diff options
| author |   Michael Ellerman <mpe@ellerman.id.au> | 2022-03-08 13:11:46 +1100 |
|---|---|---|
| committer | Michael Ellerman <mpe@ellerman.id.au> | 2022-03-08 13:13:08 +1100 |
| commit | 04a5b0ee97046293431685404ef7352917f1e243 (patch) | |
| tree | a08d6eb6bb8b37dce0fceb472fc3dd506ce1d295 | |
| parent | KVM: PPC: Book3S HV P9: Fix "lost kick" race (diff) | |
| parent | KVM: PPC: reserve capability 210 for KVM_CAP_PPC_AIL_MODE_3 (diff) | |
| download | linux-dev-04a5b0ee97046293431685404ef7352917f1e243.tar.xz linux-dev-04a5b0ee97046293431685404ef7352917f1e243.zip | |
Merge branch 'kvm-ppc-cap-210' of https://git.kernel.org/pub/scm/virt/kvm/kvm into topic/ppc-kvm
Merge this branch from the KVM tree to bring in a new KVM capability
KVM_CAP_PPC_AIL_MODE_3.
It also brings in some unrelated KVM changes as well as v5.17-rc3.
389 files changed, 5413 insertions, 2555 deletions
@@ -80,6 +80,9 @@ Chris Chiu <chris.chiu@canonical.com> <chiu@endlessos.org> Christian Borntraeger <borntraeger@linux.ibm.com> <borntraeger@de.ibm.com> Christian Borntraeger <borntraeger@linux.ibm.com> <cborntra@de.ibm.com> Christian Borntraeger <borntraeger@linux.ibm.com> <borntrae@de.ibm.com> +Christian Brauner <brauner@kernel.org> <christian@brauner.io> +Christian Brauner <brauner@kernel.org> <christian.brauner@canonical.com> +Christian Brauner <brauner@kernel.org> <christian.brauner@ubuntu.com> Christophe Ricard <christophe.ricard@gmail.com> Christoph Hellwig <hch@lst.de> Colin Ian King <colin.king@intel.com> <colin.king@canonical.com> 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/kselftest.rst b/Documentation/dev-tools/kselftest.rst index dcefee707ccd..a833ecf12fbc 100644 --- a/Documentation/dev-tools/kselftest.rst +++ b/Documentation/dev-tools/kselftest.rst @@ -7,6 +7,14 @@ directory. These are intended to be small tests to exercise individual code paths in the kernel. Tests are intended to be run after building, installing and booting a kernel. +Kselftest from mainline can be run on older stable kernels. Running tests +from mainline offers the best coverage. Several test rings run mainline +kselftest suite on stable releases. The reason is that when a new test +gets added to test existing code to regression test a bug, we should be +able to run that test on an older kernel. Hence, it is important to keep +code that can still test an older kernel and make sure it skips the test +gracefully on newer releases. + You can find additional information on Kselftest framework, how to write new tests using the framework on Kselftest wiki: diff --git a/Documentation/devicetree/bindings/net/qcom,ipa.yaml b/Documentation/devicetree/bindings/net/qcom,ipa.yaml index b86edf67ce62..58ecc62adfaa 100644 --- a/Documentation/devicetree/bindings/net/qcom,ipa.yaml +++ b/Documentation/devicetree/bindings/net/qcom,ipa.yaml @@ -107,6 +107,10 @@ properties: - const: imem - const: config + qcom,qmp: + $ref: /schemas/types.yaml#/definitions/phandle + description: phandle to the AOSS side-channel message RAM + qcom,smem-states: $ref: /schemas/types.yaml#/definitions/phandle-array description: State bits used in by the AP to signal the modem. @@ -222,6 +226,8 @@ examples: "imem", "config"; + qcom,qmp = <&aoss_qmp>; + qcom,smem-states = <&ipa_smp2p_out 0>, <&ipa_smp2p_out 1>; qcom,smem-state-names = "ipa-clock-enabled-valid", diff --git a/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml b/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml index 5dd209206e88..3ec2d7b83775 100644 --- a/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml +++ b/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml @@ -23,8 +23,9 @@ properties: minItems: 1 maxItems: 256 items: - minimum: 0 - maximum: 256 + items: + - minimum: 0 + maximum: 256 description: Chip select used by the device. 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/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index a4267104db50..9954568c7eab 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6997,6 +6997,20 @@ indicated by the fd to the VM this is called on. This is intended to support intra-host migration of VMs between userspace VMMs, upgrading the VMM process without interrupting the guest. +7.30 KVM_CAP_PPC_AIL_MODE_3 +------------------------------- + +:Capability: KVM_CAP_PPC_AIL_MODE_3 +:Architectures: ppc +:Type: vm + +This capability indicates that the kernel supports the mode 3 setting for the +"Address Translation Mode on Interrupt" aka "Alternate Interrupt Location" +resource that is controlled with the H_SET_MODE hypercall. + +This capability allows a guest kernel to use a better-performance mode for +handling interrupts and system calls. + 8. Other capabilities. ====================== diff --git a/MAINTAINERS b/MAINTAINERS index f41088418aae..69a2935daf6c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4157,9 +4157,8 @@ N: csky K: csky CA8210 IEEE-802.15.4 RADIO DRIVER -M: Harry Morris <h.morris@cascoda.com> L: linux-wpan@vger.kernel.org -S: Maintained +S: Orphan W: https://github.com/Cascoda/ca8210-linux.git F: Documentation/devicetree/bindings/net/ieee802154/ca8210.txt F: drivers/net/ieee802154/ca8210.c @@ -10880,6 +10879,12 @@ 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 @@ -12400,7 +12405,7 @@ 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 @@ -16469,6 +16474,14 @@ 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/kvm/vgic/vgic-mmio.c b/arch/arm64/kvm/vgic/vgic-mmio.c index 7068da080799..49837d3a3ef5 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio.c +++ b/arch/arm64/kvm/vgic/vgic-mmio.c @@ -248,6 +248,8 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, IRQCHIP_STATE_PENDING, &val); WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); + } else if (vgic_irq_is_mapped_level(irq)) { + val = vgic_get_phys_line_level(irq); } else { val = irq_is_pending(irq); } 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/cavium-octeon/octeon-memcpy.S b/arch/mips/cavium-octeon/octeon-memcpy.S index 0a515cde1c18..25860fba6218 100644 --- a/arch/mips/cavium-octeon/octeon-memcpy.S +++ b/arch/mips/cavium-octeon/octeon-memcpy.S @@ -74,7 +74,7 @@ #define EXC(inst_reg,addr,handler) \ 9: inst_reg, addr; \ .section __ex_table,"a"; \ - PTR 9b, handler; \ + PTR_WD 9b, handler; \ .previous /* 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/mips/kvm/vz.c b/arch/mips/kvm/vz.c index 4adca5abbc72..c706f5890a05 100644 --- a/arch/mips/kvm/vz.c +++ b/arch/mips/kvm/vz.c @@ -458,8 +458,8 @@ void kvm_vz_acquire_htimer(struct kvm_vcpu *vcpu) /** * _kvm_vz_save_htimer() - Switch to software emulation of guest timer. * @vcpu: Virtual CPU. - * @compare: Pointer to write compare value to. - * @cause: Pointer to write cause value to. + * @out_compare: Pointer to write compare value to. + * @out_cause: Pointer to write cause value to. * * Save VZ guest timer state and switch to software emulation of guest CP0 * timer. The hard timer must already be in use, so preemption should be @@ -1541,11 +1541,14 @@ static int kvm_trap_vz_handle_guest_exit(struct kvm_vcpu *vcpu) } /** - * kvm_trap_vz_handle_cop_unusuable() - Guest used unusable coprocessor. + * kvm_trap_vz_handle_cop_unusable() - Guest used unusable coprocessor. * @vcpu: Virtual CPU context. * * Handle when the guest attempts to use a coprocessor which hasn't been allowed * by the root context. + * + * Return: value indicating whether to resume the host or the guest + * (RESUME_HOST or RESUME_GUEST) */ static int kvm_trap_vz_handle_cop_unusable(struct kvm_vcpu *vcpu) { @@ -1592,6 +1595,9 @@ static int kvm_trap_vz_handle_cop_unusable(struct kvm_vcpu *vcpu) * * Handle when the guest attempts to use MSA when it is disabled in the root * context. + * + * Return: value indicating whether to resume the host or the guest + * (RESUME_HOST or RESUME_GUEST) */ static int kvm_trap_vz_handle_msa_disabled(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/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/msr-index.h b/arch/x86/include/asm/msr-index.h index 3faf0f97edb1..a4a39c3e0f19 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -476,6 +476,7 @@ #define MSR_AMD64_ICIBSEXTDCTL 0xc001103c #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ +#define MSR_AMD64_SVM_AVIC_DOORBELL 0xc001011b #define MSR_AMD64_VM_PAGE_FLUSH 0xc001011e #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index b00dbc5fac2b..bb2fb78523ce 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -220,6 +220,42 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define SVM_NESTED_CTL_SEV_ENABLE BIT(1) #define SVM_NESTED_CTL_SEV_ES_ENABLE BIT(2) + +/* AVIC */ +#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF) +#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31 +#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) + +#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK (0xFFULL) +#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12) +#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62) +#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63) +#define AVIC_PHYSICAL_ID_TABLE_SIZE_MASK (0xFF) + +#define AVIC_DOORBELL_PHYSICAL_ID_MASK (0xFF) + +#define AVIC_UNACCEL_ACCESS_WRITE_MASK 1 +#define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0 +#define AVIC_UNACCEL_ACCESS_VECTOR_MASK 0xFFFFFFFF + +enum avic_ipi_failure_cause { + AVIC_IPI_FAILURE_INVALID_INT_TYPE, + AVIC_IPI_FAILURE_TARGET_NOT_RUNNING, + AVIC_IPI_FAILURE_INVALID_TARGET, + AVIC_IPI_FAILURE_INVALID_BACKING_PAGE, +}; + + +/* + * 0xff is broadcast, so the max index allowed for physical APIC ID + * table is 0xfe. APIC IDs above 0xff are reserved. + */ +#define AVIC_MAX_PHYSICAL_ID_COUNT 0xff + +#define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF) +#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL + + struct vmcb_seg { u16 selector; u16 attrib; 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..9322e6340a74 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: @@ -2312,7 +2306,12 @@ void kvm_apic_update_apicv(struct kvm_vcpu *vcpu) apic->irr_pending = true; apic->isr_count = 1; } else { - apic->irr_pending = (apic_search_irr(apic) != -1); + /* + * Don't clear irr_pending, searching the IRR can race with + * updates from the CPU as APICv is still active from hardware's + * perspective. The flag will be cleared as appropriate when + * KVM injects the interrupt. + */ apic->isr_count = count_vectors(apic->regs + APIC_ISR); } } diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index f614f95acc6b..b1a02993782b 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -95,7 +95,7 @@ static void kvm_perf_overflow(struct perf_event *perf_event, } static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, - unsigned config, bool exclude_user, + u64 config, bool exclude_user, bool exclude_kernel, bool intr, bool in_tx, bool in_tx_cp) { @@ -181,7 +181,8 @@ static int cmp_u64(const void *a, const void *b) void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) { - unsigned config, type = PERF_TYPE_RAW; + u64 config; + u32 type = PERF_TYPE_RAW; struct kvm *kvm = pmc->vcpu->kvm; struct kvm_pmu_event_filter *filter; bool allow_event = true; @@ -220,7 +221,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) } if (type == PERF_TYPE_RAW) - config = eventsel & X86_RAW_EVENT_MASK; + config = eventsel & AMD64_RAW_EVENT_MASK; if (pmc->current_config == eventsel && pmc_resume_counter(pmc)) return; diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 90364d02f22a..fb3e20791338 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -27,20 +27,6 @@ #include "irq.h" #include "svm.h" -#define SVM_AVIC_DOORBELL 0xc001011b - -#define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF) - -/* - * 0xff is broadcast, so the max index allowed for physical APIC ID - * table is 0xfe. APIC IDs above 0xff are reserved. - */ -#define AVIC_MAX_PHYSICAL_ID_COUNT 255 - -#define AVIC_UNACCEL_ACCESS_WRITE_MASK 1 -#define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0 -#define AVIC_UNACCEL_ACCESS_VECTOR_MASK 0xFFFFFFFF - /* AVIC GATAG is encoded using VM and VCPU IDs */ #define AVIC_VCPU_ID_BITS 8 #define AVIC_VCPU_ID_MASK ((1 << AVIC_VCPU_ID_BITS) - 1) @@ -73,12 +59,6 @@ struct amd_svm_iommu_ir { void *data; /* Storing pointer to struct amd_ir_data */ }; -enum avic_ipi_failure_cause { - AVIC_IPI_FAILURE_INVALID_INT_TYPE, - AVIC_IPI_FAILURE_TARGET_NOT_RUNNING, - AVIC_IPI_FAILURE_INVALID_TARGET, - AVIC_IPI_FAILURE_INVALID_BACKING_PAGE, -}; /* Note: * This function is called from IOMMU driver to notify @@ -289,6 +269,22 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) return 0; } +void avic_ring_doorbell(struct kvm_vcpu *vcpu) +{ + /* + * Note, the vCPU could get migrated to a different pCPU at any point, + * which could result in signalling the wrong/previous pCPU. But if + * that happens the vCPU is guaranteed to do a VMRUN (after being + * migrated) and thus will process pending interrupts, i.e. a doorbell + * is not needed (and the spurious one is harmless). + */ + int cpu = READ_ONCE(vcpu->cpu); + + if (cpu != get_cpu()) + wrmsrl(MSR_AMD64_SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpu)); + put_cpu(); +} + static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, u32 icrl, u32 icrh) { @@ -304,8 +300,13 @@ static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, kvm_for_each_vcpu(i, vcpu, kvm) { if (kvm_apic_match_dest(vcpu, source, icrl & APIC_SHORT_MASK, GET_APIC_DEST_FIELD(icrh), - icrl & APIC_DEST_MASK)) - kvm_vcpu_wake_up(vcpu); + icrl & APIC_DEST_MASK)) { + vcpu->arch.apic->irr_pending = true; + svm_complete_interrupt_delivery(vcpu, + icrl & APIC_MODE_MASK, + icrl & APIC_INT_LEVELTRIG, + icrl & APIC_VECTOR_MASK); + } } } @@ -345,8 +346,6 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu) avic_kick_target_vcpus(vcpu->kvm, apic, icrl, icrh); break; case AVIC_IPI_FAILURE_INVALID_TARGET: - WARN_ONCE(1, "Invalid IPI target: index=%u, vcpu=%d, icr=%#0x:%#0x\n", - index, vcpu->vcpu_id, icrh, icrl); break; case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE: WARN_ONCE(1, "Invalid backing page\n"); @@ -669,52 +668,6 @@ void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) return; } -int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) -{ - if (!vcpu->arch.apicv_active) - return -1; - - kvm_lapic_set_irr(vec, vcpu->arch.apic); - - /* - * Pairs with the smp_mb_*() after setting vcpu->guest_mode in - * vcpu_enter_guest() to ensure the write to the vIRR is ordered before - * the read of guest_mode, which guarantees that either VMRUN will see - * and process the new vIRR entry, or that the below code will signal - * the doorbell if the vCPU is already running in the guest. - */ - smp_mb__after_atomic(); - - /* - * Signal the doorbell to tell hardware to inject the IRQ if the vCPU - * is in the guest. If the vCPU is not in the guest, hardware will - * automatically process AVIC interrupts at VMRUN. - */ - if (vcpu->mode == IN_GUEST_MODE) { - int cpu = READ_ONCE(vcpu->cpu); - - /* - * Note, the vCPU could get migrated to a different pCPU at any - * point, which could result in signalling the wrong/previous - * pCPU. But if that happens the vCPU is guaranteed to do a - * VMRUN (after being migrated) and thus will process pending - * interrupts, i.e. a doorbell is not needed (and the spurious - * one is harmless). - */ - if (cpu != get_cpu()) - wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpu)); - put_cpu(); - } else { - /* - * Wake the vCPU if it was blocking. KVM will then detect the - * pending IRQ when checking if the vCPU has a wake event. - */ - kvm_vcpu_wake_up(vcpu); - } - - return 0; -} - bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) { return false; diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 1218b5a342fc..39d280e7e80e 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1457,18 +1457,6 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, !__nested_vmcb_check_save(vcpu, &save_cached)) goto out_free; - /* - * While the nested guest CR3 is already checked and set by - * KVM_SET_SREGS, it was set when nested state was yet loaded, - * thus MMU might not be initialized correctly. - * Set it again to fix this. - */ - - ret = nested_svm_load_cr3(&svm->vcpu, vcpu->arch.cr3, - nested_npt_enabled(svm), false); - if (WARN_ON_ONCE(ret)) - goto out_free; - /* * All checks done, we can enter guest mode. Userspace provides @@ -1494,6 +1482,20 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, svm_switch_vmcb(svm, &svm->nested.vmcb02); nested_vmcb02_prepare_control(svm); + + /* + * While the nested guest CR3 is already checked and set by + * KVM_SET_SREGS, it was set when nested state was yet loaded, + * thus MMU might not be initialized correctly. + * Set it again to fix this. + */ + + ret = nested_svm_load_cr3(&svm->vcpu, vcpu->arch.cr3, + nested_npt_enabled(svm), false); + if (WARN_ON_ONCE(ret)) + goto out_free; + + kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); ret = 0; out_free: diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 6d97629655e3..821edf664e7a 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1585,6 +1585,7 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { struct vcpu_svm *svm = to_svm(vcpu); u64 hcr0 = cr0; + bool old_paging = is_paging(vcpu); #ifdef CONFIG_X86_64 if (vcpu->arch.efer & EFER_LME && !vcpu->arch.guest_state_protected) { @@ -1601,8 +1602,11 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) #endif vcpu->arch.cr0 = cr0; - if (!npt_enabled) + if (!npt_enabled) { hcr0 |= X86_CR0_PG | X86_CR0_WP; + if (old_paging != is_paging(vcpu)) + svm_set_cr4(vcpu, kvm_read_cr4(vcpu)); + } /* * re-enable caching here because the QEMU bios @@ -1646,8 +1650,12 @@ void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) svm_flush_tlb(vcpu); vcpu->arch.cr4 = cr4; - if (!npt_enabled) + if (!npt_enabled) { cr4 |= X86_CR4_PAE; + + if (!is_paging(vcpu)) + cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE); + } cr4 |= host_cr4_mce; to_svm(vcpu)->vmcb->save.cr4 = cr4; vmcb_mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR); @@ -3291,6 +3299,55 @@ static void svm_set_irq(struct kvm_vcpu *vcpu) SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR; } +void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, + int trig_mode, int vector) +{ + /* + * vcpu->arch.apicv_active must be read after vcpu->mode. + * Pairs with smp_store_release in vcpu_enter_guest. + */ + bool in_guest_mode = (smp_load_acquire(&vcpu->mode) == IN_GUEST_MODE); + + if (!READ_ONCE(vcpu->arch.apicv_active)) { + /* Process the interrupt via inject_pending_event */ + kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_vcpu_kick(vcpu); + return; + } + + trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, trig_mode, vector); + if (in_guest_mode) { + /* + * Signal the doorbell to tell hardware to inject the IRQ. If + * the vCPU exits the guest before the doorbell chimes, hardware + * will automatically process AVIC interrupts at the next VMRUN. + */ + avic_ring_doorbell(vcpu); + } else { + /* + * Wake the vCPU if it was blocking. KVM will then detect the + * pending IRQ when checking if the vCPU has a wake event. + */ + kvm_vcpu_wake_up(vcpu); + } +} + +static void svm_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector) +{ + kvm_lapic_set_irr(vector, apic); + + /* + * Pairs with the smp_mb_*() after setting vcpu->guest_mode in + * vcpu_enter_guest() to ensure the write to the vIRR is ordered before + * the read of guest_mode. This guarantees that either VMRUN will see + * and process the new vIRR entry, or that svm_complete_interrupt_delivery + * will signal the doorbell if the CPU has already entered the guest. + */ + smp_mb__after_atomic(); + svm_complete_interrupt_delivery(apic->vcpu, 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); @@ -3338,11 +3395,13 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) if (svm->nested.nested_run_pending) return -EBUSY; + if (svm_nmi_blocked(vcpu)) + return 0; + /* An NMI must not be injected into L2 if it's supposed to VM-Exit. */ if (for_injection && is_guest_mode(vcpu) && nested_exit_on_nmi(svm)) return -EBUSY; - - return !svm_nmi_blocked(vcpu); + return 1; } static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu) @@ -3394,9 +3453,13 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu) static int svm_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) { struct vcpu_svm *svm = to_svm(vcpu); + if (svm->nested.nested_run_pending) return -EBUSY; + if (svm_interrupt_blocked(vcpu)) + return 0; + /* * An IRQ must not be injected into L2 if it's supposed to VM-Exit, * e.g. if the IRQ arrived asynchronously after checking nested events. @@ -3404,7 +3467,7 @@ static int svm_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) if (for_injection && is_guest_mode(vcpu) && nested_exit_on_intr(svm)) return -EBUSY; - return !svm_interrupt_blocked(vcpu); + return 1; } static void svm_enable_irq_window(struct kvm_vcpu *vcpu) @@ -3615,7 +3678,7 @@ 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 +3698,7 @@ 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) @@ -4135,11 +4198,14 @@ static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) if (svm->nested.nested_run_pending) return -EBUSY; + if (svm_smi_blocked(vcpu)) + return 0; + /* An SMI must not be injected into L2 if it's supposed to VM-Exit. */ if (for_injection && is_guest_mode(vcpu) && nested_exit_on_smi(svm)) return -EBUSY; - return !svm_smi_blocked(vcpu); + return 1; } static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) @@ -4233,11 +4299,18 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) * Enter the nested guest now */ + vmcb_mark_all_dirty(svm->vmcb01.ptr); + vmcb12 = map.hva; nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false); + if (ret) + goto unmap_save; + + svm->nested.nested_run_pending = 1; + unmap_save: kvm_vcpu_unmap(vcpu, &map_save, true); unmap_map: @@ -4545,7 +4618,7 @@ 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, @@ -4622,6 +4695,7 @@ static __init void svm_set_cpu_caps(void) /* CPUID 0x80000001 and 0x8000000A (SVM features) */ if (nested) { kvm_cpu_cap_set(X86_FEATURE_SVM); + kvm_cpu_cap_set(X86_FEATURE_VMCBCLEAN); if (nrips) kvm_cpu_cap_set(X86_FEATURE_NRIPS); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 73525353e424..fa98d6844728 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -489,6 +489,8 @@ void svm_set_gif(struct vcpu_svm *svm, bool value); int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code); void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr, int read, int write); +void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, + int trig_mode, int vec); /* nested.c */ @@ -556,17 +558,6 @@ extern struct kvm_x86_nested_ops svm_nested_ops; /* avic.c */ -#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF) -#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31 -#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) - -#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK (0xFFULL) -#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12) -#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62) -#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63) - -#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL - int avic_ga_log_notifier(u32 ga_tag); void avic_vm_destroy(struct kvm *kvm); int avic_vm_init(struct kvm *kvm); @@ -583,12 +574,12 @@ bool svm_check_apicv_inhibit_reasons(ulong bit); void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr); void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr); -int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec); bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu); int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); void avic_vcpu_blocking(struct kvm_vcpu *vcpu); void avic_vcpu_unblocking(struct kvm_vcpu *vcpu); +void avic_ring_doorbell(struct kvm_vcpu *vcpu); /* sev.c */ diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index aca3ae2a02f3..efda5e4d6247 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) @@ -7644,6 +7659,7 @@ static int vmx_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) if (ret) return ret; + vmx->nested.nested_run_pending = 1; vmx->nested.smm.guest_mode = false; } return 0; @@ -7768,7 +7784,7 @@ 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..641044db415d 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; } @@ -9981,7 +9983,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * result in virtual interrupt delivery. */ local_irq_disable(); - vcpu->mode = IN_GUEST_MODE; + + /* Store vcpu->apicv_active before vcpu->mode. */ + smp_store_release(&vcpu->mode, IN_GUEST_MODE); srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); @@ -10041,6 +10045,8 @@ 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 +10131,7 @@ 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 +11645,6 @@ 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/kvm/xen.c b/arch/x86/kvm/xen.c index bad57535fad0..74be1fda58e3 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -133,32 +133,57 @@ static void kvm_xen_update_runstate(struct kvm_vcpu *v, int state) void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) { struct kvm_vcpu_xen *vx = &v->arch.xen; + struct gfn_to_hva_cache *ghc = &vx->runstate_cache; + struct kvm_memslots *slots = kvm_memslots(v->kvm); + bool atomic = (state == RUNSTATE_runnable); uint64_t state_entry_time; - unsigned int offset; + int __user *user_state; + uint64_t __user *user_times; kvm_xen_update_runstate(v, state); if (!vx->runstate_set) return; - BUILD_BUG_ON(sizeof(struct compat_vcpu_runstate_info) != 0x2c); + if (unlikely(slots->generation != ghc->generation || kvm_is_error_hva(ghc->hva)) && + kvm_gfn_to_hva_cache_init(v->kvm, ghc, ghc->gpa, ghc->len)) + return; + + /* We made sure it fits in a single page */ + BUG_ON(!ghc->memslot); + + if (atomic) + pagefault_disable(); - offset = offsetof(struct compat_vcpu_runstate_info, state_entry_time); -#ifdef CONFIG_X86_64 /* - * The only difference is alignment of uint64_t in 32-bit. - * So the first field 'state' is accessed directly using - * offsetof() (where its offset happens to be zero), while the - * remaining fields which are all uint64_t, start at 'offset' - * which we tweak here by adding 4. + * The only difference between 32-bit and 64-bit versions of the + * runstate struct us the alignment of uint64_t in 32-bit, which + * means that the 64-bit version has an additional 4 bytes of + * padding after the first field 'state'. + * + * So we use 'int __user *user_state' to point to the state field, + * and 'uint64_t __user *user_times' for runstate_entry_time. So + * the actual array of time[] in each state starts at user_times[1]. */ + BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state) != 0); + BUILD_BUG_ON(offsetof(struct compat_vcpu_runstate_info, state) != 0); + user_state = (int __user *)ghc->hva; + + BUILD_BUG_ON(sizeof(struct compat_vcpu_runstate_info) != 0x2c); + + user_times = (uint64_t __user *)(ghc->hva + + offsetof(struct compat_vcpu_runstate_info, + state_entry_time)); +#ifdef CONFIG_X86_64 BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state_entry_time) != offsetof(struct compat_vcpu_runstate_info, state_entry_time) + 4); BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, time) != offsetof(struct compat_vcpu_runstate_info, time) + 4); if (v->kvm->arch.xen.long_mode) - offset = offsetof(struct vcpu_runstate_info, state_entry_time); + user_times = (uint64_t __user *)(ghc->hva + + offsetof(struct vcpu_runstate_info, + state_entry_time)); #endif /* * First write