diff --git a/Documentation/devicetree/bindings/bus/fsl,imx8qxp-pixel-link-msi-bus.yaml b/Documentation/devicetree/bindings/bus/fsl,imx8qxp-pixel-link-msi-bus.yaml index b568d0ce438d2..7e1ffc5510465 100644 --- a/Documentation/devicetree/bindings/bus/fsl,imx8qxp-pixel-link-msi-bus.yaml +++ b/Documentation/devicetree/bindings/bus/fsl,imx8qxp-pixel-link-msi-bus.yaml @@ -73,9 +73,6 @@ patternProperties: "^.*@[0-9a-f]+$": description: Devices attached to the bus type: object - properties: - reg: - maxItems: 1 required: - reg diff --git a/Documentation/devicetree/bindings/cache/andestech,ax45mp-cache.yaml b/Documentation/devicetree/bindings/cache/andestech,ax45mp-cache.yaml index 9ab5f0c435d4d..d2cbe49f4e15f 100644 --- a/Documentation/devicetree/bindings/cache/andestech,ax45mp-cache.yaml +++ b/Documentation/devicetree/bindings/cache/andestech,ax45mp-cache.yaml @@ -69,7 +69,7 @@ examples: - | #include - cache-controller@2010000 { + cache-controller@13400000 { compatible = "andestech,ax45mp-cache", "cache"; reg = <0x13400000 0x100000>; interrupts = <508 IRQ_TYPE_LEVEL_HIGH>; diff --git a/Documentation/devicetree/bindings/display/imx/fsl,imx6-hdmi.yaml b/Documentation/devicetree/bindings/display/imx/fsl,imx6-hdmi.yaml index af7fe9c4d1963..7979cf07f1199 100644 --- a/Documentation/devicetree/bindings/display/imx/fsl,imx6-hdmi.yaml +++ b/Documentation/devicetree/bindings/display/imx/fsl,imx6-hdmi.yaml @@ -87,7 +87,7 @@ required: - interrupts - ports -additionalProperties: false +unevaluatedProperties: false examples: - | diff --git a/Documentation/devicetree/bindings/media/i2c/sony,imx415.yaml b/Documentation/devicetree/bindings/media/i2c/sony,imx415.yaml index ffccf5f3c9e34..642f9b15d3597 100644 --- a/Documentation/devicetree/bindings/media/i2c/sony,imx415.yaml +++ b/Documentation/devicetree/bindings/media/i2c/sony,imx415.yaml @@ -54,6 +54,7 @@ properties: port: $ref: /schemas/graph.yaml#/$defs/port-base + unevaluatedProperties: false properties: endpoint: diff --git a/Documentation/devicetree/bindings/media/i2c/toshiba,tc358746.yaml b/Documentation/devicetree/bindings/media/i2c/toshiba,tc358746.yaml index c5cab549ee8ea..1c476b635b690 100644 --- a/Documentation/devicetree/bindings/media/i2c/toshiba,tc358746.yaml +++ b/Documentation/devicetree/bindings/media/i2c/toshiba,tc358746.yaml @@ -69,6 +69,7 @@ properties: properties: port@0: $ref: /schemas/graph.yaml#/$defs/port-base + unevaluatedProperties: false description: Input port properties: @@ -89,6 +90,7 @@ properties: port@1: $ref: /schemas/graph.yaml#/$defs/port-base + unevaluatedProperties: false description: Output port properties: diff --git a/Documentation/devicetree/bindings/media/nxp,imx7-csi.yaml b/Documentation/devicetree/bindings/media/nxp,imx7-csi.yaml index 358019e85d907..326284e151f66 100644 --- a/Documentation/devicetree/bindings/media/nxp,imx7-csi.yaml +++ b/Documentation/devicetree/bindings/media/nxp,imx7-csi.yaml @@ -59,7 +59,6 @@ allOf: compatible: contains: enum: - - fsl,imx8mq-csi - fsl,imx8mm-csi then: required: diff --git a/Documentation/devicetree/bindings/media/renesas,vin.yaml b/Documentation/devicetree/bindings/media/renesas,vin.yaml index 324703bfb1bde..5539d0f8e74d2 100644 --- a/Documentation/devicetree/bindings/media/renesas,vin.yaml +++ b/Documentation/devicetree/bindings/media/renesas,vin.yaml @@ -95,7 +95,7 @@ properties: synchronization is selected. default: 1 - field-active-even: true + field-even-active: true bus-width: true @@ -144,7 +144,7 @@ properties: synchronization is selected. default: 1 - field-active-even: true + field-even-active: true bus-width: true diff --git a/Documentation/devicetree/bindings/media/samsung,fimc.yaml b/Documentation/devicetree/bindings/media/samsung,fimc.yaml index 79ff6d83a9fd6..b3486c38a05b9 100644 --- a/Documentation/devicetree/bindings/media/samsung,fimc.yaml +++ b/Documentation/devicetree/bindings/media/samsung,fimc.yaml @@ -57,6 +57,7 @@ properties: patternProperties: "^port@[01]$": $ref: /schemas/graph.yaml#/$defs/port-base + unevaluatedProperties: false description: Camera A and camera B inputs. diff --git a/Documentation/devicetree/bindings/pci/brcm,iproc-pcie.yaml b/Documentation/devicetree/bindings/pci/brcm,iproc-pcie.yaml index 0972868735fca..0e07ab61a48d2 100644 --- a/Documentation/devicetree/bindings/pci/brcm,iproc-pcie.yaml +++ b/Documentation/devicetree/bindings/pci/brcm,iproc-pcie.yaml @@ -12,7 +12,6 @@ maintainers: allOf: - $ref: /schemas/pci/pci-bus.yaml# - - $ref: /schemas/interrupt-controller/msi-controller.yaml# properties: compatible: @@ -34,13 +33,6 @@ properties: description: > Base address and length of the PCIe controller I/O register space - interrupt-map: true - - interrupt-map-mask: true - - "#interrupt-cells": - const: 1 - ranges: minItems: 1 maxItems: 2 @@ -54,16 +46,8 @@ properties: items: - const: pcie-phy - bus-range: true - dma-coherent: true - "#address-cells": true - - "#size-cells": true - - device_type: true - brcm,pcie-ob: type: boolean description: > @@ -78,20 +62,24 @@ properties: msi: type: object + $ref: /schemas/interrupt-controller/msi-controller.yaml# + unevaluatedProperties: false + properties: compatible: items: - const: brcm,iproc-msi - msi-parent: true + interrupts: + maxItems: 4 - msi-controller: true + brcm,pcie-msi-inten: + type: boolean + description: + Needs to be present for some older iProc platforms that require the + interrupt enable registers to be set explicitly to enable MSI - brcm,pcie-msi-inten: - type: boolean - description: > - Needs to be present for some older iProc platforms that require the - interrupt enable registers to be set explicitly to enable MSI + msi-parent: true dependencies: brcm,pcie-ob-axi-offset: ["brcm,pcie-ob"] @@ -117,68 +105,69 @@ unevaluatedProperties: false examples: - | - #include - - bus { - #address-cells = <1>; - #size-cells = <1>; - pcie0: pcie@18012000 { - compatible = "brcm,iproc-pcie"; - reg = <0x18012000 0x1000>; - - #interrupt-cells = <1>; - interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &gic GIC_SPI 100 IRQ_TYPE_NONE>; - - linux,pci-domain = <0>; - - bus-range = <0x00 0xff>; - - #address-cells = <3>; - #size-cells = <2>; - device_type = "pci"; - ranges = <0x81000000 0 0 0x28000000 0 0x00010000>, - <0x82000000 0 0x20000000 0x20000000 0 0x04000000>; - - phys = <&phy 0 5>; - phy-names = "pcie-phy"; - - brcm,pcie-ob; - brcm,pcie-ob-axi-offset = <0x00000000>; - - msi-parent = <&msi0>; - - /* iProc event queue based MSI */ - msi0: msi { - compatible = "brcm,iproc-msi"; - msi-controller; - interrupt-parent = <&gic>; - interrupts = , - , - , - ; - }; - }; - - pcie1: pcie@18013000 { - compatible = "brcm,iproc-pcie"; - reg = <0x18013000 0x1000>; - - #interrupt-cells = <1>; - interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &gic GIC_SPI 106 IRQ_TYPE_NONE>; - - linux,pci-domain = <1>; - - bus-range = <0x00 0xff>; - - #address-cells = <3>; - #size-cells = <2>; - device_type = "pci"; - ranges = <0x81000000 0 0 0x48000000 0 0x00010000>, - <0x82000000 0 0x40000000 0x40000000 0 0x04000000>; - - phys = <&phy 1 6>; - phy-names = "pcie-phy"; - }; + #include + + gic: interrupt-controller { + interrupt-controller; + #interrupt-cells = <3>; + }; + + pcie@18012000 { + compatible = "brcm,iproc-pcie"; + reg = <0x18012000 0x1000>; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0>; + interrupt-map = <0 0 0 0 &gic GIC_SPI 100 IRQ_TYPE_NONE>; + + linux,pci-domain = <0>; + + bus-range = <0x00 0xff>; + + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + ranges = <0x81000000 0 0 0x28000000 0 0x00010000>, + <0x82000000 0 0x20000000 0x20000000 0 0x04000000>; + + phys = <&phy 0 5>; + phy-names = "pcie-phy"; + + brcm,pcie-ob; + brcm,pcie-ob-axi-offset = <0x00000000>; + + msi-parent = <&msi0>; + + /* iProc event queue based MSI */ + msi0: msi { + compatible = "brcm,iproc-msi"; + msi-controller; + interrupt-parent = <&gic>; + interrupts = , + , + , + ; + }; + }; + - | + pcie@18013000 { + compatible = "brcm,iproc-pcie"; + reg = <0x18013000 0x1000>; + + #interrupt-cells = <1>; + interrupt-map-mask = <0 0 0 0>; + interrupt-map = <0 0 0 0 &gic GIC_SPI 106 IRQ_TYPE_NONE>; + + linux,pci-domain = <1>; + + bus-range = <0x00 0xff>; + + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; + ranges = <0x81000000 0 0 0x48000000 0 0x00010000>, + <0x82000000 0 0x40000000 0x40000000 0 0x04000000>; + + phys = <&phy 1 6>; + phy-names = "pcie-phy"; }; diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml index 38c0b5213736a..97e8441eda1c2 100644 --- a/Documentation/devicetree/bindings/riscv/cpus.yaml +++ b/Documentation/devicetree/bindings/riscv/cpus.yaml @@ -91,6 +91,7 @@ properties: interrupt-controller: type: object + additionalProperties: false description: Describes the CPU's local interrupt controller properties: diff --git a/Documentation/devicetree/bindings/trivial-devices.yaml b/Documentation/devicetree/bindings/trivial-devices.yaml index cd58179ae3379..430a814f64a56 100644 --- a/Documentation/devicetree/bindings/trivial-devices.yaml +++ b/Documentation/devicetree/bindings/trivial-devices.yaml @@ -232,7 +232,7 @@ properties: # MEMSIC magnetometer - memsic,mmc35240 # MEMSIC 3-axis accelerometer - - memsic,mx4005 + - memsic,mxc4005 # MEMSIC 2-axis 8-bit digital accelerometer - memsic,mxc6225 # MEMSIC 2-axis 8-bit digital accelerometer diff --git a/MAINTAINERS b/MAINTAINERS index 81d5fc0bba68f..6c4cce45a09db 