diff options
| author | Jakub Kicinski <kuba@kernel.org> | 2022-02-10 17:29:56 -0800 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2022-02-10 17:29:56 -0800 |
| commit | 5b91c5cc0e7be4e41567cb2a6e21a8bb682c7cc5 (patch) | |
| tree | ed284edec0db783dfa80366ae8df078b02f35be9 | |
| parent | 4f5e483b8c7a644733db941a1ae00173baa7b463 (diff) | |
| parent | f1baf68e1383f6ed93eb9cff2866d46562607a43 (diff) | |
| download | linux-stable-5b91c5cc0e7be4e41567cb2a6e21a8bb682c7cc5.tar.gz linux-stable-5b91c5cc0e7be4e41567cb2a6e21a8bb682c7cc5.tar.bz2 linux-stable-5b91c5cc0e7be4e41567cb2a6e21a8bb682c7cc5.zip | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
No conflicts.
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
328 files changed, 4072 insertions, 1720 deletions
diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 0ec7b7f1524b..ea281dd75517 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -100,6 +100,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A510 | #2051678 | ARM64_ERRATUM_2051678 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A510 | #2077057 | ARM64_ERRATUM_2077057 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A710 | #2119858 | ARM64_ERRATUM_2119858 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A710 | #2054223 | ARM64_ERRATUM_2054223 | diff --git a/Documentation/dev-tools/kunit/usage.rst b/Documentation/dev-tools/kunit/usage.rst index 76af931a332c..1c83e7d60a8a 100644 --- a/Documentation/dev-tools/kunit/usage.rst +++ b/Documentation/dev-tools/kunit/usage.rst @@ -242,7 +242,7 @@ example: int rectangle_area(struct shape *this) { - struct rectangle *self = container_of(this, struct shape, parent); + struct rectangle *self = container_of(this, struct rectangle, parent); return self->length * self->width; }; diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst index 136f8da3d0e2..4f373a8ec47b 100644 --- a/Documentation/filesystems/netfs_library.rst +++ b/Documentation/filesystems/netfs_library.rst @@ -462,6 +462,10 @@ operation table looks like the following:: struct iov_iter *iter, netfs_io_terminated_t term_func, void *term_func_priv); + + int (*query_occupancy)(struct netfs_cache_resources *cres, + loff_t start, size_t len, size_t granularity, + loff_t *_data_start, size_t *_data_len); }; With a termination handler function pointer:: @@ -536,6 +540,18 @@ The methods defined in the table are: indicating whether the termination is definitely happening in the caller's context. + * ``query_occupancy()`` + + [Required] Called to find out where the next piece of data is within a + particular region of the cache. The start and length of the region to be + queried are passed in, along with the granularity to which the answer needs + to be aligned. The function passes back the start and length of the data, + if any, available within that region. Note that there may be a hole at the + front. + + It returns 0 if some data was found, -ENODATA if there was no usable data + within the region or -ENOBUFS if there is no caching on this file. + Note that these methods are passed a pointer to the cache resource structure, not the read request structure as they could be used in other situations where there isn't a read request structure as well, such as writing dirty data to the diff --git a/Documentation/gpu/todo.rst b/Documentation/gpu/todo.rst index da138dd39883..a1212b5b3026 100644 --- a/Documentation/gpu/todo.rst +++ b/Documentation/gpu/todo.rst @@ -300,30 +300,6 @@ Contact: Daniel Vetter, Noralf Tronnes Level: Advanced -Garbage collect fbdev scrolling acceleration --------------------------------------------- - -Scroll acceleration has been disabled in fbcon. Now it works as the old -SCROLL_REDRAW mode. A ton of code was removed in fbcon.c and the hook bmove was -removed from fbcon_ops. -Remaining tasks: - -- a bunch of the hooks in fbcon_ops could be removed or simplified by calling - directly instead of the function table (with a switch on p->rotate) - -- fb_copyarea is unused after this, and can be deleted from all drivers - -- after that, fb_copyarea can be deleted from fb_ops in include/linux/fb.h as - well as cfb_copyarea - -Note that not all acceleration code can be deleted, since clearing and cursor -support is still accelerated, which might be good candidates for further -deletion projects. - -Contact: Daniel Vetter - -Level: Intermediate - idr_init_base() --------------- diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index 687efcf245c1..e6fce2cbd99e 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -115,6 +115,7 @@ Code Seq# Include File Comments 'B' 00-1F linux/cciss_ioctl.h conflict! 'B' 00-0F include/linux/pmu.h conflict! 'B' C0-FF advanced bbus <mailto:maassen@uni-freiburg.de> +'B' 00-0F xen/xenbus_dev.h conflict! 'C' all linux/soundcard.h conflict! 'C' 01-2F linux/capi.h conflict! 'C' F0-FF drivers/net/wan/cosa.h conflict! @@ -134,6 +135,7 @@ Code Seq# Include File Comments 'F' 80-8F linux/arcfb.h conflict! 'F' DD video/sstfb.h conflict! 'G' 00-3F drivers/misc/sgi-gru/grulib.h conflict! +'G' 00-0F xen/gntalloc.h, xen/gntdev.h conflict! 'H' 00-7F linux/hiddev.h conflict! 'H' 00-0F linux/hidraw.h conflict! 'H' 01 linux/mei.h conflict! @@ -176,6 +178,7 @@ Code Seq# Include File Comments 'P' 60-6F sound/sscape_ioctl.h conflict! 'P' 00-0F drivers/usb/class/usblp.c conflict! 'P' 01-09 drivers/misc/pci_endpoint_test.c conflict! +'P' 00-0F xen/privcmd.h conflict! 'Q' all linux/soundcard.h 'R' 00-1F linux/random.h conflict! 'R' 01 linux/rfkill.h conflict! diff --git a/MAINTAINERS b/MAINTAINERS index e70f5b26bc50..25eb3097baae 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10881,6 +10881,12 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git F: drivers/ata/pata_arasan_cf.c F: include/linux/pata_arasan_cf_data.h +LIBATA PATA DRIVERS +R: Sergey Shtylyov <s.shtylyov@omp.ru> +L: linux-ide@vger.kernel.org +F: drivers/ata/ata_*.c +F: drivers/ata/pata_*.c + LIBATA PATA FARADAY FTIDE010 AND GEMINI SATA BRIDGE DRIVERS M: Linus Walleij <linus.walleij@linaro.org> L: linux-ide@vger.kernel.org @@ -12401,7 +12407,7 @@ F: include/uapi/linux/membarrier.h F: kernel/sched/membarrier.c MEMBLOCK -M: Mike Rapoport <rppt@linux.ibm.com> +M: Mike Rapoport <rppt@kernel.org> L: linux-mm@kvack.org S: Maintained F: Documentation/core-api/boot-time-mm.rst @@ -13299,8 +13305,8 @@ W: http://www.iptables.org/ W: http://www.nftables.org/ Q: http://patchwork.ozlabs.org/project/netfilter-devel/list/ C: irc://irc.libera.chat/netfilter -T: git git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf.git -T: git git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf-next.git F: include/linux/netfilter* F: include/linux/netfilter/ F: include/net/netfilter/ @@ -13567,7 +13573,7 @@ F: tools/testing/selftests/nci/ NFS, SUNRPC, AND LOCKD CLIENTS M: Trond Myklebust <trond.myklebust@hammerspace.com> -M: Anna Schumaker <anna.schumaker@netapp.com> +M: Anna Schumaker <anna@kernel.org> L: linux-nfs@vger.kernel.org S: Maintained W: http://client.linux-nfs.org @@ -16469,6 +16475,14 @@ F: Documentation/devicetree/bindings/i2c/renesas,rmobile-iic.yaml F: drivers/i2c/busses/i2c-rcar.c F: drivers/i2c/busses/i2c-sh_mobile.c +RENESAS R-CAR SATA DRIVER +R: Sergey Shtylyov <s.shtylyov@omp.ru> +S: Supported +L: linux-ide@vger.kernel.org +L: linux-renesas-soc@vger.kernel.org +F: Documentation/devicetree/bindings/ata/renesas,rcar-sata.yaml +F: drivers/ata/sata_rcar.c + RENESAS R-CAR THERMAL DRIVERS M: Niklas Söderlund <niklas.soderlund@ragnatech.se> L: linux-renesas-soc@vger.kernel.org @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 17 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Gobble Gobble # *DOCUMENTATION* diff --git a/arch/arm/crypto/blake2s-shash.c b/arch/arm/crypto/blake2s-shash.c index 17c1c3bfe2f5..763c73beea2d 100644 --- a/arch/arm/crypto/blake2s-shash.c +++ b/arch/arm/crypto/blake2s-shash.c @@ -13,12 +13,12 @@ static int crypto_blake2s_update_arm(struct shash_desc *desc, const u8 *in, unsigned int inlen) { - return crypto_blake2s_update(desc, in, inlen, blake2s_compress); + return crypto_blake2s_update(desc, in, inlen, false); } static int crypto_blake2s_final_arm(struct shash_desc *desc, u8 *out) { - return crypto_blake2s_final(desc, out, blake2s_compress); + return crypto_blake2s_final(desc, out, false); } #define BLAKE2S_ALG(name, driver_name, digest_size) \ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index f2b5a4abef21..cbcd42decb2a 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -680,6 +680,22 @@ config ARM64_ERRATUM_2051678 If unsure, say Y. +config ARM64_ERRATUM_2077057 + bool "Cortex-A510: 2077057: workaround software-step corrupting SPSR_EL2" + help + This option adds the workaround for ARM Cortex-A510 erratum 2077057. + Affected Cortex-A510 may corrupt SPSR_EL2 when the a step exception is + expected, but a Pointer Authentication trap is taken instead. The + erratum causes SPSR_EL1 to be copied to SPSR_EL2, which could allow + EL1 to cause a return to EL2 with a guest controlled ELR_EL2. + + This can only happen when EL2 is stepping EL1. + + When these conditions occur, the SPSR_EL2 value is unchanged from the + previous guest entry, and can be restored from the in-memory copy. + + If unsure, say Y. + config ARM64_ERRATUM_2119858 bool "Cortex-A710/X2: 2119858: workaround TRBE overwriting trace data in FILL mode" default y diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 066098198c24..b217941713a8 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -600,6 +600,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = { CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_2077057 + { + .desc = "ARM erratum 2077057", + .capability = ARM64_WORKAROUND_2077057, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 2), + }, +#endif #ifdef CONFIG_ARM64_ERRATUM_2064142 { .desc = "ARM erratum 2064142", diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index a4a0063df456..ecc5958e27fe 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -797,6 +797,24 @@ static bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu, int *ret) xfer_to_guest_mode_work_pending(); } +/* + * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while + * the vCPU is running. + * + * This must be noinstr as instrumentation may make use of RCU, and this is not + * safe during the EQS. + */ +static int noinstr kvm_arm_vcpu_enter_exit(struct kvm_vcpu *vcpu) +{ + int ret; + + guest_state_enter_irqoff(); + ret = kvm_call_hyp_ret(__kvm_vcpu_run, vcpu); + guest_state_exit_irqoff(); + + return ret; +} + /** * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code * @vcpu: The VCPU pointer @@ -881,9 +899,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) * Enter the guest */ trace_kvm_entry(*vcpu_pc(vcpu)); - guest_enter_irqoff(); + guest_timing_enter_irqoff(); - ret = kvm_call_hyp_ret(__kvm_vcpu_run, vcpu); + ret = kvm_arm_vcpu_enter_exit(vcpu); vcpu->mode = OUTSIDE_GUEST_MODE; vcpu->stat.exits++; @@ -918,26 +936,23 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_arch_vcpu_ctxsync_fp(vcpu); /* - * We may have taken a host interrupt in HYP mode (ie - * while executing the guest). This interrupt is still - * pending, as we haven't serviced it yet! + * We must ensure that any pending interrupts are taken before + * we exit guest timing so that timer ticks are accounted as + * guest time. Transiently unmask interrupts so that any + * pending interrupts are taken. * - * We're now back in SVC mode, with interrupts - * disabled. Enabling the interrupts now will have - * the effect of taking the interrupt again, in SVC - * mode this time. + * Per ARM DDI 0487G.b section D1.13.4, an ISB (or other + * context synchronization event) is necessary to ensure that + * pending interrupts are taken. */ local_irq_enable(); + isb(); + local_irq_disable(); + + guest_timing_exit_irqoff(); + + local_irq_enable(); - /* - * We do local_irq_enable() before calling guest_exit() so - * that if a timer interrupt hits while running the guest we - * account that tick as being spent in the guest. We enable - * preemption after calling guest_exit() so that if we get - * preempted we make sure ticks after that is not counted as - * guest time. - */ - guest_exit(); trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu)); /* Exit types that need handling before we can be preempted */ diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index fd2dd26caf91..e3140abd2e2e 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -228,6 +228,14 @@ int handle_exit(struct kvm_vcpu *vcpu, int exception_index) { struct kvm_run *run = vcpu->run; + if (ARM_SERROR_PENDING(exception_index)) { + /* + * The SError is handled by handle_exit_early(). If the guest + * survives it will re-execute the original instruction. + */ + return 1; + } + exception_index = ARM_EXCEPTION_CODE(exception_index); switch (exception_index) { diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 58e14f8ead23..701cfb964905 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -402,6 +402,24 @@ static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code) return false; } +static inline void synchronize_vcpu_pstate(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + /* + * Check for the conditions of Cortex-A510's #2077057. When these occur + * SPSR_EL2 can't be trusted, but isn't needed either as it is + * unchanged from the value in vcpu_gp_regs(vcpu)->pstate. + * Are we single-stepping the guest, and took a PAC exception from the + * active-not-pending state? + */ + if (cpus_have_final_cap(ARM64_WORKAROUND_2077057) && + vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP && + *vcpu_cpsr(vcpu) & DBG_SPSR_SS && + ESR_ELx_EC(read_sysreg_el2(SYS_ESR)) == ESR_ELx_EC_PAC) + write_sysreg_el2(*vcpu_cpsr(vcpu), SYS_SPSR); + + vcpu->arch.ctxt.regs.pstate = read_sysreg_el2(SYS_SPSR); +} + /* * Return true when we were able to fixup the guest exit and should return to * the guest, false when we should restore the host state and return to the @@ -413,7 +431,7 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) * Save PSTATE early so that we can evaluate the vcpu mode * early on. */ - vcpu->arch.ctxt.regs.pstate = read_sysreg_el2(SYS_SPSR); + synchronize_vcpu_pstate(vcpu, exit_code); /* * Check whether we want to repaint the state one way or @@ -424,7 +442,8 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR); - if (ARM_SERROR_PENDING(*exit_code)) { + if (ARM_SERROR_PENDING(*exit_code) && + ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) { u8 esr_ec = kvm_vcpu_trap_get_class(vcpu); /* diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index e7719e8f18de..9c65b1e25a96 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -55,9 +55,10 @@ WORKAROUND_1418040 WORKAROUND_1463225 WORKAROUND_1508412 WORKAROUND_1542419 -WORKAROUND_2064142 -WORKAROUND_2038923 WORKAROUND_1902691 +WORKAROUND_2038923 +WORKAROUND_2064142 +WORKAROUND_2077057 WORKAROUND_TRBE_OVERWRITE_FILL_MODE WORKAROUND_TSB_FLUSH_FAILURE WORKAROUND_TRBE_WRITE_OUT_OF_RANGE diff --git a/arch/mips/boot/dts/ingenic/ci20.dts b/arch/mips/boot/dts/ingenic/ci20.dts index 3e336b3dbb10..ab6e3dc0bc1d 100644 --- a/arch/mips/boot/dts/ingenic/ci20.dts +++ b/arch/mips/boot/dts/ingenic/ci20.dts @@ -83,6 +83,8 @@ label = "HDMI OUT"; type = "a"; + ddc-en-gpios = <&gpa 25 GPIO_ACTIVE_HIGH>; + port { hdmi_con: endpoint { remote-endpoint = <&dw_hdmi_out>; @@ -114,17 +116,6 @@ gpio = <&gpf 14 GPIO_ACTIVE_LOW>; enable-active-high; }; - - hdmi_power: fixedregulator@3 { - compatible = "regulator-fixed"; - - regulator-name = "hdmi_power"; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - - gpio = <&gpa 25 0>; - enable-active-high; - }; }; &ext { @@ -576,8 +567,6 @@ pinctrl-names = "default"; pinctrl-0 = <&pins_hdmi_ddc>; - hdmi-5v-supply = <&hdmi_power>; - ports { #address-cells = <1>; #size-cells = <0>; diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index e59cb6246f76..a25e0b73ee70 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -414,6 +414,24 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, return -ENOIOCTLCMD; } +/* + * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while + * the vCPU is running. + * + * This must be noinstr as instrumentation may make use of RCU, and this is not + * safe during the EQS. + */ +static int noinstr kvm_mips_vcpu_enter_exit(struct kvm_vcpu *vcpu) +{ + int ret; + + guest_state_enter_irqoff(); + ret = kvm_mips_callbacks->vcpu_run(vcpu); + guest_state_exit_irqoff(); + + return ret; +} + int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { int r = -EINTR; @@ -434,7 +452,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) lose_fpu(1); local_irq_disable(); - guest_enter_irqoff(); + guest_timing_enter_irqoff(); trace_kvm_enter(vcpu); /* @@ -445,10 +463,23 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) */ smp_store_mb(vcpu->mode, IN_GUEST_MODE); - r = kvm_mips_callbacks->vcpu_run(vcpu); + r = kvm_mips_vcpu_enter_exit(vcpu); + + /* + * We must ensure that any pending interrupts are taken before + * we exit guest timing so that timer ticks are accounted as + * guest time. Transiently unmask interrupts so that any + * pending interrupts are taken. + * + * TODO: is there a barrier which ensures that pending interrupts are + * recognised? Currently this just hopes that the CPU takes any pending + * interrupts between the enable and disable. + */ + local_irq_enable(); + local_irq_disable(); trace_kvm_out(vcpu); - guest_exit_irqoff(); + guest_timing_exit_irqoff(); local_irq_enable(); out: @@ -1168,7 +1199,7 @@ static void kvm_mips_set_c0_status(void) /* * Return value is in the form (errcode<<2 | RESUME_FLAG_HOST | RESUME_FLAG_NV) */ -int kvm_mips_handle_exit(struct kvm_vcpu *vcpu) +static int __kvm_mips_handle_exit(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; u32 cause = vcpu->arch.host_cp0_cause; @@ -1357,6 +1388,17 @@ int kvm_mips_handle_exit(struct kvm_vcpu *vcpu) return ret; } +int noinstr kvm_mips_handle_exit(struct kvm_vcpu *vcpu) +{ + int ret; + + guest_state_exit_irqoff(); + ret = __kvm_mips_handle_exit(vcpu); + guest_state_enter_irqoff(); + + return ret; +} + /* Enable FPU for guest and restore context */ void kvm_own_fpu(struct kvm_vcpu *vcpu) { diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 0c5239e05721..624166004e36 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -90,6 +90,7 @@ int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *cntx; + struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr; /* Mark this VCPU never ran */ vcpu->arch.ran_atleast_once = false; @@ -106,6 +107,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) cntx->hstatus |= HSTATUS_SPVP; cntx->hstatus |= HSTATUS_SPV; + /* By default, make CY, TM, and IR counters accessible in VU mode */ + reset_csr->scounteren = 0x7; + /* Setup VCPU timer */ kvm_riscv_vcpu_timer_init(vcpu); @@ -699,6 +703,20 @@ static void kvm_riscv_update_hvip(struct kvm_vcpu *vcpu) csr_write(CSR_HVIP, csr->hvip); } +/* + * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while + * the vCPU is running. + * + * This must be noinstr as instrumentation may make use of RCU, and this is not + * safe during the EQS. + */ +static void noinstr kvm_riscv_vcpu_enter_exit(struct kvm_vcpu *vcpu) +{ + guest_state_enter_irqoff(); + __kvm_riscv_switch_to(&vcpu->arch); + guest_state_exit_irqoff(); +} + int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { int ret; @@ -790,9 +808,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) continue; } - guest_enter_irqoff(); + guest_timing_enter_irqoff(); - __kvm_riscv_switch_to(&vcpu->arch); + kvm_riscv_vcpu_enter_exit(vcpu); vcpu->mode = OUTSIDE_GUEST_MODE; vcpu->stat.exits++; @@ -812,25 +830,21 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_riscv_vcpu_sync_interrupts(vcpu); /* - * We may have taken a host interrupt in VS/VU-mode (i.e. - * while executing the guest). This interrupt is still - * pending, as we haven't serviced it yet! + * We must ensure that any pending interrupts are taken before + * we exit guest timing so that timer ticks are accounted as + * guest time. Transiently unmask interrupts so that any + * pending interrupts are taken. * - * We're now back in HS-mode with interrupts disabled - * so enabling the interrupts now will have the effect - * of taking the interrupt again, in HS-mode this time. + * There's no barrier which ensures that pending interrupts are + * recognised, so we just hope that the CPU takes any pending + * interrupts between the enable and disable. */ local_irq_enable(); + local_irq_disable(); - /* - * We do local_irq_enable() before calling guest_exit() so - * that if a timer interrupt hits while running the guest - * we account that tick as being spent in the guest. We - * enable preemption after calling guest_exit() so that if - * we get preempted we make sure ticks after that is not - * counted as guest time. - */ - guest_exit(); + guest_timing_exit_irqoff(); + + local_irq_enable(); preempt_enable(); diff --git a/arch/riscv/kvm/vcpu_sbi_base.c b/arch/riscv/kvm/vcpu_sbi_base.c index 4ecf377f483b..48f431091cdb 100644 --- a/arch/riscv/kvm/vcpu_sbi_base.c +++ b/arch/riscv/kvm/vcpu_sbi_base.c @@ -9,6 +9,7 @@ #include <linux/errno.h> #include <linux/err.h> #include <linux/kvm_host.h> +#include <linux/version.h> #include <asm/csr.h> #include <asm/sbi.h> #include <asm/kvm_vcpu_timer.h> @@ -32,7 +33,7 @@ static int kvm_sbi_ext_base_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, *out_val = KVM_SBI_IMPID; break; case SBI_EXT_BASE_GET_IMP_VERSION: - *out_val = 0; + *out_val = LINUX_VERSION_CODE; break; case SBI_EXT_BASE_PROBE_EXT: if ((cp->a0 >= SBI_EXT_EXPERIMENTAL_START && diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 577f1ead6a51..2296b1ff1e02 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4667,6 +4667,8 @@ static long kvm_s390_guest_sida_op(struct kvm_vcpu *vcpu, return -EINVAL; if (mop->size + mop->sida_offset > sida_size(vcpu->arch.sie_block)) return -E2BIG; + if (!kvm_s390_pv_cpu_is_protected(vcpu)) + return -EINVAL; switch (mop->op) { case KVM_S390_MEMOP_SIDA_READ: diff --git a/arch/x86/crypto/blake2s-shash.c b/arch/x86/crypto/blake2s-shash.c index f9e2fecdb761..59ae28abe35c 100644 --- a/arch/x86/crypto/blake2s-shash.c +++ b/arch/x86/crypto/blake2s-shash.c @@ -18,12 +18,12 @@ static int crypto_blake2s_update_x86(struct shash_desc *desc, const u8 *in, unsigned int inlen) { - return crypto_blake2s_update(desc, in, inlen, blake2s_compress); + return crypto_blake2s_update(desc, in, inlen, false); } static int crypto_blake2s_final_x86(struct shash_desc *desc, u8 *out) { - return crypto_blake2s_final(desc, out, blake2s_compress); + return crypto_blake2s_final(desc, out, false); } #define BLAKE2S_ALG(name, driver_name, digest_size) \ diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index c91434056c29..a3c7ca876aeb 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4703,6 +4703,19 @@ static __initconst const struct x86_pmu intel_pmu = { .lbr_read = intel_pmu_lbr_read_64, .lbr_save = intel_pmu_lbr_save, .lbr_restore = intel_pmu_lbr_restore, + + /* + * SMM has access to all 4 rings and while traditionally SMM code only + * ran in CPL0, 2021-era firmware is starting to make use of CPL3 in SMM. + * + * Since the EVENTSEL.{USR,OS} CPL filtering makes no distinction + * between SMM or not, this results in what should be pure userspace + * counters including SMM data. + * + * This is a clear privilege issue, therefore globally disable + * counting SMM by default. + */ + .attr_freeze_on_smi = 1, }; static __init void intel_clovertown_quirk(void) diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 7f406c14715f..2d33bba9a144 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -897,8 +897,9 @@ static void pt_handle_status(struct pt *pt) * means we are already losing data; need to let the decoder * know. */ - if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries) || - buf->output_off == pt_buffer_region_size(buf)) { + if (!buf->single && + (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries) || + buf->output_off == pt_buffer_region_size(buf))) { perf_aux_output_flag(&pt->handle, PERF_AUX_FLAG_TRUNCATED); advance++; diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 631d5040b31e..d39e0de06be2 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -82,7 +82,7 @@ KVM_X86_OP_NULL(guest_apic_has_interrupt) KVM_X86_OP(load_eoi_exitmap) KVM_X86_OP(set_virtual_apic_mode) KVM_X86_OP_NULL(set_apic_access_page_addr) -KVM_X86_OP(deliver_posted_interrupt) +KVM_X86_OP(deliver_interrupt) KVM_X86_OP_NULL(sync_pir_to_irr) KVM_X86_OP(set_tss_addr) KVM_X86_OP(set_identity_map_addr) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6e7c545bc7ee..6dcccb304775 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1410,7 +1410,8 @@ struct kvm_x86_ops { void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu); - int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); + void (*deliver_interrupt)(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector); int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr); diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index 1bf2ad34188a..16f548a661cf 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -43,20 +43,6 @@ static inline uint32_t xen_cpuid_base(void) return hypervisor_cpuid_base("XenVMMXenVMM", 2); } -#ifdef CONFIG_XEN -extern bool __init xen_hvm_need_lapic(void); - -static inline bool __init xen_x2apic_para_available(void) -{ - return xen_hvm_need_lapic(); -} -#else -static inline bool __init xen_x2apic_para_available(void) -{ - return (xen_cpuid_base() != 0); -} -#endif - struct pci_dev; #ifdef CONFIG_XEN_PV_DOM0 diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 28be02adc669..494d4d351859 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -554,12 +554,13 @@ void kvm_set_cpu_caps(void) ); kvm_cpu_cap_mask(CPUID_7_0_EBX, - F(FSGSBASE) | F(SGX) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) | - F(BMI2) | F(ERMS) | F(INVPCID) | F(RTM) | 0 /*MPX*/ | F(RDSEED) | - F(ADX) | F(SMAP) | F(AVX512IFMA) | F(AVX512F) | F(AVX512PF) | - F(AVX512ER) | F(AVX512CD) | F(CLFLUSHOPT) | F(CLWB) | F(AVX512DQ) | - F(SHA_NI) | F(AVX512BW) | F(AVX512VL) | 0 /*INTEL_PT*/ - ); + F(FSGSBASE) | F(SGX) | F(BMI1) | F(HLE) | F(AVX2) | + F(FDP_EXCPTN_ONLY) | F(SMEP) | F(BMI2) | F(ERMS) | F(INVPCID) | + F(RTM) | F(ZERO_FCS_FDS) | 0 /*MPX*/ | F(AVX512F) | + F(AVX512DQ) | F(RDSEED) | F(ADX) | F(SMAP) | F(AVX512IFMA) | + F(CLFLUSHOPT) | F(CLWB) | 0 /*INTEL_PT*/ | F(AVX512PF) | + F(AVX512ER) | F(AVX512CD) | F(SHA_NI) | F(AVX512BW) | + F(AVX512VL)); kvm_cpu_cap_mask(CPUID_7_ECX, F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(RDPID) | diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 4662469240bc..d7e6fde82d25 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1096,14 +1096,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, apic->regs + APIC_TMR); } - if (static_call(kvm_x86_deliver_posted_interrupt)(vcpu, vector)) { - kvm_lapic_set_irr(vector, apic); - kvm_make_request(KVM_REQ_EVENT, vcpu); - kvm_vcpu_kick(vcpu); - } else { - trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, - trig_mode, vector); - } + static_call(kvm_x86_deliver_interrupt)(apic, delivery_mode, + trig_mode, vector); break; case APIC_DM_REMRD: diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 6d97629655e3..a290efb272ad 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3291,6 +3291,21 @@ static void svm_set_irq(struct kvm_vcpu *vcpu) SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR; } +static void svm_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector) +{ + struct kvm_vcpu *vcpu = apic->vcpu; + + if (svm_deliver_avic_intr(vcpu, vector)) { + kvm_lapic_set_irr(vector, apic); + kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_vcpu_kick(vcpu); + } else { + trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, + trig_mode, vector); + } +} + static void svm_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3615,7 +3630,7 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); unsigned long vmcb_pa = svm->current_vmcb->pa; - kvm_guest_enter_irqoff(); + guest_state_enter_irqoff(); if (sev_es_guest(vcpu->kvm)) { __svm_sev_es_vcpu_run(vmcb_pa); @@ -3635,7 +3650,7 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu) vmload(__sme_page_pa(sd->save_area)); } - kvm_guest_exit_irqoff(); + guest_state_exit_irqoff(); } static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) @@ -4545,7 +4560,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .pmu_ops = &amd_pmu_ops, .nested_ops = &svm_nested_ops, - .deliver_posted_interrupt = svm_deliver_avic_intr, + .deliver_interrupt = svm_deliver_interrupt, .dy_apicv_has_pending_interrupt = svm_dy_apicv_has_pending_interrupt, .update_pi_irte = svm_update_pi_irte, .setup_mce = svm_setup_mce, diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index aca3ae2a02f3..6c27bd0c89e1 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4041,6 +4041,21 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) return 0; } +static void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector) +{ + struct kvm_vcpu *vcpu = apic->vcpu; + + if (vmx_deliver_posted_interrupt(vcpu, vector)) { + kvm_lapic_set_irr(vector, apic); + kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_vcpu_kick(vcpu); + } else { + trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, + trig_mode, vector); + } +} + /* * Set up the vmcs's constant host-state fields, i.e., host-state fields that * will not change in the lifetime of the guest. @@ -6754,7 +6769,7 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) { - kvm_guest_enter_irqoff(); + guest_state_enter_irqoff(); /* L1D Flush includes CPU buffer clear to mitigate MDS */ if (static_branch_unlikely(&vmx_l1d_should_flush)) @@ -6770,7 +6785,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, vcpu->arch.cr2 = native_read_cr2(); - kvm_guest_exit_irqoff(); + guest_state_exit_irqoff(); } static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) @@ -7768,7 +7783,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .hwapic_isr_update = vmx_hwapic_isr_update, .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, .sync_pir_to_irr = vmx_sync_pir_to_irr, - .deliver_posted_interrupt = vmx_deliver_posted_interrupt, + .deliver_interrupt = vmx_deliver_interrupt, .dy_apicv_has_pending_interrupt = pi_has_pending_interrupt, .set_tss_addr = vmx_set_tss_addr, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 74b53a16f38a..7131d735b1ef 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -90,6 +90,8 @@ u64 __read_mostly kvm_mce_cap_supported = MCG_CTL_P | MCG_SER_P; EXPORT_SYMBOL_GPL(kvm_mce_cap_supported); +#define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e)) + #define emul_to_vcpu(ctxt) \ ((struct kvm_vcpu *)(ctxt)->vcpu) @@ -4340,7 +4342,7 @@ static inline void __user *kvm_get_attr_addr(struct kvm_device_attr *attr) void __user *uaddr = (void __user*)(unsigned long)attr->addr; if ((u64)(unsigned long)uaddr != attr->addr) - return ERR_PTR(-EFAULT); + return ERR_PTR_USR(-EFAULT); return uaddr; } @@ -10041,6 +10043,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) set_debugreg(0, 7); } + guest_timing_enter_irqoff(); + for (;;) { /* * Assert that vCPU vs. VM APICv state is consistent. An APICv @@ -10125,7 +10129,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * of accounting via context tracking, but the loss of accuracy is * acceptable for all known use cases. */ - vtime_account_guest_exit(); + guest_timing_exit_irqoff(); if (lapic_in_kernel(vcpu)) { s64 delta = vcpu->arch.apic->lapic_timer.advance_expire_delta; @@ -11639,8 +11643,6 @@ void kvm_arch_sync_events(struct kvm *kvm) kvm_free_pit(kvm); } -#define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e)) - /** * __x86_set_memory_region: Setup KVM internal memory slot * diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 635b75f9e145..767ec7f99516 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -10,51 +10,6 @@ void kvm_spurious_fault(void); -static __always_inline void kvm_guest_enter_irqoff(void) -{ - /* - * VMENTER enables interrupts (host state), but the kernel state is - * interrupts disabled when this is invoked. Also tell RCU about - * it. This is the same logic as for exit_to_user_mode(). - * - * This ensures that e.g. latency analysis on the host observes - * guest mode as interrupt enabled. - * - * guest_enter_irqoff() informs context tracking about the - * transition to guest mode and if enabled adjusts RCU state - * accordingly. - */ - instrumentation_begin(); - trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); - instrumentation_end(); - - guest_enter_irqoff(); - lockdep_hardirqs_on(CALLER_ADDR0); -} - -static __always_inline void kvm_guest_exit_irqoff(void) -{ - /* - * VMEXIT disables interrupts (host state), but tracing and lockdep - * have them in state 'on' as recorded before entering guest mode. - * Same as enter_from_user_mode(). - * - * context_tracking_guest_exit() restores host context and reinstates - * RCU if enabled and required. - * - * This needs to be done immediately after VM-Exit, before any code - * that might contain tracepoints or call out to the greater world, - * e.g. before x86_spec_ctrl_restore_host(). - */ - lockdep_hardirqs_off(CALLER_ADDR0); - context_tracking_guest_exit(); - - instrumentation_begin(); - trace_hardirqs_off_finish(); - instrumentation_end(); -} - #define KVM_NESTED_VMENTER_CONSISTENCY_CHECK(consistency_check) \ ({ \ bool failed = (consistency_check); \ diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 42300941ec29..6448c5071117 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -9,6 +9,7 @@ #include <xen/events.h> #include <xen/interface/memory.h> +#include <asm/apic.h> #include <asm/cpu.h> #include <asm/smp.h> #include <asm/io_apic.h> @@ -242,15 +243,9 @@ static __init int xen_parse_no_vector_callback(char *arg) } early_param("xen_no_vector_callback", xen_parse_no_vector_callback); -bool __init xen_hvm_need_lapic(void) +static __init bool xen_x2apic_available(void) { - if (xen_pv_domain()) - return false; - if (!xen_hvm_domain()) - return false; - if (xen_feature(XENFEAT_hvm_pirqs) && xen_have_vector_callback) - return false; - return true; + return x2apic_supported(); } static __init void xen_hvm_guest_late_init(void) @@ -312,7 +307,7 @@ struct hypervisor_x86 x86_hyper_xen_hvm __initdata = { .detect = xen_platform_hvm, .type = X86_HYPER_XEN_HVM, .init.init_platform = xen_hvm_guest_init, - .init.x2apic_available = xen_x2apic_para_available, + .init.x2apic_available = xen_x2apic_available, .init.init_mem_mapping = xen_hvm_init_mem_mapping, .init.guest_late_init = xen_hvm_guest_late_init, .runtime.pin_vcpu = xen_pin_vcpu, diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 5004feb16783..d47c3d176ae4 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1341,10 +1341,6 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_acpi_sleep_register(); - /* Avoid searching for BIOS MP tables */ - x86_init.mpparse.find_smp_config = x86_init_noop; - x86_init.mpparse.get_smp_config = x86_init_uint_noop; - xen_boot_params_init_edd(); #ifdef CONFIG_ACPI diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 6a8f3b53ab83..4a6019238ee7 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -148,28 +148,12 @@ int xen_smp_intr_init_pv(unsigned int cpu) return rc; } -static void __init xen_fill_possible_map(void) -{ - int i, rc; - - if (xen_initial_domain()) - return; - - for (i = 0; i < nr_cpu_ids; i++) { - rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL); - if (rc >= 0) { - num_processors++; - set_cpu_possible(i, true); - } - } -} - -static void __init xen_filter_cpu_maps(void) +static void __init _get_smp_config(unsigned int early) { int i, rc; unsigned int subtract = 0; - if (!xen_initial_domain()) + if (early) return; num_processors = 0; @@ -210,7 +194,6 @@ static void __init xen_pv_smp_prepare_boot_cpu(void) * sure the old memory can be recycled. */ make_lowmem_page_readwrite(xen_initial_gdt); - xen_filter_cpu_maps(); xen_setup_vcpu_info_placement(); /* @@ -476,5 +459,8 @@ static const struct smp_ops xen_smp_ops __initconst = { void __init xen_smp_init(void) { smp_ops = xen_smp_ops; - xen_fill_possible_map(); + + /* Avoid searching for BIOS MP tables */ + x86_init.mpparse.find_smp_config = x86_init_noop; + x86_init.mpparse.get_smp_config = _get_smp_config; } diff --git a/block/bio-integrity.c b/block/bio-integrity.c index d25114715459..0827b19820c5 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -373,7 +373,7 @@ void bio_integrity_advance(struct bio *bio, unsigned int bytes_done) struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk); unsigned bytes = bio_integrity_bytes(bi, bytes_done >> 9); - bip->bip_iter.bi_sector += bytes_done >> 9; + bip->bip_iter.bi_sector += bio_integrity_intervals(bi, bytes_done >> 9); bvec_iter_advance(bip->bip_vec, &bip->bip_iter, bytes); } diff --git a/block/fops.c b/block/fops.c index 26bf15c770d2..4f59e0f5bf30 100644 --- a/block/fops.c +++ b/block/fops.c @@ -566,34 +566,37 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct block_device *bdev = iocb->ki_filp->private_data; loff_t size = bdev_nr_bytes(bdev); - size_t count = iov_iter_count(to); loff_t pos = iocb->ki_pos; size_t shorted = 0; ssize_t ret = 0; + size_t count; - if (unlikely(pos + count > size)) { + if (unlikely(pos + iov_iter_count(to) > size)) { if (pos >= size) return 0; size -= pos; - if (count > size) { - shorted = count - size; - iov_iter_truncate(to, size); - } + shorted = iov_iter_count(to) - size; + iov_iter_truncate(to, size); } + count = iov_iter_count(to); + if (!count) + goto reexpand; /* skip atime */ + if (iocb->ki_flags & IOCB_DIRECT) { struct address_space *mapping = iocb->ki_filp->f_mapping; if (iocb->ki_flags & IOCB_NOWAIT) { - if (filemap_range_needs_writeback(mapping, iocb->ki_pos, - iocb->ki_pos + count - 1)) - return -EAGAIN; + if (filemap_range_needs_writeback(mapping, pos, + pos + count - 1)) { + ret = -EAGAIN; + goto reexpand; + } } else { - ret = filemap_write_and_wait_range(mapping, - iocb->ki_pos, - iocb->ki_pos + count - 1); + ret = filemap_write_and_wait_range(mapping, pos, + pos + count - 1); if (ret < 0) - return ret; + goto reexpand; } file_accessed(iocb->ki_filp); @@ -603,12 +606,14 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) iocb->ki_pos += ret; count -= ret; } + iov_iter_revert(to, count - iov_iter_count(to)); if (ret < 0 || !count) - return ret; + goto reexpand; } ret = filemap_read(iocb, to, ret); +reexpand: if (unlikely(shorted)) iov_iter_reexpand(to, iov_iter_count(to) + shorted); return ret; diff --git a/crypto/algapi.c b/crypto/algapi.c index a366cb3e8aa1..76fdaa16bd4a 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -1324,3 +1324,4 @@ module_exit(crypto_algapi_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Cryptographic algorithms API"); +MODULE_SOFTDEP("pre: cryptomgr"); diff --git a/crypto/api.c b/crypto/api.c index cf0869dd130b..7ddfe946dd56 100644 --- a/crypto/api.c +++ b/crypto/api.c @@ -643,4 +643,3 @@ EXPORT_SYMBOL_GPL(crypto_req_done); MODULE_DESCRIPTION("Cryptographic core API"); MODULE_LICENSE("GPL"); -MODULE_SOFTDEP("pre: cryptomgr"); diff --git a/crypto/blake2s_generic.c b/crypto/blake2s_generic.c index 72fe480f9bd6..5f96a21f8788 100644 --- a/crypto/blake2s_generic.c +++ b/crypto/blake2s_generic.c @@ -15,12 +15,12 @@ static int crypto_blake2s_update_generic(struct shash_desc *desc, const u8 *in, unsigned int inlen) { - return crypto_blake2s_update(desc, in, inlen, blake2s_compress_generic); + return crypto_blake2s_update(desc, in, inlen, true); } static int crypto_blake2s_final_generic(struct shash_desc *desc, u8 *out) { - return crypto_blake2s_final(desc, out, blake2s_compress_generic); + return crypto_blake2s_final(desc, out, true); } #define BLAKE2S_ALG(name, driver_name, digest_size) \ diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index ba45541b1f1f..273741dedfd2 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -11,6 +11,7 @@ menuconfig ACPI depends on ARCH_SUPPORTS_ACPI select PNP select NLS + select CRC32 default y if X86 help Advanced Configuration and Power Interface (ACPI) support for diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 67f88027680a..ba9273f80069 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2007,6 +2007,9 @@ static bool ata_log_supported(struct ata_device *dev, u8 log) { struct ata_port *ap = dev->link->ap; + if (dev->horkage & ATA_HORKAGE_NO_LOG_DIR) + return false; + if (ata_read_log_page(dev, ATA_LOG_DIRECTORY, 0, ap->sector_buf, 1)) return false; return get_unaligned_le16(&ap->sector_buf[log * 2]) ? true : false; @@ -2445,23 +2448,21 @@ static void ata_dev_config_cpr(struct ata_device *dev) struct ata_cpr_log *cpr_log = NULL; u8 *desc, *buf = NULL; - if (!ata_identify_page_supported(dev, - ATA_LOG_CONCURRENT_POSITIONING_RANGES)) + if (ata_id_major_version(dev->id) < 11 || + !ata_log_supported(dev, ATA_LOG_CONCURRENT_POSITIONING_RANGES)) goto out; /* - * Read IDENTIFY DEVICE data log, page 0x47 - * (concurrent positioning ranges). We can have at most 255 32B range - * descriptors plus a 64B header. + * Read the concurrent positioning ranges log (0x47). We can have at + * most 255 32B range descriptors plus a 64B header. */ buf_len = (64 + 255 * 32 + 511) & ~511; buf = kzalloc(buf_len, GFP_KERNEL); if (!buf) goto out; - err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, - ATA_LOG_CONCURRENT_POSITIONING_RANGES, - buf, buf_len >> 9); + err_mask = ata_read_log_page(dev, ATA_LOG_CONCURRENT_POSITIONING_RANGES, + 0, buf, buf_len >> 9); if (err_mask) goto out; @@ -4073,6 +4074,13 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "WDC WD3000JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, { "WDC WD3200JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, + /* + * This sata dom device goes on a walkabout when the ATA_LOG_DIRECTORY + * log page is accessed. Ensure we never ask for this log page with + * these devices. + */ + { "SATADOM-ML 3ME", NULL, ATA_HORKAGE_NO_LOG_DIR }, + /* End Marker */ { } }; diff --git a/drivers/char/random.c b/drivers/char/random.c index 68613f0b6887..3404a91edf29 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -762,7 +762,7 @@ static bool crng_init_try_arch(struct crng_state *crng) return arch_init; } -static bool __init crng_init_try_arch_early(struct crng_state *crng) +static bool __init crng_init_try_arch_early(void) { int i; bool arch_init = true; @@ -774,7 +774,7 @@ static bool __init crng_init_try_arch_early(struct crng_state *crng) rv = random_get_entropy(); arch_init = false; } - crng->state[i] ^= rv; + primary_crng.state[i] ^= rv; } return arch_init; @@ -788,22 +788,20 @@ static void crng_initialize_secondary(struct crng_state *crng) crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1; } -static void __init crng_initialize_primary(struct crng_state *crng) +static void __init crng_initialize_primary(void) { - _extract_entropy(&crng->state[4], sizeof(u32) * 12); - if (crng_init_try_arch_early(crng) && trust_cpu && crng_init < 2) { + _extract_entropy(&primary_crng.state[4], sizeof(u32) * 12); + if (crng_init_try_arch_early() && trust_cpu && crng_init < 2) { invalidate_batched_entropy(); numa_crng_init(); crng_init = 2; pr_notice("crng init done (trusting CPU's manufacturer)\n"); } - crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1; + primary_crng.init_time = jiffies - CRNG_RESEED_INTERVAL - 1; } -static void crng_finalize_init(struct crng_state *crng) +static void crng_finalize_init(void) { - if (crng != &primary_crng || crng_init >= 2) - return; if (!system_wq) { /* We can't call numa_crng_init until we have workqueues, * so mark this for processing later. */ @@ -814,6 +812,7 @@ static void crng_finalize_init(struct crng_state *crng) invalidate_batched_entropy(); numa_crng_init(); crng_init = 2; + crng_need_final_init = false; process_random_ready_list(); wake_up_interruptible(&crng_init_wait); kill_fasync(&fasync, SIGIO, POLL_IN); @@ -980,7 +979,8 @@ static void crng_reseed(struct crng_state *crng, bool use_input_pool) memzero_explicit(&buf, sizeof(buf)); WRITE_ONCE(crng->init_time, jiffies); spin_unlock_irqrestore(&crng->lock, flags); - crng_finalize_init(crng); + if (crng == &primary_crng && crng_init < 2) + crng_finalize_init(); } static void _extract_crng(struct crng_state *crng, u8 out[CHACHA_BLOCK_SIZE]) @@ -1697,8 +1697,8 @@ int __init rand_initialize(void) { init_std_data(); if (crng_need_final_init) - crng_finalize_init(&primary_crng); - crng_initialize_primary(&primary_crng); + crng_finalize_init(); + crng_initialize_primary(); crng_global_init_time = jiffies; if (ratelimit_disable) { urandom_warning.interval = 0; @@ -1856,7 +1856,10 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg) */ if (!capable(CAP_SYS_ADMIN)) return -EPERM; - input_pool.entropy_count = 0; + if (xchg(&input_pool.entropy_count, 0) && random_write_wakeup_bits) { + wake_up_interruptible(&random_write_wait); + kill_fasync(&fasync, SIGIO, POLL_OUT); + } return 0; case RNDRESEEDCRNG: if (!capable(CAP_SYS_ADMIN)) @@ -2205,13 +2208,15 @@ void add_hwgenerator_randomness(const char *buffer, size_t count, return; } - /* Suspend writing if we're above the trickle threshold. + /* Throttle writing if we're above the trickle threshold. * We'll be woken up again once below random_write_wakeup_thresh, - * or when the calling thread is about to terminate. + * when the calling thread is about to terminate, or once + * CRNG_RESEED_INTERVAL has lapsed. */ - wait_event_interruptible(random_write_wait, + wait_event_interruptible_timeout(random_write_wait, !system_wq || kthread_should_stop() || - POOL_ENTROPY_BITS() <= random_write_wakeup_bits); + POOL_ENTROPY_BITS() <= random_write_wakeup_bits, + CRNG_RESEED_INTERVAL); mix_pool_bytes(buffer, count); credit_entropy_bits(entropy); } diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c index 4c8ebdf671ca..1b4d425bbf0e 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c @@ -1753,7 +1753,6 @@ void otx2_cpt_print_uc_dbg_info(struct otx2_cptpf_dev *cptpf) char engs_info[2 * OTX2_CPT_NAME_LENGTH]; struct otx2_cpt_eng_grp_info *grp; struct otx2_cpt_engs_rsvd *engs; - u32 mask[4]; int i, j; pr_debug("Engine groups global info"); @@ -1785,6 +1784,8 @@ void otx2_cpt_print_uc_dbg_info(struct otx2_cptpf_dev *cptpf) for (j = 0; j < OTX2_CPT_MAX_ETYPES_PER_GRP; j++) { engs = &grp->engs[j]; if (engs->type) { + u32 mask[5] = { }; + get_engs_info(grp, engs_info, 2 * OTX2_CPT_NAME_LENGTH, j); pr_debug("Slot%d: %s", j, engs_info); diff --git a/drivers/dma-buf/dma-heap.c b/drivers/dma-buf/dma-heap.c index 56bf5ad01ad5..8f5848aa144f 100644 --- a/drivers/dma-buf/dma-heap.c +++ b/drivers/dma-buf/dma-heap.c @@ -14,6 +14,7 @@ #include <linux/xarray.h> #include <linux/list.h> #include <linux/slab.h> +#include <linux/nospec.h> #include <linux/uaccess.h> #include <linux/syscalls.h> #include <linux/dma-heap.h> @@ -135,6 +136,7 @@ static long dma_heap_ioctl(struct file *file, unsigned int ucmd, if (nr >= ARRAY_SIZE(dma_heap_ioctl_cmds)) return -EINVAL; + nr = array_index_nospec(nr, ARRAY_SIZE(dma_heap_ioctl_cmds)); /* Get the kernel ioctl cmd that matches */ kcmd = dma_heap_ioctl_cmds[nr]; diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index 3a6d2416cb0f..5dd29789f97d 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -350,7 +350,7 @@ static int altr_sdram_probe(struct platform_device *pdev) if (irq < 0) { edac_printk(KERN_ERR, EDAC_MC, "No irq %d in DT\n", irq); - return -ENODEV; + return irq; } /* Arria10 has a 2nd IRQ */ diff --git a/drivers/edac/xgene_edac.c b/drivers/edac/xgene_edac.c index 2ccd1db5e98f..7197f9fa0245 100644 --- a/drivers/edac/xgene_edac.c +++ b/drivers/edac/xgene_edac.c @@ -1919,7 +1919,7 @@ static int xgene_edac_probe(struct platform_device *pdev) irq = platform_get_irq_optional(pdev, i); if (irq < 0) { dev_err(&pdev->dev, "No IRQ resource\n"); - rc = -EINVAL; + rc = irq; goto out_err; } rc = devm_request_irq(&pdev->dev, irq, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index d8b854fcbffa..9a53a4de2bb7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1408,12 +1408,10 @@ int amdgpu_acpi_smart_shift_update(struct drm_device *dev, enum amdgpu_ss ss_sta int amdgpu_acpi_pcie_notify_device_ready(struct amdgpu_device *adev); void amdgpu_acpi_get_backlight_caps(struct amdgpu_dm_backlight_caps *caps); -bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev); void amdgpu_acpi_detect(void); #else static inline int amdgpu_acpi_init(struct amdgpu_device *adev) { return 0; } static inline void amdgpu_acpi_fini(struct amdgpu_device *adev) { } -static inline bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) { return false; } static inline void amdgpu_acpi_detect(void) { } static inline bool amdgpu_acpi_is_power_shift_control_supported(void) { return false; } static inline int amdgpu_acpi_power_shift_control(struct amdgpu_device *adev, @@ -1422,6 +1420,14 @@ static inline int amdgpu_acpi_smart_shift_update(struct drm_device *dev, enum amdgpu_ss ss_state) { return 0; } #endif +#if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND) +bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev); +bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev); +#else +static inline bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) { return false; } +static inline bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev) { return false; } +#endif + int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser, uint64_t addr, struct amdgpu_bo **bo, struct amdgpu_bo_va_mapping **mapping); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index 4811b0faafd9..0e12315fa0cb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -1031,6 +1031,20 @@ void amdgpu_acpi_detect(void) } } +#if IS_ENABLED(CONFIG_SUSPEND) +/** + * amdgpu_acpi_is_s3_active + * + * @adev: amdgpu_device_pointer + * + * returns true if supported, false if not. + */ +bool amdgpu_acpi_is_s3_active(struct amdgpu_device *adev) +{ + return !(adev->flags & AMD_IS_APU) || + (pm_suspend_target_state == PM_SUSPEND_MEM); +} + /** * amdgpu_acpi_is_s0ix_active * @@ -1040,11 +1054,24 @@ void amdgpu_acpi_detect(void) */ bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev) { -#if IS_ENABLED(CONFIG_AMD_PMC) && IS_ENABLED(CONFIG_SUSPEND) - if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0) { - if (adev->flags & AMD_IS_APU) - return pm_suspend_target_state == PM_SUSPEND_TO_IDLE; + if (!(adev->flags & AMD_IS_APU) || + (pm_suspend_target_state != PM_SUSPEND_TO_IDLE)) + return false; + + if (!(acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0)) { + dev_warn_once(adev->dev, + "Power consumption will be higher as BIOS has not been configured for suspend-to-idle.\n" + "To use suspend-to-idle change the sleep mode in BIOS setup.\n"); + return false; } -#endif + +#if !IS_ENABLED(CONFIG_AMD_PMC) + dev_warn_once(adev->dev, + "Power consumption will be higher as the kernel has not been compiled with CONFIG_AMD_PMC.\n"); return false; +#else + return true; +#endif /* CONFIG_AMD_PMC */ } + +#endif /* CONFIG_SUSPEND */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 4c83f1db8a24..63a089992645 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2246,13 +2246,20 @@ static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work) static int amdgpu_pmops_prepare(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(drm_dev); /* Return a positive number here so * DPM_FLAG_SMART_SUSPEND works properly */ if (amdgpu_device_supports_boco(drm_dev)) - return pm_runtime_suspended(dev) && - pm_suspend_via_firmware(); + return pm_runtime_suspended(dev); + + /* if we will not support s3 or s2i for the device + * then skip suspend + */ + if (!amdgpu_acpi_is_s0ix_active(adev) && + !amdgpu_acpi_is_s3_active(adev)) + return 1; return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 5c3f24069f2a..4655702a5e00 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1904,7 +1904,7 @@ int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset, unsigned i; int r; - if (direct_submit && !ring->sched.ready) { + if (!direct_submit && !ring->sched.ready) { DRM_ERROR("Trying to move memory with ring turned off.