the updated state_entry_time at the appropriate @@ -172,10 +197,8 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state_entry_time) != sizeof(state_entry_time)); - if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, - &state_entry_time, offset, - sizeof(state_entry_time))) - return; + if (__put_user(state_entry_time, user_times)) + goto out; smp_wmb(); /* @@ -189,11 +212,8 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state) != sizeof(vx->current_runstate)); - if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, - &vx->current_runstate, - offsetof(struct vcpu_runstate_info, state), - sizeof(vx->current_runstate))) - return; + if (__put_user(vx->current_runstate, user_state)) + goto out; /* * Write the actual runstate times immediately after the @@ -208,24 +228,23 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) != sizeof(vx->runstate_times)); - if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, - &vx->runstate_times[0], - offset + sizeof(u64), - sizeof(vx->runstate_times))) - return; - + if (__copy_to_user(user_times + 1, vx->runstate_times, sizeof(vx->runstate_times))) + goto out; smp_wmb(); /* * Finally, clear the XEN_RUNSTATE_UPDATE bit in the guest's * runstate_entry_time field. */ - state_entry_time &= ~XEN_RUNSTATE_UPDATE; - if (kvm_write_guest_offset_cached(v->kvm, &v->arch.xen.runstate_cache, - &state_entry_time, offset, - sizeof(state_entry_time))) - return; + __put_user(state_entry_time, user_times); + smp_wmb(); + + out: + mark_page_dirty_in_slot(v->kvm, ghc->memslot, ghc->gpa >> PAGE_SHIFT); + + if (atomic) + pagefault_enable(); } int __kvm_xen_has_interrupt(struct kvm_vcpu *v) @@ -443,6 +462,12 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; } + /* It must fit within a single page */ + if ((data->u.gpa & ~PAGE_MASK) + sizeof(struct vcpu_info) > PAGE_SIZE) { + r = -EINVAL; + break; + } + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache, data->u.gpa, @@ -460,6 +485,12 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; } + /* It must fit within a single page */ + if ((data->u.gpa & ~PAGE_MASK) + sizeof(struct pvclock_vcpu_time_info) > PAGE_SIZE) { + r = -EINVAL; + break; + } + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.xen.vcpu_time_info_cache, data->u.gpa, @@ -481,6 +512,12 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; } + /* It must fit within a single page */ + if ((data->u.gpa & ~PAGE_MASK) + sizeof(struct vcpu_runstate_info) > PAGE_SIZE) { + r = -EINVAL; + break; + } + r = kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.xen.runstate_cache, data->u.gpa, 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/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..e1b1dd215267 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; @@ -4073,6 +4076,13 @@ 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/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/net/dsa/Kconfig b/drivers/net/dsa/Kconfig index 7b1457a6e327..c0c91440340a 100644 --- a/drivers/net/dsa/Kconfig +++ b/drivers/net/dsa/Kconfig @@ -36,6 +36,7 @@ config NET_DSA_LANTIQ_GSWIP config NET_DSA_MT7530 tristate "MediaTek MT753x and MT7621 Ethernet switch support" select NET_DSA_TAG_MTK + select MEDIATEK_GE_PHY help This enables support for the MediaTek MT7530, MT7531, and MT7621 Ethernet switch chips. diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 492ac383f16d..a3593290886f 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -721,7 +721,9 @@ static void xgbe_stop_timers(struct xgbe_prv_data *pdata) if (!channel->tx_ring) break; + /* Deactivate the Tx timer */ del_timer_sync(&channel->tx_timer); + channel->tx_timer_active = 0; } } @@ -2550,6 +2552,14 @@ read_again: buf2_len = xgbe_rx_buf2_len(rdata, packet, len); len += buf2_len; + if (buf2_len > rdata->rx.buf.dma_len) { + /* Hardware inconsistency within the descriptors + * that has resulted in a length underflow. + */ + error = 1; + goto skip_data; + } + if (!skb) { skb = xgbe_create_skb(pdata, napi, rdata, buf1_len); @@ -2579,8 +2589,10 @@ skip_data: if (!last || context_next) goto read_again; - if (!skb) + if (!skb || error) { + dev_kfree_skb(skb); goto next_packet; + } /* Be sure we don't exceed the configured MTU */ max_len = netdev->mtu + ETH_HLEN; diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c index 2ad7f57f7e5b..f7621ab672b9 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.c +++ b/drivers/net/ethernet/google/gve/gve_adminq.c @@ -301,7 +301,7 @@ static int gve_adminq_parse_err(struct gve_priv *priv, u32 status) */ static int gve_adminq_kick_and_wait(struct gve_priv *priv) { - u32 tail, head; + int tail, head; int i; tail = ioread32be(&priv->reg_bar0->adminq_event_counter); diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index c3def0ee7788..8d06c9d8ff8b 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -115,7 +115,8 @@ enum e1000_boards { board_pch_lpt, board_pch_spt, board_pch_cnp, - board_pch_tgp + board_pch_tgp, + board_pch_adp }; struct e1000_ps_page { @@ -502,6 +503,7 @@ extern const struct e1000_info e1000_pch_lpt_info; extern const struct e1000_info e1000_pch_spt_info; extern const struct e1000_info e1000_pch_cnp_info; extern const struct e1000_info e1000_pch_tgp_info; +extern const struct e1000_info e1000_pch_adp_info; extern const struct e1000_info e1000_es2_info; void e1000e_ptp_init(struct e1000_adapter *adapter); diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 5e4fc9b4e2ad..c908c84b86d2 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -6021,3 +6021,23 @@ const struct e1000_info e1000_pch_tgp_info = { .phy_ops = &ich8_phy_ops, .nvm_ops = &spt_nvm_ops, }; + +const struct e1000_info e1000_pch_adp_info = { + .mac = e1000_pch_adp, + .flags = FLAG_IS_ICH + | FLAG_HAS_WOL + | FLAG_HAS_HW_TIMESTAMP + | FLAG_HAS_CTRLEXT_ON_LOAD + | FLAG_HAS_AMT + | FLAG_HAS_FLASH + | FLAG_HAS_JUMBO_FRAMES + | FLAG_APME_IN_WUC, + .flags2 = FLAG2_HAS_PHY_STATS + | FLAG2_HAS_EEE, + .pba = 26, + .max_hw_frame_size = 9022, + .get_variants = e1000_get_variants_ich8lan, + .mac_ops = &ich8_mac_ops, + .phy_ops = &ich8_phy_ops, + .nvm_ops = &spt_nvm_ops, +}; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 635a95927e93..a42aeb555f34 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -52,6 +52,7 @@ static const struct e1000_info *e1000_info_tbl[] = { [board_pch_spt] = &e1000_pch_spt_info, [board_pch_cnp] = &e1000_pch_cnp_info, [board_pch_tgp] = &e1000_pch_tgp_info, + [board_pch_adp] = &e1000_pch_adp_info, }; struct e1000_reg_info { @@ -6341,7 +6342,8 @@ static void e1000e_s0ix_entry_flow(struct e1000_adapter *adapter) u32 mac_data; u16 phy_data; - if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID) { + if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID && + hw->mac.type >= e1000_pch_adp) { /* Request ME configure the device for S0ix */ mac_data = er32(H2ME); mac_data |= E1000_H2ME_START_DPG; @@ -6490,7 +6492,8 @@ static void e1000e_s0ix_exit_flow(struct e1000_adapter *adapter) u16 phy_data; u32 i = 0; - if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID) { + if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID && + hw->mac.type >= e1000_pch_adp) { /* Request ME unconfigure the device from S0ix */ mac_data = er32(H2ME); mac_data &= ~E1000_H2ME_START_DPG; @@ -7898,22 +7901,22 @@ static const struct pci_device_id e1000_pci_tbl[] = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V14), board_pch_tgp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM15), board_pch_tgp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V15), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM23), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V23), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM16), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V16), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM17), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V17), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM22), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V22), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM18), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V18), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM19), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V19), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM20), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V20), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM21), board_pch_tgp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_tgp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM23), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V23), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM16), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V16), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM17), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V17), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM22), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V22), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM18), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V18), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM19), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V19), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM20), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V20), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM21), board_pch_adp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_adp }, { 0, 0, 0, 0, 0, 0, 0 } /* terminate list */ }; diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 2e02cc68cd3f..80c5cecaf2b5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -144,6 +144,7 @@ enum i40e_state_t { __I40E_VIRTCHNL_OP_PENDING, __I40E_RECOVERY_MODE, __I40E_VF_RESETS_DISABLED, /* disable resets during i40e_remove */ + __I40E_IN_REMOVE, __I40E_VFS_RELEASING, /* This must be last as it determines the size of the BITMAP */ __I40E_STATE_SIZE__, diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index f70c478dafdb..0c4b7dfb3b35 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5372,7 +5372,15 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc, /* There is no need to reset BW when mqprio mode is on. */ if (pf->flags & I40E_FLAG_TC_MQPRIO) return 0; - if (!vsi->mqprio_qopt.qopt.hw && !(pf->flags & I40E_FLAG_DCB_ENABLED)) { + + if (!vsi->mqprio_qopt.qopt.hw) { + if (pf->flags & I40E_FLAG_DCB_ENABLED) + goto skip_reset; + + if (IS_ENABLED(CONFIG_I40E_DCB) && + i40e_dcb_hw_get_num_tc(&pf->hw) == 1) + goto skip_reset; + ret = i40e_set_bw_limit(vsi, vsi->seid, 0); if (ret) dev_info(&pf->pdev->dev, @@ -5380,6 +5388,8 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc, vsi->seid); return ret; } + +skip_reset: memset(&bw_data, 0, sizeof(bw_data)); bw_data.tc_valid_bits = enabled_tc; for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) @@ -10853,6 +10863,9 @@ static void i40e_reset_and_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) { int ret; + + if (test_bit(__I40E_IN_REMOVE, pf->state)) + return; /* Now we wait for GRST to settle out. * We don't have to delete the VEBs or VSIs from the hw switch * because the reset will make them disappear. @@ -12212,6 +12225,8 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count) vsi->req_queue_pairs = queue_count; i40e_prep_for_reset(pf); + if (test_bit(__I40E_IN_REMOVE, pf->state)) + return pf->alloc_rss_size; pf->alloc_rss_size = new_rss_size; @@ -13038,6 +13053,10 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog, if (need_reset) i40e_prep_for_reset(pf); + /* VSI shall be deleted in a moment, just return EINVAL */ + if (test_bit(__I40E_IN_REMOVE, pf->state)) + return -EINVAL; + old_prog = xchg(&vsi->xdp_prog, prog); if (need_reset) { @@ -15928,8 +15947,13 @@ static void i40e_remove(struct pci_dev *pdev) i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), 0); i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0); - while (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) + /* Grab __I40E_RESET_RECOVERY_PENDING and set __I40E_IN_REMOVE + * flags, once they are set, i40e_rebuild should not be called as + * i40e_prep_for_reset always returns early. + */ + while (test_and_set_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) usleep_range(1000, 2000); + set_bit(__I40E_IN_REMOVE, pf->state); if (pf->flags & I40E_FLAG_SRIOV_ENABLED) { set_bit(__I40E_VF_RESETS_DISABLED, pf->state); @@ -16128,6 +16152,9 @@ static void i40e_pci_error_reset_done(struct pci_dev *pdev) { struct i40e_pf *pf = pci_get_drvdata(pdev); + if (test_bit(__I40E_IN_REMOVE, pf->state)) + return; + i40e_reset_and_rebuild(pf, false, false); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 812e6810cb3b..c14e06ca64d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -224,7 +224,7 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) struct mlx5e_tx_wqe { struct mlx5_wqe_ctrl_seg ctrl; struct mlx5_wqe_eth_seg eth; - struct mlx5_wqe_data_seg data[0]; + struct mlx5_wqe_data_seg data[]; }; struct mlx5e_rx_wqe_ll { @@ -241,8 +241,8 @@ struct mlx5e_umr_wqe { struct mlx5_wqe_umr_ctrl_seg uctrl; struct mlx5_mkey_seg mkc; union { - struct mlx5_mtt inline_mtts[0]; - struct mlx5_klm inline_klms[0]; + DECLARE_FLEX_ARRAY(struct mlx5_mtt, inline_mtts); + DECLARE_FLEX_ARRAY(struct mlx5_klm, inline_klms); }; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c index 00449df98a5e..c1e07496c89c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c @@ -570,7 +570,8 @@ static int mlx5e_htb_convert_rate(struct mlx5e_priv *priv, u64 rate, static void mlx5e_htb_convert_ceil(struct mlx5e_priv *priv, u64 ceil, u32 *max_average_bw) { - *max_average_bw = div_u64(ceil, BYTES_IN_MBIT); + /* Hardware treats 0 as "unlimited", set at least 1. */ + *max_average_bw = max_t(u32, div_u64(ceil, BYTES_IN_MBIT), 1); qos_dbg(priv->mdev, "Convert: ceil %llu -> max_average_bw %u\n", ceil, *max_average_bw); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c index 9c076aa20306..b6f5c1bcdbcd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bond.c @@ -183,18 +183,7 @@ void mlx5e_rep_bond_unslave(struct mlx5_eswitch *esw, static bool mlx5e_rep_is_lag_netdev(struct net_device *netdev) { - struct mlx5e_rep_priv *rpriv; - struct mlx5e_priv *priv; - - /* A given netdev is not a representor or not a slave of LAG configuration */ - if (!mlx5e_eswitch_rep(netdev) || !netif_is_lag_port(netdev)) - return false; - - priv = netdev_priv(netdev); - rpriv = priv->ppriv; - - /* Egress acl forward to vport is supported only non-uplink representor */ - return rpriv->rep->vport != MLX5_VPORT_UPLINK; + return netif_is_lag_port(netdev) && mlx5e_eswitch_vf_rep(netdev); } static void mlx5e_rep_changelowerstate_event(struct net_device *netdev, void *ptr) @@ -210,9 +199,6 @@ static void mlx5e_rep_changelowerstate_event(struct net_device *netdev, void *pt u16 fwd_vport_num; int err; - if (!mlx5e_rep_is_lag_netdev(netdev)) - return; - info = ptr; lag_info = info->lower_state_info; /* This is not an event of a representor becoming active slave */ @@ -266,9 +252,6 @@ static void mlx5e_rep_changeupper_event(struct net_device *netdev, void *ptr) struct net_device *lag_dev; struct mlx5e_priv *priv; - if (!mlx5e_rep_is_lag_netdev(netdev)) - return; - priv = netdev_priv(netdev); rpriv = priv->ppriv; lag_dev = info->upper_dev; @@ -293,6 +276,19 @@ static int mlx5e_rep_esw_bond_netevent(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct mlx5e_rep_priv *rpriv; + struct mlx5e_rep_bond *bond; + struct mlx5e_priv *priv; + + if (!mlx5e_rep_is_lag_netdev(netdev)) + return NOTIFY_DONE; + + bond = container_of(nb, struct mlx5e_rep_bond, nb); + priv = netdev_priv(netdev); + rpriv = mlx5_eswitch_get_uplink_priv(priv->mdev->priv.eswitch, REP_ETH); + /* Verify VF representor is on the same device of the bond handling the netevent. */ + if (rpriv->uplink_priv.bond != bond) + return NOTIFY_DONE; switch (event) { case NETDEV_CHANGELOWERSTATE: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c index c6d2f8c78db7..48dc121b2cb4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c @@ -491,7 +491,7 @@ void mlx5e_rep_bridge_init(struct mlx5e_priv *priv) } br_offloads->netdev_nb.notifier_call = mlx5_esw_bridge_switchdev_port_event; - err = register_netdevice_notifier(&br_offloads->netdev_nb); + err = register_netdevice_notifier_net(&init_net, &br_offloads->netdev_nb); if (err) { esw_warn(mdev, "Failed to register bridge offloads netdevice notifier (err=%d)\n", err); @@ -509,7 +509,9 @@ err_register_swdev_blk: err_register_swdev: destroy_workqueue(br_offloads->wq); err_alloc_wq: + rtnl_lock(); mlx5_esw_bridge_cleanup(esw); + rtnl_unlock(); } void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv) @@ -524,7 +526,7 @@ void mlx5e_rep_bridge_cleanup(struct mlx5e_priv *priv) return; cancel_delayed_work_sync(&br_offloads->update_work); - unregister_netdevice_notifier(&br_offloads->netdev_nb); + unregister_netdevice_notifier_net(&init_net, &br_offloads->netdev_nb); unregister_switchdev_blocking_notifier(&br_offloads->nb_blk); unregister_switchdev_notifier(&br_offloads->nb); destroy_workqueue(br_offloads->wq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 4cdf8e5b24c2..b789af07829c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -167,6 +167,11 @@ static inline u16 mlx5e_txqsq_get_next_pi(struct mlx5e_txqsq *sq, u16 size) return pi; } +static inline u16 mlx5e_shampo_get_cqe_header_index(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) +{ + return be16_to_cpu(cqe->shampo.header_entry_index) & (rq->mpwqe.shampo->hd_per_wq - 1); +} + struct mlx5e_shampo_umr { u16 len; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 338d65e2c9ce..56e10c84a706 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -341,8 +341,10 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd, /* copy the inline part if required */ if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) { - memcpy(eseg->inline_hdr.start, xdptxd->data, MLX5E_XDP_MIN_INLINE); + memcpy(eseg->inline_hdr.start, xdptxd->data, sizeof(eseg->inline_hdr.start)); eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE); + memcpy(dseg, xdptxd->data + sizeof(eseg->inline_hdr.start), + MLX5E_XDP_MIN_INLINE - sizeof(eseg->inline_hdr.start)); dma_len -= MLX5E_XDP_MIN_INLINE; dma_addr += MLX5E_XDP_MIN_INLINE; dseg++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c index 2db9573a3fe6..b56fea142c24 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c @@ -157,11 +157,20 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb, /* Tunnel mode */ if (mode == XFRM_MODE_TUNNEL) { eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2; - eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2; if (xo->proto == IPPROTO_IPV6) eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6; - if (inner_ip_hdr(skb)->protocol == IPPROTO_UDP) + + switch (xo->inner_ipproto) { + case IPPROTO_UDP: eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP; + fallthrough; + case IPPROTO_TCP: + /* IP | ESP | IP | [TCP | UDP] */ + eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2; + break; + default: + break; + } return; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h index b98db50c3418..428881e0adcb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h @@ -131,14 +131,17 @@ static inline bool mlx5e_ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_wqe_eth_seg *eseg) { - struct xfrm_offload *xo = xfrm_offload(skb); + u8 inner_ipproto; if (!mlx5e_ipsec_eseg_meta(eseg)) return false; eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM; - if (xo->inner_ipproto) { - eseg->cs_flags |= MLX5_ETH_WQE_L4_INNER_CSUM | MLX5_ETH_WQE_L3_INNER_CSUM; + inner_ipproto = xfrm_offload(skb)->inner_ipproto; + if (inner_ipproto) { + eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM; + if (inner_ipproto == IPPROTO_TCP || inner_ipproto == IPPROTO_UDP) + eseg->cs_flags |= MLX5_ETH_WQE_L4_INNER_CSUM; } else if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM; sq->stats->csum_partial_inner++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index e86ccc22fb82..ee0a8f5206e3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1117,7 +1117,7 @@ static void mlx5e_shampo_update_ipv6_udp_hdr(struct mlx5e_rq *rq, struct ipv6hdr static void mlx5e_shampo_update_fin_psh_flags(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, struct tcphdr *skb_tcp_hd) { - u16 header_index = be16_to_cpu(cqe->shampo.header_entry_index); + u16 header_index = mlx5e_shampo_get_cqe_header_index(rq, cqe); struct tcphdr *last_tcp_hd; void *last_hd_addr; @@ -1871,7 +1871,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, return skb; } -static void +static struct sk_buff * mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, struct mlx5_cqe64 *cqe, u16 header_index) { @@ -1895,7 +1895,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, skb = mlx5e_build_linear_skb(rq, hdr, frag_size, rx_headroom, head_size); if (unlikely(!skb)) - return; + return NULL; /* queue up for recycling/reuse */ page_ref_inc(head->page); @@ -1907,7 +1907,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, ALIGN(head_size, sizeof(long))); if (unlikely(!skb)) { rq->stats->buff_alloc_err++; - return; + return NULL; } prefetchw(skb->data); @@ -1918,9 +1918,7 @@ mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, skb->tail += head_size; skb->len += head_size; } - rq->hw_gro_data->skb = skb; - NAPI_GRO_CB(skb)->count = 1; - skb_shinfo(skb)->gso_size = mpwrq_get_cqe_byte_cnt(cqe) - head_size; + return skb; } static void @@ -1973,13 +1971,14 @@ mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index) static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) { u16 data_bcnt = mpwrq_get_cqe_byte_cnt(cqe) - cqe->shampo.header_size; - u16 header_index = be16_to_cpu(cqe->shampo.header_entry_index); + u16 header_index = mlx5e_shampo_get_cqe_header_index(rq, cqe); u32 wqe_offset = be32_to_cpu(cqe->shampo.data_offset); u16 cstrides = mpwrq_get_cqe_consumed_strides(cqe); u32 data_offset = wqe_offset & (PAGE_SIZE - 1); u32 cqe_bcnt = mpwrq_get_cqe_byte_cnt(cqe); u16 wqe_id = be16_to_cpu(cqe->wqe_id); u32 page_idx = wqe_offset >> PAGE_SHIFT; + u16 head_size = cqe->shampo.header_size; struct sk_buff **skb = &rq->hw_gro_data->skb; bool flush = cqe->shampo.flush; bool match = cqe->shampo.match; @@ -2011,9 +2010,16 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq } if (!*skb) { - mlx5e_skb_from_cqe_shampo(rq, wi, cqe, header_index); + if (likely(head_size)) + *skb = mlx5e_skb_from_cqe_shampo(rq, wi, cqe, header_index); + else + *skb = mlx5e_skb_from_cqe_mpwrq_nonlinear(rq, wi, cqe_bcnt, data_offset, + page_idx); if (unlikely(!*skb)) goto free_hd_entry; + + NAPI_GRO_CB(*skb)->count = 1; + skb_shinfo(*skb)->gso_size = cqe_bcnt - head_size; } else { NAPI_GRO_CB(*skb)->count++; if (NAPI_GRO_CB(*skb)->count == 2 && @@ -2027,8 +2033,10 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq } } - di = &wi->umr.dma_info[page_idx]; - mlx5e_fill_skb_data(*skb, rq, di, data_bcnt, data_offset); + if (likely(head_size)) { + di = &wi->umr.dma_info[page_idx]; + mlx5e_fill_skb_data(*skb, rq, di, data_bcnt, data_offset); + } mlx5e_shampo_complete_rx_cqe(rq, cqe, cqe_bcnt, *skb); if (flush) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 3d908a7e1406..2022fa4a9598 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1414,7 +1414,8 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, if (err) goto err_out; - if (!attr->chain && esw_attr->int_port) { + if (!attr->chain && esw_attr->int_port && + attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { /* If decap route device is internal port, change the * source vport value in reg_c0 back to uplink just in * case the rule performs goto chain > 0. If we have a miss @@ -3191,6 +3192,18 @@ actions_match_supported(struct mlx5e_priv *priv, return false; } + if (!(~actions & + (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) { + NL_SET_ERR_MSG_MOD(extack, "Rule cannot support forward+drop action"); + return false; + } + + if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR && + actions & MLX5_FLOW_CONTEXT_ACTION_DROP) { + NL_SET_ERR_MSG_MOD(extack, "Drop with modify header action is not supported"); + return false; + } + if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR && !modify_header_match_supported(priv, &parse_attr->spec, flow_action, actions, ct_flow, ct_clear, extack)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 7fd33b356cc8..ee7ecb88adc1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -208,7 +208,7 @@ static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs) int cpy1_sz = 2 * ETH_ALEN; int cpy2_sz = ihs - cpy1_sz; - memcpy(vhdr, skb->data, cpy1_sz); + memcpy(&vhdr->addrs, skb->data, cpy1_sz); vhdr->h_vlan_proto = skb->vlan_proto; vhdr->h_vlan_TCI = cpu_to_be16(skb_vlan_tag_get(skb)); memcpy(&vhdr->h_vlan_encapsulated_proto, skb->data + cpy1_sz, cpy2_sz); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index f690f430f40f..05e08cec5a8c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -1574,6 +1574,8 @@ struct mlx5_esw_bridge_offloads *mlx5_esw_bridge_init(struct mlx5_eswitch *esw) { struct mlx5_esw_bridge_offloads *br_offloads; + ASSERT_RTNL(); + br_offloads = kvzalloc(sizeof(*br_offloads), GFP_KERNEL); if (!br_offloads) return ERR_PTR(-ENOMEM); @@ -1590,6 +1592,8 @@ void mlx5_esw_bridge_cleanup(struct mlx5_eswitch *esw) { struct mlx5_esw_bridge_offloads *br_offloads = esw->br_offloads; + ASSERT_RTNL(); + if (!br_offloads) return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h index 3401188e0a60..51ac24e6ec3c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h @@ -21,7 +21,7 @@ DECLARE_EVENT_CLASS(mlx5_esw_bridge_fdb_template, __field(unsigned int, used) ), TP_fast_assign( - strncpy(__entry->dev_name, + strscpy(__entry->dev_name, netdev_name(fdb->dev), IFNAMSIZ); memcpy(__entry->addr, fdb->key.addr, ETH_ALEN); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 0b0234f9d694..84dbe46d5ede 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -132,7 +132,7 @@ static void mlx5_stop_sync_reset_poll(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; - del_timer(&fw_reset->timer); + del_timer_sync(&fw_reset->timer); } static void mlx5_sync_reset_clear_reset_requested(struct mlx5_core_dev *dev, bool poll_health) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c index d5e47630e284..df58cba37930 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c @@ -121,12 +121,13 @@ u32 mlx5_chains_get_nf_ft_chain(struct mlx5_fs_chains *chains) u32 mlx5_chains_get_prio_range(struct mlx5_fs_chains *chains) { - if (!mlx5_chains_prios_supported(chains)) - return 1; - if (mlx5_chains_ignore_flow_level_supported(chains)) return UINT_MAX; + if (!chains->dev->priv.eswitch || + chains->dev->priv.eswitch->mode != MLX5_ESWITCH_OFFLOADS) + return 1; + /* We should get here only for eswitch case */ return FDB_TC_MAX_PRIO; } @@ -211,7 +212,7 @@ static int create_chain_restore(struct fs_chain *chain) { struct mlx5_eswitch *esw = chain->chains->dev->priv.eswitch; - char modact[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)]; + u8 modact[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; struct mlx5_fs_chains *chains = chain->chains; enum mlx5e_tc_attr_to_reg chain_to_reg; struct mlx5_modify_hdr *mod_hdr; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 1ef2b6a848c1..7b16a1188aab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -406,23 +406,24 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, switch (module_id) { case MLX5_MODULE_ID_SFP: - mlx5_sfp_eeprom_params_set(&query.i2c_address, &query.page, &query.offset); + mlx5_sfp_eeprom_params_set(&query.i2c_address, &query.page, &offset); break; case MLX5_MODULE_ID_QSFP: case MLX5_MODULE_ID_QSFP_PLUS: case MLX5_MODULE_ID_QSFP28: - mlx5_qsfp_eeprom_params_set(&query.i2c_address, &query.page, &query.offset); + mlx5_qsfp_eeprom_params_set(&query.i2c_address, &query.page, &offset); break; default: mlx5_core_err(dev, "Module ID not recognized: 0x%x\n", module_id); return -EINVAL; } - if (query.offset + size > MLX5_EEPROM_PAGE_LENGTH) + if (offset + size > MLX5_EEPROM_PAGE_LENGTH) /* Cross pages read, read until offset 256 in low page */ - size -= offset + size - MLX5_EEPROM_PAGE_LENGTH; + size = MLX5_EEPROM_PAGE_LENGTH - offset; query.size = size; + query.offset = offset; return mlx5_query_mcia(dev, &query, data); } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c index dc7e5ea6ec15..148d431fcde4 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c @@ -145,9 +145,9 @@ static void sparx5_xtr_grp(struct sparx5 *sparx5, u8 grp, bool byte_swap) skb_put(skb, byte_cnt - ETH_FCS_LEN); eth_skb_pad(skb); skb->protocol = eth_type_trans(skb, netdev); - netif_rx(skb); netdev->stats.rx_bytes += skb->len; netdev->stats.rx_packets++; + netif_rx(skb); } static int sparx5_inject(struct sparx5 *sparx5, diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c index dd6f69ced4ee..fc9cef9dcefc 100644 --- a/drivers/net/ethernet/smsc/smc911x.c +++ b/drivers/net/ethernet/smsc/smc911x.c @@ -1648,7 +1648,7 @@ static int smc911x_ethtool_geteeprom(struct net_device *dev, return ret; if ((ret=smc911x_ethtool_read_eeprom_byte(dev, &eebuf[i]))!