diff options
166 files changed, 1573 insertions, 958 deletions
diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt index c55df29..cd9c9f6 100644 --- a/Documentation/PCI/MSI-HOWTO.txt +++ b/Documentation/PCI/MSI-HOWTO.txt @@ -94,14 +94,11 @@ has a requirements for a minimum number of vectors the driver can pass a min_vecs argument set to this limit, and the PCI core will return -ENOSPC if it can't meet the minimum number of vectors. -The flags argument should normally be set to 0, but can be used to pass the -PCI_IRQ_NOMSI and PCI_IRQ_NOMSIX flag in case a device claims to support -MSI or MSI-X, but the support is broken, or to pass PCI_IRQ_NOLEGACY in -case the device does not support legacy interrupt lines. - -By default this function will spread the interrupts around the available -CPUs, but this feature can be disabled by passing the PCI_IRQ_NOAFFINITY -flag. +The flags argument is used to specify which type of interrupt can be used +by the device and the driver (PCI_IRQ_LEGACY, PCI_IRQ_MSI, PCI_IRQ_MSIX). +A convenient short-hand (PCI_IRQ_ALL_TYPES) is also available to ask for +any possible kind of interrupt. If the PCI_IRQ_AFFINITY flag is set, +pci_alloc_irq_vectors() will spread the interrupts around the available CPUs. To get the Linux IRQ numbers passed to request_irq() and free_irq() and the vectors, use the following function: @@ -131,7 +128,7 @@ larger than the number supported by the device it will automatically be capped to the supported limit, so there is no need to query the number of vectors supported beforehand: - nvec = pci_alloc_irq_vectors(pdev, 1, nvec, 0); + nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_ALL_TYPES) if (nvec < 0) goto out_err; @@ -140,7 +137,7 @@ interrupts it can request a particular number of interrupts by passing that number to pci_alloc_irq_vectors() function as both 'min_vecs' and 'max_vecs' parameters: - ret = pci_alloc_irq_vectors(pdev, nvec, nvec, 0); + ret = pci_alloc_irq_vectors(pdev, nvec, nvec, PCI_IRQ_ALL_TYPES); if (ret < 0) goto out_err; @@ -148,15 +145,14 @@ The most notorious example of the request type described above is enabling the single MSI mode for a device. It could be done by passing two 1s as 'min_vecs' and 'max_vecs': - ret = pci_alloc_irq_vectors(pdev, 1, 1, 0); + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES); if (ret < 0) goto out_err; Some devices might not support using legacy line interrupts, in which case -the PCI_IRQ_NOLEGACY flag can be used to fail the request if the platform -can't provide MSI or MSI-X interrupts: +the driver can specify that only MSI or MSI-X is acceptable: - nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_NOLEGACY); + nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_MSI | PCI_IRQ_MSIX); if (nvec < 0) goto out_err; diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt index 4da60b4..ccc6032 100644 --- a/Documentation/arm64/silicon-errata.txt +++ b/Documentation/arm64/silicon-errata.txt @@ -53,6 +53,7 @@ stable kernels. | ARM | Cortex-A57 | #832075 | ARM64_ERRATUM_832075 | | ARM | Cortex-A57 | #852523 | N/A | | ARM | Cortex-A57 | #834220 | ARM64_ERRATUM_834220 | +| ARM | Cortex-A72 | #853709 | N/A | | ARM | MMU-500 | #841119,#826419 | N/A | | | | | | | Cavium | ThunderX ITS | #22375, #24313 | CAVIUM_ERRATUM_22375 | diff --git a/Documentation/devicetree/bindings/sound/omap-mcpdm.txt b/Documentation/devicetree/bindings/sound/omap-mcpdm.txt index 6f6c2f8..0741dff 100644 --- a/Documentation/devicetree/bindings/sound/omap-mcpdm.txt +++ b/Documentation/devicetree/bindings/sound/omap-mcpdm.txt @@ -8,8 +8,6 @@ Required properties: - interrupts: Interrupt number for McPDM - interrupt-parent: The parent interrupt controller - ti,hwmods: Name of the hwmod associated to the McPDM -- clocks: phandle for the pdmclk provider, likely <&twl6040> -- clock-names: Must be "pdmclk" Example: @@ -21,11 +19,3 @@ mcpdm: mcpdm@40132000 { interrupt-parent = <&gic>; ti,hwmods = "mcpdm"; }; - -In board DTS file the pdmclk needs to be added: - -&mcpdm { - clocks = <&twl6040>; - clock-names = "pdmclk"; - status = "okay"; -}; diff --git a/Documentation/devicetree/bindings/thermal/thermal.txt b/Documentation/devicetree/bindings/thermal/thermal.txt index 41b817f..88b6ea1 100644 --- a/Documentation/devicetree/bindings/thermal/thermal.txt +++ b/Documentation/devicetree/bindings/thermal/thermal.txt @@ -62,7 +62,7 @@ For more examples of cooling devices, refer to the example sections below. Required properties: - #cooling-cells: Used to provide cooling device specific information Type: unsigned while referring to it. Must be at least 2, in order - Size: one cell to specify minimum and maximum cooling state used + Size: one cell to specify minimum and maximum cooling state used in the reference. The first cell is the minimum cooling state requested and the second cell is the maximum cooling state requested in the reference. @@ -119,7 +119,7 @@ Required properties: Optional property: - contribution: The cooling contribution to the thermal zone of the Type: unsigned referred cooling device at the referred trip point. - Size: one cell The contribution is a ratio of the sum + Size: one cell The contribution is a ratio of the sum of all cooling contributions within a thermal zone. Note: Using the THERMAL_NO_LIMIT (-1UL) constant in the cooling-device phandle @@ -145,7 +145,7 @@ Required properties: Size: one cell - thermal-sensors: A list of thermal sensor phandles and sensor specifier - Type: list of used while monitoring the thermal zone. + Type: list of used while monitoring the thermal zone. phandles + sensor specifier @@ -473,7 +473,7 @@ thermal-zones { <&adc>; /* pcb north */ /* hotspot = 100 * bandgap - 120 * adc + 484 */ - coefficients = <100 -120 484>; + coefficients = <100 -120 484>; trips { ... @@ -502,7 +502,7 @@ from the ADC sensor. The binding would be then: thermal-sensors = <&adc>; /* hotspot = 1 * adc + 6000 */ - coefficients = <1 6000>; + coefficients = <1 6000>; (d) - Board thermal diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 46c030a..a4f4d69 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3032,6 +3032,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. PAGE_SIZE is used as alignment. PCI-PCI bridge can be specified, if resource windows need to be expanded. + To specify the alignment for several + instances of a device, the PCI vendor, + device, subvendor, and subdevice may be + specified, e.g., 4096@pci:8086:9c22:103c:198f ecrc= Enable/disable PCIe ECRC (transaction layer end-to-end CRC checking). bios: Use BIOS/firmware settings. This is the diff --git a/MAINTAINERS b/MAINTAINERS index 4705c94..71aa5da 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7670,7 +7670,7 @@ L: linux-rdma@vger.kernel.org S: Supported W: https://github.com/SoftRoCE/rxe-dev/wiki/rxe-dev:-Home Q: http://patchwork.kernel.org/project/linux-rdma/list/ -F: drivers/infiniband/hw/rxe/ +F: drivers/infiniband/sw/rxe/ F: include/uapi/rdma/rdma_user_rxe.h MEMBARRIER SUPPORT diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h index ad7860c..51597f3 100644 --- a/arch/arc/include/asm/entry.h +++ b/arch/arc/include/asm/entry.h @@ -142,7 +142,7 @@ #ifdef CONFIG_ARC_CURR_IN_REG ; Retrieve orig r25 and save it with rest of callee_regs - ld.as r12, [r12, PT_user_r25] + ld r12, [r12, PT_user_r25] PUSH r12 #else PUSH r25 @@ -198,7 +198,7 @@ ; SP is back to start of pt_regs #ifdef CONFIG_ARC_CURR_IN_REG - st.as r12, [sp, PT_user_r25] + st r12, [sp, PT_user_r25] #endif .endm diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h index c1d3645..4c6eed8 100644 --- a/arch/arc/include/asm/irqflags-compact.h +++ b/arch/arc/include/asm/irqflags-compact.h @@ -188,10 +188,10 @@ static inline int arch_irqs_disabled(void) .endm .macro IRQ_ENABLE scratch + TRACE_ASM_IRQ_ENABLE lr \scratch, [status32] or \scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK) flag \scratch - TRACE_ASM_IRQ_ENABLE .endm #endif /* __ASSEMBLY__ */ diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 0f92d97..89eeb37 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -280,7 +280,7 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep) #define pte_page(pte) pfn_to_page(pte_pfn(pte)) #define mk_pte(page, prot) pfn_pte(page_to_pfn(page), prot) -#define pfn_pte(pfn, prot) (__pte(((pte_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))) +#define pfn_pte(pfn, prot) __pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot)) /* Don't use virt_to_pfn for macros below: could cause truncations for PAE40*/ #define pte_pfn(pte) (pte_val(pte) >> PAGE_SHIFT) diff --git a/arch/arc/include/uapi/asm/elf.h b/arch/arc/include/uapi/asm/elf.h index 0f99ac8..0037a58 100644 --- a/arch/arc/include/uapi/asm/elf.h +++ b/arch/arc/include/uapi/asm/elf.h @@ -13,8 +13,15 @@ /* Machine specific ELF Hdr flags */ #define EF_ARC_OSABI_MSK 0x00000f00 -#define EF_ARC_OSABI_ORIG 0x00000000 /* MUST be zero for back-compat */ -#define EF_ARC_OSABI_CURRENT 0x00000300 /* v3 (no legacy syscalls) */ + +#define EF_ARC_OSABI_V3 0x00000300 /* v3 (no legacy syscalls) */ +#define EF_ARC_OSABI_V4 0x00000400 /* v4 (64bit data any reg align) */ + +#if __GNUC__ < 6 +#define EF_ARC_OSABI_CURRENT EF_ARC_OSABI_V3 +#else +#define EF_ARC_OSABI_CURRENT EF_ARC_OSABI_V4 +#endif typedef unsigned long elf_greg_t; typedef unsigned long elf_fpregset_t; diff --git a/arch/arc/kernel/arcksyms.c b/arch/arc/kernel/arcksyms.c index 4d9e777..000dd04 100644 --- a/arch/arc/kernel/arcksyms.c +++ b/arch/arc/kernel/arcksyms.c @@ -28,6 +28,7 @@ extern void __muldf3(void); extern void __divdf3(void); extern void __floatunsidf(void); extern void __floatunsisf(void); +extern void __udivdi3(void); EXPORT_SYMBOL(__ashldi3); EXPORT_SYMBOL(__ashrdi3); @@ -45,6 +46,7 @@ EXPORT_SYMBOL(__muldf3); EXPORT_SYMBOL(__divdf3); EXPORT_SYMBOL(__floatunsidf); EXPORT_SYMBOL(__floatunsisf); +EXPORT_SYMBOL(__udivdi3); /* ARC optimised assembler routines */ EXPORT_SYMBOL(memset); diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index b5db9e7..be1972b 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -199,7 +199,7 @@ int elf_check_arch(const struct elf32_hdr *x) } eflags = x->e_flags; - if ((eflags & EF_ARC_OSABI_MSK) < EF_ARC_OSABI_CURRENT) { + if ((eflags & EF_ARC_OSABI_MSK) != EF_ARC_OSABI_CURRENT) { pr_err("ABI mismatch - you need newer toolchain\n"); force_sigsegv(SIGSEGV, current); return 0; diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index a946400..f52a0d0d 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -291,8 +291,10 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) cpu->dccm.base_addr, TO_KB(cpu->dccm.sz), cpu->iccm.base_addr, TO_KB(cpu->iccm.sz)); - n += scnprintf(buf + n, len - n, - "OS ABI [v3]\t: no-legacy-syscalls\n"); + n += scnprintf(buf + n, len - n, "OS ABI [v%d]\t: %s\n", + EF_ARC_OSABI_CURRENT >> 8, + EF_ARC_OSABI_CURRENT == EF_ARC_OSABI_V3 ? + "no-legacy-syscalls" : "64-bit data any register aligned"); return buf; } diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 5a294b2..0b10efe 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -921,6 +921,15 @@ void arc_cache_init(void) printk(arc_cache_mumbojumbo(0, str, sizeof(str))); + /* + * Only master CPU needs to execute rest of function: + * - Assume SMP so all cores will have same cache config so + * any geomtry checks will be same for all + * - IOC setup / dma callbacks only need to be setup once + */ + if (cpu) + return; + if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE)) { struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache; diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c index 04f8332..77ff64a 100644 --- a/arch/arc/mm/highmem.c +++ b/arch/arc/mm/highmem.c @@ -61,6 +61,7 @@ void *kmap(struct page *page) return kmap_high(page); } +EXPORT_SYMBOL(kmap); void *kmap_atomic(struct page *page) { diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index bda27b6..29d0b23 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -1309,7 +1309,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, smp_rmb(); pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writable); - if (is_error_pfn(pfn)) + if (is_error_noslot_pfn(pfn)) return -EFAULT; if (kvm_is_device_pfn(pfn)) { diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index b0b82f5..3d2cef6 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -50,7 +50,7 @@ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu); static struct vcpu_info __percpu *xen_vcpu_info; /* Linux <-> Xen vCPU id mapping */ -DEFINE_PER_CPU(int, xen_vcpu_id) = -1; +DEFINE_PER_CPU(uint32_t, xen_vcpu_id); EXPORT_PER_CPU_SYMBOL(xen_vcpu_id); /* These are unused until we support booting "pre-ballooned" */ diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index b77f583..3e7b050 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -757,6 +757,9 @@ ENTRY(__enable_mmu) isb bl __create_page_tables // recreate kernel mapping + tlbi vmalle1 // Remove any stale TLB entries + dsb nsh + msr sctlr_el1, x19 // re-enable the MMU isb ic iallu // flush instructions fetched diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index ae7855f..5a84b45 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -256,7 +256,7 @@ static int __hyp_text __guest_run(struct kvm_vcpu *vcpu) /* * We must restore the 32-bit state before the sysregs, thanks - * to Cortex-A57 erratum #852523. + * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72). */ __sysreg32_restore_state(vcpu); __sysreg_restore_guest_state(guest_ctxt); diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index b0b225c..e51367d 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -823,14 +823,6 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, * Architected system registers. * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2 * - * We could trap ID_DFR0 and tell the guest we don't support performance - * monitoring. Unfortunately the patch to make the kernel check ID_DFR0 was - * NAKed, so it will read the PMCR anyway. - * - * Therefore we tell the guest we have 0 counters. Unfortunately, we - * must always support PMCCNTR (the cycle counter): we just RAZ/WI for - * all PM registers, which doesn't crash the guest kernel at least. - * * Debug handling: We do trap most, if not all debug related system * registers. The implementation is good enough to ensure that a guest * can use these with minimal performance degradation. The drawback is @@ -1360,7 +1352,7 @@ static const struct sys_reg_desc cp15_regs[] = { { Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 }, /* ICC_SRE */ - { Op1( 0), CRn(12), CRm(12), Op2( 5), trap_raz_wi }, + { Op1( 0), CRn(12), CRm(12), Op2( 5), access_gic_sre }, { Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID }, diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index ea0cd97..5f98759 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -164,7 +164,7 @@ typedef struct { unsigned long pgprot; } pgprot_t; */ static inline unsigned long ___pa(unsigned long x) { - if (config_enabled(CONFIG_64BIT)) { + if (IS_ENABLED(CONFIG_64BIT)) { /* * For MIPS64 the virtual address may either be in one of * the compatibility segements ckseg0 or ckseg1, or it may @@ -173,7 +173,7 @@ static inline unsigned long ___pa(unsigned long x) return x < CKSEG0 ? XPHYSADDR(x) : CPHYSADDR(x); } - if (!config_enabled(CONFIG_EVA)) { + if (!IS_ENABLED(CONFIG_EVA)) { /* * We're using the standard MIPS32 legacy memory map, ie. * the address x is going to be in kseg0 or kseg1. We can diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index 6cfdcf5..121008c 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -40,7 +40,7 @@ static int kvm_mips_map_page(struct kvm *kvm, gfn_t gfn) srcu_idx = srcu_read_lock(&kvm->srcu); pfn = gfn_to_pfn(kvm, gfn); - if (is_error_pfn(pfn)) { + if (is_error_noslot_pfn(pfn)) { kvm_err("Couldn't get pfn for gfn %#llx!\n", gfn); err = -EFAULT; goto out; diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index ba5f456..7f7ba5f2 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -204,11 +204,9 @@ static void __init conmode_default(void) #endif } } else if (MACHINE_IS_KVM) { - if (sclp.has_vt220 && - config_enabled(CONFIG_SCLP_VT220_CONSOLE)) + if (sclp.has_vt220 && IS_ENABLED(CONFIG_SCLP_VT220_CONSOLE)) SET_CONSOLE_VT220; - else if (sclp.has_linemode && - config_enabled(CONFIG_SCLP_CONSOLE)) + else if (sclp.has_linemode && IS_ENABLED(CONFIG_SCLP_CONSOLE)) SET_CONSOLE_SCLP; else SET_CONSOLE_HVC; diff --git a/arch/um/include/asm/common.lds.S b/arch/um/include/asm/common.lds.S index 1dd5bd8..1330553 100644 --- a/arch/um/include/asm/common.lds.S +++ b/arch/um/include/asm/common.lds.S @@ -81,7 +81,7 @@ .altinstr_replacement : { *(.altinstr_replacement) } /* .exit.text is discard at runtime, not link time, to deal with references from .altinstructions and .eh_frame */ - .exit.text : { *(.exit.text) } + .exit.text : { EXIT_TEXT } .exit.data : { *(.exit.data) } .preinit_array : { diff --git a/arch/x86/crypto/sha256-mb/sha256_mb.c b/arch/x86/crypto/sha256-mb/sha256_mb.c index 89fa85e..6f97fb3 100644 --- a/arch/x86/crypto/sha256-mb/sha256_mb.c +++ b/arch/x86/crypto/sha256-mb/sha256_mb.c @@ -485,10 +485,10 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx, req = cast_mcryptd_ctx_to_req(req_ctx); if (irqs_disabled()) - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); else { local_bh_disable(); - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); local_bh_enable(); } } diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S index b691da9..a78a069 100644 --- a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S +++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S @@ -265,13 +265,14 @@ ENTRY(sha256_mb_mgr_get_comp_job_avx2) vpinsrd $1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0 vpinsrd $2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0 vpinsrd $3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0 - movl _args_digest+4*32(state, idx, 4), tmp2_w + vmovd _args_digest(state , idx, 4) , %xmm0 vpinsrd $1, _args_digest+5*32(state, idx, 4), %xmm1, %xmm1 vpinsrd $2, _args_digest+6*32(state, idx, 4), %xmm1, %xmm1 vpinsrd $3, _args_digest+7*32(state, idx, 4), %xmm1, %xmm1 - vmovdqu %xmm0, _result_digest(job_rax) - movl tmp2_w, _result_digest+1*16(job_rax) + vmovdqu %xmm0, _result_digest(job_rax) + offset = (_result_digest + 1*16) + vmovdqu %xmm1, offset(job_rax) pop %rbx diff --git a/arch/x86/crypto/sha512-mb/sha512_mb.c b/arch/x86/crypto/sha512-mb/sha512_mb.c index f4cf5b7..d210174 100644 --- a/arch/x86/crypto/sha512-mb/sha512_mb.c +++ b/arch/x86/crypto/sha512-mb/sha512_mb.c @@ -497,10 +497,10 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx, req = cast_mcryptd_ctx_to_req(req_ctx); if (irqs_disabled()) - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); else { local_bh_disable(); - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); local_bh_enable(); } } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a45d858..5cede40 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -422,6 +422,7 @@ struct nested_vmx { struct list_head vmcs02_pool; int vmcs02_num; u64 vmcs01_tsc_offset; + bool change_vmcs01_virtual_x2apic_mode; /* L2 must run next, and mustn't decide to exit to L1. */ bool nested_run_pending; /* @@ -435,6 +436,8 @@ struct nested_vmx { bool pi_pending; u16 posted_intr_nv; + unsigned long *msr_bitmap; + struct hrtimer preemption_timer; bool preemption_timer_expired; @@ -924,7 +927,6 @@ static unsigned long *vmx_msr_bitmap_legacy; static unsigned long *vmx_msr_bitmap_longmode; static unsigned long *vmx_msr_bitmap_legacy_x2apic; static unsigned long *vmx_msr_bitmap_longmode_x2apic; -static unsigned long *vmx_msr_bitmap_nested; static unsigned long *vmx_vmread_bitmap; static unsigned long *vmx_vmwrite_bitmap; @@ -2198,6 +2200,12 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) new.control) != old.control); } +static void decache_tsc_multiplier(struct vcpu_vmx *vmx) +{ + vmx->current_tsc_ratio = vmx->vcpu.arch.tsc_scaling_ratio; + vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); +} + /* * Switches to specified vcpu, until a matching vcpu_put(), but assumes * vcpu mutex is already taken. @@ -2256,10 +2264,8 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) /* Setup TSC multiplier */ if (kvm_has_tsc_control && - vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) { - vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio; - vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); - } + vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) + decache_tsc_multiplier(vmx); vmx_vcpu_pi_load(vcpu, cpu); vmx->host_pkru = read_pkru(); @@ -2508,7 +2514,7 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu) unsigned long *msr_bitmap; if (is_guest_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_nested; + msr_bitmap = to_vmx(vcpu)->nested.msr_bitmap; else if (cpu_has_secondary_exec_ctrls() && (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { @@ -6363,13 +6369,6 @@ static __init int hardware_setup(void) if (!vmx_msr_bitmap_longmode_x2apic) goto out4; - if (nested) { - vmx_msr_bitmap_nested = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_nested) - goto out5; - } - vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_vmread_bitmap) goto out6; @@ -6392,8 +6391,6 @@ static __init int hardware_setup(void) memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE); memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE); - if (nested) - memset(vmx_msr_bitmap_nested, 0xff, PAGE_SIZE); if (setup_vmcs_config(&vmcs_config) < 0) { r = -EIO; @@ -6529,9 +6526,6 @@ out8: out7: free_page((unsigned long)vmx_vmread_bitmap); out6: - if (nested) - free_page((unsigned long)vmx_msr_bitmap_nested); -out5: free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic); out4: free_page((unsigned long)vmx_msr_bitmap_longmode); @@ -6557,8 +6551,6 @@ static __exit void hardware_unsetup(void) free_page((unsigned long)vmx_io_bitmap_a); free_page((unsigned long)vmx_vmwrite_bitmap); free_page((unsigned long)vmx_vmread_bitmap); - if (nested) - free_page((unsigned long)vmx_msr_bitmap_nested); free_kvm_area(); } @@ -6995,16 +6987,21 @@ static int handle_vmon(struct kvm_vcpu *vcpu) return 1; } + if (cpu_has_vmx_msr_bitmap()) { + vmx->nested.msr_bitmap = + (unsigned long *)__get_free_page(GFP_KERNEL); + if (!vmx->nested.msr_bitmap) + goto out_msr_bitmap; + } + vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL); if (!vmx->nested.cached_vmcs12) - return -ENOMEM; + goto out_cached_vmcs12; if (enable_shadow_vmcs) { shadow_vmcs = alloc_vmcs(); - if (!shadow_vmcs) { - kfree(vmx->nested.cached_vmcs12); - return -ENOMEM; - } + if (!shadow_vmcs) + goto out_shadow_vmcs; /* mark vmcs as shadow */ shadow_vmcs->revision_id |= (1u << 31); /* init shadow vmcs */ @@ -7024,6 +7021,15 @@ static int handle_vmon(struct kvm_vcpu *vcpu) skip_emulated_instruction(vcpu); nested_vmx_succeed(vcpu); return 1; + +out_shadow_vmcs: + kfree(vmx->nested.cached_vmcs12); + +out_cached_vmcs12: + free_page((unsigned long)vmx->nested.msr_bitmap); + +out_msr_bitmap: + return -ENOMEM; } /* @@ -7098,6 +7104,10 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->nested.vmxon = false; free_vpid(vmx->nested.vpid02); nested_release_vmcs12(vmx); + if (vmx->nested.msr_bitmap) { + free_page((unsigned long)vmx->nested.msr_bitmap); + vmx->nested.msr_bitmap = NULL; + } if (enable_shadow_vmcs) free_vmcs(vmx->nested.current_shadow_vmcs); kfree(vmx->nested.cached_vmcs12); @@ -8419,6 +8429,12 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) { u32 sec_exec_control; + /* Postpone execution until vmcs01 is the current VMCS. */ + if (is_guest_mode(vcpu)) { + to_vmx(vcpu)->nested.change_vmcs01_virtual_x2apic_mode = true; + return; + } + /* * There is not point to enable virtualize x2apic without enable * apicv @@ -9472,8 +9488,10 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, { int msr; struct page *page; - unsigned long *msr_bitmap; + unsigned long *msr_bitmap_l1; + unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.msr_bitmap; + /* This shortcut is ok because we support only x2APIC MSRs so far. */ if (!nested_cpu_has_virt_x2apic_mode(vmcs12)) return false; @@ -9482,63 +9500,37 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, WARN_ON(1); return false; } - msr_bitmap = (unsigned long *)kmap(page); - if (!msr_bitmap) { + msr_bitmap_l1 = (unsigned long *)kmap(page); + if (!msr_bitmap_l1) { nested_release_page_clean(page); WARN_ON(1); return false; } + memset(msr_bitmap_l0, 0xff, PAGE_SIZE); + if (nested_cpu_has_virt_x2apic_mode(vmcs12)) { if (nested_cpu_has_apic_reg_virt(vmcs12)) for (msr = 0x800; msr <= 0x8ff; msr++) nested_vmx_disable_intercept_for_msr( - msr_bitmap, - vmx_msr_bitmap_nested, + msr_bitmap_l1, msr_bitmap_l0, msr, MSR_TYPE_R); - /* TPR is allowed */ - nested_vmx_disable_intercept_for_msr(msr_bitmap, - vmx_msr_bitmap_nested, + + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, APIC_BASE_MSR + (APIC_TASKPRI >> 4), MSR_TYPE_R | MSR_TYPE_W); + if (nested_cpu_has_vid(vmcs12)) { - /* EOI and self-IPI