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5984,8 +5984,8 @@ F: include/linux/devm-helpers.h DEVICE-MAPPER (LVM) M: Alasdair Kergon M: Mike Snitzer -M: dm-devel@redhat.com -L: dm-devel@redhat.com +M: dm-devel@lists.linux.dev +L: dm-devel@lists.linux.dev S: Maintained W: http://sources.redhat.com/dm Q: http://patchwork.kernel.org/project/dm-devel/list/ diff --git a/Makefile b/Makefile index 373649c7374ee..88ebf65479644 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 6 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h index 6d28b5514699a..ee9e071859b2f 100644 --- a/arch/parisc/include/asm/ldcw.h +++ b/arch/parisc/include/asm/ldcw.h @@ -2,39 +2,42 @@ #ifndef __PARISC_LDCW_H #define __PARISC_LDCW_H -#ifndef CONFIG_PA20 /* Because kmalloc only guarantees 8-byte alignment for kmalloc'd data, and GCC only guarantees 8-byte alignment for stack locals, we can't be assured of 16-byte alignment for atomic lock data even if we specify "__attribute ((aligned(16)))" in the type declaration. So, we use a struct containing an array of four ints for the atomic lock type and dynamically select the 16-byte aligned int from the array - for the semaphore. */ + for the semaphore. */ + +/* From: "Jim Hull" + I've attached a summary of the change, but basically, for PA 2.0, as + long as the ",CO" (coherent operation) completer is implemented, then the + 16-byte alignment requirement for ldcw and ldcd is relaxed, and instead + they only require "natural" alignment (4-byte for ldcw, 8-byte for + ldcd). + + Although the cache control hint is accepted by all PA 2.0 processors, + it is only implemented on PA8800/PA8900 CPUs. Prior PA8X00 CPUs still + require 16-byte alignment. If the address is unaligned, the operation + of the instruction is undefined. The ldcw instruction does not generate + unaligned data reference traps so misaligned accesses are not detected. + This hid the problem for years. So, restore the 16-byte alignment dropped + by Kyle McMartin in "Remove __ldcw_align for PA-RISC 2.0 processors". */ #define __PA_LDCW_ALIGNMENT 16 -#define __PA_LDCW_ALIGN_ORDER 4 #define __ldcw_align(a) ({ \ unsigned long __ret = (unsigned long) &(a)->lock[0]; \ __ret = (__ret + __PA_LDCW_ALIGNMENT - 1) \ & ~(__PA_LDCW_ALIGNMENT - 1); \ (volatile unsigned int *) __ret; \ }) -#define __LDCW "ldcw" -#else /*CONFIG_PA20*/ -/* From: "Jim Hull" - I've attached a summary of the change, but basically, for PA 2.0, as - long as the ",CO" (coherent operation) completer is specified, then the - 16-byte alignment requirement for ldcw and ldcd is relaxed, and instead - they only require "natural" alignment (4-byte for ldcw, 8-byte for - ldcd). */ - -#define __PA_LDCW_ALIGNMENT 4 -#define __PA_LDCW_ALIGN_ORDER 2 -#define __ldcw_align(a) (&(a)->slock) +#ifdef CONFIG_PA20 #define __LDCW "ldcw,co" - -#endif /*!CONFIG_PA20*/ +#else +#define __LDCW "ldcw" +#endif /* LDCW, the only atomic read-write operation PA-RISC has. *sigh*. We don't explicitly expose that "*a" may be written as reload diff --git a/arch/parisc/include/asm/spinlock_types.h b/arch/parisc/include/asm/spinlock_types.h index efd06a897c6a3..7b986b09dba84 100644 --- a/arch/parisc/include/asm/spinlock_types.h +++ b/arch/parisc/include/asm/spinlock_types.h @@ -9,15 +9,10 @@ #ifndef __ASSEMBLY__ typedef struct { -#ifdef CONFIG_PA20 - volatile unsigned int slock; -# define __ARCH_SPIN_LOCK_UNLOCKED { __ARCH_SPIN_LOCK_UNLOCKED_VAL } -#else volatile unsigned int lock[4]; # define __ARCH_SPIN_LOCK_UNLOCKED \ { { __ARCH_SPIN_LOCK_UNLOCKED_VAL, __ARCH_SPIN_LOCK_UNLOCKED_VAL, \ __ARCH_SPIN_LOCK_UNLOCKED_VAL, __ARCH_SPIN_LOCK_UNLOCKED_VAL } } -#endif } arch_spinlock_t; diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index 4098f9a0964b9..2019c1f04bd03 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -440,7 +440,9 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) if (cpu_online(cpu)) return 0; - if (num_online_cpus() < setup_max_cpus && smp_boot_one_cpu(cpu, tidle)) + if (num_online_cpus() < nr_cpu_ids && + num_online_cpus() < setup_max_cpus && + smp_boot_one_cpu(cpu, tidle)) return -EIO; return cpu_online(cpu) ? 0 : -EIO; diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index 2eabccde94fb3..dcf325b7b0229 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -256,7 +256,7 @@ static int __sev_cpuid_hv(u32 fn, int reg_idx, u32 *reg) return 0; } -static int sev_cpuid_hv(struct cpuid_leaf *leaf) +static int __sev_cpuid_hv_msr(struct cpuid_leaf *leaf) { int ret; @@ -279,6 +279,45 @@ static int sev_cpuid_hv(struct cpuid_leaf *leaf) return ret; } +static int __sev_cpuid_hv_ghcb(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) +{ + u32 cr4 = native_read_cr4(); + int ret; + + ghcb_set_rax(ghcb, leaf->fn); + ghcb_set_rcx(ghcb, leaf->subfn); + + if (cr4 & X86_CR4_OSXSAVE) + /* Safe to read xcr0 */ + ghcb_set_xcr0(ghcb, xgetbv(XCR_XFEATURE_ENABLED_MASK)); + else + /* xgetbv will cause #UD - use reset value for xcr0 */ + ghcb_set_xcr0(ghcb, 1); + + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_CPUID, 0, 0); + if (ret != ES_OK) + return ret; + + if (!(ghcb_rax_is_valid(ghcb) && + ghcb_rbx_is_valid(ghcb) && + ghcb_rcx_is_valid(ghcb) && + ghcb_rdx_is_valid(ghcb))) + return ES_VMM_ERROR; + + leaf->eax = ghcb->save.rax; + leaf->ebx = ghcb->save.rbx; + leaf->ecx = ghcb->save.rcx; + leaf->edx = ghcb->save.rdx; + + return ES_OK; +} + +static int sev_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) +{ + return ghcb ? __sev_cpuid_hv_ghcb(ghcb, ctxt, leaf) + : __sev_cpuid_hv_msr(leaf); +} + /* * This may be called early while still running on the initial identity * mapping. Use RIP-relative addressing to obtain the correct address @@ -388,19 +427,20 @@ snp_cpuid_get_validated_func(struct cpuid_leaf *leaf) return false; } -static void snp_cpuid_hv(struct cpuid_leaf *leaf) +static void snp_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) { - if (sev_cpuid_hv(leaf)) + if (sev_cpuid_hv(ghcb, ctxt, leaf)) sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID_HV); } -static int snp_cpuid_postprocess(struct cpuid_leaf *leaf) +static int snp_cpuid_postprocess(struct ghcb *ghcb, struct es_em_ctxt *ctxt, + struct cpuid_leaf *leaf) { struct cpuid_leaf leaf_hv = *leaf; switch (leaf->fn) { case 0x1: - snp_cpuid_hv(&leaf_hv); + snp_cpuid_hv(ghcb, ctxt, &leaf_hv); /* initial APIC ID */ leaf->ebx = (leaf_hv.ebx & GENMASK(31, 24)) | (leaf->ebx & GENMASK(23, 0)); @@ -419,7 +459,7 @@ static int snp_cpuid_postprocess(struct cpuid_leaf *leaf) break; case 0xB: leaf_hv.subfn = 0; - snp_cpuid_hv(&leaf_hv); + snp_cpuid_hv(ghcb, ctxt, &leaf_hv); /* extended APIC ID */ leaf->edx = leaf_hv.edx; @@ -467,7 +507,7 @@ static int snp_cpuid_postprocess(struct cpuid_leaf *leaf) } break; case 0x8000001E: - snp_cpuid_hv(&leaf_hv); + snp_cpuid_hv(ghcb, ctxt, &leaf_hv); /* extended APIC ID */ leaf->eax = leaf_hv.eax; @@ -488,7 +528,7 @@ static int snp_cpuid_postprocess(struct cpuid_leaf *leaf) * Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value * should be treated as fatal by caller. */ -static int snp_cpuid(struct cpuid_leaf *leaf) +static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) { const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); @@ -522,7 +562,7 @@ static int snp_cpuid(struct cpuid_leaf *leaf) return 0; } - return snp_cpuid_postprocess(leaf); + return snp_cpuid_postprocess(ghcb, ctxt, leaf); } /* @@ -544,14 +584,14 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) leaf.fn = fn; leaf.subfn = subfn; - ret = snp_cpuid(&leaf); + ret = snp_cpuid(NULL, NULL, &leaf); if (!ret) goto cpuid_done; if (ret != -EOPNOTSUPP) goto fail; - if (sev_cpuid_hv(&leaf)) + if (__sev_cpuid_hv_msr(&leaf)) goto fail; cpuid_done: @@ -848,14 +888,15 @@ static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ret; } -static int vc_handle_cpuid_snp(struct pt_regs *regs) +static int vc_handle_cpuid_snp(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { + struct pt_regs *regs = ctxt->regs; struct cpuid_leaf leaf; int ret; leaf.fn = regs->ax; leaf.subfn = regs->cx; - ret = snp_cpuid(&leaf); + ret = snp_cpuid(ghcb, ctxt, &leaf); if (!ret) { regs->ax = leaf.eax; regs->bx = leaf.ebx; @@ -874,7 +915,7 @@ static enum es_result vc_handle_cpuid(struct ghcb *ghcb, enum es_result ret; int snp_cpuid_ret; - snp_cpuid_ret = vc_handle_cpuid_snp(regs); + snp_cpuid_ret = vc_handle_cpuid_snp(ghcb, ctxt); if (!snp_cpuid_ret) return ES_OK; if (snp_cpuid_ret != -EOPNOTSUPP) diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index 2787826d9f607..d8c1e3be74c0b 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -868,8 +868,7 @@ void snp_set_memory_private(unsigned long vaddr, unsigned long npages) void snp_accept_memory(phys_addr_t start, phys_addr_t end) { - unsigned long vaddr; - unsigned int npages; + unsigned long vaddr, npages; if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) return; diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c index da33bbbdacb95..58f107194fdaf 100644 --- a/drivers/gpio/gpio-aspeed.c +++ b/drivers/gpio/gpio-aspeed.c @@ -973,7 +973,7 @@ static int aspeed_gpio_set_config(struct gpio_chip *chip, unsigned int offset, else if (param == PIN_CONFIG_BIAS_DISABLE || param == PIN_CONFIG_BIAS_PULL_DOWN || param == PIN_CONFIG_DRIVE_STRENGTH) - return pinctrl_gpio_set_config(offset, config); + return pinctrl_gpio_set_config(chip->base + offset, config); else if (param == PIN_CONFIG_DRIVE_OPEN_DRAIN || param == PIN_CONFIG_DRIVE_OPEN_SOURCE) /* Return -ENOTSUPP to trigger emulation, as per datasheet */ diff --git a/drivers/gpio/gpio-pxa.c b/drivers/gpio/gpio-pxa.c index 7e9f7a32d3ee5..cae9661862fe1 100644 --- a/drivers/gpio/gpio-pxa.c +++ b/drivers/gpio/gpio-pxa.c @@ -237,6 +237,7 @@ static bool pxa_gpio_has_pinctrl(void) switch (gpio_type) { case PXA3XX_GPIO: case MMP2_GPIO: + case MMP_GPIO: return false; default: diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index c343edf2f6640..1e2cd7c8716e8 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -4968,7 +4968,7 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, int err = 0; struct sockaddr *addr = (struct sockaddr *)&mc->addr; struct net_device *ndev = NULL; - struct ib_sa_multicast ib; + struct ib_sa_multicast ib = {}; enum ib_gid_type gid_type; bool send_only; diff --git a/drivers/infiniband/core/cma_configfs.c b/drivers/infiniband/core/cma_configfs.c index 7b68b3ea979f7..f2fb2d8a65970 100644 --- a/drivers/infiniband/core/cma_configfs.c +++ b/drivers/infiniband/core/cma_configfs.c @@ -217,7 +217,7 @@ static int make_cma_ports(struct cma_dev_group *cma_dev_group, return -ENOMEM; for (i = 0; i < ports_num; i++) { - char port_str[10]; + char port_str[11]; ports[i].port_num = i + 1; snprintf(port_str, sizeof(port_str), "%u", i + 1); diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index d5d3e4f0de779..6d1dbc9787590 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -2529,6 +2529,7 @@ static const struct rdma_nl_cbs nldev_cb_table[RDMA_NLDEV_NUM_OPS] = { }, [RDMA_NLDEV_CMD_SYS_SET] = { .doit = nldev_set_sys_set_doit, + .flags = RDMA_NL_ADMIN_PERM, }, [RDMA_NLDEV_CMD_STAT_SET] = { .doit = nldev_stat_set_doit, diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index bf800f8cb3e4b..495d5a5d0373f 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -546,7 +546,7 @@ static ssize_t verify_hdr(struct ib_uverbs_cmd_hdr *hdr, if (hdr->in_words * 4 != count) return -EINVAL; - if (count < method_elm->req_size + sizeof(hdr)) { + if (count < method_elm->req_size + sizeof(*hdr)) { /* * rdma-core v18 and v19 have a bug where they send DESTROY_CQ * with a 16 byte write instead of 24. Old kernels didn't diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 0848c2c2ffcf2..faa88d12ee868 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -910,6 +910,10 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp, struct ib_udata *udata) list_del(&qp->list); mutex_unlock(&rdev->qp_lock); atomic_dec(&rdev->stats.res.qp_count); + if (qp->qplib_qp.type == CMDQ_CREATE_QP_TYPE_RC) + atomic_dec(&rdev->stats.res.rc_qp_count); + else if (qp->qplib_qp.type == CMDQ_CREATE_QP_TYPE_UD) + atomic_dec(&rdev->stats.res.ud_qp_count); ib_umem_release(qp->rumem); ib_umem_release(qp->sumem); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c index c8c4017fe4059..e47b4ca64d33e 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c @@ -665,7 +665,6 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw, blocked = cookie & RCFW_CMD_IS_BLOCKING; cookie &= RCFW_MAX_COOKIE_VALUE; crsqe = &rcfw->crsqe_tbl[cookie]; - crsqe->is_in_used = false; if (WARN_ONCE(test_bit(FIRMWARE_STALL_DETECTED, &rcfw->cmdq.flags), @@ -681,8 +680,14 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw, atomic_dec(&rcfw->timeout_send); if (crsqe->is_waiter_alive) { - if (crsqe->resp) + if (crsqe->resp) { memcpy(crsqe->resp, qp_event, sizeof(*qp_event)); + /* Insert write memory barrier to ensure that + * response data is copied before clearing the + * flags + */ + smp_wmb(); + } if (!blocked) wait_cmds++; } @@ -694,6 +699,8 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw, if (!is_waiter_alive) crsqe->resp = NULL; + crsqe->is_in_used = false; + hwq->cons += req_size; /* This is a case to handle below scenario - diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index ced615b5ea096..040ba2224f9ff 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -1965,6 +1965,9 @@ static int send_fw_act_open_req(struct c4iw_ep *ep, unsigned int atid) int win; skb = get_skb(NULL, sizeof(*req), GFP_KERNEL); + if (!skb) + return -ENOMEM; + req = __skb_put_zero(skb, sizeof(*req)); req->op_compl = htonl(WR_OP_V(FW_OFLD_CONNECTION_WR)); req->len16_pkd = htonl(FW_WR_LEN16_V(DIV_ROUND_UP(sizeof(*req), 16))); diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.c b/drivers/infiniband/hw/erdma/erdma_verbs.c index dcccb60152323..c317947563fbc 100644 --- a/drivers/infiniband/hw/erdma/erdma_verbs.c +++ b/drivers/infiniband/hw/erdma/erdma_verbs.c @@ -133,8 +133,8 @@ static int create_qp_cmd(struct erdma_ucontext *uctx, struct erdma_qp *qp) static int regmr_cmd(struct erdma_dev *dev, struct erdma_mr *mr) { struct erdma_pd *pd = to_epd(mr->ibmr.pd); + u32 mtt_level = ERDMA_MR_MTT_0LEVEL; struct erdma_cmdq_reg_mr_req req; - u32 mtt_level; erdma_cmdq_build_reqhdr(&req.hdr, CMDQ_SUBMOD_RDMA, CMDQ_OPCODE_REG_MR); @@ -147,10 +147,9 @@ static int regmr_cmd(struct erdma_dev *dev, struct erdma_mr *mr) req.phy_addr[0] = sg_dma_address(mr->mem.mtt->sglist); mtt_level = mr->mem.mtt->level; } - } else { + } else if (mr->type != ERDMA_MR_TYPE_DMA) { memcpy(req.phy_addr, mr->mem.mtt->buf, MTT_SIZE(mr->mem.page_cnt)); - mtt_level = ERDMA_MR_MTT_0LEVEL; } req.cfg0 = FIELD_PREP(ERDMA_CMD_MR_VALID_MASK, mr->valid) | @@ -655,7 +654,7 @@ static struct erdma_mtt *erdma_create_scatter_mtt(struct erdma_dev *dev, mtt = kzalloc(sizeof(*mtt), GFP_KERNEL); if (!mtt) - return NULL; + return ERR_PTR(-ENOMEM); mtt->size = ALIGN(size, PAGE_SIZE); mtt->buf = vzalloc(mtt->size); diff --git a/drivers/infiniband/hw/mlx4/sysfs.c b/drivers/infiniband/hw/mlx4/sysfs.c index 24ee79aa2122e..88f534cf690e9 100644 --- a/drivers/infiniband/hw/mlx4/sysfs.c +++ b/drivers/infiniband/hw/mlx4/sysfs.c @@ -223,7 +223,7 @@ void del_sysfs_port_mcg_attr(struct mlx4_ib_dev *device, int port_num, static int add_port_entries(struct mlx4_ib_dev *device, int port_num) { int i; - char buff[11]; + char buff[12]; struct mlx4_ib_iov_port *port = NULL; int ret = 0 ; struct ib_port_attr attr; diff --git a/drivers/infiniband/hw/mlx5/fs.c b/drivers/infiniband/hw/mlx5/fs.c index 1e419e080b535..520034acf73aa 100644 --- a/drivers/infiniband/hw/mlx5/fs.c +++ b/drivers/infiniband/hw/mlx5/fs.c @@ -2470,8 +2470,8 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_STEERING_ANCHOR_CREATE)( mlx5_steering_anchor_destroy_res(ft_prio); put_flow_table: put_flow_table(dev, ft_prio, true); - mutex_unlock(&dev->flow_db->lock); free_obj: + mutex_unlock(&dev->flow_db->lock); kfree(obj); return err; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index aed5cdea50e6c..555629b798b95 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -2084,7 +2084,7 @@ static inline char *mmap_cmd2str(enum mlx5_ib_mmap_cmd cmd) case MLX5_IB_MMAP_DEVICE_MEM: return "Device Memory"; default: - return NULL; + return "Unknown"; } } diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 3e345ef380f17..8a3762d9ff58c 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -301,7 +301,8 @@ static int get_mkc_octo_size(unsigned int access_mode, unsigned int ndescs) static void set_cache_mkc(struct mlx5_cache_ent *ent, void *mkc) { - set_mkc_access_pd_addr_fields(mkc, 0, 0, ent->dev->umrc.pd); + set_mkc_access_pd_addr_fields(mkc, ent->rb_key.access_flags, 0, + ent->dev->umrc.pd); MLX5_SET(mkc, mkc, free, 1); MLX5_SET(mkc, mkc, umr_en, 1); MLX5_SET(mkc, mkc, access_mode_1_0, ent->rb_key.access_mode & 0x3); @@ -1024,19 +1025,26 @@ void mlx5_mkey_cache_cleanup(struct mlx5_ib_dev *dev) if (!dev->cache.wq) return; - cancel_delayed_work_sync(&dev->cache.remove_ent_dwork); mutex_lock(&dev->cache.rb_lock); for (node = rb_first(root); node; node = rb_next(node)) { ent = rb_entry(node, struct mlx5_cache_ent, node); xa_lock_irq(&ent->mkeys); ent->disabled = true; xa_unlock_irq(&ent->mkeys); - cancel_delayed_work_sync(&ent->dwork); } + mutex_unlock(&dev->cache.rb_lock); + + /* + * After all entries are disabled and will not reschedule on WQ, + * flush it and all async commands. + */ + flush_workqueue(dev->cache.wq); mlx5_mkey_cache_debugfs_cleanup(dev); mlx5_cmd_cleanup_async_ctx(&dev->async_ctx); + /* At this point all entries are disabled and have no concurrent work. */ + mutex_lock(&dev->cache.rb_lock); node = rb_first(root); while (node) { ent = rb_entry(node, struct mlx5_cache_ent, node); diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c index a2605178f4eda..43e776073f49f 100644 --- a/drivers/infiniband/sw/siw/siw_cm.c +++ b/drivers/infiniband/sw/siw/siw_cm.c @@ -976,6 +976,7 @@ static void siw_accept_newconn(struct siw_cep *cep) siw_cep_put(cep); new_cep->listen_cep = NULL; if (rv) { + siw_cancel_mpatimer(new_cep); siw_cep_set_free(new_cep); goto error; } @@ -1100,9 +1101,12 @@ static void siw_cm_work_handler(struct work_struct *w) /* * Socket close before MPA request received. */ - siw_dbg_cep(cep, "no mpareq: drop listener\n"); - siw_cep_put(cep->listen_cep); - cep->listen_cep = NULL; + if (cep->listen_cep) { + siw_dbg_cep(cep, + "no mpareq: drop listener\n"); + siw_cep_put(cep->listen_cep); + cep->listen_cep = NULL; + } } } release_cep = 1; @@ -1227,7 +1231,11 @@ static void siw_cm_llp_data_ready(struct sock *sk) if (!cep) goto out; - siw_dbg_cep(cep, "state: %d\n", cep->state); + siw_dbg_cep(cep, "cep state: %d, socket state %d\n", + cep->state, sk->sk_state); + + if (sk->sk_state != TCP_ESTABLISHED) + goto