=0) return ret; - } + } memcpy(data, eebuf+eeprom->offset, eeprom->len); return 0; } @@ -1667,11 +1667,11 @@ static int smc911x_ethtool_seteeprom(struct net_device *dev, return ret; /* write byte */ if ((ret=smc911x_ethtool_write_eeprom_byte(dev, *data))!=0) - return ret; + return ret; if ((ret=smc911x_ethtool_write_eeprom_cmd(dev, E2P_CMD_EPC_CMD_WRITE_, i ))!=0) return ret; - } - return 0; + } + return 0; } static int smc911x_ethtool_geteeprom_len(struct net_device *dev) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c index dde5b772a5af..c3f10a92b62b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c @@ -49,13 +49,15 @@ struct visconti_eth { void __iomem *reg; u32 phy_intf_sel; struct clk *phy_ref_clk; + struct device *dev; spinlock_t lock; /* lock to protect register update */ }; static void visconti_eth_fix_mac_speed(void *priv, unsigned int speed) { struct visconti_eth *dwmac = priv; - unsigned int val, clk_sel_val; + struct net_device *netdev = dev_get_drvdata(dwmac->dev); + unsigned int val, clk_sel_val = 0; unsigned long flags; spin_lock_irqsave(&dwmac->lock, flags); @@ -85,7 +87,9 @@ static void visconti_eth_fix_mac_speed(void *priv, unsigned int speed) break; default: /* No bit control */ - break; + netdev_err(netdev, "Unsupported speed request (%d)", speed); + spin_unlock_irqrestore(&dwmac->lock, flags); + return; } writel(val, dwmac->reg + MAC_CTRL_REG); @@ -229,6 +233,7 @@ static int visconti_eth_dwmac_probe(struct platform_device *pdev) spin_lock_init(&dwmac->lock); dwmac->reg = stmmac_res.addr; + dwmac->dev = &pdev->dev; plat_dat->bsp_priv = dwmac; plat_dat->fix_mac_speed = visconti_eth_fix_mac_speed; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h index 1914ad698cab..acd70b9a3173 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h @@ -150,6 +150,7 @@ #define NUM_DWMAC100_DMA_REGS 9 #define NUM_DWMAC1000_DMA_REGS 23 +#define NUM_DWMAC4_DMA_REGS 27 void dwmac_enable_dma_transmission(void __iomem *ioaddr); void dwmac_enable_dma_irq(void __iomem *ioaddr, u32 chan, bool rx, bool tx); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 164dff5ec32e..abfb3cd5958d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -21,10 +21,18 @@ #include "dwxgmac2.h" #define REG_SPACE_SIZE 0x1060 +#define GMAC4_REG_SPACE_SIZE 0x116C #define MAC100_ETHTOOL_NAME "st_mac100" #define GMAC_ETHTOOL_NAME "st_gmac" #define XGMAC_ETHTOOL_NAME "st_xgmac" +/* Same as DMA_CHAN_BASE_ADDR defined in dwmac4_dma.h + * + * It is here because dwmac_dma.h and dwmac4_dam.h can not be included at the + * same time due to the conflicting macro names. + */ +#define GMAC4_DMA_CHAN_BASE_ADDR 0x00001100 + #define ETHTOOL_DMA_OFFSET 55 struct stmmac_stats { @@ -434,6 +442,8 @@ static int stmmac_ethtool_get_regs_len(struct net_device *dev) if (priv->plat->has_xgmac) return XGMAC_REGSIZE * 4; + else if (priv->plat->has_gmac4) + return GMAC4_REG_SPACE_SIZE; return REG_SPACE_SIZE; } @@ -446,8 +456,13 @@ static void stmmac_ethtool_gregs(struct net_device *dev, stmmac_dump_mac_regs(priv, priv->hw, reg_space); stmmac_dump_dma_regs(priv, priv->ioaddr, reg_space); - if (!priv->plat->has_xgmac) { - /* Copy DMA registers to where ethtool expects them */ + /* Copy DMA registers to where ethtool expects them */ + if (priv->plat->has_gmac4) { + /* GMAC4 dumps its DMA registers at its DMA_CHAN_BASE_ADDR */ + memcpy(®_space[ETHTOOL_DMA_OFFSET], + ®_space[GMAC4_DMA_CHAN_BASE_ADDR / 4], + NUM_DWMAC4_DMA_REGS * 4); + } else if (!priv->plat->has_xgmac) { memcpy(®_space[ETHTOOL_DMA_OFFSET], ®_space[DMA_BUS_MODE / 4], NUM_DWMAC1000_DMA_REGS * 4); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index 074e2cdfb0fa..a7ec9f4d46ce 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -145,15 +145,20 @@ static int adjust_systime(void __iomem *ioaddr, u32 sec, u32 nsec, static void get_systime(void __iomem *ioaddr, u64 *systime) { - u64 ns; - - /* Get the TSSS value */ - ns = readl(ioaddr + PTP_STNSR); - /* Get the TSS and convert sec time value to nanosecond */ - ns += readl(ioaddr + PTP_STSR) * 1000000000ULL; + u64 ns, sec0, sec1; + + /* Get the TSS value */ + sec1 = readl_relaxed(ioaddr + PTP_STSR); + do { + sec0 = sec1; + /* Get the TSSS value */ + ns = readl_relaxed(ioaddr + PTP_STNSR); + /* Get the TSS value */ + sec1 = readl_relaxed(ioaddr + PTP_STSR); + } while (sec0 != sec1); if (systime) - *systime = ns; + *systime = ns + (sec1 * 1000000000ULL); } static void get_ptptime(void __iomem *ptpaddr, u64 *ptp_time) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 639a753266e6..bde76ea2deec 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -7252,6 +7252,10 @@ int stmmac_dvr_remove(struct device *dev) netdev_info(priv->dev, "%s: removing driver", __func__); + pm_runtime_get_sync(dev); + pm_runtime_disable(dev); + pm_runtime_put_noidle(dev); + stmmac_stop_all_dma(priv); stmmac_mac_set(priv, priv->ioaddr, false); netif_carrier_off(ndev); @@ -7270,8 +7274,6 @@ int stmmac_dvr_remove(struct device *dev) if (priv->plat->stmmac_rst) reset_control_assert(priv->plat->stmmac_rst); reset_control_assert(priv->plat->stmmac_ahb_rst); - pm_runtime_put(dev); - pm_runtime_disable(dev); if (priv->hw->pcs != STMMAC_PCS_TBI && priv->hw->pcs != STMMAC_PCS_RTBI) stmmac_mdio_unregister(ndev); diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c index 7d67f41387f5..4f5ef8a9a9a8 100644 --- a/drivers/net/ieee802154/at86rf230.c +++ b/drivers/net/ieee802154/at86rf230.c @@ -100,6 +100,7 @@ struct at86rf230_local { unsigned long cal_timeout; bool is_tx; bool is_tx_from_off; + bool was_tx; u8 tx_retry; struct sk_buff *tx_skb; struct at86rf230_state_change tx; @@ -343,7 +344,11 @@ at86rf230_async_error_recover_complete(void *context) if (ctx->free) kfree(ctx); - ieee802154_wake_queue(lp->hw); + if (lp->was_tx) { + lp->was_tx = 0; + dev_kfree_skb_any(lp->tx_skb); + ieee802154_wake_queue(lp->hw); + } } static void @@ -352,7 +357,11 @@ at86rf230_async_error_recover(void *context) struct at86rf230_state_change *ctx = context; struct at86rf230_local *lp = ctx->lp; - lp->is_tx = 0; + if (lp->is_tx) { + lp->was_tx = 1; + lp->is_tx = 0; + } + at86rf230_async_state_change(lp, ctx, STATE_RX_AACK_ON, at86rf230_async_error_recover_complete); } diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index ece6ff6049f6..f3438d3e104a 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -1771,6 +1771,7 @@ static int ca8210_async_xmit_complete( status ); if (status != MAC_TRANSACTION_OVERFLOW) { + dev_kfree_skb_any(priv->tx_skb); ieee802154_wake_queue(priv->hw); return 0; } diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c index 8caa61ec718f..36f1c5aa98fc 100644 --- a/drivers/net/ieee802154/mac802154_hwsim.c +++ b/drivers/net/ieee802154/mac802154_hwsim.c @@ -786,6 +786,7 @@ static int hwsim_add_one(struct genl_info *info, struct device *dev, goto err_pib; } + pib->channel = 13; rcu_assign_pointer(phy->pib, pib); phy->idx = idx; INIT_LIST_HEAD(&phy->edges); diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c index 8dc04e2590b1..383231b85464 100644 --- a/drivers/net/ieee802154/mcr20a.c +++ b/drivers/net/ieee802154/mcr20a.c @@ -976,8 +976,8 @@ static void mcr20a_hw_setup(struct mcr20a_local *lp) dev_dbg(printdev(lp), "%s\n", __func__); phy->symbol_duration = 16; - phy->lifs_period = 40; - phy->sifs_period = 12; + phy->lifs_period = 40 * phy->symbol_duration; + phy->sifs_period = 12 * phy->symbol_duration; hw->flags = IEEE802154_HW_TX_OMIT_CKSUM | IEEE802154_HW_AFILT | diff --git a/drivers/net/ipa/ipa_power.c b/drivers/net/ipa/ipa_power.c index b1c6c0fcb654..f2989aac47a6 100644 --- a/drivers/net/ipa/ipa_power.c +++ b/drivers/net/ipa/ipa_power.c @@ -11,6 +11,8 @@ #include <linux/pm_runtime.h> #include <linux/bitops.h> +#include "linux/soc/qcom/qcom_aoss.h" + #include "ipa.h" #include "ipa_power.h" #include "ipa_endpoint.h" @@ -64,6 +66,7 @@ enum ipa_power_flag { * struct ipa_power - IPA power management information * @dev: IPA device pointer * @core: IPA core clock + * @qmp: QMP handle for AOSS communication * @spinlock: Protects modem TX queue enable/disable * @flags: Boolean state flags * @interconnect_count: Number of elements in interconnect[] @@ -72,6 +75,7 @@ enum ipa_power_flag { struct ipa_power { struct device *dev; struct clk *core; + struct qmp *qmp; spinlock_t spinlock; /* used with STOPPED/STARTED power flags */ DECLARE_BITMAP(flags, IPA_POWER_FLAG_COUNT); u32 interconnect_count; @@ -382,6 +386,47 @@ void ipa_power_modem_queue_active(struct ipa *ipa) clear_bit(IPA_POWER_FLAG_STARTED, ipa->power->flags); } +static int ipa_power_retention_init(struct ipa_power *power) +{ + struct qmp *qmp = qmp_get(power->dev); + + if (IS_ERR(qmp)) { + if (PTR_ERR(qmp) == -EPROBE_DEFER) + return -EPROBE_DEFER; + + /* We assume any other error means it's not defined/needed */ + qmp = NULL; + } + power->qmp = qmp; + + return 0; +} + +static void ipa_power_retention_exit(struct ipa_power *power) +{ + qmp_put(power->qmp); + power->qmp = NULL; +} + +/* Control register retention on power collapse */ +void ipa_power_retention(struct ipa *ipa, bool enable) +{ + static const char fmt[] = "{ class: bcm, res: ipa_pc, val: %c }"; + struct ipa_power *power = ipa->power; + char buf[36]; /* Exactly enough for fmt[]; size a multiple of 4 */ + int ret; + + if (!power->qmp) + return; /* Not needed on this platform */ + + (void)snprintf(buf, sizeof(buf), fmt, enable ? '1' : '0'); + + ret = qmp_send(power->qmp, buf, sizeof(buf)); + if (ret) + dev_err(power->dev, "error %d sending QMP %sable request\n", + ret, enable ? "en" : "dis"); +} + int ipa_power_setup(struct ipa *ipa) { int ret; @@ -438,12 +483,18 @@ ipa_power_init(struct device *dev, const struct ipa_power_data *data) if (ret) goto err_kfree; + ret = ipa_power_retention_init(power); + if (ret) + goto err_interconnect_exit; + pm_runtime_set_autosuspend_delay(dev, IPA_AUTOSUSPEND_DELAY); pm_runtime_use_autosuspend(dev); pm_runtime_enable(dev); return power; +err_interconnect_exit: + ipa_interconnect_exit(power); err_kfree: kfree(power); err_clk_put: @@ -460,6 +511,7 @@ void ipa_power_exit(struct ipa_power *power) pm_runtime_disable(dev); pm_runtime_dont_use_autosuspend(dev); + ipa_power_retention_exit(power); ipa_interconnect_exit(power); kfree(power); clk_put(clk); diff --git a/drivers/net/ipa/ipa_power.h b/drivers/net/ipa/ipa_power.h index 2151805d7fbb..6f84f057a209 100644 --- a/drivers/net/ipa/ipa_power.h +++ b/drivers/net/ipa/ipa_power.h @@ -41,6 +41,13 @@ void ipa_power_modem_queue_wake(struct ipa *ipa); void ipa_power_modem_queue_active(struct ipa *ipa); /** + * ipa_power_retention() - Control register retention on power collapse + * @ipa: IPA pointer + * @enable: Whether retention should be enabled or disabled + */ +void ipa_power_retention(struct ipa *ipa, bool enable); + +/** * ipa_power_setup() - Set up IPA power management * @ipa: IPA pointer * diff --git a/drivers/net/ipa/ipa_uc.c b/drivers/net/ipa/ipa_uc.c index 856e55a080a7..fe11910518d9 100644 --- a/drivers/net/ipa/ipa_uc.c +++ b/drivers/net/ipa/ipa_uc.c @@ -11,6 +11,7 @@ #include "ipa.h" #include "ipa_uc.h" +#include "ipa_power.h" /** * DOC: The IPA embedded microcontroller @@ -154,6 +155,7 @@ static void ipa_uc_response_hdlr(struct ipa *ipa, enum ipa_irq_id irq_id) case IPA_UC_RESPONSE_INIT_COMPLETED: if (ipa->uc_powered) { ipa->uc_loaded = true; + ipa_power_retention(ipa, true); pm_runtime_mark_last_busy(dev); (void)pm_runtime_put_autosuspend(dev); ipa->uc_powered = false; @@ -184,6 +186,9 @@ void ipa_uc_deconfig(struct ipa *ipa) ipa_interrupt_remove(ipa->interrupt, IPA_IRQ_UC_1); ipa_interrupt_remove(ipa->interrupt, IPA_IRQ_UC_0); + if (ipa->uc_loaded) + ipa_power_retention(ipa, false); + if (!ipa->uc_powered) return; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 16aa3a478e9e..3d0874331763 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3870,6 +3870,18 @@ static void macsec_common_dellink(struct net_device *dev, struct list_head *head struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; + /* If h/w offloading is available, propagate to the device */ + if (macsec_is_offloaded(macsec)) { + const struct macsec_ops *ops; + struct macsec_context ctx; + + ops = macsec_get_ops(netdev_priv(dev), &ctx); + if (ops) { + ctx.secy = &macsec->secy; + macsec_offload(ops->mdo_del_secy, &ctx); + } + } + unregister_netdevice_queue(dev, head); list_del_rcu(&macsec->secys); macsec_del_dev(macsec); @@ -3884,18 +3896,6 @@ static void macsec_dellink(struct net_device *dev, struct list_head *head) struct net_device *real_dev = macsec->real_dev; struct macsec_rxh_data *rxd = macsec_data_rtnl(real_dev); - /* If h/w offloading is available, propagate to the device */ - if (macsec_is_offloaded(macsec)) { - const struct macsec_ops *ops; - struct macsec_context ctx; - - ops = macsec_get_ops(netdev_priv(dev), &ctx); - if (ops) { - ctx.secy = &macsec->secy; - macsec_offload(ops->mdo_del_secy, &ctx); - } - } - macsec_common_dellink(dev, head); if (list_empty(&rxd->secys)) { @@ -4018,6 +4018,15 @@ static int macsec_newlink(struct net *net, struct net_device *dev, !macsec_check_offload(macsec->offload, macsec)) return -EOPNOTSUPP; + /* send_sci must be set to true when transmit sci explicitly is set */ + if ((data && data[IFLA_MACSEC_SCI]) && + (data && data[IFLA_MACSEC_INC_SCI])) { + u8 send_sci = !!nla_get_u8(data[IFLA_MACSEC_INC_SCI]); + + if (!send_sci) + return -EINVAL; + } + if (data && data[IFLA_MACSEC_ICV_LEN]) icv_len = nla_get_u8(data[IFLA_MACSEC_ICV_LEN]); mtu = real_dev->mtu - icv_len - macsec_extra_len(true); diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index 5b6c0d120e09..29aa811af430 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -1688,19 +1688,19 @@ static int qca808x_read_status(struct phy_device *phydev) if (ret < 0) return ret; - if (phydev->link && phydev->speed == SPEED_2500) - phydev->interface = PHY_INTERFACE_MODE_2500BASEX; - else - phydev->interface = PHY_INTERFACE_MODE_SMII; - - /* generate seed as a lower random value to make PHY linked as SLAVE easily, - * except for master/slave configuration fault detected. - * the reason for not putting this code into the function link_change_notify is - * the corner case where the link partner is also the qca8081 PHY and the seed - * value is configured as the same value, the link can't be up and no link change - * occurs. - */ - if (!phydev->link) { + if (phydev->link) { + if (phydev->speed == SPEED_2500) + phydev->interface = PHY_INTERFACE_MODE_2500BASEX; + else + phydev->interface = PHY_INTERFACE_MODE_SGMII; + } else { + /* generate seed as a lower random value to make PHY linked as SLAVE easily, + * except for master/slave configuration fault detected. + * the reason for not putting this code into the function link_change_notify is + * the corner case where the link partner is also the qca8081 PHY and the seed + * value is configured as the same value, the link can't be up and no link change + * occurs. + */ if (phydev->master_slave_state == MASTER_SLAVE_STATE_ERR) { qca808x_phy_ms_seed_enable(phydev, false); } else { diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index cd33955df0b6..6a769df0b421 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -121,7 +121,7 @@ static int ipheth_alloc_urbs(struct ipheth_device *iphone) if (tx_buf == NULL) goto free_rx_urb; - rx_buf = usb_alloc_coherent(iphone->udev, IPHETH_BUF_SIZE, + rx_buf = usb_alloc_coherent(iphone->udev, IPHETH_BUF_SIZE + IPHETH_IP_ALIGN, GFP_KERNEL, &rx_urb->transfer_dma); if (rx_buf == NULL) goto free_tx_buf; @@ -146,7 +146,7 @@ error_nomem: static void ipheth_free_urbs(struct ipheth_device *iphone) { - usb_free_coherent(iphone->udev, IPHETH_BUF_SIZE, iphone->rx_buf, + usb_free_coherent(iphone->udev, IPHETH_BUF_SIZE + IPHETH_IP_ALIGN, iphone->rx_buf, iphone->rx_urb->transfer_dma); usb_free_coherent(iphone->udev, IPHETH_BUF_SIZE, iphone->tx_buf, iphone->tx_urb->transfer_dma); @@ -317,7 +317,7 @@ static int ipheth_rx_submit(struct ipheth_device *dev, gfp_t mem_flags) usb_fill_bulk_urb(dev->rx_urb, udev, usb_rcvbulkpipe(udev, dev->bulk_in), - dev->rx_buf, IPHETH_BUF_SIZE, + dev->rx_buf, IPHETH_BUF_SIZE + IPHETH_IP_ALIGN, ipheth_rcvbulk_callback, dev); dev->rx_urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; 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/pinctrl/Makefile b/drivers/pinctrl/Makefile index 08c364d611f5..f64d29f614ec 100644 --- a/drivers/pinctrl/Makefile +++ b/drivers/pinctrl/Makefile @@ -42,9 +42,9 @@ obj-$(CONFIG_PINCTRL_PISTACHIO) += pinctrl-pistachio.o obj-$(CONFIG_PINCTRL_RK805) += pinctrl-rk805.o obj-$(CONFIG_PINCTRL_ROCKCHIP) += pinctrl-rockchip.o obj-$(CONFIG_PINCTRL_SINGLE) += pinctrl-single.o +obj-$(CONFIG_PINCTRL_ST) += pinctrl-st.o obj-$(CONFIG_PINCTRL_STARFIVE) += pinctrl-starfive.o obj-$(CONFIG_PINCTRL_STMFX) += pinctrl-stmfx.o -obj-$(CONFIG_PINCTRL_ST) += pinctrl-st.o obj-$(CONFIG_PINCTRL_SX150X) += pinctrl-sx150x.o obj-$(CONFIG_PINCTRL_TB10X) += pinctrl-tb10x.o obj-$(CONFIG_PINCTRL_THUNDERBAY) += pinctrl-thunderbay.o diff --git a/drivers/pinctrl/bcm/Kconfig b/drivers/pinctrl/bcm/Kconfig index 5123f4c33854..ac1e400bbbac 100644 --- a/drivers/pinctrl/bcm/Kconfig +++ b/drivers/pinctrl/bcm/Kconfig @@ -35,6 +35,7 @@ config PINCTRL_BCM63XX select PINCONF select GENERIC_PINCONF select GPIOLIB + select REGMAP select GPIO_REGMAP config PINCTRL_BCM6318 diff --git a/drivers/pinctrl/bcm/pinctrl-bcm2835.c b/drivers/pinctrl/bcm/pinctrl-bcm2835.c index c4ebfa852b42..47e433e09c5c 100644 --- a/drivers/pinctrl/bcm/pinctrl-bcm2835.c +++ b/drivers/pinctrl/bcm/pinctrl-bcm2835.c @@ -1269,16 +1269,18 @@ static int bcm2835_pinctrl_probe(struct platform_device *pdev) sizeof(*girq->parents), GFP_KERNEL); if (!girq->parents) { - pinctrl_remove_gpio_range(pc->pctl_dev, &pc->gpio_range); - return -ENOMEM; + err = -ENOMEM; + goto out_remove; } if (is_7211) { pc->wake_irq = devm_kcalloc(dev, BCM2835_NUM_IRQS, sizeof(*pc->wake_irq), GFP_KERNEL); - if (!pc->wake_irq) - return -ENOMEM; + if (!pc->wake_irq) { + err = -ENOMEM; + goto out_remove; + } } /* @@ -1306,8 +1308,10 @@ static int bcm2835_pinctrl_probe(struct platform_device *pdev) len = strlen(dev_name(pc->dev)) + 16; name = devm_kzalloc(pc->dev, len, GFP_KERNEL); - if (!name) - return -ENOMEM; + if (!name) { + err = -ENOMEM; + goto out_remove; + } snprintf(name, len, "%s:bank%d", dev_name(pc->dev), i); @@ -1326,11 +1330,14 @@ static int bcm2835_pinctrl_probe(struct platform_device *pdev) err = gpiochip_add_data(&pc->gpio_chip, pc); if (err) { dev_err(dev, "could not add GPIO chip\n"); - pinctrl_remove_gpio_range(pc->pctl_dev, &pc->gpio_range); - return err; + goto out_remove; } return 0; + +out_remove: + pinctrl_remove_gpio_range(pc->pctl_dev, &pc->gpio_range); + return err; } static struct platform_driver bcm2835_pinctrl_driver = { diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index abffda1fd51e..1d5818269076 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -1471,8 +1471,9 @@ static void chv_gpio_irq_handler(struct irq_desc *desc) offset = cctx->intr_lines[intr_line]; if (offset == CHV_INVALID_HWIRQ) { - dev_err(dev, "interrupt on unused interrupt line %u\n", intr_line); - continue; + dev_warn_once(dev, "interrupt on unmapped interrupt line %u\n", intr_line); + /* Some boards expect hwirq 0 to trigger in this case */ + offset = 0; } generic_handle_domain_irq(gc->irq.domain, offset); diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index 85750974d182..826d494f3cc6 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -451,8 +451,8 @@ static void intel_gpio_set_gpio_mode(void __iomem *padcfg0) value &= ~PADCFG0_PMODE_MASK; value |= PADCFG0_PMODE_GPIO; - /* Disable input and output buffers */ - value |= PADCFG0_GPIORXDIS; + /* Disable TX buffer and enable RX (this will be input) */ + value &= ~PADCFG0_GPIORXDIS; value |= PADCFG0_GPIOTXDIS; /* Disable SCI/SMI/NMI generation */ @@ -497,9 +497,6 @@ static int intel_gpio_request_enable(struct pinctrl_dev *pctldev, intel_gpio_set_gpio_mode(padcfg0); - /* Disable TX buffer and enable RX (this will be input) */ - __intel_gpio_set_direction(padcfg0, true); - raw_spin_unlock_irqrestore(&pctrl->lock, flags); return 0; @@ -1115,9 +1112,6 @@ static int intel_gpio_irq_type(struct irq_data *d, unsigned int type) intel_gpio_set_gpio_mode(reg); - /* Disable TX buffer and enable RX (this will be input) */ - __intel_gpio_set_direction(reg, true); - value = readl(reg); value &= ~(PADCFG0_RXEVCFG_MASK | PADCFG0_RXINV); @@ -1216,6 +1210,39 @@ static irqreturn_t intel_gpio_irq(int irq, void *data) return IRQ_RETVAL(ret); } +static void intel_gpio_irq_init(struct intel_pinctrl *pctrl) +{ + int i; + + for (i = 0; i < pctrl->ncommunities; i++) { + const struct intel_community *community; + void __iomem *base; + unsigned int gpp; + + community = &pctrl->communities[i]; + base = community->regs; + + for (gpp = 0; gpp < community->ngpps; gpp++) { + /* Mask and clear all interrupts */ + writel(0, base + community->ie_offset + gpp * 4); + writel(0xffff, base + community->is_offset + gpp * 4); + } + } +} + +static int intel_gpio_irq_init_hw(struct gpio_chip *gc) +{ + struct intel_pinctrl *pctrl = gpiochip_get_data(gc); + + /* + * Make sure the interrupt lines are in a proper state before + * further configuration. + */ + intel_gpio_irq_init(pctrl); + + return 0; +} + static int intel_gpio_add_community_ranges(struct intel_pinctrl *pctrl, const struct intel_community *community) { @@ -1320,6 +1347,7 @@ static int intel_gpio_probe(struct intel_pinctrl *pctrl, int irq) girq->num_parents = 0; girq->default_type = IRQ_TYPE_NONE; girq->handler = handle_bad_irq; + girq->init_hw = intel_gpio_irq_init_hw; ret = devm_gpiochip_add_data(pctrl->dev, &pctrl->chip, pctrl); if (ret) { @@ -1695,26 +1723,6 @@ int intel_pinctrl_suspend_noirq(struct device *dev) } EXPORT_SYMBOL_GPL(intel_pinctrl_suspend_noirq); -static void intel_gpio_irq_init(struct intel_pinctrl *pctrl) -{ - size_t i; - - for (i = 0; i < pctrl->ncommunities; i++) { - const struct intel_community *community; - void __iomem *base; - unsigned int gpp; - - community = &pctrl->communities[i]; - base = community->regs; - - for (gpp = 0; gpp < community->ngpps; gpp++) { - /* Mask and clear all interrupts */ - writel(0, base + community->ie_offset + gpp * 4); - writel(0xffff, base + community->is_offset + gpp * 4); - } - } -} - static bool intel_gpio_update_reg(void __iomem *reg, u32 mask, u32 value) { u32 curr, updated; diff --git a/drivers/pinctrl/pinctrl-microchip-sgpio.c b/drivers/pinctrl/pinctrl-microchip-sgpio.c index 8e081c90bdb2..639f1130e989 100644 --- a/drivers/pinctrl/pinctrl-microchip-sgpio.c +++ b/drivers/pinctrl/pinctrl-microchip-sgpio.c @@ -137,7 +137,8 @@ static inline int sgpio_addr_to_pin(struct sgpio_priv *priv, int port, int bit) static inline u32 sgpio_get_addr(struct sgpio_priv *priv, u32 rno, u32 off) { - return priv->properties->regoff[rno] + off; + return (priv->properties->regoff[rno] + off) * + regmap_get_reg_stride(priv->regs); } static u32 sgpio_readl(struct sgpio_priv *priv, u32 rno, u32 off) diff --git a/drivers/pinctrl/pinctrl-thunderbay.c b/drivers/pinctrl/pinctrl-thunderbay.c index b5b47f4dd774..79d44bca039e 100644 --- a/drivers/pinctrl/pinctrl-thunderbay.c +++ b/drivers/pinctrl/pinctrl-thunderbay.c @@ -773,63 +773,42 @@ static int thunderbay_build_groups(struct thunderbay_pinctrl *tpc) static int thunderbay_add_functions(struct thunderbay_pinctrl *tpc, struct function_desc *funcs) { - struct function_desc *function = funcs; int i; /* Assign the groups for each function */ - for (i = 0; i < tpc->soc->npins; i++) { - const struct pinctrl_pin_desc *pin_info = thunderbay_pins + i; - struct thunderbay_mux_desc *pin_mux = pin_info->drv_data; - - while (pin_mux->name) { - const char **grp; - int j, grp_num, match = 0; - size_t grp_size; - struct function_desc *func; - - for (j = 0; j < tpc->nfuncs; j++) { - if (!strcmp(pin_mux->name, function[j].name)) { - match = 1; - break; - } - } - - if (!match) - return -EINVAL; - - func = function + j; - grp_num = func->num_group_names; - grp_size = sizeof(*func->group_names); - - if (!func->group_names) { - func->group_names = devm_kcalloc(tpc->dev, - grp_num, - grp_size, - GFP_KERNEL); - if (!func->group_names) { - kfree(func); - return -ENOMEM; - } + for (i = 0; i < tpc->nfuncs; i++) { + struct function_desc *func = &funcs[i]; + const char **group_names; + unsigned int grp_idx = 0; + int j; + + group_names = devm_kcalloc(tpc->dev, func->num_group_names, + sizeof(*group_names), GFP_KERNEL); + if (!group_names) + return -ENOMEM; + + for (j = 0; j < tpc->soc->npins; j++) { + const struct pinctrl_pin_desc *pin_info = &thunderbay_pins[j]; + struct thunderbay_mux_desc *pin_mux; + + for (pin_mux = pin_info->drv_data; pin_mux->name; pin_mux++) { + if (!strcmp(pin_mux->name, func->name)) + group_names[grp_idx++] = pin_info->name; } - - grp = func->group_names; - while (*grp) - grp++; - - *grp = pin_info->name; - pin_mux++; } + + func->group_names = group_names; } /* Add all functions */ for (i = 0; i < tpc->nfuncs; i++) { pinmux_generic_add_function(tpc->pctrl, - function[i].name, - function[i].group_names, - function[i].num_group_names, - function[i].data); + funcs[i].name, + funcs[i].group_names, + funcs[i].num_group_names, + funcs[i].data); } - kfree(function); + kfree(funcs); return 0; } @@ -839,27 +818,30 @@ static int thunderbay_build_functions(struct thunderbay_pinctrl *tpc) void *ptr; int pin; - /* Total number of functions is unknown at this point. Allocate first. */ + /* + * Allocate maximum possible number of functions. Assume every pin + * being part of 8 (hw maximum) globally unique muxes. + */ tpc->nfuncs = 0; thunderbay_funcs = kcalloc(tpc->soc->npins * 8, sizeof(*thunderbay_funcs), GFP_KERNEL); if (!thunderbay_funcs) return -ENOMEM; - /* Find total number of functions and each's properties */ + /* Setup 1 function for each unique mux */ for (pin = 0; pin < tpc->soc->npins; pin++) { const struct pinctrl_pin_desc *pin_info = thunderbay_pins + pin; - struct thunderbay_mux_desc *pin_mux = pin_info->drv_data; + struct thunderbay_mux_desc *pin_mux; - while (pin_mux->name) { - struct function_desc *func = thunderbay_funcs; + for (pin_mux = pin_info->drv_data; pin_mux->name; pin_mux++) { + struct function_desc *func; - while (func->name) { + /* Check if we already have function for this mux */ + for (func = thunderbay_funcs; func->name; func++) { if (!strcmp(pin_mux->name, func->name)) { func->num_group_names++; break; } - func++; } if (!func->name) { @@ -868,8 +850,6 @@ static int thunderbay_build_functions(struct thunderbay_pinctrl *tpc) func->data = (int *)&pin_mux->mode; tpc->nfuncs++; } - - pin_mux++; } } diff --git a/drivers/pinctrl/pinctrl-zynqmp.c b/drivers/pinctrl/pinctrl-zynqmp.c index 42da6bd399ee..e14012209992 100644 --- a/drivers/pinctrl/pinctrl-zynqmp.c +++ b/drivers/pinctrl/pinctrl-zynqmp.c @@ -809,7 +809,6 @@ static int zynqmp_pinctrl_prepare_pin_desc(struct device *dev, unsigned int *npins) { struct pinctrl_pin_desc *pins, *pin; - char **pin_names; int ret; int i; @@ -821,14 +820,13 @@ static int zynqmp_pinctrl_prepare_pin_desc(struct device *dev, if (!pins) return -ENOMEM; - pin_names = devm_kasprintf_strarray(dev, ZYNQMP_PIN_PREFIX, *npins); - if (IS_ERR(pin_names)) - return PTR_ERR(pin_names); - for (i = 0; i < *npins; i++) { pin = &pins[i]; pin->number = i; - pin->name = pin_names[i]; + pin->name = devm_kasprintf(dev, GFP_KERNEL, "%s%d", + ZYNQMP_PIN_PREFIX, i); + if (!pin->name) + return -ENOMEM; } *zynqmp_pins = pins; diff --git a/drivers/pinctrl/sunxi/pinctrl-sun50i-h616.c b/drivers/pinctrl/sunxi/pinctrl-sun50i-h616.c index ce1917e230f4..152b71226a80 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sun50i-h616.c +++ b/drivers/pinctrl/sunxi/pinctrl-sun50i-h616.c @@ -363,16 +363,16 @@ static const struct sunxi_desc_pin h616_pins[] = { SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), SUNXI_FUNCTION(0x2, "uart2"), /* CTS */ - SUNXI_FUNCTION(0x3, "i2s3"), /* DO0 */ + SUNXI_FUNCTION(0x3, "i2s3_dout0"), /* DO0 */ SUNXI_FUNCTION(0x4, "spi1"), /* MISO */ - SUNXI_FUNCTION(0x5, "i2s3"), /* DI1 */ + SUNXI_FUNCTION(0x5, "i2s3_din1"), /* DI1 */ SUNXI_FUNCTION_IRQ_BANK(0x6, 6, 8)), /* PH_EINT8 */ SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 9), SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), - SUNXI_FUNCTION(0x3, "i2s3"), /* DI0 */ + SUNXI_FUNCTION(0x3, "i2s3_din0"), /* DI0 */ SUNXI_FUNCTION(0x4, "spi1"), /* CS1 */ - SUNXI_FUNCTION(0x3, "i2s3"), /* DO1 */ + SUNXI_FUNCTION(0x5, "i2s3_dout1"), /* DO1 */ SUNXI_FUNCTION_IRQ_BANK(0x6, 6, 9)), /* PH_EINT9 */ SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 10), SUNXI_FUNCTION(0x0, "gpio_in"), diff --git a/drivers/platform/surface/Kconfig b/drivers/platform/surface/Kconfig index 5f0578e25f71..463f1ec5c14e 100644 --- a/drivers/platform/surface/Kconfig +++ b/drivers/platform/surface/Kconfig @@ -5,6 +5,7 @@ menuconfig SURFACE_PLATFORMS bool "Microsoft Surface Platform-Specific Device Drivers" + depends on ARM64 || X86 || COMPILE_TEST default y help Say Y here to get to see options for platform-specific device drivers diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index f794343d6aaa..4c72ba68b315 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -124,9 +124,10 @@ struct amd_pmc_dev { u32 cpu_id; u32 active_ips; /* SMU version information */ - u16 major; - u16 minor; - u16 rev; + u8 smu_program; + u8 major; + u8 minor; + u8 rev; struct device *dev; struct pci_dev *rdev; struct mutex lock; /* generic mutex lock */ @@ -180,11 +181,13 @@ static int amd_pmc_get_smu_version(struct amd_pmc_dev *dev) if (rc) return rc; - dev->major = (val >> 16) & GENMASK(15, 0); + dev->smu_program = (val >> 24) & GENMASK(7, 0); + dev->major = (val >> 16) & GENMASK(7, 0); dev->minor = (val >> 8) & GENMASK(7, 0); dev->rev = (val >> 0) & GENMASK(7, 0); - dev_dbg(dev->dev, "SMU version is %u.