_ptrs_c(k); bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { - struct bpos bucket_pos; + struct bpos bucket_pos = POS_MIN; struct bch_backpointer bp; if (p.ptr.cached) diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h index bc0ea2c4efef..2a538eb2af11 100644 --- a/fs/bcachefs/bcachefs.h +++ b/fs/bcachefs/bcachefs.h @@ -457,6 +457,7 @@ enum bch_time_stats { }; #include "alloc_types.h" +#include "btree_gc_types.h" #include "btree_types.h" #include "btree_node_scan_types.h" #include "btree_write_buffer_types.h" @@ -488,49 +489,6 @@ enum bch_time_stats { struct btree; -enum gc_phase { - GC_PHASE_NOT_RUNNING, - GC_PHASE_START, - GC_PHASE_SB, - - GC_PHASE_BTREE_stripes, - GC_PHASE_BTREE_extents, - GC_PHASE_BTREE_inodes, - GC_PHASE_BTREE_dirents, - GC_PHASE_BTREE_xattrs, - GC_PHASE_BTREE_alloc, - GC_PHASE_BTREE_quotas, - GC_PHASE_BTREE_reflink, - GC_PHASE_BTREE_subvolumes, - GC_PHASE_BTREE_snapshots, - GC_PHASE_BTREE_lru, - GC_PHASE_BTREE_freespace, - GC_PHASE_BTREE_need_discard, - GC_PHASE_BTREE_backpointers, - GC_PHASE_BTREE_bucket_gens, - GC_PHASE_BTREE_snapshot_trees, - GC_PHASE_BTREE_deleted_inodes, - GC_PHASE_BTREE_logged_ops, - GC_PHASE_BTREE_rebalance_work, - GC_PHASE_BTREE_subvolume_children, - - GC_PHASE_PENDING_DELETE, -}; - -struct gc_pos { - enum gc_phase phase; - u16 level; - struct bpos pos; -}; - -struct reflink_gc { - u64 offset; - u32 size; - u32 refcount; -}; - -typedef GENRADIX(struct reflink_gc) reflink_gc_table; - struct io_count { u64 sectors[2][BCH_DATA_NR]; }; diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h index d801e19cb489..90c12fe2a2cd 100644 --- a/fs/bcachefs/bcachefs_format.h +++ b/fs/bcachefs/bcachefs_format.h @@ -503,16 +503,22 @@ struct bch_sb_field { #include "alloc_background_format.h" #include "extents_format.h" -#include "reflink_format.h" #include "ec_format.h" -#include "inode_format.h" #include "dirent_format.h" -#include "xattr_format.h" -#include "quota_format.h" +#include "disk_groups_format.h" +#include "inode_format.h" +#include "journal_seq_blacklist_format.h" #include "logged_ops_format.h" +#include "quota_format.h" +#include "reflink_format.h" +#include "replicas_format.h" #include "snapshot_format.h" #include "subvolume_format.h" #include "sb-counters_format.h" +#include "sb-downgrade_format.h" +#include "sb-errors_format.h" +#include "sb-members_format.h" +#include "xattr_format.h" enum bch_sb_field_type { #define x(f, nr) BCH_SB_FIELD_##f = nr, @@ -545,107 +551,6 @@ struct bch_sb_field_journal_v2 { } d[]; }; -/* BCH_SB_FIELD_members_v1: */ - -#define BCH_MIN_NR_NBUCKETS (1 << 6) - -#define BCH_IOPS_MEASUREMENTS() \ - x(seqread, 0) \ - x(seqwrite, 1) \ - x(randread, 2) \ - x(randwrite, 3) - -enum bch_iops_measurement { -#define x(t, n) BCH_IOPS_##t = n, - BCH_IOPS_MEASUREMENTS() -#undef x - BCH_IOPS_NR -}; - -#define BCH_MEMBER_ERROR_TYPES() \ - x(read, 0) \ - x(write, 1) \ - x(checksum, 2) - -enum bch_member_error_type { -#define x(t, n) BCH_MEMBER_ERROR_##t = n, - BCH_MEMBER_ERROR_TYPES() -#undef x - BCH_MEMBER_ERROR_NR -}; - -struct bch_member { - __uuid_t uuid; - __le64 nbuckets; /* device size */ - __le16 first_bucket; /* index of first bucket used */ - __le16 bucket_size; /* sectors */ - __u8 btree_bitmap_shift; - __u8 pad[3]; - __le64 last_mount; /* time_t */ - - __le64 flags; - __le32 iops[4]; - __le64 errors[BCH_MEMBER_ERROR_NR]; - __le64 errors_at_reset[BCH_MEMBER_ERROR_NR]; - __le64 errors_reset_time; - __le64 seq; - __le64 btree_allocated_bitmap; - /* - * On recovery from a clean shutdown we don't normally read the journal, - * but we still want to resume writing from where we left off so we - * don't overwrite more than is necessary, for list journal debugging: - */ - __le32 last_journal_bucket; - __le32 last_journal_bucket_offset; -}; - -/* - * This limit comes from the bucket_gens array - it's a single allocation, and - * kernel allocation are limited to INT_MAX - */ -#define BCH_MEMBER_NBUCKETS_MAX (INT_MAX - 64) - -#define BCH_MEMBER_V1_BYTES 56 - -LE64_BITMASK(BCH_MEMBER_STATE, struct bch_member, flags, 0, 4) -/* 4-14 unused, was TIER, HAS_(META)DATA, REPLACEMENT */ -LE64_BITMASK(BCH_MEMBER_DISCARD, struct bch_member, flags, 14, 15) -LE64_BITMASK(BCH_MEMBER_DATA_ALLOWED, struct bch_member, flags, 15, 20) -LE64_BITMASK(BCH_MEMBER_GROUP, struct bch_member, flags, 20, 28) -LE64_BITMASK(BCH_MEMBER_DURABILITY, struct bch_member, flags, 28, 30) -LE64_BITMASK(BCH_MEMBER_FREESPACE_INITIALIZED, - struct bch_member, flags, 30, 31) - -#if 0 -LE64_BITMASK(BCH_MEMBER_NR_READ_ERRORS, struct bch_member, flags[1], 0, 20); -LE64_BITMASK(BCH_MEMBER_NR_WRITE_ERRORS,struct bch_member, flags[1], 20, 40); -#endif - -#define BCH_MEMBER_STATES() \ - x(rw, 0) \ - x(ro, 1) \ - x(failed, 2) \ - x(spare, 3) - -enum bch_member_state { -#define x(t, n) BCH_MEMBER_STATE_##t = n, - BCH_MEMBER_STATES() -#undef x - BCH_MEMBER_STATE_NR -}; - -struct bch_sb_field_members_v1 { - struct bch_sb_field field; - struct bch_member _members[]; //Members are now variable size -}; - -struct bch_sb_field_members_v2 { - struct bch_sb_field field; - __le16 member_bytes; //size of single member entry - u8 pad[6]; - struct bch_member _members[]; -}; - /* BCH_SB_FIELD_crypt: */ struct nonce { @@ -694,8 +599,6 @@ LE64_BITMASK(BCH_KDF_SCRYPT_N, struct bch_sb_field_crypt, kdf_flags, 0, 16); LE64_BITMASK(BCH_KDF_SCRYPT_R, struct bch_sb_field_crypt, kdf_flags, 16, 32); LE64_BITMASK(BCH_KDF_SCRYPT_P, struct bch_sb_field_crypt, kdf_flags, 32, 48); -/* BCH_SB_FIELD_replicas: */ - #define BCH_DATA_TYPES() \ x(free, 0) \ x(sb, 1) \ @@ -738,50 +641,6 @@ static inline bool data_type_is_hidden(enum bch_data_type type) } } -struct bch_replicas_entry_v0 { - __u8 data_type; - __u8 nr_devs; - __u8 devs[]; -} __packed; - -struct bch_sb_field_replicas_v0 { - struct bch_sb_field field; - struct bch_replicas_entry_v0 entries[]; -} __packed __aligned(8); - -struct bch_replicas_entry_v1 { - __u8 data_type; - __u8 nr_devs; - __u8 nr_required; - __u8 devs[]; -} __packed; - -#define replicas_entry_bytes(_i) \ - (offsetof(typeof(*(_i)), devs) + (_i)->nr_devs) - -struct bch_sb_field_replicas { - struct bch_sb_field field; - struct bch_replicas_entry_v1 entries[]; -} __packed __aligned(8); - -/* BCH_SB_FIELD_disk_groups: */ - -#define BCH_SB_LABEL_SIZE 32 - -struct bch_disk_group { - __u8 label[BCH_SB_LABEL_SIZE]; - __le64 flags[2]; -} __packed __aligned(8); - -LE64_BITMASK(BCH_GROUP_DELETED, struct bch_disk_group, flags[0], 0, 1) -LE64_BITMASK(BCH_GROUP_DATA_ALLOWED, struct bch_disk_group, flags[0], 1, 6) -LE64_BITMASK(BCH_GROUP_PARENT, struct bch_disk_group, flags[0], 6, 24) - -struct bch_sb_field_disk_groups { - struct bch_sb_field field; - struct bch_disk_group entries[]; -} __packed __aligned(8); - /* * On clean shutdown, store btree roots and current journal sequence number in * the superblock: @@ -809,27 +668,6 @@ struct bch_sb_field_clean { __u64 _data[]; }; -struct journal_seq_blacklist_entry { - __le64 start; - __le64 end; -}; - -struct bch_sb_field_journal_seq_blacklist { - struct bch_sb_field field; - struct journal_seq_blacklist_entry start[]; -}; - -struct bch_sb_field_errors { - struct bch_sb_field field; - struct bch_sb_field_error_entry { - __le64 v; - __le64 last_error_time; - } entries[]; -}; - -LE64_BITMASK(BCH_SB_ERROR_ENTRY_ID, struct bch_sb_field_error_entry, v, 0, 16); -LE64_BITMASK(BCH_SB_ERROR_ENTRY_NR, struct bch_sb_field_error_entry, v, 16, 64); - struct bch_sb_field_ext { struct bch_sb_field field; __le64 recovery_passes_required[2]; @@ -837,18 +675,6 @@ struct bch_sb_field_ext { __le64 btrees_lost_data; }; -struct bch_sb_field_downgrade_entry { - __le16 version; - __le64 recovery_passes[2]; - __le16 nr_errors; - __le16 errors[] __counted_by(nr_errors); -} __packed __aligned(2); - -struct bch_sb_field_downgrade { - struct bch_sb_field field; - struct bch_sb_field_downgrade_entry entries[]; -}; - /* Superblock: */ /* @@ -909,7 +735,6 @@ unsigned bcachefs_metadata_required_upgrade_below = bcachefs_metadata_version_re #define bcachefs_metadata_version_current (bcachefs_metadata_version_max - 1) #define BCH_SB_SECTOR 8 -#define BCH_SB_MEMBERS_MAX 64 /* XXX kill */ #define BCH_SB_LAYOUT_SIZE_BITS_MAX 16 /* 32 MB */ diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c index 8035c8b797ab..dc97991bcd6a 100644 --- a/fs/bcachefs/btree_gc.c +++ b/fs/bcachefs/btree_gc.c @@ -585,16 +585,17 @@ static int bch2_gc_mark_key(struct btree_trans *trans, enum btree_id btree_id, if (fsck_err_on(k.k->version.lo > atomic64_read(&c->key_version), c, bkey_version_in_future, - "key version number higher than recorded: %llu > %llu", - k.k->version.lo, - atomic64_read(&c->key_version))) + "key version number higher than recorded %llu\n %s", + atomic64_read(&c->key_version), + (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) atomic64_set(&c->key_version, k.k->version.lo); } if (mustfix_fsck_err_on(level && !bch2_dev_btree_bitmap_marked(c, k), c, btree_bitmap_not_marked, "btree ptr not marked in member info btree allocated bitmap\n %s", - (bch2_bkey_val_to_text(&buf, c, k), + (printbuf_reset(&buf), + bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { mutex_lock(&c->sb_lock); bch2_dev_btree_bitmap_mark(c, k); @@ -673,8 +674,7 @@ static int bch2_gc_btree(struct btree_trans *trans, enum btree_id btree, bool in static inline int btree_id_gc_phase_cmp(enum btree_id l, enum btree_id r) { - return (int) btree_id_to_gc_phase(l) - - (int) btree_id_to_gc_phase(r); + return cmp_int(gc_btree_order(l), gc_btree_order(r)); } static int bch2_gc_btrees(struct bch_fs *c) @@ -711,7 +711,7 @@ fsck_err: static int bch2_mark_superblocks(struct bch_fs *c) { mutex_lock(&c->sb_lock); - gc_pos_set(c, gc_phase(GC_PHASE_SB)); + gc_pos_set(c, gc_phase(GC_PHASE_sb)); int ret = bch2_trans_mark_dev_sbs_flags(c, BTREE_TRIGGER_gc); mutex_unlock(&c->sb_lock); @@ -1209,7 +1209,7 @@ int bch2_check_allocations(struct bch_fs *c) if (ret) goto out; - gc_pos_set(c, gc_phase(GC_PHASE_START)); + gc_pos_set(c, gc_phase(GC_PHASE_start)); ret = bch2_mark_superblocks(c); BUG_ON(ret); @@ -1231,7 +1231,7 @@ out: percpu_down_write(&c->mark_lock); /* Indicates that gc is no longer in progress: */ - __gc_pos_set(c, gc_phase(GC_PHASE_NOT_RUNNING)); + __gc_pos_set(c, gc_phase(GC_PHASE_not_running)); bch2_gc_free(c); percpu_up_write(&c->mark_lock); diff --git a/fs/bcachefs/btree_gc.h b/fs/bcachefs/btree_gc.h index 1b6489d8e0f4..876d81e2017d 100644 --- a/fs/bcachefs/btree_gc.h +++ b/fs/bcachefs/btree_gc.h @@ -3,6 +3,7 @@ #define _BCACHEFS_BTREE_GC_H #include "bkey.h" +#include "btree_gc_types.h" #include "btree_types.h" int bch2_check_topology(struct bch_fs *); @@ -32,36 +33,15 @@ int bch2_check_allocations(struct bch_fs *); /* Position of (the start of) a gc phase: */ static inline struct gc_pos gc_phase(enum gc_phase phase) { - return (struct gc_pos) { - .phase = phase, - .level = 0, - .pos = POS_MIN, - }; -} - -static inline int gc_pos_cmp(struct gc_pos l, struct gc_pos r) -{ - return cmp_int(l.phase, r.phase) ?: - -cmp_int(l.level, r.level) ?: - bpos_cmp(l.pos, r.pos); -} - -static inline enum gc_phase btree_id_to_gc_phase(enum btree_id id) -{ - switch (id) { -#define x(name, v, ...) case BTREE_ID_##name: return GC_PHASE_BTREE_##name; - BCH_BTREE_IDS() -#undef x - default: - BUG(); - } + return (struct gc_pos) { .phase = phase, }; } static inline struct gc_pos gc_pos_btree(enum btree_id btree, unsigned level, struct bpos pos) { return (struct gc_pos) { - .phase = btree_id_to_gc_phase(btree), + .phase = GC_PHASE_btree, + .btree = btree, .level = level, .pos = pos, }; @@ -76,6 +56,22 @@ static inline struct gc_pos gc_pos_btree_node(struct btree *b) return gc_pos_btree(b->c.btree_id, b->c.level, b->key.k.p); } +static inline int gc_btree_order(enum btree_id btree) +{ + if (btree == BTREE_ID_stripes) + return -1; + return btree; +} + +static inline int gc_pos_cmp(struct gc_pos l, struct gc_pos r) +{ + return cmp_int(l.phase, r.phase) ?: + cmp_int(gc_btree_order(l.btree), + gc_btree_order(r.btree)) ?: + -cmp_int(l.level, r.level) ?: + bpos_cmp(l.pos, r.pos); +} + static inline bool gc_visited(struct bch_fs *c, struct gc_pos pos) { unsigned seq; diff --git a/fs/bcachefs/btree_gc_types.h b/fs/bcachefs/btree_gc_types.h new file mode 100644 index 000000000000..b82c24bcc088 --- /dev/null +++ b/fs/bcachefs/btree_gc_types.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BCACHEFS_BTREE_GC_TYPES_H +#define _BCACHEFS_BTREE_GC_TYPES_H + +#include <linux/generic-radix-tree.h> + +enum gc_phase { + GC_PHASE_not_running, + GC_PHASE_start, + GC_PHASE_sb, + GC_PHASE_btree, +}; + +struct gc_pos { + enum gc_phase phase:8; + enum btree_id btree:8; + u16 level; + struct bpos pos; +}; + +struct reflink_gc { + u64 offset; + u32 size; + u32 refcount; +}; + +typedef GENRADIX(struct reflink_gc) reflink_gc_table; + +#endif /* _BCACHEFS_BTREE_GC_TYPES_H */ diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index cbf8f5d90602..829c1b91477d 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -519,7 +519,7 @@ void bch2_btree_init_next(struct btree_trans *trans, struct btree *b) static void btree_err_msg(struct printbuf *out, struct bch_fs *c, struct bch_dev *ca, - struct btree *b, struct bset *i, + struct btree *b, struct bset *i, struct bkey_packed *k, unsigned offset, int write) { prt_printf(out, bch2_log_msg(c, "%s"), @@ -537,15 +537,20 @@ static void btree_err_msg(struct printbuf *out, struct bch_fs *c, b->written, btree_ptr_sectors_written(&b->key)); if (i) prt_printf(out, " bset u64s %u", le16_to_cpu(i->u64s)); + if (k) + prt_printf(out, " bset byte offset %lu", + (unsigned long)(void *)k - + ((unsigned long)(void *)i & ~511UL)); prt_str(out, ": "); } -__printf(9, 10) +__printf(10, 11) static int __btree_err(int ret, struct bch_fs *c, struct bch_dev *ca, struct btree *b, struct bset *i, + struct bkey_packed *k, int write, bool have_retry, enum bch_sb_error_id err_type, @@ -555,7 +560,7 @@ static int __btree_err(int ret, bool silent = c->curr_recovery_pass == BCH_RECOVERY_PASS_scan_for_btree_nodes; va_list args; - btree_err_msg(&out, c, ca, b, i, b->written, write); + btree_err_msg(&out, c, ca, b, i, k, b->written, write); va_start(args, fmt); prt_vprintf(&out, fmt, args); @@ -611,9 +616,9 @@ fsck_err: return ret; } -#define btree_err(type, c, ca, b, i, _err_type, msg, ...) \ +#define btree_err(type, c, ca, b, i, k, _err_type, msg, ...) \ ({ \ - int _ret = __btree_err(type, c, ca, b, i, write, have_retry, \ + int _ret = __btree_err(type, c, ca, b, i, k, write, have_retry, \ BCH_FSCK_ERR_##_err_type, \ msg, ##__VA_ARGS__); \ \ @@ -690,7 +695,7 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca, btree_err_on(!bch2_version_compatible(version), -BCH_ERR_btree_node_read_err_incompatible, - c, ca, b, i, + c, ca, b, i, NULL, btree_node_unsupported_version, "unsupported bset version %u.