out; switch (cep->state) { case SIW_EPSTATE_RDMA_MODE: diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 1574218764e0a..2916e77f589b8 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -2784,7 +2784,6 @@ static int srp_abort(struct scsi_cmnd *scmnd) u32 tag; u16 ch_idx; struct srp_rdma_ch *ch; - int ret; shost_printk(KERN_ERR, target->scsi_host, "SRP abort called\n"); @@ -2798,19 +2797,14 @@ static int srp_abort(struct scsi_cmnd *scmnd) shost_printk(KERN_ERR, target->scsi_host, "Sending SRP abort for tag %#x\n", tag); if (srp_send_tsk_mgmt(ch, tag, scmnd->device->lun, - SRP_TSK_ABORT_TASK, NULL) == 0) - ret = SUCCESS; - else if (target->rport->state == SRP_RPORT_LOST) - ret = FAST_IO_FAIL; - else - ret = FAILED; - if (ret == SUCCESS) { + SRP_TSK_ABORT_TASK, NULL) == 0) { srp_free_req(ch, req, scmnd, 0); - scmnd->result = DID_ABORT << 16; - scsi_done(scmnd); + return SUCCESS; } + if (target->rport->state == SRP_RPORT_LOST) + return FAST_IO_FAIL; - return ret; + return FAILED; } static int srp_reset_device(struct scsi_cmnd *scmnd) diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index ad8e670a2f9be..b487f7acc860f 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -748,17 +748,16 @@ static int dmz_get_zoned_device(struct dm_target *ti, char *path, /* * Cleanup zoned device information. */ -static void dmz_put_zoned_device(struct dm_target *ti) +static void dmz_put_zoned_devices(struct dm_target *ti) { struct dmz_target *dmz = ti->private; int i; - for (i = 0; i < dmz->nr_ddevs; i++) { - if (dmz->ddev[i]) { + for (i = 0; i < dmz->nr_ddevs; i++) + if (dmz->ddev[i]) dm_put_device(ti, dmz->ddev[i]); - dmz->ddev[i] = NULL; - } - } + + kfree(dmz->ddev); } static int dmz_fixup_devices(struct dm_target *ti) @@ -948,7 +947,7 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv) err_meta: dmz_dtr_metadata(dmz->metadata); err_dev: - dmz_put_zoned_device(ti); + dmz_put_zoned_devices(ti); err: kfree(dmz->dev); kfree(dmz); @@ -978,7 +977,7 @@ static void dmz_dtr(struct dm_target *ti) bioset_exit(&dmz->bio_set); - dmz_put_zoned_device(ti); + dmz_put_zoned_devices(ti); mutex_destroy(&dmz->chunk_lock); diff --git a/drivers/media/pci/intel/Kconfig b/drivers/media/pci/intel/Kconfig index e113902fa8064..ee4684159d3de 100644 --- a/drivers/media/pci/intel/Kconfig +++ b/drivers/media/pci/intel/Kconfig @@ -1,11 +1,19 @@ # SPDX-License-Identifier: GPL-2.0-only + +source "drivers/media/pci/intel/ipu3/Kconfig" +source "drivers/media/pci/intel/ivsc/Kconfig" + config IPU_BRIDGE - tristate + tristate "Intel IPU Bridge" depends on I2C && ACPI help - This is a helper module for the IPU bridge, which can be - used by ipu3 and other drivers. In order to handle module - dependencies, this is selected by each driver that needs it. + The IPU bridge is a helper library for Intel IPU drivers to + function on systems shipped with Windows. -source "drivers/media/pci/intel/ipu3/Kconfig" -source "drivers/media/pci/intel/ivsc/Kconfig" + Currently used by the ipu3-cio2 and atomisp drivers. + + Supported systems include: + + - Microsoft Surface models (except Surface Pro 3) + - The Lenovo Miix line (for example the 510, 520, 710 and 720) + - Dell 7285 diff --git a/drivers/media/pci/intel/ipu3/Kconfig b/drivers/media/pci/intel/ipu3/Kconfig index 0951545eab21a..c0a250daa9270 100644 --- a/drivers/media/pci/intel/ipu3/Kconfig +++ b/drivers/media/pci/intel/ipu3/Kconfig @@ -2,13 +2,13 @@ config VIDEO_IPU3_CIO2 tristate "Intel ipu3-cio2 driver" depends on VIDEO_DEV && PCI + depends on IPU_BRIDGE || !IPU_BRIDGE depends on ACPI || COMPILE_TEST depends on X86 select MEDIA_CONTROLLER select VIDEO_V4L2_SUBDEV_API select V4L2_FWNODE select VIDEOBUF2_DMA_SG - select IPU_BRIDGE if CIO2_BRIDGE help This is the Intel IPU3 CIO2 CSI-2 receiver unit, found in Intel @@ -18,22 +18,3 @@ config VIDEO_IPU3_CIO2 Say Y or M here if you have a Skylake/Kaby Lake SoC with MIPI CSI-2 connected camera. The module will be called ipu3-cio2. - -config CIO2_BRIDGE - bool "IPU3 CIO2 Sensors Bridge" - depends on VIDEO_IPU3_CIO2 && ACPI - depends on I2C - help - This extension provides an API for the ipu3-cio2 driver to create - connections to cameras that are hidden in the SSDB buffer in ACPI. - It can be used to enable support for cameras in detachable / hybrid - devices that ship with Windows. - - Say Y here if your device is a detachable / hybrid laptop that comes - with Windows installed by the OEM, for example: - - - Microsoft Surface models (except Surface Pro 3) - - The Lenovo Miix line (for example the 510, 520, 710 and 720) - - Dell 7285 - - If in doubt, say N here. diff --git a/drivers/media/pci/intel/ivsc/Kconfig b/drivers/media/pci/intel/ivsc/Kconfig index 212753450576a..a8cb981544f71 100644 --- a/drivers/media/pci/intel/ivsc/Kconfig +++ b/drivers/media/pci/intel/ivsc/Kconfig @@ -6,7 +6,7 @@ config INTEL_VSC depends on INTEL_MEI && ACPI && VIDEO_DEV select MEDIA_CONTROLLER select VIDEO_V4L2_SUBDEV_API - select V4L2_ASYNC + select V4L2_FWNODE help This adds support for Intel Visual Sensing Controller (IVSC). diff --git a/drivers/media/platform/intel/pxa_camera.c b/drivers/media/platform/intel/pxa_camera.c index 6e6caf50e11ef..59b89e421dc28 100644 --- a/drivers/media/platform/intel/pxa_camera.c +++ b/drivers/media/platform/intel/pxa_camera.c @@ -2398,7 +2398,7 @@ static int pxa_camera_probe(struct platform_device *pdev) PXA_CAM_DRV_NAME, pcdev); if (err) { dev_err(&pdev->dev, "Camera interrupt register failed\n"); - goto exit_v4l2_device_unregister; + goto exit_deactivate; } pcdev->notifier.ops = &pxa_camera_sensor_ops; diff --git a/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c b/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c index d299cc2962a5a..ae6290d28f8e9 100644 --- a/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c +++ b/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c @@ -138,7 +138,8 @@ int vpu_enc_init(struct venc_vpu_inst *vpu) vpu->ctx->vpu_inst = vpu; status = mtk_vcodec_fw_ipi_register(vpu->ctx->dev->fw_handler, vpu->id, - vpu_enc_ipi_handler, "venc", NULL); + vpu_enc_ipi_handler, "venc", + vpu->ctx->dev); if (status) { mtk_venc_err(vpu->ctx, "vpu_ipi_register fail %d", status); diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c index 0a3483e247a89..f63250c650caf 100644 --- a/drivers/of/dynamic.c +++ b/drivers/of/dynamic.c @@ -890,13 +890,13 @@ int of_changeset_action(struct of_changeset *ocs, unsigned long action, { struct of_changeset_entry *ce; + if (WARN_ON(action >= ARRAY_SIZE(action_names))) + return -EINVAL; + ce = kzalloc(sizeof(*ce), GFP_KERNEL); if (!ce) return -ENOMEM; - if (WARN_ON(action >= ARRAY_SIZE(action_names))) - return -EINVAL; - /* get a reference to the node */ ce->action = action; ce->np = of_node_get(np); diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c index dfb6fb962fc70..a9a292d6d59b2 100644 --- a/drivers/of/overlay.c +++ b/drivers/of/overlay.c @@ -45,8 +45,8 @@ struct target { /** * struct fragment - info about fragment nodes in overlay expanded device tree - * @target: target of the overlay operation * @overlay: pointer to the __overlay__ node + * @target: target of the overlay operation */ struct fragment { struct device_node *overlay; diff --git a/drivers/staging/media/atomisp/Kconfig b/drivers/staging/media/atomisp/Kconfig index 5d8917160d41b..75c985da75b5c 100644 --- a/drivers/staging/media/atomisp/Kconfig +++ b/drivers/staging/media/atomisp/Kconfig @@ -12,12 +12,12 @@ menuconfig INTEL_ATOMISP config VIDEO_ATOMISP tristate "Intel Atom Image Signal Processor Driver" depends on VIDEO_DEV && INTEL_ATOMISP + depends on IPU_BRIDGE depends on MEDIA_PCI_SUPPORT depends on PMIC_OPREGION depends on I2C select V4L2_FWNODE select IOSF_MBI - select IPU_BRIDGE select VIDEOBUF2_VMALLOC select VIDEO_V4L2_SUBDEV_API help diff --git a/drivers/staging/media/tegra-video/vi.c b/drivers/staging/media/tegra-video/vi.c index e98b3010520e2..94171e62dee9e 100644 --- a/drivers/staging/media/tegra-video/vi.c +++ b/drivers/staging/media/tegra-video/vi.c @@ -1455,17 +1455,18 @@ static int __maybe_unused vi_runtime_suspend(struct device *dev) } /* - * Graph Management + * Find the entity matching a given fwnode in an v4l2_async_notifier list */ static struct tegra_vi_graph_entity * -tegra_vi_graph_find_entity(struct tegra_vi_channel *chan, +tegra_vi_graph_find_entity(struct list_head *list, const struct fwnode_handle *fwnode) { struct tegra_vi_graph_entity *entity; struct v4l2_async_connection *asd; - list_for_each_entry(asd, &chan->notifier.done_list, asc_entry) { + list_for_each_entry(asd, list, asc_entry) { entity = to_tegra_vi_graph_entity(asd); + if (entity->asd.match.fwnode == fwnode) return entity; } @@ -1532,7 +1533,8 @@ static int tegra_vi_graph_build(struct tegra_vi_channel *chan, } /* find the remote entity from notifier list */ - ent = tegra_vi_graph_find_entity(chan, link.remote_node); + ent = tegra_vi_graph_find_entity(&chan->notifier.done_list, + link.remote_node); if (!ent) { dev_err(vi->dev, "no entity found for %pOF\n", to_of_node(link.remote_node)); @@ -1664,7 +1666,8 @@ static int tegra_vi_graph_notify_bound(struct v4l2_async_notifier *notifier, * Locate the entity corresponding to the bound subdev and store the * subdev pointer. */ - entity = tegra_vi_graph_find_entity(chan, subdev->fwnode); + entity = tegra_vi_graph_find_entity(&chan->notifier.waiting_list, + subdev->fwnode); if (!entity) { dev_err(vi->dev, "no entity for subdev %s\n", subdev->name); return -EINVAL; @@ -1713,7 +1716,8 @@ static int tegra_vi_graph_parse_one(struct tegra_vi_channel *chan, /* skip entities that are already processed */ if (device_match_fwnode(vi->dev, remote) || - tegra_vi_graph_find_entity(chan, remote)) { + tegra_vi_graph_find_entity(&chan->notifier.waiting_list, + remote)) { fwnode_handle_put(remote); continue; } diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 3902e90dca6b0..7b923e36501b0 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -2474,8 +2474,9 @@ cifs_put_tcon(struct cifs_tcon *tcon) static struct cifs_tcon * cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) { - int rc, xid; struct cifs_tcon *tcon; + bool nohandlecache; + int rc, xid; tcon = cifs_find_tcon(ses, ctx); if (tcon) { @@ -2493,14 +2494,17 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) goto out_fail; } - if (ses->server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING) - tcon = tcon_info_alloc(true); + if (ses->server->dialect >= SMB20_PROT_ID && + (ses->server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING)) + nohandlecache = ctx->nohandlecache; else - tcon = tcon_info_alloc(false); + nohandlecache = true; + tcon = tcon_info_alloc(!nohandlecache); if (tcon == NULL) { rc = -ENOMEM; goto out_fail; } + tcon->nohandlecache = nohandlecache; if (ctx->snapshot_time) { if (ses->server->vals->protocol_id == 0) { @@ -2662,10 +2666,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) tcon->nocase = ctx->nocase; tcon->broken_sparse_sup = ctx->no_sparse; tcon->max_cached_dirs = ctx->max_cached_dirs; - if (ses->server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING) - tcon->nohandlecache = ctx->nohandlecache; - else - tcon->nohandlecache = true; tcon->nodelete = ctx->nodelete; tcon->local_lease = ctx->local_lease; INIT_LIST_HEAD(&tcon->pending_opens); @@ -2895,9 +2895,9 @@ bind_socket(struct TCP_Server_Info *server) if (server->srcaddr.ss_family != AF_UNSPEC) { /* Bind to the specified local IP address */ struct socket *socket = server->ssocket; - rc = socket->ops->bind(socket, - (struct sockaddr *) &server->srcaddr, - sizeof(server->srcaddr)); + rc = kernel_bind(socket, + (struct sockaddr *) &server->srcaddr, + sizeof(server->srcaddr)); if (rc < 0) { struct sockaddr_in *saddr4; struct sockaddr_in6 *saddr6; @@ -3046,8 +3046,8 @@ generic_ip_connect(struct TCP_Server_Info *server) socket->sk->sk_sndbuf, socket->sk->sk_rcvbuf, socket->sk->sk_rcvtimeo); - rc = socket->ops->connect(socket, saddr, slen, - server->noblockcnt ? O_NONBLOCK : 0); + rc = kernel_connect(socket, saddr, slen, + server->noblockcnt ? O_NONBLOCK : 0); /* * When mounting SMB root file systems, we do not want to block in * connect. Otherwise bail out and then let cifs_reconnect() perform diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index db7fa704a3f60..4b38c3a285f60 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -84,6 +84,8 @@ struct ksmbd_conn *ksmbd_conn_alloc(void) spin_lock_init(&conn->llist_lock); INIT_LIST_HEAD(&conn->lock_list); + init_rwsem(&conn->session_lock); + down_write(&conn_list_lock); list_add(&conn->conns_list, &conn_list); up_write(&conn_list_lock); diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index ab2583f030ceb..3c005246a32e8 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -50,6 +50,7 @@ struct ksmbd_conn { struct nls_table *local_nls; struct unicode_map *um; struct list_head conns_list; + struct rw_semaphore session_lock; /* smb session 1 per user */ struct xarray sessions; unsigned long last_active; diff --git a/fs/smb/server/mgmt/tree_connect.c b/fs/smb/server/mgmt/tree_connect.c index 408cddf2f094a..d2c81a8a11dda 100644 --- a/fs/smb/server/mgmt/tree_connect.c +++ b/fs/smb/server/mgmt/tree_connect.c @@ -73,7 +73,10 @@ ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess, tree_conn->user = sess->user; tree_conn->share_conf = sc; + tree_conn->t_state = TREE_NEW; status.tree_conn = tree_conn; + atomic_set(&tree_conn->refcount, 1); + init_waitqueue_head(&tree_conn->refcount_q); ret = xa_err(xa_store(&sess->tree_conns, tree_conn->id, tree_conn, GFP_KERNEL)); @@ -93,14 +96,33 @@ ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess, return status; } +void ksmbd_tree_connect_put(struct ksmbd_tree_connect *tcon) +{ + /* + * Checking waitqueue to releasing tree connect on + * tree disconnect. waitqueue_active is safe because it + * uses atomic operation for condition. + */ + if (!atomic_dec_return(&tcon->refcount) && + waitqueue_active(&tcon->refcount_q)) + wake_up(&tcon->refcount_q); +} + int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess, struct ksmbd_tree_connect *tree_conn) { int ret; + write_lock(&sess->tree_conns_lock); + xa_erase(&sess->tree_conns, tree_conn->id); + write_unlock(&sess->tree_conns_lock); + + if (!atomic_dec_and_test(&tree_conn->refcount)) + wait_event(tree_conn->refcount_q, + atomic_read(&tree_conn->refcount) == 0); + ret = ksmbd_ipc_tree_disconnect_request(sess->id, tree_conn->id); ksmbd_release_tree_conn_id(sess, tree_conn->id); - xa_erase(&sess->tree_conns, tree_conn->id); ksmbd_share_config_put(tree_conn->share_conf); kfree(tree_conn); return ret; @@ -111,11 +133,15 @@ struct ksmbd_tree_connect *ksmbd_tree_conn_lookup(struct ksmbd_session *sess, { struct ksmbd_tree_connect *tcon; + read_lock(&sess->tree_conns_lock); tcon = xa_load(&sess->tree_conns, id); if (tcon) { - if (test_bit(TREE_CONN_EXPIRE, &tcon->status)) + if (tcon->t_state != TREE_CONNECTED) + tcon = NULL; + else if (!atomic_inc_not_zero(&tcon->refcount)) tcon = NULL; } + read_unlock(&sess->tree_conns_lock); return tcon; } @@ -129,8 +155,18 @@ int ksmbd_tree_conn_session_logoff(struct ksmbd_session *sess) if (!sess) return -EINVAL; - xa_for_each(&sess->tree_conns, id, tc) + xa_for_each(&sess->tree_conns, id, tc) { + write_lock(&sess->tree_conns_lock); + if (tc->t_state == TREE_DISCONNECTED) { + write_unlock(&sess->tree_conns_lock); + ret = -ENOENT; + continue; + } + tc->t_state = TREE_DISCONNECTED; + write_unlock(&sess->tree_conns_lock); + ret |= ksmbd_tree_conn_disconnect(sess, tc); + } xa_destroy(&sess->tree_conns); return ret; } diff --git a/fs/smb/server/mgmt/tree_connect.h b/fs/smb/server/mgmt/tree_connect.h index 562d647ad9fad..6377a70b811c8 100644 --- a/fs/smb/server/mgmt/tree_connect.h +++ b/fs/smb/server/mgmt/tree_connect.h @@ -14,7 +14,11 @@ struct ksmbd_share_config; struct ksmbd_user; struct ksmbd_conn; -#define TREE_CONN_EXPIRE 1 +enum { + TREE_NEW = 0, + TREE_CONNECTED, + TREE_DISCONNECTED +}; struct ksmbd_tree_connect { int id; @@ -27,7 +31,9 @@ struct ksmbd_tree_connect { int maximal_access; bool posix_extensions; - unsigned long status; + atomic_t refcount; + wait_queue_head_t refcount_q; + unsigned int t_state; }; struct ksmbd_tree_conn_status { @@ -46,6 +52,7 @@ struct ksmbd_session; struct ksmbd_tree_conn_status ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess, const char *share_name); +void ksmbd_tree_connect_put(struct ksmbd_tree_connect *tcon); int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess, struct ksmbd_tree_connect *tree_conn); diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index 8a5dcab05614f..15f68ee050894 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -174,7 +174,7 @@ static void ksmbd_expire_session(struct ksmbd_conn *conn) unsigned long id; struct ksmbd_session *sess; - down_write(&sessions_table_lock); + down_write(&conn->session_lock); xa_for_each(&conn->sessions, id, sess) { if (sess->state != SMB2_SESSION_VALID || time_after(jiffies, @@ -185,7 +185,7 @@ static void ksmbd_expire_session(struct ksmbd_conn *conn) continue; } } - up_write(&sessions_table_lock); + up_write(&conn->session_lock); } int ksmbd_session_register(struct ksmbd_conn *conn, @@ -227,7 +227,9 @@ void ksmbd_sessions_deregister(struct ksmbd_conn *conn) } } } + up_write(&sessions_table_lock); + down_write(&conn->session_lock); xa_for_each(&conn->sessions, id, sess) { unsigned long chann_id; struct channel *chann; @@ -244,7 +246,7 @@ void ksmbd_sessions_deregister(struct ksmbd_conn *conn) ksmbd_session_destroy(sess); } } - up_write(&sessions_table_lock); + up_write(&conn->session_lock); } struct ksmbd_session *ksmbd_session_lookup(struct ksmbd_conn *conn, @@ -252,9 +254,11 @@ struct ksmbd_session *ksmbd_session_lookup(struct ksmbd_conn *conn, { struct ksmbd_session *sess; + down_read(&conn->session_lock); sess = xa_load(&conn->sessions, id); if (sess) sess->last_active = jiffies; + up_read(&conn->session_lock); return sess; } @@ -351,6 +355,7 @@ static struct ksmbd_session *__session_create(int protocol) xa_init(&sess->ksmbd_chann_list); xa_init(&sess->rpc_handle_list); sess->sequence_number = 1; + rwlock_init(&sess->tree_conns_lock); ret = __init_smb2_session(sess); if (ret) diff --git a/fs/smb/server/mgmt/user_session.h b/fs/smb/server/mgmt/user_session.h index f99d475b28db4..63cb08fffde84 100644 --- a/fs/smb/server/mgmt/user_session.h +++ b/fs/smb/server/mgmt/user_session.h @@ -60,6 +60,7 @@ struct ksmbd_session { struct ksmbd_file_table file_table; unsigned long last_active; + rwlock_t tree_conns_lock; }; static inline int test_session_flag(struct ksmbd_session *sess, int bit) diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 32347fec33c4e..3079e607c5fe6 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -241,6 +241,8 @@ static