\n"); return -EINVAL; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 38bb42727715..a2f8ed0e6a64 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -1140,6 +1140,9 @@ static void gmc_v10_0_get_clockgating_state(void *handle, u32 *flags) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(10, 1, 3)) + return; + adev->mmhub.funcs->get_clockgating(adev, flags); if (adev->ip_versions[ATHUB_HWIP][0] >= IP_VERSION(2, 1, 0)) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c index 48005def1164..bc4ddc36fe58 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn301/vg_clk_mgr.c @@ -570,32 +570,32 @@ static struct wm_table lpddr5_wm_table = { .wm_inst = WM_A, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.65333, - .sr_exit_time_us = 7.95, - .sr_enter_plus_exit_time_us = 9, + .sr_exit_time_us = 13.5, + .sr_enter_plus_exit_time_us = 16.5, .valid = true, }, { .wm_inst = WM_B, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.65333, - .sr_exit_time_us = 9.82, - .sr_enter_plus_exit_time_us = 11.196, + .sr_exit_time_us = 13.5, + .sr_enter_plus_exit_time_us = 16.5, .valid = true, }, { .wm_inst = WM_C, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.65333, - .sr_exit_time_us = 9.89, - .sr_enter_plus_exit_time_us = 11.24, + .sr_exit_time_us = 13.5, + .sr_enter_plus_exit_time_us = 16.5, .valid = true, }, { .wm_inst = WM_D, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.65333, - .sr_exit_time_us = 9.748, - .sr_enter_plus_exit_time_us = 11.102, + .sr_exit_time_us = 13.5, + .sr_enter_plus_exit_time_us = 16.5, .valid = true, }, } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c index 4162ce40089b..9d17c5a5ae01 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c @@ -329,38 +329,38 @@ static struct clk_bw_params dcn31_bw_params = { }; -static struct wm_table ddr4_wm_table = { +static struct wm_table ddr5_wm_table = { .entries = { { .wm_inst = WM_A, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.72, - .sr_exit_time_us = 6.09, - .sr_enter_plus_exit_time_us = 7.14, + .sr_exit_time_us = 9, + .sr_enter_plus_exit_time_us = 11, .valid = true, }, { .wm_inst = WM_B, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.72, - .sr_exit_time_us = 10.12, - .sr_enter_plus_exit_time_us = 11.48, + .sr_exit_time_us = 9, + .sr_enter_plus_exit_time_us = 11, .valid = true, }, { .wm_inst = WM_C, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.72, - .sr_exit_time_us = 10.12, - .sr_enter_plus_exit_time_us = 11.48, + .sr_exit_time_us = 9, + .sr_enter_plus_exit_time_us = 11, .valid = true, }, { .wm_inst = WM_D, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.72, - .sr_exit_time_us = 10.12, - .sr_enter_plus_exit_time_us = 11.48, + .sr_exit_time_us = 9, + .sr_enter_plus_exit_time_us = 11, .valid = true, }, } @@ -687,7 +687,7 @@ void dcn31_clk_mgr_construct( if (ctx->dc_bios->integrated_info->memory_type == LpDdr5MemType) { dcn31_bw_params.wm_table = lpddr5_wm_table; } else { - dcn31_bw_params.wm_table = ddr4_wm_table; + dcn31_bw_params.wm_table = ddr5_wm_table; } /* Saved clocks configured at boot for debug purposes */ dcn31_dump_clk_registers(&clk_mgr->base.base.boot_snapshot, &clk_mgr->base.base, &log_info); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c index 4c3ab2575e4b..61b8f29a0c30 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c @@ -5597,6 +5597,26 @@ static bool retrieve_link_cap(struct dc_link *link) dp_hw_fw_revision.ieee_fw_rev, sizeof(dp_hw_fw_revision.ieee_fw_rev)); + /* Quirk for Apple MBP 2018 15" Retina panels: wrong DP_MAX_LINK_RATE */ + { + uint8_t str_mbp_2018[] = { 101, 68, 21, 103, 98, 97 }; + uint8_t fwrev_mbp_2018[] = { 7, 4 }; + uint8_t fwrev_mbp_2018_vega[] = { 8, 4 }; + + /* We also check for the firmware revision as 16,1 models have an + * identical device id and are incorrectly quirked otherwise. + */ + if ((link->dpcd_caps.sink_dev_id == 0x0010fa) && + !memcmp(link->dpcd_caps.sink_dev_id_str, str_mbp_2018, + sizeof(str_mbp_2018)) && + (!memcmp(link->dpcd_caps.sink_fw_revision, fwrev_mbp_2018, + sizeof(fwrev_mbp_2018)) || + !memcmp(link->dpcd_caps.sink_fw_revision, fwrev_mbp_2018_vega, + sizeof(fwrev_mbp_2018_vega)))) { + link->reported_link_cap.link_rate = LINK_RATE_RBR2; + } + } + memset(&link->dpcd_caps.dsc_caps, '\0', sizeof(link->dpcd_caps.dsc_caps)); memset(&link->dpcd_caps.fec_cap, '\0', sizeof(link->dpcd_caps.fec_cap)); diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index f3ff141b706a..26ec69bb5db9 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -1608,11 +1608,6 @@ static enum dc_status apply_single_controller_ctx_to_hw( pipe_ctx->stream_res.stream_enc, pipe_ctx->stream_res.tg->inst); - if (dc_is_embedded_signal(pipe_ctx->stream->signal) && - pipe_ctx->stream_res.stream_enc->funcs->reset_fifo) - pipe_ctx->stream_res.stream_enc->funcs->reset_fifo( - pipe_ctx->stream_res.stream_enc); - if (dc_is_dp_signal(pipe_ctx->stream->signal)) dp_source_sequence_trace(link, DPCD_SOURCE_SEQ_AFTER_CONNECT_DIG_FE_OTG); diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c index bf4436d7aaab..b0c08ee6bc2c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c @@ -902,19 +902,6 @@ void enc1_stream_encoder_stop_dp_info_packets( } -void enc1_stream_encoder_reset_fifo( - struct stream_encoder *enc) -{ - struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc); - - /* set DIG_START to 0x1 to reset FIFO */ - REG_UPDATE(DIG_FE_CNTL, DIG_START, 1); - udelay(100); - - /* write 0 to take the FIFO out of reset */ - REG_UPDATE(DIG_FE_CNTL, DIG_START, 0); -} - void enc1_stream_encoder_dp_blank( struct dc_link *link, struct stream_encoder *enc) @@ -1600,8 +1587,6 @@ static const struct stream_encoder_funcs dcn10_str_enc_funcs = { enc1_stream_encoder_send_immediate_sdp_message, .stop_dp_info_packets = enc1_stream_encoder_stop_dp_info_packets, - .reset_fifo = - enc1_stream_encoder_reset_fifo, .dp_blank = enc1_stream_encoder_dp_blank, .dp_unblank = diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h index a146a41f68e9..687d7e4bf7ca 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h @@ -626,9 +626,6 @@ void enc1_stream_encoder_send_immediate_sdp_message( void enc1_stream_encoder_stop_dp_info_packets( struct stream_encoder *enc); -void enc1_stream_encoder_reset_fifo( - struct stream_encoder *enc); - void enc1_stream_encoder_dp_blank( struct dc_link *link, struct stream_encoder *enc); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c index 8a70f92795c2..aab25ca8343a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c @@ -593,8 +593,6 @@ static const struct stream_encoder_funcs dcn20_str_enc_funcs = { enc1_stream_encoder_send_immediate_sdp_message, .stop_dp_info_packets = enc1_stream_encoder_stop_dp_info_packets, - .reset_fifo = - enc1_stream_encoder_reset_fifo, .dp_blank = enc1_stream_encoder_dp_blank, .dp_unblank = diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_stream_encoder.c index 8daa12730bc1..a04ca4a98392 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_stream_encoder.c @@ -789,8 +789,6 @@ static const struct stream_encoder_funcs dcn30_str_enc_funcs = { enc3_stream_encoder_update_dp_info_packets, .stop_dp_info_packets = enc1_stream_encoder_stop_dp_info_packets, - .reset_fifo = - enc1_stream_encoder_reset_fifo, .dp_blank = enc1_stream_encoder_dp_blank, .dp_unblank = diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h b/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h index 073f8b667eff..c88e113b94d1 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h @@ -164,10 +164,6 @@ struct stream_encoder_funcs { void (*stop_dp_info_packets)( struct stream_encoder *enc); - void (*reset_fifo)( - struct stream_encoder *enc - ); - void (*dp_blank)( struct dc_link *link, struct stream_encoder *enc); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index 777f717c37ae..a4207293158c 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -3696,14 +3696,14 @@ static ssize_t sienna_cichlid_get_gpu_metrics(struct smu_context *smu, static int sienna_cichlid_enable_mgpu_fan_boost(struct smu_context *smu) { - struct smu_table_context *table_context = &smu->smu_table; - PPTable_t *smc_pptable = table_context->driver_pptable; + uint16_t *mgpu_fan_boost_limit_rpm; + GET_PPTABLE_MEMBER(MGpuFanBoostLimitRpm, &mgpu_fan_boost_limit_rpm); /* * Skip the MGpuFanBoost setting for those ASICs * which do not support it */ - if (!smc_pptable->MGpuFanBoostLimitRpm) + if (*mgpu_fan_boost_limit_rpm == 0) return 0; return smu_cmn_send_smc_msg_with_param(smu, diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c index 1a376e9a1ff3..d610e48cab94 100644 --- a/drivers/gpu/drm/i915/display/intel_overlay.c +++ b/drivers/gpu/drm/i915/display/intel_overlay.c @@ -959,6 +959,9 @@ static int check_overlay_dst(struct intel_overlay *overlay, const struct intel_crtc_state *pipe_config = overlay->crtc->config; + if (rec->dst_height == 0 || rec->dst_width == 0) + return -EINVAL; + if (rec->dst_x < pipe_config->pipe_src_w && rec->dst_x + rec->dst_width <= pipe_config->pipe_src_w && rec->dst_y < pipe_config->pipe_src_h && diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c index 40faa18947c9..dbd7d0d83a14 100644 --- a/drivers/gpu/drm/i915/display/intel_tc.c +++ b/drivers/gpu/drm/i915/display/intel_tc.c @@ -345,10 +345,11 @@ static bool icl_tc_phy_status_complete(struct intel_digital_port *dig_port) static bool adl_tc_phy_status_complete(struct intel_digital_port *dig_port) { struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); + enum tc_port tc_port = intel_port_to_tc(i915, dig_port->base.port); struct intel_uncore *uncore = &i915->uncore; u32 val; - val = intel_uncore_read(uncore, TCSS_DDI_STATUS(dig_port->tc_phy_fia_idx)); + val = intel_uncore_read(uncore, TCSS_DDI_STATUS(tc_port)); if (val == 0xffffffff) { drm_dbg_kms(&i915->drm, "Port %s: PHY in TCCOLD, assuming not complete\n", diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 3a5b247be738..1736efa43339 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -2505,9 +2505,14 @@ static int eb_pin_timeline(struct i915_execbuffer *eb, struct intel_context *ce, timeout) < 0) { i915_request_put(rq); - tl = intel_context_timeline_lock(ce); + /* + * Error path, cannot use intel_context_timeline_lock as + * that is user interruptable and this clean up step + * must be done. + */ + mutex_lock(&ce->timeline->mutex); intel_context_exit(ce); - intel_context_timeline_unlock(tl); + mutex_unlock(&ce->timeline->mutex); if (nonblock) return -EWOULDBLOCK; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index f9240d4baa69..3aabe164c329 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -206,6 +206,11 @@ struct intel_guc { * context usage for overflows. */ struct delayed_work work; + + /** + * @shift: Right shift value for the gpm timestamp + */ + u32 shift; } timestamp; #ifdef CONFIG_DRM_I915_SELFTEST diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index e7517206af82..154ad726e266 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1113,6 +1113,19 @@ __extend_last_switch(struct intel_guc *guc, u64 *prev_start, u32 new_start) if (new_start == lower_32_bits(*prev_start)) return; + /* + * When gt is unparked, we update the gt timestamp and start the ping + * worker that updates the gt_stamp every POLL_TIME_CLKS. As long as gt + * is unparked, all switched in contexts will have a start time that is + * within +/- POLL_TIME_CLKS of the most recent gt_stamp. + * + * If neither gt_stamp nor new_start has rolled over, then the + * gt_stamp_hi does not need to be adjusted, however if one of them has + * rolled over, we need to adjust gt_stamp_hi accordingly. + * + * The below conditions address the cases of new_start rollover and + * gt_stamp_last rollover respectively. + */ if (new_start < gt_stamp_last && (new_start - gt_stamp_last) <= POLL_TIME_CLKS) gt_stamp_hi++; @@ -1124,17 +1137,45 @@ __extend_last_switch(struct intel_guc *guc, u64 *prev_start, u32 new_start) *prev_start = ((u64)gt_stamp_hi << 32) | new_start; } -static void guc_update_engine_gt_clks(struct intel_engine_cs *engine) +/* + * GuC updates shared memory and KMD reads it. Since this is not synchronized, + * we run into a race where the value read is inconsistent. Sometimes the + * inconsistency is in reading the upper MSB bytes of the last_in value when + * this race occurs. 2 types of cases are seen - upper 8 bits are zero and upper + * 24 bits are zero. Since these are non-zero values, it is non-trivial to + * determine validity of these values. Instead we read the values multiple times + * until they are consistent. In test runs, 3 attempts results in consistent + * values. The upper bound is set to 6 attempts and may need to be tuned as per + * any new occurences. + */ +static void __get_engine_usage_record(struct intel_engine_cs *engine, + u32 *last_in, u32 *id, u32 *total) { struct guc_engine_usage_record *rec = intel_guc_engine_usage(engine); + int i = 0; + + do { + *last_in = READ_ONCE(rec->last_switch_in_stamp); + *id = READ_ONCE(rec->current_context_index); + *total = READ_ONCE(rec->total_runtime); + + if (READ_ONCE(rec->last_switch_in_stamp) == *last_in && + READ_ONCE(rec->current_context_index) == *id && + READ_ONCE(rec->total_runtime) == *total) + break; + } while (++i < 6); +} + +static void guc_update_engine_gt_clks(struct intel_engine_cs *engine) +{ struct intel_engine_guc_stats *stats = &engine->stats.guc; struct intel_guc *guc = &engine->gt->uc.guc; - u32 last_switch = rec->last_switch_in_stamp; - u32 ctx_id = rec->current_context_index; - u32 total = rec->total_runtime; + u32 last_switch, ctx_id, total; lockdep_assert_held(&guc->timestamp.lock); + __get_engine_usage_record(engine, &last_switch, &ctx_id, &total); + stats->running = ctx_id != ~0U && last_switch; if (stats->running) __extend_last_switch(guc, &stats->start_gt_clk, last_switch); @@ -1149,23 +1190,51 @@ static void guc_update_engine_gt_clks(struct intel_engine_cs *engine) } } -static void guc_update_pm_timestamp(struct intel_guc *guc, - struct intel_engine_cs *engine, - ktime_t *now) +static u32 gpm_timestamp_shift(struct intel_gt *gt) +{ + intel_wakeref_t wakeref; + u32 reg, shift; + + with_intel_runtime_pm(gt->uncore->rpm, wakeref) + reg = intel_uncore_read(gt->uncore, RPM_CONFIG0); + + shift = (reg & GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK) >> + GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_SHIFT; + + return 3 - shift; +} + +static u64 gpm_timestamp(struct intel_gt *gt) +{ + u32 lo, hi, old_hi, loop = 0; + + hi = intel_uncore_read(gt->uncore, MISC_STATUS1); + do { + lo = intel_uncore_read(gt->uncore, MISC_STATUS0); + old_hi = hi; + hi = intel_uncore_read(gt->uncore, MISC_STATUS1); + } while (old_hi != hi && loop++ < 2); + + return ((u64)hi << 32) | lo; +} + +static void guc_update_pm_timestamp(struct intel_guc *guc, ktime_t *now) { - u32 gt_stamp_now, gt_stamp_hi; + struct intel_gt *gt = guc_to_gt(guc); + u32 gt_stamp_lo, gt_stamp_hi; + u64 gpm_ts; lockdep_assert_held(&guc->timestamp.lock); gt_stamp_hi = upper_32_bits(guc->timestamp.gt_stamp); - gt_stamp_now = intel_uncore_read(engine->uncore, - RING_TIMESTAMP(engine->mmio_base)); + gpm_ts = gpm_timestamp(gt) >> guc->timestamp.shift; + gt_stamp_lo = lower_32_bits(gpm_ts); *now = ktime_get(); - if (gt_stamp_now < lower_32_bits(guc->timestamp.gt_stamp)) + if (gt_stamp_lo < lower_32_bits(guc->timestamp.gt_stamp)) gt_stamp_hi++; - guc->timestamp.gt_stamp = ((u64)gt_stamp_hi << 32) | gt_stamp_now; + guc->timestamp.gt_stamp = ((u64)gt_stamp_hi << 32) | gt_stamp_lo; } /* @@ -1208,8 +1277,12 @@ static ktime_t guc_engine_busyness(struct intel_engine_cs *engine, ktime_t *now) if (!in_reset && intel_gt_pm_get_if_awake(gt)) { stats_saved = *stats; gt_stamp_saved = guc->timestamp.gt_stamp; + /* + * Update gt_clks, then gt timestamp to simplify the 'gt_stamp - + * start_gt_clk' calculation below for active engines. + */ guc_update_engine_gt_clks(engine); - guc_update_pm_timestamp(guc, engine, now); + guc_update_pm_timestamp(guc, now); intel_gt_pm_put_async(gt); if (i915_reset_count(gpu_error) != reset_count) { *stats = stats_saved; @@ -1241,8 +1314,8 @@ static void __reset_guc_busyness_stats(struct intel_guc *guc) spin_lock_irqsave(&guc->timestamp.lock, flags); + guc_update_pm_timestamp(guc, &unused); for_each_engine(engine, gt, id) { - guc_update_pm_timestamp(guc, engine, &unused); guc_update_engine_gt_clks(engine); engine->stats.guc.prev_total = 0; } @@ -1259,10 +1332,11 @@ static void __update_guc_busyness_stats(struct intel_guc *guc) ktime_t unused; spin_lock_irqsave(&guc->timestamp.lock, flags); - for_each_engine(engine, gt, id) { - guc_update_pm_timestamp(guc, engine, &unused); + + guc_update_pm_timestamp(guc, &unused); + for_each_engine(engine, gt, id) guc_update_engine_gt_clks(engine); - } + spin_unlock_irqrestore(&guc->timestamp.lock, flags); } @@ -1335,10 +1409,15 @@ void intel_guc_busyness_park(struct intel_gt *gt) void intel_guc_busyness_unpark(struct intel_gt *gt) { struct intel_guc *guc = >->uc.guc; + unsigned long flags; + ktime_t unused; if (!guc_submission_initialized(guc)) return; + spin_lock_irqsave(&guc->timestamp.lock, flags); + guc_update_pm_timestamp(guc, &unused); + spin_unlock_irqrestore(&guc->timestamp.lock, flags); mod_delayed_work(system_highpri_wq, &guc->timestamp.work, guc->timestamp.ping_delay); } @@ -1783,6 +1862,7 @@ int intel_guc_submission_init(struct intel_guc *guc) spin_lock_init(&guc->timestamp.lock); INIT_DELAYED_WORK(&guc->timestamp.work, guc_timestamp_ping); guc->timestamp.ping_delay = (POLL_TIME_CLKS / gt->clock_frequency + 1) * HZ; + guc->timestamp.shift = gpm_timestamp_shift(gt); return 0; } diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 5ae812d60abe..0633888a411e 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1522,7 +1522,7 @@ capture_engine(struct intel_engine_cs *engine, struct i915_request *rq = NULL; unsigned long flags; - ee = intel_engine_coredump_alloc(engine, GFP_KERNEL); + ee = intel_engine_coredump_alloc(engine, ALLOW_FAIL); if (!ee) return NULL; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index c32420cb8ed5..c2bb33febb68 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2684,7 +2684,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define RING_WAIT (1 << 11) /* gen3+, PRBx_CTL */ #define RING_WAIT_SEMAPHORE (1 << 10) /* gen6+ */ -#define GUCPMTIMESTAMP _MMIO(0xC3E8) +#define MISC_STATUS0 _MMIO(0xA500) +#define MISC_STATUS1 _MMIO(0xA504) /* There are 16 64-bit CS General Purpose Registers per-engine on Gen8+ */ #define GEN8_RING_CS_GPR(base, n) _MMIO((base) + 0x600 + (n) * 8) diff --git a/drivers/gpu/drm/kmb/kmb_plane.c b/drivers/gpu/drm/kmb/kmb_plane.c index 00404ba4126d..2735b8eb3537 100644 --- a/drivers/gpu/drm/kmb/kmb_plane.c +++ b/drivers/gpu/drm/kmb/kmb_plane.c @@ -158,12 +158,6 @@ static void kmb_plane_atomic_disable(struct drm_plane *plane, case LAYER_1: kmb->plane_status[plane_id].ctrl = LCD_CTRL_VL2_ENABLE; break; - case LAYER_2: - kmb->plane_status[plane_id].ctrl = LCD_CTRL_GL1_ENABLE; - break; - case LAYER_3: - kmb->plane_status[plane_id].ctrl = LCD_CTRL_GL2_ENABLE; - break; } kmb->plane_status[plane_id].disable = true; diff --git a/drivers/gpu/drm/mxsfb/mxsfb_kms.c b/drivers/gpu/drm/mxsfb/mxsfb_kms.c index 0655582ae8ed..4cfb6c001679 100644 --- a/drivers/gpu/drm/mxsfb/mxsfb_kms.c +++ b/drivers/gpu/drm/mxsfb/mxsfb_kms.c @@ -361,7 +361,11 @@ static void mxsfb_crtc_atomic_enable(struct drm_crtc *crtc, bridge_state = drm_atomic_get_new_bridge_state(state, mxsfb->bridge); - bus_format = bridge_state->input_bus_cfg.format; + if (!bridge_state) + bus_format = MEDIA_BUS_FMT_FIXED; + else + bus_format = bridge_state->input_bus_cfg.format; + if (bus_format == MEDIA_BUS_FMT_FIXED) { dev_warn_once(drm->dev, "Bridge does not provide bus format, assuming MEDIA_BUS_FMT_RGB888_1X24.\n" diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/base.c index d0f52d59fc2f..64e423dddd9e 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/base.c @@ -38,7 +38,7 @@ nvbios_addr(struct nvkm_bios *bios, u32 *addr, u8 size) *addr += bios->imaged_addr; } - if (unlikely(*addr + size >= bios->size)) { + if (unlikely(*addr + size > bios->size)) { nvkm_error(&bios->subdev, "OOB %d %08x %08x\n", size, p, *addr); return false; } diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c index c903b74f46a4..35f0d5e7533d 100644 --- a/drivers/infiniband/core/cm.c +++ b/drivers/infiniband/core/cm.c @@ -3322,7 +3322,7 @@ static int cm_lap_handler(struct cm_work *work) ret = cm_init_av_by_path(param->alternate_path, NULL, &alt_av); if (ret) { rdma_destroy_ah_attr(&ah_attr); - return -EINVAL; + goto deref; } spin_lock_irq(&cm_id_priv->lock); diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 27a00ce2e101..c447526288f4 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -67,8 +67,8 @@ static const char * const cma_events[] = { [RDMA_CM_EVENT_TIMEWAIT_EXIT] = "timewait exit", }; -static void cma_set_mgid(struct rdma_id_private *id_priv, struct sockaddr *addr, - union ib_gid *mgid); +static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid, + enum ib_gid_type gid_type); const char *__attribute_const__ rdma_event_msg(enum rdma_cm_event_type event) { @@ -1846,17 +1846,19 @@ static void destroy_mc(struct rdma_id_private *id_priv, if (dev_addr->bound_dev_if) ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); - if (ndev) { + if (ndev && !send_only) { + enum ib_gid_type gid_type; union ib_gid mgid; - cma_set_mgid(id_priv, (struct sockaddr *)&mc->addr, - &mgid); - - if (!send_only) - cma_igmp_send(ndev, &mgid, false); - - dev_put(ndev); + gid_type = id_priv->cma_dev->default_gid_type + [id_priv->id.port_num - + rdma_start_port( + id_priv->cma_dev->device)]; + cma_iboe_set_mgid((struct sockaddr *)&mc->addr, &mgid, + gid_type); + cma_igmp_send(ndev, &mgid, false); } + dev_put(ndev); cancel_work_sync(&mc->iboe_join.work); } diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 2b72c4fa9550..9d6ac9dff39a 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -95,6 +95,7 @@ struct ucma_context { u64 uid; struct list_head list; + struct list_head mc_list; struct work_struct close_work; }; @@ -105,6 +106,7 @@ struct ucma_multicast { u64 uid; u8 join_state; + struct list_head list; struct sockaddr_storage addr; }; @@ -198,6 +200,7 @@ static struct ucma_context *ucma_alloc_ctx(struct ucma_file *file) INIT_WORK(&ctx->close_work, ucma_close_id); init_completion(&ctx->comp); + INIT_LIST_HEAD(&ctx->mc_list); /* So list_del() will work if we don't do ucma_finish_ctx() */ INIT_LIST_HEAD(&ctx->list); ctx->file = file; @@ -484,19 +487,19 @@ err1: static void ucma_cleanup_multicast(struct ucma_context *ctx) { - struct ucma_multicast *mc; - unsigned long index; + struct ucma_multicast *mc, *tmp; - xa_for_each(&multicast_table, index, mc) { - if (mc->ctx != ctx) - continue; + xa_lock(&multicast_table); + list_for_each_entry_safe(mc, tmp, &ctx->mc_list, list) { + list_del(&mc->list); /* * At this point mc->ctx->ref is 0 so the mc cannot leave the * lock on the reader and this is enough serialization */ - xa_erase(&multicast_table, index); + __xa_erase(&multicast_table, mc->id); kfree(mc); } + xa_unlock(&multicast_table); } static void ucma_cleanup_mc_events(struct ucma_multicast *mc) @@ -1469,12 +1472,16 @@ static ssize_t ucma_process_join(struct ucma_file *file, mc->uid = cmd->uid; memcpy(&mc->addr, addr, cmd->addr_size); - if (xa_alloc(&multicast_table, &mc->id, NULL, xa_limit_32b, + xa_lock(&multicast_table); + if (__xa_alloc(&multicast_table, &mc->id, NULL, xa_limit_32b, GFP_KERNEL)) { ret = -ENOMEM; goto err_free_mc; } + list_add_tail(&mc->list, &ctx->mc_list); + xa_unlock(&multicast_table); + mutex_lock(&ctx->mutex); ret = rdma_join_multicast(ctx->cm_id, (struct sockaddr *)&mc->addr, join_state, mc); @@ -1500,8 +1507,11 @@ err_leave_multicast: mutex_unlock(&ctx->mutex); ucma_cleanup_mc_events(mc); err_xa_erase: - xa_erase(&multicast_table, mc->id); + xa_lock(&multicast_table); + list_del(&mc->list); + __xa_erase(&multicast_table, mc->id); err_free_mc: + xa_unlock(&multicast_table); kfree(mc); err_put_ctx: ucma_put_ctx(ctx); @@ -1569,15 +1579,17 @@ static ssize_t ucma_leave_multicast(struct ucma_file *file, mc = ERR_PTR(-EINVAL); else if (!refcount_inc_not_zero(&mc->ctx->ref)) mc = ERR_PTR(-ENXIO); - else - __xa_erase(&multicast_table, mc->id); - xa_unlock(&multicast_table); if (IS_ERR(mc)) { + xa_unlock(&multicast_table); ret = PTR_ERR(mc); goto out; } + list_del(&mc->list); + __xa_erase(&multicast_table, mc->id); + xa_unlock(&multicast_table); + mutex_lock(&mc->ctx->mutex); rdma_leave_multicast(mc->ctx->cm_id, (struct sockaddr *) &mc->addr); mutex_unlock(&mc->ctx->mutex); diff --git a/drivers/infiniband/hw/hfi1/ipoib.h b/drivers/infiniband/hw/hfi1/ipoib.h index 909122934246..aec60d4888eb 100644 --- a/drivers/infiniband/hw/hfi1/ipoib.h +++ b/drivers/infiniband/hw/hfi1/ipoib.h @@ -55,7 +55,7 @@ union hfi1_ipoib_flow { */ struct ipoib_txreq { struct sdma_txreq txreq; - struct hfi1_sdma_header sdma_hdr; + struct hfi1_sdma_header *sdma_hdr; int sdma_status; int complete; struct hfi1_ipoib_dev_priv *priv; diff --git a/drivers/infiniband/hw/hfi1/ipoib_main.c b/drivers/infiniband/hw/hfi1/ipoib_main.c index e1a2b02bbd91..5d814afdf7f3 100644 --- a/drivers/infiniband/hw/hfi1/ipoib_main.c +++ b/drivers/infiniband/hw/hfi1/ipoib_main.c @@ -22,26 +22,35 @@ static int hfi1_ipoib_dev_init(struct net_device *dev) int ret; dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!dev->tstats) + return -ENOMEM; ret = priv->netdev_ops->ndo_init(dev); if (ret) - return ret; + goto out_ret; ret = hfi1_netdev_add_data(priv->dd, qpn_from_mac(priv->netdev->dev_addr), dev); if (ret < 0) { priv->netdev_ops->ndo_uninit(dev); - return ret; + goto out_ret; } return 0; +out_ret: + free_percpu(dev->tstats); + dev->tstats = NULL; + return ret; } static void hfi1_ipoib_dev_uninit(struct net_device *dev) { struct hfi1_ipoib_dev_priv *priv = hfi1_ipoib_priv(dev); + free_percpu(dev->tstats); + dev->tstats = NULL; + hfi1_netdev_remove_data(priv->dd, qpn_from_mac(priv->netdev->dev_addr)); priv->netdev_ops->ndo_uninit(dev); @@ -166,12 +175,7 @@ static void hfi1_ipoib_netdev_dtor(struct net_device *dev) hfi1_ipoib_rxq_deinit(priv->netdev); free_percpu(dev->tstats); -} - -static void hfi1_ipoib_free_rdma_netdev(struct net_device *dev) -{ - hfi1_ipoib_netdev_dtor(dev); - free_netdev(dev); + dev->tstats = NULL; } static void hfi1_ipoib_set_id(struct net_device *dev, int id) @@ -211,24 +215,23 @@ static int hfi1_ipoib_setup_rn(struct ib_device *device, priv->port_num = port_num; priv->netdev_ops = netdev->netdev_ops; - netdev->netdev_ops = &hfi1_ipoib_netdev_ops; - ib_query_pkey(device, port_num, priv->pkey_index, &priv->pkey); rc = hfi1_ipoib_txreq_init(priv); if (rc) { dd_dev_err(dd, "IPoIB netdev TX init - failed(%d)\n", rc); - hfi1_ipoib_free_rdma_netdev(netdev); return rc; } rc = hfi1_ipoib_rxq_init(netdev); if (rc) { dd_dev_err(dd, "IPoIB netdev RX init - failed(%d)\n", rc); - hfi1_ipoib_free_rdma_netdev(netdev); + hfi1_ipoib_txreq_deinit(priv); return rc; } + netdev->netdev_ops = &hfi1_ipoib_netdev_ops; + netdev->priv_destructor = hfi1_ipoib_netdev_dtor; netdev->needs_free_netdev = true; diff --git a/drivers/infiniband/hw/hfi1/ipoib_tx.c b/drivers/infiniband/hw/hfi1/ipoib_tx.c index f4010890309f..d6bbdb8fcb50 100644 --- a/drivers/infiniband/hw/hfi1/ipoib_tx.c +++ b/drivers/infiniband/hw/hfi1/ipoib_tx.c @@ -122,7 +122,7 @@ static void hfi1_ipoib_free_tx(struct ipoib_txreq *tx, int budget) dd_dev_warn(priv->dd, "%s: Status = 0x%x pbc 0x%llx txq = %d sde = %d\n", __func__, tx->sdma_status, - le64_to_cpu(tx->sdma_hdr.pbc), tx->txq->q_idx, + le64_to_cpu(tx->sdma_hdr->pbc), tx->txq->q_idx, tx->txq->sde->this_idx); } @@ -231,7 +231,7 @@ static int hfi1_ipoib_build_tx_desc(struct ipoib_txreq *tx, { struct hfi1_devdata *dd = txp->dd; struct sdma_txreq *txreq = &tx->txreq; - struct hfi1_sdma_header *sdma_hdr = &tx->sdma_hdr; + struct hfi1_sdma_header *sdma_hdr = tx->sdma_hdr; u16 pkt_bytes = sizeof(sdma_hdr->pbc) + (txp->hdr_dwords << 2) + tx->skb->len; int ret; @@ -256,7 +256,7 @@ static void hfi1_ipoib_build_ib_tx_headers(struct ipoib_txreq *tx, struct ipoib_txparms *txp) { struct hfi1_ipoib_dev_priv *priv = tx->txq->priv; - struct hfi1_sdma_header *sdma_hdr = &tx->sdma_hdr; + struct hfi1_sdma_header *sdma_hdr = tx->sdma_hdr; struct sk_buff *skb = tx->skb; struct hfi1_pportdata *ppd = ppd_from_ibp(txp->ibp); struct rdma_ah_attr *ah_attr = txp->ah_attr; @@ -483,7 +483,7 @@ static int hfi1_ipoib_send_dma_single(struct net_device *dev, if (likely(!ret)) { tx_ok: trace_sdma_output_ibhdr(txq->priv->dd, - &tx->sdma_hdr.hdr, + &tx->sdma_hdr->hdr, ib_is_sc5(txp->flow.sc5)); hfi1_ipoib_check_queue_depth(txq); return NETDEV_TX_OK; @@ -547,7 +547,7 @@ static int hfi1_ipoib_send_dma_list(struct net_device *dev, hfi1_ipoib_check_queue_depth(txq); trace_sdma_output_ibhdr(txq->priv->dd, - &tx->sdma_hdr.hdr, + &tx->sdma_hdr->hdr, ib_is_sc5(txp->flow.sc5)); if (!netdev_xmit_more()) @@ -683,7 +683,8 @@ int hfi1_ipoib_txreq_init(struct hfi1_ipoib_dev_priv *priv) { struct net_device *dev = priv->netdev; u32 tx_ring_size, tx_item_size; - int i; + struct hfi1_ipoib_circ_buf *tx_ring; + int i, j; /* * Ring holds 1 less than tx_ring_size @@ -701,7 +702,9 @@ int hfi1_ipoib_txreq_init(struct hfi1_ipoib_dev_priv *priv) for (i = 0; i < dev->num_tx_queues; i++) { struct hfi1_ipoib_txq *txq = &priv->txqs[i]; + struct ipoib_txreq *tx; + tx_ring = &txq->tx_ring; iowait_init(&txq->wait, 0, hfi1_ipoib_flush_txq, @@ -725,14 +728,19 @@ int hfi1_ipoib_txreq_init(struct hfi1_ipoib_dev_priv *priv) priv->dd->node); txq->tx_ring.items = - kcalloc_node(tx_ring_size, tx_item_size, - GFP_KERNEL, priv->dd->node); + kvzalloc_node(array_size(tx_ring_size, tx_item_size), + GFP_KERNEL, priv->dd->node); if (!txq->tx_ring.items) goto free_txqs; txq->tx_ring.max_items = tx_ring_size; - txq->tx_ring.shift = ilog2(tx_ring_size); + txq->tx_ring.shift = ilog2(tx_item_size); txq->tx_ring.avail = hfi1_ipoib_ring_hwat(txq); + tx_ring = &txq->tx_ring; + for (j = 0; j < tx_ring_size; j++) + hfi1_txreq_from_idx(tx_ring, j)->sdma_hdr = + kzalloc_node(sizeof(*tx->sdma_hdr), + GFP_KERNEL, priv->dd->node); netif_tx_napi_add(dev, &txq->napi, hfi1_ipoib_poll_tx_ring, @@ -746,7 +754,10 @@ free_txqs: struct hfi1_ipoib_txq *txq = &priv->txqs[i]; netif_napi_del(&txq->napi); - kfree(txq->tx_ring.items); + tx_ring = &txq->tx_ring; + for (j = 0; j < tx_ring_size; j++) + kfree(hfi1_txreq_from_idx(tx_ring, j)->sdma_hdr); + kvfree(tx_ring->items); } kfree(priv->txqs); @@ -780,17 +791,20 @@ static void hfi1_ipoib_drain_tx_list(struct hfi1_ipoib_txq *txq) void hfi1_ipoib_txreq_deinit(struct hfi1_ipoib_dev_priv *priv) { - int i; + int i, j; for (i = 0; i < priv->netdev->num_tx_queues; i++) { struct hfi1_ipoib_txq *txq = &priv->txqs[i]; + struct hfi1_ipoib_circ_buf *tx_ring = &txq->tx_ring; iowait_cancel_work(&txq->wait); iowait_sdma_drain(&txq->wait); hfi1_ipoib_drain_tx_list(txq); netif_napi_del(&txq->napi); hfi1_ipoib_drain_tx_ring(txq); - kfree(txq->tx_ring.items); + for (j = 0; j < tx_ring->max_items; j++) + kfree(hfi1_txreq_from_idx(tx_ring, j)->sdma_hdr); + kvfree(tx_ring->items); } kfree(priv->txqs); diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 1c3d97229988..93b1650eacfa 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -3237,7 +3237,7 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr, case MLX4_DEV_EVENT_PORT_MGMT_CHANGE: ew = kmalloc(sizeof *ew, GFP_ATOMIC); if (!ew) - break; + return; INIT_WORK(&ew->work, handle_port_mgmt_change_event); memcpy(&ew->ib_eqe, eqe, sizeof *eqe); diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 3305f2744bfa..ae50b56e8913 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -3073,6 +3073,8 @@ do_write: case IB_WR_ATOMIC_FETCH_AND_ADD: if (unlikely(!(qp->qp_access_flags & IB_ACCESS_REMOTE_ATOMIC))) goto inv_err; + if (unlikely(wqe->atomic_wr.remote_addr & (sizeof(u64) - 1))) + goto inv_err; if (unlikely(!rvt_rkey_ok(qp, &qp->r_sge.sge, sizeof(u64), wqe->atomic_wr.remote_addr, wqe->atomic_wr.rkey, diff --git a/drivers/infiniband/sw/siw/siw.h b/drivers/infiniband/sw/siw/siw.h index 368959ae9a8c..df03d84c6868 100644 --- a/drivers/infiniband/sw/siw/siw.h +++ b/drivers/infiniband/sw/siw/siw.h @@ -644,14 +644,9 @@ static inline struct siw_sqe *orq_get_current(struct siw_qp *qp) return &qp->orq[qp->orq_get % qp->attrs.orq_size]; } -static inline struct siw_sqe *orq_get_tail(struct siw_qp *qp) -{ - return &qp->orq[qp->orq_put % qp->attrs.orq_size]; -} - static inline struct siw_sqe *orq_get_free(struct siw_qp *qp) { - struct siw_sqe *orq_e = orq_get_tail(qp); + struct siw_sqe *orq_e = &qp->orq[qp->orq_put % qp->attrs.orq_size]; if (READ_ONCE(orq_e->flags) == 0) return orq_e; diff --git a/drivers/infiniband/sw/siw/siw_qp_rx.c b/drivers/infiniband/sw/siw/siw_qp_rx.c index 60116f20653c..875ea6f1b04a 100644 --- a/drivers/infiniband/sw/siw/siw_qp_rx.c +++ b/drivers/infiniband/sw/siw/siw_qp_rx.c @@ -1153,11 +1153,12 @@ static int siw_check_tx_fence(struct siw_qp *qp) spin_lock_irqsave(&qp->orq_lock, flags); - rreq = orq_get_current(qp); - /* free current orq entry */ + rreq = orq_get_current(qp); WRITE_ONCE(rreq->flags, 0); + qp->orq_get++; + if (qp->tx_ctx.orq_fence) { if (unlikely(tx_waiting->wr_status != SIW_WR_QUEUED)) { pr_warn("siw: [QP %u]: fence resume: bad status %d\n", @@ -1165,10 +1166,12 @@ static int siw_check_tx_fence(struct siw_qp *qp) rv = -EPROTO; goto out; } - /* resume SQ processing */ + /* resume SQ processing, if possible */ if (tx_waiting->sqe.opcode == SIW_OP_READ || tx_waiting->sqe.opcode == SIW_OP_READ_LOCAL_INV) { - rreq = orq_get_tail(qp); + + /* SQ processing was stopped because of a full ORQ */ + rreq = orq_get_free(qp); if (unlikely(!rreq)) { pr_warn("siw: [QP %u]: no ORQE\n", qp_id(qp)); rv = -EPROTO; @@ -1181,15 +1184,14 @@ static int siw_check_tx_fence(struct siw_qp *qp) resume_tx = 1; } else if (siw_orq_empty(qp)) { + /* + * SQ processing was stopped by fenced work request. + * Resume since all previous Read's are now completed. + */ qp->tx_ctx.orq_fence = 0; resume_tx = 1; - } else { - pr_warn("siw: [QP %u]: fence resume: orq idx: %d:%d\n", - qp_id(qp), qp->orq_get, qp->orq_put); - rv = -EPROTO; } } - qp->orq_get++; out: spin_unlock_irqrestore(&qp->orq_lock, flags); diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c index a3dd2cb6d5c9..54ef367b074a 100644 --- a/drivers/infiniband/sw/siw/siw_verbs.c +++ b/drivers/infiniband/sw/siw/siw_verbs.c @@ -313,7 +313,8 @@ int siw_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *attrs, if (atomic_inc_return(&sdev->num_qp) > SIW_MAX_QP) { siw_dbg(base_dev, "too many QP's\n"); - return -ENOMEM; + rv = -ENOMEM; + goto err_atomic; } if (attrs->qp_type != IB_QPT_RC) { siw_dbg(base_dev, "only RC QP's supported\n"); diff --git a/drivers/input/touchscreen/wm97xx-core.c b/drivers/input/touchscreen/wm97xx-core.c index 78d2ee99f37a..1b58611c8084 100644 --- a/drivers/input/touchscreen/wm97xx-core.c +++ b/drivers/input/touchscreen/wm97xx-core.c @@ -615,10 +615,9 @@ static int wm97xx_register_touch(struct wm97xx *wm) * extensions) */ wm->touch_dev = platform_device_alloc("wm97xx-touch", -1); - if (!wm->touch_dev) { - ret = -ENOMEM; - goto touch_err; - } + if (!wm->touch_dev) + return -ENOMEM; + platform_set_drvdata(wm->touch_dev, wm); wm->touch_dev->dev.parent = wm->dev; wm->touch_dev->dev.platform_data = pdata; @@ -629,9 +628,6 @@ static int wm97xx_register_touch(struct wm97xx *wm) return 0; touch_reg_err: platform_device_put(wm->touch_dev); -touch_err: - input_unregister_device(wm->input_dev); - wm->input_dev = NULL; return ret; } @@ -639,8 +635,6 @@ touch_err: static void wm97xx_unregister_touch(struct wm97xx *wm) { platform_device_unregister(wm->touch_dev); - input_unregister_device(wm->input_dev); - wm->input_dev = NULL; } static int _wm97xx_probe(struct wm97xx *wm) diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index dc338acf3338..b10fb52ea442 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -21,6 +21,7 @@ #include <linux/export.h> #include <linux/kmemleak.h> #include <linux/cc_platform.h> +#include <linux/iopoll.h> #include <asm/pci-direct.h> #include <asm/iommu.h> #include <asm/apic.h> @@ -834,6 +835,7 @@ static int iommu_ga_log_enable(struct amd_iommu *iommu) status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET); if (status & (MMIO_STATUS_GALOG_RUN_MASK)) break; + udelay(10); } if (WARN_ON(i >= LOOP_TIMEOUT)) diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index f912fe45bea2..a67319597884 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -569,9 +569,8 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu) fn, &intel_ir_domain_ops, iommu); if (!iommu->ir_domain) { - irq_domain_free_fwnode(fn); pr_err("IR%d: failed to allocate irqdomain\n", iommu->seq_id); - goto out_free_bitmap; + goto out_free_fwnode; } iommu->ir_msi_domain = arch_create_remap_msi_irq_domain(iommu->ir_domain, @@ -595,7 +594,7 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu) if (dmar_enable_qi(iommu)) { pr_err("Failed to enable queued invalidation\n"); - goto out_free_bitmap; + goto out_free_ir_domain; } } @@ -619,6 +618,14 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu) return 0; +out_free_ir_domain: + if (iommu->ir_msi_domain) + irq_domain_remove(iommu->ir_msi_domain); + iommu->ir_msi_domain = NULL; + irq_domain_remove(iommu->ir_domain); + iommu->ir_domain = NULL; +out_free_fwnode: + irq_domain_free_fwnode(fn); out_free_bitmap: bitmap_free(bitmap); out_free_pages: diff --git a/drivers/iommu/ioasid.c b/drivers/iommu/ioasid.c index 50ee27bbd04e..06fee7416816 100644 --- a/drivers/iommu/ioasid.c +++ b/drivers/iommu/ioasid.c @@ -349,6 +349,7 @@ EXPORT_SYMBOL_GPL(ioasid_alloc); /** * ioasid_get - obtain a reference to the IOASID + * @ioasid: the ID to get */ void ioasid_get(ioasid_t ioasid) { diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 8b86406b7162..107dcf5938d6 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -207,9 +207,14 @@ static struct dev_iommu *dev_iommu_get(struct device *dev) static void dev_iommu_free(struct device *dev) { - iommu_fwspec_free(dev); - kfree(dev->iommu); + struct dev_iommu *param = dev->iommu; + dev->iommu = NULL; + if (param->fwspec) { + fwnode_handle_put(param->fwspec->iommu_fwnode); + kfree(param->fwspec); + } + kfree(param); } static int __iommu_probe_device(struct device *dev, struct list_head *group_list) @@ -980,17 +985,6 @@ static int iommu_group_device_count(struct iommu_group *group) return ret; } -/** - * iommu_group_for_each_dev - iterate over each device in the group - * @group: the group - * @data: caller opaque data to be passed to callback function - * @fn: caller supplied callback function - * - * This function is called by group users to iterate over group devices. - * Callers should hold a reference count to the group during callback. - * The group->mutex is held across callbacks, which will block calls to - * iommu_group_add/remove_device. - */ static int __iommu_group_for_each_dev(struct iommu_group *group, void *data, int (*fn)(struct device *, void *)) { @@ -1005,7 +999,17 @@ static int __iommu_group_for_each_dev(struct iommu_group *group, void *data, return ret; } - +/** + * iommu_group_for_each_dev - iterate over each device in the group + * @group: the group + * @data: caller opaque data to be passed to callback function + * @fn: caller supplied callback function + * + * This function is called by group users to iterate over group devices. + * Callers should hold a reference count to the group during callback. + * The group->mutex is held across callbacks, which will block calls to + * iommu_group_add/remove_device. + */ int iommu_group_for_each_dev(struct iommu_group *group, void *data, int (*fn)(struct device *, void *)) { @@ -3032,6 +3036,7 @@ EXPORT_SYMBOL_GPL(iommu_aux_get_pasid); * iommu_sva_bind_device() - Bind a process address space to a device * @dev: the device * @mm: the mm to bind, caller must hold a reference to it + * @drvdata: opaque data pointer to pass to bind callback * * Create a bond between device and address space, allowing the device to access * the mm using the returned PASID. If a bond already exists between @device and diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index 91749654fd49..980e4af3f06b 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1085,7 +1085,7 @@ static __maybe_unused int omap_iommu_runtime_resume(struct device *dev) } /** - * omap_iommu_suspend_prepare - prepare() dev_pm_ops implementation + * omap_iommu_prepare - prepare() dev_pm_ops implementation * @dev: iommu device * * This function performs the necessary checks to determine if the IOMMU diff --git a/drivers/md/md.c b/drivers/md/md.c index 5881d05a76eb..4d38bd7dadd6 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5869,10 +5869,6 @@ int md_run(struct mddev *mddev) nowait = nowait && blk_queue_nowait(bdev_get_queue(rdev->bdev)); } - /* Set the NOWAIT flags if all underlying devices support it */ - if (nowait) - blk_queue_flag_set(QUEUE_FLAG_NOWAIT, mddev->queue); - if (!bioset_initialized(&mddev->bio_set)) { err = bioset_init(&mddev->bio_set, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); if (err) @@ -6010,6 +6006,10 @@ int md_run(struct mddev *mddev) else blk_queue_flag_clear(QUEUE_FLAG_NONROT, mddev->queue); blk_queue_flag_set(QUEUE_FLAG_IO_STAT, mddev->queue); + + /* Set the NOWAIT flags if all underlying devices support it */ + if (nowait) + blk_queue_flag_set(QUEUE_FLAG_NOWAIT, mddev->queue); } if (pers->sync_request) { if (mddev->kobj.sd && diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c index 45f578793980..bd87012c220c 100644 --- a/drivers/mmc/core/sd.c +++ b/drivers/mmc/core/sd.c @@ -67,7 +67,7 @@ static const unsigned int sd_au_size[] = { __res & __mask; \ }) -#define SD_POWEROFF_NOTIFY_TIMEOUT_MS 2000 +#define SD_POWEROFF_NOTIFY_TIMEOUT_MS 1000 #define SD_WRITE_EXTR_SINGLE_TIMEOUT_MS 1000 struct sd_busy_data { @@ -1664,6 +1664,12 @@ static int sd_poweroff_notify(struct mmc_card *card) goto out; } + /* Find out when the command is completed. */ + err = mmc_poll_for_busy(card, SD_WRITE_EXTR_SINGLE_TIMEOUT_MS, false, + MMC_BUSY_EXTR_SINGLE); + if (err) + goto out; + cb_data.card = card; cb_data.reg_buf = reg_buf; err = __mmc_poll_for_busy(card->host, SD_POWEROFF_NOTIFY_TIMEOUT_MS, diff --git a/drivers/mmc/host/moxart-mmc.c b/drivers/mmc/host/moxart-mmc.c index 16d1c7a43d33..b6eb75f4bbfc 100644 --- a/drivers/mmc/host/moxart-mmc.c +++ b/drivers/mmc/host/moxart-mmc.c @@ -705,12 +705,12 @@ static int moxart_remove(struct platform_device *pdev) if (!IS_ERR_OR_NULL(host->dma_chan_rx)) dma_release_channel(host->dma_chan_rx); mmc_remove_host(mmc); - mmc_free_host(mmc); writel(0, host->base + REG_INTERRUPT_MASK); writel(0, host->base + REG_POWER_CONTROL); writel(readl(host->base + REG_CLOCK_CONTROL) | CLK_OFF, host->base + REG_CLOCK_CONTROL); + mmc_free_host(mmc); return 0; } diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c index a593b1fbd69e..0f3658b36513 100644 --- a/drivers/mmc/host/sdhci-of-esdhc.c +++ b/drivers/mmc/host/sdhci-of-esdhc.c @@ -524,12 +524,16 @@ static void esdhc_of_adma_workaround(struct sdhci_host *host, u32 intmask) static int esdhc_of_enable_dma(struct sdhci_host *host) { + int ret; u32 value; struct device *dev = mmc_dev(host->mmc); if (of_device_is_compatible(dev->of_node, "fsl,ls1043a-esdhc") || - of_device_is_compatible(dev->of_node, "fsl,ls1046a-esdhc")) - dma_set_mask_and_coherent(dev, DMA_BIT_MASK(40)); + of_device_is_compatible(dev->of_node, "fsl,ls1046a-esdhc")) { + ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(40)); + if (ret) + return ret; + } value = sdhci_readl(host, ESDHC_DMA_SYSCTL); diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c index bcc595c70a9f..104dcd702870 100644 --- a/drivers/mmc/host/sh_mmcif.c +++ b/drivers/mmc/host/sh_mmcif.c @@ -405,6 +405,9 @@ static int sh_mmcif_dma_slave_config(struct sh_mmcif_host *host, struct dma_slave_config cfg = { 0, }; res = platform_get_resource(host->pd, IORESOURCE_MEM, 0); + if (!res) + return -EINVAL; + cfg.direction = direction; if (direction == DMA_DEV_TO_MEM) { diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 6006c2e8fa2b..9fd1d6cba3cd 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -1021,8 +1021,8 @@ static void ad_mux_machine(struct port *port, bool *update_slave_arr) if (port->aggregator && port->aggregator->is_active && !__port_is_enabled(port)) { - __enable_port(port); + *update_slave_arr = true; } } break; @@ -1779,6 +1779,7 @@ static void ad_agg_selection_logic(struct aggregator *agg, port = port->next_port_in_aggregator) { __enable_port(port); } + *update_slave_arr = true; } } diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 9161ce4ca352..cf82b1fa9725 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -621,7 +621,7 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds) get_device(&priv->master_mii_bus->dev); priv->master_mii_dn = dn; - priv->slave_mii_bus = devm_mdiobus_alloc(ds->dev); + priv->slave_mii_bus = mdiobus_alloc(); if (!priv->slave_mii_bus) { of_node_put(dn); return -ENOMEM; @@ -681,8 +681,10 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds) } err = mdiobus_register(priv->slave_mii_bus); - if (err && dn) + if (err && dn) { + mdiobus_free(priv->slave_mii_bus); of_node_put(dn); + } return err; } @@ -690,6 +692,7 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds) static void bcm_sf2_mdio_unregister(struct bcm_sf2_priv *priv) { mdiobus_unregister(priv->slave_mii_bus); + mdiobus_free(priv->slave_mii_bus); of_node_put(priv->master_mii_dn); } diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 46ed953e787e..320ee7fe91a8 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -498,8 +498,9 @@ static int gswip_mdio_rd(struct mii_bus *bus, int addr, int reg) static int gswip_mdio(struct gswip_priv *priv, struct device_node *mdio_np) { struct dsa_switch *ds = priv->ds; + int err; - ds->slave_mii_bus = devm_mdiobus_alloc(priv->dev); + ds->slave_mii_bus = mdiobus_alloc(); if (!ds->slave_mii_bus) return -ENOMEM; @@ -512,7 +513,11 @@ static int gswip_mdio(struct gswip_priv *priv, struct device_node *mdio_np) ds->slave_mii_bus->parent = priv->dev; ds->slave_mii_bus->phy_mask = ~ds->phys_mii_mask; - return of_mdiobus_register(ds->slave_mii_bus, mdio_np); + err = of_mdiobus_register(ds->slave_mii_bus, mdio_np); + if (err) + mdiobus_free(ds->slave_mii_bus); + + return err; } static int gswip_pce_table_entry_read(struct gswip_priv *priv, @@ -2145,8 +2150,10 @@ disable_switch: gswip_mdio_mask(priv, GSWIP_MDIO_GLOB_ENABLE, 0, GSWIP_MDIO_GLOB); dsa_unregister_switch(priv->ds); mdio_bus: - if (mdio_np) + if (mdio_np) { mdiobus_unregister(priv->ds->slave_mii_bus); + mdiobus_free(priv->ds->slave_mii_bus); + } put_mdio_node: of_node_put(mdio_np); for (i = 0; i < priv->num_gphy_fw; i++) @@ -2169,6 +2176,7 @@ static int gswip_remove(struct platform_device *pdev) if (priv->ds->slave_mii_bus) { mdiobus_unregister(priv->ds->slave_mii_bus); + mdiobus_free(priv->ds->slave_mii_bus); of_node_put(priv->ds->slave_mii_bus->dev.of_node); } diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index bc77a26c825a..f74f25f479ed 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -2074,7 +2074,7 @@ mt7530_setup_mdio(struct mt7530_priv *priv) if (priv->irq) mt7530_setup_mdio_irq(priv); - ret = mdiobus_register(bus); + ret = devm_mdiobus_register(dev, bus); if (ret) { dev_err(dev, "failed to register MDIO bus: %d\n", ret); if (priv->irq) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index c54649c4c3a0..5344d0c0647e 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3566,7 +3566,7 @@ static int mv88e6xxx_mdio_register(struct mv88e6xxx_chip *chip, return err; } - bus = devm_mdiobus_alloc_size(chip->dev, sizeof(*mdio_bus)); + bus = mdiobus_alloc_size(sizeof(*mdio_bus)); if (!bus) return -ENOMEM; @@ -3591,14 +3591,14 @@ static int mv88e6xxx_mdio_register(struct mv88e6xxx_chip *chip, if (!external) { err = mv88e6xxx_g2_irq_mdio_setup(chip, bus); if (err) - return err; + goto out; } err = of_mdiobus_register(bus, np); if (err) { dev_err(chip->dev, "Cannot register MDIO bus (%d)\n", err); mv88e6xxx_g2_irq_mdio_free(chip, bus); - return err; + goto out; } if (external) @@ -3607,21 +3607,26 @@ static int mv88e6xxx_mdio_register(struct mv88e6xxx_chip *chip, list_add(&mdio_bus->list, &chip->mdios); return 0; + +out: + mdiobus_free(bus); + return err; } static void mv88e6xxx_mdios_unregister(struct mv88e6xxx_chip *chip) { - struct mv88e6xxx_mdio_bus *mdio_bus; + struct mv88e6xxx_mdio_bus *mdio_bus, *p; struct mii_bus *bus; - list_for_each_entry(mdio_bus, &chip->mdios, list) { + list_for_each_entry_safe(mdio_bus, p, &chip->mdios, list) { bus = mdio_bus->bus; if (!mdio_bus->external) mv88e6xxx_g2_irq_mdio_free(chip, bus); mdiobus_unregister(bus); + mdiobus_free(bus); } } diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index bf8d38239e7e..33f0ceae381d 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1061,7 +1061,7 @@ static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot) return PTR_ERR(hw); } - bus = devm_mdiobus_alloc_size(dev, sizeof(*mdio_priv)); + bus = mdiobus_alloc_size(sizeof(*mdio_priv)); if (!bus) return -ENOMEM; @@ -1081,6 +1081,7 @@ static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot) rc = mdiobus_register(bus); if (rc < 0) { dev_err(dev, "failed to register MDIO bus\n"); + mdiobus_free(bus); return rc; } @@ -1132,6 +1133,7 @@ static void vsc9959_mdio_bus_free(struct ocelot *ocelot) lynx_pcs_destroy(phylink_pcs); } mdiobus_unregister(felix->imdio); + mdiobus_free(felix->imdio); } static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port, diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c index 8c1c9da61602..f2f1608a476c 100644 --- a/drivers/net/dsa/ocelot/seville_vsc9953.c +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -1029,7 +1029,7 @@ static int vsc9953_mdio_bus_alloc(struct ocelot *ocelot) } /* Needed in order to initialize the bus mutex lock */ - rc = of_mdiobus_register(bus, NULL); + rc = devm_of_mdiobus_register(dev, bus, NULL); if (rc < 0) { dev_err(dev, "failed to register MDIO bus\n"); return rc; @@ -1083,7 +1083,8 @@ static void vsc9953_mdio_bus_free(struct ocelot *ocelot) mdio_device_free(mdio_device); lynx_pcs_destroy(phylink_pcs); } - mdiobus_unregister(felix->imdio); + + /* mdiobus_unregister and mdiobus_free handled by devres */ } static const struct felix_info seville_info_vsc9953 = { diff --git a/drivers/net/dsa/qca/ar9331.c b/drivers/net/dsa/qca/ar9331.c index 3bda7015f0c1..e5098cfe44bc 100644 --- a/drivers/net/dsa/qca/ar9331.c +++ b/drivers/net/dsa/qca/ar9331.c @@ -378,7 +378,7 @@ static int ar9331_sw_mbus_init(struct ar9331_sw_priv *priv) if (!mnp) return -ENODEV; - ret = of_mdiobus_register(mbus, mnp); + ret = devm_of_mdiobus_register(dev, mbus, mnp); of_node_put(mnp); if (ret) return ret; @@ -1066,7 +1066,6 @@ static void ar9331_sw_remove(struct mdio_device *mdiodev) } irq_domain_remove(priv->irqdomain); - mdiobus_unregister(priv->mbus); dsa_unregister_switch(&priv->ds); reset_control_assert(priv->sw_reset); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c index efdcf484a510..2af3da4b2d05 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c @@ -425,6 +425,9 @@ static void xgbe_pci_remove(struct pci_dev *pdev) pci_free_irq_vectors(pdata->pcidev); + /* Disable all interrupts in the hardware */ + XP_IOWRITE(pdata, XP_INT_EN, 0x0); + xgbe_free_pdata(pdata); } diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 1ce20bf52f72..4c231159b562 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -4765,7 +4765,7 @@ static int macb_probe(struct platform_device *pdev) #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT if (GEM_BFEXT(DAW64, gem_readl(bp, DCFG6))) { - dma_set_mask(&pdev->dev, DMA_BIT_MASK(44)); + dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(44)); bp->hw_dma_cap |= HW_DMA_CAP_64B; } #endif diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 88534aa29af2..c4a48e6f1758 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -4733,12 +4733,12 @@ static int dpaa2_eth_remove(struct fsl_mc_device *ls_dev) #ifdef CONFIG_DEBUG_FS dpaa2_dbg_remove(priv); #endif + + unregister_netdev(net_dev); rtnl_lock(); dpaa2_eth_disconnect_mac(priv); rtnl_unlock(); - unregister_netdev(net_dev); - dpaa2_eth_dl_port_del(priv); dpaa2_eth_dl_traps_unregister(priv); dpaa2_eth_dl_free(priv); diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index 2068199445bd..e4e98aa7745f 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -609,6 +609,7 @@ static bool gve_rx(struct gve_rx_ring *rx, netdev_features_t feat, *packet_size_bytes = skb->len + (skb->protocol ? ETH_HLEN : 0); *work_done = work_cnt; + skb_record_rx_queue(skb, rx->q_num); if (skb_is_nonlinear(skb)) napi_gro_frags(napi); else diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index bda7a2a9d211..29617a86b299 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -110,6 +110,7 @@ static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter, struct ibmvnic_sub_crq_queue *tx_scrq); static void free_long_term_buff(struct ibmvnic_adapter *adapter, struct ibmvnic_long_term_buff *ltb); +static void ibmvnic_disable_irqs(struct ibmvnic_adapter *adapter); struct ibmvnic_stat { char name[ETH_GSTRING_LEN]; @@ -1424,7 +1425,7 @@ static int __ibmvnic_open(struct net_device *netdev) rc = set_link_state(adapter, IBMVNIC_LOGICAL_LNK_UP); if (rc) { ibmvnic_napi_disable(adapter); - release_resources(adapter); + ibmvnic_disable_irqs(adapter); return rc; } @@ -1474,9 +1475,6 @@ static int ibmvnic_open(struct net_device *netdev) rc = init_resources(adapter); if (rc) { netdev_err(netdev, "failed to initialize resources\n"); - release_resources(adapter); - release_rx_pools(adapter); - release_tx_pools(adapter); goto out; } } @@ -1493,6 +1491,13 @@ out: adapter->state = VNIC_OPEN; rc = 0; } + + if (rc) { + release_resources(adapter); + release_rx_pools(adapter); + release_tx_pools(adapter); + } + return rc; } diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 6a710c209707..827fcb5e0d4c 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -487,6 +487,7 @@ enum ice_pf_flags { ICE_FLAG_MDD_AUTO_RESET_VF, ICE_FLAG_VF_VLAN_PRUNING, ICE_FLAG_LINK_LENIENT_MODE_ENA, + ICE_FLAG_PLUG_AUX_DEV, ICE_PF_FLAGS_NBITS /* must be last */ }; @@ -891,7 +892,7 @@ static inline void ice_set_rdma_cap(struct ice_pf *pf) if (pf->hw.func_caps.common_cap.rdma && pf->num_rdma_msix) { set_bit(ICE_FLAG_RDMA_ENA, pf->flags); set_bit(ICE_FLAG_AUX_ENA, pf->flags); - ice_plug_aux_dev(pf); + set_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags); } } diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 464ecb7b54cb..c57e5fc41cf8 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -3381,7 +3381,8 @@ ice_cfg_phy_fec(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, !ice_fw_supports_report_dflt_cfg(hw)) { struct ice_link_default_override_tlv tlv; - if (ice_get_link_default_override(&tlv, pi)) + status = ice_get_link_default_override(&tlv, pi); + if (status) goto out; if (!