diff options
231 files changed, 4617 insertions, 1983 deletions
diff --git a/.clang-format b/.clang-format index 1247d54f9e49..8d01225bfcb7 100644 --- a/.clang-format +++ b/.clang-format @@ -535,6 +535,7 @@ ForEachMacros: - 'perf_hpp_list__for_each_sort_list_safe' - 'perf_pmu__for_each_hybrid_pmu' - 'ping_portaddr_for_each_entry' + - 'ping_portaddr_for_each_entry_rcu' - 'plist_for_each' - 'plist_for_each_continue' - 'plist_for_each_entry' @@ -287,6 +287,7 @@ Matthew Wilcox <[email protected]> <[email protected]> Matthew Wilcox <[email protected]> <[email protected]> Matthias Fuchs <[email protected]> <[email protected]> Matthieu CASTET <[email protected]> +Matti Vaittinen <[email protected]> <[email protected]> Matt Ranostay <[email protected]> <[email protected]> Matt Ranostay <[email protected]> Matthew Ranostay <[email protected]> Matt Ranostay <[email protected]> <[email protected]> @@ -372,6 +373,8 @@ Ricardo Ribalda <[email protected]> <[email protected]> Roman Gushchin <[email protected]> <[email protected]> Roman Gushchin <[email protected]> <[email protected]> Roman Gushchin <[email protected]> <[email protected]> +Muchun Song <[email protected]> <[email protected]> +Muchun Song <[email protected]> <[email protected]> Ross Zwisler <[email protected]> <[email protected]> Rudolf Marek <[email protected]> Rui Saraiva <[email protected]> diff --git a/Documentation/PCI/msi-howto.rst b/Documentation/PCI/msi-howto.rst index aa2046af69f7..8ae461e97c54 100644 --- a/Documentation/PCI/msi-howto.rst +++ b/Documentation/PCI/msi-howto.rst @@ -285,3 +285,13 @@ to bridges between the PCI root and the device, MSIs are disabled. It is also worth checking the device driver to see whether it supports MSIs. For example, it may contain calls to pci_alloc_irq_vectors() with the PCI_IRQ_MSI or PCI_IRQ_MSIX flags. + + +List of device drivers MSI(-X) APIs +=================================== + +The PCI/MSI subystem has a dedicated C file for its exported device driver +APIs — `drivers/pci/msi/api.c`. The following functions are exported: + +.. kernel-doc:: drivers/pci/msi/api.c + :export: diff --git a/Documentation/devicetree/bindings/interrupt-controller/loongarch,cpu-interrupt-controller.yaml b/Documentation/devicetree/bindings/interrupt-controller/loongarch,cpu-interrupt-controller.yaml new file mode 100644 index 000000000000..2a1cf885c99d --- /dev/null +++ b/Documentation/devicetree/bindings/interrupt-controller/loongarch,cpu-interrupt-controller.yaml @@ -0,0 +1,34 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/interrupt-controller/loongarch,cpu-interrupt-controller.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: LoongArch CPU Interrupt Controller + +maintainers: + - Liu Peibao <[email protected]> + +properties: + compatible: + const: loongarch,cpu-interrupt-controller + + '#interrupt-cells': + const: 1 + + interrupt-controller: true + +additionalProperties: false + +required: + - compatible + - '#interrupt-cells' + - interrupt-controller + +examples: + - | + interrupt-controller { + compatible = "loongarch,cpu-interrupt-controller"; + #interrupt-cells = <1>; + interrupt-controller; + }; diff --git a/Documentation/devicetree/bindings/interrupt-controller/mediatek,cirq.txt b/Documentation/devicetree/bindings/interrupt-controller/mediatek,cirq.txt deleted file mode 100644 index 5865f4f2c69d..000000000000 --- a/Documentation/devicetree/bindings/interrupt-controller/mediatek,cirq.txt +++ /dev/null @@ -1,33 +0,0 @@ -* Mediatek 27xx cirq - -In Mediatek SOCs, the CIRQ is a low power interrupt controller designed to -work outside MCUSYS which comprises with Cortex-Ax cores,CCI and GIC. -The external interrupts (outside MCUSYS) will feed through CIRQ and connect -to GIC in MCUSYS. When CIRQ is enabled, it will record the edge-sensitive -interrupts and generate a pulse signal to parent interrupt controller when -flush command is executed. With CIRQ, MCUSYS can be completely turned off -to improve the system power consumption without losing interrupts. - -Required properties: -- compatible: should be one of - - "mediatek,mt2701-cirq" for mt2701 CIRQ - - "mediatek,mt8135-cirq" for mt8135 CIRQ - - "mediatek,mt8173-cirq" for mt8173 CIRQ - and "mediatek,cirq" as a fallback. -- interrupt-controller : Identifies the node as an interrupt controller. -- #interrupt-cells : Use the same format as specified by GIC in arm,gic.txt. -- reg: Physical base address of the cirq registers and length of memory - mapped region. -- mediatek,ext-irq-range: Identifies external irq number range in different - SOCs. - -Example: - cirq: interrupt-controller@10204000 { - compatible = "mediatek,mt2701-cirq", - "mediatek,mtk-cirq"; - interrupt-controller; - #interrupt-cells = <3>; - interrupt-parent = <&sysirq>; - reg = <0 0x10204000 0 0x400>; - mediatek,ext-irq-start = <32 200>; - }; diff --git a/Documentation/devicetree/bindings/interrupt-controller/mediatek,mtk-cirq.yaml b/Documentation/devicetree/bindings/interrupt-controller/mediatek,mtk-cirq.yaml new file mode 100644 index 000000000000..fdcb4d8db818 --- /dev/null +++ b/Documentation/devicetree/bindings/interrupt-controller/mediatek,mtk-cirq.yaml @@ -0,0 +1,68 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/interrupt-controller/mediatek,mtk-cirq.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: MediaTek System Interrupt Controller + +maintainers: + - Youlin Pei <[email protected]> + +description: + In MediaTek SoCs, the CIRQ is a low power interrupt controller designed to + work outside of MCUSYS which comprises with Cortex-Ax cores, CCI and GIC. + The external interrupts (outside MCUSYS) will feed through CIRQ and connect + to GIC in MCUSYS. When CIRQ is enabled, it will record the edge-sensitive + interrupts and generate a pulse signal to parent interrupt controller when + flush command is executed. With CIRQ, MCUSYS can be completely turned off + to improve the system power consumption without losing interrupts. + + +properties: + compatible: + items: + - enum: + - mediatek,mt2701-cirq + - mediatek,mt8135-cirq + - mediatek,mt8173-cirq + - mediatek,mt8192-cirq + - const: mediatek,mtk-cirq + + reg: + maxItems: 1 + + '#interrupt-cells': + const: 3 + + interrupt-controller: true + + mediatek,ext-irq-range: + $ref: /schemas/types.yaml#/definitions/uint32-array + items: + - description: First CIRQ interrupt + - description: Last CIRQ interrupt + description: + Identifies the range of external interrupts in different SoCs + +required: + - compatible + - reg + - '#interrupt-cells' + - interrupt-controller + - mediatek,ext-irq-range + +additionalProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/irq.h> + + cirq: interrupt-controller@10204000 { + compatible = "mediatek,mt2701-cirq", "mediatek,mtk-cirq"; + reg = <0x10204000 0x400>; + #interrupt-cells = <3>; + interrupt-controller; + interrupt-parent = <&sysirq>; + mediatek,ext-irq-range = <32 200>; + }; diff --git a/Documentation/loongarch/booting.rst b/Documentation/loongarch/booting.rst new file mode 100644 index 000000000000..91eccd410478 --- /dev/null +++ b/Documentation/loongarch/booting.rst @@ -0,0 +1,42 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================= +Booting Linux/LoongArch +======================= + +:Author: Yanteng Si <[email protected]> +:Date: 18 Nov 2022 + +Information passed from BootLoader to kernel +============================================ + +LoongArch supports ACPI and FDT. The information that needs to be passed +to the kernel includes the memmap, the initrd, the command line, optionally +the ACPI/FDT tables, and so on. + +The kernel is passed the following arguments on `kernel_entry` : + + - a0 = efi_boot: `efi_boot` is a flag indicating whether + this boot environment is fully UEFI-compliant. + + - a1 = cmdline: `cmdline` is a pointer to the kernel command line. + + - a2 = systemtable: `systemtable` points to the EFI system table. + All pointers involved at this stage are in physical addresses. + +Header of Linux/LoongArch kernel images +======================================= + +Linux/LoongArch kernel images are EFI images. Being PE files, they have +a 64-byte header structured like:: + + u32 MZ_MAGIC /* "MZ", MS-DOS header */ + u32 res0 = 0 /* Reserved */ + u64 kernel_entry /* Kernel entry point */ + u64 _end - _text /* Kernel image effective size */ + u64 load_offset /* Kernel image load offset from start of RAM */ + u64 res1 = 0 /* Reserved */ + u64 res2 = 0 /* Reserved */ + u64 res3 = 0 /* Reserved */ + u32 LINUX_PE_MAGIC /* Magic number */ + u32 pe_header - _head /* Offset to the PE header */ diff --git a/Documentation/loongarch/index.rst b/Documentation/loongarch/index.rst index aaba648db907..c779bfa00c05 100644 --- a/Documentation/loongarch/index.rst +++ b/Documentation/loongarch/index.rst @@ -9,6 +9,7 @@ LoongArch Architecture :numbered: introduction + booting irq-chip-model features diff --git a/Documentation/translations/zh_CN/loongarch/booting.rst b/Documentation/translations/zh_CN/loongarch/booting.rst new file mode 100644 index 000000000000..fb6440c438f0 --- /dev/null +++ b/Documentation/translations/zh_CN/loongarch/booting.rst @@ -0,0 +1,48 @@ +.. SPDX-License-Identifier: GPL-2.0 + +.. include:: ../disclaimer-zh_CN.rst + +:Original: Documentation/loongarch/booting.rst + +:翻译: + + 司延腾 Yanteng Si <[email protected]> + +==================== +启动 Linux/LoongArch +==================== + +:作者: 司延腾 <[email protected]> +:日期: 2022年11月18日 + +BootLoader传递给内核的信息 +========================== + +LoongArch支持ACPI和FDT启动，需要传递给内核的信息包括memmap、initrd、cmdline、可 +选的ACPI/FDT表等。 + +内核在 `kernel_entry` 入口处被传递以下参数: + + - a0 = efi_boot: `efi_boot` 是一个标志，表示这个启动环境是否完全符合UEFI + 的要求。 + + - a1 = cmdline: `cmdline` 是一个指向内核命令行的指针。 + + - a2 = systemtable: `systemtable` 指向EFI的系统表，在这个阶段涉及的所有 + 指针都是物理地址。 + +Linux/LoongArch内核镜像文件头 +============================= + +内核镜像是EFI镜像。作为PE文件，它们有一个64字节的头部结构体，如下所示:: + + u32 MZ_MAGIC /* "MZ", MS-DOS 头 */ + u32 res0 = 0 /* 保留 */ + u64 kernel_entry /* 内核入口点 */ + u64 _end - _text /* 内核镜像有效大小 */ + u64 load_offset /* 加载内核镜像相对内存起始地址的偏移量 */ + u64 res1 = 0 /* 保留 */ + u64 res2 = 0 /* 保留 */ + u64 res3 = 0 /* 保留 */ + u32 LINUX_PE_MAGIC /* 魔术数 */ + u32 pe_header - _head /* 到PE头的偏移量 */ diff --git a/Documentation/translations/zh_CN/loongarch/index.rst b/Documentation/translations/zh_CN/loongarch/index.rst index 7d23eb78379d..0273a08342f7 100644 --- a/Documentation/translations/zh_CN/loongarch/index.rst +++ b/Documentation/translations/zh_CN/loongarch/index.rst @@ -14,6 +14,7 @@ LoongArch体系结构 :numbered: introduction + booting irq-chip-model features diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index eee9f857a986..896914e3a847 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -7213,14 +7213,13 @@ veto the transition. :Parameters: args[0] is the maximum poll time in nanoseconds :Returns: 0 on success; -1 on error -This capability overrides the kvm module parameter halt_poll_ns for the -target VM. - -VCPU polling allows a VCPU to poll for wakeup events instead of immediately -scheduling during guest halts. The maximum time a VCPU can spend polling is -controlled by the kvm module parameter halt_poll_ns. This capability allows -the maximum halt time to specified on a per-VM basis, effectively overriding -the module parameter for the target VM. +KVM_CAP_HALT_POLL overrides the kvm.halt_poll_ns module parameter to set the +maximum halt-polling time for all vCPUs in the target VM. This capability can +be invoked at any time and any number of times to dynamically change the +maximum halt-polling time. + +See Documentation/virt/kvm/halt-polling.rst for more information on halt +polling. 7.21 KVM_CAP_X86_USER_SPACE_MSR ------------------------------- diff --git a/Documentation/virt/kvm/x86/halt-polling.rst b/Documentation/virt/kvm/halt-polling.rst index 4922e4a15f18..3fae39b1a5ba 100644 --- a/Documentation/virt/kvm/x86/halt-polling.rst +++ b/Documentation/virt/kvm/halt-polling.rst @@ -119,6 +119,19 @@ These module parameters can be set from the debugfs files in: Note: that these module parameters are system wide values and are not able to be tuned on a per vm basis. +Any changes to these parameters will be picked up by new and existing vCPUs the +next time they halt, with the notable exception of VMs using KVM_CAP_HALT_POLL +(see next section). + +KVM_CAP_HALT_POLL +================= + +KVM_CAP_HALT_POLL is a VM capability that allows userspace to override halt_poll_ns +on a per-VM basis. VMs using KVM_CAP_HALT_POLL ignore halt_poll_ns completely (but +still obey halt_poll_ns_grow, halt_poll_ns_grow_start, and halt_poll_ns_shrink). + +See Documentation/virt/kvm/api.rst for more information on this capability. + Further Notes ============= diff --git a/Documentation/virt/kvm/index.rst b/Documentation/virt/kvm/index.rst index e0a2c74e1043..ad13ec55ddfe 100644 --- a/Documentation/virt/kvm/index.rst +++ b/Documentation/virt/kvm/index.rst @@ -17,4 +17,5 @@ KVM locking vcpu-requests + halt-polling review-checklist diff --git a/Documentation/virt/kvm/x86/index.rst b/Documentation/virt/kvm/x86/index.rst index 7ff588826b9f..9ece6b8dc817 100644 --- a/Documentation/virt/kvm/x86/index.rst +++ b/Documentation/virt/kvm/x86/index.rst @@ -10,7 +10,6 @@ KVM for x86 systems amd-memory-encryption cpuid errata - halt-polling hypercalls mmu msr diff --git a/MAINTAINERS b/MAINTAINERS index 1daadaa4d48b..886d3f69ee64 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5299,7 +5299,7 @@ M: Johannes Weiner <[email protected]> M: Michal Hocko <[email protected]> M: Roman Gushchin <[email protected]> M: Shakeel Butt <[email protected]> -R: Muchun Song <[email protected]> +R: Muchun Song <[email protected]> S: Maintained @@ -9439,7 +9439,7 @@ F: drivers/net/ethernet/huawei/hinic/ HUGETLB SUBSYSTEM M: Mike Kravetz <[email protected]> -M: Muchun Song <[email protected]> +M: Muchun Song <[email protected]> S: Maintained F: Documentation/ABI/testing/sysfs-kernel-mm-hugepages @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 1 SUBLEVEL = 0 -EXTRAVERSION = -rc8 +EXTRAVERSION = NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index 03d2e8544a4e..0fc9e6b8b05d 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -1270,10 +1270,10 @@ clocks = <&clks IMX7D_NAND_USDHC_BUS_RAWNAND_CLK>; }; - gpmi: nand-controller@33002000 { + gpmi: nand-controller@33002000{ compatible = "fsl,imx7d-gpmi-nand"; #address-cells = <1>; - #size-cells = <0>; + #size-cells = <1>; reg = <0x33002000 0x2000>, <0x33004000 0x4000>; reg-names = "gpmi-nand", "bch"; interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>; diff --git a/arch/arm/mach-at91/sama5.c b/arch/arm/mach-at91/sama5.c index 67ed68fbe3a5..bf2b5c6a18c6 100644 --- a/arch/arm/mach-at91/sama5.c +++ b/arch/arm/mach-at91/sama5.c @@ -26,7 +26,7 @@ static void sama5_l2c310_write_sec(unsigned long val, unsigned reg) static void __init sama5_secure_cache_init(void) { sam_secure_init(); - if (sam_linux_is_optee_available()) + if (IS_ENABLED(CONFIG_OUTER_CACHE) && sam_linux_is_optee_available()) outer_cache.write_sec = sama5_l2c310_write_sec; } diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 46cccd6bf705..de988cba9a4b 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -105,6 +105,19 @@ static inline bool is_write_fault(unsigned int fsr) return (fsr & FSR_WRITE) && !(fsr & FSR_CM); } +static inline bool is_translation_fault(unsigned int fsr) +{ + int fs = fsr_fs(fsr); +#ifdef CONFIG_ARM_LPAE + if ((fs & FS_MMU_NOLL_MASK) == FS_TRANS_NOLL) + return true; +#else + if (fs == FS_L1_TRANS || fs == FS_L2_TRANS) + return true; +#endif + return false; +} + static void die_kernel_fault(const char *msg, struct mm_struct *mm, unsigned long addr, unsigned int fsr, struct pt_regs *regs) @@ -140,7 +153,8 @@ __do_kernel_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr, if (addr < PAGE_SIZE) { msg = "NULL pointer dereference"; } else { - if (kfence_handle_page_fault(addr, is_write_fault(fsr), regs)) + if (is_translation_fault(fsr) && + kfence_handle_page_fault(addr, is_write_fault(fsr), regs)) return; msg = "paging request"; @@ -208,7 +222,7 @@ static inline bool is_permission_fault(unsigned int fsr) { int fs = fsr_fs(fsr); #ifdef CONFIG_ARM_LPAE - if ((fs & FS_PERM_NOLL_MASK) == FS_PERM_NOLL) + if ((fs & FS_MMU_NOLL_MASK) == FS_PERM_NOLL) return true; #else if (fs == FS_L1_PERM || fs == FS_L2_PERM) diff --git a/arch/arm/mm/fault.h b/arch/arm/mm/fault.h index 83b5ab32d7a4..54927ba1fa6e 100644 --- a/arch/arm/mm/fault.h +++ b/arch/arm/mm/fault.h @@ -14,8 +14,9 @@ #ifdef CONFIG_ARM_LPAE #define FSR_FS_AEA 17 +#define FS_TRANS_NOLL 0x4 #define FS_PERM_NOLL 0xC -#define FS_PERM_NOLL_MASK 0x3C +#define FS_MMU_NOLL_MASK 0x3C static inline int fsr_fs(unsigned int fsr) { @@ -23,8 +24,10 @@ static inline int fsr_fs(unsigned int fsr) } #else #define FSR_FS_AEA 22 -#define FS_L1_PERM 0xD -#define FS_L2_PERM 0xF +#define FS_L1_TRANS 0x5 +#define FS_L2_TRANS 0x7 +#define FS_L1_PERM 0xD +#define FS_L2_PERM 0xF static inline int fsr_fs(unsigned int fsr) { diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 3cb101e8cb29..5240f6acad64 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -36,7 +36,22 @@ void arch_dma_prep_coherent(struct page *page, size_t size) { unsigned long start = (unsigned long)page_address(page); - dcache_clean_poc(start, start + size); + /* + * The architecture only requires a clean to the PoC here in order to + * meet the requirements of the DMA API. However, some vendors (i.e. + * Qualcomm) abuse the DMA API for transferring buffers from the + * non-secure to the secure world, resetting the system if a non-secure + * access shows up after the buffer has been transferred: + * + * https://lore.kernel.org/r/[email protected] + * + * Using clean+invalidate appears to make this issue less likely, but + * the drivers themselves still need fixing as the CPU could issue a + * speculative read from the buffer via the linear mapping irrespective + * of the cache maintenance we use. Once the drivers are fixed, we can + * relax this to a clean operation. + */ + dcache_clean_inval_poc(start, start + size); } #ifdef CONFIG_IOMMU_DMA diff --git a/arch/loongarch/include/asm/irq.h b/arch/loongarch/include/asm/irq.h index 5332b1433f38..a115e8999c69 100644 --- a/arch/loongarch/include/asm/irq.h +++ b/arch/loongarch/include/asm/irq.h @@ -93,7 +93,7 @@ int liointc_acpi_init(struct irq_domain *parent, int eiointc_acpi_init(struct irq_domain *parent, struct acpi_madt_eio_pic *acpi_eiointc); -struct irq_domain *htvec_acpi_init(struct irq_domain *parent, +int htvec_acpi_init(struct irq_domain *parent, struct acpi_madt_ht_pic *acpi_htvec); int pch_lpc_acpi_init(struct irq_domain *parent, struct acpi_madt_lpc_pic *acpi_pchlpc); diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h index 3dd172d9ffea..d82687390b4a 100644 --- a/arch/loongarch/include/asm/smp.h +++ b/arch/loongarch/include/asm/smp.h @@ -78,16 +78,6 @@ extern void calculate_cpu_foreign_map(void); */ extern void show_ipi_list(struct seq_file *p, int prec); -/* - * This function sends a 'reschedule' IPI to another CPU. - * it goes straight through and wastes no time serializing - * anything. Worst case is that we lose a reschedule ... - */ -static inline void smp_send_reschedule(int cpu) -{ - loongson_send_ipi_single(cpu, SMP_RESCHEDULE); -} - static inline void arch_send_call_function_single_ipi(int cpu) { loongson_send_ipi_single(cpu, SMP_CALL_FUNCTION); diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c index 6ed72f7ff278..14508d429ffa 100644 --- a/arch/loongarch/kernel/smp.c +++ b/arch/loongarch/kernel/smp.c @@ -149,6 +149,17 @@ void loongson_send_ipi_mask(const struct cpumask *mask, unsigned int action) ipi_write_action(cpu_logical_map(i), (u32)action); } +/* + * This function sends a 'reschedule' IPI to another CPU. + * it goes straight through and wastes no time serializing + * anything. Worst case is that we lose a reschedule ... + */ +void smp_send_reschedule(int cpu) +{ + loongson_send_ipi_single(cpu, SMP_RESCHEDULE); +} +EXPORT_SYMBOL_GPL(smp_send_reschedule); + irqreturn_t loongson_ipi_interrupt(int irq, void *dev) { unsigned int action; diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S index d8ee8fbc8c67..58781c6e4191 100644 --- a/arch/loongarch/mm/tlbex.S +++ b/arch/loongarch/mm/tlbex.S @@ -10,6 +10,8 @@ #include <asm/regdef.h> #include <asm/stackframe.h> +#define INVTLB_ADDR_GFALSE_AND_ASID 5 + #define PTRS_PER_PGD_BITS (PAGE_SHIFT - 3) #define PTRS_PER_PUD_BITS (PAGE_SHIFT - 3) #define PTRS_PER_PMD_BITS (PAGE_SHIFT - 3) @@ -136,13 +138,10 @@ tlb_huge_update_load: ori t0, ra, _PAGE_VALID st.d t0, t1, 0 #endif - tlbsrch - addu16i.d t1, zero, -(CSR_TLBIDX_EHINV >> 16) - addi.d ra, t1, 0 - csrxchg ra, t1, LOONGARCH_CSR_TLBIDX - tlbwr - - csrxchg zero, t1, LOONGARCH_CSR_TLBIDX + csrrd ra, LOONGARCH_CSR_ASID + csrrd t1, LOONGARCH_CSR_BADV + andi ra, ra, CSR_ASID_ASID + invtlb INVTLB_ADDR_GFALSE_AND_ASID, ra, t1 /* * A huge PTE describes an area the size of the @@ -287,13 +286,11 @@ tlb_huge_update_store: ori t0, ra, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) st.d t0, t1, 0 #endif - tlbsrch - addu16i.d t1, zero, -(CSR_TLBIDX_EHINV >> 16) - addi.d ra, t1, 0 - csrxchg ra, t1, LOONGARCH_CSR_TLBIDX - tlbwr + csrrd ra, LOONGARCH_CSR_ASID + csrrd t1, LOONGARCH_CSR_BADV + andi ra, ra, CSR_ASID_ASID + invtlb INVTLB_ADDR_GFALSE_AND_ASID, ra, t1 - csrxchg zero, t1, LOONGARCH_CSR_TLBIDX /* * A huge PTE describes an area the size of the * configured huge page size. This is twice the @@ -436,6 +433,11 @@ tlb_huge_update_modify: ori t0, ra, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED) st.d t0, t1, 0 #endif + csrrd ra, LOONGARCH_CSR_ASID + csrrd t1, LOONGARCH_CSR_BADV + andi ra, ra, CSR_ASID_ASID + invtlb INVTLB_ADDR_GFALSE_AND_ASID, ra, t1 + /* * A huge PTE describes an area the size of the * configured huge page size. This is twice the @@ -466,7 +468,7 @@ tlb_huge_update_modify: addu16i.d t1, zero, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16)) csrxchg t1, t0, LOONGARCH_CSR_TLBIDX - tlbwr + tlbfill /* Reset default page size */ addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16) diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index a3a71d37cb9a..3f05507e444d 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -447,21 +447,18 @@ static void pseries_msi_ops_msi_free(struct irq_domain *domain, * RTAS can not disable one MSI at a time. It's all or nothing. Do it * at the end after all IRQs have been freed. */ -static void pseries_msi_domain_free_irqs(struct irq_domain *domain, - struct device *dev) +static void pseries_msi_post_free(struct irq_domain *domain, struct device *dev) { if (WARN_ON_ONCE(!dev_is_pci(dev))) return; - __msi_domain_free_irqs(domain, dev); - rtas_disable_msi(to_pci_dev(dev)); } static struct msi_domain_ops pseries_pci_msi_domain_ops = { .msi_prepare = pseries_msi_ops_prepare, .msi_free = pseries_msi_ops_msi_free, - .domain_free_irqs = pseries_msi_domain_free_irqs, + .msi_post_free = pseries_msi_post_free, }; static void pseries_msi_shutdown(struct irq_data *d) diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 94138f8f0c1c..ace2541ababd 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -546,8 +546,10 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_CEI)) scb_s->eca |= scb_o->eca & ECA_CEI; /* Epoch Extension */ - if (test_kvm_facility(vcpu->kvm, 139)) + if (test_kvm_facility(vcpu->kvm, 139)) { scb_s->ecd |= scb_o->ecd & ECD_MEF; + scb_s->epdx = scb_o->epdx; + } /* etoken */ if (test_kvm_facility(vcpu->kvm, 156)) diff --git a/arch/um/drivers/Kconfig b/arch/um/drivers/Kconfig index 5903e2b598aa..a4f0a19fbe14 100644 --- a/arch/um/drivers/Kconfig +++ b/arch/um/drivers/Kconfig @@ -381,7 +381,6 @@ config UML_PCI_OVER_VIRTIO select UML_IOMEM_EMULATION select UML_DMA_EMULATION select PCI_MSI - select PCI_MSI_IRQ_DOMAIN select PCI_LOCKLESS_CONFIG config UML_PCI_OVER_VIRTIO_DEVICE_ID diff --git a/arch/um/include/asm/pci.h b/arch/um/include/asm/pci.h index 34fe4921b5fa..238d2e7faff8 100644 --- a/arch/um/include/asm/pci.h +++ b/arch/um/include/asm/pci.h @@ -7,7 +7,7 @@ /* Generic PCI */ #include <asm-generic/pci.h> -#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN +#ifdef CONFIG_PCI_MSI /* * This is a bit of an annoying hack, and it assumes we only have * the virt-pci (if anything). Which is true, but still. diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 67745ceab0db..64f81a10bfc8 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1109,7 +1109,6 @@ config X86_LOCAL_APIC def_bool y depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI select IRQ_DOMAIN_HIERARCHY - select PCI_MSI_IRQ_DOMAIN if PCI_MSI config X86_IO_APIC def_bool y diff --git a/arch/x86/include/asm/hyperv_timer.h b/arch/x86/include/asm/hyperv_timer.h new file mode 100644 index 000000000000..388fa81b8f38 --- /dev/null +++ b/arch/x86/include/asm/hyperv_timer.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_HYPERV_TIMER_H +#define _ASM_X86_HYPERV_TIMER_H + +#include <asm/msr.h> + +#define hv_get_raw_timer() rdtsc_ordered() + +#endif diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index 7cc49432187f..7a2ed154a5e1 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -44,10 +44,6 @@ extern int irq_remapping_reenable(int); extern int irq_remap_enable_fault_handling(void); extern void panic_if_irq_remap(const char *msg); -/* Create PCI MSI/MSIx irqdomain, use @parent as the parent irqdomain. */ -extern struct irq_domain * -arch_create_remap_msi_irq_domain(struct irq_domain *par, const char *n, int id); - /* Get parent irqdomain for interrupt remapping irqdomain */ static inline struct irq_domain *arch_get_ir_parent_domain(void) { diff --git a/arch/x86/include/asm/irqdomain.h b/arch/x86/include/asm/irqdomain.h index 125c23b7bad3..30c325c235c0 100644 --- a/arch/x86/include/asm/irqdomain.h +++ b/arch/x86/include/asm/irqdomain.h @@ -7,9 +7,7 @@ #ifdef CONFIG_X86_LOCAL_APIC enum { - /* Allocate contiguous CPU vectors */ - X86_IRQ_ALLOC_CONTIGUOUS_VECTORS = 0x1, - X86_IRQ_ALLOC_LEGACY = 0x2, + X86_IRQ_ALLOC_LEGACY = 0x1, }; extern int x86_fwspec_is_ioapic(struct irq_fwspec *fwspec); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 61f0c206bff0..6d502f3efb0f 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -19,8 +19,6 @@ typedef int (*hyperv_fill_flush_list_func)( struct hv_guest_mapping_flush_list *flush, void *data); -#define hv_get_raw_timer() rdtsc_ordered() - void hyperv_vector_handler(struct pt_regs *regs); #if IS_ENABLED(CONFIG_HYPERV) diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h index d71c7e8b738d..935c6d470341 100644 --- a/arch/x86/include/asm/msi.h +++ b/arch/x86/include/asm/msi.h @@ -62,4 +62,10 @@ typedef struct x86_msi_addr_hi { struct msi_msg; u32 x86_msi_msg_get_destid(struct msi_msg *msg, bool extid); +#define X86_VECTOR_MSI_FLAGS_SUPPORTED \ + (MSI_GENERIC_FLAGS_MASK | MSI_FLAG_PCI_MSIX | MSI_FLAG_PCI_MSIX_ALLOC_DYN) + +#define X86_VECTOR_MSI_FLAGS_REQUIRED \ + (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS) + #endif /* _ASM_X86_MSI_H */ diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 736793d65bcb..b40c462b4af3 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -21,7 +21,7 @@ struct pci_sysdata { #ifdef CONFIG_X86_64 void *iommu; /* IOMMU private data */ #endif -#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN +#ifdef CONFIG_PCI_MSI void *fwnode; /* IRQ domain for MSI assignment */ #endif #if IS_ENABLED(CONFIG_VMD) @@ -52,7 +52,7 @@ static inline int pci_proc_domain(struct pci_bus *bus) } #endif -#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN +#ifdef CONFIG_PCI_MSI static inline void *_pci_root_bus_fwnode(struct pci_bus *bus) { return to_pci_sysdata(bus)->fwnode; @@ -92,6 +92,7 @@ void pcibios_scan_root(int bus); struct irq_routing_table *pcibios_get_irq_routing_table(void); int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq); +bool pci_dev_has_default_msi_parent_domain(struct pci_dev *dev); #define HAVE_PCI_MMAP #define arch_can_pci_mmap_wc() pat_enabled() diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 7517eb05bdc1..35d5b8fb18ef 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -142,70 +142,139 @@ msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force) return ret; } -/* - * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, - * which implement the MSI or MSI-X Capability Structure. +/** + * pci_dev_has_default_msi_parent_domain - Check whether the device has the default + * MSI parent domain associated + * @dev: Pointer to the PCI device */ -static struct irq_chip pci_msi_controller = { - .name = "PCI-MSI", - .irq_unmask = pci_msi_unmask_irq, - .irq_mask = pci_msi_mask_irq, - .irq_ack = irq_chip_ack_parent, - .irq_retrigger = irq_chip_retrigger_hierarchy, - .irq_set_affinity = msi_set_affinity, - .flags = IRQCHIP_SKIP_SET_WAKE | - IRQCHIP_AFFINITY_PRE_STARTUP, -}; +bool pci_dev_has_default_msi_parent_domain(struct pci_dev *dev) +{ + struct irq_domain *domain = dev_get_msi_domain(&dev->dev); -int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, - msi_alloc_info_t *arg) + if (!domain) + domain = dev_get_msi_domain(&dev->bus->dev); + if (!domain) + return false; + + return domain == x86_vector_domain; +} + +/** + * x86_msi_prepare - Setup of msi_alloc_info_t for allocations + * @domain: The domain for which this setup happens + * @dev: The device for which interrupts are allocated + * @nvec: The number of vectors to allocate + * @alloc: The allocation info structure to initialize + * + * This function is to be used for all types of MSI domains above the x86 + * vector domain and any intermediates. It is always invoked from the + * top level interrupt domain. The domain specific allocation + * functionality is determined via the @domain's bus token which allows to + * map the X86 specific allocation type. + */ +static int x86_msi_prepare(struct irq_domain *domain, struct device *dev, + int nvec, msi_alloc_info_t *alloc) { - init_irq_alloc_info(arg, NULL); - if (to_pci_dev(dev)->msix_enabled) { - arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSIX; - } else { - arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSI; - arg->flags |= X86_IRQ_ALLOC_CONTIGUOUS_VECTORS; + struct msi_domain_info *info = domain->host_data; + + init_irq_alloc_info(alloc, NULL); + + switch (info->bus_token) { + case DOMAIN_BUS_PCI_DEVICE_MSI: + alloc->type = X86_IRQ_ALLOC_TYPE_PCI_MSI; + return 0; + case DOMAIN_BUS_PCI_DEVICE_MSIX: + case DOMAIN_BUS_PCI_DEVICE_IMS: + alloc->type = X86_IRQ_ALLOC_TYPE_PCI_MSIX; + return 0; + default: + return -EINVAL; } - - return 0; } -EXPORT_SYMBOL_GPL(pci_msi_prepare); -static struct msi_domain_ops pci_msi_domain_ops = { - .msi_prepare = pci_msi_prepare, -}; +/** + * x86_init_dev_msi_info - Domain info setup for MSI domains + * @dev: The device for which the domain should be created + * @domain: The (root) domain providing this callback + * @real_parent: The real parent domain of the to initialize domain + * @info: The domain info for the to initialize domain + * + * This function is to be used for all types of MSI domains above the x86 + * vector domain and any intermediates. The domain specific functionality + * is determined via the @real_parent. + */ +static bool x86_init_dev_msi_info(struct device *dev, struct irq_domain *domain, + struct irq_domain *real_parent, struct msi_domain_info *info) +{ + const struct msi_parent_ops *pops = real_parent->msi_parent_ops; + + /* MSI parent domain specific settings */ + switch (real_parent->bus_token) { + case DOMAIN_BUS_ANY: + /* Only the vector domain can have the ANY token */ + if (WARN_ON_ONCE(domain != real_parent)) + return false; + info->chip->irq_set_affinity = msi_set_affinity; + /* See msi_set_affinity() for the gory details */ + info->flags |= MSI_FLAG_NOMASK_QUIRK; + break; + case DOMAIN_BUS_DMAR: + case DOMAIN_BUS_AMDVI: + break; + default: + WARN_ON_ONCE(1); + return false; + } + + /* Is the target supported? */ + switch(info->bus_token) { + case DOMAIN_BUS_PCI_DEVICE_MSI: + case DOMAIN_BUS_PCI_DEVICE_MSIX: + break; + case DOMAIN_BUS_PCI_DEVICE_IMS: + if (!(pops->supported_flags & MSI_FLAG_PCI_IMS)) + return false; + break; + default: + WARN_ON_ONCE(1); + return false; + } + + /* + * Mask out the domain specific MSI feature flags which are not + * supported by the real parent. + */ + info->flags &= pops->supported_flags; + /* Enforce the required flags */ + info->flags |= X86_VECTOR_MSI_FLAGS_REQUIRED; + + /* This is always invoked from the top level MSI domain! */ + info->ops->msi_prepare = x86_msi_prepare; + + info->chip->irq_ack = irq_chip_ack_parent; + info->chip->irq_retrigger = irq_chip_retrigger_hierarchy; + info->chip->flags |= IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP; -static struct msi_domain_info pci_msi_domain_info = { - .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_PCI_MSIX, - .ops = &pci_msi_domain_ops, - .chip = &pci_msi_controller, - .handler = handle_edge_irq, - .handler_name = "edge", + info->handler = handle_edge_irq; + info->handler_name = "edge"; + + return true; +} + +static const struct msi_parent_ops x86_vector_msi_parent_ops = { + .supported_flags = X86_VECTOR_MSI_FLAGS_SUPPORTED, + .init_dev_msi_info = x86_init_dev_msi_info, }; struct irq_domain * __init native_create_pci_msi_domain(void) { - struct fwnode_handle *fn; - struct irq_domain *d; - if (disable_apic) return NULL; - fn = irq_domain_alloc_named_fwnode("PCI-MSI"); - if (!fn) - return NULL; - - d = pci_msi_create_irq_domain(fn, &pci_msi_domain_info, - x86_vector_domain); - if (!d) { - irq_domain_free_fwnode(fn); - pr_warn("Failed to initialize PCI-MSI irqdomain.\n"); - } else { - d->flags |= IRQ_DOMAIN_MSI_NOMASK_QUIRK; - } - return d; + x86_vector_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT; + x86_vector_domain->msi_parent_ops = &x86_vector_msi_parent_ops; + return x86_vector_domain; } void __init x86_create_pci_msi_domain(void) @@ -213,41 +282,19 @@ void __init x86_create_pci_msi_domain(void) x86_pci_msi_default_domain = x86_init.irqs.create_pci_msi_domain(); } -#ifdef CONFIG_IRQ_REMAP -static struct irq_chip pci_msi_ir_controller = { - .name = "IR-PCI-MSI", - .irq_unmask = pci_msi_unmask_irq, - .irq_mask = pci_msi_mask_irq, - .irq_ack = irq_chip_ack_parent, - .irq_retrigger = irq_chip_retrigger_hierarchy, - .flags = IRQCHIP_SKIP_SET_WAKE | - IRQCHIP_AFFINITY_PRE_STARTUP, -}; - -static struct msi_domain_info pci_msi_ir_domain_info = { - .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX, - .ops = &pci_msi_domain_ops, - .chip = &pci_msi_ir_controller, - .handler = handle_edge_irq, - .handler_name = "edge", -}; - -struct irq_domain *arch_create_remap_msi_irq_domain(struct irq_domain *parent, - const char *name, int id) +/* Keep around for hyperV */ +int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, + msi_alloc_info_t *arg) { - struct fwnode_handle *fn; - struct irq_domain *d; + init_irq_alloc_info(arg, NULL); - fn = irq_domain_alloc_named_id_fwnode(name, id); - if (!fn) - return NULL; - d = pci_msi_create_irq_domain(fn, &pci_msi_ir_domain_info, parent); - if (!d) - irq_domain_free_fwnode(fn); - return d; + if (to_pci_dev(dev)->msix_enabled) + arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSIX; + else + arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSI; + return 0; } -#endif +EXPORT_SYMBOL_GPL(pci_msi_prepare); #ifdef CONFIG_DMAR_TABLE /* diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 3e6f6b448f6a..c1efebd27e6c 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -539,10 +539,6 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, if (disable_apic) return -ENXIO; - /* Currently vector allocator can't guarantee contiguous allocations */ - if ((info->flags & X86_IRQ_ALLOC_CONTIGUOUS_VECTORS) && nr_irqs > 1) - return -ENOSYS; - /* * Catch any attempt to touch the cascade interrupt on a PIC * equipped system. diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2835bd796639..69227f77b201 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10574,8 +10574,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; vcpu->mmio_needed = 0; r = 0; + goto out; } - goto out; } if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) { /* Page is swapped out. Do synthetic halt */ diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index 08e15774fb9f..ff30ceca2203 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -387,13 +387,15 @@ int acpi_pci_irq_enable(struct pci_dev *dev) u8 pin; int triggering = ACPI_LEVEL_SENSITIVE; /* - * On ARM systems with the GIC interrupt model, level interrupts + * On ARM systems with the GIC interrupt model, or LoongArch + * systems with the LPIC interrupt model, level interrupts * are always polarity high by specification; PCI legacy * IRQs lines are inverted before reaching the interrupt * controller and must therefore be considered active high * as default. */ - int polarity = acpi_irq_model == ACPI_IRQ_MODEL_GIC ? + int polarity = acpi_irq_model == ACPI_IRQ_MODEL_GIC || + acpi_irq_model == ACPI_IRQ_MODEL_LPIC ? ACPI_ACTIVE_HIGH : ACPI_ACTIVE_LOW; char *link = NULL; char link_desc[16]; diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index ddf17e2d266c..b9e336bacf17 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -109,7 +109,7 @@ struct clk *ahci_platform_find_clk(struct ahci_host_priv *hpriv, const char *con int i; for (i = 0; i < hpriv->n_clks; i++) { - if (!strcmp(hpriv->clks[i].id, con_id)) + if (hpriv->clks[i].id && !strcmp(hpriv->clks[i].id, con_id)) return hpriv->clks[i].clk; } diff --git a/drivers/base/Makefile b/drivers/base/Makefile index 83217d243c25..3079bfe53d04 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -22,7 +22,7 @@ obj-$(CONFIG_REGMAP) += regmap/ obj-$(CONFIG_SOC_BUS) += soc.o obj-$(CONFIG_PINCTRL) += pinctrl.o obj-$(CONFIG_DEV_COREDUMP) += devcoredump.o -obj-$(CONFIG_GENERIC_MSI_IRQ_DOMAIN) += platform-msi.o +obj-$(CONFIG_GENERIC_MSI_IRQ) += platform-msi.o obj-$(CONFIG_GENERIC_ARCH_TOPOLOGY) += arch_topology.o obj-$(CONFIG_GENERIC_ARCH_NUMA) += arch_numa.o obj-$(CONFIG_ACPI) += physical_location.o diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c index 12b044151298..5883e7634a2b 100644 --- a/drivers/base/platform-msi.c +++ b/drivers/base/platform-msi.c @@ -213,7 +213,7 @@ int platform_msi_domain_alloc_irqs(struct device *dev, unsigned int nvec, if (err) return err; - err = msi_domain_alloc_irqs(dev->msi.domain, dev, nvec); + err = msi_domain_alloc_irqs_range(dev, MSI_DEFAULT_DOMAIN, 0, nvec - 1); if (err) platform_msi_free_priv_data(dev); @@ -227,7 +227,7 @@ EXPORT_SYMBOL_GPL(platform_msi_domain_alloc_irqs); */ void platform_msi_domain_free_irqs(struct device *dev) { - msi_domain_free_irqs(dev->msi.domain, dev); + msi_domain_free_irqs_all(dev, MSI_DEFAULT_DOMAIN); platform_msi_free_priv_data(dev); } EXPORT_SYMBOL_GPL(platform_msi_domain_free_irqs); @@ -325,7 +325,7 @@ void platform_msi_device_domain_free(struct irq_domain *domain, unsigned int vir msi_lock_descs(data->dev); irq_domain_free_irqs_common(domain, virq, nr_irqs); - msi_free_msi_descs_range(data->dev, MSI_DESC_ALL, virq, virq + nr_irqs - 1); + msi_free_msi_descs_range(data->dev, virq, virq + nr_irqs - 1); msi_unlock_descs(data->dev); } diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 271963805a38..f05018988a17 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -2056,6 +2056,11 @@ static int btusb_setup_csr(struct hci_dev *hdev) rp = (struct hci_rp_read_local_version *)skb->data; + bt_dev_info(hdev, "CSR: Setting up dongle with HCI ver=%u rev=%04x; LMP ver=%u subver=%04x; manufacturer=%u", + le16_to_cpu(rp->hci_ver), le16_to_cpu(rp->hci_rev), + le16_to_cpu(rp->lmp_ver), le16_to_cpu(rp->lmp_subver), + le16_to_cpu(rp->manufacturer)); + /* Detect a wide host of Chinese controllers that aren't CSR. * * Known fake bcdDevices: 0x0100, 0x0134, 0x1915, 0x2520, 0x7558, 0x8891 @@ -2118,6 +2123,7 @@ static int btusb_setup_csr(struct hci_dev *hdev) * without these the controller will lock up. */ set_bit(HCI_QUIRK_BROKEN_STORED_LINK_KEY, &hdev->quirks); + set_bit(HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, &hdev->quirks); set_bit(HCI_QUIRK_BROKEN_FILTER_CLEAR_ALL, &hdev->quirks); set_bit(HCI_QUIRK_NO_SUSPEND_NOTIFIER, &hdev->quirks); diff --git a/drivers/bus/fsl-mc/Kconfig b/drivers/bus/fsl-mc/Kconfig index b1fd55901c50..9492342e7d13 100644 --- a/drivers/bus/fsl-mc/Kconfig +++ b/drivers/bus/fsl-mc/Kconfig @@ -8,7 +8,7 @@ config FSL_MC_BUS bool "QorIQ DPAA2 fsl-mc bus driver" depends on OF && (ARCH_LAYERSCAPE || (COMPILE_TEST && (ARM || ARM64 || X86_LOCAL_APIC || PPC))) - select GENERIC_MSI_IRQ_DOMAIN + select GENERIC_MSI_IRQ help Driver to enable the bus infrastructure for the QorIQ DPAA2 architecture. The fsl-mc bus driver handles discovery of diff --git a/drivers/bus/fsl-mc/dprc-driver.c b/drivers/bus/fsl-mc/dprc-driver.c index 5e70f9775a0e..4c84be378bf2 100644 --- a/drivers/bus/fsl-mc/dprc-driver.c +++ b/drivers/bus/fsl-mc/dprc-driver.c @@ -11,7 +11,6 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/interrupt.h> -#include <linux/msi.h> #include <linux/fsl/mc.h> #include "fsl-mc-private.h" diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c index 6143dbf31f31..774f307844b4 100644 --- a/drivers/bus/fsl-mc/fsl-mc-bus.c +++ b/drivers/bus/fsl-mc/fsl-mc-bus.c @@ -17,7 +17,6 @@ #include <linux/slab.h> #include <linux/limits.h> #include <linux/bitops.h> -#include <linux/msi.h> #include <linux/dma-mapping.h> #include <linux/acpi.h> #include <linux/iommu.h> diff --git a/drivers/bus/fsl-mc/fsl-mc-msi.c b/drivers/bus/fsl-mc/fsl-mc-msi.c index 0cfe859a4ac4..f3f8af9426c9 100644 --- a/drivers/bus/fsl-mc/fsl-mc-msi.c +++ b/drivers/bus/fsl-mc/fsl-mc-msi.c @@ -213,21 +213,8 @@ struct irq_domain *fsl_mc_find_msi_domain(struct device *dev) int fsl_mc_msi_domain_alloc_irqs(struct device *dev, unsigned int irq_count) { - struct irq_domain *msi_domain; - int error; - - msi_domain = dev_get_msi_domain(dev); - if (!msi_domain) - return -EINVAL; - - error = msi_setup_device_data(dev); - if (error) - return error; + int error = msi_setup_device_data(dev); - msi_lock_descs(dev); - if (msi_first_desc(dev, MSI_DESC_ALL)) - error = -EINVAL; - msi_unlock_descs(dev); if (error) return error; @@ -235,7 +222,7 @@ int fsl_mc_msi_domain_alloc_irqs(struct device *dev, unsigned int irq_count) * NOTE: Calling this function will trigger the invocation of the * its_fsl_mc_msi_prepare() callback */ - error = msi_domain_alloc_irqs(msi_domain, dev, irq_count); + error = msi_domain_alloc_irqs_range(dev, MSI_DEFAULT_DOMAIN, 0, irq_count - 1); if (error) dev_err(dev, "Failed to allocate IRQs\n"); @@ -244,11 +231,5 @@ int fsl_mc_msi_domain_alloc_irqs(struct device *dev, unsigned int irq_count) void fsl_mc_msi_domain_free_irqs(struct device *dev) { - struct irq_domain *msi_domain; - - msi_domain = dev_get_msi_domain(dev); - if (!msi_domain) - return; - - msi_domain_free_irqs(msi_domain, dev); + msi_domain_free_irqs_all(dev, MSI_DEFAULT_DOMAIN); } diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 7524b62a8870..25e111ab21f8 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -462,7 +462,7 @@ config MV_XOR_V2 select DMA_ENGINE select DMA_ENGINE_RAID select ASYNC_TX_ENABLE_CHANNEL_SWITCH - select GENERIC_MSI_IRQ_DOMAIN + select GENERIC_MSI_IRQ help Enable support for the Marvell version 2 XOR engine. diff --git a/drivers/dma/qcom/hidma.c b/drivers/dma/qcom/hidma.c index 210f1a9eb441..04d1c33afc12 100644 --- a/drivers/dma/qcom/hidma.c +++ b/drivers/dma/qcom/hidma.c @@ -610,7 +610,7 @@ static irqreturn_t hidma_chirq_handler(int chirq, void *arg) return hidma_ll_inthandler(chirq, lldev); } -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +#ifdef CONFIG_GENERIC_MSI_IRQ static irqreturn_t hidma_chirq_handler_msi(int chirq, void *arg) { struct hidma_lldev **lldevp = arg; @@ -671,7 +671,7 @@ static int hidma_sysfs_init(struct hidma_dev *dev) return device_create_file(dev->ddev.dev, dev->chid_attrs); } -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +#ifdef CONFIG_GENERIC_MSI_IRQ static void hidma_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg) { struct device *dev = msi_desc_to_dev(desc); @@ -687,7 +687,7 @@ static void hidma_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg) static void hidma_free_msis(struct hidma_dev *dmadev) { -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +#ifdef CONFIG_GENERIC_MSI_IRQ struct device *dev = dmadev->ddev.dev; int i, virq; @@ -704,7 +704,7 @@ static void hidma_free_msis(struct hidma_dev *dmadev) static int hidma_request_msi(struct hidma_dev *dmadev, struct platform_device *pdev) { -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +#ifdef CONFIG_GENERIC_MSI_IRQ int rc, i, virq; rc = platform_msi_domain_alloc_irqs(&pdev->dev, HIDMA_MSI_INTS, diff --git a/drivers/gpio/gpio-amd8111.c b/drivers/gpio/gpio-amd8111.c index 14e6b3e64add..6f3ded619c8b 100644 --- a/drivers/gpio/gpio-amd8111.c +++ b/drivers/gpio/gpio-amd8111.c @@ -226,7 +226,10 @@ found: ioport_unmap(gp.pm); goto out; } + return 0; + out: + pci_dev_put(pdev); return err; } @@ -234,6 +237,7 @@ static void __exit amd_gpio_exit(void) { gpiochip_remove(&gp.chip); ioport_unmap(gp.pm); + pci_dev_put(gp.pdev); } module_init(amd_gpio_init); diff --git a/drivers/gpio/gpio-rockchip.c b/drivers/gpio/gpio-rockchip.c index 870910bb9dd3..200e43a6f4b4 100644 --- a/drivers/gpio/gpio-rockchip.c +++ b/drivers/gpio/gpio-rockchip.c @@ -610,6 +610,7 @@ static int rockchip_gpiolib_register(struct rockchip_pin_bank *bank) return -ENODATA; pctldev = of_pinctrl_get(pctlnp); + of_node_put(pctlnp); if (!pctldev) return -ENODEV; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 4756ea08894f..a70522aef355 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -526,12 +526,13 @@ static int gpiochip_setup_dev(struct gpio_device *gdev) if (ret) return ret; + /* From this point, the .release() function cleans up gpio_device */ + gdev->dev.release = gpiodevice_release; + ret = gpiochip_sysfs_register(gdev); if (ret) goto err_remove_device; - /* From this point, the .release() function cleans up gpio_device */ - gdev->dev.release = gpiodevice_release; dev_dbg(&gdev->dev, "registered GPIOs %d to %d on %s\n", gdev->base, gdev->base + gdev->ngpio - 1, gdev->chip->label ? : "generic"); @@ -597,10 +598,10 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, struct fwnode_handle *fwnode = NULL; struct gpio_device *gdev; unsigned long flags; - int base = gc->base; unsigned int i; + u32 ngpios = 0; + int base = 0; int ret = 0; - u32 ngpios; if (gc->fwnode) fwnode = gc->fwnode; @@ -647,17 +648,12 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, else gdev->owner = THIS_MODULE; - gdev->descs = kcalloc(gc->ngpio, sizeof(gdev->descs[0]), GFP_KERNEL); - if (!gdev->descs) { - ret = -ENOMEM; - goto err_free_dev_name; - } - /* * Try the device properties if the driver didn't supply the number * of GPIO lines. */ - if (gc->ngpio == 0) { + ngpios = gc->ngpio; + if (ngpios == 0) { ret = device_property_read_u32(&gdev->dev, "ngpios", &ngpios); if (ret == -ENODATA) /* @@ -668,7 +664,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, */ ngpios = 0; else if (ret) - goto err_free_descs; + goto err_free_dev_name; gc->ngpio = ngpios; } @@ -676,13 +672,19 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, if (gc->ngpio == 0) { chip_err(gc, "tried to insert a GPIO chip with zero lines\n"); ret = -EINVAL; - goto err_free_descs; + goto err_free_dev_name; } if (gc->ngpio > FASTPATH_NGPIO) chip_warn(gc, "line cnt %u is greater than fast path cnt %u\n", gc->ngpio, FASTPATH_NGPIO); + gdev->descs = kcalloc(gc->ngpio, sizeof(*gdev->descs), GFP_KERNEL); + if (!gdev->descs) { + ret = -ENOMEM; + goto err_free_dev_name; + } + gdev->label = kstrdup_const(gc->label ?: "unknown", GFP_KERNEL); if (!gdev->label) { ret = -ENOMEM; @@ -701,11 +703,13 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, * it may be a pipe dream. It will not happen before we get rid * of the sysfs interface anyways. */ + base = gc->base; if (base < 0) { base = gpiochip_find_base(gc->ngpio); if (base < 0) { - ret = base; spin_unlock_irqrestore(&gpio_lock, flags); + ret = base; + base = 0; goto err_free_label; } /* @@ -816,6 +820,11 @@ err_remove_of_chip: err_free_gpiochip_mask: gpiochip_remove_pin_ranges(gc); gpiochip_free_valid_mask(gc); + if (gdev->dev.release) { + /* release() has been registered by gpiochip_setup_dev() */ + put_device(&gdev->dev); + goto err_print_message; + } err_remove_from_list: spin_lock_irqsave(&gpio_lock, flags); list_del(&gdev->list); @@ -829,13 +838,14 @@ err_free_dev_name: err_free_ida: ida_free(&gpio_ida, gdev->id); err_free_gdev: + kfree(gdev); +err_print_message: /* failures here can mean systems won't boot... */ if (ret != -EPROBE_DEFER) { pr_err("%s: GPIOs %d..