%u.%u\n", dev->major, dev->minor, dev->rev); + dev_dbg(dev->dev, "SMU program %u version is %u.%u.%u\n", + dev->smu_program, dev->major, dev->minor, dev->rev); return 0; } @@ -226,7 +229,7 @@ static int amd_pmc_stb_debugfs_release(struct inode *inode, struct file *filp) return 0; } -const struct file_operations amd_pmc_stb_debugfs_fops = { +static const struct file_operations amd_pmc_stb_debugfs_fops = { .owner = THIS_MODULE, .open = amd_pmc_stb_debugfs_open, .read = amd_pmc_stb_debugfs_read, diff --git a/drivers/platform/x86/asus-tf103c-dock.c b/drivers/platform/x86/asus-tf103c-dock.c index d4ef8f362ee6..6fd0c9fea82d 100644 --- a/drivers/platform/x86/asus-tf103c-dock.c +++ b/drivers/platform/x86/asus-tf103c-dock.c @@ -250,7 +250,7 @@ static int tf103c_dock_hid_raw_request(struct hid_device *hid, u8 reportnum, return 0; } -struct hid_ll_driver tf103c_dock_hid_ll_driver = { +static struct hid_ll_driver tf103c_dock_hid_ll_driver = { .parse = tf103c_dock_hid_parse, .start = tf103c_dock_hid_start, .stop = tf103c_dock_hid_stop, @@ -921,7 +921,7 @@ static int __maybe_unused tf103c_dock_resume(struct device *dev) return 0; } -SIMPLE_DEV_PM_OPS(tf103c_dock_pm_ops, tf103c_dock_suspend, tf103c_dock_resume); +static SIMPLE_DEV_PM_OPS(tf103c_dock_pm_ops, tf103c_dock_suspend, tf103c_dock_resume); static const struct acpi_device_id tf103c_dock_acpi_match[] = { {"NPCE69A"}, diff --git a/drivers/platform/x86/intel/crystal_cove_charger.c b/drivers/platform/x86/intel/crystal_cove_charger.c index 0374bc742513..e4299cfa2205 100644 --- a/drivers/platform/x86/intel/crystal_cove_charger.c +++ b/drivers/platform/x86/intel/crystal_cove_charger.c @@ -17,6 +17,7 @@ #include <linux/regmap.h> #define CHGRIRQ_REG 0x0a +#define MCHGRIRQ_REG 0x17 struct crystal_cove_charger_data { struct mutex buslock; /* irq_bus_lock */ @@ -25,8 +26,8 @@ struct crystal_cove_charger_data { struct irq_domain *irq_domain; int irq; int charger_irq; - bool irq_enabled; - bool irq_is_enabled; + u8 mask; + u8 new_mask; }; static irqreturn_t crystal_cove_charger_irq(int irq, void *data) @@ -53,13 +54,9 @@ static void crystal_cove_charger_irq_bus_sync_unlock(struct irq_data *data) { struct crystal_cove_charger_data *charger = irq_data_get_irq_chip_data(data); - if (charger->irq_is_enabled != charger->irq_enabled) { - if (charger->irq_enabled) - enable_irq(charger->irq); - else - disable_irq(charger->irq); - - charger->irq_is_enabled = charger->irq_enabled; + if (charger->mask != charger->new_mask) { + regmap_write(charger->regmap, MCHGRIRQ_REG, charger->new_mask); + charger->mask = charger->new_mask; } mutex_unlock(&charger->buslock); @@ -69,14 +66,14 @@ static void crystal_cove_charger_irq_unmask(struct irq_data *data) { struct crystal_cove_charger_data *charger = irq_data_get_irq_chip_data(data); - charger->irq_enabled = true; + charger->new_mask &= ~BIT(data->hwirq); } static void crystal_cove_charger_irq_mask(struct irq_data *data) { struct crystal_cove_charger_data *charger = irq_data_get_irq_chip_data(data); - charger->irq_enabled = false; + charger->new_mask |= BIT(data->hwirq); } static void crystal_cove_charger_rm_irq_domain(void *data) @@ -130,10 +127,13 @@ static int crystal_cove_charger_probe(struct platform_device *pdev) irq_set_nested_thread(charger->charger_irq, true); irq_set_noprobe(charger->charger_irq); + /* Mask the single 2nd level IRQ before enabling the 1st level IRQ */ + charger->mask = charger->new_mask = BIT(0); + regmap_write(charger->regmap, MCHGRIRQ_REG, charger->mask); + ret = devm_request_threaded_irq(&pdev->dev, charger->irq, NULL, crystal_cove_charger_irq, - IRQF_ONESHOT | IRQF_NO_AUTOEN, - KBUILD_MODNAME, charger); + IRQF_ONESHOT, KBUILD_MODNAME, charger); if (ret) return dev_err_probe(&pdev->dev, ret, "requesting irq\n"); diff --git a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c index c9a85eb2e860..e8424e70d81d 100644 --- a/drivers/platform/x86/intel/speed_select_if/isst_if_common.c +++ b/drivers/platform/x86/intel/speed_select_if/isst_if_common.c @@ -596,7 +596,10 @@ static long isst_if_def_ioctl(struct file *file, unsigned int cmd, return ret; } -static DEFINE_MUTEX(punit_misc_dev_lock); +/* Lock to prevent module registration when already opened by user space */ +static DEFINE_MUTEX(punit_misc_dev_open_lock); +/* Lock to allow one share misc device for all ISST interace */ +static DEFINE_MUTEX(punit_misc_dev_reg_lock); static int misc_usage_count; static int misc_device_ret; static int misc_device_open; @@ -606,7 +609,7 @@ static int isst_if_open(struct inode *inode, struct file *file) int i, ret = 0; /* Fail open, if a module is going away */ - mutex_lock(&punit_misc_dev_lock); + mutex_lock(&punit_misc_dev_open_lock); for (i = 0; i < ISST_IF_DEV_MAX; ++i) { struct isst_if_cmd_cb *cb = &punit_callbacks[i]; @@ -628,7 +631,7 @@ static int isst_if_open(struct inode *inode, struct file *file) } else { misc_device_open++; } - mutex_unlock(&punit_misc_dev_lock); + mutex_unlock(&punit_misc_dev_open_lock); return ret; } @@ -637,7 +640,7 @@ static int isst_if_relase(struct inode *inode, struct file *f) { int i; - mutex_lock(&punit_misc_dev_lock); + mutex_lock(&punit_misc_dev_open_lock); misc_device_open--; for (i = 0; i < ISST_IF_DEV_MAX; ++i) { struct isst_if_cmd_cb *cb = &punit_callbacks[i]; @@ -645,7 +648,7 @@ static int isst_if_relase(struct inode *inode, struct file *f) if (cb->registered) module_put(cb->owner); } - mutex_unlock(&punit_misc_dev_lock); + mutex_unlock(&punit_misc_dev_open_lock); return 0; } @@ -662,6 +665,43 @@ static struct miscdevice isst_if_char_driver = { .fops = &isst_if_char_driver_ops, }; +static int isst_misc_reg(void) +{ + mutex_lock(&punit_misc_dev_reg_lock); + if (misc_device_ret) + goto unlock_exit; + + if (!misc_usage_count) { + misc_device_ret = isst_if_cpu_info_init(); + if (misc_device_ret) + goto unlock_exit; + + misc_device_ret = misc_register(&isst_if_char_driver); + if (misc_device_ret) { + isst_if_cpu_info_exit(); + goto unlock_exit; + } + } + misc_usage_count++; + +unlock_exit: + mutex_unlock(&punit_misc_dev_reg_lock); + + return misc_device_ret; +} + +static void isst_misc_unreg(void) +{ + mutex_lock(&punit_misc_dev_reg_lock); + if (misc_usage_count) + misc_usage_count--; + if (!misc_usage_count && !misc_device_ret) { + misc_deregister(&isst_if_char_driver); + isst_if_cpu_info_exit(); + } + mutex_unlock(&punit_misc_dev_reg_lock); +} + /** * isst_if_cdev_register() - Register callback for IOCTL * @device_type: The device type this callback handling. @@ -679,38 +719,31 @@ static struct miscdevice isst_if_char_driver = { */ int isst_if_cdev_register(int device_type, struct isst_if_cmd_cb *cb) { - if (misc_device_ret) - return misc_device_ret; + int ret; if (device_type >= ISST_IF_DEV_MAX) return -EINVAL; - mutex_lock(&punit_misc_dev_lock); + mutex_lock(&punit_misc_dev_open_lock); + /* Device is already open, we don't want to add new callbacks */ if (misc_device_open) { - mutex_unlock(&punit_misc_dev_lock); + mutex_unlock(&punit_misc_dev_open_lock); return -EAGAIN; } - if (!misc_usage_count) { - int ret; - - misc_device_ret = misc_register(&isst_if_char_driver); - if (misc_device_ret) - goto unlock_exit; - - ret = isst_if_cpu_info_init(); - if (ret) { - misc_deregister(&isst_if_char_driver); - misc_device_ret = ret; - goto unlock_exit; - } - } memcpy(&punit_callbacks[device_type], cb, sizeof(*cb)); punit_callbacks[device_type].registered = 1; - misc_usage_count++; -unlock_exit: - mutex_unlock(&punit_misc_dev_lock); + mutex_unlock(&punit_misc_dev_open_lock); - return misc_device_ret; + ret = isst_misc_reg(); + if (ret) { + /* + * No need of mutex as the misc device register failed + * as no one can open device yet. Hence no contention. + */ + punit_callbacks[device_type].registered = 0; + return ret; + } + return 0; } EXPORT_SYMBOL_GPL(isst_if_cdev_register); @@ -725,16 +758,12 @@ EXPORT_SYMBOL_GPL(isst_if_cdev_register); */ void isst_if_cdev_unregister(int device_type) { - mutex_lock(&punit_misc_dev_lock); - misc_usage_count--; + isst_misc_unreg(); + mutex_lock(&punit_misc_dev_open_lock); punit_callbacks[device_type].registered = 0; if (device_type == ISST_IF_DEV_MBOX) isst_delete_hash(); - if (!misc_usage_count && !misc_device_ret) { - misc_deregister(&isst_if_char_driver); - isst_if_cpu_info_exit(); - } - mutex_unlock(&punit_misc_dev_lock); + mutex_unlock(&punit_misc_dev_open_lock); } EXPORT_SYMBOL_GPL(isst_if_cdev_unregister); diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 098180fb1cfc..bd045486b933 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -8679,9 +8679,10 @@ static const struct attribute_group fan_driver_attr_group = { .attrs = fan_driver_attributes, }; -#define TPACPI_FAN_Q1 0x0001 /* Unitialized HFSP */ -#define TPACPI_FAN_2FAN 0x0002 /* EC 0x31 bit 0 selects fan2 */ -#define TPACPI_FAN_2CTL 0x0004 /* selects fan2 control */ +#define TPACPI_FAN_Q1 0x0001 /* Uninitialized HFSP */ +#define TPACPI_FAN_2FAN 0x0002 /* EC 0x31 bit 0 selects fan2 */ +#define TPACPI_FAN_2CTL 0x0004 /* selects fan2 control */ +#define TPACPI_FAN_NOFAN 0x0008 /* no fan available */ static const struct tpacpi_quirk fan_quirk_table[] __initconst = { TPACPI_QEC_IBM('1', 'Y', TPACPI_FAN_Q1), @@ -8702,6 +8703,7 @@ static const struct tpacpi_quirk fan_quirk_table[] __initconst = { TPACPI_Q_LNV3('N', '4', '0', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (4nd gen) */ TPACPI_Q_LNV3('N', '3', '0', TPACPI_FAN_2CTL), /* P15 (1st gen) / P15v (1st gen) */ TPACPI_Q_LNV3('N', '3', '2', TPACPI_FAN_2CTL), /* X1 Carbon (9th gen) */ + TPACPI_Q_LNV3('N', '1', 'O', TPACPI_FAN_NOFAN), /* X1 Tablet (2nd gen) */ }; static int __init fan_init(struct ibm_init_struct *iibm) @@ -8730,6 +8732,11 @@ static int __init fan_init(struct ibm_init_struct *iibm) quirks = tpacpi_check_quirks(fan_quirk_table, ARRAY_SIZE(fan_quirk_table)); + if (quirks & TPACPI_FAN_NOFAN) { + pr_info("No integrated ThinkPad fan available\n"); + return -ENODEV; + } + if (gfan_handle) { /* 570, 600e/x, 770e, 770x */ fan_status_access_mode = TPACPI_FAN_RD_ACPI_GFAN; @@ -10112,6 +10119,9 @@ static struct ibm_struct proxsensor_driver_data = { #define DYTC_CMD_MMC_GET 8 /* To get current MMC function and mode */ #define DYTC_CMD_RESET 0x1ff /* To reset back to default */ +#define DYTC_CMD_FUNC_CAP 3 /* To get DYTC capabilities */ +#define DYTC_FC_MMC 27 /* MMC Mode supported */ + #define DYTC_GET_FUNCTION_BIT 8 /* Bits 8-11 - function setting */ #define DYTC_GET_MODE_BIT 12 /* Bits 12-15 - mode setting */ @@ -10324,6 +10334,15 @@ static int tpacpi_dytc_profile_init(struct ibm_init_struct *iibm) if (dytc_version < 5) return -ENODEV; + /* Check what capabilities are supported. Currently MMC is needed */ + err = dytc_command(DYTC_CMD_FUNC_CAP, &output); + if (err) + return err; + if (!(output & BIT(DYTC_FC_MMC))) { + dbg_printk(TPACPI_DBG_INIT, " DYTC MMC mode not supported\n"); + return -ENODEV; + } + dbg_printk(TPACPI_DBG_INIT, "DYTC version %d: thermal mode available\n", dytc_version); /* diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 494f23052678..bc97bfa8e8a6 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -770,6 +770,21 @@ static const struct ts_dmi_data predia_basic_data = { .properties = predia_basic_props, }; +static const struct property_entry rwc_nanote_p8_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-y", 46), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1728), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1140), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-rwc-nanote-p8.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + { } +}; + +static const struct ts_dmi_data rwc_nanote_p8_data = { + .acpi_name = "MSSL1680:00", + .properties = rwc_nanote_p8_props, +}; + static const struct property_entry schneider_sct101ctm_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1715), PROPERTY_ENTRY_U32("touchscreen-size-y", 1140), @@ -1395,6 +1410,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* RWC NANOTE P8 */ + .driver_data = (void *)&rwc_nanote_p8_data, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Default string"), + DMI_MATCH(DMI_PRODUCT_NAME, "AY07J"), + DMI_MATCH(DMI_PRODUCT_SKU, "0001") + }, + }, + { /* Schneider SCT101CTM */ .driver_data = (void *)&schneider_sct101ctm_data, .matches = { diff --git a/drivers/platform/x86/x86-android-tablets.c b/drivers/platform/x86/x86-android-tablets.c index 3ba63ad91b28..9360a8a92486 100644 --- a/drivers/platform/x86/x86-android-tablets.c +++ b/drivers/platform/x86/x86-android-tablets.c @@ -26,6 +26,7 @@ #include <linux/string.h> /* For gpio_get_desc() which is EXPORT_SYMBOL_GPL() */ #include "../../gpio/gpiolib.h" +#include "../../gpio/gpiolib-acpi.h" /* * Helper code to get Linux IRQ numbers given a description of the IRQ source @@ -47,7 +48,7 @@ struct x86_acpi_irq_data { int polarity; /* ACPI_ACTIVE_HIGH / ACPI_ACTIVE_LOW / ACPI_ACTIVE_BOTH */ }; -static int x86_acpi_irq_helper_gpiochip_find(struct gpio_chip *gc, void *data) +static int gpiochip_find_match_label(struct gpio_chip *gc, void *data) { return gc->label && !strcmp(gc->label, data); } @@ -73,7 +74,7 @@ static int x86_acpi_irq_helper_get(const struct x86_acpi_irq_data *data) return irq; case X86_ACPI_IRQ_TYPE_GPIOINT: /* Like acpi_dev_gpio_irq_get(), but without parsing ACPI resources */ - chip = gpiochip_find(data->chip, x86_acpi_irq_helper_gpiochip_find); + chip = gpiochip_find(data->chip, gpiochip_find_match_label); if (!chip) { pr_err("error cannot find GPIO chip %s\n", data->chip); return -ENODEV; @@ -143,14 +144,17 @@ struct x86_serdev_info { }; struct x86_dev_info { + char *invalid_aei_gpiochip; const char * const *modules; - struct gpiod_lookup_table **gpiod_lookup_tables; + struct gpiod_lookup_table * const *gpiod_lookup_tables; const struct x86_i2c_client_info *i2c_client_info; const struct platform_device_info *pdev_info; const struct x86_serdev_info *serdev_info; int i2c_client_count; int pdev_count; int serdev_count; + int (*init)(void); + void (*exit)(void); }; /* Generic / shared bq24190 settings */ @@ -187,8 +191,8 @@ static struct bq24190_platform_data bq24190_pdata = { }; static const char * const bq24190_modules[] __initconst = { - "crystal_cove_charger", /* For the bq24190 IRQ */ - "bq24190_charger", /* For the Vbus regulator for intel-int3496 */ + "intel_crystal_cove_charger", /* For the bq24190 IRQ */ + "bq24190_charger", /* For the Vbus regulator for intel-int3496 */ NULL }; @@ -302,7 +306,7 @@ static struct gpiod_lookup_table asus_me176c_goodix_gpios = { }, }; -static struct gpiod_lookup_table *asus_me176c_gpios[] = { +static struct gpiod_lookup_table * const asus_me176c_gpios[] = { &int3496_gpo2_pin22_gpios, &asus_me176c_goodix_gpios, NULL @@ -317,6 +321,7 @@ static const struct x86_dev_info asus_me176c_info __initconst = { .serdev_count = ARRAY_SIZE(asus_me176c_serdevs), .gpiod_lookup_tables = asus_me176c_gpios, .modules = bq24190_modules, + .invalid_aei_gpiochip = "INT33FC:02", }; /* Asus TF103C tablets have an Android factory img with everything hardcoded */ @@ -405,7 +410,7 @@ static const struct x86_i2c_client_info asus_tf103c_i2c_clients[] __initconst = }, }; -static struct gpiod_lookup_table *asus_tf103c_gpios[] = { +static struct gpiod_lookup_table * const asus_tf103c_gpios[] = { &int3496_gpo2_pin22_gpios, NULL }; @@ -417,6 +422,7 @@ static const struct x86_dev_info asus_tf103c_info __initconst = { .pdev_count = ARRAY_SIZE(int3496_pdevs), .gpiod_lookup_tables = asus_tf103c_gpios, .modules = bq24190_modules, + .invalid_aei_gpiochip = "INT33FC:02", }; /* @@ -490,6 +496,39 @@ static const struct x86_dev_info chuwi_hi8_info __initconst = { .i2c_client_count = ARRAY_SIZE(chuwi_hi8_i2c_clients), }; +#define CZC_EC_EXTRA_PORT 0x68 +#define CZC_EC_ANDROID_KEYS 0x63 + +static int __init czc_p10t_init(void) +{ + /* + * The device boots up in "Windows 7" mode, when the home button sends a + * Windows specific key sequence (Left Meta + D) and the second button + * sends an unknown one while also toggling the Radio Kill Switch. + * This is a surprising behavior when the second button is labeled "Back". + * + * The vendor-supplied Android-x86 build switches the device to a "Android" + * mode by writing value 0x63 to the I/O port 0x68. This just seems to just + * set bit 6 on address 0x96 in the EC region; switching the bit directly + * seems to achieve the same result. It uses a "p10t_switcher" to do the + * job. It doesn't seem to be able to do anything else, and no other use + * of the port 0x68 is known. + * + * In the Android mode, the home button sends just a single scancode, + * which can be handled in Linux userspace more reasonably and the back + * button only sends a scancode without toggling the kill switch. + * The scancode can then be mapped either to Back or RF Kill functionality + * in userspace, depending on how the button is labeled on that particular + * model. + */ + outb(CZC_EC_ANDROID_KEYS, CZC_EC_EXTRA_PORT); + return 0; +} + +static const struct x86_dev_info czc_p10t __initconst = { + .init = czc_p10t_init, +}; + /* * Whitelabel (sold as various brands) TM800A550L tablets. * These tablet's DSDT contains a whole bunch of bogus ACPI I2C devices @@ -559,7 +598,7 @@ static struct gpiod_lookup_table whitelabel_tm800a550l_goodix_gpios = { }, }; -static struct gpiod_lookup_table *whitelabel_tm800a550l_gpios[] = { +static struct gpiod_lookup_table * const whitelabel_tm800a550l_gpios[] = { &whitelabel_tm800a550l_goodix_gpios, NULL }; @@ -642,6 +681,24 @@ static const struct dmi_system_id x86_android_tablet_ids[] __initconst = { .driver_data = (void *)&chuwi_hi8_info, }, { + /* CZC P10T */ + .ident = "CZC ODEON TPC-10 (\"P10T\")", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "CZC"), + DMI_MATCH(DMI_PRODUCT_NAME, "ODEON*TPC-10"), + }, + .driver_data = (void *)&czc_p10t, + }, + { + /* A variant of CZC P10T */ + .ident = "ViewSonic ViewPad 10", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ViewSonic"), + DMI_MATCH(DMI_PRODUCT_NAME, "VPAD10"), + }, + .driver_data = (void *)&czc_p10t, + }, + { /* Whitelabel (sold as various brands) TM800A550L */ .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), @@ -669,7 +726,8 @@ static int serdev_count; static struct i2c_client **i2c_clients; static struct platform_device **pdevs; static struct serdev_device **serdevs; -static struct gpiod_lookup_table **gpiod_lookup_tables; +static struct gpiod_lookup_table * const *gpiod_lookup_tables; +static void (*exit_handler)(void); static __init int x86_instantiate_i2c_client(const struct x86_dev_info *dev_info, int idx) @@ -787,6 +845,9 @@ static void x86_android_tablet_cleanup(void) kfree(i2c_clients); + if (exit_handler) + exit_handler(); + for (i = 0; gpiod_lookup_tables && gpiod_lookup_tables[i]; i++) gpiod_remove_lookup_table(gpiod_lookup_tables[i]); } @@ -795,6 +856,7 @@ static __init int x86_android_tablet_init(void) { const struct x86_dev_info *dev_info; const struct dmi_system_id *id; + struct gpio_chip *chip; int i, ret = 0; id = dmi_first_match(x86_android_tablet_ids); @@ -804,6 +866,20 @@ static __init int x86_android_tablet_init(void) dev_info = id->driver_data; /* + * The broken DSDTs on these devices often also include broken + * _AEI (ACPI Event Interrupt) handlers, disable these. + */ + if (dev_info->invalid_aei_gpiochip) { + chip = gpiochip_find(dev_info->invalid_aei_gpiochip, + gpiochip_find_match_label); + if (!chip) { + pr_err("error cannot find GPIO chip %s\n", dev_info->invalid_aei_gpiochip); + return -ENODEV; + } + acpi_gpiochip_free_interrupts(chip); + } + + /* * Since this runs from module_init() it cannot use -EPROBE_DEFER, * instead pre-load any modules which are listed as requirements. */ @@ -814,6 +890,15 @@ static __init int x86_android_tablet_init(void) for (i = 0; gpiod_lookup_tables && gpiod_lookup_tables[i]; i++) gpiod_add_lookup_table(gpiod_lookup_tables[i]); + if (dev_info->init) { + ret = dev_info->init(); + if (ret < 0) { + x86_android_tablet_cleanup(); + return ret; + } + exit_handler = dev_info->exit; + } + i2c_clients = kcalloc(dev_info->i2c_client_count, sizeof(*i2c_clients), GFP_KERNEL); if (!i2c_clients) { x86_android_tablet_cleanup(); @@ -865,6 +950,6 @@ static __init int x86_android_tablet_init(void) module_init(x86_android_tablet_init); module_exit(x86_android_tablet_cleanup); -MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com"); +MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>"); MODULE_DESCRIPTION("X86 Android tablets DSDT fixups driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/regulator/max20086-regulator.c b/drivers/regulator/max20086-regulator.c index fbc56b043071..b8bf76c170fe 100644 --- a/drivers/regulator/max20086-regulator.c +++ b/drivers/regulator/max20086-regulator.c @@ -7,6 +7,7 @@ #include <linux/err.h> #include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include <linux/i2c.h> #include <linux/module.h> #include <linux/regmap.h> @@ -140,7 +141,7 @@ static int max20086_parse_regulators_dt(struct max20086 *chip, bool *boot_on) node = of_get_child_by_name(chip->dev->of_node, "regulators"); if (!node) { dev_err(chip->dev, "regulators node not found\n"); - return PTR_ERR(node); + return -ENODEV; } for (i = 0; i < chip->info->num_outputs; ++i) 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/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c index c9a769b8594b..86c76211b3d3 100644 --- a/drivers/spi/spi-bcm-qspi.c +++ b/drivers/spi/spi-bcm-qspi.c @@ -585,7 +585,7 @@ static void bcm_qspi_chip_select(struct bcm_qspi *qspi, int cs) u32 rd = 0; u32 wr = 0; - if (qspi->base[CHIP_SELECT]) { + if (cs >= 0 && qspi->base[CHIP_SELECT]) { rd = bcm_qspi_read(qspi, CHIP_SELECT, 0); wr = (rd & ~0xff) | (1 << cs); if (rd == wr) diff --git a/drivers/spi/spi-meson-spicc.c b/drivers/spi/spi-meson-spicc.c index c208efeadd18..0bc7daa7afc8 100644 --- a/drivers/spi/spi-meson-spicc.c +++ b/drivers/spi/spi-meson-spicc.c @@ -693,6 +693,11 @@ static int meson_spicc_probe(struct platform_device *pdev) writel_relaxed(0, spicc->base + SPICC_INTREG); irq = platform_get_irq(pdev, 0); + if (irq < 0) { + ret = irq; + goto out_master; + } + ret = devm_request_irq(&pdev->dev, irq, meson_spicc_irq, 0, NULL, spicc); if (ret) { diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index a15de10ee286..753bd313e6fd 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -624,7 +624,7 @@ static irqreturn_t mtk_spi_interrupt(int irq, void *dev_id) else mdata->state = MTK_SPI_IDLE; - if (!master->can_dma(master, master->cur_msg->spi, trans)) { + if (!master->can_dma(master, NULL, trans)) { if (trans->rx_buf) { cnt = mdata->xfer_len / 4; ioread32_rep(mdata->base + SPI_RX_DATA_REG, diff --git a/drivers/spi/spi-stm32-qspi.c b/drivers/spi/spi-stm32-qspi.c index 514337c86d2c..ffdc55f87e82 100644 --- a/drivers/spi/spi-stm32-qspi.c +++ b/drivers/spi/spi-stm32-qspi.c @@ -688,7 +688,7 @@ static int stm32_qspi_probe(struct platform_device *pdev) struct resource *res; int ret, irq; - ctrl = spi_alloc_master(dev, sizeof(*qspi)); + ctrl = devm_spi_alloc_master(dev, sizeof(*qspi)); if (!ctrl) return -ENOMEM; @@ -697,58 +697,46 @@ static int stm32_qspi_probe(struct platform_device *pdev) res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "qspi"); qspi->io_base = devm_ioremap_resource(dev, res); - if (IS_ERR(qspi->io_base)) { - ret = PTR_ERR(qspi->io_base); - goto err_master_put; - } + if (IS_ERR(qspi->io_base)) + return PTR_ERR(qspi->io_base); qspi->phys_base = res->start; res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "qspi_mm"); qspi->mm_base = devm_ioremap_resource(dev, res); - if (IS_ERR(qspi->mm_base)) { - ret = PTR_ERR(qspi->mm_base); - goto err_master_put; - } + if (IS_ERR(qspi->mm_base)) + return PTR_ERR(qspi->mm_base); qspi->mm_size = resource_size(res); - if (qspi->mm_size > STM32_QSPI_MAX_MMAP_SZ) { - ret = -EINVAL; - goto err_master_put; - } + if (qspi->mm_size > STM32_QSPI_MAX_MMAP_SZ) + return -EINVAL; irq = platform_get_irq(pdev, 0); - if (irq < 0) { - ret = irq; - goto err_master_put; - } + if (irq < 0) + return irq; ret = devm_request_irq(dev, irq, stm32_qspi_irq, 0, dev_name(dev), qspi); if (ret) { dev_err(dev, "failed to request irq\n"); - goto err_master_put; + return ret; } init_completion(&qspi->data_completion); init_completion(&qspi->match_completion); qspi->clk = devm_clk_get(dev, NULL); - if (IS_ERR(qspi->clk)) { - ret = PTR_ERR(qspi->clk); - goto err_master_put; - } + if (IS_ERR(qspi->clk)) + return PTR_ERR(qspi->clk); qspi->clk_rate = clk_get_rate(qspi->clk); - if (!qspi->clk_rate) { - ret = -EINVAL; - goto err_master_put; - } + if (!qspi->clk_rate) + return -EINVAL; ret = clk_prepare_enable(qspi->clk); if (ret) { dev_err(dev, "can not enable the clock\n"); - goto err_master_put; + return ret; } rstc = devm_reset_control_get_exclusive(dev, NULL); @@ -784,7 +772,7 @@ static int stm32_qspi_probe(struct platform_device *pdev) pm_runtime_enable(dev); pm_runtime_get_noresume(dev); - ret = devm_spi_register_master(dev, ctrl); + ret = spi_register_master(ctrl); if (ret) goto err_pm_runtime_free; @@ -806,8 +794,6 @@ err_dma_free: stm32_qspi_dma_free(qspi); err_clk_disable: clk_disable_unprepare(qspi->clk); -err_master_put: - spi_master_put(qspi->ctrl); return ret; } @@ -817,6 +803,7 @@ static int stm32_qspi_remove(struct platform_device *pdev) struct stm32_qspi *qspi = platform_get_drvdata(pdev); pm_runtime_get_sync(qspi->dev); + spi_unregister_master(qspi->ctrl); /* disable qspi */ writel_relaxed(0, qspi->io_base + QSPI_CR); stm32_qspi_dma_free(qspi); diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c index 9bd3fd1652f7..7fc24505a72c 100644 --- a/drivers/spi/spi-stm32.c +++ b/drivers/spi/spi-stm32.c @@ -221,7 +221,6 @@ struct stm32_spi; * time between frames (if driver has this functionality) * @set_number_of_data: optional routine to configure registers to desired * number of data (if driver has this functionality) - * @can_dma: routine to determine if the transfer is eligible for DMA use * @transfer_one_dma_start: routine to start transfer a single spi_transfer * using DMA * @dma_rx_cb: routine to call after DMA RX channel operation is complete @@ -232,7 +231,7 @@ struct stm32_spi; * @baud_rate_div_min: minimum baud rate divisor * @baud_rate_div_max: maximum baud rate divisor * @has_fifo: boolean to know if fifo is used for driver - * @has_startbit: boolean to know if start bit is used to start transfer + * @flags: compatible specific SPI controller flags used at registration time */ struct stm32_spi_cfg { const struct stm32_spi_regspec *regs; @@ -253,6 +252,7 @@ struct stm32_spi_cfg { unsigned int baud_rate_div_min; unsigned int baud_rate_div_max; bool has_fifo; + u16 flags; }; /** @@ -1722,6 +1722,7 @@ static const struct stm32_spi_cfg stm32f4_spi_cfg = { .baud_rate_div_min = STM32F4_SPI_BR_DIV_MIN, .baud_rate_div_max = STM32F4_SPI_BR_DIV_MAX, .has_fifo = false, + .flags = SPI_MASTER_MUST_TX, }; static const struct stm32_spi_cfg stm32h7_spi_cfg = { @@ -1854,7 +1855,7 @@ static int stm32_spi_probe(struct platform_device *pdev) master->prepare_message = stm32_spi_prepare_msg; master->transfer_one = stm32_spi_transfer_one; master->unprepare_message = stm32_spi_unprepare_msg; - master->flags = SPI_MASTER_MUST_TX; + master->flags = spi->cfg->flags; spi->dma_tx = dma_request_chan(spi->dev, "tx"); if (IS_ERR(spi->dma_tx)) { diff --git a/drivers/spi/spi-uniphier.c b/drivers/spi/spi-uniphier.c index 342ee8d2c476..cc0da4822231 100644 --- a/drivers/spi/spi-uniphier.c +++ b/drivers/spi/spi-uniphier.c @@ -726,7 +726,7 @@ static int uniphier_spi_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "failed to get TX DMA capacities: %d\n", ret); - goto out_disable_clk; + goto out_release_dma; } dma_tx_burst = caps.max_burst; } @@ -735,7 +735,7 @@ static int uniphier_spi_probe(struct platform_device *pdev) if (IS_ERR_OR_NULL(master->dma_rx)) { if (PTR_ERR(master->dma_rx) == -EPROBE_DEFER) { ret = -EPROBE_DEFER; - goto out_disable_clk; + goto out_release_dma; } master->dma_rx = NULL; dma_rx_burst = INT_MAX; @@ -744,7 +744,7 @@ static int uniphier_spi_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "failed to get RX DMA capacities: %d\n", ret); - goto out_disable_clk; + goto out_release_dma; } dma_rx_burst = caps.max_burst; } @@ -753,10 +753,20 @@ static int uniphier_spi_probe(struct platform_device *pdev) ret = devm_spi_register_master(&pdev->dev, master); if (ret) - goto out_disable_clk; + goto out_release_dma; return 0; +out_release_dma: + if (!IS_ERR_OR_NULL(master->dma_rx)) { + dma_release_channel(master->dma_rx); + master->dma_rx = NULL; + } + if (!IS_ERR_OR_NULL(master->dma_tx)) { + dma_release_channel(master->dma_tx); + master->dma_tx = NULL; + } + out_disable_clk: clk_disable_unprepare(priv->clk); 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/Makefile b/fs/Makefile index dab324aea08f..208a74e0b00e 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -96,7 +96,7 @@ obj-$(CONFIG_EXPORTFS) += exportfs/ obj-$(CONFIG_NFSD) += nfsd/ obj-$(CONFIG_LOCKD) += lockd/ obj-$(CONFIG_NLS) += nls/ -obj-$(CONFIG_UNICODE) += unicode/ +obj-y += unicode/ obj-$(CONFIG_SYSV_FS) += sysv/ obj-$(CONFIG_SMBFS_COMMON) += smbfs_common/ obj-$(CONFIG_CIFS) += cifs/ 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 71a3cdceaa03..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) @@ -2485,7 +2483,7 @@ struct ext4_filename { #ifdef CONFIG_FS_ENCRYPTION struct fscrypt_str crypto_buf; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) struct fscrypt_str cf_name; #endif }; @@ -2721,7 +2719,7 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb, struct ext4_group_desc *gdp); ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) extern int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, struct ext4_filename *fname); @@ -2754,7 +2752,7 @@ static inline int ext4_fname_setup_filename(struct inode *dir, ext4_fname_from_fscrypt_name(fname, &name); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) err = ext4_fname_setup_ci_filename(dir, iname, fname); #endif return err; @@ -2773,7 +2771,7 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir, ext4_fname_from_fscrypt_name(fname, &name); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname); #endif return err; @@ -2790,7 +2788,7 @@ static inline void ext4_fname_free_filename(struct ext4_filename *fname) fname->usr_fname = NULL; fname->disk_name.name = NULL; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) kfree(fname->cf_name.name); fname->cf_name.name = NULL; #endif @@ -2806,7 +2804,7 @@ static inline int ext4_fname_setup_filename(struct inode *dir, fname->disk_name.name = (unsigned char *) iname->name; fname->disk_name.len = iname->len; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) err = ext4_fname_setup_ci_filename(dir, iname, fname); #endif @@ -2822,7 +2820,7 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir, static inline void ext4_fname_free_filename(struct ext4_filename *fname) { -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) kfree(fname->cf_name.name); fname->cf_name.name = NULL; #endif @@ -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/hash.c b/fs/ext4/hash.c index f34f4176c1e7..147b5241dd94 100644 --- a/fs/ext4/hash.c +++ b/fs/ext4/hash.c @@ -290,7 +290,7 @@ static int __ext4fs_dirhash(const struct inode *dir, const char *name, int len, int ext4fs_dirhash(const struct inode *dir, const char *name, int len, struct dx_hash_info *hinfo) { -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) const struct unicode_map *um = dir->i_sb->s_encoding; int r, dlen; unsigned char *buff; 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 52c9bd154122..8cf0a924a49b 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1317,7 +1317,7 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block) dx_set_count(entries, count + 1); } -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* * Test whether a case-insensitive directory entry matches the filename * being searched for. If quick is set, assume the name being looked up @@ -1428,7 +1428,7 @@ static bool ext4_match(struct inode *parent, f.crypto_buf = fname->crypto_buf; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (parent->i_sb->s_encoding && IS_CASEFOLDED(parent) && (!IS_ENCRYPTED(parent) || fscrypt_has_encryption_key(parent))) { if (fname->cf_name.name) { @@ -1800,7 +1800,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi } } -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (!inode && IS_CASEFOLDED(dir)) { /* Eventually we want to call d_add_ci(dentry, NULL) * for negative dentries in the encoding case as @@ -2308,7 +2308,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, if (fscrypt_is_nokey_name(dentry)) return -ENOKEY; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (sb_has_strict_encoding(sb) && IS_CASEFOLDED(dir) && sb->s_encoding && utf8_validate(sb->s_encoding, &dentry->d_name)) return -EINVAL; @@ -3126,7 +3126,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry) ext4_fc_track_unlink(handle, dentry); retval = ext4_mark_inode_dirty(handle, dir); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* VFS negative dentries are incompatible with Encoding and * Case-insensitiveness. Eventually we'll want avoid * invalidating the dentries here, alongside with returning the @@ -3231,7 +3231,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) retval = __ext4_unlink(handle, dir, &dentry->d_name, d_inode(dentry)); if (!retval) ext4_fc_track_unlink(handle, dentry); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* VFS negative dentries are incompatible with Encoding and * Case-insensitiveness. Eventually we'll want avoid * invalidating the dentries here, alongside with returning the @@ -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 eee0d9ebfa6c..c5021ca0a28a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1301,7 +1301,7 @@ static void ext4_put_super(struct super_block *sb) kfree(sbi->s_blockgroup_lock); fs_put_dax(sbi->s_daxdev); fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif kfree(sbi); @@ -1961,7 +1961,7 @@ static const struct mount_opts { {Opt_err, 0, 0} }; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) static const struct ext4_sb_encodings { __u16 magic; char *name; @@ -3606,7 +3606,7 @@ int ext4_feature_set_ok(struct super_block *sb, int readonly) return 0; } -#ifndef CONFIG_UNICODE +#if !IS_ENABLED(CONFIG_UNICODE) if (ext4_has_feature_casefold(sb)) { ext4_msg(sb, KERN_ERR, "Filesystem with casefold feature cannot be " @@ -4610,7 +4610,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) if (err < 0) goto failed_mount; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (ext4_has_feature_casefold(sb) && !sb->s_encoding) { const struct ext4_sb_encodings *encoding_info; struct unicode_map *encoding; @@ -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; @@ -5514,7 +5514,7 @@ failed_mount: if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif @@ -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/sysfs.c b/fs/ext4/sysfs.c index f61e65ae27d8..d233c24ea342 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -309,7 +309,7 @@ EXT4_ATTR_FEATURE(meta_bg_resize); EXT4_ATTR_FEATURE(encryption); EXT4_ATTR_FEATURE(test_dummy_encryption_v2); #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) EXT4_ATTR_FEATURE(casefold); #endif #ifdef CONFIG_FS_VERITY @@ -317,7 +317,7 @@ EXT4_ATTR_FEATURE(verity); #endif EXT4_ATTR_FEATURE(metadata_csum_seed); EXT4_ATTR_FEATURE(fast_commit); -#if defined(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) +#if IS_ENABLED(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) EXT4_ATTR_FEATURE(encrypted_casefold); #endif @@ -329,7 +329,7 @@ static struct attribute *ext4_feat_attrs[] = { ATTR_LIST(encryption), ATTR_LIST(test_dummy_encryption_v2), #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) ATTR_LIST(casefold), #endif #ifdef CONFIG_FS_VERITY @@ -337,7 +337,7 @@ static struct attribute *ext4_feat_attrs[] = { #endif ATTR_LIST(metadata_csum_seed), ATTR_LIST(fast_commit), -#if defined(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) +#if IS_ENABLED(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) ATTR_LIST(encrypted_casefold), #endif NULL, 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/f2fs/dir.c b/fs/f2fs/dir.c index 1820e9c106f7..166f08623362 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -16,7 +16,7 @@ #include "xattr.h" #include <trace/events/f2fs.h> -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) extern struct kmem_cache *f2fs_cf_name_slab; #endif @@ -79,7 +79,7 @@ unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de) int f2fs_init_casefolded_name(const struct inode *dir, struct f2fs_filename *fname) { -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) struct super_block *sb = dir->i_sb; if (IS_CASEFOLDED(dir)) { @@ -174,7 +174,7 @@ void f2fs_free_filename(struct f2fs_filename *fname) kfree(fname->crypto_buf.name); fname->crypto_buf.name = NULL; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (fname->cf_name.name) { kmem_cache_free(f2fs_cf_name_slab, fname->cf_name.name); fname->cf_name.name = NULL; @@ -208,7 +208,7 @@ static struct f2fs_dir_entry *find_in_block(struct inode *dir, return f2fs_find_target_dentry(&d, fname, max_slots); } -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* * Test whether a case-insensitive directory entry matches the filename * being searched for. @@ -266,7 +266,7 @@ static inline int f2fs_match_name(const struct inode *dir, { struct fscrypt_name f; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (fname->cf_name.name) { struct qstr cf = FSTR_TO_QSTR(&fname->cf_name); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index eb22fa91c2b2..68b44015514f 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -488,7 +488,7 @@ struct f2fs_filename { */ struct fscrypt_str crypto_buf; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* * For casefolded directories: the casefolded name, but it's left NULL * if the original name is not valid Unicode, if the directory is both diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c index e3beac546c63..3cb1e7a24740 100644 --- a/fs/f2fs/hash.c +++ b/fs/f2fs/hash.c @@ -105,7 +105,7 @@ void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname) return; } -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (IS_CASEFOLDED(dir)) { /* * If the casefolded name is provided, hash it instead of the diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index a728a0af9ce0..5f213f05556d 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -561,7 +561,7 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, goto out_iput; } out_splice: -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (!inode && IS_CASEFOLDED(dir)) { /* Eventually we want to call d_add_ci(dentry, NULL) * for negative dentries in the encoding case as @@ -622,7 +622,7 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) goto fail; } f2fs_delete_entry(de, page, dir, inode); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* VFS negative dentries are incompatible with Encoding and * Case-insensitiveness. Eventually we'll want avoid * invalidating the dentries here, alongside with returning the diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 9683c80ff8c2..79773d322c47 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -46,7 +46,7 @@ static struct kmem_cache *fsync_entry_slab; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) extern struct kmem_cache *f2fs_cf_name_slab; #endif @@ -149,7 +149,7 @@ static int init_recovered_filename(const struct inode *dir, if (err) return err; f2fs_hash_filename(dir, fname); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* Case-sensitive match is fine for recovery */ kmem_cache_free(f2fs_cf_name_slab, fname->cf_name.name); fname->cf_name.name = NULL; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 76e6a3df9aba..baefd398ec1a 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -257,7 +257,7 @@ void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...) va_end(args); } -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) static const struct f2fs_sb_encodings { __u16 magic; char *name; @@ -1259,7 +1259,7 @@ default_check: return -EINVAL; } #endif -#ifndef CONFIG_UNICODE +#if !IS_ENABLED(CONFIG_UNICODE) if (f2fs_sb_has_casefold(sbi)) { f2fs_err(sbi, "Filesystem with casefold feature cannot be mounted without CONFIG_UNICODE"); @@ -1619,7 +1619,7 @@ static void f2fs_put_super(struct super_block *sb) f2fs_destroy_iostat(sbi); for (i = 0; i < NR_PAGE_TYPE; i++) kvfree(sbi->write_io[i]); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif kfree(sbi); @@ -3903,7 +3903,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) static int f2fs_setup_casefold(struct f2fs_sb_info *sbi) { -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (f2fs_sb_has_casefold(sbi) && !sbi->sb->s_encoding) { const struct f2fs_sb_encodings *encoding_info; struct unicode_map *encoding; @@ -4458,7 +4458,7 @@ free_bio_info: for (i = 0; i < NR_PAGE_TYPE; i++) kvfree(sbi->write_io[i]); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); sb->s_encoding = NULL; #endif diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index df406c16b2eb..8ac506671245 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -201,7 +201,7 @@ static ssize_t unusable_show(struct f2fs_attr *a, static ssize_t encoding_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) struct super_block *sb = sbi->sb; if (f2fs_sb_has_casefold(sbi)) @@ -778,7 +778,7 @@ F2FS_GENERAL_RO_ATTR(avg_vblocks); #ifdef CONFIG_FS_ENCRYPTION F2FS_FEATURE_RO_ATTR(encryption); F2FS_FEATURE_RO_ATTR(test_dummy_encryption_v2); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) F2FS_FEATURE_RO_ATTR(encrypted_casefold); #endif #endif /* CONFIG_FS_ENCRYPTION */ @@ -797,7 +797,7 @@ F2FS_FEATURE_RO_ATTR(lost_found); F2FS_FEATURE_RO_ATTR(verity); #endif F2FS_FEATURE_RO_ATTR(sb_checksum); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) F2FS_FEATURE_RO_ATTR(casefold); #endif F2FS_FEATURE_RO_ATTR(readonly); @@ -910,7 +910,7 @@ static struct attribute *f2fs_feat_attrs[] = { #ifdef CONFIG_FS_ENCRYPTION ATTR_LIST(encryption), ATTR_LIST(test_dummy_encryption_v2), -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) ATTR_LIST(encrypted_casefold), #endif #endif /* CONFIG_FS_ENCRYPTION */ @@ -929,7 +929,7 @@ static struct attribute *f2fs_feat_attrs[] = { ATTR_LIST(verity), #endif ATTR_LIST(sb_checksum), -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) ATTR_LIST(casefold), #endif ATTR_LIST(readonly), 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/libfs.c b/fs/libfs.c index ba7438ab9371..974125270a42 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -1379,7 +1379,7 @@ bool is_empty_dir_inode(struct inode *inode) (inode->i_op == &empty_dir_inode_operations); } -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* * Determine if the name of a dentry should be casefolded. * @@ -1473,7 +1473,7 @@ static const struct dentry_operations generic_encrypted_dentry_ops = { }; #endif -#if defined(CONFIG_FS_ENCRYPTION) && defined(CONFIG_UNICODE) +#if defined(CONFIG_FS_ENCRYPTION) && IS_ENABLED(CONFIG_UNICODE) static const struct dentry_operations generic_encrypted_ci_dentry_ops = { .d_hash = generic_ci_d_hash, .d_compare = generic_ci_d_compare, @@ -1508,10 +1508,10 @@ void generic_set_encrypted_ci_d_ops(struct dentry *dentry) #ifdef CONFIG_FS_ENCRYPTION bool needs_encrypt_ops = dentry->d_flags & DCACHE_NOKEY_NAME; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) bool needs_ci_ops = dentry->d_sb->s_encoding; #endif -#if defined(CONFIG_FS_ENCRYPTION) && defined(CONFIG_UNICODE) +#if defined(CONFIG_FS_ENCRYPTION) && IS_ENABLED(CONFIG_UNICODE) if (needs_encrypt_ops && needs_ci_ops) { d_set_d_op(dentry, &generic_encrypted_ci_dentry_ops); return; @@ -1523,7 +1523,7 @@ void generic_set_encrypted_ci_d_ops(struct dentry *dentry) return; } #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (needs_ci_ops) { d_set_d_op(dentry, &generic_ci_dentry_ops); return; diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index cb3a7512c33e..0a22a2faf552 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -179,19 +179,21 @@ nlm_delete_file(struct nlm_file *file) static int nlm_unlock_files(struct nlm_file *file) { struct file_lock lock; - struct file *f; + locks_init_lock(&lock); lock.fl_type = F_UNLCK; lock.fl_start = 0; lock.fl_end = OFFSET_MAX; - for (f = file->f_file[0]; f <= file->f_file[1]; f++) { - if (f && vfs_lock_file(f, F_SETLK, &lock, NULL) < 0) { - pr_warn("lockd: unlock failure in %s:%d\n", - __FILE__, __LINE__); - return 1; - } - } + if (file->f_file[O_RDONLY] && + vfs_lock_file(file->f_file[O_RDONLY], F_SETLK, &lock, NULL)) + goto out_err; + if (file->f_file[O_WRONLY] && + vfs_lock_file(file->f_file[O_WRONLY], F_SETLK, &lock, NULL)) + goto out_err; return 0; +out_err: + pr_warn("lockd: unlock failure in %s:%d\n", __FILE__, __LINE__); + return 1; } /* diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 72900b89cf84..32063733443d 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -4130,8 +4130,10 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, status = nfserr_clid_inuse; if (client_has_state(old) && !same_creds(&unconf->cl_cred, - &old->cl_cred)) + &old->cl_cred)) { + old = NULL; goto out; + } status = mark_client_expired_locked(old); if (status) { old = NULL; diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 1026f67b1d1e..2ff6bd85ba8f 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -701,9 +701,6 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, if (fanotify_is_perm_event(event->mask)) FANOTIFY_PERM(event)->fd = fd; - if (f) - fd_install(fd, f); - if (info_mode) { ret = copy_info_records_to_user(event, info, info_mode, pidfd, buf, count); @@ -711,6 +708,9 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, goto out_close_fd; } + if (f) + fd_install(fd, f); + return metadata.event_len; out_close_fd: diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index b193d08a3dc3..e040970408d4 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -145,7 +145,7 @@ static int ovl_copy_fileattr(struct inode *inode, struct path *old, if (err == -ENOTTY || err == -EINVAL) return 0; pr_warn("failed to retrieve lower fileattr (%pd2, err=%i)\n", - old, err); + old->dentry, err); return err; } @@ -157,7 +157,9 @@ static int ovl_copy_fileattr(struct inode *inode, struct path *old, */ if (oldfa.flags & OVL_PROT_FS_FLAGS_MASK) { err = ovl_set_protattr(inode, new->dentry, &oldfa); - if (err) + if (err == -EPERM) + pr_warn_once("copying fileattr: no xattr on upper\n"); + else if (err) return err; } @@ -167,8 +169,16 @@ static int ovl_copy_fileattr(struct inode *inode, struct path *old, err = ovl_real_fileattr_get(new, &newfa); if (err) { + /* + * Returning an error if upper doesn't support fileattr will + * result in a regression, so revert to the old behavior. + */ + if (err == -ENOTTY || err == -EINVAL) { + pr_warn_once("copying fileattr: no support on upper\n"); + return 0; + } pr_warn("failed to retrieve upper fileattr (%pd2, err=%i)\n", - new, err); + new->dentry, err); return err; } 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/unicode/Kconfig b/fs/unicode/Kconfig index 610d7bc05d6e..da786a687fdc 100644 --- a/fs/unicode/Kconfig +++ b/fs/unicode/Kconfig @@ -3,21 +3,13 @@ # UTF-8 normalization # config UNICODE - bool "UTF-8 normalization and casefolding support" + tristate "UTF-8 normalization and casefolding support" help Say Y here to enable UTF-8 NFD normalization and NFD+CF casefolding - support. - -config UNICODE_UTF8_DATA - tristate "UTF-8 normalization and casefolding tables" - depends on UNICODE - default UNICODE - help - This contains a large table of case foldings, which can be loaded as - a separate module if you say M here. To be on the safe side stick - to the default of Y. Saying N here makes no sense, if you do not want - utf8 casefolding support, disable CONFIG_UNICODE instead. + support. If you say M here the large table of case foldings will + be a separate loadable module that gets requested only when a file + system actually use it. config UNICODE_NORMALIZATION_SELFTEST tristate "Test UTF-8 normalization support" - depends on UNICODE_UTF8_DATA + depends on UNICODE diff --git a/fs/unicode/Makefile b/fs/unicode/Makefile index 2f9d9188852b..0cc87423de82 100644 --- a/fs/unicode/Makefile +++ b/fs/unicode/Makefile @@ -1,8 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_UNICODE) += unicode.o +ifneq ($(CONFIG_UNICODE),) +obj-y += unicode.o +endif +obj-$(CONFIG_UNICODE) += utf8data.o obj-$(CONFIG_UNICODE_NORMALIZATION_SELFTEST) += utf8-selftest.o -obj-$(CONFIG_UNICODE_UTF8_DATA) += utf8data.o unicode-y := utf8-norm.o utf8-core.o 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/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/fs.h b/include/linux/fs.h index f3daaea16554..e2d892b201b0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1483,7 +1483,7 @@ struct super_block { #ifdef CONFIG_FS_VERITY const struct fsverity_operations *s_vop; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) struct unicode_map *s_encoding; __u16 s_encoding_flags; #endif diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 8420fe504927..2be4dd7e90a9 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -46,8 +46,10 @@ struct vlan_hdr { * @h_vlan_encapsulated_proto: packet type ID or len */ struct vlan_ethhdr { - unsigned char h_dest[ETH_ALEN]; - unsigned char h_source[ETH_ALEN]; + struct_group(addrs, + unsigned char h_dest[ETH_ALEN]; + unsigned char h_source[ETH_ALEN]; + ); __be16 h_vlan_proto; __be16 h_vlan_TCI; __be16 h_vlan_encapsulated_proto; 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/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/linux/sched.h b/include/linux/sched.h index f5b2be39a78c..75ba8aa60248 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1680,7 +1680,6 @@ extern struct pid *cad_pid; #define PF_MEMALLOC 0x00000800 /* Allocating memory */ #define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */ #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ -#define PF_USED_ASYNC 0x00004000 /* Used async_schedule*(), used by module init */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ #define PF_FROZEN 0x00010000 /* Frozen for system suspend */ #define PF_KSWAPD 0x00020000 /* I am kswapd */ diff --git a/include/net/ax25.h b/include/net/ax25.h index 526e49589197..8221af1811df 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -239,6 +239,7 @@ typedef struct ax25_dev { #if defined(CONFIG_AX25_DAMA_SLAVE) || defined(CONFIG_AX25_DAMA_MASTER) ax25_dama_info dama; #endif + refcount_t refcount; } ax25_dev; typedef struct ax25_cb { @@ -293,6 +294,17 @@ static __inline__ void ax25_cb_put(ax25_cb *ax25) } } +static inline void ax25_dev_hold(ax25_dev *ax25_dev) +{ + refcount_inc(&ax25_dev->refcount); +} + +static inline void ax25_dev_put(ax25_dev *ax25_dev) +{ + if (refcount_dec_and_test(&ax25_dev->refcount)) { + kfree(ax25_dev); + } +} static inline __be16 ax25_type_trans(struct sk_buff *skb, struct net_device *dev) { skb->dev = dev; diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 937389e04c8e..87419f7f5421 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -350,7 +350,8 @@ static inline struct neighbour *neigh_create(struct neigh_table *tbl, return __neigh_create(tbl, pkey, dev, true); } void neigh_destroy(struct neighbour *neigh); -int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb); +int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb, + const bool immediate_ok); int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid); void __neigh_set_probe_once(struct neighbour *neigh); @@ -460,17 +461,24 @@ static inline struct neighbour * neigh_clone(struct neighbour *neigh) #define neigh_hold(n) refcount_inc(&(n)->refcnt) -static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) +static __always_inline int neigh_event_send_probe(struct neighbour *neigh, + struct sk_buff *skb, + const bool immediate_ok) { unsigned long now = jiffies; - + if (READ_ONCE(neigh->used) != now) WRITE_ONCE(neigh->used, now); - if (!