(tlv.options & ICE_LINK_OVERRIDE_STRICT_MODE) && diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index e375ac849aec..4f954db01b92 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -204,11 +204,7 @@ ice_lag_unlink(struct ice_lag *lag, lag->upper_netdev = NULL; } - if (lag->peer_netdev) { - dev_put(lag->peer_netdev); - lag->peer_netdev = NULL; - } - + lag->peer_netdev = NULL; ice_set_sriov_cap(pf); ice_set_rdma_cap(pf); lag->bonded = false; @@ -216,6 +212,32 @@ ice_lag_unlink(struct ice_lag *lag, } /** + * ice_lag_unregister - handle netdev unregister events + * @lag: LAG info struct + * @netdev: netdev reporting the event + */ +static void ice_lag_unregister(struct ice_lag *lag, struct net_device *netdev) +{ + struct ice_pf *pf = lag->pf; + + /* check to see if this event is for this netdev + * check that we are in an aggregate + */ + if (netdev != lag->netdev || !lag->bonded) + return; + + if (lag->upper_netdev) { + dev_put(lag->upper_netdev); + lag->upper_netdev = NULL; + ice_set_sriov_cap(pf); + ice_set_rdma_cap(pf); + } + /* perform some cleanup in case we come back */ + lag->bonded = false; + lag->role = ICE_LAG_NONE; +} + +/** * ice_lag_changeupper_event - handle LAG changeupper event * @lag: LAG info struct * @ptr: opaque pointer data @@ -307,7 +329,7 @@ ice_lag_event_handler(struct notifier_block *notif_blk, unsigned long event, ice_lag_info_event(lag, ptr); break; case NETDEV_UNREGISTER: - ice_lag_unlink(lag, ptr); + ice_lag_unregister(lag, netdev); break; default: break; diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index a1fc676a4665..b3baf7c3f910 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -570,6 +570,7 @@ struct ice_tx_ctx_desc { (0x3FFFFULL << ICE_TXD_CTX_QW1_TSO_LEN_S) #define ICE_TXD_CTX_QW1_MSS_S 50 +#define ICE_TXD_CTX_MIN_MSS 64 #define ICE_TXD_CTX_QW1_VSI_S 50 #define ICE_TXD_CTX_QW1_VSI_M (0x3FFULL << ICE_TXD_CTX_QW1_VSI_S) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index ec7065976b0c..ce90ebf4b853 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2256,6 +2256,9 @@ static void ice_service_task(struct work_struct *work) return; } + if (test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) + ice_plug_aux_dev(pf); + ice_clean_adminq_subtask(pf); ice_check_media_subtask(pf); ice_check_for_hang_subtask(pf); @@ -8724,6 +8727,7 @@ ice_features_check(struct sk_buff *skb, struct net_device __always_unused *netdev, netdev_features_t features) { + bool gso = skb_is_gso(skb); size_t len; /* No point in doing any of this if neither checksum nor GSO are @@ -8736,24 +8740,32 @@ ice_features_check(struct sk_buff *skb, /* We cannot support GSO if the MSS is going to be less than * 64 bytes. If it is then we need to drop support for GSO. */ - if (skb_is_gso(skb) && (skb_shinfo(skb)->gso_size < 64)) + if (gso && (skb_shinfo(skb)->gso_size < ICE_TXD_CTX_MIN_MSS)) features &= ~NETIF_F_GSO_MASK; - len = skb_network_header(skb) - skb->data; + len = skb_network_offset(skb); if (len > ICE_TXD_MACLEN_MAX || len & 0x1) goto out_rm_features; - len = skb_transport_header(skb) - skb_network_header(skb); + len = skb_network_header_len(skb); if (len > ICE_TXD_IPLEN_MAX || len & 0x1) goto out_rm_features; if (skb->encapsulation) { - len = skb_inner_network_header(skb) - skb_transport_header(skb); - if (len > ICE_TXD_L4LEN_MAX || len & 0x1) - goto out_rm_features; + /* this must work for VXLAN frames AND IPIP/SIT frames, and in + * the case of IPIP frames, the transport header pointer is + * after the inner header! So check to make sure that this + * is a GRE or UDP_TUNNEL frame before doing that math. + */ + if (gso && (skb_shinfo(skb)->gso_type & + (SKB_GSO_GRE | SKB_GSO_UDP_TUNNEL))) { + len = skb_inner_network_header(skb) - + skb_transport_header(skb); + if (len > ICE_TXD_L4LEN_MAX || len & 0x1) + goto out_rm_features; + } - len = skb_inner_transport_header(skb) - - skb_inner_network_header(skb); + len = skb_inner_network_header_len(skb); if (len > ICE_TXD_IPLEN_MAX || len & 0x1) goto out_rm_features; } diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 7c33be9074e9..17fbc450da61 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1984,14 +1984,15 @@ static void ixgbevf_set_rx_buffer_len(struct ixgbevf_adapter *adapter, if (adapter->flags & IXGBEVF_FLAGS_LEGACY_RX) return; - set_ring_build_skb_enabled(rx_ring); + if (PAGE_SIZE < 8192) + if (max_frame > IXGBEVF_MAX_FRAME_BUILD_SKB) + set_ring_uses_large_buffer(rx_ring); - if (PAGE_SIZE < 8192) { - if (max_frame <= IXGBEVF_MAX_FRAME_BUILD_SKB) - return; + /* 82599 can't rely on RXDCTL.RLPML to restrict the size of the frame */ + if (adapter->hw.mac.type == ixgbe_mac_82599_vf && !ring_uses_large_buffer(rx_ring)) + return; - set_ring_uses_large_buffer(rx_ring); - } + set_ring_build_skb_enabled(rx_ring); } /** diff --git a/drivers/net/ethernet/litex/Kconfig b/drivers/net/ethernet/litex/Kconfig index f99adbf26ab4..04345b929d8e 100644 --- a/drivers/net/ethernet/litex/Kconfig +++ b/drivers/net/ethernet/litex/Kconfig @@ -17,7 +17,7 @@ if NET_VENDOR_LITEX config LITEX_LITEETH tristate "LiteX Ethernet support" - depends on OF + depends on OF && HAS_IOMEM help If you wish to compile a kernel for hardware with a LiteX LiteEth device then you should answer Y to this. diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_ethtool.c b/drivers/net/ethernet/microchip/sparx5/sparx5_ethtool.c index 59783fc46a7b..10b866e9f726 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_ethtool.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_ethtool.c @@ -1103,7 +1103,7 @@ void sparx5_get_stats64(struct net_device *ndev, stats->tx_carrier_errors = portstats[spx5_stats_tx_csense_cnt]; stats->tx_window_errors = portstats[spx5_stats_tx_late_coll_cnt]; stats->rx_dropped = portstats[spx5_stats_ana_ac_port_stat_lsb_cnt]; - for (idx = 0; idx < 2 * SPX5_PRIOS; ++idx, ++stats) + for (idx = 0; idx < 2 * SPX5_PRIOS; ++idx) stats->rx_dropped += portstats[spx5_stats_green_p0_rx_port_drop + idx]; stats->tx_dropped = portstats[spx5_stats_tx_local_drop]; diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 455293aa6343..e6de86552df0 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1432,6 +1432,8 @@ static void ocelot_populate_ipv4_ptp_event_trap_key(struct ocelot_vcap_filter *trap) { trap->key_type = OCELOT_VCAP_KEY_IPV4; + trap->key.ipv4.proto.value[0] = IPPROTO_UDP; + trap->key.ipv4.proto.mask[0] = 0xff; trap->key.ipv4.dport.value = PTP_EV_PORT; trap->key.ipv4.dport.mask = 0xffff; } @@ -1440,6 +1442,8 @@ static void ocelot_populate_ipv6_ptp_event_trap_key(struct ocelot_vcap_filter *trap) { trap->key_type = OCELOT_VCAP_KEY_IPV6; + trap->key.ipv4.proto.value[0] = IPPROTO_UDP; + trap->key.ipv4.proto.mask[0] = 0xff; trap->key.ipv6.dport.value = PTP_EV_PORT; trap->key.ipv6.dport.mask = 0xffff; } @@ -1448,6 +1452,8 @@ static void ocelot_populate_ipv4_ptp_general_trap_key(struct ocelot_vcap_filter *trap) { trap->key_type = OCELOT_VCAP_KEY_IPV4; + trap->key.ipv4.proto.value[0] = IPPROTO_UDP; + trap->key.ipv4.proto.mask[0] = 0xff; trap->key.ipv4.dport.value = PTP_GEN_PORT; trap->key.ipv4.dport.mask = 0xffff; } @@ -1456,6 +1462,8 @@ static void ocelot_populate_ipv6_ptp_general_trap_key(struct ocelot_vcap_filter *trap) { trap->key_type = OCELOT_VCAP_KEY_IPV6; + trap->key.ipv4.proto.value[0] = IPPROTO_UDP; + trap->key.ipv4.proto.mask[0] = 0xff; trap->key.ipv6.dport.value = PTP_GEN_PORT; trap->key.ipv6.dport.mask = 0xffff; } @@ -1737,12 +1745,11 @@ void ocelot_get_strings(struct ocelot *ocelot, int port, u32 sset, u8 *data) } EXPORT_SYMBOL(ocelot_get_strings); +/* Caller must hold &ocelot->stats_lock */ static void ocelot_update_stats(struct ocelot *ocelot) { int i, j; - mutex_lock(&ocelot->stats_lock); - for (i = 0; i < ocelot->num_phys_ports; i++) { /* Configure the port to read the stats from */ ocelot_write(ocelot, SYS_STAT_CFG_STAT_VIEW(i), SYS_STAT_CFG); @@ -1761,8 +1768,6 @@ static void ocelot_update_stats(struct ocelot *ocelot) ~(u64)U32_MAX) + val; } } - - mutex_unlock(&ocelot->stats_lock); } static void ocelot_check_stats_work(struct work_struct *work) @@ -1771,7 +1776,9 @@ static void ocelot_check_stats_work(struct work_struct *work) struct ocelot *ocelot = container_of(del_work, struct ocelot, stats_work); + mutex_lock(&ocelot->stats_lock); ocelot_update_stats(ocelot); + mutex_unlock(&ocelot->stats_lock); queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work, OCELOT_STATS_CHECK_DELAY); @@ -1781,12 +1788,16 @@ void ocelot_get_ethtool_stats(struct ocelot *ocelot, int port, u64 *data) { int i; + mutex_lock(&ocelot->stats_lock); + /* check and update now */ ocelot_update_stats(ocelot); /* Copy all counters */ for (i = 0; i < ocelot->num_stats; i++) *data++ = ocelot->stats[port * ocelot->num_stats + i]; + + mutex_unlock(&ocelot->stats_lock); } EXPORT_SYMBOL(ocelot_get_ethtool_stats); diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index ce865e619568..cd50db779dda 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -1011,6 +1011,7 @@ nfp_tunnel_del_shared_mac(struct nfp_app *app, struct net_device *netdev, struct nfp_flower_repr_priv *repr_priv; struct nfp_tun_offloaded_mac *entry; struct nfp_repr *repr; + u16 nfp_mac_idx; int ida_idx; entry = nfp_tunnel_lookup_offloaded_macs(app, mac); @@ -1029,8 +1030,6 @@ nfp_tunnel_del_shared_mac(struct nfp_app *app, struct net_device *netdev, entry->bridge_count--; if (!entry->bridge_count && entry->ref_count) { - u16 nfp_mac_idx; - nfp_mac_idx = entry->index & ~NFP_TUN_PRE_TUN_IDX_BIT; if (__nfp_tunnel_offload_mac(app, mac, nfp_mac_idx, false)) { @@ -1046,7 +1045,6 @@ nfp_tunnel_del_shared_mac(struct nfp_app *app, struct net_device *netdev, /* If MAC is now used by 1 repr set the offloaded MAC index to port. */ if (entry->ref_count == 1 && list_is_singular(&entry->repr_list)) { - u16 nfp_mac_idx; int port, err; repr_priv = list_first_entry(&entry->repr_list, @@ -1074,8 +1072,14 @@ nfp_tunnel_del_shared_mac(struct nfp_app *app, struct net_device *netdev, WARN_ON_ONCE(rhashtable_remove_fast(&priv->tun.offloaded_macs, &entry->ht_node, offloaded_macs_params)); + + if (nfp_flower_is_supported_bridge(netdev)) + nfp_mac_idx = entry->index & ~NFP_TUN_PRE_TUN_IDX_BIT; + else + nfp_mac_idx = entry->index; + /* If MAC has global ID then extract and free the ida entry. */ - if (nfp_tunnel_is_mac_idx_global(entry->index)) { + if (nfp_tunnel_is_mac_idx_global(nfp_mac_idx)) { ida_idx = nfp_tunnel_get_ida_from_global_mac_idx(entry->index); ida_simple_remove(&priv->tun.mac_off_ids, ida_idx); } diff --git a/drivers/net/mdio/mdio-aspeed.c b/drivers/net/mdio/mdio-aspeed.c index 966c3b4ad59d..e2273588c75b 100644 --- a/drivers/net/mdio/mdio-aspeed.c +++ b/drivers/net/mdio/mdio-aspeed.c @@ -148,6 +148,7 @@ static const struct of_device_id aspeed_mdio_of_match[] = { { .compatible = "aspeed,ast2600-mdio", }, { }, }; +MODULE_DEVICE_TABLE(of, aspeed_mdio_of_match); static struct platform_driver aspeed_mdio_driver = { .driver = { diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index fa71fb7a66b5..2429db614b59 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -553,9 +553,9 @@ static int m88e1121_config_aneg_rgmii_delays(struct phy_device *phydev) else mscr = 0; - return phy_modify_paged(phydev, MII_MARVELL_MSCR_PAGE, - MII_88E1121_PHY_MSCR_REG, - MII_88E1121_PHY_MSCR_DELAY_MASK, mscr); + return phy_modify_paged_changed(phydev, MII_MARVELL_MSCR_PAGE, + MII_88E1121_PHY_MSCR_REG, + MII_88E1121_PHY_MSCR_DELAY_MASK, mscr); } static int m88e1121_config_aneg(struct phy_device *phydev) @@ -569,11 +569,13 @@ static int m88e1121_config_aneg(struct phy_device *phydev) return err; } + changed = err; + err = marvell_set_polarity(phydev, phydev->mdix_ctrl); if (err < 0) return err; - changed = err; + changed |= err; err = genphy_config_aneg(phydev); if (err < 0) @@ -1213,16 +1215,15 @@ static int m88e1118_config_aneg(struct phy_device *phydev) { int err; - err = genphy_soft_reset(phydev); + err = marvell_set_polarity(phydev, phydev->mdix_ctrl); if (err < 0) return err; - err = marvell_set_polarity(phydev, phydev->mdix_ctrl); + err = genphy_config_aneg(phydev); if (err < 0) return err; - err = genphy_config_aneg(phydev); - return 0; + return genphy_soft_reset(phydev); } static int m88e1118_config_init(struct phy_device *phydev) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 37e5f3495362..3353e761016d 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1400,6 +1400,8 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81d7, 0)}, /* Dell Wireless 5821e */ {QMI_FIXED_INTF(0x413c, 0x81d7, 1)}, /* Dell Wireless 5821e preproduction config */ {QMI_FIXED_INTF(0x413c, 0x81e0, 0)}, /* Dell Wireless 5821e with eSIM support*/ + {QMI_FIXED_INTF(0x413c, 0x81e4, 0)}, /* Dell Wireless 5829e with eSIM support*/ + {QMI_FIXED_INTF(0x413c, 0x81e6, 0)}, /* Dell Wireless 5829e */ {QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */ {QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)}, /* HP lt4120 Snapdragon X5 LTE */ {QMI_QUIRK_SET_DTR(0x22de, 0x9051, 2)}, /* Hucom Wireless HM-211S/K */ diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 354a963075c5..d29fb9759cc9 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -265,9 +265,10 @@ static void __veth_xdp_flush(struct veth_rq *rq) { /* Write ptr_ring before reading rx_notify_masked */ smp_mb(); - if (!rq->rx_notify_masked) { - rq->rx_notify_masked = true; - napi_schedule(&rq->xdp_napi); + if (!READ_ONCE(rq->rx_notify_masked) && + napi_schedule_prep(&rq->xdp_napi)) { + WRITE_ONCE(rq->rx_notify_masked, true); + __napi_schedule(&rq->xdp_napi); } } @@ -912,8 +913,10 @@ static int veth_poll(struct napi_struct *napi, int budget) /* Write rx_notify_masked before reading ptr_ring */ smp_store_mb(rq->rx_notify_masked, false); if (unlikely(!__ptr_ring_empty(&rq->xdp_ring))) { - rq->rx_notify_masked = true; - napi_schedule(&rq->xdp_napi); + if (napi_schedule_prep(&rq->xdp_napi)) { + WRITE_ONCE(rq->rx_notify_masked, true); + __napi_schedule(&rq->xdp_napi); + } } } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 5e0bfda04bd7..961a5f8a44d2 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4253,7 +4253,14 @@ static void nvme_async_event_work(struct work_struct *work) container_of(work, struct nvme_ctrl, async_event_work); nvme_aen_uevent(ctrl); - ctrl->ops->submit_async_event(ctrl); + + /* + * The transport drivers must guarantee AER submission here is safe by + * flushing ctrl async_event_work after changing the controller state + * from LIVE and before freeing the admin queue. + */ + if (ctrl->state == NVME_CTRL_LIVE) + ctrl->ops->submit_async_event(ctrl); } static bool nvme_ctrl_pp_status(struct nvme_ctrl *ctrl) diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index c3203ff1c654..1e3a09cad961 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -170,6 +170,7 @@ nvmf_ctlr_matches_baseopts(struct nvme_ctrl *ctrl, struct nvmf_ctrl_options *opts) { if (ctrl->state == NVME_CTRL_DELETING || + ctrl->state == NVME_CTRL_DELETING_NOIO || ctrl->state == NVME_CTRL_DEAD || strcmp(opts->subsysnqn, ctrl->opts->subsysnqn) || strcmp(opts->host->nqn, ctrl->opts->host->nqn) || diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 850f84d204d0..9c55e4be8a39 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1200,6 +1200,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work) struct nvme_rdma_ctrl, err_work); nvme_stop_keep_alive(&ctrl->ctrl); + flush_work(&ctrl->ctrl.async_event_work); nvme_rdma_teardown_io_queues(ctrl, false); nvme_start_queues(&ctrl->ctrl); nvme_rdma_teardown_admin_queue(ctrl, false); diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 4ceb28675fdf..01e24b5703db 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -2096,6 +2096,7 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work) struct nvme_ctrl *ctrl = &tcp_ctrl->ctrl; nvme_stop_keep_alive(ctrl); + flush_work(&ctrl->async_event_work); nvme_tcp_teardown_io_queues(ctrl, false); /* unquiesce to fail fast pending requests */ nvme_start_queues(ctrl); diff --git a/drivers/pci/controller/cadence/pci-j721e.c b/drivers/pci/controller/cadence/pci-j721e.c index 489586a4cdc7..768d33f9ebc8 100644 --- a/drivers/pci/controller/cadence/pci-j721e.c +++ b/drivers/pci/controller/cadence/pci-j721e.c @@ -356,8 +356,8 @@ static int j721e_pcie_probe(struct platform_device *pdev) const struct j721e_pcie_data *data; struct cdns_pcie *cdns_pcie; struct j721e_pcie *pcie; - struct cdns_pcie_rc *rc; - struct cdns_pcie_ep *ep; + struct cdns_pcie_rc *rc = NULL; + struct cdns_pcie_ep *ep = NULL; struct gpio_desc *gpiod; void __iomem *base; struct clk *clk; @@ -376,6 +376,46 @@ static int j721e_pcie_probe(struct platform_device *pdev) if (!pcie) return -ENOMEM; + switch (mode) { + case PCI_MODE_RC: + if (!IS_ENABLED(CONFIG_PCIE_CADENCE_HOST)) + return -ENODEV; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*rc)); + if (!bridge) + return -ENOMEM; + + if (!data->byte_access_allowed) + bridge->ops = &cdns_ti_pcie_host_ops; + rc = pci_host_bridge_priv(bridge); + rc->quirk_retrain_flag = data->quirk_retrain_flag; + rc->quirk_detect_quiet_flag = data->quirk_detect_quiet_flag; + + cdns_pcie = &rc->pcie; + cdns_pcie->dev = dev; + cdns_pcie->ops = &j721e_pcie_ops; + pcie->cdns_pcie = cdns_pcie; + break; + case PCI_MODE_EP: + if (!IS_ENABLED(CONFIG_PCIE_CADENCE_EP)) + return -ENODEV; + + ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL); + if (!ep) + return -ENOMEM; + + ep->quirk_detect_quiet_flag = data->quirk_detect_quiet_flag; + + cdns_pcie = &ep->pcie; + cdns_pcie->dev = dev; + cdns_pcie->ops = &j721e_pcie_ops; + pcie->cdns_pcie = cdns_pcie; + break; + default: + dev_err(dev, "INVALID device type %d\n", mode); + return 0; + } + pcie->mode = mode; pcie->linkdown_irq_regfield = data->linkdown_irq_regfield; @@ -426,28 +466,6 @@ static int j721e_pcie_probe(struct platform_device *pdev) switch (mode) { case PCI_MODE_RC: - if (!IS_ENABLED(CONFIG_PCIE_CADENCE_HOST)) { - ret = -ENODEV; - goto err_get_sync; - } - - bridge = devm_pci_alloc_host_bridge(dev, sizeof(*rc)); - if (!bridge) { - ret = -ENOMEM; - goto err_get_sync; - } - - if (!data->byte_access_allowed) - bridge->ops = &cdns_ti_pcie_host_ops; - rc = pci_host_bridge_priv(bridge); - rc->quirk_retrain_flag = data->quirk_retrain_flag; - rc->quirk_detect_quiet_flag = data->quirk_detect_quiet_flag; - - cdns_pcie = &rc->pcie; - cdns_pcie->dev = dev; - cdns_pcie->ops = &j721e_pcie_ops; - pcie->cdns_pcie = cdns_pcie; - gpiod = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW); if (IS_ERR(gpiod)) { ret = PTR_ERR(gpiod); @@ -497,23 +515,6 @@ static int j721e_pcie_probe(struct platform_device *pdev) break; case PCI_MODE_EP: - if (!IS_ENABLED(CONFIG_PCIE_CADENCE_EP)) { - ret = -ENODEV; - goto err_get_sync; - } - - ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL); - if (!ep) { - ret = -ENOMEM; - goto err_get_sync; - } - ep->quirk_detect_quiet_flag = data->quirk_detect_quiet_flag; - - cdns_pcie = &ep->pcie; - cdns_pcie->dev = dev; - cdns_pcie->ops = &j721e_pcie_ops; - pcie->cdns_pcie = cdns_pcie; - ret = cdns_pcie_init_phy(dev, cdns_pcie); if (ret) { dev_err(dev, "Failed to init phy\n"); @@ -525,8 +526,6 @@ static int j721e_pcie_probe(struct platform_device *pdev) goto err_pcie_setup; break; - default: - dev_err(dev, "INVALID device type %d\n", mode); } return 0; diff --git a/drivers/pci/controller/dwc/pcie-kirin.c b/drivers/pci/controller/dwc/pcie-kirin.c index fa6886d66488..c625fc6bb287 100644 --- a/drivers/pci/controller/dwc/pcie-kirin.c +++ b/drivers/pci/controller/dwc/pcie-kirin.c @@ -756,22 +756,28 @@ static int __exit kirin_pcie_remove(struct platform_device *pdev) return 0; } +struct kirin_pcie_data { + enum pcie_kirin_phy_type phy_type; +}; + +static const struct kirin_pcie_data kirin_960_data = { + .phy_type = PCIE_KIRIN_INTERNAL_PHY, +}; + +static const struct kirin_pcie_data kirin_970_data = { + .phy_type = PCIE_KIRIN_EXTERNAL_PHY, +}; + static const struct of_device_id kirin_pcie_match[] = { - { - .compatible = "hisilicon,kirin960-pcie", - .data = (void *)PCIE_KIRIN_INTERNAL_PHY - }, - { - .compatible = "hisilicon,kirin970-pcie", - .data = (void *)PCIE_KIRIN_EXTERNAL_PHY - }, + { .compatible = "hisilicon,kirin960-pcie", .data = &kirin_960_data }, + { .compatible = "hisilicon,kirin970-pcie", .data = &kirin_970_data }, {}, }; static int kirin_pcie_probe(struct platform_device *pdev) { - enum pcie_kirin_phy_type phy_type; struct device *dev = &pdev->dev; + const struct kirin_pcie_data *data; struct kirin_pcie *kirin_pcie; struct dw_pcie *pci; int ret; @@ -781,13 +787,12 @@ static int kirin_pcie_probe(struct platform_device *pdev) return -EINVAL; } - phy_type = (long)of_device_get_match_data(dev); - if (!phy_type) { + data = of_device_get_match_data(dev); + if (!data) { dev_err(dev, "OF data missing\n"); return -EINVAL; } - kirin_pcie = devm_kzalloc(dev, sizeof(struct kirin_pcie), GFP_KERNEL); if (!kirin_pcie) return -ENOMEM; @@ -800,7 +805,7 @@ static int kirin_pcie_probe(struct platform_device *pdev) pci->ops = &kirin_dw_pcie_ops; pci->pp.ops = &kirin_pcie_host_ops; kirin_pcie->pci = pci; - kirin_pcie->type = phy_type; + kirin_pcie->type = data->phy_type; ret = kirin_pcie_get_resource(kirin_pcie, pdev); if (ret) diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index c19c7ca58186..9037a7827eca 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -1111,7 +1111,8 @@ const struct cpumask *pci_irq_get_affinity(struct pci_dev *dev, int nr) if (!desc) return cpu_possible_mask; - if (WARN_ON_ONCE(!desc->affinity)) + /* MSI[X] interrupts can be allocated without affinity descriptor */ + if (!desc->affinity) return NULL; /* diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c index 9be273c320e2..a826456c6075 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c +++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c @@ -508,7 +508,8 @@ static int bnx2fc_l2_rcv_thread(void *arg) static void bnx2fc_recv_frame(struct sk_buff *skb) { - u32 fr_len; + u64 crc_err; + u32 fr_len, fr_crc; struct fc_lport *lport; struct fcoe_rcv_info *fr; struct fc_stats *stats; @@ -542,6 +543,11 @@ static void bnx2fc_recv_frame(struct sk_buff *skb) skb_pull(skb, sizeof(struct fcoe_hdr)); fr_len = skb->len - sizeof(struct fcoe_crc_eof); + stats = per_cpu_ptr(lport->stats, get_cpu()); + stats->RxFrames++; + stats->RxWords += fr_len / FCOE_WORD_TO_BYTE; + put_cpu(); + fp = (struct fc_frame *)skb; fc_frame_init(fp); fr_dev(fp) = lport; @@ -624,16 +630,15 @@ static void bnx2fc_recv_frame(struct sk_buff *skb) return; } - stats = per_cpu_ptr(lport->stats, smp_processor_id()); - stats->RxFrames++; - stats->RxWords += fr_len / FCOE_WORD_TO_BYTE; + fr_crc = le32_to_cpu(fr_crc(fp)); - if (le32_to_cpu(fr_crc(fp)) != - ~crc32(~0, skb->data, fr_len)) { - if (stats->InvalidCRCCount < 5) + if (unlikely(fr_crc != ~crc32(~0, skb->data, fr_len))) { + stats = per_cpu_ptr(lport->stats, get_cpu()); + crc_err = (stats->InvalidCRCCount++); + put_cpu(); + if (crc_err < 5) printk(KERN_WARNING PFX "dropping frame with " "CRC error\n"); - stats->InvalidCRCCount++; kfree_skb(skb); return; } diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index 2f53a2ee024a..ebf5ec38891b 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -400,8 +400,7 @@ void hisi_sas_task_deliver(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot, struct hisi_sas_dq *dq, struct hisi_sas_device *sas_dev, - struct hisi_sas_internal_abort *abort, - struct hisi_sas_tmf_task *tmf) + struct hisi_sas_internal_abort *abort) { struct hisi_sas_cmd_hdr *cmd_hdr_base; int dlvry_queue_slot, dlvry_queue; @@ -427,8 +426,6 @@ void hisi_sas_task_deliver(struct hisi_hba *hisi_hba, cmd_hdr_base = hisi_hba->cmd_hdr[dlvry_queue]; slot->cmd_hdr = &cmd_hdr_base[dlvry_queue_slot]; - slot->tmf = tmf; - slot->is_internal = tmf; task->lldd_task = slot; memset(slot->cmd_hdr, 0, sizeof(struct hisi_sas_cmd_hdr)); @@ -587,7 +584,7 @@ static int hisi_sas_task_exec(struct sas_task *task, gfp_t gfp_flags, slot->is_internal = tmf; /* protect task_prep and start_delivery sequence */ - hisi_sas_task_deliver(hisi_hba, slot, dq, sas_dev, NULL, tmf); + hisi_sas_task_deliver(hisi_hba, slot, dq, sas_dev, NULL); return 0; @@ -1380,12 +1377,13 @@ static int hisi_sas_softreset_ata_disk(struct domain_device *device) struct hisi_hba *hisi_hba = dev_to_hisi_hba(device); struct device *dev = hisi_hba->dev; int s = sizeof(struct host_to_dev_fis); + struct hisi_sas_tmf_task tmf = {}; ata_for_each_link(link, ap, EDGE) { int pmp = sata_srst_pmp(link); hisi_sas_fill_ata_reset_cmd(link->device, 1, pmp, fis); - rc = hisi_sas_exec_internal_tmf_task(device, fis, s, NULL); + rc = hisi_sas_exec_internal_tmf_task(device, fis, s, &tmf); if (rc != TMF_RESP_FUNC_COMPLETE) break; } @@ -1396,7 +1394,7 @@ static int hisi_sas_softreset_ata_disk(struct domain_device *device) hisi_sas_fill_ata_reset_cmd(link->device, 0, pmp, fis); rc = hisi_sas_exec_internal_tmf_task(device, fis, - s, NULL); + s, &tmf); if (rc != TMF_RESP_FUNC_COMPLETE) dev_err(dev, "ata disk %016llx de-reset failed\n", SAS_ADDR(device->sas_addr)); @@ -2067,7 +2065,7 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, int device_id, slot->port = port; slot->is_internal = true; - hisi_sas_task_deliver(hisi_hba, slot, dq, sas_dev, abort, NULL); + hisi_sas_task_deliver(hisi_hba, slot, dq, sas_dev, abort); return 0; diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c index c814e5071712..9ec310b795c3 100644 --- a/drivers/scsi/pm8001/pm8001_hwi.c +++ b/drivers/scsi/pm8001/pm8001_hwi.c @@ -2692,7 +2692,6 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha, void *piomb) u32 tag = le32_to_cpu(psataPayload->tag); u32 port_id = le32_to_cpu(psataPayload->port_id); u32 dev_id = le32_to_cpu(psataPayload->device_id); - unsigned long flags; if (event) pm8001_dbg(pm8001_ha, FAIL, "SATA EVENT 0x%x\n", event); @@ -2724,8 +2723,6 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha, void *piomb) ts->resp = SAS_TASK_COMPLETE; ts->stat = SAS_DATA_OVERRUN; ts->residual = 0; - if (pm8001_dev) - atomic_dec(&pm8001_dev->running_req); break; case IO_XFER_ERROR_BREAK: pm8001_dbg(pm8001_ha, IO, "IO_XFER_ERROR_BREAK\n"); @@ -2767,7 +2764,6 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha, void *piomb) IO_OPEN_CNX_ERROR_IT_NEXUS_LOSS); ts->resp = SAS_TASK_COMPLETE; ts->stat = SAS_QUEUE_FULL; - pm8001_ccb_task_free_done(pm8001_ha, t, ccb, tag); return; } break; @@ -2853,20 +2849,6 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha, void *piomb) ts->stat = SAS_OPEN_TO; break; } - spin_lock_irqsave(&t->task_state_lock, flags); - t->task_state_flags &= ~SAS_TASK_STATE_PENDING; - t->task_state_flags &= ~SAS_TASK_AT_INITIATOR; - t->task_state_flags |= SAS_TASK_STATE_DONE; - if (unlikely((t->task_state_flags & SAS_TASK_STATE_ABORTED))) { - spin_unlock_irqrestore(&t->task_state_lock, flags); - pm8001_dbg(pm8001_ha, FAIL, - "task 0x%p done with io_status 0x%x resp 0x%x stat 0x%x but aborted by upper layer!\n", - t, event, ts->resp, ts->stat); - pm8001_ccb_task_free(pm8001_ha, t, ccb, tag); - } else { - spin_unlock_irqrestore(&t->task_state_lock, flags); - pm8001_ccb_task_free_done(pm8001_ha, t, ccb, tag); - } } /*See the comments for mpi_ssp_completion */ diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c index 160ee8b228c9..32edda3e55c6 100644 --- a/drivers/scsi/pm8001/pm8001_sas.c +++ b/drivers/scsi/pm8001/pm8001_sas.c @@ -769,8 +769,13 @@ static int pm8001_exec_internal_tmf_task(struct domain_device *dev, res = -TMF_RESP_FUNC_FAILED; /* Even TMF timed out, return direct. */ if (task->task_state_flags & SAS_TASK_STATE_ABORTED) { + struct pm8001_ccb_info *ccb = task->lldd_task; + pm8001_dbg(pm8001_ha, FAIL, "TMF task[%x]timeout.\n", tmf->tmf); + + if (ccb) + ccb->task = NULL; goto ex_err; } diff --git a/drivers/scsi/pm8001/pm80xx_hwi.c b/drivers/scsi/pm8001/pm80xx_hwi.c index 2530d1365556..9d20f8009b89 100644 --- a/drivers/scsi/pm8001/pm80xx_hwi.c +++ b/drivers/scsi/pm8001/pm80xx_hwi.c @@ -2185,9 +2185,9 @@ mpi_ssp_completion(struct pm8001_hba_info *pm8001_ha, void *piomb) pm8001_dbg(pm8001_ha, FAIL, "task 0x%p done with io_status 0x%x resp 0x%x stat 0x%x but aborted by upper layer!\n", t, status, ts->resp, ts->stat); + pm8001_ccb_task_free(pm8001_ha, t, ccb, tag); if (t->slow_task) complete(&t->slow_task->completion); - pm8001_ccb_task_free(pm8001_ha, t, ccb, tag); } else { spin_unlock_irqrestore(&t->task_state_lock, flags); pm8001_ccb_task_free(pm8001_ha, t, ccb, tag); @@ -2794,9 +2794,9 @@ mpi_sata_completion(struct pm8001_hba_info *pm8001_ha, pm8001_dbg(pm8001_ha, FAIL, "task 0x%p done with io_status 0x%x resp 0x%x stat 0x%x but aborted by upper layer!\n", t, status, ts->resp, ts->stat); + pm8001_ccb_task_free(pm8001_ha, t, ccb, tag); if (t->slow_task) complete(&t->slow_task->completion); - pm8001_ccb_task_free(pm8001_ha, t, ccb, tag); } else { spin_unlock_irqrestore(&t->task_state_lock, flags); spin_unlock_irqrestore(&circularQ->oq_lock, @@ -2821,7 +2821,6 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha, u32 tag = le32_to_cpu(psataPayload->tag); u32 port_id = le32_to_cpu(psataPayload->port_id); u32 dev_id = le32_to_cpu(psataPayload->device_id); - unsigned long flags; if (event) pm8001_dbg(pm8001_ha, FAIL, "SATA EVENT 0x%x\n", event); @@ -2854,8 +2853,6 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha, ts->resp = SAS_TASK_COMPLETE; ts->stat = SAS_DATA_OVERRUN; ts->residual = 0; - if (pm8001_dev) - atomic_dec(&pm8001_dev->running_req); break; case IO_XFER_ERROR_BREAK: pm8001_dbg(pm8001_ha, IO, "IO_XFER_ERROR_BREAK\n"); @@ -2904,11 +2901,6 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha, IO_OPEN_CNX_ERROR_IT_NEXUS_LOSS); ts->resp = SAS_TASK_COMPLETE; ts->stat = SAS_QUEUE_FULL; - spin_unlock_irqrestore(&circularQ->oq_lock, - circularQ->lock_flags); - pm8001_ccb_task_free_done(pm8001_ha, t, ccb, tag); - spin_lock_irqsave(&circularQ->oq_lock, - circularQ->lock_flags); return; } break; @@ -3008,24 +3000,6 @@ static void mpi_sata_event(struct pm8001_hba_info *pm8001_ha, ts->stat = SAS_OPEN_TO; break; } - spin_lock_irqsave(&t->task_state_lock, flags); - t->task_state_flags &= ~SAS_TASK_STATE_PENDING; - t->task_state_flags &= ~SAS_TASK_AT_INITIATOR; - t->task_state_flags |= SAS_TASK_STATE_DONE; - if (unlikely((t->task_state_flags & SAS_TASK_STATE_ABORTED))) { - spin_unlock_irqrestore(&t->task_state_lock, flags); - pm8001_dbg(pm8001_ha, FAIL, - "task 0x%p done with io_status 0x%x resp 0x%x stat 0x%x but aborted by upper layer!\n", - t, event, ts->resp, ts->stat); - pm8001_ccb_task_free(pm8001_ha, t, ccb, tag); - } else { - spin_unlock_irqrestore(&t->task_state_lock, flags); - spin_unlock_irqrestore(&circularQ->oq_lock, - circularQ->lock_flags); - pm8001_ccb_task_free_done(pm8001_ha, t, ccb, tag); - spin_lock_irqsave(&circularQ->oq_lock, - circularQ->lock_flags); - } } /*See the comments for mpi_ssp_completion */ @@ -3931,6 +3905,7 @@ static int ssp_coalesced_comp_resp(struct pm8001_hba_info *pm8001_ha, /** * process_one_iomb - process one outbound Queue memory block * @pm8001_ha: our hba card information + * @circularQ: outbound circular queue * @piomb: IO message buffer */ static void process_one_iomb(struct pm8001_hba_info *pm8001_ha, diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 3520b9384428..f4e6c68ac99e 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -214,6 +214,48 @@ static void scsi_unlock_floptical(struct scsi_device *sdev, SCSI_TIMEOUT, 3, NULL); } +static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev, + unsigned int depth) +{ + int new_shift = sbitmap_calculate_shift(depth); + bool need_alloc = !sdev->budget_map.map; + bool need_free = false; + int ret; + struct sbitmap sb_backup; + + /* + * realloc if new shift is calculated, which is caused by setting + * up one new default queue depth after calling ->slave_configure + */ + if (!need_alloc && new_shift != sdev->budget_map.shift) + need_alloc = need_free = true; + + if (!need_alloc) + return 0; + + /* + * Request queue has to be frozen for reallocating budget map, + * and here disk isn't added yet, so freezing is pretty fast + */ + if (need_free) { + blk_mq_freeze_queue(sdev->request_queue); + sb_backup = sdev->budget_map; + } + ret = sbitmap_init_node(&sdev->budget_map, + scsi_device_max_queue_depth(sdev), + new_shift, GFP_KERNEL, + sdev->request_queue->node, false, true); + if (need_free) { + if (ret) + sdev->budget_map = sb_backup; + else + sbitmap_free(&sb_backup); + ret = 0; + blk_mq_unfreeze_queue(sdev->request_queue); + } + return ret; +} + /** * scsi_alloc_sdev - allocate and setup a scsi_Device * @starget: which target to allocate a &scsi_device for @@ -306,11 +348,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget, * default device queue depth to figure out sbitmap shift * since we use this queue depth most of times. */ - if (sbitmap_init_node(&sdev->budget_map, - scsi_device_max_queue_depth(sdev), - sbitmap_calculate_shift(depth), - GFP_KERNEL, sdev->request_queue->node, - false, true)) { + if (scsi_realloc_sdev_budget_map(sdev, depth)) { put_device(&starget->dev); kfree(sdev); goto out; @@ -1017,6 +1055,13 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, } return SCSI_SCAN_NO_RESPONSE; } + + /* + * The queue_depth is often changed in ->slave_configure. + * Set up budget map again since memory consumption of + * the map depends on actual queue depth. + */ + scsi_realloc_sdev_budget_map(sdev, sdev->queue_depth); } if (sdev->scsi_level >= SCSI_3) diff --git a/drivers/video/console/Kconfig b/drivers/video/console/Kconfig index 840d9813b0bc..fcc46380e7c9 100644 --- a/drivers/video/console/Kconfig +++ b/drivers/video/console/Kconfig @@ -78,6 +78,26 @@ config FRAMEBUFFER_CONSOLE help Low-level framebuffer-based console driver. +config FRAMEBUFFER_CONSOLE_LEGACY_ACCELERATION + bool "Enable legacy fbcon hardware acceleration code" + depends on FRAMEBUFFER_CONSOLE + default y if PARISC + default n + help + This option enables the fbcon (framebuffer text-based) hardware + acceleration for graphics drivers which were written for the fbdev + graphics interface. + + On modern machines, on mainstream machines (like x86-64) or when + using a modern Linux distribution those fbdev drivers usually aren't used. + So enabling this option wouldn't have any effect, which is why you want + to disable this option on such newer machines. + + If you compile this kernel for older machines which still require the + fbdev drivers, you may want to say Y. + + If unsure, select n. + config FRAMEBUFFER_CONSOLE_DETECT_PRIMARY bool "Map the console to the primary display device" depends on FRAMEBUFFER_CONSOLE diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c index 01fae2c96965..f98e8f298bc1 100644 --- a/drivers/video/fbdev/core/bitblit.c +++ b/drivers/video/fbdev/core/bitblit.c @@ -43,6 +43,21 @@ static void update_attr(u8 *dst, u8 *src, int attribute, } } +static void bit_bmove(struct vc_data *vc, struct fb_info *info, int sy, + int sx, int dy, int dx, int height, int width) +{ + struct fb_copyarea area; + + area.sx = sx * vc->vc_font.width; + area.sy = sy * vc->vc_font.height; + area.dx = dx * vc->vc_font.width; + area.dy = dy * vc->vc_font.height; + area.height = height * vc->vc_font.height; + area.width = width * vc->vc_font.width; + + info->fbops->fb_copyarea(info, &area); +} + static void bit_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { @@ -378,6 +393,7 @@ static int bit_update_start(struct fb_info *info) void fbcon_set_bitops(struct fbcon_ops *ops) { + ops->bmove = bit_bmove; ops->clear = bit_clear; ops->putcs = bit_putcs; ops->clear_margins = bit_clear_margins; diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 99ecd9a6d844..f36829eeb5a9 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -173,6 +173,8 @@ static void fbcon_putcs(struct vc_data *vc, const unsigned short *s, int count, int ypos, int xpos); static void fbcon_clear_margins(struct vc_data *vc, int bottom_only); static void fbcon_cursor(struct vc_data *vc, int mode); +static void fbcon_bmove(struct vc_data *vc, int sy, int sx, int dy, int dx, + int height, int width); static int fbcon_switch(struct vc_data *vc); static int fbcon_blank(struct vc_data *vc, int blank, int mode_switch); static void fbcon_set_palette(struct vc_data *vc, const unsigned char *table); @@ -180,8 +182,16 @@ static void fbcon_set_palette(struct vc_data *vc, const unsigned char *table); /* * Internal routines */ +static __inline__ void ywrap_up(struct vc_data *vc, int count); +static __inline__ void ywrap_down(struct vc_data *vc, int count); +static __inline__ void ypan_up(struct vc_data *vc, int count); +static __inline__ void ypan_down(struct vc_data *vc, int count); +static void fbcon_bmove_rec(struct vc_data *vc, struct fbcon_display *p, int sy, int sx, + int dy, int dx, int height, int width, u_int y_break); static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var, int unit); +static void fbcon_redraw_move(struct vc_data *vc, struct fbcon_display *p, + int line, int count, int dy); static void fbcon_modechanged(struct fb_info *info); static void fbcon_set_all_vcs(struct fb_info *info); static void fbcon_start(void); @@ -1015,7 +1025,7 @@ static void fbcon_init(struct vc_data *vc, int init) struct vc_data *svc = *default_mode; struct fbcon_display *t, *p = &fb_display[vc->vc_num]; int logo = 1, new_rows, new_cols, rows, cols; - int ret; + int cap, ret; if (WARN_ON(info_idx == -1)) return; @@ -1024,6 +1034,7 @@ static void fbcon_init(struct vc_data *vc, int init) con2fb_map[vc->vc_num] = info_idx; info = registered_fb[con2fb_map[vc->vc_num]]; + cap = info->flags; if (logo_shown < 0 && console_loglevel <= CONSOLE_LOGLEVEL_QUIET) logo_shown = FBCON_LOGO_DONTSHOW; @@ -1125,6 +1136,14 @@ static void fbcon_init(struct vc_data *vc, int init) ops->graphics = 0; +#ifdef CONFIG_FRAMEBUFFER_CONSOLE_LEGACY_ACCELERATION + if ((cap & FBINFO_HWACCEL_COPYAREA) && + !(cap & FBINFO_HWACCEL_DISABLED)) + p->scrollmode = SCROLL_MOVE; + else /* default to something safe */ + p->scrollmode = SCROLL_REDRAW; +#endif + /* * ++guenther: console.c:vc_allocate() relies on initializing * vc_{cols,rows}, but we must not set those if we are only @@ -1211,13 +1230,14 @@ finished: * This system is now divided into two levels because of complications * caused by hardware scrolling. Top level functions: * - * fbcon_clear(), fbcon_putc(), fbcon_clear_margins() + * fbcon_bmove(), fbcon_clear(), fbcon_putc(), fbcon_clear_margins() * * handles y values in range [0, scr_height-1] that correspond to real * screen positions. y_wrap shift means that first line of bitmap may be * anywhere on this display. These functions convert lineoffsets to * bitmap offsets and deal with the wrap-around case by splitting blits. * + * fbcon_bmove_physical_8() -- These functions fast implementations * fbcon_clear_physical_8() -- of original fbcon_XXX fns. * fbcon_putc_physical_8() -- (font width != 8) may be added later * @@ -1390,6 +1410,224 @@ static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var, } } +static __inline__ void ywrap_up(struct vc_data *vc, int count) +{ + struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_display *p = &fb_display[vc->vc_num]; + + p->yscroll += count; + if (p->yscroll >= p->vrows) /* Deal with wrap */ + p->yscroll -= p->vrows; + ops->var.xoffset = 0; + ops->var.yoffset = p->yscroll * vc->vc_font.height; + ops->var.vmode |= FB_VMODE_YWRAP; + ops->update_start(info); + scrollback_max += count; + if (scrollback_max > scrollback_phys_max) + scrollback_max = scrollback_phys_max; + scrollback_current = 0; +} + +static __inline__ void ywrap_down(struct vc_data *vc, int count) +{ + struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_display *p = &fb_display[vc->vc_num]; + + p->yscroll -= count; + if (p->yscroll < 0) /* Deal with wrap */ + p->yscroll += p->vrows; + ops->var.xoffset = 0; + ops->var.yoffset = p->yscroll * vc->vc_font.height; + ops->var.vmode |= FB_VMODE_YWRAP; + ops->update_start(info); + scrollback_max -= count; + if (scrollback_max < 0) + scrollback_max = 0; + scrollback_current = 0; +} + +static __inline__ void ypan_up(struct vc_data *vc, int count) +{ + struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fbcon_display *p = &fb_display[vc->vc_num]; + struct fbcon_ops *ops = info->fbcon_par; + + p->yscroll += count; + if (p->yscroll > p->vrows - vc->vc_rows) { + ops->bmove(vc, info, p->vrows - vc->vc_rows, + 0, 0, 0, vc->vc_rows, vc->vc_cols); + p->yscroll -= p->vrows - vc->vc_rows; + } + + ops->var.xoffset = 0; + ops->var.yoffset = p->yscroll * vc->vc_font.height; + ops->var.vmode &= ~FB_VMODE_YWRAP; + ops->update_start(info); + fbcon_clear_margins(vc, 1); + scrollback_max += count; + if (scrollback_max > scrollback_phys_max) + scrollback_max = scrollback_phys_max; + scrollback_current = 0; +} + +static __inline__ void ypan_up_redraw(struct vc_data *vc, int t, int count) +{ + struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_display *p = &fb_display[vc->vc_num]; + + p->yscroll += count; + + if (p->yscroll > p->vrows - vc->vc_rows) { + p->yscroll -= p->vrows - vc->vc_rows; + fbcon_redraw_move(vc, p, t + count, vc->vc_rows - count, t); + } + + ops->var.xoffset = 0; + ops->var.yoffset = p->yscroll * vc->vc_font.height; + ops->var.vmode &= ~FB_VMODE_YWRAP; + ops->update_start(info); + fbcon_clear_margins(vc, 1); + scrollback_max += count; + if (scrollback_max > scrollback_phys_max) + scrollback_max = scrollback_phys_max; + scrollback_current = 0; +} + +static __inline__ void ypan_down(struct vc_data *vc, int count) +{ + struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fbcon_display *p = &fb_display[vc->vc_num]; + struct fbcon_ops *ops = info->fbcon_par; + + p->yscroll -= count; + if (p->yscroll < 0) { + ops->bmove(vc, info, 0, 0, p->vrows - vc->vc_rows, + 0, vc->vc_rows, vc->vc_cols); + p->yscroll += p->vrows - vc->vc_rows; + } + + ops->var.xoffset = 0; + ops->var.yoffset = p->yscroll * vc->vc_font.height; + ops->var.vmode &= ~FB_VMODE_YWRAP; + ops->update_start(info); + fbcon_clear_margins(vc, 1); + scrollback_max -= count; + if (scrollback_max < 0) + scrollback_max = 0; + scrollback_current = 0; +} + +static __inline__ void ypan_down_redraw(struct vc_data *vc, int t, int count) +{ + struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_display *p = &fb_display[vc->vc_num]; + + p->yscroll -= count; + + if (p->yscroll < 0) { + p->yscroll += p->vrows - vc->vc_rows; + fbcon_redraw_move(vc, p, t, vc->vc_rows - count, t + count); + } + + ops->var.xoffset = 0; + ops->var.yoffset = p->yscroll * vc->vc_font.height; + ops->var.vmode &= ~FB_VMODE_YWRAP; + ops->update_start(info); + fbcon_clear_margins(vc, 1); + scrollback_max -= count; + if (scrollback_max < 0) + scrollback_max = 0; + scrollback_current = 0; +} + +static void fbcon_redraw_move(struct vc_data *vc, struct fbcon_display *p, + int line, int count, int dy) +{ + unsigned short *s = (unsigned short *) + (vc->vc_origin + vc->vc_size_row * line); + + while (count--) { + unsigned short *start = s; + unsigned short *le = advance_row(s, 1); + unsigned short c; + int x = 0; + unsigned short attr = 1; + + do { + c = scr_readw(s); + if (attr != (c & 0xff00)) { + attr = c & 0xff00; + if (s > start) { + fbcon_putcs(vc, start, s - start, + dy, x); + x += s - start; + start = s; + } + } + console_conditional_schedule(); + s++; + } while (s < le); + if (s > start) + fbcon_putcs(vc, start, s - start, dy, x); + console_conditional_schedule(); + dy++; + } +} + +static void fbcon_redraw_blit(struct vc_data *vc, struct fb_info *info, + struct fbcon_display *p, int line, int count, int ycount) +{ + int offset = ycount * vc->vc_cols; + unsigned short *d = (unsigned short *) + (vc->vc_origin + vc->vc_size_row * line); + unsigned short *s = d + offset; + struct fbcon_ops *ops = info->fbcon_par; + + while (count--) { + unsigned short *start = s; + unsigned short *le = advance_row(s, 1); + unsigned short c; + int x = 0; + + do { + c = scr_readw(s); + + if (c == scr_readw(d)) { + if (s > start) { + ops->bmove(vc, info, line + ycount, x, + line, x, 1, s-start); + x += s - start + 1; + start = s + 1; + } else { + x++; + start++; + } + } + + scr_writew(c, d); + console_conditional_schedule(); + s++; + d++; + } while (s < le); + if (s > start) + ops->bmove(vc, info, line + ycount, x, line, x, 1, + s-start); + console_conditional_schedule(); + if (ycount > 0) + line++; + else { + line--; + /* NOTE: We subtract two lines from these pointers */ + s -= vc->vc_size_row; + d -= vc->vc_size_row; + } + } +} + static void fbcon_redraw(struct vc_data *vc, struct fbcon_display *p, int line, int count, int offset) { @@ -1450,6 +1688,7 @@ static bool fbcon_scroll(struct vc_data *vc, unsigned int t, unsigned int b, { struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; struct fbcon_display *p = &fb_display[vc->vc_num]; + int scroll_partial = info->flags & FBINFO_PARTIAL_PAN_OK; if (fbcon_is_inactive(vc, info)) return true; @@ -1466,32 +1705,291 @@ static bool fbcon_scroll(struct vc_data *vc, unsigned int t, unsigned int b, case SM_UP: if (count > vc->vc_rows) /* Maximum realistic size */ count = vc->vc_rows; - fbcon_redraw(vc, p, t, b - t - count, - count * vc->vc_cols); - fbcon_clear(vc, b - count, 0, count, vc->vc_cols); - scr_memsetw((unsigned short *) (vc->vc_origin + - vc->vc_size_row * - (b - count)), - vc->vc_video_erase_char, - vc->vc_size_row * count); - return true; + if (logo_shown >= 0) + goto redraw_up; + switch (fb_scrollmode(p)) { + case SCROLL_MOVE: + fbcon_redraw_blit(vc, info, p, t, b - t - count, + count); + fbcon_clear(vc, b - count, 0, count, vc->vc_cols); + scr_memsetw((unsigned short *) (vc->vc_origin + + vc->vc_size_row * + (b - count)), + vc->vc_video_erase_char, + vc->vc_size_row * count); + return true; + + case SCROLL_WRAP_MOVE: + if (b - t - count > 3 * vc->vc_rows >> 2) { + if (t > 0) + fbcon_bmove(vc, 0, 0, count, 0, t, + vc->vc_cols); + ywrap_up(vc, count); + if (vc->vc_rows - b > 0) + fbcon_bmove(vc, b - count, 0, b, 0, + vc->vc_rows - b, + vc->vc_cols); + } else if (info->flags & FBINFO_READS_FAST) + fbcon_bmove(vc, t + count, 0, t, 0, + b - t - count, vc->vc_cols); + else + goto redraw_up; + fbcon_clear(vc, b - count, 0, count, vc->vc_cols); + break; + + case SCROLL_PAN_REDRAW: + if ((p->yscroll + count <= + 2 * (p->vrows - vc->vc_rows)) + && ((!scroll_partial && (b - t == vc->vc_rows)) + || (scroll_partial + && (b - t - count > + 3 * vc->vc_rows >> 2)))) { + if (t > 0) + fbcon_redraw_move(vc, p, 0, t, count); + ypan_up_redraw(vc, t, count); + if (vc->vc_rows - b > 0) + fbcon_redraw_move(vc, p, b, + vc->vc_rows - b, b); + } else + fbcon_redraw_move(vc, p, t + count, b - t - count, t); + fbcon_clear(vc, b - count, 0, count, vc->vc_cols); + break; + + case SCROLL_PAN_MOVE: + if ((p->yscroll + count <= + 2 * (p->vrows - vc->vc_rows)) + && ((!scroll_partial && (b - t == vc->vc_rows)) + || (scroll_partial + && (b - t - count > + 3 * vc->vc_rows >> 2)))) { + if (t > 0) + fbcon_bmove(vc, 0, 0, count, 0, t, + vc->vc_cols); + ypan_up(vc, count); + if (vc->vc_rows - b > 0) + fbcon_bmove(vc, b - count, 0, b, 0, + vc->vc_rows - b, + vc->vc_cols); + } else if (info->flags & FBINFO_READS_FAST) + fbcon_bmove(vc, t + count, 0, t, 0, + b - t - count, vc->vc_cols); + else + goto redraw_up; + fbcon_clear(vc, b - count, 0, count, vc->vc_cols); + break; + + case SCROLL_REDRAW: + redraw_up: + fbcon_redraw(vc, p, t, b - t - count, + count * vc->vc_cols); + fbcon_clear(vc, b - count, 0, count, vc->vc_cols); + scr_memsetw((unsigned short *) (vc->vc_origin + + vc->vc_size_row * + (b - count)), + vc->vc_video_erase_char, + vc->vc_size_row * count); + return true; + } + break; case SM_DOWN: if (count > vc->vc_rows) /* Maximum realistic size */ count = vc->vc_rows; - fbcon_redraw(vc, p, b - 1, b - t - count, - -count * vc->vc_cols); - fbcon_clear(vc, t, 0, count, vc->vc_cols); - scr_memsetw((unsigned short *) (vc->vc_origin + - vc->vc_size_row * - t), - vc->vc_video_erase_char, - vc->vc_size_row * count); - return true; + if (logo_shown >= 0) + goto redraw_down; + switch (fb_scrollmode(p)) { + case SCROLL_MOVE: + fbcon_redraw_blit(vc, info, p, b - 1, b - t - count, + -count); + fbcon_clear(vc, t, 0, count, vc->vc_cols); + scr_memsetw((unsigned short *) (vc->vc_origin + + vc->vc_size_row * + t), + vc->vc_video_erase_char, + vc->vc_size_row * count); + return true; + + case SCROLL_WRAP_MOVE: + if (b - t - count > 3 * vc->vc_rows >> 2) { + if (vc->vc_rows - b > 0) + fbcon_bmove(vc, b, 0, b - count, 0, + vc->vc_rows - b, + vc->vc_cols); + ywrap_down(vc, count); + if (t > 0) + fbcon_bmove(vc, count, 0, 0, 0, t, + vc->vc_cols); + } else if (info->flags & FBINFO_READS_FAST) + fbcon_bmove(vc, t, 0, t + count, 0, + b - t - count, vc->vc_cols); + else + goto redraw_down; + fbcon_clear(vc, t, 0, count, vc->vc_cols); + break; + + case SCROLL_PAN_MOVE: + if ((count - p->yscroll <= p->vrows - vc->vc_rows) + && ((!scroll_partial && (b - t == vc->vc_rows)) + || (scroll_partial + && (b - t - count > + 3 * vc->vc_rows >> 2)))) { + if (vc->vc_rows - b > 0) + fbcon_bmove(vc, b, 0, b - count, 0, + vc->vc_rows - b, + vc->vc_cols); + ypan_down(vc, count); + if (t > 0) + fbcon_bmove(vc, count, 0, 0, 0, t, + vc->vc_cols); + } else if (info->flags & FBINFO_READS_FAST) + fbcon_bmove(vc, t, 0, t + count, 0, + b - t - count, vc->vc_cols); + else + goto redraw_down; + fbcon_clear(vc, t, 0, count, vc->vc_cols); + break; + + case SCROLL_PAN_REDRAW: + if ((count - p->yscroll <= p->vrows - vc->vc_rows) + && ((!scroll_partial && (b - t == vc->vc_rows)) + || (scroll_partial + && (b - t - count > + 3 * vc->vc_rows >> 2)))) { + if (vc->vc_rows - b > 0) + fbcon_redraw_move(vc, p, b, vc->vc_rows - b, + b - count); + ypan_down_redraw(vc, t, count); + if (t > 0) + fbcon_redraw_move(vc, p, count, t, 0); + } else + fbcon_redraw_move(vc, p, t, b - t - count, t + count); + fbcon_clear(vc, t, 0, count, vc->vc_cols); + break; + + case SCROLL_REDRAW: + redraw_down: + fbcon_redraw(vc, p, b - 1, b - t - count, + -count * vc->vc_cols); + fbcon_clear(vc, t, 0, count, vc->vc_cols); + scr_memsetw((unsigned short *) (vc->vc_origin + + vc->vc_size_row * + t), + vc->vc_video_erase_char, + vc->vc_size_row * count); + return true; + } } return false; } + +static void fbcon_bmove(struct vc_data *vc, int sy, int sx, int dy, int dx, + int height, int width) +{ + struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fbcon_display *p = &fb_display[vc->vc_num]; + + if (fbcon_is_inactive(vc, info)) + return; + + if (!width || !height) + return; + + /* Split blits that cross physical y_wrap case. + * Pathological case involves 4 blits, better to use recursive + * code rather than unrolled case + * + * Recursive invocations don't need to erase the cursor over and + * over again, so we use fbcon_bmove_rec() + */ + fbcon_bmove_rec(vc, p, sy, sx, dy, dx, height, width, + p->vrows - p->yscroll); +} + +static void fbcon_bmove_rec(struct vc_data *vc, struct fbcon_display *p, int sy, int sx, + int dy, int dx, int height, int width, u_int y_break) +{ + struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fbcon_ops *ops = info->fbcon_par; + u_int b; + + if (sy < y_break && sy + height > y_break) { + b = y_break - sy; + if (dy < sy) { /* Avoid trashing self */ + fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, + y_break); + fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, + height - b, width, y_break); + } else { + fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, + height - b, width, y_break); + fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, + y_break); + } + return; + } + + if (dy < y_break && dy + height > y_break) { + b = y_break - dy; + if (dy < sy) { /* Avoid trashing self */ + fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, + y_break); + fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, + height - b, width, y_break); + } else { + fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, + height - b, width, y_break); + fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, + y_break); + } + return; + } + ops->bmove(vc, info, real_y(p, sy), sx, real_y(p, dy), dx, + height, width); +} + +static void updatescrollmode_accel(struct fbcon_display *p, + struct fb_info *info, + struct vc_data *vc) +{ +#ifdef CONFIG_FRAMEBUFFER_CONSOLE_LEGACY_ACCELERATION + struct fbcon_ops *ops = info->fbcon_par; + int cap = info->flags; + u16 t = 0; + int ypan = FBCON_SWAP(ops->rotate, info->fix.ypanstep, + info->fix.xpanstep); + int ywrap = FBCON_SWAP(ops->rotate, info->fix.ywrapstep, t); + int yres = FBCON_SWAP(ops->rotate, info->var.yres, info->var.xres); + int vyres = FBCON_SWAP(ops->rotate, info->var.yres_virtual, + info->var.xres_virtual); + int good_pan = (cap & FBINFO_HWACCEL_YPAN) && + divides(ypan, vc->vc_font.height) && vyres > yres; + int good_wrap = (cap & FBINFO_HWACCEL_YWRAP) && + divides(ywrap, vc->vc_font.height) && + divides(vc->vc_font.height, vyres) && + divides(vc->vc_font.height, yres); + int reading_fast = cap & FBINFO_READS_FAST; + int fast_copyarea = (cap & FBINFO_HWACCEL_COPYAREA) && + !