%d (%s) failed to register, %d\n", __func__, - gdev->base, gdev->base + gdev->ngpio - 1, + base, base + (int)ngpios - 1, gc->label ? : "generic", ret); } - kfree(gdev); return ret; } EXPORT_SYMBOL_GPL(gpiochip_add_data_with_key); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 1122bd4eae98..4d780e4430e7 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -907,13 +907,13 @@ static void sdma_v4_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 se /** - * sdma_v4_0_gfx_stop - stop the gfx async dma engines + * sdma_v4_0_gfx_enable - enable the gfx async dma engines * * @adev: amdgpu_device pointer - * - * Stop the gfx async dma ring buffers (VEGA10). + * @enable: enable SDMA RB/IB + * control the gfx async dma ring buffers (VEGA10). */ -static void sdma_v4_0_gfx_stop(struct amdgpu_device *adev) +static void sdma_v4_0_gfx_enable(struct amdgpu_device *adev, bool enable) { u32 rb_cntl, ib_cntl; int i; @@ -922,10 +922,10 @@ static void sdma_v4_0_gfx_stop(struct amdgpu_device *adev) for (i = 0; i < adev->sdma.num_instances; i++) { rb_cntl = RREG32_SDMA(i, mmSDMA0_GFX_RB_CNTL); - rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 0); + rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, enable ? 1 : 0); WREG32_SDMA(i, mmSDMA0_GFX_RB_CNTL, rb_cntl); ib_cntl = RREG32_SDMA(i, mmSDMA0_GFX_IB_CNTL); - ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_ENABLE, 0); + ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_ENABLE, enable ? 1 : 0); WREG32_SDMA(i, mmSDMA0_GFX_IB_CNTL, ib_cntl); } } @@ -1044,7 +1044,7 @@ static void sdma_v4_0_enable(struct amdgpu_device *adev, bool enable) int i; if (!enable) { - sdma_v4_0_gfx_stop(adev); + sdma_v4_0_gfx_enable(adev, enable); sdma_v4_0_rlc_stop(adev); if (adev->sdma.has_page_queue) sdma_v4_0_page_stop(adev); @@ -1960,8 +1960,10 @@ static int sdma_v4_0_suspend(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; /* SMU saves SDMA state for us */ - if (adev->in_s0ix) + if (adev->in_s0ix) { + sdma_v4_0_gfx_enable(adev, false); return 0; + } return sdma_v4_0_hw_fini(adev); } @@ -1971,8 +1973,12 @@ static int sdma_v4_0_resume(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; /* SMU restores SDMA state for us */ - if (adev->in_s0ix) + if (adev->in_s0ix) { + sdma_v4_0_enable(adev, true); + sdma_v4_0_gfx_enable(adev, true); + amdgpu_ttm_set_buffer_funcs_status(adev, true); return 0; + } return sdma_v4_0_hw_init(adev); } diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h index 630f3395e90a..a0207a8f8756 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h @@ -1153,7 +1153,7 @@ struct vba_vars_st { double UrgBurstFactorLumaPre[DC__NUM_DPP__MAX]; double UrgBurstFactorChromaPre[DC__NUM_DPP__MAX]; bool NotUrgentLatencyHidingPre[DC__NUM_DPP__MAX]; - bool LinkCapacitySupport[DC__NUM_DPP__MAX]; + bool LinkCapacitySupport[DC__VOLTAGE_STATES]; bool VREADY_AT_OR_AFTER_VSYNC[DC__NUM_DPP__MAX]; unsigned int MIN_DST_Y_NEXT_START[DC__NUM_DPP__MAX]; unsigned int VFrontPorch[DC__NUM_DPP__MAX]; diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c index 40d8ca37f5bc..aa51c61a78c7 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c @@ -2720,6 +2720,9 @@ static u32 *dw_hdmi_bridge_atomic_get_output_bus_fmts(struct drm_bridge *bridge, * if supported. In any case the default RGB888 format is added */ + /* Default 8bit RGB fallback */ + output_fmts[i++] = MEDIA_BUS_FMT_RGB888_1X24; + if (max_bpc >= 16 && info->bpc == 16) { if (info->color_formats & DRM_COLOR_FORMAT_YCBCR444) output_fmts[i++] = MEDIA_BUS_FMT_YUV16_1X48; @@ -2753,9 +2756,6 @@ static u32 *dw_hdmi_bridge_atomic_get_output_bus_fmts(struct drm_bridge *bridge, if (info->color_formats & DRM_COLOR_FORMAT_YCBCR444) output_fmts[i++] = MEDIA_BUS_FMT_YUV8_1X24; - /* Default 8bit RGB fallback */ - output_fmts[i++] = MEDIA_BUS_FMT_RGB888_1X24; - *num_output_fmts = i; return output_fmts; diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 3c3561942eb6..eb24322df721 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -931,9 +931,9 @@ static void ti_sn_bridge_set_video_timings(struct ti_sn65dsi86 *pdata) &pdata->bridge.encoder->crtc->state->adjusted_mode; u8 hsync_polarity = 0, vsync_polarity = 0; - if (mode->flags & DRM_MODE_FLAG_PHSYNC) + if (mode->flags & DRM_MODE_FLAG_NHSYNC) hsync_polarity = CHA_HSYNC_POLARITY; - if (mode->flags & DRM_MODE_FLAG_PVSYNC) + if (mode->flags & DRM_MODE_FLAG_NVSYNC) vsync_polarity = CHA_VSYNC_POLARITY; ti_sn65dsi86_write_u16(pdata, SN_CHA_ACTIVE_LINE_LENGTH_LOW_REG, diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 35138f8a375c..b602cd72a120 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -571,12 +571,20 @@ static void drm_gem_shmem_vm_open(struct vm_area_struct *vma) { struct drm_gem_object *obj = vma->vm_private_data; struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); - int ret; WARN_ON(shmem->base.import_attach); - ret = drm_gem_shmem_get_pages(shmem); - WARN_ON_ONCE(ret != 0); + mutex_lock(&shmem->pages_lock); + + /* + * We should have already pinned the pages when the buffer was first + * mmap'd, vm_open() just grabs an additional reference for the new + * mm the vma is getting copied into (ie. on fork()). + */ + if (!WARN_ON_ONCE(!shmem->pages_use_count)) + shmem->pages_use_count++; + + mutex_unlock(&shmem->pages_lock); drm_gem_vm_open(vma); } @@ -622,10 +630,8 @@ int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct } ret = drm_gem_shmem_get_pages(shmem); - if (ret) { - drm_gem_vm_close(vma); + if (ret) return ret; - } vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c index 089046fa21be..50fa3df0bc0c 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c @@ -1085,21 +1085,21 @@ int vmw_mksstat_add_ioctl(struct drm_device *dev, void *data, reset_ppn_array(pdesc->strsPPNs, ARRAY_SIZE(pdesc->strsPPNs)); /* Pin mksGuestStat user pages and store those in the instance descriptor */ - nr_pinned_stat = pin_user_pages(arg->stat, num_pages_stat, FOLL_LONGTERM, pages_stat, NULL); + nr_pinned_stat = pin_user_pages_fast(arg->stat, num_pages_stat, FOLL_LONGTERM, pages_stat); if (num_pages_stat != nr_pinned_stat) goto err_pin_stat; for (i = 0; i < num_pages_stat; ++i) pdesc->statPPNs[i] = page_to_pfn(pages_stat[i]); - nr_pinned_info = pin_user_pages(arg->info, num_pages_info, FOLL_LONGTERM, pages_info, NULL); + nr_pinned_info = pin_user_pages_fast(arg->info, num_pages_info, FOLL_LONGTERM, pages_info); if (num_pages_info != nr_pinned_info) goto err_pin_info; for (i = 0; i < num_pages_info; ++i) pdesc->infoPPNs[i] = page_to_pfn(pages_info[i]); - nr_pinned_strs = pin_user_pages(arg->strs, num_pages_strs, FOLL_LONGTERM, pages_strs, NULL); + nr_pinned_strs = pin_user_pages_fast(arg->strs, num_pages_strs, FOLL_LONGTERM, pages_strs); if (num_pages_strs != nr_pinned_strs) goto err_pin_strs; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c index ecd3c2fc978b..9c79873f62f0 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c @@ -949,6 +949,10 @@ int vmw_kms_sou_init_display(struct vmw_private *dev_priv) struct drm_device *dev = &dev_priv->drm; int i, ret; + /* Screen objects won't work if GMR's aren't available */ + if (!dev_priv->has_gmr) + return -ENOSYS; + if (!(dev_priv->capabilities & SVGA_CAP_SCREEN_OBJECT_2)) { return -ENOSYS; } diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 9c1d31f63f85..bd47628da6be 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1315,6 +1315,9 @@ static s32 snto32(__u32 value, unsigned n) if (!value || !n) return 0; + if (n > 32) + n = 32; + switch (n) { case 8: return ((__s8)value); case 16: return ((__s16)value); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index dad953f66996..8f58c3c1bec3 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -274,6 +274,7 @@ #define USB_DEVICE_ID_CH_AXIS_295 0x001c #define USB_VENDOR_ID_CHERRY 0x046a +#define USB_DEVICE_ID_CHERRY_MOUSE_000C 0x000c #define USB_DEVICE_ID_CHERRY_CYMOTION 0x0023 #define USB_DEVICE_ID_CHERRY_CYMOTION_SOLAR 0x0027 @@ -917,6 +918,7 @@ #define USB_DEVICE_ID_MS_XBOX_ONE_S_CONTROLLER 0x02fd #define USB_DEVICE_ID_MS_PIXART_MOUSE 0x00cb #define USB_DEVICE_ID_8BITDO_SN30_PRO_PLUS 0x02e0 +#define USB_DEVICE_ID_MS_MOUSE_0783 0x0783 #define USB_VENDOR_ID_MOJO 0x8282 #define USB_DEVICE_ID_RETRO_ADAPTER 0x3201 @@ -1215,6 +1217,7 @@ #define USB_DEVICE_ID_SYNAPTICS_DELL_K15A 0x6e21 #define USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1002 0x73f4 #define USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1003 0x73f5 +#define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_017 0x73f6 #define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5 0x81a7 #define USB_VENDOR_ID_TEXAS_INSTRUMENTS 0x2047 @@ -1381,6 +1384,7 @@ #define USB_VENDOR_ID_PRIMAX 0x0461 #define USB_DEVICE_ID_PRIMAX_MOUSE_4D22 0x4d22 +#define USB_DEVICE_ID_PRIMAX_MOUSE_4E2A 0x4e2a #define USB_DEVICE_ID_PRIMAX_KEYBOARD 0x4e05 #define USB_DEVICE_ID_PRIMAX_REZEL 0x4e72 #define USB_DEVICE_ID_PRIMAX_PIXART_MOUSE_4D0F 0x4d0f diff --git a/drivers/hid/hid-ite.c b/drivers/hid/hid-ite.c index 430fa4f52ed3..75ebfcf31889 100644 --- a/drivers/hid/hid-ite.c +++ b/drivers/hid/hid-ite.c @@ -121,6 +121,11 @@ static const struct hid_device_id ite_devices[] = { USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_ACER_ONE_S1003), .driver_data = QUIRK_TOUCHPAD_ON_OFF_REPORT }, + /* ITE8910 USB kbd ctlr, with Synaptics touchpad connected to it. */ + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_SYNAPTICS, + USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_017), + .driver_data = QUIRK_TOUCHPAD_ON_OFF_REPORT }, { } }; MODULE_DEVICE_TABLE(hid, ite_devices); diff --git a/drivers/hid/hid-lg4ff.c b/drivers/hid/hid-lg4ff.c index 5e6a0cef2a06..e3fcf1353fb3 100644 --- a/drivers/hid/hid-lg4ff.c +++ b/drivers/hid/hid-lg4ff.c @@ -872,6 +872,12 @@ static ssize_t lg4ff_alternate_modes_store(struct device *dev, struct device_att return -ENOMEM; i = strlen(lbuf); + + if (i == 0) { + kfree(lbuf); + return -EINVAL; + } + if (lbuf[i-1] == '\n') { if (i == 1) { kfree(lbuf); diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index 71a9c258a20b..8a2aac18dcc5 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -4269,21 +4269,6 @@ static void hidpp_remove(struct hid_device *hdev) mutex_destroy(&hidpp->send_mutex); } -static const struct hid_device_id unhandled_hidpp_devices[] = { - /* Logitech Harmony Adapter for PS3, handled in hid-sony */ - { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_HARMONY_PS3) }, - /* Handled in hid-generic */ - { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_DINOVO_EDGE_KBD) }, - {} -}; - -static bool hidpp_match(struct hid_device *hdev, - bool ignore_special_driver) -{ - /* Refuse to handle devices handled by other HID drivers */ - return !hid_match_id(hdev, unhandled_hidpp_devices); -} - #define LDJ_DEVICE(product) \ HID_DEVICE(BUS_USB, HID_GROUP_LOGITECH_DJ_DEVICE, \ USB_VENDOR_ID_LOGITECH, (product)) @@ -4367,9 +4352,15 @@ static const struct hid_device_id hidpp_devices[] = { { /* MX5500 keyboard over Bluetooth */ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb30b), .driver_data = HIDPP_QUIRK_HIDPP_CONSUMER_VENDOR_KEYS }, - - { /* And try to enable HID++ for all the Logitech Bluetooth devices */ - HID_DEVICE(BUS_BLUETOOTH, HID_GROUP_ANY, USB_VENDOR_ID_LOGITECH, HID_ANY_ID) }, + { /* M-RCQ142 V470 Cordless Laser Mouse over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb008) }, + { /* MX Master mouse over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb012) }, + { /* MX Ergo trackball over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb01d) }, + { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb01e) }, + { /* MX Master 3 mouse over Bluetooth */ + HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, 0xb023) }, {} }; @@ -4383,7 +4374,6 @@ static const struct hid_usage_id hidpp_usages[] = { static struct hid_driver hidpp_driver = { .name = "logitech-hidpp-device", .id_table = hidpp_devices, - .match = hidpp_match, .report_fixup = hidpp_report_fixup, .probe = hidpp_probe, .remove = hidpp_remove, diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 50e1c717fc0a..0e9702c7f7d6 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -54,6 +54,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FLIGHT_SIM_YOKE), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_PRO_PEDALS), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_PRO_THROTTLE), HID_QUIRK_NOGET }, + { HID_USB_DEVICE(USB_VENDOR_ID_CHERRY, USB_DEVICE_ID_CHERRY_MOUSE_000C), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB_RAPIDFIRE), HID_QUIRK_NO_INIT_REPORTS | HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K70RGB), HID_QUIRK_NO_INIT_REPORTS }, @@ -122,6 +123,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C05A), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C06A), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_MCS, USB_DEVICE_ID_MCS_GAMEPADBLOCK), HID_QUIRK_MULTI_INPUT }, + { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_MOUSE_0783), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PIXART_MOUSE), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_POWER_COVER), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_SURFACE3_COVER), HID_QUIRK_NO_INIT_REPORTS }, @@ -146,6 +148,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_PIXART, USB_DEVICE_ID_PIXART_OPTICAL_TOUCH_SCREEN), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_PIXART, USB_DEVICE_ID_PIXART_USB_OPTICAL_MOUSE), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_PRIMAX, USB_DEVICE_ID_PRIMAX_MOUSE_4D22), HID_QUIRK_ALWAYS_POLL }, + { HID_USB_DEVICE(USB_VENDOR_ID_PRIMAX, USB_DEVICE_ID_PRIMAX_MOUSE_4E2A), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_PRIMAX, USB_DEVICE_ID_PRIMAX_PIXART_MOUSE_4D0F), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_PRIMAX, USB_DEVICE_ID_PRIMAX_PIXART_MOUSE_4D65), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_PRIMAX, USB_DEVICE_ID_PRIMAX_PIXART_MOUSE_4E22), HID_QUIRK_ALWAYS_POLL }, diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c index 0fbc408c2607..7fa6fe04f1b2 100644 --- a/drivers/hid/hid-uclogic-core.c +++ b/drivers/hid/hid-uclogic-core.c @@ -192,6 +192,7 @@ static int uclogic_probe(struct hid_device *hdev, * than the pen, so use QUIRK_MULTI_INPUT for all tablets. */ hdev->quirks |= HID_QUIRK_MULTI_INPUT; + hdev->quirks |= HID_QUIRK_HIDINPUT_FORCE; /* Allocate and assign driver data */ drvdata = devm_kzalloc(&hdev->dev, sizeof(*drvdata), GFP_KERNEL); diff --git a/drivers/hid/hid-uclogic-rdesc.c b/drivers/hid/hid-uclogic-rdesc.c index 4bd54c4fb5b0..6b73eb0df6bd 100644 --- a/drivers/hid/hid-uclogic-rdesc.c +++ b/drivers/hid/hid-uclogic-rdesc.c @@ -1193,7 +1193,7 @@ __u8 *uclogic_rdesc_template_apply(const __u8 *template_ptr, p[sizeof(btn_head)] < param_num) { v = param_list[p[sizeof(btn_head)]]; put_unaligned((__u8)0x2A, p); /* Usage Maximum */ - put_unaligned_le16((__force u16)cpu_to_le16(v), p + 1); + put_unaligned((__force u16)cpu_to_le16(v), (s16 *)(p + 1)); p += sizeof(btn_head) + 1; } else { p++; diff --git a/drivers/hid/i2c-hid/Kconfig b/drivers/hid/i2c-hid/Kconfig index 5273ee2bb134..d65abe65ce73 100644 --- a/drivers/hid/i2c-hid/Kconfig +++ b/drivers/hid/i2c-hid/Kconfig @@ -66,6 +66,6 @@ endmenu config I2C_HID_CORE tristate - default y if I2C_HID_ACPI=y || I2C_HID_OF=y || I2C_HID_OF_GOODIX=y - default m if I2C_HID_ACPI=m || I2C_HID_OF=m || I2C_HID_OF_GOODIX=m + default y if I2C_HID_ACPI=y || I2C_HID_OF=y || I2C_HID_OF_ELAN=y || I2C_HID_OF_GOODIX=y + default m if I2C_HID_ACPI=m || I2C_HID_OF=m || I2C_HID_OF_ELAN=m || I2C_HID_OF_GOODIX=m select HID diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index a55b641b70f6..ff7994ef9b74 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -37,6 +37,7 @@ #include <linux/dma-map-ops.h> #include <linux/pci.h> #include <clocksource/hyperv_timer.h> +#include <asm/mshyperv.h> #include "hyperv_vmbus.h" struct vmbus_dynid { diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index dc5f7a156ff5..8eaf9b72a995 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -389,7 +389,7 @@ config ARM_SMMU_V3 depends on ARM64 select IOMMU_API select IOMMU_IO_PGTABLE_LPAE - select GENERIC_MSI_IRQ_DOMAIN + select GENERIC_MSI_IRQ help Support for implementations of the ARM System MMU architecture version 3 providing translation support to a PCIe root complex. diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 1d0a70c85333..3d684190b4d5 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -734,7 +734,6 @@ struct amd_iommu { u8 max_counters; #ifdef CONFIG_IRQ_REMAP struct irq_domain *ir_domain; - struct irq_domain *msi_domain; struct amd_irte_ops *irte_ops; #endif diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index d3b39d0416fa..4d28967f910d 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -812,10 +812,10 @@ static void amd_iommu_set_pci_msi_domain(struct device *dev, struct amd_iommu *iommu) { if (!irq_remapping_enabled || !dev_is_pci(dev) || - pci_dev_has_special_msi_domain(to_pci_dev(dev))) + !pci_dev_has_default_msi_parent_domain(to_pci_dev(dev))) return; - dev_set_msi_domain(dev, iommu->msi_domain); + dev_set_msi_domain(dev, iommu->ir_domain); } #else /* CONFIG_IRQ_REMAP */ @@ -3294,17 +3294,9 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq, if (!info) return -EINVAL; - if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_PCI_MSI && - info->type != X86_IRQ_ALLOC_TYPE_PCI_MSIX) + if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_PCI_MSI) return -EINVAL; - /* - * With IRQ remapping enabled, don't need contiguous CPU vectors - * to support multiple MSI interrupts. - */ - if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI) - info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS; - sbdf = get_devid(info); if (sbdf < 0) return -EINVAL; @@ -3656,6 +3648,21 @@ static struct irq_chip amd_ir_chip = { .irq_compose_msi_msg = ir_compose_msi_msg, }; +static const struct msi_parent_ops amdvi_msi_parent_ops = { + .supported_flags = X86_VECTOR_MSI_FLAGS_SUPPORTED | + MSI_FLAG_MULTI_PCI_MSI | + MSI_FLAG_PCI_IMS, + .prefix = "IR-", + .init_dev_msi_info = msi_parent_init_dev_msi_info, +}; + +static const struct msi_parent_ops virt_amdvi_msi_parent_ops = { + .supported_flags = X86_VECTOR_MSI_FLAGS_SUPPORTED | + MSI_FLAG_MULTI_PCI_MSI, + .prefix = "vIR-", + .init_dev_msi_info = msi_parent_init_dev_msi_info, +}; + int amd_iommu_create_irq_domain(struct amd_iommu *iommu) { struct fwnode_handle *fn; @@ -3663,16 +3670,21 @@ int amd_iommu_create_irq_domain(struct amd_iommu *iommu) fn = irq_domain_alloc_named_id_fwnode("AMD-IR", iommu->index); if (!fn) return -ENOMEM; - iommu->ir_domain = irq_domain_create_tree(fn, &amd_ir_domain_ops, iommu); + iommu->ir_domain = irq_domain_create_hierarchy(arch_get_ir_parent_domain(), 0, 0, + fn, &amd_ir_domain_ops, iommu); if (!iommu->ir_domain) { irq_domain_free_fwnode(fn); return -ENOMEM; } - iommu->ir_domain->parent = arch_get_ir_parent_domain(); - iommu->msi_domain = arch_create_remap_msi_irq_domain(iommu->ir_domain, - "AMD-IR-MSI", - iommu->index); + irq_domain_update_bus_token(iommu->ir_domain, DOMAIN_BUS_AMDVI); + iommu->ir_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT; + + if (amd_iommu_np_cache) + iommu->ir_domain->msi_parent_ops = &virt_amdvi_msi_parent_ops; + else + iommu->ir_domain->msi_parent_ops = &amdvi_msi_parent_ops; + return 0; } diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 5287efe247b1..644ca49e8cf8 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1402,7 +1402,7 @@ static void domain_update_iotlb(struct dmar_domain *domain) * check because it applies only to the built-in QAT devices and it doesn't * grant additional privileges. */ -#define BUGGY_QAT_DEVID_MASK 0x494c +#define BUGGY_QAT_DEVID_MASK 0x4940 static bool dev_needs_extra_dtlb_flush(struct pci_dev *pdev) { if (pdev->vendor != PCI_VENDOR_ID_INTEL) diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index db9df7c3790c..b3d82d7093e6 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -600,7 +600,6 @@ struct intel_iommu { #ifdef CONFIG_IRQ_REMAP struct ir_table *ir_table; /* Interrupt remapping info */ struct irq_domain *ir_domain; - struct irq_domain *ir_msi_domain; #endif struct iommu_device iommu; /* IOMMU core code handle */ int node; diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index 5962bb5027d0..a723f53ba472 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -82,6 +82,7 @@ static const struct irq_domain_ops intel_ir_domain_ops; static void iommu_disable_irq_remapping(struct intel_iommu *iommu); static int __init parse_ioapics_under_ir(void); +static const struct msi_parent_ops dmar_msi_parent_ops, virt_dmar_msi_parent_ops; static bool ir_pre_enabled(struct intel_iommu *iommu) { @@ -230,7 +231,7 @@ static struct irq_domain *map_dev_to_ir(struct pci_dev *dev) { struct dmar_drhd_unit *drhd = dmar_find_matched_drhd_unit(dev); - return drhd ? drhd->iommu->ir_msi_domain : NULL; + return drhd ? drhd->iommu->ir_domain : NULL; } static int clear_entries(struct irq_2_iommu *irq_iommu) @@ -573,10 +574,14 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu) pr_err("IR%d: failed to allocate irqdomain\n", iommu->seq_id); goto out_free_fwnode; } - iommu->ir_msi_domain = - arch_create_remap_msi_irq_domain(iommu->ir_domain, - "INTEL-IR-MSI", - iommu->seq_id); + + irq_domain_update_bus_token(iommu->ir_domain, DOMAIN_BUS_DMAR); + iommu->ir_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT; + + if (cap_caching_mode(iommu->cap)) + iommu->ir_domain->msi_parent_ops = &virt_dmar_msi_parent_ops; + else + iommu->ir_domain->msi_parent_ops = &dmar_msi_parent_ops; ir_table->base = page_address(pages); ir_table->bitmap = bitmap; @@ -620,9 +625,6 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu) return 0; out_free_ir_domain: - if (iommu->ir_msi_domain) - irq_domain_remove(iommu->ir_msi_domain); - iommu->ir_msi_domain = NULL; irq_domain_remove(iommu->ir_domain); iommu->ir_domain = NULL; out_free_fwnode: @@ -644,13 +646,6 @@ static void intel_teardown_irq_remapping(struct intel_iommu *iommu) struct fwnode_handle *fn; if (iommu && iommu->ir_table) { - if (iommu->ir_msi_domain) { - fn = iommu->ir_msi_domain->fwnode; - - irq_domain_remove(iommu->ir_msi_domain); - irq_domain_free_fwnode(fn); - iommu->ir_msi_domain = NULL; - } if (iommu->ir_domain) { fn = iommu->ir_domain->fwnode; @@ -1107,7 +1102,7 @@ error: */ void intel_irq_remap_add_device(struct dmar_pci_notify_info *info) { - if (!irq_remapping_enabled || pci_dev_has_special_msi_domain(info->dev)) + if (!irq_remapping_enabled || !pci_dev_has_default_msi_parent_domain(info->dev)) return; dev_set_msi_domain(&info->dev->dev, map_dev_to_ir(info->dev)); @@ -1334,17 +1329,9 @@ static int intel_irq_remapping_alloc(struct irq_domain *domain, if (!info || !iommu) return -EINVAL; - if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_PCI_MSI && - info->type != X86_IRQ_ALLOC_TYPE_PCI_MSIX) + if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_PCI_MSI) return -EINVAL; - /* - * With IRQ remapping enabled, don't need contiguous CPU vectors - * to support multiple MSI interrupts. - */ - if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI) - info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS; - ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg); if (ret < 0) return ret; @@ -1445,6 +1432,21 @@ static const struct irq_domain_ops intel_ir_domain_ops = { .deactivate = intel_irq_remapping_deactivate, }; +static const struct msi_parent_ops dmar_msi_parent_ops = { + .supported_flags = X86_VECTOR_MSI_FLAGS_SUPPORTED | + MSI_FLAG_MULTI_PCI_MSI | + MSI_FLAG_PCI_IMS, + .prefix = "IR-", + .init_dev_msi_info = msi_parent_init_dev_msi_info, +}; + +static const struct msi_parent_ops virt_dmar_msi_parent_ops = { + .supported_flags = X86_VECTOR_MSI_FLAGS_SUPPORTED | + MSI_FLAG_MULTI_PCI_MSI, + .prefix = "vIR-", + .init_dev_msi_info = msi_parent_init_dev_msi_info, +}; + /* * Support of Interrupt Remapping Unit Hotplug */ diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c index 5696314ae69e..00d98f08732f 100644 --- a/drivers/iommu/of_iommu.c +++ b/drivers/iommu/of_iommu.c @@ -9,7 +9,6 @@ #include <linux/iommu.h> #include <linux/limits.h> #include <linux/module.h> -#include <linux/msi.h> #include <linux/of.h> #include <linux/of_iommu.h> #include <linux/of_pci.h> diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 7ef9f5e696d3..d07568a2c539 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -38,7 +38,7 @@ config ARM_GIC_V3 config ARM_GIC_V3_ITS bool - select GENERIC_MSI_IRQ_DOMAIN + select GENERIC_MSI_IRQ default ARM_GIC_V3 config ARM_GIC_V3_ITS_PCI @@ -86,7 +86,7 @@ config ALPINE_MSI config AL_FIC bool "Amazon's Annapurna Labs Fabric Interrupt Controller" - depends on OF || COMPILE_TEST + depends on OF select GENERIC_IRQ_CHIP select IRQ_DOMAIN help @@ -375,7 +375,7 @@ config MVEBU_ICU config MVEBU_ODMI bool - select GENERIC_MSI_IRQ_DOMAIN + select GENERIC_MSI_IRQ config MVEBU_PIC bool @@ -488,7 +488,7 @@ config IMX_MU_MSI default m if ARCH_MXC select IRQ_DOMAIN select IRQ_DOMAIN_HIERARCHY - select GENERIC_MSI_IRQ_DOMAIN + select GENERIC_MSI_IRQ help Provide a driver for the i.MX Messaging Unit block used as a CPU-to-CPU MSI controller. This requires a specially crafted DT @@ -576,6 +576,7 @@ config IRQ_LOONGARCH_CPU select GENERIC_IRQ_CHIP select IRQ_DOMAIN select GENERIC_IRQ_EFFECTIVE_AFF_MASK + select LOONGSON_HTVEC select LOONGSON_LIOINTC select LOONGSON_EIOINTC select LOONGSON_PCH_PIC diff --git a/drivers/irqchip/irq-apple-aic.c b/drivers/irqchip/irq-apple-aic.c index 1c2813ad8bbe..ae3437f03e6c 100644 --- a/drivers/irqchip/irq-apple-aic.c +++ b/drivers/irqchip/irq-apple-aic.c @@ -248,14 +248,14 @@ struct aic_info { bool fast_ipi; }; -static const struct aic_info aic1_info = { +static const struct aic_info aic1_info __initconst = { .version = 1, .event = AIC_EVENT, .target_cpu = AIC_TARGET_CPU, }; -static const struct aic_info aic1_fipi_info = { +static const struct aic_info aic1_fipi_info __initconst = { .version = 1, .event = AIC_EVENT, @@ -264,7 +264,7 @@ static const struct aic_info aic1_fipi_info = { .fast_ipi = true, }; -static const struct aic_info aic2_info = { +static const struct aic_info aic2_info __initconst = { .version = 2, .irq_cfg = AIC2_IRQ_CFG, diff --git a/drivers/irqchip/irq-gic-pm.c b/drivers/irqchip/irq-gic-pm.c index b60e1853593f..3989d16f997b 100644 --- a/drivers/irqchip/irq-gic-pm.c +++ b/drivers/irqchip/irq-gic-pm.c @@ -102,7 +102,7 @@ static int gic_probe(struct platform_device *pdev) pm_runtime_enable(dev); - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) goto rpm_disable; diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c index 6e1ac330d7a6..f4d7eeb13951 100644 --- a/drivers/irqchip/irq-gic-v2m.c +++ b/drivers/irqchip/irq-gic-v2m.c @@ -24,6 +24,7 @@ #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/irqchip/arm-gic.h> +#include <linux/irqchip/arm-gic-common.h> /* * MSI_TYPER: @@ -262,7 +263,7 @@ static struct msi_domain_info gicv2m_pmsi_domain_info = { .chip = &gicv2m_pmsi_irq_chip, }; -static void gicv2m_teardown(void) +static void __init gicv2m_teardown(void) { struct v2m_data *v2m, *tmp; @@ -277,7 +278,7 @@ static void gicv2m_teardown(void) } } -static int gicv2m_allocate_domains(struct irq_domain *parent) +static __init int gicv2m_allocate_domains(struct irq_domain *parent) { struct irq_domain *inner_domain, *pci_domain, *plat_domain; struct v2m_data *v2m; @@ -404,7 +405,7 @@ err_free_v2m: return ret; } -static const struct of_device_id gicv2m_device_id[] = { +static __initconst struct of_device_id gicv2m_device_id[] = { { .compatible = "arm,gic-v2m-frame", }, {}, }; @@ -454,7 +455,7 @@ static int __init gicv2m_of_init(struct fwnode_handle *parent_handle, #ifdef CONFIG_ACPI static int acpi_num_msi; -static struct fwnode_handle *gicv2m_get_fwnode(struct device *dev) +static __init struct fwnode_handle *gicv2m_get_fwnode(struct device *dev) { struct v2m_data *data; @@ -469,7 +470,7 @@ static struct fwnode_handle *gicv2m_get_fwnode(struct device *dev) return data->fwnode; } -static bool acpi_check_amazon_graviton_quirks(void) +static __init bool acpi_check_amazon_graviton_quirks(void) { static struct acpi_table_madt *madt; acpi_status status; diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 34d58567b78d..997104d4338e 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -12,6 +12,7 @@ #include <linux/delay.h> #include <linux/interrupt.h> #include <linux/irqdomain.h> +#include <linux/kstrtox.h> #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_irq.h> @@ -1171,7 +1172,7 @@ static bool gicv3_nolpi; static int __init gicv3_nolpi_cfg(char *buf) { - return strtobool(buf, &gicv3_nolpi); + return kstrtobool(buf, &gicv3_nolpi); } early_param("irqchip.gicv3_nolpi", gicv3_nolpi_cfg); diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 4c7bae0ec8f9..210bc2f4d555 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -19,6 +19,7 @@ */ #include <linux/init.h> #include <linux/kernel.h> +#include <linux/kstrtox.h> #include <linux/err.h> #include <linux/module.h> #include <linux/list.h> @@ -401,8 +402,8 @@ static void gic_irq_print_chip(struct irq_data *d, struct seq_file *p) { struct gic_chip_data *gic = irq_data_get_irq_chip_data(d); - if (gic->domain->dev) - seq_printf(p, gic->domain->dev->of_node->name); + if (gic->domain->pm_dev) + seq_printf(p, gic->domain->pm_dev->of_node->name); else seq_printf(p, "GIC-%d", (int)(gic - &gic_data[0])); } @@ -1332,7 +1333,7 @@ static bool gicv2_force_probe; static int __init gicv2_force_probe_cfg(char *buf) { - return strtobool(buf, &gicv2_force_probe); + return kstrtobool(buf, &gicv2_force_probe); } early_param("irqchip.gicv2_force_probe", gicv2_force_probe_cfg); diff --git a/drivers/irqchip/irq-loongarch-cpu.c b/drivers/irqchip/irq-loongarch-cpu.c index 741612ba6a52..9d8f2c406043 100644 --- a/drivers/irqchip/irq-loongarch-cpu.c +++ b/drivers/irqchip/irq-loongarch-cpu.c @@ -92,18 +92,34 @@ static const struct irq_domain_ops loongarch_cpu_intc_irq_domain_ops = { .xlate = irq_domain_xlate_onecell, }; -static int __init -liointc_parse_madt(union acpi_subtable_headers *header, - const unsigned long end) +#ifdef CONFIG_OF +static int __init cpuintc_of_init(struct device_node *of_node, + struct device_node *parent) +{ + cpuintc_handle = of_node_to_fwnode(of_node); + + irq_domain = irq_domain_create_linear(cpuintc_handle, EXCCODE_INT_NUM, + &loongarch_cpu_intc_irq_domain_ops, NULL); + if (!irq_domain) + panic("Failed to add irqdomain for loongarch CPU"); + + set_handle_irq(&handle_cpu_irq); + + return 0; +} +IRQCHIP_DECLARE(cpu_intc, "loongson,cpu-interrupt-controller", cpuintc_of_init); +#endif + +static int __init liointc_parse_madt(union acpi_subtable_headers *header, + const unsigned long end) { struct acpi_madt_lio_pic *liointc_entry = (struct acpi_madt_lio_pic *)header; return liointc_acpi_init(irq_domain, liointc_entry); } -static int __init -eiointc_parse_madt(union acpi_subtable_headers *header, - const unsigned long end) +static int __init eiointc_parse_madt(union acpi_subtable_headers *header, + const unsigned long end) { struct acpi_madt_eio_pic *eiointc_entry = (struct acpi_madt_eio_pic *)header; @@ -112,16 +128,24 @@ eiointc_parse_madt(union acpi_subtable_headers *header, static int __init acpi_cascade_irqdomain_init(void) { - acpi_table_parse_madt(ACPI_MADT_TYPE_LIO_PIC, - liointc_parse_madt, 0); - acpi_table_parse_madt(ACPI_MADT_TYPE_EIO_PIC, - eiointc_parse_madt, 0); + int r; + + r = acpi_table_parse_madt(ACPI_MADT_TYPE_LIO_PIC, liointc_parse_madt, 0); + if (r < 0) + return r; + + r = acpi_table_parse_madt(ACPI_MADT_TYPE_EIO_PIC, eiointc_parse_madt, 0); + if (r < 0) + return r; + return 0; } static int __init cpuintc_acpi_init(union acpi_subtable_headers *header, const unsigned long end) { + int ret; + if (irq_domain) return 0; @@ -139,9 +163,9 @@ static int __init cpuintc_acpi_init(union acpi_subtable_headers *header, set_handle_irq(&handle_cpu_irq); acpi_set_irq_model(ACPI_IRQ_MODEL_LPIC, lpic_get_gsi_domain_id); acpi_set_gsi_to_irq_fallback(lpic_gsi_to_irq); - acpi_cascade_irqdomain_init(); + ret = acpi_cascade_irqdomain_init(); - return 0; + return ret; } IRQCHIP_ACPI_DECLARE(cpuintc_v1, ACPI_MADT_TYPE_CORE_PIC, diff --git a/drivers/irqchip/irq-loongson-eiointc.c b/drivers/irqchip/irq-loongson-eiointc.c index 16e9af8d8b1e..d15fd38c1756 100644 --- a/drivers/irqchip/irq-loongson-eiointc.c +++ b/drivers/irqchip/irq-loongson-eiointc.c @@ -17,6 +17,7 @@ #include <linux/of_address.h> #include <linux/of_irq.h> #include <linux/of_platform.h> +#include <linux/syscore_ops.h> #define EIOINTC_REG_NODEMAP 0x14a0 #define EIOINTC_REG_IPMAP 0x14c0 @@ -301,9 +302,39 @@ static struct irq_domain *acpi_get_vec_parent(int node, struct acpi_vector_group return NULL; } -static int __init -pch_pic_parse_madt(union acpi_subtable_headers *header, - const unsigned long end) +static int eiointc_suspend(void) +{ + return 0; +} + +static void eiointc_resume(void) +{ + int i, j; + struct irq_desc *desc; + struct irq_data *irq_data; + + eiointc_router_init(0); + + for (i = 0; i < nr_pics; i++) { + for (j = 0; j < VEC_COUNT; j++) { + desc = irq_resolve_mapping(eiointc_priv[i]->eiointc_domain, j); + if (desc && desc->handle_irq && desc->handle_irq != handle_bad_irq) { + raw_spin_lock(&desc->lock); + irq_data = &desc->irq_data; + eiointc_set_irq_affinity(irq_data, irq_data->common->affinity, 0); + raw_spin_unlock(&desc->lock); + } + } + } +} + +static struct syscore_ops eiointc_syscore_ops = { + .suspend = eiointc_suspend, + .resume = eiointc_resume, +}; + +static int __init pch_pic_parse_madt(union acpi_subtable_headers *header, + const unsigned long end) { struct acpi_madt_bio_pic *pchpic_entry = (struct acpi_madt_bio_pic *)header; unsigned int node = (pchpic_entry->address >> 44) & 0xf; @@ -315,9 +346,8 @@ pch_pic_parse_madt(union acpi_subtable_headers *header, return -EINVAL; } -static int __init -pch_msi_parse_madt(union acpi_subtable_headers *header, - const unsigned long end) +static int __init pch_msi_parse_madt(union acpi_subtable_headers *header, + const unsigned long end) { struct acpi_madt_msi_pic *pchmsi_entry = (struct acpi_madt_msi_pic *)header; struct irq_domain *parent = acpi_get_vec_parent(eiointc_priv[nr_pics - 1]->node, msi_group); @@ -330,17 +360,23 @@ pch_msi_parse_madt(union acpi_subtable_headers *header, static int __init acpi_cascade_irqdomain_init(void) { - acpi_table_parse_madt(ACPI_MADT_TYPE_BIO_PIC, - pch_pic_parse_madt, 0); - acpi_table_parse_madt(ACPI_MADT_TYPE_MSI_PIC, - pch_msi_parse_madt, 1); + int r; + + r = acpi_table_parse_madt(ACPI_MADT_TYPE_BIO_PIC, pch_pic_parse_madt, 0); + if (r < 0) + return r; + + r = acpi_table_parse_madt(ACPI_MADT_TYPE_MSI_PIC, pch_msi_parse_madt, 1); + if (r < 0) + return r; + return 0; } int __init eiointc_acpi_init(struct irq_domain *parent, struct acpi_madt_eio_pic *acpi_eiointc) { - int i, parent_irq; + int i, ret, parent_irq; unsigned long node_map; struct eiointc_priv *priv; @@ -380,15 +416,16 @@ int __init eiointc_acpi_init(struct irq_domain *parent, parent_irq = irq_create_mapping(parent, acpi_eiointc->cascade); irq_set_chained_handler_and_data(parent_irq, eiointc_irq_dispatch, priv); + register_syscore_ops(&eiointc_syscore_ops); cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_LOONGARCH_STARTING, "irqchip/loongarch/intc:starting", eiointc_router_init, NULL); acpi_set_vec_parent(acpi_eiointc->node, priv->eiointc_domain, pch_group); acpi_set_vec_parent(acpi_eiointc->node, priv->eiointc_domain, msi_group); - acpi_cascade_irqdomain_init(); + ret = acpi_cascade_irqdomain_init(); - return 0; + return ret; out_free_handle: irq_domain_free_fwnode(priv->domain_handle); diff --git a/drivers/irqchip/irq-loongson-htvec.c b/drivers/irqchip/irq-loongson-htvec.c index 60a335d7e64e..fc8bf1f5d41b 100644 --- a/drivers/irqchip/irq-loongson-htvec.c +++ b/drivers/irqchip/irq-loongson-htvec.c @@ -16,11 +16,11 @@ #include <linux/of_address.h> #include <linux/of_irq.h> #include <linux/of_platform.h> +#include <linux/syscore_ops.h> /* Registers */ #define HTVEC_EN_OFF 0x20 #define HTVEC_MAX_PARENT_IRQ 8 - #define VEC_COUNT_PER_REG 32 #define VEC_REG_IDX(irq_id) ((irq_id) / VEC_COUNT_PER_REG) #define VEC_REG_BIT(irq_id) ((irq_id) % VEC_COUNT_PER_REG) @@ -30,8 +30,11 @@ struct htvec { void __iomem *base; struct irq_domain *htvec_domain; raw_spinlock_t htvec_lock; + u32 saved_vec_en[HTVEC_MAX_PARENT_IRQ]; }; +static struct htvec *htvec_priv; + static void htvec_irq_dispatch(struct irq_desc *desc) { int i; @@ -155,64 +158,169 @@ static void htvec_reset(struct htvec *priv) } } -static int htvec_of_init(struct device_node *node, - struct device_node *parent) +static int htvec_suspend(void) +{ + int i; + + for (i = 0; i < htvec_priv->num_parents; i++) + htvec_priv->saved_vec_en[i] = readl(htvec_priv->base + HTVEC_EN_OFF + 4 * i); + + return 0; +} + +static void htvec_resume(void) { + int i; + + for (i = 0; i < htvec_priv->num_parents; i++) + writel(htvec_priv->saved_vec_en[i], htvec_priv->base + HTVEC_EN_OFF + 4 * i); +} + +static struct syscore_ops htvec_syscore_ops = { + .suspend = htvec_suspend, + .resume = htvec_resume, +}; + +static int htvec_init(phys_addr_t addr, unsigned long size, + int num_parents, int parent_irq[], struct fwnode_handle *domain_handle) +{ + int i; struct htvec *priv; - int err, parent_irq[8], i; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; + priv->num_parents = num_parents; + priv->base = ioremap(addr, size); raw_spin_lock_init(&priv->htvec_lock); - priv->base = of_iomap(node, 0); - if (!priv->base) { - err = -ENOMEM; - goto free_priv; - } - - /* Interrupt may come from any of the 8 interrupt lines */ - for (i = 0; i < HTVEC_MAX_PARENT_IRQ; i++) { - parent_irq[i] = irq_of_parse_and_map(node, i); - if (parent_irq[i] <= 0) - break; - priv->num_parents++; - } - - if (!priv->num_parents) { - pr_err("Failed to get parent irqs\n"); - err = -ENODEV; - goto iounmap_base; - } - - priv->htvec_domain = irq_domain_create_linear(of_node_to_fwnode(node), + /* Setup IRQ domain */ + priv->htvec_domain = irq_domain_create_linear(domain_handle, (VEC_COUNT_PER_REG * priv->num_parents), &htvec_domain_ops, priv); if (!priv->htvec_domain) { - pr_err("Failed to create IRQ domain\n"); - err = -ENOMEM; - goto irq_dispose; + pr_err("loongson-htvec: cannot add IRQ domain\n"); + goto iounmap_base; } htvec_reset(priv); - for (i = 0; i < priv->num_parents; i++) + for (i = 0; i < priv->num_parents; i++) { irq_set_chained_handler_and_data(parent_irq[i], htvec_irq_dispatch, priv); + } + + htvec_priv = priv; + + register_syscore_ops(&htvec_syscore_ops); return 0; -irq_dispose: - for (; i > 0; i--) - irq_dispose_mapping(parent_irq[i - 1]); iounmap_base: iounmap(priv->base); -free_priv: kfree(priv); - return err; + return -EINVAL; +} + +#ifdef CONFIG_OF + +static int htvec_of_init(struct device_node *node, + struct device_node *parent) +{ + int i, err; + int parent_irq[8]; + int num_parents = 0; + struct resource res; + + if (of_address_to_resource(node, 0, &res)) + return -EINVAL; + + /* Interrupt may come from any of the 8 interrupt lines */ + for (i = 0; i < HTVEC_MAX_PARENT_IRQ; i++) { + parent_irq[i] = irq_of_parse_and_map(node, i); + if (parent_irq[i] <= 0) + break; + + num_parents++; + } + + err = htvec_init(res.start, resource_size(&res), + num_parents, parent_irq, of_node_to_fwnode(node)); + if (err < 0) + return err; + + return 0; } IRQCHIP_DECLARE(htvec, "loongson,htvec-1.0", htvec_of_init); + +#endif + +#ifdef CONFIG_ACPI +static int __init pch_pic_parse_madt(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_bio_pic *pchpic_entry = (struct acpi_madt_bio_pic *)header; + + return pch_pic_acpi_init(htvec_priv->htvec_domain, pchpic_entry); +} + +static int __init pch_msi_parse_madt(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_msi_pic *pchmsi_entry = (struct acpi_madt_msi_pic *)header; + + return pch_msi_acpi_init(htvec_priv->htvec_domain, pchmsi_entry); +} + +static int __init acpi_cascade_irqdomain_init(void) +{ + int r; + + r = acpi_table_parse_madt(ACPI_MADT_TYPE_BIO_PIC, pch_pic_parse_madt, 0); + if (r < 0) + return r; + + r = acpi_table_parse_madt(ACPI_MADT_TYPE_MSI_PIC, pch_msi_parse_madt, 0); + if (r < 0) + return r; + + return 0; +} + +int __init htvec_acpi_init(struct irq_domain *parent, + struct acpi_madt_ht_pic *acpi_htvec) +{ + int i, ret; + int num_parents, parent_irq[8]; + struct fwnode_handle *domain_handle; + + if (!acpi_htvec) + return -EINVAL; + + num_parents = HTVEC_MAX_PARENT_IRQ; + + domain_handle = irq_domain_alloc_fwnode(&acpi_htvec->address); + if (!domain_handle) { + pr_err("Unable to allocate domain handle\n"); + return -ENOMEM; + } + + /* Interrupt may come from any of the 8 interrupt lines */ + for (i = 0; i < HTVEC_MAX_PARENT_IRQ; i++) + parent_irq[i] = irq_create_mapping(parent, acpi_htvec->cascade[i]); + + ret = htvec_init(acpi_htvec->address, acpi_htvec->size, + num_parents, parent_irq, domain_handle); + + if (ret == 0) + ret = acpi_cascade_irqdomain_init(); + else + irq_domain_free_fwnode(domain_handle); + + return ret; +} + +#endif diff --git a/drivers/irqchip/irq-loongson-liointc.c b/drivers/irqchip/irq-loongson-liointc.c index 0da8716f8f24..85b754f7f4e6 100644 --- a/drivers/irqchip/irq-loongson-liointc.c +++ b/drivers/irqchip/irq-loongson-liointc.c @@ -167,7 +167,12 @@ static int liointc_domain_xlate(struct irq_domain *d, struct device_node *ctrlr, if (WARN_ON(intsize < 1)) return -EINVAL; *out_hwirq = intspec[0] - GSI_MIN_CPU_IRQ; - *out_type = IRQ_TYPE_NONE; + + if (intsize > 1) + *out_type = intspec[1] & IRQ_TYPE_SENSE_MASK; + else + *out_type = IRQ_TYPE_NONE; + return 0; } @@ -207,10 +212,13 @@ static int liointc_init(phys_addr_t addr, unsigned long size, int revision, "reg-names", core_reg_names[i]); if (index < 0) - goto out_iounmap; + continue; priv->core_isr[i] = of_iomap(node, index); } + + if (!priv->core_isr[0]) + goto out_iounmap; } /* Setup IRQ domain */ @@ -349,6 +357,26 @@ IRQCHIP_DECLARE(loongson_liointc_2_0, "loongson,liointc-2.0", liointc_of_init); #endif #ifdef CONFIG_ACPI +static int __init htintc_parse_madt(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_madt_ht_pic *htintc_entry = (struct acpi_madt_ht_pic *)header; + struct irq_domain *parent = irq_find_matching_fwnode(liointc_handle, DOMAIN_BUS_ANY); + + return htvec_acpi_init(parent, htintc_entry); +} + +static int __init acpi_cascade_irqdomain_init(void) +{ + int r; + + r = acpi_table_parse_madt(ACPI_MADT_TYPE_HT_PIC, htintc_parse_madt, 0); + if (r < 0) + return r; + + return 0; +} + int __init liointc_acpi_init(struct irq_domain *parent, struct acpi_madt_lio_pic *acpi_liointc) { int ret; @@ -365,9 +393,12 @@ int __init liointc_acpi_init(struct irq_domain *parent, struct acpi_madt_lio_pic pr_err("Unable to allocate domain handle\n"); return -ENOMEM; } + ret = liointc_init(acpi_liointc->address, acpi_liointc->size, 1, domain_handle, NULL); - if (ret) + if (ret == 0) + ret = acpi_cascade_irqdomain_init(); + else irq_domain_free_fwnode(domain_handle); return ret; diff --git a/drivers/irqchip/irq-loongson-pch-lpc.c b/drivers/irqchip/irq-loongson-pch-lpc.c index bf2324910a75..9b35492fb6be 100644 --- a/drivers/irqchip/irq-loongson-pch-lpc.c +++ b/drivers/irqchip/irq-loongson-pch-lpc.c @@ -13,6 +13,7 @@ #include <linux/irqchip/chained_irq.h> #include <linux/irqdomain.h> #include <linux/kernel.h> +#include <linux/syscore_ops.h> /* Registers */ #define LPC_INT_CTL 0x00 @@ -34,6 +35,7 @@ struct pch_lpc { u32 saved_reg_pol; }; +static struct pch_lpc *pch_lpc_priv; struct fwnode_handle *pch_lpc_handle; static void lpc_irq_ack(struct irq_data *d) @@ -147,6 +149,26 @@ static int pch_lpc_disabled(struct pch_lpc *priv) (readl(priv->base + LPC_INT_STS) == 0xffffffff); } +static int pch_lpc_suspend(void) +{ + pch_lpc_priv->saved_reg_ctl = readl(pch_lpc_priv->base + LPC_INT_CTL); + pch_lpc_priv->saved_reg_ena = readl(pch_lpc_priv->base + LPC_INT_ENA); + pch_lpc_priv->saved_reg_pol = readl(pch_lpc_priv->base + LPC_INT_POL); + return 0; +} + +static void pch_lpc_resume(void) +{ + writel(pch_lpc_priv->saved_reg_ctl, pch_lpc_priv->base + LPC_INT_CTL); + writel(pch_lpc_priv->saved_reg_ena, pch_lpc_priv->base + LPC_INT_ENA); + writel(pch_lpc_priv->saved_reg_pol, pch_lpc_priv->base + LPC_INT_POL); +} + +static struct syscore_ops pch_lpc_syscore_ops = { + .suspend = pch_lpc_suspend, + .resume = pch_lpc_resume, +}; + int __init pch_lpc_acpi_init(struct irq_domain *parent, struct acpi_madt_lpc_pic *acpi_pchlpc) { @@ -191,7 +213,10 @@ int __init pch_lpc_acpi_init(struct irq_domain *parent, parent_irq = irq_create_fwspec_mapping(&fwspec); irq_set_chained_handler_and_data(parent_irq, lpc_irq_dispatch, priv); + pch_lpc_priv = priv; pch_lpc_handle = irq_handle; + register_syscore_ops(&pch_lpc_syscore_ops); + return 0; free_irq_handle: diff --git a/drivers/irqchip/irq-loongson-pch-pic.c b/drivers/irqchip/irq-loongson-pch-pic.c index c01b9c257005..437f1af693d0 100644 --- a/drivers/irqchip/irq-loongson-pch-pic.c +++ b/drivers/irqchip/irq-loongson-pch-pic.c @@ -15,6 +15,7 @@ #include <linux/of_address.h> #include <linux/of_irq.h> #include <linux/of_platform.h> +#include <linux/syscore_ops.h> /* Registers */ #define PCH_PIC_MASK 0x20 @@ -42,6 +43,9 @@ struct pch_pic { raw_spinlock_t pic_lock; u32 vec_count; u32 gsi_base; + u32 saved_vec_en[PIC_REG_COUNT]; + u32 saved_vec_pol[PIC_REG_COUNT]; + u32 saved_vec_edge[PIC_REG_COUNT]; }; static struct pch_pic *pch_pic_priv[MAX_IO_PICS]; @@ -145,6 +149,7 @@ static struct irq_chip pch_pic_irq_chip = { .irq_ack = pch_pic_ack_irq, .irq_set_affinity = irq_chip_set_affinity_parent, .irq_set_type = pch_pic_set_type, + .flags = IRQCHIP_SKIP_SET_WAKE, }; static int pch_pic_domain_translate(struct irq_domain *d, @@ -155,15 +160,21 @@ static int pch_pic_domain_translate(struct irq_domain *d, struct pch_pic *priv = d->host_data; struct device_node *of_node = to_of_node(fwspec->fwnode); - if (fwspec->param_count < 1) - return -EINVAL; - if (of_node) { + if (fwspec->param_count < 2) + return -EINVAL; + *hwirq = fwspec->param[0] + priv->ht_vec_base; *type = fwspec->param[1] & IRQ_TYPE_SENSE_MASK; } else { + if (fwspec->param_count < 1) + return -EINVAL; + *hwirq = fwspec->param[0] - priv->gsi_base; - *type = IRQ_TYPE_NONE; + if (fwspec->param_count > 1) + *type = fwspec->param[1] & IRQ_TYPE_SENSE_MASK; + else + *type = IRQ_TYPE_NONE; } return 0; @@ -228,6 +239,46 @@ static void pch_pic_reset(struct pch_pic *priv) } } +static int pch_pic_suspend(void) +{ + int i, j; + + for (i = 0; i < nr_pics; i++) { + for (j = 0; j < PIC_REG_COUNT; j++) { + pch_pic_priv[i]->saved_vec_pol[j] = + readl(pch_pic_priv[i]->base + PCH_PIC_POL + 4 * j); + pch_pic_priv[i]->saved_vec_edge[j] = + readl(pch_pic_priv[i]->base + PCH_PIC_EDGE + 4 * j); + pch_pic_priv[i]->saved_vec_en[j] = + readl(pch_pic_priv[i]->base + PCH_PIC_MASK + 4 * j); + } + } + + return 0; +} + +static void pch_pic_resume(void) +{ + int i, j; + + for (i = 0; i < nr_pics; i++) { + pch_pic_reset(pch_pic_priv[i]); + for (j = 0; j < PIC_REG_COUNT; j++) { + writel(pch_pic_priv[i]->saved_vec_pol[j], + pch_pic_priv[i]->base + PCH_PIC_POL + 4 * j); + writel(pch_pic_priv[i]->saved_vec_edge[j], + pch_pic_priv[i]->base + PCH_PIC_EDGE + 4 * j); + writel(pch_pic_priv[i]->saved_vec_en[j], + pch_pic_priv[i]->base + PCH_PIC_MASK + 4 * j); + } + } +} + +static struct syscore_ops pch_pic_syscore_ops = { + .suspend = pch_pic_suspend, + .resume = pch_pic_resume, +}; + static int pch_pic_init(phys_addr_t addr, unsigned long size, int vec_base, struct irq_domain *parent_domain, struct fwnode_handle *domain_handle, u32 gsi_base) @@ -260,6 +311,8 @@ static int pch_pic_init(phys_addr_t addr, unsigned long size, int vec_base, pch_pic_handle[nr_pics] = domain_handle; pch_pic_priv[nr_pics++] = priv; + register_syscore_ops(&pch_pic_syscore_ops); + return 0; iounmap_base: @@ -325,9 +378,8 @@ int find_pch_pic(u32 gsi) return -1; } -static int __init -pch_lpc_parse_madt(union acpi_subtable_headers *header, - const unsigned long end) +static int __init pch_lpc_parse_madt(union acpi_subtable_headers *header, + const unsigned long end) { struct acpi_madt_lpc_pic *pchlpc_entry = (struct acpi_madt_lpc_pic *)header; @@ -336,8 +388,12 @@ pch_lpc_parse_madt(union acpi_subtable_headers *header, static int __init acpi_cascade_irqdomain_init(void) { - acpi_table_parse_madt(ACPI_MADT_TYPE_LPC_PIC, - pch_lpc_parse_madt, 0); + int r; + + r = acpi_table_parse_madt(ACPI_MADT_TYPE_LPC_PIC, pch_lpc_parse_madt, 0); + if (r < 0) + return r; + return 0; } @@ -364,7 +420,7 @@ int __init pch_pic_acpi_init(struct irq_domain *parent, } if (acpi_pchpic->id == 0) - acpi_cascade_irqdomain_init(); + ret = acpi_cascade_irqdomain_init(); return ret; } diff --git a/drivers/irqchip/irq-ls-extirq.c b/drivers/irqchip/irq-ls-extirq.c index d8d48b1f7c29..139f26b0a6ef 100644 --- a/drivers/irqchip/irq-ls-extirq.c +++ b/drivers/irqchip/irq-ls-extirq.c @@ -203,7 +203,7 @@ ls_extirq_of_init(struct device_node *node, struct device_node *parent) if (ret) goto err_parse_map; - priv->big_endian = of_device_is_big_endian(parent); + priv->big_endian = of_device_is_big_endian(node->parent); priv->is_ls1021a_or_ls1043a = of_device_is_compatible(node, "fsl,ls1021a-extirq") || of_device_is_compatible(node, "fsl,ls1043a-extirq"); raw_spin_lock_init(&priv->lock); diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 1ba0f1555c80..1a6a7a672ad7 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -494,7 +494,7 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq, map = GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin; /* - * If adding support for more per-cpu interrupts, keep the the + * If adding support for more per-cpu interrupts, keep the * array in gic_all_vpes_irq_cpu_online() in sync. */ switch (intr) { diff --git a/drivers/irqchip/irq-mtk-cirq.c b/drivers/irqchip/irq-mtk-cirq.c index 9bca0918078e..76bc0283e3b9 100644 --- a/drivers/irqchip/irq-mtk-cirq.c +++ b/drivers/irqchip/irq-mtk-cirq.c @@ -15,14 +15,41 @@ #include <linux/slab.h> #include <linux/syscore_ops.h> -#define CIRQ_ACK 0x40 -#define CIRQ_MASK_SET 0xc0 -#define CIRQ_MASK_CLR 0x100 -#define CIRQ_SENS_SET 0x180 -#define CIRQ_SENS_CLR 0x1c0 -#define CIRQ_POL_SET 0x240 -#define CIRQ_POL_CLR 0x280 -#define CIRQ_CONTROL 0x300 +enum mtk_cirq_regoffs_index { + CIRQ_STA, + CIRQ_ACK, + CIRQ_MASK_SET, + CIRQ_MASK_CLR, + CIRQ_SENS_SET, + CIRQ_SENS_CLR, + CIRQ_POL_SET, + CIRQ_POL_CLR, + CIRQ_CONTROL +}; + +static const u32 mtk_cirq_regoffs_v1[] = { + [CIRQ_STA] = 0x0, + [CIRQ_ACK] = 0x40, + [CIRQ_MASK_SET] = 0xc0, + [CIRQ_MASK_CLR] = 0x100, + [CIRQ_SENS_SET] = 0x180, + [CIRQ_SENS_CLR] = 0x1c0, + [CIRQ_POL_SET] = 0x240, + [CIRQ_POL_CLR] = 0x280, + [CIRQ_CONTROL] = 0x300, +}; + +static const u32 mtk_cirq_regoffs_v2[] = { + [CIRQ_STA] = 0x0, + [CIRQ_ACK] = 0x80, + [CIRQ_MASK_SET] = 0x180, + [CIRQ_MASK_CLR] = 0x200, + [CIRQ_SENS_SET] = 0x300, + [CIRQ_SENS_CLR] = 0x380, + [CIRQ_POL_SET] = 0x480, + [CIRQ_POL_CLR] = 0x500, + [CIRQ_CONTROL] = 0x600, +}; #define CIRQ_EN 0x1 #define CIRQ_EDGE 0x2 @@ -32,18 +59,32 @@ struct mtk_cirq_chip_data { void __iomem *base; unsigned int ext_irq_start; unsigned int ext_irq_end; + const u32 *offsets; struct irq_domain *domain; }; static struct mtk_cirq_chip_data *cirq_data; -static void mtk_cirq_write_mask(struct irq_data *data, unsigned int offset) +static void __iomem *mtk_cirq_reg(struct mtk_cirq_chip_data *chip_data, + enum mtk_cirq_regoffs_index idx) +{ + return chip_data->base + chip_data->offsets[idx]; +} + +static void __iomem *mtk_cirq_irq_reg(struct mtk_cirq_chip_data *chip_data, + enum mtk_cirq_regoffs_index idx, + unsigned int cirq_num) +{ + return mtk_cirq_reg(chip_data, idx) + (cirq_num / 32) * 4; +} + +static void mtk_cirq_write_mask(struct irq_data *data, enum mtk_cirq_regoffs_index idx) { struct mtk_cirq_chip_data *chip_data = data->chip_data; unsigned int cirq_num = data->hwirq; u32 mask = 1 << (cirq_num % 32); - writel_relaxed(mask, chip_data->base + offset + (cirq_num / 32) * 4); + writel_relaxed(mask, mtk_cirq_irq_reg(chip_data, idx, cirq_num)); } static void mtk_cirq_mask(struct irq_data *data) @@ -160,6 +201,7 @@ static const struct irq_domain_ops cirq_domain_ops = { #ifdef CONFIG_PM_SLEEP static int mtk_cirq_suspend(void) { + void __iomem *reg; u32 value, mask; unsigned int irq, hwirq_num; bool pending, masked; @@ -200,31 +242,34 @@ static int mtk_cirq_suspend(void) continue; } + reg = mtk_cirq_irq_reg(cirq_data, CIRQ_ACK, i); mask = 1 << (i % 32); - writel_relaxed(mask, cirq_data->base + CIRQ_ACK + (i / 32) * 4); + writel_relaxed(mask, reg); } /* set edge_only mode, record edge-triggerd interrupts */ /* enable cirq */ - value = readl_relaxed(cirq_data->base + CIRQ_CONTROL); + reg = mtk_cirq_reg(cirq_data, CIRQ_CONTROL); + value = readl_relaxed(reg); value |= (CIRQ_EDGE | CIRQ_EN); - writel_relaxed(value, cirq_data->base + CIRQ_CONTROL); + writel_relaxed(value, reg); return 0; } static void mtk_cirq_resume(void) { + void __iomem *reg = mtk_cirq_reg(cirq_data, CIRQ_CONTROL); u32 value; /* flush recorded interrupts, will send signals to parent controller */ - value = readl_relaxed(cirq_data->base + CIRQ_CONTROL); - writel_relaxed(value | CIRQ_FLUSH, cirq_data->base + CIRQ_CONTROL); + value = readl_relaxed(reg); + writel_relaxed(value | CIRQ_FLUSH, reg); /* disable cirq */ - value = readl_relaxed(cirq_data->base + CIRQ_CONTROL); + value = readl_relaxed(reg); value &= ~(CIRQ_EDGE | CIRQ_EN); - writel_relaxed(value, cirq_data->base + CIRQ_CONTROL); + writel_relaxed(value, reg); } static struct syscore_ops mtk_cirq_syscore_ops = { @@ -240,10 +285,19 @@ static void mtk_cirq_syscore_init(void) static inline void mtk_cirq_syscore_init(void) {} #endif +static const struct of_device_id mtk_cirq_of_match[] = { + { .compatible = "mediatek,mt2701-cirq", .data = &mtk_cirq_regoffs_v1 }, + { .compatible = "mediatek,mt8135-cirq", .data = &mtk_cirq_regoffs_v1 }, + { .compatible = "mediatek,mt8173-cirq", .data = &mtk_cirq_regoffs_v1 }, + { .compatible = "mediatek,mt8192-cirq", .data = &mtk_cirq_regoffs_v2 }, + { /* sentinel */ } +}; + static int __init mtk_cirq_of_init(struct device_node *node, struct device_node *parent) { struct irq_domain *domain, *domain_parent; + const struct of_device_id *match; unsigned int irq_num; int ret; @@ -274,6 +328,13 @@ static int __init mtk_cirq_of_init(struct device_node *node, if (ret) goto out_unmap; + match = of_match_node(mtk_cirq_of_match, node); + if (!match) { + ret = -ENODEV; + goto out_unmap; + } + cirq_data->offsets = match->data; + irq_num = cirq_data->ext_irq_end - cirq_data->ext_irq_start + 1; domain = irq_domain_add_hierarchy(domain_parent, 0, irq_num, node, diff --git a/drivers/irqchip/irq-mvebu-icu.c b/drivers/irqchip/irq-mvebu-icu.c index 497da344717c..3c77acc7ec6a 100644 --- a/drivers/irqchip/irq-mvebu-icu.c +++ b/drivers/irqchip/irq-mvebu-icu.c @@ -151,9 +151,9 @@ static int mvebu_icu_irq_domain_translate(struct irq_domain *d, struct irq_fwspec *fwspec, unsigned long *hwirq, unsigned int *type) { - struct mvebu_icu_msi_data *msi_data = platform_msi_get_host_data(d); - struct mvebu_icu *icu = platform_msi_get_host_data(d); unsigned int param_count = static_branch_unlikely(&legacy_bindings) ? 3 : 2; + struct mvebu_icu_msi_data *msi_data = platform_msi_get_host_data(d); + struct mvebu_icu *icu = msi_data->icu; /* Check the count of the parameters in dt */ if (WARN_ON(fwspec->param_count != param_count)) { diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c index 2f4784860df5..ff47bd0dec45 100644 --- a/drivers/irqchip/irq-sifive-plic.c +++ b/drivers/irqchip/irq-sifive-plic.c @@ -187,7 +187,8 @@ static struct irq_chip plic_edge_chip = { .irq_set_affinity = plic_set_affinity, #endif .irq_set_type = plic_irq_set_type, - .flags = IRQCHIP_AFFINITY_PRE_STARTUP, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; static struct irq_chip plic_chip = { @@ -201,7 +202,8 @@ static struct irq_chip plic_chip = { .irq_set_affinity = plic_set_affinity, #endif .irq_set_type = plic_irq_set_type, - .flags = IRQCHIP_AFFINITY_PRE_STARTUP, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; static int plic_irq_set_type(struct irq_data *d, unsigned int type) diff --git a/drivers/irqchip/irq-sl28cpld.c b/drivers/irqchip/irq-sl28cpld.c index fbb354413ffa..f2172240172c 100644 --- a/drivers/irqchip/irq-sl28cpld.c +++ b/drivers/irqchip/irq-sl28cpld.c @@ -65,8 +65,7 @@ static int sl28cpld_intc_probe(struct platform_device *pdev) irqchip->chip.num_irqs = ARRAY_SIZE(sl28cpld_irqs); irqchip->chip.num_regs = 1; irqchip->chip.status_base = base + INTC_IP; - irqchip->chip.mask_base = base + INTC_IE; - irqchip->chip.mask_invert = true; + irqchip->chip.unmask_base = base + INTC_IE; irqchip->chip.ack_base = base + INTC_IP; return devm_regmap_add_irq_chip_fwnode(dev, dev_fwnode(dev), diff --git a/drivers/irqchip/irq-st.c b/drivers/irqchip/irq-st.c index 801551e46a7b..1b83512b29c6 100644 --- a/drivers/irqchip/irq-st.c +++ b/drivers/irqchip/irq-st.c @@ -153,18 +153,13 @@ static int st_irq_syscfg_enable(struct platform_device *pdev) static int st_irq_syscfg_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; - const struct of_device_id *match; struct st_irq_syscfg *ddata; ddata = devm_kzalloc(&pdev->dev, sizeof(*ddata), GFP_KERNEL); if (!ddata) return -ENOMEM; - match = of_match_device(st_irq_syscfg_match, &pdev->dev); - if (!match) - return -ENODEV; - - ddata->syscfg = (unsigned int)match->data; + ddata->syscfg = (unsigned int) device_get_match_data(&pdev->dev); ddata->regmap = syscon_regmap_lookup_by_phandle(np, "st,syscfg"); if (IS_ERR(ddata->regmap)) { diff --git a/drivers/irqchip/irq-ti-sci-inta.c b/drivers/irqchip/irq-ti-sci-inta.c index 5fdbb4358dd0..a6ecc53d055c 100644 --- a/drivers/irqchip/irq-ti-sci-inta.c +++ b/drivers/irqchip/irq-ti-sci-inta.c @@ -168,7 +168,7 @@ static void ti_sci_inta_irq_handler(struct irq_desc *desc) /** * ti_sci_inta_xlate_irq() - Translate hwirq to parent's hwirq. * @inta: IRQ domain corresponding to Interrupt Aggregator - * @irq: Hardware irq corresponding to the above irq domain + * @vint_id: Hardware irq corresponding to the above irq domain * * Return parent irq number if translation is available else -ENOENT. */ diff --git a/drivers/irqchip/irq-wpcm450-aic.c b/drivers/irqchip/irq-wpcm450-aic.c index 0dcbeb1a05a1..91df62a64cd9 100644 --- a/drivers/irqchip/irq-wpcm450-aic.c +++ b/drivers/irqchip/irq-wpcm450-aic.c @@ -146,6 +146,7 @@ static int __init wpcm450_aic_of_init(struct device_node *node, aic->regs = of_iomap(node, 0); if (!aic->regs) { pr_err("Failed to map WPCM450 AIC registers\n"); + kfree(aic); return -ENOMEM; } diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig index 05d6fae800e3..d7af896cbd7b 100644 --- a/drivers/mailbox/Kconfig +++ b/drivers/mailbox/Kconfig @@ -223,7 +223,7 @@ config BCM_FLEXRM_MBOX tristate "Broadcom FlexRM Mailbox" depends on ARM64 depends on ARCH_BCM_IPROC || COMPILE_TEST - select GENERIC_MSI_IRQ_DOMAIN + select GENERIC_MSI_IRQ default m if ARCH_BCM_IPROC help Mailbox implementation of the Broadcom FlexRM ring manager, diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index ab9697f3b5f1..92efc4676df6 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -813,7 +813,13 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, num_buffers = max_t(unsigned int, *count, q->min_buffers_needed); num_buffers = min_t(unsigned int, num_buffers, VB2_MAX_FRAME); memset(q->alloc_devs, 0, sizeof(q->alloc_devs)); + /* + * Set this now to ensure that drivers see the correct q->memory value + * in the queue_setup op. + */ + mutex_lock(&q->mmap_lock); q->memory = memory; + mutex_unlock(&q->mmap_lock); set_queue_coherency(q, non_coherent_mem); /* @@ -823,22 +829,27 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, ret = call_qop(q, queue_setup, q, &num_buffers, &num_planes, plane_sizes, q->alloc_devs); if (ret) - return ret; + goto error; /* Check that driver has set sane values */ - if (WARN_ON(!num_planes)) - return -EINVAL; + if (WARN_ON(!num_planes)) { + ret = -EINVAL; + goto error; + } for (i = 0; i < num_planes; i++) - if (WARN_ON(!plane_sizes[i])) - return -EINVAL; + if (WARN_ON(!plane_sizes[i])) { + ret = -EINVAL; + goto error; + } /* Finally, allocate buffers and video memory */ allocated_buffers = __vb2_queue_alloc(q, memory, num_buffers, num_planes, plane_sizes); if (allocated_buffers == 0) { dprintk(q, 1, "memory allocation failed\n"); - return -ENOMEM; + ret = -ENOMEM; + goto error; } /* @@ -879,7 +890,8 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, if (ret < 0) { /* * Note: __vb2_queue_free() will subtract 'allocated_buffers' - * from q->num_buffers. + * from q->num_buffers and it will reset q->memory to + * VB2_MEMORY_UNKNOWN. */ __vb2_queue_free(q, allocated_buffers); mutex_unlock(&q->mmap_lock); @@ -895,6 +907,12 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, q->waiting_for_buffers = !q->is_output; return 0; + +error: + mutex_lock(&q->mmap_lock); + q->memory = VB2_MEMORY_UNKNOWN; + mutex_unlock(&q->mmap_lock); + return ret; } EXPORT_SYMBOL_GPL(vb2_core_reqbufs); @@ -906,6 +924,7 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, unsigned int num_planes = 0, num_buffers, allocated_buffers; unsigned plane_sizes[VB2_MAX_PLANES] = { }; bool non_coherent_mem = flags & V4L2_MEMORY_FLAG_NON_COHERENT; + bool no_previous_buffers = !q->num_buffers; int ret; if (q->num_buffers == VB2_MAX_FRAME) { @@ -913,13 +932,19 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, return -ENOBUFS; } - if (!q->num_buffers) { + if (no_previous_buffers) { if (q->waiting_in_dqbuf && *count) { dprintk(q, 1, "another dup()ped fd is waiting for a buffer\n"); return -EBUSY; } memset(q->alloc_devs, 0, sizeof(q->alloc_devs)); + /* + * Set this now to ensure that drivers see the correct q->memory + * value in the queue_setup op. + */ + mutex_lock(&q->mmap_lock); q->memory = memory; + mutex_unlock(&q->mmap_lock); q->waiting_for_buffers = !q->is_output; set_queue_coherency(q, non_coherent_mem); } else { @@ -945,14 +970,15 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, ret = call_qop(q, queue_setup, q, &num_buffers, &num_planes, plane_sizes, q->alloc_devs); if (ret) - return ret; + goto error; /* Finally, allocate buffers and video memory */ allocated_buffers = __vb2_queue_alloc(q, memory, num_buffers, num_planes, plane_sizes); if (allocated_buffers == 0) { dprintk(q, 1, "memory allocation failed\n"); - return -ENOMEM; + ret = -ENOMEM; + goto error; } /* @@ -983,7 +1009,8 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, if (ret < 0) { /* * Note: __vb2_queue_free() will subtract 'allocated_buffers' - * from q->num_buffers. + * from q->num_buffers and it will reset q->memory to + * VB2_MEMORY_UNKNOWN. */ __vb2_queue_free(q, allocated_buffers); mutex_unlock(&q->mmap_lock); @@ -998,6 +1025,14 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, *count = allocated_buffers; return 0; + +error: + if (no_previous_buffers) { + mutex_lock(&q->mmap_lock); + q->memory = VB2_MEMORY_UNKNOWN; + mutex_unlock(&q->mmap_lock); + } + return ret; } EXPORT_SYMBOL_GPL(vb2_core_create_bufs); @@ -2165,6 +2200,22 @@ static int __find_plane_by_offset(struct vb2_queue *q, unsigned long off, unsigned int buffer, plane; /* + * Sanity checks to ensure the lock is held, MEMORY_MMAP is + * used and fileio isn't active. + */ + lockdep_assert_held(&q->mmap_lock); + + if (q->memory != VB2_MEMORY_MMAP) { + dprintk(q, 1, "queue is not currently set up for mmap\n"); + return -EINVAL; + } + + if (vb2_fileio_is_active(q)) { + dprintk(q, 1, "file io in progress\n"); + return -EBUSY; + } + + /* * Go over all buffers and their planes, comparing the given offset * with an offset assigned to each plane. If a match is found, * return its buffer and plane numbers. @@ -2265,11 +2316,6 @@ int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma) int ret; unsigned long length; - if (q->memory != VB2_MEMORY_MMAP) { - dprintk(q, 1, "queue is not currently set up for mmap\n"); - return -EINVAL; - } - /* * Check memory area access mode. */ @@ -2291,14 +2337,9 @@ int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma) mutex_lock(&q->mmap_lock); - if (vb2_fileio_is_active(q)) { - dprintk(q, 1, "mmap: file io in progress\n"); - ret = -EBUSY; - goto unlock; - } - /* - * Find the plane corresponding to the offset passed by userspace. + * Find the plane corresponding to the offset passed by userspace. This + * will return an error if not MEMORY_MMAP or file I/O is in progress. */ ret = __find_plane_by_offset(q, off, &buffer, &plane); if (ret) @@ -2351,22 +2392,25 @@ unsigned long vb2_get_unmapped_area(struct vb2_queue *q, void *vaddr; int ret; - if (q->memory != VB2_MEMORY_MMAP) { - dprintk(q, 1, "queue is not currently set up for mmap\n"); - return -EINVAL; - } + mutex_lock(&q->mmap_lock); /* - * Find the plane corresponding to the offset passed by userspace. + * Find the plane corresponding to the offset passed by userspace. This + * will return an error if not MEMORY_MMAP or file I/O is in progress. */ ret = __find_plane_by_offset(q, off, &buffer, &plane); if (ret) - return ret; + goto unlock; vb = q->bufs[buffer]; vaddr = vb2_plane_vaddr(vb, plane); + mutex_unlock(&q->mmap_lock); return vaddr ? (unsigned long)vaddr : -EINVAL; + +unlock: + mutex_unlock(&q->mmap_lock); + return ret; } EXPORT_SYMBOL_GPL(vb2_get_unmapped_area); #endif diff --git a/drivers/media/v4l2-core/v4l2-dv-timings.c b/drivers/media/v4l2-core/v4l2-dv-timings.c index 003c32fed3f7..942d0005c55e 100644 --- a/drivers/media/v4l2-core/v4l2-dv-timings.c +++ b/drivers/media/v4l2-core/v4l2-dv-timings.c @@ -145,6 +145,8 @@ bool v4l2_valid_dv_timings(const struct v4l2_dv_timings *t, const struct v4l2_bt_timings *bt = &t->bt; const struct v4l2_bt_timings_cap *cap = &dvcap->bt; u32 caps = cap->capabilities; + const u32 max_vert = 10240; + u32 max_hor = 3 * bt->width; if (t->type != V4L2_DV_BT_656_1120) return false; @@ -166,14 +168,20 @@ bool v4l2_valid_dv_timings(const struct v4l2_dv_timings *t, if (!bt->interlaced && (bt->il_vbackporch || bt->il_vsync || bt->il_vfrontporch)) return false; - if (bt->hfrontporch > 2 * bt->width || - bt->hsync > 1024 || bt->hbackporch > 1024) + /* + * Some video receivers cannot properly separate the frontporch, + * backporch and sync values, and instead they only have the total + * blanking. That can be assigned to any of these three fields. + * So just check that none of these are way out of range. + */ + if (bt->hfrontporch > max_hor || + bt->hsync > max_hor || bt->hbackporch > max_hor) return false; - if (bt->vfrontporch > 4096 || - bt->vsync > 128 || bt->vbackporch > 4096) + if (bt->vfrontporch > max_vert || + bt->vsync > max_vert || bt->vbackporch > max_vert) return false; - if (bt->interlaced && (bt->il_vfrontporch > 4096 || - bt->il_vsync > 128 || bt->il_vbackporch > 4096)) + if (bt->interlaced && (bt->il_vfrontporch > max_vert || + bt->il_vsync > max_vert || bt->il_vbackporch > max_vert)) return false; return fnc == NULL || fnc(t, fnc_handle); } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index f298b9b3eb77..b9a882f182d2 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3247,7 +3247,7 @@ static int bond_na_rcv(const struct sk_buff *skb, struct bonding *bond, goto out; saddr = &combined->ip6.saddr; - daddr = &combined->ip6.saddr; + daddr = &combined->ip6.daddr; slave_dbg(bond->dev, slave->dev, "%s: %s/%d av %d sv %d sip %pI6c tip %pI6c\n", __func__, slave->dev->name, bond_slave_state(slave), diff --git a/drivers/net/can/can327.c b/drivers/net/can/can327.c index ed3d0b8989a0..dc7192ecb001 100644 --- a/drivers/net/can/can327.c +++ b/drivers/net/can/can327.c @@ -796,9 +796,9 @@ static int can327_netdev_close(struct net_device *dev) netif_stop_queue(dev); - /* Give UART one final chance to flush. */ - clear_bit(TTY_DO_WRITE_WAKEUP, &elm->tty->flags); - flush_work(&elm->tx_work); + /* We don't flush the UART TX queue here, as we want final stop + * commands (like the above dummy char) to be flushed out. + */ can_rx_offload_disable(&elm->offload); elm->can.state = CAN_STATE_STOPPED; @@ -1069,12 +1069,15 @@ static void can327_ldisc_close(struct tty_struct *tty) { struct can327 *elm = (struct can327 *)tty->disc_data; - /* unregister_netdev() calls .ndo_stop() so we don't have to. - * Our .ndo_stop() also flushes the TTY write wakeup handler, - * so we can safely set elm->tty = NULL after this. - */ + /* unregister_netdev() calls .ndo_stop() so we don't have to. */ unregister_candev(elm->dev); + /* Give UART one final chance to flush. + * No need to clear TTY_DO_WRITE_WAKEUP since .write_wakeup() is + * serialised against .close() and will not be called once we return. + */ + flush_work(&elm->tx_work); + /* Mark channel as dead */ spin_lock_bh(&elm->lock); tty->disc_data = NULL; diff --git a/drivers/net/can/slcan/slcan-core.c b/drivers/net/can/slcan/slcan-core.c index fbb34139daa1..f4db77007c13 100644 --- a/drivers/net/can/slcan/slcan-core.c +++ b/drivers/net/can/slcan/slcan-core.c @@ -864,12 +864,14 @@ static void slcan_close(struct tty_struct *tty) { struct slcan *sl = (struct slcan *)tty->disc_data; - /* unregister_netdev() calls .ndo_stop() so we don't have to. - * Our .ndo_stop() also flushes the TTY write wakeup handler, - * so we can safely set sl->tty = NULL after this. - */ unregister_candev(sl->dev); + /* + * The netdev needn't be UP (so .ndo_stop() is not called). Hence make + * sure this is not running before freeing it up. + */ + flush_work(&sl->tx_work); + /* Mark channel as dead */ spin_lock_bh(&sl->lock); tty->disc_data = NULL; diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c index 81b88e9e5bdc..42323f5e6f3a 100644 --- a/drivers/net/can/usb/esd_usb.c +++ b/drivers/net/can/usb/esd_usb.c @@ -234,6 +234,10 @@ static void esd_usb_rx_event(struct esd_usb_net_priv *priv, u8 rxerr = msg->msg.rx.data[2]; u8 txerr = msg->msg.rx.data[3]; + netdev_dbg(priv->netdev, + "CAN_ERR_EV_EXT: dlc=%#02x state=%02x ecc=%02x rec=%02x tec=%02x\n", + msg->msg.rx.dlc, state, ecc, rxerr, txerr); + skb = alloc_can_err_skb(priv->netdev, &cf); if (skb == NULL) { stats->rx_dropped++; @@ -260,6 +264,8 @@ static void esd_usb_rx_event(struct esd_usb_net_priv *priv, break; default: priv->can.state = CAN_STATE_ERROR_ACTIVE; + txerr = 0; + rxerr = 0; break; } } else { diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 2479be3a1e35..937cb22cb3d4 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -833,10 +833,13 @@ static void mv88e6xxx_get_caps(struct dsa_switch *ds, int port, chip->info->ops->phylink_get_caps(chip, port, config); - /* Internal ports need GMII for PHYLIB */ - if (mv88e6xxx_phy_is_internal(ds, port)) + if (mv88e6xxx_phy_is_internal(ds, port)) { + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + config->supported_interfaces); + /* Internal ports with no phy-mode need GMII for PHYLIB */ __set_bit(PHY_INTERFACE_MODE_GMII, config->supported_interfaces); + } } static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/sja1105/sja1105_devlink.c b/drivers/net/dsa/sja1105/sja1105_devlink.c index 10c6fea1227f..bdbbff2a7909 100644 --- a/drivers/net/dsa/sja1105/sja1105_devlink.c +++ b/drivers/net/dsa/sja1105/sja1105_devlink.c @@ -95,6 +95,8 @@ static int sja1105_setup_devlink_regions(struct dsa_switch *ds) if (IS_ERR(region)) { while (--i >= 0) dsa_devlink_region_destroy(priv->regions[i]); + + kfree(priv->regions); return PTR_ERR(region); } diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 412666111b0c..b70dcf32a26d 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1038,7 +1038,7 @@ static int sja1105_init_l2_policing(struct sja1105_private *priv) policing[bcast].sharindx = port; /* Only SJA1110 has multicast policers */ - if (mcast <= table->ops->max_entry_count) + if (mcast < table->ops->max_entry_count) policing[mcast].sharindx = port; } diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c index e104fb02817d..aa0d2f3aaeaa 100644 --- a/drivers/net/ethernet/aeroflex/greth.c +++ b/drivers/net/ethernet/aeroflex/greth.c @@ -258,6 +258,7 @@ static int greth_init_rings(struct greth_private *greth) if (dma_mapping_error(greth->dev, dma_addr)) { if (netif_msg_ifup(greth)) dev_err(greth->dev, "Could not create initial DMA mapping\n"); + dev_kfree_skb(skb); goto cleanup; } greth->rx_skbuff[i] = skb; diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index 55dfdb34e37b..f4ca0c6c0f51 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -71,13 +71,14 @@ config BCM63XX_ENET config BCMGENET tristate "Broadcom GENET internal MAC support" depends on HAS_IOMEM + depends on PTP_1588_CLOCK_OPTIONAL || !ARCH_BCM2835 select MII select PHYLIB select FIXED_PHY select BCM7XXX_PHY select MDIO_BCM_UNIMAC select DIMLIB - select BROADCOM_PHY if (ARCH_BCM2835 && PTP_1588_CLOCK_OPTIONAL) + select BROADCOM_PHY if ARCH_BCM2835 help This driver supports the built-in Ethernet MACs found in the Broadcom BCM7xxx Set Top Box family chipset. diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 98f3dc460ca7..f2f95493ec89 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -2239,7 +2239,7 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = register_netdev(netdev); if (err) { dev_err(dev, "Failed to register netdevice\n"); - goto err_unregister_interrupts; + goto err_destroy_workqueue; } nic->msg_enable = debug; @@ -2248,6 +2248,8 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; +err_destroy_workqueue: + destroy_workqueue(nic->nicvf_rx_mode_wq); err_unregister_interrupts: nicvf_unregister_interrupts(nic); err_free_netdev: diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c index cacd454ac696..c39b866e2582 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch-flower.c @@ -132,6 +132,7 @@ int dpaa2_switch_acl_entry_add(struct dpaa2_switch_filter_block *filter_block, DMA_TO_DEVICE); if (unlikely(dma_mapping_error(dev, acl_entry_cfg->key_iova))) { dev_err(dev, "DMA mapping failed\n"); + kfree(cmd_buff); return -EFAULT; } @@ -142,6 +143,7 @@ int dpaa2_switch_acl_entry_add(struct dpaa2_switch_filter_block *filter_block, DMA_TO_DEVICE); if (err) { dev_err(dev, "dpsw_acl_add_entry() failed %d\n", err); + kfree(cmd_buff); return err; } @@ -172,6 +174,7 @@ dpaa2_switch_acl_entry_remove(struct dpaa2_switch_filter_block *block, DMA_TO_DEVICE); if (unlikely(dma_mapping_error(dev, acl_entry_cfg->key_iova))) { dev_err(dev, "DMA mapping failed\n"); + kfree(cmd_buff); return -EFAULT; } @@ -182,6 +185,7 @@ dpaa2_switch_acl_entry_remove(struct dpaa2_switch_filter_block *block, DMA_TO_DEVICE); if (err) { dev_err(dev, "dpsw_acl_remove_entry() failed %d\n", err); + kfree(cmd_buff); return err; } diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 2ca2b61b451f..23e1a94b9ce4 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1220,7 +1220,8 @@ fec_restart(struct net_device *ndev) writel(0, fep->hwp + FEC_IMASK); /* Init the interrupt coalescing */ - fec_enet_itr_coal_set(ndev); + if (fep->quirks & FEC_QUIRK_HAS_COALESCE) + fec_enet_itr_coal_set(ndev); } static int fec_enet_ipc_handle_init(struct fec_enet_private *fep) diff --git a/drivers/net/ethernet/hisilicon/hisi_femac.c b/drivers/net/ethernet/hisilicon/hisi_femac.c index 93846bace028..ce2571c16e43 100644 --- a/drivers/net/ethernet/hisilicon/hisi_femac.c +++ b/drivers/net/ethernet/hisilicon/hisi_femac.c @@ -283,7 +283,7 @@ static int hisi_femac_rx(struct net_device *dev, int limit) skb->protocol = eth_type_trans(skb, dev); napi_gro_receive(&priv->napi, skb); dev->stats.rx_packets++; - dev->stats.rx_bytes += skb->len; + dev->stats.rx_bytes += len; next: pos = (pos + 1) % rxq->num; if (rx_pkts_num >= limit) diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c index ffcf797dfa90..f867e9531117 100644 --- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c +++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c @@ -550,7 +550,7 @@ static int hix5hd2_rx(struct net_device *dev, int limit) skb->protocol = eth_type_trans(skb, dev); napi_gro_receive(&priv->napi, skb); dev->stats.rx_packets++; - dev->stats.rx_bytes += skb->len; + dev->stats.rx_bytes += len; next: pos = dma_ring_incr(pos, RX_DESC_NUM); } diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 49e926959ad3..55cf2f62bb30 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -5936,9 +5936,9 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, e1000_tx_queue(tx_ring, tx_flags, count); /* Make sure there is space in the ring for the next send. */ e1000_maybe_stop_tx(tx_ring, - (MAX_SKB_FRAGS * + ((MAX_SKB_FRAGS + 1) * DIV_ROUND_UP(PAGE_SIZE, - adapter->tx_fifo_limit) + 2)); + adapter->tx_fifo_limit) + 4)); if (!netdev_xmit_more() || netif_xmit_stopped(netdev_get_tx_queue(netdev, 0))) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 4a6a6e48c615..f6fa63e4253c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -4464,11 +4464,7 @@ static int i40e_check_fdir_input_set(struct i40e_vsi *vsi, return -EOPNOTSUPP; /* First 4 bytes of L4 header */ - if (usr_ip4_spec->l4_4_bytes == htonl(0xFFFFFFFF)) - new_mask |= I40E_L4_SRC_MASK | I40E_L4_DST_MASK; - else if (!usr_ip4_spec->l4_4_bytes) - new_mask &= ~(I40E_L4_SRC_MASK | I40E_L4_DST_MASK); - else + if (usr_ip4_spec->l4_4_bytes) return -EOPNOTSUPP; /* Filtering on Type of Service is not supported. */ @@ -4507,11 +4503,7 @@ static int i40e_check_fdir_input_set(struct i40e_vsi *vsi, else return -EOPNOTSUPP; - if (usr_ip6_spec->l4_4_bytes == htonl(0xFFFFFFFF)) - new_mask |= I40E_L4_SRC_MASK | I40E_L4_DST_MASK; - else if (!usr_ip6_spec->l4_4_bytes) - new_mask &= ~(I40E_L4_SRC_MASK | I40E_L4_DST_MASK); - else + if (usr_ip6_spec->l4_4_bytes) return -EOPNOTSUPP; /* Filtering on Traffic class is not supported. */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index b3cb587a2032..6416322d7c18 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -10655,6 +10655,21 @@ static int i40e_rebuild_channels(struct i40e_vsi *vsi) } /** + * i40e_clean_xps_state - clean xps state for every tx_ring + * @vsi: ptr to the VSI + **/ +static void i40e_clean_xps_state(struct i40e_vsi *vsi) +{ + int i; + + if (vsi->tx_rings) + for (i = 0; i < vsi->num_queue_pairs; i++) + if (vsi->tx_rings[i]) + clear_bit(__I40E_TX_XPS_INIT_DONE, + vsi->tx_rings[i]->state); +} + +/** * i40e_prep_for_reset - prep for the core to reset * @pf: board private structure * @@ -10678,8 +10693,10 @@ static void i40e_prep_for_reset(struct i40e_pf *pf) i40e_pf_quiesce_all_vsi(pf); for (v = 0; v < pf->num_alloc_vsi; v++) { - if (pf->vsi[v]) + if (pf->vsi[v]) { + i40e_clean_xps_state(pf->vsi[v]); pf->vsi[v]->seid = 0; + } } i40e_shutdown_adminq(&pf->hw); diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 72ddcefc45b1..635f93d60318 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1578,6 +1578,7 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr) i40e_cleanup_reset_vf(vf); i40e_flush(hw); + usleep_range(20000, 40000); clear_bit(I40E_VF_STATE_RESETTING, &vf->vf_states); return true; @@ -1701,6 +1702,7 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr) } i40e_flush(hw); + usleep_range(20000, 40000); clear_bit(__I40E_VF_DISABLE, pf->state); return true; diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index e5f3e7680dc6..ff911af16a4b 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -1413,6 +1413,8 @@ static int igb_intr_test(struct igb_adapter *adapter, u64 *data) *data = 1; return -1; } + wr32(E1000_IVAR_MISC, E1000_IVAR_VALID << 8); + wr32(E1000_EIMS, BIT(0)); } else if (adapter->flags & IGB_FLAG_HAS_MSI) { shared_int = false; if (request_irq(irq, diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index ff3e361e06e7..5aefaaff0871 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -4271,7 +4271,7 @@ static void mvneta_percpu_elect(struct mvneta_port *pp) /* Use the cpu associated to the rxq when it is online, in all * the other cases, use the cpu 0 which can't be offline. */ - if (cpu_online(pp->rxq_def)) + if (pp->rxq_def < nr_cpu_ids && cpu_online(pp->rxq_def)) elected_cpu = pp->rxq_def; max_cpu = num_present_cpus(); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index e64318c110fd..6a01ab1a6e6f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -1134,7 +1134,12 @@ int otx2_init_tc(struct otx2_nic *nic) return err; tc->flow_ht_params = tc_flow_ht_params; - return rhashtable_init(&tc->flow_table, &tc->flow_ht_params); + err = rhashtable_init(&tc->flow_table, &tc->flow_ht_params); + if (err) { + kfree(tc->tc_entries_bitmap); + tc->tc_entries_bitmap = NULL; + } + return err; } EXPORT_SYMBOL(otx2_init_tc); diff --git a/drivers/net/ethernet/microchip/encx24j600-regmap.c b/drivers/net/ethernet/microchip/encx24j600-regmap.c index 81a8ccca7e5e..5693784eec5b 100644 --- a/drivers/net/ethernet/microchip/encx24j600-regmap.c +++ b/drivers/net/ethernet/microchip/encx24j600-regmap.c @@ -359,7 +359,7 @@ static int regmap_encx24j600_phy_reg_read(void *context, unsigned int reg, goto err_out; usleep_range(26, 100); - while ((ret = regmap_read(ctx->regmap, MISTAT, &mistat) != 0) && + while (((ret = regmap_read(ctx->regmap, MISTAT, &mistat)) == 0) && (mistat & BUSY)) cpu_relax(); @@ -397,7 +397,7 @@ static int regmap_encx24j600_phy_reg_write(void *context, unsigned int reg, goto err_out; usleep_range(26, 100); - while ((ret = regmap_read(ctx->regmap, MISTAT, &mistat) != 0) && + while (((ret = regmap_read(ctx->regmap, MISTAT, &mistat)) == 0) && (mistat & BUSY)) cpu_relax(); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c index 66360c8c5a38..141897dfe388 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_fdma.c @@ -317,7 +317,7 @@ int sparx5_fdma_xmit(struct sparx5 *sparx5, u32 *ifh, struct sk_buff *skb) next_dcb_hw = sparx5_fdma_next_dcb(tx, tx->curr_entry); db_hw = &next_dcb_hw->db[0]; if (!(db_hw->status & FDMA_DCB_STATUS_DONE)) - tx->dropped++; + return -EINVAL; db = list_first_entry(&tx->db_list, struct sparx5_db, list); list_move_tail(&db->list, &tx->db_list); next_dcb_hw->nextptr = FDMA_DCB_INVALID_DATA; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c index eeac04b84638..b6bbb3c9bd7a 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -887,6 +887,8 @@ static int mchp_sparx5_probe(struct platform_device *pdev) cleanup_ports: sparx5_cleanup_ports(sparx5); + if (sparx5->mact_queue) + destroy_workqueue(sparx5->mact_queue); cleanup_config: kfree(configs); cleanup_pnode: @@ -911,6 +913,7 @@ static int mchp_sparx5_remove(struct platform_device *pdev) sparx5_cleanup_ports(sparx5); /* Unregister netdevs */ sparx5_unregister_notifier_blocks(sparx5); + destroy_workqueue(sparx5->mact_queue); return 0; } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c index 83c16ca5b30f..6db6ac6a3bbc 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c @@ -234,9 +234,8 @@ netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev) sparx5_set_port_ifh(ifh, port->portno); if (sparx5->ptp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { - ret = sparx5_ptp_txtstamp_request(port, skb); - if (ret) - return ret; + if (sparx5_ptp_txtstamp_request(port, skb) < 0) + return NETDEV_TX_BUSY; sparx5_set_port_ifh_rew_op(ifh, SPARX5_SKB_CB(skb)->rew_op); sparx5_set_port_ifh_pdu_type(ifh, SPARX5_SKB_CB(skb)->pdu_type); @@ -250,23 +249,31 @@ netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev) else ret = sparx5_inject(sparx5, ifh, skb, dev); - if (ret == NETDEV_TX_OK) { - stats->tx_bytes += skb->len; - stats->tx_packets++; + if (ret == -EBUSY) + goto busy; + if (ret < 0) + goto drop; - if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP && - SPARX5_SKB_CB(skb)->rew_op == IFH_REW_OP_TWO_STEP_PTP) - return ret; + stats->tx_bytes += skb->len; + stats->tx_packets++; + sparx5->tx.packets++; - dev_kfree_skb_any(skb); - } else { - stats->tx_dropped++; + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP && + SPARX5_SKB_CB(skb)->rew_op == IFH_REW_OP_TWO_STEP_PTP) + return NETDEV_TX_OK; - if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP && - SPARX5_SKB_CB(skb)->rew_op == IFH_REW_OP_TWO_STEP_PTP) - sparx5_ptp_txtstamp_release(port, skb); - } - return ret; + dev_consume_skb_any(skb); + return NETDEV_TX_OK; +drop: + stats->tx_dropped++; + sparx5->tx.dropped++; + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; +busy: + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP && + SPARX5_SKB_CB(skb)->rew_op == IFH_REW_OP_TWO_STEP_PTP) + sparx5_ptp_txtstamp_release(port, skb); + return NETDEV_TX_BUSY; } static enum hrtimer_restart sparx5_injection_timeout(struct hrtimer *tmr) diff --git a/drivers/net/ethernet/microsoft/mana/gdma.h b/drivers/net/ethernet/microsoft/mana/gdma.h index 4a6efe6ada08..65c24ee49efd 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma.h +++ b/drivers/net/ethernet/microsoft/mana/gdma.h @@ -498,7 +498,14 @@ enum { #define GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT BIT(0) -#define GDMA_DRV_CAP_FLAGS1 GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT +/* Advertise to the NIC firmware: the NAPI work_done variable race is fixed, + * so the driver is able to reliably support features like busy_poll. + */ +#define GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX BIT(2) + +#define GDMA_DRV_CAP_FLAGS1 \ + (GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \ + GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX) #define GDMA_DRV_CAP_FLAGS2 0 diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 9259a74eca40..27a0f3af8aab 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1303,10 +1303,11 @@ static void mana_poll_rx_cq(struct mana_cq *cq) xdp_do_flush(); } -static void mana_cq_handler(void *context, struct gdma_queue *gdma_queue) +static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) { struct mana_cq *cq = context; u8 arm_bit; + int w; WARN_ON_ONCE(cq->gdma_cq != gdma_queue); @@ -1315,26 +1316,31 @@ static void mana_cq_handler(void *context, struct gdma_queue *gdma_queue) else mana_poll_tx_cq(cq); - if (cq->work_done < cq->budget && - napi_complete_done(&cq->napi, cq->work_done)) { + w = cq->work_done; + + if (w < cq->budget && + napi_complete_done(&cq->napi, w)) { arm_bit = SET_ARM_BIT; } else { arm_bit = 0; } mana_gd_ring_cq(gdma_queue, arm_bit); + + return w; } static int mana_poll(struct napi_struct *napi, int budget) { struct mana_cq *cq = container_of(napi, struct mana_cq, napi); + int w; cq->work_done = 0; cq->budget = budget; - mana_cq_handler(cq, cq->gdma_cq); + w = mana_cq_handler(cq, cq->gdma_cq); - return min(cq->work_done, budget); + return min(w, budget); } static void mana_schedule_napi(void *context, struct gdma_queue *gdma_queue) diff --git a/drivers/net/ethernet/netronome/nfp/nfdk/dp.c b/drivers/net/ethernet/netronome/nfp/nfdk/dp.c index 2b427d8ccb2f..ccacb6ab6c39 100644 --- a/drivers/net/ethernet/netronome/nfp/nfdk/dp.c +++ b/drivers/net/ethernet/netronome/nfp/nfdk/dp.c @@ -282,7 +282,7 @@ netdev_tx_t nfp_nfdk_tx(struct sk_buff *skb, struct net_device *netdev) dma_len = skb_headlen(skb); if (skb_is_gso(skb)) type = NFDK_DESC_TX_TYPE_TSO; - else if (!nr_frags && dma_len < NFDK_TX_MAX_DATA_PER_HEAD) + else if (!nr_frags && dma_len <= NFDK_TX_MAX_DATA_PER_HEAD) type = NFDK_DESC_TX_TYPE_SIMPLE; else type = NFDK_DESC_TX_TYPE_GATHER; @@ -927,7 +927,7 @@ nfp_nfdk_tx_xdp_buf(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring, dma_len = pkt_len; dma_addr = rxbuf->dma_addr + dma_off; - if (dma_len < NFDK_TX_MAX_DATA_PER_HEAD) + if (dma_len <= NFDK_TX_MAX_DATA_PER_HEAD) type = NFDK_DESC_TX_TYPE_SIMPLE; else type = NFDK_DESC_TX_TYPE_GATHER; @@ -1325,7 +1325,7 @@ nfp_nfdk_ctrl_tx_one(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, txbuf = &tx_ring->ktxbufs[wr_idx]; dma_len = skb_headlen(skb); - if (dma_len < NFDK_TX_MAX_DATA_PER_HEAD) + if (dma_len <= NFDK_TX_MAX_DATA_PER_HEAD) type = NFDK_DESC_TX_TYPE_SIMPLE; else type = NFDK_DESC_TX_TYPE_GATHER; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 6bc923326268..33f723a9f471 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -841,7 +841,7 @@ static bool ravb_rx_gbeth(struct net_device *ndev, int *quota, int q) napi_gro_receive(&priv->napi[q], priv->rx_1st_skb); stats->rx_packets++; - stats->rx_bytes += priv->rx_1st_skb->len; + stats->rx_bytes += pkt_len; break; } } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 50f6b4a14be4..eb6d9cd8e93f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -108,10 +108,10 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev) axi->axi_lpi_en = of_property_read_bool(np, "snps,lpi_en"); axi->axi_xit_frm = of_property_read_bool(np, "snps,xit_frm"); - axi->axi_kbbe = of_property_read_bool(np, "snps,axi_kbbe"); - axi->axi_fb = of_property_read_bool(np, "snps,axi_fb"); - axi->axi_mb = of_property_read_bool(np, "snps,axi_mb"); - axi->axi_rb = of_property_read_bool(np, "snps,axi_rb"); + axi->axi_kbbe = of_property_read_bool(np, "snps,kbbe"); + axi->axi_fb = of_property_read_bool(np, "snps,fb"); + axi->axi_mb = of_property_read_bool(np, "snps,mb"); + axi->axi_rb = of_property_read_bool(np, "snps,rb"); if (of_property_read_u32(np, "snps,wr_osr_lmt", &axi->axi_wr_osr_lmt)) axi->axi_wr_osr_lmt = 1; diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index d04a239c658e..b3b0ba842541 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1454,7 +1454,7 @@ static void am65_cpsw_nuss_mac_link_up(struct phylink_config *config, struct phy if (speed == SPEED_1000) mac_control |= CPSW_SL_CTL_GIG; - if (speed == SPEED_10 && interface == PHY_INTERFACE_MODE_RGMII) + if (speed == SPEED_10 && phy_interface_mode_is_rgmii(interface)) /* Can be used with in band mode only */ mac_control |= CPSW_SL_CTL_EXT_EN; if (speed == SPEED_100 && interface == PHY_INTERFACE_MODE_RMII) diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index 450b16ad40a4..e1a569b99e4a 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -885,7 +885,7 @@ static int ca8210_spi_transfer( dev_dbg(&spi->dev, "%s called\n", __func__); - cas_ctl = kmalloc(sizeof(*cas_ctl), GFP_ATOMIC); + cas_ctl = kzalloc(sizeof(*cas_ctl), GFP_ATOMIC); if (!cas_ctl) return -ENOMEM; diff --git a/drivers/net/ieee802154/cc2520.c b/drivers/net/ieee802154/cc2520.c index c69b87d3837d..edc769daad07 100644 --- a/drivers/net/ieee802154/cc2520.c +++ b/drivers/net/ieee802154/cc2520.c @@ -970,7 +970,7 @@ static int cc2520_hw_init(struct cc2520_private *priv) if (timeout-- <= 0) { dev_err(&priv->spi->dev, "oscillator start failed!\n"); - return ret; + return -ETIMEDOUT; } udelay(1); } while (!