are allowed */ nested_vmx_disable_intercept_for_msr( - msr_bitmap, - vmx_msr_bitmap_nested, + msr_bitmap_l1, msr_bitmap_l0, APIC_BASE_MSR + (APIC_EOI >> 4), MSR_TYPE_W); nested_vmx_disable_intercept_for_msr( - msr_bitmap, - vmx_msr_bitmap_nested, + msr_bitmap_l1, msr_bitmap_l0, APIC_BASE_MSR + (APIC_SELF_IPI >> 4), MSR_TYPE_W); } - } else { - /* - * Enable reading intercept of all the x2apic - * MSRs. We should not rely on vmcs12 to do any - * optimizations here, it may have been modified - * by L1. - */ - for (msr = 0x800; msr <= 0x8ff; msr++) - __vmx_enable_intercept_for_msr( - vmx_msr_bitmap_nested, - msr, - MSR_TYPE_R); - - __vmx_enable_intercept_for_msr( - vmx_msr_bitmap_nested, - APIC_BASE_MSR + (APIC_TASKPRI >> 4), - MSR_TYPE_W); - __vmx_enable_intercept_for_msr( - vmx_msr_bitmap_nested, - APIC_BASE_MSR + (APIC_EOI >> 4), - MSR_TYPE_W); - __vmx_enable_intercept_for_msr( - vmx_msr_bitmap_nested, - APIC_BASE_MSR + (APIC_SELF_IPI >> 4), - MSR_TYPE_W); } kunmap(page); nested_release_page_clean(page); @@ -9957,10 +9949,10 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) } if (cpu_has_vmx_msr_bitmap() && - exec_control & CPU_BASED_USE_MSR_BITMAPS) { - nested_vmx_merge_msr_bitmap(vcpu, vmcs12); - /* MSR_BITMAP will be set by following vmx_set_efer. */ - } else + exec_control & CPU_BASED_USE_MSR_BITMAPS && + nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) + ; /* MSR_BITMAP will be set by following vmx_set_efer. */ + else exec_control &= ~CPU_BASED_USE_MSR_BITMAPS; /* @@ -10011,6 +10003,8 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset); else vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset); + if (kvm_has_tsc_control) + decache_tsc_multiplier(vmx); if (enable_vpid) { /* @@ -10767,6 +10761,14 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, else vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, PIN_BASED_VMX_PREEMPTION_TIMER); + if (kvm_has_tsc_control) + decache_tsc_multiplier(vmx); + + if (vmx->nested.change_vmcs01_virtual_x2apic_mode) { + vmx->nested.change_vmcs01_virtual_x2apic_mode = false; + vmx_set_virtual_x2apic_mode(vcpu, + vcpu->arch.apic_base & X2APIC_ENABLE); + } /* This is needed for same reason as it was needed in prepare_vmcs02 */ vmx->host_rsp = 0; diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index ec8654f..bda8d5e 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -77,7 +77,7 @@ static inline unsigned long get_padding(struct kaslr_memory_region *region) */ static inline bool kaslr_memory_enabled(void) { - return kaslr_enabled() && !config_enabled(CONFIG_KASAN); + return kaslr_enabled() && !IS_ENABLED(CONFIG_KASAN); } /* Initialize base and padding for each memory region randomized with KASLR */ diff --git a/arch/x86/pci/vmd.c b/arch/x86/pci/vmd.c index b814ca6..7948be3 100644 --- a/arch/x86/pci/vmd.c +++ b/arch/x86/pci/vmd.c @@ -41,6 +41,7 @@ static DEFINE_RAW_SPINLOCK(list_lock); * @node: list item for parent traversal. * @rcu: RCU callback item for freeing. * @irq: back pointer to parent. + * @enabled: true if driver enabled IRQ * @virq: the virtual IRQ value provided to the requesting driver. * * Every MSI/MSI-X IRQ requested for a device in a VMD domain will be mapped to @@ -50,6 +51,7 @@ struct vmd_irq { struct list_head node; struct rcu_head rcu; struct vmd_irq_list *irq; + bool enabled; unsigned int virq; }; @@ -122,7 +124,9 @@ static void vmd_irq_enable(struct irq_data *data) unsigned long flags; raw_spin_lock_irqsave(&list_lock, flags); + WARN_ON(vmdirq->enabled); list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list); + vmdirq->enabled = true; raw_spin_unlock_irqrestore(&list_lock, flags); data->chip->irq_unmask(data); @@ -136,8 +140,10 @@ static void vmd_irq_disable(struct irq_data *data) data->chip->irq_mask(data); raw_spin_lock_irqsave(&list_lock, flags); - list_del_rcu(&vmdirq->node); - INIT_LIST_HEAD_RCU(&vmdirq->node); + if (vmdirq->enabled) { + list_del_rcu(&vmdirq->node); + vmdirq->enabled = false; + } raw_spin_unlock_irqrestore(&list_lock, flags); } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 8ffb089..b86ebb1 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -118,7 +118,7 @@ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu); DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info); /* Linux <-> Xen vCPU id mapping */ -DEFINE_PER_CPU(int, xen_vcpu_id) = -1; +DEFINE_PER_CPU(uint32_t, xen_vcpu_id); EXPORT_PER_CPU_SYMBOL(xen_vcpu_id); enum xen_domain_type xen_domain_type = XEN_NATIVE; diff --git a/block/bio.c b/block/bio.c index f394775..aa73540 100644 --- a/block/bio.c +++ b/block/bio.c @@ -667,18 +667,19 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask, bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; - if (bio_op(bio) == REQ_OP_DISCARD) - goto integrity_clone; - - if (bio_op(bio) == REQ_OP_WRITE_SAME) { + switch (bio_op(bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: + break; + case REQ_OP_WRITE_SAME: bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0]; - goto integrity_clone; + break; + default: + bio_for_each_segment(bv, bio_src, iter) + bio->bi_io_vec[bio->bi_vcnt++] = bv; + break; } - bio_for_each_segment(bv, bio_src, iter) - bio->bi_io_vec[bio->bi_vcnt++] = bv; - -integrity_clone: if (bio_integrity(bio_src)) { int ret; @@ -1788,7 +1789,7 @@ struct bio *bio_split(struct bio *bio, int sectors, * Discards need a mutable bio_vec to accommodate the payload * required by the DSM TRIM and UNMAP commands. */ - if (bio_op(bio) == REQ_OP_DISCARD) + if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE) split = bio_clone_bioset(bio, gfp, bs); else split = bio_clone_fast(bio, gfp, bs); diff --git a/block/blk-core.c b/block/blk-core.c index 999442e..36c7ac3 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -515,7 +515,9 @@ EXPORT_SYMBOL_GPL(blk_queue_bypass_end); void blk_set_queue_dying(struct request_queue *q) { - queue_flag_set_unlocked(QUEUE_FLAG_DYING, q); + spin_lock_irq(q->queue_lock); + queue_flag_set(QUEUE_FLAG_DYING, q); + spin_unlock_irq(q->queue_lock); if (q->mq_ops) blk_mq_wake_waiters(q); diff --git a/block/blk-merge.c b/block/blk-merge.c index 3eec75a..2642e5f 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -94,9 +94,31 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, bool do_split = true; struct bio *new = NULL; const unsigned max_sectors = get_max_io_size(q, bio); + unsigned bvecs = 0; bio_for_each_segment(bv, bio, iter) { /* + * With arbitrary bio size, the incoming bio may be very + * big. We have to split the bio into small bios so that + * each holds at most BIO_MAX_PAGES bvecs because + * bio_clone() can fail to allocate big bvecs. + * + * It should have been better to apply the limit per + * request queue in which bio_clone() is involved, + * instead of globally. The biggest blocker is the + * bio_clone() in bio bounce. + * + * If bio is splitted by this reason, we should have + * allowed to continue bios merging, but don't do + * that now for making the change simple. + * + * TODO: deal with bio bounce's bio_clone() gracefully + * and convert the global limit into per-queue limit. + */ + if (bvecs++ >= BIO_MAX_PAGES) + goto split; + + /* * If the queue doesn't support SG gaps and adding this * offset would create a gap, disallow it. */ @@ -172,12 +194,18 @@ void blk_queue_split(struct request_queue *q, struct bio **bio, struct bio *split, *res; unsigned nsegs; - if (bio_op(*bio) == REQ_OP_DISCARD) + switch (bio_op(*bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: split = blk_bio_discard_split(q, *bio, bs, &nsegs); - else if (bio_op(*bio) == REQ_OP_WRITE_SAME) + break; + case REQ_OP_WRITE_SAME: split = blk_bio_write_same_split(q, *bio, bs, &nsegs); - else + break; + default: split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs); + break; + } /* physical segments can be figured out during splitting */ res = split ? split : *bio; @@ -213,7 +241,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, * This should probably be returning 0, but blk_add_request_payload() * (Christoph!!!!) */ - if (bio_op(bio) == REQ_OP_DISCARD) + if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE) return 1; if (bio_op(bio) == REQ_OP_WRITE_SAME) @@ -385,7 +413,9 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, nsegs = 0; cluster = blk_queue_cluster(q); - if (bio_op(bio) == REQ_OP_DISCARD) { + switch (bio_op(bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: /* * This is a hack - drivers should be neither modifying the * biovec, nor relying on bi_vcnt - but because of @@ -393,19 +423,16 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, * a payload we need to set up here (thank you Christoph) and * bi_vcnt is really the only way of telling if we need to. */ - - if (bio->bi_vcnt) - goto single_segment; - - return 0; - } - - if (bio_op(bio) == REQ_OP_WRITE_SAME) { -single_segment: + if (!bio->bi_vcnt) + return 0; + /* Fall through */ + case REQ_OP_WRITE_SAME: *sg = sglist; bvec = bio_iovec(bio); sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset); return 1; + default: + break; } for_each_bio(bio) diff --git a/block/blk-mq.c b/block/blk-mq.c index e931a0e..13f5a6c 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -793,11 +793,12 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx) struct list_head *dptr; int queued; - WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)); - if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state))) return; + WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) && + cpu_online(hctx->next_cpu)); + hctx->run++; /* @@ -1036,10 +1037,11 @@ void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) EXPORT_SYMBOL(blk_mq_delay_queue); static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx, - struct blk_mq_ctx *ctx, struct request *rq, bool at_head) { + struct blk_mq_ctx *ctx = rq->mq_ctx; + trace_block_rq_insert(hctx->queue, rq); if (at_head) @@ -1053,20 +1055,16 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, { struct blk_mq_ctx *ctx = rq->mq_ctx; - __blk_mq_insert_req_list(hctx, ctx, rq, at_head); + __blk_mq_insert_req_list(hctx, rq, at_head); blk_mq_hctx_mark_pending(hctx, ctx); } void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue, - bool async) + bool async) { + struct blk_mq_ctx *ctx = rq->mq_ctx; struct request_queue *q = rq->q; struct blk_mq_hw_ctx *hctx; - struct blk_mq_ctx *ctx = rq->mq_ctx, *current_ctx; - - current_ctx = blk_mq_get_ctx(q); - if (!cpu_online(ctx->cpu)) - rq->mq_ctx = ctx = current_ctx; hctx = q->mq_ops->map_queue(q, ctx->cpu); @@ -1076,8 +1074,6 @@ void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue, if (run_queue) blk_mq_run_hw_queue(hctx, async); - - blk_mq_put_ctx(current_ctx); } static void blk_mq_insert_requests(struct request_queue *q, @@ -1088,14 +1084,9 @@ static void blk_mq_insert_requests(struct request_queue *q, { struct blk_mq_hw_ctx *hctx; - struct blk_mq_ctx *current_ctx; trace_block_unplug(q, depth, !from_schedule); - current_ctx = blk_mq_get_ctx(q); - - if (!cpu_online(ctx->cpu)) - ctx = current_ctx; hctx = q->mq_ops->map_queue(q, ctx->cpu); /* @@ -1107,15 +1098,14 @@ static void blk_mq_insert_requests(struct request_queue *q, struct request *rq; rq = list_first_entry(list, struct request, queuelist); + BUG_ON(rq->mq_ctx != ctx); list_del_init(&rq->queuelist); - rq->mq_ctx = ctx; - __blk_mq_insert_req_list(hctx, ctx, rq, false); + __blk_mq_insert_req_list(hctx, rq, false); } blk_mq_hctx_mark_pending(hctx, ctx); spin_unlock(&ctx->lock); blk_mq_run_hw_queue(hctx, from_schedule); - blk_mq_put_ctx(current_ctx); } static int plug_ctx_cmp(void *priv, struct list_head *a, struct list_head *b) @@ -1630,16 +1620,17 @@ static int blk_mq_alloc_bitmap(struct blk_mq_ctxmap *bitmap, int node) return 0; } +/* + * 'cpu' is going away. splice any existing rq_list entries from this + * software queue to the hw queue dispatch list, and ensure that it + * gets run. + */ static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu) { - struct request_queue *q = hctx->queue; struct blk_mq_ctx *ctx; LIST_HEAD(tmp); - /* - * Move ctx entries to new CPU, if this one is going away. - */ - ctx = __blk_mq_get_ctx(q, cpu); + ctx = __blk_mq_get_ctx(hctx->queue, cpu); spin_lock(&ctx->lock); if (!list_empty(&ctx->rq_list)) { @@ -1651,24 +1642,11 @@ static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu) if (list_empty(&tmp)) return NOTIFY_OK; - ctx = blk_mq_get_ctx(q); - spin_lock(&ctx->lock); - - while (!list_empty(&tmp)) { - struct request *rq; - - rq = list_first_entry(&tmp, struct request, queuelist); - rq->mq_ctx = ctx; - list_move_tail(&rq->queuelist, &ctx->rq_list); - } - - hctx = q->mq_ops->map_queue(q, ctx->cpu); - blk_mq_hctx_mark_pending(hctx, ctx); - - spin_unlock(&ctx->lock); + spin_lock(&hctx->lock); + list_splice_tail_init(&tmp, &hctx->dispatch); + spin_unlock(&hctx->lock); blk_mq_run_hw_queue(hctx, true); - blk_mq_put_ctx(ctx); return NOTIFY_OK; } diff --git a/block/elevator.c b/block/elevator.c index 7096c22..f7d973a 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -366,7 +366,7 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq) list_for_each_prev(entry, &q->queue_head) { struct request *pos = list_entry_rq(entry); - if ((req_op(rq) == REQ_OP_DISCARD) != (req_op(pos) == REQ_OP_DISCARD)) + if (req_op(rq) != req_op(pos)) break; if (rq_data_dir(rq) != rq_data_dir(pos)) break; diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index b71a9c7..e3d8e4c 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -3706,22 +3706,21 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) if (UFDCS->rawcmd == 1) UFDCS->rawcmd = 2; - if (mode & (FMODE_READ|FMODE_WRITE)) { - UDRS->last_checked = 0; - clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags); - check_disk_change(bdev); - if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags)) - goto out; - if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags)) + if (!(mode & FMODE_NDELAY)) { + if (mode & (FMODE_READ|FMODE_WRITE)) { + UDRS->last_checked = 0; + clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags); + check_disk_change(bdev); + if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags)) + goto out; + if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags)) + goto out; + } + res = -EROFS; + if ((mode & FMODE_WRITE) && + !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags)) goto out; } - - res = -EROFS; - - if ((mode & FMODE_WRITE) && - !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags)) - goto out; - mutex_unlock(&open_lock); mutex_unlock(&floppy_mutex); return 0; diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index be4fea6..88ef6d4 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -189,6 +189,8 @@ struct blkfront_info struct mutex mutex; struct xenbus_device *xbdev; struct gendisk *gd; + u16 sector_size; + unsigned int physical_sector_size; int vdevice; blkif_vdev_t handle; enum blkif_state connected; @@ -910,9 +912,45 @@ static struct blk_mq_ops blkfront_mq_ops = { .map_queue = blk_mq_map_queue, }; +static void blkif_set_queue_limits(struct blkfront_info *info) +{ + struct request_queue *rq = info->rq; + struct gendisk *gd = info->gd; + unsigned int segments = info->max_indirect_segments ? : + BLKIF_MAX_SEGMENTS_PER_REQUEST; + + queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq); + + if (info->feature_discard) { + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq); + blk_queue_max_discard_sectors(rq, get_capacity(gd)); + rq->limits.discard_granularity = info->discard_granularity; + rq->limits.discard_alignment = info->discard_alignment; + if (info->feature_secdiscard) + queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq); + } + + /* Hard sector size and max sectors impersonate the equiv. hardware. */ + blk_queue_logical_block_size(rq, info->sector_size); + blk_queue_physical_block_size(rq, info->physical_sector_size); + blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512); + + /* Each segment in a request is up to an aligned page in size. */ + blk_queue_segment_boundary(rq, PAGE_SIZE - 1); + blk_queue_max_segment_size(rq, PAGE_SIZE); + + /* Ensure a merged request will fit in a single I/O ring slot. */ + blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG); + + /* Make sure buffer addresses are sector-aligned. */ + blk_queue_dma_alignment(rq, 511); + + /* Make sure we don't use bounce buffers. */ + blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY); +} + static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size, - unsigned int physical_sector_size, - unsigned int segments) + unsigned int physical_sector_size) { struct request_queue *rq; struct blkfront_info *info = gd->private_data; @@ -944,36 +982,11 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size, } rq->queuedata = info; - queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq); - - if (info->feature_discard) { - queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq); - blk_queue_max_discard_sectors(rq, get_capacity(gd)); - rq->limits.discard_granularity = info->discard_granularity; - rq->limits.discard_alignment = info->discard_alignment; - if (info->feature_secdiscard) - queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq); - } - - /* Hard sector size and max sectors impersonate the equiv. hardware. */ - blk_queue_logical_block_size(rq, sector_size); - blk_queue_physical_block_size(rq, physical_sector_size); - blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512); - - /* Each segment in a request is up to an aligned page in size. */ - blk_queue_segment_boundary(rq, PAGE_SIZE - 1); - blk_queue_max_segment_size(rq, PAGE_SIZE); - - /* Ensure a merged request will fit in a single I/O ring slot. */ - blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG); - - /* Make sure buffer addresses are sector-aligned. */ - blk_queue_dma_alignment(rq, 511); - - /* Make sure we don't use bounce buffers. */ - blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY); - - gd->queue = rq; + info->rq = gd->queue = rq; + info->gd = gd; + info->sector_size = sector_size; + info->physical_sector_size = physical_sector_size; + blkif_set_queue_limits(info); return 0; } @@ -1136,16 +1149,11 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, gd->private_data = info; set_capacity(gd, capacity); - if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size, - info->max_indirect_segments ? : - BLKIF_MAX_SEGMENTS_PER_REQUEST)) { + if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size)) { del_gendisk(gd); goto release; } - info->rq = gd->queue; - info->gd = gd; - xlvbd_flush(info); if (vdisk_info & VDISK_READONLY) @@ -1315,7 +1323,7 @@ free_shadow: rinfo->ring_ref[i] = GRANT_INVALID_REF; } } - free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * PAGE_SIZE)); + free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * XEN_PAGE_SIZE)); rinfo->ring.sring = NULL; if (rinfo->irq) @@ -2007,8 +2015,10 @@ static int blkif_recover(struct blkfront_info *info) struct split_bio *split_bio; blkfront_gather_backend_features(info); + /* Reset limits changed by blk_mq_update_nr_hw_queues(). */ + blkif_set_queue_limits(info); segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST; - blk_queue_max_segments(info->rq, segs); + blk_queue_max_segments(info->rq, segs / GRANTS_PER_PSEG); for (r_index = 0; r_index < info->nr_rings; r_index++) { struct blkfront_ring_info *rinfo = &info->rinfo[r_index]; @@ -2432,7 +2442,7 @@ static void blkfront_connect(struct blkfront_info *info) if (err) { xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s", info->xbdev->otherend); - return; + goto fail; } xenbus_switch_state(info->xbdev, XenbusStateConnected); @@ -2445,6 +2455,11 @@ static void blkfront_connect(struct blkfront_info *info) device_add_disk(&info->xbdev->dev, info->gd); info->is_ready = 1; + return; + +fail: + blkif_free(info, 0); + return; } /** diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c index dfb1685..1f01e98 100644 --- a/drivers/dax/pmem.c +++ b/drivers/dax/pmem.c @@ -116,6 +116,9 @@ static int dax_pmem_probe(struct device *dev) if (rc) return rc; + /* adjust the dax_region resource to the start of data */ + res.start += le64_to_cpu(pfn_sb->dataoff); + nd_region = to_nd_region(dev->parent); dax_region = alloc_dax_region(dev, nd_region->id, &res, le32_to_cpu(pfn_sb->align), addr, PFN_DEV|PFN_MAP); diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 98dd47a..66a9410 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -50,6 +50,7 @@ config GPIO_DEVRES config OF_GPIO def_bool y depends on OF + depends on HAS_IOMEM config GPIO_ACPI def_bool y @@ -188,7 +189,7 @@ config GPIO_EP93XX config GPIO_ETRAXFS bool "Axis ETRAX FS General I/O" depends on CRIS || COMPILE_TEST - depends on OF + depends on OF_GPIO select GPIO_GENERIC select GPIOLIB_IRQCHIP help @@ -214,7 +215,7 @@ config GPIO_GENERIC_PLATFORM config GPIO_GRGPIO tristate "Aeroflex Gaisler GRGPIO support" - depends on OF + depends on OF_GPIO select GPIO_GENERIC select IRQ_DOMAIN help @@ -312,7 +313,7 @@ config GPIO_MPC8XXX config GPIO_MVEBU def_bool y depends on PLAT_ORION - depends on OF + depends on OF_GPIO select GENERIC_IRQ_CHIP config GPIO_MXC @@ -405,7 +406,7 @@ config GPIO_TEGRA bool "NVIDIA Tegra GPIO support" default ARCH_TEGRA depends on ARCH_TEGRA || COMPILE_TEST - depends on OF + depends on OF_GPIO help Say yes here to support GPIO pins on NVIDIA Tegra SoCs. @@ -1099,7 +1100,7 @@ menu "SPI GPIO expanders" config GPIO_74X164 tristate "74x164 serial-in/parallel-out 8-bits shift register" - depends on OF + depends on OF_GPIO help Driver for 74x164 compatible serial-in/parallel-out 8-outputs shift registers. This driver can be used to provide access diff --git a/drivers/gpio/gpio-max730x.c b/drivers/gpio/gpio-max730x.c index 0880736..946d091 100644 --- a/drivers/gpio/gpio-max730x.c +++ b/drivers/gpio/gpio-max730x.c @@ -192,6 +192,10 @@ int __max730x_probe(struct max7301 *ts) ts->chip.parent = dev; ts->chip.owner = THIS_MODULE; + ret = gpiochip_add_data(&ts->chip, ts); + if (ret) + goto exit_destroy; + /* * initialize pullups according to platform data and cache the * register values for later use. @@ -213,10 +217,6 @@ int __max730x_probe(struct max7301 *ts) } } - ret = gpiochip_add_data(&ts->chip, ts); - if (ret) - goto exit_destroy; - return ret; exit_destroy: diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index e6dfa1b..5f65a78 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2462,18 +2462,24 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) if (addr->dev_addr.bound_dev_if) { ndev = dev_get_by_index(&init_net, addr->dev_addr.bound_dev_if); - if (!ndev) - return -ENODEV; + if (!ndev) { + ret = -ENODEV; + goto err2; + } if (ndev->flags & IFF_LOOPBACK) { dev_put(ndev); - if (!id_priv->id.device->get_netdev) - return -EOPNOTSUPP; + if (!id_priv->id.device->get_netdev) { + ret = -EOPNOTSUPP; + goto err2; + } ndev = id_priv->id.device->get_netdev(id_priv->id.device, id_priv->id.port_num); - if (!ndev) - return -ENODEV; + if (!ndev) { + ret = -ENODEV; + goto err2; + } } route->path_rec->net = &init_net; diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 3aca7f6..b6a953a 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -1827,8 +1827,12 @@ static int process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb) (ep->mpa_pkt + sizeof(*mpa)); ep->ird = ntohs(mpa_v2_params->ird) & MPA_V2_IRD_ORD_MASK; + ep->ird = min_t(u32, ep->ird, + cur_max_read_depth(ep->com.dev)); ep->ord = ntohs(mpa_v2_params->ord) & MPA_V2_IRD_ORD_MASK; + ep->ord = min_t(u32, ep->ord, + cur_max_read_depth(ep->com.dev)); PDBG("%s initiator ird %u ord %u\n", __func__, ep->ird, ep->ord); if (ntohs(mpa_v2_params->ird) & MPA_V2_PEER2PEER_MODEL) @@ -3136,7 +3140,7 @@ int c4iw_accept_cr(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) if (ep->mpa_attr.version == 2 && ep->mpa_attr.enhanced_rdma_conn) { if (conn_param->ord > ep->ird) { if (RELAXED_IRD_NEGOTIATION) { - ep->ord = ep->ird; + conn_param->ord = ep->ird; } else { ep->ird = conn_param->ird; ep->ord = conn_param->ord; diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c index 812ab72..ac926c9 100644 --- a/drivers/infiniband/hw/cxgb4/cq.c +++ b/drivers/infiniband/hw/cxgb4/cq.c @@ -1016,15 +1016,15 @@ int c4iw_resize_cq(struct ib_cq *cq, int cqe, struct ib_udata *udata) int c4iw_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags) { struct c4iw_cq *chp; - int ret; + int ret = 0; unsigned long flag; chp = to_c4iw_cq(ibcq); spin_lock_irqsave(&chp->lock, flag); - ret = t4_arm_cq(&chp->cq, - (flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED); + t4_arm_cq(&chp->cq, + (flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED); + if (flags & IB_CQ_REPORT_MISSED_EVENTS) + ret = t4_cq_notempty(&chp->cq); spin_unlock_irqrestore(&chp->lock, flag); - if (ret && !