void __handle_ksmbd_work(struct ksmbd_work *work, } while (is_chained == true); send: + if (work->tcon) + ksmbd_tree_connect_put(work->tcon); smb3_preauth_hash_rsp(work); if (work->sess && work->sess->enc && work->encrypted && conn->ops->encrypt_resp) { diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 544022dd6d200..898860adf9290 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -1993,6 +1993,9 @@ int smb2_tree_connect(struct ksmbd_work *work) if (conn->posix_ext_supported) status.tree_conn->posix_extensions = true; + write_lock(&sess->tree_conns_lock); + status.tree_conn->t_state = TREE_CONNECTED; + write_unlock(&sess->tree_conns_lock); rsp->StructureSize = cpu_to_le16(16); out_err1: rsp->Capabilities = 0; @@ -2122,27 +2125,50 @@ int smb2_tree_disconnect(struct ksmbd_work *work) ksmbd_debug(SMB, "request\n"); + if (!tcon) { + ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); + + rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; + err = -ENOENT; + goto err_out; + } + + ksmbd_close_tree_conn_fds(work); + + write_lock(&sess->tree_conns_lock); + if (tcon->t_state == TREE_DISCONNECTED) { + write_unlock(&sess->tree_conns_lock); + rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; + err = -ENOENT; + goto err_out; + } + + WARN_ON_ONCE(atomic_dec_and_test(&tcon->refcount)); + tcon->t_state = TREE_DISCONNECTED; + write_unlock(&sess->tree_conns_lock); + + err = ksmbd_tree_conn_disconnect(sess, tcon); + if (err) { + rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; + goto err_out; + } + + work->tcon = NULL; + rsp->StructureSize = cpu_to_le16(4); err = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_tree_disconnect_rsp)); if (err) { rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; - smb2_set_err_rsp(work); - return err; + goto err_out; } - if (!tcon || test_and_set_bit(TREE_CONN_EXPIRE, &tcon->status)) { - ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); + return 0; - rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; - smb2_set_err_rsp(work); - return -ENOENT; - } +err_out: + smb2_set_err_rsp(work); + return err; - ksmbd_close_tree_conn_fds(work); - ksmbd_tree_conn_disconnect(sess, tcon); - work->tcon = NULL; - return 0; } /** @@ -2164,17 +2190,17 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_debug(SMB, "request\n"); - sess_id = le64_to_cpu(req->hdr.SessionId); - - rsp->StructureSize = cpu_to_le16(4); - err = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_logoff_rsp)); - if (err) { - rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; + ksmbd_conn_lock(conn); + if (!ksmbd_conn_good(conn)) { + ksmbd_conn_unlock(conn); + rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; smb2_set_err_rsp(work); - return err; + return -ENOENT; } - + sess_id = le64_to_cpu(req->hdr.SessionId); ksmbd_all_conn_set_status(sess_id, KSMBD_SESS_NEED_RECONNECT); + ksmbd_conn_unlock(conn); + ksmbd_close_session_fds(work); ksmbd_conn_wait_idle(conn, sess_id); @@ -2196,6 +2222,14 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_free_user(sess->user); sess->user = NULL; ksmbd_all_conn_set_status(sess_id, KSMBD_SESS_NEED_NEGOTIATE); + + rsp->StructureSize = cpu_to_le16(4); + err = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_logoff_rsp)); + if (err) { + rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; + smb2_set_err_rsp(work); + return err; + } return 0; } @@ -3370,8 +3404,10 @@ int smb2_open(struct ksmbd_work *work) } ksmbd_revert_fsids(work); err_out1: - if (!rc) + if (!rc) { + ksmbd_update_fstate(&work->sess->file_table, fp, FP_INITED); rc = ksmbd_iov_pin_rsp(work, (void *)rsp, iov_len); + } if (rc) { if (rc == -EINVAL) rsp->hdr.Status = STATUS_INVALID_PARAMETER; @@ -7028,10 +7064,6 @@ int smb2_lock(struct ksmbd_work *work) ksmbd_debug(SMB, "would have to wait for getting lock\n"); - spin_lock(&work->conn->llist_lock); - list_add_tail(&smb_lock->clist, - &work->conn->lock_list); - spin_unlock(&work->conn->llist_lock); list_add(&smb_lock->llist, &rollback_list); argv = kmalloc(sizeof(void *), GFP_KERNEL); @@ -7062,9 +7094,6 @@ int smb2_lock(struct ksmbd_work *work) if (work->state != KSMBD_WORK_ACTIVE) { list_del(&smb_lock->llist); - spin_lock(&work->conn->llist_lock); - list_del(&smb_lock->clist); - spin_unlock(&work->conn->llist_lock); locks_free_lock(flock); if (work->state == KSMBD_WORK_CANCELLED) { @@ -7084,19 +7113,16 @@ int smb2_lock(struct ksmbd_work *work) } list_del(&smb_lock->llist); - spin_lock(&work->conn->llist_lock); - list_del(&smb_lock->clist); - spin_unlock(&work->conn->llist_lock); release_async_work(work); goto retry; } else if (!rc) { + list_add(&smb_lock->llist, &rollback_list); spin_lock(&work->conn->llist_lock); list_add_tail(&smb_lock->clist, &work->conn->lock_list); list_add_tail(&smb_lock->flist, &fp->lock_list); spin_unlock(&work->conn->llist_lock); - list_add(&smb_lock->llist, &rollback_list); ksmbd_debug(SMB, "successful in taking lock\n"); } else { goto out; @@ -8036,10 +8062,10 @@ static void smb20_oplock_break_ack(struct ksmbd_work *work) goto err_out; } - opinfo_put(opinfo); - ksmbd_fd_put(work, fp); opinfo->op_state = OPLOCK_STATE_NONE; wake_up_interruptible_all(&opinfo->oplock_q); + opinfo_put(opinfo); + ksmbd_fd_put(work, fp); rsp->StructureSize = cpu_to_le16(24); rsp->OplockLevel = rsp_oplevel; diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index f41f8d6108ce9..c4b80ab7df743 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -333,6 +333,9 @@ static void __ksmbd_close_fd(struct ksmbd_file_table *ft, struct ksmbd_file *fp) static struct ksmbd_file *ksmbd_fp_get(struct ksmbd_file *fp) { + if (fp->f_state != FP_INITED) + return NULL; + if (!atomic_inc_not_zero(&fp->refcount)) return NULL; return fp; @@ -382,15 +385,20 @@ int ksmbd_close_fd(struct ksmbd_work *work, u64 id) return 0; ft = &work->sess->file_table; - read_lock(&ft->lock); + write_lock(&ft->lock); fp = idr_find(ft->idr, id); if (fp) { set_close_state_blocked_works(fp); - if (!atomic_dec_and_test(&fp->refcount)) + if (fp->f_state != FP_INITED) fp = NULL; + else { + fp->f_state = FP_CLOSED; + if (!atomic_dec_and_test(&fp->refcount)) + fp = NULL; + } } - read_unlock(&ft->lock); + write_unlock(&ft->lock); if (!fp) return -EINVAL; @@ -570,6 +578,7 @@ struct ksmbd_file *ksmbd_open_fd(struct ksmbd_work *work, struct file *filp) fp->tcon = work->tcon; fp->volatile_id = KSMBD_NO_FID; fp->persistent_id = KSMBD_NO_FID; + fp->f_state = FP_NEW; fp->f_ci = ksmbd_inode_get(fp); if (!fp->f_ci) { @@ -591,6 +600,14 @@ struct ksmbd_file *ksmbd_open_fd(struct ksmbd_work *work, struct file *filp) return ERR_PTR(ret); } +void ksmbd_update_fstate(struct ksmbd_file_table *ft, struct ksmbd_file *fp, + unsigned int state) +{ + write_lock(&ft->lock); + fp->f_state = state; + write_unlock(&ft->lock); +} + static int __close_file_table_ids(struct ksmbd_file_table *ft, struct ksmbd_tree_connect *tcon, diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index fcb13413fa8d9..03d0bf941216f 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -60,6 +60,12 @@ struct ksmbd_inode { __le32 m_fattr; }; +enum { + FP_NEW = 0, + FP_INITED, + FP_CLOSED +}; + struct ksmbd_file { struct file *filp; u64 persistent_id; @@ -98,6 +104,7 @@ struct ksmbd_file { /* if ls is happening on directory, below is valid*/ struct ksmbd_readdir_data readdir_data; int dot_dotdot[2]; + unsigned int f_state; }; static inline void set_ctx_actor(struct dir_context *ctx, @@ -142,6 +149,8 @@ int ksmbd_close_inode_fds(struct ksmbd_work *work, struct inode *inode); int ksmbd_init_global_file_table(void); void ksmbd_free_global_file_table(void); void ksmbd_set_fd_limit(unsigned long limit); +void ksmbd_update_fstate(struct ksmbd_file_table *ft, struct ksmbd_file *fp, + unsigned int state); /* * INODE hash diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index afc4c78b9eed6..d5787991bb5b4 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Copyright (C) 2010 Red Hat, Inc. + * Copyright (C) 2010, 2023 Red Hat, Inc. * All Rights Reserved. */ #include "xfs.h" @@ -19,21 +19,147 @@ #include "xfs_log.h" #include "xfs_ag.h" -STATIC int -xfs_trim_extents( +/* + * Notes on an efficient, low latency fstrim algorithm + * + * We need to walk the filesystem free space and issue discards on the free + * space that meet the search criteria (size and location). We cannot issue + * discards on extents that might be in use, or are so recently in use they are + * still marked as busy. To serialise against extent state changes whilst we are + * gathering extents to trim, we must hold the AGF lock to lock out other + * allocations and extent free operations that might change extent state. + * + * However, we cannot just hold the AGF for the entire AG free space walk whilst + * we issue discards on each free space that is found. Storage devices can have + * extremely slow discard implementations (e.g. ceph RBD) and so walking a + * couple of million free extents and issuing synchronous discards on each + * extent can take a *long* time. Whilst we are doing this walk, nothing else + * can access the AGF, and we can stall transactions and hence the log whilst + * modifications wait for the AGF lock to be released. This can lead hung tasks + * kicking the hung task timer and rebooting the system. This is bad. + * + * Hence we need to take a leaf from the bulkstat playbook. It takes the AGI + * lock, gathers a range of inode cluster