(status & CC2520_STATUS_XOSC32M_STABLE)); diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index f41f67b583db..2fbac51b9b19 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3698,6 +3698,7 @@ static const struct nla_policy macsec_rtnl_policy[IFLA_MACSEC_MAX + 1] = { [IFLA_MACSEC_SCB] = { .type = NLA_U8 }, [IFLA_MACSEC_REPLAY_PROTECT] = { .type = NLA_U8 }, [IFLA_MACSEC_VALIDATION] = { .type = NLA_U8 }, + [IFLA_MACSEC_OFFLOAD] = { .type = NLA_U8 }, }; static void macsec_free_netdev(struct net_device *dev) diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c index eb344f6d4a7b..b782c35c4ac1 100644 --- a/drivers/net/mdio/fwnode_mdio.c +++ b/drivers/net/mdio/fwnode_mdio.c @@ -98,6 +98,7 @@ int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, */ rc = phy_device_register(phy); if (rc) { + device_set_node(&phy->mdio.dev, NULL); fwnode_handle_put(child); return rc; } @@ -153,7 +154,8 @@ int fwnode_mdiobus_register_phy(struct mii_bus *bus, /* All data is now stored in the phy struct, so register it */ rc = phy_device_register(phy); if (rc) { - fwnode_handle_put(phy->mdio.dev.fwnode); + phy->mdio.dev.fwnode = NULL; + fwnode_handle_put(child); goto clean_phy; } } else if (is_of_node(child)) { diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c index 796e9c7857d0..510822d6d0d9 100644 --- a/drivers/net/mdio/of_mdio.c +++ b/drivers/net/mdio/of_mdio.c @@ -68,8 +68,9 @@ static int of_mdiobus_register_device(struct mii_bus *mdio, /* All data is now stored in the mdiodev struct; register it. */ rc = mdio_device_register(mdiodev); if (rc) { + device_set_node(&mdiodev->dev, NULL); + fwnode_handle_put(fwnode); mdio_device_free(mdiodev); - of_node_put(child); return rc; } diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c index 250742ffdfd9..044828d081d2 100644 --- a/drivers/net/phy/mdio_device.c +++ b/drivers/net/phy/mdio_device.c @@ -21,6 +21,7 @@ #include <linux/slab.h> #include <linux/string.h> #include <linux/unistd.h> +#include <linux/property.h> void mdio_device_free(struct mdio_device *mdiodev) { @@ -30,6 +31,7 @@ EXPORT_SYMBOL(mdio_device_free); static void mdio_device_release(struct device *dev) { + fwnode_handle_put(dev->fwnode); kfree(to_mdio_device(dev)); } diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c index 24bae27eedef..cae24091fb6f 100644 --- a/drivers/net/phy/mxl-gpy.c +++ b/drivers/net/phy/mxl-gpy.c @@ -9,6 +9,7 @@ #include <linux/module.h> #include <linux/bitfield.h> #include <linux/hwmon.h> +#include <linux/mutex.h> #include <linux/phy.h> #include <linux/polynomial.h> #include <linux/netdevice.h> @@ -70,6 +71,14 @@ #define VPSPEC1_TEMP_STA 0x0E #define VPSPEC1_TEMP_STA_DATA GENMASK(9, 0) +/* Mailbox */ +#define VSPEC1_MBOX_DATA 0x5 +#define VSPEC1_MBOX_ADDRLO 0x6 +#define VSPEC1_MBOX_CMD 0x7 +#define VSPEC1_MBOX_CMD_ADDRHI GENMASK(7, 0) +#define VSPEC1_MBOX_CMD_RD (0 << 8) +#define VSPEC1_MBOX_CMD_READY BIT(15) + /* WoL */ #define VPSPEC2_WOL_CTL 0x0E06 #define VPSPEC2_WOL_AD01 0x0E08 @@ -77,7 +86,13 @@ #define VPSPEC2_WOL_AD45 0x0E0A #define WOL_EN BIT(0) +/* Internal registers, access via mbox */ +#define REG_GPIO0_OUT 0xd3ce00 + struct gpy_priv { + /* serialize mailbox acesses */ + struct mutex mbox_lock; + u8 fw_major; u8 fw_minor; }; @@ -187,6 +202,45 @@ static int gpy_hwmon_register(struct phy_device *phydev) } #endif +static int gpy_mbox_read(struct phy_device *phydev, u32 addr) +{ + struct gpy_priv *priv = phydev->priv; + int val, ret; + u16 cmd; + + mutex_lock(&priv->mbox_lock); + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND1, VSPEC1_MBOX_ADDRLO, + addr); + if (ret) + goto out; + + cmd = VSPEC1_MBOX_CMD_RD; + cmd |= FIELD_PREP(VSPEC1_MBOX_CMD_ADDRHI, addr >> 16); + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND1, VSPEC1_MBOX_CMD, cmd); + if (ret) + goto out; + + /* The mbox read is used in the interrupt workaround. It was observed + * that a read might take up to 2.5ms. This is also the time for which + * the interrupt line is stuck low. To be on the safe side, poll the + * ready bit for 10ms. + */ + ret = phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1, + VSPEC1_MBOX_CMD, val, + (val & VSPEC1_MBOX_CMD_READY), + 500, 10000, false); + if (ret) + goto out; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, VSPEC1_MBOX_DATA); + +out: + mutex_unlock(&priv->mbox_lock); + return ret; +} + static int gpy_config_init(struct phy_device *phydev) { int ret; @@ -201,6 +255,13 @@ static int gpy_config_init(struct phy_device *phydev) return ret < 0 ? ret : 0; } +static bool gpy_has_broken_mdint(struct phy_device *phydev) +{ + /* At least these PHYs are known to have broken interrupt handling */ + return phydev->drv->phy_id == PHY_ID_GPY215B || + phydev->drv->phy_id == PHY_ID_GPY215C; +} + static int gpy_probe(struct phy_device *phydev) { struct device *dev = &phydev->mdio.dev; @@ -218,6 +279,7 @@ static int gpy_probe(struct phy_device *phydev) if (!priv) return -ENOMEM; phydev->priv = priv; + mutex_init(&priv->mbox_lock); fw_version = phy_read(phydev, PHY_FWV); if (fw_version < 0) @@ -492,6 +554,29 @@ static irqreturn_t gpy_handle_interrupt(struct phy_device *phydev) if (!(reg & PHY_IMASK_MASK)) return IRQ_NONE; + /* The PHY might leave the interrupt line asserted even after PHY_ISTAT + * is read. To avoid interrupt storms, delay the interrupt handling as + * long as the PHY drives the interrupt line. An internal bus read will + * stall as long as the interrupt line is asserted, thus just read a + * random register here. + * Because we cannot access the internal bus at all while the interrupt + * is driven by the PHY, there is no way to make the interrupt line + * unstuck (e.g. by changing the pinmux to GPIO input) during that time + * frame. Therefore, polling is the best we can do and won't do any more + * harm. + * It was observed that this bug happens on link state and link speed + * changes on a GPY215B and GYP215C independent of the firmware version + * (which doesn't mean that this list is exhaustive). + */ + if (gpy_has_broken_mdint(phydev) && + (reg & (PHY_IMASK_LSTC | PHY_IMASK_LSPC))) { + reg = gpy_mbox_read(phydev, REG_GPIO0_OUT); + if (reg < 0) { + phy_error(phydev); + return IRQ_NONE; + } + } + phy_trigger_machine(phydev); return IRQ_HANDLED; diff --git a/drivers/net/plip/plip.c b/drivers/net/plip/plip.c index c8791e9b451d..40ce8abe6999 100644 --- a/drivers/net/plip/plip.c +++ b/drivers/net/plip/plip.c @@ -450,12 +450,12 @@ plip_bh_timeout_error(struct net_device *dev, struct net_local *nl, } rcv->state = PLIP_PK_DONE; if (rcv->skb) { - kfree_skb(rcv->skb); + dev_kfree_skb_irq(rcv->skb); rcv->skb = NULL; } snd->state = PLIP_PK_DONE; if (snd->skb) { - dev_kfree_skb(snd->skb); + dev_consume_skb_irq(snd->skb); snd->skb = NULL; } spin_unlock_irq(&nl->lock); diff --git a/drivers/net/thunderbolt.c b/drivers/net/thunderbolt.c index a52ee2bf5575..6312f67f260e 100644 --- a/drivers/net/thunderbolt.c +++ b/drivers/net/thunderbolt.c @@ -914,6 +914,7 @@ static int tbnet_open(struct net_device *dev) eof_mask, tbnet_start_poll, net); if (!ring) { netdev_err(dev, "failed to allocate Rx ring\n"); + tb_xdomain_release_out_hopid(xd, hopid); tb_ring_free(net->tx_ring.ring); net->tx_ring.ring = NULL; return -ENOMEM; diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index d3e7b27eb933..6f1e560fb15c 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -75,8 +75,14 @@ vmxnet3_enable_all_intrs(struct vmxnet3_adapter *adapter) for (i = 0; i < adapter->intr.num_intrs; i++) vmxnet3_enable_intr(adapter, i); - adapter->shared->devRead.intrConf.intrCtrl &= + if (!VMXNET3_VERSION_GE_6(adapter) || + !adapter->queuesExtEnabled) { + adapter->shared->devRead.intrConf.intrCtrl &= + cpu_to_le32(~VMXNET3_IC_DISABLE_ALL); + } else { + adapter->shared->devReadExt.intrConfExt.intrCtrl &= cpu_to_le32(~VMXNET3_IC_DISABLE_ALL); + } } @@ -85,8 +91,14 @@ vmxnet3_disable_all_intrs(struct vmxnet3_adapter *adapter) { int i; - adapter->shared->devRead.intrConf.intrCtrl |= + if (!VMXNET3_VERSION_GE_6(adapter) || + !adapter->queuesExtEnabled) { + adapter->shared->devRead.intrConf.intrCtrl |= + cpu_to_le32(VMXNET3_IC_DISABLE_ALL); + } else { + adapter->shared->devReadExt.intrConfExt.intrCtrl |= cpu_to_le32(VMXNET3_IC_DISABLE_ALL); + } for (i = 0; i < adapter->intr.num_intrs; i++) vmxnet3_disable_intr(adapter, i); } @@ -1396,6 +1408,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, }; u32 num_pkts = 0; bool skip_page_frags = false; + bool encap_lro = false; struct Vmxnet3_RxCompDesc *rcd; struct vmxnet3_rx_ctx *ctx = &rq->rx_ctx; u16 segCnt = 0, mss = 0; @@ -1556,13 +1569,18 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, if (VMXNET3_VERSION_GE_2(adapter) && rcd->type == VMXNET3_CDTYPE_RXCOMP_LRO) { struct Vmxnet3_RxCompDescExt *rcdlro; + union Vmxnet3_GenericDesc *gdesc; + rcdlro = (struct Vmxnet3_RxCompDescExt *)rcd; + gdesc = (union Vmxnet3_GenericDesc *)rcd; segCnt = rcdlro->segCnt; WARN_ON_ONCE(segCnt == 0); mss = rcdlro->mss; if (unlikely(segCnt <= 1)) segCnt = 0; + encap_lro = (le32_to_cpu(gdesc->dword[0]) & + (1UL << VMXNET3_RCD_HDR_INNER_SHIFT)); } else { segCnt = 0; } @@ -1630,7 +1648,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, vmxnet3_rx_csum(adapter, skb, (union Vmxnet3_GenericDesc *)rcd); skb->protocol = eth_type_trans(skb, adapter->netdev); - if (!rcd->tcp || + if ((!rcd->tcp && !encap_lro) || !(adapter->netdev->features & NETIF_F_LRO)) goto not_lro; @@ -1639,7 +1657,7 @@ vmxnet3_rq_rx_complete(struct vmxnet3_rx_queue *rq, SKB_GSO_TCPV4 : SKB_GSO_TCPV6; skb_shinfo(skb)->gso_size = mss; skb_shinfo(skb)->gso_segs = segCnt; - } else if (segCnt != 0 || skb->len > mtu) { + } else if ((segCnt != 0 || skb->len > mtu) && !encap_lro) { u32 hlen; hlen = vmxnet3_get_hdr_len(adapter, skb, @@ -1668,6 +1686,7 @@ not_lro: napi_gro_receive(&rq->napi, skb); ctx->skb = NULL; + encap_lro = false; num_pkts++; } diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux.c b/drivers/net/wwan/iosm/iosm_ipc_mux.c index 9c7a9a2a1f25..fc928b298a98 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux.c +++ b/drivers/net/wwan/iosm/iosm_ipc_mux.c @@ -332,6 +332,7 @@ struct iosm_mux *ipc_mux_init(struct ipc_mux_config *mux_cfg, if (!ipc_mux->ul_adb.pp_qlt[i]) { for (j = i - 1; j >= 0; j--) kfree(ipc_mux->ul_adb.pp_qlt[j]); + kfree(ipc_mux); return NULL; } } diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 1545cbee77a4..3dbfc8a6924e 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -386,7 +386,7 @@ int xenvif_dealloc_kthread(void *data); irqreturn_t xenvif_ctrl_irq_fn(int irq, void *data); bool xenvif_have_rx_work(struct xenvif_queue *queue, bool test_kthread); -void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb); +bool xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb); void xenvif_carrier_on(struct xenvif *vif); diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 650fa180220f..f3f2c07423a6 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -254,14 +254,16 @@ xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE) skb_clear_hash(skb); - xenvif_rx_queue_tail(queue, skb); + if (!xenvif_rx_queue_tail(queue, skb)) + goto drop; + xenvif_kick_thread(queue); return NETDEV_TX_OK; drop: vif->dev->stats.tx_dropped++; - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 3d2081bbbc86..bf627af723bf 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -332,10 +332,13 @@ static int xenvif_count_requests(struct xenvif_queue *queue, struct xenvif_tx_cb { - u16 pending_idx; + u16 copy_pending_idx[XEN_NETBK_LEGACY_SLOTS_MAX + 1]; + u8 copy_count; }; #define XENVIF_TX_CB(skb) ((struct xenvif_tx_cb *)(skb)->cb) +#define copy_pending_idx(skb, i) (XENVIF_TX_CB(skb)->copy_pending_idx[i]) +#define copy_count(skb) (XENVIF_TX_CB(skb)->copy_count) static inline void xenvif_tx_create_map_op(struct xenvif_queue *queue, u16 pending_idx, @@ -370,31 +373,93 @@ static inline struct sk_buff *xenvif_alloc_skb(unsigned int size) return skb; } -static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif_queue *queue, - struct sk_buff *skb, - struct xen_netif_tx_request *txp, - struct gnttab_map_grant_ref *gop, - unsigned int frag_overflow, - struct sk_buff *nskb) +static void xenvif_get_requests(struct xenvif_queue *queue, + struct sk_buff *skb, + struct xen_netif_tx_request *first, + struct xen_netif_tx_request *txfrags, + unsigned *copy_ops, + unsigned *map_ops, + unsigned int frag_overflow, + struct sk_buff *nskb, + unsigned int extra_count, + unsigned int data_len) { struct skb_shared_info *shinfo = skb_shinfo(skb); skb_frag_t *frags = shinfo->frags; - u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx; - int start; + u16 pending_idx; pending_ring_idx_t index; unsigned int nr_slots; + struct gnttab_copy *cop = queue->tx_copy_ops + *copy_ops; + struct gnttab_map_grant_ref *gop = queue->tx_map_ops + *map_ops; + struct xen_netif_tx_request *txp = first; + + nr_slots = shinfo->nr_frags + 1; + + copy_count(skb) = 0; + + /* Create copy ops for exactly data_len bytes into the skb head. */ + __skb_put(skb, data_len); + while (data_len > 0) { + int amount = data_len > txp->size ? txp->size : data_len; + + cop->source.u.ref = txp->gref; + cop->source.domid = queue->vif->domid; + cop->source.offset = txp->offset; + + cop->dest.domid = DOMID_SELF; + cop->dest.offset = (offset_in_page(skb->data + + skb_headlen(skb) - + data_len)) & ~XEN_PAGE_MASK; + cop->dest.u.gmfn = virt_to_gfn(skb->data + skb_headlen(skb) + - data_len); + + cop->len = amount; + cop->flags = GNTCOPY_source_gref; - nr_slots = shinfo->nr_frags; + index = pending_index(queue->pending_cons); + pending_idx = queue->pending_ring[index]; + callback_param(queue, pending_idx).ctx = NULL; + copy_pending_idx(skb, copy_count(skb)) = pending_idx; + copy_count(skb)++; + + cop++; + data_len -= amount; - /* Skip first skb fragment if it is on same page as header fragment. */ - start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx); + if (amount == txp->size) { + /* The copy op covered the full tx_request */ + + memcpy(&queue->pending_tx_info[pending_idx].req, + txp, sizeof(*txp)); + queue->pending_tx_info[pending_idx].extra_count = + (txp == first) ? extra_count : 0; + + if (txp == first) + txp = txfrags; + else + txp++; + queue->pending_cons++; + nr_slots--; + } else { + /* The copy op partially covered the tx_request. + * The remainder will be mapped. + */ + txp->offset += amount; + txp->size -= amount; + } + } - for (shinfo->nr_frags = start; shinfo->nr_frags < nr_slots; - shinfo->nr_frags++, txp++, gop++) { + for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; + shinfo->nr_frags++, gop++) { index = pending_index(queue->pending_cons++); pending_idx = queue->pending_ring[index]; - xenvif_tx_create_map_op(queue, pending_idx, txp, 0, gop); + xenvif_tx_create_map_op(queue, pending_idx, txp, + txp == first ? extra_count : 0, gop); frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx); + + if (txp == first) + txp = txfrags; + else + txp++; } if (frag_overflow) { @@ -415,7 +480,8 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif_queue *que skb_shinfo(skb)->frag_list = nskb; } - return gop; + (*copy_ops) = cop - queue->tx_copy_ops; + (*map_ops) = gop - queue->tx_map_ops; } static inline void xenvif_grant_handle_set(struct xenvif_queue *queue, @@ -451,7 +517,7 @@ static int xenvif_tx_check_gop(struct xenvif_queue *queue, struct gnttab_copy **gopp_copy) { struct gnttab_map_grant_ref *gop_map = *gopp_map; - u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx; + u16 pending_idx; /* This always points to the shinfo of the skb being checked, which * could be either the first or the one on the frag_list */ @@ -462,24 +528,37 @@ static int xenvif_tx_check_gop(struct xenvif_queue *queue, struct skb_shared_info *first_shinfo = NULL; int nr_frags = shinfo->nr_frags; const bool sharedslot = nr_frags && - frag_get_pending_idx(&shinfo->frags[0]) == pending_idx; - int i, err; + frag_get_pending_idx(&shinfo->frags[0]) == + copy_pending_idx(skb, copy_count(skb) - 1); + int i, err = 0; - /* Check status of header. */ - err = (*gopp_copy)->status; - if (unlikely(err)) { - if (net_ratelimit()) - netdev_dbg(queue->vif->dev, - "Grant copy of header failed! status: %d pending_idx: %u ref: %u\n", - (*gopp_copy)->status, - pending_idx, - (*gopp_copy)->source.u.ref); - /* The first frag might still have this slot mapped */ - if (!sharedslot) - xenvif_idx_release(queue, pending_idx, - XEN_NETIF_RSP_ERROR); + for (i = 0; i < copy_count(skb); i++) { + int newerr; + + /* Check status of header. */ + pending_idx = copy_pending_idx(skb, i); + + newerr = (*gopp_copy)->status; + if (likely(!newerr)) { + /* The first frag might still have this slot mapped */ + if (i < copy_count(skb) - 1 || !sharedslot) + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_OKAY); + } else { + err = newerr; + if (net_ratelimit()) + netdev_dbg(queue->vif->dev, + "Grant copy of header failed! status: %d pending_idx: %u ref: %u\n", + (*gopp_copy)->status, + pending_idx, + (*gopp_copy)->source.u.ref); + /* The first frag might still have this slot mapped */ + if (i < copy_count(skb) - 1 || !sharedslot) + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_ERROR); + } + (*gopp_copy)++; } - (*gopp_copy)++; check_frags: for (i = 0; i < nr_frags; i++, gop_map++) { @@ -526,14 +605,6 @@ check_frags: if (err) continue; - /* First error: if the header haven't shared a slot with the - * first frag, release it as well. - */ - if (!sharedslot) - xenvif_idx_release(queue, - XENVIF_TX_CB(skb)->pending_idx, - XEN_NETIF_RSP_OKAY); - /* Invalidate preceding fragments of this skb. */ for (j = 0; j < i; j++) { pending_idx = frag_get_pending_idx(&shinfo->frags[j]); @@ -803,7 +874,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, unsigned *copy_ops, unsigned *map_ops) { - struct gnttab_map_grant_ref *gop = queue->tx_map_ops; struct sk_buff *skb, *nskb; int ret; unsigned int frag_overflow; @@ -885,8 +955,12 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, continue; } + data_len = (txreq.size > XEN_NETBACK_TX_COPY_LEN) ? + XEN_NETBACK_TX_COPY_LEN : txreq.size; + ret = xenvif_count_requests(queue, &txreq, extra_count, txfrags, work_to_do); + if (unlikely(ret < 0)) break; @@ -912,9 +986,8 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, index = pending_index(queue->pending_cons); pending_idx = queue->pending_ring[index]; - data_len = (txreq.size > XEN_NETBACK_TX_COPY_LEN && - ret < XEN_NETBK_LEGACY_SLOTS_MAX) ? - XEN_NETBACK_TX_COPY_LEN : txreq.size; + if (ret >= XEN_NETBK_LEGACY_SLOTS_MAX - 1 && data_len < txreq.size) + data_len = txreq.size; skb = xenvif_alloc_skb(data_len); if (unlikely(skb == NULL)) { @@ -925,8 +998,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, } skb_shinfo(skb)->nr_frags = ret; - if (data_len < txreq.size) - skb_shinfo(skb)->nr_frags++; /* At this point shinfo->nr_frags is in fact the number of * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX. */ @@ -988,54 +1059,19 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, type); } - XENVIF_TX_CB(skb)->pending_idx = pending_idx; - - __skb_put(skb, data_len); - queue->tx_copy_ops[*copy_ops].source.u.ref = txreq.gref; - queue->tx_copy_ops[*copy_ops].source.domid = queue->vif->domid; - queue->tx_copy_ops[*copy_ops].source.offset = txreq.offset; - - queue->tx_copy_ops[*copy_ops].dest.u.gmfn = - virt_to_gfn(skb->data); - queue->tx_copy_ops[*copy_ops].dest.domid = DOMID_SELF; - queue->tx_copy_ops[*copy_ops].dest.offset = - offset_in_page(skb->data) & ~XEN_PAGE_MASK; - - queue->tx_copy_ops[*copy_ops].len = data_len; - queue->tx_copy_ops[*copy_ops].flags = GNTCOPY_source_gref; - - (*copy_ops)++; - - if (data_len < txreq.size) { - frag_set_pending_idx(&skb_shinfo(skb)->frags[0], - pending_idx); - xenvif_tx_create_map_op(queue, pending_idx, &txreq, - extra_count, gop); - gop++; - } else { - frag_set_pending_idx(&skb_shinfo(skb)->frags[0], - INVALID_PENDING_IDX); - memcpy(&queue->pending_tx_info[pending_idx].req, - &txreq, sizeof(txreq)); - queue->pending_tx_info[pending_idx].extra_count = - extra_count; - } - - queue->pending_cons++; - - gop = xenvif_get_requests(queue, skb, txfrags, gop, - frag_overflow, nskb); + xenvif_get_requests(queue, skb, &txreq, txfrags, copy_ops, + map_ops, frag_overflow, nskb, extra_count, + data_len); __skb_queue_tail(&queue->tx_queue, skb); queue->tx.req_cons = idx; - if (((gop-queue->tx_map_ops) >= ARRAY_SIZE(queue->tx_map_ops)) || + if ((*map_ops >= ARRAY_SIZE(queue->tx_map_ops)) || (*copy_ops >= ARRAY_SIZE(queue->tx_copy_ops))) break; } - (*map_ops) = gop - queue->tx_map_ops; return; } @@ -1114,9 +1150,8 @@ static int xenvif_tx_submit(struct xenvif_queue *queue) while ((skb = __skb_dequeue(&queue->tx_queue)) != NULL) { struct xen_netif_tx_request *txp; u16 pending_idx; - unsigned data_len; - pending_idx = XENVIF_TX_CB(skb)->pending_idx; + pending_idx = copy_pending_idx(skb, 0); txp = &queue->pending_tx_info[pending_idx].req; /* Check the remap error code. */ @@ -1135,18 +1170,6 @@ static int xenvif_tx_submit(struct xenvif_queue *queue) continue; } - data_len = skb->len; - callback_param(queue, pending_idx).ctx = NULL; - if (data_len < txp->size) { - /* Append the packet payload as a fragment. */ - txp->offset += data_len; - txp->size -= data_len; - } else { - /* Schedule a response immediately. */ - xenvif_idx_release(queue, pending_idx, - XEN_NETIF_RSP_OKAY); - } - if (txp->flags & XEN_NETTXF_csum_blank) skb->ip_summed = CHECKSUM_PARTIAL; else if (txp->flags & XEN_NETTXF_data_validated) @@ -1332,7 +1355,7 @@ static inline void xenvif_tx_dealloc_action(struct xenvif_queue *queue) /* Called after netfront has transmitted */ int xenvif_tx_action(struct xenvif_queue *queue, int budget) { - unsigned nr_mops, nr_cops = 0; + unsigned nr_mops = 0, nr_cops = 0; int work_done, ret; if (unlikely(!tx_work_todo(queue))) diff --git a/drivers/net/xen-netback/rx.c b/drivers/net/xen-netback/rx.c index 932762177110..0ba754ebc5ba 100644 --- a/drivers/net/xen-netback/rx.c +++ b/drivers/net/xen-netback/rx.c @@ -82,9 +82,10 @@ static bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue) return false; } -void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb) +bool xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb) { unsigned long flags; + bool ret = true; spin_lock_irqsave(&queue->rx_queue.lock, flags); @@ -92,8 +93,7 @@ void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb) struct net_device *dev = queue->vif->dev; netif_tx_stop_queue(netdev_get_tx_queue(dev, queue->id)); - kfree_skb(skb); - queue->vif->dev->stats.rx_dropped++; + ret = false; } else { if (skb_queue_empty(&queue->rx_queue)) xenvif_update_needed_slots(queue, skb); @@ -104,6 +104,8 @@ void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb) } spin_unlock_irqrestore(&queue->rx_queue.lock, flags); + + return ret; } static struct sk_buff *xenvif_rx_dequeue(struct xenvif_queue *queue) diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 9af2b027c19c..dc404e05970c 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -1862,6 +1862,12 @@ static int netfront_resume(struct xenbus_device *dev) netif_tx_unlock_bh(info->netdev); xennet_disconnect_backend(info); + + rtnl_lock(); + if (info->queues) + xennet_destroy_queues(info); + rtnl_unlock(); + return 0; } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 69e333922bea..7e3893d06bab 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3095,10 +3095,6 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) if (!ctrl->identified) { unsigned int i; - ret = nvme_init_subsystem(ctrl, id); - if (ret) - goto out_free; - /* * Check for quirks. Quirk can depend on firmware version, * so, in principle, the set of quirks present can change @@ -3111,6 +3107,10 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) if (quirk_matches(id, &core_quirks[i])) ctrl->quirks |= core_quirks[i].quirks; } + + ret = nvme_init_subsystem(ctrl, id); + if (ret) + goto out_free; } memcpy(ctrl->subsys->firmware_rev, id->fr, sizeof(ctrl->subsys->firmware_rev)); diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig index 55c028af4bd9..9309f2469b41 100644 --- a/drivers/pci/Kconfig +++ b/drivers/pci/Kconfig @@ -51,11 +51,6 @@ config PCI_MSI If you don't know what to do here, say Y. -config PCI_MSI_IRQ_DOMAIN - def_bool y - depends on PCI_MSI - select GENERIC_MSI_IRQ_DOMAIN - config PCI_MSI_ARCH_FALLBACKS bool @@ -192,7 +187,7 @@ config PCI_LABEL config PCI_HYPERV tristate "Hyper-V PCI Frontend" - depends on ((X86 && X86_64) || ARM64) && HYPERV && PCI_MSI && PCI_MSI_IRQ_DOMAIN && SYSFS + depends on ((X86 && X86_64) || ARM64) && HYPERV && PCI_MSI && SYSFS select PCI_HYPERV_INTERFACE help The PCI device frontend driver allows the kernel to import arbitrary diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig index bfd9bac37e24..1569d9a3ada0 100644 --- a/drivers/pci/controller/Kconfig +++ b/drivers/pci/controller/Kconfig @@ -19,7 +19,7 @@ config PCI_AARDVARK tristate "Aardvark PCIe controller" depends on (ARCH_MVEBU && ARM64) || COMPILE_TEST depends on OF - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCI_BRIDGE_EMUL help Add support for Aardvark 64bit PCIe Host Controller. This @@ -29,7 +29,7 @@ config PCI_AARDVARK config PCIE_XILINX_NWL bool "NWL PCIe Core" depends on ARCH_ZYNQMP || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI help Say 'Y' here if you want kernel support for Xilinx NWL PCIe controller. The controller can act as Root Port @@ -53,7 +53,7 @@ config PCI_IXP4XX config PCI_TEGRA bool "NVIDIA Tegra PCIe controller" depends on ARCH_TEGRA || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI help Say Y here if you want support for the PCIe host controller found on NVIDIA Tegra SoCs. @@ -70,7 +70,7 @@ config PCI_RCAR_GEN2 config PCIE_RCAR_HOST bool "Renesas R-Car PCIe host controller" depends on ARCH_RENESAS || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI help Say Y here if you want PCIe controller support on R-Car SoCs in host mode. @@ -99,7 +99,7 @@ config PCI_HOST_GENERIC config PCIE_XILINX bool "Xilinx AXI PCIe host bridge support" depends on OF || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI help Say 'Y' here if you want kernel to support the Xilinx AXI PCIe Host Bridge driver. @@ -124,7 +124,7 @@ config PCI_XGENE config PCI_XGENE_MSI bool "X-Gene v1 PCIe MSI feature" depends on PCI_XGENE - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI default y help Say Y here if you want PCIe MSI support for the APM X-Gene v1 SoC. @@ -170,7 +170,7 @@ config PCIE_IPROC_BCMA config PCIE_IPROC_MSI bool "Broadcom iProc PCIe MSI support" depends on PCIE_IPROC_PLATFORM || PCIE_IPROC_BCMA - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI default ARCH_BCM_IPROC help Say Y here if you want to enable MSI support for Broadcom's iProc @@ -186,7 +186,7 @@ config PCIE_ALTERA config PCIE_ALTERA_MSI tristate "Altera PCIe MSI feature" depends on PCIE_ALTERA - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI help Say Y here if you want PCIe MSI support for the Altera FPGA. This MSI driver supports Altera MSI to GIC controller IP. @@ -215,7 +215,7 @@ config PCIE_ROCKCHIP_HOST tristate "Rockchip PCIe host controller" depends on ARCH_ROCKCHIP || COMPILE_TEST depends on OF - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select MFD_SYSCON select PCIE_ROCKCHIP help @@ -239,7 +239,7 @@ config PCIE_MEDIATEK tristate "MediaTek PCIe controller" depends on ARCH_AIROHA || ARCH_MEDIATEK || COMPILE_TEST depends on OF - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI help Say Y here if you want to enable PCIe controller support on MediaTek SoCs. @@ -247,7 +247,7 @@ config PCIE_MEDIATEK config PCIE_MEDIATEK_GEN3 tristate "MediaTek Gen3 PCIe controller" depends on ARCH_MEDIATEK || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI help Adds support for PCIe Gen3 MAC controller for MediaTek SoCs. This PCIe controller is compatible with Gen3, Gen2 and Gen1 speed, @@ -277,7 +277,7 @@ config PCIE_BRCMSTB depends on ARCH_BRCMSTB || ARCH_BCM2835 || ARCH_BCMBCA || \ BMIPS_GENERIC || COMPILE_TEST depends on OF - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI default ARCH_BRCMSTB || BMIPS_GENERIC help Say Y here to enable PCIe host controller support for @@ -285,7 +285,7 @@ config PCIE_BRCMSTB config PCI_HYPERV_INTERFACE tristate "Hyper-V PCI Interface" - depends on ((X86 && X86_64) || ARM64) && HYPERV && PCI_MSI && PCI_MSI_IRQ_DOMAIN + depends on ((X86 && X86_64) || ARM64) && HYPERV && PCI_MSI && PCI_MSI help The Hyper-V PCI Interface is a helper driver allows other drivers to have a common interface with the Hyper-V PCI frontend driver. @@ -303,8 +303,6 @@ config PCI_LOONGSON config PCIE_MICROCHIP_HOST bool "Microchip AXI PCIe host bridge support" depends on PCI_MSI && OF - select PCI_MSI_IRQ_DOMAIN - select GENERIC_MSI_IRQ_DOMAIN select PCI_HOST_COMMON help Say Y here if you want kernel to support the Microchip AXI PCIe @@ -326,7 +324,7 @@ config PCIE_APPLE tristate "Apple PCIe controller" depends on ARCH_APPLE || COMPILE_TEST depends on OF - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCI_HOST_COMMON help Say Y here if you want to enable PCIe controller support on Apple diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig index 62ce3abf0f19..f3c462130627 100644 --- a/drivers/pci/controller/dwc/Kconfig +++ b/drivers/pci/controller/dwc/Kconfig @@ -21,7 +21,7 @@ config PCI_DRA7XX_HOST tristate "TI DRA7xx PCIe controller Host Mode" depends on SOC_DRA7XX || COMPILE_TEST depends on OF && HAS_IOMEM && TI_PIPE3 - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST select PCI_DRA7XX default y if SOC_DRA7XX @@ -53,7 +53,7 @@ config PCIE_DW_PLAT config PCIE_DW_PLAT_HOST bool "Platform bus based DesignWare PCIe Controller - Host mode" - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST select PCIE_DW_PLAT help @@ -67,7 +67,7 @@ config PCIE_DW_PLAT_HOST config PCIE_DW_PLAT_EP bool "Platform bus based DesignWare PCIe Controller - Endpoint mode" - depends on PCI && PCI_MSI_IRQ_DOMAIN + depends on PCI && PCI_MSI depends on PCI_ENDPOINT select PCIE_DW_EP select PCIE_DW_PLAT @@ -83,7 +83,7 @@ config PCIE_DW_PLAT_EP config PCI_EXYNOS tristate "Samsung Exynos PCIe controller" depends on ARCH_EXYNOS || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST help Enables support for the PCIe controller in the Samsung Exynos SoCs @@ -94,13 +94,13 @@ config PCI_EXYNOS config PCI_IMX6 bool "Freescale i.MX6/7/8 PCIe controller" depends on ARCH_MXC || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST config PCIE_SPEAR13XX bool "STMicroelectronics SPEAr PCIe controller" depends on ARCH_SPEAR13XX || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST help Say Y here if you want PCIe support on SPEAr13XX SoCs. @@ -111,7 +111,7 @@ config PCI_KEYSTONE config PCI_KEYSTONE_HOST bool "PCI Keystone Host Mode" depends on ARCH_KEYSTONE || ARCH_K3 || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST select PCI_KEYSTONE help @@ -135,7 +135,7 @@ config PCI_KEYSTONE_EP config PCI_LAYERSCAPE bool "Freescale Layerscape PCIe controller - Host mode" depends on OF && (ARM || ARCH_LAYERSCAPE || COMPILE_TEST) - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST select MFD_SYSCON help @@ -160,7 +160,7 @@ config PCI_LAYERSCAPE_EP config PCI_HISI depends on OF && (ARM64 || COMPILE_TEST) bool "HiSilicon Hip05 and Hip06 SoCs PCIe controllers" - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST select PCI_HOST_COMMON help @@ -170,7 +170,7 @@ config PCI_HISI config PCIE_QCOM bool "Qualcomm PCIe controller" depends on OF && (ARCH_QCOM || COMPILE_TEST) - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST select CRC8 help @@ -191,7 +191,7 @@ config PCIE_QCOM_EP config PCIE_ARMADA_8K bool "Marvell Armada-8K PCIe controller" depends on ARCH_MVEBU || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST help Say Y here if you want to enable PCIe controller support on @@ -205,7 +205,7 @@ config PCIE_ARTPEC6 config PCIE_ARTPEC6_HOST bool "Axis ARTPEC-6 PCIe controller Host Mode" depends on MACH_ARTPEC6 || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST select PCIE_ARTPEC6 help @@ -226,7 +226,7 @@ config PCIE_ROCKCHIP_DW_HOST bool "Rockchip DesignWare PCIe controller" select PCIE_DW select PCIE_DW_HOST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI depends on ARCH_ROCKCHIP || COMPILE_TEST depends on OF help @@ -236,7 +236,7 @@ config PCIE_ROCKCHIP_DW_HOST config PCIE_INTEL_GW bool "Intel Gateway PCIe host controller support" depends on OF && (X86 || COMPILE_TEST) - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST help Say 'Y' here to enable PCIe Host controller support on Intel @@ -250,7 +250,7 @@ config PCIE_KEEMBAY config PCIE_KEEMBAY_HOST bool "Intel Keem Bay PCIe controller - Host mode" depends on ARCH_KEEMBAY || COMPILE_TEST - depends on PCI && PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST select PCIE_KEEMBAY help @@ -262,7 +262,7 @@ config PCIE_KEEMBAY_HOST config PCIE_KEEMBAY_EP bool "Intel Keem Bay PCIe controller - Endpoint mode" depends on ARCH_KEEMBAY || COMPILE_TEST - depends on PCI && PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI depends on PCI_ENDPOINT select PCIE_DW_EP select PCIE_KEEMBAY @@ -275,7 +275,7 @@ config PCIE_KEEMBAY_EP config PCIE_KIRIN depends on OF && (ARM64 || COMPILE_TEST) tristate "HiSilicon Kirin series SoCs PCIe controllers" - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST help Say Y here if you want PCIe controller support @@ -284,7 +284,7 @@ config PCIE_KIRIN config PCIE_HISI_STB bool "HiSilicon STB SoCs PCIe controllers" depends on ARCH_HISI || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST help Say Y here if you want PCIe controller support on HiSilicon STB SoCs @@ -292,7 +292,7 @@ config PCIE_HISI_STB config PCI_MESON tristate "MESON PCIe controller" default m if ARCH_MESON - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST help Say Y here if you want to enable PCI controller support on Amlogic @@ -306,7 +306,7 @@ config PCIE_TEGRA194 config PCIE_TEGRA194_HOST tristate "NVIDIA Tegra194 (and later) PCIe controller - Host Mode" depends on ARCH_TEGRA_194_SOC || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST select PHY_TEGRA194_P2U select PCIE_TEGRA194 @@ -336,7 +336,7 @@ config PCIE_TEGRA194_EP config PCIE_VISCONTI_HOST bool "Toshiba Visconti PCIe controllers" depends on ARCH_VISCONTI || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST help Say Y here if you want PCIe controller support on Toshiba Visconti SoC. @@ -346,7 +346,7 @@ config PCIE_UNIPHIER bool "Socionext UniPhier PCIe host controllers" depends on ARCH_UNIPHIER || COMPILE_TEST depends on OF && HAS_IOMEM - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST help Say Y here if you want PCIe host controller support on UniPhier SoCs. @@ -365,7 +365,7 @@ config PCIE_UNIPHIER_EP config PCIE_AL bool "Amazon Annapurna Labs PCIe controller" depends on OF && (ARM64 || COMPILE_TEST) - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST select PCI_ECAM help @@ -377,7 +377,7 @@ config PCIE_AL config PCIE_FU740 bool "SiFive FU740 PCIe host controller" - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI depends on SOC_SIFIVE || COMPILE_TEST select PCIE_DW_HOST help diff --git a/drivers/pci/controller/mobiveil/Kconfig b/drivers/pci/controller/mobiveil/Kconfig index e4643fb94e78..1d7a07ba9ccd 100644 --- a/drivers/pci/controller/mobiveil/Kconfig +++ b/drivers/pci/controller/mobiveil/Kconfig @@ -8,14 +8,14 @@ config PCIE_MOBIVEIL config PCIE_MOBIVEIL_HOST bool - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_MOBIVEIL config PCIE_MOBIVEIL_PLAT bool "Mobiveil AXI PCIe controller" depends on ARCH_ZYNQMP || COMPILE_TEST depends on OF - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_MOBIVEIL_HOST help Say Y here if you want to enable support for the Mobiveil AXI PCIe @@ -25,7 +25,7 @@ config PCIE_MOBIVEIL_PLAT config PCIE_LAYERSCAPE_GEN4 bool "Freescale Layerscape PCIe Gen4 controller" depends on ARCH_LAYERSCAPE || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_MOBIVEIL_HOST help Say Y here if you want PCIe Gen4 controller support on diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index f1ec8931dfbc..d6d3e5c358d5 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -611,20 +611,7 @@ static unsigned int hv_msi_get_int_vector(struct irq_data *data) return cfg->vector; } -static int hv_msi_prepare(struct irq_domain *domain, struct device *dev, - int nvec, msi_alloc_info_t *info) -{ - int ret = pci_msi_prepare(domain, dev, nvec, info); - - /* - * By using the interrupt remapper in the hypervisor IOMMU, contiguous - * CPU vectors is not needed for multi-MSI - */ - if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI) - info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS; - - return ret; -} +#define hv_msi_prepare pci_msi_prepare /** * hv_arch_irq_unmask() - "Unmask" the IRQ by setting its current diff --git a/drivers/pci/msi/Makefile b/drivers/pci/msi/Makefile index 93ef7b9e404d..839ff72d72a8 100644 --- a/drivers/pci/msi/Makefile +++ b/drivers/pci/msi/Makefile @@ -2,6 +2,5 @@ # # Makefile for the PCI/MSI obj-$(CONFIG_PCI) += pcidev_msi.o -obj-$(CONFIG_PCI_MSI) += msi.o -obj-$(CONFIG_PCI_MSI_IRQ_DOMAIN) += irqdomain.o +obj-$(CONFIG_PCI_MSI) += api.o msi.o irqdomain.o obj-$(CONFIG_PCI_MSI_ARCH_FALLBACKS) += legacy.o diff --git a/drivers/pci/msi/api.c b/drivers/pci/msi/api.c new file mode 100644 index 000000000000..b8009aa11f3c --- /dev/null +++ b/drivers/pci/msi/api.c @@ -0,0 +1,458 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCI MSI/MSI-X — Exported APIs for device drivers + * + * Copyright (C) 2003-2004 Intel + * Copyright (C) Tom Long Nguyen ([email protected]) + * Copyright (C) 2016 Christoph Hellwig. + * Copyright (C) 2022 Linutronix GmbH + */ + +#include <linux/export.h> +#include <linux/irq.h> + +#include "msi.h" + +/** + * pci_enable_msi() - Enable MSI interrupt mode on device + * @dev: the PCI device to operate on + * + * Legacy device driver API to enable MSI interrupts mode on device and + * allocate a single interrupt vector. On success, the allocated vector + * Linux IRQ will be saved at @dev->irq. The driver must invoke + * pci_disable_msi() on cleanup. + * + * NOTE: The newer pci_alloc_irq_vectors() / pci_free_irq_vectors() API + * pair should, in general, be used instead. + * + * Return: 0 on success, errno otherwise + */ +int pci_enable_msi(struct pci_dev *dev) +{ + int rc = __pci_enable_msi_range(dev, 1, 1, NULL); + if (rc < 0) + return rc; + return 0; +} +EXPORT_SYMBOL(pci_enable_msi); + +/** + * pci_disable_msi() - Disable MSI interrupt mode on device + * @dev: the PCI device to operate on + * + * Legacy device driver API to disable MSI interrupt mode on device, + * free earlier allocated interrupt vectors, and restore INTx emulation. + * The PCI device Linux IRQ (@dev->irq) is restored to its default + * pin-assertion IRQ. This is the cleanup pair of pci_enable_msi(). + * + * NOTE: The newer pci_alloc_irq_vectors() / pci_free_irq_vectors() API + * pair should, in general, be used instead. + */ +void pci_disable_msi(struct pci_dev *dev) +{ + if (!pci_msi_enabled() || !dev || !dev->msi_enabled) + return; + + msi_lock_descs(&dev->dev); + pci_msi_shutdown(dev); + pci_free_msi_irqs(dev); + msi_unlock_descs(&dev->dev); +} +EXPORT_SYMBOL(pci_disable_msi); + +/** + * pci_msix_vec_count() - Get number of MSI-X interrupt vectors on device + * @dev: the PCI device to operate on + * + * Return: number of MSI-X interrupt vectors available on this device + * (i.e., the device's MSI-X capability structure "table size"), -EINVAL + * if the device is not MSI-X capable, other errnos otherwise. + */ +int pci_msix_vec_count(struct pci_dev *dev) +{ + u16 control; + + if (!dev->msix_cap) + return -EINVAL; + + pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control); + return msix_table_size(control); +} +EXPORT_SYMBOL(pci_msix_vec_count); + +/** + * pci_enable_msix_range() - Enable MSI-X interrupt mode on device + * @dev: the PCI device to operate on + * @entries: input/output parameter, array of MSI-X configuration entries + * @minvec: minimum required number of MSI-X vectors + * @maxvec: maximum desired number of MSI-X vectors + * + * Legacy device driver API to enable MSI-X interrupt mode on device and + * configure its MSI-X capability structure as appropriate. The passed + * @entries array must have each of its members "entry" field set to a + * desired (valid) MSI-X vector number, where the range of valid MSI-X + * vector numbers can be queried through pci_msix_vec_count(). If + * successful, the driver must invoke pci_disable_msix() on cleanup. + * + * NOTE: The newer pci_alloc_irq_vectors() / pci_free_irq_vectors() API + * pair should, in general, be used instead. + * + * Return: number of MSI-X vectors allocated (which might be smaller + * than @maxvecs), where Linux IRQ numbers for such allocated vectors + * are saved back in the @entries array elements' "vector" field. Return + * -ENOSPC if less than @minvecs interrupt vectors are available. + * Return -EINVAL if one of the passed @entries members "entry" field + * was invalid or a duplicate, or if plain MSI interrupts mode was + * earlier enabled on device. Return other errnos otherwise. + */ +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, NULL, 0); +} +EXPORT_SYMBOL(pci_enable_msix_range); + +/** + * pci_msix_can_alloc_dyn - Query whether dynamic allocation after enabling + * MSI-X is supported + * + * @dev: PCI device to operate on + * + * Return: True if supported, false otherwise + */ +bool pci_msix_can_alloc_dyn(struct pci_dev *dev) +{ + if (!dev->msix_cap) + return false; + + return pci_msi_domain_supports(dev, MSI_FLAG_PCI_MSIX_ALLOC_DYN, DENY_LEGACY); +} +EXPORT_SYMBOL_GPL(pci_msix_can_alloc_dyn); + +/** + * pci_msix_alloc_irq_at - Allocate an MSI-X interrupt after enabling MSI-X + * at a given MSI-X vector index or any free vector index + * + * @dev: PCI device to operate on + * @index: Index to allocate. If @index == MSI_ANY_INDEX this allocates + * the next free index in the MSI-X table + * @affdesc: Optional pointer to an affinity descriptor structure. NULL otherwise + * + * Return: A struct msi_map + * + * On success msi_map::index contains the allocated index (>= 0) and + * msi_map::virq contains the allocated Linux interrupt number (> 0). + * + * On fail msi_map::index contains the error code and msi_map::virq + * is set to 0. + */ +struct msi_map pci_msix_alloc_irq_at(struct pci_dev *dev, unsigned int index, + const struct irq_affinity_desc *affdesc) +{ + struct msi_map map = { .index = -ENOTSUPP }; + + if (!dev->msix_enabled) + return map; + + if (!pci_msix_can_alloc_dyn(dev)) + return map; + + return msi_domain_alloc_irq_at(&dev->dev, MSI_DEFAULT_DOMAIN, index, affdesc, NULL); +} +EXPORT_SYMBOL_GPL(pci_msix_alloc_irq_at); + +/** + * pci_msix_free_irq - Free an interrupt on a PCI/MSIX interrupt domain + * which was allocated via pci_msix_alloc_irq_at() + * + * @dev: The PCI device to operate on + * @map: A struct msi_map describing the interrupt to free + * as returned from the allocation function. + */ +void pci_msix_free_irq(struct pci_dev *dev, struct msi_map map) +{ + if (WARN_ON_ONCE(map.index < 0 || map.virq <= 0)) + return; + if (WARN_ON_ONCE(!pci_msix_can_alloc_dyn(dev))) + return; + msi_domain_free_irqs_range(&dev->dev, MSI_DEFAULT_DOMAIN, map.index, map.index); +} +EXPORT_SYMBOL_GPL(pci_msix_free_irq); + +/** + * pci_disable_msix() - Disable MSI-X interrupt mode on device + * @dev: the PCI device to operate on + * + * Legacy device driver API to disable MSI-X interrupt mode on device, + * free earlier-allocated interrupt vectors, and restore INTx. + * The PCI device Linux IRQ (@dev->irq) is restored to its default pin + * assertion IRQ. This is the cleanup pair of pci_enable_msix_range(). + * + * NOTE: The newer pci_alloc_irq_vectors() / pci_free_irq_vectors() API + * pair should, in general, be used instead. + */ +void pci_disable_msix(struct pci_dev *dev) +{ + if (!pci_msi_enabled() || !dev || !dev->msix_enabled) + return; + + msi_lock_descs(&dev->dev); + pci_msix_shutdown(dev); + pci_free_msi_irqs(dev); + msi_unlock_descs(&dev->dev); +} +EXPORT_SYMBOL(pci_disable_msix); + +/** + * pci_alloc_irq_vectors() - Allocate multiple device interrupt vectors + * @dev: the PCI device to operate on + * @min_vecs: minimum required number of vectors (must be >= 1) + * @max_vecs: maximum desired number of vectors + * @flags: One or more of: + * + * * %PCI_IRQ_MSIX Allow trying MSI-X vector allocations + * * %PCI_IRQ_MSI Allow trying MSI vector allocations + * + * * %PCI_IRQ_LEGACY Allow trying legacy INTx interrupts, if + * and only if @min_vecs == 1 + * + * * %PCI_IRQ_AFFINITY Auto-manage IRQs affinity by spreading + * the vectors around available CPUs + * + * Allocate up to @max_vecs interrupt vectors on device. MSI-X irq + * vector allocation has a higher precedence over plain MSI, which has a + * higher precedence over legacy INTx emulation. + * + * Upon a successful allocation, the caller should use pci_irq_vector() + * to get the Linux IRQ number to be passed to request_threaded_irq(). + * The driver must call pci_free_irq_vectors() on cleanup. + * + * Return: number of allocated vectors (which might be smaller than + * @max_vecs), -ENOSPC if less than @min_vecs interrupt vectors are + * available, other errnos otherwise. + */ +int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, + unsigned int max_vecs, unsigned int flags) +{ + return pci_alloc_irq_vectors_affinity(dev, min_vecs, max_vecs, + flags, NULL); +} +EXPORT_SYMBOL(pci_alloc_irq_vectors); + +/** + * pci_alloc_irq_vectors_affinity() - Allocate multiple device interrupt + * vectors with affinity requirements + * @dev: the PCI device to operate on + * @min_vecs: minimum required number of vectors (must be >= 1) + * @max_vecs: maximum desired number of vectors + * @flags: allocation flags, as in pci_alloc_irq_vectors() + * @affd: affinity requirements (can be %NULL). + * + * Same as pci_alloc_irq_vectors(), but with the extra @affd parameter. + * Check that function docs, and &struct irq_affinity, for more details. + */ +int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, + unsigned int max_vecs, unsigned int flags, + struct irq_affinity *affd) +{ + struct irq_affinity msi_default_affd = {0}; + int nvecs = -ENOSPC; + + if (flags & PCI_IRQ_AFFINITY) { + if (!affd) + affd = &msi_default_affd; + } else { + if (WARN_ON(affd)) + affd = NULL; + } + + if (flags & PCI_IRQ_MSIX) { + nvecs = __pci_enable_msix_range(dev, NULL, min_vecs, max_vecs, + affd, flags); + if (nvecs > 0) + return nvecs; + } + + if (flags & PCI_IRQ_MSI) { + nvecs = __pci_enable_msi_range(dev, min_vecs, max_vecs, affd); + if (nvecs > 0) + return nvecs; + } + + /* use legacy IRQ if allowed */ + if (flags & PCI_IRQ_LEGACY) { + if (min_vecs == 1 && dev->irq) { + /* + * Invoke the affinity spreading logic to ensure that + * the device driver can adjust queue configuration + * for the single interrupt case. + */ + if (affd) + irq_create_affinity_masks(1, affd); + pci_intx(dev, 1); + return 1; + } + } + + return nvecs; +} +EXPORT_SYMBOL(pci_alloc_irq_vectors_affinity); + +/** + * pci_irq_vector() - Get Linux IRQ number of a device interrupt vector + * @dev: the PCI device to operate on + * @nr: device-relative interrupt vector index (0-based); has different + * meanings, depending on interrupt mode: + * + * * MSI-X the index in the MSI-X vector table + * * MSI the index of the enabled MSI vectors + * * INTx must be 0 + * + * Return: the Linux IRQ number, or -EINVAL if @nr is out of range + */ +int pci_irq_vector(struct pci_dev *dev, unsigned int nr) +{ + unsigned int irq; + + if (!dev->msi_enabled && !dev->msix_enabled) + return !nr ? dev->irq : -EINVAL; + + irq = msi_get_virq(&dev->dev, nr); + return irq ? irq : -EINVAL; +} +EXPORT_SYMBOL(pci_irq_vector); + +/** + * pci_irq_get_affinity() - Get a device interrupt vector affinity + * @dev: the PCI device to operate on + * @nr: device-relative interrupt vector index (0-based); has different + * meanings, depending on interrupt mode: + * + * * MSI-X the index in the MSI-X vector table + * * MSI the index of the enabled MSI vectors + * * INTx must be 0 + * + * Return: MSI/MSI-X vector affinity, NULL if @nr is out of range or if + * the MSI(-X) vector was allocated without explicit affinity + * requirements (e.g., by pci_enable_msi(), pci_enable_msix_range(), or + * pci_alloc_irq_vectors() without the %PCI_IRQ_AFFINITY flag). Return a + * generic set of CPU IDs representing all possible CPUs available + * during system boot if the device is in legacy INTx mode. + */ +const struct cpumask *pci_irq_get_affinity(struct pci_dev *dev, int nr) +{ + int idx, irq = pci_irq_vector(dev, nr); + struct msi_desc *desc; + + if (WARN_ON_ONCE(irq <= 0)) + return NULL; + + desc = irq_get_msi_desc(irq); + /* Non-MSI does not have the information handy */ + if (!desc) + return cpu_possible_mask; + + /* MSI[X] interrupts can be allocated without affinity descriptor */ + if (!desc->affinity) + return NULL; + + /* + * MSI has a mask array in the descriptor. + * MSI-X has a single mask. + */ + idx = dev->msi_enabled ? nr : 0; + return &desc->affinity[idx].mask; +} +EXPORT_SYMBOL(pci_irq_get_affinity); + +/** + * pci_ims_alloc_irq - Allocate an interrupt on a PCI/IMS interrupt domain + * @dev: The PCI device to operate on + * @icookie: Pointer to an IMS implementation specific cookie for this + * IMS instance (PASID, queue ID, pointer...). + * The cookie content is copied into the MSI descriptor for the + * interrupt chip callbacks or domain specific setup functions. + * @affdesc: Optional pointer to an interrupt affinity descriptor + * + * There is no index for IMS allocations as IMS is an implementation + * specific storage and does not have any direct associations between + * index, which might be a pure software construct, and device + * functionality. This association is established by the driver either via + * the index - if there is a hardware table - or in case of purely software + * managed IMS implementation the association happens via the + * irq_write_msi_msg() callback of the implementation specific interrupt + * chip, which utilizes the provided @icookie to store the MSI message in + * the appropriate place. + * + * Return: A struct msi_map + * + * On success msi_map::index contains the allocated index (>= 0) and + * msi_map::virq the allocated Linux interrupt number (> 0). + * + * On fail msi_map::index contains the error code and msi_map::virq + * is set to 0. + */ +struct msi_map pci_ims_alloc_irq(struct pci_dev *dev, union msi_instance_cookie *icookie, + const struct irq_affinity_desc *affdesc) +{ + return msi_domain_alloc_irq_at(&dev->dev, MSI_SECONDARY_DOMAIN, MSI_ANY_INDEX, + affdesc, icookie); +} +EXPORT_SYMBOL_GPL(pci_ims_alloc_irq); + +/** + * pci_ims_free_irq - Allocate an interrupt on a PCI/IMS interrupt domain + * which was allocated via pci_ims_alloc_irq() + * @dev: The PCI device to operate on + * @map: A struct msi_map describing the interrupt to free as + * returned from pci_ims_alloc_irq() + */ +void pci_ims_free_irq(struct pci_dev *dev, struct msi_map map) +{ + if (WARN_ON_ONCE(map.index < 0 || map.virq <= 0)) + return; + msi_domain_free_irqs_range(&dev->dev, MSI_SECONDARY_DOMAIN, map.index, map.index); +} +EXPORT_SYMBOL_GPL(pci_ims_free_irq); + +/** + * pci_free_irq_vectors() - Free previously allocated IRQs for a device + * @dev: the PCI device to operate on + * + * Undo the interrupt vector allocations and possible device MSI/MSI-X + * enablement earlier done through pci_alloc_irq_vectors_affinity() or + * pci_alloc_irq_vectors(). + */ +void pci_free_irq_vectors(struct pci_dev *dev) +{ + pci_disable_msix(dev); + pci_disable_msi(dev); +} +EXPORT_SYMBOL(pci_free_irq_vectors); + +/** + * pci_restore_msi_state() - Restore cached MSI(-X) state on device + * @dev: the PCI device to operate on + * + * Write the Linux-cached MSI(-X) state back on device. This is + * typically useful upon system resume, or after an error-recovery PCI + * adapter reset. + */ +void pci_restore_msi_state(struct pci_dev *dev) +{ + __pci_restore_msi_state(dev); + __pci_restore_msix_state(dev); +} +EXPORT_SYMBOL_GPL(pci_restore_msi_state); + +/** + * pci_msi_enabled() - Are MSI(-X) interrupts enabled system-wide? + * + * Return: true if MSI has not been globally disabled through ACPI FADT, + * PCI bridge quirks, or the "pci=nomsi" kernel command-line option. + */ +int pci_msi_enabled(void) +{ + return pci_msi_enable; +} +EXPORT_SYMBOL(pci_msi_enabled); diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index e9cf318e6670..e33bcc872699 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -14,7 +14,7 @@ int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) domain = dev_get_msi_domain(&dev->dev); if (domain && irq_domain_is_hierarchy(domain)) - return msi_domain_alloc_irqs_descs_locked(domain, &dev->dev, nvec); + return msi_domain_alloc_irqs_all_locked(&dev->dev, MSI_DEFAULT_DOMAIN, nvec); return pci_msi_legacy_setup_msi_irqs(dev, nvec, type); } @@ -24,11 +24,12 @@ void pci_msi_teardown_msi_irqs(struct pci_dev *dev) struct irq_domain *domain; domain = dev_get_msi_domain(&dev->dev); - if (domain && irq_domain_is_hierarchy(domain)) - msi_domain_free_irqs_descs_locked(domain, &dev->dev); - else + if (domain && irq_domain_is_hierarchy(domain)) { + msi_domain_free_irqs_all_locked(&dev->dev, MSI_DEFAULT_DOMAIN); + } else { pci_msi_legacy_teardown_msi_irqs(dev); - msi_free_msi_descs(&dev->dev); + msi_free_msi_descs(&dev->dev); + } } /** @@ -63,51 +64,6 @@ static irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc) (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 27; } -static inline bool pci_msi_desc_is_multi_msi(struct msi_desc *desc) -{ - return !desc->pci.msi_attrib.is_msix && desc->nvec_used > 1; -} - -/** - * pci_msi_domain_check_cap - Verify that @domain supports the capabilities - * for @dev - * @domain: The interrupt domain to check - * @info: The domain info for verification - * @dev: The device to check - * - * Returns: - * 0 if the functionality is supported - * 1 if Multi MSI is requested, but the domain does not support it - * -ENOTSUPP otherwise - */ -static int pci_msi_domain_check_cap(struct irq_domain *domain, - struct msi_domain_info *info, - struct device *dev) -{ - struct msi_desc *desc = msi_first_desc(dev, MSI_DESC_ALL); - - /* Special handling to support __pci_enable_msi_range() */ - if (pci_msi_desc_is_multi_msi(desc) && - !