%u", BCH_VERSION_MAJOR(version), @@ -698,7 +703,7 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca, if (btree_err_on(version < c->sb.version_min, -BCH_ERR_btree_node_read_err_fixable, - c, NULL, b, i, + c, NULL, b, i, NULL, btree_node_bset_older_than_sb_min, "bset version %u older than superblock version_min %u", version, c->sb.version_min)) { @@ -711,7 +716,7 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca, if (btree_err_on(BCH_VERSION_MAJOR(version) > BCH_VERSION_MAJOR(c->sb.version), -BCH_ERR_btree_node_read_err_fixable, - c, NULL, b, i, + c, NULL, b, i, NULL, btree_node_bset_newer_than_sb, "bset version %u newer than superblock version %u", version, c->sb.version)) { @@ -723,13 +728,13 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca, btree_err_on(BSET_SEPARATE_WHITEOUTS(i), -BCH_ERR_btree_node_read_err_incompatible, - c, ca, b, i, + c, ca, b, i, NULL, btree_node_unsupported_version, "BSET_SEPARATE_WHITEOUTS no longer supported"); if (btree_err_on(offset + sectors > btree_sectors(c), -BCH_ERR_btree_node_read_err_fixable, - c, ca, b, i, + c, ca, b, i, NULL, bset_past_end_of_btree_node, "bset past end of btree node")) { i->u64s = 0; @@ -739,13 +744,13 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca, btree_err_on(offset && !i->u64s, -BCH_ERR_btree_node_read_err_fixable, - c, ca, b, i, + c, ca, b, i, NULL, bset_empty, "empty bset"); btree_err_on(BSET_OFFSET(i) && BSET_OFFSET(i) != offset, -BCH_ERR_btree_node_read_err_want_retry, - c, ca, b, i, + c, ca, b, i, NULL, bset_wrong_sector_offset, "bset at wrong sector offset"); @@ -761,20 +766,20 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca, /* XXX endianness */ btree_err_on(bp->seq != bn->keys.seq, -BCH_ERR_btree_node_read_err_must_retry, - c, ca, b, NULL, + c, ca, b, NULL, NULL, bset_bad_seq, "incorrect sequence number (wrong btree node)"); } btree_err_on(BTREE_NODE_ID(bn) != b->c.btree_id, -BCH_ERR_btree_node_read_err_must_retry, - c, ca, b, i, + c, ca, b, i, NULL, btree_node_bad_btree, "incorrect btree id"); btree_err_on(BTREE_NODE_LEVEL(bn) != b->c.level, -BCH_ERR_btree_node_read_err_must_retry, - c, ca, b, i, + c, ca, b, i, NULL, btree_node_bad_level, "incorrect level"); @@ -793,7 +798,7 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca, btree_err_on(!bpos_eq(b->data->min_key, bp->min_key), -BCH_ERR_btree_node_read_err_must_retry, - c, ca, b, NULL, + c, ca, b, NULL, NULL, btree_node_bad_min_key, "incorrect min_key: got %s should be %s", (printbuf_reset(&buf1), @@ -804,7 +809,7 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca, btree_err_on(!bpos_eq(bn->max_key, b->key.k.p), -BCH_ERR_btree_node_read_err_must_retry, - c, ca, b, i, + c, ca, b, i, NULL, btree_node_bad_max_key, "incorrect max key %s", (printbuf_reset(&buf1), @@ -816,7 +821,7 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca, btree_err_on(bch2_bkey_format_invalid(c, &bn->format, write, &buf1), -BCH_ERR_btree_node_read_err_bad_node, - c, ca, b, i, + c, ca, b, i, NULL, btree_node_bad_format, "invalid bkey format: %s\n %s", buf1.buf, (printbuf_reset(&buf2), @@ -883,7 +888,7 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b, if (btree_err_on(bkey_p_next(k) > vstruct_last(i), -BCH_ERR_btree_node_read_err_fixable, - c, NULL, b, i, + c, NULL, b, i, k, btree_node_bkey_past_bset_end, "key extends past end of bset")) { i->u64s = cpu_to_le16((u64 *) k - i->_data); @@ -892,14 +897,14 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b, if (btree_err_on(k->format > KEY_FORMAT_CURRENT, -BCH_ERR_btree_node_read_err_fixable, - c, NULL, b, i, + c, NULL, b, i, k, btree_node_bkey_bad_format, "invalid bkey format %u", k->format)) goto drop_this_key; if (btree_err_on(!bkeyp_u64s_valid(&b->format, k), -BCH_ERR_btree_node_read_err_fixable, - c, NULL, b, i, + c, NULL, b, i, k, btree_node_bkey_bad_u64s, "bad k->u64s %u (min %u max %zu)", k->u64s, bkeyp_key_u64s(&b->format, k), @@ -921,7 +926,7 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b, bch2_bkey_val_to_text(&buf, c, u.s_c); btree_err(-BCH_ERR_btree_node_read_err_fixable, - c, NULL, b, i, + c, NULL, b, i, k, btree_node_bad_bkey, "invalid bkey: %s", buf.buf); goto drop_this_key; @@ -942,7 +947,7 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b, bch2_bkey_to_text(&buf, u.k); if (btree_err(-BCH_ERR_btree_node_read_err_fixable, - c, NULL, b, i, + c, NULL, b, i, k, btree_node_bkey_out_of_order, "%s", buf.buf)) goto drop_this_key; @@ -1011,13 +1016,13 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, if (bch2_meta_read_fault("btree")) btree_err(-BCH_ERR_btree_node_read_err_must_retry, - c, ca, b, NULL, + c, ca, b, NULL, NULL, btree_node_fault_injected, "dynamic fault"); btree_err_on(le64_to_cpu(b->data->magic) != bset_magic(c), -BCH_ERR_btree_node_read_err_must_retry, - c, ca, b, NULL, + c, ca, b, NULL, NULL, btree_node_bad_magic, "bad magic: want %llx, got %llx", bset_magic(c), le64_to_cpu(b->data->magic)); @@ -1032,7 +1037,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, btree_err_on(b->data->keys.seq != bp->seq, -BCH_ERR_btree_node_read_err_must_retry, - c, ca, b, NULL, + c, ca, b, NULL, NULL, btree_node_bad_seq, "got wrong btree node: got\n%s", (printbuf_reset(&buf), @@ -1041,7 +1046,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, } else { btree_err_on(!b->data->keys.seq, -BCH_ERR_btree_node_read_err_must_retry, - c, ca, b, NULL, + c, ca, b, NULL, NULL, btree_node_bad_seq, "bad btree header: seq 0\n%s", (printbuf_reset(&buf), @@ -1060,7 +1065,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, btree_err_on(!bch2_checksum_type_valid(c, BSET_CSUM_TYPE(i)), -BCH_ERR_btree_node_read_err_want_retry, - c, ca, b, i, + c, ca, b, i, NULL, bset_unknown_csum, "unknown checksum type %llu", BSET_CSUM_TYPE(i)); @@ -1073,7 +1078,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, btree_err_on(csum_bad, -BCH_ERR_btree_node_read_err_want_retry, - c, ca, b, i, + c, ca, b, i, NULL, bset_bad_csum, "%s", (printbuf_reset(&buf), @@ -1088,7 +1093,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, btree_err_on(btree_node_type_is_extents(btree_node_type(b)) && !BTREE_NODE_NEW_EXTENT_OVERWRITE(b->data), -BCH_ERR_btree_node_read_err_incompatible, - c, NULL, b, NULL, + c, NULL, b, NULL, NULL, btree_node_unsupported_version, "btree node does not have NEW_EXTENT_OVERWRITE set"); @@ -1102,7 +1107,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, btree_err_on(!bch2_checksum_type_valid(c, BSET_CSUM_TYPE(i)), -BCH_ERR_btree_node_read_err_want_retry, - c, ca, b, i, + c, ca, b, i, NULL, bset_unknown_csum, "unknown checksum type %llu", BSET_CSUM_TYPE(i)); @@ -1114,7 +1119,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, btree_err_on(csum_bad, -BCH_ERR_btree_node_read_err_want_retry, - c, ca, b, i, + c, ca, b, i, NULL, bset_bad_csum, "%s", (printbuf_reset(&buf), @@ -1152,14 +1157,14 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, btree_err_on(blacklisted && first, -BCH_ERR_btree_node_read_err_fixable, - c, ca, b, i, + c, ca, b, i, NULL, bset_blacklisted_journal_seq, "first btree node bset has blacklisted journal seq (%llu)", le64_to_cpu(i->journal_seq)); btree_err_on(blacklisted && ptr_written, -BCH_ERR_btree_node_read_err_fixable, - c, ca, b, i, + c, ca, b, i, NULL, first_bset_blacklisted_journal_seq, "found blacklisted bset (journal seq %llu) in btree node at offset %u-%u/%u", le64_to_cpu(i->journal_seq), @@ -1178,7 +1183,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, if (ptr_written) { btree_err_on(b->written < ptr_written, -BCH_ERR_btree_node_read_err_want_retry, - c, ca, b, NULL, + c, ca, b, NULL, NULL, btree_node_data_missing, "btree node data missing: expected %u sectors, found %u", ptr_written, b->written); @@ -1191,7 +1196,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, le64_to_cpu(bne->keys.journal_seq), true), -BCH_ERR_btree_node_read_err_want_retry, - c, ca, b, NULL, + c, ca, b, NULL, NULL, btree_node_bset_after_end, "found bset signature after last bset"); } @@ -1235,7 +1240,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, bch2_bkey_val_to_text(&buf, c, u.s_c); btree_err(-BCH_ERR_btree_node_read_err_fixable, - c, NULL, b, i, + c, NULL, b, i, k, btree_node_bad_bkey, "%s", buf.buf); @@ -1471,18 +1476,18 @@ static CLOSURE_CALLBACK(btree_node_read_all_replicas_done) written2 = btree_node_sectors_written(c, ra->buf[i]); if (btree_err_on(written2 != written, -BCH_ERR_btree_node_read_err_fixable, - c, NULL, b, NULL, + c, NULL, b, NULL, NULL, btree_node_replicas_sectors_written_mismatch, "btree node sectors written mismatch: %u != %u", written, written2) || btree_err_on(btree_node_has_extra_bsets(c, written2, ra->buf[i]), -BCH_ERR_btree_node_read_err_fixable, - c, NULL, b, NULL, + c, NULL, b, NULL, NULL, btree_node_bset_after_end, "found bset signature after last bset") || btree_err_on(memcmp(ra->buf[best], ra->buf[i], written << 9), -BCH_ERR_btree_node_read_err_fixable, - c, NULL, b, NULL, + c, NULL, b, NULL, NULL, btree_node_replicas_data_mismatch, "btree node replicas content mismatch")) dump_bset_maps = true; diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c index 75f5e6fe4634..34056aaece00 100644 --- a/fs/bcachefs/btree_key_cache.c +++ b/fs/bcachefs/btree_key_cache.c @@ -424,16 +424,16 @@ static int btree_key_cache_fill(struct btree_trans *trans, goto err; } - if (!bch2_btree_node_relock(trans, ck_path, 0)) { + ret = bch2_trans_relock(trans); + if (ret) { kfree(new_k); - trace_and_count(trans->c, trans_restart_relock_key_cache_fill, trans, _THIS_IP_, ck_path); - ret = btree_trans_restart(trans, BCH_ERR_transaction_restart_key_cache_fill); goto err; } - ret = bch2_trans_relock(trans); - if (ret) { + if (!bch2_btree_node_relock(trans, ck_path, 0)) { kfree(new_k); + trace_and_count(trans->c, trans_restart_relock_key_cache_fill, trans, _THIS_IP_, ck_path); + ret = btree_trans_restart(trans, BCH_ERR_transaction_restart_key_cache_fill); goto err; } } diff --git a/fs/bcachefs/buckets.c b/fs/bcachefs/buckets.c index b469586517a8..ed97712d0db1 100644 --- a/fs/bcachefs/buckets.c +++ b/fs/bcachefs/buckets.c @@ -1134,7 +1134,7 @@ static int __trigger_extent(struct btree_trans *trans, r.e.nr_required = 1; bkey_for_each_ptr_decode(k.k, ptrs, p, entry) { - s64 disk_sectors; + s64 disk_sectors = 0; ret = bch2_trigger_pointer(trans, btree_id, level, k, p, entry, &disk_sectors, flags); if (ret < 0) return ret; diff --git a/fs/bcachefs/disk_groups_format.h b/fs/bcachefs/disk_groups_format.h new file mode 100644 index 000000000000..698990bbf1d2 --- /dev/null +++ b/fs/bcachefs/disk_groups_format.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BCACHEFS_DISK_GROUPS_FORMAT_H +#define _BCACHEFS_DISK_GROUPS_FORMAT_H + +#define BCH_SB_LABEL_SIZE 32 + +struct bch_disk_group { + __u8 label[BCH_SB_LABEL_SIZE]; + __le64 flags[2]; +} __packed __aligned(8); + +LE64_BITMASK(BCH_GROUP_DELETED, struct bch_disk_group, flags[0], 0, 1) +LE64_BITMASK(BCH_GROUP_DATA_ALLOWED, struct bch_disk_group, flags[0], 1, 6) +LE64_BITMASK(BCH_GROUP_PARENT, struct bch_disk_group, flags[0], 6, 24) + +struct bch_sb_field_disk_groups { + struct bch_sb_field field; + struct bch_disk_group entries[]; +} __packed __aligned(8); + +#endif /* _BCACHEFS_DISK_GROUPS_FORMAT_H */ diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c index b26dc7424662..d8b9beca3776 100644 --- a/fs/bcachefs/ec.c +++ b/fs/bcachefs/ec.c @@ -908,7 +908,7 @@ static int __ec_stripe_mem_alloc(struct bch_fs *c, size_t idx, gfp_t gfp) if (!genradix_ptr_alloc(&c->stripes, idx, gfp)) return -BCH_ERR_ENOMEM_ec_stripe_mem_alloc; - if (c->gc_pos.phase != GC_PHASE_NOT_RUNNING && + if (c->gc_pos.phase != GC_PHASE_not_running && !genradix_ptr_alloc(&c->gc_stripes, idx, gfp)) return -BCH_ERR_ENOMEM_ec_stripe_mem_alloc; diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c index 6b69e5cd68dd..54873ecc635c 100644 --- a/fs/bcachefs/fs-io-buffered.c +++ b/fs/bcachefs/fs-io-buffered.c @@ -437,8 +437,8 @@ static void bch2_writepage_io_done(struct bch_write_op *op) */ /* - * PageWriteback is effectively our ref on the inode - fixup i_blocks - * before calling end_page_writeback: + * The writeback flag is effectively our ref on the inode - + * fixup i_blocks before calling folio_end_writeback: */ bch2_i_sectors_acct(c, io->inode, NULL, io->op.i_sectors_delta); @@ -898,7 +898,7 @@ static int __bch2_buffered_write(struct bch_inode_info *inode, darray_for_each(fs, fi) { f = *fi; f_len = min(end, folio_end_pos(f)) - f_pos; - f_copied = copy_page_from_iter_atomic(&f->page, f_offset, f_len, iter); + f_copied = copy_folio_from_iter_atomic(f, f_offset, f_len, iter); if (!f_copied) { folios_trunc(&fs, fi); break; diff --git a/fs/bcachefs/fs-io-direct.c b/fs/bcachefs/fs-io-direct.c index 09d21aef879a..049b61bc9a5b 100644 --- a/fs/bcachefs/fs-io-direct.c +++ b/fs/bcachefs/fs-io-direct.c @@ -609,8 +609,10 @@ ssize_t bch2_direct_write(struct kiocb *req, struct iov_iter *iter) if (unlikely(ret)) goto err_put_write_ref; - if (unlikely((req->ki_pos|iter->count) & (block_bytes(c) - 1))) + if (unlikely((req->ki_pos|iter->count) & (block_bytes(c) - 1))) { + ret = -EINVAL; goto err_put_write_ref; + } inode_dio_begin(&inode->v); bch2_pagecache_block_get(inode); diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index 96040a95cf46..cd388f1702dc 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -1939,8 +1939,7 @@ got_sb: if (IS_ERR(sb)) { ret = PTR_ERR(sb); - ret = bch2_err_class(ret); - return ERR_PTR(ret); + goto err; } c = sb->s_fs_info; @@ -2016,6 +2015,15 @@ out: err_put_super: __bch2_fs_stop(c); deactivate_locked_super(sb); +err: + /* + * On an inconsistency error in recovery we might see an -EROFS derived + * errorcode (from the journal), but we don't want to return that to + * userspace as that causes util-linux to retry the mount RO - which is + * confusing: + */ + if (bch2_err_matches(ret, EROFS) && ret != -EROFS) + ret = -EIO; return ERR_PTR(bch2_err_class(ret)); } diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index c8f57465131c..fd277bd58ed3 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -77,21 +77,17 @@ static int lookup_first_inode(struct btree_trans *trans, u64 inode_nr, struct bkey_s_c k; int ret; - bch2_trans_iter_init(trans, &iter, BTREE_ID_inodes, - POS(0, inode_nr), - BTREE_ITER_all_snapshots); - k = bch2_btree_iter_peek(&iter); - ret = bkey_err(k); - if (ret) - goto err; - - if (!k.k || !bkey_eq(k.k->p, POS(0, inode_nr))) { - ret = -BCH_ERR_ENOENT_inode; - goto err; + for_each_btree_key_norestart(trans, iter, BTREE_ID_inodes, POS(0, inode_nr), + BTREE_ITER_all_snapshots, k, ret) { + if (k.k->p.offset != inode_nr) + break; + if (!bkey_is_inode(k.k)) + continue; + ret = bch2_inode_unpack(k, inode); + goto found; } - - ret = bch2_inode_unpack(k, inode); -err: + ret = -BCH_ERR_ENOENT_inode; +found: bch_err_msg(trans->c, ret, "fetching inode %llu", inode_nr); bch2_trans_iter_exit(trans, &iter); return ret; @@ -770,25 +766,6 @@ static int get_visible_inodes(struct btree_trans *trans, return ret; } -static int check_key_has_snapshot(struct btree_trans *trans, - struct btree_iter *iter, - struct bkey_s_c k) -{ - struct bch_fs *c = trans->c; - struct printbuf buf = PRINTBUF; - int ret = 0; - - if (mustfix_fsck_err_on(!bch2_snapshot_equiv(c, k.k->p.snapshot), c, - bkey_in_missing_snapshot, - "key in missing snapshot: %s", - (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) - ret = bch2_btree_delete_at(trans, iter, - BTREE_UPDATE_internal_snapshot_node) ?: 1; -fsck_err: - printbuf_exit(&buf); - return ret; -} - static int hash_redo_key(struct btree_trans *trans, const struct bch_hash_desc desc, struct bch_hash_info *hash_info, @@ -983,7 +960,7 @@ static int check_inode(struct btree_trans *trans, bool do_update = false; int ret; - ret = check_key_has_snapshot(trans, iter, k); + ret = bch2_check_key_has_snapshot(trans, iter, k); if (ret < 0) goto err; if (ret) @@ -1487,7 +1464,7 @@ static int check_extent(struct btree_trans *trans, struct btree_iter *iter, struct printbuf buf = PRINTBUF; int ret = 0; - ret = check_key_has_snapshot(trans, iter, k); + ret = bch2_check_key_has_snapshot(trans, iter, k); if (ret) { ret = ret < 0 ? ret : 0; goto out; @@ -2010,7 +1987,7 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, struct printbuf buf = PRINTBUF; int ret = 0; - ret = check_key_has_snapshot(trans, iter, k); + ret = bch2_check_key_has_snapshot(trans, iter, k); if (ret) { ret = ret < 0 ? ret : 0; goto out; @@ -2165,7 +2142,7 @@ static int check_xattr(struct btree_trans *trans, struct btree_iter *iter, struct inode_walker_entry *i; int ret; - ret = check_key_has_snapshot(trans, iter, k); + ret = bch2_check_key_has_snapshot(trans, iter, k); if (ret < 0) return ret; if (ret) diff --git a/fs/bcachefs/journal_seq_blacklist_format.h b/fs/bcachefs/journal_seq_blacklist_format.h new file mode 100644 index 000000000000..2566b12dbc04 --- /dev/null +++ b/fs/bcachefs/journal_seq_blacklist_format.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BCACHEFS_JOURNAL_SEQ_BLACKLIST_FORMAT_H +#define _BCACHEFS_JOURNAL_SEQ_BLACKLIST_FORMAT_H + +struct journal_seq_blacklist_entry { + __le64 start; + __le64 end; +}; + +struct bch_sb_field_journal_seq_blacklist { + struct bch_sb_field field; + struct journal_seq_blacklist_entry start[]; +}; + +#endif /* _BCACHEFS_JOURNAL_SEQ_BLACKLIST_FORMAT_H */ diff --git a/fs/bcachefs/mean_and_variance_test.c b/fs/bcachefs/mean_and_variance_test.c index 4c298e74723d..e9d9c0212e44 100644 --- a/fs/bcachefs/mean_and_variance_test.c +++ b/fs/bcachefs/mean_and_variance_test.c @@ -217,4 +217,5 @@ static struct kunit_suite mean_and_variance_test_suite = { kunit_test_suite(mean_and_variance_test_suite); MODULE_AUTHOR("Daniel B. Hill"); +MODULE_DESCRIPTION("bcachefs filesystem mean and variance unit tests"); MODULE_LICENSE("GPL"); diff --git a/fs/bcachefs/replicas_format.h b/fs/bcachefs/replicas_format.h new file mode 100644 index 000000000000..b97208195d06 --- /dev/null +++ b/fs/bcachefs/replicas_format.