diff options
415 files changed, 4415 insertions, 1985 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 533ff5c68970..fc1fab76a6c8 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1716,7 +1716,8 @@ merge nomerge soft - pt [x86, IA-64] + pt [x86] + nopt [x86] nobypass [PPC/POWERNV] Disable IOMMU bypass, using IOMMU for PCI devices. diff --git a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt index ffadb7c6f1f3..c6e2d855fe13 100644 --- a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt +++ b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt @@ -19,7 +19,10 @@ Required Properties: - "renesas,ipmmu-r8a7794" for the R8A7794 (R-Car E2) IPMMU. - "renesas,ipmmu-r8a7795" for the R8A7795 (R-Car H3) IPMMU. - "renesas,ipmmu-r8a7796" for the R8A7796 (R-Car M3-W) IPMMU. + - "renesas,ipmmu-r8a77965" for the R8A77965 (R-Car M3-N) IPMMU. - "renesas,ipmmu-r8a77970" for the R8A77970 (R-Car V3M) IPMMU. + - "renesas,ipmmu-r8a77980" for the R8A77980 (R-Car V3H) IPMMU. + - "renesas,ipmmu-r8a77990" for the R8A77990 (R-Car E3) IPMMU. - "renesas,ipmmu-r8a77995" for the R8A77995 (R-Car D3) IPMMU. - "renesas,ipmmu-vmsa" for generic R-Car Gen2 or RZ/G1 VMSA-compatible IPMMU. diff --git a/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt b/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt index 252a05c5d976..c8c4b00ecb94 100644 --- a/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt +++ b/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt @@ -16,7 +16,8 @@ A child node must exist to represent the core DWC3 IP block. The name of the node is not important. The content of the node is defined in dwc3.txt. Phy documentation is provided in the following places: -Documentation/devicetree/bindings/phy/qcom-dwc3-usb-phy.txt +Documentation/devicetree/bindings/phy/phy-rockchip-inno-usb2.txt - USB2.0 PHY +Documentation/devicetree/bindings/phy/phy-rockchip-typec.txt - Type-C PHY Example device nodes: diff --git a/Documentation/networking/dpaa2/overview.rst b/Documentation/networking/dpaa2/overview.rst index 79fede4447d6..d638b5a8aadd 100644 --- a/Documentation/networking/dpaa2/overview.rst +++ b/Documentation/networking/dpaa2/overview.rst @@ -1,5 +1,6 @@ .. include:: <isonum.txt> +========================================================= DPAA2 (Data Path Acceleration Architecture Gen2) Overview ========================================================= diff --git a/MAINTAINERS b/MAINTAINERS index 0fe4228f78cb..7cebd5bba8a8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5444,6 +5444,7 @@ F: drivers/iommu/exynos-iommu.c EZchip NPS platform support M: Vineet Gupta <vgupta@synopsys.com> +M: Ofer Levi <oferle@mellanox.com> S: Supported F: arch/arc/plat-eznps F: arch/arc/boot/dts/eznps.dts @@ -7095,6 +7096,7 @@ F: include/uapi/linux/input.h F: include/uapi/linux/input-event-codes.h F: include/linux/input/ F: Documentation/devicetree/bindings/input/ +F: Documentation/devicetree/bindings/serio/ F: Documentation/input/ INPUT MULTITOUCH (MT) PROTOCOL @@ -7984,7 +7986,7 @@ F: lib/test_kmod.c F: tools/testing/selftests/kmod/ KPROBES -M: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com> +M: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> M: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> M: "David S. Miller" <davem@davemloft.net> M: Masami Hiramatsu <mhiramat@kernel.org> @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 18 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc8 NAME = Merciless Moray # *DOCUMENTATION* diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 9cf59fc60eab..5151d81476a1 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -50,6 +50,9 @@ config ARC select HAVE_KERNEL_LZMA select ARCH_HAS_PTE_SPECIAL +config ARCH_HAS_CACHE_LINE_SIZE + def_bool y + config MIGHT_HAVE_PCI bool diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h index 8486f328cc5d..ff7d3232764a 100644 --- a/arch/arc/include/asm/cache.h +++ b/arch/arc/include/asm/cache.h @@ -48,7 +48,9 @@ }) /* Largest line length for either L1 or L2 is 128 bytes */ -#define ARCH_DMA_MINALIGN 128 +#define SMP_CACHE_BYTES 128 +#define cache_line_size() SMP_CACHE_BYTES +#define ARCH_DMA_MINALIGN SMP_CACHE_BYTES extern void arc_cache_init(void); extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len); diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h index d5da2115d78a..03d6bb0f4e13 100644 --- a/arch/arc/include/asm/delay.h +++ b/arch/arc/include/asm/delay.h @@ -17,8 +17,11 @@ #ifndef __ASM_ARC_UDELAY_H #define __ASM_ARC_UDELAY_H +#include <asm-generic/types.h> #include <asm/param.h> /* HZ */ +extern unsigned long loops_per_jiffy; + static inline void __delay(unsigned long loops) { __asm__ __volatile__( diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 9dbe645ee127..25c631942500 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -1038,7 +1038,7 @@ void flush_cache_mm(struct mm_struct *mm) void flush_cache_page(struct vm_area_struct *vma, unsigned long u_vaddr, unsigned long pfn) { - unsigned int paddr = pfn << PAGE_SHIFT; + phys_addr_t paddr = pfn << PAGE_SHIFT; u_vaddr &= PAGE_MASK; @@ -1058,8 +1058,9 @@ void flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long u_vaddr) { /* TBD: do we really need to clear the kernel mapping */ - __flush_dcache_page(page_address(page), u_vaddr); - __flush_dcache_page(page_address(page), page_address(page)); + __flush_dcache_page((phys_addr_t)page_address(page), u_vaddr); + __flush_dcache_page((phys_addr_t)page_address(page), + (phys_addr_t)page_address(page)); } @@ -1246,6 +1247,16 @@ void __init arc_cache_init_master(void) } } + /* + * Check that SMP_CACHE_BYTES (and hence ARCH_DMA_MINALIGN) is larger + * or equal to any cache line length. + */ + BUILD_BUG_ON_MSG(L1_CACHE_BYTES > SMP_CACHE_BYTES, + "SMP_CACHE_BYTES must be >= any cache line length"); + if (is_isa_arcv2() && (l2_line_sz > SMP_CACHE_BYTES)) + panic("L2 Cache line [%d] > kernel Config [%d]\n", + l2_line_sz, SMP_CACHE_BYTES); + /* Note that SLC disable not formally supported till HS 3.0 */ if (is_isa_arcv2() && l2_line_sz && !slc_enable) arc_slc_disable(); diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index 8c1071840979..ec47e6079f5d 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -129,14 +129,59 @@ int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma, return ret; } +/* + * Cache operations depending on function and direction argument, inspired by + * https://lkml.org/lkml/2018/5/18/979 + * "dma_sync_*_for_cpu and direction=TO_DEVICE (was Re: [PATCH 02/20] + * dma-mapping: provide a generic dma-noncoherent implementation)" + * + * | map == for_device | unmap == for_cpu + * |---------------------------------------------------------------- + * TO_DEV | writeback writeback | none none + * FROM_DEV | invalidate invalidate | invalidate* invalidate* + * BIDIR | writeback+inv writeback+inv | invalidate invalidate + * + * [*] needed for CPU speculative prefetches + * + * NOTE: we don't check the validity of direction argument as it is done in + * upper layer functions (in include/linux/dma-mapping.h) + */ + void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr, size_t size, enum dma_data_direction dir) { - dma_cache_wback(paddr, size); + switch (dir) { + case DMA_TO_DEVICE: + dma_cache_wback(paddr, size); + break; + + case DMA_FROM_DEVICE: + dma_cache_inv(paddr, size); + break; + + case DMA_BIDIRECTIONAL: + dma_cache_wback_inv(paddr, size); + break; + + default: + break; + } } void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, size_t size, enum dma_data_direction dir) { - dma_cache_inv(paddr, size); + switch (dir) { + case DMA_TO_DEVICE: + break; + + /* FROM_DEVICE invalidate needed if speculative CPU prefetch only */ + case DMA_FROM_DEVICE: + case DMA_BIDIRECTIONAL: + dma_cache_inv(paddr, size); + break; + + default: + break; + } } diff --git a/arch/arc/plat-eznps/include/plat/ctop.h b/arch/arc/plat-eznps/include/plat/ctop.h index 0c7d11022d0f..4f6a1673b3a6 100644 --- a/arch/arc/plat-eznps/include/plat/ctop.h +++ b/arch/arc/plat-eznps/include/plat/ctop.h @@ -21,6 +21,7 @@ #error "Incorrect ctop.h include" #endif +#include <linux/types.h> #include <soc/nps/common.h> /* core auxiliary registers */ @@ -143,6 +144,15 @@ struct nps_host_reg_gim_p_int_dst { }; /* AUX registers definition */ +struct nps_host_reg_aux_dpc { + union { + struct { + u32 ien:1, men:1, hen:1, reserved:29; + }; + u32 value; + }; +}; + struct nps_host_reg_aux_udmc { union { struct { diff --git a/arch/arc/plat-eznps/mtm.c b/arch/arc/plat-eznps/mtm.c index 2388de3d09ef..ed0077ef666e 100644 --- a/arch/arc/plat-eznps/mtm.c +++ b/arch/arc/plat-eznps/mtm.c @@ -15,6 +15,8 @@ */ #include <linux/smp.h> +#include <linux/init.h> +#include <linux/kernel.h> #include <linux/io.h> #include <linux/log2.h> #include <asm/arcregs.h> @@ -157,10 +159,10 @@ void mtm_enable_core(unsigned int cpu) /* Verify and set the value of the mtm hs counter */ static int __init set_mtm_hs_ctr(char *ctr_str) { - long hs_ctr; + int hs_ctr; int ret; - ret = kstrtol(ctr_str, 0, &hs_ctr); + ret = kstrtoint(ctr_str, 0, &hs_ctr); if (ret || hs_ctr > MT_HS_CNT_MAX || hs_ctr < MT_HS_CNT_MIN) { pr_err("** Invalid @nps_mtm_hs_ctr [%d] needs to be [%d:%d] (incl)\n", diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index 106a1466518d..746565a876dc 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -48,6 +48,7 @@ saved_pc .req lr * from those features make this path too inefficient. */ ret_fast_syscall: +__ret_fast_syscall: UNWIND(.fnstart ) UNWIND(.cantunwind ) disable_irq_notrace @ disable interrupts @@ -78,6 +79,7 @@ fast_work_pending: * call. */ ret_fast_syscall: +__ret_fast_syscall: UNWIND(.fnstart ) UNWIND(.cantunwind ) str r0, [sp, #S_R0 + S_OFF]! @ save returned r0 @@ -255,7 +257,7 @@ local_restart: tst r10, #_TIF_SYSCALL_WORK @ are we tracing syscalls? bne __sys_trace - invoke_syscall tbl, scno, r10, ret_fast_syscall + invoke_syscall tbl, scno, r10, __ret_fast_syscall add r1, sp, #S_OFF 2: cmp scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE) diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 225d1c58d2de..d9c299133111 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -338,6 +338,7 @@ static struct vm_area_struct gate_vma = { static int __init gate_vma_init(void) { + vma_init(&gate_vma, NULL); gate_vma.vm_page_prot = PAGE_READONLY_EXEC; return 0; } diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c index 39aef4876ed4..04b2f22c2739 100644 --- a/arch/arm/mach-rpc/ecard.c +++ b/arch/arm/mach-rpc/ecard.c @@ -212,7 +212,7 @@ static DEFINE_MUTEX(ecard_mutex); */ static void ecard_init_pgtables(struct mm_struct *mm) { - struct vm_area_struct vma; + struct vm_area_struct vma = TLB_FLUSH_VMA(mm, VM_EXEC); /* We want to set up the page tables for the following mapping: * Virtual Physical @@ -237,9 +237,6 @@ static void ecard_init_pgtables(struct mm_struct *mm) memcpy(dst_pgd, src_pgd, sizeof(pgd_t) * (EASI_SIZE / PGDIR_SIZE)); - vma.vm_flags = VM_EXEC; - vma.vm_mm = mm; - flush_tlb_range(&vma, IO_START, IO_START + IO_SIZE); flush_tlb_range(&vma, EASI_START, EASI_START + EASI_SIZE); } diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c index 7cf0b1aa6ea8..8a10f1d7199a 100644 --- a/arch/arm64/crypto/ghash-ce-glue.c +++ b/arch/arm64/crypto/ghash-ce-glue.c @@ -488,9 +488,13 @@ static int gcm_decrypt(struct aead_request *req) err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE); } - if (walk.nbytes) - pmull_gcm_encrypt_block(iv, iv, NULL, + if (walk.nbytes) { + kernel_neon_begin(); + pmull_gcm_encrypt_block(iv, iv, ctx->aes_key.key_enc, num_rounds(&ctx->aes_key)); + kernel_neon_end(); + } + } else { __aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, num_rounds(&ctx->aes_key)); diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index ffdaea7954bb..0ad1cf233470 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -37,7 +37,7 @@ static inline void __tlb_remove_table(void *_table) static inline void tlb_flush(struct mmu_gather *tlb) { - struct vm_area_struct vma = { .vm_mm = tlb->mm, }; + struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0); /* * The ASID allocator will either invalidate the ASID or mark diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index f24892a40d2c..c6d80743f4ed 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1351,9 +1351,9 @@ static void __update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, static void update_cpu_capabilities(u16 scope_mask) { - __update_cpu_capabilities(arm64_features, scope_mask, "detected:"); __update_cpu_capabilities(arm64_errata, scope_mask, "enabling workaround for"); + __update_cpu_capabilities(arm64_features, scope_mask, "detected:"); } static int __enable_cpu_capability(void *arg) @@ -1408,8 +1408,8 @@ __enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps, static void __init enable_cpu_capabilities(u16 scope_mask) { - __enable_cpu_capabilities(arm64_features, scope_mask); __enable_cpu_capabilities(arm64_errata, scope_mask); + __enable_cpu_capabilities(arm64_features, scope_mask); } /* diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index ecc6818191df..192b3ba07075 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -108,7 +108,6 @@ static pte_t get_clear_flush(struct mm_struct *mm, unsigned long pgsize, unsigned long ncontig) { - struct vm_area_struct vma = { .vm_mm = mm }; pte_t orig_pte = huge_ptep_get(ptep); bool valid = pte_valid(orig_pte); unsigned long i, saddr = addr; @@ -125,8 +124,10 @@ static pte_t get_clear_flush(struct mm_struct *mm, orig_pte = pte_mkdirty(orig_pte); } - if (valid) + if (valid) { + struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); flush_tlb_range(&vma, saddr, addr); + } return orig_pte; } @@ -145,7 +146,7 @@ static void clear_flush(struct mm_struct *mm, unsigned long pgsize, unsigned long ncontig) { - struct vm_area_struct vma = { .vm_mm = mm }; + struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); unsigned long i, saddr = addr; for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 325cfb3b858a..9abf8a1e7b25 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -611,11 +611,13 @@ void __init mem_init(void) BUILD_BUG_ON(TASK_SIZE_32 > TASK_SIZE_64); #endif +#ifdef CONFIG_SPARSEMEM_VMEMMAP /* * Make sure we chose the upper bound of sizeof(struct page) - * correctly. + * correctly when sizing the VMEMMAP array. */ BUILD_BUG_ON(sizeof(struct page) > (1 << STRUCT_PAGE_MAX_SHIFT)); +#endif if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) { extern int sysctl_overcommit_memory; diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h index 44f0ac0df308..516355a774bf 100644 --- a/arch/ia64/include/asm/tlb.h +++ b/arch/ia64/include/asm/tlb.h @@ -115,12 +115,11 @@ ia64_tlb_flush_mmu_tlbonly(struct mmu_gather *tlb, unsigned long start, unsigned flush_tlb_all(); } else { /* - * XXX fix me: flush_tlb_range() should take an mm pointer instead of a - * vma pointer. + * flush_tlb_range() takes a vma instead of a mm pointer because + * some architectures want the vm_flags for ITLB/DTLB flush. */ - struct vm_area_struct vma; + struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0); - vma.vm_mm = tlb->mm; /* flush the address range from the tlb: */ flush_tlb_range(&vma, start, end); /* now flush the virt. page-table area mapping the address range: */ diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index bdb14a369137..3b85c3ecac38 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -116,6 +116,7 @@ ia64_init_addr_space (void) */ vma = vm_area_alloc(current->mm); if (vma) { + vma_set_anonymous(vma); vma->vm_start = current->thread.rbs_bot & PAGE_MASK; vma->vm_end = vma->vm_start + PAGE_SIZE; vma->vm_flags = VM_DATA_DEFAULT_FLAGS|VM_GROWSUP|VM_ACCOUNT; @@ -133,6 +134,7 @@ ia64_init_addr_space (void) if (!(current->personality & MMAP_PAGE_ZERO)) { vma = vm_area_alloc(current->mm); if (vma) { + vma_set_anonymous(vma); vma->vm_end = PAGE_SIZE; vma->vm_page_prot = __pgprot(pgprot_val(PAGE_READONLY) | _PAGE_MA_NAT); vma->vm_flags = VM_READ | VM_MAYREAD | VM_IO | @@ -273,7 +275,7 @@ static struct vm_area_struct gate_vma; static int __init gate_vma_init(void) { - gate_vma.vm_mm = NULL; + vma_init(&gate_vma, NULL); gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; diff --git a/arch/mips/ath79/common.c b/arch/mips/ath79/common.c index 10a405d593df..c782b10ddf50 100644 --- a/arch/mips/ath79/common.c +++ b/arch/mips/ath79/common.c @@ -58,7 +58,7 @@ EXPORT_SYMBOL_GPL(ath79_ddr_ctrl_init); void ath79_ddr_wb_flush(u32 reg) { - void __iomem *flush_reg = ath79_ddr_wb_flush_base + reg; + void __iomem *flush_reg = ath79_ddr_wb_flush_base + (reg * 4); /* Flush the DDR write buffer. */ __raw_writel(0x1, flush_reg); diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c index 8c9cbf13d32a..6054d49e608e 100644 --- a/arch/mips/bcm47xx/setup.c +++ b/arch/mips/bcm47xx/setup.c @@ -212,12 +212,6 @@ static int __init bcm47xx_cpu_fixes(void) */ if (bcm47xx_bus.bcma.bus.chipinfo.id == BCMA_CHIP_ID_BCM4706) cpu_wait = NULL; - - /* - * BCM47XX Erratum "R10: PCIe Transactions Periodically Fail" - * Enable ExternalSync for sync instruction to take effect - */ - set_c0_config7(MIPS_CONF7_ES); break; #endif } diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h index 0bc270806ec5..ae461d91cd1f 100644 --- a/arch/mips/include/asm/mipsregs.h +++ b/arch/mips/include/asm/mipsregs.h @@ -681,8 +681,6 @@ #define MIPS_CONF7_WII (_ULCAST_(1) << 31) #define MIPS_CONF7_RPS (_ULCAST_(1) << 2) -/* ExternalSync */ -#define MIPS_CONF7_ES (_ULCAST_(1) << 8) #define MIPS_CONF7_IAR (_ULCAST_(1) << 10) #define MIPS_CONF7_AR (_ULCAST_(1) << 16) @@ -2767,7 +2765,6 @@ __BUILD_SET_C0(status) __BUILD_SET_C0(cause) __BUILD_SET_C0(config) __BUILD_SET_C0(config5) -__BUILD_SET_C0(config7) __BUILD_SET_C0(intcontrol) __BUILD_SET_C0(intctl) __BUILD_SET_C0(srsmap) diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c index 9632436d74d7..c2e94cf5ecda 100644 --- a/arch/mips/pci/pci.c +++ b/arch/mips/pci/pci.c @@ -54,5 +54,5 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar, phys_addr_t size = resource_size(rsrc); *start = fixup_bigphys_addr(rsrc->start, size); - *end = rsrc->start + size; + *end = rsrc->start + size - 1; } diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 79d570cbf332..b2f89b621b15 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -143,24 +143,33 @@ static inline void mm_context_remove_copro(struct mm_struct *mm) { int c; - c = atomic_dec_if_positive(&mm->context.copros); - - /* Detect imbalance between add and remove */ - WARN_ON(c < 0); - /* - * Need to broadcast a global flush of the full mm before - * decrementing active_cpus count, as the next TLBI may be - * local and the nMMU and/or PSL need to be cleaned up. - * Should be rare enough so that it's acceptable. + * When removing the last copro, we need to broadcast a global + * flush of the full mm, as the next TLBI may be local and the + * nMMU and/or PSL need to be cleaned up. + * + * Both the 'copros' and 'active_cpus' counts are looked at in + * flush_all_mm() to determine the scope (local/global) of the + * TLBIs, so we need to flush first before decrementing + * 'copros'. If this API is used by several callers for the + * same context, it can lead to over-flushing. It's hopefully + * not common enough to be a problem. * * Skip on hash, as we don't know how to do the proper flush * for the time being. Invalidations will remain global if - * used on hash. + * used on hash. Note that we can't drop 'copros' either, as + * it could make some invalidations local with no flush + * in-between. */ - if (c == 0 && radix_enabled()) { + if (radix_enabled()) { flush_all_mm(mm); - dec_mm_active_cpus(mm); + + c = atomic_dec_if_positive(&mm->context.copros); + /* Detect imbalance between add and remove */ + WARN_ON(c < 0); + + if (c == 0) + dec_mm_active_cpus(mm); } } #else diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index fe9733ffffaa..471aac313b89 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -42,6 +42,8 @@ #include <asm/ppc-pci.h> #include <asm/eeh.h> +#include "../../../drivers/pci/pci.h" + /* hose_spinlock protects accesses to the the phb_bitmap. */ static DEFINE_SPINLOCK(hose_spinlock); LIST_HEAD(hose_list); @@ -1014,7 +1016,7 @@ void pcibios_setup_bus_devices(struct pci_bus *bus) /* Cardbus can call us to add new devices to a bus, so ignore * those who are already fully discovered */ - if (dev->is_added) + if (pci_dev_is_added(dev)) continue; pcibios_setup_device(dev); diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 380cbf9a40d9..c0a9bcd28356 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -286,6 +286,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u64 imm64; u8 *func; u32 true_cond; + u32 tmp_idx; /* * addrs[] maps a BPF bytecode address into a real offset from @@ -637,11 +638,7 @@ emit_clear: case BPF_STX | BPF_XADD | BPF_W: /* Get EA into TMP_REG_1 */ PPC_ADDI(b2p[TMP_REG_1], dst_reg, off); - /* error if EA is not word-aligned */ - PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x03); - PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + 12); - PPC_LI(b2p[BPF_REG_0], 0); - PPC_JMP(exit_addr); + tmp_idx = ctx->idx * 4; /* load value from memory into TMP_REG_2 */ PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); /* add value from src_reg into this */ @@ -649,32 +646,16 @@ emit_clear: /* store result back */ PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); /* we're done if this succeeded */ - PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4)); - /* otherwise, let's try once more */ - PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); - PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg); - PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); - /* exit if the store was not successful */ - PPC_LI(b2p[BPF_REG_0], 0); - PPC_BCC(COND_NE, exit_addr); + PPC_BCC_SHORT(COND_NE, tmp_idx); break; /* *(u64 *)(dst + off) += src */ case BPF_STX | BPF_XADD | BPF_DW: PPC_ADDI(b2p[TMP_REG_1], dst_reg, off); - /* error if EA is not doubleword-aligned */ - PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x07); - PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (3*4)); - PPC_LI(b2p[BPF_REG_0], 0); - PPC_JMP(exit_addr); - PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); - PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg); - PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); - PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4)); + tmp_idx = ctx->idx * 4; PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg); PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); - PPC_LI(b2p[BPF_REG_0], 0); - PPC_BCC(COND_NE, exit_addr); + PPC_BCC_SHORT(COND_NE, tmp_idx); break; /* diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 5bd0eb6681bc..70b2e1e0f23c 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -46,6 +46,7 @@ #include "powernv.h" #include "pci.h" +#include "../../../../drivers/pci/pci.h" #define PNV_IODA1_M64_NUM 16 /* Number of M64 BARs */ #define PNV_IODA1_M64_SEGS 8 /* Segments per M64 BAR */ @@ -3138,7 +3139,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) struct pci_dn *pdn; int mul, total_vfs; - if (!pdev->is_physfn || pdev->is_added) + if (!pdev->is_physfn || pci_dev_is_added(pdev)) return; pdn = pci_get_pdn(pdev); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 139f0af6c3d9..8a4868a3964b 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -71,6 +71,7 @@ #include <asm/security_features.h> #include "pseries.h" +#include "../../../../drivers/pci/pci.h" int CMO_PrPSP = -1; int CMO_SecPSP = -1; @@ -664,7 +665,7 @@ static void pseries_pci_fixup_iov_resources(struct pci_dev *pdev) const int *indexes; struct device_node *dn = pci_device_to_OF_node(pdev); - if (!pdev->is_physfn || pdev->is_added) + if (!pdev->is_physfn || pci_dev_is_added(pdev)) return; /*Firmware must support open sriov otherwise dont configure*/ indexes = of_get_property(dn, "ibm,open-sriov-vf-bar-info", NULL); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index e44bb2b2873e..8a1863d9ed53 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -140,7 +140,7 @@ config S390 select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_FUTEX_CMPXCHG if FUTEX - select HAVE_GCC_PLUGINS + select HAVE_GCC_PLUGINS if BROKEN select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZ4 diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index ac67828da201..410b263ef5c8 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -13,6 +13,7 @@ generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += module.h +generic-y += msi.h generic-y += preempt.h generic-y += rwsem.h generic-y += serial.h diff --git a/arch/sparc/include/asm/msi.h b/arch/sparc/include/asm/msi.h deleted file mode 100644 index 3c17c1074431..000000000000 --- a/arch/sparc/include/asm/msi.h +++ /dev/null @@ -1,32 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * msi.h: Defines specific to the MBus - Sbus - Interface. - * - * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu) - * Copyright (C) 1996 Eddie C. Dost (ecd@skynet.be) - */ - -#ifndef _SPARC_MSI_H -#define _SPARC_MSI_H - -/* - * Locations of MSI Registers. - */ -#define MSI_MBUS_ARBEN 0xe0001008 /* MBus Arbiter Enable register */ - -/* - * Useful bits in the MSI Registers. - */ -#define MSI_ASYNC_MODE 0x80000000 /* Operate the MSI asynchronously */ - - -static inline void msi_set_sync(void) -{ - __asm__ __volatile__ ("lda [%0] %1, %%g3\n\t" - "andn %%g3, %2, %%g3\n\t" - "sta %%g3, [%0] %1\n\t" : : - "r" (MSI_MBUS_ARBEN), - "i" (ASI_M_CTL), "r" (MSI_ASYNC_MODE) : "g3"); -} - -#endif /* !(_SPARC_MSI_H) */ diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c index 2ef8cfa9677e..f0eba72aa1ad 100644 --- a/arch/sparc/kernel/time_64.c +++ b/arch/sparc/kernel/time_64.c @@ -814,7 +814,7 @@ static void __init get_tick_patch(void) } } -static void init_tick_ops(struct sparc64_tick_ops *ops) +static void __init init_tick_ops(struct sparc64_tick_ops *ops) { unsigned long freq, quotient, tick; diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index 1d70c3f6d986..be9cb0065179 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -37,7 +37,6 @@ #include <asm/mbus.h> #include <asm/page.h> #include <asm/asi.h> -#include <asm/msi.h> #include <asm/smp.h> #include <asm/io.h> @@ -116,6 +115,25 @@ static inline void srmmu_ctxd_set(ctxd_t *ctxp, pgd_t *pgdp) set_pte((pte_t *)ctxp, pte); } +/* + * Locations of MSI Registers. + */ +#define MSI_MBUS_ARBEN 0xe0001008 /* MBus Arbiter Enable register */ + +/* + * Useful bits in the MSI Registers. + */ +#define MSI_ASYNC_MODE 0x80000000 /* Operate the MSI asynchronously */ + +static void msi_set_sync(void) +{ + __asm__ __volatile__ ("lda [%0] %1, %%g3\n\t" + "andn %%g3, %2, %%g3\n\t" + "sta %%g3, [%0] %1\n\t" : : + "r" (MSI_MBUS_ARBEN), + "i" (ASI_M_CTL), "r" (MSI_ASYNC_MODE) : "g3"); +} + void pmd_set(pmd_t *pmdp, pte_t *ptep) { unsigned long ptp; /* Physical address, shifted right by 4 */ diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index fa42f895fdde..169c2feda14a 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -106,9 +106,13 @@ define cmd_check_data_rel done endef +# We need to run two commands under "if_changed", so merge them into a +# single invocation. +quiet_cmd_check-and-link-vmlinux = LD $@ + cmd_check-and-link-vmlinux = $(cmd_check_data_rel); $(cmd_ld) + $(obj)/vmlinux: $(vmlinux-objs-y) FORCE - $(call if_changed,check_data_rel) - $(call if_changed,ld) + $(call if_changed,check-and-link-vmlinux) OBJCOPYFLAGS_vmlinux.bin := -R .comment -S $(obj)/vmlinux.bin: vmlinux FORCE diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index 8c5107545251..9e2157371491 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -1,3 +1,4 @@ +#include <asm/e820/types.h> #include <asm/processor.h> #include "pgtable.h" #include "../string.h" @@ -34,10 +35,62 @@ unsigned long *trampoline_32bit __section(.data); extern struct boot_params *boot_params; int cmdline_find_option_bool(const char *option); +static unsigned long find_trampoline_placement(void) +{ + unsigned long bios_start, ebda_start; + unsigned long trampoline_start; + struct boot_e820_entry *entry; + int i; + + /* + * Find a suitable spot for the trampoline. + * This code is based on reserve_bios_regions(). + */ + + ebda_start = *(unsigned short *)0x40e << 4; + bios_start = *(unsigned short *)0x413 << 10; + + if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX) + bios_start = BIOS_START_MAX; + + if (ebda_start > BIOS_START_MIN && ebda_start < bios_start) + bios_start = ebda_start; + + bios_start = round_down(bios_start, PAGE_SIZE); + + /* Find the first usable memory region under bios_start. */ + for (i = boot_params->e820_entries - 1; i >= 0; i--) { + entry = &boot_params->e820_table[i]; + + /* Skip all entries above bios_start. */ + if (bios_start <= entry->addr) + continue; + + /* Skip non-RAM entries. */ + if (entry->type != E820_TYPE_RAM) + continue; + + /* Adjust bios_start to the end of the entry if needed. */ + if (bios_start > entry->addr + entry->size) + bios_start = entry->addr + entry->size; + + /* Keep bios_start page-aligned. */ + bios_start = round_down(bios_start, PAGE_SIZE); + + /* Skip the entry if it's too small. */ + if (bios_start - TRAMPOLINE_32BIT_SIZE < entry->addr) + continue; + + break; + } + + /* Place the trampoline just below the end of low memory */ + return bios_start - TRAMPOLINE_32BIT_SIZE; +} + struct paging_config paging_prepare(void *rmode) { struct paging_config paging_config = {}; - unsigned long bios_start, ebda_start; /* Initialize boot_params. Required for cmdline_find_option_bool(). */ boot_params = rmode; @@ -61,23 +114,7 @@ struct paging_config paging_prepare(void *rmode) paging_config.l5_required = 1; } - /* - * Find a suitable spot for the trampoline. - * This code is based on reserve_bios_regions(). - */ - - ebda_start = *(unsigned short *)0x40e << 4; - bios_start = *(unsigned short *)0x413 << 10; - - if (bios_start < BIOS_START_MIN || bios_start > BIOS_START_MAX) - bios_start = BIOS_START_MAX; - - if (ebda_start > BIOS_START_MIN && ebda_start < bios_start) - bios_start = ebda_start; - - /* Place the trampoline just below the end of low memory, aligned to 4k */ - paging_config.trampoline_start = bios_start - TRAMPOLINE_32BIT_SIZE; - paging_config.trampoline_start = round_down(paging_config.trampoline_start, PAGE_SIZE); + paging_config.trampoline_start = find_trampoline_placement(); trampoline_32bit = (unsigned long *)paging_config.trampoline_start; diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 73a522d53b53..8ae7ffda8f98 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -981,7 +981,7 @@ ENTRY(\sym) call \do_sym - jmp error_exit /* %ebx: no swapgs flag */ + jmp error_exit .endif END(\sym) .endm @@ -1222,7 +1222,6 @@ END(paranoid_exit) /* * Save all registers in pt_regs, and switch GS if needed. - * Return: EBX=0: came from user mode; EBX=1: otherwise */ ENTRY(error_entry) UNWIND_HINT_FUNC @@ -1269,7 +1268,6 @@ ENTRY(error_entry) * for these here too. */ .Lerror_kernelspace: - incl %ebx leaq native_irq_return_iret(%rip), %rcx cmpq %rcx, RIP+8(%rsp) je .Lerror_bad_iret @@ -1303,28 +1301,20 @@ ENTRY(error_entry) /* * Pretend that the exception came from user mode: set up pt_regs - * as if we faulted immediately after IRET and clear EBX so that - * error_exit knows that we will be returning to user mode. + * as if we faulted immediately after IRET. */ mov %rsp, %rdi call fixup_bad_iret mov %rax, %rsp - decl %ebx jmp .Lerror_entry_from_usermode_after_swapgs END(error_entry) - -/* - * On entry, EBX is a "return to kernel mode" flag: - * 1: already in kernel mode, don't need SWAPGS - * 0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode - */ ENTRY(error_exit) UNWIND_HINT_REGS DISABLE_INTERRUPTS(CLBR_ANY) TRACE_IRQS_OFF - testl %ebx, %ebx - jnz retint_kernel + testb $3, CS(%rsp) + jz retint_kernel jmp retint_user END(error_exit) diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 4b98101209a1..d50bb4dc0650 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -579,7 +579,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs) { struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu); struct perf_event *event = pcpu->event; - struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event *hwc; struct perf_sample_data data; struct perf_raw_record raw; struct pt_regs regs; @@ -602,6 +602,10 @@ fail: return 0; } + if (WARN_ON_ONCE(!event)) + goto fail; + + hwc = &event->hw; msr = hwc->config_base; buf = ibs_data.regs; rdmsrl(msr, *buf); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 707b2a96e516..86f0c15dcc2d 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2997,6 +2997,9 @@ static int intel_pmu_hw_config(struct perf_event *event) } if (x86_pmu.pebs_aliases) x86_pmu.pebs_aliases(event); + + if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) + event->attr.sample_type |= __PERF_SAMPLE_CALLCHAIN_EARLY; } if (needs_branch_stack(event)) { diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 8cf03f101938..8dbba77e0518 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1186,16 +1186,20 @@ static void setup_pebs_sample_data(struct perf_event *event, } /* + * We must however always use iregs for the unwinder to stay sane; the + * record BP,SP,IP can point into thin air when the record is from a + * previous PMI context or an (I)RET happend between the record and + * PMI. + */ + if (sample_type & PERF_SAMPLE_CALLCHAIN) + data->callchain = perf_callchain(event, iregs); + + /* * We use the interrupt regs as a base because the PEBS record does not * contain a full regs set, specifically it seems to lack segment * descriptors, which get used by things like user_mode(). * * In the simple case fix up only the IP for PERF_SAMPLE_IP. - * - * We must however always use BP,SP from iregs for the unwinder to stay - * sane; the record BP,SP can point into thin air when the record is - * from a previous PMI context or an (I)RET happend between the record - * and PMI. */ *regs = *iregs; @@ -1214,15 +1218,8 @@ static void setup_pebs_sample_data(struct perf_event *event, regs->si = pebs->si; regs->di = pebs->di; - /* - * Per the above; only set BP,SP if we don't need callchains. - * - * XXX: does this make sense? - */ - if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) { - regs->bp = pebs->bp; - regs->sp = pebs->sp; - } + regs->bp = pebs->bp; + regs->sp = pebs->sp; #ifndef CONFIG_X86_32 regs->r8 = pebs->r8; diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index c9e1e0bef3c3..e17ab885b1e9 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -28,7 +28,7 @@ #define UNCORE_PCI_DEV_TYPE(data) ((data >> 8) & 0xff) #define UNCORE_PCI_DEV_IDX(data) (data & 0xff) #define UNCORE_EXTRA_PCI_DEV 0xff -#define UNCORE_EXTRA_PCI_DEV_MAX 3 +#define UNCORE_EXTRA_PCI_DEV_MAX 4 #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff) diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 87dc0263a2e1..51d7c117e3c7 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1029,6 +1029,7 @@ void snbep_uncore_cpu_init(void) enum { SNBEP_PCI_QPI_PORT0_FILTER, SNBEP_PCI_QPI_PORT1_FILTER, + BDX_PCI_QPI_PORT2_FILTER, HSWEP_PCI_PCU_3, }; @@ -3286,15 +3287,18 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = { }, { /* QPI Port 0 filter */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f86), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 0), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT0_FILTER), }, { /* QPI Port 1 filter */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f96), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 1), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT1_FILTER), }, { /* QPI Port 2 filter */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + BDX_PCI_QPI_PORT2_FILTER), }, { /* PCU.3 (for Capability registers) */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0), diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index 023b4a9fc846..5f26962eff42 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -33,6 +33,11 @@ enum irq_remap_cap { IRQ_POSTING_CAP = 0, }; +enum { + IRQ_REMAP_XAPIC_MODE, + IRQ_REMAP_X2APIC_MODE, +}; + struct vcpu_data { u64 pi_desc_addr; /* Physical address of PI Descriptor */ u32 vector; /* Guest vector of the interrupt */ diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h index 9ef5ee03d2d7..159622ee0674 100644 --- a/arch/x86/include/asm/qspinlock_paravirt.h +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -43,7 +43,7 @@ asm (".pushsection .text;" "push %rdx;" "mov $0x1,%eax;" "xor %edx,%edx;" - "lock cmpxchg %dl,(%rdi);" + LOCK_PREFIX "cmpxchg %dl,(%rdi);" "cmp $0x1,%al;" "jne .slowpath;" "pop %rdx;" diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 2aabd4cb0e3f..adbda5847b14 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -573,6 +573,9 @@ static u32 skx_deadline_rev(void) case 0x04: return 0x02000014; } + if (boot_cpu_data.x86_stepping > 4) + return 0; + return ~0U; } diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index ab5d9dd668d2..0acb135de7fb 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -40,8 +40,14 @@ int iommu_detected __read_mostly = 0; * devices and allow every device to access to whole physical memory. This is * useful if a user wants to use an IOMMU only for KVM device assignment to * guests and not for driver dma translation. + * It is also possible to disable by default in kernel config, and enable with + * iommu=nopt at boot time. */ +#ifdef CONFIG_IOMMU_DEFAULT_PASSTHROUGH +int iommu_pass_through __read_mostly = 1; +#else int iommu_pass_through __read_mostly; +#endif extern struct iommu_table_entry __iommu_table[], __iommu_table_end[]; @@ -135,6 +141,8 @@ static __init int iommu_setup(char *p) #endif if (!strncmp(p, "pt", 2)) iommu_pass_through = 1; + if (!strncmp(p, "nopt", 4)) + iommu_pass_through = 0; gart_parse_options(p); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index d594690d8b95..6b8f11521c41 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -890,7 +890,7 @@ static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache, if (cache->nobjs >= min) return 0; while (cache->nobjs < ARRAY_SIZE(cache->objects)) { - page = (void *)__get_free_page(GFP_KERNEL); + page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT); if (!page) return -ENOMEM; cache->objects[cache->nobjs++] = page; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index e30da9a2430c..5d8e317c2b04 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -7893,6 +7893,8 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu) HRTIMER_MODE_REL_PINNED); vmx->nested.preemption_timer.function = vmx_preemption_timer_fn; + vmx->nested.vpid02 = allocate_vpid(); + vmx->nested.vmxon = true; return 0; @@ -8480,21 +8482,20 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) /* Emulate the VMPTRST instruction */ static int handle_vmptrst(struct kvm_vcpu *vcpu) { - unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); - gva_t vmcs_gva; + unsigned long exit_qual = vmcs_readl(EXIT_QUALIFICATION); + u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO); + gpa_t current_vmptr = to_vmx(vcpu)->nested.current_vmptr; struct x86_exception e; + gva_t gva; if (!nested_vmx_check_permission(vcpu)) return 1; - if (get_vmx_mem_address(vcpu, exit_qualification, - vmx_instruction_info, true, &vmcs_gva)) + if (get_vmx_mem_address(vcpu, exit_qual, instr_info, true, &gva)) return 1; /* *_system ok, nested_vmx_check_permission has verified cpl=0 */ - if (kvm_write_guest_virt_system(vcpu, vmcs_gva, - (void *)&to_vmx(vcpu)->nested.current_vmptr, - sizeof(u64), &e)) { + if (kvm_write_guest_virt_system(vcpu, gva, (void *)¤t_vmptr, + sizeof(gpa_t), &e)) { kvm_inject_page_fault(vcpu, &e); return 1; } @@ -10370,11 +10371,9 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) goto free_vmcs; } - if (nested) { + if (nested) nested_vmx_setup_ctls_msrs(&vmx->nested.msrs, kvm_vcpu_apicv_active(&vmx->vcpu)); - vmx->nested.vpid02 = allocate_vpid(); - } vmx->nested.posted_intr_nv = -1; vmx->nested.current_vmptr = -1ull; @@ -10391,7 +10390,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) return &vmx->vcpu; free_vmcs: - free_vpid(vmx->nested.vpid02); free_loaded_vmcs(vmx->loaded_vmcs); free_msrs: kfree(vmx->guest_msrs); diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 55799873ebe5..8f6cc71e0848 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -1441,8 +1441,8 @@ static void emit_prologue(u8 **pprog, u32 stack_depth) /* sub esp,STACK_SIZE */ EMIT2_off32(0x81, 0xEC, STACK_SIZE); - /* sub ebp,SCRATCH_SIZE+4+12*/ - EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 16); + /* sub ebp,SCRATCH_SIZE+12*/ + EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 12); /* xor ebx,ebx */ EMIT2(0x31, add_2reg(0xC0, IA32_EBX, IA32_EBX)); @@ -1475,8 +1475,8 @@ static void emit_epilogue(u8 **pprog, u32 stack_depth) /* mov edx,dword ptr [ebp+off]*/ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(r0[1])); - /* add ebp,SCRATCH_SIZE+4+12*/ - EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 16); + /* add ebp,SCRATCH_SIZE+12*/ + EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 12); /* mov ebx,dword ptr [ebp-12]*/ EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX), -12); diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 77873ce700ae..5f2eb3231607 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -417,7 +417,7 @@ static void __init __map_region(efi_memory_desc_t *md, u64 va) if (!(md->attribute & EFI_MEMORY_WB)) flags |= _PAGE_PCD; - if (sev_active()) + if (sev_active() && md->type != EFI_MEMORY_MAPPED_IO) flags |= _PAGE_ENC; pfn = md->phys_addr >> PAGE_SHIFT; diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c index 744afdc18cf3..56c44d865f7b 100644 --- a/arch/x86/um/mem_32.c +++ b/arch/x86/um/mem_32.c @@ -16,7 +16,7 @@ static int __init gate_vma_init(void) if (!FIXADDR_USER_START) return 0; - gate_vma.vm_mm = NULL; + vma_init(&gate_vma, NULL); gate_vma.vm_start = FIXADDR_USER_START; gate_vma.vm_end = FIXADDR_USER_END; gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; diff --git a/block/bio.c b/block/bio.c index 67eff5eddc49..047c5dca6d90 100644 --- a/block/bio.c +++ b/block/bio.c @@ -903,25 +903,27 @@ int bio_add_page(struct bio *bio, struct page *page, EXPORT_SYMBOL(bio_add_page); /** - * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio + * __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio * @bio: bio to add pages to * @iter: iov iterator describing the region to be mapped * - * Pins as many pages from *iter and appends them to @bio's bvec array. The + * Pins pages from *iter and appends them to @bio's bvec array. The * pages will have to be released using put_page() when done. + * For multi-segment *iter, this function only adds pages from the + * the next non-empty segment of the iov iterator. */ -int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) +static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { - unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt; + unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt, idx; struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt; struct page **pages = (struct page **)bv; - size_t offset, diff; + size_t offset; ssize_t size; size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset); if (unlikely(size <= 0)) return size ? size : -EFAULT; - nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE; + idx = nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE; /* * Deep magic below: We need to walk the pinned pages backwards @@ -934,21 +936,46 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) bio->bi_iter.bi_size += size; bio->bi_vcnt += nr_pages; - diff = (nr_pages * PAGE_SIZE - offset) - size; - while (nr_pages--) { - bv[nr_pages].bv_page = pages[nr_pages]; - bv[nr_pages].bv_len = PAGE_SIZE; - bv[nr_pages].bv_offset = 0; + while (idx--) { + bv[idx].bv_page = pages[idx]; + bv[idx].bv_len = PAGE_SIZE; + bv[idx].bv_offset = 0; } bv[0].bv_offset += offset; bv[0].bv_len -= offset; - if (diff) - bv[bio->bi_vcnt - 1].bv_len -= diff; + bv[nr_pages - 1].bv_len -= nr_pages * PAGE_SIZE - offset - size; iov_iter_advance(iter, size); return 0; } + +/** + * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio + * @bio: bio to add pages to + * @iter: iov iterator describing the region to be mapped + * + * Pins pages from *iter and appends them to @bio's bvec array. The + * pages will have to be released using put_page() when done. + * The function tries, but does not guarantee, to pin as many pages as + * fit into the bio, or are requested in *iter, whatever is smaller. + * If MM encounters an error pinning the requested pages, it stops. + * Error is returned only if 0 pages could be pinned. + */ +int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) +{ + unsigned short orig_vcnt = bio->bi_vcnt; + + do { + int ret = __bio_iov_iter_get_pages(bio, iter); + + if (unlikely(ret)) + return bio->bi_vcnt > orig_vcnt ? 0 : ret; + + } while (iov_iter_count(iter) && !bio_full(bio)); + + return 0; +} EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages); static void submit_bio_wait_endio(struct bio *bio) @@ -1866,6 +1893,7 @@ struct bio *bio_split(struct bio *bio, int sectors, bio_integrity_trim(split); bio_advance(bio, split->bi_iter.bi_size); + bio->bi_iter.bi_done = 0; if (bio_flagged(bio, BIO_TRACE_COMPLETION)) bio_set_flag(split, BIO_TRACE_COMPLETION); diff --git a/block/blk-core.c b/block/blk-core.c index f84a9b7b6f5a..ee33590f54eb 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2155,11 +2155,12 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) if (part->policy && op_is_write(bio_op(bio))) { char b[BDEVNAME_SIZE]; - printk(KERN_ERR + WARN_ONCE(1, "generic_make_request: Trying to write " "to read-only block-device %s (partno %d)\n", bio_devname(bio, b), part->partno); - return true; + /* Older lvm-tools actually trigger this */ + return false; } return false; diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 09b2ee6694fb..3de0836163c2 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -271,7 +271,7 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) * test and set the bit before assining ->rqs[]. */ rq = tags->rqs[bitnr]; - if (rq && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT) + if (rq && blk_mq_request_started(rq)) iter_data->fn(rq, iter_data->data, reserved); return true; diff --git a/block/blk-mq.c b/block/blk-mq.c index 95919268564b..654b0dc7e001 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -558,10 +558,8 @@ static void __blk_mq_complete_request(struct request *rq) bool shared = false; int cpu; - if (cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) != - MQ_RQ_IN_FLIGHT) + if (!blk_mq_mark_complete(rq)) return; - if (rq->internal_tag != -1) blk_mq_sched_completed_request(rq); diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index f8fecfec5df9..9706613eecf9 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -879,6 +879,7 @@ static void acpi_lpss_dismiss(struct device *dev) #define LPSS_GPIODEF0_DMA_LLP BIT(13) static DEFINE_MUTEX(lpss_iosf_mutex); +static bool lpss_iosf_d3_entered; static void lpss_iosf_enter_d3_state(void) { @@ -921,6 +922,9 @@ static void lpss_iosf_enter_d3_state(void) iosf_mbi_modify(LPSS_IOSF_UNIT_LPIOEP, MBI_CR_WRITE, LPSS_IOSF_GPIODEF0, value1, mask1); + + lpss_iosf_d3_entered = true; + exit: mutex_unlock(&lpss_iosf_mutex); } @@ -935,6 +939,11 @@ static void lpss_iosf_exit_d3_state(void) mutex_lock(&lpss_iosf_mutex); + if (!lpss_iosf_d3_entered) + goto exit; + + lpss_iosf_d3_entered = false; + iosf_mbi_modify(LPSS_IOSF_UNIT_LPIOEP, MBI_CR_WRITE, LPSS_IOSF_GPIODEF0, value1, mask1); @@ -944,13 +953,13 @@ static void lpss_iosf_exit_d3_state(void) iosf_mbi_modify(LPSS_IOSF_UNIT_LPIO1, MBI_CFG_WRITE, LPSS_IOSF_PMCSR, value2, mask2); +exit: mutex_unlock(&lpss_iosf_mutex); } -static int acpi_lpss_suspend(struct device *dev, bool runtime) +static int acpi_lpss_suspend(struct device *dev, bool wakeup) { struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev)); - bool wakeup = runtime || device_may_wakeup(dev); int ret; if (pdata->dev_desc->flags & LPSS_SAVE_CTX) @@ -963,14 +972,14 @@ static int acpi_lpss_suspend(struct device *dev, bool runtime) * wrong status for devices being about to be powered off. See * lpss_iosf_enter_d3_state() for further information. */ - if ((runtime || !pm_suspend_via_firmware()) && + if (acpi_target_system_state() == ACPI_STATE_S0 && lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available()) lpss_iosf_enter_d3_state(); return ret; } -static int acpi_lpss_resume(struct device *dev, bool runtime) +static int acpi_lpss_resume(struct device *dev) { struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev)); int ret; @@ -979,8 +988,7 @@ static int acpi_lpss_resume(struct device *dev, bool runtime) * This call is kept first to be in symmetry with * acpi_lpss_runtime_suspend() one. */ - if ((runtime || !pm_resume_via_firmware()) && - lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available()) + if (lpss_quirks & LPSS_QUIRK_ALWAYS_POWER_ON && iosf_mbi_available()) lpss_iosf_exit_d3_state(); ret = acpi_dev_resume(dev); @@ -1004,12 +1012,12 @@ static int acpi_lpss_suspend_late(struct device *dev) return 0; ret = pm_generic_suspend_late(dev); - return ret ? ret : acpi_lpss_suspend(dev, false); + return ret ? ret : acpi_lpss_suspend(dev, device_may_wakeup(dev)); } static int acpi_lpss_resume_early(struct device *dev) { - int ret = acpi_lpss_resume(dev, false); + int ret = acpi_lpss_resume(dev); return ret ? ret : pm_generic_resume_early(dev); } @@ -1024,7 +1032,7 @@ static int acpi_lpss_runtime_suspend(struct device *dev) static int acpi_lpss_runtime_resume(struct device *dev) { - int ret = acpi_lpss_resume(dev, true); + int ret = acpi_lpss_resume(dev); return ret ? ret : pm_generic_runtime_resume(dev); } diff --git a/drivers/acpi/acpica/psloop.c b/drivers/acpi/acpica/psloop.c index bc5f05906bd1..44f35ab3347d 100644 --- a/drivers/acpi/acpica/psloop.c +++ b/drivers/acpi/acpica/psloop.c @@ -497,6 +497,18 @@ acpi_status acpi_ps_parse_loop(struct acpi_walk_state *walk_state) status = acpi_ps_create_op(walk_state, aml_op_start, &op); if (ACPI_FAILURE(status)) { + /* + * ACPI_PARSE_MODULE_LEVEL means that we are loading a table by + * executing it as a control method. However, if we encounter + * an error while loading the table, we need to keep trying to + * load the table rather than aborting the table load. Set the + * status to AE_OK to proceed with the table load. + */ + if ((walk_state-> + parse_flags & ACPI_PARSE_MODULE_LEVEL) + && status == AE_ALREADY_EXISTS) { + status = AE_OK; + } if (status == AE_CTRL_PARSE_CONTINUE) { continue; } @@ -694,6 +706,25 @@ acpi_status acpi_ps_parse_loop(struct acpi_walk_state *walk_state) acpi_ps_next_parse_state(walk_state, op, status); if (status == AE_CTRL_PENDING) { status = AE_OK; + } else + if ((walk_state-> + parse_flags & ACPI_PARSE_MODULE_LEVEL) + && status != AE_CTRL_TRANSFER + && ACPI_FAILURE(status)) { + /* + * ACPI_PARSE_MODULE_LEVEL flag means that we are currently + * loading a table by executing it as a control method. + * However, if we encounter an error while loading the table, + * we need to keep trying to load the table rather than + * aborting the table load (setting the status to AE_OK + * continues the table load). If we get a failure at this + * point, it means that the dispatcher got an error while + * processing Op (most likely an AML operand error) or a + * control method was called from module level and the + * dispatcher returned AE_CTRL_TRANSFER. In the latter case, + * leave the status alone, there's nothing wrong with it. + */ + status = AE_OK; } } diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 1435d7281c66..6ebcd65d64b6 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -434,14 +434,6 @@ re_probe: goto probe_failed; } - /* - * Ensure devices are listed in devices_kset in correct order - * It's important to move Dev to the end of devices_kset before - * calling .probe, because it could be recursive and parent Dev - * should always go first - */ - devices_kset_move_last(dev); - if (dev->bus->probe) { ret = dev->bus->probe(dev); if (ret) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 74a05561b620..3fb95c8d9fd8 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -112,12 +112,16 @@ struct nbd_device { struct task_struct *task_setup; }; +#define NBD_CMD_REQUEUED 1 + struct nbd_cmd { struct nbd_device *nbd; + struct mutex lock; int index; int cookie; - struct completion send_complete; blk_status_t status; + unsigned long flags; + u32 cmd_cookie; }; #if IS_ENABLED(CONFIG_DEBUG_FS) @@ -146,6 +150,35 @@ static inline struct device *nbd_to_dev(struct nbd_device *nbd) return disk_to_dev(nbd->disk); } +static void nbd_requeue_cmd(struct nbd_cmd *cmd) +{ + struct request *req = blk_mq_rq_from_pdu(cmd); + + if (!test_and_set_bit(NBD_CMD_REQUEUED, &cmd->flags)) + blk_mq_requeue_request(req, true); +} + +#define NBD_COOKIE_BITS 32 + +static u64 nbd_cmd_handle(struct nbd_cmd *cmd) +{ + struct request *req = blk_mq_rq_from_pdu(cmd); + u32 tag = blk_mq_unique_tag(req); + u64 cookie = cmd->cmd_cookie; + + return (cookie << NBD_COOKIE_BITS) | tag; +} + +static u32 nbd_handle_to_tag(u64 handle) +{ + return (u32)handle; +} + +static u32 nbd_handle_to_cookie(u64 handle) +{ + return (u32)(handle >> NBD_COOKIE_BITS); +} + static const char *nbdcmd_to_ascii(int cmd) { switch (cmd) { @@ -319,6 +352,9 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, } config = nbd->config; + if (!mutex_trylock(&cmd->lock)) + return BLK_EH_RESET_TIMER; + if (config->num_connections > 1) { dev_err_ratelimited(nbd_to_dev(nbd), "Connection timed out, retrying (%d/%d alive)\n", @@ -343,7 +379,8 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, nbd_mark_nsock_dead(nbd, nsock, 1); mutex_unlock(&nsock->tx_lock); } - blk_mq_requeue_request(req, true); + mutex_unlock(&cmd->lock); + nbd_requeue_cmd(cmd); nbd_config_put(nbd); return BLK_EH_DONE; } @@ -353,6 +390,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, } set_bit(NBD_TIMEDOUT, &config->runtime_flags); cmd->status = BLK_STS_IOERR; + mutex_unlock(&cmd->lock); sock_shutdown(nbd); nbd_config_put(nbd); done: @@ -430,9 +468,9 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) struct iov_iter from; unsigned long size = blk_rq_bytes(req); struct bio *bio; + u64 handle; u32 type; u32 nbd_cmd_flags = 0; - u32 tag = blk_mq_unique_tag(req); int sent = nsock->sent, skip = 0; iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request)); @@ -474,6 +512,8 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) goto send_pages; } iov_iter_advance(&from, sent); + } else { + cmd->cmd_cookie++; } cmd->index = index; cmd->cookie = nsock->cookie; @@ -482,7 +522,8 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9); request.len = htonl(size); } - memcpy(request.handle, &tag, sizeof(tag)); + handle = nbd_cmd_handle(cmd); + memcpy(request.handle, &handle, sizeof(handle)); dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n", req, nbdcmd_to_ascii(type), @@ -500,6 +541,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) nsock->pending = req; nsock->sent = sent; } + set_bit(NBD_CMD_REQUEUED, &cmd->flags); return BLK_STS_RESOURCE; } dev_err_ratelimited(disk_to_dev(nbd->disk), @@ -541,6 +583,7 @@ send_pages: */ nsock->pending = req; nsock->sent = sent; + set_bit(NBD_CMD_REQUEUED, &cmd->flags); return BLK_STS_RESOURCE; } dev_err(disk_to_dev(nbd->disk), @@ -573,10 +616,12 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) struct nbd_reply reply; struct nbd_cmd *cmd; struct request *req = NULL; + u64 handle; u16 hwq; u32 tag; struct kvec iov = {.iov_base = &reply, .iov_len = sizeof(reply)}; struct iov_iter to; + int ret = 0; reply.magic = 0; iov_iter_kvec(&to, READ | ITER_KVEC, &iov, 1, sizeof(reply)); @@ -594,8 +639,8 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) return ERR_PTR(-EPROTO); } - memcpy(&tag, reply.handle, sizeof(u32)); - + memcpy(&handle, reply.handle, sizeof(handle)); + tag = nbd_handle_to_tag(handle); hwq = blk_mq_unique_tag_to_hwq(tag); if (hwq < nbd->tag_set.nr_hw_queues) req = blk_mq_tag_to_rq(nbd->tag_set.tags[hwq], @@ -606,11 +651,25 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) return ERR_PTR(-ENOENT); } cmd = blk_mq_rq_to_pdu(req); + + mutex_lock(&cmd->lock); + if (cmd->cmd_cookie != nbd_handle_to_cookie(handle)) { + dev_err(disk_to_dev(nbd->disk), "Double reply on req %p, cmd_cookie %u, handle cookie %u\n", + req, cmd->cmd_cookie, nbd_handle_to_cookie(handle)); + ret = -ENOENT; + goto out; + } + if (test_bit(NBD_CMD_REQUEUED, &cmd->flags)) { + dev_err(disk_to_dev(nbd->disk), "Raced with timeout on req %p\n", + req); + ret = -ENOENT; + goto out; + } if (ntohl(reply.error)) { dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n", ntohl(reply.error)); cmd->status = BLK_STS_IOERR; - return cmd; + goto out; } dev_dbg(nbd_to_dev(nbd), "request %p: got reply\n", req); @@ -635,18 +694,18 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) if (nbd_disconnected(config) || config->num_connections <= 1) { cmd->status = BLK_STS_IOERR; - return cmd; + goto out; } - return ERR_PTR(-EIO); + ret = -EIO; + goto out; } dev_dbg(nbd_to_dev(nbd), "request %p: got %d bytes data\n", req, bvec.bv_len); } - } else { - /* See the comment in nbd_queue_rq. */ - wait_for_completion(&cmd->send_complete); } - return cmd; +out: + mutex_unlock(&cmd->lock); + return ret ? ERR_PTR(ret) : cmd; } static void recv_work(struct work_struct *work) @@ -805,7 +864,7 @@ again: */ blk_mq_start_request(req); if (unlikely(nsock->pending && nsock->pending != req)) { - blk_mq_requeue_request(req, true); + nbd_requeue_cmd(cmd); ret = 0; goto out; } @@ -818,7 +877,7 @@ again: dev_err_ratelimited(disk_to_dev(nbd->disk), "Request send failed, requeueing\n"); nbd_mark_nsock_dead(nbd, nsock, 1); - blk_mq_requeue_request(req, true); + nbd_requeue_cmd(cmd); ret = 0; } out: @@ -842,7 +901,8 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, * that the server is misbehaving (or there was an error) before we're * done sending everything over the wire. */ - init_completion(&cmd->send_complete); + mutex_lock(&cmd->lock); + clear_bit(NBD_CMD_REQUEUED, &cmd->flags); /* We can be called directly from the user space process, which means we * could possibly have signals pending so our sendmsg will fail. In @@ -854,7 +914,7 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, ret = BLK_STS_IOERR; else if (!ret) ret = BLK_STS_OK; - complete(&cmd->send_complete); + mutex_unlock(&cmd->lock); return ret; } @@ -1460,6 +1520,8 @@ static int nbd_init_request(struct blk_mq_tag_set *set, struct request *rq, { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(rq); cmd->nbd = set->driver_data; + cmd->flags = 0; + mutex_init(&cmd->lock); return 0; } diff --git a/drivers/char/mem.c b/drivers/char/mem.c index ffeb60d3434c..df66a9dd0aae 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -708,6 +708,7 @@ static int mmap_zero(struct file *file, struct vm_area_struct *vma) #endif if (vma->vm_flags & VM_SHARED) return shmem_zero_setup(vma); + vma_set_anonymous(vma); return 0; } diff --git a/drivers/char/random.c b/drivers/char/random.c index cd888d4ee605..bd449ad52442 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1895,14 +1895,22 @@ static int write_pool(struct entropy_store *r, const char __user *buffer, size_t count) { size_t bytes; - __u32 buf[16]; + __u32 t, buf[16]; const char __user *p = buffer; while (count > 0) { + int b, i = 0; + bytes = min(count, sizeof(buf)); if (copy_from_user(&buf, p, bytes)) return -EFAULT; + for (b = bytes ; b > 0 ; b -= sizeof(__u32), i++) { + if (!arch_get_random_int(&t)) + break; + buf[i] ^= t; + } + count -= bytes; p += bytes; diff --git a/drivers/clk/clk-aspeed.c b/drivers/clk/clk-aspeed.c index 38b366b00c57..7b70a074095d 100644 --- a/drivers/clk/clk-aspeed.c +++ b/drivers/clk/clk-aspeed.c @@ -24,7 +24,7 @@ #define ASPEED_MPLL_PARAM 0x20 #define ASPEED_HPLL_PARAM 0x24 #define AST2500_HPLL_BYPASS_EN BIT(20) -#define AST2400_HPLL_STRAPPED BIT(18) +#define AST2400_HPLL_PROGRAMMED BIT(18) #define AST2400_HPLL_BYPASS_EN BIT(17) #define ASPEED_MISC_CTRL 0x2c #define UART_DIV13_EN BIT(12) @@ -91,8 +91,8 @@ static const struct aspeed_gate_data aspeed_gates[] = { [ASPEED_CLK_GATE_GCLK] = { 1, 7, "gclk-gate", NULL, 0 }, /* 2D engine */ [ASPEED_CLK_GATE_MCLK] = { 2, -1, "mclk-gate", "mpll", CLK_IS_CRITICAL }, /* SDRAM */ [ASPEED_CLK_GATE_VCLK] = { 3, 6, "vclk-gate", NULL, 0 }, /* Video Capture */ - [ASPEED_CLK_GATE_BCLK] = { 4, 8, "bclk-gate", "bclk", 0 }, /* PCIe/PCI */ - [ASPEED_CLK_GATE_DCLK] = { 5, -1, "dclk-gate", NULL, 0 }, /* DAC */ + [ASPEED_CLK_GATE_BCLK] = { 4, 8, "bclk-gate", "bclk", CLK_IS_CRITICAL }, /* PCIe/PCI */ + [ASPEED_CLK_GATE_DCLK] = { 5, -1, "dclk-gate", NULL, CLK_IS_CRITICAL }, /* DAC */ [ASPEED_CLK_GATE_REFCLK] = { 6, -1, "refclk-gate", "clkin", CLK_IS_CRITICAL }, [ASPEED_CLK_GATE_USBPORT2CLK] = { 7, 3, "usb-port2-gate", NULL, 0 }, /* USB2.0 Host port 2 */ [ASPEED_CLK_GATE_LCLK] = { 8, 5, "lclk-gate", NULL, 0 }, /* LPC */ @@ -212,9 +212,22 @@ static int aspeed_clk_is_enabled(struct clk_hw *hw) { struct aspeed_clk_gate *gate = to_aspeed_clk_gate(hw); u32 clk = BIT(gate->clock_idx); + u32 rst = BIT(gate->reset_idx); u32 enval = (gate->flags & CLK_GATE_SET_TO_DISABLE) ? 0 : clk; u32 reg; + /* + * If the IP is in reset, treat the clock as not enabled, + * this happens with some clocks such as the USB one when + * coming from cold reset. Without this, aspeed_clk_enable() + * will fail to lift the reset. + */ + if (gate->reset_idx >= 0) { + regmap_read(gate->map, ASPEED_RESET_CTRL, ®); + if (reg & rst) + return 0; + } + regmap_read(gate->map, ASPEED_CLK_STOP_CTRL, ®); return ((reg & clk) == enval) ? 1 : 0; @@ -565,29 +578,45 @@ builtin_platform_driver(aspeed_clk_driver); static void __init aspeed_ast2400_cc(struct regmap *map) { struct clk_hw *hw; - u32 val, freq, div; + u32 val, div, clkin, hpll; + const u16 hpll_rates[][4] = { + {384, 360, 336, 408}, + {400, 375, 350, 425}, + }; + int rate; /* * CLKIN is the crystal oscillator, 24, 48 or 25MHz selected by * strapping */ regmap_read(map, ASPEED_STRAP, &val); - if (val & CLKIN_25MHZ_EN) - freq = 25000000; - else if (val & AST2400_CLK_SOURCE_SEL) - freq = 48000000; - else - freq = 24000000; - hw = clk_hw_register_fixed_rate(NULL, "clkin", NULL, 0, freq); - pr_debug("clkin @%u MHz\n", freq / 1000000); + rate = (val >> 8) & 3; + if (val & CLKIN_25MHZ_EN) { + clkin = 25000000; + hpll = hpll_rates[1][rate]; + } else if (val & AST2400_CLK_SOURCE_SEL) { + clkin = 48000000; + hpll = hpll_rates[0][rate]; + } else { + clkin = 24000000; + hpll = hpll_rates[0][rate]; + } + hw = clk_hw_register_fixed_rate(NULL, "clkin", NULL, 0, clkin); + pr_debug("clkin @%u MHz\n", clkin / 1000000); /* * High-speed PLL clock derived from the crystal. This the CPU clock, - * and we assume that it is enabled + * and we assume that it is enabled. It can be configured through the + * HPLL_PARAM register, or set to a specified frequency by strapping. */ regmap_read(map, ASPEED_HPLL_PARAM, &val); - WARN(val & AST2400_HPLL_STRAPPED, "hpll is strapped not configured"); - aspeed_clk_data->hws[ASPEED_CLK_HPLL] = aspeed_ast2400_calc_pll("hpll", val); + if (val & AST2400_HPLL_PROGRAMMED) + hw = aspeed_ast2400_calc_pll("hpll", val); + else + hw = clk_hw_register_fixed_rate(NULL, "hpll", "clkin", 0, + hpll * 1000000); + + aspeed_clk_data->hws[ASPEED_CLK_HPLL] = hw; /* * Strap bits 11:10 define the CPU/AHB clock frequency ratio (aka HCLK) diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 9760b526ca31..e2ed078abd90 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -24,7 +24,6 @@ #include <linux/pm_runtime.h> #include <linux/sched.h> #include <linux/clkdev.h> -#include <linux/stringify.h> #include "clk.h" @@ -2559,7 +2558,7 @@ static const struct { unsigned long flag; const char *name; } clk_flags[] = { -#define ENTRY(f) { f, __stringify(f) } +#define ENTRY(f) { f, #f } ENTRY(CLK_SET_RATE_GATE), ENTRY(CLK_SET_PARENT_GATE), ENTRY(CLK_SET_RATE_PARENT), diff --git a/drivers/clk/meson/clk-audio-divider.c b/drivers/clk/meson/clk-audio-divider.c index 58f546e04807..e4cf96ba704e 100644 --- a/drivers/clk/meson/clk-audio-divider.c +++ b/drivers/clk/meson/clk-audio-divider.c @@ -51,7 +51,7 @@ static unsigned long audio_divider_recalc_rate(struct clk_hw *hw, struct meson_clk_audio_div_data *adiv = meson_clk_audio_div_data(clk); unsigned long divider; - divider = meson_parm_read(clk->map, &adiv->div); + divider = meson_parm_read(clk->map, &adiv->div) + 1; return DIV_ROUND_UP_ULL((u64)parent_rate, divider); } diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c index 240658404367..177fffb9ebef 100644 --- a/drivers/clk/meson/gxbb.c +++ b/drivers/clk/meson/gxbb.c @@ -498,6 +498,7 @@ static struct clk_regmap gxbb_fclk_div2 = { .ops = &clk_regmap_gate_ops, .parent_names = (const char *[]){ "fclk_div2_div" }, .num_parents = 1, + .flags = CLK_IS_CRITICAL, }, }; diff --git a/drivers/clk/mvebu/armada-37xx-periph.c b/drivers/clk/mvebu/armada-37xx-periph.c index 6860bd5a37c5..44e4e27eddad 100644 --- a/drivers/clk/mvebu/armada-37xx-periph.c +++ b/drivers/clk/mvebu/armada-37xx-periph.c @@ -35,6 +35,7 @@ #define CLK_SEL 0x10 #define CLK_DIS 0x14 +#define ARMADA_37XX_DVFS_LOAD_1 1 #define LOAD_LEVEL_NR 4 #define ARMADA_37XX_NB_L0L1 0x18 @@ -507,6 +508,40 @@ static long clk_pm_cpu_round_rate(struct clk_hw *hw, unsigned long rate, return -EINVAL; } +/* + * Switching the CPU from the L2 or L3 frequencies (300 and 200 Mhz + * respectively) to L0 frequency (1.2 Ghz) requires a significant + * amount of time to let VDD stabilize to the appropriate + * voltage. This amount of time is large enough that it cannot be + * covered by the hardware countdown register. Due to this, the CPU + * might start operating at L0 before the voltage is stabilized, + * leading to CPU stalls. + * + * To work around this problem, we prevent switching directly from the + * L2/L3 frequencies to the L0 frequency, and instead switch to the L1 + * frequency in-between. The sequence therefore becomes: + * 1. First switch from L2/L3(200/300MHz) to L1(600MHZ) + * 2. Sleep 20ms for stabling VDD voltage + * 3. Then switch from L1(600MHZ) to L0(1200Mhz). + */ +static void clk_pm_cpu_set_rate_wa(unsigned long rate, struct regmap *base) +{ + unsigned int cur_level; + + if (rate != 1200 * 1000 * 1000) + return; + + regmap_read(base, ARMADA_37XX_NB_CPU_LOAD, &cur_level); + cur_level &= ARMADA_37XX_NB_CPU_LOAD_MASK; + if (cur_level <= ARMADA_37XX_DVFS_LOAD_1) + return; + + regmap_update_bits(base, ARMADA_37XX_NB_CPU_LOAD, + ARMADA_37XX_NB_CPU_LOAD_MASK, + ARMADA_37XX_DVFS_LOAD_1); + msleep(20); +} + static int clk_pm_cpu_set_rate(struct clk_hw *hw, unsigned long rate, unsigned long parent_rate) { @@ -537,6 +572,9 @@ static int clk_pm_cpu_set_rate(struct clk_hw *hw, unsigned long rate, */ reg = ARMADA_37XX_NB_CPU_LOAD; mask = ARMADA_37XX_NB_CPU_LOAD_MASK; + + clk_pm_cpu_set_rate_wa(rate, base); + regmap_update_bits(base, reg, mask, load_level); return rate; diff --git a/drivers/clk/qcom/gcc-msm8996.c b/drivers/clk/qcom/gcc-msm8996.c index 9f35b3fe1d97..ff8d66fd94e6 100644 --- a/drivers/clk/qcom/gcc-msm8996.c +++ b/drivers/clk/qcom/gcc-msm8996.c @@ -2781,6 +2781,7 @@ static struct clk_branch gcc_ufs_rx_cfg_clk = { static struct clk_branch gcc_ufs_tx_symbol_0_clk = { .halt_reg = 0x75018, + .halt_check = BRANCH_HALT_SKIP, .clkr = { .enable_reg = 0x75018, .enable_mask = BIT(0), diff --git a/drivers/clk/qcom/mmcc-msm8996.c b/drivers/clk/qcom/mmcc-msm8996.c index 1a25ee4f3658..4b20d1b67a1b 100644 --- a/drivers/clk/qcom/mmcc-msm8996.c +++ b/drivers/clk/qcom/mmcc-msm8996.c @@ -2910,6 +2910,7 @@ static struct gdsc mmagic_bimc_gdsc = { .name = "mmagic_bimc", }, .pwrsts = PWRSTS_OFF_ON, + .flags = ALWAYS_ON, }; static struct gdsc mmagic_video_gdsc = { diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 3c3971256130..d4ed0022b0dd 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -311,12 +311,20 @@ static DEFINE_MUTEX(intel_pstate_limits_lock); #ifdef CONFIG_ACPI -static bool intel_pstate_get_ppc_enable_status(void) +static bool intel_pstate_acpi_pm_profile_server(void) { if (acpi_gbl_FADT.preferred_profile == PM_ENTERPRISE_SERVER || acpi_gbl_FADT.preferred_profile == PM_PERFORMANCE_SERVER) return true; + return false; +} + +static bool intel_pstate_get_ppc_enable_status(void) +{ + if (intel_pstate_acpi_pm_profile_server()) + return true; + return acpi_ppc; } @@ -459,6 +467,11 @@ static inline void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *pol static inline void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy) { } + +static inline bool intel_pstate_acpi_pm_profile_server(void) +{ + return false; +} #endif static inline void update_turbo_state(void) @@ -1841,7 +1854,7 @@ static int intel_pstate_init_cpu(unsigned int cpunum) intel_pstate_hwp_enable(cpu); id = x86_match_cpu(intel_pstate_hwp_boost_ids); - if (id) + if (id && intel_pstate_acpi_pm_profile_server()) hwp_boost = true; } diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c index 29389accf3e9..efc9a7ae4857 100644 --- a/drivers/cpufreq/qcom-cpufreq-kryo.c +++ b/drivers/cpufreq/qcom-cpufreq-kryo.c @@ -183,6 +183,7 @@ static struct platform_driver qcom_cpufreq_kryo_driver = { static const struct of_device_id qcom_cpufreq_kryo_match_list[] __initconst = { { .compatible = "qcom,apq8096", }, { .compatible = "qcom,msm8996", }, + {} }; /* diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c index 1c6cbda56afe..09d823d36d3a 100644 --- a/drivers/crypto/padlock-aes.c +++ b/drivers/crypto/padlock-aes.c @@ -266,6 +266,8 @@ static inline void padlock_xcrypt_ecb(const u8 *input, u8 *output, void *key, return; } + count -= initial; + if (initial) asm volatile (".byte 0xf3,0x0f,0xa7,0xc8" /* rep xcryptecb */ : "+S"(input), "+D"(output) @@ -273,7 +275,7 @@ static inline void padlock_xcrypt_ecb(const u8 *input, u8 *output, void *key, asm volatile (".byte 0xf3,0x0f,0xa7,0xc8" /* rep xcryptecb */ : "+S"(input), "+D"(output) - : "d"(control_word), "b"(key), "c"(count - initial)); + : "d"(control_word), "b"(key), "c"(count)); } static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key, @@ -284,6 +286,8 @@ static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key, if (count < cbc_fetch_blocks) return cbc_crypt(input, output, key, iv, control_word, count); + count -= initial; + if (initial) asm volatile (".byte 0xf3,0x0f,0xa7,0xd0" /* rep xcryptcbc */ : "+S" (input), "+D" (output), "+a" (iv) @@ -291,7 +295,7 @@ static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key, asm volatile (".byte 0xf3,0x0f,0xa7,0xd0" /* rep xcryptcbc */ : "+S" (input), "+D" (output), "+a" (iv) - : "d" (control_word), "b" (key), "c" (count-initial)); + : "d" (control_word), "b" (key), "c" (count)); return iv; } diff --git a/drivers/gpio/gpio-uniphier.c b/drivers/gpio/gpio-uniphier.c index d3cf9502e7e7..58faeb1cef63 100644 --- a/drivers/gpio/gpio-uniphier.c +++ b/drivers/gpio/gpio-uniphier.c @@ -181,7 +181,11 @@ static int uniphier_gpio_to_irq(struct gpio_chip *chip, unsigned int offset) fwspec.fwnode = of_node_to_fwnode(chip->parent->of_node); fwspec.param_count = 2; fwspec.param[0] = offset - UNIPHIER_GPIO_IRQ_OFFSET; - fwspec.param[1] = IRQ_TYPE_NONE; + /* + * IRQ_TYPE_NONE is rejected by the parent irq domain. Set LEVEL_HIGH + * temporarily. Anyway, ->irq_set_type() will override it later. + */ + fwspec.param[1] = IRQ_TYPE_LEVEL_HIGH; return irq_create_fwspec_mapping(&fwspec); } diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index 28d968088131..53a14ee8ad6d 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -64,7 +64,8 @@ static void of_gpio_flags_quirks(struct device_node *np, * Note that active low is the default. */ if (IS_ENABLED(CONFIG_REGULATOR) && - (of_device_is_compatible(np, "reg-fixed-voltage") || + (of_device_is_compatible(np, "regulator-fixed") || + of_device_is_compatible(np, "reg-fixed-voltage") || of_device_is_compatible(np, "regulator-gpio"))) { /* * The regulator GPIO handles are specified such that the diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index 73021b388e12..dd3ff2f2cdce 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -429,6 +429,18 @@ static void adv7511_hpd_work(struct work_struct *work) else status = connector_status_disconnected; + /* + * The bridge resets its registers on unplug. So when we get a plug + * event and we're already supposed to be powered, cycle the bridge to + * restore its state. + */ + if (status == connector_status_connected && + adv7511->connector.status == connector_status_disconnected && + adv7511->powered) { + regcache_mark_dirty(adv7511->regmap); + adv7511_power_on(adv7511); + } + if (adv7511->connector.status != status) { adv7511->connector.status = status; if (status == connector_status_disconnected) diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 130da5195f3b..81e32199d3ef 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -1510,8 +1510,9 @@ int drm_atomic_helper_async_check(struct drm_device *dev, { struct drm_crtc *crtc; struct drm_crtc_state *crtc_state; - struct drm_plane *plane; - struct drm_plane_state *old_plane_state, *new_plane_state; + struct drm_plane *plane = NULL; + struct drm_plane_state *old_plane_state = NULL; + struct drm_plane_state *new_plane_state = NULL; const struct drm_plane_helper_funcs *funcs; int i, n_planes = 0; @@ -1527,7 +1528,8 @@ int drm_atomic_helper_async_check(struct drm_device *dev, if (n_planes != 1) return -EINVAL; - if (!new_plane_state->crtc) + if (!new_plane_state->crtc || + old_plane_state->crtc != new_plane_state->crtc) return -EINVAL; funcs = plane->helper_private; diff --git a/drivers/gpu/drm/drm_context.c b/drivers/gpu/drm/drm_context.c index 3c4000facb36..f973d287696a 100644 --- a/drivers/gpu/drm/drm_context.c +++ b/drivers/gpu/drm/drm_context.c @@ -372,7 +372,7 @@ int drm_legacy_addctx(struct drm_device *dev, void *data, ctx->handle = drm_legacy_ctxbitmap_next(dev); } DRM_DEBUG("%d\n", ctx->handle); - if (ctx->handle == -1) { + if (ctx->handle < 0) { DRM_DEBUG("Not enough free contexts.