(info->flags & MSI_FLAG_MULTI_PCI_MSI)) - return 1; - - if (desc->pci.msi_attrib.is_msix) { - if (!(info->flags & MSI_FLAG_PCI_MSIX)) - return -ENOTSUPP; - - if (info->flags & MSI_FLAG_MSIX_CONTIGUOUS) { - unsigned int idx = 0; - - /* Check for gaps in the entry indices */ - msi_for_each_desc(desc, dev, MSI_DESC_ALL) { - if (desc->msi_index != idx++) - return -ENOTSUPP; - } - } - } - return 0; -} - static void pci_msi_domain_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) { @@ -117,7 +73,6 @@ static void pci_msi_domain_set_desc(msi_alloc_info_t *arg, static struct msi_domain_ops pci_msi_domain_ops_default = { .set_desc = pci_msi_domain_set_desc, - .msi_check = pci_msi_domain_check_cap, }; static void pci_msi_domain_update_dom_ops(struct msi_domain_info *info) @@ -129,8 +84,6 @@ static void pci_msi_domain_update_dom_ops(struct msi_domain_info *info) } else { if (ops->set_desc == NULL) ops->set_desc = pci_msi_domain_set_desc; - if (ops->msi_check == NULL) - ops->msi_check = pci_msi_domain_check_cap; } } @@ -162,8 +115,6 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent) { - struct irq_domain *domain; - if (WARN_ON(info->flags & MSI_FLAG_LEVEL_CAPABLE)) info->flags &= ~MSI_FLAG_LEVEL_CAPABLE; @@ -172,23 +123,298 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS) pci_msi_domain_update_chip_ops(info); + /* Let the core code free MSI descriptors when freeing interrupts */ + info->flags |= MSI_FLAG_FREE_MSI_DESCS; + info->flags |= MSI_FLAG_ACTIVATE_EARLY | MSI_FLAG_DEV_SYSFS; if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE)) info->flags |= MSI_FLAG_MUST_REACTIVATE; /* PCI-MSI is oneshot-safe */ info->chip->flags |= IRQCHIP_ONESHOT_SAFE; + /* Let the core update the bus token */ + info->bus_token = DOMAIN_BUS_PCI_MSI; - domain = msi_create_irq_domain(fwnode, info, parent); - if (!domain) - return NULL; - - irq_domain_update_bus_token(domain, DOMAIN_BUS_PCI_MSI); - return domain; + return msi_create_irq_domain(fwnode, info, parent); } EXPORT_SYMBOL_GPL(pci_msi_create_irq_domain); /* + * Per device MSI[-X] domain functionality + */ +static void pci_device_domain_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) +{ + arg->desc = desc; + arg->hwirq = desc->msi_index; +} + +static void pci_irq_mask_msi(struct irq_data *data) +{ + struct msi_desc *desc = irq_data_get_msi_desc(data); + + pci_msi_mask(desc, BIT(data->irq - desc->irq)); +} + +static void pci_irq_unmask_msi(struct irq_data *data) +{ + struct msi_desc *desc = irq_data_get_msi_desc(data); + + pci_msi_unmask(desc, BIT(data->irq - desc->irq)); +} + +#ifdef CONFIG_GENERIC_IRQ_RESERVATION_MODE +# define MSI_REACTIVATE MSI_FLAG_MUST_REACTIVATE +#else +# define MSI_REACTIVATE 0 +#endif + +#define MSI_COMMON_FLAGS (MSI_FLAG_FREE_MSI_DESCS | \ + MSI_FLAG_ACTIVATE_EARLY | \ + MSI_FLAG_DEV_SYSFS | \ + MSI_REACTIVATE) + +static const struct msi_domain_template pci_msi_template = { + .chip = { + .name = "PCI-MSI", + .irq_mask = pci_irq_mask_msi, + .irq_unmask = pci_irq_unmask_msi, + .irq_write_msi_msg = pci_msi_domain_write_msg, + .flags = IRQCHIP_ONESHOT_SAFE, + }, + + .ops = { + .set_desc = pci_device_domain_set_desc, + }, + + .info = { + .flags = MSI_COMMON_FLAGS | MSI_FLAG_MULTI_PCI_MSI, + .bus_token = DOMAIN_BUS_PCI_DEVICE_MSI, + }, +}; + +static void pci_irq_mask_msix(struct irq_data *data) +{ + pci_msix_mask(irq_data_get_msi_desc(data)); +} + +static void pci_irq_unmask_msix(struct irq_data *data) +{ + pci_msix_unmask(irq_data_get_msi_desc(data)); +} + +static void pci_msix_prepare_desc(struct irq_domain *domain, msi_alloc_info_t *arg, + struct msi_desc *desc) +{ + /* Don't fiddle with preallocated MSI descriptors */ + if (!desc->pci.mask_base) + msix_prepare_msi_desc(to_pci_dev(desc->dev), desc); +} + +static const struct msi_domain_template pci_msix_template = { + .chip = { + .name = "PCI-MSIX", + .irq_mask = pci_irq_mask_msix, + .irq_unmask = pci_irq_unmask_msix, + .irq_write_msi_msg = pci_msi_domain_write_msg, + .flags = IRQCHIP_ONESHOT_SAFE, + }, + + .ops = { + .prepare_desc = pci_msix_prepare_desc, + .set_desc = pci_device_domain_set_desc, + }, + + .info = { + .flags = MSI_COMMON_FLAGS | MSI_FLAG_PCI_MSIX | + MSI_FLAG_PCI_MSIX_ALLOC_DYN, + .bus_token = DOMAIN_BUS_PCI_DEVICE_MSIX, + }, +}; + +static bool pci_match_device_domain(struct pci_dev *pdev, enum irq_domain_bus_token bus_token) +{ + return msi_match_device_irq_domain(&pdev->dev, MSI_DEFAULT_DOMAIN, bus_token); +} + +static bool pci_create_device_domain(struct pci_dev *pdev, const struct msi_domain_template *tmpl, + unsigned int hwsize) +{ + struct irq_domain *domain = dev_get_msi_domain(&pdev->dev); + + if (!domain || !irq_domain_is_msi_parent(domain)) + return true; + + return msi_create_device_irq_domain(&pdev->dev, MSI_DEFAULT_DOMAIN, tmpl, + hwsize, NULL, NULL); +} + +/** + * pci_setup_msi_device_domain - Setup a device MSI interrupt domain + * @pdev: The PCI device to create the domain on + * + * Return: + * True when: + * - The device does not have a MSI parent irq domain associated, + * which keeps the legacy architecture specific and the global + * PCI/MSI domain models working + * - The MSI domain exists already + * - The MSI domain was successfully allocated + * False when: + * - MSI-X is enabled + * - The domain creation fails. + * + * The created MSI domain is preserved until: + * - The device is removed + * - MSI is disabled and a MSI-X domain is created + */ +bool pci_setup_msi_device_domain(struct pci_dev *pdev) +{ + if (WARN_ON_ONCE(pdev->msix_enabled)) + return false; + + if (pci_match_device_domain(pdev, DOMAIN_BUS_PCI_DEVICE_MSI)) + return true; + if (pci_match_device_domain(pdev, DOMAIN_BUS_PCI_DEVICE_MSIX)) + msi_remove_device_irq_domain(&pdev->dev, MSI_DEFAULT_DOMAIN); + + return pci_create_device_domain(pdev, &pci_msi_template, 1); +} + +/** + * pci_setup_msix_device_domain - Setup a device MSI-X interrupt domain + * @pdev: The PCI device to create the domain on + * @hwsize: The size of the MSI-X vector table + * + * Return: + * True when: + * - The device does not have a MSI parent irq domain associated, + * which keeps the legacy architecture specific and the global + * PCI/MSI domain models working + * - The MSI-X domain exists already + * - The MSI-X domain was successfully allocated + * False when: + * - MSI is enabled + * - The domain creation fails. + * + * The created MSI-X domain is preserved until: + * - The device is removed + * - MSI-X is disabled and a MSI domain is created + */ +bool pci_setup_msix_device_domain(struct pci_dev *pdev, unsigned int hwsize) +{ + if (WARN_ON_ONCE(pdev->msi_enabled)) + return false; + + if (pci_match_device_domain(pdev, DOMAIN_BUS_PCI_DEVICE_MSIX)) + return true; + if (pci_match_device_domain(pdev, DOMAIN_BUS_PCI_DEVICE_MSI)) + msi_remove_device_irq_domain(&pdev->dev, MSI_DEFAULT_DOMAIN); + + return pci_create_device_domain(pdev, &pci_msix_template, hwsize); +} + +/** + * pci_msi_domain_supports - Check for support of a particular feature flag + * @pdev: The PCI device to operate on + * @feature_mask: The feature mask to check for (full match) + * @mode: If ALLOW_LEGACY this grants the feature when there is no irq domain + * associated to the device. If DENY_LEGACY the lack of an irq domain + * makes the feature unsupported + */ +bool pci_msi_domain_supports(struct pci_dev *pdev, unsigned int feature_mask, + enum support_mode mode) +{ + struct msi_domain_info *info; + struct irq_domain *domain; + unsigned int supported; + + domain = dev_get_msi_domain(&pdev->dev); + + if (!domain || !irq_domain_is_hierarchy(domain)) + return mode == ALLOW_LEGACY; + + if (!irq_domain_is_msi_parent(domain)) { + /* + * For "global" PCI/MSI interrupt domains the associated + * msi_domain_info::flags is the authoritive source of + * information. + */ + info = domain->host_data; + supported = info->flags; + } else { + /* + * For MSI parent domains the supported feature set + * is avaliable in the parent ops. This makes checks + * possible before actually instantiating the + * per device domain because the parent is never + * expanding the PCI/MSI functionality. + */ + supported = domain->msi_parent_ops->supported_flags; + } + + return (supported & feature_mask) == feature_mask; +} + +/** + * pci_create_ims_domain - Create a secondary IMS domain for a PCI device + * @pdev: The PCI device to operate on + * @template: The MSI info template which describes the domain + * @hwsize: The size of the hardware entry table or 0 if the domain + * is purely software managed + * @data: Optional pointer to domain specific data to be stored + * in msi_domain_info::data + * + * Return: True on success, false otherwise + * + * An IMS domain is expected to have the following constraints: + * - The index space is managed by the core code + * + * - There is no requirement for consecutive index ranges + * + * - The interrupt chip must provide the following callbacks: + * - irq_mask() + * - irq_unmask() + * - irq_write_msi_msg() + * + * - The interrupt chip must provide the following optional callbacks + * when the irq_mask(), irq_unmask() and irq_write_msi_msg() callbacks + * cannot operate directly on hardware, e.g. in the case that the + * interrupt message store is in queue memory: + * - irq_bus_lock() + * - irq_bus_unlock() + * + * These callbacks are invoked from preemptible task context and are + * allowed to sleep. In this case the mandatory callbacks above just + * store the information. The irq_bus_unlock() callback is supposed + * to make the change effective before returning. + * + * - Interrupt affinity setting is handled by the underlying parent + * interrupt domain and communicated to the IMS domain via + * irq_write_msi_msg(). + * + * The domain is automatically destroyed when the PCI device is removed. + */ +bool pci_create_ims_domain(struct pci_dev *pdev, const struct msi_domain_template *template, + unsigned int hwsize, void *data) +{ + struct irq_domain *domain = dev_get_msi_domain(&pdev->dev); + + if (!domain || !irq_domain_is_msi_parent(domain)) + return false; + + if (template->info.bus_token != DOMAIN_BUS_PCI_DEVICE_IMS || + !(template->info.flags & MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS) || + !(template->info.flags & MSI_FLAG_FREE_MSI_DESCS) || + !template->chip.irq_mask || !template->chip.irq_unmask || + !template->chip.irq_write_msi_msg || template->chip.irq_set_affinity) + return false; + + return msi_create_device_irq_domain(&pdev->dev, MSI_SECONDARY_DOMAIN, template, + hwsize, data, NULL); +} +EXPORT_SYMBOL_GPL(pci_create_ims_domain); + +/* * Users of the generic MSI infrastructure expect a device to have a single ID, * so with DMA aliases we have to pick the least-worst compromise. Devices with * DMA phantom functions tend to still emit MSIs from the real function number, @@ -257,24 +483,3 @@ struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev) DOMAIN_BUS_PCI_MSI); return dom; } - -/** - * pci_dev_has_special_msi_domain - Check whether the device is handled by - * a non-standard PCI-MSI domain - * @pdev: The PCI device to check. - * - * Returns: True if the device irqdomain or the bus irqdomain is - * non-standard PCI/MSI. - */ -bool pci_dev_has_special_msi_domain(struct pci_dev *pdev) -{ - struct irq_domain *dom = dev_get_msi_domain(&pdev->dev); - - if (!dom) - dom = dev_get_msi_domain(&pdev->bus->dev); - - if (!dom) - return true; - - return dom->bus_token != DOMAIN_BUS_PCI_MSI; -} diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index fdd2ec09651e..1f716624ca56 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -13,82 +13,114 @@ #include "../pci.h" #include "msi.h" -static int pci_msi_enable = 1; +int pci_msi_enable = 1; int pci_msi_ignore_mask; -static noinline void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 set) +/** + * pci_msi_supported - check whether MSI may be enabled on a device + * @dev: pointer to the pci_dev data structure of MSI device function + * @nvec: how many MSIs have been requested? + * + * Look at global flags, the device itself, and its parent buses + * to determine if MSI/-X are supported for the device. If MSI/-X is + * supported return 1, else return 0. + **/ +static int pci_msi_supported(struct pci_dev *dev, int nvec) { - raw_spinlock_t *lock = &to_pci_dev(desc->dev)->msi_lock; - unsigned long flags; + struct pci_bus *bus; - if (!desc->pci.msi_attrib.can_mask) - return; + /* MSI must be globally enabled and supported by the device */ + if (!pci_msi_enable) + return 0; - raw_spin_lock_irqsave(lock, flags); - desc->pci.msi_mask &= ~clear; - desc->pci.msi_mask |= set; - pci_write_config_dword(msi_desc_to_pci_dev(desc), desc->pci.mask_pos, - desc->pci.msi_mask); - raw_spin_unlock_irqrestore(lock, flags); -} + if (!dev || dev->no_msi) + return 0; -static inline void pci_msi_mask(struct msi_desc *desc, u32 mask) -{ - pci_msi_update_mask(desc, 0, mask); -} + /* + * You can't ask to have 0 or less MSIs configured. + * a) it's stupid .. + * b) the list manipulation code assumes nvec >= 1. + */ + if (nvec < 1) + return 0; -static inline void pci_msi_unmask(struct msi_desc *desc, u32 mask) -{ - pci_msi_update_mask(desc, mask, 0); + /* + * Any bridge which does NOT route MSI transactions from its + * secondary bus to its primary bus must set NO_MSI flag on + * the secondary pci_bus. + * + * The NO_MSI flag can either be set directly by: + * - arch-specific PCI host bus controller drivers (deprecated) + * - quirks for specific PCI bridges + * + * or indirectly by platform-specific PCI host bridge drivers by + * advertising the 'msi_domain' property, which results in + * the NO_MSI flag when no MSI domain is found for this bridge + * at probe time. + */ + for (bus = dev->bus; bus; bus = bus->parent) + if (bus->bus_flags & PCI_BUS_FLAGS_NO_MSI) + return 0; + + return 1; } -static inline void __iomem *pci_msix_desc_addr(struct msi_desc *desc) +static void pcim_msi_release(void *pcidev) { - return desc->pci.mask_base + desc->msi_index * PCI_MSIX_ENTRY_SIZE; + struct pci_dev *dev = pcidev; + + dev->is_msi_managed = false; + pci_free_irq_vectors(dev); } /* - * This internal function does not flush PCI writes to the device. All - * users must ensure that they read from the device before either assuming - * that the device state is up to date, or returning out of this file. - * It does not affect the msi_desc::msix_ctrl cache either. Use with care! + * Needs to be separate from pcim_release to prevent an ordering problem + * vs. msi_device_data_release() in the MSI core code. */ -static void pci_msix_write_vector_ctrl(struct msi_desc *desc, u32 ctrl) +static int pcim_setup_msi_release(struct pci_dev *dev) { - void __iomem *desc_addr = pci_msix_desc_addr(desc); + int ret; - if (desc->pci.msi_attrib.can_mask) - writel(ctrl, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL); -} + if (!pci_is_managed(dev) || dev->is_msi_managed) + return 0; -static inline void pci_msix_mask(struct msi_desc *desc) -{ - desc->pci.msix_ctrl |= PCI_MSIX_ENTRY_CTRL_MASKBIT; - pci_msix_write_vector_ctrl(desc, desc->pci.msix_ctrl); - /* Flush write to device */ - readl(desc->pci.mask_base); + ret = devm_add_action(&dev->dev, pcim_msi_release, dev); + if (!ret) + dev->is_msi_managed = true; + return ret; } -static inline void pci_msix_unmask(struct msi_desc *desc) +/* + * Ordering vs. devres: msi device data has to be installed first so that + * pcim_msi_release() is invoked before it on device release. + */ +static int pci_setup_msi_context(struct pci_dev *dev) { - desc->pci.msix_ctrl &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT; - pci_msix_write_vector_ctrl(desc, desc->pci.msix_ctrl); -} + int ret = msi_setup_device_data(&dev->dev); -static void __pci_msi_mask_desc(struct msi_desc *desc, u32 mask) -{ - if (desc->pci.msi_attrib.is_msix) - pci_msix_mask(desc); - else - pci_msi_mask(desc, mask); + if (!ret) + ret = pcim_setup_msi_release(dev); + return ret; } -static void __pci_msi_unmask_desc(struct msi_desc *desc, u32 mask) +/* + * Helper functions for mask/unmask and MSI message handling + */ + +void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 set) { - if (desc->pci.msi_attrib.is_msix) - pci_msix_unmask(desc); - else - pci_msi_unmask(desc, mask); + raw_spinlock_t *lock = &to_pci_dev(desc->dev)->msi_lock; + unsigned long flags; + + if (!desc->pci.msi_attrib.can_mask) + return; + + raw_spin_lock_irqsave(lock, flags); + desc->pci.msi_mask &= ~clear; + desc->pci.msi_mask |= set; + pci_write_config_dword(msi_desc_to_pci_dev(desc), desc->pci.mask_pos, + desc->pci.msi_mask); + raw_spin_unlock_irqrestore(lock, flags); } /** @@ -148,6 +180,58 @@ void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg) } } +static inline void pci_write_msg_msi(struct pci_dev *dev, struct msi_desc *desc, + struct msi_msg *msg) +{ + int pos = dev->msi_cap; + u16 msgctl; + + pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl); + msgctl &= ~PCI_MSI_FLAGS_QSIZE; + msgctl |= desc->pci.msi_attrib.multiple << 4; + pci_write_config_word(dev, pos + PCI_MSI_FLAGS, msgctl); + + pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_LO, msg->address_lo); + if (desc->pci.msi_attrib.is_64) { + pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_HI, msg->address_hi); + pci_write_config_word(dev, pos + PCI_MSI_DATA_64, msg->data); + } else { + pci_write_config_word(dev, pos + PCI_MSI_DATA_32, msg->data); + } + /* Ensure that the writes are visible in the device */ + pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl); +} + +static inline void pci_write_msg_msix(struct msi_desc *desc, struct msi_msg *msg) +{ + void __iomem *base = pci_msix_desc_addr(desc); + u32 ctrl = desc->pci.msix_ctrl; + bool unmasked = !(ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT); + + if (desc->pci.msi_attrib.is_virtual) + return; + /* + * The specification mandates that the entry is masked + * when the message is modified: + * + * "If software changes the Address or Data value of an + * entry while the entry is unmasked, the result is + * undefined." + */ + if (unmasked) + pci_msix_write_vector_ctrl(desc, ctrl | PCI_MSIX_ENTRY_CTRL_MASKBIT); + + writel(msg->address_lo, base + PCI_MSIX_ENTRY_LOWER_ADDR); + writel(msg->address_hi, base + PCI_MSIX_ENTRY_UPPER_ADDR); + writel(msg->data, base + PCI_MSIX_ENTRY_DATA); + + if (unmasked) + pci_msix_write_vector_ctrl(desc, ctrl); + + /* Ensure that the writes are visible in the device */ + readl(base + PCI_MSIX_ENTRY_DATA); +} + void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) { struct pci_dev *dev = msi_desc_to_pci_dev(entry); @@ -155,63 +239,15 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) if (dev->current_state != PCI_D0 || pci_dev_is_disconnected(dev)) { /* Don't touch the hardware now */ } else if (entry->pci.msi_attrib.is_msix) { - void __iomem *base = pci_msix_desc_addr(entry); - u32 ctrl = entry->pci.msix_ctrl; - bool unmasked = !(ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT); - - if (entry->pci.msi_attrib.is_virtual) - goto skip; - - /* - * The specification mandates that the entry is masked - * when the message is modified: - * - * "If software changes the Address or Data value of an - * entry while the entry is unmasked, the result is - * undefined." - */ - if (unmasked) - pci_msix_write_vector_ctrl(entry, ctrl | PCI_MSIX_ENTRY_CTRL_MASKBIT); - - writel(msg->address_lo, base + PCI_MSIX_ENTRY_LOWER_ADDR); - writel(msg->address_hi, base + PCI_MSIX_ENTRY_UPPER_ADDR); - writel(msg->data, base + PCI_MSIX_ENTRY_DATA); - - if (unmasked) - pci_msix_write_vector_ctrl(entry, ctrl); - - /* Ensure that the writes are visible in the device */ - readl(base + PCI_MSIX_ENTRY_DATA); + pci_write_msg_msix(entry, msg); } else { - int pos = dev->msi_cap; - u16 msgctl; - - pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl); - msgctl &= ~PCI_MSI_FLAGS_QSIZE; - msgctl |= entry->pci.msi_attrib.multiple << 4; - pci_write_config_word(dev, pos + PCI_MSI_FLAGS, msgctl); - - pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_LO, - msg->address_lo); - if (entry->pci.msi_attrib.is_64) { - pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_HI, - msg->address_hi); - pci_write_config_word(dev, pos + PCI_MSI_DATA_64, - msg->data); - } else { - pci_write_config_word(dev, pos + PCI_MSI_DATA_32, - msg->data); - } - /* Ensure that the writes are visible in the device */ - pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl); + pci_write_msg_msi(dev, entry, msg); } -skip: entry->msg = *msg; if (entry->write_msi_msg) entry->write_msi_msg(entry, entry->write_msi_msg_data); - } void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg) @@ -222,15 +258,8 @@ void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg) } EXPORT_SYMBOL_GPL(pci_write_msi_msg); -static void free_msi_irqs(struct pci_dev *dev) -{ - pci_msi_teardown_msi_irqs(dev); - if (dev->msix_base) { - iounmap(dev->msix_base); - dev->msix_base = NULL; - } -} +/* PCI/MSI specific functionality */ static void pci_intx_for_msi(struct pci_dev *dev, int enable) { @@ -249,118 +278,6 @@ static void pci_msi_set_enable(struct pci_dev *dev, int enable) pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control); } -/* - * Architecture override returns true when the PCI MSI message should be - * written by the generic restore function. - */ -bool __weak arch_restore_msi_irqs(struct pci_dev *dev) -{ - return true; -} - -static void __pci_restore_msi_state(struct pci_dev *dev) -{ - struct msi_desc *entry; - u16 control; - - if (!dev->msi_enabled) - return; - - entry = irq_get_msi_desc(dev->irq); - - pci_intx_for_msi(dev, 0); - pci_msi_set_enable(dev, 0); - if (arch_restore_msi_irqs(dev)) - __pci_write_msi_msg(entry, &entry->msg); - - pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control); - pci_msi_update_mask(entry, 0, 0); - control &= ~PCI_MSI_FLAGS_QSIZE; - control |= (entry->pci.msi_attrib.multiple << 4) | PCI_MSI_FLAGS_ENABLE; - pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control); -} - -static void pci_msix_clear_and_set_ctrl(struct pci_dev *dev, u16 clear, u16 set) -{ - u16 ctrl; - - pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &ctrl); - ctrl &= ~clear; - ctrl |= set; - pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, ctrl); -} - -static void __pci_restore_msix_state(struct pci_dev *dev) -{ - struct msi_desc *entry; - bool write_msg; - - if (!dev->msix_enabled) - return; - - /* route the table */ - pci_intx_for_msi(dev, 0); - pci_msix_clear_and_set_ctrl(dev, 0, - PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL); - - write_msg = arch_restore_msi_irqs(dev); - - msi_lock_descs(&dev->dev); - msi_for_each_desc(entry, &dev->dev, MSI_DESC_ALL) { - if (write_msg) - __pci_write_msi_msg(entry, &entry->msg); - pci_msix_write_vector_ctrl(entry, entry->pci.msix_ctrl); - } - msi_unlock_descs(&dev->dev); - - pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0); -} - -void pci_restore_msi_state(struct pci_dev *dev) -{ - __pci_restore_msi_state(dev); - __pci_restore_msix_state(dev); -} -EXPORT_SYMBOL_GPL(pci_restore_msi_state); - -static void pcim_msi_release(void *pcidev) -{ - struct pci_dev *dev = pcidev; - - dev->is_msi_managed = false; - pci_free_irq_vectors(dev); -} - -/* - * Needs to be separate from pcim_release to prevent an ordering problem - * vs. msi_device_data_release() in the MSI core code. - */ -static int pcim_setup_msi_release(struct pci_dev *dev) -{ - int ret; - - if (!pci_is_managed(dev) || dev->is_msi_managed) - return 0; - - ret = devm_add_action(&dev->dev, pcim_msi_release, dev); - if (!ret) - dev->is_msi_managed = true; - return ret; -} - -/* - * Ordering vs. devres: msi device data has to be installed first so that - * pcim_msi_release() is invoked before it on device release. - */ -static int pci_setup_msi_context(struct pci_dev *dev) -{ - int ret = msi_setup_device_data(&dev->dev); - - if (!ret) - ret = pcim_setup_msi_release(dev); - return ret; -} - static int msi_setup_msi_desc(struct pci_dev *dev, int nvec, struct irq_affinity_desc *masks) { @@ -395,7 +312,7 @@ static int msi_setup_msi_desc(struct pci_dev *dev, int nvec, if (desc.pci.msi_attrib.can_mask) pci_read_config_dword(dev, desc.pci.mask_pos, &desc.pci.msi_mask); - return msi_add_msi_desc(&dev->dev, &desc); + return msi_insert_msi_desc(&dev->dev, &desc); } static int msi_verify_entries(struct pci_dev *dev) @@ -434,6 +351,10 @@ static int msi_capability_init(struct pci_dev *dev, int nvec, struct msi_desc *entry; int ret; + /* Reject multi-MSI early on irq domain enabled architectures */ + if (nvec > 1 && !pci_msi_domain_supports(dev, MSI_FLAG_MULTI_PCI_MSI, ALLOW_LEGACY)) + return 1; + /* * Disable MSI during setup in the hardware, but mark it enabled * so that setup code can evaluate it. @@ -472,7 +393,7 @@ static int msi_capability_init(struct pci_dev *dev, int nvec, err: pci_msi_unmask(entry, msi_multi_mask(entry)); - free_msi_irqs(dev); + pci_free_msi_irqs(dev); fail: dev->msi_enabled = 0; unlock: @@ -481,6 +402,152 @@ unlock: return ret; } +int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, + struct irq_affinity *affd) +{ + int nvec; + int rc; + + if (!pci_msi_supported(dev, minvec) || dev->current_state != PCI_D0) + return -EINVAL; + + /* Check whether driver already requested MSI-X IRQs */ + if (dev->msix_enabled) { + pci_info(dev, "can't enable MSI (MSI-X already enabled)\n"); + return -EINVAL; + } + + if (maxvec < minvec) + return -ERANGE; + + if (WARN_ON_ONCE(dev->msi_enabled)) + return -EINVAL; + + nvec = pci_msi_vec_count(dev); + if (nvec < 0) + return nvec; + if (nvec < minvec) + return -ENOSPC; + + if (nvec > maxvec) + nvec = maxvec; + + rc = pci_setup_msi_context(dev); + if (rc) + return rc; + + if (!pci_setup_msi_device_domain(dev)) + return -ENODEV; + + for (;;) { + if (affd) { + nvec = irq_calc_affinity_vectors(minvec, nvec, affd); + if (nvec < minvec) + return -ENOSPC; + } + + rc = msi_capability_init(dev, nvec, affd); + if (rc == 0) + return nvec; + + if (rc < 0) + return rc; + if (rc < minvec) + return -ENOSPC; + + nvec = rc; + } +} + +/** + * pci_msi_vec_count - Return the number of MSI vectors a device can send + * @dev: device to report about + * + * This function returns the number of MSI vectors a device requested via + * Multiple Message Capable register. It returns a negative errno if the + * device is not capable sending MSI interrupts. Otherwise, the call succeeds + * and returns a power of two, up to a maximum of 2^5 (32), according to the + * MSI specification. + **/ +int pci_msi_vec_count(struct pci_dev *dev) +{ + int ret; + u16 msgctl; + + if (!dev->msi_cap) + return -EINVAL; + + pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &msgctl); + ret = 1 << ((msgctl & PCI_MSI_FLAGS_QMASK) >> 1); + + return ret; +} +EXPORT_SYMBOL(pci_msi_vec_count); + +/* + * Architecture override returns true when the PCI MSI message should be + * written by the generic restore function. + */ +bool __weak arch_restore_msi_irqs(struct pci_dev *dev) +{ + return true; +} + +void __pci_restore_msi_state(struct pci_dev *dev) +{ + struct msi_desc *entry; + u16 control; + + if (!dev->msi_enabled) + return; + + entry = irq_get_msi_desc(dev->irq); + + pci_intx_for_msi(dev, 0); + pci_msi_set_enable(dev, 0); + if (arch_restore_msi_irqs(dev)) + __pci_write_msi_msg(entry, &entry->msg); + + pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control); + pci_msi_update_mask(entry, 0, 0); + control &= ~PCI_MSI_FLAGS_QSIZE; + control |= (entry->pci.msi_attrib.multiple << 4) | PCI_MSI_FLAGS_ENABLE; + pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control); +} + +void pci_msi_shutdown(struct pci_dev *dev) +{ + struct msi_desc *desc; + + if (!pci_msi_enable || !dev || !dev->msi_enabled) + return; + + pci_msi_set_enable(dev, 0); + pci_intx_for_msi(dev, 1); + dev->msi_enabled = 0; + + /* Return the device with MSI unmasked as initial states */ + desc = msi_first_desc(&dev->dev, MSI_DESC_ALL); + if (!WARN_ON_ONCE(!desc)) + pci_msi_unmask(desc, msi_multi_mask(desc)); + + /* Restore dev->irq to its default pin-assertion IRQ */ + dev->irq = desc->pci.msi_attrib.default_irq; + pcibios_alloc_irq(dev); +} + +/* PCI/MSI-X specific functionality */ + +static void pci_msix_clear_and_set_ctrl(struct pci_dev *dev, u16 clear, u16 set) +{ + u16 ctrl; + + pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &ctrl); + ctrl &= ~clear; + ctrl |= set; + pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, ctrl); +} + static void __iomem *msix_map_region(struct pci_dev *dev, unsigned int nr_entries) { @@ -502,36 +569,58 @@ static void __iomem *msix_map_region(struct pci_dev *dev, return ioremap(phys_addr, nr_entries * PCI_MSIX_ENTRY_SIZE); } -static int msix_setup_msi_descs(struct pci_dev *dev, void __iomem *base, - struct msix_entry *entries, int nvec, - struct irq_affinity_desc *masks) +/** + * msix_prepare_msi_desc - Prepare a half initialized MSI descriptor for operation + * @dev: The PCI device for which the descriptor is prepared + * @desc: The MSI descriptor for preparation + * + * This is separate from msix_setup_msi_descs() below to handle dynamic + * allocations for MSI-X after initial enablement. + * + * Ideally the whole MSI-X setup would work that way, but there is no way to + * support this for the legacy arch_setup_msi_irqs() mechanism and for the + * fake irq domains like the x86 XEN one. Sigh... + * + * The descriptor is zeroed and only @desc::msi_index and @desc::affinity + * are set. When called from msix_setup_msi_descs() then the is_virtual + * attribute is initialized as well. + * + * Fill in the rest. + */ +void msix_prepare_msi_desc(struct pci_dev *dev, struct msi_desc *desc) +{ + desc->nvec_used = 1; + desc->pci.msi_attrib.is_msix = 1; + desc->pci.msi_attrib.is_64 = 1; + desc->pci.msi_attrib.default_irq = dev->irq; + desc->pci.mask_base = dev->msix_base; + desc->pci.msi_attrib.can_mask = !pci_msi_ignore_mask && + !desc->pci.msi_attrib.is_virtual; + + if (desc->pci.msi_attrib.can_mask) { + void __iomem *addr = pci_msix_desc_addr(desc); + + desc->pci.msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL); + } +} + +static int msix_setup_msi_descs(struct pci_dev *dev, struct msix_entry *entries, + int nvec, struct irq_affinity_desc *masks) { int ret = 0, i, vec_count = pci_msix_vec_count(dev); struct irq_affinity_desc *curmsk; struct msi_desc desc; - void __iomem *addr; memset(&desc, 0, sizeof(desc)); - desc.nvec_used = 1; - desc.pci.msi_attrib.is_msix = 1; - desc.pci.msi_attrib.is_64 = 1; - desc.pci.msi_attrib.default_irq = dev->irq; - desc.pci.mask_base = base; - for (i = 0, curmsk = masks; i < nvec; i++, curmsk++) { desc.msi_index = entries ? entries[i].entry : i; desc.affinity = masks ? curmsk : NULL; desc.pci.msi_attrib.is_virtual = desc.msi_index >= vec_count; - desc.pci.msi_attrib.can_mask = !pci_msi_ignore_mask && - !desc.pci.msi_attrib.is_virtual; - if (desc.pci.msi_attrib.can_mask) { - addr = pci_msix_desc_addr(&desc); - desc.pci.msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL); - } + msix_prepare_msi_desc(dev, &desc); - ret = msi_add_msi_desc(&dev->dev, &desc); + ret = msi_insert_msi_desc(&dev->dev, &desc); if (ret) break; } @@ -562,9 +651,8 @@ static void msix_mask_all(void __iomem *base, int tsize) writel(ctrl, base + PCI_MSIX_ENTRY_VECTOR_CTRL); } -static int msix_setup_interrupts(struct pci_dev *dev, void __iomem *base, - struct msix_entry *entries, int nvec, - struct irq_affinity *affd) +static int msix_setup_interrupts(struct pci_dev *dev, struct msix_entry *entries, + int nvec, struct irq_affinity *affd) { struct irq_affinity_desc *masks = NULL; int ret; @@ -573,7 +661,7 @@ static int msix_setup_interrupts(struct pci_dev *dev, void __iomem *base, masks = irq_create_affinity_masks(nvec, affd); msi_lock_descs(&dev->dev); - ret = msix_setup_msi_descs(dev, base, entries, nvec, masks); + ret = msix_setup_msi_descs(dev, entries, nvec, masks); if (ret) goto out_free; @@ -590,7 +678,7 @@ static int msix_setup_interrupts(struct pci_dev *dev, void __iomem *base, goto out_unlock; out_free: - free_msi_irqs(dev); + pci_free_msi_irqs(dev); out_unlock: msi_unlock_descs(&dev->dev); kfree(masks); @@ -611,7 +699,6 @@ out_unlock: static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, int nvec, struct irq_affinity *affd) { - void __iomem *base; int ret, tsize; u16 control; @@ -629,15 +716,13 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control); /* Request & Map MSI-X table region */ tsize = msix_table_size(control); - base = msix_map_region(dev, tsize); - if (!base) { + dev->msix_base = msix_map_region(dev, tsize); + if (!dev->msix_base) { ret = -ENOMEM; goto out_disable; } - dev->msix_base = base; - - ret = msix_setup_interrupts(dev, base, entries, nvec, affd); + ret = msix_setup_interrupts(dev, entries, nvec, affd); if (ret) goto out_disable; @@ -652,7 +737,7 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, * which takes the MSI-X mask bits into account even * when MSI-X is disabled, which prevents MSI delivery. */ - msix_mask_all(base, tsize); + msix_mask_all(dev->msix_base, tsize); pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0); pcibios_free_irq(dev); @@ -665,236 +750,82 @@ out_disable: return ret; } -/** - * pci_msi_supported - check whether MSI may be enabled on a device - * @dev: pointer to the pci_dev data structure of MSI device function - * @nvec: how many MSIs have been requested? - * - * Look at global flags, the device itself, and its parent buses - * to determine if MSI/-X are supported for the device. If MSI/-X is - * supported return 1, else return 0. - **/ -static int pci_msi_supported(struct pci_dev *dev, int nvec) -{ - struct pci_bus *bus; - - /* MSI must be globally enabled and supported by the device */ - if (!pci_msi_enable) - return 0; - - if (!dev || dev->no_msi) - return 0; - - /* - * You can't ask to have 0 or less MSIs configured. - * a) it's stupid .. - * b) the list manipulation code assumes nvec >= 1. - */ - if (nvec < 1) - return 0; - - /* - * Any bridge which does NOT route MSI transactions from its - * secondary bus to its primary bus must set NO_MSI flag on - * the secondary pci_bus. - * - * The NO_MSI flag can either be set directly by: - * - arch-specific PCI host bus controller drivers (deprecated) - * - quirks for specific PCI bridges - * - * or indirectly by platform-specific PCI host bridge drivers by - * advertising the 'msi_domain' property, which results in - * the NO_MSI flag when no MSI domain is found for this bridge - * at probe time. - */ - for (bus = dev->bus; bus; bus = bus->parent) - if (bus->bus_flags & PCI_BUS_FLAGS_NO_MSI) - return 0; - - return 1; -} - -/** - * pci_msi_vec_count - Return the number of MSI vectors a device can send - * @dev: device to report about - * - * This function returns the number of MSI vectors a device requested via - * Multiple Message Capable register. It returns a negative errno if the - * device is not capable sending MSI interrupts. Otherwise, the call succeeds - * and returns a power of two, up to a maximum of 2^5 (32), according to the - * MSI specification. - **/ -int pci_msi_vec_count(struct pci_dev *dev) -{ - int ret; - u16 msgctl; - - if (!dev->msi_cap) - return -EINVAL; - - pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &msgctl); - ret = 1 << ((msgctl & PCI_MSI_FLAGS_QMASK) >> 1); - - return ret; -} -EXPORT_SYMBOL(pci_msi_vec_count); - -static void pci_msi_shutdown(struct pci_dev *dev) -{ - struct msi_desc *desc; - - if (!pci_msi_enable || !dev || !dev->msi_enabled) - return; - - pci_msi_set_enable(dev, 0); - pci_intx_for_msi(dev, 1); - dev->msi_enabled = 0; - - /* Return the device with MSI unmasked as initial states */ - desc = msi_first_desc(&dev->dev, MSI_DESC_ALL); - if (!WARN_ON_ONCE(!desc)) - pci_msi_unmask(desc, msi_multi_mask(desc)); - - /* Restore dev->irq to its default pin-assertion IRQ */ - dev->irq = desc->pci.msi_attrib.default_irq; - pcibios_alloc_irq(dev); -} - -void pci_disable_msi(struct pci_dev *dev) -{ - if (!pci_msi_enable || !dev || !dev->msi_enabled) - return; - - msi_lock_descs(&dev->dev); - pci_msi_shutdown(dev); - free_msi_irqs(dev); - msi_unlock_descs(&dev->dev); -} -EXPORT_SYMBOL(pci_disable_msi); - -/** - * pci_msix_vec_count - return the number of device's MSI-X table entries - * @dev: pointer to the pci_dev data structure of MSI-X device function - * This function returns the number of device's MSI-X table entries and - * therefore the number of MSI-X vectors device is capable of sending. - * It returns a negative errno if the device is not capable of sending MSI-X - * interrupts. - **/ -int pci_msix_vec_count(struct pci_dev *dev) -{ - u16 control; - - if (!dev->msix_cap) - return -EINVAL; - - pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control); - return msix_table_size(control); -} -EXPORT_SYMBOL(pci_msix_vec_count); - -static int __pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, - int nvec, struct irq_affinity *affd, int flags) +static bool pci_msix_validate_entries(struct pci_dev *dev, struct msix_entry *entries, + int nvec, int hwsize) { - int nr_entries; + bool nogap; int i, j; - if (!pci_msi_supported(dev, nvec) || dev->current_state != PCI_D0) - return -EINVAL; + if (!entries) + return true; - nr_entries = pci_msix_vec_count(dev); - if (nr_entries < 0) - return nr_entries; - if (nvec > nr_entries && !