buffers that are allocated, drops the + * AGI lock and then reads all the inode cluster buffers and processes them. It + * loops doing this, using a cursor to keep track of where it is up to in the AG + * for each iteration to restart the INOBT lookup from. + * + * We can't do this exactly with free space - once we drop the AGF lock, the + * state of the free extent is out of our control and we cannot run a discard + * safely on it in this situation. Unless, of course, we've marked the free + * extent as busy and undergoing a discard operation whilst we held the AGF + * locked. + * + * This is exactly how online discard works - free extents are marked busy when + * they are freed, and once the extent free has been committed to the journal, + * the busy extent record is marked as "undergoing discard" and the discard is + * then issued on the free extent. Once the discard completes, the busy extent + * record is removed and the extent is able to be allocated again. + * + * In the context of fstrim, if we find a free extent we need to discard, we + * don't have to discard it immediately. All we need to do it record that free + * extent as being busy and under discard, and all the allocation routines will + * now avoid trying to allocate it. Hence if we mark the extent as busy under + * the AGF lock, we can safely discard it without holding the AGF lock because + * nothing will attempt to allocate that free space until the discard completes. + * + * This also allows us to issue discards asynchronously like we do with online + * discard, and so for fast devices fstrim will run much faster as we can have + * multiple discard operations in flight at once, as well as pipeline the free + * extent search so that it overlaps in flight discard IO. + */ + +struct workqueue_struct *xfs_discard_wq; + +static void +xfs_discard_endio_work( + struct work_struct *work) +{ + struct xfs_busy_extents *extents = + container_of(work, struct xfs_busy_extents, endio_work); + + xfs_extent_busy_clear(extents->mount, &extents->extent_list, false); + kmem_free(extents->owner); +} + +/* + * Queue up the actual completion to a thread to avoid IRQ-safe locking for + * pagb_lock. + */ +static void +xfs_discard_endio( + struct bio *bio) +{ + struct xfs_busy_extents *extents = bio->bi_private; + + INIT_WORK(&extents->endio_work, xfs_discard_endio_work); + queue_work(xfs_discard_wq, &extents->endio_work); + bio_put(bio); +} + +/* + * Walk the discard list and issue discards on all the busy extents in the + * list. We plug and chain the bios so that we only need a single completion + * call to clear all the busy extents once the discards are complete. + */ +int +xfs_discard_extents( + struct xfs_mount *mp, + struct xfs_busy_extents *extents) +{ + struct xfs_extent_busy *busyp; + struct bio *bio = NULL; + struct blk_plug plug; + int error = 0; + + blk_start_plug(&plug); + list_for_each_entry(busyp, &extents->extent_list, list) { + trace_xfs_discard_extent(mp, busyp->agno, busyp->bno, + busyp->length); + + error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev, + XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno), + XFS_FSB_TO_BB(mp, busyp->length), + GFP_NOFS, &bio); + if (error && error != -EOPNOTSUPP) { + xfs_info(mp, + "discard failed for extent [0x%llx,%u], error %d", + (unsigned long long)busyp->bno, + busyp->length, + error); + break; + } + } + + if (bio) { + bio->bi_private = extents; + bio->bi_end_io = xfs_discard_endio; + submit_bio(bio); + } else { + xfs_discard_endio_work(&extents->endio_work); + } + blk_finish_plug(&plug); + + return error; +} + + +static int +xfs_trim_gather_extents( struct xfs_perag *pag, xfs_daddr_t start, xfs_daddr_t end, xfs_daddr_t minlen, + struct xfs_alloc_rec_incore *tcur, + struct xfs_busy_extents *extents, uint64_t *blocks_trimmed) { struct xfs_mount *mp = pag->pag_mount; - struct block_device *bdev = mp->m_ddev_targp->bt_bdev; struct xfs_btree_cur *cur; struct xfs_buf *agbp; - struct xfs_agf *agf; int error; int i; + int batch = 100; /* * Force out the log. This means any transactions that might have freed @@ -45,20 +171,28 @@ xfs_trim_extents( error = xfs_alloc_read_agf(pag, NULL, 0, &agbp); if (error) return error; - agf = agbp->b_addr; cur = xfs_allocbt_init_cursor(mp, NULL, agbp, pag, XFS_BTNUM_CNT); /* - * Look up the longest btree in the AGF and start with it. + * Look up the extent length requested in the AGF and start with it. */ - error = xfs_alloc_lookup_ge(cur, 0, be32_to_cpu(agf->agf_longest), &i); + if (tcur->ar_startblock == NULLAGBLOCK) + error = xfs_alloc_lookup_ge(cur, 0, tcur->ar_blockcount, &i); + else + error = xfs_alloc_lookup_le(cur, tcur->ar_startblock, + tcur->ar_blockcount, &i); if (error) goto out_del_cursor; + if (i == 0) { + /* nothing of that length left in the AG, we are done */ + tcur->ar_blockcount = 0; + goto out_del_cursor; + } /* * Loop until we are done with all extents that are large - * enough to be worth discarding. + * enough to be worth discarding or we hit batch limits. */ while (i) { xfs_agblock_t fbno; @@ -73,7 +207,16 @@ xfs_trim_extents( error = -EFSCORRUPTED; break; } - ASSERT(flen <= be32_to_cpu(agf->agf_longest)); + + if (--batch <= 0) { + /* + * Update the cursor to point at this extent so we + * restart the next batch from this extent. + */ + tcur->ar_startblock = fbno; + tcur->ar_blockcount = flen; + break; + } /* * use daddr format for all range/len calculations as that is @@ -88,6 +231,7 @@ xfs_trim_extents( */ if (dlen < minlen) { trace_xfs_discard_toosmall(mp, pag->pag_agno, fbno, flen); + tcur->ar_blockcount = 0; break; } @@ -110,29 +254,103 @@ xfs_trim_extents( goto next_extent; } - trace_xfs_discard_extent(mp, pag->pag_agno, fbno, flen); - error = blkdev_issue_discard(bdev, dbno, dlen, GFP_NOFS); - if (error) - break; + xfs_extent_busy_insert_discard(pag, fbno, flen, + &extents->extent_list); *blocks_trimmed += flen; - next_extent: error = xfs_btree_decrement(cur, 0, &i); if (error) break; - if (fatal_signal_pending(current)) { - error = -ERESTARTSYS; - break; - } + /* + * If there's no more records in the tree, we are done. Set the + * cursor block count to 0 to indicate to the caller that there + * is no more extents to search. + */ + if (i == 0) + tcur->ar_blockcount = 0; } + /* + * If there was an error, release all the gathered busy extents because + * we aren't going to issue a discard on them any more. + */ + if (error) + xfs_extent_busy_clear(mp, &extents->extent_list, false); out_del_cursor: xfs_btree_del_cursor(cur, error); xfs_buf_relse(agbp); return error; } +static bool +xfs_trim_should_stop(void) +{ + return fatal_signal_pending(current) || freezing(current); +} + +/* + * Iterate the free list gathering extents and discarding them. We need a cursor + * for the repeated iteration of gather/discard loop, so use the longest extent + * we found in the last batch as the key to start the next. + */ +static int +xfs_trim_extents( + struct xfs_perag *pag, + xfs_daddr_t start, + xfs_daddr_t end, + xfs_daddr_t minlen, + uint64_t *blocks_trimmed) +{ + struct xfs_alloc_rec_incore tcur = { + .ar_blockcount = pag->pagf_longest, + .ar_startblock = NULLAGBLOCK, + }; + int error = 0; + + do { + struct xfs_busy_extents *extents; + + extents = kzalloc(sizeof(*extents), GFP_KERNEL); + if (!extents) { + error = -ENOMEM; + break; + } + + extents->mount = pag->pag_mount; + extents->owner = extents; + INIT_LIST_HEAD(&extents->extent_list); + + error = xfs_trim_gather_extents(pag, start, end, minlen, + &tcur, extents, blocks_trimmed); + if (error) { + kfree(extents); + break; + } + + /* + * We hand the extent list to the discard function here so the + * discarded extents can be removed from the busy extent list. + * This allows the discards to run asynchronously with gathering + * the next round of extents to discard. + * + * However, we must ensure that we do not reference the extent + * list after this function call, as it may have been freed by + * the time control returns to us. + */ + error = xfs_discard_extents(pag->pag_mount, extents); + if (error) + break; + + if (xfs_trim_should_stop()) + break; + + } while (tcur.ar_blockcount != 0); + + return error; + +} + /* * trim a range of the filesystem. * @@ -195,12 +413,12 @@ xfs_ioc_trim( for_each_perag_range(mp, agno, xfs_daddr_to_agno(mp, end), pag) { error = xfs_trim_extents(pag, start, end, minlen, &blocks_trimmed); - if (error) { + if (error) last_error = error; - if (error == -ERESTARTSYS) { - xfs_perag_rele(pag); - break; - } + + if (xfs_trim_should_stop()) { + xfs_perag_rele(pag); + break; } } diff --git a/fs/xfs/xfs_discard.h b/fs/xfs/xfs_discard.h index de92d9cc958ff..2b1a85223a56c 100644 --- a/fs/xfs/xfs_discard.h +++ b/fs/xfs/xfs_discard.h @@ -3,8 +3,10 @@ #define XFS_DISCARD_H 1 struct fstrim_range; -struct list_head; +struct xfs_mount; +struct xfs_busy_extents; -extern int xfs_ioc_trim(struct xfs_mount *, struct fstrim_range __user *); +int xfs_discard_extents(struct xfs_mount *mp, struct xfs_busy_extents *busy); +int xfs_ioc_trim(struct xfs_mount *mp, struct fstrim_range __user *fstrim); #endif /* XFS_DISCARD_H */ diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c index 7c2fdc71e42d4..746814815b1da 100644 --- a/fs/xfs/xfs_extent_busy.c +++ b/fs/xfs/xfs_extent_busy.c @@ -19,13 +19,13 @@ #include "xfs_log.h" #include "xfs_ag.h" -void -xfs_extent_busy_insert( - struct