\n"); /* Should this return -EBUSY instead? */ return -ENOMEM; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 52f3b91d14fd..71e1aa54f774 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -652,6 +652,7 @@ enum intel_sbi_destination { #define QUIRK_BACKLIGHT_PRESENT (1<<3) #define QUIRK_PIN_SWIZZLED_PAGES (1<<5) #define QUIRK_INCREASE_T12_DELAY (1<<6) +#define QUIRK_INCREASE_DDI_DISABLED_TIME (1<<7) struct intel_fbdev; struct intel_fbc_work; diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index f4a8598a2d39..fed26d6e4e27 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1782,15 +1782,24 @@ void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state) I915_WRITE(TRANS_DDI_FUNC_CTL(cpu_transcoder), temp); } -void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv, - enum transcoder cpu_transcoder) +void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state) { + struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc); + struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); + enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; i915_reg_t reg = TRANS_DDI_FUNC_CTL(cpu_transcoder); uint32_t val = I915_READ(reg); val &= ~(TRANS_DDI_FUNC_ENABLE | TRANS_DDI_PORT_MASK | TRANS_DDI_DP_VC_PAYLOAD_ALLOC); val |= TRANS_DDI_PORT_NONE; I915_WRITE(reg, val); + + if (dev_priv->quirks & QUIRK_INCREASE_DDI_DISABLED_TIME && + intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) { + DRM_DEBUG_KMS("Quirk Increase DDI disabled time\n"); + /* Quirk time at 100ms for reliable operation */ + msleep(100); + } } int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder, diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 2cc6faa1daa8..dec0d60921bf 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -5809,7 +5809,7 @@ static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state, intel_ddi_set_vc_payload_alloc(intel_crtc->config, false); if (!transcoder_is_dsi(cpu_transcoder)) - intel_ddi_disable_transcoder_func(dev_priv, cpu_transcoder); + intel_ddi_disable_transcoder_func(old_crtc_state); if (INTEL_GEN(dev_priv) >= 9) skylake_scaler_disable(intel_crtc); @@ -14646,6 +14646,18 @@ static void quirk_increase_t12_delay(struct drm_device *dev) DRM_INFO("Applying T12 delay quirk\n"); } +/* + * GeminiLake NUC HDMI outputs require additional off time + * this allows the onboard retimer to correctly sync to signal + */ +static void quirk_increase_ddi_disabled_time(struct drm_device *dev) +{ + struct drm_i915_private *dev_priv = to_i915(dev); + + dev_priv->quirks |= QUIRK_INCREASE_DDI_DISABLED_TIME; + DRM_INFO("Applying Increase DDI Disabled quirk\n"); +} + struct intel_quirk { int device; int subsystem_vendor; @@ -14732,6 +14744,13 @@ static struct intel_quirk intel_quirks[] = { /* Toshiba Satellite P50-C-18C */ { 0x191B, 0x1179, 0xF840, quirk_increase_t12_delay }, + + /* GeminiLake NUC */ + { 0x3185, 0x8086, 0x2072, quirk_increase_ddi_disabled_time }, + { 0x3184, 0x8086, 0x2072, quirk_increase_ddi_disabled_time }, + /* ASRock ITX*/ + { 0x3185, 0x1849, 0x2212, quirk_increase_ddi_disabled_time }, + { 0x3184, 0x1849, 0x2212, quirk_increase_ddi_disabled_time }, }; static void intel_init_quirks(struct drm_device *dev) diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index 0361130500a6..b8eefbffc77d 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -1388,8 +1388,7 @@ void hsw_fdi_link_train(struct intel_crtc *crtc, void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port); bool intel_ddi_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe); void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state); -void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv, - enum transcoder cpu_transcoder); +void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state); void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state); void intel_ddi_disable_pipe_clock(const struct intel_crtc_state *crtc_state); struct intel_encoder * diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index 56dd7a9a8e25..dd5312b02a8d 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -612,6 +612,9 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) return PTR_ERR(imx_ldb->regmap); } + /* disable LDB by resetting the control register to POR default */ + regmap_write(imx_ldb->regmap, IOMUXC_GPR2, 0); + imx_ldb->dev = dev; if (of_id) @@ -652,14 +655,14 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) if (ret || i < 0 || i > 1) return -EINVAL; + if (!of_device_is_available(child)) + continue; + if (dual && i > 0) { dev_warn(dev, "dual-channel mode, ignoring second output\n"); continue; } - if (!of_device_is_available(child)) - continue; - channel = &imx_ldb->channel[i]; channel->ldb = imx_ldb; channel->chno = i; diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index 1d34619eb3fe..a951ec75d01f 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -320,6 +320,9 @@ static int vc4_plane_setup_clipping_and_scaling(struct drm_plane_state *state) vc4_state->x_scaling[0] = VC4_SCALING_TPZ; if (vc4_state->y_scaling[0] == VC4_SCALING_NONE) vc4_state->y_scaling[0] = VC4_SCALING_TPZ; + } else { + vc4_state->x_scaling[1] = VC4_SCALING_NONE; + vc4_state->y_scaling[1] = VC4_SCALING_NONE; } vc4_state->is_unity = (vc4_state->x_scaling[0] == VC4_SCALING_NONE && diff --git a/drivers/gpu/ipu-v3/ipu-csi.c b/drivers/gpu/ipu-v3/ipu-csi.c index caa05b0702e1..5450a2db1219 100644 --- a/drivers/gpu/ipu-v3/ipu-csi.c +++ b/drivers/gpu/ipu-v3/ipu-csi.c @@ -339,7 +339,8 @@ static void fill_csi_bus_cfg(struct ipu_csi_bus_config *csicfg, break; case V4L2_MBUS_BT656: csicfg->ext_vsync = 0; - if (V4L2_FIELD_HAS_BOTH(mbus_fmt->field)) + if (V4L2_FIELD_HAS_BOTH(mbus_fmt->field) || + mbus_fmt->field == V4L2_FIELD_ALTERNATE) csicfg->clk_mode = IPU_CSI_CLK_MODE_CCIR656_INTERLACED; else csicfg->clk_mode = IPU_CSI_CLK_MODE_CCIR656_PROGRESSIVE; diff --git a/drivers/i2c/busses/i2c-davinci.c b/drivers/i2c/busses/i2c-davinci.c index 75d6ab177055..7379043711df 100644 --- a/drivers/i2c/busses/i2c-davinci.c +++ b/drivers/i2c/busses/i2c-davinci.c @@ -237,12 +237,16 @@ static void i2c_davinci_calc_clk_dividers(struct davinci_i2c_dev *dev) /* * It's not always possible to have 1 to 2 ratio when d=7, so fall back * to minimal possible clkh in this case. + * + * Note: + * CLKH is not allowed to be 0, in this case I2C clock is not generated + * at all */ - if (clk >= clkl + d) { + if (clk > clkl + d) { clkh = clk - clkl - d; clkl -= d; } else { - clkh = 0; + clkh = 1; clkl = clk - (d << 1); } diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c index 0207e194f84b..498c5e891649 100644 --- a/drivers/i2c/busses/i2c-imx.c +++ b/drivers/i2c/busses/i2c-imx.c @@ -368,6 +368,7 @@ static int i2c_imx_dma_xfer(struct imx_i2c_struct *i2c_imx, goto err_desc; } + reinit_completion(&dma->cmd_complete); txdesc->callback = i2c_imx_dma_callback; txdesc->callback_param = i2c_imx; if (dma_submit_error(dmaengine_submit(txdesc))) { @@ -622,7 +623,6 @@ static int i2c_imx_dma_write(struct imx_i2c_struct *i2c_imx, * The first byte must be transmitted by the CPU. */ imx_i2c_write_reg(i2c_8bit_addr_from_msg(msgs), i2c_imx, IMX_I2C_I2DR); - reinit_completion(&i2c_imx->dma->cmd_complete); time_left = wait_for_completion_timeout( &i2c_imx->dma->cmd_complete, msecs_to_jiffies(DMA_TIMEOUT)); @@ -681,7 +681,6 @@ static int i2c_imx_dma_read(struct imx_i2c_struct *i2c_imx, if (result) return result; - reinit_completion(&i2c_imx->dma->cmd_complete); time_left = wait_for_completion_timeout( &i2c_imx->dma->cmd_complete, msecs_to_jiffies(DMA_TIMEOUT)); @@ -1010,7 +1009,7 @@ static int i2c_imx_init_recovery_info(struct imx_i2c_struct *i2c_imx, i2c_imx->pinctrl_pins_gpio = pinctrl_lookup_state(i2c_imx->pinctrl, "gpio"); rinfo->sda_gpiod = devm_gpiod_get(&pdev->dev, "sda", GPIOD_IN); - rinfo->scl_gpiod = devm_gpiod_get(&pdev->dev, "scl", GPIOD_OUT_HIGH); + rinfo->scl_gpiod = devm_gpiod_get(&pdev->dev, "scl", GPIOD_OUT_HIGH_OPEN_DRAIN); if (PTR_ERR(rinfo->sda_gpiod) == -EPROBE_DEFER || PTR_ERR(rinfo->scl_gpiod) == -EPROBE_DEFER) { diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c index 5e310efd9446..3c1c817f6968 100644 --- a/drivers/i2c/busses/i2c-rcar.c +++ b/drivers/i2c/busses/i2c-rcar.c @@ -32,6 +32,7 @@ #include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> +#include <linux/reset.h> #include <linux/slab.h> /* register offsets */ @@ -111,8 +112,9 @@ #define ID_ARBLOST (1 << 3) #define ID_NACK (1 << 4) /* persistent flags */ +#define ID_P_NO_RXDMA (1 << 30) /* HW forbids RXDMA sometimes */ #define ID_P_PM_BLOCKED (1 << 31) -#define ID_P_MASK ID_P_PM_BLOCKED +#define ID_P_MASK (ID_P_PM_BLOCKED | ID_P_NO_RXDMA) enum rcar_i2c_type { I2C_RCAR_GEN1, @@ -141,6 +143,8 @@ struct rcar_i2c_priv { struct dma_chan *dma_rx; struct scatterlist sg; enum dma_data_direction dma_direction; + + struct reset_control *rstc; }; #define rcar_i2c_priv_to_dev(p) ((p)->adap.dev.parent) @@ -370,6 +374,11 @@ static void rcar_i2c_dma_unmap(struct rcar_i2c_priv *priv) dma_unmap_single(chan->device->dev, sg_dma_address(&priv->sg), sg_dma_len(&priv->sg), priv->dma_direction); + /* Gen3 can only do one RXDMA per transfer and we just completed it */ + if (priv->devtype == I2C_RCAR_GEN3 && + priv->dma_direction == DMA_FROM_DEVICE) + priv->flags |= ID_P_NO_RXDMA; + priv->dma_direction = DMA_NONE; } @@ -407,8 +416,9 @@ static void rcar_i2c_dma(struct rcar_i2c_priv *priv) unsigned char *buf; int len; - /* Do not use DMA if it's not available or for messages < 8 bytes */ - if (IS_ERR(chan) || msg->len < 8 || !(msg->flags & I2C_M_DMA_SAFE)) + /* Do various checks to see if DMA is feasible at all */ + if (IS_ERR(chan) || msg->len < 8 || !(msg->flags & I2C_M_DMA_SAFE) || + (read && priv->flags & ID_P_NO_RXDMA)) return; if (read) { @@ -739,6 +749,25 @@ static void rcar_i2c_release_dma(struct rcar_i2c_priv *priv) } } +/* I2C is a special case, we need to poll the status of a reset */ +static int rcar_i2c_do_reset(struct rcar_i2c_priv *priv) +{ + int i, ret; + + ret = reset_control_reset(priv->rstc); + if (ret) + return ret; + + for (i = 0; i < LOOP_TIMEOUT; i++) { + ret = reset_control_status(priv->rstc); + if (ret == 0) + return 0; + udelay(1); + } + + return -ETIMEDOUT; +} + static int rcar_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) @@ -750,6 +779,16 @@ static int rcar_i2c_master_xfer(struct i2c_adapter *adap, pm_runtime_get_sync(dev); + /* Gen3 needs a reset before allowing RXDMA once */ + if (priv->devtype == I2C_RCAR_GEN3) { + priv->flags |= ID_P_NO_RXDMA; + if (!IS_ERR(priv->rstc)) { + ret = rcar_i2c_do_reset(priv); + if (ret == 0) + priv->flags &= ~ID_P_NO_RXDMA; + } + } + rcar_i2c_init(priv); ret = rcar_i2c_bus_barrier(priv); @@ -920,6 +959,15 @@ static int rcar_i2c_probe(struct platform_device *pdev) if (ret < 0) goto out_pm_put; + if (priv->devtype == I2C_RCAR_GEN3) { + priv->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL); + if (!IS_ERR(priv->rstc)) { + ret = reset_control_status(priv->rstc); + if (ret < 0) + priv->rstc = ERR_PTR(-ENOTSUPP); + } + } + /* Stay always active when multi-master to keep arbitration working */ if (of_property_read_bool(dev->of_node, "multi-master")) priv->flags |= ID_P_PM_BLOCKED; diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 301285c54603..15c95aaa484c 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -624,7 +624,7 @@ static int i2c_check_addr_busy(struct i2c_adapter *adapter, int addr) static void i2c_adapter_lock_bus(struct i2c_adapter *adapter, unsigned int flags) { - rt_mutex_lock(&adapter->bus_lock); + rt_mutex_lock_nested(&adapter->bus_lock, i2c_adapter_depth(adapter)); } /** diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c index 300ab4b672e4..29646aa6132e 100644 --- a/drivers/i2c/i2c-mux.c +++ b/drivers/i2c/i2c-mux.c @@ -144,7 +144,7 @@ static void i2c_mux_lock_bus(struct i2c_adapter *adapter, unsigned int flags) struct i2c_mux_priv *priv = adapter->algo_data; struct i2c_adapter *parent = priv->muxc->parent; - rt_mutex_lock(&parent->mux_lock); + rt_mutex_lock_nested(&parent->mux_lock, i2c_adapter_depth(adapter)); if (!(flags & I2C_LOCK_ROOT_ADAPTER)) return; i2c_lock_bus(parent, flags); @@ -181,7 +181,7 @@ static void i2c_parent_lock_bus(struct i2c_adapter *adapter, struct i2c_mux_priv *priv = adapter->algo_data; struct i2c_adapter *parent = priv->muxc->parent; - rt_mutex_lock(&parent->mux_lock); + rt_mutex_lock_nested(&parent->mux_lock, i2c_adapter_depth(adapter)); i2c_lock_bus(parent, flags); } diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index cc06e8404e9b..583d3a10b940 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -1984,15 +1984,64 @@ static int modify_qp(struct ib_uverbs_file *file, goto release_qp; } - if ((cmd->base.attr_mask & IB_QP_AV) && - !rdma_is_port_valid(qp->device, cmd->base.dest.port_num)) { - ret = -EINVAL; - goto release_qp; + if ((cmd->base.attr_mask & IB_QP_AV)) { + if (!rdma_is_port_valid(qp->device, cmd->base.dest.port_num)) { + ret = -EINVAL; + goto release_qp; + } + + if (cmd->base.attr_mask & IB_QP_STATE && + cmd->base.qp_state == IB_QPS_RTR) { + /* We are in INIT->RTR TRANSITION (if we are not, + * this transition will be rejected in subsequent checks). + * In the INIT->RTR transition, we cannot have IB_QP_PORT set, + * but the IB_QP_STATE flag is required. + * + * Since kernel 3.14 (commit dbf727de7440), the uverbs driver, + * when IB_QP_AV is set, has required inclusion of a valid + * port number in the primary AV. (AVs are created and handled + * differently for infiniband and ethernet (RoCE) ports). + * + * Check the port number included in the primary AV against + * the port number in the qp struct, which was set (and saved) + * in the RST->INIT transition. + */ + if (cmd->base.dest.port_num != qp->real_qp->port) { + ret = -EINVAL; + goto release_qp; + } + } else { + /* We are in SQD->SQD. (If we are not, this transition will + * be rejected later in the verbs layer checks). + * Check for both IB_QP_PORT and IB_QP_AV, these can be set + * together in the SQD->SQD transition. + * + * If only IP_QP_AV was set, add in IB_QP_PORT as well (the + * verbs layer driver does not track primary port changes + * resulting from path migration. Thus, in SQD, if the primary + * AV is modified, the primary port should also be modified). + * + * Note that in this transition, the IB_QP_STATE flag + * is not allowed. + */ + if (((cmd->base.attr_mask & (IB_QP_AV | IB_QP_PORT)) + == (IB_QP_AV | IB_QP_PORT)) && + cmd->base.port_num != cmd->base.dest.port_num) { + ret = -EINVAL; + goto release_qp; + } + if ((cmd->base.attr_mask & (IB_QP_AV | IB_QP_PORT)) + == IB_QP_AV) { + cmd->base.attr_mask |= IB_QP_PORT; + cmd->base.port_num = cmd->base.dest.port_num; + } + } } if ((cmd->base.attr_mask & IB_QP_ALT_PATH) && (!rdma_is_port_valid(qp->device, cmd->base.alt_port_num) || - !rdma_is_port_valid(qp->device, cmd->base.alt_dest.port_num))) { + !rdma_is_port_valid(qp->device, cmd->base.alt_dest.port_num) || + cmd->base.alt_port_num != cmd->base.alt_dest.port_num)) { ret = -EINVAL; goto release_qp; } diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index 1f9cd7d8b7ad..f5ae24865355 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -1346,6 +1346,8 @@ static const struct acpi_device_id elan_acpi_id[] = { { "ELAN0611", 0 }, { "ELAN0612", 0 }, { "ELAN0618", 0 }, + { "ELAN061D", 0 }, + { "ELAN0622", 0 }, { "ELAN1000", 0 }, { } }; diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index b353d494ad40..136f6e7bf797 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -527,6 +527,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "N24_25BU"), }, }, + { + /* Lenovo LaVie Z */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo LaVie Z"), + }, + }, { } }; diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 689ffe538370..c60395b7470f 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -60,6 +60,27 @@ config IOMMU_IO_PGTABLE_ARMV7S_SELFTEST endmenu +config IOMMU_DEBUGFS + bool "Export IOMMU internals in DebugFS" + depends on DEBUG_FS + help + Allows exposure of IOMMU device internals. This option enables + the use of debugfs by IOMMU drivers as required. Devices can, + at initialization time, cause the IOMMU code to create a top-level + debug/iommu directory, and then populate a subdirectory with + entries as required. + +config IOMMU_DEFAULT_PASSTHROUGH + bool "IOMMU passthrough by default" + depends on IOMMU_API + help + Enable passthrough by default, removing the need to pass in + iommu.passthrough=on or iommu=pt through command line. If this + is enabled, you can still disable with iommu.passthrough=off + or iommu=nopt depending on the architecture. + + If unsure, say N here. + config IOMMU_IOVA tristate @@ -135,6 +156,18 @@ config AMD_IOMMU_V2 hardware. Select this option if you want to use devices that support the PCI PRI and PASID interface. +config AMD_IOMMU_DEBUGFS + bool "Enable AMD IOMMU internals in DebugFS" + depends on AMD_IOMMU && IOMMU_DEBUGFS + ---help--- + !!!WARNING!!! !!!WARNING!!! !!!WARNING!!! !!!WARNING!!! + + DO NOT ENABLE THIS OPTION UNLESS YOU REALLY, -REALLY- KNOW WHAT YOU ARE DOING!!! + Exposes AMD IOMMU device internals in DebugFS. + + This option is -NOT- intended for production environments, and should + not generally be enabled. + # Intel IOMMU support config DMAR_TABLE bool @@ -284,8 +317,8 @@ config IPMMU_VMSA select IOMMU_IO_PGTABLE_LPAE select ARM_DMA_USE_IOMMU help - Support for the Renesas VMSA-compatible IPMMU Renesas found in the - R-Mobile APE6 and R-Car H2/M2 SoCs. + Support for the Renesas VMSA-compatible IPMMU found in the R-Mobile + APE6, R-Car Gen2, and R-Car Gen3 SoCs. If unsure, say N. diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index 1fb695854809..ab5eba6edf82 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -2,6 +2,7 @@ obj-$(CONFIG_IOMMU_API) += iommu.o obj-$(CONFIG_IOMMU_API) += iommu-traces.o obj-$(CONFIG_IOMMU_API) += iommu-sysfs.o +obj-$(CONFIG_IOMMU_DEBUGFS) += iommu-debugfs.o obj-$(CONFIG_IOMMU_DMA) += dma-iommu.o obj-$(CONFIG_IOMMU_IO_PGTABLE) += io-pgtable.o obj-$(CONFIG_IOMMU_IO_PGTABLE_ARMV7S) += io-pgtable-arm-v7s.o @@ -10,11 +11,12 @@ obj-$(CONFIG_IOMMU_IOVA) += iova.o obj-$(CONFIG_OF_IOMMU) += of_iommu.o obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o +obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd_iommu_debugfs.o obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o obj-$(CONFIG_ARM_SMMU) += arm-smmu.o obj-$(CONFIG_ARM_SMMU_V3) += arm-smmu-v3.o obj-$(CONFIG_DMAR_TABLE) += dmar.o -obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o +obj-$(CONFIG_INTEL_IOMMU) += intel-iommu.o intel-pasid.o obj-$(CONFIG_INTEL_IOMMU_SVM) += intel-svm.o obj-$(CONFIG_IPMMU_VMSA) += ipmmu-vmsa.o obj-$(CONFIG_IRQ_REMAP) += intel_irq_remapping.o irq_remapping.o diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 596b95c50051..2aded63548c7 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -1404,6 +1404,8 @@ static u64 *fetch_pte(struct protection_domain *domain, int level; u64 *pte; + *page_size = 0; + if (address > PM_LEVEL_SIZE(domain->mode)) return NULL; @@ -1944,12 +1946,6 @@ static int __attach_device(struct iommu_dev_data *dev_data, { int ret; - /* - * Must be called with IRQs disabled. Warn here to detect early - * when its not. - */ - WARN_ON(!irqs_disabled()); - /* lock domain */ spin_lock(&domain->lock); @@ -2115,12 +2111,6 @@ static void __detach_device(struct iommu_dev_data *dev_data) { struct protection_domain *domain; - /* - * Must be called with IRQs disabled. Warn here to detect early - * when its not. - */ - WARN_ON(!irqs_disabled()); - domain = dev_data->domain; spin_lock(&domain->lock); @@ -2405,9 +2395,9 @@ static void __unmap_single(struct dma_ops_domain *dma_dom, } if (amd_iommu_unmap_flush) { - dma_ops_free_iova(dma_dom, dma_addr, pages); domain_flush_tlb(&dma_dom->domain); domain_flush_complete(&dma_dom->domain); + dma_ops_free_iova(dma_dom, dma_addr, pages); } else { pages = __roundup_pow_of_two(pages); queue_iova(&dma_dom->iovad, dma_addr >> PAGE_SHIFT, pages, 0); @@ -3192,7 +3182,6 @@ const struct iommu_ops amd_iommu_ops = { .detach_dev = amd_iommu_detach_device, .map = amd_iommu_map, .unmap = amd_iommu_unmap, - .map_sg = default_iommu_map_sg, .iova_to_phys = amd_iommu_iova_to_phys, .add_device = amd_iommu_add_device, .remove_device = amd_iommu_remove_device, @@ -3874,7 +3863,8 @@ static void irte_ga_prepare(void *entry, irte->lo.fields_remap.int_type = delivery_mode; irte->lo.fields_remap.dm = dest_mode; irte->hi.fields.vector = vector; - irte->lo.fields_remap.destination = dest_apicid; + irte->lo.fields_remap.destination = APICID_TO_IRTE_DEST_LO(dest_apicid); + irte->hi.fields.destination = APICID_TO_IRTE_DEST_HI(dest_apicid); irte->lo.fields_remap.valid = 1; } @@ -3927,7 +3917,10 @@ static void irte_ga_set_affinity(void *entry, u16 devid, u16 index, if (!irte->lo.fields_remap.guest_mode) { irte->hi.fields.vector = vector; - irte->lo.fields_remap.destination = dest_apicid; + irte->lo.fields_remap.destination = + APICID_TO_IRTE_DEST_LO(dest_apicid); + irte->hi.fields.destination = + APICID_TO_IRTE_DEST_HI(dest_apicid); modify_irte_ga(devid, index, irte, NULL); } } @@ -4344,7 +4337,10 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info) irte->lo.val = 0; irte->hi.fields.vector = cfg->vector; irte->lo.fields_remap.guest_mode = 0; - irte->lo.fields_remap.destination = cfg->dest_apicid; + irte->lo.fields_remap.destination = + APICID_TO_IRTE_DEST_LO(cfg->dest_apicid); + irte->hi.fields.destination = + APICID_TO_IRTE_DEST_HI(cfg->dest_apicid); irte->lo.fields_remap.int_type = apic->irq_delivery_mode; irte->lo.fields_remap.dm = apic->irq_dest_mode; @@ -4461,8 +4457,12 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data) raw_spin_lock_irqsave(&table->lock, flags); if (ref->lo.fields_vapic.guest_mode) { - if (cpu >= 0) - ref->lo.fields_vapic.destination = cpu; + if (cpu >= 0) { + ref->lo.fields_vapic.destination = + APICID_TO_IRTE_DEST_LO(cpu); + ref->hi.fields.destination = + APICID_TO_IRTE_DEST_HI(cpu); + } ref->lo.fields_vapic.is_run = is_run; barrier(); } diff --git a/drivers/iommu/amd_iommu_debugfs.c b/drivers/iommu/amd_iommu_debugfs.c new file mode 100644 index 000000000000..c6a5c737ef09 --- /dev/null +++ b/drivers/iommu/amd_iommu_debugfs.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * AMD IOMMU driver + * + * Copyright (C) 2018 Advanced Micro Devices, Inc. + * + * Author: Gary R Hook <gary.hook@amd.com> + */ + +#include <linux/debugfs.h> +#include <linux/iommu.h> +#include <linux/pci.h> +#include "amd_iommu_proto.h" +#include "amd_iommu_types.h" + +static struct dentry *amd_iommu_debugfs; +static DEFINE_MUTEX(amd_iommu_debugfs_lock); + +#define MAX_NAME_LEN 20 + +void amd_iommu_debugfs_setup(struct amd_iommu *iommu) +{ + char name[MAX_NAME_LEN + 1]; + + mutex_lock(&amd_iommu_debugfs_lock); + if (!amd_iommu_debugfs) + amd_iommu_debugfs = debugfs_create_dir("amd", + iommu_debugfs_dir); + mutex_unlock(&amd_iommu_debugfs_lock); + + snprintf(name, MAX_NAME_LEN, "iommu%02d", iommu->index); + iommu->debugfs = debugfs_create_dir(name, amd_iommu_debugfs); +} diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 904c575d1677..84b3e4445d46 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -153,6 +153,7 @@ bool amd_iommu_dump; bool amd_iommu_irq_remap __read_mostly; int amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_VAPIC; +static int amd_iommu_xt_mode = IRQ_REMAP_X2APIC_MODE; static bool amd_iommu_detected; static bool __initdata amd_iommu_disabled; @@ -280,9 +281,9 @@ static void clear_translation_pre_enabled(struct amd_iommu *iommu) static void init_translation_status(struct amd_iommu *iommu) { - u32 ctrl; + u64 ctrl; - ctrl = readl(iommu->mmio_base + MMIO_CONTROL_OFFSET); + ctrl = readq(iommu->mmio_base + MMIO_CONTROL_OFFSET); if (ctrl & (1<<CONTROL_IOMMU_EN)) iommu->flags |= AMD_IOMMU_FLAG_TRANS_PRE_ENABLED; } @@ -386,30 +387,30 @@ static void iommu_set_device_table(struct amd_iommu *iommu) /* Generic functions to enable/disable certain features of the IOMMU. */ static void iommu_feature_enable(struct amd_iommu *iommu, u8 bit) { - u32 ctrl; + u64 ctrl; - ctrl = readl(iommu->mmio_base + MMIO_CONTROL_OFFSET); - ctrl |= (1 << bit); - writel(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET); + ctrl = readq(iommu->mmio_base + MMIO_CONTROL_OFFSET); + ctrl |= (1ULL << bit); + writeq(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET); } static void iommu_feature_disable(struct amd_iommu *iommu, u8 bit) { - u32 ctrl; + u64 ctrl; - ctrl = readl(iommu->mmio_base + MMIO_CONTROL_OFFSET); - ctrl &= ~(1 << bit); - writel(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET); + ctrl = readq(iommu->mmio_base + MMIO_CONTROL_OFFSET); + ctrl &= ~(1ULL << bit); + writeq(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET); } static void iommu_set_inv_tlb_timeout(struct amd_iommu *iommu, int timeout) { - u32 ctrl; + u64 ctrl; - ctrl = readl(iommu->mmio_base + MMIO_CONTROL_OFFSET); + ctrl = readq(iommu->mmio_base + MMIO_CONTROL_OFFSET); ctrl &= ~CTRL_INV_TO_MASK; ctrl |= (timeout << CONTROL_INV_TIMEOUT) & CTRL_INV_TO_MASK; - writel(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET); + writeq(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET); } /* Function to enable the hardware */ @@ -827,6 +828,19 @@ static int iommu_init_ga(struct amd_iommu *iommu) return ret; } +static void iommu_enable_xt(struct amd_iommu *iommu) +{ +#ifdef CONFIG_IRQ_REMAP + /* + * XT mode (32-bit APIC destination ID) requires + * GA mode (128-bit IRTE support) as a prerequisite. + */ + if (AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir) && + amd_iommu_xt_mode == IRQ_REMAP_X2APIC_MODE) + iommu_feature_enable(iommu, CONTROL_XT_EN); +#endif /* CONFIG_IRQ_REMAP */ +} + static void iommu_enable_gt(struct amd_iommu *iommu) { if (!iommu_feature(iommu, FEATURE_GT)) @@ -1507,6 +1521,8 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h) iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET; if (((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0)) amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY; + if (((h->efr_attr & (0x1 << IOMMU_FEAT_XTSUP_SHIFT)) == 0)) + amd_iommu_xt_mode = IRQ_REMAP_XAPIC_MODE; break; case 0x11: case 0x40: @@ -1516,6 +1532,8 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h) iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET; if (((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0)) amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY; + if (((h->efr_reg & (0x1 << IOMMU_EFR_XTSUP_SHIFT)) == 0)) + amd_iommu_xt_mode = IRQ_REMAP_XAPIC_MODE; break; default: return -EINVAL; @@ -1832,6 +1850,8 @@ static void print_iommu_info(void) pr_info("AMD-Vi: Interrupt remapping enabled\n"); if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir)) pr_info("AMD-Vi: virtual APIC enabled\n"); + if (amd_iommu_xt_mode == IRQ_REMAP_X2APIC_MODE) + pr_info("AMD-Vi: X2APIC enabled\n"); } } @@ -2168,6 +2188,7 @@ static void early_enable_iommu(struct amd_iommu *iommu) iommu_enable_event_buffer(iommu); iommu_set_exclusion_range(iommu); iommu_enable_ga(iommu); + iommu_enable_xt(iommu); iommu_enable(iommu); iommu_flush_all_caches(iommu); } @@ -2212,6 +2233,7 @@ static void early_enable_iommus(void) iommu_enable_command_buffer(iommu); iommu_enable_event_buffer(iommu); iommu_enable_ga(iommu); + iommu_enable_xt(iommu); iommu_set_device_table(iommu); iommu_flush_all_caches(iommu); } @@ -2691,8 +2713,7 @@ int __init amd_iommu_enable(void) return ret; irq_remapping_enabled = 1; - - return 0; + return amd_iommu_xt_mode; } void amd_iommu_disable(void) @@ -2721,6 +2742,7 @@ int __init amd_iommu_enable_faulting(void) */ static int __init amd_iommu_init(void) { + struct amd_iommu *iommu; int ret; ret = iommu_go_to_state(IOMMU_INITIALIZED); @@ -2730,14 +2752,15 @@ static int __init amd_iommu_init(void) disable_iommus(); free_iommu_resources(); } else { - struct amd_iommu *iommu; - uninit_device_table_dma(); for_each_iommu(iommu) iommu_flush_all_caches(iommu); } } + for_each_iommu(iommu) + amd_iommu_debugfs_setup(iommu); + return ret; } diff --git a/drivers/iommu/amd_iommu_proto.h b/drivers/iommu/amd_iommu_proto.h index 640c286a0ab9..a8cd0296fb16 100644 --- a/drivers/iommu/amd_iommu_proto.h +++ b/drivers/iommu/amd_iommu_proto.h @@ -33,6 +33,12 @@ extern void amd_iommu_uninit_devices(void); extern void amd_iommu_init_notifier(void); extern int amd_iommu_init_api(void); +#ifdef CONFIG_AMD_IOMMU_DEBUGFS +void amd_iommu_debugfs_setup(struct amd_iommu *iommu); +#else +static inline void amd_iommu_debugfs_setup(struct amd_iommu *iommu) {} +#endif + /* Needed for interrupt remapping */ extern int amd_iommu_prepare(void); extern int amd_iommu_enable(void); diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index 986cbe0cc189..e2b342e65a7b 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -161,6 +161,7 @@ #define CONTROL_GAM_EN 0x19ULL #define CONTROL_GALOG_EN 0x1CULL #define CONTROL_GAINT_EN 0x1DULL +#define CONTROL_XT_EN 0x32ULL #define CTRL_INV_TO_MASK (7 << CONTROL_INV_TIMEOUT) #define CTRL_INV_TO_NONE 0 @@ -378,9 +379,11 @@ #define IOMMU_CAP_EFR 27 /* IOMMU Feature Reporting Field (for IVHD type 10h */ +#define IOMMU_FEAT_XTSUP_SHIFT 0 #define IOMMU_FEAT_GASUP_SHIFT 6 /* IOMMU Extended Feature Register (EFR) */ +#define IOMMU_EFR_XTSUP_SHIFT 2 #define IOMMU_EFR_GASUP_SHIFT 7 #define MAX_DOMAIN_ID 65536 @@ -437,7 +440,6 @@ extern struct kmem_cache *amd_iommu_irq_cache; #define APERTURE_RANGE_INDEX(a) ((a) >> APERTURE_RANGE_SHIFT) #define APERTURE_PAGE_INDEX(a) (((a) >> 21) & 0x3fULL) - /* * This struct is used to pass information about * incoming PPR faults around. @@ -594,6 +596,11 @@ struct amd_iommu { u32 flags; volatile u64 __aligned(8) cmd_sem; + +#ifdef CONFIG_AMD_IOMMU_DEBUGFS + /* DebugFS Info */ + struct dentry *debugfs; +#endif }; static inline struct amd_iommu *dev_to_amd_iommu(struct device *dev) @@ -810,6 +817,9 @@ union irte { } fields; }; +#define APICID_TO_IRTE_DEST_LO(x) (x & 0xffffff) +#define APICID_TO_IRTE_DEST_HI(x) ((x >> 24) & 0xff) + union irte_ga_lo { u64 val; @@ -823,8 +833,8 @@ union irte_ga_lo { dm : 1, /* ------ */ guest_mode : 1, - destination : 8, - rsvd : 48; + destination : 24, + ga_tag : 32; } fields_remap; /* For guest vAPIC */ @@ -837,8 +847,7 @@ union irte_ga_lo { is_run : 1, /* ------ */ guest_mode : 1, - destination : 8, - rsvd2 : 16, + destination : 24, ga_tag : 