(flags & IB_CQ_REPORT_MISSED_EVENTS)) - ret = 0; return ret; } diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h index 6126bbe..02173f4 100644 --- a/drivers/infiniband/hw/cxgb4/t4.h +++ b/drivers/infiniband/hw/cxgb4/t4.h @@ -634,6 +634,11 @@ static inline int t4_valid_cqe(struct t4_cq *cq, struct t4_cqe *cqe) return (CQE_GENBIT(cqe) == cq->gen); } +static inline int t4_cq_notempty(struct t4_cq *cq) +{ + return cq->sw_in_use || t4_valid_cqe(cq, &cq->queue[cq->cidx]); +} + static inline int t4_next_hw_cqe(struct t4_cq *cq, struct t4_cqe **cqe) { int ret; diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c index 79575ee..0566393 100644 --- a/drivers/infiniband/hw/hfi1/affinity.c +++ b/drivers/infiniband/hw/hfi1/affinity.c @@ -47,7 +47,6 @@ #include <linux/topology.h> #include <linux/cpumask.h> #include <linux/module.h> -#include <linux/cpumask.h> #include "hfi.h" #include "affinity.h" @@ -682,7 +681,7 @@ int hfi1_set_sdma_affinity(struct hfi1_devdata *dd, const char *buf, size_t count) { struct hfi1_affinity_node *entry; - struct cpumask mask; + cpumask_var_t mask; int ret, i; spin_lock(&node_affinity.lock); @@ -692,19 +691,24 @@ int hfi1_set_sdma_affinity(struct hfi1_devdata *dd, const char *buf, if (!entry) return -EINVAL; - ret = cpulist_parse(buf, &mask); + ret = zalloc_cpumask_var(&mask, GFP_KERNEL); + if (!ret) + return -ENOMEM; + + ret = cpulist_parse(buf, mask); if (ret) - return ret; + goto out; - if (!cpumask_subset(&mask, cpu_online_mask) || cpumask_empty(&mask)) { + if (!cpumask_subset(mask, cpu_online_mask) || cpumask_empty(mask)) { dd_dev_warn(dd, "Invalid CPU mask\n"); - return -EINVAL; + ret = -EINVAL; + goto out; } mutex_lock(&sdma_affinity_mutex); /* reset the SDMA interrupt affinity details */ init_cpu_mask_set(&entry->def_intr); - cpumask_copy(&entry->def_intr.mask, &mask); + cpumask_copy(&entry->def_intr.mask, mask); /* * Reassign the affinity for each SDMA interrupt. */ @@ -720,8 +724,9 @@ int hfi1_set_sdma_affinity(struct hfi1_devdata *dd, const char *buf, if (ret) break; } - mutex_unlock(&sdma_affinity_mutex); +out: + free_cpumask_var(mask); return ret ? ret : strnlen(buf, PAGE_SIZE); } diff --git a/drivers/infiniband/hw/hfi1/debugfs.c b/drivers/infiniband/hw/hfi1/debugfs.c index dbab9d9..a49cc88 100644 --- a/drivers/infiniband/hw/hfi1/debugfs.c +++ b/drivers/infiniband/hw/hfi1/debugfs.c @@ -223,28 +223,32 @@ DEBUGFS_SEQ_FILE_OPEN(ctx_stats) DEBUGFS_FILE_OPS(ctx_stats); static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos) -__acquires(RCU) + __acquires(RCU) { struct qp_iter *iter; loff_t n = *pos; - rcu_read_lock(); iter = qp_iter_init(s->private); + + /* stop calls rcu_read_unlock */ + rcu_read_lock(); + if (!iter) return NULL; - while (n--) { + do { if (qp_iter_next(iter)) { kfree(iter); return NULL; } - } + } while (n--); return iter; } static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, loff_t *pos) + __must_hold(RCU) { struct qp_iter *iter = iter_ptr; @@ -259,7 +263,7 @@ static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, } static void _qp_stats_seq_stop(struct seq_file *s, void *iter_ptr) -__releases(RCU) + __releases(RCU) { rcu_read_unlock(); } diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c index 8246dc7..303f105 100644 --- a/drivers/infiniband/hw/hfi1/driver.c +++ b/drivers/infiniband/hw/hfi1/driver.c @@ -888,14 +888,15 @@ void set_all_slowpath(struct hfi1_devdata *dd) } static inline int set_armed_to_active(struct hfi1_ctxtdata *rcd, - struct hfi1_packet packet, + struct hfi1_packet *packet, struct hfi1_devdata *dd) { struct work_struct *lsaw = &rcd->ppd->linkstate_active_work; - struct hfi1_message_header *hdr = hfi1_get_msgheader(packet.rcd->dd, - packet.rhf_addr); + struct hfi1_message_header *hdr = hfi1_get_msgheader(packet->rcd->dd, + packet->rhf_addr); + u8 etype = rhf_rcv_type(packet->rhf); - if (hdr2sc(hdr, packet.rhf) != 0xf) { + if (etype == RHF_RCV_TYPE_IB && hdr2sc(hdr, packet->rhf) != 0xf) { int hwstate = read_logical_state(dd); if (hwstate != LSTATE_ACTIVE) { @@ -979,7 +980,7 @@ int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread) /* Auto activate link on non-SC15 packet receive */ if (unlikely(rcd->ppd->host_link_state == HLS_UP_ARMED) && - set_armed_to_active(rcd, packet, dd)) + set_armed_to_active(rcd, &packet, dd)) goto bail; last = process_rcv_packet(&packet, thread); } diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index 1ecbec1..7e03ccd 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -183,6 +183,7 @@ static int hfi1_file_open(struct inode *inode, struct file *fp) if (fd) { fd->rec_cpu_num = -1; /* no cpu affinity by default */ fd->mm = current->mm; + atomic_inc(&fd->mm->mm_count); } fp->private_data = fd; @@ -222,7 +223,7 @@ static long hfi1_file_ioctl(struct file *fp, unsigned int cmd, ret = assign_ctxt(fp, &uinfo); if (ret < 0) return ret; - setup_ctxt(fp); + ret = setup_ctxt(fp); if (ret) return ret; ret = user_init(fp); @@ -779,6 +780,7 @@ static int hfi1_file_close(struct inode *inode, struct file *fp) mutex_unlock(&hfi1_mutex); hfi1_free_ctxtdata(dd, uctxt); done: + mmdrop(fdata->mm); kobject_put(&dd->kobj); kfree(fdata); return 0; diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index 1000e0f..a021e66 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -1272,9 +1272,26 @@ static inline int hdr2sc(struct hfi1_message_header *hdr, u64 rhf) ((!!(rhf_dc_info(rhf))) << 4); } +#define HFI1_JKEY_WIDTH 16 +#define HFI1_JKEY_MASK (BIT(16) - 1) +#define HFI1_ADMIN_JKEY_RANGE 32 + +/* + * J_KEYs are split and allocated in the following groups: + * 0 - 31 - users with administrator privileges + * 32 - 63 - kernel protocols using KDETH packets + * 64 - 65535 - all other users using KDETH packets + */ static inline u16 generate_jkey(kuid_t uid) { - return from_kuid(current_user_ns(), uid) & 0xffff; + u16 jkey = from_kuid(current_user_ns(), uid) & HFI1_JKEY_MASK; + + if (capable(CAP_SYS_ADMIN)) + jkey &= HFI1_ADMIN_JKEY_RANGE - 1; + else if (jkey < 64) + jkey |= BIT(HFI1_JKEY_WIDTH - 1); + + return jkey; } /* @@ -1656,7 +1673,6 @@ struct cc_state *get_cc_state_protected(struct hfi1_pportdata *ppd) struct hfi1_devdata *hfi1_init_dd(struct pci_dev *, const struct pci_device_id *); void hfi1_free_devdata(struct hfi1_devdata *); -void cc_state_reclaim(struct rcu_head *rcu); struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, size_t extra); /* LED beaconing functions */ diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index a358d23..b793545 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -1333,7 +1333,7 @@ static void cleanup_device_data(struct hfi1_devdata *dd) spin_unlock(&ppd->cc_state_lock); if (cc_state) - call_rcu(&cc_state->rcu, cc_state_reclaim); + kfree_rcu(cc_state, rcu); } free_credit_return(dd); diff --git a/drivers/infiniband/hw/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c index 1263abe..39e42c3 100644 --- a/drivers/infiniband/hw/hfi1/mad.c +++ b/drivers/infiniband/hw/hfi1/mad.c @@ -1819,6 +1819,11 @@ static int __subn_get_opa_cable_info(struct opa_smp *smp, u32 am, u8 *data, u32 len = OPA_AM_CI_LEN(am) + 1; int ret; + if (dd->pport->port_type != PORT_TYPE_QSFP) { + smp->status |= IB_SMP_INVALID_FIELD; + return reply((struct ib_mad_hdr *)smp); + } + #define __CI_PAGE_SIZE BIT(7) /* 128 bytes */ #define __CI_PAGE_MASK ~(__CI_PAGE_SIZE - 1) #define __CI_PAGE_NUM(a) ((a) & __CI_PAGE_MASK) @@ -3398,7 +3403,7 @@ static void apply_cc_state(struct hfi1_pportdata *ppd) spin_unlock(&ppd->cc_state_lock); - call_rcu(&old_cc_state->rcu, cc_state_reclaim); + kfree_rcu(old_cc_state, rcu); } static int __subn_set_opa_cong_setting(struct opa_smp *smp, u32 am, u8 *data, @@ -3553,13 +3558,6 @@ static int __subn_get_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data, return reply((struct ib_mad_hdr *)smp); } -void cc_state_reclaim(struct rcu_head *rcu) -{ - struct cc_state *cc_state = container_of(rcu, struct cc_state, rcu); - - kfree(cc_state); -} - static int __subn_set_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, u32 *resp_len) diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c index a5aa351..4e4d831 100644 --- a/drivers/infiniband/hw/hfi1/qp.c +++ b/drivers/infiniband/hw/hfi1/qp.c @@ -656,10 +656,6 @@ struct qp_iter *qp_iter_init(struct hfi1_ibdev *dev) iter->dev = dev; iter->specials = dev->rdi.ibdev.phys_port_cnt * 2; - if (qp_iter_next(iter)) { - kfree(iter); - return NULL; - } return iter; } diff --git a/drivers/infiniband/hw/hfi1/qsfp.c b/drivers/infiniband/hw/hfi1/qsfp.c index a207717..4e95ad8 100644 --- a/drivers/infiniband/hw/hfi1/qsfp.c +++ b/drivers/infiniband/hw/hfi1/qsfp.c @@ -706,8 +706,8 @@ int get_cable_info(struct hfi1_devdata *dd, u32 port_num, u32 addr, u32 len, u8 *data) { struct hfi1_pportdata *ppd; - u32 excess_len = 0; - int ret = 0; + u32 excess_len = len; + int ret = 0, offset = 0; if (port_num > dd->num_pports || port_num < 1) { dd_dev_info(dd, "%s: Invalid port number %d\n", @@ -740,6 +740,34 @@ int get_cable_info(struct hfi1_devdata *dd, u32 port_num, u32 addr, u32 len, } memcpy(data, &ppd->qsfp_info.cache[addr], len); + + if (addr <= QSFP_MONITOR_VAL_END && + (addr + len) >= QSFP_MONITOR_VAL_START) { + /* Overlap with the dynamic channel monitor range */ + if (addr < QSFP_MONITOR_VAL_START) { + if (addr + len <= QSFP_MONITOR_VAL_END) + len = addr + len - QSFP_MONITOR_VAL_START; + else + len = QSFP_MONITOR_RANGE; + offset = QSFP_MONITOR_VAL_START - addr; + addr = QSFP_MONITOR_VAL_START; + } else if (addr == QSFP_MONITOR_VAL_START) { + offset = 0; + if (addr + len > QSFP_MONITOR_VAL_END) + len = QSFP_MONITOR_RANGE; + } else { + offset = 0; + if (addr + len > QSFP_MONITOR_VAL_END) + len = QSFP_MONITOR_VAL_END - addr + 1; + } + /* Refresh the values of the dynamic monitors from the cable */ + ret = one_qsfp_read(ppd, dd->hfi1_id, addr, data + offset, len); + if (ret != len) { + ret = -EAGAIN; + goto set_zeroes; + } + } + return 0; set_zeroes: diff --git a/drivers/infiniband/hw/hfi1/qsfp.h b/drivers/infiniband/hw/hfi1/qsfp.h index 69275eb..36cf523 100644 --- a/drivers/infiniband/hw/hfi1/qsfp.h +++ b/drivers/infiniband/hw/hfi1/qsfp.h @@ -74,6 +74,9 @@ /* Defined fields that Intel requires of qualified cables */ /* Byte 0 is Identifier, not checked */ /* Byte 1 is reserved "status MSB" */ +#define QSFP_MONITOR_VAL_START 22 +#define QSFP_MONITOR_VAL_END 81 +#define QSFP_MONITOR_RANGE (QSFP_MONITOR_VAL_END - QSFP_MONITOR_VAL_START + 1) #define QSFP_TX_CTRL_BYTE_OFFS 86 #define QSFP_PWR_CTRL_BYTE_OFFS 93 #define QSFP_CDR_CTRL_BYTE_OFFS 98 diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h index b738acd..8ec09e4 100644 --- a/drivers/infiniband/hw/i40iw/i40iw.h +++ b/drivers/infiniband/hw/i40iw/i40iw.h @@ -232,7 +232,7 @@ struct i40iw_device { struct i40e_client *client; struct i40iw_hw hw; struct i40iw_cm_core cm_core; - unsigned long *mem_resources; + u8 *mem_resources; unsigned long *allocated_qps; unsigned long *allocated_cqs; unsigned long *allocated_mrs; @@ -435,8 +435,8 @@ static inline int i40iw_alloc_resource(struct i40iw_device *iwdev, *next = resource_num + 1; if (*next == max_resources) *next = 0; - spin_unlock_irqrestore(&iwdev->resource_lock, flags); *req_resource_num = resource_num; + spin_unlock_irqrestore(&iwdev->resource_lock, flags); return 0; } diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c index 5026dc7..7ca0638 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_cm.c +++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c @@ -535,8 +535,8 @@ static struct i40iw_puda_buf *i40iw_form_cm_frame(struct i40iw_cm_node *cm_node, buf += hdr_len; } - if (pd_len) - memcpy(buf, pdata->addr, pd_len); + if (pdata && pdata->addr) + memcpy(buf, pdata->addr, pdata->size); atomic_set(&sqbuf->refcount, 1); @@ -3347,26 +3347,6 @@ int i40iw_cm_disconn(struct i40iw_qp *iwqp) } /** - * i40iw_loopback_nop - Send a nop - * @qp: associated hw qp - */ -static void i40iw_loopback_nop(struct i40iw_sc_qp *qp) -{ - u64 *wqe; - u64 header; - - wqe = qp->qp_uk.sq_base->elem; - set_64bit_val(wqe, 0, 0); - set_64bit_val(wqe, 8, 0); - set_64bit_val(wqe, 16, 0); - - header = LS_64(I40IWQP_OP_NOP, I40IWQPSQ_OPCODE) | - LS_64(0, I40IWQPSQ_SIGCOMPL) | - LS_64(qp->qp_uk.swqe_polarity, I40IWQPSQ_VALID); - set_64bit_val(wqe, 24, header); -} - -/** * i40iw_qp_disconnect - free qp and close cm * @iwqp: associate qp for the connection */ @@ -3638,7 +3618,7 @@ int i40iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) } else { if (iwqp->page) iwqp->sc_qp.qp_uk.sq_base = kmap(iwqp->page); - i40iw_loopback_nop(&iwqp->sc_qp); + dev->iw_priv_qp_ops->qp_send_lsmm(&iwqp->sc_qp, NULL, 0, 0); } if (iwqp->page) diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c index 6e90813..0cbbe40 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_main.c +++ b/drivers/infiniband/hw/i40iw/i40iw_main.c @@ -1558,6 +1558,10 @@ static int i40iw_open(struct i40e_info *ldev, struct i40e_client *client) enum i40iw_status_code status; struct i40iw_handler *hdl; + hdl = i40iw_find_netdev(ldev->netdev); + if (hdl) + return 0; + hdl = kzalloc(sizeof(*hdl), GFP_KERNEL); if (!hdl) return -ENOMEM; diff --git a/drivers/infiniband/hw/i40iw/i40iw_utils.c b/drivers/infiniband/hw/i40iw/i40iw_utils.c index 0e8db0a..6fd043b 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_utils.c +++ b/drivers/infiniband/hw/i40iw/i40iw_utils.c @@ -673,8 +673,11 @@ enum i40iw_status_code i40iw_free_virt_mem(struct i40iw_hw *hw, { if (!mem) return I40IW_ERR_PARAM; + /* + * mem->va points to the parent of mem, so both mem and mem->va + * can not be touched once mem->va is freed + */ kfree(mem->va); - mem->va = NULL; return 0; } diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 2360338..6329c97 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -794,7 +794,6 @@ static struct ib_qp *i40iw_create_qp(struct ib_pd *ibpd, return &iwqp->ibqp; error: i40iw_free_qp_resources(iwdev, iwqp, qp_num); - kfree(mem); return ERR_PTR(err_code); } @@ -1926,8 +1925,7 @@ static int i40iw_dereg_mr(struct ib_mr *ib_mr) } if (iwpbl->pbl_allocated) i40iw_free_pble(iwdev->pble_rsrc, palloc); - kfree(iwpbl->iwmr); - iwpbl->iwmr = NULL; + kfree(iwmr); return 0; } diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index d6fc8a6..006db64 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -576,8 +576,8 @@ static int mlx4_ib_ipoib_csum_ok(__be16 status, __be16 checksum) checksum == cpu_to_be16(0xffff); } -static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct ib_wc *wc, - unsigned tail, struct mlx4_cqe *cqe, int is_eth) +static void use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct ib_wc *wc, + unsigned tail, struct mlx4_cqe *cqe, int is_eth) { struct mlx4_ib_proxy_sqp_hdr *hdr; @@ -600,8 +600,6 @@ static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct wc->slid = be16_to_cpu(hdr->tun.slid_mac_47_32); wc->sl = (u8) (be16_to_cpu(hdr->tun.sl_vid) >> 12); } - - return 0; } static void mlx4_ib_qp_sw_comp(struct mlx4_ib_qp *qp, int num_entries, @@ -692,7 +690,7 @@ repoll: if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == MLX4_OPCODE_NOP && is_send)) { pr_warn("Completion for NOP opcode detected!\n"); - return -EINVAL; + return -EAGAIN; } /* Resize CQ in progress */ @@ -723,7 +721,7 @@ repoll: if (unlikely(!mqp)) { pr_warn("CQ %06x with entry for unknown QPN %06x\n", cq->mcq.cqn, be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_QPN_MASK); - return -EINVAL; + return -EAGAIN; } *cur_qp = to_mibqp(mqp); @@ -741,7 +739,7 @@ repoll: if (unlikely(!msrq)) { pr_warn("CQ %06x with entry for unknown SRQN %06x\n", cq->mcq.cqn, srq_num); - return -EINVAL; + return -EAGAIN; } } @@ -852,9 +850,11 @@ repoll: if (mlx4_is_mfunc(to_mdev(cq->ibcq.device)->dev)) { if ((*cur_qp)->mlx4_ib_qp_type & (MLX4_IB_QPT_PROXY_SMI_OWNER | - MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI)) - return use_tunnel_data(*cur_qp, cq, wc, tail, - cqe, is_eth); + MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI)) { + use_tunnel_data(*cur_qp, cq, wc, tail, cqe, + is_eth); + return 0; + } } wc->slid = be16_to_cpu(cqe->rlid); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index a84bb76..1b4094b 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -37,7 +37,6 @@ #include <linux/pci.h> #include <linux/dma-mapping.h> #include <linux/slab.h> -#include <linux/io-mapping.h> #if defined(CONFIG_X86) #include <asm/pat.h> #endif diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c index 16740dc..67fc0b6 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c @@ -1156,18 +1156,18 @@ static void ocrdma_get_attr(struct ocrdma_dev *dev, attr->max_srq = (rsp->max_srq_rpir_qps & OCRDMA_MBX_QUERY_CFG_MAX_SRQ_MASK) >> OCRDMA_MBX_QUERY_CFG_MAX_SRQ_OFFSET; - attr->max_send_sge = ((rsp->max_write_send_sge & + attr->max_send_sge = ((rsp->max_recv_send_sge & OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_MASK) >> OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_SHIFT); - attr->max_recv_sge = (rsp->max_write_send_sge & - OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_MASK) >> - OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_SHIFT; + attr->max_recv_sge = (rsp->max_recv_send_sge & + OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_MASK) >> + OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_SHIFT; attr->max_srq_sge = (rsp->max_srq_rqe_sge & OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_MASK) >> OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_OFFSET; - attr->max_rdma_sge = (rsp->max_write_send_sge & - OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_MASK) >> - OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_SHIFT; + attr->max_rdma_sge = (rsp->max_wr_rd_sge & + OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_MASK) >> + OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_SHIFT; attr->max_ord_per_qp = (rsp->max_ird_ord_per_qp & OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_MASK) >> OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_SHIFT; diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h index 0efc966..37df448 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h @@ -554,9 +554,9 @@ enum { OCRDMA_MBX_QUERY_CFG_L3_TYPE_MASK = 0x18, OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_SHIFT = 0, OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_MASK = 0xFFFF, - OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_SHIFT = 16, - OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_MASK = 0xFFFF << - OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_SHIFT, + OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_SHIFT = 16, + OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_MASK = 0xFFFF << + OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_SHIFT, OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_SHIFT = 0, OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_MASK = 0xFFFF, @@ -612,6 +612,8 @@ enum { OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_OFFSET = 0, OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_MASK = 0xFFFF << OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_OFFSET, + OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_SHIFT = 0, + OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_MASK = 0xFFFF, }; struct ocrdma_mbx_query_config { @@ -619,7 +621,7 @@ struct ocrdma_mbx_query_config { struct ocrdma_mbx_rsp rsp; u32 qp_srq_cq_ird_ord; u32 max_pd_ca_ack_delay; - u32 max_write_send_sge; + u32 max_recv_send_sge; u32 max_ird_ord_per_qp; u32 max_shared_ird_ord; u32 max_mr; @@ -639,6 +641,8 @@ struct ocrdma_mbx_query_config { u32 max_wqes_rqes_per_q; u32 max_cq_cqes_per_cq; u32 max_srq_rqe_sge; + u32 max_wr_rd_sge; + u32 ird_pgsz_num_pages; }; struct ocrdma_fw_ver_rsp { diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c index b1a3d91..0aa8547 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c @@ -125,8 +125,8 @@ int ocrdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr, IB_DEVICE_SYS_IMAGE_GUID | IB_DEVICE_LOCAL_DMA_LKEY | IB_DEVICE_MEM_MGT_EXTENSIONS; - attr->max_sge = dev->attr.max_send_sge; - attr->max_sge_rd = attr->max_sge; + attr->max_sge = min(dev->attr.max_send_sge, dev->attr.max_recv_sge); + attr->max_sge_rd = dev->attr.max_rdma_sge; attr->max_cq = dev->attr.max_cq; attr->max_cqe = dev->attr.max_cqe; attr->max_mr = dev->attr.max_mr; diff --git a/drivers/infiniband/hw/qib/qib_debugfs.c b/drivers/infiniband/hw/qib/qib_debugfs.c index 5e75b43..5bad8e3 100644 --- a/drivers/infiniband/hw/qib/qib_debugfs.c +++ b/drivers/infiniband/hw/qib/qib_debugfs.c @@ -189,27 +189,32 @@ static int _ctx_stats_seq_show(struct seq_file *s, void *v) DEBUGFS_FILE(ctx_stats) static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos) + __acquires(RCU) { struct qib_qp_iter *iter; loff_t n = *pos; - rcu_read_lock(); iter = qib_qp_iter_init(s->private); + + /* stop calls rcu_read_unlock */ + rcu_read_lock(); + if (!iter) return NULL; - while (n--) { + do { if (qib_qp_iter_next(iter)) { kfree(iter); return NULL; } - } + } while (n--); return iter; } static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, loff_t *pos) + __must_hold(RCU) { struct qib_qp_iter *iter = iter_ptr; @@ -224,6 +229,7 @@ static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, } static void _qp_stats_seq_stop(struct seq_file *s, void *iter_ptr) + __releases(RCU) { rcu_read_unlock(); } diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c index fcdf3791..c3edc03 100644 --- a/drivers/infiniband/hw/qib/qib_fs.c +++ b/drivers/infiniband/hw/qib/qib_fs.c @@ -328,26 +328,12 @@ static ssize_t flash_write(struct file *file, const char __user *buf, pos = *ppos; - if (pos != 0) { - ret = -EINVAL; - goto bail; - } - - if (count != sizeof(struct qib_flash)) { - ret = -EINVAL; - goto bail; - } - - tmp = kmalloc(count, GFP_KERNEL); - if (!tmp) { - ret = -ENOMEM; - goto bail; - } + if (pos != 0 || count != sizeof(struct qib_flash)) + return -EINVAL; - if (copy_from_user(tmp, buf, count)) { - ret = -EFAULT; - goto bail_tmp; - } + tmp = memdup_user(buf, count); + if (IS_ERR(tmp)) + return PTR_ERR(tmp); dd = private2dd(file); if (qib_eeprom_write(dd, pos, tmp, count)) { @@ -361,8 +347,6 @@ static ssize_t flash_write(struct file *file, const char __user *buf, bail_tmp: kfree(tmp); - -bail: return ret; } diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c index 9cc0aae..f9b8cd2 100644 --- a/drivers/infiniband/hw/qib/qib_qp.c +++ b/drivers/infiniband/hw/qib/qib_qp.c @@ -573,10 +573,6 @@ struct qib_qp_iter *qib_qp_iter_init(struct qib_ibdev *dev) return NULL; iter->dev = dev; - if (qib_qp_iter_next(iter)) { - kfree(iter); - return NULL; - } return iter; } diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c index c229b9f..0a89a95 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_main.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c @@ -664,7 +664,8 @@ static int __init usnic_ib_init(void) return err; } - if (pci_register_driver(&usnic_ib_pci_driver)) { + err = pci_register_driver(&usnic_ib_pci_driver); + if (err) { usnic_err("Unable to register with PCI\n"); goto out_umem_fini; } diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index bdb540f..870b4f2 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -873,7 +873,8 @@ bail_qpn: free_qpn(&rdi->qp_dev->qpn_table, qp->ibqp.qp_num); bail_rq_wq: - vfree(qp->r_rq.wq); + if (!qp->ip) + vfree(qp->r_rq.wq); bail_driver_priv: rdi->driver_f.qp_priv_free(rdi, qp); diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index ba6be06..7914c14 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -448,7 +448,7 @@ isert_alloc_login_buf(struct isert_conn *isert_conn, isert_conn->login_rsp_buf = kzalloc(ISER_RX_PAYLOAD_SIZE, GFP_KERNEL); if (!isert_conn->login_rsp_buf) { - isert_err("Unable to allocate isert_conn->login_rspbuf\n"); + ret = -ENOMEM; goto out_unmap_login_req_buf; } diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index dfa23b0..883bbfe 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -522,6 +522,11 @@ static int srpt_refresh_port(struct srpt_port *sport) if (ret) goto err_query_port; + snprintf(sport->port_guid, sizeof(sport->port_guid), + "0x%016llx%016llx", + be64_to_cpu(sport->gid.global.subnet_prefix), + be64_to_cpu(sport->gid.global.interface_id)); + if (!sport->mad_agent) { memset(®_req, 0, sizeof(reg_req)); reg_req.mgmt_class = IB_MGMT_CLASS_DEVICE_MGMT; @@ -2548,10 +2553,6 @@ static void srpt_add_one(struct ib_device *device) sdev->device->name, i); goto err_ring; } - snprintf(sport->port_guid, sizeof(sport->port_guid), - "0x%016llx%016llx", - be64_to_cpu(sport->gid.global.subnet_prefix), - be64_to_cpu(sport->gid.global.interface_id)); } spin_lock(&srpt_dev_lock); diff --git a/drivers/input/keyboard/tegra-kbc.c b/drivers/input/keyboard/tegra-kbc.c index 7d61439..0c07e10 100644 --- a/drivers/input/keyboard/tegra-kbc.c +++ b/drivers/input/keyboard/tegra-kbc.c @@ -376,7 +376,7 @@ static int tegra_kbc_start(struct tegra_kbc *kbc) /* Reset the KBC controller to clear all previous status.