(neigh->nud_state&(NUD_CONNECTED|NUD_DELAY|NUD_PROBE))) - return __neigh_event_send(neigh, skb); + if (!(neigh->nud_state & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE))) + return __neigh_event_send(neigh, skb, immediate_ok); return 0; } +static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) +{ + return neigh_event_send_probe(neigh, skb, true); +} + #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb) { 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..507ee1f2aa96 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1134,6 +1134,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_VM_GPA_BITS 207 #define KVM_CAP_XSAVE2 208 #define KVM_CAP_SYS_ATTRIBUTES 209 +#define KVM_CAP_PPC_AIL_MODE_3 210 #ifdef KVM_CAP_IRQ_ROUTING @@ -1624,9 +1625,6 @@ 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 +2046,7 @@ 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/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/linux/smc_diag.h b/include/uapi/linux/smc_diag.h index c7008d87f1a4..8cb3a6fef553 100644 --- a/include/uapi/linux/smc_diag.h +++ b/include/uapi/linux/smc_diag.h @@ -84,12 +84,11 @@ struct smc_diag_conninfo { /* SMC_DIAG_LINKINFO */ struct smc_diag_linkinfo { - __u8 link_id; /* link identifier */ - __u8 ibname[IB_DEVICE_NAME_MAX]; /* name of the RDMA device */ - __u8 ibport; /* RDMA device port number */ - __u8 gid[40]; /* local GID */ - __u8 peer_gid[40]; /* peer GID */ - __aligned_u64 net_cookie; /* RDMA device net namespace */ + __u8 link_id; /* link identifier */ + __u8 ibname[IB_DEVICE_NAME_MAX]; /* name of the RDMA device */ + __u8 ibport; /* RDMA device port number */ + __u8 gid[40]; /* local GID */ + __u8 peer_gid[40]; /* peer GID */ }; struct smc_diag_lgrinfo { 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/async.c b/kernel/async.c index b8d7a663497f..b2c4ba5686ee 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -205,9 +205,6 @@ async_cookie_t async_schedule_node_domain(async_func_t func, void *data, atomic_inc(&entry_count); spin_unlock_irqrestore(&async_lock, flags); - /* mark that this task has queued an async job, used by module init */ - current->flags |= PF_USED_ASYNC; - /* schedule for execution */ queue_work_node(node, system_unbound_wq, &entry->work); diff --git a/kernel/audit.c b/kernel/audit.c index e4bbe2c70c26..7690c29d4ee4 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -541,20 +541,22 @@ static void kauditd_printk_skb(struct sk_buff *skb) /** * kauditd_rehold_skb - Handle a audit record send failure in the hold queue * @skb: audit record + * @error: error code (unused) * * Description: * This should only be used by the kauditd_thread when it fails to flush the * hold queue. */ -static void kauditd_rehold_skb(struct sk_buff *skb) +static void kauditd_rehold_skb(struct sk_buff *skb, __always_unused int error) { - /* put the record back in the queue at the same place */ - skb_queue_head(&audit_hold_queue, skb); + /* put the record back in the queue */ + skb_queue_tail(&audit_hold_queue, skb); } /** * kauditd_hold_skb - Queue an audit record, waiting for auditd * @skb: audit record + * @error: error code * * Description: * Queue the audit record, waiting for an instance of auditd. When this @@ -564,19 +566,31 @@ static void kauditd_rehold_skb(struct sk_buff *skb) * and queue it, if we have room. If we want to hold on to the record, but we * don't have room, record a record lost message. */ -static void kauditd_hold_skb(struct sk_buff *skb) +static void kauditd_hold_skb(struct sk_buff *skb, int error) { /* at this point it is uncertain if we will ever send this to auditd so * try to send the message via printk before we go any further */ kauditd_printk_skb(skb); /* can we just silently drop the message? */ - if (!audit_default) { - kfree_skb(skb); - return; + if (!audit_default) + goto drop; + + /* the hold queue is only for when the daemon goes away completely, + * not -EAGAIN failures; if we are in a -EAGAIN state requeue the + * record on the retry queue unless it's full, in which case drop it + */ + if (error == -EAGAIN) { + if (!audit_backlog_limit || + skb_queue_len(&audit_retry_queue) < audit_backlog_limit) { + skb_queue_tail(&audit_retry_queue, skb); + return; + } + audit_log_lost("kauditd retry queue overflow"); + goto drop; } - /* if we have room, queue the message */ + /* if we have room in the hold queue, queue the message */ if (!audit_backlog_limit || skb_queue_len(&audit_hold_queue) < audit_backlog_limit) { skb_queue_tail(&audit_hold_queue, skb); @@ -585,24 +599,32 @@ static void kauditd_hold_skb(struct sk_buff *skb) /* we have no other options - drop the message */ audit_log_lost("kauditd hold queue overflow"); +drop: kfree_skb(skb); } /** * kauditd_retry_skb - Queue an audit record, attempt to send again to auditd * @skb: audit record + * @error: error code (unused) * * Description: * Not as serious as kauditd_hold_skb() as we still have a connected auditd, * but for some reason we are having problems sending it audit records so * queue the given record and attempt to resend. */ -static void kauditd_retry_skb(struct sk_buff *skb) +static void kauditd_retry_skb(struct sk_buff *skb, __always_unused int error) { - /* NOTE: because records should only live in the retry queue for a - * short period of time, before either being sent or moved to the hold - * queue, we don't currently enforce a limit on this queue */ - skb_queue_tail(&audit_retry_queue, skb); + if (!audit_backlog_limit || + skb_queue_len(&audit_retry_queue) < audit_backlog_limit) { + skb_queue_tail(&audit_retry_queue, skb); + return; + } + + /* we have to drop the record, send it via printk as a last effort */ + kauditd_printk_skb(skb); + audit_log_lost("kauditd retry queue overflow"); + kfree_skb(skb); } /** @@ -640,7 +662,7 @@ static void auditd_reset(const struct auditd_connection *ac) /* flush the retry queue to the hold queue, but don't touch the main * queue since we need to process that normally for multicast */ while ((skb = skb_dequeue(&audit_retry_queue))) - kauditd_hold_skb(skb); + kauditd_hold_skb(skb, -ECONNREFUSED); } /** @@ -714,16 +736,18 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, struct sk_buff_head *queue, unsigned int retry_limit, void (*skb_hook)(struct sk_buff *skb), - void (*err_hook)(struct sk_buff *skb)) + void (*err_hook)(struct sk_buff *skb, int error)) { int rc = 0; - struct sk_buff *skb; + struct sk_buff *skb = NULL; + struct sk_buff *skb_tail; unsigned int failed = 0; /* NOTE: kauditd_thread takes care of all our locking, we just use * the netlink info passed to us (e.g. sk and portid) */ - while ((skb = skb_dequeue(queue))) { + skb_tail = skb_peek_tail(queue); + while ((skb != skb_tail) && (skb = skb_dequeue(queue))) { /* call the skb_hook for each skb we touch */ if (skb_hook) (*skb_hook)(skb); @@ -731,7 +755,7 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, /* can we send to anyone via unicast? */ if (!sk) { if (err_hook) - (*err_hook)(skb); + (*err_hook)(skb, -ECONNREFUSED); continue; } @@ -745,7 +769,7 @@ retry: rc == -ECONNREFUSED || rc == -EPERM) { sk = NULL; if (err_hook) - (*err_hook)(skb); + (*err_hook)(skb, rc); if (rc == -EAGAIN) rc = 0; /* continue to drain the queue */ diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 06062370c3b8..9e4ecc990647 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -207,7 +207,7 @@ BTF_ID(func, bpf_lsm_socket_socketpair) BTF_ID(func, bpf_lsm_syslog) BTF_ID(func, bpf_lsm_task_alloc) -BTF_ID(func, bpf_lsm_task_getsecid_subj) +BTF_ID(func, bpf_lsm_current_getsecid_subj) BTF_ID(func, bpf_lsm_task_getsecid_obj) BTF_ID(func, bpf_lsm_task_prctl) BTF_ID(func, bpf_lsm_task_setscheduler) diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 638d7fd7b375..710ba9de12ce 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -104,7 +104,7 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node) } rb = vmap(pages, nr_meta_pages + 2 * nr_data_pages, - VM_ALLOC | VM_USERMAP, PAGE_KERNEL); + VM_MAP | VM_USERMAP, PAGE_KERNEL); if (rb) { kmemleak_not_leak(pages); rb->pages = pages; diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 4b6974a195c1..5e7edf913060 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -550,11 +550,12 @@ static __always_inline u64 notrace bpf_prog_start_time(void) static void notrace inc_misses_counter(struct bpf_prog *prog) { struct bpf_prog_stats *stats; + unsigned int flags; stats = this_cpu_ptr(prog->stats); - u64_stats_update_begin(&stats->syncp); + flags = u64_stats_update_begin_irqsave(&stats->syncp); u64_stats_inc(&stats->misses); - u64_stats_update_end(&stats->syncp); + u64_stats_update_end_irqrestore(&stats->syncp, flags); } /* The logic is similar to bpf_prog_run(), but with an explicit diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 41e0837a5a0b..0e877dbcfeea 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -549,6 +549,14 @@ static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of, BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); + /* + * Release agent gets called with all capabilities, + * require capabilities to set release agent. + */ + if ((of->file->f_cred->user_ns != &init_user_ns) || + !capable(CAP_SYS_ADMIN)) + return -EPERM; + cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; @@ -954,6 +962,12 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) /* Specifying two release agents is forbidden */ if (ctx->release_agent) return invalfc(fc, "release_agent respecified"); + /* + * Release agent gets called with all capabilities, + * require capabilities to set release agent. + */ + if ((fc->user_ns != &init_user_ns) || !capable(CAP_SYS_ADMIN)) + return invalfc(fc, "Setting release_agent not allowed"); ctx->release_agent = param->string; param->string = NULL; break; diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index dc653ab26e50..4c7254e8f49a 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -591,6 +591,35 @@ static inline void free_cpuset(struct cpuset *cs) } /* + * validate_change_legacy() - Validate conditions specific to legacy (v1) + * behavior. + */ +static int validate_change_legacy(struct cpuset *cur, struct cpuset *trial) +{ + struct cgroup_subsys_state *css; + struct cpuset *c, *par; + int ret; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + /* Each of our child cpusets must be a subset of us */ + ret = -EBUSY; + cpuset_for_each_child(c, css, cur) + if (!is_cpuset_subset(c, trial)) + goto out; + + /* On legacy hierarchy, we must be a subset of our parent cpuset. */ + ret = -EACCES; + par = parent_cs(cur); + if (par && !is_cpuset_subset(trial, par)) + goto out; + + ret = 0; +out: + return ret; +} + +/* * validate_change() - Used to validate that any proposed cpuset change * follows the structural rules for cpusets. * @@ -614,20 +643,21 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial) { struct cgroup_subsys_state *css; struct cpuset *c, *par; - int ret; - - /* The checks don't apply to root cpuset */ - if (cur == &top_cpuset) - return 0; + int ret = 0; rcu_read_lock(); - par = parent_cs(cur); - /* On legacy hierarchy, we must be a subset of our parent cpuset. */ - ret = -EACCES; - if (!is_in_v2_mode() && !is_cpuset_subset(trial, par)) + if (!is_in_v2_mode()) + ret = validate_change_legacy(cur, trial); + if (ret) + goto out; + + /* Remaining checks don't apply to root cpuset */ + if (cur == &top_cpuset) goto out; + par = parent_cs(cur); + /* * If either I or some sibling (!= me) is exclusive, we can't * overlap @@ -1175,9 +1205,7 @@ enum subparts_cmd { * * Because of the implicit cpu exclusive nature of a partition root, * cpumask changes that violates the cpu exclusivity rule will not be - * permitted when checked by validate_change(). The validate_change() - * function will also prevent any changes to the cpu list if it is not - * a superset of children's cpu lists. + * permitted when checked by validate_change(). */ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, struct cpumask *newmask, @@ -1522,10 +1550,15 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, struct cpuset *sibling; struct cgroup_subsys_state *pos_css; + percpu_rwsem_assert_held(&cpuset_rwsem); + /* * Check all its siblings and call update_cpumasks_hier() * if their use_parent_ecpus flag is set in order for them * to use the right effective_cpus value. + * + * The update_cpumasks_hier() function may sleep. So we have to + * release the RCU read lock before calling it. */ rcu_read_lock(); cpuset_for_each_child(sibling, pos_css, parent) { @@ -1533,8 +1566,13 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, continue; if (!sibling->use_parent_ecpus) continue; + if (!css_tryget_online(&sibling->css)) + continue; + rcu_read_unlock(); update_cpumasks_hier(sibling, tmp); + rcu_read_lock(); + css_put(&sibling->css); } rcu_read_unlock(); } @@ -1607,8 +1645,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, * Make sure that subparts_cpus is a subset of cpus_allowed. */ if (cs->nr_subparts_cpus) { - cpumask_andnot(cs->subparts_cpus, cs->subparts_cpus, - cs->cpus_allowed); + cpumask_and(cs->subparts_cpus, cs->subparts_cpus, cs->cpus_allowed); cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus); } spin_unlock_irq(&callback_lock); 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/kernel/module.c b/kernel/module.c index 24dab046e16c..46a5c2ed1928 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3725,12 +3725,6 @@ static noinline int do_init_module(struct module *mod) } freeinit->module_init = mod->init_layout.base; - /* - * We want to find out whether @mod uses async during init. Clear - * PF_USED_ASYNC. async_schedule*() will set it. - */ - current->flags &= ~PF_USED_ASYNC; - do_mod_ctors(mod); /* Start the module */ if (mod->init != NULL) @@ -3756,22 +3750,13 @@ static noinline int do_init_module(struct module *mod) /* * We need to finish all async code before the module init sequence - * is done. This has potential to deadlock. For example, a newly - * detected block device can trigger request_module() of the - * default iosched from async probing task. Once userland helper - * reaches here, async_synchronize_full() will wait on the async - * task waiting on request_module() and deadlock. - * - * This deadlock is avoided by perfomring async_synchronize_full() - * iff module init queued any async jobs. This isn't a full - * solution as it will deadlock the same if module loading from - * async jobs nests more than once; however, due to the various - * constraints, this hack seems to be the best option for now. - * Please refer to the following thread for details. + * is done. This has potential to deadlock if synchronous module + * loading is requested from async (which is not allowed!). * - * http://thread.gmane.org/gmane.linux.kernel/1420814 + * See commit 0fdff3ec6d87 ("async, kmod: warn on synchronous + * request_module() from async workers") for more details. */ - if (!mod->async_probe_requested && (current->flags & PF_USED_ASYNC)) + if (!mod->async_probe_requested) async_synchronize_full(); ftrace_free_mem(mod, mod->init_layout.base, mod->init_layout.base + diff --git a/kernel/printk/sysctl.c b/kernel/printk/sysctl.c index 653ae04aab7f..c228343eeb97 100644 --- a/kernel/printk/sysctl.c +++ b/kernel/printk/sysctl.c @@ -12,7 +12,7 @@ static const int ten_thousand = 10000; static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { if (write && !capable(CAP_SYS_ADMIN)) return -EPERM; diff --git a/kernel/stackleak.c b/kernel/stackleak.c index 66b8af394e58..ddb5a7f48d69 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -70,7 +70,7 @@ late_initcall(stackleak_sysctls_init); #define skip_erasing() false #endif /* CONFIG_STACKLEAK_RUNTIME_DISABLE */ -asmlinkage void notrace stackleak_erase(void) +asmlinkage void noinstr stackleak_erase(void) { /* It would be nice not to have 'kstack_ptr' and 'boundary' on stack */ unsigned long kstack_ptr = current->lowest_stack; @@ -124,9 +124,8 @@ asmlinkage void notrace stackleak_erase(void) /* Reset the 'lowest_stack' value for the next syscall */ current->lowest_stack = current_top_of_stack() - THREAD_SIZE/64; } -NOKPROBE_SYMBOL(stackleak_erase); -void __used __no_caller_saved_registers notrace stackleak_track_stack(void) +void __used __no_caller_saved_registers noinstr stackleak_track_stack(void) { unsigned long sp = current_stack_pointer; 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) @@ -124,8 +124,8 @@ static inline struct page *try_get_compound_head(struct page *page, int refs) * considered failure, and furthermore, a likely bug in the caller, so a warning * is also emitted. */ -struct page *try_grab_compound_head(struct page *page, - int refs, unsigned int flags) +__maybe_unused struct page *try_grab_compound_head(struct page *page, + int refs, unsigned int flags) { if (flags & FOLL_GET) return try_get_compound_head(page, refs); @@ -208,10 +208,35 @@ static void put_compound_head(struct page *page, int refs, unsigned int flags) */ bool __must_check try_grab_page(struct page *page, unsigned int flags) { - if (!(flags & (FOLL_GET | FOLL_PIN))) - return true; + WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == (FOLL_GET | FOLL_PIN)); - return try_grab_compound_head(page, 1, flags); + if (flags & FOLL_GET) + return try_get_page(page); + else if (flags & FOLL_PIN) { + int refs = 1; + + page = compound_head(page); + + if (WARN_ON_ONCE(page_ref_count(page) <= 0)) + return false; + + if (hpage_pincount_available(page)) + hpage_pincount_add(page, 1); + else + refs = GUP_PIN_COUNTING_BIAS; + + /* + * Similar to try_grab_compound_head(): even if using the + * hpage_pincount_add/_sub() routines, be sure to + * *also* increment the normal page refcount field at least + * once, so that the page really is pinned. + */ + page_ref_add(page, refs); + + mod_node_page_state(page_pgdat(page), NR_FOLL_PIN_ACQUIRED, 1); + } + + return true; } /** 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/ax25/af_ax25.c b/net/ax25/af_ax25.c index 02f43f3e2c56..3e49d28824ed 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -77,6 +77,7 @@ static void ax25_kill_by_device(struct net_device *dev) { ax25_dev *ax25_dev; ax25_cb *s; + struct sock *sk; if ((ax25_dev = ax25_dev_ax25dev(dev)) == NULL) return; @@ -85,13 +86,16 @@ static void ax25_kill_by_device(struct net_device *dev) again: ax25_for_each(s, &ax25_list) { if (s->ax25_dev == ax25_dev) { + sk = s->sk; + sock_hold(sk); spin_unlock_bh(&ax25_list_lock); - lock_sock(s->sk); + lock_sock(sk); s->ax25_dev = NULL; - release_sock(s->sk); + ax25_dev_put(ax25_dev); + release_sock(sk); ax25_disconnect(s, ENETUNREACH); spin_lock_bh(&ax25_list_lock); - + sock_put(sk); /* The entry could have been deleted from the * list meanwhile and thus the next pointer is * no longer valid. Play it safe and restart @@ -355,21 +359,25 @@ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg) if (copy_from_user(&ax25_ctl, arg, sizeof(ax25_ctl))) return -EFAULT; - if ((ax25_dev = ax25_addr_ax25dev(&ax25_ctl.port_addr)) == NULL) - return -ENODEV; - if (ax25_ctl.digi_count > AX25_MAX_DIGIS) return -EINVAL; if (ax25_ctl.arg > ULONG_MAX / HZ && ax25_ctl.cmd != AX25_KILL) return -EINVAL; + ax25_dev = ax25_addr_ax25dev(&ax25_ctl.port_addr); + if (!ax25_dev) + return -ENODEV; + digi.ndigi = ax25_ctl.digi_count; for (k = 0; k < digi.ndigi; k++) digi.calls[k] = ax25_ctl.digi_addr[k]; - if ((ax25 = ax25_find_cb(&ax25_ctl.source_addr, &ax25_ctl.dest_addr, &digi, ax25_dev->dev)) == NULL) + ax25 = ax25_find_cb(&ax25_ctl.source_addr, &ax25_ctl.dest_addr, &digi, ax25_dev->dev); + if (!ax25) { + ax25_dev_put(ax25_dev); return -ENOTCONN; + } switch (ax25_ctl.cmd) { case AX25_KILL: @@ -436,6 +444,7 @@ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg) } out_put: + ax25_dev_put(ax25_dev); ax25_cb_put(ax25); return ret; diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c index 256fadb94df3..d2a244e1c260 100644 --- a/net/ax25/ax25_dev.c +++ b/net/ax25/ax25_dev.c @@ -37,6 +37,7 @@ ax25_dev *ax25_addr_ax25dev(ax25_address *addr) for (ax25_dev = ax25_dev_list; ax25_dev != NULL; ax25_dev = ax25_dev->next) if (ax25cmp(addr, (const ax25_address *)ax25_dev->dev->dev_addr) == 0) { res = ax25_dev; + ax25_dev_hold(ax25_dev); } spin_unlock_bh(&ax25_dev_lock); @@ -56,6 +57,7 @@ void ax25_dev_device_up(struct net_device *dev) return; } + refcount_set(&ax25_dev->refcount, 1); dev->ax25_ptr = ax25_dev; ax25_dev->dev = dev; dev_hold_track(dev, &ax25_dev->dev_tracker, GFP_ATOMIC); @@ -84,6 +86,7 @@ void ax25_dev_device_up(struct net_device *dev) ax25_dev->next = ax25_dev_list; ax25_dev_list = ax25_dev; spin_unlock_bh(&ax25_dev_lock); + ax25_dev_hold(ax25_dev); ax25_register_dev_sysctl(ax25_dev); } @@ -113,9 +116,10 @@ void ax25_dev_device_down(struct net_device *dev) if ((s = ax25_dev_list) == ax25_dev) { ax25_dev_list = s->next; spin_unlock_bh(&ax25_dev_lock); + ax25_dev_put(ax25_dev); dev->ax25_ptr = NULL; dev_put_track(dev, &ax25_dev->dev_tracker); - kfree(ax25_dev); + ax25_dev_put(ax25_dev); return; } @@ -123,9 +127,10 @@ void ax25_dev_device_down(struct net_device *dev) if (s->next == ax25_dev) { s->next = ax25_dev->next; spin_unlock_bh(&ax25_dev_lock); + ax25_dev_put(ax25_dev); dev->ax25_ptr = NULL; dev_put_track(dev, &ax25_dev->dev_tracker); - kfree(ax25_dev); + ax25_dev_put(ax25_dev); return; } @@ -133,6 +138,7 @@ void ax25_dev_device_down(struct net_device *dev) } spin_unlock_bh(&ax25_dev_lock); dev->ax25_ptr = NULL; + ax25_dev_put(ax25_dev); } int ax25_fwd_ioctl(unsigned int cmd, struct ax25_fwd_struct *fwd) @@ -144,20 +150,32 @@ int ax25_fwd_ioctl(unsigned int cmd, struct ax25_fwd_struct *fwd) switch (cmd) { case SIOCAX25ADDFWD: - if ((fwd_dev = ax25_addr_ax25dev(&fwd->port_to)) == NULL) + fwd_dev = ax25_addr_ax25dev(&fwd->port_to); + if (!fwd_dev) { + ax25_dev_put(ax25_dev); return -EINVAL; - if (ax25_dev->forward != NULL) + } + if (ax25_dev->forward) { + ax25_dev_put(fwd_dev); + ax25_dev_put(ax25_dev); return -EINVAL; + } ax25_dev->forward = fwd_dev->dev; + ax25_dev_put(fwd_dev); + ax25_dev_put(ax25_dev); break; case SIOCAX25DELFWD: - if (ax25_dev->forward == NULL) + if (!ax25_dev->forward) { + ax25_dev_put(ax25_dev); return -EINVAL; + } ax25_dev->forward = NULL; + ax25_dev_put(ax25_dev); break; default: + ax25_dev_put(ax25_dev); return -EINVAL; } diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c index d0b2e094bd55..9751207f7757 100644 --- a/net/ax25/ax25_route.c +++ b/net/ax25/ax25_route.c @@ -75,11 +75,13 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) ax25_dev *ax25_dev; int i; - if ((ax25_dev = ax25_addr_ax25dev(&route->port_addr)) == NULL) - return -EINVAL; if (route->digi_count > AX25_MAX_DIGIS) return -EINVAL; + ax25_dev = ax25_addr_ax25dev(&route->port_addr); + if (!ax25_dev) + return -EINVAL; + write_lock_bh(&ax25_route_lock); ax25_rt = ax25_route_list; @@ -91,6 +93,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) if (route->digi_count != 0) { if ((ax25_rt->digipeat = kmalloc(sizeof(ax25_digi), GFP_ATOMIC)) == NULL) { write_unlock_bh(&ax25_route_lock); + ax25_dev_put(ax25_dev); return -ENOMEM; } ax25_rt->digipeat->lastrepeat = -1; @@ -101,6 +104,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) } } write_unlock_bh(&ax25_route_lock); + ax25_dev_put(ax25_dev); return 0; } ax25_rt = ax25_rt->next; @@ -108,6 +112,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) if ((ax25_rt = kmalloc(sizeof(ax25_route), GFP_ATOMIC)) == NULL) { write_unlock_bh(&ax25_route_lock); + ax25_dev_put(ax25_dev); return -ENOMEM; } @@ -120,6 +125,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) if ((ax25_rt->digipeat = kmalloc(sizeof(ax25_digi), GFP_ATOMIC)) == NULL) { write_unlock_bh(&ax25_route_lock); kfree(ax25_rt); + ax25_dev_put(ax25_dev); return -ENOMEM; } ax25_rt->digipeat->lastrepeat = -1; @@ -132,6 +138,7 @@ static int __must_check ax25_rt_add(struct ax25_routes_struct *route) ax25_rt->next = ax25_route_list; ax25_route_list = ax25_rt; write_unlock_bh(&ax25_route_lock); + ax25_dev_put(ax25_dev); return 0; } @@ -173,6 +180,7 @@ static int ax25_rt_del(struct ax25_routes_struct *route) } } write_unlock_bh(&ax25_route_lock); + ax25_dev_put(ax25_dev); return 0; } @@ -215,6 +223,7 @@ static int ax25_rt_opt(struct ax25_route_opt_struct *rt_option) out: write_unlock_bh(&ax25_route_lock); + ax25_dev_put(ax25_dev); return err; } diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index eba0efe64d05..fbf858ddec35 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -49,7 +49,7 @@ static void nft_reject_br_send_v4_tcp_reset(struct net *net, { struct sk_buff *nskb; - nskb = nf_reject_skb_v4_tcp_reset(net, oldskb, dev, hook); + nskb = nf_reject_skb_v4_tcp_reset(net, oldskb, NULL, hook); if (!nskb) return; @@ -65,7 +65,7 @@ static void nft_reject_br_send_v4_unreach(struct net *net, { struct sk_buff *nskb; - nskb = nf_reject_skb_v4_unreach(net, oldskb, dev, hook, code); + nskb = nf_reject_skb_v4_unreach(net, oldskb, NULL, hook, code); if (!nskb) return; @@ -81,7 +81,7 @@ static void nft_reject_br_send_v6_tcp_reset(struct net *net, { struct sk_buff *nskb; - nskb = nf_reject_skb_v6_tcp_reset(net, oldskb, dev, hook); + nskb = nf_reject_skb_v6_tcp_reset(net, oldskb, NULL, hook); if (!nskb) return; @@ -98,7 +98,7 @@ static void nft_reject_br_send_v6_unreach(struct net *net, { struct sk_buff *nskb; - nskb = nf_reject_skb_v6_unreach(net, oldskb, dev, hook, code); + nskb = nf_reject_skb_v6_unreach(net, oldskb, NULL, hook, code); if (!nskb) return; 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/neighbour.c b/net/core/neighbour.c index 6c2016f7f3d1..ec0bf737b076 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1133,7 +1133,8 @@ out: neigh_release(neigh); } -int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) +int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb, + const bool immediate_ok) { int rc; bool immediate_probe = false; @@ -1154,12 +1155,17 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES)); neigh_del_timer(neigh); - neigh->nud_state = NUD_INCOMPLETE; + neigh->nud_state = NUD_INCOMPLETE; neigh->updated = now; - next = now + max(NEIGH_VAR(neigh->parms, RETRANS_TIME), - HZ/100); + if (!immediate_ok) { + next = now + 1; + } else { + immediate_probe = true; + next = now + max(NEIGH_VAR(neigh->parms, + RETRANS_TIME), + HZ / 100); + } neigh_add_timer(neigh, next); - immediate_probe = true; } else { neigh->nud_state = NUD_FAILED; neigh->updated = jiffies; @@ -1571,7 +1577,7 @@ static void neigh_managed_work(struct work_struct *work) write_lock_bh(&tbl->lock); list_for_each_entry(neigh, &tbl->managed_list, managed_list) - neigh_event_send(neigh, NULL); + neigh_event_send_probe(neigh, NULL, false); queue_delayed_work(system_power_efficient_wq, &tbl->managed_work, NEIGH_VAR(&tbl->parms, DELAY_PROBE_TIME)); write_unlock_bh(&tbl->lock); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e476403231f0..710da8a36729 