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BCACHEFS_REPLICAS_FORMAT_H +#define _BCACHEFS_REPLICAS_FORMAT_H + +struct bch_replicas_entry_v0 { + __u8 data_type; + __u8 nr_devs; + __u8 devs[]; +} __packed; + +struct bch_sb_field_replicas_v0 { + struct bch_sb_field field; + struct bch_replicas_entry_v0 entries[]; +} __packed __aligned(8); + +struct bch_replicas_entry_v1 { + __u8 data_type; + __u8 nr_devs; + __u8 nr_required; + __u8 devs[]; +} __packed; + +struct bch_sb_field_replicas { + struct bch_sb_field field; + struct bch_replicas_entry_v1 entries[]; +} __packed __aligned(8); + +#define replicas_entry_bytes(_i) \ + (offsetof(typeof(*(_i)), devs) + (_i)->nr_devs) + +#endif /* _BCACHEFS_REPLICAS_FORMAT_H */ diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c index 390a1bbd2567..3fb23e399ffb 100644 --- a/fs/bcachefs/sb-downgrade.c +++ b/fs/bcachefs/sb-downgrade.c @@ -146,10 +146,17 @@ static int bch2_sb_downgrade_validate(struct bch_sb *sb, struct bch_sb_field *f, for (const struct bch_sb_field_downgrade_entry *i = e->entries; (void *) i < vstruct_end(&e->field); i = downgrade_entry_next_c(i)) { + /* + * Careful: sb_field_downgrade_entry is only 2 byte aligned, but + * section sizes are 8 byte aligned - an empty entry spanning + * the end of the section is allowed (and ignored): + */ + if ((void *) &i->errors[0] > vstruct_end(&e->field)) + break; + if (flags & BCH_VALIDATE_write && - ((void *) &i->errors[0] > vstruct_end(&e->field) || - (void *) downgrade_entry_next_c(i) > vstruct_end(&e->field))) { - prt_printf(err, "downgrade entry overruns end of superblock section)"); + (void *) downgrade_entry_next_c(i) > vstruct_end(&e->field)) { + prt_printf(err, "downgrade entry overruns end of superblock section"); return -BCH_ERR_invalid_sb_downgrade; } diff --git a/fs/bcachefs/sb-downgrade_format.h b/fs/bcachefs/sb-downgrade_format.h new file mode 100644 index 000000000000..cffd932be3ec --- /dev/null +++ b/fs/bcachefs/sb-downgrade_format.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BCACHEFS_SB_DOWNGRADE_FORMAT_H +#define _BCACHEFS_SB_DOWNGRADE_FORMAT_H + +struct bch_sb_field_downgrade_entry { + __le16 version; + __le64 recovery_passes[2]; + __le16 nr_errors; + __le16 errors[] __counted_by(nr_errors); +} __packed __aligned(2); + +struct bch_sb_field_downgrade { + struct bch_sb_field field; + struct bch_sb_field_downgrade_entry entries[]; +}; + +#endif /* _BCACHEFS_SB_DOWNGRADE_FORMAT_H */ diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h new file mode 100644 index 000000000000..84d2763bd597 --- /dev/null +++ b/fs/bcachefs/sb-errors_format.h @@ -0,0 +1,296 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BCACHEFS_SB_ERRORS_FORMAT_H +#define _BCACHEFS_SB_ERRORS_FORMAT_H + +#define BCH_SB_ERRS() \ + x(clean_but_journal_not_empty, 0) \ + x(dirty_but_no_journal_entries, 1) \ + x(dirty_but_no_journal_entries_post_drop_nonflushes, 2) \ + x(sb_clean_journal_seq_mismatch, 3) \ + x(sb_clean_btree_root_mismatch, 4) \ + x(sb_clean_missing, 5) \ + x(jset_unsupported_version, 6) \ + x(jset_unknown_csum, 7) \ + x(jset_last_seq_newer_than_seq, 8) \ + x(jset_past_bucket_end, 9) \ + x(jset_seq_blacklisted, 10) \ + x(journal_entries_missing, 11) \ + x(journal_entry_replicas_not_marked, 12) \ + x(journal_entry_past_jset_end, 13) \ + x(journal_entry_replicas_data_mismatch, 14) \ + x(journal_entry_bkey_u64s_0, 15) \ + x(journal_entry_bkey_past_end, 16) \ + x(journal_entry_bkey_bad_format, 17) \ + x(journal_entry_bkey_invalid, 18) \ + x(journal_entry_btree_root_bad_size, 19) \ + x(journal_entry_blacklist_bad_size, 20) \ + x(journal_entry_blacklist_v2_bad_size, 21) \ + x(journal_entry_blacklist_v2_start_past_end, 22) \ + x(journal_entry_usage_bad_size, 23) \ + x(journal_entry_data_usage_bad_size, 24) \ + x(journal_entry_clock_bad_size, 25) \ + x(journal_entry_clock_bad_rw, 26) \ + x(journal_entry_dev_usage_bad_size, 27) \ + x(journal_entry_dev_usage_bad_dev, 28) \ + x(journal_entry_dev_usage_bad_pad, 29) \ + x(btree_node_unreadable, 30) \ + x(btree_node_fault_injected, 31) \ + x(btree_node_bad_magic, 32) \ + x(btree_node_bad_seq, 33) \ + x(btree_node_unsupported_version, 34) \ + x(btree_node_bset_older_than_sb_min, 35) \ + x(btree_node_bset_newer_than_sb, 36) \ + x(btree_node_data_missing, 37) \ + x(btree_node_bset_after_end, 38) \ + x(btree_node_replicas_sectors_written_mismatch, 39) \ + x(btree_node_replicas_data_mismatch, 40) \ + x(bset_unknown_csum, 41) \ + x(bset_bad_csum, 42) \ + x(bset_past_end_of_btree_node, 43) \ + x(bset_wrong_sector_offset, 44) \ + x(bset_empty, 45) \ + x(bset_bad_seq, 46) \ + x(bset_blacklisted_journal_seq, 47) \ + x(first_bset_blacklisted_journal_seq, 48) \ + x(btree_node_bad_btree, 49) \ + x(btree_node_bad_level, 50) \ + x(btree_node_bad_min_key, 51) \ + x(btree_node_bad_max_key, 52) \ + x(btree_node_bad_format, 53) \ + x(btree_node_bkey_past_bset_end, 54) \ + x(btree_node_bkey_bad_format, 55) \ + x(btree_node_bad_bkey, 56) \ + x(btree_node_bkey_out_of_order, 57) \ + x(btree_root_bkey_invalid, 58) \ + x(btree_root_read_error, 59) \ + x(btree_root_bad_min_key, 60) \ + x(btree_root_bad_max_key, 61) \ + x(btree_node_read_error, 62) \ + x(btree_node_topology_bad_min_key, 63) \ + x(btree_node_topology_bad_max_key, 64) \ + x(btree_node_topology_overwritten_by_prev_node, 65) \ + x(btree_node_topology_overwritten_by_next_node, 66) \ + x(btree_node_topology_interior_node_empty, 67) \ + x(fs_usage_hidden_wrong, 68) \ + x(fs_usage_btree_wrong, 69) \ + x(fs_usage_data_wrong, 70) \ + x(fs_usage_cached_wrong, 71) \ + x(fs_usage_reserved_wrong, 72) \ + x(fs_usage_persistent_reserved_wrong, 73) \ + x(fs_usage_nr_inodes_wrong, 74) \ + x(fs_usage_replicas_wrong, 75) \ + x(dev_usage_buckets_wrong, 76) \ + x(dev_usage_sectors_wrong, 77) \ + x(dev_usage_fragmented_wrong, 78) \ + x(dev_usage_buckets_ec_wrong, 79) \ + x(bkey_version_in_future, 80) \ + x(bkey_u64s_too_small, 81) \ + x(bkey_invalid_type_for_btree, 82) \ + x(bkey_extent_size_zero, 83) \ + x(bkey_extent_size_greater_than_offset, 84) \ + x(bkey_size_nonzero, 85) \ + x(bkey_snapshot_nonzero, 86) \ + x(bkey_snapshot_zero, 87) \ + x(bkey_at_pos_max, 88) \ + x(bkey_before_start_of_btree_node, 89) \ + x(bkey_after_end_of_btree_node, 90) \ + x(bkey_val_size_nonzero, 91) \ + x(bkey_val_size_too_small, 92) \ + x(alloc_v1_val_size_bad, 93) \ + x(alloc_v2_unpack_error, 94) \ + x(alloc_v3_unpack_error, 95) \ + x(alloc_v4_val_size_bad, 96) \ + x(alloc_v4_backpointers_start_bad, 97) \ + x(alloc_key_data_type_bad, 98) \ + x(alloc_key_empty_but_have_data, 99) \ + x(alloc_key_dirty_sectors_0, 100) \ + x(alloc_key_data_type_inconsistency, 101) \ + x(alloc_key_to_missing_dev_bucket, 102) \ + x(alloc_key_cached_inconsistency, 103) \ + x(alloc_key_cached_but_read_time_zero, 104) \ + x(alloc_key_to_missing_lru_entry, 105) \ + x(alloc_key_data_type_wrong, 106) \ + x(alloc_key_gen_wrong, 107) \ + x(alloc_key_dirty_sectors_wrong, 108) \ + x(alloc_key_cached_sectors_wrong, 109) \ + x(alloc_key_stripe_wrong, 110) \ + x(alloc_key_stripe_redundancy_wrong, 111) \ + x(bucket_sector_count_overflow, 112) \ + x(bucket_metadata_type_mismatch, 113) \ + x(need_discard_key_wrong, 114) \ + x(freespace_key_wrong, 115) \ + x(freespace_hole_missing, 116) \ + x(bucket_gens_val_size_bad, 117) \ + x(bucket_gens_key_wrong, 118) \ + x(bucket_gens_hole_wrong, 119) \ + x(bucket_gens_to_invalid_dev, 120) \ + x(bucket_gens_to_invalid_buckets, 121) \ + x(bucket_gens_nonzero_for_invalid_buckets, 122) \ + x(need_discard_freespace_key_to_invalid_dev_bucket, 123) \ + x(need_discard_freespace_key_bad, 124) \ + x(backpointer_bucket_offset_wrong, 125) \ + x(backpointer_to_missing_device, 126) \ + x(backpointer_to_missing_alloc, 127) \ + x(backpointer_to_missing_ptr, 128) \ + x(lru_entry_at_time_0, 129) \ + x(lru_entry_to_invalid_bucket, 130) \ + x(lru_entry_bad, 131) \ + x(btree_ptr_val_too_big, 132) \ + x(btree_ptr_v2_val_too_big, 133) \ + x(btree_ptr_has_non_ptr, 134) \ + x(extent_ptrs_invalid_entry, 135) \ + x(extent_ptrs_no_ptrs, 136) \ + x(extent_ptrs_too_many_ptrs, 137) \ + x(extent_ptrs_redundant_crc, 138) \ + x(extent_ptrs_redundant_stripe, 139) \ + x(extent_ptrs_unwritten, 140) \ + x(extent_ptrs_written_and_unwritten, 141) \ + x(ptr_to_invalid_device, 142) \ + x(ptr_to_duplicate_device, 143) \ + x(ptr_after_last_bucket, 144) \ + x(ptr_before_first_bucket, 145) \ + x(ptr_spans_multiple_buckets, 146) \ + x(ptr_to_missing_backpointer, 147) \ + x(ptr_to_missing_alloc_key, 148) \ + x(ptr_to_missing_replicas_entry, 149) \ + x(ptr_to_missing_stripe, 150) \ + x(ptr_to_incorrect_stripe, 151) \ + x(ptr_gen_newer_than_bucket_gen, 152) \ + x(ptr_too_stale, 153) \ + x(stale_dirty_ptr, 154) \ + x(ptr_bucket_data_type_mismatch, 155) \ + x(ptr_cached_and_erasure_coded, 156) \ + x(ptr_crc_uncompressed_size_too_small, 157) \ + x(ptr_crc_csum_type_unknown, 158) \ + x(ptr_crc_compression_type_unknown, 159) \ + x(ptr_crc_redundant, 160) \ + x(ptr_crc_uncompressed_size_too_big, 161) \ + x(ptr_crc_nonce_mismatch, 162) \ + x(ptr_stripe_redundant, 163) \ + x(reservation_key_nr_replicas_invalid, 164) \ + x(reflink_v_refcount_wrong, 165) \ + x(reflink_p_to_missing_reflink_v, 166) \ + x(stripe_pos_bad, 167) \ + x(stripe_val_size_bad, 168) \ + x(stripe_sector_count_wrong, 169) \ + x(snapshot_tree_pos_bad, 170) \ + x(snapshot_tree_to_missing_snapshot, 171) \ + x(snapshot_tree_to_missing_subvol, 172) \ + x(snapshot_tree_to_wrong_subvol, 173) \ + x(snapshot_tree_to_snapshot_subvol, 174) \ + x(snapshot_pos_bad, 175) \ + x(snapshot_parent_bad, 176) \ + x(snapshot_children_not_normalized, 177) \ + x(snapshot_child_duplicate, 178) \ + x(snapshot_child_bad, 179) \ + x(snapshot_skiplist_not_normalized, 180) \ + x(snapshot_skiplist_bad, 181) \ + x(snapshot_should_not_have_subvol, 182) \ + x(snapshot_to_bad_snapshot_tree, 183) \ + x(snapshot_bad_depth, 184) \ + x(snapshot_bad_skiplist, 185) \ + x(subvol_pos_bad, 186) \ + x(subvol_not_master_and_not_snapshot, 187) \ + x(subvol_to_missing_root, 188) \ + x(subvol_root_wrong_bi_subvol, 189) \ + x(bkey_in_missing_snapshot, 190) \ + x(inode_pos_inode_nonzero, 191) \ + x(inode_pos_blockdev_range, 192) \ + x(inode_unpack_error, 193) \ + x(inode_str_hash_invalid, 194) \ + x(inode_v3_fields_start_bad, 195) \ + x(inode_snapshot_mismatch, 196) \ + x(inode_unlinked_but_clean, 197) \ + x(inode_unlinked_but_nlink_nonzero, 198) \ + x(inode_checksum_type_invalid, 199) \ + x(inode_compression_type_invalid, 200) \ + x(inode_subvol_root_but_not_dir, 201) \ + x(inode_i_size_dirty_but_clean, 202) \ + x(inode_i_sectors_dirty_but_clean, 203) \ + x(inode_i_sectors_wrong, 204) \ + x(inode_dir_wrong_nlink, 205) \ + x(inode_dir_multiple_links, 206) \ + x(inode_multiple_links_but_nlink_0, 207) \ + x(inode_wrong_backpointer, 208) \ + x(inode_wrong_nlink, 209) \ + x(inode_unreachable, 210) \ + x(deleted_inode_but_clean, 211) \ + x(deleted_inode_missing, 212) \ + x(deleted_inode_is_dir, 213) \ + x(deleted_inode_not_unlinked, 214) \ + x(extent_overlapping, 215) \ + x(extent_in_missing_inode, 216) \ + x(extent_in_non_reg_inode, 217) \ + x(extent_past_end_of_inode, 218) \ + x(dirent_empty_name, 219) \ + x(dirent_val_too_big, 220) \ + x(dirent_name_too_long, 221) \ + x(dirent_name_embedded_nul, 222) \ + x(dirent_name_dot_or_dotdot, 223) \ + x(dirent_name_has_slash, 224) \ + x(dirent_d_type_wrong, 225) \ + x(inode_bi_parent_wrong, 226) \ + x(dirent_in_missing_dir_inode, 227) \ + x(dirent_in_non_dir_inode, 228) \ + x(dirent_to_missing_inode, 229) \ + x(dirent_to_missing_subvol, 230) \ + x(dirent_to_itself, 231) \ + x(quota_type_invalid, 232) \ + x(xattr_val_size_too_small, 233) \ + x(xattr_val_size_too_big, 234) \ + x(xattr_invalid_type, 235) \ + x(xattr_name_invalid_chars, 236) \ + x(xattr_in_missing_inode, 237) \ + x(root_subvol_missing, 238) \ + x(root_dir_missing, 239) \ + x(root_inode_not_dir, 240) \ + x(dir_loop, 241) \ + x(hash_table_key_duplicate, 242) \ + x(hash_table_key_wrong_offset, 243) \ + x(unlinked_inode_not_on_deleted_list, 244) \ + x(reflink_p_front_pad_bad, 245) \ + x(journal_entry_dup_same_device, 246) \ + x(inode_bi_subvol_missing, 247) \ + x(inode_bi_subvol_wrong, 248) \ + x(inode_points_to_missing_dirent, 249) \ + x(inode_points_to_wrong_dirent, 250) \ + x(inode_bi_parent_nonzero, 251) \ + x(dirent_to_missing_parent_subvol, 252) \ + x(dirent_not_visible_in_parent_subvol, 253) \ + x(subvol_fs_path_parent_wrong, 254) \ + x(subvol_root_fs_path_parent_nonzero, 255) \ + x(subvol_children_not_set, 256) \ + x(subvol_children_bad, 257) \ + x(subvol_loop, 258) \ + x(subvol_unreachable, 259) \ + x(btree_node_bkey_bad_u64s, 260) \ + x(btree_node_topology_empty_interior_node, 261) \ + x(btree_ptr_v2_min_key_bad, 262) \ + x(btree_root_unreadable_and_scan_found_nothing, 263) \ + x(snapshot_node_missing, 264) \ + x(dup_backpointer_to_bad_csum_extent, 265) \ + x(btree_bitmap_not_marked, 266) \ + x(sb_clean_entry_overrun, 267) \ + x(btree_ptr_v2_written_0, 268) \ + x(subvol_snapshot_bad, 269) \ + x(subvol_inode_bad, 270) + +enum bch_sb_error_id { +#define x(t, n) BCH_FSCK_ERR_##t = n, + BCH_SB_ERRS() +#undef x + BCH_SB_ERR_MAX +}; + +struct bch_sb_field_errors { + struct bch_sb_field field; + struct bch_sb_field_error_entry { + __le64 v; + __le64 last_error_time; + } entries[]; +}; + +LE64_BITMASK(BCH_SB_ERROR_ENTRY_ID, struct bch_sb_field_error_entry, v, 0, 16); +LE64_BITMASK(BCH_SB_ERROR_ENTRY_NR, struct bch_sb_field_error_entry, v, 16, 64); + +#endif /* _BCACHEFS_SB_ERRORS_FORMAT_H */ diff --git a/fs/bcachefs/sb-errors_types.h b/fs/bcachefs/sb-errors_types.h index 666599d3fb9d..40325239c3b0 100644 --- a/fs/bcachefs/sb-errors_types.h +++ b/fs/bcachefs/sb-errors_types.h @@ -4,286 +4,6 @@ #include "darray.h" -#define BCH_SB_ERRS() \ - x(clean_but_journal_not_empty, 0) \ - x(dirty_but_no_journal_entries, 1) \ - x(dirty_but_no_journal_entries_post_drop_nonflushes, 2) \ - x(sb_clean_journal_seq_mismatch, 3) \ - x(sb_clean_btree_root_mismatch, 4) \ - x(sb_clean_missing, 5) \ - x(jset_unsupported_version, 6) \ - x(jset_unknown_csum, 7) \ - x(jset_last_seq_newer_than_seq, 8) \ - x(jset_past_bucket_end, 9) \ - x(jset_seq_blacklisted, 10) \ - x(journal_entries_missing, 11) \ - x(journal_entry_replicas_not_marked, 12) \ - x(journal_entry_past_jset_end, 13) \ - x(journal_entry_replicas_data_mismatch, 14) \ - x(journal_entry_bkey_u64s_0, 15) \ - x(journal_entry_bkey_past_end, 16) \ - x(journal_entry_bkey_bad_format, 17) \ - x(journal_entry_bkey_invalid, 18) \ - x(journal_entry_btree_root_bad_size, 19) \ - x(journal_entry_blacklist_bad_size, 20) \ - x(journal_entry_blacklist_v2_bad_size, 21) \ - x(journal_entry_blacklist_v2_start_past_end, 22) \ - x(journal_entry_usage_bad_size, 23) \ - x(journal_entry_data_usage_bad_size, 24) \ - x(journal_entry_clock_bad_size, 25) \ - x(journal_entry_clock_bad_rw, 26) \ - x(journal_entry_dev_usage_bad_size, 27) \ - x(journal_entry_dev_usage_bad_dev, 28) \ - x(journal_entry_dev_usage_bad_pad, 29) \ - x(btree_node_unreadable, 30) \ - x(btree_node_fault_injected, 31) \ - x(btree_node_bad_magic, 32) \ - x(btree_node_bad_seq, 33) \ - x(btree_node_unsupported_version, 34) \ - x(btree_node_bset_older_than_sb_min, 35) \ - x(btree_node_bset_newer_than_sb, 36) \ - x(btree_node_data_missing, 37) \ - x(btree_node_bset_after_end, 38) \ - x(btree_node_replicas_sectors_written_mismatch, 39) \ - x(btree_node_replicas_data_mismatch, 40) \ - x(bset_unknown_csum, 41) \ - x(bset_bad_csum, 42) \ - x(bset_past_end_of_btree_node, 43) \ - x(bset_wrong_sector_offset, 44) \ - x(bset_empty, 45) \ - x(bset_bad_seq, 46) \ - x(bset_blacklisted_journal_seq, 47) \ - x(first_bset_blacklisted_journal_seq, 48) \ - x(btree_node_bad_btree, 49) \ - x(btree_node_bad_level, 50) \ - x(btree_node_bad_min_key, 51) \ - x(btree_node_bad_max_key, 52) \ - x(btree_node_bad_format, 53) \ - x(btree_node_bkey_past_bset_end, 54) \ - x(btree_node_bkey_bad_format, 55) \ - x(btree_node_bad_bkey, 56) \ - x(btree_node_bkey_out_of_order, 57) \ - x(btree_root_bkey_invalid, 58) \ - x(btree_root_read_error, 59) \ - x(btree_root_bad_min_key, 60) \ - x(btree_root_bad_max_key, 61) \ - x(btree_node_read_error, 62) \ - x(btree_node_topology_bad_min_key, 63) \ - x(btree_node_topology_bad_max_key, 64) \ - x(btree_node_topology_overwritten_by_prev_node, 65) \ - x(btree_node_topology_overwritten_by_next_node, 66) \ - x(btree_node_topology_interior_node_empty, 67) \ - x(fs_usage_hidden_wrong, 68) \ - x(fs_usage_btree_wrong, 69) \ - x(fs_usage_data_wrong, 70) \ - x(fs_usage_cached_wrong, 71) \ - x(fs_usage_reserved_wrong, 72) \ - x(fs_usage_persistent_reserved_wrong, 73) \ - x(fs_usage_nr_inodes_wrong, 74) \ - x(fs_usage_replicas_wrong, 75) \ - x(dev_usage_buckets_wrong, 76) \ - x(dev_usage_sectors_wrong, 77) \ - x(dev_usage_fragmented_wrong, 78) \ - x(dev_usage_buckets_ec_wrong, 79) \ - x(bkey_version_in_future, 80) \ - x(bkey_u64s_too_small, 81) \ - x(bkey_invalid_type_for_btree, 82) \ - x(bkey_extent_size_zero, 83) \ - x(bkey_extent_size_greater_than_offset, 84) \ - x(bkey_size_nonzero, 85) \ - x(bkey_snapshot_nonzero, 86) \ - x(bkey_snapshot_zero, 87) \ - x(bkey_at_pos_max, 88) \ - x(bkey_before_start_of_btree_node, 89) \ - x(bkey_after_end_of_btree_node, 90) \ - x(bkey_val_size_nonzero, 91) \ - x(bkey_val_size_too_small, 92) \ - x(alloc_v1_val_size_bad, 93) \ - x(alloc_v2_unpack_error, 94) \ - x(alloc_v3_unpack_error, 95) \ - x(alloc_v4_val_size_bad, 