*/ reset_control_assert(kbc->rst); udelay(100); - reset_control_assert(kbc->rst); + reset_control_deassert(kbc->rst); udelay(100); tegra_kbc_config_pins(kbc); diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c index faa295e..c83bce8 100644 --- a/drivers/input/rmi4/rmi_driver.c +++ b/drivers/input/rmi4/rmi_driver.c @@ -553,7 +553,6 @@ int rmi_read_register_desc(struct rmi_device *d, u16 addr, goto free_struct_buff; reg = find_first_bit(rdesc->presense_map, RMI_REG_DESC_PRESENSE_BITS); - map_offset = 0; for (i = 0; i < rdesc->num_registers; i++) { struct rmi_register_desc_item *item = &rdesc->registers[i]; int reg_size = struct_buf[offset]; @@ -576,6 +575,8 @@ int rmi_read_register_desc(struct rmi_device *d, u16 addr, item->reg = reg; item->reg_size = reg_size; + map_offset = 0; + do { for (b = 0; b < 7; b++) { if (struct_buf[offset] & (0x1 << b)) diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index b4d3408..405252a 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -1305,6 +1305,7 @@ static int __init i8042_create_aux_port(int idx) serio->write = i8042_aux_write; serio->start = i8042_start; serio->stop = i8042_stop; + serio->ps2_cmd_mutex = &i8042_mutex; serio->port_data = port; serio->dev.parent = &i8042_platform_device->dev; if (idx < 0) { diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c index a61b215..1ce3ecb 100644 --- a/drivers/input/touchscreen/ads7846.c +++ b/drivers/input/touchscreen/ads7846.c @@ -1473,7 +1473,6 @@ static int ads7846_remove(struct spi_device *spi) ads784x_hwmon_unregister(spi, ts); - regulator_disable(ts->reg); regulator_put(ts->reg); if (!ts->get_pendown_state) { diff --git a/drivers/input/touchscreen/silead.c b/drivers/input/touchscreen/silead.c index 7379fe1..b2744a6 100644 --- a/drivers/input/touchscreen/silead.c +++ b/drivers/input/touchscreen/silead.c @@ -464,7 +464,7 @@ static int silead_ts_probe(struct i2c_client *client, return -ENODEV; /* Power GPIO pin */ - data->gpio_power = gpiod_get_optional(dev, "power", GPIOD_OUT_LOW); + data->gpio_power = devm_gpiod_get_optional(dev, "power", GPIOD_OUT_LOW); if (IS_ERR(data->gpio_power)) { if (PTR_ERR(data->gpio_power) != -EPROBE_DEFER) dev_err(dev, "Shutdown GPIO request failed\n"); diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index ce80117..641e887 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -879,7 +879,7 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu) * We may have concurrent producers, so we need to be careful * not to touch any of the shadow cmdq state. */ - queue_read(cmd, Q_ENT(q, idx), q->ent_dwords); + queue_read(cmd, Q_ENT(q, cons), q->ent_dwords); dev_err(smmu->dev, "skipping command in error state:\n"); for (i = 0; i < ARRAY_SIZE(cmd); ++i) dev_err(smmu->dev, "\t0x%016llx\n", (unsigned long long)cmd[i]); @@ -890,7 +890,7 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu) return; } - queue_write(cmd, Q_ENT(q, idx), q->ent_dwords); + queue_write(Q_ENT(q, cons), cmd, q->ent_dwords); } static void arm_smmu_cmdq_issue_cmd(struct arm_smmu_device *smmu, @@ -1034,6 +1034,9 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, case STRTAB_STE_0_CFG_S2_TRANS: ste_live = true; break; + case STRTAB_STE_0_CFG_ABORT: + if (disable_bypass) + break; default: BUG(); /* STE corruption */ } diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 4f49fe2..2db74eb 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -686,8 +686,7 @@ static struct iommu_gather_ops arm_smmu_gather_ops = { static irqreturn_t arm_smmu_context_fault(int irq, void *dev) { - int flags, ret; - u32 fsr, fsynr, resume; + u32 fsr, fsynr; unsigned long iova; struct iommu_domain *domain = dev; struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); @@ -701,34 +700,15 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev) if (!(fsr & FSR_FAULT)) return IRQ_NONE; - if (fsr & FSR_IGN) - dev_err_ratelimited(smmu->dev, - "Unexpected context fault (fsr 0x%x)\n", - fsr); - fsynr = readl_relaxed(cb_base + ARM_SMMU_CB_FSYNR0); - flags = fsynr & FSYNR0_WNR ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ; - iova = readq_relaxed(cb_base + ARM_SMMU_CB_FAR); - if (!report_iommu_fault(domain, smmu->dev, iova, flags)) { - ret = IRQ_HANDLED; - resume = RESUME_RETRY; - } else { - dev_err_ratelimited(smmu->dev, - "Unhandled context fault: iova=0x%08lx, fsynr=0x%x, cb=%d\n", - iova, fsynr, cfg->cbndx); - ret = IRQ_NONE; - resume = RESUME_TERMINATE; - } - - /* Clear the faulting FSR */ - writel(fsr, cb_base + ARM_SMMU_CB_FSR); - /* Retry or terminate any stalled transactions */ - if (fsr & FSR_SS) - writel_relaxed(resume, cb_base + ARM_SMMU_CB_RESUME); + dev_err_ratelimited(smmu->dev, + "Unhandled context fault: fsr=0x%x, iova=0x%08lx, fsynr=0x%x, cb=%d\n", + fsr, iova, fsynr, cfg->cbndx); - return ret; + writel(fsr, cb_base + ARM_SMMU_CB_FSR); + return IRQ_HANDLED; } static irqreturn_t arm_smmu_global_fault(int irq, void *dev) @@ -837,7 +817,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain, } /* SCTLR */ - reg = SCTLR_CFCFG | SCTLR_CFIE | SCTLR_CFRE | SCTLR_M | SCTLR_EAE_SBOP; + reg = SCTLR_CFIE | SCTLR_CFRE | SCTLR_M | SCTLR_EAE_SBOP; if (stage1) reg |= SCTLR_S1_ASIDPNE; #ifdef __BIG_ENDIAN diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index 8c61399..def8ca1 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -286,12 +286,14 @@ static int arm_v7s_pte_to_prot(arm_v7s_iopte pte, int lvl) int prot = IOMMU_READ; arm_v7s_iopte attr = pte >> ARM_V7S_ATTR_SHIFT(lvl); - if (attr & ARM_V7S_PTE_AP_RDONLY) + if (!(attr & ARM_V7S_PTE_AP_RDONLY)) prot |= IOMMU_WRITE; if ((attr & (ARM_V7S_TEX_MASK << ARM_V7S_TEX_SHIFT)) == 0) prot |= IOMMU_MMIO; else if (pte & ARM_V7S_ATTR_C) prot |= IOMMU_CACHE; + if (pte & ARM_V7S_ATTR_XN(lvl)) + prot |= IOMMU_NOEXEC; return prot; } diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 95a4ca6..849ad44 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -760,7 +760,8 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size, if (!d->nr_stripes || d->nr_stripes > INT_MAX || d->nr_stripes > SIZE_MAX / sizeof(atomic_t)) { - pr_err("nr_stripes too large"); + pr_err("nr_stripes too large or invalid: %u (start sector beyond end of disk?)", + (unsigned)d->nr_stripes); return -ENOMEM; } @@ -1820,7 +1821,7 @@ static int cache_alloc(struct cache *ca) free = roundup_pow_of_two(ca->sb.nbuckets) >> 10; if (!init_fifo(&ca->free[RESERVE_BTREE], 8, GFP_KERNEL) || - !init_fifo(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) || + !init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) || !init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL) || !init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL) || !init_fifo(&ca->free_inc, free << 2, GFP_KERNEL) || @@ -1844,7 +1845,7 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page, struct block_device *bdev, struct cache *ca) { char name[BDEVNAME_SIZE]; - const char *err = NULL; + const char *err = NULL; /* must be set for any error case */ int ret = 0; memcpy(&ca->sb, sb, sizeof(struct cache_sb)); @@ -1861,8 +1862,13 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page, ca->discard = CACHE_DISCARD(&ca->sb); ret = cache_alloc(ca); - if (ret != 0) + if (ret != 0) { + if (ret == -ENOMEM) + err = "cache_alloc(): -ENOMEM"; + else + err = "cache_alloc(): unknown error"; goto err; + } if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache")) { err = "error calling kobject_add"; diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 97e446d..6a2e8dd 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -289,15 +289,13 @@ static int flakey_map(struct dm_target *ti, struct bio *bio) pb->bio_submitted = true; /* - * Map reads as normal only if corrupt_bio_byte set. + * Error reads if neither corrupt_bio_byte or drop_writes are set. + * Otherwise, flakey_end_io() will decide if the reads should be modified. */ if (bio_data_dir(bio) == READ) { - /* If flags were specified, only corrupt those that match. */ - if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) && - all_corrupt_bio_flags_match(bio, fc)) - goto map_bio; - else + if (!fc->corrupt_bio_byte && !test_bit(DROP_WRITES, &fc->flags)) return -EIO; + goto map_bio; } /* @@ -334,14 +332,21 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, int error) struct flakey_c *fc = ti->private; struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); - /* - * Corrupt successful READs while in down state. - */ if (!error && pb->bio_submitted && (bio_data_dir(bio) == READ)) { - if (fc->corrupt_bio_byte) + if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) && + all_corrupt_bio_flags_match(bio, fc)) { + /* + * Corrupt successful matching READs while in down state. + */ corrupt_bio_data(bio, fc); - else + + } else if (!test_bit(DROP_WRITES, &fc->flags)) { + /* + * Error read during the down_interval if drop_writes + * wasn't configured. + */ return -EIO; + } } return error; diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c index 4ca2d1d..07fc1ad 100644 --- a/drivers/md/dm-log.c +++ b/drivers/md/dm-log.c @@ -291,9 +291,10 @@ static void header_from_disk(struct log_header_core *core, struct log_header_dis core->nr_regions = le64_to_cpu(disk->nr_regions); } -static int rw_header(struct log_c *lc, int rw) +static int rw_header(struct log_c *lc, int op) { - lc->io_req.bi_op = rw; + lc->io_req.bi_op = op; + lc->io_req.bi_op_flags = 0; return dm_io(&lc->io_req, 1, &lc->header_location, NULL); } @@ -316,7 +317,7 @@ static int read_header(struct log_c *log) { int r; - r = rw_header(log, READ); + r = rw_header(log, REQ_OP_READ); if (r) return r; @@ -630,7 +631,7 @@ static int disk_resume(struct dm_dirty_log *log) header_to_disk(&lc->header, lc->disk_header); /* write the new header */ - r = rw_header(lc, WRITE); + r = rw_header(lc, REQ_OP_WRITE); if (!r) { r = flush_header(lc); if (r) @@ -698,7 +699,7 @@ static int disk_flush(struct dm_dirty_log *log) log_clear_bit(lc, lc->clean_bits, i); } - r = rw_header(lc, WRITE); + r = rw_header(lc, REQ_OP_WRITE); if (r) fail_log_device(lc); else { diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 48a5dd7..2206d44 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -1726,6 +1726,7 @@ static u8 mmc_blk_prep_packed_list(struct mmc_queue *mq, struct request *req) break; if (req_op(next) == REQ_OP_DISCARD || + req_op(next) == REQ_OP_SECURE_ERASE || req_op(next) == REQ_OP_FLUSH) break; @@ -2150,6 +2151,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req) struct mmc_card *card = md->queue.card; struct mmc_host *host = card->host; unsigned long flags; + bool req_is_special = mmc_req_is_special(req); if (req && !mq->mqrq_prev->req) /* claim host only for the first request */ @@ -2190,8 +2192,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req) } out: - if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) || - mmc_req_is_special(req)) + if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) || req_is_special) /* * Release host when there are no more requests * and after special request(discard, flush) is done. diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index bf14642..7080572 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -33,7 +33,8 @@ static int mmc_prep_request(struct request_queue *q, struct request *req) /* * We only like normal block requests and discards. */ - if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD) { + if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD && + req_op(req) != REQ_OP_SECURE_ERASE) { blk_dump_rq_flags(req, "MMC bad request"); return BLKPREP_KILL; } @@ -64,6 +65,8 @@ static int mmc_queue_thread(void *d) spin_unlock_irq(q->queue_lock); if (req || mq->mqrq_prev->req) { + bool req_is_special = mmc_req_is_special(req); + set_current_state(TASK_RUNNING); mq->issue_fn(mq, req); cond_resched(); @@ -79,7 +82,7 @@ static int mmc_queue_thread(void *d) * has been finished. Do not assign it to previous * request. */ - if (mmc_req_is_special(req)) + if (req_is_special) mq->mqrq_cur->req = NULL; mq->mqrq_prev->brq.mrq.data = NULL; diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h index d625311..fee5e12 100644 --- a/drivers/mmc/card/queue.h +++ b/drivers/mmc/card/queue.h @@ -4,7 +4,9 @@ static inline bool mmc_req_is_special(struct request *req) { return req && - (req_op(req) == REQ_OP_FLUSH || req_op(req) == REQ_OP_DISCARD); + (req_op(req) == REQ_OP_FLUSH || + req_op(req) == REQ_OP_DISCARD || + req_op(req) == REQ_OP_SECURE_ERASE); } struct request; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 7ff2e82..2feacc7 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -81,10 +81,12 @@ EXPORT_SYMBOL_GPL(nvme_cancel_request); bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, enum nvme_ctrl_state new_state) { - enum nvme_ctrl_state old_state = ctrl->state; + enum nvme_ctrl_state old_state; bool changed = false; spin_lock_irq(&ctrl->lock); + + old_state = ctrl->state; switch (new_state) { case NVME_CTRL_LIVE: switch (old_state) { @@ -140,11 +142,12 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, default: break; } - spin_unlock_irq(&ctrl->lock); if (changed) ctrl->state = new_state; + spin_unlock_irq(&ctrl->lock); + return changed; } EXPORT_SYMBOL_GPL(nvme_change_ctrl_state); @@ -608,7 +611,7 @@ int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid, ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0, NVME_QID_ANY, 0, 0); - if (ret >= 0) + if (ret >= 0 && result) *result = le32_to_cpu(cqe.result); return ret; } @@ -628,7 +631,7 @@ int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0, NVME_QID_ANY, 0, 0); - if (ret >= 0) + if (ret >= 0 && result) *result = le32_to_cpu(cqe.result); return ret; } diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index eafa613..98f1222 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -1069,7 +1069,7 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, nvec = maxvec; for (;;) { - if (!(flags & PCI_IRQ_NOAFFINITY)) { + if (flags & PCI_IRQ_AFFINITY) { dev->irq_affinity = irq_create_affinity_mask(&nvec); if (nvec < minvec) return -ENOSPC; @@ -1105,7 +1105,7 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, **/ int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec) { - return __pci_enable_msi_range(dev, minvec, maxvec, PCI_IRQ_NOAFFINITY); + return __pci_enable_msi_range(dev, minvec, maxvec, 0); } EXPORT_SYMBOL(pci_enable_msi_range); @@ -1120,7 +1120,7 @@ static int __pci_enable_msix_range(struct pci_dev *dev, return -ERANGE; for (;;) { - if (!(flags & PCI_IRQ_NOAFFINITY)) { + if (flags & PCI_IRQ_AFFINITY) { dev->irq_affinity = irq_create_affinity_mask(&nvec); if (nvec < minvec) return -ENOSPC; @@ -1160,8 +1160,7 @@ static int __pci_enable_msix_range(struct pci_dev *dev, int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, int maxvec) { - return __pci_enable_msix_range(dev, entries, minvec, maxvec, - PCI_IRQ_NOAFFINITY); + return __pci_enable_msix_range(dev, entries, minvec, maxvec, 0); } EXPORT_SYMBOL(pci_enable_msix_range); @@ -1187,22 +1186,25 @@ int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, { int vecs = -ENOSPC; - if (!(flags & PCI_IRQ_NOMSIX)) { + if (flags & PCI_IRQ_MSIX) { vecs = __pci_enable_msix_range(dev, NULL, min_vecs, max_vecs, flags); if (vecs > 0) return vecs; } - if (!(flags & PCI_IRQ_NOMSI)) { + if (flags & PCI_IRQ_MSI) { vecs = __pci_enable_msi_range(dev, min_vecs, max_vecs, flags); if (vecs > 0) return vecs; } /* use legacy irq if allowed */ - if (!(flags & PCI_IRQ_NOLEGACY) && min_vecs == 1) + if ((flags & PCI_IRQ_LEGACY) && min_vecs == 1) { + pci_intx(dev, 1); return 1; + } + return vecs; } EXPORT_SYMBOL(pci_alloc_irq_vectors); diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 3788ed7..a32b417 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -740,12 +740,22 @@ static int cpufreq_power2state(struct thermal_cooling_device *cdev, } /* Bind cpufreq callbacks to thermal cooling device ops */ + static struct thermal_cooling_device_ops cpufreq_cooling_ops = { .get_max_state = cpufreq_get_max_state, .get_cur_state = cpufreq_get_cur_state, .set_cur_state = cpufreq_set_cur_state, }; +static struct thermal_cooling_device_ops cpufreq_power_cooling_ops = { + .get_max_state = cpufreq_get_max_state, + .get_cur_state = cpufreq_get_cur_state, + .set_cur_state = cpufreq_set_cur_state, + .get_requested_power = cpufreq_get_requested_power, + .state2power = cpufreq_state2power, + .power2state = cpufreq_power2state, +}; + /* Notifier for cpufreq policy change */ static struct notifier_block thermal_cpufreq_notifier_block = { .notifier_call = cpufreq_thermal_notifier, @@ -795,6 +805,7 @@ __cpufreq_cooling_register(struct device_node *np, struct cpumask temp_mask; unsigned int freq, i, num_cpus; int ret; + struct thermal_cooling_device_ops *cooling_ops; cpumask_and(&temp_mask, clip_cpus, cpu_online_mask); policy = cpufreq_cpu_get(cpumask_first(&temp_mask)); @@ -850,10 +861,6 @@ __cpufreq_cooling_register(struct device_node *np, cpumask_copy(&cpufreq_dev->allowed_cpus, clip_cpus); if (capacitance) { - cpufreq_cooling_ops.get_requested_power = - cpufreq_get_requested_power; - cpufreq_cooling_ops.state2power = cpufreq_state2power; - cpufreq_cooling_ops.power2state = cpufreq_power2state; cpufreq_dev->plat_get_static_power = plat_static_func; ret = build_dyn_power_table(cpufreq_dev, capacitance); @@ -861,6 +868,10 @@ __cpufreq_cooling_register(struct device_node *np, cool_dev = ERR_PTR(ret); goto free_table; } + + cooling_ops = &cpufreq_power_cooling_ops; + } else { + cooling_ops = &cpufreq_cooling_ops; } ret = get_idr(&cpufreq_idr, &cpufreq_dev->id); @@ -885,7 +896,7 @@ __cpufreq_cooling_register(struct device_node *np, cpufreq_dev->id); cool_dev = thermal_of_cooling_device_register(np, dev_name, cpufreq_dev, - &cpufreq_cooling_ops); + cooling_ops); if (IS_ERR(cool_dev)) goto remove_idr; diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c index c5547bd..e473548 100644 --- a/drivers/thermal/imx_thermal.c +++ b/drivers/thermal/imx_thermal.c @@ -471,8 +471,6 @@ MODULE_DEVICE_TABLE(of, of_imx_thermal_match); static int imx_thermal_probe(struct platform_device *pdev) { - const struct of_device_id *of_id = - of_match_device(of_imx_thermal_match, &pdev->dev); struct imx_thermal_data *data; struct regmap *map; int measure_freq; @@ -490,7 +488,7 @@ static int imx_thermal_probe(struct platform_device *pdev) } data->tempmon = map; - data->socdata = of_id->data; + data->socdata = of_device_get_match_data(&pdev->dev); /* make sure the IRQ flag is clear before enabling irq on i.MX6SX */ if (data->socdata->version == TEMPMON_IMX6SX) { diff --git a/drivers/thermal/int340x_thermal/int3406_thermal.c b/drivers/thermal/int340x_thermal/int3406_thermal.c index a578cd2..1891f34 100644 --- a/drivers/thermal/int340x_thermal/int3406_thermal.c +++ b/drivers/thermal/int340x_thermal/int3406_thermal.c @@ -225,7 +225,6 @@ static struct platform_driver int3406_thermal_driver = { .remove = int3406_thermal_remove, .driver = { .name = "int3406 thermal", - .owner = THIS_MODULE, .acpi_match_table = int3406_thermal_match, }, }; diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 9d6320e..6e29d05 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -88,7 +88,7 @@ struct vhost_scsi_cmd { struct scatterlist *tvc_prot_sgl; struct page **tvc_upages; /* Pointer to response header iovec */ - struct iovec *tvc_resp_iov; + struct iovec tvc_resp_iov; /* Pointer to vhost_scsi for our device */ struct vhost_scsi *tvc_vhost; /* Pointer to vhost_virtqueue for the cmd */ @@ -547,7 +547,7 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work) memcpy(v_rsp.sense, cmd->tvc_sense_buf, se_cmd->scsi_sense_length); - iov_iter_init(&iov_iter, READ, cmd->tvc_resp_iov, + iov_iter_init(&iov_iter, READ, &cmd->tvc_resp_iov, cmd->tvc_in_iovs, sizeof(v_rsp)); ret = copy_to_iter(&v_rsp, sizeof(v_rsp), &iov_iter); if (likely(ret == sizeof(v_rsp))) { @@ -1044,7 +1044,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) } cmd->tvc_vhost = vs; cmd->tvc_vq = vq; - cmd->tvc_resp_iov = &vq->iov[out]; + cmd->tvc_resp_iov = vq->iov[out]; cmd->tvc_in_iovs = in; pr_debug("vhost_scsi got command opcode: %#02x, lun: %d\n", diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 7487971..c1010f01 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -316,7 +316,7 @@ static int xenbus_write_transaction(unsigned msg_type, rc = -ENOMEM; goto out; } - } else { + } else if (msg_type == XS_TRANSACTION_END) { list_for_each_entry(trans, &u->transactions, list) if (trans->handle.id == u->u.msg.tx_id) break; diff --git a/fs/block_dev.c b/fs/block_dev.c index c3cdde8..08ae993 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -249,7 +249,8 @@ struct super_block *freeze_bdev(struct block_device *bdev) * thaw_bdev drops it. */ sb = get_super(bdev); - drop_super(sb); + if (sb) + drop_super(sb); mutex_unlock(&bdev->bd_fsfreeze_mutex); return sb; } @@ -646,7 +647,7 @@ static struct dentry *bd_mount(struct file_system_type *fs_type, { struct dentry *dent; dent = mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, BDEVFS_MAGIC); - if (dent) + if (!IS_ERR(dent)) dent->d_sb->s_iflags |= SB_I_CGROUPWB; return dent; } diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 2b88439..455a6b2 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -589,6 +589,7 @@ static void __merge_refs(struct list_head *head, int mode) list_del(&ref2->list); kmem_cache_free(btrfs_prelim_ref_cache, ref2); + cond_resched(); } } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 2fe8f89..eff3993 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1028,6 +1028,7 @@ struct btrfs_fs_info { struct btrfs_workqueue *qgroup_rescan_workers; struct completion qgroup_rescan_completion; struct btrfs_work qgroup_rescan_work; + bool qgroup_rescan_running; /* protected by qgroup_rescan_lock */ /* filesystem state */ unsigned long fs_state; @@ -1079,6 +1080,8 @@ struct btrfs_fs_info { struct list_head pinned_chunks; int creating_free_space_tree; + /* Used to record internally whether fs has been frozen */ + int fs_frozen; }; struct btrfs_subvolume_writers { @@ -2578,7 +2581,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 root_objectid, u64 owner, u64 offset, struct btrfs_key *ins); -int btrfs_reserve_extent(struct btrfs_root *root, u64 num_bytes, +int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, u64 num_bytes, u64 min_alloc_size, u64 empty_size, u64 hint_byte, struct btrfs_key *ins, int is_data, int delalloc); int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index d9ddcfc..ac02e04 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -541,7 +541,6 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_head *existing; struct btrfs_delayed_ref_head *head_ref = NULL; struct btrfs_delayed_ref_root *delayed_refs; - struct btrfs_qgroup_extent_record *qexisting; int count_mod = 1; int must_insert_reserved = 0; @@ -606,10 +605,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, qrecord->num_bytes = num_bytes; qrecord->old_roots = NULL; - qexisting = btrfs_qgroup_insert_dirty_extent(fs_info, - delayed_refs, - qrecord); - if (qexisting) + if(btrfs_qgroup_insert_dirty_extent_nolock(fs_info, + delayed_refs, qrecord)) kfree(qrecord); } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 59febfb..54bc8c7 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -559,8 +559,29 @@ static noinline int check_leaf(struct btrfs_root *root, u32 nritems = btrfs_header_nritems(leaf); int slot; - if (nritems == 0) + if (nritems == 0) { + struct btrfs_root *check_root; + + key.objectid = btrfs_header_owner(leaf); + key.type = BTRFS_ROOT_ITEM_KEY; + key.offset = (u64)-1; + + check_root = btrfs_get_fs_root(root->fs_info, &key, false); + /* + * The only reason we also check NULL here is that during + * open_ctree() some roots has not yet been set up. + */ + if (!IS_ERR_OR_NULL(check_root)) { + /* if leaf is the root, then it's fine */ + if (leaf->start != + btrfs_root_bytenr(&check_root->root_item)) { + CORRUPT("non-root leaf's nritems is 0", + leaf, root, 0); + return -EIO; + } + } return 0; + } /* Check the 0 item */ if (btrfs_item_offset_nr(leaf, 0) + btrfs_item_size_nr(leaf, 0) != @@ -612,6 +633,19 @@ static noinline int check_leaf(struct btrfs_root *root, return 0; } +static int check_node(struct btrfs_root *root, struct extent_buffer *node) +{ + unsigned long nr = btrfs_header_nritems(node); + + if (nr == 0 || nr > BTRFS_NODEPTRS_PER_BLOCK(root)) { + btrfs_crit(root->fs_info, + "corrupt node: block %llu root %llu nritems %lu", + node->start, root->objectid, nr); + return -EIO; + } + return 0; +} + static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, u64 phy_offset, struct page *page, u64 start, u64 end, int mirror) @@ -682,6 +716,9 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, ret = -EIO; } + if (found_level > 0 && check_node(root, eb)) + ret = -EIO; + if (!ret) set_extent_buffer_uptodate(eb); err: @@ -1618,8 +1655,8 @@ fail: return ret; } -static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, - u64 root_id) +struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, + u64 root_id) { struct btrfs_root *root; @@ -2298,6 +2335,7 @@ static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info) fs_info->quota_enabled = 0; fs_info->pending_quota_state = 0; fs_info->qgroup_ulist = NULL; + fs_info->qgroup_rescan_running = false; mutex_init(&fs_info->qgroup_rescan_lock); } @@ -2624,6 +2662,7 @@ int open_ctree(struct super_block *sb, atomic_set(&fs_info->qgroup_op_seq, 0); atomic_set(&fs_info->reada_works_cnt, 0); atomic64_set(&fs_info->tree_mod_seq, 0); + fs_info->fs_frozen = 0; fs_info->sb = sb; fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE; fs_info->metadata_ratio = 0; @@ -3739,8 +3778,15 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, if (btrfs_root_refs(&root->root_item) == 0) synchronize_srcu(&fs_info->subvol_srcu); - if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) + if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { btrfs_free_log(NULL, root); + if (root->reloc_root) { + free_extent_buffer(root->reloc_root->node); + free_extent_buffer(root->reloc_root->commit_root); + btrfs_put_fs_root(root->reloc_root); + root->reloc_root = NULL; + } + } if (root->free_ino_pinned) __btrfs_remove_free_space_cache(root->free_ino_pinned); @@ -3851,7 +3897,7 @@ void close_ctree(struct btrfs_root *root) smp_mb(); /* wait for the qgroup rescan worker to stop */ - btrfs_qgroup_wait_for_completion(fs_info); + btrfs_qgroup_wait_for_completion(fs_info, false); /* wait for the uuid_scan task to finish */ down(&fs_info->uuid_tree_rescan_sem); diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index b3207a0e..f19a982 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -68,6 +68,8 @@ struct extent_buffer *btrfs_find_tree_block(struct btrfs_fs_info *fs_info, struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root, struct btrfs_key *location); int btrfs_init_fs_root(struct btrfs_root *root); +struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, + u64 root_id); int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root); void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 61b494e..0450dc4 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -60,21 +60,6 @@ enum { CHUNK_ALLOC_FORCE = 2, }; -/* - * Control how reservations are dealt with. - * - * RESERVE_FREE - freeing a reservation. - * RESERVE_ALLOC - allocating space and we need to update bytes_may_use for - * ENOSPC accounting - * RESERVE_ALLOC_NO_ACCOUNT - allocating space and we should not update - * bytes_may_use as the ENOSPC accounting is done elsewhere - */ -enum { - RESERVE_FREE = 0, - RESERVE_ALLOC = 1, - RESERVE_ALLOC_NO_ACCOUNT = 2, -}; - static int update_block_group(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, int alloc); @@ -104,9 +89,10 @@ static int find_next_key(struct btrfs_path *path, int level, struct btrfs_key *key); static void dump_space_info(struct btrfs_space_info *info, u64 bytes, int dump_block_groups); -static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache, - u64 num_bytes, int reserve, - int delalloc); +static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache, + u64 ram_bytes, u64 num_bytes, int delalloc); +static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache, + u64 num_bytes, int delalloc); static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv, u64 num_bytes); int btrfs_pin_extent(struct btrfs_root *root, @@ -3501,7 +3487,6 @@ again: dcs = BTRFS_DC_SETUP; else if (ret == -ENOSPC) set_bit(BTRFS_TRANS_CACHE_ENOSPC, &trans->transaction->flags); - btrfs_free_reserved_data_space(inode, 0, num_pages); out_put: iput(inode); @@ -4472,6 +4457,15 @@ void check_system_chunk(struct btrfs_trans_handle *trans, } } +/* + * If force is CHUNK_ALLOC_FORCE: + * - return 1 if it successfully allocates a chunk, + * - return errors including -ENOSPC otherwise. + * If force is NOT CHUNK_ALLOC_FORCE: + * - return 0 if it doesn't need to allocate a new chunk, + * - return 1 if it successfully allocates a chunk, + * - return errors including -ENOSPC otherwise. + */ static int do_chunk_alloc(struct btrfs_trans_handle *trans, struct btrfs_root *extent_root, u64 flags, int force) { @@ -4882,7 +4876,7 @@ static int flush_space(struct btrfs_root *root, btrfs_get_alloc_profile(root, 0), CHUNK_ALLOC_NO_FORCE); btrfs_end_transaction(trans, root); - if (ret == -ENOSPC) + if (ret > 0 || ret == -ENOSPC) ret = 0; break; case COMMIT_TRANS: @@ -6497,19 +6491,15 @@ void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg) } /** - * btrfs_update_reserved_bytes - update the block_group and space info counters + * btrfs_add_reserved_bytes - update the block_group and space info counters * @cache: The cache we are manipulating + * @ram_bytes: The number of bytes of file content, and will be same to + * @num_bytes except for the compress path. * @num_bytes: The number of bytes in question - * @reserve: One of the reservation enums * @delalloc: The blocks are allocated for the delalloc write * - * This is called by the allocator when it reserves space, or by somebody who is - * freeing space that was never actually used on disk. For example if you - * reserve some space for a new leaf in transaction A and before transaction A - * commits you free that leaf, you call this with reserve set to 0 in order to - * clear the reservation. - * - * Metadata reservations should be called with RESERVE_ALLOC so we do the proper + * This is called by the allocator when it reserves space. Metadata + * reservations should be called with RESERVE_ALLOC so we do the proper * ENOSPC accounting. For data we handle the reservation through clearing the * delalloc bits in the io_tree. We have to do this since we could end up * allocating less disk space for the amount of data we have reserved in the @@ -6519,44 +6509,63 @@ void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg) * make the reservation and return -EAGAIN, otherwise this function always * succeeds. */ -static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache, - u64 num_bytes, int reserve, int delalloc) +static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache, + u64 ram_bytes, u64 num_bytes, int delalloc) { struct btrfs_space_info *space_info = cache->space_info; int ret = 0; spin_lock(&space_info->lock); spin_lock(&cache->lock); - if (reserve != RESERVE_FREE) { - if (cache->ro) { - ret = -EAGAIN; - } else { - cache->reserved += num_bytes; - space_info->bytes_reserved += num_bytes; - if (reserve == RESERVE_ALLOC) { - trace_btrfs_space_reservation(cache->fs_info, - "space_info", space_info->flags, - num_bytes, 0); - space_info->bytes_may_use -= num_bytes; - } - - if (delalloc) - cache->delalloc_bytes += num_bytes; - } + if (cache->ro) { + ret = -EAGAIN; } else { - if (cache->ro) - space_info->bytes_readonly += num_bytes; - cache->reserved -= num_bytes; - space_info->bytes_reserved -= num_bytes; + cache->reserved += num_bytes; + space_info->bytes_reserved += num_bytes; + trace_btrfs_space_reservation(cache->fs_info, + "space_info", space_info->flags, + ram_bytes, 0); + space_info->bytes_may_use -= ram_bytes; if (delalloc) - cache->delalloc_bytes -= num_bytes; + cache->delalloc_bytes += num_bytes; } spin_unlock(&cache->lock); spin_unlock(&space_info->lock); return ret; } +/** + * btrfs_free_reserved_bytes - update the block_group and space info counters + * @cache: The cache we are manipulating + * @num_bytes: The number of bytes in question + * @delalloc: The blocks are allocated for the delalloc write + * + * This is called by somebody who is freeing space that was never actually used + * on disk. For example if you reserve some space for a new leaf in transaction + * A and before transaction A commits you free that leaf, you call this with + * reserve set to 0 in order to clear the reservation. + */ + +static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache, + u64 num_bytes, int delalloc) +{ + struct btrfs_space_info *space_info = cache->space_info; + int ret = 0; + + spin_lock(&space_info->lock); + spin_lock(&cache->lock); + if (cache->ro) + space_info->bytes_readonly += num_bytes; + cache->reserved -= num_bytes; + space_info->bytes_reserved -= num_bytes; + + if (delalloc) + cache->delalloc_bytes -= num_bytes; + spin_unlock(&cache->lock); + spin_unlock(&space_info->lock); + return ret; +} void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans, struct btrfs_root *root) { @@ -7191,7 +7200,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)); btrfs_add_free_space(cache, buf->start, buf->len); - btrfs_update_reserved_bytes(cache, buf->len, RESERVE_FREE, 0); + btrfs_free_reserved_bytes(cache, buf->len, 0); btrfs_put_block_group(cache); trace_btrfs_reserved_extent_free(root, buf->start, buf->len); pin = 0; @@ -7416,9 +7425,9 @@ btrfs_release_block_group(struct btrfs_block_group_cache *cache, * the free space extent currently. */ static noinline int find_free_extent(struct btrfs_root *orig_root, - u64 num_bytes, u64 empty_size, - u64 hint_byte, struct btrfs_key *ins, - u64 flags, int delalloc) + u64 ram_bytes, u64 num_bytes, u64 empty_size, + u64 hint_byte, struct btrfs_key *ins, + u64 flags, int delalloc) { int ret = 0; struct btrfs_root *root = orig_root->fs_info->extent_root; @@ -7430,8 +7439,6 @@ static noinline int find_free_extent(struct btrfs_root *orig_root, struct btrfs_space_info *space_info; int loop = 0; int index = __get_raid_index(flags); - int alloc_type = (flags & BTRFS_BLOCK_GROUP_DATA) ? - RESERVE_ALLOC_NO_ACCOUNT : RESERVE_ALLOC; bool failed_cluster_refill = false; bool failed_alloc = false; bool use_cluster = true; @@ -7763,8 +7770,8 @@ checks: search_start - offset); BUG_ON(offset > search_start); - ret = btrfs_update_reserved_bytes(block_group, num_bytes, - alloc_type, delalloc); + ret = btrfs_add_reserved_bytes(block_group, ram_bytes, + num_bytes, delalloc); if (ret == -EAGAIN) { btrfs_add_free_space(block_group, offset, num_bytes); goto loop; @@ -7936,7 +7943,7 @@ again: up_read(&info->groups_sem); } -int btrfs_reserve_extent(struct btrfs_root *root, +int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, u64 num_bytes, u64 min_alloc_size, u64 empty_size, u64 hint_byte, struct btrfs_key *ins, int is_data, int delalloc) @@ -7948,8 +7955,8 @@ int btrfs_reserve_extent(struct btrfs_root *root, flags = btrfs_get_alloc_profile(root, is_data); again: WARN_ON(num_bytes < root->sectorsize); - ret = find_free_extent(root, num_bytes, empty_size, hint_byte, ins, - flags, delalloc); + ret = find_free_extent(root, ram_bytes, num_bytes, empty_size, + hint_byte, ins, flags, delalloc); if (!ret && !is_data) { btrfs_dec_block_group_reservations(root->fs_info, ins->objectid); @@ -7958,6 +7965,7 @@ again: num_bytes = min(num_bytes >> 1, ins->offset); num_bytes = round_down(num_bytes, root->sectorsize); num_bytes = max(num_bytes, min_alloc_size); + ram_bytes = num_bytes; if (num_bytes == min_alloc_size) final_tried = true; goto again; @@ -7995,7 +8003,7 @@ static int __btrfs_free_reserved_extent(struct btrfs_root *root, if (btrfs_test_opt(root->fs_info, DISCARD)) ret = btrfs_discard_extent(root, start, len, NULL); btrfs_add_free_space(cache, start, len); - btrfs_update_reserved_bytes(cache, len, RESERVE_FREE, delalloc); + btrfs_free_reserved_bytes(cache, len, delalloc); trace_btrfs_reserved_extent_free(root, start, len); } @@ -8223,8 +8231,8 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, if (!block_group) return -EINVAL; - ret = btrfs_update_reserved_bytes(block_group, ins->offset, - RESERVE_ALLOC_NO_ACCOUNT, 0); + ret = btrfs_add_reserved_bytes(block_group, ins->offset, + ins->offset, 0); BUG_ON(ret); /* logic error */ ret = alloc_reserved_file_extent(trans, root, 0, root_objectid, 0, owner, offset, ins, 1); @@ -8368,7 +8376,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, if (IS_ERR(block_rsv)) return ERR_CAST(block_rsv); - ret = btrfs_reserve_extent(root, blocksize, blocksize, + ret = btrfs_reserve_extent(root, blocksize, blocksize, blocksize, empty_size, hint, &ins, 0, 0); if (ret) goto out_unuse; @@ -8521,35 +8529,6 @@ reada: wc->reada_slot = slot; } -/* - * These may not be seen by the usual inc/dec ref code so we have to - * add them here. - */ -static int record_one_subtree_extent(struct btrfs_trans_handle *trans, - struct btrfs_root *root, u64 bytenr, - u64 num_bytes) -{ - struct btrfs_qgroup_extent_record *qrecord; - struct btrfs_delayed_ref_root *delayed_refs; - - qrecord = kmalloc(sizeof(*qrecord), GFP_NOFS); - if (!qrecord) - return -ENOMEM; - - qrecord->bytenr = bytenr; - qrecord->num_bytes = num_bytes; - qrecord->old_roots = NULL; - - delayed_refs = &trans->transaction->delayed_refs; - spin_lock(&delayed_refs->lock); - if (btrfs_qgroup_insert_dirty_extent(trans->fs_info, - delayed_refs, qrecord)) - kfree(qrecord); - spin_unlock(&delayed_refs->lock); - - return 0; -} - static int account_leaf_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *eb) @@ -8583,7 +8562,8 @@ static int account_leaf_items(struct btrfs_trans_handle *trans, num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi); - ret = record_one_subtree_extent(trans, root, bytenr, num_bytes); + ret = btrfs_qgroup_insert_dirty_extent(trans, root->fs_info, + bytenr, num_bytes, GFP_NOFS); if (ret) return ret; } @@ -8732,8 +8712,9 @@ walk_down: btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); path->locks[level] = BTRFS_READ_LOCK_BLOCKING; - ret = record_one_subtree_extent(trans, root, child_bytenr, - root->nodesize); + ret = btrfs_qgroup_insert_dirty_extent(trans, + root->fs_info, child_bytenr, + root->nodesize, GFP_NOFS); if (ret) goto out; } @@ -9906,6 +9887,7 @@ static int find_first_block_group(struct btrfs_root *root, } else { ret = 0; } + free_extent_map(em); goto out; } path->slots[0]++; @@ -9942,6 +9924,7 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info) block_group->iref = 0; block_group->inode = NULL; spin_unlock(&block_group->lock); + ASSERT(block_group->io_ctl.inode == NULL); iput(inode); last = block_group->key.objectid + block_group->key.offset; btrfs_put_block_group(block_group); @@ -9999,6 +9982,10 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) free_excluded_extents(info->extent_root, block_group); btrfs_remove_free_space_cache(block_group); + ASSERT(list_empty(&block_group->dirty_list)); + ASSERT(list_empty(&block_group->io_list)); + ASSERT(list_empty(&block_group->bg_list)); + ASSERT(atomic_read(&block_group->count) == 1); btrfs_put_block_group(block_group); spin_lock(&info->block_group_cache_lock); diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index bc2729a..28cd88f 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -20,6 +20,7 @@ #define EXTENT_DAMAGED (1U << 14) #define EXTENT_NORESERVE (1U << 15) #define EXTENT_QGROUP_RESERVED (1U << 16) +#define EXTENT_CLEAR_DATA_RESV (1U << 17) #define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK) #define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 5842423..fea31a4 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2070,7 +2070,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) } trans->sync = true; - btrfs_init_log_ctx(&ctx); + btrfs_init_log_ctx(&ctx, inode); ret = btrfs_log_dentry_safe(trans, root, dentry, start, end, &ctx); if (ret < 0) { @@ -2675,6 +2675,7 @@ static long btrfs_fallocate(struct file *file, int mode, alloc_start = round_down(offset, blocksize); alloc_end = round_up(offset + len, blocksize); + cur_offset = alloc_start; /* Make sure we aren't being give some crap mode */ if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) @@ -2767,7 +2768,6 @@ static long btrfs_fallocate(struct file *file, int mode, /* First, check if we exceed the qgroup limit */ INIT_LIST_HEAD(&reserve_list); - cur_offset = alloc_start; while (1) { em = btrfs_get_extent(inode, NULL, 0, cur_offset, alloc_end - cur_offset, 0); @@ -2794,6 +2794,14 @@ static long btrfs_fallocate(struct file *file, int mode, last_byte - cur_offset); if (ret < 0) break; + } else { + /* + * Do not need to reserve unwritten extent for this + * range, free reserved data space first, otherwise + * it'll result in false ENOSPC error. + */ + btrfs_free_reserved_data_space(inode, cur_offset, + last_byte - cur_offset); } free_extent_map(em); cur_offset = last_byte; @@ -2811,6 +2819,9 @@ static long btrfs_fallocate(struct file *file, int mode, range->start, range->len, 1 << inode->i_blkbits, offset + len, &alloc_hint); + else + btrfs_free_reserved_data_space(inode, range->start, + range->len); list_del(&range->list); kfree(range); } @@ -2845,18 +2856,11 @@ out_unlock: unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end, &cached_state, GFP_KERNEL); out: - /* - * As we waited the extent range, the data_rsv_map must be empty - * in the range, as written data range will be released from it. - * And for prealloacted extent, it will also be released when - * its metadata is written. - * So this is completely used as cleanup. - */ - btrfs_qgroup_free_data(inode, alloc_start, alloc_end - alloc_start); inode_unlock(inode); /* Let go of our reservation. */ - btrfs_free_reserved_data_space(inode, alloc_start, - alloc_end - alloc_start); + if (ret != 0) + btrfs_free_reserved_data_space(inode, alloc_start, + alloc_end - cur_offset); return ret; } diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index aa6faba..359ee86 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -495,10 +495,9 @@ again: ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc, prealloc, prealloc, &alloc_hint); if (ret) { - btrfs_delalloc_release_space(inode, 0, prealloc); + btrfs_delalloc_release_metadata(inode, prealloc); goto out_put; } - btrfs_free_reserved_data_space(inode, 0, prealloc); ret = btrfs_write_out_ino_cache(root, trans, path, inode); out_put: diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 08dfc57..e6811c42 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -566,6 +566,8 @@ cont: PAGE_SET_WRITEBACK | page_error_op | PAGE_END_WRITEBACK); + btrfs_free_reserved_data_space_noquota(inode, start, + end - start + 1); goto free_pages_out; } } @@ -742,7 +744,7 @@ retry: lock_extent(io_tree, async_extent->start, async_extent->start + async_extent->ram_size - 1); - ret = btrfs_reserve_extent(root, + ret = btrfs_reserve_extent(root, async_extent->ram_size, async_extent->compressed_size, async_extent->compressed_size, 0, alloc_hint, &ins, 1, 1); @@ -969,7 +971,8 @@ static noinline int cow_file_range(struct inode *inode, EXTENT_DEFRAG, PAGE_UNLOCK | PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK); - + btrfs_free_reserved_data_space_noquota(inode, start, + end - start + 1); *nr_written = *nr_written + (end - start + PAGE_SIZE) / PAGE_SIZE; *page_started = 1; @@ -989,7 +992,7 @@ static noinline int cow_file_range(struct inode *inode, unsigned long op; cur_alloc_size = disk_num_bytes; - ret = btrfs_reserve_extent(root, cur_alloc_size, + ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size, root->sectorsize, 0, alloc_hint, &ins, 1, 1); if (ret < 0) @@ -1489,8 +1492,10 @@ out_check: extent_clear_unlock_delalloc(inode, cur_offset, cur_offset + num_bytes - 1, locked_page, EXTENT_LOCKED | - EXTENT_DELALLOC, PAGE_UNLOCK | - PAGE_SET_PRIVATE2); + EXTENT_DELALLOC | + EXTENT_CLEAR_DATA_RESV, + PAGE_UNLOCK | PAGE_SET_PRIVATE2); + if (!nolock && nocow) btrfs_end_write_no_snapshoting(root); cur_offset = extent_end; @@ -1807,7 +1812,9 @@ static void btrfs_clear_bit_hook(struct inode *inode, return; if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID - && do_list && !(state->state & EXTENT_NORESERVE)) + && do_list && !(state->state & EXTENT_NORESERVE) + && (*bits & (EXTENT_DO_ACCOUNTING | + EXTENT_CLEAR_DATA_RESV))) btrfs_free_reserved_data_space_noquota(inode, state->start, len); @@ -7251,7 +7258,7 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode, int ret; alloc_hint = get_extent_allocation_hint(inode, start, len); - ret = btrfs_reserve_extent(root, len, root->sectorsize, 0, + ret = btrfs_reserve_extent(root, len, len, root->sectorsize, 0, alloc_hint, &ins, 1, 1); if (ret) return ERR_PTR(ret); @@ -7751,6 +7758,13 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, ret = PTR_ERR(em2); goto unlock_err; } + /* + * For inode marked NODATACOW or extent marked PREALLOC, + * use the existing or preallocated extent, so does not + * need to adjust btrfs_space_info's bytes_may_use. + */ + btrfs_free_reserved_data_space_noquota(inode, + start, len); goto unlock; } } @@ -7785,7 +7799,6 @@ unlock: i_size_write(inode, start + len); adjust_dio_outstanding_extents(inode, dio_data, len); - btrfs_free_reserved_data_space(inode, start, len); WARN_ON(dio_data->reserve < len); dio_data->reserve -= len; dio_data->unsubmitted_oe_range_end = start + len; @@ -10306,6 +10319,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, u64 last_alloc = (u64)-1; int ret = 0; bool own_trans = true; + u64 end = start + num_bytes - 1; if (trans) own_trans = false; @@ -10327,8 +10341,8 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, * sized chunks. */ cur_bytes = min(cur_bytes, last_alloc); - ret = btrfs_reserve_extent(root, cur_bytes, min_size, 0, - *alloc_hint, &ins, 1, 0); + ret = btrfs_reserve_extent(root, cur_bytes, cur_bytes, + min_size, 0, *alloc_hint, &ins, 1, 0); if (ret) { if (own_trans) btrfs_end_transaction(trans, root); @@ -10414,6 +10428,9 @@ next: if (own_trans) btrfs_end_transaction(trans, root); } + if (cur_offset < end) + btrfs_free_reserved_data_space(inode, cur_offset, + end - cur_offset + 1); return ret; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 14ed1e9..b2a2da5 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -5084,7 +5084,7 @@ static long btrfs_ioctl_quota_rescan_wait(struct file *file, void __user *arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - return btrfs_qgroup_wait_for_completion(root->fs_info); + return btrfs_qgroup_wait_for_completion(root->fs_info, true); } static long _btrfs_ioctl_set_received_subvol(struct file *file, diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 93ee1c1..8db2e29 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -995,7 +995,7 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, goto out; fs_info->quota_enabled = 0; fs_info->pending_quota_state = 0; - btrfs_qgroup_wait_for_completion(fs_info); + 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; @@ -1453,10 +1453,9 @@ int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans, return ret; } -struct btrfs_qgroup_extent_record * -btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info, - struct btrfs_delayed_ref_root *delayed_refs, - struct btrfs_qgroup_extent_record *record) +int btrfs_qgroup_insert_dirty_extent_nolock(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_qgroup_extent_record *record) { struct rb_node **p = &delayed_refs->dirty_extent_root.rb_node; struct rb_node *parent_node = NULL; @@ -1475,12 +1474,42 @@ btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info, else if (bytenr > entry->bytenr) p = &(*p)->rb_right; else - return entry; + return 1; } rb_link_node(&record->node, parent_node, p); rb_insert_color(&record->node, &delayed_refs->dirty_extent_root); - return NULL; + return 0; +} + +int btrfs_qgroup_insert_dirty_extent(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes, + gfp_t gfp_flag) +{ + struct btrfs_qgroup_extent_record *record; + struct btrfs_delayed_ref_root *delayed_refs; + int ret; + + if (!fs_info->quota_enabled || bytenr == 0 || num_bytes == 0) + return 0; + if (WARN_ON(trans == NULL)) + return -EINVAL; + record = kmalloc(sizeof(*record), gfp_flag); + if (!record) + return -ENOMEM; + + delayed_refs = &trans->transaction->delayed_refs; + record->bytenr = bytenr; + record->num_bytes = num_bytes; + record->old_roots = NULL; + + spin_lock(&delayed_refs->lock); + ret = btrfs_qgroup_insert_dirty_extent_nolock(fs_info, delayed_refs, + record); + spin_unlock(&delayed_refs->lock); + if (ret > 0) + kfree(record); + return 0; } #define UPDATE_NEW 0 @@ -2303,6 +2332,10 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) int err = -ENOMEM; int ret = 0; + mutex_lock(&fs_info->qgroup_rescan_lock); + fs_info->qgroup_rescan_running = true; + mutex_unlock(&fs_info->qgroup_rescan_lock); + path = btrfs_alloc_path(); if (!path) goto out; @@ -2369,6 +2402,9 @@ out: } done: + mutex_lock(&fs_info->qgroup_rescan_lock); + fs_info->qgroup_rescan_running = false; + mutex_unlock(&fs_info->qgroup_rescan_lock); complete_all(&fs_info->qgroup_rescan_completion); } @@ -2487,20 +2523,26 @@ btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info) return 0; } -int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info) +int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info, + bool interruptible) { int running; int ret = 0; mutex_lock(&fs_info->qgroup_rescan_lock); spin_lock(&fs_info->qgroup_lock); - running = fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN; + running = fs_info->qgroup_rescan_running; spin_unlock(&fs_info->qgroup_lock); mutex_unlock(&fs_info->qgroup_rescan_lock); - if (running) + if (!running) + return 0; + + if (interruptible) ret = wait_for_completion_interruptible( &fs_info->qgroup_rescan_completion); + else + wait_for_completion(&fs_info->qgroup_rescan_completion); return ret; } diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 710887c..1bc64c8 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -46,7 +46,8 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info); void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info); -int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info); +int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info, + bool