(flags & PCI_IRQ_VIRTUAL)) - return nr_entries; + nogap = pci_msi_domain_supports(dev, MSI_FLAG_MSIX_CONTIGUOUS, DENY_LEGACY); - if (entries) { - /* Check for any invalid entries */ - for (i = 0; i < nvec; i++) { - if (entries[i].entry >= nr_entries) - return -EINVAL; /* invalid entry */ - for (j = i + 1; j < nvec; j++) { - if (entries[i].entry == entries[j].entry) - return -EINVAL; /* duplicate entry */ - } - } - } + for (i = 0; i < nvec; i++) { + /* Entry within hardware limit? */ + if (entries[i].entry >= hwsize) + return false; - /* Check whether driver already requested for MSI IRQ */ - if (dev->msi_enabled) { - pci_info(dev, "can't enable MSI-X (MSI IRQ already assigned)\n"); - return -EINVAL; + /* Check for duplicate entries */ + for (j = i + 1; j < nvec; j++) { + if (entries[i].entry == entries[j].entry) + return false; + } + /* Check for unsupported gaps */ + if (nogap && entries[i].entry != i) + return false; } - return msix_capability_init(dev, entries, nvec, affd); + return true; } -static void pci_msix_shutdown(struct pci_dev *dev) +int __pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, + int maxvec, struct irq_affinity *affd, int flags) { - struct msi_desc *desc; + int hwsize, rc, nvec = maxvec; - if (!pci_msi_enable || !dev || !dev->msix_enabled) - return; + if (maxvec < minvec) + return -ERANGE; - if (pci_dev_is_disconnected(dev)) { - dev->msix_enabled = 0; - return; + if (dev->msi_enabled) { + pci_info(dev, "can't enable MSI-X (MSI already enabled)\n"); + return -EINVAL; } - /* Return the device with MSI-X masked as initial states */ - msi_for_each_desc(desc, &dev->dev, MSI_DESC_ALL) - pci_msix_mask(desc); + if (WARN_ON_ONCE(dev->msix_enabled)) + return -EINVAL; - pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0); - pci_intx_for_msi(dev, 1); - dev->msix_enabled = 0; - pcibios_alloc_irq(dev); -} + /* Check MSI-X early on irq domain enabled architectures */ + if (!pci_msi_domain_supports(dev, MSI_FLAG_PCI_MSIX, ALLOW_LEGACY)) + return -ENOTSUPP; -void pci_disable_msix(struct pci_dev *dev) -{ - if (!pci_msi_enable || !dev || !dev->msix_enabled) - return; - - msi_lock_descs(&dev->dev); - pci_msix_shutdown(dev); - free_msi_irqs(dev); - msi_unlock_descs(&dev->dev); -} -EXPORT_SYMBOL(pci_disable_msix); + if (!pci_msi_supported(dev, nvec) || dev->current_state != PCI_D0) + return -EINVAL; -static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, - struct irq_affinity *affd) -{ - int nvec; - int rc; + hwsize = pci_msix_vec_count(dev); + if (hwsize < 0) + return hwsize; - if (!pci_msi_supported(dev, minvec) || dev->current_state != PCI_D0) + if (!pci_msix_validate_entries(dev, entries, nvec, hwsize)) return -EINVAL; - /* Check whether driver already requested MSI-X IRQs */ - if (dev->msix_enabled) { - pci_info(dev, "can't enable MSI (MSI-X already enabled)\n"); - return -EINVAL; + if (hwsize < nvec) { + /* Keep the IRQ virtual hackery working */ + if (flags & PCI_IRQ_VIRTUAL) + hwsize = nvec; + else + nvec = hwsize; } - if (maxvec < minvec) - return -ERANGE; - - if (WARN_ON_ONCE(dev->msi_enabled)) - return -EINVAL; - - nvec = pci_msi_vec_count(dev); - if (nvec < 0) - return nvec; if (nvec < minvec) return -ENOSPC; - if (nvec > maxvec) - nvec = maxvec; - rc = pci_setup_msi_context(dev); if (rc) return rc; + if (!pci_setup_msix_device_domain(dev, hwsize)) + return -ENODEV; + for (;;) { if (affd) { nvec = irq_calc_affinity_vectors(minvec, nvec, affd); @@ -902,7 +833,7 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, return -ENOSPC; } - rc = msi_capability_init(dev, nvec, affd); + rc = msix_capability_init(dev, entries, nvec, affd); if (rc == 0) return nvec; @@ -915,214 +846,67 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, } } -/* deprecated, don't use */ -int pci_enable_msi(struct pci_dev *dev) -{ - int rc = __pci_enable_msi_range(dev, 1, 1, NULL); - if (rc < 0) - return rc; - return 0; -} -EXPORT_SYMBOL(pci_enable_msi); - -static int __pci_enable_msix_range(struct pci_dev *dev, - struct msix_entry *entries, int minvec, - int maxvec, struct irq_affinity *affd, - int flags) +void __pci_restore_msix_state(struct pci_dev *dev) { - int rc, nvec = maxvec; - - if (maxvec < minvec) - return -ERANGE; - - if (WARN_ON_ONCE(dev->msix_enabled)) - return -EINVAL; - - rc = pci_setup_msi_context(dev); - if (rc) - return rc; + struct msi_desc *entry; + bool write_msg; - for (;;) { - if (affd) { - nvec = irq_calc_affinity_vectors(minvec, nvec, affd); - if (nvec < minvec) - return -ENOSPC; - } + if (!dev->msix_enabled) + return; - rc = __pci_enable_msix(dev, entries, nvec, affd, flags); - if (rc == 0) - return nvec; + /* route the table */ + pci_intx_for_msi(dev, 0); + pci_msix_clear_and_set_ctrl(dev, 0, + PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL); - if (rc < 0) - return rc; - if (rc < minvec) - return -ENOSPC; + write_msg = arch_restore_msi_irqs(dev); - nvec = rc; + msi_lock_descs(&dev->dev); + msi_for_each_desc(entry, &dev->dev, MSI_DESC_ALL) { + if (write_msg) + __pci_write_msi_msg(entry, &entry->msg); + pci_msix_write_vector_ctrl(entry, entry->pci.msix_ctrl); } -} + msi_unlock_descs(&dev->dev); -/** - * pci_enable_msix_range - configure device's MSI-X capability structure - * @dev: pointer to the pci_dev data structure of MSI-X device function - * @entries: pointer to an array of MSI-X entries - * @minvec: minimum number of MSI-X IRQs requested - * @maxvec: maximum number of MSI-X IRQs requested - * - * Setup the MSI-X capability structure of device function with a maximum - * possible number of interrupts in the range between @minvec and @maxvec - * upon its software driver call to request for MSI-X mode enabled on its - * hardware device function. It returns a negative errno if an error occurs. - * If it succeeds, it returns the actual number of interrupts allocated and - * indicates the successful configuration of MSI-X capability structure - * with new allocated MSI-X interrupts. - **/ -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, NULL, 0); + pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0); } -EXPORT_SYMBOL(pci_enable_msix_range); -/** - * pci_alloc_irq_vectors_affinity - allocate multiple IRQs for a device - * @dev: PCI device to operate on - * @min_vecs: minimum number of vectors required (must be >= 1) - * @max_vecs: maximum (desired) number of vectors - * @flags: flags or quirks for the allocation - * @affd: optional description of the affinity requirements - * - * Allocate up to @max_vecs interrupt vectors for @dev, using MSI-X or MSI - * vectors if available, and fall back to a single legacy vector - * if neither is available. Return the number of vectors allocated, - * (which might be smaller than @max_vecs) if successful, or a negative - * error code on error. If less than @min_vecs interrupt vectors are - * available for @dev the function will fail with -ENOSPC. - * - * To get the Linux IRQ number used for a vector that can be passed to - * request_irq() use the pci_irq_vector() helper. - */ -int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, - unsigned int max_vecs, unsigned int flags, - struct irq_affinity *affd) +void pci_msix_shutdown(struct pci_dev *dev) { - struct irq_affinity msi_default_affd = {0}; - int nvecs = -ENOSPC; - - if (flags & PCI_IRQ_AFFINITY) { - if (!affd) - affd = &msi_default_affd; - } else { - if (WARN_ON(affd)) - affd = NULL; - } + struct msi_desc *desc; - if (flags & PCI_IRQ_MSIX) { - nvecs = __pci_enable_msix_range(dev, NULL, min_vecs, max_vecs, - affd, flags); - if (nvecs > 0) - return nvecs; - } + if (!pci_msi_enable || !dev || !dev->msix_enabled) + return; - if (flags & PCI_IRQ_MSI) { - nvecs = __pci_enable_msi_range(dev, min_vecs, max_vecs, affd); - if (nvecs > 0) - return nvecs; + if (pci_dev_is_disconnected(dev)) { + dev->msix_enabled = 0; + return; } - /* use legacy IRQ if allowed */ - if (flags & PCI_IRQ_LEGACY) { - if (min_vecs == 1 && dev->irq) { - /* - * Invoke the affinity spreading logic to ensure that - * the device driver can adjust queue configuration - * for the single interrupt case. - */ - if (affd) - irq_create_affinity_masks(1, affd); - pci_intx(dev, 1); - return 1; - } - } + /* Return the device with MSI-X masked as initial states */ + msi_for_each_desc(desc, &dev->dev, MSI_DESC_ALL) + pci_msix_mask(desc); - return nvecs; + pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0); + pci_intx_for_msi(dev, 1); + dev->msix_enabled = 0; + pcibios_alloc_irq(dev); } -EXPORT_SYMBOL(pci_alloc_irq_vectors_affinity); -/** - * pci_free_irq_vectors - free previously allocated IRQs for a device - * @dev: PCI device to operate on - * - * Undoes the allocations and enabling in pci_alloc_irq_vectors(). - */ -void pci_free_irq_vectors(struct pci_dev *dev) -{ - pci_disable_msix(dev); - pci_disable_msi(dev); -} -EXPORT_SYMBOL(pci_free_irq_vectors); +/* Common interfaces */ -/** - * pci_irq_vector - return Linux IRQ number of a device vector - * @dev: PCI device to operate on - * @nr: Interrupt vector index (0-based) - * - * @nr has the following meanings depending on the interrupt mode: - * MSI-X: The index in the MSI-X vector table - * MSI: The index of the enabled MSI vectors - * INTx: Must be 0 - * - * Return: The Linux interrupt number or -EINVAl if @nr is out of range. - */ -int pci_irq_vector(struct pci_dev *dev, unsigned int nr) +void pci_free_msi_irqs(struct pci_dev *dev) { - unsigned int irq; - - if (!dev->msi_enabled && !dev->msix_enabled) - return !nr ? dev->irq : -EINVAL; + pci_msi_teardown_msi_irqs(dev); - irq = msi_get_virq(&dev->dev, nr); - return irq ? irq : -EINVAL; + if (dev->msix_base) { + iounmap(dev->msix_base); + dev->msix_base = NULL; + } } -EXPORT_SYMBOL(pci_irq_vector); -/** - * pci_irq_get_affinity - return the affinity of a particular MSI vector - * @dev: PCI device to operate on - * @nr: device-relative interrupt vector index (0-based). - * - * @nr has the following meanings depending on the interrupt mode: - * MSI-X: The index in the MSI-X vector table - * MSI: The index of the enabled MSI vectors - * INTx: Must be 0 - * - * Return: A cpumask pointer or NULL if @nr is out of range - */ -const struct cpumask *pci_irq_get_affinity(struct pci_dev *dev, int nr) -{ - int idx, irq = pci_irq_vector(dev, nr); - struct msi_desc *desc; - - if (WARN_ON_ONCE(irq <= 0)) - return NULL; - - desc = irq_get_msi_desc(irq); - /* Non-MSI does not have the information handy */ - if (!desc) - return cpu_possible_mask; - - /* MSI[X] interrupts can be allocated without affinity descriptor */ - if (!desc->affinity) - return NULL; - - /* - * MSI has a mask array in the descriptor. - * MSI-X has a single mask. - */ - idx = dev->msi_enabled ? nr : 0; - return &desc->affinity[idx].mask; -} -EXPORT_SYMBOL(pci_irq_get_affinity); +/* Misc. infrastructure */ struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc) { @@ -1134,15 +918,3 @@ void pci_no_msi(void) { pci_msi_enable = 0; } - -/** - * pci_msi_enabled - is MSI enabled? - * - * Returns true if MSI has not been disabled by the command-line option - * pci=nomsi. - **/ -int pci_msi_enabled(void) -{ - return pci_msi_enable; -} -EXPORT_SYMBOL(pci_msi_enabled); diff --git a/drivers/pci/msi/msi.h b/drivers/pci/msi/msi.h index dbeff066bedd..ee53cf079f4e 100644 --- a/drivers/pci/msi/msi.h +++ b/drivers/pci/msi/msi.h @@ -5,24 +5,70 @@ #define msix_table_size(flags) ((flags & PCI_MSIX_FLAGS_QSIZE) + 1) -extern int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); -extern void pci_msi_teardown_msi_irqs(struct pci_dev *dev); +int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); +void pci_msi_teardown_msi_irqs(struct pci_dev *dev); -#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS -extern int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); -extern void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev); -#else -static inline int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) +/* Mask/unmask helpers */ +void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 set); + +static inline void pci_msi_mask(struct msi_desc *desc, u32 mask) { - WARN_ON_ONCE(1); - return -ENODEV; + pci_msi_update_mask(desc, 0, mask); } -static inline void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev) +static inline void pci_msi_unmask(struct msi_desc *desc, u32 mask) { - WARN_ON_ONCE(1); + pci_msi_update_mask(desc, mask, 0); +} + +static inline void __iomem *pci_msix_desc_addr(struct msi_desc *desc) +{ + return desc->pci.mask_base + desc->msi_index * PCI_MSIX_ENTRY_SIZE; +} + +/* + * This internal function does not flush PCI writes to the device. All + * users must ensure that they read from the device before either assuming + * that the device state is up to date, or returning out of this file. + * It does not affect the msi_desc::msix_ctrl cache either. Use with care! + */ +static inline void pci_msix_write_vector_ctrl(struct msi_desc *desc, u32 ctrl) +{ + void __iomem *desc_addr = pci_msix_desc_addr(desc); + + if (desc->pci.msi_attrib.can_mask) + writel(ctrl, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL); +} + +static inline void pci_msix_mask(struct msi_desc *desc) +{ + desc->pci.msix_ctrl |= PCI_MSIX_ENTRY_CTRL_MASKBIT; + pci_msix_write_vector_ctrl(desc, desc->pci.msix_ctrl); + /* Flush write to device */ + readl(desc->pci.mask_base); +} + +static inline void pci_msix_unmask(struct msi_desc *desc) +{ + desc->pci.msix_ctrl &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT; + pci_msix_write_vector_ctrl(desc, desc->pci.msix_ctrl); +} + +static inline void __pci_msi_mask_desc(struct msi_desc *desc, u32 mask) +{ + if (desc->pci.msi_attrib.is_msix) + pci_msix_mask(desc); + else + pci_msi_mask(desc, mask); +} + +static inline void __pci_msi_unmask_desc(struct msi_desc *desc, u32 mask) +{ + if (desc->pci.msi_attrib.is_msix) + pci_msix_unmask(desc); + else + pci_msi_unmask(desc, mask); } -#endif /* * PCI 2.3 does not specify mask bits for each MSI interrupt. Attempting to @@ -37,3 +83,47 @@ static inline __attribute_const__ u32 msi_multi_mask(struct msi_desc *desc) return 0xffffffff; return (1 << (1 << desc->pci.msi_attrib.multi_cap)) - 1; } + +void msix_prepare_msi_desc(struct pci_dev *dev, struct msi_desc *desc); + +/* Subsystem variables */ +extern int pci_msi_enable; + +/* MSI internal functions invoked from the public APIs */ +void pci_msi_shutdown(struct pci_dev *dev); +void pci_msix_shutdown(struct pci_dev *dev); +void pci_free_msi_irqs(struct pci_dev *dev); +int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, struct irq_affinity *affd); +int __pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, + int maxvec, struct irq_affinity *affd, int flags); +void __pci_restore_msi_state(struct pci_dev *dev); +void __pci_restore_msix_state(struct pci_dev *dev); + +/* irq_domain related functionality */ + +enum support_mode { + ALLOW_LEGACY, + DENY_LEGACY, +}; + +bool pci_msi_domain_supports(struct pci_dev *dev, unsigned int feature_mask, enum support_mode mode); +bool pci_setup_msi_device_domain(struct pci_dev *pdev); +bool pci_setup_msix_device_domain(struct pci_dev *pdev, unsigned int hwsize); + +/* Legacy (!IRQDOMAIN) fallbacks */ + +#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS +int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); +void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev); +#else +static inline int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) +{ + WARN_ON_ONCE(1); + return -ENODEV; +} + +static inline void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev) +{ + WARN_ON_ONCE(1); +} +#endif diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index b66fa42c4b1f..fdd7e56ddf40 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -842,7 +842,6 @@ static struct irq_domain *pci_host_bridge_msi_domain(struct pci_bus *bus) if (!d) d = pci_host_bridge_acpi_msi_domain(bus); -#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN /* * If no IRQ domain was found via the OF tree, try looking it up * directly through the fwnode_handle. @@ -854,7 +853,6 @@ static struct irq_domain *pci_host_bridge_msi_domain(struct pci_bus *bus) d = irq_find_matching_fwnode(fwnode, DOMAIN_BUS_PCI_MSI); } -#endif return d; } diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig index 341010f20b77..692ffd56f5cc 100644 --- a/drivers/perf/Kconfig +++ b/drivers/perf/Kconfig @@ -93,7 +93,7 @@ config ARM_PMU_ACPI config ARM_SMMU_V3_PMU tristate "ARM SMMUv3 Performance Monitors Extension" depends on (ARM64 && ACPI) || (COMPILE_TEST && 64BIT) - depends on GENERIC_MSI_IRQ_DOMAIN + depends on GENERIC_MSI_IRQ help Provides support for the ARM SMMUv3 Performance Monitor Counter Groups (PMCG), which provide monitoring of transactions passing diff --git a/drivers/platform/x86/amd/pmc.c b/drivers/platform/x86/amd/pmc.c index ef4ae977b8e0..439d282aafd1 100644 --- a/drivers/platform/x86/amd/pmc.c +++ b/drivers/platform/x86/amd/pmc.c @@ -739,8 +739,14 @@ static void amd_pmc_s2idle_prepare(void) static void amd_pmc_s2idle_check(void) { struct amd_pmc_dev *pdev = &pmc; + struct smu_metrics table; int rc; + /* CZN: Ensure that future s0i3 entry attempts at least 10ms passed */ + if (pdev->cpu_id == AMD_CPU_ID_CZN && !get_metrics_table(pdev, &table) && + table.s0i3_last_entry_status) + usleep_range(10000, 20000); + /* Dump the IdleMask before we add to the STB */ amd_pmc_idlemask_read(pdev, pdev->dev, NULL); diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 9dc935886e9f..c6ded3fdd715 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -758,7 +758,6 @@ static void qeth_l2_br2dev_worker(struct work_struct *work) struct list_head *iter; int err = 0; - kfree(br2dev_event_work); QETH_CARD_TEXT_(card, 4, "b2dw%04lx", event); QETH_CARD_TEXT_(card, 4, "ma%012llx", ether_addr_to_u64(addr)); @@ -815,6 +814,7 @@ unlock: dev_put(brdev); dev_put(lsyncdev); dev_put(dstdev); + kfree(br2dev_event_work); } static int qeth_l2_br2dev_queue_work(struct net_device *brdev, diff --git a/drivers/soc/fsl/dpio/dpio-driver.c b/drivers/soc/fsl/dpio/dpio-driver.c index 5a2edc48dd79..74eace3109a1 100644 --- a/drivers/soc/fsl/dpio/dpio-driver.c +++ b/drivers/soc/fsl/dpio/dpio-driver.c @@ -10,7 +10,6 @@ #include <linux/module.h> #include <linux/platform_device.h> #include <linux/interrupt.h> -#include <linux/msi.h> #include <linux/dma-mapping.h> #include <linux/delay.h> #include <linux/io.h> diff --git a/drivers/soc/ti/Kconfig b/drivers/soc/ti/Kconfig index 7e2fb1c16af1..e9a597e4bdc8 100644 --- a/drivers/soc/ti/Kconfig +++ b/drivers/soc/ti/Kconfig @@ -98,6 +98,6 @@ endif # SOC_TI config TI_SCI_INTA_MSI_DOMAIN bool - select GENERIC_MSI_IRQ_DOMAIN + select GENERIC_MSI_IRQ help Driver to enable Interrupt Aggregator specific MSI Domain. diff --git a/drivers/soc/ti/ti_sci_inta_msi.c b/drivers/soc/ti/ti_sci_inta_msi.c index 991c78b34745..b9251e1d9a5c 100644 --- a/drivers/soc/ti/ti_sci_inta_msi.c +++ b/drivers/soc/ti/ti_sci_inta_msi.c @@ -73,13 +73,13 @@ static int ti_sci_inta_msi_alloc_descs(struct device *dev, for (set = 0; set < res->sets; set++) { for (i = 0; i < res->desc[set].num; i++, count++) { msi_desc.msi_index = res->desc[set].start + i; - if (msi_add_msi_desc(dev, &msi_desc)) + if (msi_insert_msi_desc(dev, &msi_desc)) goto fail; } for (i = 0; i < res->desc[set].num_sec; i++, count++) { msi_desc.msi_index = res->desc[set].start_sec + i; - if (msi_add_msi_desc(dev, &msi_desc)) + if (msi_insert_msi_desc(dev, &msi_desc)) goto fail; } } @@ -93,13 +93,8 @@ int ti_sci_inta_msi_domain_alloc_irqs(struct device *dev, struct ti_sci_resource *res) { struct platform_device *pdev = to_platform_device(dev); - struct irq_domain *msi_domain; int ret, nvec; - msi_domain = dev_get_msi_domain(dev); - if (!msi_domain) - return -EINVAL; - if (pdev->id < 0) return -ENODEV; @@ -114,7 +109,8 @@ int ti_sci_inta_msi_domain_alloc_irqs(struct device *dev, goto unlock; } - ret = msi_domain_alloc_irqs_descs_locked(msi_domain, dev, nvec); + /* Use alloc ALL as it's unclear whether there are gaps in the indices */ + ret = msi_domain_alloc_irqs_all_locked(dev, MSI_DEFAULT_DOMAIN, nvec); if (ret) dev_err(dev, "Failed to allocate IRQs %d\n", ret); unlock: diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c index 7b428eac3d3e..64d01f3fb13d 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c @@ -8,7 +8,6 @@ #include <linux/slab.h> #include <linux/types.h> #include <linux/eventfd.h> -#include <linux/msi.h> #include "linux/fsl/mc.h" #include "vfio_fsl_mc_private.h" diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 451d8a077e12..bce2492186d0 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -605,6 +605,14 @@ again: set_bit(FSCACHE_COOKIE_DO_PREP_TO_WRITE, &cookie->flags); queue = true; } + /* + * We could race with cookie_lru which may set LRU_DISCARD bit + * but has yet to run the cookie state machine. If this happens + * and another thread tries to use the cookie, clear LRU_DISCARD + * so we don't end up withdrawing the cookie while in use. + */ + if (test_and_clear_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags)) + fscache_see_cookie(cookie, fscache_cookie_see_lru_discard_clear); break; case FSCACHE_COOKIE_STATE_FAILED: diff --git a/include/asm-generic/msi.h b/include/asm-generic/msi.h index bf910d47e900..124c734ca5d9 100644 --- a/include/asm-generic/msi.h +++ b/include/asm-generic/msi.h @@ -4,7 +4,7 @@ #include <linux/types.h> -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +#ifdef CONFIG_GENERIC_MSI_IRQ #ifndef NUM_MSI_ALLOC_SCRATCHPAD_REGS # define NUM_MSI_ALLOC_SCRATCHPAD_REGS 2 @@ -36,6 +36,6 @@ typedef struct msi_alloc_info { #define GENERIC_MSI_DOMAIN_OPS 1 -#endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */ +#endif /* CONFIG_GENERIC_MSI_IRQ */ #endif diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h index b3f5d73ae1d6..b4a3935801ca 100644 --- a/include/clocksource/hyperv_timer.h +++ b/include/clocksource/hyperv_timer.h @@ -15,13 +15,15 @@ #include <linux/clocksource.h> #include <linux/math64.h> -#include <asm/mshyperv.h> +#include <asm/hyperv-tlfs.h> #define HV_MAX_MAX_DELTA_TICKS 0xffffffff #define HV_MIN_DELTA_TICKS 1 #ifdef CONFIG_HYPERV_TIMER +#include <asm/hyperv_timer.h> + /* Routines called by the VMbus driver */ extern int hv_stimer_alloc(bool have_percpu_irqs); extern int hv_stimer_cleanup(unsigned int cpu); diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 528bd44b59e2..2b7d077de7ef 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -68,6 +68,7 @@ struct css_task_iter { struct list_head iters_node; /* css_set->task_iters */ }; +extern struct file_system_type cgroup_fs_type; extern struct cgroup_root cgrp_dfl_root; extern struct css_set init_css_set; diff --git a/include/linux/device.h b/include/linux/device.h index 424b55df0272..c90a444be1c4 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -378,10 +378,8 @@ struct dev_links_info { * @data: Pointer to MSI device data */ struct dev_msi_info { -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN - struct irq_domain *domain; -#endif #ifdef CONFIG_GENERIC_MSI_IRQ + struct irq_domain *domain; struct msi_device_data *data; #endif }; @@ -742,7 +740,7 @@ static inline void set_dev_node(struct device *dev, int node) static inline struct irq_domain *dev_get_msi_domain(const struct device *dev) { -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +#ifdef CONFIG_GENERIC_MSI_IRQ return dev->msi.domain; #else return NULL; @@ -751,7 +749,7 @@ static inline struct irq_domain *dev_get_msi_domain(const struct device *dev) static inline void dev_set_msi_domain(struct device *dev, struct irq_domain *d) { -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +#ifdef CONFIG_GENERIC_MSI_IRQ dev->msi.domain = d; #endif } diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 6aeea1071b1b..88ae4513abb5 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -27,7 +27,7 @@ struct gpio_chip; union gpio_irq_fwspec { struct irq_fwspec fwspec; -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +#ifdef CONFIG_GENERIC_MSI_IRQ msi_alloc_info_t msiinfo; #endif }; diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 00d577f90883..a372086750ca 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -31,6 +31,7 @@ #define _LINUX_IRQDOMAIN_H #include <linux/types.h> +#include <linux/irqdomain_defs.h> #include <linux/irqhandler.h> #include <linux/of.h> #include <linux/mutex.h> @@ -45,6 +46,7 @@ struct irq_desc; struct cpumask; struct seq_file; struct irq_affinity_desc; +struct msi_parent_ops; #define IRQ_DOMAIN_IRQ_SPEC_PARAMS 16 @@ -68,27 +70,6 @@ struct irq_fwspec { void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args, unsigned int count, struct irq_fwspec *fwspec); -/* - * Should several domains have the same device node, but serve - * different purposes (for example one domain is for PCI/MSI, and the - * other for wired IRQs), they can be distinguished using a - * bus-specific token. Most domains are expected to only carry - * DOMAIN_BUS_ANY. - */ -enum irq_domain_bus_token { - DOMAIN_BUS_ANY = 0, - DOMAIN_BUS_WIRED, - DOMAIN_BUS_GENERIC_MSI, - DOMAIN_BUS_PCI_MSI, - DOMAIN_BUS_PLATFORM_MSI, - DOMAIN_BUS_NEXUS, - DOMAIN_BUS_IPI, - DOMAIN_BUS_FSL_MC_MSI, - DOMAIN_BUS_TI_SCI_INTA_MSI, - DOMAIN_BUS_WAKEUP, - DOMAIN_BUS_VMD_MSI, -}; - /** * struct irq_domain_ops - Methods for irq_domain objects * @match: Match an interrupt controller device node to a host, returns @@ -137,53 +118,61 @@ struct irq_domain_chip_generic; /** * struct irq_domain - Hardware interrupt number translation object - * @link: Element in global irq_domain list. - * @name: Name of interrupt domain - * @ops: pointer to irq_domain methods - * @host_data: private data pointer for use by owner. Not touched by irq_domain - * core code. - * @flags: host per irq_domain flags - * @mapcount: The number of mapped interrupts + * @link: Element in global irq_domain list. + * @name: Name of interrupt domain + * @ops: Pointer to irq_domain methods + * @host_data: Private data pointer for use by owner. Not touched by irq_domain + * core code. + * @flags: Per irq_domain flags + * @mapcount: The number of mapped interrupts * - * Optional elements - * @fwnode: Pointer to firmware node associated with the irq_domain. Pretty easy - * to swap it for the of_node via the irq_domain_get_of_node accessor - * @gc: Pointer to a list of generic chips. There is a helper function for - * setting up one or more generic chips for interrupt controllers - * drivers using the generic chip library which uses this pointer. - * @dev: Pointer to a device that the domain represent, and that will be - * used for power management purposes. - * @parent: Pointer to parent irq_domain to support hierarchy irq_domains + * Optional elements: + * @fwnode: Pointer to firmware node associated with the irq_domain. Pretty easy + * to swap it for the of_node via the irq_domain_get_of_node accessor + * @gc: Pointer to a list of generic chips. There is a helper function for + * setting up one or more generic chips for interrupt controllers + * drivers using the generic chip library which uses this pointer. + * @dev: Pointer to the device which instantiated the irqdomain + * With per device irq domains this is not necessarily the same + * as @pm_dev. + * @pm_dev: Pointer to a device that can be utilized for power management + * purposes related to the irq domain. + * @parent: Pointer to parent irq_domain to support hierarchy irq_domains + * @msi_parent_ops: Pointer to MSI parent domain methods for per device domain init * - * Revmap data, used internally by irq_domain - * @revmap_size: Size of the linear map table @revmap[] - * @revmap_tree: Radix map tree for hwirqs that don't fit in the linear map - * @revmap_mutex: Lock for the revmap - * @revmap: Linear table of irq_data pointers + * Revmap data, used internally by the irq domain code: + * @revmap_size: Size of the linear map table @revmap[] + * @revmap_tree: Radix map tree for hwirqs that don't fit in the linear map + * @revmap_mutex: Lock for the revmap + * @revmap: Linear table of irq_data pointers */ struct irq_domain { - struct list_head link; - const char *name; - const struct irq_domain_ops *ops; - void *host_data; - unsigned int flags; - unsigned int mapcount; + struct list_head link; + const char *name; + const struct irq_domain_ops *ops; + void *host_data; + unsigned int flags; + unsigned int mapcount; /* Optional data */ - struct fwnode_handle *fwnode; - enum irq_domain_bus_token bus_token; - struct irq_domain_chip_generic *gc; - struct device *dev; + struct fwnode_handle *fwnode; + enum irq_domain_bus_token bus_token; + struct irq_domain_chip_generic *gc; + struct device *dev; + struct device *pm_dev; #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY - struct irq_domain *parent; + struct irq_domain *parent; +#endif +#ifdef CONFIG_GENERIC_MSI_IRQ + const struct msi_parent_ops *msi_parent_ops; #endif /* reverse map data. The linear map gets appended to the irq_domain */ - irq_hw_number_t hwirq_max; - unsigned int revmap_size; - struct radix_tree_root revmap_tree; - struct mutex revmap_mutex; - struct irq_data __rcu *revmap[]; + irq_hw_number_t hwirq_max; + unsigned int revmap_size; + struct radix_tree_root revmap_tree; + struct mutex revmap_mutex; + struct irq_data __rcu *revmap[]; }; /* Irq domain flags */ @@ -206,15 +195,14 @@ enum { /* Irq domain implements MSI remapping */ IRQ_DOMAIN_FLAG_MSI_REMAP = (1 << 5), - /* - * Quirk to handle MSI implementations which do not provide - * masking. Currently known to affect x86, but partially - * handled in core code. - */ - IRQ_DOMAIN_MSI_NOMASK_QUIRK = (1 << 6), - /* Irq domain doesn't translate anything */ - IRQ_DOMAIN_FLAG_NO_MAP = (1 << 7), + IRQ_DOMAIN_FLAG_NO_MAP = (1 << 6), + + /* Irq domain is a MSI parent domain */ + IRQ_DOMAIN_FLAG_MSI_PARENT = (1 << 8), + + /* Irq domain is a MSI device domain */ + IRQ_DOMAIN_FLAG_MSI_DEVICE = (1 << 9), /* * Flags starting from IRQ_DOMAIN_FLAG_NONCORE are reserved @@ -233,7 +221,7 @@ static inline void irq_domain_set_pm_device(struct irq_domain *d, struct device *dev) { if (d) - d->dev = dev; + d->pm_dev = dev; } #ifdef CONFIG_IRQ_DOMAIN @@ -578,6 +566,16 @@ static inline bool irq_domain_is_msi_remap(struct irq_domain *domain) extern bool irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain); +static inline bool irq_domain_is_msi_parent(struct irq_domain *domain) +{ + return domain->flags & IRQ_DOMAIN_FLAG_MSI_PARENT; +} + +static inline bool irq_domain_is_msi_device(struct irq_domain *domain) +{ + return domain->flags & IRQ_DOMAIN_FLAG_MSI_DEVICE; +} + #else /* CONFIG_IRQ_DOMAIN_HIERARCHY */ static inline int irq_domain_alloc_irqs(struct irq_domain *domain, unsigned int nr_irqs, int node, void *arg) @@ -623,6 +621,17 @@ irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain) { return false; } + +static inline bool irq_domain_is_msi_parent(struct irq_domain *domain) +{ + return false; +} + +static inline bool irq_domain_is_msi_device(struct irq_domain *domain) +{ + return false; +} + #endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ #else /* CONFIG_IRQ_DOMAIN */ diff --git a/include/linux/irqdomain_defs.h b/include/linux/irqdomain_defs.h new file mode 100644 index 000000000000..c29921fd8cd1 --- /dev/null +++ b/include/linux/irqdomain_defs.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_IRQDOMAIN_DEFS_H +#define _LINUX_IRQDOMAIN_DEFS_H + +/* + * Should several domains have the same device node, but serve + * different purposes (for example one domain is for PCI/MSI, and the + * other for wired IRQs), they can be distinguished using a + * bus-specific token. Most domains are expected to only carry + * DOMAIN_BUS_ANY. + */ +enum irq_domain_bus_token { + DOMAIN_BUS_ANY = 0, + DOMAIN_BUS_WIRED, + DOMAIN_BUS_GENERIC_MSI, + DOMAIN_BUS_PCI_MSI, + DOMAIN_BUS_PLATFORM_MSI, + DOMAIN_BUS_NEXUS, + DOMAIN_BUS_IPI, + DOMAIN_BUS_FSL_MC_MSI, + DOMAIN_BUS_TI_SCI_INTA_MSI, + DOMAIN_BUS_WAKEUP, + DOMAIN_BUS_VMD_MSI, + DOMAIN_BUS_PCI_DEVICE_MSI, + DOMAIN_BUS_PCI_DEVICE_MSIX, + DOMAIN_BUS_DMAR, + DOMAIN_BUS_AMDVI, + DOMAIN_BUS_PCI_DEVICE_IMS, +}; + +#endif /* _LINUX_IRQDOMAIN_DEFS_H */ diff --git a/include/linux/irqreturn.h b/include/linux/irqreturn.h index bd4c066ad39b..d426c7ad92bf 100644 --- a/include/linux/irqreturn.h +++ b/include/linux/irqreturn.h @@ -3,10 +3,10 @@ #define _LINUX_IRQRETURN_H /** - * enum irqreturn - * @IRQ_NONE interrupt was not from this device or was not handled - * @IRQ_HANDLED interrupt was handled by this device - * @IRQ_WAKE_THREAD handler requests to wake the handler thread + * enum irqreturn - irqreturn type values + * @IRQ_NONE: interrupt was not from this device or was not handled + * @IRQ_HANDLED: interrupt was handled by this device + * @IRQ_WAKE_THREAD: handler requests to wake the handler thread */ enum irqreturn { IRQ_NONE = (0 << 0), diff --git a/include/linux/msi.h b/include/linux/msi.h index fc918a658d48..a112b913fff9 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -13,13 +13,20 @@ * * Regular device drivers have no business with any of these functions and * especially storing MSI descriptor pointers in random code is considered - * abuse. The only function which is relevant for drivers is msi_get_virq(). + * abuse. + * + * Device driver relevant functions are available in <linux/msi_api.h> */ +#include <linux/irqdomain_defs.h> #include <linux/cpumask.h> +#include <linux/msi_api.h> #include <linux/xarray.h> #include <linux/mutex.h> #include <linux/list.h> +#include <linux/irq.h> +#include <linux/bits.h> + #include <asm/msi.h> /* Dummy shadow structures if an architecture does not define them */ @@ -68,19 +75,18 @@ struct msi_msg { extern int pci_msi_ignore_mask; /* Helper functions */ -struct irq_data; struct msi_desc; struct pci_dev; struct platform_msi_priv_data; struct device_attribute; +struct irq_domain; +struct irq_affinity_desc; void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg); #ifdef CONFIG_GENERIC_MSI_IRQ void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg); #else -static inline void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg) -{ -} +static inline void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg) { } #endif typedef void (*irq_write_msi_msg_t)(struct msi_desc *desc, @@ -120,6 +126,38 @@ struct pci_msi_desc { }; }; +/** + * union msi_domain_cookie - Opaque MSI domain specific data + * @value: u64 value store + * @ptr: Pointer to domain specific data + * @iobase: Domain specific IOmem pointer + * + * The content of this data is implementation defined and used by the MSI + * domain to store domain specific information which is requried for + * interrupt chip callbacks. + */ +union msi_domain_cookie { + u64 value; + void *ptr; + void __iomem *iobase; +}; + +/** + * struct msi_desc_data - Generic MSI descriptor data + * @dcookie: Cookie for MSI domain specific data which is required + * for irq_chip callbacks + * @icookie: Cookie for the MSI interrupt instance provided by + * the usage site to the allocation function + * + * The content of this data is implementation defined, e.g. PCI/IMS + * implementations define the meaning of the data. The MSI core ignores + * this data completely. + */ +struct msi_desc_data { + union msi_domain_cookie dcookie; + union msi_instance_cookie icookie; +}; + #define MSI_MAX_INDEX ((unsigned int)USHRT_MAX) /** @@ -137,6 +175,7 @@ struct pci_msi_desc { * * @msi_index: Index of the msi descriptor * @pci: PCI specific msi descriptor data + * @data: Generic MSI descriptor data */ struct msi_desc { /* Shared device/bus type independent data */ @@ -156,7 +195,10 @@ struct msi_desc { void *write_msi_msg_data; u16 msi_index; - struct pci_msi_desc pci; + union { + struct pci_msi_desc pci; + struct msi_desc_data data; + }; }; /* @@ -171,33 +213,80 @@ enum msi_desc_filter { MSI_DESC_ASSOCIATED, }; + +/** + * struct msi_dev_domain - The internals of MSI domain info per device + * @store: Xarray for storing MSI descriptor pointers + * @irqdomain: Pointer to a per device interrupt domain + */ +struct msi_dev_domain { + struct xarray store; + struct irq_domain *domain; +}; + /** * msi_device_data - MSI per device data * @properties: MSI properties which are interesting to drivers * @platform_data: Platform-MSI specific data * @mutex: Mutex protecting the MSI descriptor store - * @__store: Xarray for storing MSI descriptor pointers + * @__domains: Internal data for per device MSI domains * @__iter_idx: Index to search the next entry for iterators */ struct msi_device_data { unsigned long properties; struct platform_msi_priv_data *platform_data; struct mutex mutex; - struct xarray __store; + struct msi_dev_domain __domains[MSI_MAX_DEVICE_IRQDOMAINS]; unsigned long __iter_idx; }; int msi_setup_device_data(struct device *dev); -unsigned int msi_get_virq(struct device *dev, unsigned int index); void msi_lock_descs(struct device *dev); void msi_unlock_descs(struct device *dev); -struct msi_desc *msi_first_desc(struct device *dev, enum msi_desc_filter filter); -struct msi_desc *msi_next_desc(struct device *dev, enum msi_desc_filter filter); +struct msi_desc *msi_domain_first_desc(struct device *dev, unsigned int domid, + enum msi_desc_filter filter); /** - * msi_for_each_desc - Iterate the MSI descriptors + * msi_first_desc - Get the first MSI descriptor of the default irqdomain + * @dev: Device to operate on + * @filter: Descriptor state filter + * + * Must be called with the MSI descriptor mutex held, i.e. msi_lock_descs() + * must be invoked before the call. + * + * Return: Pointer to the first MSI descriptor matching the search + * criteria, NULL if none found. + */ +static inline struct msi_desc *msi_first_desc(struct device *dev, + enum msi_desc_filter filter) +{ + return msi_domain_first_desc(dev, MSI_DEFAULT_DOMAIN, filter); +} + +struct msi_desc *msi_next_desc(struct device *dev, unsigned int domid, + enum msi_desc_filter filter); + +/** + * msi_domain_for_each_desc - Iterate the MSI descriptors in a specific domain + * + * @desc: struct msi_desc pointer used as iterator + * @dev: struct device pointer - device to iterate + * @domid: The id of the interrupt domain which should be walked. + * @filter: Filter for descriptor selection + * + * Notes: + * - The loop must be protected with a msi_lock_descs()/msi_unlock_descs() + * pair. + * - It is safe to remove a retrieved MSI descriptor in the loop. + */ +#define msi_domain_for_each_desc(desc, dev, domid, filter) \ + for ((desc) = msi_domain_first_desc((dev), (domid), (filter)); (desc); \ + (desc) = msi_next_desc((dev), (domid), (filter))) + +/** + * msi_for_each_desc - Iterate the MSI descriptors in the default irqdomain * * @desc: struct msi_desc pointer used as iterator * @dev: struct device pointer - device to iterate @@ -208,9 +297,8 @@ struct msi_desc *msi_next_desc(struct device *dev, enum msi_desc_filter filter); * pair. * - It is safe to remove a retrieved MSI descriptor in the loop. */ -#define msi_for_each_desc(desc, dev, filter) \ - for ((desc) = msi_first_desc((dev), (filter)); (desc); \ - (desc) = msi_next_desc((dev), (filter))) +#define msi_for_each_desc(desc, dev, filter) \ + msi_domain_for_each_desc((desc), (dev), MSI_DEFAULT_DOMAIN, (filter)) #define msi_desc_to_dev(desc) ((desc)->dev) @@ -237,34 +325,47 @@ static inline void msi_desc_set_iommu_cookie(struct msi_desc *desc, } #endif -#ifdef CONFIG_PCI_MSI -struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc); -void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg); -#else /* CONFIG_PCI_MSI */ -static inline void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg) +int msi_domain_insert_msi_desc(struct device *dev, unsigned int domid, + struct msi_desc *init_desc); +/** + * msi_insert_msi_desc - Allocate and initialize a MSI descriptor in the + * default irqdomain and insert it at @init_desc->msi_index + * @dev: Pointer to the device for which the descriptor is allocated + * @init_desc: Pointer to an MSI descriptor to initialize the new descriptor + * + * Return: 0 on success or an appropriate failure code. + */ +static inline int msi_insert_msi_desc(struct device *dev, struct msi_desc *init_desc) { + return msi_domain_insert_msi_desc(dev, MSI_DEFAULT_DOMAIN, init_desc); } -#endif /* CONFIG_PCI_MSI */ -int msi_add_msi_desc(struct device *dev, struct msi_desc *init_desc); -void msi_free_msi_descs_range(struct device *dev, enum msi_desc_filter filter, - unsigned int first_index, unsigned int last_index); +void msi_domain_free_msi_descs_range(struct device *dev, unsigned int domid, + unsigned int first, unsigned int last); + +/** + * msi_free_msi_descs_range - Free a range of MSI descriptors of a device + * in the default irqdomain + * + * @dev: Device for which to free the descriptors + * @first: Index to start freeing from (inclusive) + * @last: Last index to be freed (inclusive) + */ +static inline void msi_free_msi_descs_range(struct device *dev, unsigned int first, + unsigned int last) +{ + msi_domain_free_msi_descs_range(dev, MSI_DEFAULT_DOMAIN, first, last); +} /** - * msi_free_msi_descs - Free MSI descriptors of a device + * msi_free_msi_descs - Free all MSI descriptors of a device in the default irqdomain * @dev: Device to free the descriptors */ static inline void msi_free_msi_descs(struct device *dev) { - msi_free_msi_descs_range(dev, MSI_DESC_ALL, 0, MSI_MAX_INDEX); + msi_free_msi_descs_range(dev, 0, MSI_MAX_INDEX); } -void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg); -void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); - -void pci_msi_mask_irq(struct irq_data *data); -void pci_msi_unmask_irq(struct irq_data *data); - /* * The arch hooks to setup up msi irqs. Default functions are implemented * as weak symbols so that they /can/ be overriden by architecture specific @@ -293,7 +394,7 @@ static inline void msi_device_destroy_sysfs(struct device *dev) { } */ bool arch_restore_msi_irqs(struct pci_dev *dev); -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +#ifdef CONFIG_GENERIC_MSI_IRQ #include <linux/irqhandler.h> @@ -309,19 +410,22 @@ struct msi_domain_info; * @get_hwirq: Retrieve the resulting hw irq number * @msi_init: Domain specific init function for MSI interrupts * @msi_free: Domain specific function to free a MSI interrupts - * @msi_check: Callback for verification of the domain/info/dev data * @msi_prepare: Prepare the allocation of the interrupts in the domain + * @prepare_desc: Optional function to prepare the allocated MSI descriptor + * in the domain * @set_desc: Set the msi descriptor for an interrupt * @domain_alloc_irqs: Optional function to override the default allocation * function. * @domain_free_irqs: Optional function to override the default free * function. + * @msi_post_free: Optional function which is invoked after freeing + * all interrupts. * * @get_hwirq, @msi_init and @msi_free are callbacks used by the underlying * irqdomain. * - * @msi_check, @msi_prepare and @set_desc are callbacks used by - * msi_domain_alloc/free_irqs(). + * @msi_check, @msi_prepare, @prepare_desc and @set_desc are callbacks used by the + * msi_domain_alloc/free_irqs*() variants. * * @domain_alloc_irqs, @domain_free_irqs can be used to override the * default allocation/free functions (__msi_domain_alloc/free_irqs). This @@ -329,15 +433,6 @@ struct msi_domain_info; * be wrapped into the regular irq domains concepts by mere mortals. This * allows to universally use msi_domain_alloc/free_irqs without having to * special case XEN all over the place. - * - * Contrary to other operations @domain_alloc_irqs and @domain_free_irqs - * are set to the default implementation if NULL and even when - * MSI_FLAG_USE_DEF_DOM_OPS is not set to avoid breaking existing users and - * because these callbacks are obviously mandatory. - * - * This is NOT meant to be abused, but it can be useful to build wrappers - * for specialized MSI irq domains which need extra work before and after - * calling __msi_domain_alloc_irqs()/__msi_domain_free_irqs(). */ struct msi_domain_ops { irq_hw_number_t (*get_hwirq)(struct msi_domain_info *info, @@ -349,23 +444,29 @@ struct msi_domain_ops { void (*msi_free)(struct irq_domain *domain, struct msi_domain_info *info, unsigned int virq); - int (*msi_check)(struct irq_domain *domain, - struct msi_domain_info *info, - struct device *dev); int (*msi_prepare)(struct irq_domain *domain, struct device *dev, int nvec, msi_alloc_info_t *arg); + void (*prepare_desc)(struct irq_domain *domain, msi_alloc_info_t *arg, + struct msi_desc *desc); void (*set_desc)(msi_alloc_info_t *arg, struct msi_desc *desc); int (*domain_alloc_irqs)(struct irq_domain *domain, struct device *dev, int nvec); void (*domain_free_irqs)(struct irq_domain *domain, struct device *dev); + void (*msi_post_free)(struct irq_domain *domain, + struct device *dev); }; /** * struct msi_domain_info - MSI interrupt domain data * @flags: Flags to decribe features and capabilities + * @bus_token: The domain bus token + * @hwsize: The hardware table size or the software index limit. + * If 0 then the size is considered unlimited and + * gets initialized to the maximum software index limit + * by the domain creation code. * @ops: The callback data structure * @chip: Optional: associated interrupt chip * @chip_data: Optional: associated interrupt chip data @@ -375,17 +476,42 @@ struct msi_domain_ops { * @data: Optional: domain specific data */ struct msi_domain_info { - u32 flags; - struct msi_domain_ops *ops; - struct irq_chip *chip; - void *chip_data; - irq_flow_handler_t handler; - void *handler_data; - const char *handler_name; - void *data; + u32 flags; + enum irq_domain_bus_token bus_token; + unsigned int hwsize; + struct msi_domain_ops *ops; + struct irq_chip *chip; + void *chip_data; + irq_flow_handler_t handler; + void *handler_data; + const char *handler_name; + void *data; }; -/* Flags for msi_domain_info */ +/** + * struct msi_domain_template - Template for MSI device domains + * @name: Storage for the resulting name. Filled in by the core. + * @chip: Interrupt chip for this domain + * @ops: MSI domain ops + * @info: MSI domain info data + */ +struct msi_domain_template { + char name[48]; + struct irq_chip chip; + struct msi_domain_ops ops; + struct msi_domain_info info; +}; + +/* + * Flags for msi_domain_info + * + * Bit 0-15: Generic MSI functionality which is not subject to restriction + * by parent domains + * + * Bit 16-31: Functionality which depends on the underlying parent domain and + * can be masked out by msi_parent_ops::init_dev_msi_info() when + * a device MSI domain is initialized. + */ enum { /* * Init non implemented ops callbacks with default MSI domain @@ -397,44 +523,100 @@ enum { * callbacks. */ MSI_FLAG_USE_DEF_CHIP_OPS = (1 << 1), - /* Support multiple PCI MSI interrupts */ - MSI_FLAG_MULTI_PCI_MSI = (1 << 2), - /* Support PCI MSIX interrupts */ - MSI_FLAG_PCI_MSIX = (1 << 3), /* Needs early activate, required for PCI */ - MSI_FLAG_ACTIVATE_EARLY = (1 << 4), + MSI_FLAG_ACTIVATE_EARLY = (1 << 2), /* * Must reactivate when irq is started even when * MSI_FLAG_ACTIVATE_EARLY has been set. */ - MSI_FLAG_MUST_REACTIVATE = (1 << 5), - /* Is level-triggered capable, using two messages */ - MSI_FLAG_LEVEL_CAPABLE = (1 << 6), + MSI_FLAG_MUST_REACTIVATE = (1 << 3), /* Populate sysfs on alloc() and destroy it on free() */ - MSI_FLAG_DEV_SYSFS = (1 << 7), - /* MSI-X entries must be contiguous */ - MSI_FLAG_MSIX_CONTIGUOUS = (1 << 8), + MSI_FLAG_DEV_SYSFS = (1 << 4), /* Allocate simple MSI descriptors */ - MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS = (1 << 9), + MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS = (1 << 5), /* Free MSI descriptors */ - MSI_FLAG_FREE_MSI_DESCS = (1 << 10), + MSI_FLAG_FREE_MSI_DESCS = (1 << 6), + /* + * Quirk to handle MSI implementations which do not provide + * masking. Currently known to affect x86, but has to be partially + * handled in the core MSI code. + */ + MSI_FLAG_NOMASK_QUIRK = (1 << 7), + + /* Mask for the generic functionality */ + MSI_GENERIC_FLAGS_MASK = GENMASK(15, 0), + + /* Mask for the domain specific functionality */ + MSI_DOMAIN_FLAGS_MASK = GENMASK(31, 16), + + /* Support multiple PCI MSI interrupts */ + MSI_FLAG_MULTI_PCI_MSI = (1 << 16), + /* Support PCI MSIX interrupts */ + MSI_FLAG_PCI_MSIX = (1 << 17), + /* Is level-triggered capable, using two messages */ + MSI_FLAG_LEVEL_CAPABLE = (1 << 18), + /* MSI-X entries must be contiguous */ + MSI_FLAG_MSIX_CONTIGUOUS = (1 << 19), + /* PCI/MSI-X vectors can be dynamically allocated/freed post MSI-X enable */ + MSI_FLAG_PCI_MSIX_ALLOC_DYN = (1 << 20), + /* Support for PCI/IMS */ + MSI_FLAG_PCI_IMS = (1 << 21), }; +/** + * struct msi_parent_ops - MSI parent domain callbacks and configuration info + * + * @supported_flags: Required: The supported MSI flags of the parent domain + * @prefix: Optional: Prefix for the domain and chip name + * @init_dev_msi_info: Required: Callback for MSI parent domains to setup parent + * domain specific domain flags, domain ops and interrupt chip + * callbacks when a per device domain is created. + */ +struct msi_parent_ops { + u32 supported_flags; + const char *prefix; + bool (*init_dev_msi_info)(struct device *dev, struct irq_domain *domain, + struct irq_domain *msi_parent_domain, + struct msi_domain_info *msi_child_info); +}; + +bool msi_parent_init_dev_msi_info(struct device *dev, struct irq_domain *domain, + struct irq_domain *msi_parent_domain, + struct msi_domain_info *msi_child_info); + int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force); struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent); -int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, - int nvec); -int msi_domain_alloc_irqs_descs_locked(struct irq_domain *domain, struct device *dev, - int nvec); -int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, - int nvec); -void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev); -void msi_domain_free_irqs_descs_locked(struct irq_domain *domain, struct device *dev); -void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev); + +bool msi_create_device_irq_domain(struct device *dev, unsigned int domid, + const struct msi_domain_template *template, + unsigned int hwsize, void *domain_data, + void *chip_data); +void msi_remove_device_irq_domain(struct device *dev, unsigned int domid); + +bool msi_match_device_irq_domain(struct device *dev, unsigned int domid, + enum irq_domain_bus_token bus_token); + +int msi_domain_alloc_irqs_range_locked(struct device *dev, unsigned int domid, + unsigned int first, unsigned int last); +int msi_domain_alloc_irqs_range(struct device *dev, unsigned int domid, + unsigned int first, unsigned int last); +int msi_domain_alloc_irqs_all_locked(struct device *dev, unsigned int domid, int nirqs); + +struct msi_map msi_domain_alloc_irq_at(struct device *dev, unsigned int domid, unsigned int index, + const struct irq_affinity_desc *affdesc, + union msi_instance_cookie *cookie); + +void msi_domain_free_irqs_range_locked(struct device *dev, unsigned int domid, + unsigned int first, unsigned int last); +void msi_domain_free_irqs_range(struct device *dev, unsigned int domid, + unsigned int first, unsigned int last); +void msi_domain_free_irqs_all_locked(struct device *dev, unsigned int domid); +void msi_domain_free_irqs_all(struct device *dev, unsigned int domid); + struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain); struct irq_domain *platform_msi_create_irq_domain(struct fwnode_handle *fwnode, @@ -467,20 +649,27 @@ int platform_msi_device_domain_alloc(struct irq_domain *domain, unsigned int vir void platform_msi_device_domain_free(struct irq_domain *domain, unsigned int virq, unsigned int nvec); void *platform_msi_get_host_data(struct irq_domain *domain); -#endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */ +#endif /* CONFIG_GENERIC_MSI_IRQ */ -#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN +/* PCI specific interfaces */ +#ifdef CONFIG_PCI_MSI +struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc); +void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg); +void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg); +void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); +void pci_msi_mask_irq(struct irq_data *data); +void pci_msi_unmask_irq(struct irq_data *data); struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent); u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev); struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev); -bool pci_dev_has_special_msi_domain(struct pci_dev *pdev); -#else +#else /* CONFIG_PCI_MSI */ static inline struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev) { return NULL; } -#endif /* CONFIG_PCI_MSI_IRQ_DOMAIN */ +static inline void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg) { } +#endif /* !CONFIG_PCI_MSI */ #endif /* LINUX_MSI_H */ diff --git a/include/linux/msi_api.h b/include/linux/msi_api.h new file mode 100644 index 000000000000..391087ad99b1 --- /dev/null +++ b/include/linux/msi_api.