xfs_trans *tp, +static void +xfs_extent_busy_insert_list( struct xfs_perag *pag, xfs_agblock_t bno, xfs_extlen_t len, - unsigned int flags) + unsigned int flags, + struct list_head *busy_list) { struct xfs_extent_busy *new; struct xfs_extent_busy *busyp; @@ -40,7 +40,7 @@ xfs_extent_busy_insert( new->flags = flags; /* trace before insert to be able to see failed inserts */ - trace_xfs_extent_busy(tp->t_mountp, pag->pag_agno, bno, len); + trace_xfs_extent_busy(pag->pag_mount, pag->pag_agno, bno, len); spin_lock(&pag->pagb_lock); rbp = &pag->pagb_tree.rb_node; @@ -62,10 +62,32 @@ xfs_extent_busy_insert( rb_link_node(&new->rb_node, parent, rbp); rb_insert_color(&new->rb_node, &pag->pagb_tree); - list_add(&new->list, &tp->t_busy); + list_add(&new->list, busy_list); spin_unlock(&pag->pagb_lock); } +void +xfs_extent_busy_insert( + struct xfs_trans *tp, + struct xfs_perag *pag, + xfs_agblock_t bno, + xfs_extlen_t len, + unsigned int flags) +{ + xfs_extent_busy_insert_list(pag, bno, len, flags, &tp->t_busy); +} + +void +xfs_extent_busy_insert_discard( + struct xfs_perag *pag, + xfs_agblock_t bno, + xfs_extlen_t len, + struct list_head *busy_list) +{ + xfs_extent_busy_insert_list(pag, bno, len, XFS_EXTENT_BUSY_DISCARDED, + busy_list); +} + /* * Search for a busy extent within the range of the extent we are about to * allocate. You need to be holding the busy extent tree lock when calling diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h index c37bf87e6781b..0639aab336f3f 100644 --- a/fs/xfs/xfs_extent_busy.h +++ b/fs/xfs/xfs_extent_busy.h @@ -16,9 +16,6 @@ struct xfs_alloc_arg; /* * Busy block/extent entry. Indexed by a rbtree in perag to mark blocks that * have been freed but whose transactions aren't committed to disk yet. - * - * Note that we use the transaction ID to record the transaction, not the - * transaction structure itself. See xfs_extent_busy_insert() for details. */ struct xfs_extent_busy { struct rb_node rb_node; /* ag by-bno indexed search tree */ @@ -31,10 +28,31 @@ struct xfs_extent_busy { #define XFS_EXTENT_BUSY_SKIP_DISCARD 0x02 /* do not discard */ }; +/* + * List used to track groups of related busy extents all the way through + * to discard completion. + */ +struct xfs_busy_extents { + struct xfs_mount *mount; + struct list_head extent_list; + struct work_struct endio_work; + + /* + * Owner is the object containing the struct xfs_busy_extents to free + * once the busy extents have been processed. If only the + * xfs_busy_extents object needs freeing, then point this at itself. + */ + void *owner; +}; + void xfs_extent_busy_insert(struct xfs_trans *tp, struct xfs_perag *pag, xfs_agblock_t bno, xfs_extlen_t len, unsigned int flags); +void +xfs_extent_busy_insert_discard(struct xfs_perag *pag, xfs_agblock_t bno, + xfs_extlen_t len, struct list_head *busy_list); + void xfs_extent_busy_clear(struct xfs_mount *mp, struct list_head *list, bool do_discard); diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index ebc70aaa299c0..67a99d94701e5 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -16,8 +16,7 @@ #include "xfs_log.h" #include "xfs_log_priv.h" #include "xfs_trace.h" - -struct workqueue_struct *xfs_discard_wq; +#include "xfs_discard.h" /* * Allocate a new ticket. Failing to get a new ticket makes it really hard to @@ -103,7 +102,7 @@ xlog_cil_ctx_alloc(void) ctx = kmem_zalloc(sizeof(*ctx), KM_NOFS); INIT_LIST_HEAD(&ctx->committing); - INIT_LIST_HEAD(&ctx->busy_extents); + INIT_LIST_HEAD(&ctx->busy_extents.extent_list); INIT_LIST_HEAD(&ctx->log_items); INIT_LIST_HEAD(&ctx->lv_chain); INIT_WORK(&ctx->push_work, xlog_cil_push_work); @@ -132,7 +131,7 @@ xlog_cil_push_pcp_aggregate( if (!list_empty(&cilpcp->busy_extents)) { list_splice_init(&cilpcp->busy_extents, - &ctx->busy_extents); + &ctx->busy_extents.extent_list); } if (!list_empty(&cilpcp->log_items)) list_splice_init(&cilpcp->log_items, &ctx->log_items); @@ -708,76 +707,6 @@ xlog_cil_free_logvec( } } -static void -xlog_discard_endio_work( - struct work_struct *work) -{ - struct xfs_cil_ctx *ctx = - container_of(work, struct xfs_cil_ctx, discard_endio_work); - struct xfs_mount *mp = ctx->cil->xc_log->l_mp; - - xfs_extent_busy_clear(mp, &ctx->busy_extents, false); - kmem_free(ctx); -} - -/* - * Queue up the actual completion to a thread to avoid IRQ-safe locking for - * pagb_lock. Note that we need a unbounded workqueue, otherwise we might - * get the execution delayed up to 30 seconds for weird reasons. - */ -static void -xlog_discard_endio( - struct bio *bio) -{ - struct xfs_cil_ctx *ctx = bio->bi_private; - - INIT_WORK(&ctx->discard_endio_work, xlog_discard_endio_work); - queue_work(xfs_discard_wq, &ctx->discard_endio_work); - bio_put(bio); -} - -static void -xlog_discard_busy_extents( - struct xfs_mount *mp, - struct xfs_cil_ctx *ctx) -{ - struct list_head *list = &ctx->busy_extents; - struct xfs_extent_busy *busyp; - struct bio *bio = NULL; - struct blk_plug plug; - int error = 0; - - ASSERT(xfs_has_discard(mp)); - - blk_start_plug(&plug); - list_for_each_entry(busyp, list, list) { - trace_xfs_discard_extent(mp, busyp->agno, busyp->bno, - busyp->length); - - error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev, - XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno), - XFS_FSB_TO_BB(mp, busyp->length), - GFP_NOFS, &bio); - if (error && error != -EOPNOTSUPP) { - xfs_info(mp, - "discard failed for extent [0x%llx,%u], error %d", - (unsigned long long)busyp->bno, - busyp->length, - error); - break; - } - } - - if (bio) { - bio->bi_private = ctx; - bio->bi_end_io = xlog_discard_endio; - submit_bio(bio); - } else { - xlog_discard_endio_work(&ctx->discard_endio_work); - } - blk_finish_plug(&plug); -} - /* * Mark all items committed and clear busy extents. We free the log vector * chains in a separate pass so that we unpin the log items as quickly as @@ -807,8 +736,8 @@ xlog_cil_committed( xfs_trans_committed_bulk(ctx->cil->xc_log->l_ailp, &ctx->lv_chain, ctx->start_lsn, abort); - xfs_extent_busy_sort(&ctx->busy_extents); - xfs_extent_busy_clear(mp, &ctx->busy_extents, + xfs_extent_busy_sort(&ctx->busy_extents.extent_list); + xfs_extent_busy_clear(mp, &ctx->busy_extents.extent_list, xfs_has_discard(mp) && !abort); spin_lock(&ctx->cil->xc_push_lock); @@ -817,10 +746,14 @@ xlog_cil_committed( xlog_cil_free_logvec(&ctx->lv_chain); - if (!list_empty(&ctx->busy_extents)) - xlog_discard_busy_extents(mp, ctx); - else - kmem_free(ctx); + if (!list_empty(&ctx->busy_extents.extent_list)) { + ctx->busy_extents.mount = mp; + ctx->busy_extents.owner = ctx; + xfs_discard_extents(mp, &ctx->busy_extents); + return; + } + + kmem_free(ctx); } void diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index af87648331d5d..fa3ad1d7b31c8 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -6,6 +6,8 @@ #ifndef __XFS_LOG_PRIV_H__ #define __XFS_LOG_PRIV_H__ +#include "xfs_extent_busy.h" /* for struct xfs_busy_extents */ + struct xfs_buf; struct xlog; struct xlog_ticket; @@ -223,12 +225,11 @@ struct xfs_cil_ctx { struct xlog_in_core *commit_iclog; struct xlog_ticket *ticket; /* chkpt ticket */ atomic_t space_used; /* aggregate size of regions */ - struct list_head busy_extents; /* busy extents in chkpt */ + struct xfs_busy_extents busy_extents; struct list_head log_items; /* log items in chkpt */ struct list_head lv_chain; /* logvecs being pushed */ struct list_head iclog_entry; struct list_head committing; /* ctx committing list */ - struct work_struct discard_endio_work; struct work_struct push_work; atomic_t order_id; diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 4492608b7d7f1..458d359f5991c 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -350,7 +350,8 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time, * Except when the rq is capped by uclamp_max. */ if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) && - sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) { + sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq && + !sg_policy->need_freq_update) { next_f = sg_policy->next_freq; /* Restore cached freq as next_freq has changed */ diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index cb225921bbca4..ef7490c4b8b40 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -664,6 +664,10 @@ void avg_vruntime_update(struct cfs_rq *cfs_rq, s64 delta) cfs_rq->avg_vruntime -= cfs_rq->avg_load * delta; } +/* + * Specifically: avg_runtime() + 0 must result in entity_eligible() := true + * For this to be so, the result of this function must have a left bias. + */ u64 avg_vruntime(struct cfs_rq *cfs_rq) { struct sched_entity *curr = cfs_rq->curr; @@ -677,8 +681,12 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq) load += weight; } - if (load) + if (load) { + /* sign flips effective floor / ceil */ + if (avg < 0) + avg -= (load - 1); avg = div_s64(avg, load); + } return cfs_rq->min_vruntime + avg; } @@ -4919,10 +4927,12 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq) {} static void place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { - u64 vslice = calc_delta_fair(se->slice, se); - u64 vruntime = avg_vruntime(cfs_rq); + u64 vslice, vruntime = avg_vruntime(cfs_rq); s64 lag = 0; + se->slice = sysctl_sched_base_slice; + vslice = calc_delta_fair(se->slice, se); + /* * Due to how V is constructed as the weighted average of entities, * adding tasks with positive lag, or removing tasks with negative lag