(cap & FBINFO_HWACCEL_DISABLED); + int fast_imageblit = (cap & FBINFO_HWACCEL_IMAGEBLIT) && + !(cap & FBINFO_HWACCEL_DISABLED); + + if (good_wrap || good_pan) { + if (reading_fast || fast_copyarea) + p->scrollmode = good_wrap ? + SCROLL_WRAP_MOVE : SCROLL_PAN_MOVE; + else + p->scrollmode = good_wrap ? SCROLL_REDRAW : + SCROLL_PAN_REDRAW; + } else { + if (reading_fast || (fast_copyarea && !fast_imageblit)) + p->scrollmode = SCROLL_MOVE; + else + p->scrollmode = SCROLL_REDRAW; + } +#endif +} + static void updatescrollmode(struct fbcon_display *p, struct fb_info *info, struct vc_data *vc) @@ -1507,6 +2005,9 @@ static void updatescrollmode(struct fbcon_display *p, p->vrows -= (yres - (fh * vc->vc_rows)) / fh; if ((yres % fh) && (vyres % fh < yres % fh)) p->vrows--; + + /* update scrollmode in case hardware acceleration is used */ + updatescrollmode_accel(p, info, vc); } #define PITCH(w) (((w) + 7) >> 3) @@ -1664,7 +2165,21 @@ static int fbcon_switch(struct vc_data *vc) updatescrollmode(p, info, vc); - scrollback_phys_max = 0; + switch (fb_scrollmode(p)) { + case SCROLL_WRAP_MOVE: + scrollback_phys_max = p->vrows - vc->vc_rows; + break; + case SCROLL_PAN_MOVE: + case SCROLL_PAN_REDRAW: + scrollback_phys_max = p->vrows - 2 * vc->vc_rows; + if (scrollback_phys_max < 0) + scrollback_phys_max = 0; + break; + default: + scrollback_phys_max = 0; + break; + } + scrollback_max = 0; scrollback_current = 0; diff --git a/drivers/video/fbdev/core/fbcon.h b/drivers/video/fbdev/core/fbcon.h index a00603b4451a..969d41ecede5 100644 --- a/drivers/video/fbdev/core/fbcon.h +++ b/drivers/video/fbdev/core/fbcon.h @@ -29,6 +29,9 @@ struct fbcon_display { /* Filled in by the low-level console driver */ const u_char *fontdata; int userfont; /* != 0 if fontdata kmalloc()ed */ +#ifdef CONFIG_FRAMEBUFFER_CONSOLE_LEGACY_ACCELERATION + u_short scrollmode; /* Scroll Method, use fb_scrollmode() */ +#endif u_short inverse; /* != 0 text black on white as default */ short yscroll; /* Hardware scrolling */ int vrows; /* number of virtual rows */ @@ -51,6 +54,8 @@ struct fbcon_display { }; struct fbcon_ops { + void (*bmove)(struct vc_data *vc, struct fb_info *info, int sy, + int sx, int dy, int dx, int height, int width); void (*clear)(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width); void (*putcs)(struct vc_data *vc, struct fb_info *info, @@ -149,6 +154,73 @@ static inline int attr_col_ec(int shift, struct vc_data *vc, #define attr_bgcol_ec(bgshift, vc, info) attr_col_ec(bgshift, vc, info, 0) #define attr_fgcol_ec(fgshift, vc, info) attr_col_ec(fgshift, vc, info, 1) + /* + * Scroll Method + */ + +/* There are several methods fbcon can use to move text around the screen: + * + * Operation Pan Wrap + *--------------------------------------------- + * SCROLL_MOVE copyarea No No + * SCROLL_PAN_MOVE copyarea Yes No + * SCROLL_WRAP_MOVE copyarea No Yes + * SCROLL_REDRAW imageblit No No + * SCROLL_PAN_REDRAW imageblit Yes No + * SCROLL_WRAP_REDRAW imageblit No Yes + * + * (SCROLL_WRAP_REDRAW is not implemented yet) + * + * In general, fbcon will choose the best scrolling + * method based on the rule below: + * + * Pan/Wrap > accel imageblit > accel copyarea > + * soft imageblit > (soft copyarea) + * + * Exception to the rule: Pan + accel copyarea is + * preferred over Pan + accel imageblit. + * + * The above is typical for PCI/AGP cards. Unless + * overridden, fbcon will never use soft copyarea. + * + * If you need to override the above rule, set the + * appropriate flags in fb_info->flags. For example, + * to prefer copyarea over imageblit, set + * FBINFO_READS_FAST. + * + * Other notes: + * + use the hardware engine to move the text + * (hw-accelerated copyarea() and fillrect()) + * + use hardware-supported panning on a large virtual screen + * + amifb can not only pan, but also wrap the display by N lines + * (i.e. visible line i = physical line (i+N) % yres). + * + read what's already rendered on the screen and + * write it in a different place (this is cfb_copyarea()) + * + re-render the text to the screen + * + * Whether to use wrapping or panning can only be figured out at + * runtime (when we know whether our font height is a multiple + * of the pan/wrap step) + * + */ + +#define SCROLL_MOVE 0x001 +#define SCROLL_PAN_MOVE 0x002 +#define SCROLL_WRAP_MOVE 0x003 +#define SCROLL_REDRAW 0x004 +#define SCROLL_PAN_REDRAW 0x005 + +static inline u_short fb_scrollmode(struct fbcon_display *fb) +{ +#ifdef CONFIG_FRAMEBUFFER_CONSOLE_LEGACY_ACCELERATION + return fb->scrollmode; +#else + /* hardcoded to SCROLL_REDRAW if acceleration was disabled. */ + return SCROLL_REDRAW; +#endif +} + + #ifdef CONFIG_FB_TILEBLITTING extern void fbcon_set_tileops(struct vc_data *vc, struct fb_info *info); #endif diff --git a/drivers/video/fbdev/core/fbcon_ccw.c b/drivers/video/fbdev/core/fbcon_ccw.c index ffa78936eaab..2789ace79634 100644 --- a/drivers/video/fbdev/core/fbcon_ccw.c +++ b/drivers/video/fbdev/core/fbcon_ccw.c @@ -59,12 +59,31 @@ static void ccw_update_attr(u8 *dst, u8 *src, int attribute, } } + +static void ccw_bmove(struct vc_data *vc, struct fb_info *info, int sy, + int sx, int dy, int dx, int height, int width) +{ + struct fbcon_ops *ops = info->fbcon_par; + struct fb_copyarea area; + u32 vyres = GETVYRES(ops->p, info); + + area.sx = sy * vc->vc_font.height; + area.sy = vyres - ((sx + width) * vc->vc_font.width); + area.dx = dy * vc->vc_font.height; + area.dy = vyres - ((dx + width) * vc->vc_font.width); + area.width = height * vc->vc_font.height; + area.height = width * vc->vc_font.width; + + info->fbops->fb_copyarea(info, &area); +} + static void ccw_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { + struct fbcon_ops *ops = info->fbcon_par; struct fb_fillrect region; int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - u32 vyres = info->var.yres; + u32 vyres = GETVYRES(ops->p, info); region.color = attr_bgcol_ec(bgshift,vc,info); region.dx = sy * vc->vc_font.height; @@ -121,7 +140,7 @@ static void ccw_putcs(struct vc_data *vc, struct fb_info *info, u32 cnt, pitch, size; u32 attribute = get_attribute(info, scr_readw(s)); u8 *dst, *buf = NULL; - u32 vyres = info->var.yres; + u32 vyres = GETVYRES(ops->p, info); if (!ops->fontbuffer) return; @@ -210,7 +229,7 @@ static void ccw_cursor(struct vc_data *vc, struct fb_info *info, int mode, int attribute, use_sw = vc->vc_cursor_type & CUR_SW; int err = 1, dx, dy; char *src; - u32 vyres = info->var.yres; + u32 vyres = GETVYRES(ops->p, info); if (!ops->fontbuffer) return; @@ -368,7 +387,7 @@ static int ccw_update_start(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; u32 yoffset; - u32 vyres = info->var.yres; + u32 vyres = GETVYRES(ops->p, info); int err; yoffset = (vyres - info->var.yres) - ops->var.xoffset; @@ -383,6 +402,7 @@ static int ccw_update_start(struct fb_info *info) void fbcon_rotate_ccw(struct fbcon_ops *ops) { + ops->bmove = ccw_bmove; ops->clear = ccw_clear; ops->putcs = ccw_putcs; ops->clear_margins = ccw_clear_margins; diff --git a/drivers/video/fbdev/core/fbcon_cw.c b/drivers/video/fbdev/core/fbcon_cw.c index 92e5b7fb51ee..86a254c1b2b7 100644 --- a/drivers/video/fbdev/core/fbcon_cw.c +++ b/drivers/video/fbdev/core/fbcon_cw.c @@ -44,12 +44,31 @@ static void cw_update_attr(u8 *dst, u8 *src, int attribute, } } + +static void cw_bmove(struct vc_data *vc, struct fb_info *info, int sy, + int sx, int dy, int dx, int height, int width) +{ + struct fbcon_ops *ops = info->fbcon_par; + struct fb_copyarea area; + u32 vxres = GETVXRES(ops->p, info); + + area.sx = vxres - ((sy + height) * vc->vc_font.height); + area.sy = sx * vc->vc_font.width; + area.dx = vxres - ((dy + height) * vc->vc_font.height); + area.dy = dx * vc->vc_font.width; + area.width = height * vc->vc_font.height; + area.height = width * vc->vc_font.width; + + info->fbops->fb_copyarea(info, &area); +} + static void cw_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { + struct fbcon_ops *ops = info->fbcon_par; struct fb_fillrect region; int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - u32 vxres = info->var.xres; + u32 vxres = GETVXRES(ops->p, info); region.color = attr_bgcol_ec(bgshift,vc,info); region.dx = vxres - ((sy + height) * vc->vc_font.height); @@ -106,7 +125,7 @@ static void cw_putcs(struct vc_data *vc, struct fb_info *info, u32 cnt, pitch, size; u32 attribute = get_attribute(info, scr_readw(s)); u8 *dst, *buf = NULL; - u32 vxres = info->var.xres; + u32 vxres = GETVXRES(ops->p, info); if (!ops->fontbuffer) return; @@ -193,7 +212,7 @@ static void cw_cursor(struct vc_data *vc, struct fb_info *info, int mode, int attribute, use_sw = vc->vc_cursor_type & CUR_SW; int err = 1, dx, dy; char *src; - u32 vxres = info->var.xres; + u32 vxres = GETVXRES(ops->p, info); if (!ops->fontbuffer) return; @@ -350,7 +369,7 @@ static void cw_cursor(struct vc_data *vc, struct fb_info *info, int mode, static int cw_update_start(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; - u32 vxres = info->var.xres; + u32 vxres = GETVXRES(ops->p, info); u32 xoffset; int err; @@ -366,6 +385,7 @@ static int cw_update_start(struct fb_info *info) void fbcon_rotate_cw(struct fbcon_ops *ops) { + ops->bmove = cw_bmove; ops->clear = cw_clear; ops->putcs = cw_putcs; ops->clear_margins = cw_clear_margins; diff --git a/drivers/video/fbdev/core/fbcon_rotate.h b/drivers/video/fbdev/core/fbcon_rotate.h index b528b2e54283..01cbe303b8a2 100644 --- a/drivers/video/fbdev/core/fbcon_rotate.h +++ b/drivers/video/fbdev/core/fbcon_rotate.h @@ -11,6 +11,15 @@ #ifndef _FBCON_ROTATE_H #define _FBCON_ROTATE_H +#define GETVYRES(s,i) ({ \ + (fb_scrollmode(s) == SCROLL_REDRAW || fb_scrollmode(s) == SCROLL_MOVE) ? \ + (i)->var.yres : (i)->var.yres_virtual; }) + +#define GETVXRES(s,i) ({ \ + (fb_scrollmode(s) == SCROLL_REDRAW || fb_scrollmode(s) == SCROLL_MOVE || !(i)->fix.xpanstep) ? \ + (i)->var.xres : (i)->var.xres_virtual; }) + + static inline int pattern_test_bit(u32 x, u32 y, u32 pitch, const char *pat) { u32 tmp = (y * pitch) + x, index = tmp / 8, bit = tmp % 8; diff --git a/drivers/video/fbdev/core/fbcon_ud.c b/drivers/video/fbdev/core/fbcon_ud.c index 09619bd8e021..23bc045769d0 100644 --- a/drivers/video/fbdev/core/fbcon_ud.c +++ b/drivers/video/fbdev/core/fbcon_ud.c @@ -44,13 +44,33 @@ static void ud_update_attr(u8 *dst, u8 *src, int attribute, } } + +static void ud_bmove(struct vc_data *vc, struct fb_info *info, int sy, + int sx, int dy, int dx, int height, int width) +{ + struct fbcon_ops *ops = info->fbcon_par; + struct fb_copyarea area; + u32 vyres = GETVYRES(ops->p, info); + u32 vxres = GETVXRES(ops->p, info); + + area.sy = vyres - ((sy + height) * vc->vc_font.height); + area.sx = vxres - ((sx + width) * vc->vc_font.width); + area.dy = vyres - ((dy + height) * vc->vc_font.height); + area.dx = vxres - ((dx + width) * vc->vc_font.width); + area.height = height * vc->vc_font.height; + area.width = width * vc->vc_font.width; + + info->fbops->fb_copyarea(info, &area); +} + static void ud_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { + struct fbcon_ops *ops = info->fbcon_par; struct fb_fillrect region; int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - u32 vyres = info->var.yres; - u32 vxres = info->var.xres; + u32 vyres = GETVYRES(ops->p, info); + u32 vxres = GETVXRES(ops->p, info); region.color = attr_bgcol_ec(bgshift,vc,info); region.dy = vyres - ((sy + height) * vc->vc_font.height); @@ -142,8 +162,8 @@ static void ud_putcs(struct vc_data *vc, struct fb_info *info, u32 mod = vc->vc_font.width % 8, cnt, pitch, size; u32 attribute = get_attribute(info, scr_readw(s)); u8 *dst, *buf = NULL; - u32 vyres = info->var.yres; - u32 vxres = info->var.xres; + u32 vyres = GETVYRES(ops->p, info); + u32 vxres = GETVXRES(ops->p, info); if (!ops->fontbuffer) return; @@ -239,8 +259,8 @@ static void ud_cursor(struct vc_data *vc, struct fb_info *info, int mode, int attribute, use_sw = vc->vc_cursor_type & CUR_SW; int err = 1, dx, dy; char *src; - u32 vyres = info->var.yres; - u32 vxres = info->var.xres; + u32 vyres = GETVYRES(ops->p, info); + u32 vxres = GETVXRES(ops->p, info); if (!ops->fontbuffer) return; @@ -390,8 +410,8 @@ static int ud_update_start(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; int xoffset, yoffset; - u32 vyres = info->var.yres; - u32 vxres = info->var.xres; + u32 vyres = GETVYRES(ops->p, info); + u32 vxres = GETVXRES(ops->p, info); int err; xoffset = vxres - info->var.xres - ops->var.xoffset; @@ -409,6 +429,7 @@ static int ud_update_start(struct fb_info *info) void fbcon_rotate_ud(struct fbcon_ops *ops) { + ops->bmove = ud_bmove; ops->clear = ud_clear; ops->putcs = ud_putcs; ops->clear_margins = ud_clear_margins; diff --git a/drivers/video/fbdev/core/tileblit.c b/drivers/video/fbdev/core/tileblit.c index 72af95053bcb..2768eff247ba 100644 --- a/drivers/video/fbdev/core/tileblit.c +++ b/drivers/video/fbdev/core/tileblit.c @@ -16,6 +16,21 @@ #include <asm/types.h> #include "fbcon.h" +static void tile_bmove(struct vc_data *vc, struct fb_info *info, int sy, + int sx, int dy, int dx, int height, int width) +{ + struct fb_tilearea area; + + area.sx = sx; + area.sy = sy; + area.dx = dx; + area.dy = dy; + area.height = height; + area.width = width; + + info->tileops->fb_tilecopy(info, &area); +} + static void tile_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { @@ -118,6 +133,7 @@ void fbcon_set_tileops(struct vc_data *vc, struct fb_info *info) struct fb_tilemap map; struct fbcon_ops *ops = info->fbcon_par; + ops->bmove = tile_bmove; ops->clear = tile_clear; ops->putcs = tile_putcs; ops->clear_margins = tile_clear_margins; diff --git a/drivers/video/fbdev/skeletonfb.c b/drivers/video/fbdev/skeletonfb.c index 0fe922f726e9..bcacfb6934fa 100644 --- a/drivers/video/fbdev/skeletonfb.c +++ b/drivers/video/fbdev/skeletonfb.c @@ -505,15 +505,15 @@ void xxxfb_fillrect(struct fb_info *p, const struct fb_fillrect *region) } /** - * xxxfb_copyarea - OBSOLETE function. + * xxxfb_copyarea - REQUIRED function. Can use generic routines if + * non acclerated hardware and packed pixel based. * Copies one area of the screen to another area. - * Will be deleted in a future version * * @info: frame buffer structure that represents a single frame buffer * @area: Structure providing the data to copy the framebuffer contents * from one region to another. * - * This drawing operation copied a rectangular area from one area of the + * This drawing operation copies a rectangular area from one area of the * screen to another area. */ void xxxfb_copyarea(struct fb_info *p, const struct fb_copyarea *area) @@ -645,9 +645,9 @@ static const struct fb_ops xxxfb_ops = { .fb_setcolreg = xxxfb_setcolreg, .fb_blank = xxxfb_blank, .fb_pan_display = xxxfb_pan_display, - .fb_fillrect = xxxfb_fillrect, /* Needed !!! */ - .fb_copyarea = xxxfb_copyarea, /* Obsolete */ - .fb_imageblit = xxxfb_imageblit, /* Needed !!! */ + .fb_fillrect = xxxfb_fillrect, /* Needed !!! */ + .fb_copyarea = xxxfb_copyarea, /* Needed !!! */ + .fb_imageblit = xxxfb_imageblit, /* Needed !!! */ .fb_cursor = xxxfb_cursor, /* Optional !!! */ .fb_sync = xxxfb_sync, .fb_ioctl = xxxfb_ioctl, diff --git a/fs/9p/fid.c b/fs/9p/fid.c index 6aab046c98e2..79df61fe0e59 100644 --- a/fs/9p/fid.c +++ b/fs/9p/fid.c @@ -96,12 +96,8 @@ static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any) dentry, dentry, from_kuid(&init_user_ns, uid), any); ret = NULL; - - if (d_inode(dentry)) - ret = v9fs_fid_find_inode(d_inode(dentry), uid); - /* we'll recheck under lock if there's anything to look in */ - if (!ret && dentry->d_fsdata) { + if (dentry->d_fsdata) { struct hlist_head *h = (struct hlist_head *)&dentry->d_fsdata; spin_lock(&dentry->d_lock); @@ -113,6 +109,9 @@ static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any) } } spin_unlock(&dentry->d_lock); + } else { + if (dentry->d_inode) + ret = v9fs_fid_find_inode(dentry->d_inode, uid); } return ret; diff --git a/fs/Kconfig b/fs/Kconfig index 7a2b11c0b803..6c7dc1387beb 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -369,8 +369,8 @@ source "fs/ksmbd/Kconfig" config SMBFS_COMMON tristate - default y if CIFS=y - default m if CIFS=m + default y if CIFS=y || SMB_SERVER=y + default m if CIFS=m || SMB_SERVER=m source "fs/coda/Kconfig" source "fs/afs/Kconfig" diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index c07f35719ee3..e1eae7ea823a 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -817,20 +817,16 @@ static struct file_system_type bm_fs_type = { }; MODULE_ALIAS_FS("binfmt_misc"); -static struct ctl_table_header *binfmt_misc_header; - static int __init init_misc_binfmt(void) { int err = register_filesystem(&bm_fs_type); if (!err) insert_binfmt(&misc_format); - binfmt_misc_header = register_sysctl_mount_point("fs/binfmt_misc"); - return 0; + return err; } static void __exit exit_misc_binfmt(void) { - unregister_sysctl_table(binfmt_misc_header); unregister_binfmt(&misc_format); unregister_filesystem(&bm_fs_type); } diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 1db24e6d6d90..8202ad6aa131 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -124,7 +124,16 @@ void btrfs_put_block_group(struct btrfs_block_group *cache) { if (refcount_dec_and_test(&cache->refs)) { WARN_ON(cache->pinned > 0); - WARN_ON(cache->reserved > 0); + /* + * If there was a failure to cleanup a log tree, very likely due + * to an IO failure on a writeback attempt of one or more of its + * extent buffers, we could not do proper (and cheap) unaccounting + * of their reserved space, so don't warn on reserved > 0 in that + * case. + */ + if (!(cache->flags & BTRFS_BLOCK_GROUP_METADATA) || + !BTRFS_FS_LOG_CLEANUP_ERROR(cache->fs_info)) + WARN_ON(cache->reserved > 0); /* * A block_group shouldn't be on the discard_list anymore. @@ -2544,6 +2553,19 @@ int btrfs_inc_block_group_ro(struct btrfs_block_group *cache, int ret; bool dirty_bg_running; + /* + * This can only happen when we are doing read-only scrub on read-only + * mount. + * In that case we should not start a new transaction on read-only fs. + * Thus here we skip all chunk allocations. + */ + if (sb_rdonly(fs_info->sb)) { + mutex_lock(&fs_info->ro_block_group_mutex); + ret = inc_block_group_ro(cache, 0); + mutex_unlock(&fs_info->ro_block_group_mutex); + return ret; + } + do { trans = btrfs_join_transaction(root); if (IS_ERR(trans)) @@ -3974,9 +3996,22 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) * important and indicates a real bug if this happens. */ if (WARN_ON(space_info->bytes_pinned > 0 || - space_info->bytes_reserved > 0 || space_info->bytes_may_use > 0)) btrfs_dump_space_info(info, space_info, 0, 0); + + /* + * If there was a failure to cleanup a log tree, very likely due + * to an IO failure on a writeback attempt of one or more of its + * extent buffers, we could not do proper (and cheap) unaccounting + * of their reserved space, so don't warn on bytes_reserved > 0 in + * that case. + */ + if (!(space_info->flags & BTRFS_BLOCK_GROUP_METADATA) || + !BTRFS_FS_LOG_CLEANUP_ERROR(info)) { + if (WARN_ON(space_info->bytes_reserved > 0)) + btrfs_dump_space_info(info, space_info, 0, 0); + } + WARN_ON(space_info->reclaim_size > 0); list_del(&space_info->list); btrfs_sysfs_remove_space_info(space_info); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index b4a9b1c58d22..8992e0096163 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -145,6 +145,9 @@ enum { BTRFS_FS_STATE_DUMMY_FS_INFO, BTRFS_FS_STATE_NO_CSUMS, + + /* Indicates there was an error cleaning up a log tree. */ + BTRFS_FS_STATE_LOG_CLEANUP_ERROR, }; #define BTRFS_BACKREF_REV_MAX 256 @@ -3593,6 +3596,9 @@ do { \ #define BTRFS_FS_ERROR(fs_info) (unlikely(test_bit(BTRFS_FS_STATE_ERROR, \ &(fs_info)->fs_state))) +#define BTRFS_FS_LOG_CLEANUP_ERROR(fs_info) \ + (unlikely(test_bit(BTRFS_FS_STATE_LOG_CLEANUP_ERROR, \ + &(fs_info)->fs_state))) __printf(5, 6) __cold diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index d8af6620a941..33eda39df685 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -805,10 +805,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, goto fail; } - spin_lock(&fs_info->trans_lock); - list_add(&pending_snapshot->list, - &trans->transaction->pending_snapshots); - spin_unlock(&fs_info->trans_lock); + trans->pending_snapshot = pending_snapshot; ret = btrfs_commit_transaction(trans); if (ret) @@ -3354,7 +3351,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg) struct block_device *bdev = NULL; fmode_t mode; int ret; - bool cancel; + bool cancel = false; if (!capable(CAP_SYS_ADMIN)) return -EPERM; diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 8928275823a1..f12dc687350c 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1185,9 +1185,24 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) struct btrfs_trans_handle *trans = NULL; int ret = 0; + /* + * We need to have subvol_sem write locked, to prevent races between + * concurrent tasks trying to disable quotas, because we will unlock + * and relock qgroup_ioctl_lock across BTRFS_FS_QUOTA_ENABLED changes. + */ + lockdep_assert_held_write(&fs_info->subvol_sem); + mutex_lock(&fs_info->qgroup_ioctl_lock); if (!fs_info->quota_root) goto out; + + /* + * Request qgroup rescan worker to complete and wait for it. This wait + * must be done before transaction start for quota disable since it may + * deadlock with transaction by the qgroup rescan worker. + */ + clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); + btrfs_qgroup_wait_for_completion(fs_info, false); mutex_unlock(&fs_info->qgroup_ioctl_lock); /* @@ -1205,14 +1220,13 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) if (IS_ERR(trans)) { ret = PTR_ERR(trans); trans = NULL; + set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); goto out; } if (!fs_info->quota_root) goto out; - clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); - btrfs_qgroup_wait_for_completion(fs_info, false); spin_lock(&fs_info->qgroup_lock); quota_root = fs_info->quota_root; fs_info->quota_root = NULL; @@ -3383,6 +3397,9 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid, btrfs_warn(fs_info, "qgroup rescan init failed, qgroup is not enabled"); ret = -EINVAL; + } else if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) { + /* Quota disable is in progress */ + ret = -EBUSY; } if (ret) { diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 03de89b45f27..c43bbc7f623e 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -2000,6 +2000,27 @@ static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info) btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); } +/* + * Add a pending snapshot associated with the given transaction handle to the + * respective handle. This must be called after the transaction commit started + * and while holding fs_info->trans_lock. + * This serves to guarantee a caller of btrfs_commit_transaction() that it can + * safely free the pending snapshot pointer in case btrfs_commit_transaction() + * returns an error. + */ +static void add_pending_snapshot(struct btrfs_trans_handle *trans) +{ + struct btrfs_transaction *cur_trans = trans->transaction; + + if (!trans->pending_snapshot) + return; + + lockdep_assert_held(&trans->fs_info->trans_lock); + ASSERT(cur_trans->state >= TRANS_STATE_COMMIT_START); + + list_add(&trans->pending_snapshot->list, &cur_trans->pending_snapshots); +} + int btrfs_commit_transaction(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; @@ -2073,6 +2094,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) if (cur_trans->state >= TRANS_STATE_COMMIT_START) { enum btrfs_trans_state want_state = TRANS_STATE_COMPLETED; + add_pending_snapshot(trans); + spin_unlock(&fs_info->trans_lock); refcount_inc(&cur_trans->use_count); @@ -2163,6 +2186,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans) * COMMIT_DOING so make sure to wait for num_writers to == 1 again. */ spin_lock(&fs_info->trans_lock); + add_pending_snapshot(trans); cur_trans->state = TRANS_STATE_COMMIT_DOING; spin_unlock(&fs_info->trans_lock); wait_event(cur_trans->writer_wait, diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 1852ed9de7fd..9402d8d94484 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -123,6 +123,8 @@ struct btrfs_trans_handle { struct btrfs_transaction *transaction; struct btrfs_block_rsv *block_rsv; struct btrfs_block_rsv *orig_rsv; + /* Set by a task that wants to create a snapshot. */ + struct btrfs_pending_snapshot *pending_snapshot; refcount_t use_count; unsigned int type; /* diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 72e1c942197d..9fd145f1c4bc 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -965,6 +965,7 @@ static int check_dev_item(struct extent_buffer *leaf, struct btrfs_key *key, int slot) { struct btrfs_dev_item *ditem; + const u32 item_size = btrfs_item_size(leaf, slot); if (unlikely(key->objectid != BTRFS_DEV_ITEMS_OBJECTID)) { dev_item_err(leaf, slot, @@ -972,6 +973,13 @@ static int check_dev_item(struct extent_buffer *leaf, key->objectid, BTRFS_DEV_ITEMS_OBJECTID); return -EUCLEAN; } + + if (unlikely(item_size != sizeof(*ditem))) { + dev_item_err(leaf, slot, "invalid item size: has %u expect %zu", + item_size, sizeof(*ditem)); + return -EUCLEAN; + } + ditem = btrfs_item_ptr(leaf, slot, struct btrfs_dev_item); if (unlikely(btrfs_device_id(leaf, ditem) != key->offset)) { dev_item_err(leaf, slot, @@ -1007,6 +1015,7 @@ static int check_inode_item(struct extent_buffer *leaf, struct btrfs_inode_item *iitem; u64 super_gen = btrfs_super_generation(fs_info->super_copy); u32 valid_mask = (S_IFMT | S_ISUID | S_ISGID | S_ISVTX | 0777); + const u32 item_size = btrfs_item_size(leaf, slot); u32 mode; int ret; u32 flags; @@ -1016,6 +1025,12 @@ static int check_inode_item(struct extent_buffer *leaf, if (unlikely(ret < 0)) return ret; + if (unlikely(item_size != sizeof(*iitem))) { + generic_err(leaf, slot, "invalid item size: has %u expect %zu", + item_size, sizeof(*iitem)); + return -EUCLEAN; + } + iitem = btrfs_item_ptr(leaf, slot, struct btrfs_inode_item); /* Here we use super block generation + 1 to handle log tree */ diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index c1ddbe800897..3ee014c06b82 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3414,6 +3414,29 @@ static void free_log_tree(struct btrfs_trans_handle *trans, if (log->node) { ret = walk_log_tree(trans, log, &wc); if (ret) { + /* + * We weren't able to traverse the entire log tree, the + * typical scenario is getting an -EIO when reading an + * extent buffer of the tree, due to a previous writeback + * failure of it. + */ + set_bit(BTRFS_FS_STATE_LOG_CLEANUP_ERROR, + &log->fs_info->fs_state); + + /* + * Some extent buffers of the log tree may still be dirty + * and not yet written back to storage, because we may + * have updates to a log tree without syncing a log tree, + * such as during rename and link operations. So flush + * them out and wait for their writeback to complete, so + * that we properly cleanup their state and pages. + */ + btrfs_write_marked_extents(log->fs_info, + &log->dirty_log_pages, + EXTENT_DIRTY | EXTENT_NEW); + btrfs_wait_tree_log_extents(log, + EXTENT_DIRTY | EXTENT_NEW); + if (trans) btrfs_abort_transaction(trans, ret); else diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index 04eb52736990..753986ea1583 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -192,6 +192,64 @@ presubmission_error: } /* + * Query the occupancy of the cache in a region, returning where the next chunk + * of data starts and how long it is. + */ +static int cachefiles_query_occupancy(struct netfs_cache_resources *cres, + loff_t start, size_t len, size_t granularity, + loff_t *_data_start, size_t *_data_len) +{ + struct cachefiles_object *object; + struct file *file; + loff_t off, off2; + + *_data_start = -1; + *_data_len = 0; + + if (!fscache_wait_for_operation(cres, FSCACHE_WANT_READ)) + return -ENOBUFS; + + object = cachefiles_cres_object(cres); + file = cachefiles_cres_file(cres); + granularity = max_t(size_t, object->volume->cache->bsize, granularity); + + _enter("%pD,%li,%llx,%zx/%llx", + file, file_inode(file)->i_ino, start, len, + i_size_read(file_inode(file))); + + off = cachefiles_inject_read_error(); + if (off == 0) + off = vfs_llseek(file, start, SEEK_DATA); + if (off == -ENXIO) + return -ENODATA; /* Beyond EOF */ + if (off < 0 && off >= (loff_t)-MAX_ERRNO) + return -ENOBUFS; /* Error. */ + if (round_up(off, granularity) >= start + len) + return -ENODATA; /* No data in range */ + + off2 = cachefiles_inject_read_error(); + if (off2 == 0) + off2 = vfs_llseek(file, off, SEEK_HOLE); + if (off2 == -ENXIO) + return -ENODATA; /* Beyond EOF */ + if (off2 < 0 && off2 >= (loff_t)-MAX_ERRNO) + return -ENOBUFS; /* Error. */ + + /* Round away partial blocks */ + off = round_up(off, granularity); + off2 = round_down(off2, granularity); + if (off2 <= off) + return -ENODATA; + + *_data_start = off; + if (off2 > start + len) + *_data_len = len; + else + *_data_len = off2 - off; + return 0; +} + +/* * Handle completion of a write to the cache. */ static void cachefiles_write_complete(struct kiocb *iocb, long ret) @@ -545,6 +603,7 @@ static const struct netfs_cache_ops cachefiles_netfs_cache_ops = { .write = cachefiles_write, .prepare_read = cachefiles_prepare_read, .prepare_write = cachefiles_prepare_write, + .query_occupancy = cachefiles_query_occupancy, }; /* diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 11a22a30ee14..0b742bd50642 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -162,7 +162,7 @@ static void cifs_resolve_server(struct work_struct *work) mutex_unlock(&server->srv_mutex); } -/** +/* * Mark all sessions and tcons for reconnect. * * @server needs to be previously set to CifsNeedReconnect. @@ -1831,13 +1831,9 @@ void cifs_put_smb_ses(struct cifs_ses *ses) int i; for (i = 1; i < chan_count; i++) { - /* - * note: for now, we're okay accessing ses->chans - * without chan_lock. But when chans can go away, we'll - * need to introduce ref counting to make sure that chan - * is not freed from under us. - */ + spin_unlock(&ses->chan_lock); cifs_put_tcp_session(ses->chans[i].server, 0); + spin_lock(&ses->chan_lock); ses->chans[i].server = NULL; } } @@ -1981,6 +1977,19 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses) } } + ctx->workstation_name = kstrdup(ses->workstation_name, GFP_KERNEL); + if (!ctx->workstation_name) { + cifs_dbg(FYI, "Unable to allocate memory for workstation_name\n"); + rc = -ENOMEM; + kfree(ctx->username); + ctx->username = NULL; + kfree_sensitive(ctx->password); + ctx->password = NULL; + kfree(ctx->domainname); + ctx->domainname = NULL; + goto out_key_put; + } + out_key_put: up_read(&key->sem); key_put(key); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 59334be9ed3b..e7af802dcfa6 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4269,8 +4269,6 @@ cifs_readv_complete(struct work_struct *work) for (i = 0; i < rdata->nr_pages; i++) { struct page *page = rdata->pages[i]; - lru_cache_add(page); - if (rdata->result == 0 || (rdata->result == -EAGAIN && got_bytes)) { flush_dcache_page(page); @@ -4278,12 +4276,12 @@ cifs_readv_complete(struct work_struct *work) } else SetPageError(page); - unlock_page(page); - if (rdata->result == 0 || (rdata->result == -EAGAIN && got_bytes)) cifs_readpage_to_fscache(rdata->mapping->host, page); + unlock_page(page); + got_bytes -= min_t(unsigned int, PAGE_SIZE, got_bytes); put_page(page); @@ -4340,7 +4338,6 @@ readpages_fill_pages(struct TCP_Server_Info *server, * fill them until the writes are flushed. */ zero_user(page, 0, PAGE_SIZE); - lru_cache_add(page); flush_dcache_page(page); SetPageUptodate(page); unlock_page(page); @@ -4350,7 +4347,6 @@ readpages_fill_pages(struct TCP_Server_Info *server, continue; } else { /* no need to hold page hostage */ - lru_cache_add(page); unlock_page(page); put_page(page); rdata->pages[i] = NULL; @@ -4393,92 +4389,20 @@ cifs_readpages_copy_into_pages(struct TCP_Server_Info *server, return readpages_fill_pages(server, rdata, iter, iter->count); } -static int -readpages_get_pages(struct address_space *mapping, struct list_head *page_list, - unsigned int rsize, struct list_head *tmplist, - unsigned int *nr_pages, loff_t *offset, unsigned int *bytes) -{ - struct page *page, *tpage; - unsigned int expected_index; - int rc; - gfp_t gfp = readahead_gfp_mask(mapping); - - INIT_LIST_HEAD(tmplist); - - page = lru_to_page(page_list); - - /* - * Lock the page and put it in the cache. Since no one else - * should have access to this page, we're safe to simply set - * PG_locked without checking it first. - */ - __SetPageLocked(page); - rc = add_to_page_cache_locked(page, mapping, - page->index, gfp); - - /* give up if we can't stick it in the cache */ - if (rc) { - __ClearPageLocked(page); - return rc; - } - - /* move first page to the tmplist */ - *offset = (loff_t)page->index << PAGE_SHIFT; - *bytes = PAGE_SIZE; - *nr_pages = 1; - list_move_tail(&page->lru, tmplist); - - /* now try and add more pages onto the request */ - expected_index = page->index + 1; - list_for_each_entry_safe_reverse(page, tpage, page_list, lru) { - /* discontinuity ? */ - if (page->index != expected_index) - break; - - /* would this page push the read over the rsize? */ - if (*bytes + PAGE_SIZE > rsize) - break; - - __SetPageLocked(page); - rc = add_to_page_cache_locked(page, mapping, page->index, gfp); - if (rc) { - __ClearPageLocked(page); - break; - } - list_move_tail(&page->lru, tmplist); - (*bytes) += PAGE_SIZE; - expected_index++; - (*nr_pages)++; - } - return rc; -} - -static int cifs_readpages(struct file *file, struct address_space *mapping, - struct list_head *page_list, unsigned num_pages) +static void cifs_readahead(struct readahead_control *ractl) { int rc; - int err = 0; - struct list_head tmplist; - struct cifsFileInfo *open_file = file->private_data; - struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); + struct cifsFileInfo *open_file = ractl->file->private_data; + struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(ractl->file); struct TCP_Server_Info *server; pid_t pid; - unsigned int xid; + unsigned int xid, nr_pages, last_batch_size = 0, cache_nr_pages = 0; + pgoff_t next_cached = ULONG_MAX; + bool caching = fscache_cookie_enabled(cifs_inode_cookie(ractl->mapping->host)) && + cifs_inode_cookie(ractl->mapping->host)->cache_priv; + bool check_cache = caching; xid = get_xid(); - /* - * Reads as many pages as possible from fscache. Returns -ENOBUFS - * immediately if the cookie is negative - * - * After this point, every page in the list might have PG_fscache set, - * so we will need to clean that up off of every page we don't use. - */ - rc = cifs_readpages_from_fscache(mapping->host, mapping, page_list, - &num_pages); - if (rc == 0) { - free_xid(xid); - return rc; - } if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) pid = open_file->pid; @@ -4489,39 +4413,73 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, server = cifs_pick_channel(tlink_tcon(open_file->tlink)->ses); cifs_dbg(FYI, "%s: file=%p mapping=%p num_pages=%u\n", - __func__, file, mapping, num_pages); + __func__, ractl->file, ractl->mapping, readahead_count(ractl)); /* - * Start with the page at end of list and move it to private - * list. Do the same with any following pages until we hit - * the rsize limit, hit an index discontinuity, or run out of - * pages. Issue the async read and then start the loop again - * until the list is empty. - * - * Note that list order is important. The page_list is in - * the order of declining indexes. When we put the pages in - * the rdata->pages, then we want them in increasing order. + * Chop the readahead request up into rsize-sized read requests. */ - while (!list_empty(page_list) && !err) { - unsigned int i, nr_pages, bytes, rsize; - loff_t offset; - struct page *page, *tpage; + while ((nr_pages = readahead_count(ractl) - last_batch_size)) { + unsigned int i, got, rsize; + struct page *page; struct cifs_readdata *rdata; struct cifs_credits credits_on_stack; struct cifs_credits *credits = &credits_on_stack; + pgoff_t index = readahead_index(ractl) + last_batch_size; + + /* + * Find out if we have anything cached in the range of + * interest, and if so, where the next chunk of cached data is. + */ + if (caching) { + if (check_cache) { + rc = cifs_fscache_query_occupancy( + ractl->mapping->host, index, nr_pages, + &next_cached, &cache_nr_pages); + if (rc < 0) + caching = false; + check_cache = false; + } + + if (index == next_cached) { + /* + * TODO: Send a whole batch of pages to be read + * by the cache. + */ + page = readahead_page(ractl); + last_batch_size = 1 << thp_order(page); + if (cifs_readpage_from_fscache(ractl->mapping->host, + page) < 0) { + /* + * TODO: Deal with cache read failure + * here, but for the moment, delegate + * that to readpage. + */ + caching = false; + } + unlock_page(page); + next_cached++; + cache_nr_pages--; + if (cache_nr_pages == 0) + check_cache = true; + continue; + } + } if (open_file->invalidHandle) { rc = cifs_reopen_file(open_file, true); - if (rc == -EAGAIN) - continue; - else if (rc) + if (rc) { + if (rc == -EAGAIN) + continue; break; + } } rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize, &rsize, credits); if (rc) break; + nr_pages = min_t(size_t, rsize / PAGE_SIZE, readahead_count(ractl)); + nr_pages = min_t(size_t, nr_pages, next_cached - index); /* * Give up immediately if rsize is too small to read an entire @@ -4529,16 +4487,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, * reach this point however since we set ra_pages to 0 when the * rsize is smaller than a cache page. */ - if (unlikely(rsize < PAGE_SIZE)) { - add_credits_and_wake_if(server, credits, 0); - free_xid(xid); - return 0; - } - - nr_pages = 0; - err = readpages_get_pages(mapping, page_list, rsize, &tmplist, - &nr_pages, &offset, &bytes); - if (!nr_pages) { + if (unlikely(!nr_pages)) { add_credits_and_wake_if(server, credits, 0); break; } @@ -4546,36 +4495,31 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, rdata = cifs_readdata_alloc(nr_pages, cifs_readv_complete); if (!rdata) { /* best to give up if we're out of mem */ - list_for_each_entry_safe(page, tpage, &tmplist, lru) { - list_del(&page->lru); - lru_cache_add(page); - unlock_page(page); - put_page(page); - } - rc = -ENOMEM; add_credits_and_wake_if(server, credits, 0); break; } - rdata->cfile = cifsFileInfo_get(open_file); - rdata->server = server; - rdata->mapping = mapping; - rdata->offset = offset; - rdata->bytes = bytes; - rdata->pid = pid; - rdata->pagesz = PAGE_SIZE; - rdata->tailsz = PAGE_SIZE; + got = __readahead_batch(ractl, rdata->pages, nr_pages); + if (got != nr_pages) { + pr_warn("__readahead_batch() returned %u/%u\n", + got, nr_pages); + nr_pages = got; + } + + rdata->nr_pages = nr_pages; + rdata->bytes = readahead_batch_length(ractl); + rdata->cfile = cifsFileInfo_get(open_file); + rdata->server = server; + rdata->mapping = ractl->mapping; + rdata->offset = readahead_pos(ractl); + rdata->pid = pid; + rdata->pagesz = PAGE_SIZE; + rdata->tailsz = PAGE_SIZE; rdata->read_into_pages = cifs_readpages_read_into_pages; rdata->copy_into_pages = cifs_readpages_copy_into_pages; - rdata->credits = credits_on_stack; - - list_for_each_entry_safe(page, tpage, &tmplist, lru) { - list_del(&page->lru); - rdata->pages[rdata->nr_pages++] = page; - } + rdata->credits = credits_on_stack; rc = adjust_credits(server, &rdata->credits, rdata->bytes); - if (!rc) { if (rdata->cfile->invalidHandle) rc = -EAGAIN; @@ -4587,7 +4531,6 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, add_credits_and_wake_if(server, &rdata->credits, 0); for (i = 0; i < rdata->nr_pages; i++) { page = rdata->pages[i]; - lru_cache_add(page); unlock_page(page); put_page(page); } @@ -4597,10 +4540,10 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, } kref_put(&rdata->refcount, cifs_readdata_release); + last_batch_size = nr_pages; } free_xid(xid); - return rc; } /* @@ -4924,7 +4867,7 @@ oplock_break_done: * In the non-cached mode (mount with cache=none), we shunt off direct read and write requests * so this method should never be called. * - * Direct IO is not yet supported in the cached mode. + * Direct IO is not yet supported in the cached mode. */ static ssize_t cifs_direct_io(struct kiocb *iocb, struct iov_iter *iter) @@ -5006,7 +4949,7 @@ static int cifs_set_page_dirty(struct page *page) const struct address_space_operations cifs_addr_ops = { .readpage = cifs_readpage, - .readpages = cifs_readpages, + .readahead = cifs_readahead, .writepage = cifs_writepage, .writepages = cifs_writepages, .write_begin = cifs_write_begin, diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index efaac4d5ff55..33af72e0ac0c 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -134,37 +134,127 @@ void cifs_fscache_release_inode_cookie(struct inode *inode) } } +static inline void fscache_end_operation(struct netfs_cache_resources *cres) +{ + const struct netfs_cache_ops *ops = fscache_operation_valid(cres); + + if (ops) + ops->end_operation(cres); +} + /* - * Retrieve a page from FS-Cache + * Fallback page reading interface. */ -int __cifs_readpage_from_fscache(struct inode *inode, struct page *page) +static int fscache_fallback_read_page(struct inode *inode, struct page *page) { - cifs_dbg(FYI, "%s: (fsc:%p, p:%p, i:0x%p\n", - __func__, CIFS_I(inode)->fscache, page, inode); - return -ENOBUFS; // Needs conversion to using netfslib + struct netfs_cache_resources cres; + struct fscache_cookie *cookie = cifs_inode_cookie(inode); + struct iov_iter iter; + struct bio_vec bvec[1]; + int ret; + + memset(&cres, 0, sizeof(cres)); + bvec[0].bv_page = page; + bvec[0].bv_offset = 0; + bvec[0].bv_len = PAGE_SIZE; + iov_iter_bvec(&iter, READ, bvec, ARRAY_SIZE(bvec), PAGE_SIZE); + + ret = fscache_begin_read_operation(&cres, cookie); + if (ret < 0) + return ret; + + ret = fscache_read(&cres, page_offset(page), &iter, NETFS_READ_HOLE_FAIL, + NULL, NULL); + fscache_end_operation(&cres); + return ret; } /* - * Retrieve a set of pages from FS-Cache + * Fallback page writing interface. */ -int __cifs_readpages_from_fscache(struct inode *inode, - struct address_space *mapping, - struct list_head *pages, - unsigned *nr_pages) +static int fscache_fallback_write_page(struct inode *inode, struct page *page, + bool no_space_allocated_yet) { - cifs_dbg(FYI, "%s: (0x%p/%u/0x%p)\n", - __func__, CIFS_I(inode)->fscache, *nr_pages, inode); - return -ENOBUFS; // Needs conversion to using netfslib + struct netfs_cache_resources cres; + struct fscache_cookie *cookie = cifs_inode_cookie(inode); + struct iov_iter iter; + struct bio_vec bvec[1]; + loff_t start = page_offset(page); + size_t len = PAGE_SIZE; + int ret; + + memset(&cres, 0, sizeof(cres)); + bvec[0].bv_page = page; + bvec[0].bv_offset = 0; + bvec[0].bv_len = PAGE_SIZE; + iov_iter_bvec(&iter, WRITE, bvec, ARRAY_SIZE(bvec), PAGE_SIZE); + + ret = fscache_begin_write_operation(&cres, cookie); + if (ret < 0) + return ret; + + ret = cres.ops->prepare_write(&cres, &start, &len, i_size_read(inode), + no_space_allocated_yet); + if (ret == 0) + ret = fscache_write(&cres, page_offset(page), &iter, NULL, NULL); + fscache_end_operation(&cres); + return ret; } -void __cifs_readpage_to_fscache(struct inode *inode, struct page *page) +/* + * Retrieve a page from FS-Cache + */ +int __cifs_readpage_from_fscache(struct inode *inode, struct page *page) { - struct cifsInodeInfo *cifsi = CIFS_I(inode); + int ret; - WARN_ON(!cifsi->fscache); + cifs_dbg(FYI, "%s: (fsc:%p, p:%p, i:0x%p\n", + __func__, cifs_inode_cookie(inode), page, inode); + ret = fscache_fallback_read_page(inode, page); + if (ret < 0) + return ret; + + /* Read completed synchronously */ + SetPageUptodate(page); + return 0; +} + +void __cifs_readpage_to_fscache(struct inode *inode, struct page *page) +{ cifs_dbg(FYI, "%s: (fsc: %p, p: %p, i: %p)\n", - __func__, cifsi->fscache, page, inode); + __func__, cifs_inode_cookie(inode), page, inode); + + fscache_fallback_write_page(inode, page, true); +} + +/* + * Query the cache occupancy. + */ +int __cifs_fscache_query_occupancy(struct inode *inode, + pgoff_t first, unsigned int nr_pages, + pgoff_t *_data_first, + unsigned int *_data_nr_pages) +{ + struct netfs_cache_resources cres; + struct fscache_cookie *cookie = cifs_inode_cookie(inode); + loff_t start, data_start; + size_t len, data_len; + int ret; - // Needs conversion to using netfslib + ret = fscache_begin_read_operation(&cres, cookie); + if (ret < 0) + return ret; + + start = first * PAGE_SIZE; + len = nr_pages * PAGE_SIZE; + ret = cres.ops->query_occupancy(&cres, start, len, PAGE_SIZE, + &data_start, &data_len); + if (ret == 0) { + *_data_first = data_start / PAGE_SIZE; + *_data_nr_pages = len / PAGE_SIZE; + } + + fscache_end_operation(&cres); + return ret; } diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h index c6ca49ac33d4..55129908e2c1 100644 --- a/fs/cifs/fscache.h +++ b/fs/cifs/fscache.h @@ -9,6 +9,7 @@ #ifndef _CIFS_FSCACHE_H #define _CIFS_FSCACHE_H +#include <linux/swap.h> #include <linux/fscache.h> #include "cifsglob.h" @@ -58,14 +59,6 @@ void cifs_fscache_fill_coherency(struct inode *inode, } -extern int cifs_fscache_release_page(struct page *page, gfp_t gfp); -extern int __cifs_readpage_from_fscache(struct inode *, struct page *); -extern int __cifs_readpages_from_fscache(struct inode *, - struct address_space *, - struct list_head *, - unsigned *); -extern void __cifs_readpage_to_fscache(struct inode *, struct page *); - static inline struct fscache_cookie *cifs_inode_cookie(struct inode *inode) { return CIFS_I(inode)->fscache; @@ -80,33 +73,52 @@ static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags i_size_read(inode), flags); } -static inline int cifs_readpage_from_fscache(struct inode *inode, - struct page *page) -{ - if (CIFS_I(inode)->fscache) - return __cifs_readpage_from_fscache(inode, page); +extern int __cifs_fscache_query_occupancy(struct inode *inode, + pgoff_t first, unsigned int nr_pages, + pgoff_t *_data_first, + unsigned int *_data_nr_pages); - return -ENOBUFS; +static inline int cifs_fscache_query_occupancy(struct inode *inode, + pgoff_t first, unsigned int nr_pages, + pgoff_t *_data_first, + unsigned int *_data_nr_pages) +{ + if (!cifs_inode_cookie(inode)) + return -ENOBUFS; + return __cifs_fscache_query_occupancy(inode, first, nr_pages, + _data_first, _data_nr_pages); } -static inline int cifs_readpages_from_fscache(struct inode *inode, - struct address_space *mapping, - struct list_head *pages, - unsigned *nr_pages) +extern int __cifs_readpage_from_fscache(struct inode *pinode, struct page *ppage); +extern void __cifs_readpage_to_fscache(struct inode *pinode, struct page *ppage); + + +static inline int cifs_readpage_from_fscache(struct inode *inode, + struct page *page) { - if (CIFS_I(inode)->fscache) - return __cifs_readpages_from_fscache(inode, mapping, pages, - nr_pages); + if (cifs_inode_cookie(inode)) + return __cifs_readpage_from_fscache(inode, page); return -ENOBUFS; } static inline void cifs_readpage_to_fscache(struct inode *inode, struct page *page) { - if (PageFsCache(page)) + if (cifs_inode_cookie(inode)) __cifs_readpage_to_fscache(inode, page); } +static inline int cifs_fscache_release_page(struct page *page, gfp_t gfp) +{ + if (PageFsCache(page)) { + if (current_is_kswapd() || !