96) \ - x(alloc_v4_backpointers_start_bad, 97) \ - x(alloc_key_data_type_bad, 98) \ - x(alloc_key_empty_but_have_data, 99) \ - x(alloc_key_dirty_sectors_0, 100) \ - x(alloc_key_data_type_inconsistency, 101) \ - x(alloc_key_to_missing_dev_bucket, 102) \ - x(alloc_key_cached_inconsistency, 103) \ - x(alloc_key_cached_but_read_time_zero, 104) \ - x(alloc_key_to_missing_lru_entry, 105) \ - x(alloc_key_data_type_wrong, 106) \ - x(alloc_key_gen_wrong, 107) \ - x(alloc_key_dirty_sectors_wrong, 108) \ - x(alloc_key_cached_sectors_wrong, 109) \ - x(alloc_key_stripe_wrong, 110) \ - x(alloc_key_stripe_redundancy_wrong, 111) \ - x(bucket_sector_count_overflow, 112) \ - x(bucket_metadata_type_mismatch, 113) \ - x(need_discard_key_wrong, 114) \ - x(freespace_key_wrong, 115) \ - x(freespace_hole_missing, 116) \ - x(bucket_gens_val_size_bad, 117) \ - x(bucket_gens_key_wrong, 118) \ - x(bucket_gens_hole_wrong, 119) \ - x(bucket_gens_to_invalid_dev, 120) \ - x(bucket_gens_to_invalid_buckets, 121) \ - x(bucket_gens_nonzero_for_invalid_buckets, 122) \ - x(need_discard_freespace_key_to_invalid_dev_bucket, 123) \ - x(need_discard_freespace_key_bad, 124) \ - x(backpointer_bucket_offset_wrong, 125) \ - x(backpointer_to_missing_device, 126) \ - x(backpointer_to_missing_alloc, 127) \ - x(backpointer_to_missing_ptr, 128) \ - x(lru_entry_at_time_0, 129) \ - x(lru_entry_to_invalid_bucket, 130) \ - x(lru_entry_bad, 131) \ - x(btree_ptr_val_too_big, 132) \ - x(btree_ptr_v2_val_too_big, 133) \ - x(btree_ptr_has_non_ptr, 134) \ - x(extent_ptrs_invalid_entry, 135) \ - x(extent_ptrs_no_ptrs, 136) \ - x(extent_ptrs_too_many_ptrs, 137) \ - x(extent_ptrs_redundant_crc, 138) \ - x(extent_ptrs_redundant_stripe, 139) \ - x(extent_ptrs_unwritten, 140) \ - x(extent_ptrs_written_and_unwritten, 141) \ - x(ptr_to_invalid_device, 142) \ - x(ptr_to_duplicate_device, 143) \ - x(ptr_after_last_bucket, 144) \ - x(ptr_before_first_bucket, 145) \ - x(ptr_spans_multiple_buckets, 146) \ - x(ptr_to_missing_backpointer, 147) \ - x(ptr_to_missing_alloc_key, 148) \ - x(ptr_to_missing_replicas_entry, 149) \ - x(ptr_to_missing_stripe, 150) \ - x(ptr_to_incorrect_stripe, 151) \ - x(ptr_gen_newer_than_bucket_gen, 152) \ - x(ptr_too_stale, 153) \ - x(stale_dirty_ptr, 154) \ - x(ptr_bucket_data_type_mismatch, 155) \ - x(ptr_cached_and_erasure_coded, 156) \ - x(ptr_crc_uncompressed_size_too_small, 157) \ - x(ptr_crc_csum_type_unknown, 158) \ - x(ptr_crc_compression_type_unknown, 159) \ - x(ptr_crc_redundant, 160) \ - x(ptr_crc_uncompressed_size_too_big, 161) \ - x(ptr_crc_nonce_mismatch, 162) \ - x(ptr_stripe_redundant, 163) \ - x(reservation_key_nr_replicas_invalid, 164) \ - x(reflink_v_refcount_wrong, 165) \ - x(reflink_p_to_missing_reflink_v, 166) \ - x(stripe_pos_bad, 167) \ - x(stripe_val_size_bad, 168) \ - x(stripe_sector_count_wrong, 169) \ - x(snapshot_tree_pos_bad, 170) \ - x(snapshot_tree_to_missing_snapshot, 171) \ - x(snapshot_tree_to_missing_subvol, 172) \ - x(snapshot_tree_to_wrong_subvol, 173) \ - x(snapshot_tree_to_snapshot_subvol, 174) \ - x(snapshot_pos_bad, 175) \ - x(snapshot_parent_bad, 176) \ - x(snapshot_children_not_normalized, 177) \ - x(snapshot_child_duplicate, 178) \ - x(snapshot_child_bad, 179) \ - x(snapshot_skiplist_not_normalized, 180) \ - x(snapshot_skiplist_bad, 181) \ - x(snapshot_should_not_have_subvol, 182) \ - x(snapshot_to_bad_snapshot_tree, 183) \ - x(snapshot_bad_depth, 184) \ - x(snapshot_bad_skiplist, 185) \ - x(subvol_pos_bad, 186) \ - x(subvol_not_master_and_not_snapshot, 187) \ - x(subvol_to_missing_root, 188) \ - x(subvol_root_wrong_bi_subvol, 189) \ - x(bkey_in_missing_snapshot, 190) \ - x(inode_pos_inode_nonzero, 191) \ - x(inode_pos_blockdev_range, 192) \ - x(inode_unpack_error, 193) \ - x(inode_str_hash_invalid, 194) \ - x(inode_v3_fields_start_bad, 195) \ - x(inode_snapshot_mismatch, 196) \ - x(inode_unlinked_but_clean, 197) \ - x(inode_unlinked_but_nlink_nonzero, 198) \ - x(inode_checksum_type_invalid, 199) \ - x(inode_compression_type_invalid, 200) \ - x(inode_subvol_root_but_not_dir, 201) \ - x(inode_i_size_dirty_but_clean, 202) \ - x(inode_i_sectors_dirty_but_clean, 203) \ - x(inode_i_sectors_wrong, 204) \ - x(inode_dir_wrong_nlink, 205) \ - x(inode_dir_multiple_links, 206) \ - x(inode_multiple_links_but_nlink_0, 207) \ - x(inode_wrong_backpointer, 208) \ - x(inode_wrong_nlink, 209) \ - x(inode_unreachable, 210) \ - x(deleted_inode_but_clean, 211) \ - x(deleted_inode_missing, 212) \ - x(deleted_inode_is_dir, 213) \ - x(deleted_inode_not_unlinked, 214) \ - x(extent_overlapping, 215) \ - x(extent_in_missing_inode, 216) \ - x(extent_in_non_reg_inode, 217) \ - x(extent_past_end_of_inode, 218) \ - x(dirent_empty_name, 219) \ - x(dirent_val_too_big, 220) \ - x(dirent_name_too_long, 221) \ - x(dirent_name_embedded_nul, 222) \ - x(dirent_name_dot_or_dotdot, 223) \ - x(dirent_name_has_slash, 224) \ - x(dirent_d_type_wrong, 225) \ - x(inode_bi_parent_wrong, 226) \ - x(dirent_in_missing_dir_inode, 227) \ - x(dirent_in_non_dir_inode, 228) \ - x(dirent_to_missing_inode, 229) \ - x(dirent_to_missing_subvol, 230) \ - x(dirent_to_itself, 231) \ - x(quota_type_invalid, 232) \ - x(xattr_val_size_too_small, 233) \ - x(xattr_val_size_too_big, 234) \ - x(xattr_invalid_type, 235) \ - x(xattr_name_invalid_chars, 236) \ - x(xattr_in_missing_inode, 237) \ - x(root_subvol_missing, 238) \ - x(root_dir_missing, 239) \ - x(root_inode_not_dir, 240) \ - x(dir_loop, 241) \ - x(hash_table_key_duplicate, 242) \ - x(hash_table_key_wrong_offset, 243) \ - x(unlinked_inode_not_on_deleted_list, 244) \ - x(reflink_p_front_pad_bad, 245) \ - x(journal_entry_dup_same_device, 246) \ - x(inode_bi_subvol_missing, 247) \ - x(inode_bi_subvol_wrong, 248) \ - x(inode_points_to_missing_dirent, 249) \ - x(inode_points_to_wrong_dirent, 250) \ - x(inode_bi_parent_nonzero, 251) \ - x(dirent_to_missing_parent_subvol, 252) \ - x(dirent_not_visible_in_parent_subvol, 253) \ - x(subvol_fs_path_parent_wrong, 254) \ - x(subvol_root_fs_path_parent_nonzero, 255) \ - x(subvol_children_not_set, 256) \ - x(subvol_children_bad, 257) \ - x(subvol_loop, 258) \ - x(subvol_unreachable, 259) \ - x(btree_node_bkey_bad_u64s, 260) \ - x(btree_node_topology_empty_interior_node, 261) \ - x(btree_ptr_v2_min_key_bad, 262) \ - x(btree_root_unreadable_and_scan_found_nothing, 263) \ - x(snapshot_node_missing, 264) \ - x(dup_backpointer_to_bad_csum_extent, 265) \ - x(btree_bitmap_not_marked, 266) \ - x(sb_clean_entry_overrun, 267) \ - x(btree_ptr_v2_written_0, 268) \ - x(subvol_snapshot_bad, 269) \ - x(subvol_inode_bad, 270) - -enum bch_sb_error_id { -#define x(t, n) BCH_FSCK_ERR_##t = n, - BCH_SB_ERRS() -#undef x - BCH_SB_ERR_MAX -}; - struct bch_sb_error_entry_cpu { u64 id:16, nr:48; @@ -293,4 +13,3 @@ struct bch_sb_error_entry_cpu { typedef DARRAY(struct bch_sb_error_entry_cpu) bch_sb_errors_cpu; #endif /* _BCACHEFS_SB_ERRORS_TYPES_H */ - diff --git a/fs/bcachefs/sb-members_format.h b/fs/bcachefs/sb-members_format.h new file mode 100644 index 000000000000..e2630548c0f6 --- /dev/null +++ b/fs/bcachefs/sb-members_format.h @@ -0,0 +1,110 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BCACHEFS_SB_MEMBERS_FORMAT_H +#define _BCACHEFS_SB_MEMBERS_FORMAT_H + +/* + * We refer to members with bitmasks in various places - but we need to get rid + * of this limit: + */ +#define BCH_SB_MEMBERS_MAX 64 + +#define BCH_MIN_NR_NBUCKETS (1 << 6) + +#define BCH_IOPS_MEASUREMENTS() \ + x(seqread, 0) \ + x(seqwrite, 1) \ + x(randread, 2) \ + x(randwrite, 3) + +enum bch_iops_measurement { +#define x(t, n) BCH_IOPS_##t = n, + BCH_IOPS_MEASUREMENTS() +#undef x + BCH_IOPS_NR +}; + +#define BCH_MEMBER_ERROR_TYPES() \ + x(read, 0) \ + x(write, 1) \ + x(checksum, 2) + +enum bch_member_error_type { +#define x(t, n) BCH_MEMBER_ERROR_##t = n, + BCH_MEMBER_ERROR_TYPES() +#undef x + BCH_MEMBER_ERROR_NR +}; + +struct bch_member { + __uuid_t uuid; + __le64 nbuckets; /* device size */ + __le16 first_bucket; /* index of first bucket used */ + __le16 bucket_size; /* sectors */ + __u8 btree_bitmap_shift; + __u8 pad[3]; + __le64 last_mount; /* time_t */ + + __le64 flags; + __le32 iops[4]; + __le64 errors[BCH_MEMBER_ERROR_NR]; + __le64 errors_at_reset[BCH_MEMBER_ERROR_NR]; + __le64 errors_reset_time; + __le64 seq; + __le64 btree_allocated_bitmap; + /* + * On recovery from a clean shutdown we don't normally read the journal, + * but we still want to resume writing from where we left off so we + * don't overwrite more than is necessary, for list journal debugging: + */ + __le32 last_journal_bucket; + __le32 last_journal_bucket_offset; +}; + +/* + * This limit comes from the bucket_gens array - it's a single allocation, and + * kernel allocation are limited to INT_MAX + */ +#define BCH_MEMBER_NBUCKETS_MAX (INT_MAX - 64) + +#define BCH_MEMBER_V1_BYTES 56 + +LE64_BITMASK(BCH_MEMBER_STATE, struct bch_member, flags, 0, 4) +/* 4-14 unused, was TIER, HAS_(META)DATA, REPLACEMENT */ +LE64_BITMASK(BCH_MEMBER_DISCARD, struct bch_member, flags, 14, 15) +LE64_BITMASK(BCH_MEMBER_DATA_ALLOWED, struct bch_member, flags, 15, 20) +LE64_BITMASK(BCH_MEMBER_GROUP, struct bch_member, flags, 20, 28) +LE64_BITMASK(BCH_MEMBER_DURABILITY, struct bch_member, flags, 28, 30) +LE64_BITMASK(BCH_MEMBER_FREESPACE_INITIALIZED, + struct bch_member, flags, 30, 31) + +#if 0 +LE64_BITMASK(BCH_MEMBER_NR_READ_ERRORS, struct bch_member, flags[1], 0, 20); +LE64_BITMASK(BCH_MEMBER_NR_WRITE_ERRORS,struct bch_member, flags[1], 20, 40); +#endif + +#define BCH_MEMBER_STATES() \ + x(rw, 0) \ + x(ro, 1) \ + x(failed, 2) \ + x(spare, 3) + +enum bch_member_state { +#define x(t, n) BCH_MEMBER_STATE_##t = n, + BCH_MEMBER_STATES() +#undef x + BCH_MEMBER_STATE_NR +}; + +struct bch_sb_field_members_v1 { + struct bch_sb_field field; + struct bch_member _members[]; //Members are now variable size +}; + +struct bch_sb_field_members_v2 { + struct bch_sb_field field; + __le16 member_bytes; //size of single member entry + u8 pad[6]; + struct bch_member _members[]; +}; + +#endif /* _BCACHEFS_SB_MEMBERS_FORMAT_H */ diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c index 629900a5e641..51918acfd726 100644 --- a/fs/bcachefs/snapshot.c +++ b/fs/bcachefs/snapshot.c @@ -1042,6 +1042,25 @@ err: return ret; } +int bch2_check_key_has_snapshot(struct btree_trans *trans, + struct btree_iter *iter, + struct bkey_s_c k) +{ + struct bch_fs *c = trans->c; + struct printbuf buf = PRINTBUF; + int ret = 0; + + if (fsck_err_on(!bch2_snapshot_equiv(c, k.k->p.snapshot), c, + bkey_in_missing_snapshot, + "key in missing snapshot %s, delete?", + (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) + ret = bch2_btree_delete_at(trans, iter, + BTREE_UPDATE_internal_snapshot_node) ?: 1; +fsck_err: + printbuf_exit(&buf); + return ret; +} + /* * Mark a snapshot as deleted, for future cleanup: */ @@ -1351,35 +1370,39 @@ int bch2_snapshot_node_create(struct btree_trans *trans, u32 parent, * that key to snapshot leaf nodes, where we can mutate it */ -static int snapshot_delete_key(struct btree_trans *trans, +static int delete_dead_snapshots_process_key(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, snapshot_id_list *deleted, snapshot_id_list *equiv_seen, struct bpos *last_pos) { + int ret = bch2_check_key_has_snapshot(trans, iter, k); + if (ret) + return ret < 0 ? ret : 0; + struct bch_fs *c = trans->c; u32 equiv = bch2_snapshot_equiv(c, k.k->p.snapshot); + if (!equiv) /* key for invalid snapshot node, but we chose not to delete */ + return 0; if (!bkey_eq(k.k->p, *last_pos)) equiv_seen->nr = 0; - *last_pos = k.k->p; - if (snapshot_list_has_id(deleted, k.k->p.snapshot) || - snapshot_list_has_id(equiv_seen, equiv)) { + if (snapshot_list_has_id(deleted, k.k->p.snapshot)) return bch2_btree_delete_at(trans, iter, BTREE_UPDATE_internal_snapshot_node); - } else { - return snapshot_list_add(c, equiv_seen, equiv); - } -} -static int move_key_to_correct_snapshot(struct btree_trans *trans, - struct btree_iter *iter, - struct bkey_s_c k) -{ - struct bch_fs *c = trans->c; - u32 equiv = bch2_snapshot_equiv(c, k.k->p.snapshot); + if (!bpos_eq(*last_pos, k.k->p) && + snapshot_list_has_id(equiv_seen, equiv)) + return bch2_btree_delete_at(trans, iter, + BTREE_UPDATE_internal_snapshot_node); + + *last_pos = k.k->p; + + ret = snapshot_list_add_nodup(c, equiv_seen, equiv); + if (ret) + return ret; /* * When we have a linear chain of snapshot nodes, we consider @@ -1389,21 +1412,20 @@ static int move_key_to_correct_snapshot(struct btree_trans *trans, * * If there are multiple keys in different snapshots at the same * position, we're only going to keep the one in the newest - * snapshot - the rest have been overwritten and are redundant, - * and for the key we're going to keep we need to move it to the - * equivalance class ID if it's not there already. + * snapshot (we delete the others above) - the rest have been + * overwritten and are redundant, and for the key we're going to keep we + * need to move it to the equivalance class ID if it's not there + * already. */ if (equiv != k.k->p.snapshot) { struct bkey_i *new = bch2_bkey_make_mut_noupdate(trans, k); - struct btree_iter new_iter; - int ret; - - ret = PTR_ERR_OR_ZERO(new); + int ret = PTR_ERR_OR_ZERO(new); if (ret) return ret; new->k.p.snapshot = equiv; + struct btree_iter new_iter; bch2_trans_iter_init(trans, &new_iter, iter->btree_id, new->k.p, BTREE_ITER_all_snapshots| BTREE_ITER_cached| @@ -1538,7 +1560,6 @@ int bch2_delete_dead_snapshots(struct bch_fs *c) struct btree_trans *trans; snapshot_id_list deleted = { 0 }; snapshot_id_list deleted_interior = { 0 }; - u32 id; int ret = 0; if (!test_and_clear_bit(BCH_FS_need_delete_dead_snapshots, &c->flags)) @@ -1585,33 +1606,20 @@ int bch2_delete_dead_snapshots(struct bch_fs *c) if (ret) goto err; - for (id = 0; id < BTREE_ID_NR; id++) { + for (unsigned btree = 0; btree < BTREE_ID_NR; btree++) { struct bpos last_pos = POS_MIN; snapshot_id_list equiv_seen = { 0 }; struct disk_reservation res = { 0 }; - if (!btree_type_has_snapshots(id)) - continue; - - /* - * deleted inodes btree is maintained by a trigger on the inodes - * btree - no work for us to do here, and it's not safe to scan - * it because we'll see out of date keys due to the btree write - * buffer: - */ - if (id == BTREE_ID_deleted_inodes) + if (!btree_type_has_snapshots(btree)) continue; ret = for_each_btree_key_commit(trans, iter, - id, POS_MIN, - BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, - &res, NULL, BCH_TRANS_COMMIT_no_enospc, - snapshot_delete_key(trans, &iter, k, &deleted, &equiv_seen, &last_pos)) ?: - for_each_btree_key_commit(trans, iter, - id, POS_MIN, + btree, POS_MIN, BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, &res, NULL, BCH_TRANS_COMMIT_no_enospc, - move_key_to_correct_snapshot(trans, &iter, k)); + delete_dead_snapshots_process_key(trans, &iter, k, &deleted, + &equiv_seen, &last_pos)); bch2_disk_reservation_put(c, &res); darray_exit(&equiv_seen); diff --git a/fs/bcachefs/snapshot.h b/fs/bcachefs/snapshot.h index ab13d8f4b41e..31b0ee03e962 100644 --- a/fs/bcachefs/snapshot.h +++ b/fs/bcachefs/snapshot.h @@ -242,6 +242,7 @@ int bch2_snapshot_node_create(struct btree_trans *, u32, int bch2_check_snapshot_trees(struct bch_fs *); int bch2_check_snapshots(struct bch_fs *); int bch2_reconstruct_snapshots(struct bch_fs *); +int bch2_check_key_has_snapshot(struct btree_trans *, struct btree_iter *, struct bkey_s_c); int bch2_snapshot_node_set_deleted(struct btree_trans *, u32); void bch2_delete_dead_snapshots_work(struct work_struct *); diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c index f1bee6c5222d..d73a0222f709 100644 --- a/fs/bcachefs/super-io.c +++ b/fs/bcachefs/super-io.c @@ -1132,18 +1132,12 @@ bool bch2_check_version_downgrade(struct bch_fs *c) * c->sb will be checked before we write the superblock, so update it as * well: */ - if (BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb) > bcachefs_metadata_version_current) { + if (BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb) > bcachefs_metadata_version_current) SET_BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb, bcachefs_metadata_version_current); - c->sb.version_upgrade_complete = bcachefs_metadata_version_current; - } - if (c->sb.version > bcachefs_metadata_version_current) { + if (c->sb.version > bcachefs_metadata_version_current) c->disk_sb.sb->version = cpu_to_le16(bcachefs_metadata_version_current); - c->sb.version = bcachefs_metadata_version_current; - } - if (c->sb.version_min > bcachefs_metadata_version_current) { + if (c->sb.version_min > bcachefs_metadata_version_current) c->disk_sb.sb->version_min = cpu_to_le16(bcachefs_metadata_version_current); - c->sb.version_min = bcachefs_metadata_version_current; - } c->disk_sb.sb->compat[0] &= cpu_to_le64((1ULL << BCH_COMPAT_NR) - 1); return ret; } diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c index 2206a8dee693..df2bea38e83f 100644 --- a/fs/bcachefs/super.c +++ b/fs/bcachefs/super.c @@ -564,7 +564,7 @@ static void __bch2_fs_free(struct bch_fs *c) BUG_ON(atomic_read(&c->journal_keys.ref)); bch2_fs_btree_write_buffer_exit(c); percpu_free_rwsem(&c->mark_lock); - EBUG_ON(percpu_u64_get(c->online_reserved)); + EBUG_ON(c->online_reserved && percpu_u64_get(c->online_reserved)); free_percpu(c->online_reserved); darray_exit(&c->btree_roots_extra); diff --git a/fs/dcache.c b/fs/dcache.c index 1ee6404b430b..407095188f83 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2360,17 +2360,19 @@ EXPORT_SYMBOL(d_hash_and_lookup); * - unhash this dentry and free it. * * Usually, we want to just turn this into - * a negative dentry, but certain workloads can - * generate a large number of negative dentries. - * Therefore, it would be better to simply - * unhash it. + * a negative dentry, but if anybody else is + * currently using the dentry or the inode + * we can't do that and we fall back on removing + * it from the hash queues and waiting for + * it to be deleted later when it has no users */ /** * d_delete - delete a dentry * @dentry: The dentry to delete * - * Remove the dentry from the hash queues so it can be deleted later. + * Turn the dentry into a negative dentry if possible, otherwise + * remove it from the hash queues so it can be deleted later */ void d_delete(struct dentry * dentry) @@ -2379,8 +2381,6 @@ void d_delete(struct dentry * dentry) spin_lock(&inode->i_lock); spin_lock(&dentry->d_lock); - __d_drop(dentry); - /* * Are we the only user? */ @@ -2388,6 +2388,7 @@ void d_delete(struct dentry * dentry) dentry->d_flags &= ~DCACHE_CANT_MOUNT; dentry_unlink_inode(dentry); } else { + __d_drop(dentry); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); } diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 41c8f0c68ef5..c5802a459334 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -898,11 +898,11 @@ static bool iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len, static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) { loff_t length = iomap_length(iter); - size_t chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER; loff_t pos = iter->pos; ssize_t total_written = 0; long status = 0; struct address_space *mapping = iter->inode->i_mapping; + size_t chunk = mapping_max_folio_size(mapping); unsigned int bdp_flags = (iter->flags & IOMAP_NOWAIT) ? BDP_ASYNC : 0; do { diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index 1121601536d1..07bc1fd43530 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -181,7 +181,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, struct folio *folio, *writethrough = NULL; enum netfs_how_to_modify howto; enum netfs_folio_trace trace; - unsigned int bdp_flags = (iocb->ki_flags & IOCB_SYNC) ? 0: BDP_ASYNC; + unsigned int bdp_flags = (iocb->ki_flags & IOCB_NOWAIT) ? BDP_ASYNC : 0; ssize_t written = 0, ret, ret2; loff_t i_size, pos = iocb->ki_pos, from, to; size_t max_chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER; diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index f516460e994e..e14cd53ac9fd 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -12,7 +12,7 @@ static void netfs_cleanup_dio_write(struct netfs_io_request *wreq) { struct inode *inode = wreq->inode; - unsigned long long end = wreq->start + wreq->len; + unsigned long long end = wreq->start + wreq->transferred; if (!wreq->error && i_size_read(inode) < end) { diff --git a/fs/netfs/objects.c b/fs/netfs/objects.c index c90d482b1650..f4a642727479 100644 --- a/fs/netfs/objects.c +++ b/fs/netfs/objects.c @@ -72,6 +72,7 @@ struct netfs_io_request *netfs_alloc_request(struct address_space *mapping, } } + atomic_inc(&ctx->io_count); trace_netfs_rreq_ref(rreq->debug_id, 1, netfs_rreq_trace_new); netfs_proc_add_rreq(rreq); netfs_stat(&netfs_n_rh_rreq); @@ -124,6 +125,7 @@ static void netfs_free_request(struct work_struct *work) { struct netfs_io_request *rreq = container_of(work, struct netfs_io_request, work); + struct netfs_inode *ictx = netfs_inode(rreq->inode); unsigned int i; trace_netfs_rreq(rreq, netfs_rreq_trace_free); @@ -142,6 +144,9 @@ static void netfs_free_request(struct work_struct *work) } kvfree(rreq->direct_bv); } + + if (atomic_dec_and_test(&ictx->io_count)) + wake_up_var(&ictx->io_count); call_rcu(&rreq->rcu, netfs_free_request_rcu); } diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 60112e4b2c5e..426cf87aaf2e 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -510,7 +510,7 @@ reassess_streams: * stream has a gap that can be jumped. */ if (notes & SOME_EMPTY) { - unsigned long long jump_to = wreq->start + wreq->len; + unsigned long long jump_to = wreq->start + READ_ONCE(wreq->submitted); for (s = 0; s < NR_IO_STREAMS; s++) { stream = &wreq->io_streams[s]; @@ -690,10 +690,11 @@ void netfs_write_collection_worker(struct work_struct *work) wake_up_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS); if (wreq->iocb) { - wreq->iocb->ki_pos += wreq->transferred; + size_t written = min(wreq->transferred, wreq->len); + wreq->iocb->ki_pos += written; if (wreq->iocb->ki_complete) wreq->iocb->ki_complete( - wreq->iocb, wreq->error ? wreq->error : wreq->transferred); + wreq->iocb, wreq->error ? wreq->error : written); wreq->iocb = VFS_PTR_POISON; } diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index e190043bc0da..3aa86e268f40 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -254,7 +254,7 @@ static void netfs_issue_write(struct netfs_io_request *wreq, stream->construct = NULL; if (subreq->start + subreq->len > wreq->start + wreq->submitted) - wreq->len = wreq->submitted = subreq->start + subreq->len - wreq->start; + WRITE_ONCE(wreq->submitted, subreq->start + subreq->len - wreq->start); netfs_do_issue_write(stream, subreq); } @@ -636,7 +636,12 @@ int netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_contr mutex_unlock(&ictx->wb_lock); - ret = wreq->error; + if (wreq->iocb) { + ret = -EIOCBQUEUED; + } else { + wait_on_bit(&wreq->flags, NETFS_RREQ_IN_PROGRESS, TASK_UNINTERRUPTIBLE); + ret = wreq->error; + } netfs_put_request(wreq, false, netfs_rreq_trace_put_return); return ret; } diff --git a/fs/signalfd.c b/fs/signalfd.c index 4a5614442dbf..ec7b2da2477a 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -282,14 +282,10 @@ static int do_signalfd4(int ufd, sigset_t *mask, int flags) if (IS_ERR(file)) { put_unused_fd(ufd); kfree(ctx); - return ufd; + return PTR_ERR(file); } file->f_mode |= FMODE_NOWAIT; - /* - * When we call this, the initialization must be complete, since - * anon_inode_getfd() will install the fd. - */ fd_install(ufd, file); } else { struct fd f = fdget(ufd); diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index a665aac9be9f..bb86fc0641d8 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -431,6 +431,7 @@ cifs_free_inode(struct inode *inode) static void cifs_evict_inode(struct inode *inode) { + netfs_wait_for_outstanding_io(inode); truncate_inode_pages_final(&inode->i_data); if (inode->i_state & I_PINNING_NETFS_WB) cifs_fscache_unuse_inode_cookie(inode, true); diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 2ad1ffa4ccb9..0ed47d00549b 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -636,6 +636,14 @@ static inline void eth_skb_pkt_type(struct sk_buff *skb, } } +static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb) +{ + struct ethhdr *eth = (struct ethhdr *)skb->data; + + skb_pull_inline(skb, ETH_HLEN); + return eth; +} + /** * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame * @skb: Buffer to pad diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f468763478ae..5df52e15f7d6 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10308,9 +10308,9 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 mfrl[0x1]; u8 regs_39_to_32[0x8]; - u8 regs_31_to_10[0x16]; + u8 regs_31_to_11[0x15]; u8 mtmp[0x1]; - u8 regs_8_to_0[0x9]; + u8 regs_9_to_0[0xa]; }; struct mlx5_ifc_mcam_access_reg_bits1 { diff --git a/include/linux/netfs.h b/include/linux/netfs.h index d2d291a9cdad..3ca3906bb8da 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -68,6 +68,7 @@ struct netfs_inode { loff_t remote_i_size; /* Size of the remote file */ loff_t zero_point; /* Size after which we assume there's no data * on the server */ + atomic_t io_count; /* Number of outstanding reqs */ unsigned long flags; #define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ #define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ @@ -474,6 +475,7 @@ static inline void netfs_inode_init(struct netfs_inode *ctx, ctx->remote_i_size = i_size_read(&ctx->inode); ctx->zero_point = LLONG_MAX; ctx->flags = 0; + atomic_set(&ctx->io_count, 0); #if IS_ENABLED(CONFIG_FSCACHE) ctx->cache = NULL; #endif @@ -517,4 +519,20 @@ static inline struct fscache_cookie *netfs_i_cookie(struct netfs_inode *ctx) #endif } +/** + * netfs_wait_for_outstanding_io - Wait for outstanding I/O to complete + * @ctx: The netfs inode to wait on + * + * Wait for outstanding I/O requests of any type to complete. This is intended + * to be called from inode eviction routines. This makes sure that any + * resources held by those requests are cleaned up before we let the inode get + * cleaned up. + */ +static inline void netfs_wait_for_outstanding_io(struct inode *inode) +{ + struct netfs_inode *ictx = netfs_inode(inode); + + wait_var_event(&ictx->io_count, atomic_read(&ictx->io_count) == 0); +} + #endif /* _LINUX_NETFS_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 3d69589c00a4..ee633712bba0 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -346,6 +346,19 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) m->gfp_mask = mask; } +/* + * There are some parts of the kernel which assume that PMD entries + * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then, + * limit the maximum allocation order to PMD size. I'm not aware of any + * assumptions about maximum order if THP are disabled, but 8 seems like + * a good order (that's 1MB if you're using 4kB pages) + */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER +#else +#define MAX_PAGECACHE_ORDER 8 +#endif + /** * mapping_set_large_folios() - Indicate the file supports large folios. * @mapping: The file. @@ -372,6 +385,14 @@ static inline bool mapping_large_folio_support(struct address_space *mapping) test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } +/* Return the maximum folio size for this pagecache mapping, in bytes. */ +static inline size_t mapping_max_folio_size(struct address_space *mapping) +{ + if (mapping_large_folio_support(mapping)) + return PAGE_SIZE << MAX_PAGECACHE_ORDER; + return PAGE_SIZE; +} + static inline int filemap_nr_thps(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS @@ -530,19 +551,6 @@ static inline void *detach_page_private(struct page *page) return folio_detach_private(page_folio(page)); } -/* - * There are some parts of the kernel which assume that PMD entries - * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then, - * limit the maximum allocation order to PMD size. I'm not aware of any - * assumptions about maximum order if THP are disabled, but 8 seems like - * a good order (that's 1MB if you're using 4kB pages) - */ -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER -#else -#define MAX_PAGECACHE_ORDER 8 -#endif - #ifdef CONFIG_NUMA struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order); #else diff --git a/include/linux/tpm.h b/include/linux/tpm.h index c17e4efbb2e5..21a67dc9efe8 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -394,21 +394,6 @@ enum tpm2_object_attributes { TPM2_OA_SIGN = BIT(18), }; -/* - * definitions for the canonical template. These are mandated - * by the TCG key template documents - */ - -#define AES_KEY_BYTES AES_KEYSIZE_128 -#define AES_KEY_BITS (AES_KEY_BYTES*8) -#define TPM2_OA_TMPL (TPM2_OA_NO_DA | \ - TPM2_OA_FIXED_TPM | \ - TPM2_OA_FIXED_PARENT | \ - TPM2_OA_SENSITIVE_DATA_ORIGIN | \ - TPM2_OA_USER_WITH_AUTH | \ - TPM2_OA_DECRYPT | \ - TPM2_OA_RESTRICTED) - enum tpm2_session_attributes { TPM2_SA_CONTINUE_SESSION = BIT(0), TPM2_SA_AUDIT_EXCLUSIVE = BIT(1), @@ -437,8 +422,6 @@ u8 tpm_buf_read_u8(struct tpm_buf *buf, off_t *offset); u16 tpm_buf_read_u16(struct tpm_buf *buf, off_t *offset); u32 tpm_buf_read_u32(struct tpm_buf *buf, off_t *offset); -u8 *tpm_buf_parameters(struct tpm_buf *buf); - /* * Check if TPM device is in the firmware upgrade mode. */ diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 6d1c8541183d..3a9001a042a5 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -24,7 +24,7 @@ struct dst_ops { void (*destroy)(struct dst_entry *); void (*ifdown)(struct dst_entry *, struct net_device *dev); - struct dst_entry * (*negative_advice)(struct dst_entry *); + void (*negative_advice)(struct sock *sk, struct dst_entry *); void (*link_failure)(struct sk_buff *); void (*update_pmtu)(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index b088d131aeb0..7e8477057f3d 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -45,16 +45,17 @@ struct pp_alloc_cache { /** * struct page_pool_params - page pool parameters + * @fast: params accessed frequently on hotpath * @order: 2^order pages on allocation * @pool_size: size of the ptr_ring * @nid: NUMA node id to allocate from pages from * @dev: device, for DMA pre-mapping purposes - * @netdev: netdev this pool will serve (leave as NULL if none or multiple) * @napi: NAPI which is the sole consumer of pages, otherwise NULL * @dma_dir: DMA mapping direction * @max_len: max DMA sync memory size for PP_FLAG_DMA_SYNC_DEV * @offset: DMA sync address offset for PP_FLAG_DMA_SYNC_DEV - * @netdev: corresponding &net_device for Netlink introspection + * @slow: params with slowpath access only (initialization and Netlink) + * @netdev: netdev this pool will serve (leave as NULL if none or multiple) * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_SYSTEM_POOL */ struct page_pool_params { diff --git a/include/net/request_sock.h b/include/net/request_sock.h index d88c0dfc2d46..ebcb8896bffc 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -285,4 +285,16 @@ static inline int reqsk_queue_len_young(const struct request_sock_queue *queue) return atomic_read(&queue->young); } +/* RFC 7323 2.3 Using the Window Scale Option + * The window field (SEG.WND) of every outgoing segment, with the + * exception of <SYN> segments, MUST be right-shifted by + * Rcv.Wind.Shift bits. + * + * This means the SEG.WND carried in SYNACK can not exceed 65535. + * We use this property to harden TCP stack while in NEW_SYN_RECV state. + */ +static inline u32 tcp_synack_window(const struct request_sock *req) +{ + return min(req->rsk_rcv_wnd, 65535U); +} #endif /* _REQUEST_SOCK_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 5f4d0629348f..953c8dc4e259 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2063,17 +2063,10 @@ sk_dst_get(const struct sock *sk) static inline void __dst_negative_advice(struct sock *sk) { - struct dst_entry *ndst, *dst = __sk_dst_get(sk); + struct dst_entry *dst = __sk_dst_get(sk); - if (dst && dst->ops->negative_advice) { - ndst = dst->ops->negative_advice(dst); - - if (ndst != dst) { - rcu_assign_pointer(sk->sk_dst_cache, ndst); - sk_tx_queue_clear(sk); - WRITE_ONCE(sk->sk_dst_pending_confirm, 0); - } - } + if (dst && dst->ops->negative_advice) + dst->ops->negative_advice(sk, dst); } static inline void dst_negative_advice(struct sock *sk) diff --git a/include/uapi/linux/cn_proc.h b/include/uapi/linux/cn_proc.h index f2afb7cc4926..18e3745b86cd 100644 --- a/include/uapi/linux/cn_proc.h +++ b/include/uapi/linux/cn_proc.h @@ -69,8 +69,7 @@ struct proc_input { static inline enum proc_cn_event valid_event(enum proc_cn_event ev_type) { - ev_type &= PROC_EVENT_ALL; - return ev_type; + return (enum proc_cn_event)(ev_type & PROC_EVENT_ALL); } /* diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index a8188202413e..43742ac5b00d 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -148,6 +148,7 @@ enum { NETDEV_A_QSTATS_RX_ALLOC_FAIL, NETDEV_A_QSTATS_RX_HW_DROPS, NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS, + NETDEV_A_QSTATS_RX_CSUM_COMPLETE, NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY, NETDEV_A_QSTATS_RX_CSUM_NONE, NETDEV_A_QSTATS_RX_CSUM_BAD, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 77da1f438bec..48f3a9acdef3 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8882,7 +8882,8 @@ static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id) enum bpf_attach_type eatype = env->prog->expected_attach_type; enum bpf_prog_type type = resolve_prog_type(env->prog); - if (func_id != BPF_FUNC_map_update_elem) + if (func_id != BPF_FUNC_map_update_elem && + func_id != BPF_FUNC_map_delete_elem) return false; /* It's not possible to get access to a locked struct sock in these @@ -8893,6 +8894,11 @@ static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id) if (eatype == BPF_TRACE_ITER) return true; break; + case BPF_PROG_TYPE_SOCK_OPS: + /* map_update allowed only via dedicated helpers with event type checks */ + if (func_id == BPF_FUNC_map_delete_elem) + return true; + break; case BPF_PROG_TYPE_SOCKET_FILTER: case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: @@ -8988,7 +8994,6 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_SOCKMAP: if (func_id != BPF_FUNC_sk_redirect_map && func_id != BPF_FUNC_sock_map_update && - func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_msg_redirect_map && func_id != BPF_FUNC_sk_select_reuseport && func_id != BPF_FUNC_map_lookup_elem && @@ -8998,7 +9003,6 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_SOCKHASH: if (func_id != BPF_FUNC_sk_redirect_hash && func_id != BPF_FUNC_sock_hash_update && - func_id != BPF_FUNC_map_delete_elem && func_id != BPF_FUNC_msg_redirect_hash && func_id != BPF_FUNC_sk_select_reuseport && func_id != BPF_FUNC_map_lookup_elem && diff --git a/kernel/power/swap.c b/kernel/power/swap.c index d9abb7ab031d..753b8dd42a59 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -1595,7 +1595,7 @@ int swsusp_check(bool exclusive) put: if (error) - fput(hib_resume_bdev_file); + bdev_fput(hib_resume_bdev_file); else pr_debug("Image signature found, resuming\n"); } else { diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index f5154c051d2c..6249dac61701 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -3295,7 +3295,7 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe, struct bpf_run_ctx *old_run_ctx; int err = 0; - if (link->task && current != link->task) + if (link->task && current->mm != link->task->mm) return 0; if (sleepable) @@ -3396,8 +3396,9 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr upath = u64_to_user_ptr(attr->link_create.uprobe_multi.path); uoffsets = u64_to_user_ptr(attr->link_create.uprobe_multi.offsets); cnt = attr->link_create.uprobe_multi.cnt; + pid = attr->link_create.uprobe_multi.pid; - if (!upath || !uoffsets || !cnt) + if (!upath || !uoffsets || !cnt || pid < 0) return -EINVAL; if (cnt > MAX_UPROBE_MULTI_CNT) return -E2BIG; @@ -3421,11 +3422,8 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr goto error_path_put; } - pid = attr->link_create.uprobe_multi.pid; if (pid) { - rcu_read_lock(); - task = get_pid_task(find_vpid(pid), PIDTYPE_PID); - rcu_read_unlock(); + task = get_pid_task(find_vpid(pid), PIDTYPE_TGID); if (!task) { err = -ESRCH; goto error_path_put; diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 5e263c141574..39877c80d6cb 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -554,6 +554,10 @@ static int parse_btf_field(char *fieldname, const struct btf_type *type, anon_offs = 0; field = btf_find_struct_member(ctx->btf, type, fieldname, &anon_offs); + if (IS_ERR(field)) { + trace_probe_log_err(ctx->offset, BAD_BTF_TID); + return PTR_ERR(field); + } if (!field) { trace_probe_log_err(ctx->offset, NO_BTF_FIELD); return -ENOENT; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 8541fa1494ae..c98e3b3386ba 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -970,19 +970,17 @@ static struct uprobe_cpu_buffer *prepare_uprobe_buffer(struct trace_uprobe *tu, static void __uprobe_trace_func(struct trace_uprobe *tu, unsigned long func, struct pt_regs *regs, - struct uprobe_cpu_buffer **ucbp, + struct uprobe_cpu_buffer *ucb, struct trace_event_file *trace_file) { struct uprobe_trace_entry_head *entry; struct trace_event_buffer fbuffer; - struct uprobe_cpu_buffer *ucb; void *data; int size, esize; struct trace_event_call *call = trace_probe_event_call(&tu->tp); WARN_ON(call != trace_file->event_call); - ucb = prepare_uprobe_buffer(tu, regs, ucbp); if (WARN_ON_ONCE(ucb->dsize > PAGE_SIZE)) return; @@ -1014,13 +1012,16 @@ static int uprobe_trace_func(struct trace_uprobe *tu, struct pt_regs *regs, struct uprobe_cpu_buffer **ucbp) { struct event_file_link *link; + struct uprobe_cpu_buffer *ucb; if (is_ret_probe(tu)) return 0; + ucb = prepare_uprobe_buffer(tu, regs, ucbp); + rcu_read_lock(); trace_probe_for_each_link_rcu(link, &tu->tp) - __uprobe_trace_func(tu, 0, regs, ucbp, link->file); + __uprobe_trace_func(tu, 0, regs, ucb, link->file); rcu_read_unlock(); return 0; @@ -1031,10 +1032,13 @@ static void uretprobe_trace_func(struct trace_uprobe *tu, unsigned long func, struct uprobe_cpu_buffer **ucbp) { struct event_file_link *link; + struct uprobe_cpu_buffer *ucb; + + ucb = prepare_uprobe_buffer(tu, regs, ucbp); rcu_read_lock(); trace_probe_for_each_link_rcu(link, &tu->tp) - __uprobe_trace_func(tu, func, regs, ucbp, link->file); + __uprobe_trace_func(tu, func, regs, ucb, link->file); rcu_read_unlock(); } diff --git a/net/9p/client.c b/net/9p/client.c index 00774656eeac..5cd94721d974 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -236,6 +236,8 @@ static int p9_fcall_init(struct p9_client *c, struct p9_fcall *fc, if (!fc->sdata) return -ENOMEM; fc->capacity = alloc_msize; + fc->id = 0; + fc->tag = P9_NOTAG; return 0; } diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 9402889840bf..d3dbb92153f2 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -423,9 +423,6 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock *sk; int err = 0; - if (irqs_disabled()) - return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ - spin_lock_bh(&stab->lock); sk = *psk; if (!sk_test || sk_test == sk) @@ -948,9 +945,6 @@ static long sock_hash_delete_elem(struct bpf_map *map, void *key) struct bpf_shtab_elem *elem; int ret = -ENOENT; - if (irqs_disabled()) - return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ - hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash); @@ -1680,19 +1674,23 @@ void sock_map_close(struct sock *sk, long timeout) lock_sock(sk); rcu_read_lock(); - psock = sk_psock_get(sk); - if (unlikely(!psock)) { - rcu_read_unlock(); - release_sock(sk); - saved_close = READ_ONCE(sk->sk_prot)->close; - } else { + psock = sk_psock(sk); + if (likely(psock)) { saved_close = psock->saved_close; sock_map_remove_links(sk, psock); + psock = sk_psock_get(sk); + if (unlikely(!psock)) + goto no_psock; rcu_read_unlock(); sk_psock_stop(psock); release_sock(sk); cancel_delayed_work_sync(&psock->work); sk_psock_put(sk, psock); + } else { + saved_close = READ_ONCE(sk->sk_prot)->close; +no_psock: + rcu_read_unlock(); + release_sock(sk); } /* Make sure we do not recurse. This is a bug. diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 049c3adeb850..4e3651101b86 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -161,9 +161,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) skb->dev = dev; skb_reset_mac_header(skb); - eth = (struct ethhdr *)skb->data; - skb_pull_inline(skb, ETH_HLEN); - + eth = eth_skb_pull_mac(skb); eth_skb_pkt_type(skb, dev); /* diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e03ba4a21c39..b24d74616637 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1532,7 +1532,7 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb) } NAPI_GRO_CB(skb)->flush |= flush; - NAPI_GRO_CB(skb)->inner_network_offset = off; + NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = off; /* Note : No need to call skb_gro_postpull_rcsum() here, * as we already checked checksum over ipv4 header was 0 diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 96accde527da..f3892ee9dfb3 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1887,10 +1887,11 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) goto done; if (fillargs.ifindex) { - err = -ENODEV; dev = dev_get_by_index_rcu(tgt_net, fillargs.ifindex); - if (!dev) + if (!dev) { + err = -ENODEV; goto done; + } in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto done; @@ -1902,7 +1903,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) cb->seq = inet_base_seq(tgt_net); - for_each_netdev_dump(net, dev, ctx->ifindex) { + for_each_netdev_dump(tgt_net, dev, ctx->ifindex) { in_dev = __in_dev_get_rcu(dev); if (!in_dev) continue; diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c index 69e331799604..73e66a088e25 100644 --- a/net/ipv4/netfilter/nf_tproxy_ipv4.c +++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c @@ -58,6 +58,8 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr) laddr = 0; indev = __in_dev_get_rcu(skb->dev); + if (!indev) + return daddr; in_dev_for_each_ifa_rcu(ifa, indev) { if (ifa->ifa_flags & IFA_F_SECONDARY) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 5fd54103174f..b3073d1c8f8f 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -129,7 +129,8 @@ struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ipv4_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst); -static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); +static void ipv4_negative_advice(struct sock *sk, + struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, @@ -825,22 +826,15 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf __ip_do_redirect(rt, skb, &fl4, true); } -static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) +static void ipv4_negative_advice(struct sock *sk, + struct dst_entry *dst) { struct rtable *rt = dst_rtable(dst); - struct dst_entry *ret = dst; - if (rt) { - if (dst->obsolete > 0) { - ip_rt_put(rt); - ret = NULL; - } else if ((rt->rt_flags & RTCF_REDIRECTED) || - rt->dst.expires) { - ip_rt_put(rt); - ret = NULL; - } - } - return ret; + if ((dst->obsolete > 0) || + (rt->rt_flags & RTCF_REDIRECTED) || + rt->dst.expires) + sk_dst_reset(sk); } /* diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 30ef0c8f5e92..b710958393e6 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1144,14 +1144,9 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, #endif } - /* RFC 7323 2.3 - * The window field (SEG.WND) of every outgoing segment, with the - * exception of <SYN> segments, MUST be right-shifted by - * Rcv.Wind.Shift bits: - */ tcp_v4_send_ack(sk, skb, seq, tcp_rsk(req)->rcv_nxt, - req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, + tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale, tcp_rsk_tsval(tcp_rsk(req)), READ_ONCE(req->ts_recent), 0, &key, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index b93619b2384b..538c06f95918 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -783,8 +783,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* RFC793: "first check sequence number". */ - if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq, - tcp_rsk(req)->rcv_nxt, tcp_rsk(req)->rcv_nxt + req->rsk_rcv_wnd)) { + if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, + TCP_SKB_CB(skb)->end_seq, + tcp_rsk(req)->rcv_nxt, + tcp_rsk(req)->rcv_nxt + + tcp_synack_window(req))) { /* Out of window: send ACK and drop. */ if (!(flg & TCP_FLAG_RST) && !tcp_oow_rate_limited(sock_net(sk), skb, diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index bd5aff97d8b1..9822163428b0 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -236,7 +236,7 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head, if (unlikely(!iph)) goto out; - NAPI_GRO_CB(skb)->inner_network_offset = off; + NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = off; flush += ntohs(iph->payload_len) != skb->len - hlen; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index bbc2a0dd9314..a504b88ec06b 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -87,7 +87,8 @@ struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ip6_mtu(const struct dst_entry *dst); -static struct dst_entry *ip6_negative_advice(struct dst_entry *); +static void ip6_negative_advice(struct sock *sk, + struct dst_entry *dst); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, struct net_device *dev); @@ -2770,24 +2771,24 @@ INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, } EXPORT_INDIRECT_CALLABLE(ip6_dst_check); -static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) +static void ip6_negative_advice(struct sock *sk, + struct dst_entry *dst) { struct rt6_info *rt = dst_rt6_info(dst); - if (rt) { - if (rt->rt6i_flags & RTF_CACHE) { - rcu_read_lock(); - if (rt6_check_expired(rt)) { - rt6_remove_exception_rt(rt); - dst = NULL; - } - rcu_read_unlock(); - } else { - dst_release(dst); - dst = NULL; + if (rt->rt6i_flags & RTF_CACHE) { + rcu_read_lock(); + if (rt6_check_expired(rt)) { + /* counteract the dst_release() in sk_dst_reset() */ + dst_hold(dst); + sk_dst_reset(sk); + + rt6_remove_exception_rt(rt); } + rcu_read_unlock(); + return; } - return dst; + sk_dst_reset(sk); } static void ip6_link_failure(struct sk_buff *skb) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 4c3605485b68..8c577b651bfc 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1272,15 +1272,10 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ - /* RFC 7323 2.3 - * The window field (SEG.WND) of every outgoing segment, with the - * exception of <SYN> segments, MUST be right-shifted by - * Rcv.Wind.Shift bits: - */ tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, tcp_rsk(req)->rcv_nxt, - req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, + tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale, tcp_rsk_tsval(tcp_rsk(req)), READ_ONCE(req->ts_recent), sk->sk_bound_dev_if, &key, ipv6_get_dsfield(ipv6_hdr(skb)), 0, diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 6c3f28bc59b3..54e2a1dd7f5f 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -549,6 +549,9 @@ list_set_cancel_gc(struct ip_set *set) if (SET_WITH_TIMEOUT(set)) timer_shutdown_sync(&map->gc); + + /* Flush list to drop references to other ipsets */ + list_set_flush(set); } static const struct ip_set_type_variant set_variant = { diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 00f4bd21c59b..f1c31757e496 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -169,7 +169,9 @@ instance_destroy_rcu(struct rcu_head *head) struct nfqnl_instance *inst = container_of(head, struct nfqnl_instance, rcu); + rcu_read_lock(); nfqnl_flush(inst, NULL, 0); + rcu_read_unlock(); kfree(inst); module_put(THIS_MODULE); } diff --git a/net/netfilter/nft_fib.c b/net/netfilter/nft_fib.c index 37cfe6dd712d..b58f62195ff3 100644 --- a/net/netfilter/nft_fib.c +++ b/net/netfilter/nft_fib.c @@ -35,11 +35,9 @@ int nft_fib_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, switch (priv->result) { case NFT_FIB_RESULT_OIF: case NFT_FIB_RESULT_OIFNAME: - hooks = (1 << NF_INET_PRE_ROUTING); - if (priv->flags & NFTA_FIB_F_IIF) { - hooks |= (1 << NF_INET_LOCAL_IN) | - (1 << NF_INET_FORWARD); - } + hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD); break; case NFT_FIB_RESULT_ADDRTYPE: if (priv->flags & NFTA_FIB_F_IIF) diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 0a689c8e0295..0c43d748e23a 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -45,36 +45,27 @@ nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u8 offset, u8 len) int mac_off = skb_mac_header(skb) - skb->data; u8 *vlanh, *dst_u8 = (u8 *) d; struct vlan_ethhdr veth; - u8 vlan_hlen = 0; - - if ((skb->protocol == htons(ETH_P_8021AD) || - skb->protocol == htons(ETH_P_8021Q)) && - offset >= VLAN_ETH_HLEN && offset < VLAN_ETH_HLEN + VLAN_HLEN) - vlan_hlen += VLAN_HLEN; vlanh = (u8 *) &veth; - if (offset < VLAN_ETH_HLEN + vlan_hlen) { + if (offset < VLAN_ETH_HLEN) { u8 ethlen = len; - if (vlan_hlen && - skb_copy_bits(skb, mac_off, &veth, VLAN_ETH_HLEN) < 0) - return false; - else if (!nft_payload_rebuild_vlan_hdr(skb, mac_off, &veth)) + if (!nft_payload_rebuild_vlan_hdr(skb, mac_off, &veth)) return false; - if (offset + len > VLAN_ETH_HLEN + vlan_hlen) - ethlen -= offset + len - VLAN_ETH_HLEN - vlan_hlen; + if (offset + len > VLAN_ETH_HLEN) + ethlen -= offset + len - VLAN_ETH_HLEN; - memcpy(dst_u8, vlanh + offset - vlan_hlen, ethlen); + memcpy(dst_u8, vlanh + offset, ethlen); len -= ethlen; if (len == 0) return true; dst_u8 += ethlen; - offset = ETH_HLEN + vlan_hlen; + offset = ETH_HLEN; } else { - offset -= VLAN_HLEN + vlan_hlen; + offset -= VLAN_HLEN; } return skb_copy_bits(skb, offset + mac_off, dst_u8, len) == 0; @@ -154,12 +145,12 @@ int nft_payload_inner_offset(const struct nft_pktinfo *pkt) return pkt->inneroff; } -static bool nft_payload_need_vlan_copy(const struct nft_payload *priv) +static bool nft_payload_need_vlan_adjust(u32 offset, u32 len) { - unsigned int len = priv->offset + priv->len; + unsigned int boundary = offset + len; /* data past ether src/dst requested, copy needed */ - if (len > offsetof(struct ethhdr, h_proto)) + if (boundary > offsetof(struct ethhdr, h_proto)) return true; return false; @@ -183,7 +174,7 @@ void nft_payload_eval(const struct nft_expr *expr, goto err; if (skb_vlan_tag_present(skb) && - nft_payload_need_vlan_copy(priv)) { + nft_payload_need_vlan_adjust(priv->offset, priv->len)) { if (!nft_payload_copy_vlan(dest, skb, priv->offset, priv->len)) goto err; @@ -810,21 +801,79 @@ struct nft_payload_set { u8 csum_flags; }; +/* This is not struct vlan_hdr. */ +struct nft_payload_vlan_hdr { + __be16 h_vlan_proto; + __be16 h_vlan_TCI; +}; + +static bool +nft_payload_set_vlan(const u32 *src, struct sk_buff *skb, u8 offset, u8 len, + int *vlan_hlen) +{ + struct nft_payload_vlan_hdr *vlanh; + __be16 vlan_proto; + u16 vlan_tci; + + if (offset >= offsetof(struct vlan_ethhdr, h_vlan_encapsulated_proto)) { + *vlan_hlen = VLAN_HLEN; + return true; + } + + switch (offset) { + case offsetof(struct vlan_ethhdr, h_vlan_proto): + if (len == 2) { + vlan_proto = nft_reg_load_be16(src); + skb->vlan_proto = vlan_proto; + } else if (len == 4) { + vlanh = (struct nft_payload_vlan_hdr *)src; + __vlan_hwaccel_put_tag(skb, vlanh->h_vlan_proto, + ntohs(vlanh->h_vlan_TCI)); + } else { + return false; + } + break; + case offsetof(struct vlan_ethhdr, h_vlan_TCI): + if (len != 2) + return false; + + vlan_tci = ntohs(nft_reg_load_be16(src)); + skb->vlan_tci = vlan_tci; + break; + default: + return false; + } + + return true; +} + static void nft_payload_set_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_payload_set *priv = nft_expr_priv(expr); - struct sk_buff *skb = pkt->skb; const u32 *src = ®s->data[priv->sreg]; - int offset, csum_offset; + int offset, csum_offset, vlan_hlen = 0; + struct sk_buff *skb = pkt->skb; __wsum fsum, tsum; switch (priv->base) { case NFT_PAYLOAD_LL_HEADER: if (!skb_mac_header_was_set(skb)) goto err; - offset = skb_mac_header(skb) - skb->data; + + if (skb_vlan_tag_present(skb) && + nft_payload_need_vlan_adjust(priv->offset, priv->len)) { + if (!nft_payload_set_vlan(src, skb, + priv->offset, priv->len, + &vlan_hlen)) + goto err; + + if (!vlan_hlen) + return; + } + + offset = skb_mac_header(skb) - skb->data - vlan_hlen; break; case NFT_PAYLOAD_NETWORK_HEADER: offset = skb_network_offset(skb); diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 1ab17e8a7260..937a0c513c17 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1151,11 +1151,6 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, list_for_each_entry(entry, &new->entries, list) cycle = ktime_add_ns(cycle, entry->interval); - if (!cycle) { - NL_SET_ERR_MSG(extack, "'cycle_time' can never be 0"); - return -EINVAL; - } - if (cycle < 0 || cycle > INT_MAX) { NL_SET_ERR_MSG(extack, "'cycle_time' is too big"); return -EINVAL; @@ -1164,6 +1159,11 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, new->cycle_time = cycle; } + if (new->cycle_time < new->num_entries * length_to_duration(q, ETH_ZLEN)) { + NL_SET_ERR_MSG(extack, "'cycle_time' is too small"); + return -EINVAL; + } + taprio_calculate_gate_durations(q, new); return 0; @@ -1848,6 +1848,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, } q->flags = taprio_flags; + /* Needed for length_to_duration() during netlink attribute parsing */ + taprio_set_picos_per_byte(dev, q); + err = taprio_parse_mqprio_opt(dev, mqprio, extack, q->flags); if (err < 0) return err; @@ -1907,7 +1910,6 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, if (err < 0) goto free_sched; - taprio_set_picos_per_byte(dev, q); taprio_update_queue_max_sdu(q, new_admin, stab); if (FULL_OFFLOAD_IS_ENABLED(q->flags)) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index e4af6616e1df..25b49efc0926 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -731,7 +731,7 @@ static int unix_listen(struct socket *sock, int backlog) if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET) goto out; /* Only stream/seqpacket sockets accept */ err = -EINVAL; - if (!u->addr) + if (!READ_ONCE(u->addr)) goto out; /* No listens on an unbound socket */ unix_state_lock(sk); if (sk->sk_state != TCP_CLOSE && sk->sk_state != TCP_LISTEN) @@ -1131,8 +1131,8 @@ static struct sock *unix_find_other(struct net *net, static int unix_autobind(struct sock *sk) { - unsigned int new_hash, old_hash = sk->sk_hash; struct unix_sock *u = unix_sk(sk); + unsigned int new_hash, old_hash; struct net *net = sock_net(sk); struct unix_address *addr; u32 lastnum, ordernum; @@ -1155,6 +1155,7 @@ static int unix_autobind(struct sock *sk) addr->name->sun_family = AF_UNIX; refcount_set(&addr->refcnt, 1); + old_hash = sk->sk_hash; ordernum = get_random_u32(); lastnum = ordernum & 0xFFFFF; retry: @@ -1195,8 +1196,8 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr, { umode_t mode = S_IFSOCK | (SOCK_INODE(sk->sk_socket)->i_mode & ~current_umask()); - unsigned int new_hash, old_hash = sk->sk_hash; struct unix_sock *u = unix_sk(sk); + unsigned int new_hash, old_hash; struct net *net = sock_net(sk); struct mnt_idmap *idmap; struct unix_address *addr; @@ -1234,6 +1235,7 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr, if (u->addr) goto out_unlock; + old_hash = sk->sk_hash; new_hash = unix_bsd_hash(d_backing_inode(dentry)); unix_table_double_lock(net, old_hash, new_hash); u->path.mnt = mntget(parent.mnt); @@ -1261,8 +1263,8 @@ out: static int unix_bind_abstract(struct sock *sk, struct sockaddr_un *sunaddr, int addr_len) { - unsigned int new_hash, old_hash = sk->sk_hash; struct unix_sock *u = unix_sk(sk); + unsigned int new_hash, old_hash; struct net *net = sock_net(sk); struct unix_address *addr; int err; @@ -1280,6 +1282,7 @@ static int unix_bind_abstract(struct sock *sk, struct sockaddr_un *sunaddr, goto out_mutex; } + old_hash = sk->sk_hash; new_hash = unix_abstract_hash(addr->name, addr->len, sk->sk_type); unix_table_double_lock(net, old_hash, new_hash); @@ -1369,7 +1372,7 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, if ((test_bit(SOCK_PASSCRED, &sock->flags) || test_bit(SOCK_PASSPIDFD, &sock->flags)) && - !unix_sk(sk)->addr) { + !READ_ONCE(unix_sk(sk)->addr)) { err = unix_autobind(sk); if (err) goto out; @@ -1481,7 +1484,8 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, goto out; if ((test_bit(SOCK_PASSCRED, &sock->flags) || - test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) { + test_bit(SOCK_PASSPIDFD, &sock->flags)) && + !READ_ONCE(u->addr)) { err = unix_autobind(sk); if (err) goto out; @@ -1950,7 +1954,8 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, } if ((test_bit(SOCK_PASSCRED, &sock->flags) || - test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) { + test_bit(SOCK_PASSPIDFD, &sock->flags)) && + !READ_ONCE(u->addr)) { err = unix_autobind(sk); if (err) goto out; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 475b904fe68b..66e07de2de35 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3910,15 +3910,10 @@ static void xfrm_link_failure(struct sk_buff *skb) /* Impossible. Such dst must be popped before reaches point of failure. */ } -static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst) +static void xfrm_negative_advice(struct sock *sk, struct dst_entry *dst) { - if (dst) { - if (dst->obsolete) { - dst_release(dst); - dst = NULL; - } - } - return dst; + if (dst->obsolete) + sk_dst_reset(sk); } static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr) diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index d9520cb826b3..af393c7dee1f 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -728,7 +728,7 @@ static int sets_patch(struct object *obj) static int symbols_patch(struct object *obj) { - int err; + off_t err; if (__symbols_patch(obj, &obj->structs) || __symbols_patch(obj, &obj->unions) || diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index a8188202413e..43742ac5b00d 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -148,6 +148,7 @@ enum { NETDEV_A_QSTATS_RX_ALLOC_FAIL, NETDEV_A_QSTATS_RX_HW_DROPS, NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS, + NETDEV_A_QSTATS_RX_CSUM_COMPLETE, NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY, NETDEV_A_QSTATS_RX_CSUM_NONE, NETDEV_A_QSTATS_RX_CSUM_BAD, diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c index a336786a22a3..3df0125ed5fa 100644 --- a/tools/lib/bpf/features.c +++ b/tools/lib/bpf/features.c @@ -392,11 +392,40 @@ static int probe_uprobe_multi_link(int token_fd) link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts); err = -errno; /* close() can clobber errno */ + if (link_fd >= 0 || err != -EBADF) { + close(link_fd); + close(prog_fd); + return 0; + } + + /* Initial multi-uprobe support in kernel didn't handle PID filtering + * correctly (it was doing thread filtering, not process filtering). + * So now we'll detect if PID filtering logic was fixed, and, if not, + * we'll pretend multi-uprobes are not supported, if not. + * Multi-uprobes are used in USDT attachment logic, and we need to be + * conservative here, because multi-uprobe selection happens early at + * load time, while the use of PID filtering is known late at + * attachment time, at which point it's too late to undo multi-uprobe + * selection. + * + * Creating uprobe with pid == -1 for (invalid) '/' binary will fail + * early with -EINVAL on kernels with fixed PID filtering logic; + * otherwise -ESRCH would be returned if passed correct binary path + * (but we'll just get -BADF, of course). + */ + link_opts.uprobe_multi.pid = -1; /* invalid PID */ + link_opts.uprobe_multi.path = "/"; /* invalid path */ + link_opts.uprobe_multi.offsets = &offset; + link_opts.uprobe_multi.cnt = 1; + + link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts); + err = -errno; /* close() can clobber errno */ + if (link_fd >= 0) close(link_fd); close(prog_fd); - return link_fd < 0 && err == -EBADF; + return link_fd < 0 && err == -EINVAL; } static int probe_kern_bpf_cookie(int token_fd) diff --git a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c index 15ee7b2fc410..b9135720024c 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c @@ -73,6 +73,16 @@ static int create_netkit(int mode, int policy, int peer_policy, int *ifindex, "up primary"); ASSERT_OK(system("ip addr add dev " netkit_name " 10.0.0.1/24"), "addr primary"); + + if (mode == NETKIT_L3) { + ASSERT_EQ(system("ip link set dev " netkit_name + " addr ee:ff:bb:cc:aa:dd 2> /dev/null"), 512, + "set hwaddress"); + } else { + ASSERT_OK(system("ip link set dev " netkit_name + " addr ee:ff:bb:cc:aa:dd"), + "set hwaddress"); + } if (same_netns) { ASSERT_OK(system("ip link set dev " netkit_peer " up"), "up peer"); @@ -89,6 +99,16 @@ static int create_netkit(int mode, int policy, int peer_policy, int *ifindex, return err; } +static void move_netkit(void) +{ + ASSERT_OK(system("ip link set " netkit_peer " netns foo"), + "move peer"); + ASSERT_OK(system("ip netns exec foo ip link set dev " + netkit_peer " up"), "up peer"); + ASSERT_OK(system("ip netns exec foo ip addr add dev " + netkit_peer " 10.0.0.2/24"), "addr peer"); +} + static void destroy_netkit(void) { ASSERT_OK(system("ip link del dev " netkit_name), "del primary"); @@ -685,3 +705,77 @@ void serial_test_tc_netkit_neigh_links(void) serial_test_tc_netkit_neigh_links_target(NETKIT_L2, BPF_NETKIT_PRIMARY); serial_test_tc_netkit_neigh_links_target(NETKIT_L3, BPF_NETKIT_PRIMARY); } + +static void serial_test_tc_netkit_pkt_type_mode(int mode) +{ + LIBBPF_OPTS(bpf_netkit_opts, optl_nk); + LIBBPF_OPTS(bpf_tcx_opts, optl_tcx); + int err, ifindex, ifindex2; + struct test_tc_link *skel; + struct bpf_link *link; + + err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, + &ifindex, true); + if (err) + return; + + ifindex2 = if_nametoindex(netkit_peer); + ASSERT_NEQ(ifindex, ifindex2, "ifindex_1_2"); + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, + BPF_NETKIT_PRIMARY), 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc7, + BPF_TCX_INGRESS), 0, "tc7_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0); + assert_mprog_count_ifindex(ifindex2, BPF_TCX_INGRESS, 0); + + link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl_nk); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1); + assert_mprog_count_ifindex(ifindex2, BPF_TCX_INGRESS, 0); + + link = bpf_program__attach_tcx(skel->progs.tc7, ifindex2, &optl_tcx); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc7 = link; + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1); + assert_mprog_count_ifindex(ifindex2, BPF_TCX_INGRESS, 1); + + move_netkit(); + + tc_skel_reset_all_seen(skel); + skel->bss->set_type = true; + ASSERT_EQ(send_icmp(), 0, "icmp_pkt"); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc7, true, "seen_tc7"); + + ASSERT_EQ(skel->bss->seen_host, true, "seen_host"); + ASSERT_EQ(skel->bss->seen_mcast, true, "seen_mcast"); +cleanup: + test_tc_link__destroy(skel); + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0); + destroy_netkit(); +} + +void serial_test_tc_netkit_pkt_type(void) +{ + serial_test_tc_netkit_pkt_type_mode(NETKIT_L2); + serial_test_tc_netkit_pkt_type_mode(NETKIT_L3); +} diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c index 8269cdee33ae..bf6ca8e3eb13 100644 --- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c @@ -1,12 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 #include <unistd.h> +#include <pthread.h> #include <test_progs.h> #include "uprobe_multi.skel.h" #include "uprobe_multi_bench.skel.h" #include "uprobe_multi_usdt.skel.h" #include "bpf/libbpf_internal.h" #include "testing_helpers.h" +#include "../sdt.h" static char test_data[] = "test_data"; @@ -25,9 +27,17 @@ noinline void uprobe_multi_func_3(void) asm volatile (""); } +noinline void usdt_trigger(void) +{ + STAP_PROBE(test, pid_filter_usdt); +} + struct child { int go[2]; + int c2p[2]; /* child -> parent channel */ int pid; + int tid; + pthread_t thread; }; static void release_child(struct child *child) @@ -38,6 +48,10 @@ static void release_child(struct child *child) return; close(child->go[1]); close(child->go[0]); + if (child->thread) + pthread_join(child->thread, NULL); + close(child->c2p[0]); + close(child->c2p[1]); if (child->pid > 0) waitpid(child->pid, &child_status, 0); } @@ -63,7 +77,7 @@ static struct child *spawn_child(void) if (pipe(child.go)) return NULL; - child.pid = fork(); + child.pid = child.tid = fork(); if (child.pid < 0) { release_child(&child); errno = EINVAL; @@ -82,6 +96,7 @@ static struct child *spawn_child(void) uprobe_multi_func_1(); uprobe_multi_func_2(); uprobe_multi_func_3(); + usdt_trigger(); exit(errno); } @@ -89,6 +104,67 @@ static struct child *spawn_child(void) return &child; } +static void *child_thread(void *ctx) +{ + struct child *child = ctx; + int c = 0, err; + + child->tid = syscall(SYS_gettid); + + /* let parent know we are ready */ + err = write(child->c2p[1], &c, 1); + if (err != 1) + pthread_exit(&err); + + /* wait for parent's kick */ + err = read(child->go[0], &c, 1); + if (err != 1) + pthread_exit(&err); + + uprobe_multi_func_1(); + uprobe_multi_func_2(); + uprobe_multi_func_3(); + usdt_trigger(); + + err = 0; + pthread_exit(&err); +} + +static struct child *spawn_thread(void) +{ + static struct child child; + int c, err; + + /* pipe to notify child to execute the trigger functions */ + if (pipe(child.go)) + return NULL; + /* pipe to notify parent that child thread is ready */ + if (pipe(child.c2p)) { + close(child.go[0]); + close(child.go[1]); + return NULL; + } + + child.pid = getpid(); + + err = pthread_create(&child.thread, NULL, child_thread, &child); + if (err) { + err = -errno; + close(child.go[0]); + close(child.go[1]); + close(child.c2p[0]); + close(child.c2p[1]); + errno = -err; + return NULL; + } + + err = read(child.c2p[0], &c, 1); + if (!ASSERT_EQ(err, 1, "child_thread_ready")) + return NULL; + + return &child; +} + static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child) { skel->bss->uprobe_multi_func_1_addr = (__u64) uprobe_multi_func_1; @@ -103,15 +179,23 @@ static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child * passed at the probe attach. */ skel->bss->pid = child ? 