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef LINUX_MSI_API_H +#define LINUX_MSI_API_H + +/* + * APIs which are relevant for device driver code for allocating and + * freeing MSI interrupts and querying the associations between + * hardware/software MSI indices and the Linux interrupt number. + */ + +struct device; + +/* + * Per device interrupt domain related constants. + */ +enum msi_domain_ids { + MSI_DEFAULT_DOMAIN, + MSI_SECONDARY_DOMAIN, + MSI_MAX_DEVICE_IRQDOMAINS, +}; + +/** + * union msi_instance_cookie - MSI instance cookie + * @value: u64 value store + * @ptr: Pointer to usage site specific data + * + * This cookie is handed to the IMS allocation function and stored in the + * MSI descriptor for the interrupt chip callbacks. + * + * The content of this cookie is MSI domain implementation defined. For + * PCI/IMS implementations this could be a PASID or a pointer to queue + * memory. + */ +union msi_instance_cookie { + u64 value; + void *ptr; +}; + +/** + * msi_map - Mapping between MSI index and Linux interrupt number + * @index: The MSI index, e.g. slot in the MSI-X table or + * a software managed index if >= 0. If negative + * the allocation function failed and it contains + * the error code. + * @virq: The associated Linux interrupt number + */ +struct msi_map { + int index; + int virq; +}; + +/* + * Constant to be used for dynamic allocations when the allocation is any + * free MSI index, which is either an entry in a hardware table or a + * software managed index. + */ +#define MSI_ANY_INDEX UINT_MAX + +unsigned int msi_domain_get_virq(struct device *dev, unsigned int domid, unsigned int index); + +/** + * msi_get_virq - Lookup the Linux interrupt number for a MSI index on the default interrupt domain + * @dev: Device for which the lookup happens + * @index: The MSI index to lookup + * + * Return: The Linux interrupt number on success (> 0), 0 if not found + */ +static inline unsigned int msi_get_virq(struct device *dev, unsigned int index) +{ + return msi_domain_get_virq(dev, MSI_DEFAULT_DOMAIN, index); +} + +#endif diff --git a/include/linux/pci.h b/include/linux/pci.h index 2bda4a4e47e8..aa514b54c681 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -38,6 +38,7 @@ #include <linux/interrupt.h> #include <linux/io.h> #include <linux/resource_ext.h> +#include <linux/msi_api.h> #include <uapi/linux/pci.h> #include <linux/pci_ids.h> @@ -1553,10 +1554,17 @@ static inline int pci_enable_msix_exact(struct pci_dev *dev, return rc; return 0; } +int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, + unsigned int max_vecs, unsigned int flags); int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, unsigned int max_vecs, unsigned int flags, struct irq_affinity *affd); +bool pci_msix_can_alloc_dyn(struct pci_dev *dev); +struct msi_map pci_msix_alloc_irq_at(struct pci_dev *dev, unsigned int index, + const struct irq_affinity_desc *affdesc); +void pci_msix_free_irq(struct pci_dev *pdev, struct msi_map map); + void pci_free_irq_vectors(struct pci_dev *dev); int pci_irq_vector(struct pci_dev *dev, unsigned int nr); const struct cpumask *pci_irq_get_affinity(struct pci_dev *pdev, int vec); @@ -1586,6 +1594,13 @@ pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, return 1; return -ENOSPC; } +static inline int +pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, + unsigned int max_vecs, unsigned int flags) +{ + return pci_alloc_irq_vectors_affinity(dev, min_vecs, max_vecs, + flags, NULL); +} static inline void pci_free_irq_vectors(struct pci_dev *dev) { @@ -1898,15 +1913,13 @@ pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, { return -ENOSPC; } -#endif /* CONFIG_PCI */ - static inline int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, unsigned int max_vecs, unsigned int flags) { - return pci_alloc_irq_vectors_affinity(dev, min_vecs, max_vecs, flags, - NULL); + return -ENOSPC; } +#endif /* CONFIG_PCI */ /* Include architecture-dependent settings and functions */ @@ -2474,6 +2487,14 @@ static inline bool pci_is_thunderbolt_attached(struct pci_dev *pdev) void pci_uevent_ers(struct pci_dev *pdev, enum pci_ers_result err_type); #endif +struct msi_domain_template; + +bool pci_create_ims_domain(struct pci_dev *pdev, const struct msi_domain_template *template, + unsigned int hwsize, void *data); +struct msi_map pci_ims_alloc_irq(struct pci_dev *pdev, union msi_instance_cookie *icookie, + const struct irq_affinity_desc *affdesc); +void pci_ims_free_irq(struct pci_dev *pdev, struct msi_map map); + #include <linux/dma-mapping.h> #define pci_printk(level, pdev, fmt, arg...) \ diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 86b95ccb81bb..b07b277d6a16 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -33,11 +33,13 @@ * can use the extra bits to store other information besides PFN. */ #ifdef MAX_PHYSMEM_BITS -#define SWP_PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) +#define SWP_PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) #else /* MAX_PHYSMEM_BITS */ -#define SWP_PFN_BITS (BITS_PER_LONG - PAGE_SHIFT) +#define SWP_PFN_BITS min_t(int, \ + sizeof(phys_addr_t) * 8 - PAGE_SHIFT, \ + SWP_TYPE_SHIFT) #endif /* MAX_PHYSMEM_BITS */ -#define SWP_PFN_MASK (BIT(SWP_PFN_BITS) - 1) +#define SWP_PFN_MASK (BIT(SWP_PFN_BITS) - 1) /** * Migration swap entry specific bitfield definitions. Layout: diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index e004ba04a9ae..684f1cd28730 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -228,6 +228,17 @@ enum { */ HCI_QUIRK_VALID_LE_STATES, + /* When this quirk is set, then erroneous data reporting + * is ignored. This is mainly due to the fact that the HCI + * Read Default Erroneous Data Reporting command is advertised, + * but not supported; these controllers often reply with unknown + * command and tend to lock up randomly. Needing a hard reset. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + */ + HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, + /* * When this quirk is set, then the hci_suspend_notifier is not * registered. This is intended for devices which drop completely @@ -1424,7 +1435,6 @@ struct hci_std_codecs_v2 { } __packed; struct hci_vnd_codec_v2 { - __u8 id; __le16 cid; __le16 vid; __u8 transport; diff --git a/include/net/ping.h b/include/net/ping.h index e4ff3911cbf5..9233ad3de0ad 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -16,9 +16,6 @@ #define PING_HTABLE_SIZE 64 #define PING_HTABLE_MASK (PING_HTABLE_SIZE-1) -#define ping_portaddr_for_each_entry(__sk, node, list) \ - hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node) - /* * gid_t is either uint or ushort. We want to pass it to * proc_dointvec_minmax(), so it must not be larger than MAX_INT diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index c078c48a8e6d..a6190aa1b406 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -66,6 +66,7 @@ enum fscache_cookie_trace { fscache_cookie_put_work, fscache_cookie_see_active, fscache_cookie_see_lru_discard, + fscache_cookie_see_lru_discard_clear, fscache_cookie_see_lru_do_one, fscache_cookie_see_relinquish, fscache_cookie_see_withdraw, @@ -149,6 +150,7 @@ enum fscache_access_trace { EM(fscache_cookie_put_work, "PQ work ") \ EM(fscache_cookie_see_active, "- activ") \ EM(fscache_cookie_see_lru_discard, "- x-lru") \ + EM(fscache_cookie_see_lru_discard_clear,"- lrudc") \ EM(fscache_cookie_see_lru_do_one, "- lrudo") \ EM(fscache_cookie_see_relinquish, "- x-rlq") \ EM(fscache_cookie_see_withdraw, "- x-wth") \ diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 8840cf3e20f2..61cd7ffd0f6a 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2707,8 +2707,10 @@ static __cold void io_tctx_exit_cb(struct callback_head *cb) /* * When @in_idle, we're in cancellation and it's racy to remove the * node. It'll be removed by the end of cancellation, just ignore it. + * tctx can be NULL if the queueing of this task_work raced with + * work cancelation off the exec path. */ - if (!atomic_read(&tctx->in_idle)) + if (tctx && !atomic_read(&tctx->in_idle)) io_uring_del_tctx_node((unsigned long)work->ctx); complete(&work->completion); } diff --git a/ipc/sem.c b/ipc/sem.c index c8496f98b139..00f88aa01ac5 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -2179,14 +2179,15 @@ long __do_semtimedop(int semid, struct sembuf *sops, * scenarios where we were awakened externally, during the * window between wake_q_add() and wake_up_q(). */ + rcu_read_lock(); error = READ_ONCE(queue.status); if (error != -EINTR) { /* see SEM_BARRIER_2 for purpose/pairing */ smp_acquire__after_ctrl_dep(); + rcu_read_unlock(); goto out; } - rcu_read_lock(); locknum = sem_lock(sma, sops, nsops); if (!ipc_valid_object(&sma->sem_perm)) diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index fd4020835ec6..367b0a42ada9 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -167,7 +167,6 @@ struct cgroup_mgctx { extern spinlock_t css_set_lock; extern struct cgroup_subsys *cgroup_subsys[]; extern struct list_head cgroup_roots; -extern struct file_system_type cgroup_fs_type; /* iterate across the hierarchies */ #define for_each_root(root) \ diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index db3d174c53d4..b64c44ae4c25 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -86,15 +86,10 @@ config GENERIC_IRQ_IPI depends on SMP select IRQ_DOMAIN_HIERARCHY -# Generic MSI interrupt support -config GENERIC_MSI_IRQ - bool - # Generic MSI hierarchical interrupt domain support -config GENERIC_MSI_IRQ_DOMAIN +config GENERIC_MSI_IRQ bool select IRQ_DOMAIN_HIERARCHY - select GENERIC_MSI_IRQ config IRQ_MSI_IOMMU bool diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 8ac37e8e738a..49e7bc871fec 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1561,10 +1561,10 @@ int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) return 0; } -static struct device *irq_get_parent_device(struct irq_data *data) +static struct device *irq_get_pm_device(struct irq_data *data) { if (data->domain) - return data->domain->dev; + return data->domain->pm_dev; return NULL; } @@ -1578,7 +1578,7 @@ static struct device *irq_get_parent_device(struct irq_data *data) */ int irq_chip_pm_get(struct irq_data *data) { - struct device *dev = irq_get_parent_device(data); + struct device *dev = irq_get_pm_device(data); int retval = 0; if (IS_ENABLED(CONFIG_PM) && dev) @@ -1597,7 +1597,7 @@ int irq_chip_pm_get(struct irq_data *data) */ int irq_chip_pm_put(struct irq_data *data) { - struct device *dev = irq_get_parent_device(data); + struct device *dev = irq_get_pm_device(data); int retval = 0; if (IS_ENABLED(CONFIG_PM) && dev) diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index f09c60393e55..5fdc0b557579 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -52,6 +52,7 @@ enum { * IRQS_PENDING - irq is pending and replayed later * IRQS_SUSPENDED - irq is suspended * IRQS_NMI - irq line is used to deliver NMIs + * IRQS_SYSFS - descriptor has been added to sysfs */ enum { IRQS_AUTODETECT = 0x00000001, @@ -64,6 +65,7 @@ enum { IRQS_SUSPENDED = 0x00000800, IRQS_TIMINGS = 0x00001000, IRQS_NMI = 0x00002000, + IRQS_SYSFS = 0x00004000, }; #include "debug.h" diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index a91f9001103c..fd0996274401 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -288,22 +288,25 @@ static void irq_sysfs_add(int irq, struct irq_desc *desc) if (irq_kobj_base) { /* * Continue even in case of failure as this is nothing - * crucial. + * crucial and failures in the late irq_sysfs_init() + * cannot be rolled back. */ if (kobject_add(&desc->kobj, irq_kobj_base, "%d", irq)) pr_warn("Failed to add kobject for irq %d\n", irq); + else + desc->istate |= IRQS_SYSFS; } } static void irq_sysfs_del(struct irq_desc *desc) { /* - * If irq_sysfs_init() has not yet been invoked (early boot), then - * irq_kobj_base is NULL and the descriptor was never added. - * kobject_del() complains about a object with no parent, so make - * it conditional. + * Only invoke kobject_del() when kobject_add() was successfully + * invoked for the descriptor. This covers both early boot, where + * sysfs is not initialized yet, and the case of a failed + * kobject_add() invocation. */ - if (irq_kobj_base) + if (desc->istate & IRQS_SYSFS) kobject_del(&desc->kobj); } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 40fe7806cc8c..5b7cf28df290 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -321,7 +321,7 @@ static int irq_try_set_affinity(struct irq_data *data, } static bool irq_set_affinity_deactivated(struct irq_data *data, - const struct cpumask *mask, bool force) + const struct cpumask *mask) { struct irq_desc *desc = irq_data_to_desc(data); @@ -354,7 +354,7 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask, if (!chip || !chip->irq_set_affinity) return -EINVAL; - if (irq_set_affinity_deactivated(data, mask, force)) + if (irq_set_affinity_deactivated(data, mask)) return 0; if (irq_can_move_pcntxt(data) && !irqd_is_setaffinity_pending(data)) { diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index a9ee535293eb..bd4d4dd626b4 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -19,8 +19,31 @@ #include "internals.h" +/** + * struct msi_ctrl - MSI internal management control structure + * @domid: ID of the domain on which management operations should be done + * @first: First (hardware) slot index to operate on + * @last: Last (hardware) slot index to operate on + * @nirqs: The number of Linux interrupts to allocate. Can be larger + * than the range due to PCI/multi-MSI. + */ +struct msi_ctrl { + unsigned int domid; + unsigned int first; + unsigned int last; + unsigned int nirqs; +}; + +/* Invalid Xarray index which is outside of any searchable range */ +#define MSI_XA_MAX_INDEX (ULONG_MAX - 1) +/* The maximum domain size */ +#define MSI_XA_DOMAIN_SIZE (MSI_MAX_INDEX + 1) + +static void msi_domain_free_locked(struct device *dev, struct msi_ctrl *ctrl); +static unsigned int msi_domain_get_hwsize(struct device *dev, unsigned int domid); static inline int msi_sysfs_create_group(struct device *dev); + /** * msi_alloc_desc - Allocate an initialized msi_desc * @dev: Pointer to the device for which this is allocated @@ -33,7 +56,7 @@ static inline int msi_sysfs_create_group(struct device *dev); * Return: pointer to allocated &msi_desc on success or %NULL on failure */ static struct msi_desc *msi_alloc_desc(struct device *dev, int nvec, - const struct irq_affinity_desc *affinity) + const struct irq_affinity_desc *affinity) { struct msi_desc *desc = kzalloc(sizeof(*desc), GFP_KERNEL); @@ -58,25 +81,56 @@ static void msi_free_desc(struct msi_desc *desc) kfree(desc); } -static int msi_insert_desc(struct msi_device_data *md, struct msi_desc *desc, unsigned int index) +static int msi_insert_desc(struct device *dev, struct msi_desc *desc, + unsigned int domid, unsigned int index) { + struct msi_device_data *md = dev->msi.data; + struct xarray *xa = &md->__domains[domid].store; + unsigned int hwsize; int ret; - desc->msi_index = index; - ret = xa_insert(&md->__store, index, desc, GFP_KERNEL); - if (ret) - msi_free_desc(desc); + hwsize = msi_domain_get_hwsize(dev, domid); + + if (index == MSI_ANY_INDEX) { + struct xa_limit limit = { .min = 0, .max = hwsize - 1 }; + unsigned int index; + + /* Let the xarray allocate a free index within the limit */ + ret = xa_alloc(xa, &index, desc, limit, GFP_KERNEL); + if (ret) + goto fail; + + desc->msi_index = index; + return 0; + } else { + if (index >= hwsize) { + ret = -ERANGE; + goto fail; + } + + desc->msi_index = index; + ret = xa_insert(xa, index, desc, GFP_KERNEL); + if (ret) + goto fail; + return 0; + } +fail: + msi_free_desc(desc); return ret; } /** - * msi_add_msi_desc - Allocate and initialize a MSI descriptor + * msi_domain_insert_msi_desc - Allocate and initialize a MSI descriptor and + * insert it at @init_desc->msi_index + * * @dev: Pointer to the device for which the descriptor is allocated + * @domid: The id of the interrupt domain to which the desriptor is added * @init_desc: Pointer to an MSI descriptor to initialize the new descriptor * * Return: 0 on success or an appropriate failure code. */ -int msi_add_msi_desc(struct device *dev, struct msi_desc *init_desc) +int msi_domain_insert_msi_desc(struct device *dev, unsigned int domid, + struct msi_desc *init_desc) { struct msi_desc *desc; @@ -88,40 +142,8 @@ int msi_add_msi_desc(struct device *dev, struct msi_desc *init_desc) /* Copy type specific data to the new descriptor. */ desc->pci = init_desc->pci; - return msi_insert_desc(dev->msi.data, desc, init_desc->msi_index); -} -/** - * msi_add_simple_msi_descs - Allocate and initialize MSI descriptors - * @dev: Pointer to the device for which the descriptors are allocated - * @index: Index for the first MSI descriptor - * @ndesc: Number of descriptors to allocate - * - * Return: 0 on success or an appropriate failure code. - */ -static int msi_add_simple_msi_descs(struct device *dev, unsigned int index, unsigned int ndesc) -{ - unsigned int idx, last = index + ndesc - 1; - struct msi_desc *desc; - int ret; - - lockdep_assert_held(&dev->msi.data->mutex); - - for (idx = index; idx <= last; idx++) { - desc = msi_alloc_desc(dev, 1, NULL); - if (!desc) - goto fail_mem; - ret = msi_insert_desc(dev->msi.data, desc, idx); - if (ret) - goto fail; - } - return 0; - -fail_mem: - ret = -ENOMEM; -fail: - msi_free_msi_descs_range(dev, MSI_DESC_NOTASSOCIATED, index, last); - return ret; + return msi_insert_desc(dev, desc, domid, init_desc->msi_index); } static bool msi_desc_match(struct msi_desc *desc, enum msi_desc_filter filter) @@ -138,28 +160,96 @@ static bool msi_desc_match(struct msi_desc *desc, enum msi_desc_filter filter) return false; } +static bool msi_ctrl_valid(struct device *dev, struct msi_ctrl *ctrl) +{ + unsigned int hwsize; + + if (WARN_ON_ONCE(ctrl->domid >= MSI_MAX_DEVICE_IRQDOMAINS || + !dev->msi.data->__domains[ctrl->domid].domain)) + return false; + + hwsize = msi_domain_get_hwsize(dev, ctrl->domid); + if (WARN_ON_ONCE(ctrl->first > ctrl->last || + ctrl->first >= hwsize || + ctrl->last >= hwsize)) + return false; + return true; +} + +static void msi_domain_free_descs(struct device *dev, struct msi_ctrl *ctrl) +{ + struct msi_desc *desc; + struct xarray *xa; + unsigned long idx; + + lockdep_assert_held(&dev->msi.data->mutex); + + if (!msi_ctrl_valid(dev, ctrl)) + return; + + xa = &dev->msi.data->__domains[ctrl->domid].store; + xa_for_each_range(xa, idx, desc, ctrl->first, ctrl->last) { + xa_erase(xa, idx); + + /* Leak the descriptor when it is still referenced */ + if (WARN_ON_ONCE(msi_desc_match(desc, MSI_DESC_ASSOCIATED))) + continue; + msi_free_desc(desc); + } +} + /** - * msi_free_msi_descs_range - Free MSI descriptors of a device - * @dev: Device to free the descriptors - * @filter: Descriptor state filter - * @first_index: Index to start freeing from - * @last_index: Last index to be freed + * msi_domain_free_msi_descs_range - Free a range of MSI descriptors of a device in an irqdomain + * @dev: Device for which to free the descriptors + * @domid: Id of the domain to operate on + * @first: Index to start freeing from (inclusive) + * @last: Last index to be freed (inclusive) */ -void msi_free_msi_descs_range(struct device *dev, enum msi_desc_filter filter, - unsigned int first_index, unsigned int last_index) +void msi_domain_free_msi_descs_range(struct device *dev, unsigned int domid, + unsigned int first, unsigned int last) +{ + struct msi_ctrl ctrl = { + .domid = domid, + .first = first, + .last = last, + }; + + msi_domain_free_descs(dev, &ctrl); +} + +/** + * msi_domain_add_simple_msi_descs - Allocate and initialize MSI descriptors + * @dev: Pointer to the device for which the descriptors are allocated + * @ctrl: Allocation control struct + * + * Return: 0 on success or an appropriate failure code. + */ +static int msi_domain_add_simple_msi_descs(struct device *dev, struct msi_ctrl *ctrl) { - struct xarray *xa = &dev->msi.data->__store; struct msi_desc *desc; - unsigned long idx; + unsigned int idx; + int ret; lockdep_assert_held(&dev->msi.data->mutex); - xa_for_each_range(xa, idx, desc, first_index, last_index) { - if (msi_desc_match(desc, filter)) { - xa_erase(xa, idx); - msi_free_desc(desc); - } + if (!msi_ctrl_valid(dev, ctrl)) + return -EINVAL; + + for (idx = ctrl->first; idx <= ctrl->last; idx++) { + desc = msi_alloc_desc(dev, 1, NULL); + if (!desc) + goto fail_mem; + ret = msi_insert_desc(dev, desc, ctrl->domid, idx); + if (ret) + goto fail; } + return 0; + +fail_mem: + ret = -ENOMEM; +fail: + msi_domain_free_descs(dev, ctrl); + return ret; } void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg) @@ -178,9 +268,13 @@ EXPORT_SYMBOL_GPL(get_cached_msi_msg); static void msi_device_data_release(struct device *dev, void *res) { struct msi_device_data *md = res; + int i; - WARN_ON_ONCE(!xa_empty(&md->__store)); - xa_destroy(&md->__store); + for (i = 0; i < MSI_MAX_DEVICE_IRQDOMAINS; i++) { + msi_remove_device_irq_domain(dev, i); + WARN_ON_ONCE(!xa_empty(&md->__domains[i].store)); + xa_destroy(&md->__domains[i].store); + } dev->msi.data = NULL; } @@ -197,7 +291,7 @@ static void msi_device_data_release(struct device *dev, void *res) int msi_setup_device_data(struct device *dev) { struct msi_device_data *md; - int ret; + int ret, i; if (dev->msi.data) return 0; @@ -212,7 +306,18 @@ int msi_setup_device_data(struct device *dev) return ret; } - xa_init(&md->__store); + for (i = 0; i < MSI_MAX_DEVICE_IRQDOMAINS; i++) + xa_init_flags(&md->__domains[i].store, XA_FLAGS_ALLOC); + + /* + * If @dev::msi::domain is set and is a global MSI domain, copy the + * pointer into the domain array so all code can operate on domain + * ids. The NULL pointer check is required to keep the legacy + * architecture specific PCI/MSI support working. + */ + if (dev->msi.domain && !irq_domain_is_msi_parent(dev->msi.domain)) + md->__domains[MSI_DEFAULT_DOMAIN].domain = dev->msi.domain; + mutex_init(&md->mutex); dev->msi.data = md; devres_add(dev, md); @@ -235,27 +340,30 @@ EXPORT_SYMBOL_GPL(msi_lock_descs); */ void msi_unlock_descs(struct device *dev) { - /* Invalidate the index wich was cached by the iterator */ - dev->msi.data->__iter_idx = MSI_MAX_INDEX; + /* Invalidate the index which was cached by the iterator */ + dev->msi.data->__iter_idx = MSI_XA_MAX_INDEX; mutex_unlock(&dev->msi.data->mutex); } EXPORT_SYMBOL_GPL(msi_unlock_descs); -static struct msi_desc *msi_find_desc(struct msi_device_data *md, enum msi_desc_filter filter) +static struct msi_desc *msi_find_desc(struct msi_device_data *md, unsigned int domid, + enum msi_desc_filter filter) { + struct xarray *xa = &md->__domains[domid].store; struct msi_desc *desc; - xa_for_each_start(&md->__store, md->__iter_idx, desc, md->__iter_idx) { + xa_for_each_start(xa, md->__iter_idx, desc, md->__iter_idx) { if (msi_desc_match(desc, filter)) return desc; } - md->__iter_idx = MSI_MAX_INDEX; + md->__iter_idx = MSI_XA_MAX_INDEX; return NULL; } /** - * msi_first_desc - Get the first MSI descriptor of a device + * msi_domain_first_desc - Get the first MSI descriptor of an irqdomain associated to a device * @dev: Device to operate on + * @domid: The id of the interrupt domain which should be walked. * @filter: Descriptor state filter * * Must be called with the MSI descriptor mutex held, i.e. msi_lock_descs() @@ -264,23 +372,26 @@ static struct msi_desc *msi_find_desc(struct msi_device_data *md, enum msi_desc_ * Return: Pointer to the first MSI descriptor matching the search * criteria, NULL if none found. */ -struct msi_desc *msi_first_desc(struct device *dev, enum msi_desc_filter filter) +struct msi_desc *msi_domain_first_desc(struct device *dev, unsigned int domid, + enum msi_desc_filter filter) { struct msi_device_data *md = dev->msi.data; - if (WARN_ON_ONCE(!md)) + if (WARN_ON_ONCE(!md || domid >= MSI_MAX_DEVICE_IRQDOMAINS)) return NULL; lockdep_assert_held(&md->mutex); md->__iter_idx = 0; - return msi_find_desc(md, filter); + return msi_find_desc(md, domid, filter); } -EXPORT_SYMBOL_GPL(msi_first_desc); +EXPORT_SYMBOL_GPL(msi_domain_first_desc); /** * msi_next_desc - Get the next MSI descriptor of a device * @dev: Device to operate on + * @domid: The id of the interrupt domain which should be walked. + * @filter: Descriptor state filter * * The first invocation of msi_next_desc() has to be preceeded by a * successful invocation of __msi_first_desc(). Consecutive invocations are @@ -290,11 +401,12 @@ EXPORT_SYMBOL_GPL(msi_first_desc); * Return: Pointer to the next MSI descriptor matching the search * criteria, NULL if none found. */ -struct msi_desc *msi_next_desc(struct device *dev, enum msi_desc_filter filter) +struct msi_desc *msi_next_desc(struct device *dev, unsigned int domid, + enum msi_desc_filter filter) { struct msi_device_data *md = dev->msi.data; - if (WARN_ON_ONCE(!md)) + if (WARN_ON_ONCE(!md || domid >= MSI_MAX_DEVICE_IRQDOMAINS)) return NULL; lockdep_assert_held(&md->mutex); @@ -303,30 +415,38 @@ struct msi_desc *msi_next_desc(struct device *dev, enum msi_desc_filter filter) return NULL; md->__iter_idx++; - return msi_find_desc(md, filter); + return msi_find_desc(md, domid, filter); } EXPORT_SYMBOL_GPL(msi_next_desc); /** - * msi_get_virq - Return Linux interrupt number of a MSI interrupt + * msi_domain_get_virq - Lookup the Linux interrupt number for a MSI index on a interrupt domain * @dev: Device to operate on + * @domid: Domain ID of the interrupt domain associated to the device * @index: MSI interrupt index to look for (0-based) * * Return: The Linux interrupt number on success (> 0), 0 if not found */ -unsigned int msi_get_virq(struct device *dev, unsigned int index) +unsigned int msi_domain_get_virq(struct device *dev, unsigned int domid, unsigned int index) { struct msi_desc *desc; unsigned int ret = 0; - bool pcimsi; + bool pcimsi = false; + struct xarray *xa; if (!dev->msi.data) return 0; - pcimsi = dev_is_pci(dev) ? to_pci_dev(dev)->msi_enabled : false; + if (WARN_ON_ONCE(index > MSI_MAX_INDEX || domid >= MSI_MAX_DEVICE_IRQDOMAINS)) + return 0; + + /* This check is only valid for the PCI default MSI domain */ + if (dev_is_pci(dev) && domid == MSI_DEFAULT_DOMAIN) + pcimsi = to_pci_dev(dev)->msi_enabled; msi_lock_descs(dev); - desc = xa_load(&dev->msi.data->__store, pcimsi ? 0 : index); + xa = &dev->msi.data->__domains[domid].store; + desc = xa_load(xa, pcimsi ? 0 : index); if (desc && desc->irq) { /* * PCI-MSI has only one descriptor for multiple interrupts. @@ -340,10 +460,11 @@ unsigned int msi_get_virq(struct device *dev, unsigned int index) ret = desc->irq; } } + msi_unlock_descs(dev); return ret; } -EXPORT_SYMBOL_GPL(msi_get_virq); +EXPORT_SYMBOL_GPL(msi_domain_get_virq); #ifdef CONFIG_SYSFS static struct attribute *msi_dev_attrs[] = { @@ -459,7 +580,39 @@ static inline int msi_sysfs_populate_desc(struct device *dev, struct msi_desc *d static inline void msi_sysfs_remove_desc(struct device *dev, struct msi_desc *desc) { } #endif /* !CONFIG_SYSFS */ -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +static struct irq_domain *msi_get_device_domain(struct device *dev, unsigned int domid) +{ + struct irq_domain *domain; + + lockdep_assert_held(&dev->msi.data->mutex); + + if (WARN_ON_ONCE(domid >= MSI_MAX_DEVICE_IRQDOMAINS)) + return NULL; + + domain = dev->msi.data->__domains[domid].domain; + if (!domain) + return NULL; + + if (WARN_ON_ONCE(irq_domain_is_msi_parent(domain))) + return NULL; + + return domain; +} + +static unsigned int msi_domain_get_hwsize(struct device *dev, unsigned int domid) +{ + struct msi_domain_info *info; + struct irq_domain *domain; + + domain = msi_get_device_domain(dev, domid); + if (domain) { + info = domain->host_data; + return info->hwsize; + } + /* No domain, no size... */ + return 0; +} + static inline void irq_chip_write_msi_msg(struct irq_data *data, struct msi_msg *msg) { @@ -613,21 +766,11 @@ static int msi_domain_ops_init(struct irq_domain *domain, return 0; } -static int msi_domain_ops_check(struct irq_domain *domain, - struct msi_domain_info *info, - struct device *dev) -{ - return 0; -} - static struct msi_domain_ops msi_domain_ops_default = { .get_hwirq = msi_domain_ops_get_hwirq, .msi_init = msi_domain_ops_init, - .msi_check = msi_domain_ops_check, .msi_prepare = msi_domain_ops_prepare, .set_desc = msi_domain_ops_set_desc, - .domain_alloc_irqs = __msi_domain_alloc_irqs, - .domain_free_irqs = __msi_domain_free_irqs, }; static void msi_domain_update_dom_ops(struct msi_domain_info *info) @@ -639,11 +782,6 @@ static void msi_domain_update_dom_ops(struct msi_domain_info *info) return; } - if (ops->domain_alloc_irqs == NULL) - ops->domain_alloc_irqs = msi_domain_ops_default.domain_alloc_irqs; - if (ops->domain_free_irqs == NULL) - ops->domain_free_irqs = msi_domain_ops_default.domain_free_irqs; - if (!(info->flags & MSI_FLAG_USE_DEF_DOM_OPS)) return; @@ -651,8 +789,6 @@ static void msi_domain_update_dom_ops(struct msi_domain_info *info) ops->get_hwirq = msi_domain_ops_default.get_hwirq; if (ops->msi_init == NULL) ops->msi_init = msi_domain_ops_default.msi_init; - if (ops->msi_check == NULL) - ops->msi_check = msi_domain_ops_default.msi_check; if (ops->msi_prepare == NULL) ops->msi_prepare = msi_domain_ops_default.msi_prepare; if (ops->set_desc == NULL) @@ -668,6 +804,40 @@ static void msi_domain_update_chip_ops(struct msi_domain_info *info) chip->irq_set_affinity = msi_domain_set_affinity; } +static struct irq_domain *__msi_create_irq_domain(struct fwnode_handle *fwnode, + struct msi_domain_info *info, + unsigned int flags, + struct irq_domain *parent) +{ + struct irq_domain *domain; + + if (info->hwsize > MSI_XA_DOMAIN_SIZE) + return NULL; + + /* + * Hardware size 0 is valid for backwards compatibility and for + * domains which are not backed by a hardware table. Grant the + * maximum index space. + */ + if (!info->hwsize) + info->hwsize = MSI_XA_DOMAIN_SIZE; + + msi_domain_update_dom_ops(info); + if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS) + msi_domain_update_chip_ops(info); + + domain = irq_domain_create_hierarchy(parent, flags | IRQ_DOMAIN_FLAG_MSI, 0, + fwnode, &msi_domain_ops, info); + + if (domain) { + if (!domain->name && info->chip) + domain->name = info->chip->name; + irq_domain_update_bus_token(domain, info->bus_token); + } + + return domain; +} + /** * msi_create_irq_domain - Create an MSI interrupt domain * @fwnode: Optional fwnode of the interrupt controller @@ -680,19 +850,210 @@ struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent) { + return __msi_create_irq_domain(fwnode, info, 0, parent); +} + +/** + * msi_parent_init_dev_msi_info - Delegate initialization of device MSI info down + * in the domain hierarchy + * @dev: The device for which the domain should be created + * @domain: The domain in the hierarchy this op is being called on + * @msi_parent_domain: The IRQ_DOMAIN_FLAG_MSI_PARENT domain for the child to + * be created + * @msi_child_info: The MSI domain info of the IRQ_DOMAIN_FLAG_MSI_DEVICE + * domain to be created + * + * Return: true on success, false otherwise + * + * This is the most complex problem of per device MSI domains and the + * underlying interrupt domain hierarchy: + * + * The device domain to be initialized requests the broadest feature set + * possible and the underlying domain hierarchy puts restrictions on it. + * + * That's trivial for a simple parent->child relationship, but it gets + * interesting with an intermediate domain: root->parent->child. The + * intermediate 'parent' can expand the capabilities which the 'root' + * domain is providing. So that creates a classic hen and egg problem: + * Which entity is doing the restrictions/expansions? + * + * One solution is to let the root domain handle the initialization that's + * why there is the @domain and the @msi_parent_domain pointer. + */ +bool msi_parent_init_dev_msi_info(struct device *dev, struct irq_domain *domain, + struct irq_domain *msi_parent_domain, + struct msi_domain_info *msi_child_info) +{ + struct irq_domain *parent = domain->parent; + + if (WARN_ON_ONCE(!parent || !parent->msi_parent_ops || + !parent->msi_parent_ops->init_dev_msi_info)) + return false; + + return parent->msi_parent_ops->init_dev_msi_info(dev, parent, msi_parent_domain, + msi_child_info); +} + +/** + * msi_create_device_irq_domain - Create a device MSI interrupt domain + * @dev: Pointer to the device + * @domid: Domain id + * @template: MSI domain info bundle used as template + * @hwsize: Maximum number of MSI table entries (0 if unknown or unlimited) + * @domain_data: Optional pointer to domain specific data which is set in + * msi_domain_info::data + * @chip_data: Optional pointer to chip specific data which is set in + * msi_domain_info::chip_data + * + * Return: True on success, false otherwise + * + * There is no firmware node required for this interface because the per + * device domains are software constructs which are actually closer to the + * hardware reality than any firmware can describe them. + * + * The domain name and the irq chip name for a MSI device domain are + * composed by: "$(PREFIX)$(CHIPNAME)-$(DEVNAME)" + * + * $PREFIX: Optional prefix provided by the underlying MSI parent domain + * via msi_parent_ops::prefix. If that pointer is NULL the prefix + * is empty. + * $CHIPNAME: The name of the irq_chip in @template + * $DEVNAME: The name of the device + * + * This results in understandable chip names and hardware interrupt numbers + * in e.g. /proc/interrupts + * + * PCI-MSI-0000:00:1c.0 0-edge Parent domain has no prefix + * IR-PCI-MSI-0000:00:1c.4 0-edge Same with interrupt remapping prefix 'IR-' + * + * IR-PCI-MSIX-0000:3d:00.0 0-edge Hardware interrupt numbers reflect + * IR-PCI-MSIX-0000:3d:00.0 1-edge the real MSI-X index on that device + * IR-PCI-MSIX-0000:3d:00.0 2-edge + * + * On IMS domains the hardware interrupt number is either a table entry + * index or a purely software managed index but it is guaranteed to be + * unique. + * + * The domain pointer is stored in @dev::msi::data::__irqdomains[]. All + * subsequent operations on the domain depend on the domain id. + * + * The domain is automatically freed when the device is removed via devres + * in the context of @dev::msi::data freeing, but it can also be + * independently removed via @msi_remove_device_irq_domain(). + */ +bool msi_create_device_irq_domain(struct device *dev, unsigned int domid, + const struct msi_domain_template *template, + unsigned int hwsize, void *domain_data, + void *chip_data) +{ + struct irq_domain *domain, *parent = dev->msi.domain; + const struct msi_parent_ops *pops; + struct msi_domain_template *bundle; + struct fwnode_handle *fwnode; + + if (!irq_domain_is_msi_parent(parent)) + return false; + + if (domid >= MSI_MAX_DEVICE_IRQDOMAINS) + return false; + + bundle = kmemdup(template, sizeof(*bundle), GFP_KERNEL); + if (!bundle) + return false; + + bundle->info.hwsize = hwsize; + bundle->info.chip = &bundle->chip; + bundle->info.ops = &bundle->ops; + bundle->info.data = domain_data; + bundle->info.chip_data = chip_data; + + pops = parent->msi_parent_ops; + snprintf(bundle->name, sizeof(bundle->name), "%s%s-%s", + pops->prefix ? : "", bundle->chip.name, dev_name(dev)); + bundle->chip.name = bundle->name; + + fwnode = irq_domain_alloc_named_fwnode(bundle->name); + if (!fwnode) + goto free_bundle; + + if (msi_setup_device_data(dev)) + goto free_fwnode; + + msi_lock_descs(dev); + + if (WARN_ON_ONCE(msi_get_device_domain(dev, domid))) + goto fail; + + if (!pops->init_dev_msi_info(dev, parent, parent, &bundle->info)) + goto fail; + + domain = __msi_create_irq_domain(fwnode, &bundle->info, IRQ_DOMAIN_FLAG_MSI_DEVICE, parent); + if (!domain) + goto fail; + + domain->dev = dev; + dev->msi.data->__domains[domid].domain = domain; + msi_unlock_descs(dev); + return true; + +fail: + msi_unlock_descs(dev); +free_fwnode: + kfree(fwnode); +free_bundle: + kfree(bundle); + return false; +} + +/** + * msi_remove_device_irq_domain - Free a device MSI interrupt domain + * @dev: Pointer to the device + * @domid: Domain id + */ +void msi_remove_device_irq_domain(struct device *dev, unsigned int domid) +{ + struct msi_domain_info *info; struct irq_domain *domain; - msi_domain_update_dom_ops(info); - if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS) - msi_domain_update_chip_ops(info); + msi_lock_descs(dev); - domain = irq_domain_create_hierarchy(parent, IRQ_DOMAIN_FLAG_MSI, 0, - fwnode, &msi_domain_ops, info); + domain = msi_get_device_domain(dev, domid); - if (domain && !domain->name && info->chip) - domain->name = info->chip->name; + if (!domain || !irq_domain_is_msi_device(domain)) + goto unlock; - return domain; + dev->msi.data->__domains[domid].domain = NULL; + info = domain->host_data; + irq_domain_remove(domain); + kfree(container_of(info, struct msi_domain_template, info)); + +unlock: + msi_unlock_descs(dev); +} + +/** + * msi_match_device_irq_domain - Match a device irq domain against a bus token + * @dev: Pointer to the device + * @domid: Domain id + * @bus_token: Bus token to match against the domain bus token + * + * Return: True if device domain exists and bus tokens match. + */ +bool msi_match_device_irq_domain(struct device *dev, unsigned int domid, + enum irq_domain_bus_token bus_token) +{ + struct msi_domain_info *info; + struct irq_domain *domain; + bool ret = false; + + msi_lock_descs(dev); + domain = msi_get_device_domain(dev, domid); + if (domain && irq_domain_is_msi_device(domain)) { + info = domain->host_data; + ret = info->bus_token == bus_token; + } + msi_unlock_descs(dev); + return ret; } int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev, @@ -700,13 +1061,8 @@ int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev, { struct msi_domain_info *info = domain->host_data; struct msi_domain_ops *ops = info->ops; - int ret; - ret = ops->msi_check(domain, info, dev); - if (ret == 0) - ret = ops->msi_prepare(domain, dev, nvec, arg); - - return ret; + return ops->msi_prepare(domain, dev, nvec, arg); } int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev, @@ -714,16 +1070,27 @@ int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev, { struct msi_domain_info *info = domain->host_data; struct msi_domain_ops *ops = info->ops; + struct msi_ctrl ctrl = { + .domid = MSI_DEFAULT_DOMAIN, + .first = virq_base, + .last = virq_base + nvec - 1, + }; struct msi_desc *desc; + struct xarray *xa; int ret, virq; + if (!msi_ctrl_valid(dev, &ctrl)) + return -EINVAL; + msi_lock_descs(dev); - ret = msi_add_simple_msi_descs(dev, virq_base, nvec); + ret = msi_domain_add_simple_msi_descs(dev, &ctrl); if (ret) goto unlock; + xa = &dev->msi.data->__domains[ctrl.domid].store; + for (virq = virq_base; virq < virq_base + nvec; virq++) { - desc = xa_load(&dev->msi.data->__store, virq); + desc = xa_load(xa, virq); desc->irq = virq; ops->set_desc(arg, desc); @@ -739,7 +1106,7 @@ int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev, fail: for (--virq; virq >= virq_base; virq--) irq_domain_free_irqs_common(domain, virq, 1); - msi_free_msi_descs_range(dev, MSI_DESC_ALL, virq_base, virq_base + nvec - 1); + msi_domain_free_descs(dev, &ctrl); unlock: msi_unlock_descs(dev); return ret; @@ -764,6 +1131,8 @@ static bool msi_check_reservation_mode(struct irq_domain *domain, switch(domain->bus_token) { case DOMAIN_BUS_PCI_MSI: + case DOMAIN_BUS_PCI_DEVICE_MSI: + case DOMAIN_BUS_PCI_DEVICE_MSIX: case DOMAIN_BUS_VMD_MSI: break; default: @@ -789,6 +1158,8 @@ static int msi_handle_pci_fail(struct irq_domain *domain, struct msi_desc *desc, { switch(domain->bus_token) { case DOMAIN_BUS_PCI_MSI: + case DOMAIN_BUS_PCI_DEVICE_MSI: + case DOMAIN_BUS_PCI_DEVICE_MSIX: case DOMAIN_BUS_VMD_MSI: if (IS_ENABLED(CONFIG_PCI_MSI)) break; @@ -850,18 +1221,19 @@ static int msi_init_virq(struct irq_domain *domain, int virq, unsigned int vflag return 0; } -int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, - int nvec) +static int __msi_domain_alloc_irqs(struct device *dev, struct irq_domain *domain, + struct msi_ctrl *ctrl) { + struct xarray *xa = &dev->msi.data->__domains[ctrl->domid].store; struct msi_domain_info *info = domain->host_data; struct msi_domain_ops *ops = info->ops; + unsigned int vflags = 0, allocated = 0; msi_alloc_info_t arg = { }; - unsigned int vflags = 0; struct msi_desc *desc; - int allocated = 0; + unsigned long idx; int i, ret, virq; - ret = msi_domain_prepare_irqs(domain, dev, nvec, &arg); + ret = msi_domain_prepare_irqs(domain, dev, ctrl->nirqs, &arg); if (ret) return ret; @@ -883,11 +1255,21 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, * MSI affinity setting requires a special quirk (X86) when * reservation mode is active. */ - if (domain->flags & IRQ_DOMAIN_MSI_NOMASK_QUIRK) + if (info->flags & MSI_FLAG_NOMASK_QUIRK) vflags |= VIRQ_NOMASK_QUIRK; } - msi_for_each_desc(desc, dev, MSI_DESC_NOTASSOCIATED) { + xa_for_each_range(xa, idx, desc, ctrl->first, ctrl->last) { + if (!msi_desc_match(desc, MSI_DESC_NOTASSOCIATED)) + continue; + + /* This should return -ECONFUSED... */ + if (WARN_ON_ONCE(allocated >= ctrl->nirqs)) + return -EINVAL; + + if (ops->prepare_desc) + ops->prepare_desc(domain, &arg, desc); + ops->set_desc(&arg, desc); virq = __irq_domain_alloc_irqs(domain, -1, desc->nvec_used, @@ -913,76 +1295,213 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, return 0; } -static int msi_domain_add_simple_msi_descs(struct msi_domain_info *info, - struct device *dev, - unsigned int num_descs) +static int msi_domain_alloc_simple_msi_descs(struct device *dev, + struct msi_domain_info *info, + struct msi_ctrl *ctrl) { if (!