(gfp & __GFP_FS)) + return false; + wait_on_page_fscache(page); + fscache_note_page_release(cifs_inode_cookie(page->mapping->host)); + } + return true; +} + #else /* CONFIG_CIFS_FSCACHE */ static inline void cifs_fscache_fill_coherency(struct inode *inode, @@ -123,22 +135,29 @@ static inline void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool upd static inline struct fscache_cookie *cifs_inode_cookie(struct inode *inode) { return NULL; } static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags) {} -static inline int -cifs_readpage_from_fscache(struct inode *inode, struct page *page) +static inline int cifs_fscache_query_occupancy(struct inode *inode, + pgoff_t first, unsigned int nr_pages, + pgoff_t *_data_first, + unsigned int *_data_nr_pages) { + *_data_first = ULONG_MAX; + *_data_nr_pages = 0; return -ENOBUFS; } -static inline int cifs_readpages_from_fscache(struct inode *inode, - struct address_space *mapping, - struct list_head *pages, - unsigned *nr_pages) +static inline int +cifs_readpage_from_fscache(struct inode *inode, struct page *page) { return -ENOBUFS; } -static inline void cifs_readpage_to_fscache(struct inode *inode, - struct page *page) {} +static inline +void cifs_readpage_to_fscache(struct inode *inode, struct page *page) {} + +static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) +{ + return true; /* May release page */ +} #endif /* CONFIG_CIFS_FSCACHE */ diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 7d8b3ceb2af3..60d853c92f6a 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -83,6 +83,7 @@ static void cifs_set_ops(struct inode *inode) static void cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr) { + struct cifs_fscache_inode_coherency_data cd; struct cifsInodeInfo *cifs_i = CIFS_I(inode); cifs_dbg(FYI, "%s: revalidating inode %llu\n", @@ -113,6 +114,9 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr) cifs_dbg(FYI, "%s: invalidating inode %llu mapping\n", __func__, cifs_i->uniqueid); set_bit(CIFS_INO_INVALID_MAPPING, &cifs_i->flags); + /* Invalidate fscache cookie */ + cifs_fscache_fill_coherency(&cifs_i->vfs_inode, &cd); + fscache_invalidate(cifs_inode_cookie(inode), &cd, i_size_read(inode), 0); } /* @@ -2261,8 +2265,6 @@ cifs_dentry_needs_reval(struct dentry *dentry) int cifs_invalidate_mapping(struct inode *inode) { - struct cifs_fscache_inode_coherency_data cd; - struct cifsInodeInfo *cifsi = CIFS_I(inode); int rc = 0; if (inode->i_mapping && inode->i_mapping->nrpages != 0) { @@ -2272,8 +2274,6 @@ cifs_invalidate_mapping(struct inode *inode) __func__, inode); } - cifs_fscache_fill_coherency(&cifsi->vfs_inode, &cd); - fscache_invalidate(cifs_inode_cookie(inode), &cd, i_size_read(inode), 0); return rc; } diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index dc3b16d1be09..5723d50340e5 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -713,7 +713,11 @@ static int size_of_ntlmssp_blob(struct cifs_ses *ses, int base_size) else sz += sizeof(__le16); - sz += sizeof(__le16) * strnlen(ses->workstation_name, CIFS_MAX_WORKSTATION_LEN); + if (ses->workstation_name) + sz += sizeof(__le16) * strnlen(ses->workstation_name, + CIFS_MAX_WORKSTATION_LEN); + else + sz += sizeof(__le16); return sz; } diff --git a/fs/erofs/data.c b/fs/erofs/data.c index fa7ddb7ad980..226a57c57ee6 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -252,12 +252,10 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, return ret; iomap->offset = map.m_la; - if (flags & IOMAP_DAX) { + if (flags & IOMAP_DAX) iomap->dax_dev = mdev.m_daxdev; - iomap->offset += mdev.m_dax_part_off; - } else { + else iomap->bdev = mdev.m_bdev; - } iomap->length = map.m_llen; iomap->flags = 0; iomap->private = NULL; @@ -284,6 +282,8 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, } else { iomap->type = IOMAP_MAPPED; iomap->addr = mdev.m_pa; + if (flags & IOMAP_DAX) + iomap->addr += mdev.m_dax_part_off; } return 0; } diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 498b7666efe8..423bc1a61da5 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -810,68 +810,11 @@ static bool z_erofs_get_sync_decompress_policy(struct erofs_sb_info *sbi, return false; } -static void z_erofs_decompressqueue_work(struct work_struct *work); -static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, - bool sync, int bios) -{ - struct erofs_sb_info *const sbi = EROFS_SB(io->sb); - - /* wake up the caller thread for sync decompression */ - if (sync) { - unsigned long flags; - - spin_lock_irqsave(&io->u.wait.lock, flags); - if (!atomic_add_return(bios, &io->pending_bios)) - wake_up_locked(&io->u.wait); - spin_unlock_irqrestore(&io->u.wait.lock, flags); - return; - } - - if (atomic_add_return(bios, &io->pending_bios)) - return; - /* Use workqueue and sync decompression for atomic contexts only */ - if (in_atomic() || irqs_disabled()) { - queue_work(z_erofs_workqueue, &io->u.work); - /* enable sync decompression for readahead */ - if (sbi->opt.sync_decompress == EROFS_SYNC_DECOMPRESS_AUTO) - sbi->opt.sync_decompress = EROFS_SYNC_DECOMPRESS_FORCE_ON; - return; - } - z_erofs_decompressqueue_work(&io->u.work); -} - static bool z_erofs_page_is_invalidated(struct page *page) { return !page->mapping && !z_erofs_is_shortlived_page(page); } -static void z_erofs_decompressqueue_endio(struct bio *bio) -{ - tagptr1_t t = tagptr_init(tagptr1_t, bio->bi_private); - struct z_erofs_decompressqueue *q = tagptr_unfold_ptr(t); - blk_status_t err = bio->bi_status; - struct bio_vec *bvec; - struct bvec_iter_all iter_all; - - bio_for_each_segment_all(bvec, bio, iter_all) { - struct page *page = bvec->bv_page; - - DBG_BUGON(PageUptodate(page)); - DBG_BUGON(z_erofs_page_is_invalidated(page)); - - if (err) - SetPageError(page); - - if (erofs_page_is_managed(EROFS_SB(q->sb), page)) { - if (!err) - SetPageUptodate(page); - unlock_page(page); - } - } - z_erofs_decompress_kickoff(q, tagptr_unfold_tags(t), -1); - bio_put(bio); -} - static int z_erofs_decompress_pcluster(struct super_block *sb, struct z_erofs_pcluster *pcl, struct page **pagepool) @@ -1123,6 +1066,35 @@ static void z_erofs_decompressqueue_work(struct work_struct *work) kvfree(bgq); } +static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, + bool sync, int bios) +{ + struct erofs_sb_info *const sbi = EROFS_SB(io->sb); + + /* wake up the caller thread for sync decompression */ + if (sync) { + unsigned long flags; + + spin_lock_irqsave(&io->u.wait.lock, flags); + if (!atomic_add_return(bios, &io->pending_bios)) + wake_up_locked(&io->u.wait); + spin_unlock_irqrestore(&io->u.wait.lock, flags); + return; + } + + if (atomic_add_return(bios, &io->pending_bios)) + return; + /* Use workqueue and sync decompression for atomic contexts only */ + if (in_atomic() || irqs_disabled()) { + queue_work(z_erofs_workqueue, &io->u.work); + /* enable sync decompression for readahead */ + if (sbi->opt.sync_decompress == EROFS_SYNC_DECOMPRESS_AUTO) + sbi->opt.sync_decompress = EROFS_SYNC_DECOMPRESS_FORCE_ON; + return; + } + z_erofs_decompressqueue_work(&io->u.work); +} + static struct page *pickup_page_for_submission(struct z_erofs_pcluster *pcl, unsigned int nr, struct page **pagepool, @@ -1300,6 +1272,33 @@ static void move_to_bypass_jobqueue(struct z_erofs_pcluster *pcl, qtail[JQ_BYPASS] = &pcl->next; } +static void z_erofs_decompressqueue_endio(struct bio *bio) +{ + tagptr1_t t = tagptr_init(tagptr1_t, bio->bi_private); + struct z_erofs_decompressqueue *q = tagptr_unfold_ptr(t); + blk_status_t err = bio->bi_status; + struct bio_vec *bvec; + struct bvec_iter_all iter_all; + + bio_for_each_segment_all(bvec, bio, iter_all) { + struct page *page = bvec->bv_page; + + DBG_BUGON(PageUptodate(page)); + DBG_BUGON(z_erofs_page_is_invalidated(page)); + + if (err) + SetPageError(page); + + if (erofs_page_is_managed(EROFS_SB(q->sb), page)) { + if (!err) + SetPageUptodate(page); + unlock_page(page); + } + } + z_erofs_decompress_kickoff(q, tagptr_unfold_tags(t), -1); + bio_put(bio); +} + static void z_erofs_submit_queue(struct super_block *sb, struct z_erofs_decompress_frontend *f, struct page **pagepool, diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 18d7fd1a5064..361b1d6e4bf9 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -630,6 +630,13 @@ static int z_erofs_do_map_blocks(struct inode *inode, if (endoff >= m.clusterofs) { m.headtype = m.type; map->m_la = (m.lcn << lclusterbits) | m.clusterofs; + /* + * For ztailpacking files, in order to inline data more + * effectively, special EOF lclusters are now supported + * which can have three parts at most. + */ + if (ztailpacking && end > inode->i_size) + end = inode->i_size; break; } /* m.lcn should be >= 1 if endoff < m.clusterofs */ diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index 5a35768d6149..57e82e25f8e2 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -139,7 +139,7 @@ fail: /* * Inode operation get_posix_acl(). * - * inode->i_mutex: don't care + * inode->i_rwsem: don't care */ struct posix_acl * ext4_get_acl(struct inode *inode, int type, bool rcu) @@ -183,7 +183,7 @@ ext4_get_acl(struct inode *inode, int type, bool rcu) /* * Set the access or default ACL of an inode. * - * inode->i_mutex: down unless called from ext4_new_inode + * inode->i_rwsem: down unless called from ext4_new_inode */ static int __ext4_set_acl(handle_t *handle, struct inode *inode, int type, @@ -271,8 +271,8 @@ out_stop: /* * Initialize the ACLs of a new inode. Called from ext4_new_inode. * - * dir->i_mutex: down - * inode->i_mutex: up (access to inode is still exclusive) + * dir->i_rwsem: down + * inode->i_rwsem: up (access to inode is still exclusive) */ int ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 242e74cfb060..bcd3b9bf8069 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1028,7 +1028,7 @@ struct ext4_inode_info { /* * Extended attributes can be read independently of the main file - * data. Taking i_mutex even when reading would cause contention + * data. Taking i_rwsem even when reading would cause contention * between readers of EAs and writers of regular file data, so * instead we synchronize on xattr_sem when reading or changing * EAs. @@ -1750,6 +1750,7 @@ struct ext4_sb_info { spinlock_t s_fc_lock; struct buffer_head *s_fc_bh; struct ext4_fc_stats s_fc_stats; + tid_t s_fc_ineligible_tid; #ifdef CONFIG_EXT4_DEBUG int s_fc_debug_max_replay; #endif @@ -1795,10 +1796,7 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) enum { EXT4_MF_MNTDIR_SAMPLED, EXT4_MF_FS_ABORTED, /* Fatal error detected */ - EXT4_MF_FC_INELIGIBLE, /* Fast commit ineligible */ - EXT4_MF_FC_COMMITTING /* File system underoing a fast - * commit. - */ + EXT4_MF_FC_INELIGIBLE /* Fast commit ineligible */ }; static inline void ext4_set_mount_flag(struct super_block *sb, int bit) @@ -2926,7 +2924,7 @@ void __ext4_fc_track_create(handle_t *handle, struct inode *inode, struct dentry *dentry); void ext4_fc_track_create(handle_t *handle, struct dentry *dentry); void ext4_fc_track_inode(handle_t *handle, struct inode *inode); -void ext4_fc_mark_ineligible(struct super_block *sb, int reason); +void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handle); void ext4_fc_start_update(struct inode *inode); void ext4_fc_stop_update(struct inode *inode); void ext4_fc_del(struct inode *inode); @@ -2935,6 +2933,9 @@ void ext4_fc_replay_cleanup(struct super_block *sb); int ext4_fc_commit(journal_t *journal, tid_t commit_tid); int __init ext4_fc_init_dentry_cache(void); void ext4_fc_destroy_dentry_cache(void); +int ext4_fc_record_regions(struct super_block *sb, int ino, + ext4_lblk_t lblk, ext4_fsblk_t pblk, + int len, int replay); /* mballoc.c */ extern const struct seq_operations ext4_mb_seq_groups_ops; @@ -3407,7 +3408,7 @@ do { \ #define EXT4_FREECLUSTERS_WATERMARK 0 #endif -/* Update i_disksize. Requires i_mutex to avoid races with truncate */ +/* Update i_disksize. Requires i_rwsem to avoid races with truncate */ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize) { WARN_ON_ONCE(S_ISREG(inode->i_mode) && @@ -3418,7 +3419,7 @@ static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize) up_write(&EXT4_I(inode)->i_data_sem); } -/* Update i_size, i_disksize. Requires i_mutex to avoid races with truncate */ +/* Update i_size, i_disksize. Requires i_rwsem to avoid races with truncate */ static inline int ext4_update_inode_size(struct inode *inode, loff_t newsize) { int changed = 0; diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 0e4fa644df01..db2ae4a2b38d 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -491,7 +491,7 @@ static inline int ext4_free_data_revoke_credits(struct inode *inode, int blocks) /* * This function controls whether or not we should try to go down the * dioread_nolock code paths, which makes it safe to avoid taking - * i_mutex for direct I/O reads. This only works for extent-based + * i_rwsem for direct I/O reads. This only works for extent-based * files, and it doesn't work if data journaling is enabled, since the * dioread_nolock code uses b_private to pass information back to the * I/O completion handler, and this conflicts with the jbd's use of diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 74c91da585d7..c0f3f83e0c1b 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -97,7 +97,7 @@ static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped) * Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this * moment, get_block can be called only for blocks inside i_size since * page cache has been already dropped and writes are blocked by - * i_mutex. So we can safely drop the i_data_sem here. + * i_rwsem. So we can safely drop the i_data_sem here. */ BUG_ON(EXT4_JOURNAL(inode) == NULL); ext4_discard_preallocations(inode, 0); @@ -4572,7 +4572,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT; - /* Wait all existing dio workers, newcomers will block on i_mutex */ + /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); /* Preallocate the range including the unaligned edges */ @@ -4738,7 +4738,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) goto out; } - /* Wait all existing dio workers, newcomers will block on i_mutex */ + /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags); @@ -5334,7 +5334,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) ret = PTR_ERR(handle); goto out_mmap; } - ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE); + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle); down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode, 0); @@ -5474,7 +5474,7 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) ret = PTR_ERR(handle); goto out_mmap; } - ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE); + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle); /* Expand file to avoid data loss if there is error while shifting */ inode->i_size += len; @@ -5571,7 +5571,7 @@ out_mutex: * stuff such as page-cache locking consistency, bh mapping consistency or * extent's data copying must be performed by caller. * Locking: - * i_mutex is held for both inodes + * i_rwsem is held for both inodes * i_data_sem is locked for write for both inodes * Assumptions: * All pages from requested range are locked for both inodes @@ -6091,11 +6091,15 @@ int ext4_ext_clear_bb(struct inode *inode) ext4_mb_mark_bb(inode->i_sb, path[j].p_block, 1, 0); + ext4_fc_record_regions(inode->i_sb, inode->i_ino, + 0, path[j].p_block, 1, 1); } ext4_ext_drop_refs(path); kfree(path); } ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0); + ext4_fc_record_regions(inode->i_sb, inode->i_ino, + map.m_lblk, map.m_pblk, map.m_len, 1); } cur = cur + map.m_len; } diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 5ae8026a0c56..7964ee34e322 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -300,18 +300,32 @@ restart: } /* - * Mark file system as fast commit ineligible. This means that next commit - * operation would result in a full jbd2 commit. + * Mark file system as fast commit ineligible, and record latest + * ineligible transaction tid. This means until the recorded + * transaction, commit operation would result in a full jbd2 commit. */ -void ext4_fc_mark_ineligible(struct super_block *sb, int reason) +void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handle) { struct ext4_sb_info *sbi = EXT4_SB(sb); + tid_t tid; if (!test_opt2(sb, JOURNAL_FAST_COMMIT) || (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)) return; ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); + if (handle && !IS_ERR(handle)) + tid = handle->h_transaction->t_tid; + else { + read_lock(&sbi->s_journal->j_state_lock); + tid = sbi->s_journal->j_running_transaction ? + sbi->s_journal->j_running_transaction->t_tid : 0; + read_unlock(&sbi->s_journal->j_state_lock); + } + spin_lock(&sbi->s_fc_lock); + if (sbi->s_fc_ineligible_tid < tid) + sbi->s_fc_ineligible_tid = tid; + spin_unlock(&sbi->s_fc_lock); WARN_ON(reason >= EXT4_FC_REASON_MAX); sbi->s_fc_stats.fc_ineligible_reason_count[reason]++; } @@ -361,7 +375,8 @@ static int ext4_fc_track_template( spin_lock(&sbi->s_fc_lock); if (list_empty(&EXT4_I(inode)->i_fc_list)) list_add_tail(&EXT4_I(inode)->i_fc_list, - (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING)) ? + (sbi->s_journal->j_flags & JBD2_FULL_COMMIT_ONGOING || + sbi->s_journal->j_flags & JBD2_FAST_COMMIT_ONGOING) ? &sbi->s_fc_q[FC_Q_STAGING] : &sbi->s_fc_q[FC_Q_MAIN]); spin_unlock(&sbi->s_fc_lock); @@ -387,7 +402,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) mutex_unlock(&ei->i_fc_lock); node = kmem_cache_alloc(ext4_fc_dentry_cachep, GFP_NOFS); if (!node) { - ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM); + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM, NULL); mutex_lock(&ei->i_fc_lock); return -ENOMEM; } @@ -400,7 +415,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) if (!node->fcd_name.name) { kmem_cache_free(ext4_fc_dentry_cachep, node); ext4_fc_mark_ineligible(inode->i_sb, - EXT4_FC_REASON_NOMEM); + EXT4_FC_REASON_NOMEM, NULL); mutex_lock(&ei->i_fc_lock); return -ENOMEM; } @@ -414,7 +429,8 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) node->fcd_name.len = dentry->d_name.len; spin_lock(&sbi->s_fc_lock); - if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING)) + if (sbi->s_journal->j_flags & JBD2_FULL_COMMIT_ONGOING || + sbi->s_journal->j_flags & JBD2_FAST_COMMIT_ONGOING) list_add_tail(&node->fcd_list, &sbi->s_fc_dentry_q[FC_Q_STAGING]); else @@ -502,7 +518,7 @@ void ext4_fc_track_inode(handle_t *handle, struct inode *inode) if (ext4_should_journal_data(inode)) { ext4_fc_mark_ineligible(inode->i_sb, - EXT4_FC_REASON_INODE_JOURNAL_DATA); + EXT4_FC_REASON_INODE_JOURNAL_DATA, handle); return; } @@ -879,7 +895,6 @@ static int ext4_fc_submit_inode_data_all(journal_t *journal) int ret = 0; spin_lock(&sbi->s_fc_lock); - ext4_set_mount_flag(sb, EXT4_MF_FC_COMMITTING); list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { ext4_set_inode_state(&ei->vfs_inode, EXT4_STATE_FC_COMMITTING); while (atomic_read(&ei->i_fc_updates)) { @@ -1179,7 +1194,7 @@ fallback: * Fast commit cleanup routine. This is called after every fast commit and * full commit. full is true if we are called after a full commit. */ -static void ext4_fc_cleanup(journal_t *journal, int full) +static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid) { struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -1197,7 +1212,8 @@ static void ext4_fc_cleanup(journal_t *journal, int full) list_del_init(&iter->i_fc_list); ext4_clear_inode_state(&iter->vfs_inode, EXT4_STATE_FC_COMMITTING); - ext4_fc_reset_inode(&iter->vfs_inode); + if (iter->i_sync_tid <= tid) + ext4_fc_reset_inode(&iter->vfs_inode); /* Make sure EXT4_STATE_FC_COMMITTING bit is clear */ smp_mb(); #if (BITS_PER_LONG < 64) @@ -1226,8 +1242,10 @@ static void ext4_fc_cleanup(journal_t *journal, int full) list_splice_init(&sbi->s_fc_q[FC_Q_STAGING], &sbi->s_fc_q[FC_Q_MAIN]); - ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING); - ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); + if (tid >= sbi->s_fc_ineligible_tid) { + sbi->s_fc_ineligible_tid = 0; + ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); + } if (full) sbi->s_fc_bytes = 0; @@ -1392,14 +1410,15 @@ static int ext4_fc_record_modified_inode(struct super_block *sb, int ino) if (state->fc_modified_inodes[i] == ino) return 0; if (state->fc_modified_inodes_used == state->fc_modified_inodes_size) { - state->fc_modified_inodes_size += - EXT4_FC_REPLAY_REALLOC_INCREMENT; state->fc_modified_inodes = krealloc( - state->fc_modified_inodes, sizeof(int) * - state->fc_modified_inodes_size, - GFP_KERNEL); + state->fc_modified_inodes, + sizeof(int) * (state->fc_modified_inodes_size + + EXT4_FC_REPLAY_REALLOC_INCREMENT), + GFP_KERNEL); if (!state->fc_modified_inodes) return -ENOMEM; + state->fc_modified_inodes_size += + EXT4_FC_REPLAY_REALLOC_INCREMENT; } state->fc_modified_inodes[state->fc_modified_inodes_used++] = ino; return 0; @@ -1431,7 +1450,9 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl, } inode = NULL; - ext4_fc_record_modified_inode(sb, ino); + ret = ext4_fc_record_modified_inode(sb, ino); + if (ret) + goto out; raw_fc_inode = (struct ext4_inode *) (val + offsetof(struct ext4_fc_inode, fc_raw_inode)); @@ -1563,16 +1584,23 @@ out: } /* - * Record physical disk regions which are in use as per fast commit area. Our - * simple replay phase allocator excludes these regions from allocation. + * Record physical disk regions which are in use as per fast commit area, + * and used by inodes during replay phase. Our simple replay phase + * allocator excludes these regions from allocation. */ -static int ext4_fc_record_regions(struct super_block *sb, int ino, - ext4_lblk_t lblk, ext4_fsblk_t pblk, int len) +int ext4_fc_record_regions(struct super_block *sb, int ino, + ext4_lblk_t lblk, ext4_fsblk_t pblk, int len, int replay) { struct ext4_fc_replay_state *state; struct ext4_fc_alloc_region *region; state = &EXT4_SB(sb)->s_fc_replay_state; + /* + * during replay phase, the fc_regions_valid may not same as + * fc_regions_used, update it when do new additions. + */ + if (replay && state->fc_regions_used != state->fc_regions_valid) + state->fc_regions_used = state->fc_regions_valid; if (state->fc_regions_used == state->fc_regions_size) { state->fc_regions_size += EXT4_FC_REPLAY_REALLOC_INCREMENT; @@ -1590,6 +1618,9 @@ static int ext4_fc_record_regions(struct super_block *sb, int ino, region->pblk = pblk; region->len = len; + if (replay) + state->fc_regions_valid++; + return 0; } @@ -1621,6 +1652,8 @@ static int ext4_fc_replay_add_range(struct super_block *sb, } ret = ext4_fc_record_modified_inode(sb, inode->i_ino); + if (ret) + goto out; start = le32_to_cpu(ex->ee_block); start_pblk = ext4_ext_pblock(ex); @@ -1638,18 +1671,14 @@ static int ext4_fc_replay_add_range(struct super_block *sb, map.m_pblk = 0; ret = ext4_map_blocks(NULL, inode, &map, 0); - if (ret < 0) { - iput(inode); - return 0; - } + if (ret < 0) + goto out; if (ret == 0) { /* Range is not mapped */ path = ext4_find_extent(inode, cur, NULL, 0); - if (IS_ERR(path)) { - iput(inode); - return 0; - } + if (IS_ERR(path)) + goto out; memset(&newex, 0, sizeof(newex)); newex.ee_block = cpu_to_le32(cur); ext4_ext_store_pblock( @@ -1663,10 +1692,8 @@ static int ext4_fc_replay_add_range(struct super_block *sb, up_write((&EXT4_I(inode)->i_data_sem)); ext4_ext_drop_refs(path); kfree(path); - if (ret) { - iput(inode); - return 0; - } + if (ret) + goto out; goto next; } @@ -1679,10 +1706,8 @@ static int ext4_fc_replay_add_range(struct super_block *sb, ret = ext4_ext_replay_update_ex(inode, cur, map.m_len, ext4_ext_is_unwritten(ex), start_pblk + cur - start); - if (ret) { - iput(inode); - return 0; - } + if (ret) + goto out; /* * Mark the old blocks as free since they aren't used * anymore. We maintain an array of all the modified @@ -1702,10 +1727,8 @@ static int ext4_fc_replay_add_range(struct super_block *sb, ext4_ext_is_unwritten(ex), map.m_pblk); ret = ext4_ext_replay_update_ex(inode, cur, map.m_len, ext4_ext_is_unwritten(ex), map.m_pblk); - if (ret) { - iput(inode); - return 0; - } + if (ret) + goto out; /* * We may have split the extent tree while toggling the state. * Try to shrink the extent tree now. @@ -1717,6 +1740,7 @@ next: } ext4_ext_replay_shrink_inode(inode, i_size_read(inode) >> sb->s_blocksize_bits); +out: iput(inode); return 0; } @@ -1746,6 +1770,8 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl, } ret = ext4_fc_record_modified_inode(sb, inode->i_ino); + if (ret) + goto out; jbd_debug(1, "DEL_RANGE, inode %ld, lblk %d, len %d\n", inode->i_ino, le32_to_cpu(lrange.fc_lblk), @@ -1755,10 +1781,8 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl, map.m_len = remaining; ret = ext4_map_blocks(NULL, inode, &map, 0); - if (ret < 0) { - iput(inode); - return 0; - } + if (ret < 0) + goto out; if (ret > 0) { remaining -= ret; cur += ret; @@ -1770,18 +1794,17 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl, } down_write(&EXT4_I(inode)->i_data_sem); - ret = ext4_ext_remove_space(inode, lrange.fc_lblk, - lrange.fc_lblk + lrange.fc_len - 1); + ret = ext4_ext_remove_space(inode, le32_to_cpu(lrange.fc_lblk), + le32_to_cpu(lrange.fc_lblk) + + le32_to_cpu(lrange.fc_len) - 1); up_write(&EXT4_I(inode)->i_data_sem); - if (ret) { - iput(inode); - return 0; - } + if (ret) + goto out; ext4_ext_replay_shrink_inode(inode, i_size_read(inode) >> sb->s_blocksize_bits); ext4_mark_inode_dirty(NULL, inode); +out: iput(inode); - return 0; } @@ -1937,7 +1960,7 @@ static int ext4_fc_replay_scan(journal_t *journal, ret = ext4_fc_record_regions(sb, le32_to_cpu(ext.fc_ino), le32_to_cpu(ex->ee_block), ext4_ext_pblock(ex), - ext4_ext_get_actual_len(ex)); + ext4_ext_get_actual_len(ex), 0); if (ret < 0) break; ret = JBD2_FC_REPLAY_CONTINUE; diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 89efa78ed4b2..07a8c75b65ed 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -696,7 +696,7 @@ static int ext4_ind_trunc_restart_fn(handle_t *handle, struct inode *inode, * Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this * moment, get_block can be called only for blocks inside i_size since * page cache has been already dropped and writes are blocked by - * i_mutex. So we can safely drop the i_data_sem here. + * i_rwsem. So we can safely drop the i_data_sem here. */ BUG_ON(EXT4_JOURNAL(inode) == NULL); ext4_discard_preallocations(inode, 0); diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 635bcf68a67e..e42941803605 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -911,7 +911,7 @@ int ext4_da_write_inline_data_begin(struct address_space *mapping, struct page **pagep, void **fsdata) { - int ret, inline_size; + int ret; handle_t *handle; struct page *page; struct ext4_iloc iloc; @@ -928,14 +928,9 @@ retry_journal: goto out; } - inline_size = ext4_get_max_inline_size(inode); - - ret = -ENOSPC; - if (inline_size >= pos + len) { - ret = ext4_prepare_inline_data(handle, inode, pos + len); - if (ret && ret != -ENOSPC) - goto out_journal; - } + ret = ext4_prepare_inline_data(handle, inode, pos + len); + if (ret && ret != -ENOSPC) + goto out_journal; /* * We cannot recurse into the filesystem as the transaction @@ -1133,7 +1128,15 @@ static void ext4_restore_inline_data(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc, void *buf, int inline_size) { - ext4_create_inline_data(handle, inode, inline_size); + int ret; + + ret = ext4_create_inline_data(handle, inode, inline_size); + if (ret) { + ext4_msg(inode->i_sb, KERN_EMERG, + "error restoring inline_data for inode -- potential data loss! (inode %lu, error %d)", + inode->i_ino, ret); + return; + } ext4_write_inline_data(inode, iloc, buf, 0, inline_size); ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 5f79d265d06a..01c9e4f743ba 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -338,7 +338,7 @@ stop_handle: return; no_delete: if (!list_empty(&EXT4_I(inode)->i_fc_list)) - ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM); + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM, NULL); ext4_clear_inode(inode); /* We must guarantee clearing of inode... */ } @@ -1224,7 +1224,7 @@ retry_journal: /* * __block_write_begin may have instantiated a few blocks * outside i_size. Trim these off again. Don't need - * i_size_read because we hold i_mutex. + * i_size_read because we hold i_rwsem. * * Add inode to orphan list in case we crash before * truncate finishes @@ -3979,7 +3979,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) } - /* Wait all existing dio workers, newcomers will block on i_mutex */ + /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); /* @@ -4129,7 +4129,7 @@ int ext4_truncate(struct inode *inode) /* * There is a possibility that we're either freeing the inode * or it's a completely new inode. In those cases we might not - * have i_mutex locked because it's not necessary. + * have i_rwsem locked because it's not necessary. */ if (!(inode->i_state & (I_NEW|I_FREEING))) WARN_ON(!inode_is_locked(inode)); @@ -5271,7 +5271,7 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode) * transaction are already on disk (truncate waits for pages under * writeback). * - * Called with inode->i_mutex down. + * Called with inode->i_rwsem down. */ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, struct iattr *attr) @@ -5983,7 +5983,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) return PTR_ERR(handle); ext4_fc_mark_ineligible(inode->i_sb, - EXT4_FC_REASON_JOURNAL_FLAG_CHANGE); + EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, handle); err = ext4_mark_inode_dirty(handle, inode); ext4_handle_sync(handle); ext4_journal_stop(handle); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index bbbedf27b71c..a8022c2c6a58 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -411,7 +411,7 @@ static long swap_inode_boot_loader(struct super_block *sb, err = -EINVAL; goto err_out; } - ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_SWAP_BOOT); + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_SWAP_BOOT, handle); /* Protect extent tree against block allocations via delalloc */ ext4_double_down_write_data_sem(inode, inode_bl); @@ -1373,7 +1373,7 @@ mext_out: err = ext4_resize_fs(sb, n_blocks_count); if (EXT4_SB(sb)->s_journal) { - ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_RESIZE); + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_RESIZE, NULL); jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 9f86dd947032..67ac95c4cd9b 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5753,7 +5753,8 @@ static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle, struct super_block *sb = ar->inode->i_sb; ext4_group_t group; ext4_grpblk_t blkoff; - int i = sb->s_blocksize; + ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb); + ext4_grpblk_t i = 0; ext4_fsblk_t goal, block; struct ext4_super_block *es = EXT4_SB(sb)->s_es; @@ -5775,19 +5776,26 @@ static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle, ext4_get_group_no_and_offset(sb, max(ext4_group_first_block_no(sb, group), goal), NULL, &blkoff); - i = mb_find_next_zero_bit(bitmap_bh->b_data, sb->s_blocksize, + while (1) { + i = mb_find_next_zero_bit(bitmap_bh->b_data, max, blkoff); + if (i >= max) + break; + if (ext4_fc_replay_check_excluded(sb, + ext4_group_first_block_no(sb, group) + i)) { + blkoff = i + 1; + } else + break; + } brelse(bitmap_bh); - if (i >= sb->s_blocksize) - continue; - if (ext4_fc_replay_check_excluded(sb, - ext4_group_first_block_no(sb, group) + i)) - continue; - break; + if (i < max) + break; } - if (group >= ext4_get_groups_count(sb) && i >= sb->s_blocksize) + if (group >= ext4_get_groups_count(sb) || i >= max) { + *errp = -ENOSPC; return 0; + } block = ext4_group_first_block_no(sb, group) + i; ext4_mb_mark_bb(sb, block, 1, 1); diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index ff8916e1d38e..7a5353a8cfd7 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -485,7 +485,7 @@ int ext4_ext_migrate(struct inode *inode) * when we add extents we extent the journal */ /* - * Even though we take i_mutex we can still cause block + * Even though we take i_rwsem we can still cause block * allocation via mmap write to holes. If we have allocated * new blocks we fail migrate. New block allocation will * clear EXT4_STATE_EXT_MIGRATE flag. The flag is updated diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 269d2d051ede..8cf0a924a49b 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3889,7 +3889,7 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir, * dirents in directories. */ ext4_fc_mark_ineligible(old.inode->i_sb, - EXT4_FC_REASON_RENAME_DIR); + EXT4_FC_REASON_RENAME_DIR, handle); } else { if (new.inode) ext4_fc_track_unlink(handle, new.dentry); @@ -4049,7 +4049,7 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry, if (unlikely(retval)) goto end_rename; ext4_fc_mark_ineligible(new.inode->i_sb, - EXT4_FC_REASON_CROSS_RENAME); + EXT4_FC_REASON_CROSS_RENAME, handle); if (old.dir_bh) { retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino); if (retval) diff --git a/fs/ext4/orphan.c b/fs/ext4/orphan.c index 53adc8f570a3..7de0612eb42d 100644 --- a/fs/ext4/orphan.c +++ b/fs/ext4/orphan.c @@ -93,7 +93,7 @@ static int ext4_orphan_file_add(handle_t *handle, struct inode *inode) * At filesystem recovery time, we walk this list deleting unlinked * inodes and truncating linked inodes in ext4_orphan_cleanup(). * - * Orphan list manipulation functions must be called under i_mutex unless + * Orphan list manipulation functions must be called under i_rwsem unless * we are just creating the inode or deleting it. */ int ext4_orphan_add(handle_t *handle, struct inode *inode) @@ -119,7 +119,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) /* * Orphan handling is only valid for files with data blocks * being truncated, or files being unlinked. Note that we either - * hold i_mutex, or the inode can not be referenced from outside, + * hold i_rwsem, or the inode can not be referenced from outside, * so i_nlink should not be bumped due to race */ ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ce60b5026bde..c5021ca0a28a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5082,7 +5082,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_STAGING]); sbi->s_fc_bytes = 0; ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); - ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING); + sbi->s_fc_ineligible_tid = 0; spin_lock_init(&sbi->s_fc_lock); memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats)); sbi->s_fc_replay_state.fc_regions = NULL; @@ -5540,7 +5540,7 @@ static int ext4_fill_super(struct super_block *sb, struct fs_context *fc) sbi = ext4_alloc_sbi(sb); if (!sbi) - ret = -ENOMEM; + return -ENOMEM; fc->s_fs_info = sbi; diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 1e0fc1ed845b..042325349098 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2408,7 +2408,7 @@ retry_inode: if (IS_SYNC(inode)) ext4_handle_sync(handle); } - ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR); + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, handle); cleanup: brelse(is.iloc.bh); @@ -2486,7 +2486,7 @@ retry: if (error == 0) error = error2; } - ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR); + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, NULL); return error; } @@ -2920,7 +2920,7 @@ int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode, error); goto cleanup; } - ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR); + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, handle); } error = 0; cleanup: diff --git a/fs/file_table.c b/fs/file_table.c index 57edef16dce4..4969021fa676 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -119,6 +119,8 @@ static struct ctl_table fs_stat_sysctls[] = { static int __init init_fs_stat_sysctls(void) { register_sysctl_init("fs", fs_stat_sysctls); + if (IS_ENABLED(CONFIG_BINFMT_MISC)) + register_sysctl_mount_point("fs/binfmt_misc"); return 0; } fs_initcall(init_fs_stat_sysctls); diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index c938bbad075e..6c51a75d0be6 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -21,6 +21,8 @@ #include "../internal.h" +#define IOEND_BATCH_SIZE 4096 + /* * Structure allocated for each folio when block size < folio size * to track sub-folio uptodate status and I/O completions. @@ -1039,7 +1041,7 @@ static void iomap_finish_folio_write(struct inode *inode, struct folio *folio, * state, release holds on bios, and finally free up memory. Do not use the * ioend after this. */ -static void +static u32 iomap_finish_ioend(struct iomap_ioend *ioend, int error) { struct inode *inode = ioend->io_inode; @@ -1048,6 +1050,7 @@ iomap_finish_ioend(struct iomap_ioend *ioend, int error) u64 start = bio->bi_iter.bi_sector; loff_t offset = ioend->io_offset; bool quiet = bio_flagged(bio, BIO_QUIET); + u32 folio_count = 0; for (bio = &ioend->io_inline_bio; bio; bio = next) { struct folio_iter fi; @@ -1062,9 +1065,11 @@ iomap_finish_ioend(struct iomap_ioend *ioend, int error) next = bio->bi_private; /* walk all folios in bio, ending page IO on them */ - bio_for_each_folio_all(fi, bio) + bio_for_each_folio_all(fi, bio) { iomap_finish_folio_write(inode, fi.folio, fi.length, error); + folio_count++; + } bio_put(bio); } /* The ioend has been freed by bio_put() */ @@ -1074,20 +1079,36 @@ iomap_finish_ioend(struct iomap_ioend *ioend, int error) "%s: writeback error on inode %lu, offset %lld, sector %llu", inode->i_sb->s_id, inode->i_ino, offset, start); } + return folio_count; } +/* + * Ioend completion routine for merged bios. This can only be called from task + * contexts as merged ioends can be of unbound length. Hence we have to break up + * the writeback completions into manageable chunks to avoid long scheduler + * holdoffs. We aim to keep scheduler holdoffs down below 10ms so that we get + * good batch processing throughput without creating adverse scheduler latency + * conditions. + */ void iomap_finish_ioends(struct iomap_ioend *ioend, int error) { struct list_head tmp; + u32 completions; + + might_sleep(); list_replace_init(&ioend->io_list, &tmp); - iomap_finish_ioend(ioend, error); + completions = iomap_finish_ioend(ioend, error); while (!list_empty(&tmp)) { + if (completions > IOEND_BATCH_SIZE * 8) { + cond_resched(); + completions = 0; + } ioend = list_first_entry(&tmp, struct iomap_ioend, io_list); list_del_init(&ioend->io_list); - iomap_finish_ioend(ioend, error); + completions += iomap_finish_ioend(ioend, error); } } EXPORT_SYMBOL_GPL(iomap_finish_ioends); @@ -1108,6 +1129,18 @@ iomap_ioend_can_merge(struct iomap_ioend *ioend, struct iomap_ioend *next) return false; if (ioend->io_offset + ioend->io_size != next->io_offset) return false; + /* + * Do not merge physically discontiguous ioends. The filesystem + * completion functions will have to iterate the physical + * discontiguities even if we merge the ioends at a logical level, so + * we don't gain anything by merging physical discontiguities here. + * + * We cannot use bio->bi_iter.bi_sector here as it is modified during + * submission so does not point to the start sector of the bio at + * completion. + */ + if (ioend->io_sector + (ioend->io_size >> 9) != next->io_sector) + return false; return true; } @@ -1209,8 +1242,10 @@ iomap_alloc_ioend(struct inode *inode, struct iomap_writepage_ctx *wpc, ioend->io_flags = wpc->iomap.flags; ioend->io_inode = inode; ioend->io_size = 0; + ioend->io_folios = 0; ioend->io_offset = offset; ioend->io_bio = bio; + ioend->io_sector = sector; return ioend; } @@ -1251,6 +1286,13 @@ iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t offset, return false; if (sector != bio_end_sector(wpc->ioend->io_bio)) return false; + /* + * Limit ioend bio chain lengths to minimise IO completion latency. This + * also prevents long tight loops ending page writeback on all the + * folios in the ioend. + */ + if (wpc->ioend->io_folios >= IOEND_BATCH_SIZE) + return false; return true; } @@ -1335,6 +1377,8 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc, &submit_list); count++; } + if (count) + wpc->ioend->io_folios++; WARN_ON_ONCE(!wpc->ioend && !list_empty(&submit_list)); WARN_ON_ONCE(!folio_test_locked(folio)); diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 3cc4ab2ba7f4..5b9408e3b370 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -484,22 +484,9 @@ void jbd2_journal_commit_transaction(journal_t *journal) stats.run.rs_running = jbd2_time_diff(commit_transaction->t_start, stats.run.rs_locked); - spin_lock(&commit_transaction->t_handle_lock); - while (atomic_read(&commit_transaction->t_updates)) { - DEFINE_WAIT(wait); + // waits for any t_updates to finish + jbd2_journal_wait_updates(journal); - prepare_to_wait(&journal->j_wait_updates, &wait, - TASK_UNINTERRUPTIBLE); - if (atomic_read(&commit_transaction->t_updates)) { - spin_unlock(&commit_transaction->t_handle_lock); - write_unlock(&journal->j_state_lock); - schedule(); - write_lock(&journal->j_state_lock); - spin_lock(&commit_transaction->t_handle_lock); - } - finish_wait(&journal->j_wait_updates, &wait); - } - spin_unlock(&commit_transaction->t_handle_lock); commit_transaction->t_state = T_SWITCH; write_unlock(&journal->j_state_lock); @@ -817,7 +804,7 @@ start_journal_io: commit_transaction->t_state = T_COMMIT_DFLUSH; write_unlock(&journal->j_state_lock); - /* + /* * If the journal is not located on the file system device, * then we must flush the file system device before we issue * the commit record @@ -1170,7 +1157,7 @@ restart_loop: if (journal->j_commit_callback) journal->j_commit_callback(journal, commit_transaction); if (journal->j_fc_cleanup_callback) - journal->j_fc_cleanup_callback(journal, 1); + journal->j_fc_cleanup_callback(journal, 1, commit_transaction->t_tid); trace_jbd2_end_commit(journal, commit_transaction); jbd_debug(1, "JBD2: commit %d complete, head %d\n", diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index bf108d4493d2..c2cf74b01ddb 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -771,7 +771,7 @@ static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback) { jbd2_journal_unlock_updates(journal); if (journal->j_fc_cleanup_callback) - journal->j_fc_cleanup_callback(journal, 0); + journal->j_fc_cleanup_callback(journal, 0, tid); write_lock(&journal->j_state_lock); journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING; if (fallback) @@ -1287,6 +1287,8 @@ static int jbd2_min_tag_size(void) /** * jbd2_journal_shrink_scan() + * @shrink: shrinker to work on + * @sc: reclaim request to process * * Scan the checkpointed buffer on the checkpoint list and release the * journal_head. @@ -1312,6 +1314,8 @@ static unsigned long jbd2_journal_shrink_scan(struct shrinker *shrink, /** * jbd2_journal_shrink_count() + * @shrink: shrinker to work on + * @sc: reclaim request to process * * Count the number of checkpoint buffers on the checkpoint list. */ diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 6a3caedd2285..8e2f8275a253 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -449,7 +449,7 @@ repeat: } /* OK, account for the buffers that this operation expects to - * use and add the handle to the running transaction. + * use and add the handle to the running transaction. */ update_t_max_wait(transaction, ts); handle->h_transaction = transaction; @@ -836,6 +836,35 @@ int jbd2_journal_restart(handle_t *handle, int nblocks) } EXPORT_SYMBOL(jbd2_journal_restart); +/* + * Waits for any outstanding t_updates to finish. + * This is called with write j_state_lock held. + */ +void jbd2_journal_wait_updates(journal_t *journal) +{ + transaction_t *commit_transaction = journal->j_running_transaction; + + if (!commit_transaction) + return; + + spin_lock(&commit_transaction->t_handle_lock); + while (atomic_read(&commit_transaction->t_updates)) { + DEFINE_WAIT(wait); + + prepare_to_wait(&journal->j_wait_updates, &wait, + TASK_UNINTERRUPTIBLE); + if (atomic_read(&commit_transaction->t_updates)) { + spin_unlock(&commit_transaction->t_handle_lock); + write_unlock(&journal->j_state_lock); + schedule(); + write_lock(&journal->j_state_lock); + spin_lock(&commit_transaction->t_handle_lock); + } + finish_wait(&journal->j_wait_updates, &wait); + } + spin_unlock(&commit_transaction->t_handle_lock); +} + /** * jbd2_journal_lock_updates () - establish a transaction barrier. * @journal: Journal to establish a barrier on. @@ -863,27 +892,9 @@ void jbd2_journal_lock_updates(journal_t *journal) write_lock(&journal->j_state_lock); } - /* Wait until there are no running updates */ - while (1) { - transaction_t *transaction = journal->j_running_transaction; - - if (!transaction) - break; + /* Wait until there are no running t_updates */ + jbd2_journal_wait_updates(journal); - spin_lock(&transaction->t_handle_lock); - prepare_to_wait(&journal->j_wait_updates, &wait, - TASK_UNINTERRUPTIBLE); - if (!atomic_read(&transaction->t_updates)) { - spin_unlock(&transaction->t_handle_lock); - finish_wait(&journal->j_wait_updates, &wait); - break; - } - spin_unlock(&transaction->t_handle_lock); - write_unlock(&journal->j_state_lock); - schedule(); - finish_wait(&journal->j_wait_updates, &wait); - write_lock(&journal->j_state_lock); - } write_unlock(&journal->j_state_lock); /* diff --git a/fs/ksmbd/auth.c b/fs/ksmbd/auth.c index dc3d061edda9..911444d21267 100644 --- a/fs/ksmbd/auth.c +++ b/fs/ksmbd/auth.c @@ -29,6 +29,7 @@ #include "mgmt/user_config.h" #include "crypto_ctx.h" #include "transport_ipc.h" +#include "../smbfs_common/arc4.h" /* * Fixed format data defining GSS header and fixed string @@ -336,6 +337,29 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob, nt_len - CIFS_ENCPWD_SIZE, domain_name, conn->ntlmssp.cryptkey); kfree(domain_name); + + /* The recovered secondary session key */ + if (conn->ntlmssp.client_flags & NTLMSSP_NEGOTIATE_KEY_XCH) { + struct arc4_ctx *ctx_arc4; + unsigned int sess_key_off, sess_key_len; + + sess_key_off = le32_to_cpu(authblob->SessionKey.BufferOffset); + sess_key_len = le16_to_cpu(authblob->SessionKey.Length); + + if (blob_len < (u64)sess_key_off + sess_key_len) + return -EINVAL; + + ctx_arc4 = kmalloc(sizeof(*ctx_arc4), GFP_KERNEL); + if (!ctx_arc4) + return -ENOMEM; + + cifs_arc4_setkey(ctx_arc4, sess->sess_key, + SMB2_NTLMV2_SESSKEY_SIZE); + cifs_arc4_crypt(ctx_arc4, sess->sess_key, + (char *)authblob + sess_key_off, sess_key_len); + kfree_sensitive(ctx_arc4); + } + return ret; } @@ -408,6 +432,9 @@ ksmbd_build_ntlmssp_challenge_blob(struct challenge_message *chgblob, (cflags & NTLMSSP_NEGOTIATE_EXTENDED_SEC)) flags |= NTLMSSP_NEGOTIATE_EXTENDED_SEC; + if (cflags & NTLMSSP_NEGOTIATE_KEY_XCH) + flags |= NTLMSSP_NEGOTIATE_KEY_XCH; + chgblob->NegotiateFlags = cpu_to_le32(flags); len = strlen(ksmbd_netbios_name()); name = kmalloc(2 + UNICODE_LEN(len), GFP_KERNEL); diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 1866c81c5c99..67e8e28e3fc3 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -2688,7 +2688,7 @@ int smb2_open(struct ksmbd_work *work) (struct create_posix *)context; if (le16_to_cpu(context->DataOffset) + le32_to_cpu(context->DataLength) < - sizeof(struct create_posix)) { + sizeof(struct create_posix) - 4) { rc = -EINVAL; goto err_out1; } @@ -3422,9 +3422,9 @@ static int smb2_populate_readdir_entry(struct ksmbd_conn *conn, int info_level, goto free_conv_name; } - struct_sz = readdir_info_level_struct_sz(info_level); - next_entry_offset = ALIGN(struct_sz - 1 + conv_len, - KSMBD_DIR_INFO_ALIGNMENT); + struct_sz = readdir_info_level_struct_sz(info_level) - 1 + conv_len; + next_entry_offset = ALIGN(struct_sz, KSMBD_DIR_INFO_ALIGNMENT); + d_info->last_entry_off_align = next_entry_offset - struct_sz; if (next_entry_offset > d_info->out_buf_len) { d_info->out_buf_len = 0; @@ -3976,6 +3976,7 @@ int smb2_query_dir(struct ksmbd_work *work) ((struct file_directory_info *) ((char *)rsp->Buffer + d_info.last_entry_offset)) ->NextEntryOffset = 0; + d_info.data_count -= d_info.last_entry_off_align; rsp->StructureSize = cpu_to_le16(9); rsp->OutputBufferOffset = cpu_to_le16(72); @@ -6126,13 +6127,26 @@ static int smb2_set_remote_key_for_rdma(struct ksmbd_work *work, __le16 ChannelInfoOffset, __le16 ChannelInfoLength) { + unsigned int i, ch_count; + if (work->conn->dialect == SMB30_PROT_ID && Channel != SMB2_CHANNEL_RDMA_V1) return -EINVAL; - if (ChannelInfoOffset == 0 || - le16_to_cpu(ChannelInfoLength) < sizeof(*desc)) + ch_count = le16_to_cpu(ChannelInfoLength) / sizeof(*desc); + if (ksmbd_debug_types & KSMBD_DEBUG_RDMA) { + for (i = 0; i < ch_count; i++) { + pr_info("RDMA r/w request %#x: token %#x, length %#x\n", + i, + le32_to_cpu(desc[i].token), + le32_to_cpu(desc[i].length)); + } + } + if (ch_count != 1) { + ksmbd_debug(RDMA, "RDMA multiple buffer descriptors %d are not supported yet\n", + ch_count); return -EINVAL; + } work->need_invalidate_rkey = (Channel == SMB2_CHANNEL_RDMA_V1_INVALIDATE); @@ -6185,9 +6199,15 @@ int smb2_read(struct ksmbd_work *work) if (req->Channel == SMB2_CHANNEL_RDMA_V1_INVALIDATE || req->Channel == SMB2_CHANNEL_RDMA_V1) { + unsigned int ch_offset = le16_to_cpu(req->ReadChannelInfoOffset); + + if (ch_offset < offsetof(struct smb2_read_req, Buffer)) { + err = -EINVAL; + goto out; + } err = smb2_set_remote_key_for_rdma(work, (struct smb2_buffer_desc_v1 *) - &req->Buffer[0], + ((char *)req + ch_offset), req->Channel, req->ReadChannelInfoOffset, req->ReadChannelInfoLength); @@ -6428,11 +6448,16 @@ int smb2_write(struct ksmbd_work *work) if (req->Channel == SMB2_CHANNEL_RDMA_V1 || req->Channel == SMB2_CHANNEL_RDMA_V1_INVALIDATE) { - if (req->Length != 0 || req->DataOffset != 0) - return -EINVAL; + unsigned int ch_offset = le16_to_cpu(req->WriteChannelInfoOffset); + + if (req->Length != 0 || req->DataOffset != 0 || + ch_offset < offsetof(struct smb2_write_req, Buffer)) { + err = -EINVAL; + goto out; + } err = smb2_set_remote_key_for_rdma(work, (struct smb2_buffer_desc_v1 *) - &req->Buffer[0], + ((char *)req + ch_offset), req->Channel, req->WriteChannelInfoOffset, req->WriteChannelInfoLength); diff --git a/fs/ksmbd/smb_common.c b/fs/ksmbd/smb_common.c index ef7f42b0290a..9a7e211dbf4f 100644 --- a/fs/ksmbd/smb_common.c +++ b/fs/ksmbd/smb_common.c @@ -308,14 +308,17 @@ int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, int info_level, for (i = 0; i < 2; i++) { struct kstat kstat; struct ksmbd_kstat ksmbd_kstat; + struct dentry *dentry; if (!dir->dot_dotdot[i]) { /* fill dot entry info */ if (i == 0) { d_info->name = "."; d_info->name_len = 1; + dentry = dir->filp->f_path.dentry; } else { d_info->name = ".."; d_info->name_len = 2; + dentry = dir->filp->f_path.dentry->d_parent; } if (!match_pattern(d_info->name, d_info->name_len, @@ -327,7 +330,7 @@ int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, int info_level, ksmbd_kstat.kstat = &kstat; ksmbd_vfs_fill_dentry_attrs(work, user_ns, - dir->filp->f_path.dentry->d_parent, + dentry, &ksmbd_kstat); rc = fn(conn, info_level, d_info, &ksmbd_kstat); if (rc) diff --git a/fs/ksmbd/transport_rdma.c b/fs/ksmbd/transport_rdma.c index 3c1ec1ac0b27..ba5a22bc2e6d 100644 --- a/fs/ksmbd/transport_rdma.c +++ b/fs/ksmbd/transport_rdma.c @@ -80,7 +80,7 @@ static int smb_direct_max_fragmented_recv_size = 1024 * 1024; /* The maximum single-message size which can be received */ static int smb_direct_max_receive_size = 8192; -static int smb_direct_max_read_write_size = 1048512; +static int smb_direct_max_read_write_size = 524224; static int smb_direct_max_outstanding_rw_ops = 8; diff --git a/fs/ksmbd/vfs.h b/fs/ksmbd/vfs.h index adf94a4f22fa..8c37aaf936ab 100644 --- a/fs/ksmbd/vfs.h +++ b/fs/ksmbd/vfs.h @@ -47,6 +47,7 @@ struct ksmbd_dir_info { int last_entry_offset; bool hide_dot_file; int flags; + int last_entry_off_align; }; struct ksmbd_readdir_data { diff --git a/fs/nfs/client.c b/fs/nfs/client.c index f18e80fda9bf..d1f34229e11a 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -177,6 +177,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) INIT_LIST_HEAD(&clp->cl_superblocks); clp->cl_rpcclient = ERR_PTR(-EINVAL); + clp->cl_flags = cl_init->init_flags; clp->cl_proto = cl_init->proto; clp->cl_nconnect = cl_init->nconnect; clp->cl_max_connect = cl_init->max_connect ? cl_init->max_connect : 1; @@ -423,7 +424,6 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init) list_add_tail(&new->cl_share_link, &nn->nfs_client_list); spin_unlock(&nn->nfs_client_lock); - new->cl_flags = cl_init->init_flags; return rpc_ops->init_client(new, cl_init); } diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 848f3b8fb821..7bc7cf6b26f0 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -80,6 +80,7 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir ctx->dir_cookie = 0; ctx->dup_cookie = 0; ctx->page_index = 0; + ctx->eof = false; spin_lock(&dir->i_lock); if (list_empty(&nfsi->open_files) && (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER)) @@ -168,6 +169,7 @@ struct nfs_readdir_descriptor { unsigned int cache_entry_index; signed char duped; bool plus; + bool eob; bool eof; }; @@ -867,7 +869,8 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc, status = nfs_readdir_page_filler(desc, entry, pages, pglen, arrays, narrays); - } while (!status && nfs_readdir_page_needs_filling(page)); + } while (!status && nfs_readdir_page_needs_filling(page) && + page_mapping(page)); nfs_readdir_free_pages(pages, array_size); out: @@ -988,7 +991,7 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc, ent = &array->array[i]; if (!dir_emit(desc->ctx, ent->name, ent->name_len, nfs_compat_user_ino64(ent->ino), ent->d_type)) { - desc->eof = true; + desc->eob = true; break; } memcpy(desc->verf, verf, sizeof(desc->verf)); @@ -1004,7 +1007,7 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc, desc->duped = 1; } if (array->page_is_eof) - desc->eof = true; + desc->eof = !desc->eob; kunmap(desc->page); dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %llu\n", @@ -1041,12 +1044,13 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc) goto out; desc->page_index = 0; + desc->cache_entry_index = 0; desc->last_cookie = desc->dir_cookie; desc->duped = 0; status = nfs_readdir_xdr_to_array(desc, desc->verf, verf, arrays, sz); - for (i = 0; !desc->eof && i < sz && arrays[i]; i++) { + for (i = 0; !desc->eob && i < sz && arrays[i]; i++) { desc->page = arrays[i]; nfs_do_filldir(desc, verf); } @@ -1105,9 +1109,15 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) desc->duped = dir_ctx->duped; page_index = dir_ctx->page_index; desc->attr_gencount = dir_ctx->attr_gencount; + desc->eof = dir_ctx->eof; memcpy(desc->verf, dir_ctx->verf, sizeof(desc->verf)); spin_unlock(&file->f_lock); + if (desc->eof) { + res = 0; + goto out_free; + } + if (test_and_clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags) && list_is_singular(&nfsi->open_files)) invalidate_mapping_pages(inode->i_mapping, page_index + 1, -1); @@ -1141,7 +1151,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) nfs_do_filldir(desc, nfsi->cookieverf); nfs_readdir_page_unlock_and_put_cached(desc); - } while (!desc->eof); + } while (!desc->eob && !desc->eof); spin_lock(&file->f_lock); dir_ctx->dir_cookie = desc->dir_cookie; @@ -1149,9 +1159,10 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) dir_ctx->duped = desc->duped; dir_ctx->attr_gencount = desc->attr_gencount; dir_ctx->page_index = desc->page_index; + dir_ctx->eof = desc->eof; memcpy(dir_ctx->verf, desc->verf, sizeof(dir_ctx->verf)); spin_unlock(&file->f_lock); - +out_free: kfree(desc); out: @@ -1193,6 +1204,7 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) if (offset == 0) memset(dir_ctx->verf, 0, sizeof(dir_ctx->verf)); dir_ctx->duped = 0; + dir_ctx->eof = false; } spin_unlock(&filp->f_lock); return offset; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index b18f31b2c9e7..f5020828ab65 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -8032,7 +8032,8 @@ static int _nfs41_proc_get_locations(struct nfs_server *server, /** * nfs4_proc_get_locations - discover locations for a migrated FSID - * @inode: inode on FSID that is migrating + * @server: pointer to nfs_server to process + * @fhandle: pointer to the kernel NFS client file handle * @locations: result of query * @page: buffer * @cred: credential to use for this operation diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 8ef53f6726ec..936eebd4c56d 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -150,13 +150,17 @@ nfsd3_proc_read(struct svc_rqst *rqstp) unsigned int len; int v; - argp->count = min_t(u32, argp->count, max_blocksize); - dprintk("nfsd: READ(3) %s %lu bytes at %Lu\n", SVCFH_fmt(&argp->fh), (unsigned long) argp->count, (unsigned long long) argp->offset); + argp->count = min_t(u32, argp->count, max_blocksize); + if (argp->offset > (u64)OFFSET_MAX) + argp->offset = (u64)OFFSET_MAX; + if (argp->offset + argp->count > (u64)OFFSET_MAX) + argp->count = (u64)OFFSET_MAX - argp->offset; + v = 0; len = argp->count; resp->pages = rqstp->rq_next_page; @@ -199,6 +203,11 @@ nfsd3_proc_write(struct svc_rqst *rqstp) (unsigned long long) argp->offset, argp->stable? " stable" : ""); + resp->status = nfserr_fbig; + if (argp->offset > (u64)OFFSET_MAX || + argp->offset + argp->len > (u64)OFFSET_MAX) + return rpc_success; + fh_copy(&resp->fh, &argp->fh); resp->committed = argp->stable; nvecs = svc_fill_write_vector(rqstp, &argp->payload); @@ -651,15 +660,9 @@ nfsd3_proc_commit(struct svc_rqst *rqstp) argp->count, (unsigned long long) argp->offset); - if (argp->offset > NFS_OFFSET_MAX) { - resp->status = nfserr_inval; - goto out; - } - fh_copy(&resp->fh, &argp->fh); resp->status = nfsd_commit(rqstp, &resp->fh, argp->offset, argp->count, resp->verf); -out: return rpc_success; } diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 7c45ba4db61b..0293b8d65f10 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -254,7 +254,7 @@ svcxdr_decode_sattr3(struct svc_rqst *rqstp, struct xdr_stream *xdr, if (xdr_stream_decode_u64(xdr, &newsize) < 0) return false; iap->ia_valid |= ATTR_SIZE; - iap->ia_size = min_t(u64, newsize, NFS_OFFSET_MAX); + iap->ia_size = newsize; } if (xdr_stream_decode_u32(xdr, &set_it) < 0) return false; @@ -1060,7 +1060,7 @@ svcxdr_encode_entry3_common(struct nfsd3_readdirres *resp, const char *name, return false; /* cookie */ resp->cookie_offset = dirlist->len; - if (xdr_stream_encode_u64(xdr, NFS_OFFSET_MAX) < 0) + if (xdr_stream_encode_u64(xdr, OFFSET_MAX) < 0) return false; return true; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index ed1ee25647be..b207c76a873f 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -782,12 +782,16 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; read->rd_nf = NULL; - if (read->rd_offset >= OFFSET_MAX) - return nfserr_inval; trace_nfsd_read_start(rqstp, &cstate->current_fh, read->rd_offset, read->rd_length); + read->rd_length = min_t(u32, read->rd_length, svc_max_payload(rqstp)); + if (read->rd_offset > (u64)OFFSET_MAX) + read->rd_offset = (u64)OFFSET_MAX; + if (read->rd_offset + read->rd_length > (u64)OFFSET_MAX) + read->rd_length = (u64)OFFSET_MAX - read->rd_offset; + /* * If we do a zero copy read, then a client will see read data * that reflects the state of the file *after* performing the @@ -1018,8 +1022,9 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, unsigned long cnt; int nvecs; - if (write->wr_offset >= OFFSET_MAX) - return nfserr_inval; + if (write->wr_offset > (u64)OFFSET_MAX || + write->wr_offset + write->wr_buflen > (u64)OFFSET_MAX) + return nfserr_fbig; cnt = write->wr_buflen; trace_nfsd_write_start(rqstp, &cstate->current_fh, diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 899de438e529..714a3a3bd50c 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3495,7 +3495,7 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, p = xdr_reserve_space(xdr, 3*4 + namlen); if (!p) goto fail; - p = xdr_encode_hyper(p, NFS_OFFSET_MAX); /* offset of next entry */ + p = xdr_encode_hyper(p, OFFSET_MAX); /* offset of next entry */ p = xdr_encode_array(p, name, namlen); /* name length & name */ nfserr = nfsd4_encode_dirent_fattr(xdr, cd, name, namlen); @@ -3986,10 +3986,8 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, } xdr_commit_encode(xdr); - maxcount = svc_max_payload(resp->rqstp); - maxcount = min_t(unsigned long, maxcount, + maxcount = min_t(unsigned long, read->rd_length, (xdr->buf->buflen - xdr->buf->len)); - maxcount = min_t(unsigned long, maxcount, read->rd_length); if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags)) @@ -4826,10 +4824,8 @@ nfsd4_encode_read_plus(struct nfsd4_compoundres *resp, __be32 nfserr, return nfserr_resource; xdr_commit_encode(xdr); - maxcount = svc_max_payload(resp->rqstp); - maxcount = min_t(unsigned long, maxcount, + maxcount = min_t(unsigned long, read->rd_length, (xdr->buf->buflen - xdr->buf->len)); - maxcount = min_t(unsigned long, maxcount, read->rd_length); count = maxcount; eof = read->rd_offset >= i_size_read(file_inode(file)); diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index c4cf56327843..5889db66409d 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -306,14 +306,14 @@ TRACE_EVENT(nfsd_export_update, DECLARE_EVENT_CLASS(nfsd_io_class, TP_PROTO(struct svc_rqst *rqstp, struct svc_fh *fhp, - loff_t offset, - unsigned long len), + u64 offset, + u32 len), TP_ARGS(rqstp, fhp, offset, len), TP_STRUCT__entry( __field(u32, xid) __field(u32, fh_hash) - __field(loff_t, offset) - __field(unsigned long, len) + __field(u64, offset) + __field(u32, len) ), TP_fast_assign( __entry->xid = be32_to_cpu(rqstp->rq_xid); @@ -321,7 +321,7 @@ DECLARE_EVENT_CLASS(nfsd_io_class, __entry->offset = offset; __entry->len = len; ), - TP_printk("xid=0x%08x fh_hash=0x%08x offset=%lld len=%lu", + TP_printk("xid=0x%08x fh_hash=0x%08x offset=%llu len=%u", __entry->xid, __entry->fh_hash, __entry->offset, __entry->len) ) @@ -330,8 +330,8 @@ DECLARE_EVENT_CLASS(nfsd_io_class, DEFINE_EVENT(nfsd_io_class, nfsd_##name, \ TP_PROTO(struct svc_rqst *rqstp, \ struct svc_fh *fhp, \ - loff_t offset, \ - unsigned long len), \ + u64 offset, \ + u32 len), \ TP_ARGS(rqstp, fhp, offset, len)) DEFINE_NFSD_IO_EVENT(read_start); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 99c2b9dfbb10..91600e71be19 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -435,6 +435,10 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, .ia_size = iap->ia_size, }; + host_err = -EFBIG; + if (iap->ia_size < 0) + goto out_unlock; + host_err = notify_change(&init_user_ns, dentry, &size_attr, NULL); if (host_err) goto out_unlock; @@ -1110,42 +1114,61 @@ out: } #ifdef CONFIG_NFSD_V3 -/* - * Commit all pending writes to stable storage. +/** + * nfsd_commit - Commit pending writes to stable storage + * @rqstp: RPC request being processed + * @fhp: NFS filehandle + * @offset: raw offset from beginning of file + * @count: raw count of bytes to sync + * @verf: filled in with the server's current write verifier * - * Note: we only guarantee that data that lies within the range specified - * by the 'offset' and 'count' parameters will be synced. + * Note: we guarantee that data that lies within the range specified + * by the 'offset' and 'count' parameters will be synced. The server + * is permitted to sync data that lies outside this range at the + * same time. * * Unfortunately we cannot lock the file to make sure we return full WCC * data to the client, as locking happens lower down in the filesystem. + * + * Return values: + * An nfsstat value in network byte order. */ __be32 -nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, - loff_t offset, unsigned long count, __be32 *verf) +nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, u64 offset, + u32 count, __be32 *verf) { + u64 maxbytes; + loff_t start, end; struct nfsd_net *nn; struct nfsd_file *nf; - loff_t end = LLONG_MAX; - __be32 err = nfserr_inval; - - if (offset < 0) - goto out; - if (count != 0) { - end = offset + (loff_t)count - 1; - if (end < offset) - goto out; - } + __be32 err; err = nfsd_file_acquire(rqstp, fhp, NFSD_MAY_WRITE|NFSD_MAY_NOT_BREAK_LEASE, &nf); if (err) goto out; + + /* + * Convert the client-provided (offset, count) range to a + * (start, end) range. If the client-provided range falls + * outside the maximum file size of the underlying FS, + * clamp the sync range appropriately. + */ + start = 0; + end = LLONG_MAX; + maxbytes = (u64)fhp->fh_dentry->d_sb->s_maxbytes; + if (offset < maxbytes) { + start = offset; + if (count && (offset + count - 1 < maxbytes)) + end = offset + count - 1; + } + nn = net_generic(nf->nf_net, nfsd_net_id); if (EX_ISSYNC(fhp->fh_export)) { errseq_t since = READ_ONCE(nf->nf_file->f_wb_err); int err2; - err2 = vfs_fsync_range(nf->nf_file, offset, end, 0); + err2 = vfs_fsync_range(nf->nf_file, start, end, 0); switch (err2) { case 0: nfsd_copy_write_verifier(verf, nn); diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index 9f56dcb22ff7..2c43d10e3cab 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -74,8 +74,8 @@ __be32 do_nfsd_create(struct svc_rqst *, struct svc_fh *, char *name, int len, struct iattr *attrs, struct svc_fh *res, int createmode, u32 *verifier, bool *truncp, bool *created); -__be32 nfsd_commit(struct svc_rqst *, struct svc_fh *, - loff_t, unsigned long, __be32 *verf); +__be32 nfsd_commit(struct svc_rqst *rqst, struct svc_fh *fhp, + u64 offset, u32 count, __be32 *verf); #endif /* CONFIG_NFSD_V3 */ #ifdef CONFIG_NFSD_V4 __be32 nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 22d904bde6ab..a74aef99bd3d 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -690,9 +690,14 @@ int dquot_quota_sync(struct super_block *sb, int type) /* This is not very clever (and fast) but currently I don't know about * any other simple way of getting quota data to disk and we must get * them there for userspace to be visible... */ - if (sb->s_op->sync_fs) - sb->s_op->sync_fs(sb, 1); - sync_blockdev(sb->s_bdev); + if (sb->s_op->sync_fs) { + ret = sb->s_op->sync_fs(sb, 1); + if (ret) + return ret; + } + ret = sync_blockdev(sb->s_bdev); + if (ret) + return ret; /* * Now when everything is written we can discard the pagecache so diff --git a/fs/super.c b/fs/super.c index 7af820ba5ad5..f1d4a193602d 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1616,11 +1616,9 @@ static void lockdep_sb_freeze_acquire(struct super_block *sb) percpu_rwsem_acquire(sb->s_writers.rw_sem + level, 0, _THIS_IP_); } -static void sb_freeze_unlock(struct super_block *sb) +static void sb_freeze_unlock(struct super_block *sb, int level) { - int level; - - for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--) + for (level--; level >= 0; level--) percpu_up_write(sb->s_writers.rw_sem + level); } @@ -1691,7 +1689,14 @@ int freeze_super(struct super_block *sb) sb_wait_write(sb, SB_FREEZE_PAGEFAULT); /* All writers are done so after syncing there won't be dirty data */ - sync_filesystem(sb); + ret = sync_filesystem(sb); + if (ret) { + sb->s_writers.frozen = SB_UNFROZEN; + sb_freeze_unlock(sb, SB_FREEZE_PAGEFAULT); + wake_up(&sb->s_writers.wait_unfrozen); + deactivate_locked_super(sb); + return ret; + } /* Now wait for internal filesystem counter */ sb->s_writers.frozen = SB_FREEZE_FS; @@ -1703,7 +1708,7 @@ int freeze_super(struct super_block *sb) printk(KERN_ERR "VFS:Filesystem freeze failed\n"); sb->s_writers.frozen = SB_UNFROZEN; - sb_freeze_unlock(sb); + sb_freeze_unlock(sb, SB_FREEZE_FS); wake_up(&sb->s_writers.wait_unfrozen); deactivate_locked_super(sb); return ret; @@ -1748,7 +1753,7 @@ static int thaw_super_locked(struct super_block *sb) } sb->s_writers.frozen = SB_UNFROZEN; - sb_freeze_unlock(sb); + sb_freeze_unlock(sb, SB_FREEZE_FS); out: wake_up(&sb->s_writers.wait_unfrozen); deactivate_locked_super(sb); diff --git a/fs/sync.c b/fs/sync.c index 3ce8e2137f31..c7690016453e 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -29,7 +29,7 @@ */ int sync_filesystem(struct super_block *sb) { - int ret; + int ret = 0; /* * We need to be protected against the filesystem going from @@ -52,15 +52,21 @@ int sync_filesystem(struct super_block *sb) * at a time. */ writeback_inodes_sb(sb, WB_REASON_SYNC); - if (sb->s_op->sync_fs) - sb->s_op->sync_fs(sb, 0); + if (sb->s_op->sync_fs) { + ret = sb->s_op->sync_fs(sb, 0); + if (ret) + return ret; + } ret = sync_blockdev_nowait(sb->s_bdev); - if (ret < 0) + if (ret) return ret; sync_inodes_sb(sb); - if (sb->s_op->sync_fs) - sb->s_op->sync_fs(sb, 1); + if (sb->s_op->sync_fs) { + ret = sb->s_op->sync_fs(sb, 1); + if (ret) + return ret; + } return sync_blockdev(sb->s_bdev); } EXPORT_SYMBOL(sync_filesystem); diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 2705f91bdd0d..9d6a67c7d227 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -136,7 +136,20 @@ done: memalloc_nofs_restore(nofs_flag); } -/* Finish all pending io completions. */ +/* + * Finish all pending IO completions that require transactional modifications. + * + * We try to merge physical and logically contiguous ioends before completion to + * minimise the number of transactions we need to perform during IO completion. + * Both unwritten extent conversion and COW remapping need to iterate and modify + * one physical extent at a time, so we gain nothing by merging physically + * discontiguous extents here. + * + * The ioend chain length that we can be processing here is largely unbound in + * length and we may have to perform significant amounts of work on each ioend + * to complete it. Hence we have to be careful about holding the CPU for too + * long in this loop. + */ void xfs_end_io( struct work_struct *work) @@ -157,6 +170,7 @@ xfs_end_io( list_del_init(&ioend->io_list); iomap_ioend_try_merge(ioend, &tmp); xfs_end_ioend(ioend); + cond_resched(); } } diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index d4a387d3d0ce..eb2e387ba528 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -850,9 +850,6 @@ xfs_alloc_file_space( rblocks = 0; } - /* - * Allocate and setup the transaction. - */ error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, dblocks, rblocks, false, &tp); if (error) @@ -869,9 +866,9 @@ xfs_alloc_file_space( if (error) goto error; - /* - * Complete the transaction - */ + ip->i_diflags |= XFS_DIFLAG_PREALLOC; + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + error = xfs_trans_commit(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); if (error) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 22ad207bedf4..5bddb1e9e0b3 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -66,40 +66,6 @@ xfs_is_falloc_aligned( return !((pos | len) & mask); } -int -xfs_update_prealloc_flags( - struct xfs_inode *ip, - enum xfs_prealloc_flags flags) -{ - struct xfs_trans *tp; - int error; - - error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_writeid, - 0, 0, 0, &tp); - if (error) - return error; - - xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); - - if (!(flags & XFS_PREALLOC_INVISIBLE)) { - VFS_I(ip)->i_mode &= ~S_ISUID; - if (VFS_I(ip)->i_mode & S_IXGRP) - VFS_I(ip)->i_mode &= ~S_ISGID; - xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); - } - - if (flags & XFS_PREALLOC_SET) - ip->i_diflags |= XFS_DIFLAG_PREALLOC; - if (flags & XFS_PREALLOC_CLEAR) - ip->i_diflags &= ~XFS_DIFLAG_PREALLOC; - - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - if (flags & XFS_PREALLOC_SYNC) - xfs_trans_set_sync(tp); - return xfs_trans_commit(tp); -} - /* * Fsync operations on directories are much simpler than on regular files, * as there is no file data to flush, and thus also no need for explicit @@ -895,6 +861,21 @@ xfs_break_layouts( return error; } +/* Does this file, inode, or mount want synchronous writes? */ +static inline bool xfs_file_sync_writes(struct file *filp) +{ + struct xfs_inode *ip = XFS_I(file_inode(filp)); + + if (xfs_has_wsync(ip->i_mount)) + return true; + if (filp->f_flags & (__O_SYNC | O_DSYNC)) + return true; + if (IS_SYNC(file_inode(filp))) + return true; + + return false; +} + #define XFS_FALLOC_FL_SUPPORTED \ (FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | \ FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | \ @@ -910,7 +891,6 @@ xfs_file_fallocate( struct inode *inode = file_inode(file); struct xfs_inode *ip = XFS_I(inode); long error; - enum xfs_prealloc_flags flags = 0; uint iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; loff_t new_size = 0; bool do_file_insert = false; @@ -955,6 +935,10 @@ xfs_file_fallocate( goto out_unlock; } + error = file_modified(file); + if (error) + goto out_unlock; + if (mode & FALLOC_FL_PUNCH_HOLE) { error = xfs_free_file_space(ip, offset, len); if (error) @@ -1004,8 +988,6 @@ xfs_file_fallocate( } do_file_insert = true; } else { - flags |= XFS_PREALLOC_SET; - if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > i_size_read(inode)) { new_size = offset + len; @@ -1057,13 +1039,6 @@ xfs_file_fallocate( } } - if (file->f_flags & O_DSYNC) - flags |= XFS_PREALLOC_SYNC; - - error = xfs_update_prealloc_flags(ip, flags); - if (error) - goto out_unlock; - /* Change file size if needed */ if (new_size) { struct iattr iattr; @@ -1082,8 +1057,14 @@ xfs_file_fallocate( * leave shifted extents past EOF and hence losing access to * the data that is contained within them. */ - if (do_file_insert) + if (do_file_insert) { error = xfs_insert_file_space(ip, offset, len); + if (error) + goto out_unlock; + } + + if (xfs_file_sync_writes(file)) + error = xfs_log_force_inode(ip); out_unlock: xfs_iunlock(ip, iolock); @@ -1115,21 +1096,6 @@ xfs_file_fadvise( return ret; } -/* Does this file, inode, or mount want synchronous writes? */ -static inline bool xfs_file_sync_writes(struct file *filp) -{ - struct xfs_inode *ip = XFS_I(file_inode(filp)); - - if (xfs_has_wsync(ip->i_mount)) - return true; - if (filp->f_flags & (__O_SYNC | O_DSYNC)) - return true; - if (IS_SYNC(file_inode(filp))) - return true; - - return false; -} - STATIC loff_t xfs_file_remap_range( struct file *file_in, diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index c447bf04205a..b7e8f14d9fca 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -462,15 +462,6 @@ xfs_itruncate_extents( } /* from xfs_file.c */ -enum xfs_prealloc_flags { - XFS_PREALLOC_SET = (1 << 1), - XFS_PREALLOC_CLEAR = (1 << 2), - XFS_PREALLOC_SYNC = (1 << 3), - XFS_PREALLOC_INVISIBLE = (1 << 4), -}; - -int xfs_update_prealloc_flags(struct xfs_inode *ip, - enum xfs_prealloc_flags flags); int xfs_break_layouts(struct inode *inode, uint *iolock, enum layout_break_reason reason); diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 03a6198c97f6..2515fe8299e1 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1464,7 +1464,7 @@ xfs_ioc_getbmap( if (bmx.bmv_count < 2) return -EINVAL; - if (bmx.bmv_count > ULONG_MAX / recsize) + if (bmx.bmv_count >= INT_MAX / recsize) return -ENOMEM; buf = kvcalloc(bmx.bmv_count, sizeof(*buf), GFP_KERNEL); diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index d6334abbc0b3..4abe17312c2b 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -71,6 +71,40 @@ xfs_fs_get_uuid( } /* + * We cannot use file based VFS helpers such as file_modified() to update + * inode state as we modify the data/metadata in the inode here. Hence we have + * to open code the timestamp updates and SUID/SGID stripping. We also need + * to set the inode prealloc flag to ensure that the extents we allocate are not + * removed if the inode is reclaimed from memory before xfs_fs_block_commit() + * is from the client to indicate that data has been written and the file size + * can be extended. + */ +static int +xfs_fs_map_update_inode( + struct xfs_inode *ip) +{ + struct xfs_trans *tp; + int error; + + error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_writeid, + 0, 0, 0, &tp); + if (error) + return error; + + xfs_ilock(ip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + + VFS_I(ip)->i_mode &= ~S_ISUID; + if (VFS_I(ip)->i_mode & S_IXGRP) + VFS_I(ip)->i_mode &= ~S_ISGID; + xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); + ip->i_diflags |= XFS_DIFLAG_PREALLOC; + + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + return xfs_trans_commit(tp); +} + +/* * Get a layout for the pNFS client. */ int @@ -164,10 +198,12 @@ xfs_fs_map_blocks( * that the blocks allocated and handed out to the client are * guaranteed to be present even after a server crash. */ - error = xfs_update_prealloc_flags(ip, - XFS_PREALLOC_SET | XFS_PREALLOC_SYNC); + error = xfs_fs_map_update_inode(ip); + if (!error) + error = xfs_log_force_inode(ip); if (error) goto out_unlock; + } else { xfs_iunlock(ip, lock_flags); } @@ -255,7 +291,7 @@ xfs_fs_commit_blocks( length = end - start; if (!length) continue; - + /* * Make sure reads through the pagecache see the new data. */ diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index e8f37bdc8354..4c0dee78b2f8 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -735,6 +735,7 @@ xfs_fs_sync_fs( int wait) { struct xfs_mount *mp = XFS_M(sb); + int error; trace_xfs_fs_sync_fs(mp, __return_address); @@ -744,7 +745,10 @@ xfs_fs_sync_fs( if (!wait) return 0; - xfs_log_force(mp, XFS_LOG_SYNC); + error = xfs_log_force(mp, XFS_LOG_SYNC); + if (error) + return error; + if (laptop_mode) { /* * The disk must be active because we're syncing. diff --git a/include/crypto/internal/blake2s.h b/include/crypto/internal/blake2s.h index d39cfa0d333e..52363eee2b20 100644 --- a/include/crypto/internal/blake2s.h +++ b/include/crypto/internal/blake2s.h @@ -24,14 +24,11 @@ static inline void blake2s_set_lastblock(struct blake2s_state *state) state->f[0] = -1; } -typedef void (*blake2s_compress_t)(struct blake2s_state *state, - const u8 *block, size_t nblocks, u32 inc); - /* Helper functions for BLAKE2s shared by the library and shash APIs */ -static inline void __blake2s_update(struct blake2s_state *state, - const u8 *in, size_t inlen, - blake2s_compress_t compress) +static __always_inline void +__blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen, + bool force_generic) { const size_t fill = BLAKE2S_BLOCK_SIZE - state->buflen; @@ -39,7 +36,12 @@ static inline void __blake2s_update(struct blake2s_state *state, return; if (inlen > fill) { memcpy(state->buf + state->buflen, in, fill); - (*compress)(state, state->buf, 1, BLAKE2S_BLOCK_SIZE); + if (force_generic) + blake2s_compress_generic(state, state->buf, 1, + BLAKE2S_BLOCK_SIZE); + else + blake2s_compress(state, state->buf, 1, + BLAKE2S_BLOCK_SIZE); state->buflen = 0; in += fill; inlen -= fill; @@ -47,7 +49,12 @@ static inline void __blake2s_update(struct blake2s_state *state, if (inlen > BLAKE2S_BLOCK_SIZE) { const size_t nblocks = DIV_ROUND_UP(inlen, BLAKE2S_BLOCK_SIZE); /* Hash one less (full) block than strictly possible */ - (*compress)(state, in, nblocks - 1, BLAKE2S_BLOCK_SIZE); + if (force_generic) + blake2s_compress_generic(state, in, nblocks - 1, + BLAKE2S_BLOCK_SIZE); + else + blake2s_compress(state, in, nblocks - 1, + BLAKE2S_BLOCK_SIZE); in += BLAKE2S_BLOCK_SIZE * (nblocks - 1); inlen -= BLAKE2S_BLOCK_SIZE * (nblocks - 1); } @@ -55,13 +62,16 @@ static inline void __blake2s_update(struct blake2s_state *state, state->buflen += inlen; } -static inline void __blake2s_final(struct blake2s_state *state, u8 *out, - blake2s_compress_t compress) +static __always_inline void +__blake2s_final(struct blake2s_state *state, u8 *out, bool force_generic) { blake2s_set_lastblock(state); memset(state->buf + state->buflen, 0, BLAKE2S_BLOCK_SIZE - state->buflen); /* Padding */ - (*compress)(state, state->buf, 1, state->buflen); + if (force_generic) + blake2s_compress_generic(state, state->buf, 1, state->buflen); + else + blake2s_compress(state, state->buf, 1, state->buflen); cpu_to_le32_array(state->h, ARRAY_SIZE(state->h)); memcpy(out, state->h, state->outlen); } @@ -99,20 +109,20 @@ static inline int crypto_blake2s_init(struct shash_desc *desc) static inline int crypto_blake2s_update(struct shash_desc *desc, const u8 *in, unsigned int inlen, - blake2s_compress_t compress) + bool force_generic) { struct blake2s_state *state = shash_desc_ctx(desc); - __blake2s_update(state, in, inlen, compress); + __blake2s_update(state, in, inlen, force_generic); return 0; } static inline int crypto_blake2s_final(struct shash_desc *desc, u8 *out, - blake2s_compress_t compress) + bool force_generic) { struct blake2s_state *state = shash_desc_ctx(desc); - __blake2s_final(state, out, compress); + __blake2s_final(state, out, force_generic); return 0; } diff --git a/include/linux/ata.h b/include/linux/ata.h index 199e47e97d64..21292b5bbb55 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -324,12 +324,12 @@ enum { ATA_LOG_NCQ_NON_DATA = 0x12, ATA_LOG_NCQ_SEND_RECV = 0x13, ATA_LOG_IDENTIFY_DEVICE = 0x30, + ATA_LOG_CONCURRENT_POSITIONING_RANGES = 0x47, /* Identify device log pages: */ ATA_LOG_SECURITY = 0x06, ATA_LOG_SATA_SETTINGS = 0x08, ATA_LOG_ZONED_INFORMATION = 0x09, - ATA_LOG_CONCURRENT_POSITIONING_RANGES = 0x47, /* Identify device SATA settings log:*/ ATA_LOG_DEVSLP_OFFSET = 0x30, diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 6a89ea410e43..edf62eaa6285 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -35,6 +35,7 @@ #define CEPH_OPT_TCP_NODELAY (1<<4) /* TCP_NODELAY on TCP sockets */ #define CEPH_OPT_NOMSGSIGN (1<<5) /* don't sign msgs (msgr1) */ #define CEPH_OPT_ABORT_ON_FULL (1<<6) /* abort w/ ENOSPC when full */ +#define CEPH_OPT_RXBOUNCE (1<<7) /* double-buffer read data */ #define CEPH_OPT_DEFAULT (CEPH_OPT_TCP_NODELAY) diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index ff99ce094cfa..e7f2fb2fc207 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -383,6 +383,10 @@ struct ceph_connection_v2_info { struct ceph_gcm_nonce in_gcm_nonce; struct ceph_gcm_nonce out_gcm_nonce; + struct page **in_enc_pages; + int in_enc_page_cnt; + int in_enc_resid; + int in_enc_i; struct page **out_enc_pages; int out_enc_page_cnt; int out_enc_resid; @@ -457,6 +461,7 @@ struct ceph_connection { struct ceph_msg *out_msg; /* sending message (== tail of out_sent) */ + struct page *bounce_page; u32 in_front_crc, in_middle_crc, in_data_crc; /* calculated crc */ struct timespec64 last_keepalive_ack; /* keepalive2 ack stamp */ diff --git a/include/linux/fb.h b/include/linux/fb.h index 3da95842b207..02f362c661c8 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -262,7 +262,7 @@ struct fb_ops { /* Draws a rectangle */ void (*fb_fillrect) (struct fb_info *info, const struct fb_fillrect *rect); - /* Copy data from area to another. Obsolete. */ + /* Copy data from area to another */ void (*fb_copyarea) (struct fb_info *info, const struct fb_copyarea *region); /* Draws a image to the display */ void (*fb_imageblit) (struct fb_info *info, const struct fb_image *image); diff --git a/include/linux/iomap.h b/include/linux/iomap.h index b55bd49e55f5..97a3a2edb585 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -263,9 +263,11 @@ struct iomap_ioend { struct list_head io_list; /* next ioend in chain */ u16 io_type; u16 io_flags; /* IOMAP_F_* */ + u32 io_folios; /* folios added to ioend */ struct inode *io_inode; /* file being written to */ size_t io_size; /* size of the extent */ loff_t io_offset; /* offset in the file */ + sector_t io_sector; /* start sector of ioend */ struct bio *io_bio; /* bio being built */ struct bio io_inline_bio; /* MUST BE LAST! */ }; diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index fd933c45281a..9c3ada74ffb1 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -594,7 +594,7 @@ struct transaction_s */ unsigned long t_log_start; - /* + /* * Number of buffers on the t_buffers list [j_list_lock, no locks * needed for jbd2 thread] */ @@ -1295,7 +1295,7 @@ struct journal_s * Clean-up after fast commit or full commit. JBD2 calls this function * after every commit operation. */ - void (*j_fc_cleanup_callback)(struct journal_s *journal, int); + void (*j_fc_cleanup_callback)(struct journal_s *journal, int full, tid_t tid); /** * @j_fc_replay_callback: @@ -1419,9 +1419,7 @@ extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *); extern bool __jbd2_journal_refile_buffer(struct journal_head *); extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *); extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); -extern void __journal_free_buffer(struct journal_head *bh); extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); -extern void __journal_clean_data_list(transaction_t *transaction); static inline void jbd2_file_log_bh(struct list_head *head, struct buffer_head *bh) { list_add_tail(&bh->b_assoc_buffers, head); @@ -1486,9 +1484,6 @@ extern int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct buffer_head **bh_out, sector_t blocknr); -/* Transaction locking */ -extern void __wait_on_journal (journal_t *); - /* Transaction cache support */ extern void jbd2_journal_destroy_transaction_cache(void); extern int __init jbd2_journal_init_transaction_cache(void); @@ -1543,6 +1538,8 @@ extern int jbd2_journal_flush(journal_t *journal, unsigned int flags); extern void jbd2_journal_lock_updates (journal_t *); extern void jbd2_journal_unlock_updates (journal_t *); +void jbd2_journal_wait_updates(journal_t *); + extern journal_t * jbd2_journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int bsize); @@ -1774,8 +1771,6 @@ static inline unsigned long jbd2_log_space_left(journal_t *journal) #define BJ_Reserved 4 /* Buffer is reserved for access by journal */ #define BJ_Types 5 -extern int jbd_blocks_per_page(struct inode *inode); - /* JBD uses a CRC32 checksum */ #define JBD_MAX_CHECKSUM_SIZE 4 diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 06912d6b39d0..f11039944c08 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -29,7 +29,9 @@ #include <linux/refcount.h> #include <linux/nospec.h> #include <linux/notifier.h> +#include <linux/ftrace.h> #include <linux/hashtable.h> +#include <linux/instrumentation.h> #include <linux/interval_tree.h> #include <linux/rbtree.h> #include <linux/xarray.h> @@ -368,8 +370,11 @@ struct kvm_vcpu { u64 last_used_slot_gen; }; -/* must be called with irqs disabled */ -static __always_inline void guest_enter_irqoff(void) +/* + * Start accounting time towards a guest. + * Must be called before entering guest context. + */ +static __always_inline void guest_timing_enter_irqoff(void) { /* * This is running in ioctl context so its safe to assume that it's the @@ -378,7 +383,18 @@ static __always_inline void guest_enter_irqoff(void) instrumentation_begin(); vtime_account_guest_enter(); instrumentation_end(); +} +/* + * Enter guest context and enter an RCU extended quiescent state. + * + * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is + * unsafe to use any code which may directly or indirectly use RCU, tracing + * (including IRQ flag tracing), or lockdep. All code in this period must be + * non-instrumentable. + */ +static __always_inline void guest_context_enter_irqoff(void) +{ /* * KVM does not hold any references to rcu protected data when it * switches CPU into a guest mode. In fact switching to a guest mode @@ -394,16 +410,79 @@ static __always_inline void guest_enter_irqoff(void) } } -static __always_inline void guest_exit_irqoff(void) +/* + * Deprecated. Architectures should move to guest_timing_enter_irqoff() and + * guest_state_enter_irqoff(). + */ +static __always_inline void guest_enter_irqoff(void) +{ + guest_timing_enter_irqoff(); + guest_context_enter_irqoff(); +} + +/** + * guest_state_enter_irqoff - Fixup state when entering a guest + * + * Entry to a guest will enable interrupts, but the kernel state is interrupts + * disabled when this is invoked. Also tell RCU about it. + * + * 1) Trace interrupts on state + * 2) Invoke context tracking if enabled to adjust RCU state + * 3) Tell lockdep that interrupts are enabled + * + * Invoked from architecture specific code before entering a guest. + * Must be called with interrupts disabled and the caller must be + * non-instrumentable. + * The caller has to invoke guest_timing_enter_irqoff() before this. + * + * Note: this is analogous to exit_to_user_mode(). + */ +static __always_inline void guest_state_enter_irqoff(void) +{ + instrumentation_begin(); + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(CALLER_ADDR0); + instrumentation_end(); + + guest_context_enter_irqoff(); + lockdep_hardirqs_on(CALLER_ADDR0); +} + +/* + * Exit guest context and exit an RCU extended quiescent state. + * + * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is + * unsafe to use any code which may directly or indirectly use RCU, tracing + * (including IRQ flag tracing), or lockdep. All code in this period must be + * non-instrumentable. + */ +static __always_inline void guest_context_exit_irqoff(void) { context_tracking_guest_exit(); +} +/* + * Stop accounting time towards a guest. + * Must be called after exiting guest context. + */ +static __always_inline void guest_timing_exit_irqoff(void) +{ instrumentation_begin(); /* Flush the guest cputime we spent on the guest */ vtime_account_guest_exit(); instrumentation_end(); } +/* + * Deprecated. Architectures should move to guest_state_exit_irqoff() and + * guest_timing_exit_irqoff(). + */ +static __always_inline void guest_exit_irqoff(void) +{ + guest_context_exit_irqoff(); + guest_timing_exit_irqoff(); +} + static inline void guest_exit(void) { unsigned long flags; @@ -413,6 +492,33 @@ static inline void guest_exit(void) local_irq_restore(flags); } +/** + * guest_state_exit_irqoff - Establish state when returning from guest mode + * + * Entry from a guest disables interrupts, but guest mode is traced as + * interrupts enabled. Also with NO_HZ_FULL RCU might be idle. + * + * 1) Tell lockdep that interrupts are disabled + * 2) Invoke context tracking if enabled to reactivate RCU + * 3) Trace interrupts off state + * + * Invoked from architecture specific code after exiting a guest. + * Must be invoked with interrupts disabled and the caller must be + * non-instrumentable. + * The caller has to invoke guest_timing_exit_irqoff() after this. + * + * Note: this is analogous to enter_from_user_mode(). + */ +static __always_inline void guest_state_exit_irqoff(void) +{ + lockdep_hardirqs_off(CALLER_ADDR0); + guest_context_exit_irqoff(); + + instrumentation_begin(); + trace_hardirqs_off_finish(); + instrumentation_end(); +} + static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) { /* diff --git a/include/linux/libata.h b/include/linux/libata.h index 605756f645be..7f99b4d78822 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -380,6 +380,7 @@ enum { ATA_HORKAGE_MAX_TRIM_128M = (1 << 26), /* Limit max trim size to 128M */ ATA_HORKAGE_NO_NCQ_ON_ATI = (1 << 27), /* Disable NCQ on ATI chipset */ ATA_HORKAGE_NO_ID_DEV_LOG = (1 << 28), /* Identify device log missing */ + ATA_HORKAGE_NO_LOG_DIR = (1 << 29), /* Do not read log directory */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ diff --git a/include/linux/netfs.h b/include/linux/netfs.h index b46c39d98bbd..614f22213e21 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -244,6 +244,13 @@ struct netfs_cache_ops { int (*prepare_write)(struct netfs_cache_resources *cres, loff_t *_start, size_t *_len, loff_t i_size, bool no_space_allocated_yet); + + /* Query the occupancy of the cache in a region, returning where the + * next chunk of data starts and how long it is. + */ + int (*query_occupancy)(struct netfs_cache_resources *cres, + loff_t start, size_t len, size_t granularity, + loff_t *_data_start, size_t *_data_len); }; struct readahead_control; diff --git a/include/linux/nfs.h b/include/linux/nfs.h index 0dc7ad38a0da..b06375e88e58 100644 --- a/include/linux/nfs.h +++ b/include/linux/nfs.h @@ -36,14 +36,6 @@ static inline void nfs_copy_fh(struct nfs_fh *target, const struct nfs_fh *sourc memcpy(target->data, source->data, source->size); } - -/* - * This is really a general kernel constant, but since nothing like - * this is defined in the kernel headers, I have to do it here. - */ -#define NFS_OFFSET_MAX ((__s64)((~(__u64)0) >> 1)) - - enum nfs3_stable_how { NFS_UNSTABLE = 0, NFS_DATA_SYNC = 1, diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 02aa49323d1d..68f81d8d36de 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -107,6 +107,7 @@ struct nfs_open_dir_context { __u64 dup_cookie; pgoff_t page_index; signed char duped; + bool eof; }; /* diff --git a/include/linux/page_table_check.h b/include/linux/page_table_check.h index 38cace1da7b6..01e16c7696ec 100644 --- a/include/linux/page_table_check.h +++ b/include/linux/page_table_check.h @@ -26,6 +26,9 @@ void __page_table_check_pmd_set(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd); void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud); +void __page_table_check_pte_clear_range(struct mm_struct *mm, + unsigned long addr, + pmd_t pmd); static inline void page_table_check_alloc(struct page *page, unsigned int order) { @@ -100,6 +103,16 @@ static inline void page_table_check_pud_set(struct mm_struct *mm, __page_table_check_pud_set(mm, addr, pudp, pud); } +static inline void page_table_check_pte_clear_range(struct mm_struct *mm, + unsigned long addr, + pmd_t pmd) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pte_clear_range(mm, addr, pmd); +} + #else static inline void page_table_check_alloc(struct page *page, unsigned int order) @@ -143,5 +156,11 @@ static inline void page_table_check_pud_set(struct mm_struct *mm, { } +static inline void page_table_check_pte_clear_range(struct mm_struct *mm, + unsigned long addr, + pmd_t pmd) +{ +} + #endif /* CONFIG_PAGE_TABLE_CHECK */ #endif /* __LINUX_PAGE_TABLE_CHECK_H */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index bc8713a76e03..f4f4077b97aa 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -62,6 +62,7 @@ static inline unsigned long pte_index(unsigned long address) { return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); } +#define pte_index pte_index #ifndef pmd_index static inline unsigned long pmd_index(unsigned long address) diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h index 14efa0ded75d..adab27ba1ecb 100644 --- a/include/net/dst_metadata.h +++ b/include/net/dst_metadata.h @@ -123,8 +123,20 @@ static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb) memcpy(&new_md->u.tun_info, &md_dst->u.tun_info, sizeof(struct ip_tunnel_info) + md_size); +#ifdef CONFIG_DST_CACHE + /* Unclone the dst cache if there is one */ + if (new_md->u.tun_info.dst_cache.cache) { + int ret; + + ret = dst_cache_init(&new_md->u.tun_info.dst_cache, GFP_ATOMIC); + if (ret) { + metadata_dst_free(new_md); + return ERR_PTR(ret); + } + } +#endif + skb_dst_drop(skb); - dst_hold(&new_md->dst); skb_dst_set(skb, &new_md->dst); return new_md; } diff --git a/include/sound/pcm.h b/include/sound/pcm.h index 9b187d86e1bd..36da42cd0774 100644 --- a/include/sound/pcm.h +++ b/include/sound/pcm.h @@ -617,6 +617,7 @@ void snd_pcm_stream_unlock(struct snd_pcm_substream *substream); void snd_pcm_stream_lock_irq(struct snd_pcm_substream *substream); void snd_pcm_stream_unlock_irq(struct snd_pcm_substream *substream); unsigned long _snd_pcm_stream_lock_irqsave(struct snd_pcm_substream *substream); +unsigned long _snd_pcm_stream_lock_irqsave_nested(struct snd_pcm_substream *substream); /** * snd_pcm_stream_lock_irqsave - Lock the PCM stream @@ -636,6 +637,20 @@ void snd_pcm_stream_unlock_irqrestore(struct snd_pcm_substream *substream, unsigned long flags); /** + * snd_pcm_stream_lock_irqsave_nested - Single-nested PCM stream locking + * @substream: PCM substream + * @flags: irq flags + * + * This locks the PCM stream like snd_pcm_stream_lock_irqsave() but with + * the single-depth lockdep subclass. + */ +#define snd_pcm_stream_lock_irqsave_nested(substream, flags) \ + do { \ + typecheck(unsigned long, flags); \ + flags = _snd_pcm_stream_lock_irqsave_nested(substream); \ + } while (0) + +/** * snd_pcm_group_for_each_entry - iterate over the linked substreams * @s: the iterator * @substream: the substream diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index b46bcdb0cab1..5191b57e1562 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1624,9 +1624,6 @@ struct kvm_enc_region { #define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3) #define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4) -/* Available with KVM_CAP_XSAVE2 */ -#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave) - struct kvm_s390_pv_sec_parm { __u64 origin; __u64 length; @@ -2048,4 +2045,7 @@ struct kvm_stats_desc { #define KVM_GET_STATS_FD _IO(KVMIO, 0xce) +/* Available with KVM_CAP_XSAVE2 */ +#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave) + #endif /* __LINUX_KVM_H */ diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h index 4b3395082d15..26071021e986 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_common.h +++ b/include/uapi/linux/netfilter/nf_conntrack_common.h @@ -106,7 +106,7 @@ enum ip_conntrack_status { IPS_NAT_CLASH = IPS_UNTRACKED, #endif - /* Conntrack got a helper explicitly attached via CT target. */ + /* Conntrack got a helper explicitly attached (ruleset, ctnetlink). */ IPS_HELPER_BIT = 13, IPS_HELPER = (1 << IPS_HELPER_BIT), diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 1b65042ab1db..82858b697c05 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -465,6 +465,8 @@ struct perf_event_attr { /* * User provided data if sigtrap=1, passed back to user via * siginfo_t::si_perf_data, e.g. to permit user to identify the event. + * Note, siginfo_t::si_perf_data is long-sized, and sig_data will be + * truncated accordingly on 32 bit architectures. */ __u64 sig_data; }; diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index ef0cafe295b2..2d3e5df39a59 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -56,8 +56,10 @@ * * ****************************************************************************/ +#define AES_IEC958_STATUS_SIZE 24 + struct snd_aes_iec958 { - unsigned char status[24]; /* AES/IEC958 channel status bits */ + unsigned char status[AES_IEC958_STATUS_SIZE]; /* AES/IEC958 channel status bits */ unsigned char subcode[147]; /* AES/IEC958 subcode bits */ unsigned char pad; /* nothing */ unsigned char dig_subframe[4]; /* AES/IEC958 subframe bits */ diff --git a/include/uapi/xen/gntdev.h b/include/uapi/xen/gntdev.h index 9ac5515b9bc2..7a7145395c09 100644 --- a/include/uapi/xen/gntdev.h +++ b/include/uapi/xen/gntdev.h @@ -47,7 +47,13 @@ struct ioctl_gntdev_grant_ref { /* * Inserts the grant references into the mapping table of an instance * of gntdev. N.B. This does not perform the mapping, which is deferred - * until mmap() is called with @index as the offset. + * until mmap() is called with @index as the offset. @index should be + * considered opaque to userspace, with one exception: if no grant + * references have ever been inserted into the mapping table of this + * instance, @index will be set to 0. This is necessary to use gntdev + * with userspace APIs that expect a file descriptor that can be + * mmap()'d at offset 0, such as Wayland. If @count is set to 0, this + * ioctl will fail. */ #define IOCTL_GNTDEV_MAP_GRANT_REF \ _IOC(_IOC_NONE, 'G', 0, sizeof(struct ioctl_gntdev_map_grant_ref)) diff --git a/include/xen/xenbus_dev.h b/include/xen/xenbus_dev.h index bbee8c6a349d..4dc45a51c044 100644 --- a/include/xen/xenbus_dev.h +++ b/include/xen/xenbus_dev.h @@ -1,6 +1,4 @@ /****************************************************************************** - * evtchn.h - * * Interface to /dev/xen/xenbus_backend. * * Copyright (c) 2011 Bastian Blank <waldi@debian.org> diff --git a/ipc/sem.c b/ipc/sem.c index 6693daf4fe11..0dbdb98fdf2d 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -1964,6 +1964,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) */ un = lookup_undo(ulp, semid); if (un) { + spin_unlock(&ulp->lock); kvfree(new); goto success; } @@ -1976,9 +1977,8 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid) ipc_assert_locked_object(&sma->sem_perm); list_add(&new->list_id, &sma->list_id); un = new; - -success: spin_unlock(&ulp->lock); +success: sem_unlock(sma, -1); out: return un; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index fce5d43a933f..a83928cbdcb7 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -185,7 +185,7 @@ static int audit_match_perm(struct audit_context *ctx, int mask) case AUDITSC_EXECVE: return mask & AUDIT_PERM_EXEC; case AUDITSC_OPENAT2: - return mask & ACC_MODE((u32)((struct open_how *)ctx->argv[2])->flags); + return mask & ACC_MODE((u32)ctx->openat2.flags); default: return 0; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 76c754e45d01..57c7197838db 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3238,6 +3238,15 @@ static int perf_event_modify_breakpoint(struct perf_event *bp, return err; } +/* + * Copy event-type-independent attributes that may be modified. + */ +static void perf_event_modify_copy_attr(struct perf_event_attr *to, + const struct perf_event_attr *from) +{ + to->sig_data = from->sig_data; +} + static int perf_event_modify_attr(struct perf_event *event, struct perf_event_attr *attr) { @@ -3260,10 +3269,17 @@ static int perf_event_modify_attr(struct perf_event *event, WARN_ON_ONCE(event->ctx->parent_ctx); mutex_lock(&event->child_mutex); + /* + * Event-type-independent attributes must be copied before event-type + * modification, which will validate that final attributes match the + * source attributes after all relevant attributes have been copied. + */ + perf_event_modify_copy_attr(&event->attr, attr); err = func(event, attr); if (err) goto out; list_for_each_entry(child, &event->child_list, child_list) { + perf_event_modify_copy_attr(&child->attr, attr); err = func(child, attr); if (err) goto out; diff --git a/lib/crypto/blake2s.c b/lib/crypto/blake2s.c index 9364f79937b8..c71c09621c09 100644 --- a/lib/crypto/blake2s.c +++ b/lib/crypto/blake2s.c @@ -18,14 +18,14 @@ void blake2s_update(struct blake2s_state *state, const u8 *in, size_t inlen) { - __blake2s_update(state, in, inlen, blake2s_compress); + __blake2s_update(state, in, inlen, false); } EXPORT_SYMBOL(blake2s_update); void blake2s_final(struct blake2s_state *state, u8 *out) { WARN_ON(IS_ENABLED(DEBUG) && !out); - __blake2s_final(state, out, blake2s_compress); + __blake2s_final(state, out, false); memzero_explicit(state, sizeof(*state)); } EXPORT_SYMBOL(blake2s_final); diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index a7ac97c76762..db2abd9e415b 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -171,6 +171,8 @@ static void __init pte_advanced_tests(struct pgtable_debug_args *args) ptep_test_and_clear_young(args->vma, args->vaddr, args->ptep); pte = ptep_get(args->ptep); WARN_ON(pte_young(pte)); + + ptep_get_and_clear_full(args->mm, args->vaddr, args->ptep, 1); } static void __init pte_savedwrite_tests(struct pgtable_debug_args *args) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 35f14d0a00a6..131492fd1148 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -16,6 +16,7 @@ #include <linux/hashtable.h> #include <linux/userfaultfd_k.h> #include <linux/page_idle.h> +#include <linux/page_table_check.h> #include <linux/swapops.h> #include <linux/shmem_fs.h> @@ -1416,6 +1417,21 @@ static int khugepaged_add_pte_mapped_thp(struct mm_struct *mm, return 0; } +static void collapse_and_free_pmd(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp) +{ + spinlock_t *ptl; + pmd_t pmd; + + mmap_assert_write_locked(mm); + ptl = pmd_lock(vma->vm_mm, pmdp); + pmd = pmdp_collapse_flush(vma, addr, pmdp); + spin_unlock(ptl); + mm_dec_nr_ptes(mm); + page_table_check_pte_clear_range(mm, addr, pmd); + pte_free(mm, pmd_pgtable(pmd)); +} + /** * collapse_pte_mapped_thp - Try to collapse a pte-mapped THP for mm at * address haddr. @@ -1433,7 +1449,7 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) struct vm_area_struct *vma = find_vma(mm, haddr); struct page *hpage; pte_t *start_pte, *pte; - pmd_t *pmd, _pmd; + pmd_t *pmd; spinlock_t *ptl; int count = 0; int i; @@ -1509,12 +1525,7 @@ void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr) } /* step 4: collapse pmd */ - ptl = pmd_lock(vma->vm_mm, pmd); - _pmd = pmdp_collapse_flush(vma, haddr, pmd); - spin_unlock(ptl); - mm_dec_nr_ptes(mm); - pte_free(mm, pmd_pgtable(_pmd)); - + collapse_and_free_pmd(mm, vma, haddr, pmd); drop_hpage: unlock_page(hpage); put_page(hpage); @@ -1552,7 +1563,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) struct vm_area_struct *vma; struct mm_struct *mm; unsigned long addr; - pmd_t *pmd, _pmd; + pmd_t *pmd; i_mmap_lock_write(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { @@ -1591,14 +1602,8 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) * reverse order. Trylock is a way to avoid deadlock. */ if (mmap_write_trylock(mm)) { - if (!khugepaged_test_exit(mm)) { - spinlock_t *ptl = pmd_lock(mm, pmd); - /* assume page table is clear */ - _pmd = pmdp_collapse_flush(vma, addr, pmd); - spin_unlock(ptl); - mm_dec_nr_ptes(mm); - pte_free(mm, pmd_pgtable(_pmd)); - } + if (!khugepaged_test_exit(mm)) + collapse_and_free_pmd(mm, vma, addr, pmd); mmap_write_unlock(mm); } else { /* Try again later */ diff --git a/mm/kmemleak.c b/mm/kmemleak.c index dc3758fdba68..7580baa76af1 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1410,7 +1410,8 @@ static void kmemleak_scan(void) { unsigned long flags; struct kmemleak_object *object; - int i; + struct zone *zone; + int __maybe_unused i; int new_leaks = 0; jiffies_last_scan = jiffies; @@ -1450,9 +1451,9 @@ static void kmemleak_scan(void) * Struct page scanning for each node. */ get_online_mems(); - for_each_online_node(i) { - unsigned long start_pfn = node_start_pfn(i); - unsigned long end_pfn = node_end_pfn(i); + for_each_populated_zone(zone) { + unsigned long start_pfn = zone->zone_start_pfn; + unsigned long end_pfn = zone_end_pfn(zone); unsigned long pfn; for (pfn = start_pfn; pfn < end_pfn; pfn++) { @@ -1461,8 +1462,8 @@ static void kmemleak_scan(void) if (!page) continue; - /* only scan pages belonging to this node */ - if (page_to_nid(page) != i) + /* only scan pages belonging to this zone */ + if (page_zone(page) != zone) continue; /* only scan if page is in use */ if (page_count(page) == 0) diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 6a0ddda6b3c5..f67c4c70f17f 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -115,7 +115,7 @@ static void unset_migratetype_isolate(struct page *page, unsigned migratetype) * onlining - just onlined memory won't immediately be considered for * allocation. */ - if (!isolated_page && PageBuddy(page)) { + if (!isolated_page) { nr_pages = move_freepages_block(zone, page, migratetype, NULL); __mod_zone_freepage_state(zone, nr_pages, migratetype); } diff --git a/mm/page_table_check.c b/mm/page_table_check.c index 7504e7caa2a1..3763bd077861 100644 --- a/mm/page_table_check.c +++ b/mm/page_table_check.c @@ -86,8 +86,8 @@ static void page_table_check_clear(struct mm_struct *mm, unsigned long addr, { struct page_ext *page_ext; struct page *page; + unsigned long i; bool anon; - int i; if (!pfn_valid(pfn)) return; @@ -121,8 +121,8 @@ static void page_table_check_set(struct mm_struct *mm, unsigned long addr, { struct page_ext *page_ext; struct page *page; + unsigned long i; bool anon; - int i; if (!pfn_valid(pfn)) return; @@ -152,10 +152,10 @@ static void page_table_check_set(struct mm_struct *mm, unsigned long addr, void __page_table_check_zero(struct page *page, unsigned int order) { struct page_ext *page_ext = lookup_page_ext(page); - int i; + unsigned long i; BUG_ON(!page_ext); - for (i = 0; i < (1 << order); i++) { + for (i = 0; i < (1ul << order); i++) { struct page_table_check *ptc = get_page_table_check(page_ext); BUG_ON(atomic_read(&ptc->anon_map_count)); @@ -206,17 +206,10 @@ EXPORT_SYMBOL(__page_table_check_pud_clear); void __page_table_check_pte_set(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { - pte_t old_pte; - if (&init_mm == mm) return; - old_pte = *ptep; - if (pte_user_accessible_page(old_pte)) { - page_table_check_clear(mm, addr, pte_pfn(old_pte), - PAGE_SIZE >> PAGE_SHIFT); - } - + __page_table_check_pte_clear(mm, addr, *ptep); if (pte_user_accessible_page(pte)) { page_table_check_set(mm, addr, pte_pfn(pte), PAGE_SIZE >> PAGE_SHIFT, @@ -228,17 +221,10 @@ EXPORT_SYMBOL(__page_table_check_pte_set); void __page_table_check_pmd_set(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { - pmd_t old_pmd; - if (&init_mm == mm) return; - old_pmd = *pmdp; - if (pmd_user_accessible_page(old_pmd)) { - page_table_check_clear(mm, addr, pmd_pfn(old_pmd), - PMD_PAGE_SIZE >> PAGE_SHIFT); - } - + __page_table_check_pmd_clear(mm, addr, *pmdp); if (pmd_user_accessible_page(pmd)) { page_table_check_set(mm, addr, pmd_pfn(pmd), PMD_PAGE_SIZE >> PAGE_SHIFT, @@ -250,17 +236,10 @@ EXPORT_SYMBOL(__page_table_check_pmd_set); void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { - pud_t old_pud; - if (&init_mm == mm) return; - old_pud = *pudp; - if (pud_user_accessible_page(old_pud)) { - page_table_check_clear(mm, addr, pud_pfn(old_pud), - PUD_PAGE_SIZE >> PAGE_SHIFT); - } - + __page_table_check_pud_clear(mm, addr, *pudp); if (pud_user_accessible_page(pud)) { page_table_check_set(mm, addr, pud_pfn(pud), PUD_PAGE_SIZE >> PAGE_SHIFT, @@ -268,3 +247,23 @@ void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr, } } EXPORT_SYMBOL(__page_table_check_pud_set); + +void __page_table_check_pte_clear_range(struct mm_struct *mm, + unsigned long addr, + pmd_t pmd) +{ + if (&init_mm == mm) + return; + + if (!pmd_bad(pmd) && !pmd_leaf(pmd)) { + pte_t *ptep = pte_offset_map(&pmd, addr); + unsigned long i; + + pte_unmap(ptep); + for (i = 0; i < PTRS_PER_PTE; i++) { + __page_table_check_pte_clear(mm, addr, *ptep); + addr += PAGE_SIZE; + ptep++; + } + } +} diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 1a705a4ef7fa..5eaf38875554 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -129,6 +129,7 @@ void vlan_dev_set_ingress_priority(const struct net_device *dev, u32 skb_prio, u16 vlan_prio); int vlan_dev_set_egress_priority(const struct net_device *dev, u32 skb_prio, u16 vlan_prio); +void vlan_dev_free_egress_priority(const struct net_device *dev); int vlan_dev_change_flags(const struct net_device *dev, u32 flag, u32 mask); void vlan_dev_get_realdev_name(const struct net_device *dev, char *result, size_t size); @@ -139,7 +140,6 @@ int vlan_check_real_dev(struct net_device *real_dev, void vlan_setup(struct net_device *dev); int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack); void unregister_vlan_dev(struct net_device *dev, struct list_head *head); -void vlan_dev_uninit(struct net_device *dev); bool vlan_dev_inherit_address(struct net_device *dev, struct net_device *real_dev); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 26d031a43cc1..d1902828a18a 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -622,7 +622,7 @@ static int vlan_dev_init(struct net_device *dev) } /* Note: this function might be called multiple times for the same device. */ -void vlan_dev_uninit(struct net_device *dev) +void vlan_dev_free_egress_priority(const struct net_device *dev) { struct vlan_priority_tci_mapping *pm; struct vlan_dev_priv *vlan = vlan_dev_priv(dev); @@ -636,6 +636,16 @@ void vlan_dev_uninit(struct net_device *dev) } } +static void vlan_dev_uninit(struct net_device *dev) +{ + struct vlan_dev_priv *vlan = vlan_dev_priv(dev); + + vlan_dev_free_egress_priority(dev); + + /* Get rid of the vlan's reference to real_dev */ + dev_put_track(vlan->real_dev, &vlan->dev_tracker); +} + static netdev_features_t vlan_dev_fix_features(struct net_device *dev, netdev_features_t features) { @@ -846,9 +856,6 @@ static void vlan_dev_free(struct net_device *dev) free_percpu(vlan->vlan_pcpu_stats); vlan->vlan_pcpu_stats = NULL; - - /* Get rid of the vlan's reference to real_dev */ - dev_put_track(vlan->real_dev, &vlan->dev_tracker); } void vlan_setup(struct net_device *dev) diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 0db85aeb119b..53b1955b027f 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -183,10 +183,11 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, return -EINVAL; err = vlan_changelink(dev, tb, data, extack); - if (!err) - err = register_vlan_dev(dev, extack); if (err) - vlan_dev_uninit(dev); + return err; + err = register_vlan_dev(dev, extack); + if (err) + vlan_dev_free_egress_priority(dev); return err; } diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 3e49d28824ed..d53cbb4e2503 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -91,9 +91,10 @@ again: spin_unlock_bh(&ax25_list_lock); lock_sock(sk); s->ax25_dev = NULL; + dev_put_track(ax25_dev->dev, &ax25_dev->dev_tracker); ax25_dev_put(ax25_dev); - release_sock(sk); ax25_disconnect(s, ENETUNREACH); + release_sock(sk); spin_lock_bh(&ax25_list_lock); sock_put(sk); /* The entry could have been deleted from the @@ -1116,8 +1117,10 @@ static int ax25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) } } - if (ax25_dev != NULL) + if (ax25_dev) { ax25_fillin_cb(ax25, ax25_dev); + dev_hold_track(ax25_dev->dev, &ax25_dev->dev_tracker, GFP_ATOMIC); + } done: ax25_cb_add(ax25); diff --git a/net/can/isotp.c b/net/can/isotp.c index 02cbcb2ecf0d..d2a430b6a13b 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -56,6 +56,7 @@ #include <linux/module.h> #include <linux/init.h> #include <linux/interrupt.h> +#include <linux/spinlock.h> #include <linux/hrtimer.h> #include <linux/wait.h> #include <linux/uio.h> @@ -145,6 +146,7 @@ struct isotp_sock { struct tpcon rx, tx; struct list_head notifier; wait_queue_head_t wait; + spinlock_t rx_lock; /* protect single thread state machine */ }; static LIST_HEAD(isotp_notifier_list); @@ -615,11 +617,17 @@ static void isotp_rcv(struct sk_buff *skb, void *data) n_pci_type = cf->data[ae] & 0xF0; + /* Make sure the state changes and data structures stay consistent at + * CAN frame reception time. This locking is not needed in real world + * use cases but the inconsistency can be triggered with syzkaller. + */ + spin_lock(&so->rx_lock); + if (so->opt.flags & CAN_ISOTP_HALF_DUPLEX) { /* check rx/tx path half duplex expectations */ if ((so->tx.state != ISOTP_IDLE && n_pci_type != N_PCI_FC) || (so->rx.state != ISOTP_IDLE && n_pci_type == N_PCI_FC)) - return; + goto out_unlock; } switch (n_pci_type) { @@ -668,6 +676,9 @@ static void isotp_rcv(struct sk_buff *skb, void *data) isotp_rcv_cf(sk, cf, ae, skb); break; } + +out_unlock: + spin_unlock(&so->rx_lock); } static void isotp_fill_dataframe(struct canfd_frame *cf, struct isotp_sock *so, @@ -876,7 +887,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (!size || size > MAX_MSG_LENGTH) { err = -EINVAL; - goto err_out; + goto err_out_drop; } /* take care of a potential SF_DL ESC offset for TX_DL > 8 */ @@ -886,24 +897,24 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if ((so->opt.flags & CAN_ISOTP_SF_BROADCAST) && (size > so->tx.ll_dl - SF_PCI_SZ4 - ae - off)) { err = -EINVAL; - goto err_out; + goto err_out_drop; } err = memcpy_from_msg(so->tx.buf, msg, size); if (err < 0) - goto err_out; + goto err_out_drop; dev = dev_get_by_index(sock_net(sk), so->ifindex); if (!dev) { err = -ENXIO; - goto err_out; + goto err_out_drop; } skb = sock_alloc_send_skb(sk, so->ll.mtu + sizeof(struct can_skb_priv), msg->msg_flags & MSG_DONTWAIT, &err); if (!skb) { dev_put(dev); - goto err_out; + goto err_out_drop; } can_skb_reserve(skb); @@ -965,7 +976,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (err) { pr_notice_once("can-isotp: %s: can_send_ret %pe\n", __func__, ERR_PTR(err)); - goto err_out; + goto err_out_drop; } if (wait_tx_done) { @@ -978,6 +989,9 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) return size; +err_out_drop: + /* drop this PDU and unlock a potential wait queue */ + old_state = ISOTP_IDLE; err_out: so->tx.state = old_state; if (so->tx.state == ISOTP_IDLE) @@ -1444,6 +1458,7 @@ static int isotp_init(struct sock *sk) so->txtimer.function = isotp_tx_timer_handler; init_waitqueue_head(&so->wait); + spin_lock_init(&so->rx_lock); spin_lock(&isotp_notifier_lock); list_add_tail(&so->notifier, &isotp_notifier_list); diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index ecc400a0b7bb..4c6441536d55 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -246,6 +246,7 @@ enum { Opt_cephx_sign_messages, Opt_tcp_nodelay, Opt_abort_on_full, + Opt_rxbounce, }; enum { @@ -295,6 +296,7 @@ static const struct fs_parameter_spec ceph_parameters[] = { fsparam_u32 ("osdkeepalive", Opt_osdkeepalivetimeout), fsparam_enum ("read_from_replica", Opt_read_from_replica, ceph_param_read_from_replica), + fsparam_flag ("rxbounce", Opt_rxbounce), fsparam_enum ("ms_mode", Opt_ms_mode, ceph_param_ms_mode), fsparam_string ("secret", Opt_secret), @@ -584,6 +586,9 @@ int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt, case Opt_abort_on_full: opt->flags |= CEPH_OPT_ABORT_ON_FULL; break; + case Opt_rxbounce: + opt->flags |= CEPH_OPT_RXBOUNCE; + break; default: BUG(); @@ -660,6 +665,8 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client, seq_puts(m, "notcp_nodelay,"); if (show_all && (opt->flags & CEPH_OPT_ABORT_ON_FULL)) seq_puts(m, "abort_on_full,"); + if (opt->flags & CEPH_OPT_RXBOUNCE) + seq_puts(m, "rxbounce,"); if (opt->mount_timeout != CEPH_MOUNT_TIMEOUT_DEFAULT) seq_printf(m, "mount_timeout=%d,", diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 45eba2dcb67a..d3bb656308b4 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -515,6 +515,10 @@ static void ceph_con_reset_protocol(struct ceph_connection *con) ceph_msg_put(con->out_msg); con->out_msg = NULL; } + if (con->bounce_page) { + __free_page(con->bounce_page); + con->bounce_page = NULL; + } if (ceph_msgr2(from_msgr(con->msgr))) ceph_con_v2_reset_protocol(con); diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c index 2cb5ffdf071a..6b014eca3a13 100644 --- a/net/ceph/messenger_v1.c +++ b/net/ceph/messenger_v1.c @@ -992,8 +992,7 @@ static int read_partial_message_section(struct ceph_connection *con, static int read_partial_msg_data(struct ceph_connection *con) { - struct ceph_msg *msg = con->in_msg; - struct ceph_msg_data_cursor *cursor = &msg->cursor; + struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor; bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC); struct page *page; size_t page_offset; @@ -1001,9 +1000,6 @@ static int read_partial_msg_data(struct ceph_connection *con) u32 crc = 0; int ret; - if (!msg->num_data_items) - return -EIO; - if (do_datacrc) crc = con->in_data_crc; while (cursor->total_resid) { @@ -1031,6 +1027,46 @@ static int read_partial_msg_data(struct ceph_connection *con) return 1; /* must return > 0 to indicate success */ } +static int read_partial_msg_data_bounce(struct ceph_connection *con) +{ + struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor; + struct page *page; + size_t off, len; + u32 crc; + int ret; + + if (unlikely(!con->bounce_page)) { + con->bounce_page = alloc_page(GFP_NOIO); + if (!con->bounce_page) { + pr_err("failed to allocate bounce page\n"); + return -ENOMEM; + } + } + + crc = con->in_data_crc; + while (cursor->total_resid) { + if (!cursor->resid) { + ceph_msg_data_advance(cursor, 0); + continue; + } + + page = ceph_msg_data_next(cursor, &off, &len, NULL); + ret = ceph_tcp_recvpage(con->sock, con->bounce_page, 0, len); + if (ret <= 0) { + con->in_data_crc = crc; + return ret; + } + + crc = crc32c(crc, page_address(con->bounce_page), ret); + memcpy_to_page(page, off, page_address(con->bounce_page), ret); + + ceph_msg_data_advance(cursor, ret); + } + con->in_data_crc = crc; + + return 1; /* must return > 0 to indicate success */ +} + /* * read (part of) a message. */ @@ -1141,7 +1177,13 @@ static int read_partial_message(struct ceph_connection *con) /* (page) data */ if (data_len) { - ret = read_partial_msg_data(con); + if (!m->num_data_items) + return -EIO; + + if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) + ret = read_partial_msg_data_bounce(con); + else + ret = read_partial_msg_data(con); if (ret <= 0) return ret; } diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index c4099b641b38..c81379f93ad5 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -57,8 +57,9 @@ #define IN_S_HANDLE_CONTROL_REMAINDER 3 #define IN_S_PREPARE_READ_DATA 4 #define IN_S_PREPARE_READ_DATA_CONT 5 -#define IN_S_HANDLE_EPILOGUE 6 -#define IN_S_FINISH_SKIP 7 +#define IN_S_PREPARE_READ_ENC_PAGE 6 +#define IN_S_HANDLE_EPILOGUE 7 +#define IN_S_FINISH_SKIP 8 #define OUT_S_QUEUE_DATA 1 #define OUT_S_QUEUE_DATA_CONT 2 @@ -1032,22 +1033,41 @@ static int decrypt_control_remainder(struct ceph_connection *con) padded_len(rem_len) + CEPH_GCM_TAG_LEN); } -static int decrypt_message(struct ceph_connection *con) +static int decrypt_tail(struct ceph_connection *con) { + struct sg_table enc_sgt = {}; struct sg_table sgt = {}; + int tail_len; int ret; + tail_len = tail_onwire_len(con->in_msg, true); + ret = sg_alloc_table_from_pages(&enc_sgt, con->v2.in_enc_pages, + con->v2.in_enc_page_cnt, 0, tail_len, + GFP_NOIO); + if (ret) + goto out; + ret = setup_message_sgs(&sgt, con->in_msg, FRONT_PAD(con->v2.in_buf), MIDDLE_PAD(con->v2.in_buf), DATA_PAD(con->v2.in_buf), con->v2.in_buf, true); if (ret) goto out; - ret = gcm_crypt(con, false, sgt.sgl, sgt.sgl, - tail_onwire_len(con->in_msg, true)); + dout("%s con %p msg %p enc_page_cnt %d sg_cnt %d\n", __func__, con, + con->in_msg, con->v2.in_enc_page_cnt, sgt.orig_nents); + ret = gcm_crypt(con, false, enc_sgt.sgl, sgt.sgl, tail_len); + if (ret) + goto out; + + WARN_ON(!con->v2.in_enc_page_cnt); + ceph_release_page_vector(con->v2.in_enc_pages, + con->v2.in_enc_page_cnt); + con->v2.in_enc_pages = NULL; + con->v2.in_enc_page_cnt = 0; out: sg_free_table(&sgt); + sg_free_table(&enc_sgt); return ret; } @@ -1733,54 +1753,157 @@ static int prepare_read_control_remainder(struct ceph_connection *con) return 0; } -static void prepare_read_data(struct ceph_connection *con) +static int prepare_read_data(struct ceph_connection *con) { struct bio_vec bv; - if (!con_secure(con)) - con->in_data_crc = -1; + con->in_data_crc = -1; ceph_msg_data_cursor_init(&con->v2.in_cursor, con->in_msg, data_len(con->in_msg)); get_bvec_at(&con->v2.in_cursor, &bv); - set_in_bvec(con, &bv); + if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) { + if (unlikely(!con->bounce_page)) { + con->bounce_page = alloc_page(GFP_NOIO); + if (!con->bounce_page) { + pr_err("failed to allocate bounce page\n"); + return -ENOMEM; + } + } + + bv.bv_page = con->bounce_page; + bv.bv_offset = 0; + set_in_bvec(con, &bv); + } else { + set_in_bvec(con, &bv); + } con->v2.in_state = IN_S_PREPARE_READ_DATA_CONT; + return 0; } static void prepare_read_data_cont(struct ceph_connection *con) { struct bio_vec bv; - if (!con_secure(con)) + if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) { + con->in_data_crc = crc32c(con->in_data_crc, + page_address(con->bounce_page), + con->v2.in_bvec.bv_len); + + get_bvec_at(&con->v2.in_cursor, &bv); + memcpy_to_page(bv.bv_page, bv.bv_offset, + page_address(con->bounce_page), + con->v2.in_bvec.bv_len); + } else { con->in_data_crc = ceph_crc32c_page(con->in_data_crc, con->v2.in_bvec.bv_page, con->v2.in_bvec.bv_offset, con->v2.in_bvec.bv_len); + } ceph_msg_data_advance(&con->v2.in_cursor, con->v2.in_bvec.bv_len); if (con->v2.in_cursor.total_resid) { get_bvec_at(&con->v2.in_cursor, &bv); - set_in_bvec(con, &bv); + if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) { + bv.bv_page = con->bounce_page; + bv.bv_offset = 0; + set_in_bvec(con, &bv); + } else { + set_in_bvec(con, &bv); + } WARN_ON(con->v2.in_state != IN_S_PREPARE_READ_DATA_CONT); return; } /* - * We've read all data. Prepare to read data padding (if any) - * and epilogue. + * We've read all data. Prepare to read epilogue. */ reset_in_kvecs(con); - if (con_secure(con)) { - if (need_padding(data_len(con->in_msg))) - add_in_kvec(con, DATA_PAD(con->v2.in_buf), - padding_len(data_len(con->in_msg))); - add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_SECURE_LEN); + add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_PLAIN_LEN); + con->v2.in_state = IN_S_HANDLE_EPILOGUE; +} + +static int prepare_read_tail_plain(struct ceph_connection *con) +{ + struct ceph_msg *msg = con->in_msg; + + if (!front_len(msg) && !middle_len(msg)) { + WARN_ON(!data_len(msg)); + return prepare_read_data(con); + } + + reset_in_kvecs(con); + if (front_len(msg)) { + add_in_kvec(con, msg->front.iov_base, front_len(msg)); + WARN_ON(msg->front.iov_len != front_len(msg)); + } + if (middle_len(msg)) { + add_in_kvec(con, msg->middle->vec.iov_base, middle_len(msg)); + WARN_ON(msg->middle->vec.iov_len != middle_len(msg)); + } + + if (data_len(msg)) { + con->v2.in_state = IN_S_PREPARE_READ_DATA; } else { add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_PLAIN_LEN); + con->v2.in_state = IN_S_HANDLE_EPILOGUE; } + return 0; +} + +static void prepare_read_enc_page(struct ceph_connection *con) +{ + struct bio_vec bv; + + dout("%s con %p i %d resid %d\n", __func__, con, con->v2.in_enc_i, + con->v2.in_enc_resid); + WARN_ON(!con->v2.in_enc_resid); + + bv.bv_page = con->v2.in_enc_pages[con->v2.in_enc_i]; + bv.bv_offset = 0; + bv.bv_len = min(con->v2.in_enc_resid, (int)PAGE_SIZE); + + set_in_bvec(con, &bv); + con->v2.in_enc_i++; + con->v2.in_enc_resid -= bv.bv_len; + + if (con->v2.in_enc_resid) { + con->v2.in_state = IN_S_PREPARE_READ_ENC_PAGE; + return; + } + + /* + * We are set to read the last piece of ciphertext (ending + * with epilogue) + auth tag. + */ + WARN_ON(con->v2.in_enc_i != con->v2.in_enc_page_cnt); con->v2.in_state = IN_S_HANDLE_EPILOGUE; } +static int prepare_read_tail_secure(struct ceph_connection *con) +{ + struct page **enc_pages; + int enc_page_cnt; + int tail_len; + + tail_len = tail_onwire_len(con->in_msg, true); + WARN_ON(!tail_len); + + enc_page_cnt = calc_pages_for(0, tail_len); + enc_pages = ceph_alloc_page_vector(enc_page_cnt, GFP_NOIO); + if (IS_ERR(enc_pages)) + return PTR_ERR(enc_pages); + + WARN_ON(con->v2.in_enc_pages || con->v2.in_enc_page_cnt); + con->v2.in_enc_pages = enc_pages; + con->v2.in_enc_page_cnt = enc_page_cnt; + con->v2.in_enc_resid = tail_len; + con->v2.in_enc_i = 0; + + prepare_read_enc_page(con); + return 0; +} + static void __finish_skip(struct ceph_connection *con) { con->in_seq++; @@ -2589,47 +2712,26 @@ static int __handle_control(struct ceph_connection *con, void *p) } msg = con->in_msg; /* set in process_message_header() */ - if (!front_len(msg) && !middle_len(msg)) { - if (!data_len(msg)) - return process_message(con); - - prepare_read_data(con); - return 0; - } - - reset_in_kvecs(con); if (front_len(msg)) { WARN_ON(front_len(msg) > msg->front_alloc_len); - add_in_kvec(con, msg->front.iov_base, front_len(msg)); msg->front.iov_len = front_len(msg); - - if (con_secure(con) && need_padding(front_len(msg))) - add_in_kvec(con, FRONT_PAD(con->v2.in_buf), - padding_len(front_len(msg))); } else { msg->front.iov_len = 0; } if (middle_len(msg)) { WARN_ON(middle_len(msg) > msg->middle->alloc_len); - add_in_kvec(con, msg->middle->vec.iov_base, middle_len(msg)); msg->middle->vec.iov_len = middle_len(msg); - - if (con_secure(con) && need_padding(middle_len(msg))) - add_in_kvec(con, MIDDLE_PAD(con->v2.in_buf), - padding_len(middle_len(msg))); } else if (msg->middle) { msg->middle->vec.iov_len = 0; } - if (data_len(msg)) { - con->v2.in_state = IN_S_PREPARE_READ_DATA; - } else { - add_in_kvec(con, con->v2.in_buf, - con_secure(con) ? CEPH_EPILOGUE_SECURE_LEN : - CEPH_EPILOGUE_PLAIN_LEN); - con->v2.in_state = IN_S_HANDLE_EPILOGUE; - } - return 0; + if (!front_len(msg) && !middle_len(msg) && !data_len(msg)) + return process_message(con); + + if (con_secure(con)) + return prepare_read_tail_secure(con); + + return prepare_read_tail_plain(con); } static int handle_preamble(struct ceph_connection *con) @@ -2717,7 +2819,7 @@ static int handle_epilogue(struct ceph_connection *con) int ret; if (con_secure(con)) { - ret = decrypt_message(con); + ret = decrypt_tail(con); if (ret) { if (ret == -EBADMSG) con->error_msg = "integrity error, bad epilogue auth tag"; @@ -2785,13 +2887,16 @@ static int populate_in_iter(struct ceph_connection *con) ret = handle_control_remainder(con); break; case IN_S_PREPARE_READ_DATA: - prepare_read_data(con); - ret = 0; + ret = prepare_read_data(con); break; case IN_S_PREPARE_READ_DATA_CONT: prepare_read_data_cont(con); ret = 0; break; + case IN_S_PREPARE_READ_ENC_PAGE: + prepare_read_enc_page(con); + ret = 0; + break; case IN_S_HANDLE_EPILOGUE: ret = handle_epilogue(con); break; @@ -3326,20 +3431,16 @@ void ceph_con_v2_revoke(struct ceph_connection *con) static void revoke_at_prepare_read_data(struct ceph_connection *con) { - int remaining; /* data + [data padding] + epilogue */ + int remaining; int resid; + WARN_ON(con_secure(con)); WARN_ON(!data_len(con->in_msg)); WARN_ON(!iov_iter_is_kvec(&con->v2.in_iter)); resid = iov_iter_count(&con->v2.in_iter); WARN_ON(!resid); - if (con_secure(con)) - remaining = padded_len(data_len(con->in_msg)) + - CEPH_EPILOGUE_SECURE_LEN; - else - remaining = data_len(con->in_msg) + CEPH_EPILOGUE_PLAIN_LEN; - + remaining = data_len(con->in_msg) + CEPH_EPILOGUE_PLAIN_LEN; dout("%s con %p resid %d remaining %d\n", __func__, con, resid, remaining); con->v2.in_iter.count -= resid; @@ -3350,8 +3451,9 @@ static void revoke_at_prepare_read_data(struct ceph_connection *con) static void revoke_at_prepare_read_data_cont(struct ceph_connection *con) { int recved, resid; /* current piece of data */ - int remaining; /* [data padding] + epilogue */ + int remaining; + WARN_ON(con_secure(con)); WARN_ON(!data_len(con->in_msg)); WARN_ON(!iov_iter_is_bvec(&con->v2.in_iter)); resid = iov_iter_count(&con->v2.in_iter); @@ -3363,12 +3465,7 @@ static void revoke_at_prepare_read_data_cont(struct ceph_connection *con) ceph_msg_data_advance(&con->v2.in_cursor, recved); WARN_ON(resid > con->v2.in_cursor.total_resid); - if (con_secure(con)) - remaining = padding_len(data_len(con->in_msg)) + - CEPH_EPILOGUE_SECURE_LEN; - else - remaining = CEPH_EPILOGUE_PLAIN_LEN; - + remaining = CEPH_EPILOGUE_PLAIN_LEN; dout("%s con %p total_resid %zu remaining %d\n", __func__, con, con->v2.in_cursor.total_resid, remaining); con->v2.in_iter.count -= resid; @@ -3376,11 +3473,26 @@ static void revoke_at_prepare_read_data_cont(struct ceph_connection *con) con->v2.in_state = IN_S_FINISH_SKIP; } +static void revoke_at_prepare_read_enc_page(struct ceph_connection *con) +{ + int resid; /* current enc page (not necessarily data) */ + + WARN_ON(!con_secure(con)); + WARN_ON(!iov_iter_is_bvec(&con->v2.in_iter)); + resid = iov_iter_count(&con->v2.in_iter); + WARN_ON(!resid || resid > con->v2.in_bvec.bv_len); + + dout("%s con %p resid %d enc_resid %d\n", __func__, con, resid, + con->v2.in_enc_resid); + con->v2.in_iter.count -= resid; + set_in_skip(con, resid + con->v2.in_enc_resid); + con->v2.in_state = IN_S_FINISH_SKIP; +} + static void revoke_at_handle_epilogue(struct ceph_connection *con) { int resid; - WARN_ON(!iov_iter_is_kvec(&con->v2.in_iter)); resid = iov_iter_count(&con->v2.in_iter); WARN_ON(!resid); @@ -3399,6 +3511,9 @@ void ceph_con_v2_revoke_incoming(struct ceph_connection *con) case IN_S_PREPARE_READ_DATA_CONT: revoke_at_prepare_read_data_cont(con); break; + case IN_S_PREPARE_READ_ENC_PAGE: + revoke_at_prepare_read_enc_page(con); + break; case IN_S_HANDLE_EPILOGUE: revoke_at_handle_epilogue(con); break; @@ -3432,6 +3547,13 @@ void ceph_con_v2_reset_protocol(struct ceph_connection *con) clear_out_sign_kvecs(con); free_conn_bufs(con); + if (con->v2.in_enc_pages) { + WARN_ON(!con->v2.in_enc_page_cnt); + ceph_release_page_vector(con->v2.in_enc_pages, + con->v2.in_enc_page_cnt); + con->v2.in_enc_pages = NULL; + con->v2.in_enc_page_cnt = 0; + } if (con->v2.out_enc_pages) { WARN_ON(!con->v2.out_enc_page_cnt); ceph_release_page_vector(con->v2.out_enc_pages, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 0118f0afaa4f..9d0388bed0c1 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -681,7 +681,7 @@ exit: * while trying to recycle fragments on __skb_frag_unref() we need * to make one SKB responsible for triggering the recycle path. * So disable the recycling bit if an SKB is cloned and we have - * additional references to to the fragmented part of the SKB. + * additional references to the fragmented part of the SKB. * Eventually the last SKB will have the recycling bit set and it's * dataref set to 0, which will trigger the recycling */ diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 909b045c9b11..e498c927c3d0 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -1784,7 +1784,6 @@ EXPORT_SYMBOL_GPL(dsa_unregister_switch); void dsa_switch_shutdown(struct dsa_switch *ds) { struct net_device *master, *slave_dev; - LIST_HEAD(unregister_list); struct dsa_port *dp; mutex_lock(&dsa2_mutex); @@ -1795,25 +1794,13 @@ void dsa_switch_shutdown(struct dsa_switch *ds) slave_dev = dp->slave; netdev_upper_dev_unlink(master, slave_dev); - /* Just unlinking ourselves as uppers of the master is not - * sufficient. When the master net device unregisters, that will - * also call dev_close, which we will catch as NETDEV_GOING_DOWN - * and trigger a dev_close on our own devices (dsa_slave_close). - * In turn, that will call dev_mc_unsync on the master's net - * device. If the master is also a DSA switch port, this will - * trigger dsa_slave_set_rx_mode which will call dev_mc_sync on - * its own master. Lockdep will complain about the fact that - * all cascaded masters have the same dsa_master_addr_list_lock_key, - * which it normally would not do if the cascaded masters would - * be in a proper upper/lower relationship, which we've just - * destroyed. - * To suppress the lockdep warnings, let's actually unregister - * the DSA slave interfaces too, to avoid the nonsensical - * multicast address list synchronization on shutdown. - */ - unregister_netdevice_queue(slave_dev, &unregister_list); } - unregister_netdevice_many(&unregister_list); + + /* Disconnect from further netdevice notifiers on the master, + * since netdev_uses_dsa() will now return false. + */ + dsa_switch_for_each_cpu_port(dp, ds) + dp->master->dsa_ptr = NULL; rtnl_unlock(); mutex_unlock(&dsa2_mutex); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 4a55a620e526..c860519d57ee 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -256,7 +256,9 @@ static int __net_init ipmr_rules_init(struct net *net) return 0; err2: + rtnl_lock(); ipmr_free_table(mrt); + rtnl_unlock(); err1: fib_rules_unregister(ops); return err; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index a03a6bfb4353..760e8221d321 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -936,6 +936,22 @@ void tcp_remove_empty_skb(struct sock *sk) } } +/* skb changing from pure zc to mixed, must charge zc */ +static int tcp_downgrade_zcopy_pure(struct sock *sk, struct sk_buff *skb) +{ + if (unlikely(skb_zcopy_pure(skb))) { + u32 extra = skb->truesize - + SKB_TRUESIZE(skb_end_offset(skb)); + + if (!sk_wmem_schedule(sk, extra)) + return -ENOMEM; + + sk_mem_charge(sk, extra); + skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY; + } + return 0; +} + static struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags, struct page *page, int offset, size_t *size) { @@ -971,7 +987,7 @@ new_segment: tcp_mark_push(tp, skb); goto new_segment; } - if (!sk_wmem_schedule(sk, copy)) + if (tcp_downgrade_zcopy_pure(sk, skb) || !sk_wmem_schedule(sk, copy)) return NULL; if (can_coalesce) { @@ -1319,19 +1335,8 @@ new_segment: copy = min_t(int, copy, pfrag->size - pfrag->offset); - /* skb changing from pure zc to mixed, must charge zc */ - if (unlikely(skb_zcopy_pure(skb))) { - u32 extra = skb->truesize - - SKB_TRUESIZE(skb_end_offset(skb)); - - if (!sk_wmem_schedule(sk, extra)) - goto wait_for_space; - - sk_mem_charge(sk, extra); - skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY; - } - - if (!sk_wmem_schedule(sk, copy)) + if (tcp_downgrade_zcopy_pure(sk, skb) || + !sk_wmem_schedule(sk, copy)) goto wait_for_space; err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb, diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 881fe6b50307..0ebaaec3faf9 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -243,7 +243,9 @@ static int __net_init ip6mr_rules_init(struct net *net) return 0; err2: + rtnl_lock(); ip6mr_free_table(mrt); + rtnl_unlock(); err1: fib_rules_unregister(ops); return err; diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 48f75a56f4ae..d6fdc5782d33 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1607,6 +1607,7 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct mpls_dev *mdev; unsigned int flags; + int err; if (event == NETDEV_REGISTER) { mdev = mpls_add_dev(dev); @@ -1621,7 +1622,6 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, return NOTIFY_OK; switch (event) { - int err; case NETDEV_DOWN: err = mpls_ifdown(dev, event); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 5464c2d268bd..e4fd54fff1d2 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -925,6 +925,7 @@ out: static int mptcp_pm_nl_create_listen_socket(struct sock *sk, struct mptcp_pm_addr_entry *entry) { + int addrlen = sizeof(struct sockaddr_in); struct sockaddr_storage addr; struct mptcp_sock *msk; struct socket *ssock; @@ -949,8 +950,11 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, } mptcp_info2sockaddr(&entry->addr, &addr, entry->addr.family); - err = kernel_bind(ssock, (struct sockaddr *)&addr, - sizeof(struct sockaddr_in)); +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + if (entry->addr.family == AF_INET6) + addrlen = sizeof(struct sockaddr_in6); +#endif + err = kernel_bind(ssock, (struct sockaddr *)&addr, addrlen); if (err) { pr_warn("kernel_bind error, err=%d", err); goto out; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 3d9f9ee50294..1ea2ad732d57 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2321,7 +2321,8 @@ ctnetlink_create_conntrack(struct net *net, if (helper->from_nlattr) helper->from_nlattr(helpinfo, ct); - /* not in hash table yet so not strictly necessary */ + /* disable helper auto-assignment for this entry */ + ct->status |= IPS_HELPER; RCU_INIT_POINTER(help->helper, helper); } } else { diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 2394238d01c9..5a936334b517 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -489,6 +489,15 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, pr_debug("Setting vtag %x for dir %d\n", ih->init_tag, !dir); ct->proto.sctp.vtag[!dir] = ih->init_tag; + + /* don't renew timeout on init retransmit so + * port reuse by client or NAT middlebox cannot + * keep entry alive indefinitely (incl. nat info). + */ + if (new_state == SCTP_CONNTRACK_CLOSED && + old_state == SCTP_CONNTRACK_CLOSED && + nf_ct_is_confirmed(ct)) + ignore = true; } ct->proto.sctp.state = new_state; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index af5115e127cf..d1582b888c0d 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -446,6 +446,32 @@ static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff, } } +static void tcp_init_sender(struct ip_ct_tcp_state *sender, + struct ip_ct_tcp_state *receiver, + const struct sk_buff *skb, + unsigned int dataoff, + const struct tcphdr *tcph, + u32 end, u32 win) +{ + /* SYN-ACK in reply to a SYN + * or SYN from reply direction in simultaneous open. + */ + sender->td_end = + sender->td_maxend = end; + sender->td_maxwin = (win == 0 ? 1 : win); + + tcp_options(skb, dataoff, tcph, sender); + /* RFC 1323: + * Both sides must send the Window Scale option + * to enable window scaling in either direction. + */ + if (!(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE && + receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE)) { + sender->td_scale = 0; + receiver->td_scale = 0; + } +} + static bool tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir, unsigned int index, @@ -499,24 +525,9 @@ static bool tcp_in_window(struct nf_conn *ct, * Initialize sender data. */ if (tcph->syn) { - /* - * SYN-ACK in reply to a SYN - * or SYN from reply direction in simultaneous open. - */ - sender->td_end = - sender->td_maxend = end; - sender->td_maxwin = (win == 0 ? 1 : win); - - tcp_options(skb, dataoff, tcph, sender); - /* - * RFC 1323: - * Both sides must send the Window Scale option - * to enable window scaling in either direction. - */ - if (!(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE - && receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE)) - sender->td_scale = - receiver->td_scale = 0; + tcp_init_sender(sender, receiver, + skb, dataoff, tcph, + end, win); if (!tcph->ack) /* Simultaneous open */ return true; @@ -560,6 +571,18 @@ static bool tcp_in_window(struct nf_conn *ct, sender->td_maxwin = (win == 0 ? 1 : win); tcp_options(skb, dataoff, tcph, sender); + } else if (tcph->syn && dir == IP_CT_DIR_REPLY && + state->state == TCP_CONNTRACK_SYN_SENT) { + /* Retransmitted syn-ack, or syn (simultaneous open). + * + * Re-init state for this direction, just like for the first + * syn(-ack) reply, it might differ in seq, ack or tcp options. + */ + tcp_init_sender(sender, receiver, + skb, dataoff, tcph, + end, win); + if (!tcph->ack) + return true; } if (!(tcph->ack)) { diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index dfc06cdb8fa2..d2b9378164bb 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -167,7 +167,7 @@ nft_tcp_header_pointer(const struct nft_pktinfo *pkt, { struct tcphdr *tcph; - if (pkt->tprot != IPPROTO_TCP) + if (pkt->tprot != IPPROTO_TCP || pkt->fragoff) return NULL; tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt), sizeof(*tcph), buffer); diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 940fed9a760b..5cc06aef4345 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -83,7 +83,7 @@ static int __nft_payload_inner_offset(struct nft_pktinfo *pkt) { unsigned int thoff = nft_thoff(pkt); - if (!(pkt->flags & NFT_PKTINFO_L4PROTO)) + if (!(pkt->flags & NFT_PKTINFO_L4PROTO) || pkt->fragoff) return -1; switch (pkt->tprot) { @@ -147,7 +147,7 @@ void nft_payload_eval(const struct nft_expr *expr, offset = skb_network_offset(skb); break; case NFT_PAYLOAD_TRANSPORT_HEADER: - if (!(pkt->flags & NFT_PKTINFO_L4PROTO)) + if (!(pkt->flags & NFT_PKTINFO_L4PROTO) || pkt->fragoff) goto err; offset = nft_thoff(pkt); break; @@ -688,7 +688,7 @@ static void nft_payload_set_eval(const struct nft_expr *expr, offset = skb_network_offset(skb); break; case NFT_PAYLOAD_TRANSPORT_HEADER: - if (!(pkt->flags & NFT_PKTINFO_L4PROTO)) + if (!(pkt->flags & NFT_PKTINFO_L4PROTO) || pkt->fragoff) goto err; offset = nft_thoff(pkt); break; @@ -728,7 +728,8 @@ static void nft_payload_set_eval(const struct nft_expr *expr, if (priv->csum_type == NFT_PAYLOAD_CSUM_SCTP && pkt->tprot == IPPROTO_SCTP && skb->ip_summed != CHECKSUM_PARTIAL) { - if (nft_payload_csum_sctp(skb, nft_thoff(pkt))) + if (pkt->fragoff == 0 && + nft_payload_csum_sctp(skb, nft_thoff(pkt))) goto err; } diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 291f1484a1b7..0599246c0376 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -368,9 +368,6 @@ static int smc_pnet_add_eth(struct smc_pnettable *pnettable, struct net *net, new_pe->type = SMC_PNET_ETH; memcpy(new_pe->pnet_name, pnet_name, SMC_MAX_PNETID_LEN); strncpy(new_pe->eth_name, eth_name, IFNAMSIZ); - new_pe->ndev = ndev; - if (ndev) - netdev_tracker_alloc(ndev, &new_pe->dev_tracker, GFP_KERNEL); rc = -EEXIST; new_netdev = true; write_lock(&pnettable->lock); @@ -382,6 +379,11 @@ static int smc_pnet_add_eth(struct smc_pnettable *pnettable, struct net *net, } } if (new_netdev) { + if (ndev) { + new_pe->ndev = ndev; + netdev_tracker_alloc(ndev, &new_pe->dev_tracker, + GFP_ATOMIC); + } list_add_tail(&new_pe->list, &pnettable->pnetlist); write_unlock(&pnettable->lock); } else { diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c index b64a0286b182..05c758da6a92 100644 --- a/net/sunrpc/sysfs.c +++ b/net/sunrpc/sysfs.c @@ -115,11 +115,14 @@ static ssize_t rpc_sysfs_xprt_srcaddr_show(struct kobject *kobj, } sock = container_of(xprt, struct sock_xprt, xprt); - if (kernel_getsockname(sock->sock, (struct sockaddr *)&saddr) < 0) + mutex_lock(&sock->recv_mutex); + if (sock->sock == NULL || + kernel_getsockname(sock->sock, (struct sockaddr *)&saddr) < 0) goto out; ret = sprintf(buf, "%pISc\n", &saddr); out: + mutex_unlock(&sock->recv_mutex); xprt_put(xprt); return ret + 1; } diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index f172d1298013..7b5fce2faa10 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -413,6 +413,7 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt) IB_POLL_WORKQUEUE); if (IS_ERR(ep->re_attr.send_cq)) { rc = PTR_ERR(ep->re_attr.send_cq); + ep->re_attr.send_cq = NULL; goto out_destroy; } @@ -421,6 +422,7 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt) IB_POLL_WORKQUEUE); if (IS_ERR(ep->re_attr.recv_cq)) { rc = PTR_ERR(ep->re_attr.recv_cq); + ep->re_attr.recv_cq = NULL; goto out_destroy; } ep->re_receive_count = 0; @@ -459,6 +461,7 @@ static int rpcrdma_ep_create(struct rpcrdma_xprt *r_xprt) ep->re_pd = ib_alloc_pd(device, 0); if (IS_ERR(ep->re_pd)) { rc = PTR_ERR(ep->re_pd); + ep->re_pd = NULL; goto out_destroy; } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 69b6ee5a5fd1..0f39e08ee580 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1641,7 +1641,12 @@ static int xs_get_srcport(struct sock_xprt *transport) unsigned short get_srcport(struct rpc_xprt *xprt) { struct sock_xprt *sock = container_of(xprt, struct sock_xprt, xprt); - return xs_sock_getport(sock->sock); + unsigned short ret = 0; + mutex_lock(&sock->recv_mutex); + if (sock->sock) + ret = xs_sock_getport(sock->sock); + mutex_unlock(&sock->recv_mutex); + return ret; } EXPORT_SYMBOL(get_srcport); diff --git a/net/tipc/link.c b/net/tipc/link.c index 8d9e09f48f4c..1e14d7f8f28f 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -2200,7 +2200,7 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, struct tipc_msg *hdr = buf_msg(skb); struct tipc_gap_ack_blks *ga = NULL; bool reply = msg_probe(hdr), retransmitted = false; - u16 dlen = msg_data_sz(hdr), glen = 0; + u32 dlen = msg_data_sz(hdr), glen = 0; u16 peers_snd_nxt = msg_next_sent(hdr); u16 peers_tol = msg_link_tolerance(hdr); u16 peers_prio = msg_linkprio(hdr); @@ -2214,6 +2214,10 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, void *data; trace_tipc_proto_rcv(skb, false, l->name); + + if (dlen > U16_MAX) + goto exit; + if (tipc_link_is_blocked(l) || !xmitq) goto exit; @@ -2309,7 +2313,8 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, /* Receive Gap ACK blocks from peer if any */ glen = tipc_get_gap_ack_blks(&ga, l, hdr, true); - + if(glen > dlen) + break; tipc_mon_rcv(l->net, data + glen, dlen - glen, l->addr, &l->mon_state, l->bearer_id); diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index 407619697292..2f4d23238a7e 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -496,6 +496,8 @@ void tipc_mon_rcv(struct net *net, void *data, u16 dlen, u32 addr, state->probing = false; /* Sanity check received domain record */ + if (new_member_cnt > MAX_MON_DOMAIN) + return; if (dlen < dom_rec_len(arrv_dom, 0)) return; if (dlen != dom_rec_len(arrv_dom, new_member_cnt)) diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index bda902caa814..8267b751a526 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -313,7 +313,7 @@ static bool tipc_update_nametbl(struct net *net, struct distr_item *i, pr_warn_ratelimited("Failed to remove binding %u,%u from %u\n", ua.sr.type, ua.sr.lower, node); } else { - pr_warn("Unrecognized name table message received\n"); + pr_warn_ratelimited("Unknown name table message received\n"); } return false; } diff --git a/security/integrity/digsig_asymmetric.c b/security/integrity/digsig_asymmetric.c index 23240d793b07..895f4b9ce8c6 100644 --- a/security/integrity/digsig_asymmetric.c +++ b/security/integrity/digsig_asymmetric.c @@ -109,22 +109,25 @@ int asymmetric_verify(struct key *keyring, const char *sig, pk = asymmetric_key_public_key(key); pks.pkey_algo = pk->pkey_algo; - if (!strcmp(pk->pkey_algo, "rsa")) + if (!strcmp(pk->pkey_algo, "rsa")) { pks.encoding = "pkcs1"; - else if (!strncmp(pk->pkey_algo, "ecdsa-", 6)) + } else if (!strncmp(pk->pkey_algo, "ecdsa-", 6)) { /* edcsa-nist-p192 etc. */ pks.encoding = "x962"; - else if (!strcmp(pk->pkey_algo, "ecrdsa") || - !strcmp(pk->pkey_algo, "sm2")) + } else if (!strcmp(pk->pkey_algo, "ecrdsa") || + !strcmp(pk->pkey_algo, "sm2")) { pks.encoding = "raw"; - else - return -ENOPKG; + } else { + ret = -ENOPKG; + goto out; + } pks.digest = (u8 *)data; pks.digest_size = datalen; pks.s = hdr->sig; pks.s_size = siglen; ret = verify_signature(key, &pks); +out: key_put(key); pr_debug("%s() = %d\n", __func__, ret); return ret; diff --git a/security/integrity/ima/ima_fs.c b/security/integrity/ima/ima_fs.c index 3d8e9d5db5aa..3ad8f7734208 100644 --- a/security/integrity/ima/ima_fs.c +++ b/security/integrity/ima/ima_fs.c @@ -496,12 +496,12 @@ int __init ima_fs_init(void) return 0; out: + securityfs_remove(ima_policy); securityfs_remove(violations); securityfs_remove(runtime_measurements_count); securityfs_remove(ascii_runtime_measurements); securityfs_remove(binary_runtime_measurements); securityfs_remove(ima_symlink); securityfs_remove(ima_dir); - securityfs_remove(ima_policy); return -1; } diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 320ca80aacab..2a1f6418b10a 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -1967,6 +1967,14 @@ int ima_policy_show(struct seq_file *m, void *v) rcu_read_lock(); + /* Do not print rules with inactive LSM labels */ + for (i = 0; i < MAX_LSM_RULES; i++) { + if (entry->lsm[i].args_p && !entry->lsm[i].rule) { + rcu_read_unlock(); + return 0; + } + } + if (entry->action & MEASURE) seq_puts(m, pt(Opt_measure)); if (entry->action & DONT_MEASURE) diff --git a/security/integrity/ima/ima_template.c b/security/integrity/ima/ima_template.c index 694560396be0..db1ad6d7a57f 100644 --- a/security/integrity/ima/ima_template.c +++ b/security/integrity/ima/ima_template.c @@ -29,6 +29,7 @@ static struct ima_template_desc builtin_templates[] = { static LIST_HEAD(defined_templates); static DEFINE_SPINLOCK(template_list); +static int template_setup_done; static const struct ima_template_field supported_fields[] = { {.field_id = "d", .field_init = ima_eventdigest_init, @@ -101,10 +102,11 @@ static int __init ima_template_setup(char *str) struct ima_template_desc *template_desc; int template_len = strlen(str); - if (ima_template) + if (template_setup_done) return 1; - ima_init_template_list(); + if (!ima_template) + ima_init_template_list(); /* * Verify that a template with the supplied name exists. @@ -128,6 +130,7 @@ static int __init ima_template_setup(char *str) } ima_template = template_desc; + template_setup_done = 1; return 1; } __setup("ima_template=", ima_template_setup); @@ -136,7 +139,7 @@ static int __init ima_template_fmt_setup(char *str) { int num_templates = ARRAY_SIZE(builtin_templates); - if (ima_template) + if (template_setup_done) return 1; if (template_desc_init_fields(str, NULL, NULL) < 0) { @@ -147,6 +150,7 @@ static int __init ima_template_fmt_setup(char *str) builtin_templates[num_templates - 1].fmt = str; ima_template = builtin_templates + num_templates - 1; + template_setup_done = 1; return 1; } diff --git a/security/integrity/integrity_audit.c b/security/integrity/integrity_audit.c index 29220056207f..0ec5e4c22cb2 100644 --- a/security/integrity/integrity_audit.c +++ b/security/integrity/integrity_audit.c @@ -45,6 +45,8 @@ void integrity_audit_message(int audit_msgno, struct inode *inode, return; ab = audit_log_start(audit_context(), GFP_KERNEL, audit_msgno); + if (!ab) + return; audit_log_format(ab, "pid=%d uid=%u auid=%u ses=%u", task_pid_nr(current), from_kuid(&init_user_ns, current_uid()), diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 621883e71194..a056b3ef3c84 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -172,6 +172,19 @@ unsigned long _snd_pcm_stream_lock_irqsave(struct snd_pcm_substream *substream) } EXPORT_SYMBOL_GPL(_snd_pcm_stream_lock_irqsave); +unsigned long _snd_pcm_stream_lock_irqsave_nested(struct snd_pcm_substream *substream) +{ + unsigned long flags = 0; + if (substream->pcm->nonatomic) + mutex_lock_nested(&substream->self_group.mutex, + SINGLE_DEPTH_NESTING); + else + spin_lock_irqsave_nested(&substream->self_group.lock, flags, + SINGLE_DEPTH_NESTING); + return flags; +} +EXPORT_SYMBOL_GPL(_snd_pcm_stream_lock_irqsave_nested); + /** * snd_pcm_stream_unlock_irqrestore - Unlock the PCM stream * @substream: PCM substream diff --git a/sound/hda/intel-sdw-acpi.c b/sound/hda/intel-sdw-acpi.c index b7758dbe2371..5cb92f7ccbca 100644 --- a/sound/hda/intel-sdw-acpi.c +++ b/sound/hda/intel-sdw-acpi.c @@ -50,11 +50,11 @@ static bool is_link_enabled(struct fwnode_handle *fw_node, int i) static int sdw_intel_scan_controller(struct sdw_intel_acpi_info *info) { - struct acpi_device *adev; + struct acpi_device *adev = acpi_fetch_acpi_dev(info->handle); int ret, i; u8 count; - if (acpi_bus_get_device(info->handle, &adev)) + if (!adev) return -EINVAL; /* Found controller, find links supported */ @@ -119,7 +119,6 @@ static acpi_status sdw_intel_acpi_cb(acpi_handle handle, u32 level, void *cdata, void **return_value) { struct sdw_intel_acpi_info *info = cdata; - struct acpi_device *adev; acpi_status status; u64 adr; @@ -127,7 +126,7 @@ static acpi_status sdw_intel_acpi_cb(acpi_handle handle, u32 level, if (ACPI_FAILURE(status)) return AE_OK; /* keep going */ - if (acpi_bus_get_device(handle, &adev)) { + if (!acpi_fetch_acpi_dev(handle)) { pr_err("%s: Couldn't find ACPI handle\n", __func__); return AE_NOT_FOUND; } diff --git a/sound/pci/hda/hda_auto_parser.c b/sound/pci/hda/hda_auto_parser.c index 82c492b05667..cd1db943b7e0 100644 --- a/sound/pci/hda/hda_auto_parser.c +++ b/sound/pci/hda/hda_auto_parser.c @@ -981,7 +981,7 @@ void snd_hda_pick_fixup(struct hda_codec *codec, int id = HDA_FIXUP_ID_NOT_SET; const char *name = NULL; const char *type = NULL; - int vendor, device; + unsigned int vendor, device; if (codec->fixup_id != HDA_FIXUP_ID_NOT_SET) return; diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 7016b48227bf..f552785d301e 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -3000,6 +3000,10 @@ void snd_hda_codec_shutdown(struct hda_codec *codec) { struct hda_pcm *cpcm; + /* Skip the shutdown if codec is not registered */ + if (!codec->registered) + return; + list_for_each_entry(cpcm, &codec->pcm_list_head, list) snd_pcm_suspend_all(cpcm->pcm); diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index 3bf5e3410703..fc114e522480 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -91,6 +91,12 @@ static void snd_hda_gen_spec_free(struct hda_gen_spec *spec) free_kctls(spec); snd_array_free(&spec->paths); snd_array_free(&spec->loopback_list); +#ifdef CONFIG_SND_HDA_GENERIC_LEDS + if (spec->led_cdevs[LED_AUDIO_MUTE]) + led_classdev_unregister(spec->led_cdevs[LED_AUDIO_MUTE]); + if (spec->led_cdevs[LED_AUDIO_MICMUTE]) + led_classdev_unregister(spec->led_cdevs[LED_AUDIO_MICMUTE]); +#endif } /* @@ -3922,7 +3928,10 @@ static int create_mute_led_cdev(struct hda_codec *codec, enum led_brightness), bool micmute) { + struct hda_gen_spec *spec = codec->spec; struct led_classdev *cdev; + int idx = micmute ? LED_AUDIO_MICMUTE : LED_AUDIO_MUTE; + int err; cdev = devm_kzalloc(&codec->core.dev, sizeof(*cdev), GFP_KERNEL); if (!cdev) @@ -3932,10 +3941,14 @@ static int create_mute_led_cdev(struct hda_codec *codec, cdev->max_brightness = 1; cdev->default_trigger = micmute ? "audio-micmute" : "audio-mute"; cdev->brightness_set_blocking = callback; - cdev->brightness = ledtrig_audio_get(micmute ? LED_AUDIO_MICMUTE : LED_AUDIO_MUTE); + cdev->brightness = ledtrig_audio_get(idx); cdev->flags = LED_CORE_SUSPENDRESUME; - return devm_led_classdev_register(&codec->core.dev, cdev); + err = led_classdev_register(&codec->core.dev, cdev); + if (err < 0) + return err; + spec->led_cdevs[idx] = cdev; + return 0; } /** diff --git a/sound/pci/hda/hda_generic.h b/sound/pci/hda/hda_generic.h index 8e1bc8ea74fc..34eba40cc6e6 100644 --- a/sound/pci/hda/hda_generic.h +++ b/sound/pci/hda/hda_generic.h @@ -294,6 +294,9 @@ struct hda_gen_spec { struct hda_jack_callback *cb); void (*mic_autoswitch_hook)(struct hda_codec *codec, struct hda_jack_callback *cb); + + /* leds */ + struct led_classdev *led_cdevs[NUM_AUDIO_LEDS]; }; /* values for add_stereo_mix_input flag */ diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 668274e52674..8315bf7d4c38 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -98,6 +98,7 @@ struct alc_spec { unsigned int gpio_mic_led_mask; struct alc_coef_led mute_led_coef; struct alc_coef_led mic_led_coef; + struct mutex coef_mutex; hda_nid_t headset_mic_pin; hda_nid_t headphone_mic_pin; @@ -137,8 +138,8 @@ struct alc_spec { * COEF access helper functions */ -static int alc_read_coefex_idx(struct hda_codec *codec, hda_nid_t nid, - unsigned int coef_idx) +static int __alc_read_coefex_idx(struct hda_codec *codec, hda_nid_t nid, + unsigned int coef_idx) { unsigned int val; @@ -147,28 +148,61 @@ static int alc_read_coefex_idx(struct hda_codec *codec, hda_nid_t nid, return val; } +static int alc_read_coefex_idx(struct hda_codec *codec, hda_nid_t nid, + unsigned int coef_idx) +{ + struct alc_spec *spec = codec->spec; + unsigned int val; + + mutex_lock(&spec->coef_mutex); + val = __alc_read_coefex_idx(codec, nid, coef_idx); + mutex_unlock(&spec->coef_mutex); + return val; +} + #define alc_read_coef_idx(codec, coef_idx) \ alc_read_coefex_idx(codec, 0x20, coef_idx) -static void alc_write_coefex_idx(struct hda_codec *codec, hda_nid_t nid, - unsigned int coef_idx, unsigned int coef_val) +static void __alc_write_coefex_idx(struct hda_codec *codec, hda_nid_t nid, + unsigned