0 : getpid(); + skel->bss->expect_pid = child ? child->pid : 0; + + /* trigger all probes, if we are testing child *process*, just to make + * sure that PID filtering doesn't let through activations from wrong + * PIDs; when we test child *thread*, we don't want to do this to + * avoid double counting number of triggering events + */ + if (!child || !child->thread) { + uprobe_multi_func_1(); + uprobe_multi_func_2(); + uprobe_multi_func_3(); + usdt_trigger(); + } if (child) kick_child(child); - /* trigger all probes */ - uprobe_multi_func_1(); - uprobe_multi_func_2(); - uprobe_multi_func_3(); - /* * There are 2 entry and 2 exit probe called for each uprobe_multi_func_[123] * function and each slepable probe (6) increments uprobe_multi_sleep_result. @@ -126,8 +210,12 @@ static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child ASSERT_EQ(skel->bss->uprobe_multi_sleep_result, 6, "uprobe_multi_sleep_result"); - if (child) + ASSERT_FALSE(skel->bss->bad_pid_seen, "bad_pid_seen"); + + if (child) { ASSERT_EQ(skel->bss->child_pid, child->pid, "uprobe_multi_child_pid"); + ASSERT_EQ(skel->bss->child_tid, child->tid, "uprobe_multi_child_tid"); + } } static void test_skel_api(void) @@ -190,8 +278,24 @@ __test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_mul if (!ASSERT_OK_PTR(skel->links.uprobe_extra, "bpf_program__attach_uprobe_multi")) goto cleanup; + /* Attach (uprobe-backed) USDTs */ + skel->links.usdt_pid = bpf_program__attach_usdt(skel->progs.usdt_pid, pid, binary, + "test", "pid_filter_usdt", NULL); + if (!ASSERT_OK_PTR(skel->links.usdt_pid, "attach_usdt_pid")) + goto cleanup; + + skel->links.usdt_extra = bpf_program__attach_usdt(skel->progs.usdt_extra, -1, binary, + "test", "pid_filter_usdt", NULL); + if (!ASSERT_OK_PTR(skel->links.usdt_extra, "attach_usdt_extra")) + goto cleanup; + uprobe_multi_test_run(skel, child); + ASSERT_FALSE(skel->bss->bad_pid_seen_usdt, "bad_pid_seen_usdt"); + if (child) { + ASSERT_EQ(skel->bss->child_pid_usdt, child->pid, "usdt_multi_child_pid"); + ASSERT_EQ(skel->bss->child_tid_usdt, child->tid, "usdt_multi_child_tid"); + } cleanup: uprobe_multi__destroy(skel); } @@ -210,6 +314,13 @@ test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_multi return; __test_attach_api(binary, pattern, opts, child); + + /* pid filter (thread) */ + child = spawn_thread(); + if (!ASSERT_OK_PTR(child, "spawn_thread")) + return; + + __test_attach_api(binary, pattern, opts, child); } static void test_attach_api_pattern(void) @@ -397,7 +508,7 @@ static void test_attach_api_fails(void) link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts); if (!ASSERT_ERR(link_fd, "link_fd")) goto cleanup; - ASSERT_EQ(link_fd, -ESRCH, "pid_is_wrong"); + ASSERT_EQ(link_fd, -EINVAL, "pid_is_wrong"); cleanup: if (link_fd >= 0) @@ -495,6 +606,13 @@ static void test_link_api(void) return; __test_link_api(child); + + /* pid filter (thread) */ + child = spawn_thread(); + if (!ASSERT_OK_PTR(child, "spawn_thread")) + return; + + __test_link_api(child); } static void test_bench_attach_uprobe(void) diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index c60db8beeb73..1c9c4ec1be11 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -67,6 +67,7 @@ #include "verifier_search_pruning.skel.h" #include "verifier_sock.skel.h" #include "verifier_sock_addr.skel.h" +#include "verifier_sockmap_mutate.skel.h" #include "verifier_spill_fill.skel.h" #include "verifier_spin_lock.skel.h" #include "verifier_stack_ptr.skel.h" @@ -183,6 +184,7 @@ void test_verifier_sdiv(void) { RUN(verifier_sdiv); } void test_verifier_search_pruning(void) { RUN(verifier_search_pruning); } void test_verifier_sock(void) { RUN(verifier_sock); } void test_verifier_sock_addr(void) { RUN(verifier_sock_addr); } +void test_verifier_sockmap_mutate(void) { RUN(verifier_sockmap_mutate); } void test_verifier_spill_fill(void) { RUN(verifier_spill_fill); } void test_verifier_spin_lock(void) { RUN(verifier_spin_lock); } void test_verifier_stack_ptr(void) { RUN(verifier_stack_ptr); } diff --git a/tools/testing/selftests/bpf/progs/test_tc_link.c b/tools/testing/selftests/bpf/progs/test_tc_link.c index 992400acb957..ab3eae3d6af8 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_link.c +++ b/tools/testing/selftests/bpf/progs/test_tc_link.c @@ -4,7 +4,8 @@ #include <linux/bpf.h> #include <linux/if_ether.h> - +#include <linux/stddef.h> +#include <linux/if_packet.h> #include <bpf/bpf_endian.h> #include <bpf/bpf_helpers.h> @@ -16,7 +17,13 @@ bool seen_tc3; bool seen_tc4; bool seen_tc5; bool seen_tc6; +bool seen_tc7; + +bool set_type; + bool seen_eth; +bool seen_host; +bool seen_mcast; SEC("tc/ingress") int tc1(struct __sk_buff *skb) @@ -28,8 +35,16 @@ int tc1(struct __sk_buff *skb) if (bpf_skb_load_bytes(skb, 0, ð, sizeof(eth))) goto out; seen_eth = eth.h_proto == bpf_htons(ETH_P_IP); + seen_host = skb->pkt_type == PACKET_HOST; + if (seen_host && set_type) { + eth.h_dest[0] = 4; + if (bpf_skb_store_bytes(skb, 0, ð, sizeof(eth), 0)) + goto fail; + bpf_skb_change_type(skb, PACKET_MULTICAST); + } out: seen_tc1 = true; +fail: return TCX_NEXT; } @@ -67,3 +82,21 @@ int tc6(struct __sk_buff *skb) seen_tc6 = true; return TCX_PASS; } + +SEC("tc/ingress") +int tc7(struct __sk_buff *skb) +{ + struct ethhdr eth = {}; + + if (skb->protocol != __bpf_constant_htons(ETH_P_IP)) + goto out; + if (bpf_skb_load_bytes(skb, 0, ð, sizeof(eth))) + goto out; + if (eth.h_dest[0] == 4 && set_type) { + seen_mcast = skb->pkt_type == PACKET_MULTICAST; + bpf_skb_change_type(skb, PACKET_HOST); + } +out: + seen_tc7 = true; + return TCX_PASS; +} diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi.c b/tools/testing/selftests/bpf/progs/uprobe_multi.c index 419d9aa28fce..44190efcdba2 100644 --- a/tools/testing/selftests/bpf/progs/uprobe_multi.c +++ b/tools/testing/selftests/bpf/progs/uprobe_multi.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/bpf.h> +#include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include <stdbool.h> +#include <bpf/usdt.bpf.h> char _license[] SEC("license") = "GPL"; @@ -22,6 +22,13 @@ __u64 uprobe_multi_sleep_result = 0; int pid = 0; int child_pid = 0; +int child_tid = 0; +int child_pid_usdt = 0; +int child_tid_usdt = 0; + +int expect_pid = 0; +bool bad_pid_seen = false; +bool bad_pid_seen_usdt = false; bool test_cookie = false; void *user_ptr = 0; @@ -36,11 +43,19 @@ static __always_inline bool verify_sleepable_user_copy(void) static void uprobe_multi_check(void *ctx, bool is_return, bool is_sleep) { - child_pid = bpf_get_current_pid_tgid() >> 32; + __u64 cur_pid_tgid = bpf_get_current_pid_tgid(); + __u32 cur_pid; - if (pid && child_pid != pid) + cur_pid = cur_pid_tgid >> 32; + if (pid && cur_pid != pid) return; + if (expect_pid && cur_pid != expect_pid) + bad_pid_seen = true; + + child_pid = cur_pid_tgid >> 32; + child_tid = (__u32)cur_pid_tgid; + __u64 cookie = test_cookie ? bpf_get_attach_cookie(ctx) : 0; __u64 addr = bpf_get_func_ip(ctx); @@ -97,5 +112,32 @@ int uretprobe_sleep(struct pt_regs *ctx) SEC("uprobe.multi//proc/self/exe:uprobe_multi_func_*") int uprobe_extra(struct pt_regs *ctx) { + /* we need this one just to mix PID-filtered and global uprobes */ + return 0; +} + +SEC("usdt") +int usdt_pid(struct pt_regs *ctx) +{ + __u64 cur_pid_tgid = bpf_get_current_pid_tgid(); + __u32 cur_pid; + + cur_pid = cur_pid_tgid >> 32; + if (pid && cur_pid != pid) + return 0; + + if (expect_pid && cur_pid != expect_pid) + bad_pid_seen_usdt = true; + + child_pid_usdt = cur_pid_tgid >> 32; + child_tid_usdt = (__u32)cur_pid_tgid; + + return 0; +} + +SEC("usdt") +int usdt_extra(struct pt_regs *ctx) +{ + /* we need this one just to mix PID-filtered and global USDT probes */ return 0; } diff --git a/tools/testing/selftests/bpf/progs/verifier_sockmap_mutate.c b/tools/testing/selftests/bpf/progs/verifier_sockmap_mutate.c new file mode 100644 index 000000000000..fe4b123187b8 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_sockmap_mutate.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#include "bpf_misc.h" + +#define __always_unused __attribute__((unused)) + +char _license[] SEC("license") = "GPL"; + +struct sock { +} __attribute__((preserve_access_index)); + +struct bpf_iter__sockmap { + union { + struct sock *sk; + }; +} __attribute__((preserve_access_index)); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKHASH); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} sockhash SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 1); + __type(key, int); + __type(value, int); +} sockmap SEC(".maps"); + +enum { CG_OK = 1 }; + +int zero = 0; + +static __always_inline void test_sockmap_delete(void) +{ + bpf_map_delete_elem(&sockmap, &zero); + bpf_map_delete_elem(&sockhash, &zero); +} + +static __always_inline void test_sockmap_update(void *sk) +{ + if (sk) { + bpf_map_update_elem(&sockmap, &zero, sk, BPF_ANY); + bpf_map_update_elem(&sockhash, &zero, sk, BPF_ANY); + } +} + +static __always_inline void test_sockmap_lookup_and_update(void) +{ + struct bpf_sock *sk = bpf_map_lookup_elem(&sockmap, &zero); + + if (sk) { + test_sockmap_update(sk); + bpf_sk_release(sk); + } +} + +static __always_inline void test_sockmap_mutate(void *sk) +{ + test_sockmap_delete(); + test_sockmap_update(sk); +} + +static __always_inline void test_sockmap_lookup_and_mutate(void) +{ + test_sockmap_delete(); + test_sockmap_lookup_and_update(); +} + +SEC("action") +__success +int test_sched_act(struct __sk_buff *skb) +{ + test_sockmap_mutate(skb->sk); + return 0; +} + +SEC("classifier") +__success +int test_sched_cls(struct __sk_buff *skb) +{ + test_sockmap_mutate(skb->sk); + return 0; +} + +SEC("flow_dissector") +__success +int test_flow_dissector_delete(struct __sk_buff *skb __always_unused) +{ + test_sockmap_delete(); + return 0; +} + +SEC("flow_dissector") +__failure __msg("program of this type cannot use helper bpf_sk_release") +int test_flow_dissector_update(struct __sk_buff *skb __always_unused) +{ + test_sockmap_lookup_and_update(); /* no access to skb->sk */ + return 0; +} + +SEC("iter/sockmap") +__success +int test_trace_iter(struct bpf_iter__sockmap *ctx) +{ + test_sockmap_mutate(ctx->sk); + return 0; +} + +SEC("raw_tp/kfree") +__failure __msg("cannot update sockmap in this context") +int test_raw_tp_delete(const void *ctx __always_unused) +{ + test_sockmap_delete(); + return 0; +} + +SEC("raw_tp/kfree") +__failure __msg("cannot update sockmap in this context") +int test_raw_tp_update(const void *ctx __always_unused) +{ + test_sockmap_lookup_and_update(); + return 0; +} + +SEC("sk_lookup") +__success +int test_sk_lookup(struct bpf_sk_lookup *ctx) +{ + test_sockmap_mutate(ctx->sk); + return 0; +} + +SEC("sk_reuseport") +__success +int test_sk_reuseport(struct sk_reuseport_md *ctx) +{ + test_sockmap_mutate(ctx->sk); + return 0; +} + +SEC("socket") +__success +int test_socket_filter(struct __sk_buff *skb) +{ + test_sockmap_mutate(skb->sk); + return 0; +} + +SEC("sockops") +__success +int test_sockops_delete(struct bpf_sock_ops *ctx __always_unused) +{ + test_sockmap_delete(); + return CG_OK; +} + +SEC("sockops") +__failure __msg("cannot update sockmap in this context") +int test_sockops_update(struct bpf_sock_ops *ctx) +{ + test_sockmap_update(ctx->sk); + return CG_OK; +} + +SEC("sockops") +__success +int test_sockops_update_dedicated(struct bpf_sock_ops *ctx) +{ + bpf_sock_map_update(ctx, &sockmap, &zero, BPF_ANY); + bpf_sock_hash_update(ctx, &sockhash, &zero, BPF_ANY); + return CG_OK; +} + +SEC("xdp") +__success +int test_xdp(struct xdp_md *ctx __always_unused) +{ + test_sockmap_lookup_and_mutate(); + return XDP_PASS; +} diff --git a/tools/testing/selftests/net/hsr/hsr_ping.sh b/tools/testing/selftests/net/hsr/hsr_ping.sh index 790294c8af83..3684b813b0f6 100755 --- a/tools/testing/selftests/net/hsr/hsr_ping.sh +++ b/tools/testing/selftests/net/hsr/hsr_ping.sh @@ -174,6 +174,8 @@ trap cleanup_all_ns EXIT setup_hsr_interfaces 0 do_complete_ping_test +setup_ns ns1 ns2 ns3 + setup_hsr_interfaces 1 do_complete_ping_test diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index fefa9173bdaa..2b66c5fa71eb 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -261,6 +261,8 @@ reset() TEST_NAME="${1}" + MPTCP_LIB_SUBTEST_FLAKY=0 # reset if modified + if skip_test; then MPTCP_LIB_TEST_COUNTER=$((MPTCP_LIB_TEST_COUNTER+1)) last_test_ignored=1 @@ -448,7 +450,9 @@ reset_with_tcp_filter() # $1: err msg fail_test() { - ret=${KSFT_FAIL} + if ! mptcp_lib_subtest_is_flaky; then + ret=${KSFT_FAIL} + fi if [ ${#} -gt 0 ]; then print_fail "${@}" @@ -3069,6 +3073,7 @@ fullmesh_tests() fastclose_tests() { if reset_check_counter "fastclose test" "MPTcpExtMPFastcloseTx"; then + MPTCP_LIB_SUBTEST_FLAKY=1 test_linkfail=1024 fastclose=client \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 @@ -3077,6 +3082,7 @@ fastclose_tests() fi if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then + MPTCP_LIB_SUBTEST_FLAKY=1 test_linkfail=1024 fastclose=server \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 0 0 0 1 @@ -3095,6 +3101,7 @@ fail_tests() { # single subflow if reset_with_fail "Infinite map" 1; then + MPTCP_LIB_SUBTEST_FLAKY=1 test_linkfail=128 \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 +1 +0 1 0 1 "$(pedit_action_pkts)" @@ -3103,6 +3110,7 @@ fail_tests() # multiple subflows if reset_with_fail "MP_FAIL MP_RST" 2; then + MPTCP_LIB_SUBTEST_FLAKY=1 tc -n $ns2 qdisc add dev ns2eth1 root netem rate 1mbit delay 5ms pm_nl_set_limits $ns1 0 1 pm_nl_set_limits $ns2 0 1 diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index ad2ebda5cb64..6ffa9b7a3260 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -21,6 +21,7 @@ declare -rx MPTCP_LIB_AF_INET6=10 MPTCP_LIB_SUBTESTS=() MPTCP_LIB_SUBTESTS_DUPLICATED=0 +MPTCP_LIB_SUBTEST_FLAKY=0 MPTCP_LIB_TEST_COUNTER=0 MPTCP_LIB_TEST_FORMAT="%02u %-50s" MPTCP_LIB_IP_MPTCP=0 @@ -41,6 +42,16 @@ else readonly MPTCP_LIB_COLOR_RESET= fi +# SELFTESTS_MPTCP_LIB_OVERRIDE_FLAKY env var can be set not to ignore errors +# from subtests marked as flaky +mptcp_lib_override_flaky() { + [ "${SELFTESTS_MPTCP_LIB_OVERRIDE_FLAKY:-}" = 1 ] +} + +mptcp_lib_subtest_is_flaky() { + [ "${MPTCP_LIB_SUBTEST_FLAKY}" = 1 ] && ! mptcp_lib_override_flaky +} + # $1: color, $2: text mptcp_lib_print_color() { echo -e "${MPTCP_LIB_START_PRINT:-}${*}${MPTCP_LIB_COLOR_RESET}" @@ -72,7 +83,16 @@ mptcp_lib_pr_skip() { } mptcp_lib_pr_fail() { - mptcp_lib_print_err "[FAIL]${1:+ ${*}}" + local title cmt + + if mptcp_lib_subtest_is_flaky; then + title="IGNO" + cmt=" (flaky)" + else + title="FAIL" + fi + + mptcp_lib_print_err "[${title}]${cmt}${1:+ ${*}}" } mptcp_lib_pr_info() { @@ -208,7 +228,13 @@ mptcp_lib_result_pass() { # $1: test name mptcp_lib_result_fail() { - __mptcp_lib_result_add "not ok" "${1}" + if mptcp_lib_subtest_is_flaky; then + # It might sound better to use 'not ok # TODO' or 'ok # SKIP', + # but some CIs don't understand 'TODO' and treat SKIP as errors. + __mptcp_lib_result_add "ok" "${1} # IGNORE Flaky" + else + __mptcp_lib_result_add "not ok" "${1}" + fi } # $1: test name diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 4b14b4412166..f74e1c3c126d 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -244,7 +244,7 @@ run_test() do_transfer $small $large $time lret=$? mptcp_lib_result_code "${lret}" "${msg}" - if [ $lret -ne 0 ]; then + if [ $lret -ne 0 ] && ! mptcp_lib_subtest_is_flaky; then ret=$lret [ $bail -eq 0 ] || exit $ret fi @@ -254,7 +254,7 @@ run_test() do_transfer $large $small $time lret=$? mptcp_lib_result_code "${lret}" "${msg}" - if [ $lret -ne 0 ]; then + if [ $lret -ne 0 ] && ! mptcp_lib_subtest_is_flaky; then ret=$lret [ $bail -eq 0 ] || exit $ret fi @@ -290,7 +290,7 @@ run_test 10 10 0 0 "balanced bwidth" run_test 10 10 1 25 "balanced bwidth with unbalanced delay" # we still need some additional infrastructure to pass the following test-cases -run_test 10 3 0 0 "unbalanced bwidth" +MPTCP_LIB_SUBTEST_FLAKY=1 run_test 10 3 0 0 "unbalanced bwidth" run_test 10 3 1 25 "unbalanced bwidth with unbalanced delay" run_test 10 3 25 1 "unbalanced bwidth with opposed, unbalanced delay" diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json index 12da0a939e3e..557fb074acf0 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json @@ -133,6 +133,50 @@ ] }, { + "id": "6f62", + "name": "Add taprio Qdisc with too short interval", + "category": [ + "qdisc", + "taprio" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "echo \"1 1 8\" > /sys/bus/netdevsim/new_device" + ], + "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: taprio num_tc 2 queues 1@0 1@1 sched-entry S 01 300 sched-entry S 02 1700 clockid CLOCK_TAI", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $ETH", + "matchPattern": "qdisc taprio 1: root refcnt", + "matchCount": "0", + "teardown": [ + "echo \"1\" > /sys/bus/netdevsim/del_device" + ] + }, + { + "id": "831f", + "name": "Add taprio Qdisc with too short cycle-time", + "category": [ + "qdisc", + "taprio" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "echo \"1 1 8\" > /sys/bus/netdevsim/new_device" + ], + "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: taprio num_tc 2 queues 1@0 1@1 sched-entry S 01 200000 sched-entry S 02 200000 cycle-time 100 clockid CLOCK_TAI", + "expExitCode": "2", + "verifyCmd": "$TC qdisc show dev $ETH", + "matchPattern": "qdisc taprio 1: root refcnt", + "matchCount": "0", + "teardown": [ + "echo \"1\" > /sys/bus/netdevsim/del_device" + ] + }, + { "id": "3e1e", "name": "Add taprio Qdisc with an invalid cycle-time", "category": [ |