(info->flags & MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS)) return 0; - return msi_add_simple_msi_descs(dev, 0, num_descs); + return msi_domain_add_simple_msi_descs(dev, ctrl); +} + +static int __msi_domain_alloc_locked(struct device *dev, struct msi_ctrl *ctrl) +{ + struct msi_domain_info *info; + struct msi_domain_ops *ops; + struct irq_domain *domain; + int ret; + + if (!msi_ctrl_valid(dev, ctrl)) + return -EINVAL; + + domain = msi_get_device_domain(dev, ctrl->domid); + if (!domain) + return -ENODEV; + + info = domain->host_data; + + ret = msi_domain_alloc_simple_msi_descs(dev, info, ctrl); + if (ret) + return ret; + + ops = info->ops; + if (ops->domain_alloc_irqs) + return ops->domain_alloc_irqs(domain, dev, ctrl->nirqs); + + return __msi_domain_alloc_irqs(dev, domain, ctrl); +} + +static int msi_domain_alloc_locked(struct device *dev, struct msi_ctrl *ctrl) +{ + int ret = __msi_domain_alloc_locked(dev, ctrl); + + if (ret) + msi_domain_free_locked(dev, ctrl); + return ret; } /** - * msi_domain_alloc_irqs_descs_locked - Allocate interrupts from a MSI interrupt domain - * @domain: The domain to allocate from + * msi_domain_alloc_irqs_range_locked - Allocate interrupts from a MSI interrupt domain * @dev: Pointer to device struct of the device for which the interrupts * are allocated - * @nvec: The number of interrupts to allocate + * @domid: Id of the interrupt domain to operate on + * @first: First index to allocate (inclusive) + * @last: Last index to allocate (inclusive) * * Must be invoked from within a msi_lock_descs() / msi_unlock_descs() - * pair. Use this for MSI irqdomains which implement their own vector + * pair. Use this for MSI irqdomains which implement their own descriptor * allocation/free. * * Return: %0 on success or an error code. */ -int msi_domain_alloc_irqs_descs_locked(struct irq_domain *domain, struct device *dev, - int nvec) +int msi_domain_alloc_irqs_range_locked(struct device *dev, unsigned int domid, + unsigned int first, unsigned int last) { - struct msi_domain_info *info = domain->host_data; - struct msi_domain_ops *ops = info->ops; - int ret; - - lockdep_assert_held(&dev->msi.data->mutex); + struct msi_ctrl ctrl = { + .domid = domid, + .first = first, + .last = last, + .nirqs = last + 1 - first, + }; + + return msi_domain_alloc_locked(dev, &ctrl); +} - ret = msi_domain_add_simple_msi_descs(info, dev, nvec); - if (ret) - return ret; +/** + * msi_domain_alloc_irqs_range - Allocate interrupts from a MSI interrupt domain + * @dev: Pointer to device struct of the device for which the interrupts + * are allocated + * @domid: Id of the interrupt domain to operate on + * @first: First index to allocate (inclusive) + * @last: Last index to allocate (inclusive) + * + * Return: %0 on success or an error code. + */ +int msi_domain_alloc_irqs_range(struct device *dev, unsigned int domid, + unsigned int first, unsigned int last) +{ + int ret; - ret = ops->domain_alloc_irqs(domain, dev, nvec); - if (ret) - msi_domain_free_irqs_descs_locked(domain, dev); + msi_lock_descs(dev); + ret = msi_domain_alloc_irqs_range_locked(dev, domid, first, last); + msi_unlock_descs(dev); return ret; } /** - * msi_domain_alloc_irqs - Allocate interrupts from a MSI interrupt domain - * @domain: The domain to allocate from + * msi_domain_alloc_irqs_all_locked - Allocate all interrupts from a MSI interrupt domain + * * @dev: Pointer to device struct of the device for which the interrupts * are allocated - * @nvec: The number of interrupts to allocate + * @domid: Id of the interrupt domain to operate on + * @nirqs: The number of interrupts to allocate + * + * This function scans all MSI descriptors of the MSI domain and allocates interrupts + * for all unassigned ones. That function is to be used for MSI domain usage where + * the descriptor allocation is handled at the call site, e.g. PCI/MSI[X]. * * Return: %0 on success or an error code. */ -int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, int nvec) +int msi_domain_alloc_irqs_all_locked(struct device *dev, unsigned int domid, int nirqs) { + struct msi_ctrl ctrl = { + .domid = domid, + .first = 0, + .last = msi_domain_get_hwsize(dev, domid) - 1, + .nirqs = nirqs, + }; + + return msi_domain_alloc_locked(dev, &ctrl); +} + +/** + * msi_domain_alloc_irq_at - Allocate an interrupt from a MSI interrupt domain at + * a given index - or at the next free index + * + * @dev: Pointer to device struct of the device for which the interrupts + * are allocated + * @domid: Id of the interrupt domain to operate on + * @index: Index for allocation. If @index == %MSI_ANY_INDEX the allocation + * uses the next free index. + * @affdesc: Optional pointer to an interrupt affinity descriptor structure + * @icookie: Optional pointer to a domain specific per instance cookie. If + * non-NULL the content of the cookie is stored in msi_desc::data. + * Must be NULL for MSI-X allocations + * + * This requires a MSI interrupt domain which lets the core code manage the + * MSI descriptors. + * + * Return: struct msi_map + * + * On success msi_map::index contains the allocated index number and + * msi_map::virq the corresponding Linux interrupt number + * + * On failure msi_map::index contains the error code and msi_map::virq + * is %0. + */ +struct msi_map msi_domain_alloc_irq_at(struct device *dev, unsigned int domid, unsigned int index, + const struct irq_affinity_desc *affdesc, + union msi_instance_cookie *icookie) +{ + struct msi_ctrl ctrl = { .domid = domid, .nirqs = 1, }; + struct irq_domain *domain; + struct msi_map map = { }; + struct msi_desc *desc; int ret; msi_lock_descs(dev); - ret = msi_domain_alloc_irqs_descs_locked(domain, dev, nvec); + domain = msi_get_device_domain(dev, domid); + if (!domain) { + map.index = -ENODEV; + goto unlock; + } + + desc = msi_alloc_desc(dev, 1, affdesc); + if (!desc) { + map.index = -ENOMEM; + goto unlock; + } + + if (icookie) + desc->data.icookie = *icookie; + + ret = msi_insert_desc(dev, desc, domid, index); + if (ret) { + map.index = ret; + goto unlock; + } + + ctrl.first = ctrl.last = desc->msi_index; + + ret = __msi_domain_alloc_irqs(dev, domain, &ctrl); + if (ret) { + map.index = ret; + msi_domain_free_locked(dev, &ctrl); + } else { + map.index = desc->msi_index; + map.virq = desc->irq; + } +unlock: msi_unlock_descs(dev); - return ret; + return map; } -void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) +static void __msi_domain_free_irqs(struct device *dev, struct irq_domain *domain, + struct msi_ctrl *ctrl) { + struct xarray *xa = &dev->msi.data->__domains[ctrl->domid].store; struct msi_domain_info *info = domain->host_data; struct irq_data *irqd; struct msi_desc *desc; + unsigned long idx; int i; - /* Only handle MSI entries which have an interrupt associated */ - msi_for_each_desc(desc, dev, MSI_DESC_ASSOCIATED) { + xa_for_each_range(xa, idx, desc, ctrl->first, ctrl->last) { + /* Only handle MSI entries which have an interrupt associated */ + if (!msi_desc_match(desc, MSI_DESC_ASSOCIATED)) + continue; + /* Make sure all interrupts are deactivated */ for (i = 0; i < desc->nvec_used; i++) { irqd = irq_domain_get_irq_data(domain, desc->irq + i); @@ -997,44 +1516,99 @@ void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) } } -static void msi_domain_free_msi_descs(struct msi_domain_info *info, - struct device *dev) +static void msi_domain_free_locked(struct device *dev, struct msi_ctrl *ctrl) { + struct msi_domain_info *info; + struct msi_domain_ops *ops; + struct irq_domain *domain; + + if (!msi_ctrl_valid(dev, ctrl)) + return; + + domain = msi_get_device_domain(dev, ctrl->domid); + if (!domain) + return; + + info = domain->host_data; + ops = info->ops; + + if (ops->domain_free_irqs) + ops->domain_free_irqs(domain, dev); + else + __msi_domain_free_irqs(dev, domain, ctrl); + + if (ops->msi_post_free) + ops->msi_post_free(domain, dev); + if (info->flags & MSI_FLAG_FREE_MSI_DESCS) - msi_free_msi_descs(dev); + msi_domain_free_descs(dev, ctrl); } /** - * msi_domain_free_irqs_descs_locked - Free interrupts from a MSI interrupt @domain associated to @dev - * @domain: The domain to managing the interrupts + * msi_domain_free_irqs_range_locked - Free a range of interrupts from a MSI interrupt domain + * associated to @dev with msi_lock held * @dev: Pointer to device struct of the device for which the interrupts - * are free + * are freed + * @domid: Id of the interrupt domain to operate on + * @first: First index to free (inclusive) + * @last: Last index to free (inclusive) + */ +void msi_domain_free_irqs_range_locked(struct device *dev, unsigned int domid, + unsigned int first, unsigned int last) +{ + struct msi_ctrl ctrl = { + .domid = domid, + .first = first, + .last = last, + }; + msi_domain_free_locked(dev, &ctrl); +} + +/** + * msi_domain_free_irqs_range - Free a range of interrupts from a MSI interrupt domain + * associated to @dev + * @dev: Pointer to device struct of the device for which the interrupts + * are freed + * @domid: Id of the interrupt domain to operate on + * @first: First index to free (inclusive) + * @last: Last index to free (inclusive) + */ +void msi_domain_free_irqs_range(struct device *dev, unsigned int domid, + unsigned int first, unsigned int last) +{ + msi_lock_descs(dev); + msi_domain_free_irqs_range_locked(dev, domid, first, last); + msi_unlock_descs(dev); +} + +/** + * msi_domain_free_irqs_all_locked - Free all interrupts from a MSI interrupt domain + * associated to a device + * @dev: Pointer to device struct of the device for which the interrupts + * are freed + * @domid: The id of the domain to operate on * * Must be invoked from within a msi_lock_descs() / msi_unlock_descs() * pair. Use this for MSI irqdomains which implement their own vector * allocation. */ -void msi_domain_free_irqs_descs_locked(struct irq_domain *domain, struct device *dev) +void msi_domain_free_irqs_all_locked(struct device *dev, unsigned int domid) { - struct msi_domain_info *info = domain->host_data; - struct msi_domain_ops *ops = info->ops; - - lockdep_assert_held(&dev->msi.data->mutex); - - ops->domain_free_irqs(domain, dev); - msi_domain_free_msi_descs(info, dev); + msi_domain_free_irqs_range_locked(dev, domid, 0, + msi_domain_get_hwsize(dev, domid) - 1); } /** - * msi_domain_free_irqs - Free interrupts from a MSI interrupt @domain associated to @dev - * @domain: The domain to managing the interrupts + * msi_domain_free_irqs_all - Free all interrupts from a MSI interrupt domain + * associated to a device * @dev: Pointer to device struct of the device for which the interrupts - * are free + * are freed + * @domid: The id of the domain to operate on */ -void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) +void msi_domain_free_irqs_all(struct device *dev, unsigned int domid) { msi_lock_descs(dev); - msi_domain_free_irqs_descs_locked(domain, dev); + msi_domain_free_irqs_all_locked(dev, domid); msi_unlock_descs(dev); } @@ -1048,5 +1622,3 @@ struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain) { return (struct msi_domain_info *)domain->host_data; } - -#endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 188c305aeb8b..c6d9dec11b74 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -267,13 +267,14 @@ int proc_dostring(struct ctl_table *table, int write, ppos); } -static size_t proc_skip_spaces(char **buf) +static void proc_skip_spaces(char **buf, size_t *size) { - size_t ret; - char *tmp = skip_spaces(*buf); - ret = tmp - *buf; - *buf = tmp; - return ret; + while (*size) { + if (!isspace(**buf)) + break; + (*size)--; + (*buf)++; + } } static void proc_skip_char(char **buf, size_t *size, const char v) @@ -342,13 +343,12 @@ static int proc_get_long(char **buf, size_t *size, unsigned long *val, bool *neg, const char *perm_tr, unsigned perm_tr_len, char *tr) { - int len; char *p, tmp[TMPBUFLEN]; + ssize_t len = *size; - if (!*size) + if (len <= 0) return -EINVAL; - len = *size; if (len > TMPBUFLEN - 1) len = TMPBUFLEN - 1; @@ -521,7 +521,7 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, bool neg; if (write) { - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); if (!left) break; @@ -548,7 +548,7 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, if (!write && !first && left && !err) proc_put_char(&buffer, &left, '\n'); if (write && !err && left) - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); if (write && first) return err ? : -EINVAL; *lenp -= left; @@ -590,7 +590,7 @@ static int do_proc_douintvec_w(unsigned int *tbl_data, if (left > PAGE_SIZE - 1) left = PAGE_SIZE - 1; - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); if (!left) { err = -EINVAL; goto out_free; @@ -610,7 +610,7 @@ static int do_proc_douintvec_w(unsigned int *tbl_data, } if (!err && left) - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); out_free: if (err) @@ -1075,7 +1075,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, if (write) { bool neg; - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); if (!left) break; @@ -1104,7 +1104,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, if (!write && !first && left && !err) proc_put_char(&buffer, &left, '\n'); if (write && !err) - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); if (write && first) return err ? : -EINVAL; *lenp -= left; @@ -2852,7 +2852,7 @@ static int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned lo next = pud_addr_end(addr, end); if (unlikely(!pud_present(pud))) return 0; - if (unlikely(pud_huge(pud))) { + if (unlikely(pud_huge(pud) || pud_devmap(pud))) { if (!gup_huge_pud(pud, pudp, addr, next, flags, pages, nr)) return 0; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a1a35c12635e..266a1ab05434 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4832,6 +4832,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, unsigned int efd, cfd; struct fd efile; struct fd cfile; + struct dentry *cdentry; const char *name; char *endp; int ret; @@ -4886,6 +4887,16 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, goto out_put_cfile; /* + * The control file must be a regular cgroup1 file. As a regular cgroup + * file can't be renamed, it's safe to access its name afterwards. + */ + cdentry = cfile.file->f_path.dentry; + if (cdentry->d_sb->s_type != &cgroup_fs_type || !d_is_reg(cdentry)) { + ret = -EINVAL; + goto out_put_cfile; + } + + /* * Determine the event callbacks and set them in @event. This used * to be done via struct cftype but cgroup core no longer knows * about these events. The following is crude but the whole thing @@ -4893,7 +4904,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, * * DO NOT ADD NEW FILES. */ - name = cfile.file->f_path.dentry->d_name.name; + name = cdentry->d_name.name; if (!strcmp(name, "memory.usage_in_bytes")) { event->register_event = mem_cgroup_usage_register_event; @@ -4917,7 +4928,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, * automatically removed on cgroup destruction but the removal is * asynchronous, so take an extra ref on @css. */ - cfile_css = css_tryget_online_from_dir(cfile.file->f_path.dentry->d_parent, + cfile_css = css_tryget_online_from_dir(cdentry->d_parent, &memory_cgrp_subsys); ret = -EINVAL; if (IS_ERR(cfile_css)) diff --git a/mm/mmap.c b/mm/mmap.c index a5eb2f175da0..54abd46e6007 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -226,8 +226,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) /* Search one past newbrk */ mas_set(&mas, newbrk); brkvma = mas_find(&mas, oldbrk); - BUG_ON(brkvma == NULL); - if (brkvma->vm_start >= oldbrk) + if (!brkvma || brkvma->vm_start >= oldbrk) goto out; /* mapping intersects with an existing non-brk vma. */ /* * mm->brk must be protected by write mmap_lock. @@ -2946,9 +2945,9 @@ static int do_brk_flags(struct ma_state *mas, struct vm_area_struct *vma, * Expand the existing vma if possible; Note that singular lists do not * occur after forking, so the expand will only happen on new VMAs. */ - if (vma && - (!vma->anon_vma || list_is_singular(&vma->anon_vma_chain)) && - ((vma->vm_flags & ~VM_SOFTDIRTY) == flags)) { + if (vma && vma->vm_end == addr && !vma_policy(vma) && + can_vma_merge_after(vma, flags, NULL, NULL, + addr >> PAGE_SHIFT, NULL_VM_UFFD_CTX, NULL)) { mas_set_range(mas, vma->vm_start, addr + len - 1); if (mas_preallocate(mas, vma, GFP_KERNEL)) return -ENOMEM; @@ -3035,11 +3034,6 @@ int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags) goto munmap_failed; vma = mas_prev(&mas, 0); - if (!vma || vma->vm_end != addr || vma_policy(vma) || - !can_vma_merge_after(vma, flags, NULL, NULL, - addr >> PAGE_SHIFT, NULL_VM_UFFD_CTX, NULL)) - vma = NULL; - ret = do_brk_flags(&mas, vma, addr, len, flags); populate = ((mm->def_flags & VM_LOCKED) != 0); mmap_write_unlock(mm); diff --git a/mm/shmem.c b/mm/shmem.c index c1d8b8a1aa3b..82911fefc2d5 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -948,6 +948,15 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, index++; } + /* + * When undoing a failed fallocate, we want none of the partial folio + * zeroing and splitting below, but shall want to truncate the whole + * folio when !uptodate indicates that it was added by this fallocate, + * even when [lstart, lend] covers only a part of the folio. + */ + if (unfalloc) + goto whole_folios; + same_folio = (lstart >> PAGE_SHIFT) == (lend >> PAGE_SHIFT); folio = shmem_get_partial_folio(inode, lstart >> PAGE_SHIFT); if (folio) { @@ -973,6 +982,8 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, folio_put(folio); } +whole_folios: + index = start; while (index < end) { cond_resched(); diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 215af9b3b589..c57d643afb10 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -972,6 +972,7 @@ static int get_l2cap_conn(char *buf, bdaddr_t *addr, u8 *addr_type, hci_dev_lock(hdev); hcon = hci_conn_hash_lookup_le(hdev, addr, *addr_type); hci_dev_unlock(hdev); + hci_dev_put(hdev); if (!hcon) return -ENOENT; diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index dc65974f5adb..1c3c7ff5c3c6 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -737,7 +737,7 @@ static int __init bt_init(void) err = bt_sysfs_init(); if (err < 0) - return err; + goto cleanup_led; err = sock_register(&bt_sock_family_ops); if (err) @@ -773,6 +773,8 @@ unregister_socket: sock_unregister(PF_BLUETOOTH); cleanup_sysfs: bt_sysfs_cleanup(); +cleanup_led: + bt_leds_cleanup(); return err; } diff --git a/net/bluetooth/hci_codec.c b/net/bluetooth/hci_codec.c index 38201532f58e..3cc135bb1d30 100644 --- a/net/bluetooth/hci_codec.c +++ b/net/bluetooth/hci_codec.c @@ -72,9 +72,8 @@ static void hci_read_codec_capabilities(struct hci_dev *hdev, __u8 transport, continue; } - skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_CODEC_CAPS, - sizeof(*cmd), cmd, - HCI_CMD_TIMEOUT); + skb = __hci_cmd_sync_sk(hdev, HCI_OP_READ_LOCAL_CODEC_CAPS, + sizeof(*cmd), cmd, 0, HCI_CMD_TIMEOUT, NULL); if (IS_ERR(skb)) { bt_dev_err(hdev, "Failed to read codec capabilities (%ld)", PTR_ERR(skb)); @@ -127,8 +126,8 @@ void hci_read_supported_codecs(struct hci_dev *hdev) struct hci_op_read_local_codec_caps caps; __u8 i; - skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_CODECS, 0, NULL, - HCI_CMD_TIMEOUT); + skb = __hci_cmd_sync_sk(hdev, HCI_OP_READ_LOCAL_CODECS, 0, NULL, + 0, HCI_CMD_TIMEOUT, NULL); if (IS_ERR(skb)) { bt_dev_err(hdev, "Failed to read local supported codecs (%ld)", @@ -158,7 +157,8 @@ void hci_read_supported_codecs(struct hci_dev *hdev) for (i = 0; i < std_codecs->num; i++) { caps.id = std_codecs->codec[i]; caps.direction = 0x00; - hci_read_codec_capabilities(hdev, LOCAL_CODEC_ACL_MASK, &caps); + hci_read_codec_capabilities(hdev, + LOCAL_CODEC_ACL_MASK | LOCAL_CODEC_SCO_MASK, &caps); } skb_pull(skb, flex_array_size(std_codecs, codec, std_codecs->num) @@ -178,7 +178,8 @@ void hci_read_supported_codecs(struct hci_dev *hdev) caps.cid = vnd_codecs->codec[i].cid; caps.vid = vnd_codecs->codec[i].vid; caps.direction = 0x00; - hci_read_codec_capabilities(hdev, LOCAL_CODEC_ACL_MASK, &caps); + hci_read_codec_capabilities(hdev, + LOCAL_CODEC_ACL_MASK | LOCAL_CODEC_SCO_MASK, &caps); } error: @@ -194,8 +195,8 @@ void hci_read_supported_codecs_v2(struct hci_dev *hdev) struct hci_op_read_local_codec_caps caps; __u8 i; - skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_CODECS_V2, 0, NULL, - HCI_CMD_TIMEOUT); + skb = __hci_cmd_sync_sk(hdev, HCI_OP_READ_LOCAL_CODECS_V2, 0, NULL, + 0, HCI_CMD_TIMEOUT, NULL); if (IS_ERR(skb)) { bt_dev_err(hdev, "Failed to read local supported codecs (%ld)", diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 0540555b3704..d97fac4f7130 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2764,7 +2764,8 @@ int hci_register_suspend_notifier(struct hci_dev *hdev) { int ret = 0; - if (!test_bit(HCI_QUIRK_NO_SUSPEND_NOTIFIER, &hdev->quirks)) { + if (!hdev->suspend_notifier.notifier_call && + !test_bit(HCI_QUIRK_NO_SUSPEND_NOTIFIER, &hdev->quirks)) { hdev->suspend_notifier.notifier_call = hci_suspend_notifier; ret = register_pm_notifier(&hdev->suspend_notifier); } @@ -2776,8 +2777,11 @@ int hci_unregister_suspend_notifier(struct hci_dev *hdev) { int ret = 0; - if (!test_bit(HCI_QUIRK_NO_SUSPEND_NOTIFIER, &hdev->quirks)) + if (hdev->suspend_notifier.notifier_call) { ret = unregister_pm_notifier(&hdev->suspend_notifier); + if (!ret) + hdev->suspend_notifier.notifier_call = NULL; + } return ret; } diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index 5a0296a4352e..f7e006a36382 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -269,7 +269,7 @@ void hci_req_add_ev(struct hci_request *req, u16 opcode, u32 plen, void hci_req_add(struct hci_request *req, u16 opcode, u32 plen, const void *param) { - bt_dev_err(req->hdev, "HCI_REQ-0x%4.4x", opcode); + bt_dev_dbg(req->hdev, "HCI_REQ-0x%4.4x", opcode); hci_req_add_ev(req, opcode, plen, param, 0); } diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 76c3107c9f91..1fc693122a47 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -12,6 +12,7 @@ #include <net/bluetooth/mgmt.h> #include "hci_request.h" +#include "hci_codec.h" #include "hci_debugfs.h" #include "smp.h" #include "eir.h" @@ -3780,7 +3781,8 @@ static int hci_read_page_scan_activity_sync(struct hci_dev *hdev) static int hci_read_def_err_data_reporting_sync(struct hci_dev *hdev) { if (!(hdev->commands[18] & 0x04) || - !(hdev->features[0][6] & LMP_ERR_DATA_REPORTING)) + !(hdev->features[0][6] & LMP_ERR_DATA_REPORTING) || + test_bit(HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, &hdev->quirks)) return 0; return __hci_cmd_sync_status(hdev, HCI_OP_READ_DEF_ERR_DATA_REPORTING, @@ -4238,11 +4240,12 @@ static int hci_set_event_mask_page_2_sync(struct hci_dev *hdev) /* Read local codec list if the HCI command is supported */ static int hci_read_local_codecs_sync(struct hci_dev *hdev) { - if (!(hdev->commands[29] & 0x20)) - return 0; + if (hdev->commands[45] & 0x04) + hci_read_supported_codecs_v2(hdev); + else if (hdev->commands[29] & 0x20) + hci_read_supported_codecs(hdev); - return __hci_cmd_sync_status(hdev, HCI_OP_READ_LOCAL_CODECS, 0, NULL, - HCI_CMD_TIMEOUT); + return 0; } /* Read local pairing options if the HCI command is supported */ @@ -4298,7 +4301,8 @@ static int hci_set_err_data_report_sync(struct hci_dev *hdev) bool enabled = hci_dev_test_flag(hdev, HCI_WIDEBAND_SPEECH_ENABLED); if (!(hdev->commands[18] & 0x08) || - !(hdev->features[0][6] & LMP_ERR_DATA_REPORTING)) + !(hdev->features[0][6] & LMP_ERR_DATA_REPORTING) || + test_bit(HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, &hdev->quirks)) return 0; if (enabled == hdev->err_data_reporting) @@ -4457,6 +4461,9 @@ static const struct { HCI_QUIRK_BROKEN(STORED_LINK_KEY, "HCI Delete Stored Link Key command is advertised, " "but not supported."), + HCI_QUIRK_BROKEN(ERR_DATA_REPORTING, + "HCI Read Default Erroneous Data Reporting command is " + "advertised, but not supported."), HCI_QUIRK_BROKEN(READ_TRANSMIT_POWER, "HCI Read Transmit Power Level command is advertised, " "but not supported."), diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index f825857db6d0..26db929b97c4 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -879,6 +879,7 @@ static int iso_listen_bis(struct sock *sk) iso_pi(sk)->bc_sid); hci_dev_unlock(hdev); + hci_dev_put(hdev); return err; } diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 9c24947aa41e..9fdede5fe71c 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4453,7 +4453,8 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, chan->ident = cmd->ident; l2cap_send_cmd(conn, cmd->ident, L2CAP_CONF_RSP, len, rsp); - chan->num_conf_rsp++; + if (chan->num_conf_rsp < L2CAP_CONF_MAX_CONF_RSP) + chan->num_conf_rsp++; /* Reset config buffer. */ chan->conf_len = 0; diff --git a/net/can/af_can.c b/net/can/af_can.c index 27dcdcc0b808..c69168f11e44 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -677,7 +677,7 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev) static int can_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { - if (unlikely(dev->type != ARPHRD_CAN || (!can_is_can_skb(skb)))) { + if (unlikely(dev->type != ARPHRD_CAN || !can_get_ml_priv(dev) || !can_is_can_skb(skb))) { pr_warn_once("PF_CAN: dropped non conform CAN skbuff: dev type %d, len %d\n", dev->type, skb->len); @@ -692,7 +692,7 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { - if (unlikely(dev->type != ARPHRD_CAN || (!can_is_canfd_skb(skb)))) { + if (unlikely(dev->type != ARPHRD_CAN || !can_get_ml_priv(dev) || !can_is_canfd_skb(skb))) { pr_warn_once("PF_CAN: dropped non conform CAN FD skbuff: dev type %d, len %d\n", dev->type, skb->len); @@ -707,7 +707,7 @@ static int canfd_rcv(struct sk_buff *skb, struct net_device *dev, static int canxl_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { - if (unlikely(dev->type != ARPHRD_CAN || (!can_is_canxl_skb(skb)))) { + if (unlikely(dev->type != ARPHRD_CAN || !can_get_ml_priv(dev) || !can_is_canxl_skb(skb))) { pr_warn_once("PF_CAN: dropped non conform CAN XL skbuff: dev type %d, len %d\n", dev->type, skb->len); diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c index 846588c0070a..53a206d11685 100644 --- a/net/dsa/tag_hellcreek.c +++ b/net/dsa/tag_hellcreek.c @@ -49,7 +49,8 @@ static struct sk_buff *hellcreek_rcv(struct sk_buff *skb, return NULL; } - pskb_trim_rcsum(skb, skb->len - HELLCREEK_TAG_LEN); + if (pskb_trim_rcsum(skb, skb->len - HELLCREEK_TAG_LEN)) + return NULL; dsa_default_offload_fwd_mark(skb); diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 38fa19c1e2d5..429250298ac4 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -21,7 +21,8 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, if (!skb->dev) return NULL; - pskb_trim_rcsum(skb, skb->len - len); + if (pskb_trim_rcsum(skb, skb->len - len)) + return NULL; dsa_default_offload_fwd_mark(skb); diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 83e4136516b0..1a85125bda6d 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -665,7 +665,8 @@ static struct sk_buff *sja1110_rcv_inband_control_extension(struct sk_buff *skb, * padding and trailer we need to account for the fact that * skb->data points to skb_mac_header(skb) + ETH_HLEN. */ - pskb_trim_rcsum(skb, start_of_padding - ETH_HLEN); + if (pskb_trim_rcsum(skb, start_of_padding - ETH_HLEN)) + return NULL; /* Trap-to-host frame, no timestamp trailer */ } else { *source_port = SJA1110_RX_HEADER_SRC_PORT(rx_header); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index f361d3d56be2..b5736ef16ed2 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -841,6 +841,9 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, return -EINVAL; } + if (!cfg->fc_table) + cfg->fc_table = RT_TABLE_MAIN; + return 0; errout: return err; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 19a662003eef..ce9ff3c62e84 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -423,6 +423,7 @@ static struct fib_info *fib_find_info(struct fib_info *nfi) nfi->fib_prefsrc == fi->fib_prefsrc && nfi->fib_priority == fi->fib_priority && nfi->fib_type == fi->fib_type && + nfi->fib_tb_id == fi->fib_tb_id && memcmp(nfi->fib_metrics, fi->fib_metrics, sizeof(u32) * RTAX_MAX) == 0 && !((nfi->fib_flags ^ fi->fib_flags) & ~RTNH_COMPARE_MASK) && diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index f866d6282b2b..cae9f1a4e059 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1492,24 +1492,6 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) struct ip_tunnel_parm *p = &t->parms; __be16 o_flags = p->o_flags; - if (t->erspan_ver <= 2) { - if (t->erspan_ver != 0 && !t->collect_md) - o_flags |= TUNNEL_KEY; - - if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) - goto nla_put_failure; - - if (t->erspan_ver == 1) { - if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) - goto nla_put_failure; - } else if (t->erspan_ver == 2) { - if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir)) - goto nla_put_failure; - if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid)) - goto nla_put_failure; - } - } - if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, gre_tnl_flags_to_gre_flags(p->i_flags)) || @@ -1550,6 +1532,34 @@ nla_put_failure: return -EMSGSIZE; } +static int erspan_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct ip_tunnel *t = netdev_priv(dev); + + if (t->erspan_ver <= 2) { + if (t->erspan_ver != 0 && !t->collect_md) + t->parms.o_flags |= TUNNEL_KEY; + + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) + goto nla_put_failure; + + if (t->erspan_ver == 1) { + if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) + goto nla_put_failure; + } else if (t->erspan_ver == 2) { + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir)) + goto nla_put_failure; + if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid)) + goto nla_put_failure; + } + } + + return ipgre_fill_info(skb, dev); + +nla_put_failure: + return -EMSGSIZE; +} + static void erspan_setup(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); @@ -1628,7 +1638,7 @@ static struct rtnl_link_ops erspan_link_ops __read_mostly = { .changelink = erspan_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, - .fill_info = ipgre_fill_info, + .fill_info = erspan_fill_info, .get_link_net = ip_tunnel_get_link_net, }; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index bde333b24837..04b4ec07bb06 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -49,6 +49,11 @@ #include <net/transp_v6.h> #endif +#define ping_portaddr_for_each_entry(__sk, node, list) \ + hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node) +#define ping_portaddr_for_each_entry_rcu(__sk, node, list) \ + hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node) + struct ping_table { struct hlist_nulls_head hash[PING_HTABLE_SIZE]; spinlock_t lock; @@ -192,7 +197,7 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident) return NULL; } - ping_portaddr_for_each_entry(sk, hnode, hslot) { + ping_portaddr_for_each_entry_rcu(sk, hnode, hslot) { isk = inet_sk(sk); pr_debug("iterate\n"); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index e19507614f64..60fd91bb5171 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -920,6 +920,9 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, if (err < 0) goto fail; + /* We prevent @rt from being freed. */ + rcu_read_lock(); + for (;;) { /* Prepare header of the next frame, * before previous one went down. */ @@ -943,6 +946,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, if (err == 0) { IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGOKS); + rcu_read_unlock(); return 0; } @@ -950,6 +954,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGFAILS); + rcu_read_unlock(); return err; slow_path_clean: diff --git a/net/mac802154/iface.c b/net/mac802154/iface.c index 500ed1b81250..7e2065e72915 100644 --- a/net/mac802154/iface.c +++ b/net/mac802154/iface.c @@ -662,6 +662,7 @@ ieee802154_if_add(struct ieee802154_local *local, const char *name, sdata->dev = ndev; sdata->wpan_dev.wpan_phy = local->hw.phy; sdata->local = local; + INIT_LIST_HEAD(&sdata->wpan_dev.list); /* setup type-dependent data */ ret = ieee802154_setup_sdata(sdata, type); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 2692139ce417..23b3fedd619a 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -891,7 +891,7 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) zone = nf_ct_zone(ct); if (!nf_ct_ext_valid_pre(ct->ext)) { - NF_CT_STAT_INC(net, insert_failed); + NF_CT_STAT_INC_ATOMIC(net, insert_failed); return -ETIMEDOUT; } @@ -938,7 +938,7 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) if (!nf_ct_ext_valid_post(ct->ext)) { nf_ct_kill(ct); - NF_CT_STAT_INC(net, drop); + NF_CT_STAT_INC_ATOMIC(net, drop); return -ETIMEDOUT; } @@ -1275,7 +1275,7 @@ chaintoolong: */ if (!nf_ct_ext_valid_post(ct->ext)) { nf_ct_kill(ct); - NF_CT_STAT_INC(net, drop); + NF_CT_STAT_INC_ATOMIC(net, drop); return NF_DROP; } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index d71150a40fb0..1286ae7d4609 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -328,8 +328,13 @@ nla_put_failure: } #ifdef CONFIG_NF_CONNTRACK_MARK -static int ctnetlink_dump_mark(struct sk_buff *skb, u32 mark) +static int ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct) { + u32 mark = READ_ONCE(ct->mark); + + if (!mark) + return 0; + if (nla_put_be32(skb, CTA_MARK, htonl(mark))) goto nla_put_failure; return 0; @@ -543,7 +548,7 @@ static int ctnetlink_dump_extinfo(struct sk_buff *skb, static int ctnetlink_dump_info(struct sk_buff *skb, struct nf_conn *ct) { if (ctnetlink_dump_status(skb, ct) < 0 || - ctnetlink_dump_mark(skb, READ_ONCE(ct->mark)) < 0 || + ctnetlink_dump_mark(skb, ct) < 0 || ctnetlink_dump_secctx(skb, ct) < 0 || ctnetlink_dump_id(skb, ct) < 0 || ctnetlink_dump_use(skb, ct) < 0 || @@ -722,7 +727,6 @@ ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item) struct sk_buff *skb; unsigned int type; unsigned int flags = 0, group; - u32 mark; int err; if (events & (1 << IPCT_DESTROY)) { @@ -827,9 +831,8 @@ ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item) } #ifdef CONFIG_NF_CONNTRACK_MARK - mark = READ_ONCE(ct->mark); - if ((events & (1 << IPCT_MARK) || mark) && - ctnetlink_dump_mark(skb, mark) < 0) + if (events & (1 << IPCT_MARK) && + ctnetlink_dump_mark(skb, ct) < 0) goto nla_put_failure; #endif nlmsg_end(skb, nlh); @@ -2671,7 +2674,6 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) { const struct nf_conntrack_zone *zone; struct nlattr *nest_parms; - u32 mark; zone = nf_ct_zone(ct); @@ -2733,8 +2735,7 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_MARK - mark = READ_ONCE(ct->mark); - if (mark && ctnetlink_dump_mark(skb, mark) < 0) + if (ctnetlink_dump_mark(skb, ct) < 0) goto nla_put_failure; #endif if (ctnetlink_dump_labels(skb, ct) < 0) diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 00b522890d77..0fdcdb2c9ae4 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -997,13 +997,13 @@ static void flow_offload_queue_work(struct flow_offload_work *offload) struct net *net = read_pnet(&offload->flowtable->net); if (offload->cmd == FLOW_CLS_REPLACE) { - NF_FLOW_TABLE_STAT_INC(net, count_wq_add); + NF_FLOW_TABLE_STAT_INC_ATOMIC(net, count_wq_add); queue_work(nf_flow_offload_add_wq, &offload->work); } else if (offload->cmd == FLOW_CLS_DESTROY) { - NF_FLOW_TABLE_STAT_INC(net, count_wq_del); + NF_FLOW_TABLE_STAT_INC_ATOMIC(net, count_wq_del); queue_work(nf_flow_offload_del_wq, &offload->work); } else { - NF_FLOW_TABLE_STAT_INC(net, count_wq_stats); + NF_FLOW_TABLE_STAT_INC_ATOMIC(net, count_wq_stats); queue_work(nf_flow_offload_stats_wq, &offload->work); } } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 4f9299b9dcdd..06d46d182634 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1162,6 +1162,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, struct nft_pipapo_match *m = priv->clone; u8 genmask = nft_genmask_next(net); struct nft_pipapo_field *f; + const u8 *start_p, *end_p; int i, bsize_max, err = 0; if (nft_set_ext_exists(ext, NFT_SET_EXT_KEY_END)) @@ -1202,9 +1203,9 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, } /* Validate */ + start_p = start; + end_p = end; nft_pipapo_for_each_field(f, i, m) { - const u8 *start_p = start, *end_p = end; - if (f->rules >= (unsigned long)NFT_PIPAPO_RULE0_MAX) return -ENOSPC; diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c index 282c51051dcc..994a0a1efb58 100644 --- a/net/nfc/nci/ntf.c +++ b/net/nfc/nci/ntf.c @@ -240,6 +240,8 @@ static int nci_add_new_protocol(struct nci_dev *ndev, target->sens_res = nfca_poll->sens_res; target->sel_res = nfca_poll->sel_res; target->nfcid1_len = nfca_poll->nfcid1_len; + if (target->nfcid1_len > ARRAY_SIZE(target->nfcid1)) + return -EPROTO; if (target->nfcid1_len > 0) { memcpy(target->nfcid1, nfca_poll->nfcid1, target->nfcid1_len); @@ -248,6 +250,8 @@ static int nci_add_new_protocol(struct nci_dev *ndev, nfcb_poll = (struct rf_tech_specific_params_nfcb_poll *)params; target->sensb_res_len = nfcb_poll->sensb_res_len; + if (target->sensb_res_len > ARRAY_SIZE(target->sensb_res)) + return -EPROTO; if (target->sensb_res_len > 0) { memcpy(target->sensb_res, nfcb_poll->sensb_res, target->sensb_res_len); @@ -256,6 +260,8 @@ static int nci_add_new_protocol(struct nci_dev *ndev, nfcf_poll = (struct rf_tech_specific_params_nfcf_poll *)params; target->sensf_res_len = nfcf_poll->sensf_res_len; + if (target->sensf_res_len > ARRAY_SIZE(target->sensf_res)) + return -EPROTO; if (target->sensf_res_len > 0) { memcpy(target->sensf_res, nfcf_poll->sensf_res, target->sensf_res_len); diff --git a/net/tipc/link.c b/net/tipc/link.c index e260c0d557f5..b3ce24823f50 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -2224,7 +2224,9 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, if (tipc_own_addr(l->net) > msg_prevnode(hdr)) l->net_plane = msg_net_plane(hdr); - skb_linearize(skb); + if (skb_linearize(skb)) + goto exit; + hdr = buf_msg(skb); data = msg_data(hdr); diff --git a/net/tipc/node.c b/net/tipc/node.c index b48d97cbbe29..49ddc484c4fe 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1689,6 +1689,7 @@ int tipc_node_xmit(struct net *net, struct sk_buff_head *list, struct tipc_node *n; struct sk_buff_head xmitq; bool node_up = false; + struct net *peer_net; int bearer_id; int rc; @@ -1705,18 +1706,23 @@ int tipc_node_xmit(struct net *net, struct sk_buff_head *list, return -EHOSTUNREACH; } + rcu_read_lock(); tipc_node_read_lock(n); node_up = node_is_up(n); - if (node_up && n->peer_net && check_net(n->peer_net)) { + peer_net = n->peer_net; + tipc_node_read_unlock(n); + if (node_up && peer_net && check_net(peer_net)) { /* xmit inner linux container */ - tipc_lxc_xmit(n->peer_net, list); + tipc_lxc_xmit(peer_net, list); if (likely(skb_queue_empty(list))) { - tipc_node_read_unlock(n); + rcu_read_unlock(); tipc_node_put(n); return 0; } } + rcu_read_unlock(); + tipc_node_read_lock(n); bearer_id = n->active_links[selector & 1]; if (unlikely(bearer_id == INVALID_BEARER_ID)) { tipc_node_read_unlock(n); diff --git a/net/unix/diag.c b/net/unix/diag.c index 105f522a89fe..616b55c5b890 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -114,14 +114,16 @@ static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb) return nla_put(nlskb, UNIX_DIAG_RQLEN, sizeof(rql), &rql); } -static int sk_diag_dump_uid(struct sock *sk, struct sk_buff *nlskb) +static int sk_diag_dump_uid(struct sock *sk, struct sk_buff *nlskb, + struct user_namespace *user_ns) { - uid_t uid = from_kuid_munged(sk_user_ns(nlskb->sk), sock_i_uid(sk)); + uid_t uid = from_kuid_munged(user_ns, sock_i_uid(sk)); return nla_put(nlskb, UNIX_DIAG_UID, sizeof(uid_t), &uid); } static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req, - u32 portid, u32 seq, u32 flags, int sk_ino) + struct user_namespace *user_ns, + u32 portid, u32 seq, u32 flags, int sk_ino) { struct nlmsghdr *nlh; struct unix_diag_msg *rep; @@ -167,7 +169,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r goto out_nlmsg_trim; if ((req->udiag_show & UDIAG_SHOW_UID) && - sk_diag_dump_uid(sk, skb)) + sk_diag_dump_uid(sk, skb, user_ns)) goto out_nlmsg_trim; nlmsg_end(skb, nlh); @@ -179,7 +181,8 @@ out_nlmsg_trim: } static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req, - u32 portid, u32 seq, u32 flags) + struct user_namespace *user_ns, + u32 portid, u32 seq, u32 flags) { int sk_ino; @@ -190,7 +193,7 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct unix_diag_r if (!sk_ino) return 0; - return sk_diag_fill(sk, skb, req, portid, seq, flags, sk_ino); + return sk_diag_fill(sk, skb, req, user_ns, portid, seq, flags, sk_ino); } static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) @@ -214,7 +217,7 @@ static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) goto next; if (!(req->udiag_states & (1 << sk->sk_state))) goto next; - if (sk_diag_dump(sk, skb, req, + if (sk_diag_dump(sk, skb, req, sk_user_ns(skb->sk), NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI) < 0) { @@ -282,7 +285,8 @@ again: if (!rep) goto out; - err = sk_diag_fill(sk, rep, req, NETLINK_CB(in_skb).portid, + err = sk_diag_fill(sk, rep, req, sk_user_ns(NETLINK_CB(in_skb).sk), + NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0, req->udiag_ino); if (err < 0) { nlmsg_free(rep); diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c index 22b31ebb3513..258ddc565deb 100644 --- a/tools/testing/selftests/cgroup/test_kmem.c +++ b/tools/testing/selftests/cgroup/test_kmem.c @@ -19,12 +19,12 @@ /* - * Memory cgroup charging is performed using percpu batches 32 pages + * Memory cgroup charging is performed using percpu batches 64 pages * big (look at MEMCG_CHARGE_BATCH), whereas memory.stat is exact. So * the maximum discrepancy between charge and vmstat entries is number - * of cpus multiplied by 32 pages. + * of cpus multiplied by 64 pages. */ -#define MAX_VMSTAT_ERROR (4096 * 32 * get_nprocs()) +#define MAX_VMSTAT_ERROR (4096 * 64 * get_nprocs()) static int alloc_dcache(const char *cgroup, void *arg) diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 3d7adee7a3e6..ff8fe93f679c 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only bind_bhash cmsg_sender +diag_uid fin_ack_lat gro hwtstamp_config diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index 969620ae9928..1e4b397cece6 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -1,3 +1,3 @@ -TEST_GEN_PROGS := test_unix_oob unix_connect +TEST_GEN_PROGS := diag_uid test_unix_oob unix_connect include ../../lib.mk diff --git a/tools/testing/selftests/net/af_unix/diag_uid.c b/tools/testing/selftests/net/af_unix/diag_uid.c new file mode 100644 index 000000000000..5b88f7129fea --- /dev/null +++ b/tools/testing/selftests/net/af_unix/diag_uid.c @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright Amazon.com Inc. or its affiliates. */ + +#define _GNU_SOURCE +#include <sched.h> + +#include <unistd.h> +#include <linux/netlink.h> +#include <linux/rtnetlink.h> +#include <linux/sock_diag.h> +#include <linux/unix_diag.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <sys/un.h> + +#include "../../kselftest_harness.h" + +FIXTURE(diag_uid) +{ + int netlink_fd; + int unix_fd; + __u32 inode; + __u64 cookie; +}; + +FIXTURE_VARIANT(diag_uid) +{ + int unshare; + int udiag_show; +}; + +FIXTURE_VARIANT_ADD(diag_uid, uid) +{ + .unshare = 0, + .udiag_show = UDIAG_SHOW_UID +}; + +FIXTURE_VARIANT_ADD(diag_uid, uid_unshare) +{ + .unshare = CLONE_NEWUSER, + .udiag_show = UDIAG_SHOW_UID +}; + +FIXTURE_SETUP(diag_uid) +{ + struct stat file_stat; + socklen_t optlen; + int ret; + + if (variant->unshare) + ASSERT_EQ(unshare(variant->unshare), 0); + + self->netlink_fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG); + ASSERT_NE(self->netlink_fd, -1); + + self->unix_fd = socket(AF_UNIX, SOCK_STREAM, 0); + ASSERT_NE(self->unix_fd, -1); + + ret = fstat(self->unix_fd, &file_stat); + ASSERT_EQ(ret, 0); + + self->inode = file_stat.st_ino; + + optlen = sizeof(self->cookie); + ret = getsockopt(self->unix_fd, SOL_SOCKET, SO_COOKIE, &self->cookie, &optlen); + ASSERT_EQ(ret, 0); +} + +FIXTURE_TEARDOWN(diag_uid) +{ + close(self->netlink_fd); + close(self->unix_fd); +} + +int send_request(struct __test_metadata *_metadata, + FIXTURE_DATA(diag_uid) *self, + const FIXTURE_VARIANT(diag_uid) *variant) +{ + struct { + struct nlmsghdr nlh; + struct unix_diag_req udr; + } req = { + .nlh = { + .nlmsg_len = sizeof(req), + .nlmsg_type = SOCK_DIAG_BY_FAMILY, + .nlmsg_flags = NLM_F_REQUEST + }, + .udr = { + .sdiag_family = AF_UNIX, + .udiag_ino = self->inode, + .udiag_cookie = { + (__u32)self->cookie, + (__u32)(self->cookie >> 32) + }, + .udiag_show = variant->udiag_show + } + }; + struct sockaddr_nl nladdr = { + .nl_family = AF_NETLINK + }; + struct iovec iov = { + .iov_base = &req, + .iov_len = sizeof(req) + }; + struct msghdr msg = { + .msg_name = &nladdr, + .msg_namelen = sizeof(nladdr), + .msg_iov = &iov, + .msg_iovlen = 1 + }; + + return sendmsg(self->netlink_fd, &msg, 0); +} + +void render_response(struct __test_metadata *_metadata, + struct unix_diag_req *udr, __u32 len) +{ + unsigned int rta_len = len - NLMSG_LENGTH(sizeof(*udr)); + struct rtattr *attr; + uid_t uid; + + ASSERT_GT(len, sizeof(*udr)); + ASSERT_EQ(udr->sdiag_family, AF_UNIX); + + attr = (struct rtattr *)(udr + 1); + ASSERT_NE(RTA_OK(attr, rta_len), 0); + ASSERT_EQ(attr->rta_type, UNIX_DIAG_UID); + + uid = *(uid_t *)RTA_DATA(attr); + ASSERT_EQ(uid, getuid()); +} + +void receive_response(struct __test_metadata *_metadata, + FIXTURE_DATA(diag_uid) *self) +{ + long buf[8192 / sizeof(long)]; + struct sockaddr_nl nladdr = { + .nl_family = AF_NETLINK + }; + struct iovec iov = { + .iov_base = buf, + .iov_len = sizeof(buf) + }; + struct msghdr msg = { + .msg_name = &nladdr, + .msg_namelen = sizeof(nladdr), + .msg_iov = &iov, + .msg_iovlen = 1 + }; + struct unix_diag_req *udr; + struct nlmsghdr *nlh; + int ret; + + ret = recvmsg(self->netlink_fd, &msg, 0); + ASSERT_GT(ret, 0); + + nlh = (struct nlmsghdr *)buf; + ASSERT_NE(NLMSG_OK(nlh, ret), 0); + ASSERT_EQ(nlh->nlmsg_type, SOCK_DIAG_BY_FAMILY); + + render_response(_metadata, NLMSG_DATA(nlh), nlh->nlmsg_len); + + nlh = NLMSG_NEXT(nlh, ret); + ASSERT_EQ(NLMSG_OK(nlh, ret), 0); +} + +TEST_F(diag_uid, 1) +{ + int ret; + + ret = send_request(_metadata, self, variant); + ASSERT_GT(ret, 0); + + receive_response(_metadata, self); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index ead7963b9bf0..bd89198cd817 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -43,5 +43,5 @@ CONFIG_NET_ACT_TUNNEL_KEY=m CONFIG_NET_ACT_MIRRED=m CONFIG_BAREUDP=m CONFIG_IPV6_IOAM6_LWTUNNEL=y -CONFIG_CRYPTO_SM4=y +CONFIG_CRYPTO_SM4_GENERIC=y CONFIG_AMT=m diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 2271a8727f62..5637b5dadabd 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -1711,13 +1711,21 @@ ipv4_del_addr_test() $IP addr add dev dummy1 172.16.104.1/24 $IP addr add dev dummy1 172.16.104.11/24 + $IP addr add dev dummy1 172.16.104.12/24 + $IP addr add dev dummy1 172.16.104.13/24 $IP addr add dev dummy2 172.16.104.1/24 $IP addr add dev dummy2 172.16.104.11/24 + $IP addr add dev dummy2 172.16.104.12/24 $IP route add 172.16.105.0/24 via 172.16.104.2 src 172.16.104.11 + $IP route add 172.16.106.0/24 dev lo src 172.16.104.12 + $IP route add table 0 172.16.107.0/24 via 172.16.104.2 src 172.16.104.13 $IP route add vrf red 172.16.105.0/24 via 172.16.104.2 src 172.16.104.11 + $IP route add vrf red 172.16.106.0/24 dev lo src 172.16.104.12 set +e # removing address from device in vrf should only remove route from vrf table + echo " Regular FIB info" + $IP addr del dev dummy2 172.16.104.11/24 $IP ro ls vrf red | grep -q 172.16.105.0/24 log_test $? 1 "Route removed from VRF when source address deleted" @@ -1735,6 +1743,35 @@ ipv4_del_addr_test() $IP ro ls vrf red | grep -q 172.16.105.0/24 log_test $? 0 "Route in VRF is not removed by address delete" + # removing address from device in vrf should only remove route from vrf + # table even when the associated fib info only differs in table ID + echo " Identical FIB info with different table ID" + + $IP addr del dev dummy2 172.16.104.12/24 + $IP ro ls vrf red | grep -q 172.16.106.0/24 + log_test $? 1 "Route removed from VRF when source address deleted" + + $IP ro ls | grep -q 172.16.106.0/24 + log_test $? 0 "Route in default VRF not removed" + + $IP addr add dev dummy2 172.16.104.12/24 + $IP route add vrf red 172.16.106.0/24 dev lo src 172.16.104.12 + + $IP addr del dev dummy1 172.16.104.12/24 + $IP ro ls | grep -q 172.16.106.0/24 + log_test $? 1 "Route removed in default VRF when source address deleted" + + $IP ro ls vrf red | grep -q 172.16.106.0/24 + log_test $? 0 "Route in VRF is not removed by address delete" + + # removing address from device in default vrf should remove route from + # the default vrf even when route was inserted with a table ID of 0. + echo " Table ID 0" + + $IP addr del dev dummy1 172.16.104.13/24 + $IP ro ls | grep -q 172.16.107.0/24 + log_test $? 1 "Route removed in default VRF when source address deleted" + $IP li del dummy1 $IP li del dummy2 cleanup diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 0900c5438fbb..275491be3da2 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -782,7 +782,7 @@ kci_test_ipsec_offload() tmpl proto esp src $srcip dst $dstip spi 9 \ mode transport reqid 42 check_err $? - ip x p add dir out src $dstip/24 dst $srcip/24 \ + ip x p add dir in src $dstip/24 dst $srcip/24 \ tmpl proto esp src $dstip dst $srcip spi 9 \ mode transport reqid 42 check_err $? diff --git a/tools/testing/selftests/net/toeplitz.sh b/tools/testing/selftests/net/toeplitz.sh index 0a49907cd4fe..da5bfd834eff 100755 --- a/tools/testing/selftests/net/toeplitz.sh +++ b/tools/testing/selftests/net/toeplitz.sh @@ -32,7 +32,7 @@ DEV="eth0" # This is determined by reading the RSS indirection table using ethtool. get_rss_cfg_num_rxqs() { echo $(ethtool -x "${DEV}" | - egrep [[:space:]]+[0-9]+:[[:space:]]+ | + grep -E [[:space:]]+[0-9]+:[[:space:]]+ | cut -d: -f2- | awk '{$1=$1};1' | tr ' ' '\n' | |