interruptible); int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 src, u64 dst); int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, @@ -63,10 +64,35 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info); struct btrfs_delayed_extent_op; int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); -struct btrfs_qgroup_extent_record * -btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info, - struct btrfs_delayed_ref_root *delayed_refs, - struct btrfs_qgroup_extent_record *record); +/* + * Insert one dirty extent record into @delayed_refs, informing qgroup to + * account that extent at commit trans time. + * + * No lock version, caller must acquire delayed ref lock and allocate memory. + * + * Return 0 for success insert + * Return >0 for existing record, caller can free @record safely. + * Error is not possible + */ +int btrfs_qgroup_insert_dirty_extent_nolock( + struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_qgroup_extent_record *record); + +/* + * Insert one dirty extent record into @delayed_refs, informing qgroup to + * account that extent at commit trans time. + * + * Better encapsulated version. + * + * Return 0 if the operation is done. + * Return <0 for error, like memory allocation failure or invalid parameter + * (NULL trans) + */ +int btrfs_qgroup_insert_dirty_extent(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes, + gfp_t gfp_flag); + int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index b26a5ae..8a2c2a0 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -31,6 +31,7 @@ #include "async-thread.h" #include "free-space-cache.h" #include "inode-map.h" +#include "qgroup.h" /* * backref_node, mapping_node and tree_block start with this @@ -3037,15 +3038,19 @@ int prealloc_file_extent_cluster(struct inode *inode, u64 num_bytes; int nr = 0; int ret = 0; + u64 prealloc_start = cluster->start - offset; + u64 prealloc_end = cluster->end - offset; + u64 cur_offset; BUG_ON(cluster->start != cluster->boundary[0]); inode_lock(inode); - ret = btrfs_check_data_free_space(inode, cluster->start, - cluster->end + 1 - cluster->start); + ret = btrfs_check_data_free_space(inode, prealloc_start, + prealloc_end + 1 - prealloc_start); if (ret) goto out; + cur_offset = prealloc_start; while (nr < cluster->nr) { start = cluster->boundary[nr] - offset; if (nr + 1 < cluster->nr) @@ -3055,16 +3060,21 @@ int prealloc_file_extent_cluster(struct inode *inode, lock_extent(&BTRFS_I(inode)->io_tree, start, end); num_bytes = end + 1 - start; + if (cur_offset < start) + btrfs_free_reserved_data_space(inode, cur_offset, + start - cur_offset); ret = btrfs_prealloc_file_range(inode, 0, start, num_bytes, num_bytes, end + 1, &alloc_hint); + cur_offset = end + 1; unlock_extent(&BTRFS_I(inode)->io_tree, start, end); if (ret) break; nr++; } - btrfs_free_reserved_data_space(inode, cluster->start, - cluster->end + 1 - cluster->start); + if (cur_offset < prealloc_end) + btrfs_free_reserved_data_space(inode, cur_offset, + prealloc_end + 1 - cur_offset); out: inode_unlock(inode); return ret; @@ -3916,6 +3926,90 @@ int prepare_to_relocate(struct reloc_control *rc) return 0; } +/* + * Qgroup fixer for data chunk relocation. + * The data relocation is done in the following steps + * 1) Copy data extents into data reloc tree + * 2) Create tree reloc tree(special snapshot) for related subvolumes + * 3) Modify file extents in tree reloc tree + * 4) Merge tree reloc tree with original fs tree, by swapping tree blocks + * + * The problem is, data and tree reloc tree are not accounted to qgroup, + * and 4) will only info qgroup to track tree blocks change, not file extents + * in the tree blocks. + * + * The good news is, related data extents are all in data reloc tree, so we + * only need to info qgroup to track all file extents in data reloc tree + * before commit trans. + */ +static int qgroup_fix_relocated_data_extents(struct btrfs_trans_handle *trans, + struct reloc_control *rc) +{ + struct btrfs_fs_info *fs_info = rc->extent_root->fs_info; + struct inode *inode = rc->data_inode; + struct btrfs_root *data_reloc_root = BTRFS_I(inode)->root; + struct btrfs_path *path; + struct btrfs_key key; + int ret = 0; + + if (!fs_info->quota_enabled) + return 0; + + /* + * Only for stage where we update data pointers the qgroup fix is + * valid. + * For MOVING_DATA stage, we will miss the timing of swapping tree + * blocks, and won't fix it. + */ + if (!(rc->stage == UPDATE_DATA_PTRS && rc->extents_found)) + return 0; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + key.objectid = btrfs_ino(inode); + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = 0; + + ret = btrfs_search_slot(NULL, data_reloc_root, &key, path, 0, 0); + if (ret < 0) + goto out; + + lock_extent(&BTRFS_I(inode)->io_tree, 0, (u64)-1); + while (1) { + struct btrfs_file_extent_item *fi; + + btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); + if (key.objectid > btrfs_ino(inode)) + break; + if (key.type != BTRFS_EXTENT_DATA_KEY) + goto next; + fi = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_file_extent_item); + if (btrfs_file_extent_type(path->nodes[0], fi) != + BTRFS_FILE_EXTENT_REG) + goto next; + ret = btrfs_qgroup_insert_dirty_extent(trans, fs_info, + btrfs_file_extent_disk_bytenr(path->nodes[0], fi), + btrfs_file_extent_disk_num_bytes(path->nodes[0], fi), + GFP_NOFS); + if (ret < 0) + break; +next: + ret = btrfs_next_item(data_reloc_root, path); + if (ret < 0) + break; + if (ret > 0) { + ret = 0; + break; + } + } + unlock_extent(&BTRFS_I(inode)->io_tree, 0 , (u64)-1); +out: + btrfs_free_path(path); + return ret; +} + static noinline_for_stack int relocate_block_group(struct reloc_control *rc) { struct rb_root blocks = RB_ROOT; @@ -4102,10 +4196,16 @@ restart: /* get rid of pinned extents */ trans = btrfs_join_transaction(rc->extent_root); - if (IS_ERR(trans)) + if (IS_ERR(trans)) { err = PTR_ERR(trans); - else - btrfs_commit_transaction(trans, rc->extent_root); + goto out_free; + } + err = qgroup_fix_relocated_data_extents(trans, rc); + if (err < 0) { + btrfs_abort_transaction(trans, err); + goto out_free; + } + btrfs_commit_transaction(trans, rc->extent_root); out_free: btrfs_free_block_rsv(rc->extent_root, rc->block_rsv); btrfs_free_path(path); @@ -4468,10 +4568,16 @@ int btrfs_recover_relocation(struct btrfs_root *root) unset_reloc_control(rc); trans = btrfs_join_transaction(rc->extent_root); - if (IS_ERR(trans)) + if (IS_ERR(trans)) { err = PTR_ERR(trans); - else - err = btrfs_commit_transaction(trans, rc->extent_root); + goto out_free; + } + err = qgroup_fix_relocated_data_extents(trans, rc); + if (err < 0) { + btrfs_abort_transaction(trans, err); + goto out_free; + } + err = btrfs_commit_transaction(trans, rc->extent_root); out_free: kfree(rc); out: diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 7fd7e18..0912960 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -272,6 +272,23 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) root_key.objectid = key.offset; key.offset++; + /* + * The root might have been inserted already, as before we look + * for orphan roots, log replay might have happened, which + * triggers a transaction commit and qgroup accounting, which + * in turn reads and inserts fs roots while doing backref + * walking. + */ + root = btrfs_lookup_fs_root(tree_root->fs_info, + root_key.objectid); + if (root) { + WARN_ON(!test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, + &root->state)); + if (btrfs_root_refs(&root->root_item) == 0) + btrfs_add_dead_root(root); + continue; + } + root = btrfs_read_fs_root(tree_root, &root_key); err = PTR_ERR_OR_ZERO(root); if (err && err != -ENOENT) { @@ -310,16 +327,8 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state); err = btrfs_insert_fs_root(root->fs_info, root); - /* - * The root might have been inserted already, as before we look - * for orphan roots, log replay might have happened, which - * triggers a transaction commit and qgroup accounting, which - * in turn reads and inserts fs roots while doing backref - * walking. - */ - if (err == -EEXIST) - err = 0; if (err) { + BUG_ON(err == -EEXIST); btrfs_free_fs_root(root); break; } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 864ce33..4071fe2 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2241,6 +2241,13 @@ static int btrfs_freeze(struct super_block *sb) struct btrfs_trans_handle *trans; struct btrfs_root *root = btrfs_sb(sb)->tree_root; + root->fs_info->fs_frozen = 1; + /* + * We don't need a barrier here, we'll wait for any transaction that + * could be in progress on other threads (and do delayed iputs that + * we want to avoid on a frozen filesystem), or do the commit + * ourselves. + */ trans = btrfs_attach_transaction_barrier(root); if (IS_ERR(trans)) { /* no transaction, don't bother */ @@ -2251,6 +2258,14 @@ static int btrfs_freeze(struct super_block *sb) return btrfs_commit_transaction(trans, root); } +static int btrfs_unfreeze(struct super_block *sb) +{ + struct btrfs_root *root = btrfs_sb(sb)->tree_root; + + root->fs_info->fs_frozen = 0; + return 0; +} + static int btrfs_show_devname(struct seq_file *m, struct dentry *root) { struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb); @@ -2299,6 +2314,7 @@ static const struct super_operations btrfs_super_ops = { .statfs = btrfs_statfs, .remount_fs = btrfs_remount, .freeze_fs = btrfs_freeze, + .unfreeze_fs = btrfs_unfreeze, }; static const struct file_operations btrfs_ctl_fops = { diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 9cca0a7..95d4191 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -2278,8 +2278,13 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, kmem_cache_free(btrfs_trans_handle_cachep, trans); + /* + * If fs has been frozen, we can not handle delayed iputs, otherwise + * it'll result in deadlock about SB_FREEZE_FS. + */ if (current != root->fs_info->transaction_kthread && - current != root->fs_info->cleaner_kthread) + current != root->fs_info->cleaner_kthread && + !root->fs_info->fs_frozen) btrfs_run_delayed_iputs(root); return ret; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index fff3f3e..e935035 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -27,6 +27,7 @@ #include "backref.h" #include "hash.h" #include "compression.h" +#include "qgroup.h" /* magic values for the inode_only field in btrfs_log_inode: * @@ -680,6 +681,21 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, ins.type = BTRFS_EXTENT_ITEM_KEY; offset = key->offset - btrfs_file_extent_offset(eb, item); + /* + * Manually record dirty extent, as here we did a shallow + * file extent item copy and skip normal backref update, + * but modifying extent tree all by ourselves. + * So need to manually record dirty extent for qgroup, + * as the owner of the file extent changed from log tree + * (doesn't affect qgroup) to fs/file tree(affects qgroup) + */ + ret = btrfs_qgroup_insert_dirty_extent(trans, root->fs_info, + btrfs_file_extent_disk_bytenr(eb, item), + btrfs_file_extent_disk_num_bytes(eb, item), + GFP_NOFS); + if (ret < 0) + goto out; + if (ins.objectid > 0) { u64 csum_start; u64 csum_end; @@ -2807,7 +2823,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, */ mutex_unlock(&root->log_mutex); - btrfs_init_log_ctx(&root_log_ctx); + btrfs_init_log_ctx(&root_log_ctx, NULL); mutex_lock(&log_root_tree->log_mutex); atomic_inc(&log_root_tree->log_batch); @@ -4741,7 +4757,8 @@ again: if (ret < 0) { err = ret; goto out_unlock; - } else if (ret > 0) { + } else if (ret > 0 && ctx && + other_ino != btrfs_ino(ctx->inode)) { struct btrfs_key inode_key; struct inode *other_inode; diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h index a9f1b75..ab858e3 100644 --- a/fs/btrfs/tree-log.h +++ b/fs/btrfs/tree-log.h @@ -30,15 +30,18 @@ struct btrfs_log_ctx { int log_transid; int io_err; bool log_new_dentries; + struct inode *inode; struct list_head list; }; -static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx) +static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx, + struct inode *inode) { ctx->log_ret = 0; ctx->log_transid = 0; ctx->io_err = 0; ctx->log_new_dentries = false; + ctx->inode = inode; INIT_LIST_HEAD(&ctx->list); } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 51f1255..035efce 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -834,10 +834,6 @@ static void __free_device(struct work_struct *work) struct btrfs_device *device; device = container_of(work, struct btrfs_device, rcu_work); - - if (device->bdev) - blkdev_put(device->bdev, device->mode); - rcu_string_free(device->name); kfree(device); } @@ -852,6 +848,17 @@ static void free_device(struct rcu_head *head) schedule_work(&device->rcu_work); } +static void btrfs_close_bdev(struct btrfs_device *device) +{ + if (device->bdev && device->writeable) { + sync_blockdev(device->bdev); + invalidate_bdev(device->bdev); + } + + if (device->bdev) + blkdev_put(device->bdev, device->mode); +} + static void btrfs_close_one_device(struct btrfs_device *device) { struct btrfs_fs_devices *fs_devices = device->fs_devices; @@ -870,10 +877,7 @@ static void btrfs_close_one_device(struct btrfs_device *device) if (device->missing) fs_devices->missing_devices--; - if (device->bdev && device->writeable) { - sync_blockdev(device->bdev); - invalidate_bdev(device->bdev); - } + btrfs_close_bdev(device); new_device = btrfs_alloc_device(NULL, &device->devid, device->uuid); @@ -1932,6 +1936,8 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path, u64 devid) btrfs_sysfs_rm_device_link(root->fs_info->fs_devices, device); } + btrfs_close_bdev(device); + call_rcu(&device->rcu, free_device); num_devices = btrfs_super_num_devices(root->fs_info->super_copy) - 1; @@ -2025,6 +2031,9 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info, /* zero out the old super if it is writable */ btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str); } + + btrfs_close_bdev(srcdev); + call_rcu(&srcdev->rcu, free_device); /* @@ -2080,6 +2089,8 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, * the device_list_mutex lock. */ btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str); + + btrfs_close_bdev(tgtdev); call_rcu(&tgtdev->rcu, free_device); } diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c index eea6491..466f7d6 100644 --- a/fs/dlm/debug_fs.c +++ b/fs/dlm/debug_fs.c @@ -607,20 +607,54 @@ static const struct file_operations format2_fops; static const struct file_operations format3_fops; static const struct file_operations format4_fops; -static int table_open(struct inode *inode, struct file *file) +static int table_open1(struct inode *inode, struct file *file) { struct seq_file *seq; - int ret = -1; + int ret; - if (file->f_op == &format1_fops) - ret = seq_open(file, &format1_seq_ops); - else if (file->f_op == &format2_fops) - ret = seq_open(file, &format2_seq_ops); - else if (file->f_op == &format3_fops) - ret = seq_open(file, &format3_seq_ops); - else if (file->f_op == &format4_fops) - ret = seq_open(file, &format4_seq_ops); + ret = seq_open(file, &format1_seq_ops); + if (ret) + return ret; + + seq = file->private_data; + seq->private = inode->i_private; /* the dlm_ls */ + return 0; +} + +static int table_open2(struct inode *inode, struct file *file) +{ + struct seq_file *seq; + int ret; + + ret = seq_open(file, &format2_seq_ops); + if (ret) + return ret; + + seq = file->private_data; + seq->private = inode->i_private; /* the dlm_ls */ + return 0; +} + +static int table_open3(struct inode *inode, struct file *file) +{ + struct seq_file *seq; + int ret; + + ret = seq_open(file, &format3_seq_ops); + if (ret) + return ret; + + seq = file->private_data; + seq->private = inode->i_private; /* the dlm_ls */ + return 0; +} + +static int table_open4(struct inode *inode, struct file *file) +{ + struct seq_file *seq; + int ret; + ret = seq_open(file, &format4_seq_ops); if (ret) return ret; @@ -631,7 +665,7 @@ static int table_open(struct inode *inode, struct file *file) static const struct file_operations format1_fops = { .owner = THIS_MODULE, - .open = table_open, + .open = table_open1, .read = seq_read, .llseek = seq_lseek, .release = seq_release @@ -639,7 +673,7 @@ static const struct file_operations format1_fops = { static const struct file_operations format2_fops = { .owner = THIS_MODULE, - .open = table_open, + .open = table_open2, .read = seq_read, .llseek = seq_lseek, .release = seq_release @@ -647,7 +681,7 @@ static const struct file_operations format2_fops = { static const struct file_operations format3_fops = { .owner = THIS_MODULE, - .open = table_open, + .open = table_open3, .read = seq_read, .llseek = seq_lseek, .release = seq_release @@ -655,7 +689,7 @@ static const struct file_operations format3_fops = { static const struct file_operations format4_fops = { .owner = THIS_MODULE, - .open = table_open, + .open = table_open4, .read = seq_read, .llseek = seq_lseek, .release = seq_release diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index d64d2a5..ccb401e 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1699,11 +1699,11 @@ static int f2fs_write_end(struct file *file, trace_f2fs_write_end(inode, pos, len, copied); set_page_dirty(page); - f2fs_put_page(page, 1); if (pos + copied > i_size_read(inode)) f2fs_i_size_write(inode, pos + copied); + f2fs_put_page(page, 1); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return copied; } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 675fa79..14f5fe2 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -538,7 +538,7 @@ struct f2fs_nm_info { /* NAT cache management */ struct radix_tree_root nat_root;/* root of the nat entry cache */ struct radix_tree_root nat_set_root;/* root of the nat set cache */ - struct percpu_rw_semaphore nat_tree_lock; /* protect nat_tree_lock */ + struct rw_semaphore nat_tree_lock; /* protect nat_tree_lock */ struct list_head nat_entries; /* cached nat entry list (clean) */ unsigned int nat_cnt; /* the # of cached nat entries */ unsigned int dirty_nat_cnt; /* total num of nat entries in set */ @@ -787,7 +787,7 @@ struct f2fs_sb_info { struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */ struct inode *meta_inode; /* cache meta blocks */ struct mutex cp_mutex; /* checkpoint procedure lock */ - struct percpu_rw_semaphore cp_rwsem; /* blocking FS operations */ + struct rw_semaphore cp_rwsem; /* blocking FS operations */ struct rw_semaphore node_write; /* locking node writes */ wait_queue_head_t cp_wait; unsigned long last_time[MAX_TIME]; /* to store time in jiffies */ @@ -1074,22 +1074,22 @@ static inline void clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) static inline void f2fs_lock_op(struct f2fs_sb_info *sbi) { - percpu_down_read(&sbi->cp_rwsem); + down_read(&sbi->cp_rwsem); } static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi) { - percpu_up_read(&sbi->cp_rwsem); + up_read(&sbi->cp_rwsem); } static inline void f2fs_lock_all(struct f2fs_sb_info *sbi) { - percpu_down_write(&sbi->cp_rwsem); + down_write(&sbi->cp_rwsem); } static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi) { - percpu_up_write(&sbi->cp_rwsem); + up_write(&sbi->cp_rwsem); } static inline int __get_cp_reason(struct f2fs_sb_info *sbi) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 0e493f6..47abb96 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2086,15 +2086,19 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, if (unlikely(f2fs_readonly(src->i_sb))) return -EROFS; - if (S_ISDIR(src->i_mode) || S_ISDIR(dst->i_mode)) - return -EISDIR; + if (!S_ISREG(src->i_mode) || !S_ISREG(dst->i_mode)) + return -EINVAL; if (f2fs_encrypted_inode(src) || f2fs_encrypted_inode(dst)) return -EOPNOTSUPP; inode_lock(src); - if (src != dst) - inode_lock(dst); + if (src != dst) { + if (!inode_trylock(dst)) { + ret = -EBUSY; + goto out; + } + } ret = -EINVAL; if (pos_in + len > src->i_size || pos_in + len < pos_in) @@ -2152,6 +2156,7 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, out_unlock: if (src != dst) inode_unlock(dst); +out: inode_unlock(src); return ret; } diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index b2fa4b6..f75d197 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -206,14 +206,14 @@ int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid) struct nat_entry *e; bool need = false; - percpu_down_read(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (e) { if (!get_nat_flag(e, IS_CHECKPOINTED) && !get_nat_flag(e, HAS_FSYNCED_INODE)) need = true; } - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); return need; } @@ -223,11 +223,11 @@ bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) struct nat_entry *e; bool is_cp = true; - percpu_down_read(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (e && !get_nat_flag(e, IS_CHECKPOINTED)) is_cp = false; - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); return is_cp; } @@ -237,13 +237,13 @@ bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino) struct nat_entry *e; bool need_update = true; - percpu_down_read(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, ino); if (e && get_nat_flag(e, HAS_LAST_FSYNC) && (get_nat_flag(e, IS_CHECKPOINTED) || get_nat_flag(e, HAS_FSYNCED_INODE))) need_update = false; - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); return need_update; } @@ -284,7 +284,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; - percpu_down_write(&nm_i->nat_tree_lock); + down_write(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, ni->nid); if (!e) { e = grab_nat_entry(nm_i, ni->nid); @@ -334,7 +334,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, set_nat_flag(e, HAS_FSYNCED_INODE, true); set_nat_flag(e, HAS_LAST_FSYNC, fsync_done); } - percpu_up_write(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); } int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) @@ -342,7 +342,8 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) struct f2fs_nm_info *nm_i = NM_I(sbi); int nr = nr_shrink; - percpu_down_write(&nm_i->nat_tree_lock); + if (!down_write_trylock(&nm_i->nat_tree_lock)) + return 0; while (nr_shrink && !list_empty(&nm_i->nat_entries)) { struct nat_entry *ne; @@ -351,7 +352,7 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) __del_from_nat_cache(nm_i, ne); nr_shrink--; } - percpu_up_write(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); return nr - nr_shrink; } @@ -373,13 +374,13 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) ni->nid = nid; /* Check nat cache */ - percpu_down_read(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (e) { ni->ino = nat_get_ino(e); ni->blk_addr = nat_get_blkaddr(e); ni->version = nat_get_version(e); - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); return; } @@ -403,11 +404,11 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) node_info_from_raw_nat(ni, &ne); f2fs_put_page(page, 1); cache: - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); /* cache nat entry */ - percpu_down_write(&nm_i->nat_tree_lock); + down_write(&nm_i->nat_tree_lock); cache_nat_entry(sbi, nid, &ne); - percpu_up_write(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); } /* @@ -1788,7 +1789,7 @@ void build_free_nids(struct f2fs_sb_info *sbi) ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, META_NAT, true); - percpu_down_read(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); while (1) { struct page *page = get_current_nat_page(sbi, nid); @@ -1820,7 +1821,7 @@ void build_free_nids(struct f2fs_sb_info *sbi) remove_free_nid(nm_i, nid); } up_read(&curseg->journal_rwsem); - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid), nm_i->ra_nid_pages, META_NAT, false); @@ -2209,7 +2210,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi) if (!nm_i->dirty_nat_cnt) return; - percpu_down_write(&nm_i->nat_tree_lock); + down_write(&nm_i->nat_tree_lock); /* * if there are no enough space in journal to store dirty nat @@ -2232,7 +2233,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi) list_for_each_entry_safe(set, tmp, &sets, set_list) __flush_nat_entry_set(sbi, set); - percpu_up_write(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); f2fs_bug_on(sbi, nm_i->dirty_nat_cnt); } @@ -2268,8 +2269,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi) mutex_init(&nm_i->build_lock); spin_lock_init(&nm_i->free_nid_list_lock); - if (percpu_init_rwsem(&nm_i->nat_tree_lock)) - return -ENOMEM; + init_rwsem(&nm_i->nat_tree_lock); nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid); nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP); @@ -2326,7 +2326,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) spin_unlock(&nm_i->free_nid_list_lock); /* destroy nat cache */ - percpu_down_write(&nm_i->nat_tree_lock); + down_write(&nm_i->nat_tree_lock); while ((found = __gang_lookup_nat_cache(nm_i, nid, NATVEC_SIZE, natvec))) { unsigned idx; @@ -2351,9 +2351,8 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) kmem_cache_free(nat_entry_set_slab, setvec[idx]); } } - percpu_up_write(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); - percpu_free_rwsem(&nm_i->nat_tree_lock); kfree(nm_i->nat_bitmap); sbi->nm_info = NULL; kfree(nm_i); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 1b86d3f..7f863a6 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -706,8 +706,6 @@ static void destroy_percpu_info(struct f2fs_sb_info *sbi) percpu_counter_destroy(&sbi->nr_pages[i]); percpu_counter_destroy(&sbi->alloc_valid_block_count); percpu_counter_destroy(&sbi->total_valid_inode_count); - - percpu_free_rwsem(&sbi->cp_rwsem); } static void f2fs_put_super(struct super_block *sb) @@ -1483,9 +1481,6 @@ static int init_percpu_info(struct f2fs_sb_info *sbi) { int i, err; - if (percpu_init_rwsem(&sbi->cp_rwsem)) - return -ENOMEM; - for (i = 0; i < NR_COUNT_TYPE; i++) { err = percpu_counter_init(&sbi->nr_pages[i], 0, GFP_KERNEL); if (err) @@ -1686,6 +1681,7 @@ try_onemore: sbi->write_io[i].bio = NULL; } + init_rwsem(&sbi->cp_rwsem); init_waitqueue_head(&sbi->cp_wait); init_sb_info(sbi); diff --git a/fs/seq_file.c b/fs/seq_file.c index 19f532e..6dc4296 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -223,8 +223,10 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos) size -= n; buf += n; copied += n; - if (!m->count) + if (!m->count) { + m->from = 0; m->index++; + } if (!size) goto Done; } diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c index b45345d..51157da 100644 --- a/fs/ubifs/tnc_commit.c +++ b/fs/ubifs/tnc_commit.c @@ -370,7 +370,7 @@ static int layout_in_gaps(struct ubifs_info *c, int cnt) p = c->gap_lebs; do { - ubifs_assert(p < c->gap_lebs + sizeof(int) * c->lst.idx_lebs); + ubifs_assert(p < c->gap_lebs + c->lst.idx_lebs); written = layout_leb_in_gaps(c, p); if (written < 0) { err = written; diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index e237811..11a0041 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -575,7 +575,8 @@ static int ubifs_xattr_get(const struct xattr_handler *handler, dbg_gen("xattr '%s', ino %lu ('%pd'), buf size %zd", name, inode->i_ino, dentry, size); - return __ubifs_getxattr(inode, name, buffer, size); + name = xattr_full_name(handler, name); + return __ubifs_getxattr(inode, name, buffer, size); } static int ubifs_xattr_set(const struct xattr_handler *handler, @@ -586,6 +587,8 @@ static int ubifs_xattr_set(const struct xattr_handler *handler, dbg_gen("xattr '%s', host ino %lu ('%pd'), size %zd", name, inode->i_ino, dentry, size); + name = xattr_full_name(handler, name); + if (value) return __ubifs_setxattr(inode, name, value, size, flags); else diff --git a/include/linux/bio.h b/include/linux/bio.h index 59ffaa6..23ddf4b 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -71,7 +71,8 @@ static inline bool bio_has_data(struct bio *bio) { if (bio && bio->bi_iter.bi_size && - bio_op(bio) != REQ_OP_DISCARD) + bio_op(bio) != REQ_OP_DISCARD && + bio_op(bio) != REQ_OP_SECURE_ERASE) return true; return false; @@ -79,7 +80,9 @@ static inline bool bio_has_data(struct bio *bio) static inline bool bio_no_advance_iter(struct bio *bio) { - return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_WRITE_SAME; + return bio_op(bio) == REQ_OP_DISCARD || + bio_op(bio) == REQ_OP_SECURE_ERASE || + bio_op(bio) == REQ_OP_WRITE_SAME; } static inline bool bio_is_rw(struct bio *bio) @@ -199,6 +202,9 @@ static inline unsigned bio_segments(struct bio *bio) if (bio_op(bio) == REQ_OP_DISCARD) return 1; + if (bio_op(bio) == REQ_OP_SECURE_ERASE) + return 1; + if (bio_op(bio) == REQ_OP_WRITE_SAME) return 1; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2c210b6..e79055c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -882,7 +882,7 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq) static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, int op) { - if (unlikely(op == REQ_OP_DISCARD)) + if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)) return min(q->limits.max_discard_sectors, UINT_MAX >> 9); if (unlikely(op == REQ_OP_WRITE_SAME)) @@ -913,7 +913,9 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq, if (unlikely(rq->cmd_type != REQ_TYPE_FS)) return q->limits.max_hw_sectors; - if (!q->limits.chunk_sectors || (req_op(rq) == REQ_OP_DISCARD)) + if (!q->limits.chunk_sectors || + req_op(rq) == REQ_OP_DISCARD || + req_op(rq) == REQ_OP_SECURE_ERASE) return blk_queue_get_max_sectors(q, req_op(rq)); return min(blk_max_size_offset(q, offset), diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index e294939..8dbc892 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -242,7 +242,11 @@ */ #define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) -#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP +/* + * sparse (__CHECKER__) pretends to be gcc, but can't do constant + * folding in __builtin_bswap*() (yet), so don't set these for it. + */ +#if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) && !defined(__CHECKER__) #if GCC_VERSION >= 40400 #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ @@ -250,7 +254,7 @@ #if GCC_VERSION >= 40800 #define __HAVE_BUILTIN_BSWAP16__ #endif -#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ +#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP && !__CHECKER__ */ #if GCC_VERSION >= 50000 #define KASAN_ABI_VERSION 4 diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 56b0b7e..99ac022 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -337,6 +337,7 @@ */ #define E_ITS_MOVI_UNMAPPED_INTERRUPT 0x010107 #define E_ITS_MOVI_UNMAPPED_COLLECTION 0x010109 +#define E_ITS_INT_UNMAPPED_INTERRUPT 0x010307 #define E_ITS_CLEAR_UNMAPPED_INTERRUPT 0x010507 #define E_ITS_MAPD_DEVICE_OOR 0x010801 #define E_ITS_MAPC_PROCNUM_OOR 0x010902 diff --git a/include/linux/pci.h b/include/linux/pci.h index 2599a98..fbc1fa6 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1251,10 +1251,12 @@ resource_size_t pcibios_iov_resource_alignment(struct pci_dev *dev, int resno); int pci_set_vga_state(struct pci_dev *pdev, bool decode, unsigned int command_bits, u32 flags); -#define PCI_IRQ_NOLEGACY (1 << 0) /* don't use legacy interrupts */ -#define PCI_IRQ_NOMSI (1 << 1) /* don't use MSI interrupts */ -#define PCI_IRQ_NOMSIX (1 << 2) /* don't use MSI-X interrupts */ -#define PCI_IRQ_NOAFFINITY (1 << 3) /* don't auto-assign affinity */ +#define PCI_IRQ_LEGACY (1 << 0) /* allow legacy interrupts */ +#define PCI_IRQ_MSI (1 << 1) /* allow MSI interrupts */ +#define PCI_IRQ_MSIX (1 << 2) /* allow MSI-X interrupts */ +#define PCI_IRQ_AFFINITY (1 << 3) /* auto-assign affinity */ +#define PCI_IRQ_ALL_TYPES \ + (PCI_IRQ_LEGACY | PCI_IRQ_MSI | PCI_IRQ_MSIX) /* kmem_cache style wrapper around pci_alloc_consistent() */ diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 697e160..a4f7203 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -42,6 +42,8 @@ extern int proc_dostring(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec(struct ctl_table *, int, void __user *, size_t *, loff_t *); +extern int proc_douintvec(struct ctl_table *, int, + void __user *, size_t *, loff_t *); extern int proc_dointvec_minmax(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec_jiffies(struct ctl_table *, int, diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 8e90dd2..e1f9673 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2115,22 +2115,17 @@ static inline bool ib_is_udata_cleared(struct ib_udata *udata, size_t len) { const void __user *p = udata->inbuf + offset; - bool ret = false; + bool ret; u8 *buf; if (len > USHRT_MAX) return false; - buf = kmalloc(len, GFP_KERNEL); - if (!buf) + buf = memdup_user(p, len); + if (IS_ERR(buf)) return false; - if (copy_from_user(buf, p, len)) - goto free; - ret = !memchr_inv(buf, 0, len); - -free: kfree(buf); return ret; } diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 9a37c541..b5486e6 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -9,8 +9,8 @@ DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu); -DECLARE_PER_CPU(int, xen_vcpu_id); -static inline int xen_vcpu_nr(int cpu) +DECLARE_PER_CPU(uint32_t, xen_vcpu_id); +static inline uint32_t xen_vcpu_nr(int cpu) { return per_cpu(xen_vcpu_id, cpu); } diff --git a/kernel/printk/braille.c b/kernel/printk/braille.c index 276762f..d5760c4 100644 --- a/kernel/printk/braille.c +++ b/kernel/printk/braille.c @@ -9,10 +9,10 @@ char *_braille_console_setup(char **str, char **brl_options) { - if (!memcmp(*str, "brl,", 4)) { + if (!strncmp(*str, "brl,", 4)) { *brl_options = ""; *str += 4; - } else if (!memcmp(str, "brl=", 4)) { + } else if (!strncmp(*str, "brl=", 4)) { *brl_options = *str + 4; *str = strchr(*brl_options, ','); if (!*str) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b43d0b2..a13bbda 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2140,6 +2140,21 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp, return 0; } +static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp, + int *valp, + int write, void *data) +{ + if (write) { + if (*negp) + return -EINVAL; + *valp = *lvalp; + } else { + unsigned int val = *valp; + *lvalp = (unsigned long)val; + } + return 0; +} + static const char proc_wspace_sep[] = { ' ', '\t', '\n' }; static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, @@ -2259,8 +2274,27 @@ static int do_proc_dointvec(struct ctl_table *table, int write, int proc_dointvec(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_dointvec(table,write,buffer,lenp,ppos, - NULL,NULL); + return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL); +} + +/** + * proc_douintvec - read a vector of unsigned integers + * @table: the sysctl table + * @write: %TRUE if this is a write to the sysctl file + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * + * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer + * values from/to the user buffer, treated as an ASCII string. + * + * Returns 0 on success. + */ +int proc_douintvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return do_proc_dointvec(table, write, buffer, lenp, ppos, + do_proc_douintvec_conv, NULL); } /* @@ -2858,6 +2892,12 @@ int proc_dointvec(struct ctl_table *table, int write, return -ENOSYS; } +int proc_douintvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} + int proc_dointvec_minmax(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -2903,6 +2943,7 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, * exception granted :-) */ EXPORT_SYMBOL(proc_dointvec); +EXPORT_SYMBOL(proc_douintvec); EXPORT_SYMBOL(proc_dointvec_jiffies); EXPORT_SYMBOL(proc_dointvec_minmax); EXPORT_SYMBOL(proc_dointvec_userhz_jiffies); diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 7598e6c..dbafc5d 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -223,7 +223,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, what |= MASK_TC_BIT(op_flags, META); what |= MASK_TC_BIT(op_flags, PREFLUSH); what |= MASK_TC_BIT(op_flags, FUA); - if (op == REQ_OP_DISCARD) + if (op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE) what |= BLK_TC_ACT(BLK_TC_DISCARD); if (op == REQ_OP_FLUSH) what |= BLK_TC_ACT(BLK_TC_FLUSH); @@ -262,7 +262,14 @@ config COMPACTION select MIGRATION depends on MMU help - Allows the compaction of memory for the allocation of huge pages. + Compaction is the only memory management component to form + high order (larger physically contiguous) memory blocks + reliably. The page allocator relies on compaction heavily and + the lack of the feature can lead to unexpected OOM killer + invocations for high order memory requests. You shouldn't + disable this option unless there really is a strong reason for + it and then we would be really interested to hear about that at + linux-mm@kvack.org. # # support for page migration diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2373f0a..2db2112 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1512,7 +1512,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, struct page *page; pgtable_t pgtable; pmd_t _pmd; - bool young, write, dirty; + bool young, write, dirty, soft_dirty; unsigned long addr; int i; @@ -1546,6 +1546,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, write = pmd_write(*pmd); young = pmd_young(*pmd); dirty = pmd_dirty(*pmd); + soft_dirty = pmd_soft_dirty(*pmd); pmdp_huge_split_prepare(vma, haddr, pmd); pgtable = pgtable_trans_huge_withdraw(mm, pmd); @@ -1562,6 +1563,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, swp_entry_t swp_entry; swp_entry = make_migration_entry(page + i, write); entry = swp_entry_to_pte(swp_entry); + if (soft_dirty) + entry = pte_swp_mksoft_dirty(entry); } else { entry = mk_pte(page + i, vma->vm_page_prot); entry = maybe_mkwrite(entry, vma); @@ -1569,6 +1572,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, entry = pte_wrprotect(entry); if (!young) entry = pte_mkold(entry); + if (soft_dirty) + entry = pte_mksoft_dirty(entry); } if (dirty) SetPageDirty(page + i); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2ff0289..9a6a51a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4082,24 +4082,6 @@ static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n) atomic_add(n, &memcg->id.ref); } -static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg) -{ - while (!atomic_inc_not_zero(&memcg->id.ref)) { - /* - * The root cgroup cannot be destroyed, so it's refcount must - * always be >= 1. - */ - if (WARN_ON_ONCE(memcg == root_mem_cgroup)) { - VM_BUG_ON(1); - break; - } - memcg = parent_mem_cgroup(memcg); - if (!memcg) - memcg = root_mem_cgroup; - } - return memcg; -} - static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n) { if (atomic_sub_and_test(n, &memcg->id.ref)) { @@ -5821,6 +5803,24 @@ static int __init mem_cgroup_init(void) subsys_initcall(mem_cgroup_init); #ifdef CONFIG_MEMCG_SWAP +static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg) +{ + while (!atomic_inc_not_zero(&memcg->id.ref)) { + /* + * The root cgroup cannot be destroyed, so it's refcount must + * always be >= 1. + */ + if (WARN_ON_ONCE(memcg == root_mem_cgroup)) { + VM_BUG_ON(1); + break; + } + memcg = parent_mem_cgroup(memcg); + if (!memcg) + memcg = root_mem_cgroup; + } + return memcg; +} + /** * mem_cgroup_swapout - transfer a memsw charge to swap * @page: page whose memsw charge to transfer diff --git a/mm/readahead.c b/mm/readahead.c index 65ec288..c8a955b 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -8,6 +8,7 @@ */ #include <linux/kernel.h> +#include <linux/dax.h> #include <linux/gfp.h> #include <linux/export.h> #include <linux/blkdev.h> @@ -544,6 +545,14 @@ do_readahead(struct address_space *mapping, struct file *filp, if (!mapping || !mapping->a_ops) return -EINVAL; + /* + * Readahead doesn't make sense for DAX inodes, but we don't want it + * to report a failure either. Instead, we just return success and + * don't do any work. + */ + if (dax_mapping(mapping)) + return 0; + return force_page_cache_readahead(mapping, filp, index, nr); } diff --git a/mm/usercopy.c b/mm/usercopy.c index 8ebae91..a3cc305 100644 --- a/mm/usercopy.c +++ b/mm/usercopy.c @@ -83,7 +83,7 @@ static bool overlaps(const void *ptr, unsigned long n, unsigned long low, unsigned long check_high = check_low + n; /* Does not overlap if entirely above or entirely below. */ - if (check_low >= high || check_high < low) + if (check_low >= high || check_high <= low) return false; return true; @@ -124,7 +124,7 @@ static inline const char *check_kernel_text_object(const void *ptr, static inline const char *check_bogus_address(const void *ptr, unsigned long n) { /* Reject if object wraps past end of memory. */ - if (ptr + n < ptr) + if ((unsigned long)ptr + n < (unsigned long)ptr) return "<wrapped address>"; /* Reject if NULL or ZERO-allocation. */ diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 49a00d5..aed4511 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -2136,9 +2136,11 @@ sub vcs_file_exists { my $cmd = $VCS_cmds{"file_exists_cmd"}; $cmd =~ s/(\$\w+)/$1/eeg; # interpolate $cmd - + $cmd .= " 2>&1"; $exists = &{$VCS_cmds{"execute_cmd"}}($cmd); + return 0 if ($? != 0); + return $exists; } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 574b1b4..7100f05 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4828,7 +4828,7 @@ enum { ALC293_FIXUP_DELL1_MIC_NO_PRESENCE, ALC292_FIXUP_TPT440_DOCK, ALC292_FIXUP_TPT440, - ALC283_FIXUP_BXBT2807_MIC, + ALC283_FIXUP_HEADSET_MIC, ALC255_FIXUP_DELL_WMI_MIC_MUTE_LED, ALC282_FIXUP_ASPIRE_V5_PINS, ALC280_FIXUP_HP_GPIO4, @@ -5321,7 +5321,7 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC292_FIXUP_TPT440_DOCK, }, - [ALC283_FIXUP_BXBT2807_MIC] = { + [ALC283_FIXUP_HEADSET_MIC] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { { 0x19, 0x04a110f0 }, @@ -5651,7 +5651,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10cf, 0x1757, "Lifebook E752", ALC269_FIXUP_LIFEBOOK_HP_PIN), SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), - SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_BXBT2807_MIC), + SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE), diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c index 54c09ac..16e459a 100644 --- a/sound/soc/atmel/atmel_ssc_dai.c +++ b/sound/soc/atmel/atmel_ssc_dai.c @@ -299,8 +299,9 @@ static int atmel_ssc_startup(struct snd_pcm_substream *substream, clk_enable(ssc_p->ssc->clk); ssc_p->mck_rate = clk_get_rate(ssc_p->ssc->clk); - /* Reset the SSC to keep it at a clean status */ - ssc_writel(ssc_p->ssc->regs, CR, SSC_BIT(CR_SWRST)); + /* Reset the SSC unless initialized to keep it in a clean state */ + if (!ssc_p->initialized) + ssc_writel(ssc_p->ssc->regs, CR, SSC_BIT(CR_SWRST)); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { dir = 0; diff --git a/sound/soc/codecs/da7213.c b/sound/soc/codecs/da7213.c index e5527bc..bcf1834 100644 --- a/sound/soc/codecs/da7213.c +++ b/sound/soc/codecs/da7213.c @@ -1247,8 +1247,8 @@ static int da7213_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) return -EINVAL; } - /* By default only 32 BCLK per WCLK is supported */ - dai_clk_mode |= DA7213_DAI_BCLKS_PER_WCLK_32; + /* By default only 64 BCLK per WCLK is supported */ + dai_clk_mode |= DA7213_DAI_BCLKS_PER_WCLK_64; snd_soc_write(codec, DA7213_DAI_CLK_MODE, dai_clk_mode); snd_soc_update_bits(codec, DA7213_DAI_CTRL, DA7213_DAI_FORMAT_MASK, diff --git a/sound/soc/codecs/max98371.c b/sound/soc/codecs/max98371.c index cf0a39b..02352ed 100644 --- a/sound/soc/codecs/max98371.c +++ b/sound/soc/codecs/max98371.c @@ -412,6 +412,7 @@ static int max98371_i2c_remove(struct i2c_client *client) static const struct i2c_device_id max98371_i2c_id[] = { { "max98371", 0 }, + { } }; MODULE_DEVICE_TABLE(i2c, max98371_i2c_id); diff --git a/sound/soc/codecs/nau8825.c b/sound/soc/codecs/nau8825.c index 5c9707a..2e59a85 100644 --- a/sound/soc/codecs/nau8825.c +++ b/sound/soc/codecs/nau8825.c @@ -212,31 +212,6 @@ static const unsigned short logtable[256] = { 0xfa2f, 0xfaea, 0xfba5, 0xfc60, 0xfd1a, 0xfdd4, 0xfe8e, 0xff47 }; -static struct snd_soc_dai *nau8825_get_codec_dai(struct nau8825 *nau8825) -{ - struct snd_soc_codec *codec = snd_soc_dapm_to_codec(nau8825->dapm); - struct snd_soc_component *component = &codec->component; - struct snd_soc_dai *codec_dai, *_dai; - - list_for_each_entry_safe(codec_dai, _dai, &component->dai_list, list) { - if (!strncmp(codec_dai->name, NUVOTON_CODEC_DAI, - strlen(NUVOTON_CODEC_DAI))) - return codec_dai; - } - return NULL; -} - -static bool nau8825_dai_is_active(struct nau8825 *nau8825) -{ - struct snd_soc_dai *codec_dai = nau8825_get_codec_dai(nau8825); - - if (codec_dai) { - if (codec_dai->playback_active || codec_dai->capture_active) - return true; - } - return false; -} - /** * nau8825_sema_acquire - acquire the semaphore of nau88l25 * @nau8825: component to register the codec private data with @@ -250,19 +225,26 @@ static bool nau8825_dai_is_active(struct nau8825 *nau8825) * Acquires the semaphore without jiffies. If no more tasks are allowed * to acquire the semaphore, calling this function will put the task to * sleep until the semaphore is released. - * It returns if the semaphore was acquired. + * If the semaphore is not released within the specified number of jiffies, + * this function returns -ETIME. + * If the sleep is interrupted by a signal, this function will return -EINTR. + * It returns 0 if the semaphore was acquired successfully. */ -static void nau8825_sema_acquire(struct nau8825 *nau8825, long timeout) +static int nau8825_sema_acquire(struct nau8825 *nau8825, long timeout) { int ret; - if (timeout) + if (timeout) { ret = down_timeout(&nau8825->xtalk_sem, timeout); - else + if (ret < 0) + dev_warn(nau8825->dev, "Acquire semaphone timeout\n"); + } else { ret = down_interruptible(&nau8825->xtalk_sem); + if (ret < 0) + dev_warn(nau8825->dev, "Acquire semaphone fail\n"); + } - if (ret < 0) - dev_warn(nau8825->dev, "Acquire semaphone fail\n"); + return ret; } /** @@ -1205,6 +1187,8 @@ static int nau8825_hw_params(struct snd_pcm_substream *substream, struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec); unsigned int val_len = 0; + nau8825_sema_acquire(nau8825, 2 * HZ); + switch (params_width(params)) { case 16: val_len |= NAU8825_I2S_DL_16; @@ -1225,6 +1209,9 @@ static int nau8825_hw_params(struct snd_pcm_substream *substream, regmap_update_bits(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL1, NAU8825_I2S_DL_MASK, val_len); + /* Release the semaphone. */ + nau8825_sema_release(nau8825); + return 0; } @@ -1234,6 +1221,8 @@ static int nau8825_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec); unsigned int ctrl1_val = 0, ctrl2_val = 0; + nau8825_sema_acquire(nau8825, 2 * HZ); + switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) { case SND_SOC_DAIFMT_CBM_CFM: ctrl2_val |= NAU8825_I2S_MS_MASTER; @@ -1282,6 +1271,9 @@ static int nau8825_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) regmap_update_bits(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL2, NAU8825_I2S_MS_MASK, ctrl2_val); + /* Release the semaphone. */ + nau8825_sema_release(nau8825); + return 0; } @@ -1611,8 +1603,11 @@ static irqreturn_t nau8825_interrupt(int irq, void *data) * cess and restore changes if process * is ongoing when ejection. */ + int ret; nau8825->xtalk_protect = true; - nau8825_sema_acquire(nau8825, 0); + ret = nau8825_sema_acquire(nau8825, 0); + if (ret < 0) + nau8825->xtalk_protect = false; } /* Startup cross talk detection process */ nau8825->xtalk_state = NAU8825_XTALK_PREPARE; @@ -2238,23 +2233,14 @@ static int __maybe_unused nau8825_suspend(struct snd_soc_codec *codec) static int __maybe_unused nau8825_resume(struct snd_soc_codec *codec) { struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec); + int ret; regcache_cache_only(nau8825->regmap, false); regcache_sync(nau8825->regmap); - if (nau8825_is_jack_inserted(nau8825->regmap)) { - /* If the jack is inserted, we need to check whether the play- - * back is active before suspend. If active, the driver has to - * raise the protection for cross talk function to avoid the - * playback recovers before cross talk process finish. Other- - * wise, the playback will be interfered by cross talk func- - * tion. It is better to apply hardware related parameters - * before starting playback or record. - */ - if (nau8825_dai_is_active(nau8825)) { - nau8825->xtalk_protect = true; - nau8825_sema_acquire(nau8825, 0); - } - } + nau8825->xtalk_protect = true; + ret = nau8825_sema_acquire(nau8825, 0); + if (ret < 0) + nau8825->xtalk_protect = false; enable_irq(nau8825->irq); return 0; diff --git a/sound/soc/codecs/wm2000.c b/sound/soc/codecs/wm2000.c index a67ea10..f266439 100644 --- a/sound/soc/codecs/wm2000.c +++ b/sound/soc/codecs/wm2000.c @@ -581,7 +581,7 @@ static int wm2000_anc_transition(struct wm2000_priv *wm2000, if (anc_transitions[i].dest == ANC_OFF) clk_disable_unprepare(wm2000->mclk); - return ret; + return 0; } static int wm2000_anc_set_mode(struct wm2000_priv *wm2000) diff --git a/sound/soc/generic/Makefile b/sound/soc/generic/Makefile index 45602ca..2d53c8d 100644 --- a/sound/soc/generic/Makefile +++ b/sound/soc/generic/Makefile @@ -1,5 +1,5 @@ -obj-$(CONFIG_SND_SIMPLE_CARD_UTILS) := simple-card-utils.o - +snd-soc-simple-card-utils-objs := simple-card-utils.o snd-soc-simple-card-objs := simple-card.o -obj-$(CONFIG_SND_SIMPLE_CARD) += snd-soc-simple-card.o +obj-$(CONFIG_SND_SIMPLE_CARD_UTILS) += snd-soc-simple-card-utils.o +obj-$(CONFIG_SND_SIMPLE_CARD) += snd-soc-simple-card.o diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index d89a9a1..9599de6 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -7,6 +7,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ +#include <linux/module.h> #include <linux/of.h> #include <sound/simple_card_utils.h> @@ -95,3 +96,8 @@ int asoc_simple_card_parse_card_name(struct snd_soc_card *card, return 0; } EXPORT_SYMBOL_GPL(asoc_simple_card_parse_card_name); + +/* Module information */ +MODULE_AUTHOR("Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>"); +MODULE_DESCRIPTION("ALSA SoC Simple Card Utils"); +MODULE_LICENSE("GPL v2"); diff --git a/sound/soc/intel/skylake/skl-sst-utils.c b/sound/soc/intel/skylake/skl-sst-utils.c index 25fcb79..ddcb52a 100644 --- a/sound/soc/intel/skylake/skl-sst-utils.c +++ b/sound/soc/intel/skylake/skl-sst-utils.c @@ -123,6 +123,11 @@ int snd_skl_get_module_info(struct skl_sst *ctx, u8 *uuid, uuid_mod = (uuid_le *)uuid; + if (list_empty(&ctx->uuid_list)) { + dev_err(ctx->dev, "Module list is empty\n"); + return -EINVAL; + } + list_for_each_entry(module, &ctx->uuid_list, list) { if (uuid_le_cmp(*uuid_mod, module->uuid) == 0) { dfw_config->module_id = module->id; diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index cd59536..e3e7641 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -672,8 +672,10 @@ static int skl_probe(struct pci_dev *pci, skl->nhlt = skl_nhlt_init(bus->dev); - if (skl->nhlt == NULL) + if (skl->nhlt == NULL) { + err = -ENODEV; goto out_free; + } skl_nhlt_update_topology_bin(skl); diff --git a/sound/soc/omap/omap-abe-twl6040.c b/sound/soc/omap/omap-abe-twl6040.c index 0843a68..f61b3b5 100644 --- a/sound/soc/omap/omap-abe-twl6040.c +++ b/sound/soc/omap/omap-abe-twl6040.c @@ -38,10 +38,10 @@ struct abe_twl6040 { int jack_detection; /* board can detect jack events */ int mclk_freq; /* MCLK frequency speed for twl6040 */ - - struct platform_device *dmic_codec_dev; }; +struct platform_device *dmic_codec_dev; + static int omap_abe_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params) { @@ -258,8 +258,6 @@ static int omap_abe_probe(struct platform_device *pdev) if (priv == NULL) return -ENOMEM; - priv->dmic_codec_dev = ERR_PTR(-EINVAL); - if (snd_soc_of_parse_card_name(card, "ti,model")) { dev_err(&pdev->dev, "Card name is not provided\n"); return -ENODEV; @@ -284,13 +282,6 @@ static int omap_abe_probe(struct platform_device *pdev) num_links = 2; abe_twl6040_dai_links[1].cpu_of_node = dai_node; abe_twl6040_dai_links[1].platform_of_node = dai_node; - - priv->dmic_codec_dev = platform_device_register_simple( - "dmic-codec", -1, NULL, 0); - if (IS_ERR(priv->dmic_codec_dev)) { - dev_err(&pdev->dev, "Can't instantiate dmic-codec\n"); - return PTR_ERR(priv->dmic_codec_dev); - } } else { num_links = 1; } @@ -299,16 +290,14 @@ static int omap_abe_probe(struct platform_device *pdev) of_property_read_u32(node, "ti,mclk-freq", &priv->mclk_freq); if (!priv->mclk_freq) { dev_err(&pdev->dev, "MCLK frequency not provided\n"); - ret = -EINVAL; - goto err_unregister; + return -EINVAL; } card->fully_routed = 1; if (!priv->mclk_freq) { dev_err(&pdev->dev, "MCLK frequency missing\n"); - ret = -ENODEV; - goto err_unregister; + return -ENODEV; } card->dai_link = abe_twl6040_dai_links; @@ -317,17 +306,9 @@ static int omap_abe_probe(struct platform_device *pdev) snd_soc_card_set_drvdata(card, priv); ret = snd_soc_register_card(card); - if (ret) { + if (ret) dev_err(&pdev->dev, "snd_soc_register_card() failed: %d\n", ret); - goto err_unregister; - } - - return 0; - -err_unregister: - if (!IS_ERR(priv->dmic_codec_dev)) - platform_device_unregister(priv->dmic_codec_dev); return ret; } @@ -335,13 +316,9 @@ err_unregister: static int omap_abe_remove(struct platform_device *pdev) { struct snd_soc_card *card = platform_get_drvdata(pdev); - struct abe_twl6040 *priv = snd_soc_card_get_drvdata(card); snd_soc_unregister_card(card); - if (!IS_ERR(priv->dmic_codec_dev)) - platform_device_unregister(priv->dmic_codec_dev); - return 0; } @@ -361,7 +338,33 @@ static struct platform_driver omap_abe_driver = { .remove = omap_abe_remove, }; -module_platform_driver(omap_abe_driver); +static int __init omap_abe_init(void) +{ + int ret; + + dmic_codec_dev = platform_device_register_simple("dmic-codec", -1, NULL, + 0); + if (IS_ERR(dmic_codec_dev)) { + pr_err("%s: dmic-codec device registration failed\n", __func__); + return PTR_ERR(dmic_codec_dev); + } + + ret = platform_driver_register(&omap_abe_driver); + if (ret) { + pr_err("%s: platform driver registration failed\n", __func__); + platform_device_unregister(dmic_codec_dev); + } + + return ret; +} +module_init(omap_abe_init); + +static void __exit omap_abe_exit(void) +{ + platform_driver_unregister(&omap_abe_driver); + platform_device_unregister(dmic_codec_dev); +} +module_exit(omap_abe_exit); MODULE_AUTHOR("Misael Lopez Cruz <misael.lopez@ti.com>"); MODULE_DESCRIPTION("ALSA SoC for OMAP boards with ABE and twl6040 codec"); diff --git a/sound/soc/omap/omap-mcpdm.c b/sound/soc/omap/omap-mcpdm.c index e7cdc51..64609c7 100644 --- a/sound/soc/omap/omap-mcpdm.c +++ b/sound/soc/omap/omap-mcpdm.c @@ -31,7 +31,6 @@ #include <linux/err.h> #include <linux/io.h> #include <linux/irq.h> -#include <linux/clk.h> #include <linux/slab.h> #include <linux/pm_runtime.h> #include <linux/of_device.h> @@ -55,7 +54,6 @@ struct omap_mcpdm { unsigned long phys_base; void __iomem *io_base; int irq; - struct clk *pdmclk; struct mutex mutex; @@ -390,15 +388,14 @@ static int omap_mcpdm_probe(struct snd_soc_dai *dai) struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai); int ret; - clk_prepare_enable(mcpdm->pdmclk); pm_runtime_enable(mcpdm->dev); /* Disable lines while request is ongoing */ pm_runtime_get_sync(mcpdm->dev); omap_mcpdm_write(mcpdm, MCPDM_REG_CTRL, 0x00); - ret = devm_request_irq(mcpdm->dev, mcpdm->irq, omap_mcpdm_irq_handler, - 0, "McPDM", (void *)mcpdm); + ret = request_irq(mcpdm->irq, omap_mcpdm_irq_handler, 0, "McPDM", + (void *)mcpdm); pm_runtime_put_sync(mcpdm->dev); @@ -423,9 +420,9 @@ static int omap_mcpdm_remove(struct snd_soc_dai *dai) { struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai); + free_irq(mcpdm->irq, (void *)mcpdm); pm_runtime_disable(mcpdm->dev); - clk_disable_unprepare(mcpdm->pdmclk); return 0; } @@ -445,8 +442,6 @@ static int omap_mcpdm_suspend(struct snd_soc_dai *dai) mcpdm->pm_active_count++; } - clk_disable_unprepare(mcpdm->pdmclk); - return 0; } @@ -454,8 +449,6 @@ static int omap_mcpdm_resume(struct snd_soc_dai *dai) { struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai); - clk_prepare_enable(mcpdm->pdmclk); - if (mcpdm->pm_active_count) { while (mcpdm->pm_active_count--) pm_runtime_get_sync(mcpdm->dev); @@ -549,15 +542,6 @@ static int asoc_mcpdm_probe(struct platform_device *pdev) mcpdm->dev = &pdev->dev; - mcpdm->pdmclk = devm_clk_get(&pdev->dev, "pdmclk"); - if (IS_ERR(mcpdm->pdmclk)) { - if (PTR_ERR(mcpdm->pdmclk) == -EPROBE_DEFER) - return -EPROBE_DEFER; - dev_warn(&pdev->dev, "Error getting pdmclk (%ld)!\n", - PTR_ERR(mcpdm->pdmclk)); - mcpdm->pdmclk = NULL; - } - ret = devm_snd_soc_register_component(&pdev->dev, &omap_mcpdm_component, &omap_mcpdm_dai, 1); diff --git a/sound/soc/samsung/s3c24xx_uda134x.c b/sound/soc/samsung/s3c24xx_uda134x.c index 50849e1..92e88bc 100644 --- a/sound/soc/samsung/s3c24xx_uda134x.c +++ b/sound/soc/samsung/s3c24xx_uda134x.c @@ -58,10 +58,12 @@ static struct platform_device *s3c24xx_uda134x_snd_device; static int s3c24xx_uda134x_startup(struct snd_pcm_substream *substream) { - int ret = 0; + struct snd_soc_pcm_runtime *rtd = substream->private_data; + struct snd_soc_dai *cpu_dai = rtd->cpu_dai; #ifdef ENFORCE_RATES struct snd_pcm_runtime *runtime = substream->runtime; #endif + int ret = 0; mutex_lock(&clk_lock); pr_debug("%s %d\n", __func__, clk_users); @@ -71,8 +73,7 @@ static int s3c24xx_uda134x_startup(struct snd_pcm_substream *substream) printk(KERN_ERR "%s cannot get xtal\n", __func__); ret = PTR_ERR(xtal); } else { - pclk = clk_get(&s3c24xx_uda134x_snd_device->dev, - "pclk"); + pclk = clk_get(cpu_dai->dev, "iis"); if (IS_ERR(pclk)) { printk(KERN_ERR "%s cannot get pclk\n", __func__); diff --git a/sound/soc/sh/rcar/src.c b/sound/soc/sh/rcar/src.c index e39f916..969a516 100644 --- a/sound/soc/sh/rcar/src.c +++ b/sound/soc/sh/rcar/src.c @@ -226,8 +226,12 @@ static void rsnd_src_set_convert_rate(struct rsnd_dai_stream *io, ifscr = 0; fsrate = 0; if (fin != fout) { + u64 n; + ifscr = 1; - fsrate = 0x0400000 / fout * fin; + n = (u64)0x0400000 * fin; + do_div(n, fout); + fsrate = n; } /* diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c index d2df46c..bf7b52f 100644 --- a/sound/soc/soc-compress.c +++ b/sound/soc/soc-compress.c @@ -121,7 +121,7 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream) dpcm_be_disconnect(fe, stream); fe->dpcm[stream].runtime = NULL; - goto fe_err; + goto path_err; } dpcm_clear_pending_state(fe, stream); @@ -136,6 +136,8 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream) return 0; +path_err: + dpcm_path_put(&list); fe_err: if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->shutdown) fe->dai_link->compr_ops->shutdown(cstream); diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 16369ca..4afa8db 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1056,7 +1056,7 @@ static int soc_bind_dai_link(struct snd_soc_card *card, if (!rtd->platform) { dev_err(card->dev, "ASoC: platform %s not registered\n", dai_link->platform_name); - return -EPROBE_DEFER; + goto _err_defer; } soc_add_pcm_runtime(card, rtd); @@ -2083,14 +2083,13 @@ static int soc_cleanup_card_resources(struct snd_soc_card *card) /* remove auxiliary devices */ soc_remove_aux_devices(card); + snd_soc_dapm_free(&card->dapm); soc_cleanup_card_debugfs(card); /* remove the card */ if (card->remove) card->remove(card); - snd_soc_dapm_free(&card->dapm); - snd_card_free(card->snd_card); return 0; diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 8698c26..d908ff8 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -3493,6 +3493,7 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w, const struct snd_soc_pcm_stream *config = w->params + w->params_select; struct snd_pcm_substream substream; struct snd_pcm_hw_params *params = NULL; + struct snd_pcm_runtime *runtime = NULL; u64 fmt; int ret; @@ -3541,6 +3542,14 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w, memset(&substream, 0, sizeof(substream)); + /* Allocate a dummy snd_pcm_runtime for startup() and other ops() */ + runtime = kzalloc(sizeof(*runtime), GFP_KERNEL); + if (!runtime) { + ret = -ENOMEM; + goto out; + } + substream.runtime = runtime; + switch (event) { case SND_SOC_DAPM_PRE_PMU: substream.stream = SNDRV_PCM_STREAM_CAPTURE; @@ -3606,6 +3615,7 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w, } out: + kfree(runtime); kfree(params); return ret; } diff --git a/sound/usb/line6/pcm.c b/sound/usb/line6/pcm.c index 204cc07..41aa335 100644 --- a/sound/usb/line6/pcm.c +++ b/sound/usb/line6/pcm.c @@ -55,7 +55,6 @@ static int snd_line6_impulse_volume_put(struct snd_kcontrol *kcontrol, err = line6_pcm_acquire(line6pcm, LINE6_STREAM_IMPULSE); if (err < 0) { line6pcm->impulse_volume = 0; - line6_pcm_release(line6pcm, LINE6_STREAM_IMPULSE); return err; } } else { @@ -211,7 +210,9 @@ static void line6_stream_stop(struct snd_line6_pcm *line6pcm, int direction, spin_lock_irqsave(&pstr->lock, flags); clear_bit(type, &pstr->running); if (!pstr->running) { + spin_unlock_irqrestore(&pstr->lock, flags); line6_unlink_audio_urbs(line6pcm, pstr); + spin_lock_irqsave(&pstr->lock, flags); if (direction == SNDRV_PCM_STREAM_CAPTURE) { line6pcm->prev_fbuf = NULL; line6pcm->prev_fsize = 0; diff --git a/sound/usb/line6/pod.c b/sound/usb/line6/pod.c index daf81d16..45dd348 100644 --- a/sound/usb/line6/pod.c +++ b/sound/usb/line6/pod.c @@ -244,8 +244,8 @@ static int pod_set_system_param_int(struct usb_line6_pod *pod, int value, static ssize_t serial_number_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct usb_interface *interface = to_usb_interface(dev); - struct usb_line6_pod *pod = usb_get_intfdata(interface); + struct snd_card *card = dev_to_snd_card(dev); + struct usb_line6_pod *pod = card->private_data; return sprintf(buf, "%u\n", pod->serial_number); } @@ -256,8 +256,8 @@ static ssize_t serial_number_show(struct device *dev, static ssize_t firmware_version_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct usb_interface *interface = to_usb_interface(dev); - struct usb_line6_pod *pod = usb_get_intfdata(interface); + struct snd_card *card = dev_to_snd_card(dev); + struct usb_line6_pod *pod = card->private_data; return sprintf(buf, "%d.%02d\n", pod->firmware_version / 100, pod->firmware_version % 100); @@ -269,8 +269,8 @@ static ssize_t firmware_version_show(struct device *dev, static ssize_t device_id_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct usb_interface *interface = to_usb_interface(dev); - struct usb_line6_pod *pod = usb_get_intfdata(interface); + struct snd_card *card = dev_to_snd_card(dev); + struct usb_line6_pod *pod = card->private_data; return sprintf(buf, "%d\n", pod->device_id); } diff --git a/tools/gpio/gpio-event-mon.c b/tools/gpio/gpio-event-mon.c index 448ed96..1c14c25 100644 --- a/tools/gpio/gpio-event-mon.c +++ b/tools/gpio/gpio-event-mon.c @@ -1,5 +1,5 @@ /* - * gpio-hammer - example swiss army knife to shake GPIO lines on a system + * gpio-event-mon - monitor GPIO line events from userspace * * Copyright (C) 2016 Linus Walleij * diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index 4fde8c7..77e6ccf 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -33,6 +33,7 @@ static struct timecounter *timecounter; static struct workqueue_struct *wqueue; static unsigned int host_vtimer_irq; +static u32 host_vtimer_irq_flags; void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) { @@ -365,7 +366,7 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) static void kvm_timer_init_interrupt(void *info) { - enable_percpu_irq(host_vtimer_irq, 0); + enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); } int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) @@ -432,6 +433,14 @@ int kvm_timer_hyp_init(void) } host_vtimer_irq = info->virtual_irq; + host_vtimer_irq_flags = irq_get_trigger_type(host_vtimer_irq); + if (host_vtimer_irq_flags != IRQF_TRIGGER_HIGH && + host_vtimer_irq_flags != IRQF_TRIGGER_LOW) { + kvm_err("Invalid trigger for IRQ%d, assuming level low\n", + host_vtimer_irq); + host_vtimer_irq_flags = IRQF_TRIGGER_LOW; + } + err = request_percpu_irq(host_vtimer_irq, kvm_arch_timer_handler, "kvm guest timer", kvm_get_running_vcpus()); if (err) { diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index 07411cf..4660a7d 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -51,7 +51,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid) irq = kzalloc(sizeof(struct vgic_irq), GFP_KERNEL); if (!irq) - return NULL; + return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&irq->lpi_list); INIT_LIST_HEAD(&irq->ap_list); @@ -441,39 +441,63 @@ static unsigned long vgic_mmio_read_its_idregs(struct kvm *kvm, * Find the target VCPU and the LPI number for a given devid/eventid pair * and make this IRQ pending, possibly injecting it. * Must be called with the its_lock mutex held. + * Returns 0 on success, a positive error value for any ITS mapping + * related errors and negative error values for generic errors. */ -static void vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its, - u32 devid, u32 eventid) +static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its, + u32 devid, u32 eventid) { + struct kvm_vcpu *vcpu; struct its_itte *itte; if (!its->enabled) - return; + return -EBUSY; itte = find_itte(its, devid, eventid); - /* Triggering an unmapped IRQ gets silently dropped. */ - if (itte && its_is_collection_mapped(itte->collection)) { - struct kvm_vcpu *vcpu; - - vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr); - if (vcpu && vcpu->arch.vgic_cpu.lpis_enabled) { - spin_lock(&itte->irq->irq_lock); - itte->irq->pending = true; - vgic_queue_irq_unlock(kvm, itte->irq); - } - } + if (!itte || !its_is_collection_mapped(itte->collection)) + return E_ITS_INT_UNMAPPED_INTERRUPT; + + vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr); + if (!vcpu) + return E_ITS_INT_UNMAPPED_INTERRUPT; + + if (!vcpu->arch.vgic_cpu.lpis_enabled) + return -EBUSY; + + spin_lock(&itte->irq->irq_lock); + itte->irq->pending = true; + vgic_queue_irq_unlock(kvm, itte->irq); + + return 0; +} + +static struct vgic_io_device *vgic_get_its_iodev(struct kvm_io_device *dev) +{ + struct vgic_io_device *iodev; + + if (dev->ops != &kvm_io_gic_ops) + return NULL; + + iodev = container_of(dev, struct vgic_io_device, dev); + + if (iodev->iodev_type != IODEV_ITS) + return NULL; + + return iodev; } /* * Queries the KVM IO bus framework to get the ITS pointer from the given * doorbell address. * We then call vgic_its_trigger_msi() with the decoded data. + * According to the KVM_SIGNAL_MSI API description returns 1 on success. */ int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi) { u64 address; struct kvm_io_device *kvm_io_dev; struct vgic_io_device *iodev; + int ret; if (!vgic_has_its(kvm)) return -ENODEV; @@ -485,15 +509,28 @@ int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi) kvm_io_dev = kvm_io_bus_get_dev(kvm, KVM_MMIO_BUS, address); if (!kvm_io_dev) - return -ENODEV; + return -EINVAL; - iodev = container_of(kvm_io_dev, struct vgic_io_device, dev); + iodev = vgic_get_its_iodev(kvm_io_dev); + if (!iodev) + return -EINVAL; mutex_lock(&iodev->its->its_lock); - vgic_its_trigger_msi(kvm, iodev->its, msi->devid, msi->data); + ret = vgic_its_trigger_msi(kvm, iodev->its, msi->devid, msi->data); mutex_unlock(&iodev->its->its_lock); - return 0; + if (ret < 0) + return ret; + + /* + * KVM_SIGNAL_MSI demands a return value > 0 for success and 0 + * if the guest has blocked the MSI. So we map any LPI mapping + * related error to that. + */ + if (ret) + return 0; + else + return 1; } /* Requires the its_lock to be held. */ @@ -502,7 +539,8 @@ static void its_free_itte(struct kvm *kvm, struct its_itte *itte) list_del(&itte->itte_list); /* This put matches the get in vgic_add_lpi. */ - vgic_put_irq(kvm, itte->irq); + if (itte->irq) + vgic_put_irq(kvm, itte->irq); kfree(itte); } @@ -697,6 +735,7 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, struct its_device *device; struct its_collection *collection, *new_coll = NULL; int lpi_nr; + struct vgic_irq *irq; device = find_its_device(its, device_id); if (!device) @@ -710,6 +749,10 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, lpi_nr >= max_lpis_propbaser(kvm->arch.vgic.propbaser)) return E_ITS_MAPTI_PHYSICALID_OOR; + /* If there is an existing mapping, behavior is UNPREDICTABLE. */ + if (find_itte(its, device_id, event_id)) + return 0; + collection = find_collection(its, coll_id); if (!collection) { int ret = vgic_its_alloc_collection(its, &collection, coll_id); @@ -718,22 +761,28 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, new_coll = collection; } - itte = find_itte(its, device_id, event_id); + itte = kzalloc(sizeof(struct its_itte), GFP_KERNEL); if (!itte) { - itte = kzalloc(sizeof(struct its_itte), GFP_KERNEL); - if (!itte) { - if (new_coll) - vgic_its_free_collection(its, coll_id); - return -ENOMEM; - } - - itte->event_id = event_id; - list_add_tail(&itte->itte_list, &device->itt_head); + if (new_coll) + vgic_its_free_collection(its, coll_id); + return -ENOMEM; } + itte->event_id = event_id; + list_add_tail(&itte->itte_list, &device->itt_head); + itte->collection = collection; itte->lpi = lpi_nr; - itte->irq = vgic_add_lpi(kvm, lpi_nr); + + irq = vgic_add_lpi(kvm, lpi_nr); + if (IS_ERR(irq)) { + if (new_coll) + vgic_its_free_collection(its, coll_id); + its_free_itte(kvm, itte); + return PTR_ERR(irq); + } + itte->irq = irq; + update_affinity_itte(kvm, itte); /* @@ -981,9 +1030,7 @@ static int vgic_its_cmd_handle_int(struct kvm *kvm, struct vgic_its *its, u32 msi_data = its_cmd_get_id(its_cmd); u64 msi_devid = its_cmd_get_deviceid(its_cmd); - vgic_its_trigger_msi(kvm, its, msi_devid, msi_data); - - return 0; + return vgic_its_trigger_msi(kvm, its, msi_devid, msi_data); } /* @@ -1288,13 +1335,13 @@ void vgic_enable_lpis(struct kvm_vcpu *vcpu) its_sync_lpi_pending_table(vcpu); } -static int vgic_its_init_its(struct kvm *kvm, struct vgic_its *its) +static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its) { struct vgic_io_device *iodev = &its->iodev; int ret; - if (its->initialized) - return 0; + if (!its->initialized) + return -EBUSY; if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) return -ENXIO; @@ -1311,9 +1358,6 @@ static int vgic_its_init_its(struct kvm *kvm, struct vgic_its *its) KVM_VGIC_V3_ITS_SIZE, &iodev->dev); mutex_unlock(&kvm->slots_lock); - if (!ret) - its->initialized = true; - return ret; } @@ -1435,9 +1479,6 @@ static int vgic_its_set_attr(struct kvm_device *dev, if (type != KVM_VGIC_ITS_ADDR_TYPE) return -ENODEV; - if (its->initialized) - return -EBUSY; - if (copy_from_user(&addr, uaddr, sizeof(addr))) return -EFAULT; @@ -1453,7 +1494,9 @@ static int vgic_its_set_attr(struct kvm_device *dev, case KVM_DEV_ARM_VGIC_GRP_CTRL: switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: - return vgic_its_init_its(dev->kvm, its); + its->initialized = true; + + return 0; } break; } @@ -1498,3 +1541,30 @@ int kvm_vgic_register_its_device(void) return kvm_register_device_ops(&kvm_arm_vgic_its_ops, KVM_DEV_TYPE_ARM_VGIC_ITS); } + +/* + * Registers all ITSes with the kvm_io_bus framework. + * To follow the existing VGIC initialization sequence, this has to be + * done as late as possible, just before the first VCPU runs. + */ +int vgic_register_its_iodevs(struct kvm *kvm) +{ + struct kvm_device *dev; + int ret = 0; + + list_for_each_entry(dev, &kvm->devices, vm_node) { + if (dev->ops != &kvm_arm_vgic_its_ops) + continue; + + ret = vgic_register_its_iodev(kvm, dev->private); + if (ret) + return ret; + /* + * We don't need to care about tearing down previously + * registered ITSes, as the kvm_io_bus framework removes + * them for us if the VM gets destroyed. + */ + } + + return ret; +} diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index ff668e0..90d8181 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -306,16 +306,19 @@ static void vgic_mmio_write_propbase(struct kvm_vcpu *vcpu, { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - u64 propbaser = dist->propbaser; + u64 old_propbaser, propbaser; /* Storing a value with LPIs already enabled is undefined */ if (vgic_cpu->lpis_enabled) return; - propbaser = update_64bit_reg(propbaser, addr & 4, len, val); - propbaser = vgic_sanitise_propbaser(propbaser); - - dist->propbaser = propbaser; + do { + old_propbaser = dist->propbaser; + propbaser = old_propbaser; + propbaser = update_64bit_reg(propbaser, addr & 4, len, val); + propbaser = vgic_sanitise_propbaser(propbaser); + } while (cmpxchg64(&dist->propbaser, old_propbaser, + propbaser) != old_propbaser); } static unsigned long vgic_mmio_read_pendbase(struct kvm_vcpu *vcpu, @@ -331,16 +334,19 @@ static void vgic_mmio_write_pendbase(struct kvm_vcpu *vcpu, unsigned long val) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - u64 pendbaser = vgic_cpu->pendbaser; + u64 old_pendbaser, pendbaser; /* Storing a value with LPIs already enabled is undefined */ if (vgic_cpu->lpis_enabled) return; - pendbaser = update_64bit_reg(pendbaser, addr & 4, len, val); - pendbaser = vgic_sanitise_pendbaser(pendbaser); - - vgic_cpu->pendbaser = pendbaser; + do { + old_pendbaser = vgic_cpu->pendbaser; + pendbaser = old_pendbaser; + pendbaser = update_64bit_reg(pendbaser, addr & 4, len, val); + pendbaser = vgic_sanitise_pendbaser(pendbaser); + } while (cmpxchg64(&vgic_cpu->pendbaser, old_pendbaser, + pendbaser) != old_pendbaser); } /* diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 0506543..9f0dae3 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -289,6 +289,14 @@ int vgic_v3_map_resources(struct kvm *kvm) goto out; } + if (vgic_has_its(kvm)) { + ret = vgic_register_its_iodevs(kvm); + if (ret) { + kvm_err("Unable to register VGIC ITS MMIO regions\n"); + goto out; + } + } + dist->ready = true; out: diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c index e7aeac7..e83b7fe 100644 --- a/virt/kvm/arm/vgic/vgic.c +++ b/virt/kvm/arm/vgic/vgic.c @@ -117,17 +117,17 @@ static void vgic_irq_release(struct kref *ref) void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) { - struct vgic_dist *dist; + struct vgic_dist *dist = &kvm->arch.vgic; if (irq->intid < VGIC_MIN_LPI) return; - if (!kref_put(&irq->refcount, vgic_irq_release)) + spin_lock(&dist->lpi_list_lock); + if (!kref_put(&irq->refcount, vgic_irq_release)) { + spin_unlock(&dist->lpi_list_lock); return; + }; - dist = &kvm->arch.vgic; - - spin_lock(&dist->lpi_list_lock); list_del(&irq->lpi_list); dist->lpi_list_count--; spin_unlock(&dist->lpi_list_lock); diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index 1d8e21d..6c4625c 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -84,6 +84,7 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu); int vgic_v3_probe(const struct gic_kvm_info *info); int vgic_v3_map_resources(struct kvm *kvm); int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t dist_base_address); +int vgic_register_its_iodevs(struct kvm *kvm); bool vgic_has_its(struct kvm *kvm); int kvm_vgic_register_its_device(void); void vgic_enable_lpis(struct kvm_vcpu *vcpu); @@ -140,6 +141,11 @@ static inline int vgic_register_redist_iodevs(struct kvm *kvm, return -ENODEV; } +static inline int vgic_register_its_iodevs(struct kvm *kvm) +{ + return -ENODEV; +} + static inline bool vgic_has_its(struct kvm *kvm) { return false; |