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3275,8 +3275,8 @@ static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, struct nlattr *slave_attr[RTNL_SLAVE_MAX_TYPE + 1]; unsigned char name_assign_type = NET_NAME_USER; struct nlattr *linkinfo[IFLA_INFO_MAX + 1]; - const struct rtnl_link_ops *m_ops = NULL; - struct net_device *master_dev = NULL; + const struct rtnl_link_ops *m_ops; + struct net_device *master_dev; struct net *net = sock_net(skb->sk); const struct rtnl_link_ops *ops; struct nlattr *tb[IFLA_MAX + 1]; @@ -3314,6 +3314,8 @@ replay: else dev = NULL; + master_dev = NULL; + m_ops = NULL; if (dev) { master_dev = netdev_master_upper_dev_get(dev); if (master_dev) diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index 277124f206e0..e0b072aecf0f 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -1441,7 +1441,7 @@ static int nl802154_send_key(struct sk_buff *msg, u32 cmd, u32 portid, hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) - return -1; + return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; @@ -1634,7 +1634,7 @@ static int nl802154_send_device(struct sk_buff *msg, u32 cmd, u32 portid, hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) - return -1; + return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; @@ -1812,7 +1812,7 @@ static int nl802154_send_devkey(struct sk_buff *msg, u32 cmd, u32 portid, hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) - return -1; + return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; @@ -1988,7 +1988,7 @@ static int nl802154_send_seclevel(struct sk_buff *msg, u32 cmd, u32 portid, hdr = nl802154hdr_put(msg, portid, seq, flags, cmd); if (!hdr) - return -1; + return -ENOBUFS; if (nla_put_u32(msg, NL802154_ATTR_IFINDEX, dev->ifindex)) goto nla_put_failure; diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 67087f95579f..aab384126f61 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -58,10 +58,6 @@ config NF_TABLES_ARP endif # NF_TABLES -config NF_FLOW_TABLE_IPV4 - tristate - select NF_FLOW_TABLE_INET - config NF_DUP_IPV4 tristate "Netfilter IPv4 packet duplication to alternate destination" depends on !NF_CONNTRACK || NF_CONNTRACK diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 78e81465f5f3..bdf108f544a4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1322,10 +1322,13 @@ new_segment: /* skb changing from pure zc to mixed, must charge zc */ if (unlikely(skb_zcopy_pure(skb))) { - if (!sk_wmem_schedule(sk, skb->data_len)) + u32 extra = skb->truesize - + SKB_TRUESIZE(skb_end_offset(skb)); + + if (!sk_wmem_schedule(sk, extra)) goto wait_for_space; - sk_mem_charge(sk, skb->data_len); + sk_mem_charge(sk, extra); skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index dc49a3d551eb..bfe4112e000c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1660,6 +1660,8 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, (mss != tcp_skb_seglen(skb))) goto out; + if (!tcp_skb_can_collapse(prev, skb)) + goto out; len = skb->len; pcount = tcp_skb_pcount(skb); if (tcp_skb_shift(prev, skb, pcount, len)) diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 97d3d1b36dbc..0ba62f4868f9 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -47,10 +47,6 @@ config NFT_FIB_IPV6 endif # NF_TABLES_IPV6 endif # NF_TABLES -config NF_FLOW_TABLE_IPV6 - tristate - select NF_FLOW_TABLE_INET - config NF_DUP_IPV6 tristate "Netfilter IPv6 packet duplication to alternate destination" depends on !NF_CONNTRACK || NF_CONNTRACK diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index b85383606df7..b8d6dc9aeeb6 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -28,9 +28,6 @@ obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o obj-$(CONFIG_NFT_FIB_IPV6) += nft_fib_ipv6.o -# flow table support -obj-$(CONFIG_NF_FLOW_TABLE_IPV6) += nf_flow_table_ipv6.o - # matches obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o obj-$(CONFIG_IP6_NF_MATCH_EUI64) += ip6t_eui64.o diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/net/ipv6/netfilter/nf_flow_table_ipv6.c +++ /dev/null diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index cf454f8ca2b0..5fa16990da95 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2011,7 +2011,6 @@ static void nft_last_rule(struct nft_rule_blob *blob, const void *ptr) prule = (struct nft_rule_dp *)ptr; prule->is_last = 1; - ptr += offsetof(struct nft_rule_dp, data); /* blob size does not include the trailer rule */ } diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index 9d5947ab8d4e..e646e9ee4a98 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -167,12 +167,24 @@ nla_put_failure: return -1; } +static bool nft_byteorder_reduce(struct nft_regs_track *track, + const struct nft_expr *expr) +{ + struct nft_byteorder *priv = nft_expr_priv(expr); + + track->regs[priv->dreg].selector = NULL; + track->regs[priv->dreg].bitwise = NULL; + + return false; +} + static const struct nft_expr_ops nft_byteorder_ops = { .type = &nft_byteorder_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_byteorder)), .eval = nft_byteorder_eval, .init = nft_byteorder_init, .dump = nft_byteorder_dump, + .reduce = nft_byteorder_reduce, }; struct nft_expr_type nft_byteorder_type __read_mostly = { diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 518d96c8c247..5adf8bb628a8 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -260,9 +260,12 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr, ct = this_cpu_read(nft_ct_pcpu_template); if (likely(refcount_read(&ct->ct_general.use) == 1)) { + refcount_inc(&ct->ct_general.use); nf_ct_zone_add(ct, &zone); } else { - /* previous skb got queued to userspace */ + /* previous skb got queued to userspace, allocate temporary + * one until percpu template can be reused. + */ ct = nf_ct_tmpl_alloc(nft_net(pkt), &zone, GFP_ATOMIC); if (!ct) { regs->verdict.code = NF_DROP; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 85ea7ddb48db..ab87f22cc7ec 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1789,7 +1789,10 @@ static int fanout_add(struct sock *sk, struct fanout_args *args) err = -ENOSPC; if (refcount_read(&match->sk_ref) < match->max_num_members) { __dev_remove_pack(&po->prot_hook); - po->fanout = match; + + /* Paired with packet_setsockopt(PACKET_FANOUT_DATA) */ + WRITE_ONCE(po->fanout, match); + po->rollover = rollover; rollover = NULL; refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1); @@ -3934,7 +3937,8 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, } case PACKET_FANOUT_DATA: { - if (!po->fanout) + /* Paired with the WRITE_ONCE() in fanout_add() */ + if (!READ_ONCE(po->fanout)) return -EINVAL; return fanout_set_data(po, optval, optlen); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index d4e27c679123..5f0f346b576f 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1945,9 +1945,9 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, bool prio_allocate; u32 parent; u32 chain_index; - struct Qdisc *q = NULL; + struct Qdisc *q; struct tcf_chain_info chain_info; - struct tcf_chain *chain = NULL; + struct tcf_chain *chain; struct tcf_block *block; struct tcf_proto *tp; unsigned long cl; @@ -1976,6 +1976,8 @@ replay: tp = NULL; cl = 0; block = NULL; + q = NULL; + chain = NULL; flags = 0; if (prio == 0) { @@ -2798,8 +2800,8 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n, struct tcmsg *t; u32 parent; u32 chain_index; - struct Qdisc *q = NULL; - struct tcf_chain *chain = NULL; + struct Qdisc *q; + struct tcf_chain *chain; struct tcf_block *block; unsigned long cl; int err; @@ -2809,6 +2811,7 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n, return -EPERM; replay: + q = NULL; err = nlmsg_parse_deprecated(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack); if (err < 0) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index d5ea62b82bb8..8c89d0b0ca18 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -566,17 +566,115 @@ static void smc_stat_fallback(struct smc_sock *smc) mutex_unlock(&net->smc.mutex_fback_rsn); } +/* must be called under rcu read lock */ +static void smc_fback_wakeup_waitqueue(struct smc_sock *smc, void *key) +{ + struct socket_wq *wq; + __poll_t flags; + + wq = rcu_dereference(smc->sk.sk_wq); + if (!skwq_has_sleeper(wq)) + return; + + /* wake up smc sk->sk_wq */ + if (!key) { + /* sk_state_change */ + wake_up_interruptible_all(&wq->wait); + } else { + flags = key_to_poll(key); + if (flags & (EPOLLIN | EPOLLOUT)) + /* sk_data_ready or sk_write_space */ + wake_up_interruptible_sync_poll(&wq->wait, flags); + else if (flags & EPOLLERR) + /* sk_error_report */ + wake_up_interruptible_poll(&wq->wait, flags); + } +} + +static int smc_fback_mark_woken(wait_queue_entry_t *wait, + unsigned int mode, int sync, void *key) +{ + struct smc_mark_woken *mark = + container_of(wait, struct smc_mark_woken, wait_entry); + + mark->woken = true; + mark->key = key; + return 0; +} + +static void smc_fback_forward_wakeup(struct smc_sock *smc, struct sock *clcsk, + void (*clcsock_callback)(struct sock *sk)) +{ + struct smc_mark_woken mark = { .woken = false }; + struct socket_wq *wq; + + init_waitqueue_func_entry(&mark.wait_entry, + smc_fback_mark_woken); + rcu_read_lock(); + wq = rcu_dereference(clcsk->sk_wq); + if (!wq) + goto out; + add_wait_queue(sk_sleep(clcsk), &mark.wait_entry); + clcsock_callback(clcsk); + remove_wait_queue(sk_sleep(clcsk), &mark.wait_entry); + + if (mark.woken) + smc_fback_wakeup_waitqueue(smc, mark.key); +out: + rcu_read_unlock(); +} + +static void smc_fback_state_change(struct sock *clcsk) +{ + struct smc_sock *smc = + smc_clcsock_user_data(clcsk); + + if (!smc) + return; + smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_state_change); +} + +static void smc_fback_data_ready(struct sock *clcsk) +{ + struct smc_sock *smc = + smc_clcsock_user_data(clcsk); + + if (!smc) + return; + smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_data_ready); +} + +static void smc_fback_write_space(struct sock *clcsk) +{ + struct smc_sock *smc = + smc_clcsock_user_data(clcsk); + + if (!smc) + return; + smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_write_space); +} + +static void smc_fback_error_report(struct sock *clcsk) +{ + struct smc_sock *smc = + smc_clcsock_user_data(clcsk); + + if (!smc) + return; + smc_fback_forward_wakeup(smc, clcsk, smc->clcsk_error_report); +} + static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) { - wait_queue_head_t *smc_wait = sk_sleep(&smc->sk); - wait_queue_head_t *clc_wait; - unsigned long flags; + struct sock *clcsk; mutex_lock(&smc->clcsock_release_lock); if (!smc->clcsock) { mutex_unlock(&smc->clcsock_release_lock); return -EBADF; } + clcsk = smc->clcsock->sk; + smc->use_fallback = true; smc->fallback_rsn = reason_code; smc_stat_fallback(smc); @@ -587,16 +685,22 @@ static int smc_switch_to_fallback(struct smc_sock *smc, int reason_code) smc->clcsock->wq.fasync_list = smc->sk.sk_socket->wq.fasync_list; - /* There may be some entries remaining in - * smc socket->wq, which should be removed - * to clcsocket->wq during the fallback. + /* There might be some wait entries remaining + * in smc sk->sk_wq and they should be woken up + * as clcsock's wait queue is woken up. */ - clc_wait = sk_sleep(smc->clcsock->sk); - spin_lock_irqsave(&smc_wait->lock, flags); - spin_lock_nested(&clc_wait->lock, SINGLE_DEPTH_NESTING); - list_splice_init(&smc_wait->head, &clc_wait->head); - spin_unlock(&clc_wait->lock); - spin_unlock_irqrestore(&smc_wait->lock, flags); + smc->clcsk_state_change = clcsk->sk_state_change; + smc->clcsk_data_ready = clcsk->sk_data_ready; + smc->clcsk_write_space = clcsk->sk_write_space; + smc->clcsk_error_report = clcsk->sk_error_report; + + clcsk->sk_state_change = smc_fback_state_change; + clcsk->sk_data_ready = smc_fback_data_ready; + clcsk->sk_write_space = smc_fback_write_space; + clcsk->sk_error_report = smc_fback_error_report; + + smc->clcsock->sk->sk_user_data = + (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); } mutex_unlock(&smc->clcsock_release_lock); return 0; @@ -2115,10 +2219,9 @@ out: static void smc_clcsock_data_ready(struct sock *listen_clcsock) { - struct smc_sock *lsmc; + struct smc_sock *lsmc = + smc_clcsock_user_data(listen_clcsock); - lsmc = (struct smc_sock *) - ((uintptr_t)listen_clcsock->sk_user_data & ~SK_USER_DATA_NOCOPY); if (!lsmc) return; lsmc->clcsk_data_ready(listen_clcsock); diff --git a/net/smc/smc.h b/net/smc/smc.h index 3d0b8e300deb..37b2001a0255 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -139,6 +139,12 @@ enum smc_urg_state { SMC_URG_READ = 3, /* data was already read */ }; +struct smc_mark_woken { + bool woken; + void *key; + wait_queue_entry_t wait_entry; +}; + struct smc_connection { struct rb_node alert_node; struct smc_link_group *lgr; /* link group of connection */ @@ -228,8 +234,14 @@ struct smc_connection { struct smc_sock { /* smc sock container */ struct sock sk; struct socket *clcsock; /* internal tcp socket */ + void (*clcsk_state_change)(struct sock *sk); + /* original stat_change fct. */ void (*clcsk_data_ready)(struct sock *sk); - /* original data_ready fct. **/ + /* original data_ready fct. */ + void (*clcsk_write_space)(struct sock *sk); + /* original write_space fct. */ + void (*clcsk_error_report)(struct sock *sk); + /* original error_report fct. */ struct smc_connection conn; /* smc connection */ struct smc_sock *listen_smc; /* listen parent */ struct work_struct connect_work; /* handle non-blocking connect*/ @@ -264,6 +276,12 @@ static inline struct smc_sock *smc_sk(const struct sock *sk) return (struct smc_sock *)sk; } +static inline struct smc_sock *smc_clcsock_user_data(struct sock *clcsk) +{ + return (struct smc_sock *) + ((uintptr_t)clcsk->sk_user_data & ~SK_USER_DATA_NOCOPY); +} + extern struct workqueue_struct *smc_hs_wq; /* wq for handshake work */ extern struct workqueue_struct *smc_close_wq; /* wq for close work */ diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index b8898c787d23..1fca2f90a9c7 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -146,13 +146,11 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, (req->diag_ext & (1 << (SMC_DIAG_LGRINFO - 1))) && !list_empty(&smc->conn.lgr->list)) { struct smc_link *link = smc->conn.lnk; - struct net *net = read_pnet(&link->smcibdev->ibdev->coredev.rdma_net); struct smc_diag_lgrinfo linfo = { .role = smc->conn.lgr->role, .lnk[0].ibport = link->ibport, .lnk[0].link_id = link->link_id, - .lnk[0].net_cookie = net->net_cookie, }; memcpy(linfo.lnk[0].ibname, diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c index 2ec6e5cd25d9..feb206f3acb4 100644 --- a/security/selinux/ss/conditional.c +++ b/security/selinux/ss/conditional.c @@ -152,6 +152,8 @@ static void cond_list_destroy(struct policydb *p) for (i = 0; i < p->cond_list_len; i++) cond_node_destroy(&p->cond_list[i]); kfree(p->cond_list); + p->cond_list = NULL; + p->cond_list_len = 0; } void cond_policydb_destroy(struct policydb *p) @@ -441,7 +443,6 @@ int cond_read_list(struct policydb *p, void *fp) return 0; err: cond_list_destroy(p); - p->cond_list = NULL; return rc; } 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/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index 9ddeca947635..320a88ac28c9 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -9,7 +9,11 @@ ifeq ($(V),1) msg = else Q = @ - msg = @printf ' %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))"; + ifeq ($(silent),1) + msg = + else + msg = @printf ' %-8s %s%s\n' "$(1)" "$(notdir $(2))" "$(if $(3), $(3))"; + endif MAKEFLAGS=--no-print-directory endif diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index b46bcdb0cab1..507ee1f2aa96 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1134,6 +1134,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_VM_GPA_BITS 207 #define KVM_CAP_XSAVE2 208 #define KVM_CAP_SYS_ATTRIBUTES 209 +#define KVM_CAP_PPC_AIL_MODE_3 210 #ifdef KVM_CAP_IRQ_ROUTING @@ -1624,9 +1625,6 @@ 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 +2046,7 @@ 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/lirc.h b/tools/include/uapi/linux/lirc.h deleted file mode 100644 index 45fcbf99d72e..000000000000 --- a/tools/include/uapi/linux/lirc.h +++ /dev/null @@ -1,229 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * lirc.h - linux infrared remote control header file - * last modified 2010/07/13 by Jarod Wilson - */ - -#ifndef _LINUX_LIRC_H -#define _LINUX_LIRC_H - -#include <linux/types.h> -#include <linux/ioctl.h> - -#define PULSE_BIT 0x01000000 -#define PULSE_MASK 0x00FFFFFF - -#define LIRC_MODE2_SPACE 0x00000000 -#define LIRC_MODE2_PULSE 0x01000000 -#define LIRC_MODE2_FREQUENCY 0x02000000 -#define LIRC_MODE2_TIMEOUT 0x03000000 - -#define LIRC_VALUE_MASK 0x00FFFFFF -#define LIRC_MODE2_MASK 0xFF000000 - -#define LIRC_SPACE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_SPACE) -#define LIRC_PULSE(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_PULSE) -#define LIRC_FREQUENCY(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_FREQUENCY) -#define LIRC_TIMEOUT(val) (((val)&LIRC_VALUE_MASK) | LIRC_MODE2_TIMEOUT) - -#define LIRC_VALUE(val) ((val)&LIRC_VALUE_MASK) -#define LIRC_MODE2(val) ((val)&LIRC_MODE2_MASK) - -#define LIRC_IS_SPACE(val) (LIRC_MODE2(val) == LIRC_MODE2_SPACE) -#define LIRC_IS_PULSE(val) (LIRC_MODE2(val) == LIRC_MODE2_PULSE) -#define LIRC_IS_FREQUENCY(val) (LIRC_MODE2(val) == LIRC_MODE2_FREQUENCY) -#define LIRC_IS_TIMEOUT(val) (LIRC_MODE2(val) == LIRC_MODE2_TIMEOUT) - -/* used heavily by lirc userspace */ -#define lirc_t int - -/*** lirc compatible hardware features ***/ - -#define LIRC_MODE2SEND(x) (x) -#define LIRC_SEND2MODE(x) (x) -#define LIRC_MODE2REC(x) ((x) << 16) -#define LIRC_REC2MODE(x) ((x) >> 16) - -#define LIRC_MODE_RAW 0x00000001 -#define LIRC_MODE_PULSE 0x00000002 -#define LIRC_MODE_MODE2 0x00000004 -#define LIRC_MODE_SCANCODE 0x00000008 -#define LIRC_MODE_LIRCCODE 0x00000010 - - -#define LIRC_CAN_SEND_RAW LIRC_MODE2SEND(LIRC_MODE_RAW) -#define LIRC_CAN_SEND_PULSE LIRC_MODE2SEND(LIRC_MODE_PULSE) -#define LIRC_CAN_SEND_MODE2 LIRC_MODE2SEND(LIRC_MODE_MODE2) -#define LIRC_CAN_SEND_LIRCCODE LIRC_MODE2SEND(LIRC_MODE_LIRCCODE) - -#define LIRC_CAN_SEND_MASK 0x0000003f - -#define LIRC_CAN_SET_SEND_CARRIER 0x00000100 -#define LIRC_CAN_SET_SEND_DUTY_CYCLE 0x00000200 -#define LIRC_CAN_SET_TRANSMITTER_MASK 0x00000400 - -#define LIRC_CAN_REC_RAW LIRC_MODE2REC(LIRC_MODE_RAW) -#define LIRC_CAN_REC_PULSE LIRC_MODE2REC(LIRC_MODE_PULSE) -#define LIRC_CAN_REC_MODE2 LIRC_MODE2REC(LIRC_MODE_MODE2) -#define LIRC_CAN_REC_SCANCODE LIRC_MODE2REC(LIRC_MODE_SCANCODE) -#define LIRC_CAN_REC_LIRCCODE LIRC_MODE2REC(LIRC_MODE_LIRCCODE) - -#define LIRC_CAN_REC_MASK LIRC_MODE2REC(LIRC_CAN_SEND_MASK) - -#define LIRC_CAN_SET_REC_CARRIER (LIRC_CAN_SET_SEND_CARRIER << 16) -#define LIRC_CAN_SET_REC_DUTY_CYCLE (LIRC_CAN_SET_SEND_DUTY_CYCLE << 16) - -#define LIRC_CAN_SET_REC_DUTY_CYCLE_RANGE 0x40000000 -#define LIRC_CAN_SET_REC_CARRIER_RANGE 0x80000000 -#define LIRC_CAN_GET_REC_RESOLUTION 0x20000000 -#define LIRC_CAN_SET_REC_TIMEOUT 0x10000000 -#define LIRC_CAN_SET_REC_FILTER 0x08000000 - -#define LIRC_CAN_MEASURE_CARRIER 0x02000000 -#define LIRC_CAN_USE_WIDEBAND_RECEIVER 0x04000000 - -#define LIRC_CAN_SEND(x) ((x)&LIRC_CAN_SEND_MASK) -#define LIRC_CAN_REC(x) ((x)&LIRC_CAN_REC_MASK) - -#define LIRC_CAN_NOTIFY_DECODE 0x01000000 - -/*** IOCTL commands for lirc driver ***/ - -#define LIRC_GET_FEATURES _IOR('i', 0x00000000, __u32) - -#define LIRC_GET_SEND_MODE _IOR('i', 0x00000001, __u32) -#define LIRC_GET_REC_MODE _IOR('i', 0x00000002, __u32) -#define LIRC_GET_REC_RESOLUTION _IOR('i', 0x00000007, __u32) - -#define LIRC_GET_MIN_TIMEOUT _IOR('i', 0x00000008, __u32) -#define LIRC_GET_MAX_TIMEOUT _IOR('i', 0x00000009, __u32) - -/* code length in bits, currently only for LIRC_MODE_LIRCCODE */ -#define LIRC_GET_LENGTH _IOR('i', 0x0000000f, __u32) - -#define LIRC_SET_SEND_MODE _IOW('i', 0x00000011, __u32) -#define LIRC_SET_REC_MODE _IOW('i', 0x00000012, __u32) -/* Note: these can reset the according pulse_width */ -#define LIRC_SET_SEND_CARRIER _IOW('i', 0x00000013, __u32) -#define LIRC_SET_REC_CARRIER _IOW('i', 0x00000014, __u32) -#define LIRC_SET_SEND_DUTY_CYCLE _IOW('i', 0x00000015, __u32) -#define LIRC_SET_TRANSMITTER_MASK _IOW('i', 0x00000017, __u32) - -/* - * when a timeout != 0 is set the driver will send a - * LIRC_MODE2_TIMEOUT data packet, otherwise LIRC_MODE2_TIMEOUT is - * never sent, timeout is disabled by default - */ -#define LIRC_SET_REC_TIMEOUT _IOW('i', 0x00000018, __u32) - -/* 1 enables, 0 disables timeout reports in MODE2 */ -#define LIRC_SET_REC_TIMEOUT_REPORTS _IOW('i', 0x00000019, __u32) - -/* - * if enabled from the next key press on the driver will send - * LIRC_MODE2_FREQUENCY packets - */ -#define LIRC_SET_MEASURE_CARRIER_MODE _IOW('i', 0x0000001d, __u32) - -/* - * to set a range use LIRC_SET_REC_CARRIER_RANGE with the - * lower bound first and later LIRC_SET_REC_CARRIER with the upper bound - */ -#define LIRC_SET_REC_CARRIER_RANGE _IOW('i', 0x0000001f, __u32) - -#define LIRC_SET_WIDEBAND_RECEIVER _IOW('i', 0x00000023, __u32) - -/* - * Return the recording timeout, which is either set by - * the ioctl LIRC_SET_REC_TIMEOUT or by the kernel after setting the protocols. - */ -#define LIRC_GET_REC_TIMEOUT _IOR('i', 0x00000024, __u32) - -/* - * struct lirc_scancode - decoded scancode with protocol for use with - * LIRC_MODE_SCANCODE - * - * @timestamp: Timestamp in nanoseconds using CLOCK_MONOTONIC when IR - * was decoded. - * @flags: should be 0 for transmit. When receiving scancodes, - * LIRC_SCANCODE_FLAG_TOGGLE or LIRC_SCANCODE_FLAG_REPEAT can be set - * depending on the protocol - * @rc_proto: see enum rc_proto - * @keycode: the translated keycode. Set to 0 for transmit. - * @scancode: the scancode received or to be sent - */ -struct lirc_scancode { - __u64 timestamp; - __u16 flags; - __u16 rc_proto; - __u32 keycode; - __u64 scancode; -}; - -/* Set if the toggle bit of rc-5 or rc-6 is enabled */ -#define LIRC_SCANCODE_FLAG_TOGGLE 1 -/* Set if this is a nec or sanyo repeat */ -#define LIRC_SCANCODE_FLAG_REPEAT 2 - -/** - * enum rc_proto - the Remote Controller protocol - * - * @RC_PROTO_UNKNOWN: Protocol not known - * @RC_PROTO_OTHER: Protocol known but proprietary - * @RC_PROTO_RC5: Philips RC5 protocol - * @RC_PROTO_RC5X_20: Philips RC5x 20 bit protocol - * @RC_PROTO_RC5_SZ: StreamZap variant of RC5 - * @RC_PROTO_JVC: JVC protocol - * @RC_PROTO_SONY12: Sony 12 bit protocol - * @RC_PROTO_SONY15: Sony 15 bit protocol - * @RC_PROTO_SONY20: Sony 20 bit protocol - * @RC_PROTO_NEC: NEC protocol - * @RC_PROTO_NECX: Extended NEC protocol - * @RC_PROTO_NEC32: NEC 32 bit protocol - * @RC_PROTO_SANYO: Sanyo protocol - * @RC_PROTO_MCIR2_KBD: RC6-ish MCE keyboard - * @RC_PROTO_MCIR2_MSE: RC6-ish MCE mouse - * @RC_PROTO_RC6_0: Philips RC6-0-16 protocol - * @RC_PROTO_RC6_6A_20: Philips RC6-6A-20 protocol - * @RC_PROTO_RC6_6A_24: Philips RC6-6A-24 protocol - * @RC_PROTO_RC6_6A_32: Philips RC6-6A-32 protocol - * @RC_PROTO_RC6_MCE: MCE (Philips RC6-6A-32 subtype) protocol - * @RC_PROTO_SHARP: Sharp protocol - * @RC_PROTO_XMP: XMP protocol - * @RC_PROTO_CEC: CEC protocol - * @RC_PROTO_IMON: iMon Pad protocol - * @RC_PROTO_RCMM12: RC-MM protocol 12 bits - * @RC_PROTO_RCMM24: RC-MM protocol 24 bits - * @RC_PROTO_RCMM32: RC-MM protocol 32 bits - */ -enum rc_proto { - RC_PROTO_UNKNOWN = 0, - RC_PROTO_OTHER = 1, - RC_PROTO_RC5 = 2, - RC_PROTO_RC5X_20 = 3, - RC_PROTO_RC5_SZ = 4, - RC_PROTO_JVC = 5, - RC_PROTO_SONY12 = 6, - RC_PROTO_SONY15 = 7, - RC_PROTO_SONY20 = 8, - RC_PROTO_NEC = 9, - RC_PROTO_NECX = 10, - RC_PROTO_NEC32 = 11, - RC_PROTO_SANYO = 12, - RC_PROTO_MCIR2_KBD = 13, - RC_PROTO_MCIR2_MSE = 14, - RC_PROTO_RC6_0 = 15, - RC_PROTO_RC6_6A_20 = 16, - RC_PROTO_RC6_6A_24 = 17, - RC_PROTO_RC6_6A_32 = 18, - RC_PROTO_RC6_MCE = 19, - RC_PROTO_SHARP = 20, - RC_PROTO_XMP = 21, - RC_PROTO_CEC = 22, - RC_PROTO_IMON = 23, - RC_PROTO_RCMM12 = 24, - RC_PROTO_RCMM24 = 25, - RC_PROTO_RCMM32 = 26, -}; - -#endif 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/scripts/Makefile.include b/tools/scripts/Makefile.include index b0be5f40a3f1..79d102304470 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -90,7 +90,7 @@ EXTRA_WARNINGS += -Wstrict-aliasing=3 else ifneq ($(CROSS_COMPILE),) CLANG_CROSS_FLAGS := --target=$(notdir $(CROSS_COMPILE:%-=%)) -GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)gcc)) +GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE)gcc 2>/dev/null)) ifneq ($(GCC_TOOLCHAIN_DIR),) CLANG_CROSS_FLAGS += --prefix=$(GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE)) CLANG_CROSS_FLAGS += --sysroot=$(shell $(CROSS_COMPILE)gcc -print-sysroot) diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index 44bbe54f25f1..3c4196cef3ed 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -6,6 +6,7 @@ # Author: Felix Guo <felixguoxiuping@gmail.com> # Author: Brendan Higgins <brendanhiggins@google.com> +import importlib.abc import importlib.util import logging import subprocess diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_user.c b/tools/testing/selftests/bpf/test_lirc_mode2_user.c index ebf68dce5504..2893e9f2f1e0 100644 --- a/tools/testing/selftests/bpf/test_lirc_mode2_user.c +++ b/tools/testing/selftests/bpf/test_lirc_mode2_user.c @@ -28,7 +28,6 @@ // 5. We can read keycode from same /dev/lirc device #include <linux/bpf.h> -#include <linux/lirc.h> #include <linux/input.h> #include <errno.h> #include <stdio.h> diff --git a/tools/testing/selftests/cpufreq/main.sh b/tools/testing/selftests/cpufreq/main.sh index 31f8c9a76c5f..60ce18ed0666 100755 --- a/tools/testing/selftests/cpufreq/main.sh +++ b/tools/testing/selftests/cpufreq/main.sh @@ -194,5 +194,5 @@ prerequisite # Run requested functions clear_dumps $OUTFILE -do_test >> $OUTFILE.txt +do_test | tee -a $OUTFILE.txt dmesg_dumps $OUTFILE diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile index dd61118df66e..12c5e27d32c1 100644 --- a/tools/testing/selftests/exec/Makefile +++ b/tools/testing/selftests/exec/Makefile @@ -5,7 +5,7 @@ CFLAGS += -D_GNU_SOURCE TEST_PROGS := binfmt_script non-regular TEST_GEN_PROGS := execveat load_address_4096 load_address_2097152 load_address_16777216 -TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir pipe +TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir # Makefile is a run-time dependency, since it's accessed by the execveat test TEST_FILES := Makefile diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile index 12631f0076a1..11e157d7533b 100644 --- a/tools/testing/selftests/futex/Makefile +++ b/tools/testing/selftests/futex/Makefile @@ -11,7 +11,7 @@ all: @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ - make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ if [ -e $$DIR/$(TEST_PROGS) ]; then \ rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/; \ fi \ @@ -32,6 +32,6 @@ override define CLEAN @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ - make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ + $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@;\ done endef diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 471eaa7b3a3f..11779405dc80 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -877,7 +877,8 @@ static void __timeout_handler(int sig, siginfo_t *info, void *ucontext) } t->timed_out = true; - kill(t->pid, SIGKILL); + // signal process group + kill(-(t->pid), SIGKILL); } void __wait_for_test(struct __test_metadata *t) @@ -987,6 +988,7 @@ void __run_test(struct __fixture_metadata *f, ksft_print_msg("ERROR SPAWNING TEST CHILD\n"); t->passed = 0; } else if (t->pid == 0) { + setpgrp(); t->fn(t, variant); if (t->skip) _exit(255); diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 0e4926bc9a58..17c3f0749f05 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -82,7 +82,6 @@ TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_msrs_test TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_pi_mmio_test TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests TEST_GEN_PROGS_x86_64 += x86_64/amx_test TEST_GEN_PROGS_x86_64 += access_tracking_perf_test diff --git a/tools/testing/selftests/mincore/mincore_selftest.c b/tools/testing/selftests/mincore/mincore_selftest.c index e54106643337..4c88238fc8f0 100644 --- a/tools/testing/selftests/mincore/mincore_selftest.c +++ b/tools/testing/selftests/mincore/mincore_selftest.c @@ -207,15 +207,21 @@ TEST(check_file_mmap) errno = 0; fd = open(".", O_TMPFILE | O_RDWR, 0600); - ASSERT_NE(-1, fd) { - TH_LOG("Can't create temporary file: %s", - strerror(errno)); + if (fd < 0) { + ASSERT_EQ(errno, EOPNOTSUPP) { + TH_LOG("Can't create temporary file: %s", + strerror(errno)); + } + SKIP(goto out_free, "O_TMPFILE not supported by filesystem."); } errno = 0; retval = fallocate(fd, 0, 0, FILE_SIZE); - ASSERT_EQ(0, retval) { - TH_LOG("Error allocating space for the temporary file: %s", - strerror(errno)); + if (retval) { + ASSERT_EQ(errno, EOPNOTSUPP) { + TH_LOG("Error allocating space for the temporary file: %s", + strerror(errno)); + } + SKIP(goto out_close, "fallocate not supported by filesystem."); } /* @@ -271,7 +277,9 @@ TEST(check_file_mmap) } munmap(addr, FILE_SIZE); +out_close: close(fd); +out_free: free(vec); } diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh index ed61f6cab60f..df322e47a54f 100755 --- a/tools/testing/selftests/netfilter/nft_concat_range.sh +++ b/tools/testing/selftests/netfilter/nft_concat_range.sh @@ -27,7 +27,7 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto net6_port_net6_port net_port_mac_proto_net" # Reported bugs, also described by TYPE_ variables below -BUGS="flush_remove_add" +BUGS="flush_remove_add reload" # List of possible paths to pktgen script from kernel tree for performance tests PKTGEN_SCRIPT_PATHS=" @@ -354,6 +354,23 @@ TYPE_flush_remove_add=" display Add two elements, flush, re-add " +TYPE_reload=" +display net,mac with reload +type_spec ipv4_addr . ether_addr +chain_spec ip daddr . ether saddr +dst addr4 +src mac +start 1 +count 1 +src_delta 2000 +tools sendip nc bash +proto udp + +race_repeat 0 + +perf_duration 0 +" + # Set template for all tests, types and rules are filled in depending on test set_template=' flush ruleset @@ -1473,6 +1490,59 @@ test_bug_flush_remove_add() { nft flush ruleset } +# - add ranged element, check that packets match it +# - reload the set, check packets still match +test_bug_reload() { + setup veth send_"${proto}" set || return ${KSELFTEST_SKIP} + rstart=${start} + + range_size=1 + for i in $(seq "${start}" $((start + count))); do + end=$((start + range_size)) + + # Avoid negative or zero-sized port ranges + if [ $((end / 65534)) -gt $((start / 65534)) ]; then + start=${end} + end=$((end + 1)) + fi + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + add "$(format)" || return 1 + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + + # check kernel does allocate pcpu sctrach map + # for reload with no elemet add/delete + ( echo flush set inet filter test ; + nft list set inet filter test ) | nft -f - + + start=${rstart} + range_size=1 + + for i in $(seq "${start}" $((start + count))); do + end=$((start + range_size)) + + # Avoid negative or zero-sized port ranges + if [ $((end / 65534)) -gt $((start / 65534)) ]; then + start=${end} + end=$((end + 1)) + fi + srcstart=$((start + src_delta)) + srcend=$((end + src_delta)) + + for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do + send_match "${j}" $((j + src_delta)) || return 1 + done + + range_size=$((range_size + 1)) + start=$((end + range_size)) + done + + nft flush ruleset +} + test_reported_issues() { eval test_bug_"${subtest}" } diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index 349a319a9e51..79fe627b9e81 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -899,6 +899,144 @@ EOF ip netns exec "$ns0" nft delete table $family nat } +test_stateless_nat_ip() +{ + local lret=0 + + ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + + ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping $ns1 from $ns2 before loading stateless rules" + return 1 + fi + +ip netns exec "$ns0" nft -f /dev/stdin <<EOF +table ip stateless { + map xlate_in { + typeof meta iifname . ip saddr . ip daddr : ip daddr + elements = { + "veth1" . 10.0.2.99 . 10.0.1.99 : 10.0.2.2, + } + } + map xlate_out { + typeof meta iifname . ip saddr . ip daddr : ip daddr + elements = { + "veth0" . 10.0.1.99 . 10.0.2.2 : 10.0.2.99 + } + } + + chain prerouting { + type filter hook prerouting priority -400; policy accept; + ip saddr set meta iifname . ip saddr . ip daddr map @xlate_in + ip daddr set meta iifname . ip saddr . ip daddr map @xlate_out + } +} +EOF + if [ $? -ne 0 ]; then + echo "SKIP: Could not add ip statless rules" + return $ksft_skip + fi + + reset_counters + + ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping $ns1 from $ns2 with stateless rules" + lret=1 + fi + + # ns1 should have seen packets from .2.2, due to stateless rewrite. + expect="packets 1 bytes 84" + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0insl | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter "$ns1" ns0insl "$expect" "test_stateless 1" + lret=1 + fi + + for dir in "in" "out" ; do + cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter "$ns2" ns1$dir "$expect" "test_stateless 2" + lret=1 + fi + done + + # ns1 should not have seen packets from ns2, due to masquerade + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter "$ns1" ns0$dir "$expect" "test_stateless 3" + lret=1 + fi + + cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter "$ns0" ns1$dir "$expect" "test_stateless 4" + lret=1 + fi + done + + reset_counters + + socat -h > /dev/null 2>&1 + if [ $? -ne 0 ];then + echo "SKIP: Could not run stateless nat frag test without socat tool" + if [ $lret -eq 0 ]; then + return $ksft_skip + fi + + ip netns exec "$ns0" nft delete table ip stateless + return $lret + fi + + local tmpfile=$(mktemp) + dd if=/dev/urandom of=$tmpfile bs=4096 count=1 2>/dev/null + + local outfile=$(mktemp) + ip netns exec "$ns1" timeout 3 socat -u UDP4-RECV:4233 OPEN:$outfile < /dev/null & + sc_r=$! + + sleep 1 + # re-do with large ping -> ip fragmentation + ip netns exec "$ns2" timeout 3 socat - UDP4-SENDTO:"10.0.1.99:4233" < "$tmpfile" > /dev/null + if [ $? -ne 0 ] ; then + echo "ERROR: failed to test udp $ns1 to $ns2 with stateless ip nat" 1>&2 + lret=1 + fi + + wait + + cmp "$tmpfile" "$outfile" + if [ $? -ne 0 ]; then + ls -l "$tmpfile" "$outfile" + echo "ERROR: in and output file mismatch when checking udp with stateless nat" 1>&2 + lret=1 + fi + + rm -f "$tmpfile" "$outfile" + + # ns1 should have seen packets from 2.2, due to stateless rewrite. + expect="packets 3 bytes 4164" + cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0insl | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter "$ns1" ns0insl "$expect" "test_stateless 5" + lret=1 + fi + + ip netns exec "$ns0" nft delete table ip stateless + if [ $? -ne 0 ]; then + echo "ERROR: Could not delete table ip stateless" 1>&2 + lret=1 + fi + + test $lret -eq 0 && echo "PASS: IP statless for $ns2" + + return $lret +} + # ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99 for i in 0 1 2; do ip netns exec ns$i-$sfx nft -f /dev/stdin <<EOF @@ -965,6 +1103,19 @@ table inet filter { EOF done +# special case for stateless nat check, counter needs to +# be done before (input) ip defragmentation +ip netns exec ns1-$sfx nft -f /dev/stdin <<EOF +table inet filter { + counter ns0insl {} + + chain pre { + type filter hook prerouting priority -400; policy accept; + ip saddr 10.0.2.2 counter name "ns0insl" + } +} +EOF + sleep 3 # test basic connectivity for i in 1 2; do @@ -1019,6 +1170,7 @@ $test_inet_nat && test_redirect inet $test_inet_nat && test_redirect6 inet test_port_shadowing +test_stateless_nat_ip if [ $ret -ne 0 ];then echo -n "FAIL: " diff --git a/tools/testing/selftests/netfilter/nft_zones_many.sh b/tools/testing/selftests/netfilter/nft_zones_many.sh index 04633119b29a..5a8db0b48928 100755 --- a/tools/testing/selftests/netfilter/nft_zones_many.sh +++ b/tools/testing/selftests/netfilter/nft_zones_many.sh @@ -9,7 +9,7 @@ ns="ns-$sfx" # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 -zones=20000 +zones=2000 have_ct_tool=0 ret=0 @@ -75,10 +75,10 @@ EOF while [ $i -lt $max_zones ]; do local start=$(date +%s%3N) - i=$((i + 10000)) + i=$((i + 1000)) j=$((j + 1)) # nft rule in output places each packet in a different zone. - dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345 + dd if=/dev/zero of=/dev/stdout bs=8k count=1000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345 if [ $? -ne 0 ] ;then ret=1 break @@ -86,7 +86,7 @@ EOF stop=$(date +%s%3N) local duration=$((stop-start)) - echo "PASS: added 10000 entries in $duration ms (now $i total, loop $j)" + echo "PASS: added 1000 entries in $duration ms (now $i total, loop $j)" done if [ $have_ct_tool -eq 1 ]; then @@ -128,11 +128,11 @@ test_conntrack_tool() { break fi - if [ $((i%10000)) -eq 0 ];then + if [ $((i%1000)) -eq 0 ];then stop=$(date +%s%3N) local duration=$((stop-start)) - echo "PASS: added 10000 entries in $duration ms (now $i total)" + echo "PASS: added 1000 entries in $duration ms (now $i total)" start=$stop fi done diff --git a/tools/testing/selftests/openat2/Makefile b/tools/testing/selftests/openat2/Makefile index 4b93b1417b86..843ba56d8e49 100644 --- a/tools/testing/selftests/openat2/Makefile +++ b/tools/testing/selftests/openat2/Makefile @@ -5,4 +5,4 @@ TEST_GEN_PROGS := openat2_test resolve_test rename_attack_test include ../lib.mk -$(TEST_GEN_PROGS): helpers.c +$(TEST_GEN_PROGS): helpers.c helpers.h diff --git a/tools/testing/selftests/openat2/helpers.h b/tools/testing/selftests/openat2/helpers.h index a6ea27344db2..7056340b9339 100644 --- a/tools/testing/selftests/openat2/helpers.h +++ b/tools/testing/selftests/openat2/helpers.h @@ -9,6 +9,7 @@ #define _GNU_SOURCE #include <stdint.h> +#include <stdbool.h> #include <errno.h> #include <linux/types.h> #include "../kselftest.h" @@ -62,11 +63,12 @@ bool needs_openat2(const struct open_how *how); (similar to chroot(2)). */ #endif /* RESOLVE_IN_ROOT */ -#define E_func(func, ...) \ - do { \ - if (func(__VA_ARGS__) < 0) \ - ksft_exit_fail_msg("%s:%d %s failed\n", \ - __FILE__, __LINE__, #func);\ +#define E_func(func, ...) \ + do { \ + errno = 0; \ + if (func(__VA_ARGS__) < 0) \ + ksft_exit_fail_msg("%s:%d %s failed - errno:%d\n", \ + __FILE__, __LINE__, #func, errno); \ } while (0) #define E_asprintf(...) E_func(asprintf, __VA_ARGS__) diff --git a/tools/testing/selftests/openat2/openat2_test.c b/tools/testing/selftests/openat2/openat2_test.c index 1bddbe934204..7fb902099de4 100644 --- a/tools/testing/selftests/openat2/openat2_test.c +++ b/tools/testing/selftests/openat2/openat2_test.c @@ -259,6 +259,16 @@ void test_openat2_flags(void) unlink(path); fd = sys_openat2(AT_FDCWD, path, &test->how); + if (fd < 0 && fd == -EOPNOTSUPP) { + /* + * Skip the testcase if it failed because not supported + * by FS. (e.g. a valid O_TMPFILE combination on NFS) + */ + ksft_test_result_skip("openat2 with %s fails with %d (%s)\n", + test->name, fd, strerror(-fd)); + goto next; + } + if (test->err >= 0) failed = (fd < 0); else @@ -303,7 +313,7 @@ skip: else resultfn("openat2 with %s fails with %d (%s)\n", test->name, test->err, strerror(-test->err)); - +next: free(fdpath); fflush(stdout); } 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/rtc/settings b/tools/testing/selftests/rtc/settings index ba4d85f74cd6..a953c96aa16e 100644 --- a/tools/testing/selftests/rtc/settings +++ b/tools/testing/selftests/rtc/settings @@ -1 +1 @@ -timeout=90 +timeout=180 diff --git a/tools/testing/selftests/vDSO/vdso_test_abi.c b/tools/testing/selftests/vDSO/vdso_test_abi.c index 3d603f1394af..883ca85424bc 100644 --- a/tools/testing/selftests/vDSO/vdso_test_abi.c +++ b/tools/testing/selftests/vDSO/vdso_test_abi.c @@ -33,110 +33,114 @@ typedef long (*vdso_clock_gettime_t)(clockid_t clk_id, struct timespec *ts); typedef long (*vdso_clock_getres_t)(clockid_t clk_id, struct timespec *ts); typedef time_t (*vdso_time_t)(time_t *t); -static int vdso_test_gettimeofday(void) +#define VDSO_TEST_PASS_MSG() "\n%s(): PASS\n", __func__ +#define VDSO_TEST_FAIL_MSG(x) "\n%s(): %s FAIL\n", __func__, x +#define VDSO_TEST_SKIP_MSG(x) "\n%s(): SKIP: Could not find %s\n", __func__, x + +static void vdso_test_gettimeofday(void) { /* Find gettimeofday. */ vdso_gettimeofday_t vdso_gettimeofday = (vdso_gettimeofday_t)vdso_sym(version, name[0]); if (!vdso_gettimeofday) { - printf("Could not find %s\n", name[0]); - return KSFT_SKIP; + ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[0])); + return; } struct timeval tv; long ret = vdso_gettimeofday(&tv, 0); if (ret == 0) { - printf("The time is %lld.%06lld\n", - (long long)tv.tv_sec, (long long)tv.tv_usec); + ksft_print_msg("The time is %lld.%06lld\n", + (long long)tv.tv_sec, (long long)tv.tv_usec); + ksft_test_result_pass(VDSO_TEST_PASS_MSG()); } else { - printf("%s failed\n", name[0]); - return KSFT_FAIL; + ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[0])); } - - return KSFT_PASS; } -static int vdso_test_clock_gettime(clockid_t clk_id) +static void vdso_test_clock_gettime(clockid_t clk_id) { /* Find clock_gettime. */ vdso_clock_gettime_t vdso_clock_gettime = (vdso_clock_gettime_t)vdso_sym(version, name[1]); if (!vdso_clock_gettime) { - printf("Could not find %s\n", name[1]); - return KSFT_SKIP; + ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[1])); + return; } struct timespec ts; long ret = vdso_clock_gettime(clk_id, &ts); if (ret == 0) { - printf("The time is %lld.%06lld\n", - (long long)ts.tv_sec, (long long)ts.tv_nsec); + ksft_print_msg("The time is %lld.%06lld\n", + (long long)ts.tv_sec, (long long)ts.tv_nsec); + ksft_test_result_pass(VDSO_TEST_PASS_MSG()); } else { - printf("%s failed\n", name[1]); - return KSFT_FAIL; + ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[1])); } - - return KSFT_PASS; } -static int vdso_test_time(void) +static void vdso_test_time(void) { /* Find time. */ vdso_time_t vdso_time = (vdso_time_t)vdso_sym(version, name[2]); if (!vdso_time) { - printf("Could not find %s\n", name[2]); - return KSFT_SKIP; + ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[2])); + return; } long ret = vdso_time(NULL); if (ret > 0) { - printf("The time in hours since January 1, 1970 is %lld\n", + ksft_print_msg("The time in hours since January 1, 1970 is %lld\n", (long long)(ret / 3600)); + ksft_test_result_pass(VDSO_TEST_PASS_MSG()); } else { - printf("%s failed\n", name[2]); - return KSFT_FAIL; + ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[2])); } - - return KSFT_PASS; } -static int vdso_test_clock_getres(clockid_t clk_id) +static void vdso_test_clock_getres(clockid_t clk_id) { + int clock_getres_fail = 0; + /* Find clock_getres. */ vdso_clock_getres_t vdso_clock_getres = (vdso_clock_getres_t)vdso_sym(version, name[3]); if (!vdso_clock_getres) { - printf("Could not find %s\n", name[3]); - return KSFT_SKIP; + ksft_test_result_skip(VDSO_TEST_SKIP_MSG(name[3])); + return; } struct timespec ts, sys_ts; long ret = vdso_clock_getres(clk_id, &ts); if (ret == 0) { - printf("The resolution is %lld %lld\n", - (long long)ts.tv_sec, (long long)ts.tv_nsec); + ksft_print_msg("The vdso resolution is %lld %lld\n", + (long long)ts.tv_sec, (long long)ts.tv_nsec); } else { - printf("%s failed\n", name[3]); - return KSFT_FAIL; + clock_getres_fail++; } ret = syscall(SYS_clock_getres, clk_id, &sys_ts); - if ((sys_ts.tv_sec != ts.tv_sec) || (sys_ts.tv_nsec != ts.tv_nsec)) { - printf("%s failed\n", name[3]); - return KSFT_FAIL; - } + ksft_print_msg("The syscall resolution is %lld %lld\n", + (long long)sys_ts.tv_sec, (long long)sys_ts.tv_nsec); - return KSFT_PASS; + if ((sys_ts.tv_sec != ts.tv_sec) || (sys_ts.tv_nsec != ts.tv_nsec)) + clock_getres_fail++; + + if (clock_getres_fail > 0) { + ksft_test_result_fail(VDSO_TEST_FAIL_MSG(name[3])); + } else { + ksft_test_result_pass(VDSO_TEST_PASS_MSG()); + } } const char *vdso_clock_name[12] = { @@ -158,36 +162,23 @@ const char *vdso_clock_name[12] = { * This function calls vdso_test_clock_gettime and vdso_test_clock_getres * with different values for clock_id. */ -static inline int vdso_test_clock(clockid_t clock_id) +static inline void vdso_test_clock(clockid_t clock_id) { - int ret0, ret1; - - ret0 = vdso_test_clock_gettime(clock_id); - /* A skipped test is considered passed */ - if (ret0 == KSFT_SKIP) - ret0 = KSFT_PASS; - - ret1 = vdso_test_clock_getres(clock_id); - /* A skipped test is considered passed */ - if (ret1 == KSFT_SKIP) - ret1 = KSFT_PASS; + ksft_print_msg("\nclock_id: %s\n", vdso_clock_name[clock_id]); - ret0 += ret1; + vdso_test_clock_gettime(clock_id); - printf("clock_id: %s", vdso_clock_name[clock_id]); - - if (ret0 > 0) - printf(" [FAIL]\n"); - else - printf(" [PASS]\n"); - - return ret0; + vdso_test_clock_getres(clock_id); } +#define VDSO_TEST_PLAN 16 + int main(int argc, char **argv) { unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR); - int ret; + + ksft_print_header(); + ksft_set_plan(VDSO_TEST_PLAN); if (!sysinfo_ehdr) { printf("AT_SYSINFO_EHDR is not present!\n"); @@ -201,44 +192,42 @@ int main(int argc, char **argv) vdso_init_from_sysinfo_ehdr(getauxval(AT_SYSINFO_EHDR)); - ret = vdso_test_gettimeofday(); + vdso_test_gettimeofday(); #if _POSIX_TIMERS > 0 #ifdef CLOCK_REALTIME - ret += vdso_test_clock(CLOCK_REALTIME); + vdso_test_clock(CLOCK_REALTIME); #endif #ifdef CLOCK_BOOTTIME - ret += vdso_test_clock(CLOCK_BOOTTIME); + vdso_test_clock(CLOCK_BOOTTIME); #endif #ifdef CLOCK_TAI - ret += vdso_test_clock(CLOCK_TAI); + vdso_test_clock(CLOCK_TAI); #endif #ifdef CLOCK_REALTIME_COARSE - ret += vdso_test_clock(CLOCK_REALTIME_COARSE); + vdso_test_clock(CLOCK_REALTIME_COARSE); #endif #ifdef CLOCK_MONOTONIC - ret += vdso_test_clock(CLOCK_MONOTONIC); + vdso_test_clock(CLOCK_MONOTONIC); #endif #ifdef CLOCK_MONOTONIC_RAW - ret += vdso_test_clock(CLOCK_MONOTONIC_RAW); + vdso_test_clock(CLOCK_MONOTONIC_RAW); #endif #ifdef CLOCK_MONOTONIC_COARSE - ret += vdso_test_clock(CLOCK_MONOTONIC_COARSE); + vdso_test_clock(CLOCK_MONOTONIC_COARSE); #endif #endif - ret += vdso_test_time(); - - if (ret > 0) - return KSFT_FAIL; + vdso_test_time(); - return KSFT_PASS; + ksft_print_cnts(); + return ksft_get_fail_cnt() == 0 ? KSFT_PASS : KSFT_FAIL; } 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); } diff --git a/tools/testing/selftests/zram/zram.sh b/tools/testing/selftests/zram/zram.sh index 232e958ec454..b0b91d9b0dc2 100755 --- a/tools/testing/selftests/zram/zram.sh +++ b/tools/testing/selftests/zram/zram.sh @@ -2,9 +2,6 @@ # SPDX-License-Identifier: GPL-2.0 TCID="zram.sh" -# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 - . ./zram_lib.sh run_zram () { @@ -18,14 +15,4 @@ echo "" check_prereqs -# check zram module exists -MODULE_PATH=/lib/modules/`uname -r`/kernel/drivers/block/zram/zram.ko -if [ -f $MODULE_PATH ]; then - run_zram -elif [ -b /dev/zram0 ]; then - run_zram -else - echo "$TCID : No zram.ko module or /dev/zram0 device file not found" - echo "$TCID : CONFIG_ZRAM is not set" - exit $ksft_skip -fi +run_zram diff --git a/tools/testing/selftests/zram/zram01.sh b/tools/testing/selftests/zram/zram01.sh index 114863d9fb87..8f4affe34f3e 100755 --- a/tools/testing/selftests/zram/zram01.sh +++ b/tools/testing/selftests/zram/zram01.sh @@ -33,9 +33,7 @@ zram_algs="lzo" zram_fill_fs() { - local mem_free0=$(free -m | awk 'NR==2 {print $4}') - - for i in $(seq 0 $(($dev_num - 1))); do + for i in $(seq $dev_start $dev_end); do echo "fill zram$i..." local b=0 while [ true ]; do @@ -45,29 +43,17 @@ zram_fill_fs() b=$(($b + 1)) done echo "zram$i can be filled with '$b' KB" - done - local mem_free1=$(free -m | awk 'NR==2 {print $4}') - local used_mem=$(($mem_free0 - $mem_free1)) + local mem_used_total=`awk '{print $3}' "/sys/block/zram$i/mm_stat"` + local v=$((100 * 1024 * $b / $mem_used_total)) + if [ "$v" -lt 100 ]; then + echo "FAIL compression ratio: 0.$v:1" + ERR_CODE=-1 + return + fi - local total_size=0 - for sm in $zram_sizes; do - local s=$(echo $sm | sed 's/M//') - total_size=$(($total_size + $s)) + echo "zram compression ratio: $(echo "scale=2; $v / 100 " | bc):1: OK" done - - echo "zram used ${used_mem}M, zram disk sizes ${total_size}M" - - local v=$((100 * $total_size / $used_mem)) - - if [ "$v" -lt 100 ]; then - echo "FAIL compression ratio: 0.$v:1" - ERR_CODE=-1 - zram_cleanup - return - fi - - echo "zram compression ratio: $(echo "scale=2; $v / 100 " | bc):1: OK" } check_prereqs @@ -81,7 +67,6 @@ zram_mount zram_fill_fs zram_cleanup -zram_unload if [ $ERR_CODE -ne 0 ]; then echo "$TCID : [FAIL]" diff --git a/tools/testing/selftests/zram/zram02.sh b/tools/testing/selftests/zram/zram02.sh index e83b404807c0..2418b0c4ed13 100755 --- a/tools/testing/selftests/zram/zram02.sh +++ b/tools/testing/selftests/zram/zram02.sh @@ -36,7 +36,6 @@ zram_set_memlimit zram_makeswap zram_swapoff zram_cleanup -zram_unload if [ $ERR_CODE -ne 0 ]; then echo "$TCID : [FAIL]" diff --git a/tools/testing/selftests/zram/zram_lib.sh b/tools/testing/selftests/zram/zram_lib.sh index 6f872f266fd1..21ec1966de76 100755 --- a/tools/testing/selftests/zram/zram_lib.sh +++ b/tools/testing/selftests/zram/zram_lib.sh @@ -5,12 +5,17 @@ # Author: Alexey Kodanev <alexey.kodanev@oracle.com> # Modified: Naresh Kamboju <naresh.kamboju@linaro.org> -MODULE=0 dev_makeswap=-1 dev_mounted=-1 - +dev_start=0 +dev_end=-1 +module_load=-1 +sys_control=-1 # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 +kernel_version=`uname -r | cut -d'.' -f1,2` +kernel_major=${kernel_version%.*} +kernel_minor=${kernel_version#*.} trap INT @@ -25,68 +30,104 @@ check_prereqs() fi } +kernel_gte() +{ + major=${1%.*} + minor=${1#*.} + + if [ $kernel_major -gt $major ]; then + return 0 + elif [[ $kernel_major -eq $major && $kernel_minor -ge $minor ]]; then + return 0 + fi + + return 1 +} + zram_cleanup() { echo "zram cleanup" local i= - for i in $(seq 0 $dev_makeswap); do + for i in $(seq $dev_start $dev_makeswap); do swapoff /dev/zram$i done - for i in $(seq 0 $dev_mounted); do + for i in $(seq $dev_start $dev_mounted); do umount /dev/zram$i done - for i in $(seq 0 $(($dev_num - 1))); do + for i in $(seq $dev_start $dev_end); do echo 1 > /sys/block/zram${i}/reset rm -rf zram$i done -} + if [ $sys_control -eq 1 ]; then + for i in $(seq $dev_start $dev_end); do + echo $i > /sys/class/zram-control/hot_remove + done + fi -zram_unload() -{ - if [ $MODULE -ne 0 ] ; then - echo "zram rmmod zram" + if [ $module_load -eq 1 ]; then rmmod zram > /dev/null 2>&1 fi } zram_load() { - # check zram module exists - MODULE_PATH=/lib/modules/`uname -r`/kernel/drivers/block/zram/zram.ko - if [ -f $MODULE_PATH ]; then - MODULE=1 - echo "create '$dev_num' zram device(s)" - modprobe zram num_devices=$dev_num - if [ $? -ne 0 ]; then - echo "failed to insert zram module" - exit 1 - fi - - dev_num_created=$(ls /dev/zram* | wc -w) + echo "create '$dev_num' zram device(s)" + + # zram module loaded, new kernel + if [ -d "/sys/class/zram-control" ]; then + echo "zram modules already loaded, kernel supports" \ + "zram-control interface" + dev_start=$(ls /dev/zram* | wc -w) + dev_end=$(($dev_start + $dev_num - 1)) + sys_control=1 + + for i in $(seq $dev_start $dev_end); do + cat /sys/class/zram-control/hot_add > /dev/null + done + + echo "all zram devices (/dev/zram$dev_start~$dev_end" \ + "successfully created" + return 0 + fi - if [ "$dev_num_created" -ne "$dev_num" ]; then - echo "unexpected num of devices: $dev_num_created" - ERR_CODE=-1 + # detect old kernel or built-in + modprobe zram num_devices=$dev_num + if [ ! -d "/sys/class/zram-control" ]; then + if grep -q '^zram' /proc/modules; then + rmmod zram > /dev/null 2>&1 + if [ $? -ne 0 ]; then + echo "zram module is being used on old kernel" \ + "without zram-control interface" + exit $ksft_skip + fi else - echo "zram load module successful" + echo "test needs CONFIG_ZRAM=m on old kernel without" \ + "zram-control interface" + exit $ksft_skip fi - elif [ -b /dev/zram0 ]; then - echo "/dev/zram0 device file found: OK" - else - echo "ERROR: No zram.ko module or no /dev/zram0 device found" - echo "$TCID : CONFIG_ZRAM is not set" - exit 1 + modprobe zram num_devices=$dev_num fi + + module_load=1 + dev_end=$(($dev_num - 1)) + echo "all zram devices (/dev/zram0~$dev_end) successfully created" } zram_max_streams() { echo "set max_comp_streams to zram device(s)" - local i=0 + kernel_gte 4.7 + if [ $? -eq 0 ]; then + echo "The device attribute max_comp_streams was"\ + "deprecated in 4.7" + return 0 + fi + + local i=$dev_start for max_s in $zram_max_streams; do local sys_path="/sys/block/zram${i}/max_comp_streams" echo $max_s > $sys_path || \ @@ -98,7 +139,7 @@ zram_max_streams() echo "FAIL can't set max_streams '$max_s', get $max_stream" i=$(($i + 1)) - echo "$sys_path = '$max_streams' ($i/$dev_num)" + echo "$sys_path = '$max_streams'" done echo "zram max streams: OK" @@ -108,15 +149,16 @@ zram_compress_alg() { echo "test that we can set compression algorithm" - local algs=$(cat /sys/block/zram0/comp_algorithm) + local i=$dev_start + local algs=$(cat /sys/block/zram${i}/comp_algorithm) echo "supported algs: $algs" - local i=0 + for alg in $zram_algs; do local sys_path="/sys/block/zram${i}/comp_algorithm" echo "$alg" > $sys_path || \ echo "FAIL can't set '$alg' to $sys_path" i=$(($i + 1)) - echo "$sys_path = '$alg' ($i/$dev_num)" + echo "$sys_path = '$alg'" done echo "zram set compression algorithm: OK" @@ -125,14 +167,14 @@ zram_compress_alg() zram_set_disksizes() { echo "set disk size to zram device(s)" - local i=0 + local i=$dev_start for ds in $zram_sizes; do local sys_path="/sys/block/zram${i}/disksize" echo "$ds" > $sys_path || \ echo "FAIL can't set '$ds' to $sys_path" i=$(($i + 1)) - echo "$sys_path = '$ds' ($i/$dev_num)" + echo "$sys_path = '$ds'" done echo "zram set disksizes: OK" @@ -142,14 +184,14 @@ zram_set_memlimit() { echo "set memory limit to zram device(s)" - local i=0 + local i=$dev_start for ds in $zram_mem_limits; do local sys_path="/sys/block/zram${i}/mem_limit" echo "$ds" > $sys_path || \ echo "FAIL can't set '$ds' to $sys_path" i=$(($i + 1)) - echo "$sys_path = '$ds' ($i/$dev_num)" + echo "$sys_path = '$ds'" done echo "zram set memory limit: OK" @@ -158,8 +200,8 @@ zram_set_memlimit() zram_makeswap() { echo "make swap with zram device(s)" - local i=0 - for i in $(seq 0 $(($dev_num - 1))); do + local i=$dev_start + for i in $(seq $dev_start $dev_end); do mkswap /dev/zram$i > err.log 2>&1 if [ $? -ne 0 ]; then cat err.log @@ -182,7 +224,7 @@ zram_makeswap() zram_swapoff() { local i= - for i in $(seq 0 $dev_makeswap); do + for i in $(seq $dev_start $dev_end); do swapoff /dev/zram$i > err.log 2>&1 if [ $? -ne 0 ]; then cat err.log @@ -196,7 +238,7 @@ zram_swapoff() zram_makefs() { - local i=0 + local i=$dev_start for fs in $zram_filesystems; do # if requested fs not supported default it to ext2 which mkfs.$fs > /dev/null 2>&1 || fs=ext2 @@ -215,7 +257,7 @@ zram_makefs() zram_mount() { local i=0 - for i in $(seq 0 $(($dev_num - 1))); do + for i in $(seq $dev_start $dev_end); do echo "mount /dev/zram$i" mkdir zram$i mount /dev/zram$i zram$i > /dev/null || \ |