int coef_idx, unsigned int coef_val) { snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_COEF_INDEX, coef_idx); snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_PROC_COEF, coef_val); } +static void alc_write_coefex_idx(struct hda_codec *codec, hda_nid_t nid, + unsigned int coef_idx, unsigned int coef_val) +{ + struct alc_spec *spec = codec->spec; + + mutex_lock(&spec->coef_mutex); + __alc_write_coefex_idx(codec, nid, coef_idx, coef_val); + mutex_unlock(&spec->coef_mutex); +} + #define alc_write_coef_idx(codec, coef_idx, coef_val) \ alc_write_coefex_idx(codec, 0x20, coef_idx, coef_val) +static void __alc_update_coefex_idx(struct hda_codec *codec, hda_nid_t nid, + unsigned int coef_idx, unsigned int mask, + unsigned int bits_set) +{ + unsigned int val = __alc_read_coefex_idx(codec, nid, coef_idx); + + if (val != -1) + __alc_write_coefex_idx(codec, nid, coef_idx, + (val & ~mask) | bits_set); +} + static void alc_update_coefex_idx(struct hda_codec *codec, hda_nid_t nid, unsigned int coef_idx, unsigned int mask, unsigned int bits_set) { - unsigned int val = alc_read_coefex_idx(codec, nid, coef_idx); + struct alc_spec *spec = codec->spec; - if (val != -1) - alc_write_coefex_idx(codec, nid, coef_idx, - (val & ~mask) | bits_set); + mutex_lock(&spec->coef_mutex); + __alc_update_coefex_idx(codec, nid, coef_idx, mask, bits_set); + mutex_unlock(&spec->coef_mutex); } #define alc_update_coef_idx(codec, coef_idx, mask, bits_set) \ @@ -201,13 +235,17 @@ struct coef_fw { static void alc_process_coef_fw(struct hda_codec *codec, const struct coef_fw *fw) { + struct alc_spec *spec = codec->spec; + + mutex_lock(&spec->coef_mutex); for (; fw->nid; fw++) { if (fw->mask == (unsigned short)-1) - alc_write_coefex_idx(codec, fw->nid, fw->idx, fw->val); + __alc_write_coefex_idx(codec, fw->nid, fw->idx, fw->val); else - alc_update_coefex_idx(codec, fw->nid, fw->idx, - fw->mask, fw->val); + __alc_update_coefex_idx(codec, fw->nid, fw->idx, + fw->mask, fw->val); } + mutex_unlock(&spec->coef_mutex); } /* @@ -1153,6 +1191,7 @@ static int alc_alloc_spec(struct hda_codec *codec, hda_nid_t mixer_nid) codec->spdif_status_reset = 1; codec->forced_resume = 1; codec->patch_ops = alc_patch_ops; + mutex_init(&spec->coef_mutex); err = alc_codec_rename_from_preset(codec); if (err < 0) { @@ -2125,6 +2164,7 @@ static void alc1220_fixup_gb_x570(struct hda_codec *codec, { static const hda_nid_t conn1[] = { 0x0c }; static const struct coef_fw gb_x570_coefs[] = { + WRITE_COEF(0x07, 0x03c0), WRITE_COEF(0x1a, 0x01c1), WRITE_COEF(0x1b, 0x0202), WRITE_COEF(0x43, 0x3005), @@ -2551,7 +2591,8 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1458, 0xa002, "Gigabyte EP45-DS3/Z87X-UD3H", ALC889_FIXUP_FRONT_HP_NO_PRESENCE), SND_PCI_QUIRK(0x1458, 0xa0b8, "Gigabyte AZ370-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS), SND_PCI_QUIRK(0x1458, 0xa0cd, "Gigabyte X570 Aorus Master", ALC1220_FIXUP_GB_X570), - SND_PCI_QUIRK(0x1458, 0xa0ce, "Gigabyte X570 Aorus Xtreme", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1458, 0xa0ce, "Gigabyte X570 Aorus Xtreme", ALC1220_FIXUP_GB_X570), + SND_PCI_QUIRK(0x1458, 0xa0d5, "Gigabyte X570S Aorus Master", ALC1220_FIXUP_GB_X570), SND_PCI_QUIRK(0x1462, 0x11f7, "MSI-GE63", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1462, 0x1228, "MSI-GP63", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1462, 0x1229, "MSI-GP73", ALC1220_FIXUP_CLEVO_P950), @@ -2626,6 +2667,7 @@ static const struct hda_model_fixup alc882_fixup_models[] = { {.id = ALC882_FIXUP_NO_PRIMARY_HP, .name = "no-primary-hp"}, {.id = ALC887_FIXUP_ASUS_BASS, .name = "asus-bass"}, {.id = ALC1220_FIXUP_GB_DUAL_CODECS, .name = "dual-codecs"}, + {.id = ALC1220_FIXUP_GB_X570, .name = "gb-x570"}, {.id = ALC1220_FIXUP_CLEVO_P950, .name = "clevo-p950"}, {} }; @@ -8969,6 +9011,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS), SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401), + SND_PCI_QUIRK(0x1043, 0x16b2, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2), SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC), diff --git a/sound/soc/amd/acp/acp-mach-common.c b/sound/soc/amd/acp/acp-mach-common.c index c9caade5cb74..cd05ee2802c9 100644 --- a/sound/soc/amd/acp/acp-mach-common.c +++ b/sound/soc/amd/acp/acp-mach-common.c @@ -303,11 +303,11 @@ static const struct snd_soc_dapm_route rt1019_map_lr[] = { static struct snd_soc_codec_conf rt1019_conf[] = { { - .dlc = COMP_CODEC_CONF("i2c-10EC1019:00"), + .dlc = COMP_CODEC_CONF("i2c-10EC1019:01"), .name_prefix = "Left", }, { - .dlc = COMP_CODEC_CONF("i2c-10EC1019:01"), + .dlc = COMP_CODEC_CONF("i2c-10EC1019:00"), .name_prefix = "Right", }, }; diff --git a/sound/soc/codecs/cpcap.c b/sound/soc/codecs/cpcap.c index 598e09024e23..ffdf8b615efa 100644 --- a/sound/soc/codecs/cpcap.c +++ b/sound/soc/codecs/cpcap.c @@ -1667,6 +1667,8 @@ static int cpcap_codec_probe(struct platform_device *pdev) { struct device_node *codec_node = of_get_child_by_name(pdev->dev.parent->of_node, "audio-codec"); + if (!codec_node) + return -ENODEV; pdev->dev.of_node = codec_node; diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c index b61f980cabdc..b07607a9ecea 100644 --- a/sound/soc/codecs/hdmi-codec.c +++ b/sound/soc/codecs/hdmi-codec.c @@ -277,7 +277,7 @@ struct hdmi_codec_priv { bool busy; struct snd_soc_jack *jack; unsigned int jack_status; - u8 iec_status[5]; + u8 iec_status[AES_IEC958_STATUS_SIZE]; }; static const struct snd_soc_dapm_widget hdmi_widgets[] = { diff --git a/sound/soc/codecs/lpass-rx-macro.c b/sound/soc/codecs/lpass-rx-macro.c index aec5127260fd..6ffe88345de5 100644 --- a/sound/soc/codecs/lpass-rx-macro.c +++ b/sound/soc/codecs/lpass-rx-macro.c @@ -2688,8 +2688,8 @@ static uint32_t get_iir_band_coeff(struct snd_soc_component *component, int reg, b2_reg; /* Address does not automatically update if reading */ - reg = CDC_RX_SIDETONE_IIR0_IIR_COEF_B1_CTL + 16 * iir_idx; - b2_reg = CDC_RX_SIDETONE_IIR0_IIR_COEF_B2_CTL + 16 * iir_idx; + reg = CDC_RX_SIDETONE_IIR0_IIR_COEF_B1_CTL + 0x80 * iir_idx; + b2_reg = CDC_RX_SIDETONE_IIR0_IIR_COEF_B2_CTL + 0x80 * iir_idx; snd_soc_component_write(component, reg, ((band_idx * BAND_MAX + coeff_idx) * @@ -2718,7 +2718,7 @@ static uint32_t get_iir_band_coeff(struct snd_soc_component *component, static void set_iir_band_coeff(struct snd_soc_component *component, int iir_idx, int band_idx, uint32_t value) { - int reg = CDC_RX_SIDETONE_IIR0_IIR_COEF_B2_CTL + 16 * iir_idx; + int reg = CDC_RX_SIDETONE_IIR0_IIR_COEF_B2_CTL + 0x80 * iir_idx; snd_soc_component_write(component, reg, (value & 0xFF)); snd_soc_component_write(component, reg, (value >> 8) & 0xFF); @@ -2739,7 +2739,7 @@ static int rx_macro_put_iir_band_audio_mixer( int iir_idx = ctl->iir_idx; int band_idx = ctl->band_idx; u32 coeff[BAND_MAX]; - int reg = CDC_RX_SIDETONE_IIR0_IIR_COEF_B1_CTL + 16 * iir_idx; + int reg = CDC_RX_SIDETONE_IIR0_IIR_COEF_B1_CTL + 0x80 * iir_idx; memcpy(&coeff[0], ucontrol->value.bytes.data, params->max); diff --git a/sound/soc/codecs/max9759.c b/sound/soc/codecs/max9759.c index d75fd61b9032..bc57d7687f16 100644 --- a/sound/soc/codecs/max9759.c +++ b/sound/soc/codecs/max9759.c @@ -64,7 +64,8 @@ static int speaker_gain_control_put(struct snd_kcontrol *kcontrol, struct snd_soc_component *c = snd_soc_kcontrol_component(kcontrol); struct max9759 *priv = snd_soc_component_get_drvdata(c); - if (ucontrol->value.integer.value[0] > 3) + if (ucontrol->value.integer.value[0] < 0 || + ucontrol->value.integer.value[0] > 3) return -EINVAL; priv->gain = ucontrol->value.integer.value[0]; diff --git a/sound/soc/codecs/rt5682-i2c.c b/sound/soc/codecs/rt5682-i2c.c index 20e0f90ea498..20fc0f3766de 100644 --- a/sound/soc/codecs/rt5682-i2c.c +++ b/sound/soc/codecs/rt5682-i2c.c @@ -59,18 +59,12 @@ static void rt5682_jd_check_handler(struct work_struct *work) struct rt5682_priv *rt5682 = container_of(work, struct rt5682_priv, jd_check_work.work); - if (snd_soc_component_read(rt5682->component, RT5682_AJD1_CTRL) - & RT5682_JDH_RS_MASK) { + if (snd_soc_component_read(rt5682->component, RT5682_AJD1_CTRL) & RT5682_JDH_RS_MASK) /* jack out */ - rt5682->jack_type = rt5682_headset_detect(rt5682->component, 0); - - snd_soc_jack_report(rt5682->hs_jack, rt5682->jack_type, - SND_JACK_HEADSET | - SND_JACK_BTN_0 | SND_JACK_BTN_1 | - SND_JACK_BTN_2 | SND_JACK_BTN_3); - } else { + mod_delayed_work(system_power_efficient_wq, + &rt5682->jack_detect_work, 0); + else schedule_delayed_work(&rt5682->jd_check_work, 500); - } } static irqreturn_t rt5682_irq(int irq, void *data) @@ -198,7 +192,6 @@ static int rt5682_i2c_probe(struct i2c_client *i2c, } mutex_init(&rt5682->calibrate_mutex); - mutex_init(&rt5682->jdet_mutex); rt5682_calibrate(rt5682); rt5682_apply_patch_list(rt5682, &i2c->dev); diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index 415ec564c82e..0a0ec4a021e1 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -922,15 +922,13 @@ static void rt5682_enable_push_button_irq(struct snd_soc_component *component, * * Returns detect status. */ -int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert) +static int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert) { struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component); struct snd_soc_dapm_context *dapm = &component->dapm; unsigned int val, count; if (jack_insert) { - snd_soc_dapm_mutex_lock(dapm); - snd_soc_component_update_bits(component, RT5682_PWR_ANLG_1, RT5682_PWR_VREF2 | RT5682_PWR_MB, RT5682_PWR_VREF2 | RT5682_PWR_MB); @@ -981,8 +979,6 @@ int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert) snd_soc_component_update_bits(component, RT5682_MICBIAS_2, RT5682_PWR_CLK25M_MASK | RT5682_PWR_CLK1M_MASK, RT5682_PWR_CLK25M_PU | RT5682_PWR_CLK1M_PU); - - snd_soc_dapm_mutex_unlock(dapm); } else { rt5682_enable_push_button_irq(component, false); snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1, @@ -1011,7 +1007,6 @@ int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert) dev_dbg(component->dev, "jack_type = %d\n", rt5682->jack_type); return rt5682->jack_type; } -EXPORT_SYMBOL_GPL(rt5682_headset_detect); static int rt5682_set_jack_detect(struct snd_soc_component *component, struct snd_soc_jack *hs_jack, void *data) @@ -1094,6 +1089,7 @@ void rt5682_jack_detect_handler(struct work_struct *work) { struct rt5682_priv *rt5682 = container_of(work, struct rt5682_priv, jack_detect_work.work); + struct snd_soc_dapm_context *dapm; int val, btn_type; while (!rt5682->component) @@ -1102,7 +1098,9 @@ void rt5682_jack_detect_handler(struct work_struct *work) while (!rt5682->component->card->instantiated) usleep_range(10000, 15000); - mutex_lock(&rt5682->jdet_mutex); + dapm = snd_soc_component_get_dapm(rt5682->component); + + snd_soc_dapm_mutex_lock(dapm); mutex_lock(&rt5682->calibrate_mutex); val = snd_soc_component_read(rt5682->component, RT5682_AJD1_CTRL) @@ -1162,6 +1160,9 @@ void rt5682_jack_detect_handler(struct work_struct *work) rt5682->irq_work_delay_time = 50; } + mutex_unlock(&rt5682->calibrate_mutex); + snd_soc_dapm_mutex_unlock(dapm); + snd_soc_jack_report(rt5682->hs_jack, rt5682->jack_type, SND_JACK_HEADSET | SND_JACK_BTN_0 | SND_JACK_BTN_1 | @@ -1174,9 +1175,6 @@ void rt5682_jack_detect_handler(struct work_struct *work) else cancel_delayed_work_sync(&rt5682->jd_check_work); } - - mutex_unlock(&rt5682->calibrate_mutex); - mutex_unlock(&rt5682->jdet_mutex); } EXPORT_SYMBOL_GPL(rt5682_jack_detect_handler); @@ -1526,7 +1524,6 @@ static int rt5682_hp_event(struct snd_soc_dapm_widget *w, { struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm); - struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component); switch (event) { case SND_SOC_DAPM_PRE_PMU: @@ -1538,17 +1535,12 @@ static int rt5682_hp_event(struct snd_soc_dapm_widget *w, RT5682_DEPOP_1, 0x60, 0x60); snd_soc_component_update_bits(component, RT5682_DAC_ADC_DIG_VOL1, 0x00c0, 0x0080); - - mutex_lock(&rt5682->jdet_mutex); - snd_soc_component_update_bits(component, RT5682_HP_CTRL_2, RT5682_HP_C2_DAC_L_EN | RT5682_HP_C2_DAC_R_EN, RT5682_HP_C2_DAC_L_EN | RT5682_HP_C2_DAC_R_EN); usleep_range(5000, 10000); snd_soc_component_update_bits(component, RT5682_CHARGE_PUMP_1, RT5682_CP_SW_SIZE_MASK, RT5682_CP_SW_SIZE_L); - - mutex_unlock(&rt5682->jdet_mutex); break; case SND_SOC_DAPM_POST_PMD: diff --git a/sound/soc/codecs/rt5682.h b/sound/soc/codecs/rt5682.h index c917c76200ea..52ff0d9c36c5 100644 --- a/sound/soc/codecs/rt5682.h +++ b/sound/soc/codecs/rt5682.h @@ -1463,7 +1463,6 @@ struct rt5682_priv { int jack_type; int irq_work_delay_time; - struct mutex jdet_mutex; }; extern const char *rt5682_supply_names[RT5682_NUM_SUPPLIES]; @@ -1473,7 +1472,6 @@ int rt5682_sel_asrc_clk_src(struct snd_soc_component *component, void rt5682_apply_patch_list(struct rt5682_priv *rt5682, struct device *dev); -int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert); void rt5682_jack_detect_handler(struct work_struct *work); bool rt5682_volatile_register(struct device *dev, unsigned int reg); diff --git a/sound/soc/codecs/wcd938x.c b/sound/soc/codecs/wcd938x.c index eff200a07d9f..36cbc66914f9 100644 --- a/sound/soc/codecs/wcd938x.c +++ b/sound/soc/codecs/wcd938x.c @@ -1432,14 +1432,10 @@ static int wcd938x_sdw_connect_port(struct wcd938x_sdw_ch_info *ch_info, return 0; } -static int wcd938x_connect_port(struct wcd938x_sdw_priv *wcd, u8 ch_id, u8 enable) +static int wcd938x_connect_port(struct wcd938x_sdw_priv *wcd, u8 port_num, u8 ch_id, u8 enable) { - u8 port_num; - - port_num = wcd->ch_info[ch_id].port_num; - return wcd938x_sdw_connect_port(&wcd->ch_info[ch_id], - &wcd->port_config[port_num], + &wcd->port_config[port_num - 1], enable); } @@ -2563,7 +2559,7 @@ static int wcd938x_ear_pa_put_gain(struct snd_kcontrol *kcontrol, WCD938X_EAR_GAIN_MASK, ucontrol->value.integer.value[0]); - return 0; + return 1; } static int wcd938x_get_compander(struct snd_kcontrol *kcontrol, @@ -2593,6 +2589,7 @@ static int wcd938x_set_compander(struct snd_kcontrol *kcontrol, struct wcd938x_priv *wcd938x = snd_soc_component_get_drvdata(component); struct wcd938x_sdw_priv *wcd; int value = ucontrol->value.integer.value[0]; + int portidx; struct soc_mixer_control *mc; bool hphr; @@ -2606,12 +2603,14 @@ static int wcd938x_set_compander(struct snd_kcontrol *kcontrol, else wcd938x->comp1_enable = value; + portidx = wcd->ch_info[mc->reg].port_num; + if (value) - wcd938x_connect_port(wcd, mc->reg, true); + wcd938x_connect_port(wcd, portidx, mc->reg, true); else - wcd938x_connect_port(wcd, mc->reg, false); + wcd938x_connect_port(wcd, portidx, mc->reg, false); - return 0; + return 1; } static int wcd938x_ldoh_get(struct snd_kcontrol *kcontrol, @@ -2882,9 +2881,11 @@ static int wcd938x_get_swr_port(struct snd_kcontrol *kcontrol, struct wcd938x_sdw_priv *wcd; struct soc_mixer_control *mixer = (struct soc_mixer_control *)kcontrol->private_value; int dai_id = mixer->shift; - int portidx = mixer->reg; + int portidx, ch_idx = mixer->reg; + wcd = wcd938x->sdw_priv[dai_id]; + portidx = wcd->ch_info[ch_idx].port_num; ucontrol->value.integer.value[0] = wcd->port_enable[portidx]; @@ -2899,12 +2900,14 @@ static int wcd938x_set_swr_port(struct snd_kcontrol *kcontrol, struct wcd938x_sdw_priv *wcd; struct soc_mixer_control *mixer = (struct soc_mixer_control *)kcontrol->private_value; - int portidx = mixer->reg; + int ch_idx = mixer->reg; + int portidx; int dai_id = mixer->shift; bool enable; wcd = wcd938x->sdw_priv[dai_id]; + portidx = wcd->ch_info[ch_idx].port_num; if (ucontrol->value.integer.value[0]) enable = true; else @@ -2912,9 +2915,9 @@ static int wcd938x_set_swr_port(struct snd_kcontrol *kcontrol, wcd->port_enable[portidx] = enable; - wcd938x_connect_port(wcd, portidx, enable); + wcd938x_connect_port(wcd, portidx, ch_idx, enable); - return 0; + return 1; } diff --git a/sound/soc/fsl/pcm030-audio-fabric.c b/sound/soc/fsl/pcm030-audio-fabric.c index af3c3b90c0ac..83b4a22bf15a 100644 --- a/sound/soc/fsl/pcm030-audio-fabric.c +++ b/sound/soc/fsl/pcm030-audio-fabric.c @@ -93,16 +93,21 @@ static int pcm030_fabric_probe(struct platform_device *op) dev_err(&op->dev, "platform_device_alloc() failed\n"); ret = platform_device_add(pdata->codec_device); - if (ret) + if (ret) { dev_err(&op->dev, "platform_device_add() failed: %d\n", ret); + platform_device_put(pdata->codec_device); + } ret = snd_soc_register_card(card); - if (ret) + if (ret) { dev_err(&op->dev, "snd_soc_register_card() failed: %d\n", ret); + platform_device_del(pdata->codec_device); + platform_device_put(pdata->codec_device); + } platform_set_drvdata(op, pdata); - return ret; + } static int pcm030_fabric_remove(struct platform_device *op) diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c index a89d1cfdda32..78419e18717d 100644 --- a/sound/soc/generic/simple-card.c +++ b/sound/soc/generic/simple-card.c @@ -28,6 +28,30 @@ static const struct snd_soc_ops simple_ops = { .hw_params = asoc_simple_hw_params, }; +static int asoc_simple_parse_platform(struct device_node *node, + struct snd_soc_dai_link_component *dlc) +{ + struct of_phandle_args args; + int ret; + + if (!node) + return 0; + + /* + * Get node via "sound-dai = <&phandle port>" + * it will be used as xxx_of_node on soc_bind_dai_link() + */ + ret = of_parse_phandle_with_args(node, DAI, CELL, 0, &args); + if (ret) + return ret; + + /* dai_name is not required and may not exist for plat component */ + + dlc->of_node = args.np; + + return 0; +} + static int asoc_simple_parse_dai(struct device_node *node, struct snd_soc_dai_link_component *dlc, int *is_single_link) @@ -289,7 +313,7 @@ static int simple_dai_link_of(struct asoc_simple_priv *priv, if (ret < 0) goto dai_link_of_err; - ret = asoc_simple_parse_dai(plat, platforms, NULL); + ret = asoc_simple_parse_platform(plat, platforms); if (ret < 0) goto dai_link_of_err; diff --git a/sound/soc/mediatek/Kconfig b/sound/soc/mediatek/Kconfig index 9306b7ca2644..0d154350f180 100644 --- a/sound/soc/mediatek/Kconfig +++ b/sound/soc/mediatek/Kconfig @@ -216,7 +216,7 @@ config SND_SOC_MT8195_MT6359_RT1019_RT5682 config SND_SOC_MT8195_MT6359_RT1011_RT5682 tristate "ASoC Audio driver for MT8195 with MT6359 RT1011 RT5682 codec" - depends on I2C + depends on I2C && GPIOLIB depends on SND_SOC_MT8195 && MTK_PMIC_WRAP select SND_SOC_MT6359 select SND_SOC_RT1011 diff --git a/sound/soc/qcom/qdsp6/q6apm-dai.c b/sound/soc/qcom/qdsp6/q6apm-dai.c index eb1c3aec479b..19c4a90ec1ea 100644 --- a/sound/soc/qcom/qdsp6/q6apm-dai.c +++ b/sound/soc/qcom/qdsp6/q6apm-dai.c @@ -308,8 +308,11 @@ static int q6apm_dai_close(struct snd_soc_component *component, struct snd_pcm_runtime *runtime = substream->runtime; struct q6apm_dai_rtd *prtd = runtime->private_data; - q6apm_graph_stop(prtd->graph); - q6apm_unmap_memory_regions(prtd->graph, substream->stream); + if (prtd->state) { /* only stop graph that is started */ + q6apm_graph_stop(prtd->graph); + q6apm_unmap_memory_regions(prtd->graph, substream->stream); + } + q6apm_graph_close(prtd->graph); prtd->graph = NULL; kfree(prtd); diff --git a/sound/soc/soc-acpi.c b/sound/soc/soc-acpi.c index cbd7ea48837b..142476f1396f 100644 --- a/sound/soc/soc-acpi.c +++ b/sound/soc/soc-acpi.c @@ -55,16 +55,13 @@ EXPORT_SYMBOL_GPL(snd_soc_acpi_find_machine); static acpi_status snd_soc_acpi_find_package(acpi_handle handle, u32 level, void *context, void **ret) { - struct acpi_device *adev; + struct acpi_device *adev = acpi_fetch_acpi_dev(handle); acpi_status status; struct snd_soc_acpi_package_context *pkg_ctx = context; pkg_ctx->data_valid = false; - if (acpi_bus_get_device(handle, &adev)) - return AE_OK; - - if (adev->status.present && adev->status.functional) { + if (adev && adev->status.present && adev->status.functional) { struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL}; union acpi_object *myobj = NULL; diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c index 08eaa9ddf191..9833611b83d1 100644 --- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -316,13 +316,27 @@ int snd_soc_put_volsw(struct snd_kcontrol *kcontrol, if (sign_bit) mask = BIT(sign_bit + 1) - 1; - val = ((ucontrol->value.integer.value[0] + min) & mask); + if (ucontrol->value.integer.value[0] < 0) + return -EINVAL; + val = ucontrol->value.integer.value[0]; + if (mc->platform_max && val > mc->platform_max) + return -EINVAL; + if (val > max - min) + return -EINVAL; + val = (val + min) & mask; if (invert) val = max - val; val_mask = mask << shift; val = val << shift; if (snd_soc_volsw_is_stereo(mc)) { - val2 = ((ucontrol->value.integer.value[1] + min) & mask); + if (ucontrol->value.integer.value[1] < 0) + return -EINVAL; + val2 = ucontrol->value.integer.value[1]; + if (mc->platform_max && val2 > mc->platform_max) + return -EINVAL; + if (val2 > max - min) + return -EINVAL; + val2 = (val2 + min) & mask; if (invert) val2 = max - val2; if (reg == reg2) { @@ -409,8 +423,15 @@ int snd_soc_put_volsw_sx(struct snd_kcontrol *kcontrol, int err = 0; unsigned int val, val_mask; + if (ucontrol->value.integer.value[0] < 0) + return -EINVAL; + val = ucontrol->value.integer.value[0]; + if (mc->platform_max && val > mc->platform_max) + return -EINVAL; + if (val > max - min) + return -EINVAL; val_mask = mask << shift; - val = (ucontrol->value.integer.value[0] + min) & mask; + val = (val + min) & mask; val = val << shift; err = snd_soc_component_update_bits(component, reg, val_mask, val); @@ -858,6 +879,8 @@ int snd_soc_put_xr_sx(struct snd_kcontrol *kcontrol, long val = ucontrol->value.integer.value[0]; unsigned int i; + if (val < mc->min || val > mc->max) + return -EINVAL; if (invert) val = max - val; val &= mask; diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c index 7abfc48b26ca..9a954680d492 100644 --- a/sound/soc/soc-pcm.c +++ b/sound/soc/soc-pcm.c @@ -46,8 +46,8 @@ static inline void snd_soc_dpcm_stream_lock_irq(struct snd_soc_pcm_runtime *rtd, snd_pcm_stream_lock_irq(snd_soc_dpcm_get_substream(rtd, stream)); } -#define snd_soc_dpcm_stream_lock_irqsave(rtd, stream, flags) \ - snd_pcm_stream_lock_irqsave(snd_soc_dpcm_get_substream(rtd, stream), flags) +#define snd_soc_dpcm_stream_lock_irqsave_nested(rtd, stream, flags) \ + snd_pcm_stream_lock_irqsave_nested(snd_soc_dpcm_get_substream(rtd, stream), flags) static inline void snd_soc_dpcm_stream_unlock_irq(struct snd_soc_pcm_runtime *rtd, int stream) @@ -1268,6 +1268,7 @@ static void dpcm_be_reparent(struct snd_soc_pcm_runtime *fe, void dpcm_be_disconnect(struct snd_soc_pcm_runtime *fe, int stream) { struct snd_soc_dpcm *dpcm, *d; + LIST_HEAD(deleted_dpcms); snd_soc_dpcm_mutex_assert_held(fe); @@ -1287,13 +1288,18 @@ void dpcm_be_disconnect(struct snd_soc_pcm_runtime *fe, int stream) /* BEs still alive need new FE */ dpcm_be_reparent(fe, dpcm->be, stream); - dpcm_remove_debugfs_state(dpcm); - list_del(&dpcm->list_be); + list_move(&dpcm->list_fe, &deleted_dpcms); + } + snd_soc_dpcm_stream_unlock_irq(fe, stream); + + while (!list_empty(&deleted_dpcms)) { + dpcm = list_first_entry(&deleted_dpcms, struct snd_soc_dpcm, + list_fe); list_del(&dpcm->list_fe); + dpcm_remove_debugfs_state(dpcm); kfree(dpcm); } - snd_soc_dpcm_stream_unlock_irq(fe, stream); } /* get BE for DAI widget and stream */ @@ -2094,7 +2100,7 @@ int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream, be = dpcm->be; be_substream = snd_soc_dpcm_get_substream(be, stream); - snd_soc_dpcm_stream_lock_irqsave(be, stream, flags); + snd_soc_dpcm_stream_lock_irqsave_nested(be, stream, flags); /* is this op for this BE ? */ if (!snd_soc_dpcm_be_can_update(fe, be, stream)) diff --git a/sound/soc/xilinx/xlnx_formatter_pcm.c b/sound/soc/xilinx/xlnx_formatter_pcm.c index 91afea9d5de6..ce19a6058b27 100644 --- a/sound/soc/xilinx/xlnx_formatter_pcm.c +++ b/sound/soc/xilinx/xlnx_formatter_pcm.c @@ -37,6 +37,7 @@ #define XLNX_AUD_XFER_COUNT 0x28 #define XLNX_AUD_CH_STS_START 0x2C #define XLNX_BYTES_PER_CH 0x44 +#define XLNX_AUD_ALIGN_BYTES 64 #define AUD_STS_IOC_IRQ_MASK BIT(31) #define AUD_STS_CH_STS_MASK BIT(29) @@ -368,12 +369,32 @@ static int xlnx_formatter_pcm_open(struct snd_soc_component *component, snd_soc_set_runtime_hwparams(substream, &xlnx_pcm_hardware); runtime->private_data = stream_data; - /* Resize the period size divisible by 64 */ + /* Resize the period bytes as divisible by 64 */ err = snd_pcm_hw_constraint_step(runtime, 0, - SNDRV_PCM_HW_PARAM_PERIOD_BYTES, 64); + SNDRV_PCM_HW_PARAM_PERIOD_BYTES, + XLNX_AUD_ALIGN_BYTES); if (err) { dev_err(component->dev, - "unable to set constraint on period bytes\n"); + "Unable to set constraint on period bytes\n"); + return err; + } + + /* Resize the buffer bytes as divisible by 64 */ + err = snd_pcm_hw_constraint_step(runtime, 0, + SNDRV_PCM_HW_PARAM_BUFFER_BYTES, + XLNX_AUD_ALIGN_BYTES); + if (err) { + dev_err(component->dev, + "Unable to set constraint on buffer bytes\n"); + return err; + } + + /* Set periods as integer multiple */ + err = snd_pcm_hw_constraint_integer(runtime, + SNDRV_PCM_HW_PARAM_PERIODS); + if (err < 0) { + dev_err(component->dev, + "Unable to set constraint on periods to be integer\n"); return err; } diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index e8f3f8d622ec..630766ba259f 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -1527,6 +1527,10 @@ error: usb_audio_err(chip, "cannot get connectors status: req = %#x, wValue = %#x, wIndex = %#x, type = %d\n", UAC_GET_CUR, validx, idx, cval->val_type); + + if (val) + *val = 0; + return filter_error(cval, ret); } diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index b1522e43173e..0ea39565e623 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -84,7 +84,7 @@ * combination. */ { - USB_DEVICE(0x041e, 0x4095), + USB_AUDIO_DEVICE(0x041e, 0x4095), .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { .ifnum = QUIRK_ANY_INTERFACE, .type = QUIRK_COMPOSITE, diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 18de5f76f198..6db4e2932b3d 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -299,7 +299,9 @@ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ +#define X86_FEATURE_AMX_BF16 (18*32+22) /* AMX bf16 Support */ #define X86_FEATURE_AMX_TILE (18*32+24) /* AMX tile Support */ +#define X86_FEATURE_AMX_INT8 (18*32+25) /* AMX int8 Support */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index b46bcdb0cab1..5191b57e1562 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1624,9 +1624,6 @@ struct kvm_enc_region { #define KVM_S390_NORMAL_RESET _IO(KVMIO, 0xc3) #define KVM_S390_CLEAR_RESET _IO(KVMIO, 0xc4) -/* Available with KVM_CAP_XSAVE2 */ -#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave) - struct kvm_s390_pv_sec_parm { __u64 origin; __u64 length; @@ -2048,4 +2045,7 @@ struct kvm_stats_desc { #define KVM_GET_STATS_FD _IO(KVMIO, 0xce) +/* Available with KVM_CAP_XSAVE2 */ +#define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave) + #endif /* __LINUX_KVM_H */ diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 4cd39aaccbe7..1b65042ab1db 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -1332,9 +1332,9 @@ union perf_mem_data_src { /* hop level */ #define PERF_MEM_HOPS_0 0x01 /* remote core, same node */ -#define PERF_MEM_HOPS_1 0x02 /* remote node, same socket */ -#define PERF_MEM_HOPS_2 0x03 /* remote socket, same board */ -#define PERF_MEM_HOPS_3 0x04 /* remote board */ +#define PERF_MEM_HOPS_1 0x02 /* remote node, same socket */ +#define PERF_MEM_HOPS_2 0x03 /* remote socket, same board */ +#define PERF_MEM_HOPS_3 0x04 /* remote board */ /* 5-7 available */ #define PERF_MEM_HOPS_SHIFT 43 diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index bb73e9a0b24f..e998764f0262 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -272,4 +272,7 @@ struct prctl_mm_map { # define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1 # define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2 +#define PR_SET_VMA 0x53564d41 +# define PR_SET_VMA_ANON_NAME 0 + #endif /* _LINUX_PRCTL_H */ diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index 5fbb79e30819..2d3e5df39a59 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -56,8 +56,10 @@ * * ****************************************************************************/ +#define AES_IEC958_STATUS_SIZE 24 + struct snd_aes_iec958 { - unsigned char status[24]; /* AES/IEC958 channel status bits */ + unsigned char status[AES_IEC958_STATUS_SIZE]; /* AES/IEC958 channel status bits */ unsigned char subcode[147]; /* AES/IEC958 subcode bits */ unsigned char pad; /* nothing */ unsigned char dig_subframe[4]; /* AES/IEC958 subframe bits */ @@ -202,6 +204,11 @@ typedef int __bitwise snd_pcm_format_t; #define SNDRV_PCM_FORMAT_S24_BE ((__force snd_pcm_format_t) 7) /* low three bytes */ #define SNDRV_PCM_FORMAT_U24_LE ((__force snd_pcm_format_t) 8) /* low three bytes */ #define SNDRV_PCM_FORMAT_U24_BE ((__force snd_pcm_format_t) 9) /* low three bytes */ +/* + * For S32/U32 formats, 'msbits' hardware parameter is often used to deliver information about the + * available bit count in most significant bit. It's for the case of so-called 'left-justified' or + * `right-padding` sample which has less width than 32 bit. + */ #define SNDRV_PCM_FORMAT_S32_LE ((__force snd_pcm_format_t) 10) #define SNDRV_PCM_FORMAT_S32_BE ((__force snd_pcm_format_t) 11) #define SNDRV_PCM_FORMAT_U32_LE ((__force snd_pcm_format_t) 12) @@ -300,7 +307,7 @@ typedef int __bitwise snd_pcm_subformat_t; #define SNDRV_PCM_INFO_HAS_LINK_ESTIMATED_ATIME 0x04000000 /* report estimated link audio time */ #define SNDRV_PCM_INFO_HAS_LINK_SYNCHRONIZED_ATIME 0x08000000 /* report synchronized audio/system time */ #define SNDRV_PCM_INFO_EXPLICIT_SYNC 0x10000000 /* needs explicit sync of pointers and data */ - +#define SNDRV_PCM_INFO_NO_REWINDS 0x20000000 /* hardware can only support monotonic changes of appl_ptr */ #define SNDRV_PCM_INFO_DRAIN_TRIGGER 0x40000000 /* internal kernel flag - trigger in drain */ #define SNDRV_PCM_INFO_FIFO_IN_FRAMES 0x80000000 /* internal kernel flag - FIFO size is in frames */ diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c index f7ee07cb5818..0d1634cedf44 100644 --- a/tools/lib/perf/mmap.c +++ b/tools/lib/perf/mmap.c @@ -13,6 +13,7 @@ #include <internal/lib.h> #include <linux/kernel.h> #include <linux/math64.h> +#include <linux/stringify.h> #include "internal.h" void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev, @@ -294,6 +295,103 @@ static u64 read_timestamp(void) return low | ((u64)high) << 32; } +#elif defined(__aarch64__) +#define read_sysreg(r) ({ \ + u64 __val; \ + asm volatile("mrs %0, " __stringify(r) : "=r" (__val)); \ + __val; \ +}) + +static u64 read_pmccntr(void) +{ + return read_sysreg(pmccntr_el0); +} + +#define PMEVCNTR_READ(idx) \ + static u64 read_pmevcntr_##idx(void) { \ + return read_sysreg(pmevcntr##idx##_el0); \ + } + +PMEVCNTR_READ(0); +PMEVCNTR_READ(1); +PMEVCNTR_READ(2); +PMEVCNTR_READ(3); +PMEVCNTR_READ(4); +PMEVCNTR_READ(5); +PMEVCNTR_READ(6); +PMEVCNTR_READ(7); +PMEVCNTR_READ(8); +PMEVCNTR_READ(9); +PMEVCNTR_READ(10); +PMEVCNTR_READ(11); +PMEVCNTR_READ(12); +PMEVCNTR_READ(13); +PMEVCNTR_READ(14); +PMEVCNTR_READ(15); +PMEVCNTR_READ(16); +PMEVCNTR_READ(17); +PMEVCNTR_READ(18); +PMEVCNTR_READ(19); +PMEVCNTR_READ(20); +PMEVCNTR_READ(21); +PMEVCNTR_READ(22); +PMEVCNTR_READ(23); +PMEVCNTR_READ(24); +PMEVCNTR_READ(25); +PMEVCNTR_READ(26); +PMEVCNTR_READ(27); +PMEVCNTR_READ(28); +PMEVCNTR_READ(29); +PMEVCNTR_READ(30); + +/* + * Read a value direct from PMEVCNTR<idx> + */ +static u64 read_perf_counter(unsigned int counter) +{ + static u64 (* const read_f[])(void) = { + read_pmevcntr_0, + read_pmevcntr_1, + read_pmevcntr_2, + read_pmevcntr_3, + read_pmevcntr_4, + read_pmevcntr_5, + read_pmevcntr_6, + read_pmevcntr_7, + read_pmevcntr_8, + read_pmevcntr_9, + read_pmevcntr_10, + read_pmevcntr_11, + read_pmevcntr_13, + read_pmevcntr_12, + read_pmevcntr_14, + read_pmevcntr_15, + read_pmevcntr_16, + read_pmevcntr_17, + read_pmevcntr_18, + read_pmevcntr_19, + read_pmevcntr_20, + read_pmevcntr_21, + read_pmevcntr_22, + read_pmevcntr_23, + read_pmevcntr_24, + read_pmevcntr_25, + read_pmevcntr_26, + read_pmevcntr_27, + read_pmevcntr_28, + read_pmevcntr_29, + read_pmevcntr_30, + read_pmccntr + }; + + if (counter < ARRAY_SIZE(read_f)) + return (read_f[counter])(); + + return 0; +} + +static u64 read_timestamp(void) { return read_sysreg(cntvct_el0); } + #else static u64 read_perf_counter(unsigned int counter __maybe_unused) { return 0; } static u64 read_timestamp(void) { return 0; } diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c index 33ae9334861a..89be89afb24d 100644 --- a/tools/lib/perf/tests/test-evsel.c +++ b/tools/lib/perf/tests/test-evsel.c @@ -130,6 +130,9 @@ static int test_stat_user_read(int event) struct perf_event_attr attr = { .type = PERF_TYPE_HARDWARE, .config = event, +#ifdef __aarch64__ + .config1 = 0x2, /* Request user access */ +#endif }; int err, i; @@ -150,7 +153,7 @@ static int test_stat_user_read(int event) pc = perf_evsel__mmap_base(evsel, 0, 0); __T("failed to get mmapped address", pc); -#if defined(__i386__) || defined(__x86_64__) +#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__) __T("userspace counter access not supported", pc->cap_user_rdpmc); __T("userspace counter access not enabled", pc->index); __T("userspace counter width not set", pc->pmc_width >= 32); diff --git a/tools/objtool/check.c b/tools/objtool/check.c index c2d2ab9a2861..7c33ec67c4a9 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -2854,7 +2854,7 @@ static inline bool func_uaccess_safe(struct symbol *func) static inline const char *call_dest_name(struct instruction *insn) { - static char pvname[16]; + static char pvname[19]; struct reloc *rel; int idx; diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index dec24dc0e767..a8785dec5ca6 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -1115,6 +1115,7 @@ enum perf_ftrace_subcommand { int cmd_ftrace(int argc, const char **argv) { int ret; + int (*cmd_func)(struct perf_ftrace *) = NULL; struct perf_ftrace ftrace = { .tracer = DEFAULT_TRACER, .target = { .uid = UINT_MAX, }, @@ -1221,6 +1222,28 @@ int cmd_ftrace(int argc, const char **argv) goto out_delete_filters; } + switch (subcmd) { + case PERF_FTRACE_TRACE: + if (!argc && target__none(&ftrace.target)) + ftrace.target.system_wide = true; + cmd_func = __cmd_ftrace; + break; + case PERF_FTRACE_LATENCY: + if (list_empty(&ftrace.filters)) { + pr_err("Should provide a function to measure\n"); + parse_options_usage(ftrace_usage, options, "T", 1); + ret = -EINVAL; + goto out_delete_filters; + } + cmd_func = __cmd_latency; + break; + case PERF_FTRACE_NONE: + default: + pr_err("Invalid subcommand\n"); + ret = -EINVAL; + goto out_delete_filters; + } + ret = target__validate(&ftrace.target); if (ret) { char errbuf[512]; @@ -1248,27 +1271,7 @@ int cmd_ftrace(int argc, const char **argv) goto out_delete_evlist; } - switch (subcmd) { - case PERF_FTRACE_TRACE: - if (!argc && target__none(&ftrace.target)) - ftrace.target.system_wide = true; - ret = __cmd_ftrace(&ftrace); - break; - case PERF_FTRACE_LATENCY: - if (list_empty(&ftrace.filters)) { - pr_err("Should provide a function to measure\n"); - parse_options_usage(ftrace_usage, options, "T", 1); - ret = -EINVAL; - goto out_delete_evlist; - } - ret = __cmd_latency(&ftrace); - break; - case PERF_FTRACE_NONE: - default: - pr_err("Invalid subcommand\n"); - ret = -EINVAL; - break; - } + ret = cmd_func(&ftrace); out_delete_evlist: evlist__delete(ftrace.evlist); diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh index 3109d7b05e11..3d278785fe57 100755 --- a/tools/perf/trace/beauty/prctl_option.sh +++ b/tools/perf/trace/beauty/prctl_option.sh @@ -4,7 +4,7 @@ [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/ printf "static const char *prctl_options[] = {\n" -regex='^#define[[:space:]]+PR_(\w+)[[:space:]]*([[:xdigit:]]+).*' +regex='^#define[[:space:]]{1}PR_(\w+)[[:space:]]*([[:xdigit:]]+)([[:space:]]*\/.*)?$' egrep $regex ${header_dir}/prctl.h | grep -v PR_SET_PTRACER | \ sed -r "s/$regex/\2 \1/g" | \ sort -n | xargs printf "\t[%s] = \"%s\",\n" diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 01900689dc00..8190a124b99d 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -2036,6 +2036,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) memset(&objdump_process, 0, sizeof(objdump_process)); objdump_process.argv = objdump_argv; objdump_process.out = -1; + objdump_process.err = -1; if (start_command(&objdump_process)) { pr_err("Failure starting to run %s\n", command); err = -1; diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c index 631e34a0b66f..ac60c08e8e2a 100644 --- a/tools/perf/util/bpf_counter_cgroup.c +++ b/tools/perf/util/bpf_counter_cgroup.c @@ -266,7 +266,7 @@ static int bperf_cgrp__read(struct evsel *evsel) idx = evsel->core.idx; err = bpf_map_lookup_elem(reading_map_fd, &idx, values); if (err) { - pr_err("bpf map lookup falied: idx=%u, event=%s, cgrp=%s\n", + pr_err("bpf map lookup failed: idx=%u, event=%s, cgrp=%s\n", idx, evsel__name(evsel), evsel->cgrp->name); goto out; } diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index f70ba56912d4..394550003693 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2073,6 +2073,7 @@ static void ip__resolve_ams(struct thread *thread, ams->addr = ip; ams->al_addr = al.addr; + ams->al_level = al.level; ams->ms.maps = al.maps; ams->ms.sym = al.sym; ams->ms.map = al.map; @@ -2092,6 +2093,7 @@ static void ip__resolve_data(struct thread *thread, ams->addr = addr; ams->al_addr = al.addr; + ams->al_level = al.level; ams->ms.maps = al.maps; ams->ms.sym = al.sym; ams->ms.map = al.map; diff --git a/tools/perf/util/map_symbol.h b/tools/perf/util/map_symbol.h index 7d22ade082c8..e08817b0c30f 100644 --- a/tools/perf/util/map_symbol.h +++ b/tools/perf/util/map_symbol.h @@ -18,6 +18,7 @@ struct addr_map_symbol { struct map_symbol ms; u64 addr; u64 al_addr; + char al_level; u64 phys_addr; u64 data_page_size; }; diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c index 47b7531f51da..98af3fa4ea35 100644 --- a/tools/perf/util/perf_event_attr_fprintf.c +++ b/tools/perf/util/perf_event_attr_fprintf.c @@ -52,7 +52,7 @@ static void __p_branch_sample_type(char *buf, size_t size, u64 value) bit_name(ABORT_TX), bit_name(IN_TX), bit_name(NO_TX), bit_name(COND), bit_name(CALL_STACK), bit_name(IND_JUMP), bit_name(CALL), bit_name(NO_FLAGS), bit_name(NO_CYCLES), - bit_name(HW_INDEX), + bit_name(TYPE_SAVE), bit_name(HW_INDEX), { .name = NULL, } }; #undef bit_name diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 2c0d30f08e78..498b05708db5 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1503,11 +1503,12 @@ static int machines__deliver_event(struct machines *machines, ++evlist->stats.nr_unknown_id; return 0; } - dump_sample(evsel, event, sample, perf_env__arch(machine->env)); if (machine == NULL) { ++evlist->stats.nr_unprocessable_samples; + dump_sample(evsel, event, sample, perf_env__arch(NULL)); return 0; } + dump_sample(evsel, event, sample, perf_env__arch(machine->env)); return evlist__deliver_sample(evlist, tool, event, sample, evsel, machine); case PERF_RECORD_MMAP: return tool->mmap(tool, event, sample, machine); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index cfba8c337783..2da081ef532b 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -915,7 +915,7 @@ static int hist_entry__sym_from_snprintf(struct hist_entry *he, char *bf, struct addr_map_symbol *from = &he->branch_info->from; return _hist_entry__sym_snprintf(&from->ms, from->al_addr, - he->level, bf, size, width); + from->al_level, bf, size, width); } return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); @@ -928,7 +928,7 @@ static int hist_entry__sym_to_snprintf(struct hist_entry *he, char *bf, struct addr_map_symbol *to = &he->branch_info->to; return _hist_entry__sym_snprintf(&to->ms, to->al_addr, - he->level, bf, size, width); + to->al_level, bf, size, width); } return repsep_snprintf(bf, size, "%-*.*s", width, width, "N/A"); diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c index 5db83e51ceef..9cbe351b141f 100644 --- a/tools/perf/util/stat-display.c +++ b/tools/perf/util/stat-display.c @@ -585,15 +585,16 @@ static void collect_all_aliases(struct perf_stat_config *config, struct evsel *c alias = list_prepare_entry(counter, &(evlist->core.entries), core.node); list_for_each_entry_continue (alias, &evlist->core.entries, core.node) { - if (strcmp(evsel__name(alias), evsel__name(counter)) || - alias->scale != counter->scale || - alias->cgrp != counter->cgrp || - strcmp(alias->unit, counter->unit) || - evsel__is_clock(alias) != evsel__is_clock(counter) || - !strcmp(alias->pmu_name, counter->pmu_name)) - break; - alias->merged_stat = true; - cb(config, alias, data, false); + /* Merge events with the same name, etc. but on different PMUs. */ + if (!strcmp(evsel__name(alias), evsel__name(counter)) && + alias->scale == counter->scale && + alias->cgrp == counter->cgrp && + !strcmp(alias->unit, counter->unit) && + evsel__is_clock(alias) == evsel__is_clock(counter) && + strcmp(alias->pmu_name, counter->pmu_name)) { + alias->merged_stat = true; + cb(config, alias, data, false); + } } } diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index 70f095624a0b..b654de0841f8 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -1784,6 +1784,25 @@ int __machine__synthesize_threads(struct machine *machine, struct perf_tool *too perf_event__handler_t process, bool needs_mmap, bool data_mmap, unsigned int nr_threads_synthesize) { + /* + * When perf runs in non-root PID namespace, and the namespace's proc FS + * is not mounted, nsinfo__is_in_root_namespace() returns false. + * In this case, the proc FS is coming for the parent namespace, thus + * perf tool will wrongly gather process info from its parent PID + * namespace. + * + * To avoid the confusion that the perf tool runs in a child PID + * namespace but it synthesizes thread info from its parent PID + * namespace, returns failure with warning. + */ + if (!nsinfo__is_in_root_namespace()) { + pr_err("Perf runs in non-root PID namespace but it tries to "); + pr_err("gather process info from its parent PID namespace.\n"); + pr_err("Please mount the proc file system properly, e.g. "); + pr_err("add the option '--mount-proc' for unshare command.\n"); + return -EPERM; + } + if (target__has_task(target)) return perf_event__synthesize_thread_map(tool, threads, process, machine, needs_mmap, data_mmap); diff --git a/tools/testing/kunit/run_checks.py b/tools/testing/kunit/run_checks.py index 4f32133ed77c..13d854afca9d 100755 --- a/tools/testing/kunit/run_checks.py +++ b/tools/testing/kunit/run_checks.py @@ -61,7 +61,7 @@ def main(argv: Sequence[str]) -> None: elif isinstance(ex, subprocess.CalledProcessError): print(f'{name}: FAILED') else: - print('{name}: unexpected exception: {ex}') + print(f'{name}: unexpected exception: {ex}') continue output = ex.output diff --git a/tools/testing/selftests/clone3/clone3.c b/tools/testing/selftests/clone3/clone3.c index 076cf4325f78..cd4582129c7d 100644 --- a/tools/testing/selftests/clone3/clone3.c +++ b/tools/testing/selftests/clone3/clone3.c @@ -126,8 +126,6 @@ static void test_clone3(uint64_t flags, size_t size, int expected, int main(int argc, char *argv[]) { - pid_t pid; - uid_t uid = getuid(); ksft_print_header(); diff --git a/tools/testing/selftests/ir/ir_loopback.c b/tools/testing/selftests/ir/ir_loopback.c index 06256c96df12..f4a15cbdd5ea 100644 --- a/tools/testing/selftests/ir/ir_loopback.c +++ b/tools/testing/selftests/ir/ir_loopback.c @@ -29,6 +29,16 @@ #define SYSFS_PATH_MAX 256 #define DNAME_PATH_MAX 256 +/* + * Support ancient lirc.h which does not have these values. Can be removed + * once RHEL 8 is no longer a relevant testing platform. + */ +#if RC_PROTO_MAX < 26 +#define RC_PROTO_RCMM12 24 +#define RC_PROTO_RCMM24 25 +#define RC_PROTO_RCMM32 26 +#endif + static const struct { enum rc_proto proto; const char *name; diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 4a565fb84137..18bb0d0cf4bd 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1299,6 +1299,7 @@ signal_address_tests() pm_nl_add_endpoint $ns2 10.0.3.2 flags signal pm_nl_add_endpoint $ns2 10.0.4.2 flags signal run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr "signal addresses race test" 3 3 3 # the server will not signal the address terminating # the MPC subflow diff --git a/tools/testing/selftests/perf_events/sigtrap_threads.c b/tools/testing/selftests/perf_events/sigtrap_threads.c index 8e83cf91513a..6d849dc2bee0 100644 --- a/tools/testing/selftests/perf_events/sigtrap_threads.c +++ b/tools/testing/selftests/perf_events/sigtrap_threads.c @@ -44,9 +44,10 @@ static struct { } ctx; /* Unique value to check si_perf_data is correctly set from perf_event_attr::sig_data. */ -#define TEST_SIG_DATA(addr) (~(unsigned long)(addr)) +#define TEST_SIG_DATA(addr, id) (~(unsigned long)(addr) + id) -static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr) +static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr, + unsigned long id) { struct perf_event_attr attr = { .type = PERF_TYPE_BREAKPOINT, @@ -60,7 +61,7 @@ static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr) .inherit_thread = 1, /* ... but only cloned with CLONE_THREAD. */ .remove_on_exec = 1, /* Required by sigtrap. */ .sigtrap = 1, /* Request synchronous SIGTRAP on event. */ - .sig_data = TEST_SIG_DATA(addr), + .sig_data = TEST_SIG_DATA(addr, id), }; return attr; } @@ -110,7 +111,7 @@ FIXTURE(sigtrap_threads) FIXTURE_SETUP(sigtrap_threads) { - struct perf_event_attr attr = make_event_attr(false, &ctx.iterate_on); + struct perf_event_attr attr = make_event_attr(false, &ctx.iterate_on, 0); struct sigaction action = {}; int i; @@ -165,7 +166,7 @@ TEST_F(sigtrap_threads, enable_event) EXPECT_EQ(ctx.tids_want_signal, 0); EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on); EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT); - EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on)); + EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on, 0)); /* Check enabled for parent. */ ctx.iterate_on = 0; @@ -175,7 +176,7 @@ TEST_F(sigtrap_threads, enable_event) /* Test that modification propagates to all inherited events. */ TEST_F(sigtrap_threads, modify_and_enable_event) { - struct perf_event_attr new_attr = make_event_attr(true, &ctx.iterate_on); + struct perf_event_attr new_attr = make_event_attr(true, &ctx.iterate_on, 42); EXPECT_EQ(ioctl(self->fd, PERF_EVENT_IOC_MODIFY_ATTRIBUTES, &new_attr), 0); run_test_threads(_metadata, self); @@ -184,7 +185,7 @@ TEST_F(sigtrap_threads, modify_and_enable_event) EXPECT_EQ(ctx.tids_want_signal, 0); EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on); EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT); - EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on)); + EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on, 42)); /* Check enabled for parent. */ ctx.iterate_on = 0; @@ -204,7 +205,7 @@ TEST_F(sigtrap_threads, signal_stress) EXPECT_EQ(ctx.tids_want_signal, 0); EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on); EXPECT_EQ(ctx.first_siginfo.si_perf_type, PERF_TYPE_BREAKPOINT); - EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on)); + EXPECT_EQ(ctx.first_siginfo.si_perf_data, TEST_SIG_DATA(&ctx.iterate_on, 0)); } TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index 01f8d3c0cf2c..6922d6417e1c 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -68,7 +68,7 @@ #define PIDFD_SKIP 3 #define PIDFD_XFAIL 4 -int wait_for_pid(pid_t pid) +static inline int wait_for_pid(pid_t pid) { int status, ret; @@ -78,13 +78,20 @@ again: if (errno == EINTR) goto again; + ksft_print_msg("waitpid returned -1, errno=%d\n", errno); return -1; } - if (!WIFEXITED(status)) + if (!WIFEXITED(status)) { + ksft_print_msg( + "waitpid !WIFEXITED, WIFSIGNALED=%d, WTERMSIG=%d\n", + WIFSIGNALED(status), WTERMSIG(status)); return -1; + } - return WEXITSTATUS(status); + ret = WEXITSTATUS(status); + ksft_print_msg("waitpid WEXITSTATUS=%d\n", ret); + return ret; } static inline int sys_pidfd_open(pid_t pid, unsigned int flags) diff --git a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c index 22558524f71c..3fd8e903118f 100644 --- a/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c +++ b/tools/testing/selftests/pidfd/pidfd_fdinfo_test.c @@ -12,6 +12,7 @@ #include <string.h> #include <syscall.h> #include <sys/wait.h> +#include <sys/mman.h> #include "pidfd.h" #include "../kselftest.h" @@ -80,7 +81,10 @@ static inline int error_check(struct error *err, const char *test_name) return err->code; } +#define CHILD_STACK_SIZE 8192 + struct child { + char *stack; pid_t pid; int fd; }; @@ -89,17 +93,22 @@ static struct child clone_newns(int (*fn)(void *), void *args, struct error *err) { static int flags = CLONE_PIDFD | CLONE_NEWPID | CLONE_NEWNS | SIGCHLD; - size_t stack_size = 1024; - char *stack[1024] = { 0 }; struct child ret; if (!(flags & CLONE_NEWUSER) && geteuid() != 0) flags |= CLONE_NEWUSER; + ret.stack = mmap(NULL, CHILD_STACK_SIZE, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, -1, 0); + if (ret.stack == MAP_FAILED) { + error_set(err, -1, "mmap of stack failed (errno %d)", errno); + return ret; + } + #ifdef __ia64__ - ret.pid = __clone2(fn, stack, stack_size, flags, args, &ret.fd); + ret.pid = __clone2(fn, ret.stack, CHILD_STACK_SIZE, flags, args, &ret.fd); #else - ret.pid = clone(fn, stack + stack_size, flags, args, &ret.fd); + ret.pid = clone(fn, ret.stack + CHILD_STACK_SIZE, flags, args, &ret.fd); #endif if (ret.pid < 0) { @@ -129,6 +138,11 @@ static inline int child_join(struct child *child, struct error *err) else if (r > 0) error_set(err, r, "child %d reported: %d", child->pid, r); + if (munmap(child->stack, CHILD_STACK_SIZE)) { + error_set(err, -1, "munmap of child stack failed (errno %d)", errno); + r = -1; + } + return r; } diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index 529eb700ac26..9a2d64901d59 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -441,7 +441,6 @@ static void test_pidfd_poll_exec(int use_waitpid) { int pid, pidfd = 0; int status, ret; - pthread_t t1; time_t prog_start = time(NULL); const char *test_name = "pidfd_poll check for premature notification on child thread exec"; @@ -500,13 +499,14 @@ static int child_poll_leader_exit_test(void *args) */ *child_exit_secs = time(NULL); syscall(SYS_exit, 0); + /* Never reached, but appeases compiler thinking we should return. */ + exit(0); } static void test_pidfd_poll_leader_exit(int use_waitpid) { int pid, pidfd = 0; - int status, ret; - time_t prog_start = time(NULL); + int status, ret = 0; const char *test_name = "pidfd_poll check for premature notification on non-empty" "group leader exit"; diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c index be2943f072f6..17999e082aa7 100644 --- a/tools/testing/selftests/pidfd/pidfd_wait.c +++ b/tools/testing/selftests/pidfd/pidfd_wait.c @@ -39,7 +39,7 @@ static int sys_waitid(int which, pid_t pid, siginfo_t *info, int options, TEST(wait_simple) { - int pidfd = -1, status = 0; + int pidfd = -1; pid_t parent_tid = -1; struct clone_args args = { .parent_tid = ptr_to_u64(&parent_tid), @@ -47,7 +47,6 @@ TEST(wait_simple) .flags = CLONE_PIDFD | CLONE_PARENT_SETTID, .exit_signal = SIGCHLD, }; - int ret; pid_t pid; siginfo_t info = { .si_signo = 0, @@ -88,7 +87,7 @@ TEST(wait_simple) TEST(wait_states) { - int pidfd = -1, status = 0; + int pidfd = -1; pid_t parent_tid = -1; struct clone_args args = { .parent_tid = ptr_to_u64(&parent_tid), diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index d3fd24f9fae8..2f49c9af1b58 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -1417,6 +1417,7 @@ static void userfaultfd_pagemap_test(unsigned int test_pgsize) static int userfaultfd_stress(void) { void *area; + char *tmp_area; unsigned long nr; struct uffdio_register uffdio_register; struct uffd_stats uffd_stats[nr_cpus]; @@ -1527,9 +1528,13 @@ static int userfaultfd_stress(void) count_verify[nr], nr); /* prepare next bounce */ - swap(area_src, area_dst); + tmp_area = area_src; + area_src = area_dst; + area_dst = tmp_area; - swap(area_src_alias, area_dst_alias); + tmp_area = area_src_alias; + area_src_alias = area_dst_alias; + area_dst_alias = tmp_area; uffd_stats_report(uffd_stats, nr_cpus); } |