32; } fields_vapic; }; @@ -849,7 +858,8 @@ union irte_ga_hi { u64 vector : 8, rsvd_1 : 4, ga_root_ptr : 40, - rsvd_2 : 12; + rsvd_2 : 4, + destination : 8; } fields; }; diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 446703eeee7a..8a6140977907 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -1999,7 +1999,6 @@ static struct iommu_ops arm_smmu_ops = { .attach_dev = arm_smmu_attach_dev, .map = arm_smmu_map, .unmap = arm_smmu_unmap, - .map_sg = default_iommu_map_sg, .flush_iotlb_all = arm_smmu_iotlb_sync, .iotlb_sync = arm_smmu_iotlb_sync, .iova_to_phys = arm_smmu_iova_to_phys, diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 5349e22b5c78..32e86df80428 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -1562,7 +1562,6 @@ static struct iommu_ops arm_smmu_ops = { .attach_dev = arm_smmu_attach_dev, .map = arm_smmu_map, .unmap = arm_smmu_unmap, - .map_sg = default_iommu_map_sg, .flush_iotlb_all = arm_smmu_iotlb_sync, .iotlb_sync = arm_smmu_iotlb_sync, .iova_to_phys = arm_smmu_iova_to_phys, diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 75456b5aa825..d9c748b6f9e4 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -1339,8 +1339,8 @@ void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr, qi_submit_sync(&desc, iommu); } -void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 qdep, - u64 addr, unsigned mask) +void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid, + u16 qdep, u64 addr, unsigned mask) { struct qi_desc desc; @@ -1355,7 +1355,7 @@ void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 qdep, qdep = 0; desc.low = QI_DEV_IOTLB_SID(sid) | QI_DEV_IOTLB_QDEP(qdep) | - QI_DIOTLB_TYPE; + QI_DIOTLB_TYPE | QI_DEV_IOTLB_PFSID(pfsid); qi_submit_sync(&desc, iommu); } diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index 85879cfec52f..19e55cf6a9dd 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -1332,7 +1332,6 @@ static const struct iommu_ops exynos_iommu_ops = { .detach_dev = exynos_iommu_detach_device, .map = exynos_iommu_map, .unmap = exynos_iommu_unmap, - .map_sg = default_iommu_map_sg, .iova_to_phys = exynos_iommu_iova_to_phys, .device_group = generic_device_group, .add_device = exynos_iommu_add_device, diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 115ff26e9ced..d611a3e9c81a 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -52,6 +52,7 @@ #include <asm/iommu.h> #include "irq_remapping.h" +#include "intel-pasid.h" #define ROOT_SIZE VTD_PAGE_SIZE #define CONTEXT_SIZE VTD_PAGE_SIZE @@ -379,60 +380,6 @@ static int hw_pass_through = 1; for (idx = 0; idx < g_num_of_iommus; idx++) \ if (domain->iommu_refcnt[idx]) -struct dmar_domain { - int nid; /* node id */ - - unsigned iommu_refcnt[DMAR_UNITS_SUPPORTED]; - /* Refcount of devices per iommu */ - - - u16 iommu_did[DMAR_UNITS_SUPPORTED]; - /* Domain ids per IOMMU. Use u16 since - * domain ids are 16 bit wide according - * to VT-d spec, section 9.3 */ - - bool has_iotlb_device; - struct list_head devices; /* all devices' list */ - struct iova_domain iovad; /* iova's that belong to this domain */ - - struct dma_pte *pgd; /* virtual address */ - int gaw; /* max guest address width */ - - /* adjusted guest address width, 0 is level 2 30-bit */ - int agaw; - - int flags; /* flags to find out type of domain */ - - int iommu_coherency;/* indicate coherency of iommu access */ - int iommu_snooping; /* indicate snooping control feature*/ - int iommu_count; /* reference count of iommu */ - int iommu_superpage;/* Level of superpages supported: - 0 == 4KiB (no superpages), 1 == 2MiB, - 2 == 1GiB, 3 == 512GiB, 4 == 1TiB */ - u64 max_addr; /* maximum mapped address */ - - struct iommu_domain domain; /* generic domain data structure for - iommu core */ -}; - -/* PCI domain-device relationship */ -struct device_domain_info { - struct list_head link; /* link to domain siblings */ - struct list_head global; /* link to global list */ - u8 bus; /* PCI bus number */ - u8 devfn; /* PCI devfn number */ - u8 pasid_supported:3; - u8 pasid_enabled:1; - u8 pri_supported:1; - u8 pri_enabled:1; - u8 ats_supported:1; - u8 ats_enabled:1; - u8 ats_qdep; - struct device *dev; /* it's NULL for PCIe-to-PCI bridge */ - struct intel_iommu *iommu; /* IOMMU used by this device */ - struct dmar_domain *domain; /* pointer to domain */ -}; - struct dmar_rmrr_unit { struct list_head list; /* list of rmrr units */ struct acpi_dmar_header *hdr; /* ACPI header */ @@ -523,6 +470,27 @@ EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped); static DEFINE_SPINLOCK(device_domain_lock); static LIST_HEAD(device_domain_list); +/* + * Iterate over elements in device_domain_list and call the specified + * callback @fn against each element. This helper should only be used + * in the context where the device_domain_lock has already been holden. + */ +int for_each_device_domain(int (*fn)(struct device_domain_info *info, + void *data), void *data) +{ + int ret = 0; + struct device_domain_info *info; + + assert_spin_locked(&device_domain_lock); + list_for_each_entry(info, &device_domain_list, global) { + ret = fn(info, data); + if (ret) + return ret; + } + + return 0; +} + const struct iommu_ops intel_iommu_ops; static bool translation_pre_enabled(struct intel_iommu *iommu) @@ -629,7 +597,7 @@ static void set_iommu_domain(struct intel_iommu *iommu, u16 did, domains[did & 0xff] = domain; } -static inline void *alloc_pgtable_page(int node) +void *alloc_pgtable_page(int node) { struct page *page; void *vaddr = NULL; @@ -640,7 +608,7 @@ static inline void *alloc_pgtable_page(int node) return vaddr; } -static inline void free_pgtable_page(void *vaddr) +void free_pgtable_page(void *vaddr) { free_page((unsigned long)vaddr); } @@ -723,7 +691,7 @@ int iommu_calculate_agaw(struct intel_iommu *iommu) } /* This functionin only returns single iommu in a domain */ -static struct intel_iommu *domain_get_iommu(struct dmar_domain *domain) +struct intel_iommu *domain_get_iommu(struct dmar_domain *domain) { int iommu_id; @@ -1501,6 +1469,20 @@ static void iommu_enable_dev_iotlb(struct device_domain_info *info) return; pdev = to_pci_dev(info->dev); + /* For IOMMU that supports device IOTLB throttling (DIT), we assign + * PFSID to the invalidation desc of a VF such that IOMMU HW can gauge + * queue depth at PF level. If DIT is not set, PFSID will be treated as + * reserved, which should be set to 0. + */ + if (!ecap_dit(info->iommu->ecap)) + info->pfsid = 0; + else { + struct pci_dev *pf_pdev; + + /* pdev will be returned if device is not a vf */ + pf_pdev = pci_physfn(pdev); + info->pfsid = PCI_DEVID(pf_pdev->bus->number, pf_pdev->devfn); + } #ifdef CONFIG_INTEL_IOMMU_SVM /* The PCIe spec, in its wisdom, declares that the behaviour of @@ -1566,7 +1548,8 @@ static void iommu_flush_dev_iotlb(struct dmar_domain *domain, sid = info->bus << 8 | info->devfn; qdep = info->ats_qdep; - qi_flush_dev_iotlb(info->iommu, sid, qdep, addr, mask); + qi_flush_dev_iotlb(info->iommu, sid, info->pfsid, + qdep, addr, mask); } spin_unlock_irqrestore(&device_domain_lock, flags); } @@ -1800,7 +1783,7 @@ static void free_dmar_iommu(struct intel_iommu *iommu) if (pasid_enabled(iommu)) { if (ecap_prs(iommu->ecap)) intel_svm_finish_prq(iommu); - intel_svm_free_pasid_tables(iommu); + intel_svm_exit(iommu); } #endif } @@ -2495,6 +2478,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu, info->dev = dev; info->domain = domain; info->iommu = iommu; + info->pasid_table = NULL; if (dev && dev_is_pci(dev)) { struct pci_dev *pdev = to_pci_dev(info->dev); @@ -2552,6 +2536,15 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu, list_add(&info->global, &device_domain_list); if (dev) dev->archdata.iommu = info; + + if (dev && dev_is_pci(dev) && info->pasid_supported) { + ret = intel_pasid_alloc_table(dev); + if (ret) { + __dmar_remove_one_dev_info(info); + spin_unlock_irqrestore(&device_domain_lock, flags); + return NULL; + } + } spin_unlock_irqrestore(&device_domain_lock, flags); if (dev && domain_context_mapping(domain, dev)) { @@ -3304,6 +3297,18 @@ static int __init init_dmars(void) } for_each_active_iommu(iommu, drhd) { + /* + * Find the max pasid size of all IOMMU's in the system. + * We need to ensure the system pasid table is no bigger + * than the smallest supported. + */ + if (pasid_enabled(iommu)) { + u32 temp = 2 << ecap_pss(iommu->ecap); + + intel_pasid_max_id = min_t(u32, temp, + intel_pasid_max_id); + } + g_iommus[iommu->seq_id] = iommu; intel_iommu_init_qi(iommu); @@ -3359,7 +3364,7 @@ static int __init init_dmars(void) hw_pass_through = 0; #ifdef CONFIG_INTEL_IOMMU_SVM if (pasid_enabled(iommu)) - intel_svm_alloc_pasid_tables(iommu); + intel_svm_init(iommu); #endif } @@ -3526,7 +3531,7 @@ static unsigned long intel_alloc_iova(struct device *dev, return iova_pfn; } -static struct dmar_domain *get_valid_domain_for_dev(struct device *dev) +struct dmar_domain *get_valid_domain_for_dev(struct device *dev) { struct dmar_domain *domain, *tmp; struct dmar_rmrr_unit *rmrr; @@ -4353,7 +4358,7 @@ static int intel_iommu_add(struct dmar_drhd_unit *dmaru) #ifdef CONFIG_INTEL_IOMMU_SVM if (pasid_enabled(iommu)) - intel_svm_alloc_pasid_tables(iommu); + intel_svm_init(iommu); #endif if (dmaru->ignored) { @@ -4905,6 +4910,7 @@ static void __dmar_remove_one_dev_info(struct device_domain_info *info) if (info->dev) { iommu_disable_dev_iotlb(info); domain_context_clear(iommu, info->dev); + intel_pasid_free_table(info->dev); } unlink_domain_info(info); @@ -5230,22 +5236,16 @@ static void intel_iommu_put_resv_regions(struct device *dev, #ifdef CONFIG_INTEL_IOMMU_SVM #define MAX_NR_PASID_BITS (20) -static inline unsigned long intel_iommu_get_pts(struct intel_iommu *iommu) +static inline unsigned long intel_iommu_get_pts(struct device *dev) { - /* - * Convert ecap_pss to extend context entry pts encoding, also - * respect the soft pasid_max value set by the iommu. - * - number of PASID bits = ecap_pss + 1 - * - number of PASID table entries = 2^(pts + 5) - * Therefore, pts = ecap_pss - 4 - * e.g. KBL ecap_pss = 0x13, PASID has 20 bits, pts = 15 - */ - if (ecap_pss(iommu->ecap) < 5) + int pts, max_pasid; + + max_pasid = intel_pasid_get_dev_max_id(dev); + pts = find_first_bit((unsigned long *)&max_pasid, MAX_NR_PASID_BITS); + if (pts < 5) return 0; - /* pasid_max is encoded as actual number of entries not the bits */ - return find_first_bit((unsigned long *)&iommu->pasid_max, - MAX_NR_PASID_BITS) - 5; + return pts - 5; } int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sdev) @@ -5281,8 +5281,8 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sd if (!(ctx_lo & CONTEXT_PASIDE)) { if (iommu->pasid_state_table) context[1].hi = (u64)virt_to_phys(iommu->pasid_state_table); - context[1].lo = (u64)virt_to_phys(iommu->pasid_table) | - intel_iommu_get_pts(iommu); + context[1].lo = (u64)virt_to_phys(info->pasid_table->table) | + intel_iommu_get_pts(sdev->dev); wmb(); /* CONTEXT_TT_MULTI_LEVEL and CONTEXT_TT_DEV_IOTLB are both @@ -5349,11 +5349,6 @@ struct intel_iommu *intel_svm_device_to_iommu(struct device *dev) return NULL; } - if (!iommu->pasid_table) { - dev_err(dev, "PASID not enabled on IOMMU; cannot enable SVM\n"); - return NULL; - } - return iommu; } #endif /* CONFIG_INTEL_IOMMU_SVM */ @@ -5366,7 +5361,6 @@ const struct iommu_ops intel_iommu_ops = { .detach_dev = intel_iommu_detach_device, .map = intel_iommu_map, .unmap = intel_iommu_unmap, - .map_sg = default_iommu_map_sg, .iova_to_phys = intel_iommu_iova_to_phys, .add_device = intel_iommu_add_device, .remove_device = intel_iommu_remove_device, diff --git a/drivers/iommu/intel-pasid.c b/drivers/iommu/intel-pasid.c new file mode 100644 index 000000000000..fe95c9bd4d33 --- /dev/null +++ b/drivers/iommu/intel-pasid.c @@ -0,0 +1,239 @@ +// SPDX-License-Identifier: GPL-2.0 +/** + * intel-pasid.c - PASID idr, table and entry manipulation + * + * Copyright (C) 2018 Intel Corporation + * + * Author: Lu Baolu <baolu.lu@linux.intel.com> + */ + +#define pr_fmt(fmt) "DMAR: " fmt + +#include <linux/dmar.h> +#include <linux/intel-iommu.h> +#include <linux/iommu.h> +#include <linux/memory.h> +#include <linux/pci.h> +#include <linux/pci-ats.h> +#include <linux/spinlock.h> + +#include "intel-pasid.h" + +/* + * Intel IOMMU system wide PASID name space: + */ +static DEFINE_SPINLOCK(pasid_lock); +u32 intel_pasid_max_id = PASID_MAX; +static DEFINE_IDR(pasid_idr); + +int intel_pasid_alloc_id(void *ptr, int start, int end, gfp_t gfp) +{ + int ret, min, max; + + min = max_t(int, start, PASID_MIN); + max = min_t(int, end, intel_pasid_max_id); + + WARN_ON(in_interrupt()); + idr_preload(gfp); + spin_lock(&pasid_lock); + ret = idr_alloc(&pasid_idr, ptr, min, max, GFP_ATOMIC); + spin_unlock(&pasid_lock); + idr_preload_end(); + + return ret; +} + +void intel_pasid_free_id(int pasid) +{ + spin_lock(&pasid_lock); + idr_remove(&pasid_idr, pasid); + spin_unlock(&pasid_lock); +} + +void *intel_pasid_lookup_id(int pasid) +{ + void *p; + + spin_lock(&pasid_lock); + p = idr_find(&pasid_idr, pasid); + spin_unlock(&pasid_lock); + + return p; +} + +/* + * Per device pasid table management: + */ +static inline void +device_attach_pasid_table(struct device_domain_info *info, + struct pasid_table *pasid_table) +{ + info->pasid_table = pasid_table; + list_add(&info->table, &pasid_table->dev); +} + +static inline void +device_detach_pasid_table(struct device_domain_info *info, + struct pasid_table *pasid_table) +{ + info->pasid_table = NULL; + list_del(&info->table); +} + +struct pasid_table_opaque { + struct pasid_table **pasid_table; + int segment; + int bus; + int devfn; +}; + +static int search_pasid_table(struct device_domain_info *info, void *opaque) +{ + struct pasid_table_opaque *data = opaque; + + if (info->iommu->segment == data->segment && + info->bus == data->bus && + info->devfn == data->devfn && + info->pasid_table) { + *data->pasid_table = info->pasid_table; + return 1; + } + + return 0; +} + +static int get_alias_pasid_table(struct pci_dev *pdev, u16 alias, void *opaque) +{ + struct pasid_table_opaque *data = opaque; + + data->segment = pci_domain_nr(pdev->bus); + data->bus = PCI_BUS_NUM(alias); + data->devfn = alias & 0xff; + + return for_each_device_domain(&search_pasid_table, data); +} + +/* + * Allocate a pasid table for @dev. It should be called in a + * single-thread context. + */ +int intel_pasid_alloc_table(struct device *dev) +{ + struct device_domain_info *info; + struct pasid_table *pasid_table; + struct pasid_table_opaque data; + struct page *pages; + size_t size, count; + int ret, order; + + info = dev->archdata.iommu; + if (WARN_ON(!info || !dev_is_pci(dev) || + !info->pasid_supported || info->pasid_table)) + return -EINVAL; + + /* DMA alias device already has a pasid table, use it: */ + data.pasid_table = &pasid_table; + ret = pci_for_each_dma_alias(to_pci_dev(dev), + &get_alias_pasid_table, &data); + if (ret) + goto attach_out; + + pasid_table = kzalloc(sizeof(*pasid_table), GFP_ATOMIC); + if (!pasid_table) + return -ENOMEM; + INIT_LIST_HEAD(&pasid_table->dev); + + size = sizeof(struct pasid_entry); + count = min_t(int, pci_max_pasids(to_pci_dev(dev)), intel_pasid_max_id); + order = get_order(size * count); + pages = alloc_pages_node(info->iommu->node, + GFP_ATOMIC | __GFP_ZERO, + order); + if (!pages) + return -ENOMEM; + + pasid_table->table = page_address(pages); + pasid_table->order = order; + pasid_table->max_pasid = count; + +attach_out: + device_attach_pasid_table(info, pasid_table); + + return 0; +} + +void intel_pasid_free_table(struct device *dev) +{ + struct device_domain_info *info; + struct pasid_table *pasid_table; + + info = dev->archdata.iommu; + if (!info || !dev_is_pci(dev) || + !info->pasid_supported || !info->pasid_table) + return; + + pasid_table = info->pasid_table; + device_detach_pasid_table(info, pasid_table); + + if (!list_empty(&pasid_table->dev)) + return; + + free_pages((unsigned long)pasid_table->table, pasid_table->order); + kfree(pasid_table); +} + +struct pasid_table *intel_pasid_get_table(struct device *dev) +{ + struct device_domain_info *info; + + info = dev->archdata.iommu; + if (!info) + return NULL; + + return info->pasid_table; +} + +int intel_pasid_get_dev_max_id(struct device *dev) +{ + struct device_domain_info *info; + + info = dev->archdata.iommu; + if (!info || !info->pasid_table) + return 0; + + return info->pasid_table->max_pasid; +} + +struct pasid_entry *intel_pasid_get_entry(struct device *dev, int pasid) +{ + struct pasid_table *pasid_table; + struct pasid_entry *entries; + + pasid_table = intel_pasid_get_table(dev); + if (WARN_ON(!pasid_table || pasid < 0 || + pasid >= intel_pasid_get_dev_max_id(dev))) + return NULL; + + entries = pasid_table->table; + + return &entries[pasid]; +} + +/* + * Interfaces for PASID table entry manipulation: + */ +static inline void pasid_clear_entry(struct pasid_entry *pe) +{ + WRITE_ONCE(pe->val, 0); +} + +void intel_pasid_clear_entry(struct device *dev, int pasid) +{ + struct pasid_entry *pe; + + pe = intel_pasid_get_entry(dev, pasid); + if (WARN_ON(!pe)) + return; + + pasid_clear_entry(pe); +} diff --git a/drivers/iommu/intel-pasid.h b/drivers/iommu/intel-pasid.h new file mode 100644 index 000000000000..1c05ed6fc5a5 --- /dev/null +++ b/drivers/iommu/intel-pasid.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * intel-pasid.h - PASID idr, table and entry header + * + * Copyright (C) 2018 Intel Corporation + * + * Author: Lu Baolu <baolu.lu@linux.intel.com> + */ + +#ifndef __INTEL_PASID_H +#define __INTEL_PASID_H + +#define PASID_MIN 0x1 +#define PASID_MAX 0x100000 + +struct pasid_entry { + u64 val; +}; + +/* The representative of a PASID table */ +struct pasid_table { + void *table; /* pasid table pointer */ + int order; /* page order of pasid table */ + int max_pasid; /* max pasid */ + struct list_head dev; /* device list */ +}; + +extern u32 intel_pasid_max_id; +int intel_pasid_alloc_id(void *ptr, int start, int end, gfp_t gfp); +void intel_pasid_free_id(int pasid); +void *intel_pasid_lookup_id(int pasid); +int intel_pasid_alloc_table(struct device *dev); +void intel_pasid_free_table(struct device *dev); +struct pasid_table *intel_pasid_get_table(struct device *dev); +int intel_pasid_get_dev_max_id(struct device *dev); +struct pasid_entry *intel_pasid_get_entry(struct device *dev, int pasid); +void intel_pasid_clear_entry(struct device *dev, int pasid); + +#endif /* __INTEL_PASID_H */ diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index 45f6e581cd56..eb308363e541 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -26,21 +26,19 @@ #include <linux/interrupt.h> #include <asm/page.h> +#include "intel-pasid.h" + #define PASID_ENTRY_P BIT_ULL(0) #define PASID_ENTRY_FLPM_5LP BIT_ULL(9) #define PASID_ENTRY_SRE BIT_ULL(11) static irqreturn_t prq_event_thread(int irq, void *d); -struct pasid_entry { - u64 val; -}; - struct pasid_state_entry { u64 val; }; -int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu) +int intel_svm_init(struct intel_iommu *iommu) { struct page *pages; int order; @@ -65,15 +63,6 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu) iommu->pasid_max = 0x20000; order = get_order(sizeof(struct pasid_entry) * iommu->pasid_max); - pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order); - if (!pages) { - pr_warn("IOMMU: %s: Failed to allocate PASID table\n", - iommu->name); - return -ENOMEM; - } - iommu->pasid_table = page_address(pages); - pr_info("%s: Allocated order %d PASID table.\n", iommu->name, order); - if (ecap_dis(iommu->ecap)) { /* Just making it explicit... */ BUILD_BUG_ON(sizeof(struct pasid_entry) != sizeof(struct pasid_state_entry)); @@ -85,24 +74,18 @@ int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu) iommu->name); } - idr_init(&iommu->pasid_idr); - return 0; } -int intel_svm_free_pasid_tables(struct intel_iommu *iommu) +int intel_svm_exit(struct intel_iommu *iommu) { int order = get_order(sizeof(struct pasid_entry) * iommu->pasid_max); - if (iommu->pasid_table) { - free_pages((unsigned long)iommu->pasid_table, order); - iommu->pasid_table = NULL; - } if (iommu->pasid_state_table) { free_pages((unsigned long)iommu->pasid_state_table, order); iommu->pasid_state_table = NULL; } - idr_destroy(&iommu->pasid_idr); + return 0; } @@ -278,11 +261,9 @@ static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm) * page) so that we end up taking a fault that the hardware really * *has* to handle gracefully without affecting other processes. */ - svm->iommu->pasid_table[svm->pasid].val = 0; - wmb(); - rcu_read_lock(); list_for_each_entry_rcu(sdev, &svm->devs, list) { + intel_pasid_clear_entry(sdev->dev, svm->pasid); intel_flush_pasid_dev(svm, sdev, svm->pasid); intel_flush_svm_range_dev(svm, sdev, 0, -1, 0, !svm->mm); } @@ -298,10 +279,12 @@ static const struct mmu_notifier_ops intel_mmuops = { }; static DEFINE_MUTEX(pasid_mutex); +static LIST_HEAD(global_svm_list); int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ops *ops) { struct intel_iommu *iommu = intel_svm_device_to_iommu(dev); + struct pasid_entry *entry; struct intel_svm_dev *sdev; struct intel_svm *svm = NULL; struct mm_struct *mm = NULL; @@ -309,7 +292,7 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ int pasid_max; int ret; - if (WARN_ON(!iommu || !iommu->pasid_table)) + if (!iommu) return -EINVAL; if (dev_is_pci(dev)) { @@ -329,13 +312,13 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ mutex_lock(&pasid_mutex); if (pasid && !(flags & SVM_FLAG_PRIVATE_PASID)) { - int i; + struct intel_svm *t; - idr_for_each_entry(&iommu->pasid_idr, svm, i) { - if (svm->mm != mm || - (svm->flags & SVM_FLAG_PRIVATE_PASID)) + list_for_each_entry(t, &global_svm_list, list) { + if (t->mm != mm || (t->flags & SVM_FLAG_PRIVATE_PASID)) continue; + svm = t; if (svm->pasid >= pasid_max) { dev_warn(dev, "Limited PASID width. Cannot use existing PASID %d\n", @@ -387,13 +370,13 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ } svm->iommu = iommu; - if (pasid_max > iommu->pasid_max) - pasid_max = iommu->pasid_max; + if (pasid_max > intel_pasid_max_id) + pasid_max = intel_pasid_max_id; /* Do not use PASID 0 in caching mode (virtualised IOMMU) */ - ret = idr_alloc(&iommu->pasid_idr, svm, - !!cap_caching_mode(iommu->cap), - pasid_max - 1, GFP_KERNEL); + ret = intel_pasid_alloc_id(svm, + !!cap_caching_mode(iommu->cap), + pasid_max - 1, GFP_KERNEL); if (ret < 0) { kfree(svm); kfree(sdev); @@ -404,11 +387,12 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ svm->mm = mm; svm->flags = flags; INIT_LIST_HEAD_RCU(&svm->devs); + INIT_LIST_HEAD(&svm->list); ret = -ENOMEM; if (mm) { ret = mmu_notifier_register(&svm->notifier, mm); if (ret) { - idr_remove(&svm->iommu->pasid_idr, svm->pasid); + intel_pasid_free_id(svm->pasid); kfree(svm); kfree(sdev); goto out; @@ -420,7 +404,8 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ if (cpu_feature_enabled(X86_FEATURE_LA57)) pasid_entry_val |= PASID_ENTRY_FLPM_5LP; - iommu->pasid_table[svm->pasid].val = pasid_entry_val; + entry = intel_pasid_get_entry(dev, svm->pasid); + entry->val = pasid_entry_val; wmb(); @@ -430,6 +415,8 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ */ if (cap_caching_mode(iommu->cap)) intel_flush_pasid_dev(svm, sdev, svm->pasid); + + list_add_tail(&svm->list, &global_svm_list); } list_add_rcu(&sdev->list, &svm->devs); @@ -453,10 +440,10 @@ int intel_svm_unbind_mm(struct device *dev, int pasid) mutex_lock(&pasid_mutex); iommu = intel_svm_device_to_iommu(dev); - if (!iommu || !iommu->pasid_table) + if (!iommu) goto out; - svm = idr_find(&iommu->pasid_idr, pasid); + svm = intel_pasid_lookup_id(pasid); if (!svm) goto out; @@ -476,15 +463,15 @@ int intel_svm_unbind_mm(struct device *dev, int pasid) intel_flush_pasid_dev(svm, sdev, svm->pasid); intel_flush_svm_range_dev(svm, sdev, 0, -1, 0, !svm->mm); kfree_rcu(sdev, rcu); + intel_pasid_clear_entry(dev, svm->pasid); if (list_empty(&svm->devs)) { - svm->iommu->pasid_table[svm->pasid].val = 0; - wmb(); - - idr_remove(&svm->iommu->pasid_idr, svm->pasid); + intel_pasid_free_id(svm->pasid); if (svm->mm) mmu_notifier_unregister(&svm->notifier, svm->mm); + list_del(&svm->list); + /* We mandate that no page faults may be outstanding * for the PASID when intel_svm_unbind_mm() is called. * If that is not obeyed, subtle errors will happen. @@ -511,10 +498,10 @@ int intel_svm_is_pasid_valid(struct device *dev, int pasid) mutex_lock(&pasid_mutex); iommu = intel_svm_device_to_iommu(dev); - if (!iommu || !iommu->pasid_table) + if (!iommu) goto out; - svm = idr_find(&iommu->pasid_idr, pasid); + svm = intel_pasid_lookup_id(pasid); if (!svm) goto out; @@ -612,7 +599,7 @@ static irqreturn_t prq_event_thread(int irq, void *d) if (!svm || svm->pasid != req->pasid) { rcu_read_lock(); - svm = idr_find(&iommu->pasid_idr, req->pasid); + svm = intel_pasid_lookup_id(req->pasid); /* It *can't* go away, because the driver is not permitted * to unbind the mm while any page faults are outstanding. * So we only need RCU to protect the internal idr code. */ diff --git a/drivers/iommu/iommu-debugfs.c b/drivers/iommu/iommu-debugfs.c new file mode 100644 index 000000000000..3b1bf88fd1b0 --- /dev/null +++ b/drivers/iommu/iommu-debugfs.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * IOMMU debugfs core infrastructure + * + * Copyright (C) 2018 Advanced Micro Devices, Inc. + * + * Author: Gary R Hook <gary.hook@amd.com> + */ + +#include <linux/pci.h> +#include <linux/iommu.h> +#include <linux/debugfs.h> + +struct dentry *iommu_debugfs_dir; + +/** + * iommu_debugfs_setup - create the top-level iommu directory in debugfs + * + * Provide base enablement for using debugfs to expose internal data of an + * IOMMU driver. When called, this function creates the + * /sys/kernel/debug/iommu directory. + * + * Emit a strong warning at boot time to indicate that this feature is + * enabled. + * + * This function is called from iommu_init; drivers may then call + * iommu_debugfs_new_driver_dir() to instantiate a vendor-specific + * directory to be used to expose internal data. + */ +void iommu_debugfs_setup(void) +{ + if (!iommu_debugfs_dir) { + iommu_debugfs_dir = debugfs_create_dir("iommu", NULL); + pr_warn("\n"); + pr_warn("*************************************************************\n"); + pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); + pr_warn("** **\n"); + pr_warn("** IOMMU DebugFS SUPPORT HAS BEEN ENABLED IN THIS KERNEL **\n"); + pr_warn("** **\n"); + pr_warn("** This means that this kernel is built to expose internal **\n"); + pr_warn("** IOMMU data structures, which may compromise security on **\n"); + pr_warn("** your system. **\n"); + pr_warn("** **\n"); + pr_warn("** If you see this message and you are not debugging the **\n"); + pr_warn("** kernel, report this immediately to your vendor! **\n"); + pr_warn("** **\n"); + pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); + pr_warn("*************************************************************\n"); + } +} + +/** + * iommu_debugfs_new_driver_dir - create a vendor directory under debugfs/iommu + * @vendor: name of the vendor-specific subdirectory to create + * + * This function is called by an IOMMU driver to create the top-level debugfs + * directory for that driver. + * + * Return: upon success, a pointer to the dentry for the new directory. + * NULL in case of failure. + */ +struct dentry *iommu_debugfs_new_driver_dir(const char *vendor) +{ + return debugfs_create_dir(vendor, iommu_debugfs_dir); +} +EXPORT_SYMBOL_GPL(iommu_debugfs_new_driver_dir); diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 63b37563db7e..8c15c5980299 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -36,7 +36,11 @@ static struct kset *iommu_group_kset; static DEFINE_IDA(iommu_group_ida); +#ifdef CONFIG_IOMMU_DEFAULT_PASSTHROUGH +static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_IDENTITY; +#else static unsigned int iommu_def_domain_type = IOMMU_DOMAIN_DMA; +#endif struct iommu_callback_data { const struct iommu_ops *ops; @@ -294,11 +298,39 @@ static ssize_t iommu_group_show_resv_regions(struct iommu_group *group, return (str - buf); } +static ssize_t iommu_group_show_type(struct iommu_group *group, + char *buf) +{ + char *type = "unknown\n"; + + if (group->default_domain) { + switch (group->default_domain->type) { + case IOMMU_DOMAIN_BLOCKED: + type = "blocked\n"; + break; + case IOMMU_DOMAIN_IDENTITY: + type = "identity\n"; + break; + case IOMMU_DOMAIN_UNMANAGED: + type = "unmanaged\n"; + break; + case IOMMU_DOMAIN_DMA: + type = "DMA"; + break; + } + } + strcpy(buf, type); + + return strlen(type); +} + static IOMMU_GROUP_ATTR(name, S_IRUGO, iommu_group_show_name, NULL); static IOMMU_GROUP_ATTR(reserved_regions, 0444, iommu_group_show_resv_regions, NULL); +static IOMMU_GROUP_ATTR(type, 0444, iommu_group_show_type, NULL); + static void iommu_group_release(struct kobject *kobj) { struct iommu_group *group = to_iommu_group(kobj); @@ -380,6 +412,10 @@ struct iommu_group *iommu_group_alloc(void) if (ret) return ERR_PTR(ret); + ret = iommu_group_create_file(group, &iommu_group_attr_type); + if (ret) + return ERR_PTR(ret); + pr_debug("Allocated group %d\n", group->id); return group; @@ -1637,8 +1673,8 @@ size_t iommu_unmap_fast(struct iommu_domain *domain, } EXPORT_SYMBOL_GPL(iommu_unmap_fast); -size_t default_iommu_map_sg(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg, unsigned int nents, int prot) +size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, + struct scatterlist *sg, unsigned int nents, int prot) { struct scatterlist *s; size_t mapped = 0; @@ -1678,7 +1714,7 @@ out_err: return 0; } -EXPORT_SYMBOL_GPL(default_iommu_map_sg); +EXPORT_SYMBOL_GPL(iommu_map_sg); int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr, phys_addr_t paddr, u64 size, int prot) @@ -1748,6 +1784,8 @@ static int __init iommu_init(void) NULL, kernel_kobj); BUG_ON(!iommu_group_kset); + iommu_debugfs_setup(); + return 0; } core_initcall(iommu_init); diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c index 40ae6e87cb88..3102f2cd2a31 100644 --- a/drivers/iommu/ipmmu-vmsa.c +++ b/drivers/iommu/ipmmu-vmsa.c @@ -47,6 +47,7 @@ struct ipmmu_features { unsigned int number_of_contexts; bool setup_imbuscr; bool twobit_imttbcr_sl0; + bool reserved_context; }; struct ipmmu_vmsa_device { @@ -73,7 +74,7 @@ struct ipmmu_vmsa_domain { struct io_pgtable_ops *iop; unsigned int context_id; - spinlock_t lock; /* Protects mappings */ + struct mutex mutex; /* Protects mappings */ }; static struct ipmmu_vmsa_domain *to_vmsa_domain(struct iommu_domain *dom) @@ -194,7 +195,9 @@ static struct ipmmu_vmsa_device *to_ipmmu(struct device *dev) #define IMPMBA(n) (0x0280 + ((n) * 4)) #define IMPMBD(n) (0x02c0 + ((n) * 4)) -#define IMUCTR(n) (0x0300 + ((n) * 16)) +#define IMUCTR(n) ((n) < 32 ? IMUCTR0(n) : IMUCTR32(n)) +#define IMUCTR0(n) (0x0300 + ((n) * 16)) +#define IMUCTR32(n) (0x0600 + (((n) - 32) * 16)) #define IMUCTR_FIXADDEN (1 << 31) #define IMUCTR_FIXADD_MASK (0xff << 16) #define IMUCTR_FIXADD_SHIFT 16 @@ -204,7 +207,9 @@ static struct ipmmu_vmsa_device *to_ipmmu(struct device *dev) #define IMUCTR_FLUSH (1 << 1) #define IMUCTR_MMUEN (1 << 0) -#define IMUASID(n) (0x0308 + ((n) * 16)) +#define IMUASID(n) ((n) < 32 ? IMUASID0(n) : IMUASID32(n)) +#define IMUASID0(n) (0x0308 + ((n) * 16)) +#define IMUASID32(n) (0x0608 + (((n) - 32) * 16)) #define IMUASID_ASID8_MASK (0xff << 8) #define IMUASID_ASID8_SHIFT 8 #define IMUASID_ASID0_MASK (0xff << 0) @@ -595,7 +600,7 @@ static struct iommu_domain *__ipmmu_domain_alloc(unsigned type) if (!domain) return NULL; - spin_lock_init(&domain->lock); + mutex_init(&domain->mutex); return &domain->io_domain; } @@ -641,7 +646,6 @@ static int ipmmu_attach_device(struct iommu_domain *io_domain, struct iommu_fwspec *fwspec = dev->iommu_fwspec; struct ipmmu_vmsa_device *mmu = to_ipmmu(dev); struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain); - unsigned long flags; unsigned int i; int ret = 0; @@ -650,7 +654,7 @@ static int ipmmu_attach_device(struct iommu_domain *io_domain, return -ENXIO; } - spin_lock_irqsave(&domain->lock, flags); + mutex_lock(&domain->mutex); if (!domain->mmu) { /* The domain hasn't been used yet, initialize it. */ @@ -674,7 +678,7 @@ static int ipmmu_attach_device(struct iommu_domain *io_domain, } else dev_info(dev, "Reusing IPMMU context %u\n", domain->context_id); - spin_unlock_irqrestore(&domain->lock, flags); + mutex_unlock(&domain->mutex); if (ret < 0) return ret; @@ -756,8 +760,12 @@ static bool ipmmu_slave_whitelist(struct device *dev) return false; } -static const struct soc_device_attribute soc_r8a7795[] = { +static const struct soc_device_attribute soc_rcar_gen3[] = { { .soc_id = "r8a7795", }, + { .soc_id = "r8a7796", }, + { .soc_id = "r8a77965", }, + { .soc_id = "r8a77970", }, + { .soc_id = "r8a77995", }, { /* sentinel */ } }; @@ -765,7 +773,7 @@ static int ipmmu_of_xlate(struct device *dev, struct of_phandle_args *spec) { /* For R-Car Gen3 use a white list to opt-in slave devices */ - if (soc_device_match(soc_r8a7795) && !ipmmu_slave_whitelist(dev)) + if (soc_device_match(soc_rcar_gen3) && !ipmmu_slave_whitelist(dev)) return -ENODEV; iommu_fwspec_add_ids(dev, spec->args, 1); @@ -889,7 +897,6 @@ static const struct iommu_ops ipmmu_ops = { .unmap = ipmmu_unmap, .flush_iotlb_all = ipmmu_iotlb_sync, .iotlb_sync = ipmmu_iotlb_sync, - .map_sg = default_iommu_map_sg, .iova_to_phys = ipmmu_iova_to_phys, .add_device = ipmmu_add_device, .remove_device = ipmmu_remove_device, @@ -917,14 +924,16 @@ static const struct ipmmu_features ipmmu_features_default = { .number_of_contexts = 1, /* software only tested with one context */ .setup_imbuscr = true, .twobit_imttbcr_sl0 = false, + .reserved_context = false, }; -static const struct ipmmu_features ipmmu_features_r8a7795 = { +static const struct ipmmu_features ipmmu_features_rcar_gen3 = { .use_ns_alias_offset = false, .has_cache_leaf_nodes = true, .number_of_contexts = 8, .setup_imbuscr = false, .twobit_imttbcr_sl0 = true, + .reserved_context = true, }; static const struct of_device_id ipmmu_of_ids[] = { @@ -933,7 +942,19 @@ static const struct of_device_id ipmmu_of_ids[] = { .data = &ipmmu_features_default, }, { .compatible = "renesas,ipmmu-r8a7795", - .data = &ipmmu_features_r8a7795, + .data = &ipmmu_features_rcar_gen3, + }, { + .compatible = "renesas,ipmmu-r8a7796", + .data = &ipmmu_features_rcar_gen3, + }, { + .compatible = "renesas,ipmmu-r8a77965", + .data = &ipmmu_features_rcar_gen3, + }, { + .compatible = "renesas,ipmmu-r8a77970", + .data = &ipmmu_features_rcar_gen3, + }, { + .compatible = "renesas,ipmmu-r8a77995", + .data = &ipmmu_features_rcar_gen3, }, { /* Terminator */ }, @@ -955,7 +976,7 @@ static int ipmmu_probe(struct platform_device *pdev) } mmu->dev = &pdev->dev; - mmu->num_utlbs = 32; + mmu->num_utlbs = 48; spin_lock_init(&mmu->lock); bitmap_zero(mmu->ctx, IPMMU_CTX_MAX); mmu->features = of_device_get_match_data(&pdev->dev); @@ -1018,6 +1039,11 @@ static int ipmmu_probe(struct platform_device *pdev) } ipmmu_device_reset(mmu); + + if (mmu->features->reserved_context) { + dev_info(&pdev->dev, "IPMMU context 0 is reserved\n"); + set_bit(0, mmu->ctx); + } } /* @@ -1081,12 +1107,19 @@ static struct platform_driver ipmmu_driver = { static int __init ipmmu_init(void) { + struct device_node *np; static bool setup_done; int ret; if (setup_done) return 0; + np = of_find_matching_node(NULL, ipmmu_of_ids); + if (!np) + return 0; + + of_node_put(np); + ret = platform_driver_register(&ipmmu_driver); if (ret < 0) return ret; @@ -1110,6 +1143,10 @@ module_exit(ipmmu_exit); IOMMU_OF_DECLARE(ipmmu_vmsa_iommu_of, "renesas,ipmmu-vmsa"); IOMMU_OF_DECLARE(ipmmu_r8a7795_iommu_of, "renesas,ipmmu-r8a7795"); +IOMMU_OF_DECLARE(ipmmu_r8a7796_iommu_of, "renesas,ipmmu-r8a7796"); +IOMMU_OF_DECLARE(ipmmu_r8a77965_iommu_of, "renesas,ipmmu-r8a77965"); +IOMMU_OF_DECLARE(ipmmu_r8a77970_iommu_of, "renesas,ipmmu-r8a77970"); +IOMMU_OF_DECLARE(ipmmu_r8a77995_iommu_of, "renesas,ipmmu-r8a77995"); MODULE_DESCRIPTION("IOMMU API for Renesas VMSA-compatible IPMMU"); MODULE_AUTHOR("Laurent Pinchart <laurent.pinchart@ideasonboard.com>"); diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c index 0d3350463a3f..30f4469e952c 100644 --- a/drivers/iommu/msm_iommu.c +++ b/drivers/iommu/msm_iommu.c @@ -395,20 +395,15 @@ static int msm_iommu_add_device(struct device *dev) struct msm_iommu_dev *iommu; struct iommu_group *group; unsigned long flags; - int ret = 0; spin_lock_irqsave(&msm_iommu_lock, flags); - iommu = find_iommu_for_dev(dev); + spin_unlock_irqrestore(&msm_iommu_lock, flags); + if (iommu) iommu_device_link(&iommu->iommu, dev); else - ret = -ENODEV; - - spin_unlock_irqrestore(&msm_iommu_lock, flags); - - if (ret) - return ret; + return -ENODEV; group = iommu_group_get_for_dev(dev); if (IS_ERR(group)) @@ -425,13 +420,12 @@ static void msm_iommu_remove_device(struct device *dev) unsigned long flags; spin_lock_irqsave(&msm_iommu_lock, flags); - iommu = find_iommu_for_dev(dev); + spin_unlock_irqrestore(&msm_iommu_lock, flags); + if (iommu) iommu_device_unlink(&iommu->iommu, dev); - spin_unlock_irqrestore(&msm_iommu_lock, flags); - iommu_group_remove_device(dev); } @@ -708,7 +702,6 @@ static struct iommu_ops msm_iommu_ops = { .detach_dev = msm_iommu_detach_dev, .map = msm_iommu_map, .unmap = msm_iommu_unmap, - .map_sg = default_iommu_map_sg, .iova_to_phys = msm_iommu_iova_to_phys, .add_device = msm_iommu_add_device, .remove_device = msm_iommu_remove_device, diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index f2832a10fcea..f9f69f7111a9 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -495,7 +495,6 @@ static struct iommu_ops mtk_iommu_ops = { .detach_dev = mtk_iommu_detach_device, .map = mtk_iommu_map, .unmap = mtk_iommu_unmap, - .map_sg = default_iommu_map_sg, .flush_iotlb_all = mtk_iommu_iotlb_sync, .iotlb_sync = mtk_iommu_iotlb_sync, .iova_to_phys = mtk_iommu_iova_to_phys, diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index a7c2a973784f..676c029494e4 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -531,7 +531,6 @@ static struct iommu_ops mtk_iommu_ops = { .detach_dev = mtk_iommu_detach_device, .map = mtk_iommu_map, .unmap = mtk_iommu_unmap, - .map_sg = default_iommu_map_sg, .iova_to_phys = mtk_iommu_iova_to_phys, .add_device = mtk_iommu_add_device, .remove_device = mtk_iommu_remove_device, diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index af4a8e7fcd27..d2fb347aa4ff 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -550,7 +550,7 @@ static u32 *iopte_alloc(struct omap_iommu *obj, u32 *iopgd, pte_ready: iopte = iopte_offset(iopgd, da); - *pt_dma = virt_to_phys(iopte); + *pt_dma = iopgd_page_paddr(iopgd); dev_vdbg(obj->dev, "%s: da:%08x pgd:%p *pgd:%08x pte:%p *pte:%08x\n", __func__, da, iopgd, *iopgd, iopte, *iopte); @@ -738,7 +738,7 @@ static size_t iopgtable_clear_entry_core(struct omap_iommu *obj, u32 da) } bytes *= nent; memset(iopte, 0, nent * sizeof(*iopte)); - pt_dma = virt_to_phys(iopte); + pt_dma = iopgd_page_paddr(iopgd); flush_iopte_range(obj->dev, pt_dma, pt_offset, nent); /* @@ -1548,7 +1548,6 @@ static const struct iommu_ops omap_iommu_ops = { .detach_dev = omap_iommu_detach_dev, .map = omap_iommu_map, .unmap = omap_iommu_unmap, - .map_sg = default_iommu_map_sg, .iova_to_phys = omap_iommu_iova_to_phys, .add_device = omap_iommu_add_device, .remove_device = omap_iommu_remove_device, diff --git a/drivers/iommu/qcom_iommu.c b/drivers/iommu/qcom_iommu.c index fe88a4880d3a..6e914b3a2b4b 100644 --- a/drivers/iommu/qcom_iommu.c +++ b/drivers/iommu/qcom_iommu.c @@ -590,7 +590,6 @@ static const struct iommu_ops qcom_iommu_ops = { .detach_dev = qcom_iommu_detach_dev, .map = qcom_iommu_map, .unmap = qcom_iommu_unmap, - .map_sg = default_iommu_map_sg, .flush_iotlb_all = qcom_iommu_iotlb_sync, .iotlb_sync = qcom_iommu_iotlb_sync, .iova_to_phys = qcom_iommu_iova_to_phys, diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index 054cd2c8e9c8..90625cdd3b66 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -1110,7 +1110,6 @@ static const struct iommu_ops rk_iommu_ops = { .detach_dev = rk_iommu_detach_device, .map = rk_iommu_map, .unmap = rk_iommu_unmap, - .map_sg = default_iommu_map_sg, .add_device = rk_iommu_add_device, .remove_device = rk_iommu_remove_device, .iova_to_phys = rk_iommu_iova_to_phys, diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c index a004f6da35f2..7b1361d57a17 100644 --- a/drivers/iommu/tegra-gart.c +++ b/drivers/iommu/tegra-gart.c @@ -377,7 +377,6 @@ static const struct iommu_ops gart_iommu_ops = { .remove_device = gart_iommu_remove_device, .device_group = generic_device_group, .map = gart_iommu_map, - .map_sg = default_iommu_map_sg, .unmap = gart_iommu_unmap, .iova_to_phys = gart_iommu_iova_to_phys, .pgsize_bitmap = GART_IOMMU_PGSIZES, diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index 44d40bc771b5..0d03341317c4 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -876,7 +876,6 @@ static const struct iommu_ops tegra_smmu_ops = { .device_group = tegra_smmu_device_group, .map = tegra_smmu_map, .unmap = tegra_smmu_unmap, - .map_sg = default_iommu_map_sg, .iova_to_phys = tegra_smmu_iova_to_phys, .of_xlate = tegra_smmu_of_xlate, .pgsize_bitmap = SZ_4K, diff --git a/drivers/media/platform/vsp1/vsp1_drm.c b/drivers/media/platform/vsp1/vsp1_drm.c index edb35a5c57ea..a99fc0ced7a7 100644 --- a/drivers/media/platform/vsp1/vsp1_drm.c +++ b/drivers/media/platform/vsp1/vsp1_drm.c @@ -728,9 +728,6 @@ EXPORT_SYMBOL_GPL(vsp1_du_setup_lif); */ void vsp1_du_atomic_begin(struct device *dev, unsigned int pipe_index) { - struct vsp1_device *vsp1 = dev_get_drvdata(dev); - - mutex_lock(&vsp1->drm->lock); } EXPORT_SYMBOL_GPL(vsp1_du_atomic_begin); @@ -846,6 +843,7 @@ void vsp1_du_atomic_flush(struct device *dev, unsigned int pipe_index, drm_pipe->crc = cfg->crc; + mutex_lock(&vsp1->drm->lock); vsp1_du_pipeline_setup_inputs(vsp1, pipe); vsp1_du_pipeline_configure(pipe); mutex_unlock(&vsp1->drm->lock); diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index fcfab6635f9c..81b150e5dfdb 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -174,6 +174,7 @@ static int lirc_bpf_detach(struct rc_dev *rcdev, struct bpf_prog *prog) rcu_assign_pointer(raw->progs, new_array); bpf_prog_array_free(old_array); + bpf_prog_put(prog); unlock: mutex_unlock(&ir_raw_handler_lock); return ret; diff --git a/drivers/media/rc/rc-ir-raw.c b/drivers/media/rc/rc-ir-raw.c index 2e0066b1a31c..e7948908e78c 100644 --- a/drivers/media/rc/rc-ir-raw.c +++ b/drivers/media/rc/rc-ir-raw.c @@ -30,13 +30,13 @@ static int ir_raw_event_thread(void *data) while (kfifo_out(&raw->kfifo, &ev, 1)) { if (is_timing_event(ev)) { if (ev.duration == 0) - dev_err(&dev->dev, "nonsensical timing event of duration 0"); + dev_warn_once(&dev->dev, "nonsensical timing event of duration 0"); if (is_timing_event(raw->prev_ev) && !is_transition(&ev, &raw->prev_ev)) - dev_err(&dev->dev, "two consecutive events of type %s", - TO_STR(ev.pulse)); + dev_warn_once(&dev->dev, "two consecutive events of type %s", + TO_STR(ev.pulse)); if (raw->prev_ev.reset && ev.pulse == 0) - dev_err(&dev->dev, "timing event after reset should be pulse"); + dev_warn_once(&dev->dev, "timing event after reset should be pulse"); } list_for_each_entry(handler, &ir_raw_handler_list, list) if (dev->enabled_protocols & diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c index 2e222d9ee01f..ca68e1d2b2f9 100644 --- a/drivers/media/rc/rc-main.c +++ b/drivers/media/rc/rc-main.c @@ -679,6 +679,14 @@ static void ir_timer_repeat(struct timer_list *t) spin_unlock_irqrestore(&dev->keylock, flags); } +static unsigned int repeat_period(int protocol) +{ + if (protocol >= ARRAY_SIZE(protocols)) + return 100; + + return protocols[protocol].repeat_period; +} + /** * rc_repeat() - signals that a key is still pressed * @dev: the struct rc_dev descriptor of the device @@ -691,7 +699,7 @@ void rc_repeat(struct rc_dev *dev) { unsigned long flags; unsigned int timeout = nsecs_to_jiffies(dev->timeout) + - msecs_to_jiffies(protocols[dev->last_protocol].repeat_period); + msecs_to_jiffies(repeat_period(dev->last_protocol)); struct lirc_scancode sc = { .scancode = dev->last_scancode, .rc_proto = dev->last_protocol, .keycode = dev->keypressed ? dev->last_keycode : KEY_RESERVED, @@ -803,7 +811,7 @@ void rc_keydown(struct rc_dev *dev, enum rc_proto protocol, u32 scancode, if (dev->keypressed) { dev->keyup_jiffies = jiffies + nsecs_to_jiffies(dev->timeout) + - msecs_to_jiffies(protocols[protocol].repeat_period); + msecs_to_jiffies(repeat_period(protocol)); mod_timer(&dev->timer_keyup, dev->keyup_jiffies); } spin_unlock_irqrestore(&dev->keylock, flags); diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c index 75f781c11e89..de4e6e5bf304 100644 --- a/drivers/mmc/host/mxcmmc.c +++ b/drivers/mmc/host/mxcmmc.c @@ -293,9 +293,10 @@ static void mxcmci_swap_buffers(struct mmc_data *data) int i; for_each_sg(data->sg, sg, data->sg_len, i) { - void *buf = kmap_atomic(sg_page(sg) + sg->offset; + void *buf = kmap_atomic(sg_page(sg) + sg->offset); buffer_swap32(buf, sg->length); kunmap_atomic(buf); + } } #else static inline void mxcmci_swap_buffers(struct mmc_data *data) {} diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 63e3844c5bec..217b790d22ed 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1717,6 +1717,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, goto err_upper_unlink; } + bond->nest_level = dev_get_nest_level(bond_dev) + 1; + /* If the mode uses primary, then the following is handled by * bond_change_active_slave(). */ @@ -1764,7 +1766,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, if (bond_mode_can_use_xmit_hash(bond)) bond_update_slave_arr(bond, NULL); - bond->nest_level = dev_get_nest_level(bond_dev); netdev_info(bond_dev, "Enslaving %s as %s interface with %s link\n", slave_dev->name, @@ -3415,6 +3416,13 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res, } } +static int bond_get_nest_level(struct net_device *bond_dev) +{ + struct bonding *bond = netdev_priv(bond_dev); + + return bond->nest_level; +} + static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats) { @@ -3423,7 +3431,7 @@ static void bond_get_stats(struct net_device *bond_dev, struct list_head *iter; struct slave *slave; - spin_lock(&bond->stats_lock); + spin_lock_nested(&bond->stats_lock, bond_get_nest_level(bond_dev)); memcpy(stats, &bond->bond_stats, sizeof(*stats)); rcu_read_lock(); @@ -4227,6 +4235,7 @@ static const struct net_device_ops bond_netdev_ops = { .ndo_neigh_setup = bond_neigh_setup, .ndo_vlan_rx_add_vid = bond_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = bond_vlan_rx_kill_vid, + .ndo_get_lock_subclass = bond_get_nest_level, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_netpoll_setup = bond_netpoll_setup, .ndo_netpoll_cleanup = bond_netpoll_cleanup, @@ -4725,6 +4734,7 @@ static int bond_init(struct net_device *bond_dev) if (!bond->wq) return -ENOMEM; + bond->nest_level = SINGLE_DEPTH_NESTING; netdev_lockdep_set_classes(bond_dev); list_add_tail(&bond->bond_list, &bn->dev_list); diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 98663c50ded0..4d5d01cb8141 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -743,15 +743,20 @@ const struct bond_option *bond_opt_get(unsigned int option) static int bond_option_mode_set(struct bonding *bond, const struct bond_opt_value *newval) { - if (!bond_mode_uses_arp(newval->value) && bond->params.arp_interval) { - netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n", - newval->string); - /* disable arp monitoring */ - bond->params.arp_interval = 0; - /* set miimon to default value */ - bond->params.miimon = BOND_DEFAULT_MIIMON; - netdev_dbg(bond->dev, "Setting MII monitoring interval to %d\n", - bond->params.miimon); + if (!bond_mode_uses_arp(newval->value)) { + if (bond->params.arp_interval) { + netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n", + newval->string); + /* disable arp monitoring */ + bond->params.arp_interval = 0; + } + + if (!bond->params.miimon) { + /* set miimon to default value */ + bond->params.miimon = BOND_DEFAULT_MIIMON; + netdev_dbg(bond->dev, "Setting MII monitoring interval to %d\n", + bond->params.miimon); + } } if (newval->value == BOND_MODE_ALB) diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index b397a33f3d32..9b449400376b 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -634,10 +634,12 @@ static int m_can_clk_start(struct m_can_priv *priv) int err; err = pm_runtime_get_sync(priv->device); - if (err) + if (err < 0) { pm_runtime_put_noidle(priv->device); + return err; + } - return err; + return 0; } static void m_can_clk_stop(struct m_can_priv *priv) @@ -1109,7 +1111,8 @@ static void m_can_chip_config(struct net_device *dev) } else { /* Version 3.1.x or 3.2.x */ - cccr &= ~(CCCR_TEST | CCCR_MON | CCCR_BRSE | CCCR_FDOE); + cccr &= ~(CCCR_TEST | CCCR_MON | CCCR_BRSE | CCCR_FDOE | + CCCR_NISO); /* Only 3.2.x has NISO Bit implemented */ if (priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO) @@ -1642,8 +1645,6 @@ static int m_can_plat_probe(struct platform_device *pdev) priv->can.clock.freq = clk_get_rate(cclk); priv->mram_base = mram_addr; - m_can_of_parse_mram(priv, mram_config_vals); - platform_set_drvdata(pdev, dev); SET_NETDEV_DEV(dev, &pdev->dev); @@ -1666,6 +1667,8 @@ static int m_can_plat_probe(struct platform_device *pdev) goto clk_disable; } + m_can_of_parse_mram(priv, mram_config_vals); + devm_can_led_init(dev); of_can_transceiver(dev); @@ -1687,8 +1690,6 @@ failed_ret: return ret; } -/* TODO: runtime PM with power down or sleep mode */ - static __maybe_unused int m_can_suspend(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); @@ -1715,8 +1716,6 @@ static __maybe_unused int m_can_resume(struct device *dev) pinctrl_pm_select_default_state(dev); - m_can_init_ram(priv); - priv->can.state = CAN_STATE_ERROR_ACTIVE; if (netif_running(ndev)) { @@ -1726,6 +1725,7 @@ static __maybe_unused int m_can_resume(struct device *dev) if (ret) return ret; + m_can_init_ram(priv); m_can_start(ndev); netif_device_attach(ndev); netif_start_queue(ndev); diff --git a/drivers/net/can/mscan/mpc5xxx_can.c b/drivers/net/can/mscan/mpc5xxx_can.c index c7427bdd3a4b..2949a381a94d 100644 --- a/drivers/net/can/mscan/mpc5xxx_can.c +++ b/drivers/net/can/mscan/mpc5xxx_can.c @@ -86,6 +86,11 @@ static u32 mpc52xx_can_get_clock(struct platform_device *ofdev, return 0; } cdm = of_iomap(np_cdm, 0); + if (!cdm) { + of_node_put(np_cdm); + dev_err(&ofdev->dev, "can't map clock node!\n"); + return 0; + } if (in_8(&cdm->ipb_clk_sel) & 0x1) freq *= 2; diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c index b9e28578bc7b..455a3797a200 100644 --- a/drivers/net/can/peak_canfd/peak_pciefd_main.c +++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c @@ -58,6 +58,10 @@ MODULE_LICENSE("GPL v2"); #define PCIEFD_REG_SYS_VER1 0x0040 /* version reg #1 */ #define PCIEFD_REG_SYS_VER2 0x0044 /* version reg #2 */ +#define PCIEFD_FW_VERSION(x, y, z) (((u32)(x) << 24) | \ + ((u32)(y) << 16) | \ + ((u32)(z) << 8)) + /* System Control Registers Bits */ #define PCIEFD_SYS_CTL_TS_RST 0x00000001 /* timestamp clock */ #define PCIEFD_SYS_CTL_CLK_EN 0x00000002 /* system clock */ @@ -782,6 +786,21 @@ static int peak_pciefd_probe(struct pci_dev *pdev, "%ux CAN-FD PCAN-PCIe FPGA v%u.%u.%u:\n", can_count, hw_ver_major, hw_ver_minor, hw_ver_sub); +#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT + /* FW < v3.3.0 DMA logic doesn't handle correctly the mix of 32-bit and + * 64-bit logical addresses: this workaround forces usage of 32-bit + * DMA addresses only when such a fw is detected. + */ + if (PCIEFD_FW_VERSION(hw_ver_major, hw_ver_minor, hw_ver_sub) < + PCIEFD_FW_VERSION(3, 3, 0)) { + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) + dev_warn(&pdev->dev, + "warning: can't set DMA mask %llxh (err %d)\n", + DMA_BIT_MASK(32), err); + } +#endif + /* stop system clock */ pciefd_sys_writereg(pciefd, PCIEFD_SYS_CTL_CLK_EN, PCIEFD_REG_SYS_CTL_CLR); diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index 12ff0020ecd6..b7dfd4109d24 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -1072,6 +1072,7 @@ static void ems_usb_disconnect(struct usb_interface *intf) usb_free_urb(dev->intr_urb); kfree(dev->intr_in_buffer); + kfree(dev->tx_msg_buffer); } } diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index 89aec07c225f..5a24039733ef 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -2,6 +2,7 @@ * * Copyright (C) 2012 - 2014 Xilinx, Inc. * Copyright (C) 2009 PetaLogix. All rights reserved. + * Copyright (C) 2017 Sandvik Mining and Construction Oy * * Description: * This driver is developed for Axi CAN IP and for Zynq CANPS Controller. @@ -25,8 +26,10 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/of.h> +#include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/skbuff.h> +#include <linux/spinlock.h> #include <linux/string.h> #include <linux/types.h> #include <linux/can/dev.h> @@ -101,7 +104,7 @@ enum xcan_reg { #define XCAN_INTR_ALL (XCAN_IXR_TXOK_MASK | XCAN_IXR_BSOFF_MASK |\ XCAN_IXR_WKUP_MASK | XCAN_IXR_SLP_MASK | \ XCAN_IXR_RXNEMP_MASK | XCAN_IXR_ERROR_MASK | \ - XCAN_IXR_ARBLST_MASK | XCAN_IXR_RXOK_MASK) + XCAN_IXR_RXOFLW_MASK | XCAN_IXR_ARBLST_MASK) /* CAN register bit shift - XCAN_<REG>_<BIT>_SHIFT */ #define XCAN_BTR_SJW_SHIFT 7 /* Synchronous jump width */ @@ -118,6 +121,7 @@ enum xcan_reg { /** * struct xcan_priv - This definition define CAN driver instance * @can: CAN private data structure. + * @tx_lock: Lock for synchronizing TX interrupt handling * @tx_head: Tx CAN packets ready to send on the queue * @tx_tail: Tx CAN packets successfully sended on the queue * @tx_max: Maximum number packets the driver can send @@ -132,6 +136,7 @@ enum xcan_reg { */ struct xcan_priv { struct can_priv can; + spinlock_t tx_lock; unsigned int tx_head; unsigned int tx_tail; unsigned int tx_max; @@ -159,6 +164,11 @@ static const struct can_bittiming_const xcan_bittiming_const = { .brp_inc = 1, }; +#define XCAN_CAP_WATERMARK 0x0001 +struct xcan_devtype_data { + unsigned int caps; +}; + /** * xcan_write_reg_le - Write a value to the device register little endian * @priv: Driver private data structure @@ -238,6 +248,10 @@ static int set_reset_mode(struct net_device *ndev) usleep_range(500, 10000); } + /* reset clears FIFOs */ + priv->tx_head = 0; + priv->tx_tail = 0; + return 0; } @@ -392,6 +406,7 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev) struct net_device_stats *stats = &ndev->stats; struct can_frame *cf = (struct can_frame *)skb->data; u32 id, dlc, data[2] = {0, 0}; + unsigned long flags; if (can_dropped_invalid_skb(ndev, skb)) return NETDEV_TX_OK; @@ -439,6 +454,9 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev) data[1] = be32_to_cpup((__be32 *)(cf->data + 4)); can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max); + + spin_lock_irqsave(&priv->tx_lock, flags); + priv->tx_head++; /* Write the Frame to Xilinx CAN TX FIFO */ @@ -454,10 +472,16 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev) stats->tx_bytes += cf->can_dlc; } + /* Clear TX-FIFO-empty interrupt for xcan_tx_interrupt() */ + if (priv->tx_max > 1) + priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXFEMP_MASK); + /* Check if the TX buffer is full */ if ((priv->tx_head - priv->tx_tail) == priv->tx_max) netif_stop_queue(ndev); + spin_unlock_irqrestore(&priv->tx_lock, flags); + return NETDEV_TX_OK; } @@ -530,6 +554,123 @@ static int xcan_rx(struct net_device *ndev) } /** + * xcan_current_error_state - Get current error state from HW + * @ndev: Pointer to net_device structure + * + * Checks the current CAN error state from the HW. Note that this + * only checks for ERROR_PASSIVE and ERROR_WARNING. + * + * Return: + * ERROR_PASSIVE or ERROR_WARNING if either is active, ERROR_ACTIVE + * otherwise. + */ +static enum can_state xcan_current_error_state(struct net_device *ndev) +{ + struct xcan_priv *priv = netdev_priv(ndev); + u32 status = priv->read_reg(priv, XCAN_SR_OFFSET); + + if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK) + return CAN_STATE_ERROR_PASSIVE; + else if (status & XCAN_SR_ERRWRN_MASK) + return CAN_STATE_ERROR_WARNING; + else + return CAN_STATE_ERROR_ACTIVE; +} + +/** + * xcan_set_error_state - Set new CAN error state + * @ndev: Pointer to net_device structure + * @new_state: The new CAN state to be set + * @cf: Error frame to be populated or NULL + * + * Set new CAN error state for the device, updating statistics and + * populating the error frame if given. + */ +static void xcan_set_error_state(struct net_device *ndev, + enum can_state new_state, + struct can_frame *cf) +{ + struct xcan_priv *priv = netdev_priv(ndev); + u32 ecr = priv->read_reg(priv, XCAN_ECR_OFFSET); + u32 txerr = ecr & XCAN_ECR_TEC_MASK; + u32 rxerr = (ecr & XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT; + + priv->can.state = new_state; + + if (cf) { + cf->can_id |= CAN_ERR_CRTL; + cf->data[6] = txerr; + cf->data[7] = rxerr; + } + + switch (new_state) { + case CAN_STATE_ERROR_PASSIVE: + priv->can.can_stats.error_passive++; + if (cf) + cf->data[1] = (rxerr > 127) ? + CAN_ERR_CRTL_RX_PASSIVE : + CAN_ERR_CRTL_TX_PASSIVE; + break; + case CAN_STATE_ERROR_WARNING: + priv->can.can_stats.error_warning++; + if (cf) + cf->data[1] |= (txerr > rxerr) ? + CAN_ERR_CRTL_TX_WARNING : + CAN_ERR_CRTL_RX_WARNING; + break; + case CAN_STATE_ERROR_ACTIVE: + if (cf) + cf->data[1] |= CAN_ERR_CRTL_ACTIVE; + break; + default: + /* non-ERROR states are handled elsewhere */ + WARN_ON(1); + break; + } +} + +/** + * xcan_update_error_state_after_rxtx - Update CAN error state after RX/TX + * @ndev: Pointer to net_device structure + * + * If the device is in a ERROR-WARNING or ERROR-PASSIVE state, check if + * the performed RX/TX has caused it to drop to a lesser state and set + * the interface state accordingly. + */ +static void xcan_update_error_state_after_rxtx(struct net_device *ndev) +{ + struct xcan_priv *priv = netdev_priv(ndev); + enum can_state old_state = priv->can.state; + enum can_state new_state; + + /* changing error state due to successful frame RX/TX can only + * occur from these states + */ + if (old_state != CAN_STATE_ERROR_WARNING && + old_state != CAN_STATE_ERROR_PASSIVE) + return; + + new_state = xcan_current_error_state(ndev); + + if (new_state != old_state) { + struct sk_buff *skb; + struct can_frame *cf; + + skb = alloc_can_err_skb(ndev, &cf); + + xcan_set_error_state(ndev, new_state, skb ? cf : NULL); + + if (skb) { + struct net_device_stats *stats = &ndev->stats; + + stats->rx_packets++; + stats->rx_bytes += cf->can_dlc; + netif_rx(skb); + } + } +} + +/** * xcan_err_interrupt - error frame Isr * @ndev: net_device pointer * @isr: interrupt status register value @@ -544,16 +685,12 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr) struct net_device_stats *stats = &ndev->stats; struct can_frame *cf; struct sk_buff *skb; - u32 err_status, status, txerr = 0, rxerr = 0; + u32 err_status; skb = alloc_can_err_skb(ndev, &cf); err_status = priv->read_reg(priv, XCAN_ESR_OFFSET); priv->write_reg(priv, XCAN_ESR_OFFSET, err_status); - txerr = priv->read_reg(priv, XCAN_ECR_OFFSET) & XCAN_ECR_TEC_MASK; - rxerr = ((priv->read_reg(priv, XCAN_ECR_OFFSET) & - XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT); - status = priv->read_reg(priv, XCAN_SR_OFFSET); if (isr & XCAN_IXR_BSOFF_MASK) { priv->can.state = CAN_STATE_BUS_OFF; @@ -563,28 +700,10 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr) can_bus_off(ndev); if (skb) cf->can_id |= CAN_ERR_BUSOFF; - } else if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK) { - priv->can.state = CAN_STATE_ERROR_PASSIVE; - priv->can.can_stats.error_passive++; - if (skb) { - cf->can_id |= CAN_ERR_CRTL; - cf->data[1] = (rxerr > 127) ? - CAN_ERR_CRTL_RX_PASSIVE : - CAN_ERR_CRTL_TX_PASSIVE; - cf->data[6] = txerr; - cf->data[7] = rxerr; - } - } else if (status & XCAN_SR_ERRWRN_MASK) { - priv->can.state = CAN_STATE_ERROR_WARNING; - priv->can.can_stats.error_warning++; - if (skb) { - cf->can_id |= CAN_ERR_CRTL; - cf->data[1] |= (txerr > rxerr) ? - CAN_ERR_CRTL_TX_WARNING : - CAN_ERR_CRTL_RX_WARNING; - cf->data[6] = txerr; - cf->data[7] = rxerr; - } + } else { + enum can_state new_state = xcan_current_error_state(ndev); + + xcan_set_error_state(ndev, new_state, skb ? cf : NULL); } /* Check for Arbitration lost interrupt */ @@ -600,7 +719,6 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr) if (isr & XCAN_IXR_RXOFLW_MASK) { stats->rx_over_errors++; stats->rx_errors++; - priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK); if (skb) { cf->can_id |= CAN_ERR_CRTL; cf->data[1] |= CAN_ERR_CRTL_RX_OVERFLOW; @@ -709,26 +827,20 @@ static int xcan_rx_poll(struct napi_struct *napi, int quota) isr = priv->read_reg(priv, XCAN_ISR_OFFSET); while ((isr & XCAN_IXR_RXNEMP_MASK) && (work_done < quota)) { - if (isr & XCAN_IXR_RXOK_MASK) { - priv->write_reg(priv, XCAN_ICR_OFFSET, - XCAN_IXR_RXOK_MASK); - work_done += xcan_rx(ndev); - } else { - priv->write_reg(priv, XCAN_ICR_OFFSET, - XCAN_IXR_RXNEMP_MASK); - break; - } + work_done += xcan_rx(ndev); priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_RXNEMP_MASK); isr = priv->read_reg(priv, XCAN_ISR_OFFSET); } - if (work_done) + if (work_done) { can_led_event(ndev, CAN_LED_EVENT_RX); + xcan_update_error_state_after_rxtx(ndev); + } if (work_done < quota) { napi_complete_done(napi, work_done); ier = priv->read_reg(priv, XCAN_IER_OFFSET); - ier |= (XCAN_IXR_RXOK_MASK | XCAN_IXR_RXNEMP_MASK); + ier |= XCAN_IXR_RXNEMP_MASK; priv->write_reg(priv, XCAN_IER_OFFSET, ier); } return work_done; @@ -743,18 +855,71 @@ static void xcan_tx_interrupt(struct net_device *ndev, u32 isr) { struct xcan_priv *priv = netdev_priv(ndev); struct net_device_stats *stats = &ndev->stats; + unsigned int frames_in_fifo; + int frames_sent = 1; /* TXOK => at least 1 frame was sent */ + unsigned long flags; + int retries = 0; + + /* Synchronize with xmit as we need to know the exact number + * of frames in the FIFO to stay in sync due to the TXFEMP + * handling. + * This also prevents a race between netif_wake_queue() and + * netif_stop_queue(). + */ + spin_lock_irqsave(&priv->tx_lock, flags); + + frames_in_fifo = priv->tx_head - priv->tx_tail; + + if (WARN_ON_ONCE(frames_in_fifo == 0)) { + /* clear TXOK anyway to avoid getting back here */ + priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK); + spin_unlock_irqrestore(&priv->tx_lock, flags); + return; + } + + /* Check if 2 frames were sent (TXOK only means that at least 1 + * frame was sent). + */ + if (frames_in_fifo > 1) { + WARN_ON(frames_in_fifo > priv->tx_max); + + /* Synchronize TXOK and isr so that after the loop: + * (1) isr variable is up-to-date at least up to TXOK clear + * time. This avoids us clearing a TXOK of a second frame + * but not noticing that the FIFO is now empty and thus + * marking only a single frame as sent. + * (2) No TXOK is left. Having one could mean leaving a + * stray TXOK as we might process the associated frame + * via TXFEMP handling as we read TXFEMP *after* TXOK + * clear to satisfy (1). + */ + while ((isr & XCAN_IXR_TXOK_MASK) && !WARN_ON(++retries == 100)) { + priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK); + isr = priv->read_reg(priv, XCAN_ISR_OFFSET); + } - while ((priv->tx_head - priv->tx_tail > 0) && - (isr & XCAN_IXR_TXOK_MASK)) { + if (isr & XCAN_IXR_TXFEMP_MASK) { + /* nothing in FIFO anymore */ + frames_sent = frames_in_fifo; + } + } else { + /* single frame in fifo, just clear TXOK */ priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK); + } + + while (frames_sent--) { can_get_echo_skb(ndev, priv->tx_tail % priv->tx_max); priv->tx_tail++; stats->tx_packets++; - isr = priv->read_reg(priv, XCAN_ISR_OFFSET); } - can_led_event(ndev, CAN_LED_EVENT_TX); + netif_wake_queue(ndev); + + spin_unlock_irqrestore(&priv->tx_lock, flags); + + can_led_event(ndev, CAN_LED_EVENT_TX); + xcan_update_error_state_after_rxtx(ndev); } /** @@ -773,6 +938,7 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id) struct net_device *ndev = (struct net_device *)dev_id; struct xcan_priv *priv = netdev_priv(ndev); u32 isr, ier; + u32 isr_errors; /* Get the interrupt status from Xilinx CAN */ isr = priv->read_reg(priv, XCAN_ISR_OFFSET); @@ -791,18 +957,17 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id) xcan_tx_interrupt(ndev, isr); /* Check for the type of error interrupt and Processing it */ - if (isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK | - XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK)) { - priv->write_reg(priv, XCAN_ICR_OFFSET, (XCAN_IXR_ERROR_MASK | - XCAN_IXR_RXOFLW_MASK | XCAN_IXR_BSOFF_MASK | - XCAN_IXR_ARBLST_MASK)); + isr_errors = isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK | + XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK); + if (isr_errors) { + priv->write_reg(priv, XCAN_ICR_OFFSET, isr_errors); xcan_err_interrupt(ndev, isr); } /* Check for the type of receive interrupt and Processing it */ - if (isr & (XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK)) { + if (isr & XCAN_IXR_RXNEMP_MASK) { ier = priv->read_reg(priv, XCAN_IER_OFFSET); - ier &= ~(XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK); + ier &= ~XCAN_IXR_RXNEMP_MASK; priv->write_reg(priv, XCAN_IER_OFFSET, ier); napi_schedule(&priv->napi); } @@ -819,13 +984,9 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id) static void xcan_chip_stop(struct net_device *ndev) { struct xcan_priv *priv = netdev_priv(ndev); - u32 ier; /* Disable interrupts and leave the can in configuration mode */ - ier = priv->read_reg(priv, XCAN_IER_OFFSET); - ier &= ~XCAN_INTR_ALL; - priv->write_reg(priv, XCAN_IER_OFFSET, ier); - priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK); + set_reset_mode(ndev); priv->can.state = CAN_STATE_STOPPED; } @@ -958,10 +1119,15 @@ static const struct net_device_ops xcan_netdev_ops = { */ static int __maybe_unused xcan_suspend(struct device *dev) { - if (!device_may_wakeup(dev)) - return pm_runtime_force_suspend(dev); + struct net_device *ndev = dev_get_drvdata(dev); - return 0; + if (netif_running(ndev)) { + netif_stop_queue(ndev); + netif_device_detach(ndev); + xcan_chip_stop(ndev); + } + + return pm_runtime_force_suspend(dev); } /** @@ -973,11 +1139,27 @@ static int __maybe_unused xcan_suspend(struct device *dev) */ static int __maybe_unused xcan_resume(struct device *dev) { - if (!device_may_wakeup(dev)) - return pm_runtime_force_resume(dev); + struct net_device *ndev = dev_get_drvdata(dev); + int ret; - return 0; + ret = pm_runtime_force_resume(dev); + if (ret) { + dev_err(dev, "pm_runtime_force_resume failed on resume\n"); + return ret; + } + + if (netif_running(ndev)) { + ret = xcan_chip_start(ndev); + if (ret) { + dev_err(dev, "xcan_chip_start failed on resume\n"); + return ret; + } + + netif_device_attach(ndev); + netif_start_queue(ndev); + } + return 0; } /** @@ -992,14 +1174,6 @@ static int __maybe_unused xcan_runtime_suspend(struct device *dev) struct net_device *ndev = dev_get_drvdata(dev); struct xcan_priv *priv = netdev_priv(ndev); - if (netif_running(ndev)) { - netif_stop_queue(ndev); - netif_device_detach(ndev); - } - - priv->write_reg(priv, XCAN_MSR_OFFSET, XCAN_MSR_SLEEP_MASK); - priv->can.state = CAN_STATE_SLEEPING; - clk_disable_unprepare(priv->bus_clk); clk_disable_unprepare(priv->can_clk); @@ -1018,7 +1192,6 @@ static int __maybe_unused xcan_runtime_resume(struct device *dev) struct net_device *ndev = dev_get_drvdata(dev); struct xcan_priv *priv = netdev_priv(ndev); int ret; - u32 isr, status; ret = clk_prepare_enable(priv->bus_clk); if (ret) { @@ -1032,27 +1205,6 @@ static int __maybe_unused xcan_runtime_resume(struct device *dev) return ret; } - priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK); - isr = priv->read_reg(priv, XCAN_ISR_OFFSET); - status = priv->read_reg(priv, XCAN_SR_OFFSET); - - if (netif_running(ndev)) { - if (isr & XCAN_IXR_BSOFF_MASK) { - priv->can.state = CAN_STATE_BUS_OFF; - priv->write_reg(priv, XCAN_SRR_OFFSET, - XCAN_SRR_RESET_MASK); - } else if ((status & XCAN_SR_ESTAT_MASK) == - XCAN_SR_ESTAT_MASK) { - priv->can.state = CAN_STATE_ERROR_PASSIVE; - } else if (status & XCAN_SR_ERRWRN_MASK) { - priv->can.state = CAN_STATE_ERROR_WARNING; - } else { - priv->can.state = CAN_STATE_ERROR_ACTIVE; - } - netif_device_attach(ndev); - netif_start_queue(ndev); - } - return 0; } @@ -1061,6 +1213,18 @@ static const struct dev_pm_ops xcan_dev_pm_ops = { SET_RUNTIME_PM_OPS(xcan_runtime_suspend, xcan_runtime_resume, NULL) }; +static const struct xcan_devtype_data xcan_zynq_data = { + .caps = XCAN_CAP_WATERMARK, +}; + +/* Match table for OF platform binding */ +static const struct of_device_id xcan_of_match[] = { + { .compatible = "xlnx,zynq-can-1.0", .data = &xcan_zynq_data }, + { .compatible = "xlnx,axi-can-1.00.a", }, + { /* end of list */ }, +}; +MODULE_DEVICE_TABLE(of, xcan_of_match); + /** * xcan_probe - Platform registration call * @pdev: Handle to the platform device structure @@ -1075,8 +1239,10 @@ static int xcan_probe(struct platform_device *pdev) struct resource *res; /* IO mem resources */ struct net_device *ndev; struct xcan_priv *priv; + const struct of_device_id *of_id; + int caps = 0; void __iomem *addr; - int ret, rx_max, tx_max; + int ret, rx_max, tx_max, tx_fifo_depth; /* Get the virtual base address for the device */ res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -1086,7 +1252,8 @@ static int xcan_probe(struct platform_device *pdev) goto err; } - ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth", &tx_max); + ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth", + &tx_fifo_depth); if (ret < 0) goto err; @@ -1094,6 +1261,30 @@ static int xcan_probe(struct platform_device *pdev) if (ret < 0) goto err; + of_id = of_match_device(xcan_of_match, &pdev->dev); + if (of_id) { + const struct xcan_devtype_data *devtype_data = of_id->data; + + if (devtype_data) + caps = devtype_data->caps; + } + + /* There is no way to directly figure out how many frames have been + * sent when the TXOK interrupt is processed. If watermark programming + * is supported, we can have 2 frames in the FIFO and use TXFEMP + * to determine if 1 or 2 frames have been sent. + * Theoretically we should be able to use TXFWMEMP to determine up + * to 3 frames, but it seems that after putting a second frame in the + * FIFO, with watermark at 2 frames, it can happen that TXFWMEMP (less + * than 2 frames in FIFO) is set anyway with no TXOK (a frame was + * sent), which is not a sensible state - possibly TXFWMEMP is not + * completely synchronized with the rest of the bits? + */ + if (caps & XCAN_CAP_WATERMARK) + tx_max = min(tx_fifo_depth, 2); + else + tx_max = 1; + /* Create a CAN device instance */ ndev = alloc_candev(sizeof(struct xcan_priv), tx_max); if (!ndev) @@ -1108,6 +1299,7 @@ static int xcan_probe(struct platform_device *pdev) CAN_CTRLMODE_BERR_REPORTING; priv->reg_base = addr; priv->tx_max = tx_max; + spin_lock_init(&priv->tx_lock); /* Get IRQ for the device */ ndev->irq = platform_get_irq(pdev, 0); @@ -1172,9 +1364,9 @@ static int xcan_probe(struct platform_device *pdev) pm_runtime_put(&pdev->dev); - netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth:%d\n", + netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth: actual %d, using %d\n", priv->reg_base, ndev->irq, priv->can.clock.freq, - priv->tx_max); + tx_fifo_depth, priv->tx_max); return 0; @@ -1208,14 +1400,6 @@ static int xcan_remove(struct platform_device *pdev) return 0; } -/* Match table for OF platform binding */ -static const struct of_device_id xcan_of_match[] = { - { .compatible = "xlnx,zynq-can-1.0", }, - { .compatible = "xlnx,axi-can-1.00.a", }, - { /* end of list */ }, -}; -MODULE_DEVICE_TABLE(of, xcan_of_match); - static struct platform_driver xcan_driver = { .probe = xcan_probe, .remove = xcan_remove, diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 437cd6eb4faa..bb28c701381a 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -343,6 +343,7 @@ static const struct irq_domain_ops mv88e6xxx_g1_irq_domain_ops = { .xlate = irq_domain_xlate_twocell, }; +/* To be called with reg_lock held */ static void mv88e6xxx_g1_irq_free_common(struct mv88e6xxx_chip *chip) { int irq, virq; @@ -362,9 +363,15 @@ static void mv88e6xxx_g1_irq_free_common(struct mv88e6xxx_chip *chip) static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip) { - mv88e6xxx_g1_irq_free_common(chip); - + /* + * free_irq must be called without reg_lock taken because the irq + * handler takes this lock, too. + */ free_irq(chip->irq, chip); + + mutex_lock(&chip->reg_lock); + mv88e6xxx_g1_irq_free_common(chip); + mutex_unlock(&chip->reg_lock); } static int mv88e6xxx_g1_irq_setup_common(struct mv88e6xxx_chip *chip) @@ -469,10 +476,12 @@ static int mv88e6xxx_irq_poll_setup(struct mv88e6xxx_chip *chip) static void mv88e6xxx_irq_poll_free(struct mv88e6xxx_chip *chip) { - mv88e6xxx_g1_irq_free_common(chip); - kthread_cancel_delayed_work_sync(&chip->irq_poll_work); kthread_destroy_worker(chip->kworker); + + mutex_lock(&chip->reg_lock); + mv88e6xxx_g1_irq_free_common(chip); + mutex_unlock(&chip->reg_lock); } int mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int addr, int reg, u16 mask) @@ -2608,7 +2617,6 @@ static const struct mv88e6xxx_ops mv88e6085_ops = { .rmu_disable = mv88e6085_g1_rmu_disable, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, - .serdes_power = mv88e6341_serdes_power, }; static const struct mv88e6xxx_ops mv88e6095_ops = { @@ -2774,6 +2782,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = { .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, + .serdes_power = mv88e6341_serdes_power, .gpio_ops = &mv88e6352_gpio_ops, }; @@ -2951,7 +2960,6 @@ static const struct mv88e6xxx_ops mv88e6175_ops = { .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, - .serdes_power = mv88e6341_serdes_power, }; static const struct mv88e6xxx_ops mv88e6176_ops = { @@ -3327,6 +3335,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = { .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, + .serdes_power = mv88e6341_serdes_power, .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6390_avb_ops, }; @@ -4506,12 +4515,10 @@ out_g2_irq: if (chip->info->g2_irqs > 0) mv88e6xxx_g2_irq_free(chip); out_g1_irq: - mutex_lock(&chip->reg_lock); if (chip->irq > 0) mv88e6xxx_g1_irq_free(chip); else mv88e6xxx_irq_poll_free(chip); - mutex_unlock(&chip->reg_lock); out: if (pdata) dev_put(pdata->netdev); @@ -4539,12 +4546,10 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev) if (chip->info->g2_irqs > 0) mv88e6xxx_g2_irq_free(chip); - mutex_lock(&chip->reg_lock); if (chip->irq > 0) mv88e6xxx_g1_irq_free(chip); else mv88e6xxx_irq_poll_free(chip); - mutex_unlock(&chip->reg_lock); } static const struct of_device_id mv88e6xxx_of_match[] = { diff --git a/drivers/net/ethernet/3com/Kconfig b/drivers/net/ethernet/3com/Kconfig index 5b7658bcf020..5c3ef9fc8207 100644 --- a/drivers/net/ethernet/3com/Kconfig +++ b/drivers/net/ethernet/3com/Kconfig @@ -32,7 +32,7 @@ config EL3 config 3C515 tristate "3c515 ISA \"Fast EtherLink\"" - depends on ISA && ISA_DMA_API + depends on ISA && ISA_DMA_API && !PPC32 ---help--- If you have a 3Com ISA EtherLink XL "Corkscrew" 3c515 Fast Ethernet network card, say Y here. diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 1b9d3130af4d..17f12c18d225 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -333,6 +333,7 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev, memset(&io_sq->desc_addr, 0x0, sizeof(io_sq->desc_addr)); + io_sq->dma_addr_bits = ena_dev->dma_addr_bits; io_sq->desc_entry_size = (io_sq->direction == ENA_COM_IO_QUEUE_DIRECTION_TX) ? sizeof(struct ena_eth_io_tx_desc) : diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig index f273af136fc7..9e5cf5583c87 100644 --- a/drivers/net/ethernet/amd/Kconfig +++ b/drivers/net/ethernet/amd/Kconfig @@ -44,7 +44,7 @@ config AMD8111_ETH config LANCE tristate "AMD LANCE and PCnet (AT1500 and NE2100) support" - depends on ISA && ISA_DMA_API && !ARM + depends on ISA && ISA_DMA_API && !ARM && !PPC32 ---help--- If you have a network (Ethernet) card of this type, say Y here. Some LinkSys cards are of this type. @@ -138,7 +138,7 @@ config PCMCIA_NMCLAN config NI65 tristate "NI6510 support" - depends on ISA && ISA_DMA_API && !ARM + depends on ISA && ISA_DMA_API && !ARM && !PPC32 ---help--- If you have a network (Ethernet) card of this type, say Y here. diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 4b5d625de8f0..8a3a60bb2688 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -1111,14 +1111,14 @@ static void xgbe_phy_adjust_link(struct xgbe_prv_data *pdata) if (pdata->tx_pause != pdata->phy.tx_pause) { new_state = 1; - pdata->hw_if.config_tx_flow_control(pdata); pdata->tx_pause = pdata->phy.tx_pause; + pdata->hw_if.config_tx_flow_control(pdata); } if (pdata->rx_pause != pdata->phy.rx_pause) { new_state = 1; - pdata->hw_if.config_rx_flow_control(pdata); pdata->rx_pause = pdata->phy.rx_pause; + pdata->hw_if.config_rx_flow_control(pdata); } /* Speed support */ diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 94270f654b3b..7087b88550db 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -1686,6 +1686,7 @@ static struct sk_buff *atl1c_alloc_skb(struct atl1c_adapter *adapter) skb = build_skb(page_address(page) + adapter->rx_page_offset, adapter->rx_frag_size); if (likely(skb)) { + skb_reserve(skb, NET_SKB_PAD); adapter->rx_page_offset += adapter->rx_frag_size; if (adapter->rx_page_offset >= PAGE_SIZE) adapter->rx_page = NULL; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index da18aa239acb..a4a90b6cdb46 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -3388,14 +3388,18 @@ static int bnx2x_set_rss_flags(struct bnx2x *bp, struct ethtool_rxnfc *info) DP(BNX2X_MSG_ETHTOOL, "rss re-configured, UDP 4-tupple %s\n", udp_rss_requested ? "enabled" : "disabled"); - return bnx2x_rss(bp, &bp->rss_conf_obj, false, true); + if (bp->state == BNX2X_STATE_OPEN) + return bnx2x_rss(bp, &bp->rss_conf_obj, false, + true); } else if ((info->flow_type == UDP_V6_FLOW) && (bp->rss_conf_obj.udp_rss_v6 != udp_rss_requested)) { bp->rss_conf_obj.udp_rss_v6 = udp_rss_requested; DP(BNX2X_MSG_ETHTOOL, "rss re-configured, UDP 4-tupple %s\n", udp_rss_requested ? "enabled" : "disabled"); - return bnx2x_rss(bp, &bp->rss_conf_obj, false, true); + if (bp->state == BNX2X_STATE_OPEN) + return bnx2x_rss(bp, &bp->rss_conf_obj, false, + true); } return 0; @@ -3509,7 +3513,10 @@ static int bnx2x_set_rxfh(struct net_device *dev, const u32 *indir, bp->rss_conf_obj.ind_table[i] = indir[i] + bp->fp->cl_id; } - return bnx2x_config_rss_eth(bp, false); + if (bp->state == BNX2X_STATE_OPEN) + return bnx2x_config_rss_eth(bp, false); + + return 0; } /** diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index bc03c175a3cd..a8926e97935e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -3072,6 +3072,7 @@ static void cxgb_del_udp_tunnel(struct net_device *netdev, adapter->geneve_port = 0; t4_write_reg(adapter, MPS_RX_GENEVE_TYPE_A, 0); + break; default: return; } @@ -3157,6 +3158,7 @@ static void cxgb_add_udp_tunnel(struct net_device *netdev, t4_write_reg(adapter, MPS_RX_GENEVE_TYPE_A, GENEVE_V(be16_to_cpu(ti->port)) | GENEVE_EN_F); + break; default: return; } diff --git a/drivers/net/ethernet/cirrus/Kconfig b/drivers/net/ethernet/cirrus/Kconfig index 5ab912937aff..ec0b545197e2 100644 --- a/drivers/net/ethernet/cirrus/Kconfig +++ b/drivers/net/ethernet/cirrus/Kconfig @@ -19,6 +19,7 @@ if NET_VENDOR_CIRRUS config CS89x0 tristate "CS89x0 support" depends on ISA || EISA || ARM + depends on !PPC32 ---help--- Support for CS89x0 chipset based Ethernet cards. If you have a network (Ethernet) card of this type, say Y and read the file diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 90c645b8538e..60641e202534 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -2047,28 +2047,42 @@ static int enic_stop(struct net_device *netdev) return 0; } +static int _enic_change_mtu(struct net_device *netdev, int new_mtu) +{ + bool running = netif_running(netdev); + int err = 0; + + ASSERT_RTNL(); + if (running) { + err = enic_stop(netdev); + if (err) + return err; + } + + netdev->mtu = new_mtu; + + if (running) { + err = enic_open(netdev); + if (err) + return err; + } + + return 0; +} + static int enic_change_mtu(struct net_device *netdev, int new_mtu) { struct enic *enic = netdev_priv(netdev); - int running = netif_running(netdev); if (enic_is_dynamic(enic) || enic_is_sriov_vf(enic)) return -EOPNOTSUPP; - if (running) - enic_stop(netdev); - - netdev->mtu = new_mtu; - if (netdev->mtu > enic->port_mtu) netdev_warn(netdev, - "interface MTU (%d) set higher than port MTU (%d)\n", - netdev->mtu, enic->port_mtu); + "interface MTU (%d) set higher than port MTU (%d)\n", + netdev->mtu, enic->port_mtu); - if (running) - enic_open(netdev); - - return 0; + return _enic_change_mtu(netdev, new_mtu); } static void enic_change_mtu_work(struct work_struct *work) @@ -2076,47 +2090,9 @@ static void enic_change_mtu_work(struct work_struct *work) struct enic *enic = container_of(work, struct enic, change_mtu_work); struct net_device *netdev = enic->netdev; int new_mtu = vnic_dev_mtu(enic->vdev); - int err; - unsigned int i; - - new_mtu = max_t(int, ENIC_MIN_MTU, min_t(int, ENIC_MAX_MTU, new_mtu)); rtnl_lock(); - - /* Stop RQ */ - del_timer_sync(&enic->notify_timer); - - for (i = 0; i < enic->rq_count; i++) - napi_disable(&enic->napi[i]); - - vnic_intr_mask(&enic->intr[0]); - enic_synchronize_irqs(enic); - err = vnic_rq_disable(&enic->rq[0]); - if (err) { - rtnl_unlock(); - netdev_err(netdev, "Unable to disable RQ.\n"); - return; - } - vnic_rq_clean(&enic->rq[0], enic_free_rq_buf); - vnic_cq_clean(&enic->cq[0]); - vnic_intr_clean(&enic->intr[0]); - - /* Fill RQ with new_mtu-sized buffers */ - netdev->mtu = new_mtu; - vnic_rq_fill(&enic->rq[0], enic_rq_alloc_buf); - /* Need at least one buffer on ring to get going */ - if (vnic_rq_desc_used(&enic->rq[0]) == 0) { - rtnl_unlock(); - netdev_err(netdev, "Unable to alloc receive buffers.\n"); - return; - } - - /* Start RQ */ - vnic_rq_enable(&enic->rq[0]); - napi_enable(&enic->napi[0]); - vnic_intr_unmask(&enic->intr[0]); - enic_notify_timer_start(enic); - + (void)_enic_change_mtu(netdev, new_mtu); rtnl_unlock(); netdev_info(netdev, "interface MTU set as %d\n", netdev->mtu); @@ -2916,7 +2892,6 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) */ enic->port_mtu = enic->config.mtu; - (void)enic_change_mtu(netdev, enic->port_mtu); err = enic_set_mac_addr(netdev, enic->mac_addr); if (err) { @@ -3006,6 +2981,7 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* MTU range: 68 - 9000 */ netdev->min_mtu = ENIC_MIN_MTU; netdev->max_mtu = ENIC_MAX_MTU; + netdev->mtu = enic->port_mtu; err = register_netdev(netdev); if (err) { diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 5b122728dcb4..09e9da10b786 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -983,6 +983,7 @@ static int nic_dev_init(struct pci_dev *pdev) hinic_hwdev_cb_register(nic_dev->hwdev, HINIC_MGMT_MSG_CMD_LINK_STATUS, nic_dev, link_status_event_handler); + SET_NETDEV_DEV(netdev, &pdev->dev); err = register_netdev(netdev); if (err) { dev_err(&pdev->dev, "Failed to register netdev\n"); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c index 9128858479c4..2353ec829c04 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c @@ -229,6 +229,7 @@ netdev_tx_t hinic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) txq->txq_stats.tx_busy++; u64_stats_update_end(&txq->txq_stats.syncp); err = NETDEV_TX_BUSY; + wqe_size = 0; goto flush_skbs; } diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 7b1b5ac986d0..31bd56727022 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -2958,7 +2958,7 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave, u32 srqn = qp_get_srqn(qpc) & 0xffffff; int use_srq = (qp_get_srqn(qpc) >> 24) & 1; struct res_srq *srq; - int local_qpn = be32_to_cpu(qpc->local_qpn) & 0xffffff; + int local_qpn = vhcr->in_modifier & 0xffffff; err = adjust_qp_sched_queue(dev, slave, qpc, inbox); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c index 323ffe8bf7e4..456f30007ad6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c @@ -123,7 +123,7 @@ int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size, int i; buf->size = size; - buf->npages = 1 << get_order(size); + buf->npages = DIV_ROUND_UP(size, PAGE_SIZE); buf->page_shift = PAGE_SHIFT; buf->frags = kcalloc(buf->npages, sizeof(struct mlx5_buf_list), GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index 75e4308ba786..d258bb679271 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -381,14 +381,14 @@ static void arfs_may_expire_flow(struct mlx5e_priv *priv) HLIST_HEAD(del_list); spin_lock_bh(&priv->fs.arfs.arfs_lock); mlx5e_for_each_arfs_rule(arfs_rule, htmp, priv->fs.arfs.arfs_tables, i, j) { - if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA) - break; if (!work_pending(&arfs_rule->arfs_work) && rps_may_expire_flow(priv->netdev, arfs_rule->rxq, arfs_rule->flow_id, arfs_rule->filter_id)) { hlist_del_init(&arfs_rule->hlist); hlist_add_head(&arfs_rule->hlist, &del_list); + if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA) + break; } } spin_unlock_bh(&priv->fs.arfs.arfs_lock); @@ -711,6 +711,9 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, skb->protocol != htons(ETH_P_IPV6)) return -EPROTONOSUPPORT; + if (skb->encapsulation) + return -EPROTONOSUPPORT; + arfs_t = arfs_get_table(arfs, arfs_get_ip_proto(skb), skb->protocol); if (!arfs_t) return -EPROTONOSUPPORT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 0a52f31fef37..e33afa8d2417 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -275,7 +275,8 @@ int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets) } static int mlx5e_dbcnl_validate_ets(struct net_device *netdev, - struct ieee_ets *ets) + struct ieee_ets *ets, + bool zero_sum_allowed) { bool have_ets_tc = false; int bw_sum = 0; @@ -300,8 +301,9 @@ static int mlx5e_dbcnl_validate_ets(struct net_device *netdev, } if (have_ets_tc && bw_sum != 100) { - netdev_err(netdev, - "Failed to validate ETS: BW sum is illegal\n"); + if (bw_sum || (!bw_sum && !zero_sum_allowed)) + netdev_err(netdev, + "Failed to validate ETS: BW sum is illegal\n"); return -EINVAL; } return 0; @@ -316,7 +318,7 @@ static int mlx5e_dcbnl_ieee_setets(struct net_device *netdev, if (!MLX5_CAP_GEN(priv->mdev, ets)) return -EOPNOTSUPP; - err = mlx5e_dbcnl_validate_ets(netdev, ets); + err = mlx5e_dbcnl_validate_ets(netdev, ets, false); if (err) return err; @@ -642,12 +644,9 @@ static u8 mlx5e_dcbnl_setall(struct net_device *netdev) ets.prio_tc[i]); } - err = mlx5e_dbcnl_validate_ets(netdev, &ets); - if (err) { - netdev_err(netdev, - "%s, Failed to validate ETS: %d\n", __func__, err); + err = mlx5e_dbcnl_validate_ets(netdev, &ets, true); + if (err) goto out; - } err = mlx5e_dcbnl_ieee_setets_core(priv, &ets); if (err) { @@ -1173,6 +1172,8 @@ static int mlx5e_trust_initialize(struct mlx5e_priv *priv) struct mlx5_core_dev *mdev = priv->mdev; int err; + priv->dcbx_dp.trust_state = MLX5_QPTS_TRUST_PCP; + if (!MLX5_DSCP_SUPPORTED(mdev)) return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index dae4156a710d..c592678ab5f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3712,7 +3712,8 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, if (!reset) { params->sw_mtu = new_mtu; - set_mtu_cb(priv); + if (set_mtu_cb) + set_mtu_cb(priv); netdev->mtu = params->sw_mtu; goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 0edf4751a8ba..3a2c4e548226 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1957,6 +1957,10 @@ static bool actions_match_supported(struct mlx5e_priv *priv, else actions = flow->nic_attr->action; + if (flow->flags & MLX5E_TC_FLOW_EGRESS && + !(actions & MLX5_FLOW_CONTEXT_ACTION_DECAP)) + return false; + if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) return modify_header_match_supported(&parse_attr->spec, exts); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index b79d74860a30..40dba9e8af92 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1696,7 +1696,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) int vport_num; int err; - if (!MLX5_VPORT_MANAGER(dev)) + if (!MLX5_ESWITCH_MANAGER(dev)) return 0; esw_info(dev, @@ -1765,7 +1765,7 @@ abort: void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) { - if (!esw || !MLX5_VPORT_MANAGER(esw->dev)) + if (!esw || !MLX5_ESWITCH_MANAGER(esw->dev)) return; esw_info(esw->dev, "cleanup\n"); @@ -2216,6 +2216,6 @@ free_out: u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw) { - return esw->mode; + return ESW_ALLOWED(esw) ? esw->mode : SRIOV_NONE; } EXPORT_SYMBOL_GPL(mlx5_eswitch_mode); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index f1a86cea86a0..6ddb2565884d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1887,7 +1887,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft, if (flow_act->action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) { if (!fwd_next_prio_supported(ft)) return ERR_PTR(-EOPNOTSUPP); - if (dest) + if (dest_num) return ERR_PTR(-EINVAL); mutex_lock(&root->chain_lock); next_ft = find_next_chained_ft(prio); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index af3bb2f7a504..b7c21eb21a21 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -76,6 +76,7 @@ void mlx5i_init(struct mlx5_core_dev *mdev, void *ppriv) { struct mlx5e_priv *priv = mlx5i_epriv(netdev); + u16 max_mtu; /* priv init */ priv->mdev = mdev; @@ -84,6 +85,9 @@ void mlx5i_init(struct mlx5_core_dev *mdev, priv->ppriv = ppriv; mutex_init(&priv->state_lock); + mlx5_query_port_max_mtu(mdev, &max_mtu, 1); + netdev->mtu = max_mtu; + mlx5e_build_nic_params(mdev, &priv->channels.params, profile->max_nch(mdev), netdev->mtu); mlx5i_build_nic_params(mdev, &priv->channels.params); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 1e062e6b2587..3f767cde4c1d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -488,6 +488,7 @@ void mlx5_pps_event(struct mlx5_core_dev *mdev, void mlx5_init_clock(struct mlx5_core_dev *mdev) { struct mlx5_clock *clock = &mdev->clock; + u64 overflow_cycles; u64 ns; u64 frac = 0; u32 dev_freq; @@ -511,10 +512,17 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev) /* Calculate period in seconds to call the overflow watchdog - to make * sure counter is checked at least once every wrap around. + * The period is calculated as the minimum between max HW cycles count + * (The clock source mask) and max amount of cycles that can be + * multiplied by clock multiplier where the result doesn't exceed + * 64bits. */ - ns = cyclecounter_cyc2ns(&clock->cycles, clock->cycles.mask, + overflow_cycles = div64_u64(~0ULL >> 1, clock->cycles.mult); + overflow_cycles = min(overflow_cycles, clock->cycles.mask >> 1); + + ns = cyclecounter_cyc2ns(&clock->cycles, overflow_cycles, frac, &frac); - do_div(ns, NSEC_PER_SEC / 2 / HZ); + do_div(ns, NSEC_PER_SEC / HZ); clock->overflow_period = ns; mdev->clock_info_page = alloc_page(GFP_KERNEL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c index b97bb72b4db4..86478a6b99c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -113,35 +113,45 @@ err_db_free: return err; } -static void mlx5e_qp_set_frag_buf(struct mlx5_frag_buf *buf, - struct mlx5_wq_qp *qp) +static void mlx5_qp_set_frag_buf(struct mlx5_frag_buf *buf, + struct mlx5_wq_qp *qp) { + struct mlx5_frag_buf_ctrl *sq_fbc; struct mlx5_frag_buf *rqb, *sqb; - rqb = &qp->rq.fbc.frag_buf; + rqb = &qp->rq.fbc.frag_buf; *rqb = *buf; rqb->size = mlx5_wq_cyc_get_byte_size(&qp->rq); - rqb->npages = 1 << get_order(rqb->size); + rqb->npages = DIV_ROUND_UP(rqb->size, PAGE_SIZE); - sqb = &qp->sq.fbc.frag_buf; - *sqb = *buf; - sqb->size = mlx5_wq_cyc_get_byte_size(&qp->rq); - sqb->npages = 1 << get_order(sqb->size); + sq_fbc = &qp->sq.fbc; + sqb = &sq_fbc->frag_buf; + *sqb = *buf; + sqb->size = mlx5_wq_cyc_get_byte_size(&qp->sq); + sqb->npages = DIV_ROUND_UP(sqb->size, PAGE_SIZE); sqb->frags += rqb->npages; /* first part is for the rq */ + if (sq_fbc->strides_offset) + sqb->frags--; } int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, struct mlx5_wq_ctrl *wq_ctrl) { + u32 sq_strides_offset; int err; mlx5_fill_fbc(MLX5_GET(qpc, qpc, log_rq_stride) + 4, MLX5_GET(qpc, qpc, log_rq_size), &wq->rq.fbc); - mlx5_fill_fbc(ilog2(MLX5_SEND_WQE_BB), - MLX5_GET(qpc, qpc, log_sq_size), - &wq->sq.fbc); + + sq_strides_offset = + ((wq->rq.fbc.frag_sz_m1 + 1) % PAGE_SIZE) / MLX5_SEND_WQE_BB; + + mlx5_fill_fbc_offset(ilog2(MLX5_SEND_WQE_BB), + MLX5_GET(qpc, qpc, log_sq_size), + sq_strides_offset, + &wq->sq.fbc); err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node); if (err) { @@ -156,7 +166,7 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, goto err_db_free; } - mlx5e_qp_set_frag_buf(&wq_ctrl->buf, wq); + mlx5_qp_set_frag_buf(&wq_ctrl->buf, wq); wq->rq.db = &wq_ctrl->db.db[MLX5_RCV_DBR]; wq->sq.db = &wq_ctrl->db.db[MLX5_SND_DBR]; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c index 3c0d882ba183..f6f6a568d66a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c @@ -327,12 +327,16 @@ static void mlxsw_afa_resource_add(struct mlxsw_afa_block *block, list_add(&resource->list, &block->resource_list); } +static void mlxsw_afa_resource_del(struct mlxsw_afa_resource *resource) +{ + list_del(&resource->list); +} + static void mlxsw_afa_resources_destroy(struct mlxsw_afa_block *block) { struct mlxsw_afa_resource *resource, *tmp; list_for_each_entry_safe(resource, tmp, &block->resource_list, list) { - list_del(&resource->list); resource->destructor(block, resource); } } @@ -530,6 +534,7 @@ static void mlxsw_afa_fwd_entry_ref_destroy(struct mlxsw_afa_block *block, struct mlxsw_afa_fwd_entry_ref *fwd_entry_ref) { + mlxsw_afa_resource_del(&fwd_entry_ref->resource); mlxsw_afa_fwd_entry_put(block->afa, fwd_entry_ref->fwd_entry); kfree(fwd_entry_ref); } @@ -579,6 +584,7 @@ static void mlxsw_afa_counter_destroy(struct mlxsw_afa_block *block, struct mlxsw_afa_counter *counter) { + mlxsw_afa_resource_del(&counter->resource); block->afa->ops->counter_index_put(block->afa->ops_priv, counter->counter_index); kfree(counter); @@ -626,8 +632,8 @@ static char *mlxsw_afa_block_append_action(struct mlxsw_afa_block *block, char *oneact; char *actions; - if (WARN_ON(block->finished)) - return NULL; + if (block->finished) + return ERR_PTR(-EINVAL); if (block->cur_act_index + action_size > block->afa->max_acts_per_set) { struct mlxsw_afa_set *set; @@ -637,7 +643,7 @@ static char *mlxsw_afa_block_append_action(struct mlxsw_afa_block *block, */ set = mlxsw_afa_set_create(false); if (!set) - return NULL; + return ERR_PTR(-ENOBUFS); set->prev = block->cur_set; block->cur_act_index = 0; block->cur_set->next = set; @@ -724,8 +730,8 @@ int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block, MLXSW_AFA_VLAN_CODE, MLXSW_AFA_VLAN_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_vlan_pack(act, MLXSW_AFA_VLAN_VLAN_TAG_CMD_NOP, MLXSW_AFA_VLAN_CMD_SET_OUTER, vid, MLXSW_AFA_VLAN_CMD_SET_OUTER, pcp, @@ -806,8 +812,8 @@ int mlxsw_afa_block_append_drop(struct mlxsw_afa_block *block) MLXSW_AFA_TRAPDISC_CODE, MLXSW_AFA_TRAPDISC_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_NOP, MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD, 0); return 0; @@ -820,8 +826,8 @@ int mlxsw_afa_block_append_trap(struct mlxsw_afa_block *block, u16 trap_id) MLXSW_AFA_TRAPDISC_CODE, MLXSW_AFA_TRAPDISC_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP, MLXSW_AFA_TRAPDISC_FORWARD_ACTION_DISCARD, trap_id); @@ -836,8 +842,8 @@ int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block, MLXSW_AFA_TRAPDISC_CODE, MLXSW_AFA_TRAPDISC_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_TRAP, MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD, trap_id); @@ -856,6 +862,7 @@ static void mlxsw_afa_mirror_destroy(struct mlxsw_afa_block *block, struct mlxsw_afa_mirror *mirror) { + mlxsw_afa_resource_del(&mirror->resource); block->afa->ops->mirror_del(block->afa->ops_priv, mirror->local_in_port, mirror->span_id, @@ -908,8 +915,8 @@ mlxsw_afa_block_append_allocated_mirror(struct mlxsw_afa_block *block, char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_TRAPDISC_CODE, MLXSW_AFA_TRAPDISC_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_trapdisc_pack(act, MLXSW_AFA_TRAPDISC_TRAP_ACTION_NOP, MLXSW_AFA_TRAPDISC_FORWARD_ACTION_FORWARD, 0); mlxsw_afa_trapdisc_mirror_pack(act, true, mirror_agent); @@ -996,8 +1003,8 @@ int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block, act = mlxsw_afa_block_append_action(block, MLXSW_AFA_FORWARD_CODE, MLXSW_AFA_FORWARD_SIZE); - if (!act) { - err = -ENOBUFS; + if (IS_ERR(act)) { + err = PTR_ERR(act); goto err_append_action; } mlxsw_afa_forward_pack(act, MLXSW_AFA_FORWARD_TYPE_PBS, @@ -1052,8 +1059,8 @@ int mlxsw_afa_block_append_allocated_counter(struct mlxsw_afa_block *block, { char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_POLCNT_CODE, MLXSW_AFA_POLCNT_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_polcnt_pack(act, MLXSW_AFA_POLCNT_COUNTER_SET_TYPE_PACKETS_BYTES, counter_index); return 0; @@ -1123,8 +1130,8 @@ int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid) char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_VIRFWD_CODE, MLXSW_AFA_VIRFWD_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_virfwd_pack(act, MLXSW_AFA_VIRFWD_FID_CMD_SET, fid); return 0; } @@ -1193,8 +1200,8 @@ int mlxsw_afa_block_append_mcrouter(struct mlxsw_afa_block *block, char *act = mlxsw_afa_block_append_action(block, MLXSW_AFA_MCROUTER_CODE, MLXSW_AFA_MCROUTER_SIZE); - if (!act) - return -ENOBUFS; + if (IS_ERR(act)) + return PTR_ERR(act); mlxsw_afa_mcrouter_pack(act, MLXSW_AFA_MCROUTER_RPF_ACTION_TRAP, expected_irif, min_mtu, rmid_valid, kvdl_index); return 0; diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c index 1decf3a1cad3..e57d23746585 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.c +++ b/drivers/net/ethernet/netronome/nfp/flower/main.c @@ -80,7 +80,7 @@ nfp_flower_repr_get_type_and_port(struct nfp_app *app, u32 port_id, u8 *port) return NFP_REPR_TYPE_VF; } - return NFP_FLOWER_CMSG_PORT_TYPE_UNSPEC; + return __NFP_REPR_TYPE_MAX; } static struct net_device * @@ -91,6 +91,8 @@ nfp_flower_repr_get(struct nfp_app *app, u32 port_id) u8 port = 0; repr_type = nfp_flower_repr_get_type_and_port(app, port_id, &port); + if (repr_type > NFP_REPR_TYPE_MAX) + return NULL; reprs = rcu_dereference(app->reprs[repr_type]); if (!reprs) diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 78afe75129ab..382bb93cb090 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -317,7 +317,7 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, payload.dst_ipv4 = flow->daddr; /* If entry has expired send dst IP with all other fields 0. */ - if (!(neigh->nud_state & NUD_VALID)) { + if (!(neigh->nud_state & NUD_VALID) || neigh->dead) { nfp_tun_del_route_from_cache(app, payload.dst_ipv4); /* Trigger ARP to verify invalid neighbour state. */ neigh_event_send(neigh, NULL); diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 99973e10b179..5ede6408649d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -665,7 +665,7 @@ qed_sp_update_mcast_bin(struct qed_hwfn *p_hwfn, p_ramrod->common.update_approx_mcast_flg = 1; for (i = 0; i < ETH_MULTICAST_MAC_BINS_IN_REGS; i++) { - u32 *p_bins = (u32 *)p_params->bins; + u32 *p_bins = p_params->bins; p_ramrod->approx_mcast.bins[i] = cpu_to_le32(p_bins[i]); } @@ -1476,8 +1476,8 @@ qed_sp_eth_filter_mcast(struct qed_hwfn *p_hwfn, enum spq_mode comp_mode, struct qed_spq_comp_cb *p_comp_data) { - unsigned long bins[ETH_MULTICAST_MAC_BINS_IN_REGS]; struct vport_update_ramrod_data *p_ramrod = NULL; + u32 bins[ETH_MULTICAST_MAC_BINS_IN_REGS]; struct qed_spq_entry *p_ent = NULL; struct qed_sp_init_data init_data; u8 abs_vport_id = 0; @@ -1513,26 +1513,25 @@ qed_sp_eth_filter_mcast(struct qed_hwfn *p_hwfn, /* explicitly clear out the entire vector */ memset(&p_ramrod->approx_mcast.bins, 0, sizeof(p_ramrod->approx_mcast.bins)); - memset(bins, 0, sizeof(unsigned long) * - ETH_MULTICAST_MAC_BINS_IN_REGS); + memset(bins, 0, sizeof(bins)); /* filter ADD op is explicit set op and it removes * any existing filters for the vport */ if (p_filter_cmd->opcode == QED_FILTER_ADD) { for (i = 0; i < p_filter_cmd->num_mc_addrs; i++) { - u32 bit; + u32 bit, nbits; bit = qed_mcast_bin_from_mac(p_filter_cmd->mac[i]); - __set_bit(bit, bins); + nbits = sizeof(u32) * BITS_PER_BYTE; + bins[bit / nbits] |= 1 << (bit % nbits); } /* Convert to correct endianity */ for (i = 0; i < ETH_MULTICAST_MAC_BINS_IN_REGS; i++) { struct vport_update_ramrod_mcast *p_ramrod_bins; - u32 *p_bins = (u32 *)bins; p_ramrod_bins = &p_ramrod->approx_mcast; - p_ramrod_bins->bins[i] = cpu_to_le32(p_bins[i]); + p_ramrod_bins->bins[i] = cpu_to_le32(bins[i]); } } diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h index 806a8da257e9..8d80f1095d17 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h @@ -215,7 +215,7 @@ struct qed_sp_vport_update_params { u8 anti_spoofing_en; u8 update_accept_any_vlan_flg; u8 accept_any_vlan; - unsigned long bins[8]; + u32 bins[8]; struct qed_rss_params *rss_params; struct qed_filter_accept_flags accept_flags; struct qed_sge_tpa_params *sge_tpa_params; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 9d9e533bccdc..cdd645024a32 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -1211,6 +1211,7 @@ static void qed_mcp_handle_link_change(struct qed_hwfn *p_hwfn, break; default: p_link->speed = 0; + p_link->link_up = 0; } if (p_link->link_up && p_link->speed) @@ -1308,9 +1309,15 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up) phy_cfg.pause |= (params->pause.forced_tx) ? ETH_PAUSE_TX : 0; phy_cfg.adv_speed = params->speed.advertised_speeds; phy_cfg.loopback_mode = params->loopback_mode; - if (p_hwfn->mcp_info->capabilities & FW_MB_PARAM_FEATURE_SUPPORT_EEE) { - if (params->eee.enable) - phy_cfg.eee_cfg |= EEE_CFG_EEE_ENABLED; + + /* There are MFWs that share this capability regardless of whether + * this is feasible or not. And given that at the very least adv_caps + * would be set internally by qed, we want to make sure LFA would + * still work. + */ + if ((p_hwfn->mcp_info->capabilities & + FW_MB_PARAM_FEATURE_SUPPORT_EEE) && params->eee.enable) { + phy_cfg.eee_cfg |= EEE_CFG_EEE_ENABLED; if (params->eee.tx_lpi_enable) phy_cfg.eee_cfg |= EEE_CFG_TX_LPI; if (params->eee.adv_caps & QED_EEE_1G_ADV) diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index fd59cf45f4be..26e918d7f2f9 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -2831,7 +2831,7 @@ qed_iov_vp_update_mcast_bin_param(struct qed_hwfn *p_hwfn, p_data->update_approx_mcast_flg = 1; memcpy(p_data->bins, p_mcast_tlv->bins, - sizeof(unsigned long) * ETH_MULTICAST_MAC_BINS_IN_REGS); + sizeof(u32) * ETH_MULTICAST_MAC_BINS_IN_REGS); *tlvs_mask |= 1 << QED_IOV_VP_UPDATE_MCAST; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index 2d7fcd6a0777..be6ddde1a104 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -1126,7 +1126,7 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn, resp_size += sizeof(struct pfvf_def_resp_tlv); memcpy(p_mcast_tlv->bins, p_params->bins, - sizeof(unsigned long) * ETH_MULTICAST_MAC_BINS_IN_REGS); + sizeof(u32) * ETH_MULTICAST_MAC_BINS_IN_REGS); } update_rx = p_params->accept_flags.update_rx_mode_config; @@ -1272,7 +1272,7 @@ void qed_vf_pf_filter_mcast(struct qed_hwfn *p_hwfn, u32 bit; bit = qed_mcast_bin_from_mac(p_filter_cmd->mac[i]); - __set_bit(bit, sp_params.bins); + sp_params.bins[bit / 32] |= 1 << (bit % 32); } } diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.h b/drivers/net/ethernet/qlogic/qed/qed_vf.h index 4f05d5eb3cf5..033409db86ae 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.h +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.h @@ -392,7 +392,12 @@ struct vfpf_vport_update_mcast_bin_tlv { struct channel_tlv tl; u8 padding[4]; - u64 bins[8]; + /* There are only 256 approx bins, and in HSI they're divided into + * 32-bit values. As old VFs used to set-bit to the values on its side, + * the upper half of the array is never expected to contain any data. + */ + u64 bins[4]; + u64 obsolete_bins[4]; }; struct vfpf_vport_update_accept_param_tlv { diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index a3f69901ac87..eaedc11ed686 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -7734,8 +7734,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) return rc; } - /* override BIOS settings, use userspace tools to enable WOL */ - __rtl8169_set_wol(tp, 0); + tp->saved_wolopts = __rtl8169_get_wol(tp); if (rtl_tbi_enabled(tp)) { tp->set_speed = rtl8169_set_speed_tbi; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 60f59abab009..ef6a8d39db2f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -53,7 +53,7 @@ #include "dwmac1000.h" #include "hwif.h" -#define STMMAC_ALIGN(x) L1_CACHE_ALIGN(x) +#define STMMAC_ALIGN(x) __ALIGN_KERNEL(x, SMP_CACHE_BYTES) #define TSO_MAX_BUFF_SIZE (SZ_16K - 1) /* Module parameters */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 8d375e51a526..6a393b16a1fc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -257,7 +257,7 @@ static int stmmac_pci_probe(struct pci_dev *pdev, return -ENOMEM; /* Enable pci device */ - ret = pcim_enable_device(pdev); + ret = pci_enable_device(pdev); if (ret) { dev_err(&pdev->dev, "%s: ERROR: failed to enable device\n", __func__); @@ -300,9 +300,45 @@ static int stmmac_pci_probe(struct pci_dev *pdev, static void stmmac_pci_remove(struct pci_dev *pdev) { stmmac_dvr_remove(&pdev->dev); + pci_disable_device(pdev); } -static SIMPLE_DEV_PM_OPS(stmmac_pm_ops, stmmac_suspend, stmmac_resume); +static int stmmac_pci_suspend(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + int ret; + + ret = stmmac_suspend(dev); + if (ret) + return ret; + + ret = pci_save_state(pdev); + if (ret) + return ret; + + pci_disable_device(pdev); + pci_wake_from_d3(pdev, true); + return 0; +} + +static int stmmac_pci_resume(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + int ret; + + pci_restore_state(pdev); + pci_set_power_state(pdev, PCI_D0); + + ret = pci_enable_device(pdev); + if (ret) + return ret; + + pci_set_master(pdev); + + return stmmac_resume(dev); +} + +static SIMPLE_DEV_PM_OPS(stmmac_pm_ops, stmmac_pci_suspend, stmmac_pci_resume); /* synthetic ID, no official vendor */ #define PCI_VENDOR_ID_STMMAC 0x700 diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c index 16c3bfbe1992..757a3b37ae8a 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c @@ -218,6 +218,7 @@ issue: ret = of_mdiobus_register(bus, np1); if (ret) { mdiobus_free(bus); + lp->mii_bus = NULL; return ret; } return 0; diff --git a/drivers/net/netdevsim/devlink.c b/drivers/net/netdevsim/devlink.c index ba663e5af168..5135fc371f01 100644 --- a/drivers/net/netdevsim/devlink.c +++ b/drivers/net/netdevsim/devlink.c @@ -207,6 +207,7 @@ void nsim_devlink_teardown(struct netdevsim *ns) struct net *net = nsim_to_net(ns); bool *reg_devlink = net_generic(net, nsim_devlink_id); + devlink_resources_unregister(ns->devlink, NULL); devlink_unregister(ns->devlink); devlink_free(ns->devlink); ns->devlink = NULL; diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/phy/mdio-mux-bcm-iproc.c index 0831b7142df7..0c5b68e7da51 100644 --- a/drivers/net/phy/mdio-mux-bcm-iproc.c +++ b/drivers/net/phy/mdio-mux-bcm-iproc.c @@ -218,7 +218,7 @@ out: static int mdio_mux_iproc_remove(struct platform_device *pdev) { - struct iproc_mdiomux_desc *md = dev_get_platdata(&pdev->dev); + struct iproc_mdiomux_desc *md = platform_get_drvdata(pdev); mdio_mux_uninit(md->mux_handle); mdiobus_unregister(md->mii_bus); diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 537297d2b4b4..6c9b24fe3148 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -514,7 +514,7 @@ static int phy_start_aneg_priv(struct phy_device *phydev, bool sync) * negotiation may already be done and aneg interrupt may not be * generated. */ - if (phy_interrupt_is_valid(phydev) && (phydev->state == PHY_AN)) { + if (phydev->irq != PHY_POLL && phydev->state == PHY_AN) { err = phy_aneg_done(phydev); if (err > 0) { trigger = true; diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index ed10d49eb5e0..aeca484a75b8 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1242,6 +1242,8 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) mod_timer(&dev->stat_monitor, jiffies + STAT_UPDATE_TIMER); } + + tasklet_schedule(&dev->bh); } return ret; diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 38502809420b..cb0cc30c3d6a 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1246,7 +1246,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81b3, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {QMI_FIXED_INTF(0x413c, 0x81b6, 8)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81b6, 10)}, /* Dell Wireless 5811e */ - {QMI_FIXED_INTF(0x413c, 0x81d7, 1)}, /* Dell Wireless 5821e */ + {QMI_FIXED_INTF(0x413c, 0x81d7, 0)}, /* Dell Wireless 5821e */ {QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)}, /* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */ {QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)}, /* HP lt4120 Snapdragon X5 LTE */ {QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */ diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 53085c63277b..2b6ec927809e 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -586,7 +586,8 @@ static struct sk_buff *receive_small(struct net_device *dev, struct receive_queue *rq, void *buf, void *ctx, unsigned int len, - unsigned int *xdp_xmit) + unsigned int *xdp_xmit, + unsigned int *rbytes) { struct sk_buff *skb; struct bpf_prog *xdp_prog; @@ -601,6 +602,7 @@ static struct sk_buff *receive_small(struct net_device *dev, int err; len -= vi->hdr_len; + *rbytes += len; rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); @@ -705,11 +707,13 @@ static struct sk_buff *receive_big(struct net_device *dev, struct virtnet_info *vi, struct receive_queue *rq, void *buf, - unsigned int len) + unsigned int len, + unsigned int *rbytes) { struct page *page = buf; struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE); + *rbytes += len - vi->hdr_len; if (unlikely(!skb)) goto err; @@ -727,7 +731,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, void *buf, void *ctx, unsigned int len, - unsigned int *xdp_xmit) + unsigned int *xdp_xmit, + unsigned int *rbytes) { struct virtio_net_hdr_mrg_rxbuf *hdr = buf; u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers); @@ -740,6 +745,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, int err; head_skb = NULL; + *rbytes += len - vi->hdr_len; rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); @@ -877,6 +883,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, goto err_buf; } + *rbytes += len; page = virt_to_head_page(buf); truesize = mergeable_ctx_to_truesize(ctx); @@ -932,6 +939,7 @@ err_skb: dev->stats.rx_length_errors++; break; } + *rbytes += len; page = virt_to_head_page(buf); put_page(page); } @@ -942,14 +950,13 @@ xdp_xmit: return NULL; } -static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq, - void *buf, unsigned int len, void **ctx, - unsigned int *xdp_xmit) +static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq, + void *buf, unsigned int len, void **ctx, + unsigned int *xdp_xmit, unsigned int *rbytes) { struct net_device *dev = vi->dev; struct sk_buff *skb; struct virtio_net_hdr_mrg_rxbuf *hdr; - int ret; if (unlikely(len < vi->hdr_len + ETH_HLEN)) { pr_debug("%s: short packet %i\n", dev->name, len); @@ -961,23 +968,22 @@ static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq, } else { put_page(virt_to_head_page(buf)); } - return 0; + return; } if (vi->mergeable_rx_bufs) - skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit); + skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit, + rbytes); else if (vi->big_packets) - skb = receive_big(dev, vi, rq, buf, len); + skb = receive_big(dev, vi, rq, buf, len, rbytes); else - skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit); + skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit, rbytes); if (unlikely(!skb)) - return 0; + return; hdr = skb_vnet_hdr(skb); - ret = skb->len; - if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID) skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -994,12 +1000,11 @@ static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq, ntohs(skb->protocol), skb->len, skb->pkt_type); napi_gro_receive(&rq->napi, skb); - return ret; + return; frame_err: dev->stats.rx_frame_errors++; dev_kfree_skb(skb); - return 0; } /* Unlike mergeable buffers, all buffers are allocated to the @@ -1249,13 +1254,13 @@ static int virtnet_receive(struct receive_queue *rq, int budget, while (received < budget && (buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) { - bytes += receive_buf(vi, rq, buf, len, ctx, xdp_xmit); + receive_buf(vi, rq, buf, len, ctx, xdp_xmit, &bytes); received++; } } else { while (received < budget && (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) { - bytes += receive_buf(vi, rq, buf, len, NULL, xdp_xmit); + receive_buf(vi, rq, buf, len, NULL, xdp_xmit, &bytes); received++; } } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index f6bb1d54d4bd..e857cb3335f6 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -636,9 +636,62 @@ static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr)); } -/* Add new entry to forwarding table -- assumes lock held */ +static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan, + const u8 *mac, __u16 state, + __be32 src_vni, __u8 ndm_flags) +{ + struct vxlan_fdb *f; + + f = kmalloc(sizeof(*f), GFP_ATOMIC); + if (!f) + return NULL; + f->state = state; + f->flags = ndm_flags; + f->updated = f->used = jiffies; + f->vni = src_vni; + INIT_LIST_HEAD(&f->remotes); + memcpy(f->eth_addr, mac, ETH_ALEN); + + return f; +} + static int vxlan_fdb_create(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, + __u16 state, __be16 port, __be32 src_vni, + __be32 vni, __u32 ifindex, __u8 ndm_flags, + struct vxlan_fdb **fdb) +{ + struct vxlan_rdst *rd = NULL; + struct vxlan_fdb *f; + int rc; + + if (vxlan->cfg.addrmax && + vxlan->addrcnt >= vxlan->cfg.addrmax) + return -ENOSPC; + + netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip); + f = vxlan_fdb_alloc(vxlan, mac, state, src_vni, ndm_flags); + if (!f) + return -ENOMEM; + + rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); + if (rc < 0) { + kfree(f); + return rc; + } + + ++vxlan->addrcnt; + hlist_add_head_rcu(&f->hlist, + vxlan_fdb_head(vxlan, mac, src_vni)); + + *fdb = f; + + return 0; +} + +/* Add new entry to forwarding table -- assumes lock held */ +static int vxlan_fdb_update(struct vxlan_dev *vxlan, + const u8 *mac, union vxlan_addr *ip, __u16 state, __u16 flags, __be16 port, __be32 src_vni, __be32 vni, __u32 ifindex, __u8 ndm_flags) @@ -687,37 +740,17 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, if (!(flags & NLM_F_CREATE)) return -ENOENT; - if (vxlan->cfg.addrmax && - vxlan->addrcnt >= vxlan->cfg.addrmax) - return -ENOSPC; - /* Disallow replace to add a multicast entry */ if ((flags & NLM_F_REPLACE) && (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac))) return -EOPNOTSUPP; netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip); - f = kmalloc(sizeof(*f), GFP_ATOMIC); - if (!f) - return -ENOMEM; - - notify = 1; - f->state = state; - f->flags = ndm_flags; - f->updated = f->used = jiffies; - f->vni = src_vni; - INIT_LIST_HEAD(&f->remotes); - memcpy(f->eth_addr, mac, ETH_ALEN); - - rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd); - if (rc < 0) { - kfree(f); + rc = vxlan_fdb_create(vxlan, mac, ip, state, port, src_vni, + vni, ifindex, ndm_flags, &f); + if (rc < 0) return rc; - } - - ++vxlan->addrcnt; - hlist_add_head_rcu(&f->hlist, - vxlan_fdb_head(vxlan, mac, src_vni)); + notify = 1; } if (notify) { @@ -741,13 +774,15 @@ static void vxlan_fdb_free(struct rcu_head *head) kfree(f); } -static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f) +static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, + bool do_notify) { netdev_dbg(vxlan->dev, "delete %pM\n", f->eth_addr); --vxlan->addrcnt; - vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH); + if (do_notify) + vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH); hlist_del_rcu(&f->hlist); call_rcu(&f->rcu, vxlan_fdb_free); @@ -863,7 +898,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], return -EAFNOSUPPORT; spin_lock_bh(&vxlan->hash_lock); - err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags, + err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags, port, src_vni, vni, ifindex, ndm->ndm_flags); spin_unlock_bh(&vxlan->hash_lock); @@ -897,7 +932,7 @@ static int __vxlan_fdb_delete(struct vxlan_dev *vxlan, goto out; } - vxlan_fdb_destroy(vxlan, f); + vxlan_fdb_destroy(vxlan, f, true); out: return 0; @@ -1006,7 +1041,7 @@ static bool vxlan_snoop(struct net_device *dev, /* close off race between vxlan_flush and incoming packets */ if (netif_running(dev)) - vxlan_fdb_create(vxlan, src_mac, src_ip, + vxlan_fdb_update(vxlan, src_mac, src_ip, NUD_REACHABLE, NLM_F_EXCL|NLM_F_CREATE, vxlan->cfg.dst_port, @@ -2364,7 +2399,7 @@ static void vxlan_cleanup(struct timer_list *t) "garbage collect %pM\n", f->eth_addr); f->state = NUD_STALE; - vxlan_fdb_destroy(vxlan, f); + vxlan_fdb_destroy(vxlan, f, true); } else if (time_before(timeout, next_timer)) next_timer = timeout; } @@ -2415,7 +2450,7 @@ static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni) spin_lock_bh(&vxlan->hash_lock); f = __vxlan_find_mac(vxlan, all_zeros_mac, vni); if (f) - vxlan_fdb_destroy(vxlan, f); + vxlan_fdb_destroy(vxlan, f, true); spin_unlock_bh(&vxlan->hash_lock); } @@ -2469,7 +2504,7 @@ static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all) continue; /* the all_zeros_mac entry is deleted at vxlan_uninit */ if (!is_zero_ether_addr(f->eth_addr)) - vxlan_fdb_destroy(vxlan, f); + vxlan_fdb_destroy(vxlan, f, true); } } spin_unlock_bh(&vxlan->hash_lock); @@ -3160,6 +3195,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, { struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_dev *vxlan = netdev_priv(dev); + struct vxlan_fdb *f = NULL; int err; err = vxlan_dev_configure(net, dev, conf, false, extack); @@ -3173,24 +3209,35 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, err = vxlan_fdb_create(vxlan, all_zeros_mac, &vxlan->default_dst.remote_ip, NUD_REACHABLE | NUD_PERMANENT, - NLM_F_EXCL | NLM_F_CREATE, vxlan->cfg.dst_port, vxlan->default_dst.remote_vni, vxlan->default_dst.remote_vni, vxlan->default_dst.remote_ifindex, - NTF_SELF); + NTF_SELF, &f); if (err) return err; } err = register_netdevice(dev); + if (err) + goto errout; + + err = rtnl_configure_link(dev, NULL); if (err) { - vxlan_fdb_delete_default(vxlan, vxlan->default_dst.remote_vni); - return err; + unregister_netdevice(dev); + goto errout; } + /* notify default fdb entry */ + if (f) + vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH); + list_add(&vxlan->next, &vn->vxlan_list); return 0; +errout: + if (f) + vxlan_fdb_destroy(vxlan, f, false); + return err; } static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], @@ -3425,6 +3472,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], struct vxlan_rdst *dst = &vxlan->default_dst; struct vxlan_rdst old_dst; struct vxlan_config conf; + struct vxlan_fdb *f = NULL; int err; err = vxlan_nl2conf(tb, data, @@ -3453,16 +3501,16 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], err = vxlan_fdb_create(vxlan, all_zeros_mac, &dst->remote_ip, NUD_REACHABLE | NUD_PERMANENT, - NLM_F_CREATE | NLM_F_APPEND, vxlan->cfg.dst_port, dst->remote_vni, dst->remote_vni, dst->remote_ifindex, - NTF_SELF); + NTF_SELF, &f); if (err) { spin_unlock_bh(&vxlan->hash_lock); return err; } + vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH); } spin_unlock_bh(&vxlan->hash_lock); } diff --git a/drivers/net/wan/lmc/lmc_main.c b/drivers/net/wan/lmc/lmc_main.c index 90a4ad9a2d08..b3a1b6f5c406 100644 --- a/drivers/net/wan/lmc/lmc_main.c +++ b/drivers/net/wan/lmc/lmc_main.c @@ -1362,7 +1362,7 @@ static irqreturn_t lmc_interrupt (int irq, void *dev_instance) /*fold00*/ case 0x001: printk(KERN_WARNING "%s: Master Abort (naughty)\n", dev->name); break; - case 0x010: + case 0x002: printk(KERN_WARNING "%s: Target Abort (not so naughty)\n", dev->name); break; default: diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c index 45928b5b8d97..4fffa6988087 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c @@ -1785,7 +1785,8 @@ brcmf_pcie_prepare_fw_request(struct brcmf_pciedev_info *devinfo) fwreq->items[BRCMF_PCIE_FW_CODE].type = BRCMF_FW_TYPE_BINARY; fwreq->items[BRCMF_PCIE_FW_NVRAM].type = BRCMF_FW_TYPE_NVRAM; fwreq->items[BRCMF_PCIE_FW_NVRAM].flags = BRCMF_FW_REQF_OPTIONAL; - fwreq->domain_nr = pci_domain_nr(devinfo->pdev->bus); + /* NVRAM reserves PCI domain 0 for Broadcom's SDK faked bus */ + fwreq->domain_nr = pci_domain_nr(devinfo->pdev->bus) + 1; fwreq->bus_nr = devinfo->pdev->bus->number; return fwreq; diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c index e20c30b29c03..c8ea63d02619 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c @@ -178,6 +178,17 @@ const struct iwl_cfg iwl9260_2ac_cfg = { .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, }; +const struct iwl_cfg iwl9260_killer_2ac_cfg = { + .name = "Killer (R) Wireless-AC 1550 Wireless Network Adapter (9260NGW)", + .fw_name_pre = IWL9260A_FW_PRE, + .fw_name_pre_b_or_c_step = IWL9260B_FW_PRE, + IWL_DEVICE_9000, + .ht_params = &iwl9000_ht_params, + .nvm_ver = IWL9000_NVM_VERSION, + .nvm_calib_ver = IWL9000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, +}; + const struct iwl_cfg iwl9270_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 9270", .fw_name_pre = IWL9260A_FW_PRE, @@ -267,6 +278,34 @@ const struct iwl_cfg iwl9560_2ac_cfg_soc = { .soc_latency = 5000, }; +const struct iwl_cfg iwl9560_killer_2ac_cfg_soc = { + .name = "Killer (R) Wireless-AC 1550i Wireless Network Adapter (9560NGW)", + .fw_name_pre = IWL9000A_FW_PRE, + .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, + .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + IWL_DEVICE_9000, + .ht_params = &iwl9000_ht_params, + .nvm_ver = IWL9000_NVM_VERSION, + .nvm_calib_ver = IWL9000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, + .integrated = true, + .soc_latency = 5000, +}; + +const struct iwl_cfg iwl9560_killer_s_2ac_cfg_soc = { + .name = "Killer (R) Wireless-AC 1550s Wireless Network Adapter (9560NGW)", + .fw_name_pre = IWL9000A_FW_PRE, + .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, + .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + IWL_DEVICE_9000, + .ht_params = &iwl9000_ht_params, + .nvm_ver = IWL9000_NVM_VERSION, + .nvm_calib_ver = IWL9000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, + .integrated = true, + .soc_latency = 5000, +}; + const struct iwl_cfg iwl9460_2ac_cfg_shared_clk = { .name = "Intel(R) Dual Band Wireless AC 9460", .fw_name_pre = IWL9000A_FW_PRE, @@ -327,6 +366,36 @@ const struct iwl_cfg iwl9560_2ac_cfg_shared_clk = { .extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK }; +const struct iwl_cfg iwl9560_killer_2ac_cfg_shared_clk = { + .name = "Killer (R) Wireless-AC 1550i Wireless Network Adapter (9560NGW)", + .fw_name_pre = IWL9000A_FW_PRE, + .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, + .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + IWL_DEVICE_9000, + .ht_params = &iwl9000_ht_params, + .nvm_ver = IWL9000_NVM_VERSION, + .nvm_calib_ver = IWL9000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, + .integrated = true, + .soc_latency = 5000, + .extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK +}; + +const struct iwl_cfg iwl9560_killer_s_2ac_cfg_shared_clk = { + .name = "Killer (R) Wireless-AC 1550s Wireless Network Adapter (9560NGW)", + .fw_name_pre = IWL9000A_FW_PRE, + .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, + .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + IWL_DEVICE_9000, + .ht_params = &iwl9000_ht_params, + .nvm_ver = IWL9000_NVM_VERSION, + .nvm_calib_ver = IWL9000_TX_POWER_VERSION, + .max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K, + .integrated = true, + .soc_latency = 5000, + .extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK +}; + MODULE_FIRMWARE(IWL9000A_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL9000B_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL9000RFB_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX)); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index c503b26793f6..84a816809723 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -551,6 +551,7 @@ extern const struct iwl_cfg iwl8275_2ac_cfg; extern const struct iwl_cfg iwl4165_2ac_cfg; extern const struct iwl_cfg iwl9160_2ac_cfg; extern const struct iwl_cfg iwl9260_2ac_cfg; +extern const struct iwl_cfg iwl9260_killer_2ac_cfg; extern const struct iwl_cfg iwl9270_2ac_cfg; extern const struct iwl_cfg iwl9460_2ac_cfg; extern const struct iwl_cfg iwl9560_2ac_cfg; @@ -558,10 +559,14 @@ extern const struct iwl_cfg iwl9460_2ac_cfg_soc; extern const struct iwl_cfg iwl9461_2ac_cfg_soc; extern const struct iwl_cfg iwl9462_2ac_cfg_soc; extern const struct iwl_cfg iwl9560_2ac_cfg_soc; +extern const struct iwl_cfg iwl9560_killer_2ac_cfg_soc; +extern const struct iwl_cfg iwl9560_killer_s_2ac_cfg_soc; extern const struct iwl_cfg iwl9460_2ac_cfg_shared_clk; extern const struct iwl_cfg iwl9461_2ac_cfg_shared_clk; extern const struct iwl_cfg iwl9462_2ac_cfg_shared_clk; extern const struct iwl_cfg iwl9560_2ac_cfg_shared_clk; +extern const struct iwl_cfg iwl9560_killer_2ac_cfg_shared_clk; +extern const struct iwl_cfg iwl9560_killer_s_2ac_cfg_shared_clk; extern const struct iwl_cfg iwl22000_2ac_cfg_hr; extern const struct iwl_cfg iwl22000_2ac_cfg_hr_cdb; extern const struct iwl_cfg iwl22000_2ac_cfg_jf; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 38234bda9017..8520523b91b4 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -545,6 +545,9 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2526, 0x1210, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x1410, iwl9270_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x1420, iwl9460_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2526, 0x1550, iwl9260_killer_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2526, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x1610, iwl9270_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x2034, iwl9560_2ac_cfg_soc)}, @@ -554,6 +557,7 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2526, 0x40A4, iwl9460_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x4234, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x42A4, iwl9462_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2526, 0x8014, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0xA014, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x271B, 0x0010, iwl9160_2ac_cfg)}, {IWL_PCI_DEVICE(0x271B, 0x0014, iwl9160_2ac_cfg)}, @@ -578,6 +582,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2720, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x2720, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2720, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2720, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2720, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2720, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2720, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2720, 0x4030, iwl9560_2ac_cfg)}, @@ -604,6 +610,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x30DC, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x30DC, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x30DC, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x30DC, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x30DC, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x30DC, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x30DC, 0x4030, iwl9560_2ac_cfg_soc)}, @@ -630,6 +638,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x31DC, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x31DC, 0x1030, iwl9560_2ac_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x31DC, 0x1551, iwl9560_killer_s_2ac_cfg_shared_clk)}, + {IWL_PCI_DEVICE(0x31DC, 0x1552, iwl9560_killer_2ac_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x2030, iwl9560_2ac_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x2034, iwl9560_2ac_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x4030, iwl9560_2ac_cfg_shared_clk)}, @@ -656,6 +666,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x34F0, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x34F0, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x34F0, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x34F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x34F0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x34F0, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x34F0, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x34F0, 0x4030, iwl9560_2ac_cfg_soc)}, @@ -682,6 +694,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x3DF0, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x3DF0, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x3DF0, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x3DF0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x3DF0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x3DF0, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x3DF0, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x3DF0, 0x4030, iwl9560_2ac_cfg_soc)}, @@ -708,6 +722,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x43F0, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x43F0, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x43F0, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x43F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x43F0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x43F0, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x43F0, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x43F0, 0x4030, iwl9560_2ac_cfg_soc)}, @@ -743,6 +759,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x9DF0, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x9DF0, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x9DF0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x9DF0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x2010, iwl9460_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x2034, iwl9560_2ac_cfg_soc)}, @@ -771,6 +789,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0xA0F0, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0xA0F0, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA0F0, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0xA0F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0xA0F0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA0F0, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA0F0, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA0F0, 0x4030, iwl9560_2ac_cfg_soc)}, @@ -797,6 +817,8 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0xA370, 0x1010, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0xA370, 0x1030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x1210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0xA370, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0xA370, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x2030, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x2034, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x4030, iwl9560_2ac_cfg_soc)}, diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index a57daecf1d57..2d8812dd1534 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -87,6 +87,7 @@ struct netfront_cb { /* IRQ name is queue name with "-tx" or "-rx" appended */ #define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3) +static DECLARE_WAIT_QUEUE_HEAD(module_load_q); static DECLARE_WAIT_QUEUE_HEAD(module_unload_q); struct netfront_stats { @@ -1330,6 +1331,11 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev) netif_carrier_off(netdev); xenbus_switch_state(dev, XenbusStateInitialising); + wait_event(module_load_q, + xenbus_read_driver_state(dev->otherend) != + XenbusStateClosed && + xenbus_read_driver_state(dev->otherend) != + XenbusStateUnknown); return netdev; exit: diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 903eb4545e26..f7efe5a58cc7 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -539,14 +539,18 @@ static struct nvmf_transport_ops *nvmf_lookup_transport( /* * For something we're not in a state to send to the device the default action * is to busy it and retry it after the controller state is recovered. However, - * anything marked for failfast or nvme multipath is immediately failed. + * if the controller is deleting or if anything is marked for failfast or + * nvme multipath it is immediately failed. * * Note: commands used to initialize the controller will be marked for failfast. * Note: nvme cli/ioctl commands are marked for failfast. */ -blk_status_t nvmf_fail_nonready_command(struct request *rq) +blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl, + struct request *rq) { - if (!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH)) + if (ctrl->state != NVME_CTRL_DELETING && + ctrl->state != NVME_CTRL_DEAD && + !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH)) return BLK_STS_RESOURCE; nvme_req(rq)->status = NVME_SC_ABORT_REQ; return BLK_STS_IOERR; diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index e1818a27aa2d..aa2fdb2a2e8f 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -162,7 +162,8 @@ void nvmf_unregister_transport(struct nvmf_transport_ops *ops); void nvmf_free_options(struct nvmf_ctrl_options *opts); int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size); bool nvmf_should_reconnect(struct nvme_ctrl *ctrl); -blk_status_t nvmf_fail_nonready_command(struct request *rq); +blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl, + struct request *rq); bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq, bool queue_live); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 41d45a1b5c62..9bac912173ba 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2272,7 +2272,7 @@ nvme_fc_queue_rq(struct blk_mq_hw_ctx *hctx, if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE || !nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready)) - return nvmf_fail_nonready_command(rq); + return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq); ret = nvme_setup_cmd(ns, rq, sqe); if (ret) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 518c5b09038c..66ec5985c9f3 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1639,7 +1639,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, WARN_ON_ONCE(rq->tag < 0); if (!nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready)) - return nvmf_fail_nonready_command(rq); + return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq); dev = queue->device->dev; ib_dma_sync_single_for_cpu(dev, sqe->dma, diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index d3f3b3ec4d1a..ebea1373d1b7 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -282,6 +282,7 @@ static ssize_t nvmet_ns_device_path_store(struct config_item *item, { struct nvmet_ns *ns = to_nvmet_ns(item); struct nvmet_subsys *subsys = ns->subsys; + size_t len; int ret; mutex_lock(&subsys->lock); @@ -289,10 +290,14 @@ static ssize_t nvmet_ns_device_path_store(struct config_item *item, if (ns->enabled) goto out_unlock; - kfree(ns->device_path); + ret = -EINVAL; + len = strcspn(page, "\n"); + if (!len) + goto out_unlock; + kfree(ns->device_path); ret = -ENOMEM; - ns->device_path = kstrndup(page, strcspn(page, "\n"), GFP_KERNEL); + ns->device_path = kstrndup(page, len, GFP_KERNEL); if (!ns->device_path) goto out_unlock; diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 74d4b785d2da..9838103f2d62 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -339,7 +339,7 @@ int nvmet_ns_enable(struct nvmet_ns *ns) goto out_unlock; ret = nvmet_bdev_ns_enable(ns); - if (ret) + if (ret == -ENOTBLK) ret = nvmet_file_ns_enable(ns); if (ret) goto out_unlock; diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 408279cb6f2c..29b4b236afd8 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -58,8 +58,8 @@ struct nvmet_fc_ls_iod { struct work_struct work; } __aligned(sizeof(unsigned long long)); +/* desired maximum for a single sequence - if sg list allows it */ #define NVMET_FC_MAX_SEQ_LENGTH (256 * 1024) -#define NVMET_FC_MAX_XFR_SGENTS (NVMET_FC_MAX_SEQ_LENGTH / PAGE_SIZE) enum nvmet_fcp_datadir { NVMET_FCP_NODATA, @@ -74,6 +74,7 @@ struct nvmet_fc_fcp_iod { struct nvme_fc_cmd_iu cmdiubuf; struct nvme_fc_ersp_iu rspiubuf; dma_addr_t rspdma; + struct scatterlist *next_sg; struct scatterlist *data_sg; int data_sg_cnt; u32 offset; @@ -1025,8 +1026,7 @@ nvmet_fc_register_targetport(struct nvmet_fc_port_info *pinfo, INIT_LIST_HEAD(&newrec->assoc_list); kref_init(&newrec->ref); ida_init(&newrec->assoc_cnt); - newrec->max_sg_cnt = min_t(u32, NVMET_FC_MAX_XFR_SGENTS, - template->max_sgl_segments); + newrec->max_sg_cnt = template->max_sgl_segments; ret = nvmet_fc_alloc_ls_iodlist(newrec); if (ret) { @@ -1722,6 +1722,7 @@ nvmet_fc_alloc_tgt_pgs(struct nvmet_fc_fcp_iod *fod) ((fod->io_dir == NVMET_FCP_WRITE) ? DMA_FROM_DEVICE : DMA_TO_DEVICE)); /* note: write from initiator perspective */ + fod->next_sg = fod->data_sg; return 0; @@ -1866,24 +1867,49 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport, struct nvmet_fc_fcp_iod *fod, u8 op) { struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq; + struct scatterlist *sg = fod->next_sg; unsigned long flags; - u32 tlen; + u32 remaininglen = fod->req.transfer_len - fod->offset; + u32 tlen = 0; int ret; fcpreq->op = op; fcpreq->offset = fod->offset; fcpreq->timeout = NVME_FC_TGTOP_TIMEOUT_SEC; - tlen = min_t(u32, tgtport->max_sg_cnt * PAGE_SIZE, - (fod->req.transfer_len - fod->offset)); + /* + * for next sequence: + * break at a sg element boundary + * attempt to keep sequence length capped at + * NVMET_FC_MAX_SEQ_LENGTH but allow sequence to + * be longer if a single sg element is larger + * than that amount. This is done to avoid creating + * a new sg list to use for the tgtport api. + */ + fcpreq->sg = sg; + fcpreq->sg_cnt = 0; + while (tlen < remaininglen && + fcpreq->sg_cnt < tgtport->max_sg_cnt && + tlen + sg_dma_len(sg) < NVMET_FC_MAX_SEQ_LENGTH) { + fcpreq->sg_cnt++; + tlen += sg_dma_len(sg); + sg = sg_next(sg); + } + if (tlen < remaininglen && fcpreq->sg_cnt == 0) { + fcpreq->sg_cnt++; + tlen += min_t(u32, sg_dma_len(sg), remaininglen); + sg = sg_next(sg); + } + if (tlen < remaininglen) + fod->next_sg = sg; + else + fod->next_sg = NULL; + fcpreq->transfer_length = tlen; fcpreq->transferred_length = 0; fcpreq->fcp_error = 0; fcpreq->rsplen = 0; - fcpreq->sg = &fod->data_sg[fod->offset / PAGE_SIZE]; - fcpreq->sg_cnt = DIV_ROUND_UP(tlen, PAGE_SIZE); - /* * If the last READDATA request: check if LLDD supports * combined xfr with response. diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index d8d91f04bd7e..ae7586b8be07 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -162,7 +162,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx, blk_status_t ret; if (!nvmf_check_ready(&queue->ctrl->ctrl, req, queue_ready)) - return nvmf_fail_nonready_command(req); + return nvmf_fail_nonready_command(&queue->ctrl->ctrl, req); ret = nvme_setup_cmd(ns, req, &iod->cmd); if (ret) diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 35b7fc87eac5..5cb40b2518f9 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -330,7 +330,7 @@ void pci_bus_add_device(struct pci_dev *dev) return; } - dev->is_added = 1; + pci_dev_assign_added(dev, true); } EXPORT_SYMBOL_GPL(pci_bus_add_device); @@ -347,14 +347,14 @@ void pci_bus_add_devices(const struct pci_bus *bus) list_for_each_entry(dev, &bus->devices, bus_list) { /* Skip already-added devices */ - if (dev->is_added) + if (pci_dev_is_added(dev)) continue; pci_bus_add_device(dev); } list_for_each_entry(dev, &bus->devices, bus_list) { /* Skip if device attach failed */ - if (!dev->is_added) + if (!pci_dev_is_added(dev)) continue; child = dev->subordinate; if (child) diff --git a/drivers/pci/controller/pcie-mobiveil.c b/drivers/pci/controller/pcie-mobiveil.c index 4d6c20e47bed..cf0aa7cee5b0 100644 --- a/drivers/pci/controller/pcie-mobiveil.c +++ b/drivers/pci/controller/pcie-mobiveil.c @@ -107,7 +107,7 @@ #define CFG_WINDOW_TYPE 0 #define IO_WINDOW_TYPE 1 #define MEM_WINDOW_TYPE 2 -#define IB_WIN_SIZE (256 * 1024 * 1024 * 1024) +#define IB_WIN_SIZE ((u64)256 * 1024 * 1024 * 1024) #define MAX_PIO_WINDOWS 8 /* Parameters for the waiting for link up routine */ diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 3a17b290df5d..ef0b1b6ba86f 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -509,7 +509,7 @@ static void enable_slot(struct acpiphp_slot *slot) list_for_each_entry(dev, &bus->devices, bus_list) { /* Assume that newly added devices are powered on already. */ - if (!dev->is_added) + if (!pci_dev_is_added(dev)) dev->current_state = PCI_D0; } diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 882f1f9596df..08817253c8a2 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -288,6 +288,7 @@ struct pci_sriov { /* pci_dev priv_flags */ #define PCI_DEV_DISCONNECTED 0 +#define PCI_DEV_ADDED 1 static inline int pci_dev_set_disconnected(struct pci_dev *dev, void *unused) { @@ -300,6 +301,16 @@ static inline bool pci_dev_is_disconnected(const struct pci_dev *dev) return test_bit(PCI_DEV_DISCONNECTED, &dev->priv_flags); } +static inline void pci_dev_assign_added(struct pci_dev *dev, bool added) +{ + assign_bit(PCI_DEV_ADDED, &dev->priv_flags, added); +} + +static inline bool pci_dev_is_added(const struct pci_dev *dev) +{ + return test_bit(PCI_DEV_ADDED, &dev->priv_flags); +} + #ifdef CONFIG_PCI_ATS void pci_restore_ats_state(struct pci_dev *dev); #else diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c index f7ce0cb0b0b7..f02e334beb45 100644 --- a/drivers/pci/pcie/err.c +++ b/drivers/pci/pcie/err.c @@ -295,6 +295,7 @@ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service) parent = udev->subordinate; pci_lock_rescan_remove(); + pci_dev_get(dev); list_for_each_entry_safe_reverse(pdev, temp, &parent->devices, bus_list) { pci_dev_get(pdev); @@ -328,6 +329,7 @@ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service) pci_info(dev, "Device recovery from fatal error failed\n"); } + pci_dev_put(dev); pci_unlock_rescan_remove(); } diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index ac876e32de4b..611adcd9c169 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2433,13 +2433,13 @@ int pci_scan_slot(struct pci_bus *bus, int devfn) dev = pci_scan_single_device(bus, devfn); if (!dev) return 0; - if (!dev->is_added) + if (!pci_dev_is_added(dev)) nr++; for (fn = next_fn(bus, dev, 0); fn > 0; fn = next_fn(bus, dev, fn)) { dev = pci_scan_single_device(bus, devfn + fn); if (dev) { - if (!dev->is_added) + if (!pci_dev_is_added(dev)) nr++; dev->multifunction = 1; } diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c index 6f072eae4f7a..5e3d0dced2b8 100644 --- a/drivers/pci/remove.c +++ b/drivers/pci/remove.c @@ -19,11 +19,12 @@ static void pci_stop_dev(struct pci_dev *dev) { pci_pme_active(dev, false); - if (dev->is_added) { + if (pci_dev_is_added(dev)) { device_release_driver(&dev->dev); pci_proc_detach_device(dev); pci_remove_sysfs_dev_files(dev); - dev->is_added = 0; + + pci_dev_assign_added(dev, false); } if (dev->bus->self) diff --git a/drivers/phy/broadcom/phy-brcm-usb-init.c b/drivers/phy/broadcom/phy-brcm-usb-init.c index 1b7febc43da9..29d2c3b1913a 100644 --- a/drivers/phy/broadcom/phy-brcm-usb-init.c +++ b/drivers/phy/broadcom/phy-brcm-usb-init.c @@ -962,6 +962,10 @@ void brcm_usb_init_xhci(struct brcm_usb_init_params *params) { void __iomem *ctrl = params->ctrl_regs; + USB_CTRL_UNSET(ctrl, USB30_PCTL, PHY3_IDDQ_OVERRIDE); + /* 1 millisecond - for USB clocks to settle down */ + usleep_range(1000, 2000); + if (BRCM_ID(params->family_id) == 0x7366) { /* * The PHY3_SOFT_RESETB bits default to the wrong state. diff --git a/drivers/phy/motorola/phy-mapphone-mdm6600.c b/drivers/phy/motorola/phy-mapphone-mdm6600.c index 23705e1a0023..0075fb0bef8c 100644 --- a/drivers/phy/motorola/phy-mapphone-mdm6600.c +++ b/drivers/phy/motorola/phy-mapphone-mdm6600.c @@ -182,13 +182,13 @@ static void phy_mdm6600_status(struct work_struct *work) ddata = container_of(work, struct phy_mdm6600, status_work.work); dev = ddata->dev; - error = gpiod_get_array_value_cansleep(PHY_MDM6600_NR_CMD_LINES, + error = gpiod_get_array_value_cansleep(PHY_MDM6600_NR_STATUS_LINES, ddata->status_gpios->desc, values); if (error) return; - for (i = 0; i < PHY_MDM6600_NR_CMD_LINES; i++) { + for (i = 0; i < PHY_MDM6600_NR_STATUS_LINES; i++) { val |= values[i] << i; dev_dbg(ddata->dev, "XXX %s: i: %i values[i]: %i val: %i\n", __func__, i, values[i], val); diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index d6093838f5f2..c972cc2b3d5b 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -284,11 +284,11 @@ static int iscsi_check_tmf_restrictions(struct iscsi_task *task, int opcode) */ if (opcode != ISCSI_OP_SCSI_DATA_OUT) { iscsi_conn_printk(KERN_INFO, conn, - "task [op %x/%x itt " + "task [op %x itt " "0x%x/0x%x] " "rejected.\n", - task->hdr->opcode, opcode, - task->itt, task->hdr_itt); + opcode, task->itt, + task->hdr_itt); return -EACCES; } /* @@ -297,10 +297,10 @@ static int iscsi_check_tmf_restrictions(struct iscsi_task *task, int opcode) */ if (conn->session->fast_abort) { iscsi_conn_printk(KERN_INFO, conn, - "task [op %x/%x itt " + "task [op %x itt " "0x%x/0x%x] fast abort.\n", - task->hdr->opcode, opcode, - task->itt, task->hdr_itt); + opcode, task->itt, + task->hdr_itt); return -EACCES; } break; diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 89a4999fa631..c8731568f9c4 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -2141,6 +2141,7 @@ qla24xx_vport_delete(struct fc_vport *fc_vport) msleep(1000); qla24xx_disable_vp(vha); + qla2x00_wait_for_sess_deletion(vha); vha->flags.delete_progress = 1; diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h index f68eb6096559..2660a48d918a 100644 --- a/drivers/scsi/qla2xxx/qla_gbl.h +++ b/drivers/scsi/qla2xxx/qla_gbl.h @@ -214,6 +214,7 @@ void qla2x00_handle_login_done_event(struct scsi_qla_host *, fc_port_t *, int qla24xx_post_gnl_work(struct scsi_qla_host *, fc_port_t *); int qla24xx_async_abort_cmd(srb_t *); int qla24xx_post_relogin_work(struct scsi_qla_host *vha); +void qla2x00_wait_for_sess_deletion(scsi_qla_host_t *); /* * Global Functions in qla_mid.c source file. diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index 2c35b0b2baa0..7a3744006419 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -3708,6 +3708,10 @@ int qla24xx_async_gpnid(scsi_qla_host_t *vha, port_id_t *id) return rval; done_free_sp: + spin_lock_irqsave(&vha->hw->vport_slock, flags); + list_del(&sp->elem); + spin_unlock_irqrestore(&vha->hw->vport_slock, flags); + if (sp->u.iocb_cmd.u.ctarg.req) { dma_free_coherent(&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt), diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index db0e3279e07a..1b19b954bbae 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -1489,11 +1489,10 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint32_t lun, wait_for_completion(&tm_iocb->u.tmf.comp); - rval = tm_iocb->u.tmf.comp_status == CS_COMPLETE ? - QLA_SUCCESS : QLA_FUNCTION_FAILED; + rval = tm_iocb->u.tmf.data; - if ((rval != QLA_SUCCESS) || tm_iocb->u.tmf.data) { - ql_dbg(ql_dbg_taskm, vha, 0x8030, + if (rval != QLA_SUCCESS) { + ql_log(ql_log_warn, vha, 0x8030, "TM IOCB failed (%x).\n", rval); } diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h index 37ae0f6d8ae5..59fd5a9dfeb8 100644 --- a/drivers/scsi/qla2xxx/qla_inline.h +++ b/drivers/scsi/qla2xxx/qla_inline.h @@ -222,6 +222,8 @@ qla2xxx_get_qpair_sp(struct qla_qpair *qpair, fc_port_t *fcport, gfp_t flag) sp->fcport = fcport; sp->iocbs = 1; sp->vha = qpair->vha; + INIT_LIST_HEAD(&sp->elem); + done: if (!sp) QLA_QPAIR_MARK_NOT_BUSY(qpair); diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 9fa5a2557f2c..7756106d4555 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -631,6 +631,9 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb) unsigned long flags; fc_port_t *fcport = NULL; + if (!vha->hw->flags.fw_started) + return; + /* Setup to process RIO completion. */ handle_cnt = 0; if (IS_CNA_CAPABLE(ha)) diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 7e875f575229..f0ec13d48bf3 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -4220,6 +4220,9 @@ qla25xx_init_req_que(struct scsi_qla_host *vha, struct req_que *req) mbx_cmd_t *mcp = &mc; struct qla_hw_data *ha = vha->hw; + if (!ha->flags.fw_started) + return QLA_SUCCESS; + ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10d3, "Entered %s.\n", __func__); @@ -4289,6 +4292,9 @@ qla25xx_init_rsp_que(struct scsi_qla_host *vha, struct rsp_que *rsp) mbx_cmd_t *mcp = &mc; struct qla_hw_data *ha = vha->hw; + if (!ha->flags.fw_started) + return QLA_SUCCESS; + ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x10d6, "Entered %s.\n", __func__); diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c index f6f0a759a7c2..aa727d07b702 100644 --- a/drivers/scsi/qla2xxx/qla_mid.c +++ b/drivers/scsi/qla2xxx/qla_mid.c @@ -152,11 +152,18 @@ int qla24xx_disable_vp(scsi_qla_host_t *vha) { unsigned long flags; - int ret; + int ret = QLA_SUCCESS; + fc_port_t *fcport; + + if (vha->hw->flags.fw_started) + ret = qla24xx_control_vp(vha, VCE_COMMAND_DISABLE_VPS_LOGO_ALL); - ret = qla24xx_control_vp(vha, VCE_COMMAND_DISABLE_VPS_LOGO_ALL); atomic_set(&vha->loop_state, LOOP_DOWN); atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME); + list_for_each_entry(fcport, &vha->vp_fcports, list) + fcport->logout_on_delete = 0; + + qla2x00_mark_all_devices_lost(vha, 0); /* Remove port id from vp target map */ spin_lock_irqsave(&vha->hw->hardware_lock, flags); diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 9f309e572be4..1fbd16c8c9a7 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -303,6 +303,7 @@ static void qla2x00_free_device(scsi_qla_host_t *); static int qla2xxx_map_queues(struct Scsi_Host *shost); static void qla2x00_destroy_deferred_work(struct qla_hw_data *); + struct scsi_host_template qla2xxx_driver_template = { .module = THIS_MODULE, .name = QLA2XXX_DRIVER_NAME, @@ -1147,7 +1148,7 @@ static inline int test_fcport_count(scsi_qla_host_t *vha) * qla2x00_wait_for_sess_deletion can only be called from remove_one. * it has dependency on UNLOADING flag to stop device discovery */ -static void +void qla2x00_wait_for_sess_deletion(scsi_qla_host_t *vha) { qla2x00_mark_all_devices_lost(vha, 0); @@ -3603,6 +3604,8 @@ qla2x00_remove_one(struct pci_dev *pdev) base_vha = pci_get_drvdata(pdev); ha = base_vha->hw; + ql_log(ql_log_info, base_vha, 0xb079, + "Removing driver\n"); /* Indicate device removal to prevent future board_disable and wait * until any pending board_disable has completed. */ @@ -3625,6 +3628,21 @@ qla2x00_remove_one(struct pci_dev *pdev) } qla2x00_wait_for_hba_ready(base_vha); + if (IS_QLA25XX(ha) || IS_QLA2031(ha) || IS_QLA27XX(ha)) { + if (ha->flags.fw_started) + qla2x00_abort_isp_cleanup(base_vha); + } else if (!IS_QLAFX00(ha)) { + if (IS_QLA8031(ha)) { + ql_dbg(ql_dbg_p3p, base_vha, 0xb07e, + "Clearing fcoe driver presence.\n"); + if (qla83xx_clear_drv_presence(base_vha) != QLA_SUCCESS) + ql_dbg(ql_dbg_p3p, base_vha, 0xb079, + "Error while clearing DRV-Presence.\n"); + } + + qla2x00_try_to_stop_firmware(base_vha); + } + qla2x00_wait_for_sess_deletion(base_vha); /* @@ -3648,14 +3666,6 @@ qla2x00_remove_one(struct pci_dev *pdev) qla2x00_delete_all_vps(ha, base_vha); - if (IS_QLA8031(ha)) { - ql_dbg(ql_dbg_p3p, base_vha, 0xb07e, - "Clearing fcoe driver presence.\n"); - if (qla83xx_clear_drv_presence(base_vha) != QLA_SUCCESS) - ql_dbg(ql_dbg_p3p, base_vha, 0xb079, - "Error while clearing DRV-Presence.\n"); - } - qla2x00_abort_all_cmds(base_vha, DID_NO_CONNECT << 16); qla2x00_dfs_remove(base_vha); @@ -3715,24 +3725,6 @@ qla2x00_free_device(scsi_qla_host_t *vha) qla2x00_stop_timer(vha); qla25xx_delete_queues(vha); - - if (ha->flags.fce_enabled) - qla2x00_disable_fce_trace(vha, NULL, NULL); - - if (ha->eft) - qla2x00_disable_eft_trace(vha); - - if (IS_QLA25XX(ha) || IS_QLA2031(ha) || IS_QLA27XX(ha)) { - if (ha->flags.fw_started) - qla2x00_abort_isp_cleanup(vha); - } else { - if (ha->flags.fw_started) { - /* Stop currently executing firmware. */ - qla2x00_try_to_stop_firmware(vha); - ha->flags.fw_started = 0; - } - } - vha->flags.online = 0; /* turn-off interrupts on the card */ @@ -6028,8 +6020,9 @@ qla2x00_do_dpc(void *data) set_bit(ISP_ABORT_NEEDED, &base_vha->dpc_flags); } - if (test_and_clear_bit(ISP_ABORT_NEEDED, - &base_vha->dpc_flags)) { + if (test_and_clear_bit + (ISP_ABORT_NEEDED, &base_vha->dpc_flags) && + !test_bit(UNLOADING, &base_vha->dpc_flags)) { ql_dbg(ql_dbg_dpc, base_vha, 0x4007, "ISP abort scheduled.\n"); diff --git a/drivers/scsi/qla2xxx/qla_sup.c b/drivers/scsi/qla2xxx/qla_sup.c index 04458eb19d38..4499c787165f 100644 --- a/drivers/scsi/qla2xxx/qla_sup.c +++ b/drivers/scsi/qla2xxx/qla_sup.c @@ -1880,6 +1880,9 @@ qla24xx_beacon_off(struct scsi_qla_host *vha) if (IS_P3P_TYPE(ha)) return QLA_SUCCESS; + if (!ha->flags.fw_started) + return QLA_SUCCESS; + ha->beacon_blink_led = 0; if (IS_QLA2031(ha) || IS_QLA27XX(ha)) diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 8932ae81a15a..2715cdaa669c 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -296,6 +296,20 @@ enum blk_eh_timer_return scsi_times_out(struct request *req) rtn = host->hostt->eh_timed_out(scmd); if (rtn == BLK_EH_DONE) { + /* + * For blk-mq, we must set the request state to complete now + * before sending the request to the scsi error handler. This + * will prevent a use-after-free in the event the LLD manages + * to complete the request before the error handler finishes + * processing this timed out request. + * + * If the request was already completed, then the LLD beat the + * time out handler from transferring the request to the scsi + * error handler. In that case we can return immediately as no + * further action is required. + */ + if (req->q->mq_ops && !blk_mq_mark_complete(req)) + return rtn; if (scsi_abort_command(scmd) != SUCCESS) { set_host_byte(scmd, DID_TIME_OUT); scsi_eh_scmd_add(scmd); diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index cd2fdac000c9..ba9ba0e04f42 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1741,15 +1741,11 @@ sg_start_req(Sg_request *srp, unsigned char *cmd) * * With scsi-mq enabled, there are a fixed number of preallocated * requests equal in number to shost->can_queue. If all of the - * preallocated requests are already in use, then using GFP_ATOMIC with - * blk_get_request() will return -EWOULDBLOCK, whereas using GFP_KERNEL - * will cause blk_get_request() to sleep until an active command - * completes, freeing up a request. Neither option is ideal, but - * GFP_KERNEL is the better choice to prevent userspace from getting an - * unexpected EWOULDBLOCK. - * - * With scsi-mq disabled, blk_get_request() with GFP_KERNEL usually - * does not sleep except under memory pressure. + * preallocated requests are already in use, then blk_get_request() + * will sleep until an active command completes, freeing up a request. + * Although waiting in an asynchronous interface is less than ideal, we + * do not want to use BLK_MQ_REQ_NOWAIT here because userspace might + * not expect an EWOULDBLOCK from this condition. */ rq = blk_get_request(q, hp->dxfer_direction == SG_DXFER_TO_DEV ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0); @@ -2185,6 +2181,7 @@ sg_add_sfp(Sg_device * sdp) write_lock_irqsave(&sdp->sfd_lock, iflags); if (atomic_read(&sdp->detaching)) { write_unlock_irqrestore(&sdp->sfd_lock, iflags); + kfree(sfp); return ERR_PTR(-ENODEV); } list_add_tail(&sfp->sfd_siblings, &sdp->sfds); diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index a1a0025b59e0..d5d33e12e952 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -402,6 +402,8 @@ static int ashmem_mmap(struct file *file, struct vm_area_struct *vma) fput(asma->file); goto out; } + } else { + vma_set_anonymous(vma); } if (vma->vm_file) diff --git a/drivers/staging/ks7010/ks_hostif.c b/drivers/staging/ks7010/ks_hostif.c index 0ecffab52ec2..abdaf7cf8162 100644 --- a/drivers/staging/ks7010/ks_hostif.c +++ b/drivers/staging/ks7010/ks_hostif.c @@ -1842,15 +1842,15 @@ void hostif_sme_multicast_set(struct ks_wlan_private *priv) memset(set_address, 0, NIC_MAX_MCAST_LIST * ETH_ALEN); if (dev->flags & IFF_PROMISC) { - hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER, - MCAST_FILTER_PROMISC); + hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER, + MCAST_FILTER_PROMISC); goto spin_unlock; } if ((netdev_mc_count(dev) > NIC_MAX_MCAST_LIST) || (dev->flags & IFF_ALLMULTI)) { - hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER, - MCAST_FILTER_MCASTALL); + hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER, + MCAST_FILTER_MCASTALL); goto spin_unlock; } @@ -1866,8 +1866,8 @@ void hostif_sme_multicast_set(struct ks_wlan_private *priv) ETH_ALEN * mc_count); } else { priv->sme_i.sme_flag |= SME_MULTICAST; - hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER, - MCAST_FILTER_MCAST); + hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER, + MCAST_FILTER_MCAST); } spin_unlock: diff --git a/drivers/staging/media/omap4iss/iss_video.c b/drivers/staging/media/omap4iss/iss_video.c index a3a83424a926..16478fe9e3f8 100644 --- a/drivers/staging/media/omap4iss/iss_video.c +++ b/drivers/staging/media/omap4iss/iss_video.c @@ -11,7 +11,6 @@ * (at your option) any later version. */ -#include <asm/cacheflush.h> #include <linux/clk.h> #include <linux/mm.h> #include <linux/pagemap.h> @@ -24,6 +23,8 @@ #include <media/v4l2-ioctl.h> #include <media/v4l2-mc.h> +#include <asm/cacheflush.h> + #include "iss_video.h" #include "iss.h" diff --git a/drivers/staging/rtl8188eu/Kconfig b/drivers/staging/rtl8188eu/Kconfig index 673fdce25530..ff7832798a77 100644 --- a/drivers/staging/rtl8188eu/Kconfig +++ b/drivers/staging/rtl8188eu/Kconfig @@ -7,7 +7,6 @@ config R8188EU select LIB80211 select LIB80211_CRYPT_WEP select LIB80211_CRYPT_CCMP - select LIB80211_CRYPT_TKIP ---help--- This option adds the Realtek RTL8188EU USB device such as TP-Link TL-WN725N. If built as a module, it will be called r8188eu. diff --git a/drivers/staging/rtl8188eu/core/rtw_recv.c b/drivers/staging/rtl8188eu/core/rtw_recv.c index 05936a45eb93..c6857a5be12a 100644 --- a/drivers/staging/rtl8188eu/core/rtw_recv.c +++ b/drivers/staging/rtl8188eu/core/rtw_recv.c @@ -23,7 +23,6 @@ #include <mon.h> #include <wifi.h> #include <linux/vmalloc.h> -#include <net/lib80211.h> #define ETHERNET_HEADER_SIZE 14 /* Ethernet Header Length */ #define LLC_HEADER_SIZE 6 /* LLC Header Length */ @@ -221,20 +220,31 @@ u32 rtw_free_uc_swdec_pending_queue(struct adapter *adapter) static int recvframe_chkmic(struct adapter *adapter, struct recv_frame *precvframe) { - int res = _SUCCESS; - struct rx_pkt_attrib *prxattrib = &precvframe->attrib; - struct sta_info *stainfo = rtw_get_stainfo(&adapter->stapriv, prxattrib->ta); + int i, res = _SUCCESS; + u32 datalen; + u8 miccode[8]; + u8 bmic_err = false, brpt_micerror = true; + u8 *pframe, *payload, *pframemic; + u8 *mickey; + struct sta_info *stainfo; + struct rx_pkt_attrib *prxattrib = &precvframe->attrib; + struct security_priv *psecuritypriv = &adapter->securitypriv; + + struct mlme_ext_priv *pmlmeext = &adapter->mlmeextpriv; + struct mlme_ext_info *pmlmeinfo = &(pmlmeext->mlmext_info); + + stainfo = rtw_get_stainfo(&adapter->stapriv, &prxattrib->ta[0]); if (prxattrib->encrypt == _TKIP_) { + RT_TRACE(_module_rtl871x_recv_c_, _drv_info_, + ("\n %s: prxattrib->encrypt==_TKIP_\n", __func__)); + RT_TRACE(_module_rtl871x_recv_c_, _drv_info_, + ("\n %s: da=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n", + __func__, prxattrib->ra[0], prxattrib->ra[1], prxattrib->ra[2], + prxattrib->ra[3], prxattrib->ra[4], prxattrib->ra[5])); + + /* calculate mic code */ if (stainfo) { - int key_idx; - const int iv_len = 8, icv_len = 4, key_length = 32; - struct sk_buff *skb = precvframe->pkt; - u8 key[32], iv[8], icv[4], *pframe = skb->data; - void *crypto_private = NULL; - struct lib80211_crypto_ops *crypto_ops = try_then_request_module(lib80211_get_crypto_ops("TKIP"), "lib80211_crypt_tkip"); - struct security_priv *psecuritypriv = &adapter->securitypriv; - if (IS_MCAST(prxattrib->ra)) { if (!psecuritypriv) { res = _FAIL; @@ -243,58 +253,115 @@ static int recvframe_chkmic(struct adapter *adapter, DBG_88E("\n %s: didn't install group key!!!!!!!!!!\n", __func__); goto exit; } - key_idx = prxattrib->key_index; - memcpy(key, psecuritypriv->dot118021XGrpKey[key_idx].skey, 16); - memcpy(key + 16, psecuritypriv->dot118021XGrprxmickey[key_idx].skey, 16); + mickey = &psecuritypriv->dot118021XGrprxmickey[prxattrib->key_index].skey[0]; + + RT_TRACE(_module_rtl871x_recv_c_, _drv_info_, + ("\n %s: bcmc key\n", __func__)); } else { - key_idx = 0; - memcpy(key, stainfo->dot118021x_UncstKey.skey, 16); - memcpy(key + 16, stainfo->dot11tkiprxmickey.skey, 16); + mickey = &stainfo->dot11tkiprxmickey.skey[0]; + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("\n %s: unicast key\n", __func__)); } - if (!crypto_ops) { - res = _FAIL; - goto exit_lib80211_tkip; - } + /* icv_len included the mic code */ + datalen = precvframe->pkt->len-prxattrib->hdrlen - + prxattrib->iv_len-prxattrib->icv_len-8; + pframe = precvframe->pkt->data; + payload = pframe+prxattrib->hdrlen+prxattrib->iv_len; - memcpy(iv, pframe + prxattrib->hdrlen, iv_len); - memcpy(icv, pframe + skb->len - icv_len, icv_len); - memmove(pframe + iv_len, pframe, prxattrib->hdrlen); + RT_TRACE(_module_rtl871x_recv_c_, _drv_info_, ("\n prxattrib->iv_len=%d prxattrib->icv_len=%d\n", prxattrib->iv_len, prxattrib->icv_len)); + rtw_seccalctkipmic(mickey, pframe, payload, datalen, &miccode[0], + (unsigned char)prxattrib->priority); /* care the length of the data */ - skb_pull(skb, iv_len); - skb_trim(skb, skb->len - icv_len); + pframemic = payload+datalen; - crypto_private = crypto_ops->init(key_idx); - if (!crypto_private) { - res = _FAIL; - goto exit_lib80211_tkip; - } - if (crypto_ops->set_key(key, key_length, NULL, crypto_private) < 0) { - res = _FAIL; - goto exit_lib80211_tkip; - } - if (crypto_ops->decrypt_msdu(skb, key_idx, prxattrib->hdrlen, crypto_private)) { - res = _FAIL; - goto exit_lib80211_tkip; + bmic_err = false; + + for (i = 0; i < 8; i++) { + if (miccode[i] != *(pframemic+i)) { + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("%s: miccode[%d](%02x)!=*(pframemic+%d)(%02x) ", + __func__, i, miccode[i], i, *(pframemic + i))); + bmic_err = true; + } } - memmove(pframe, pframe + iv_len, prxattrib->hdrlen); - skb_push(skb, iv_len); - skb_put(skb, icv_len); + if (bmic_err) { + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("\n *(pframemic-8)-*(pframemic-1)=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n", + *(pframemic-8), *(pframemic-7), *(pframemic-6), + *(pframemic-5), *(pframemic-4), *(pframemic-3), + *(pframemic-2), *(pframemic-1))); + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("\n *(pframemic-16)-*(pframemic-9)=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n", + *(pframemic-16), *(pframemic-15), *(pframemic-14), + *(pframemic-13), *(pframemic-12), *(pframemic-11), + *(pframemic-10), *(pframemic-9))); + { + uint i; - memcpy(pframe + prxattrib->hdrlen, iv, iv_len); - memcpy(pframe + skb->len - icv_len, icv, icv_len); + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("\n ======demp packet (len=%d)======\n", + precvframe->pkt->len)); + for (i = 0; i < precvframe->pkt->len; i += 8) { + RT_TRACE(_module_rtl871x_recv_c_, + _drv_err_, + ("0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x", + *(precvframe->pkt->data+i), + *(precvframe->pkt->data+i+1), + *(precvframe->pkt->data+i+2), + *(precvframe->pkt->data+i+3), + *(precvframe->pkt->data+i+4), + *(precvframe->pkt->data+i+5), + *(precvframe->pkt->data+i+6), + *(precvframe->pkt->data+i+7))); + } + RT_TRACE(_module_rtl871x_recv_c_, + _drv_err_, + ("\n ====== demp packet end [len=%d]======\n", + precvframe->pkt->len)); + RT_TRACE(_module_rtl871x_recv_c_, + _drv_err_, + ("\n hrdlen=%d,\n", + prxattrib->hdrlen)); + } -exit_lib80211_tkip: - if (crypto_ops && crypto_private) - crypto_ops->deinit(crypto_private); + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, + ("ra=0x%.2x 0x%.2x 0x%.2x 0x%.2x 0x%.2x 0x%.2x psecuritypriv->binstallGrpkey=%d ", + prxattrib->ra[0], prxattrib->ra[1], prxattrib->ra[2], + prxattrib->ra[3], prxattrib->ra[4], prxattrib->ra[5], psecuritypriv->binstallGrpkey)); + + /* double check key_index for some timing issue , */ + /* cannot compare with psecuritypriv->dot118021XGrpKeyid also cause timing issue */ + if ((IS_MCAST(prxattrib->ra) == true) && (prxattrib->key_index != pmlmeinfo->key_index)) + brpt_micerror = false; + + if ((prxattrib->bdecrypted) && (brpt_micerror)) { + rtw_handle_tkip_mic_err(adapter, (u8)IS_MCAST(prxattrib->ra)); + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, (" mic error :prxattrib->bdecrypted=%d ", prxattrib->bdecrypted)); + DBG_88E(" mic error :prxattrib->bdecrypted=%d\n", prxattrib->bdecrypted); + } else { + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, (" mic error :prxattrib->bdecrypted=%d ", prxattrib->bdecrypted)); + DBG_88E(" mic error :prxattrib->bdecrypted=%d\n", prxattrib->bdecrypted); + } + res = _FAIL; + } else { + /* mic checked ok */ + if ((!psecuritypriv->bcheck_grpkey) && (IS_MCAST(prxattrib->ra))) { + psecuritypriv->bcheck_grpkey = true; + RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, ("psecuritypriv->bcheck_grpkey = true")); + } + } } else { RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, ("%s: rtw_get_stainfo==NULL!!!\n", __func__)); } + + skb_trim(precvframe->pkt, precvframe->pkt->len - 8); } exit: + return res; } diff --git a/drivers/staging/rtl8188eu/core/rtw_security.c b/drivers/staging/rtl8188eu/core/rtw_security.c index bfe0b217e679..67a2490f055e 100644 --- a/drivers/staging/rtl8188eu/core/rtw_security.c +++ b/drivers/staging/rtl8188eu/core/rtw_security.c @@ -650,71 +650,71 @@ u32 rtw_tkip_encrypt(struct adapter *padapter, u8 *pxmitframe) return res; } +/* The hlen isn't include the IV */ u32 rtw_tkip_decrypt(struct adapter *padapter, u8 *precvframe) -{ - struct rx_pkt_attrib *prxattrib = &((struct recv_frame *)precvframe)->attrib; - u32 res = _SUCCESS; +{ /* exclude ICV */ + u16 pnl; + u32 pnh; + u8 rc4key[16]; + u8 ttkey[16]; + u8 crc[4]; + struct arc4context mycontext; + int length; + + u8 *pframe, *payload, *iv, *prwskey; + union pn48 dot11txpn; + struct sta_info *stainfo; + struct rx_pkt_attrib *prxattrib = &((struct recv_frame *)precvframe)->attrib; + struct security_priv *psecuritypriv = &padapter->securitypriv; + u32 res = _SUCCESS; + + + pframe = (unsigned char *)((struct recv_frame *)precvframe)->pkt->data; /* 4 start to decrypt recvframe */ if (prxattrib->encrypt == _TKIP_) { - struct sta_info *stainfo = rtw_get_stainfo(&padapter->stapriv, prxattrib->ta); - + stainfo = rtw_get_stainfo(&padapter->stapriv, &prxattrib->ta[0]); if (stainfo) { - int key_idx; - const int iv_len = 8, icv_len = 4, key_length = 32; - void *crypto_private = NULL; - struct sk_buff *skb = ((struct recv_frame *)precvframe)->pkt; - u8 key[32], iv[8], icv[4], *pframe = skb->data; - struct lib80211_crypto_ops *crypto_ops = try_then_request_module(lib80211_get_crypto_ops("TKIP"), "lib80211_crypt_tkip"); - struct security_priv *psecuritypriv = &padapter->securitypriv; - if (IS_MCAST(prxattrib->ra)) { if (!psecuritypriv->binstallGrpkey) { res = _FAIL; DBG_88E("%s:rx bc/mc packets, but didn't install group key!!!!!!!!!!\n", __func__); goto exit; } - key_idx = prxattrib->key_index; - memcpy(key, psecuritypriv->dot118021XGrpKey[key_idx].skey, 16); - memcpy(key + 16, psecuritypriv->dot118021XGrprxmickey[key_idx].skey, 16); + prwskey = psecuritypriv->dot118021XGrpKey[prxattrib->key_index].skey; } else { - key_idx = 0; - memcpy(key, stainfo->dot118021x_UncstKey.skey, 16); - memcpy(key + 16, stainfo->dot11tkiprxmickey.skey, 16); + RT_TRACE(_module_rtl871x_security_c_, _drv_err_, ("%s: stainfo!= NULL!!!\n", __func__)); + prwskey = &stainfo->dot118021x_UncstKey.skey[0]; } - if (!crypto_ops) { - res = _FAIL; - goto exit_lib80211_tkip; - } + iv = pframe+prxattrib->hdrlen; + payload = pframe+prxattrib->iv_len+prxattrib->hdrlen; + length = ((struct recv_frame *)precvframe)->pkt->len-prxattrib->hdrlen-prxattrib->iv_len; - memcpy(iv, pframe + prxattrib->hdrlen, iv_len); - memcpy(icv, pframe + skb->len - icv_len, icv_len); + GET_TKIP_PN(iv, dot11txpn); - crypto_private = crypto_ops->init(key_idx); - if (!crypto_private) { - res = _FAIL; - goto exit_lib80211_tkip; - } - if (crypto_ops->set_key(key, key_length, NULL, crypto_private) < 0) { - res = _FAIL; - goto exit_lib80211_tkip; - } - if (crypto_ops->decrypt_mpdu(skb, prxattrib->hdrlen, crypto_private)) { - res = _FAIL; - goto exit_lib80211_tkip; - } + pnl = (u16)(dot11txpn.val); + pnh = (u32)(dot11txpn.val>>16); - memmove(pframe, pframe + iv_len, prxattrib->hdrlen); - skb_push(skb, iv_len); - skb_put(skb, icv_len); + phase1((u16 *)&ttkey[0], prwskey, &prxattrib->ta[0], pnh); + phase2(&rc4key[0], prwskey, (unsigned short *)&ttkey[0], pnl); - memcpy(pframe + prxattrib->hdrlen, iv, iv_len); - memcpy(pframe + skb->len - icv_len, icv, icv_len); + /* 4 decrypt payload include icv */ -exit_lib80211_tkip: - if (crypto_ops && crypto_private) - crypto_ops->deinit(crypto_private); + arcfour_init(&mycontext, rc4key, 16); + arcfour_encrypt(&mycontext, payload, payload, length); + + *((__le32 *)crc) = getcrc32(payload, length-4); + + if (crc[3] != payload[length-1] || + crc[2] != payload[length-2] || + crc[1] != payload[length-3] || + crc[0] != payload[length-4]) { + RT_TRACE(_module_rtl871x_security_c_, _drv_err_, + ("rtw_wep_decrypt:icv error crc (%4ph)!=payload (%4ph)\n", + &crc, &payload[length-4])); + res = _FAIL; + } } else { RT_TRACE(_module_rtl871x_security_c_, _drv_err_, ("rtw_tkip_decrypt: stainfo==NULL!!!\n")); res = _FAIL; diff --git a/drivers/staging/speakup/speakup_soft.c b/drivers/staging/speakup/speakup_soft.c index a61bc41b82d7..947c79532e10 100644 --- a/drivers/staging/speakup/speakup_soft.c +++ b/drivers/staging/speakup/speakup_soft.c @@ -198,11 +198,15 @@ static ssize_t softsynthx_read(struct file *fp, char __user *buf, size_t count, int chars_sent = 0; char __user *cp; char *init; + size_t bytes_per_ch = unicode ? 3 : 1; u16 ch; int empty; unsigned long flags; DEFINE_WAIT(wait); + if (count < bytes_per_ch) + return -EINVAL; + spin_lock_irqsave(&speakup_info.spinlock, flags); while (1) { prepare_to_wait(&speakup_event, &wait, TASK_INTERRUPTIBLE); @@ -228,7 +232,7 @@ static ssize_t softsynthx_read(struct file *fp, char __user *buf, size_t count, init = get_initstring(); /* Keep 3 bytes available for a 16bit UTF-8-encoded character */ - while (chars_sent <= count - 3) { + while (chars_sent <= count - bytes_per_ch) { if (speakup_info.flushing) { speakup_info.flushing = 0; ch = '\x18'; diff --git a/drivers/target/iscsi/cxgbit/cxgbit_target.c b/drivers/target/iscsi/cxgbit/cxgbit_target.c index 514986b57c2d..25eb3891e34b 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_target.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_target.c @@ -652,6 +652,7 @@ static int cxgbit_set_iso_npdu(struct cxgbit_sock *csk) struct iscsi_param *param; u32 mrdsl, mbl; u32 max_npdu, max_iso_npdu; + u32 max_iso_payload; if (conn->login->leading_connection) { param = iscsi_find_param_from_key(MAXBURSTLENGTH, @@ -670,8 +671,10 @@ static int cxgbit_set_iso_npdu(struct cxgbit_sock *csk) mrdsl = conn_ops->MaxRecvDataSegmentLength; max_npdu = mbl / mrdsl; - max_iso_npdu = CXGBIT_MAX_ISO_PAYLOAD / - (ISCSI_HDR_LEN + mrdsl + + max_iso_payload = rounddown(CXGBIT_MAX_ISO_PAYLOAD, csk->emss); + + max_iso_npdu = max_iso_payload / + (ISCSI_HDR_LEN + mrdsl + cxgbit_digest_len[csk->submode]); csk->max_iso_npdu = min(max_npdu, max_iso_npdu); @@ -741,6 +744,9 @@ static int cxgbit_set_params(struct iscsi_conn *conn) if (conn_ops->MaxRecvDataSegmentLength > cdev->mdsl) conn_ops->MaxRecvDataSegmentLength = cdev->mdsl; + if (cxgbit_set_digest(csk)) + return -1; + if (conn->login->leading_connection) { param = iscsi_find_param_from_key(ERRORRECOVERYLEVEL, conn->param_list); @@ -764,7 +770,7 @@ static int cxgbit_set_params(struct iscsi_conn *conn) if (is_t5(cdev->lldi.adapter_type)) goto enable_ddp; else - goto enable_digest; + return 0; } if (test_bit(CDEV_ISO_ENABLE, &cdev->flags)) { @@ -781,10 +787,6 @@ enable_ddp: } } -enable_digest: - if (cxgbit_set_digest(csk)) - return -1; - return 0; } diff --git a/drivers/usb/chipidea/Kconfig b/drivers/usb/chipidea/Kconfig index 785f0ed037f7..ee34e9046f7e 100644 --- a/drivers/usb/chipidea/Kconfig +++ b/drivers/usb/chipidea/Kconfig @@ -3,6 +3,7 @@ config USB_CHIPIDEA depends on ((USB_EHCI_HCD && USB_GADGET) || (USB_EHCI_HCD && !USB_GADGET) || (!USB_EHCI_HCD && USB_GADGET)) && HAS_DMA select EXTCON select RESET_CONTROLLER + select USB_ULPI_BUS help Say Y here if your system has a dual role high speed USB controller based on ChipIdea silicon IP. It supports: @@ -38,12 +39,4 @@ config USB_CHIPIDEA_HOST help Say Y here to enable host controller functionality of the ChipIdea driver. - -config USB_CHIPIDEA_ULPI - bool "ChipIdea ULPI PHY support" - depends on USB_ULPI_BUS=y || USB_ULPI_BUS=USB_CHIPIDEA - help - Say Y here if you have a ULPI PHY attached to your ChipIdea - controller. - endif diff --git a/drivers/usb/chipidea/Makefile b/drivers/usb/chipidea/Makefile index e3d5e728fa53..12df94f78f72 100644 --- a/drivers/usb/chipidea/Makefile +++ b/drivers/usb/chipidea/Makefile @@ -1,11 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_USB_CHIPIDEA) += ci_hdrc.o -ci_hdrc-y := core.o otg.o debug.o +ci_hdrc-y := core.o otg.o debug.o ulpi.o ci_hdrc-$(CONFIG_USB_CHIPIDEA_UDC) += udc.o ci_hdrc-$(CONFIG_USB_CHIPIDEA_HOST) += host.o ci_hdrc-$(CONFIG_USB_OTG_FSM) += otg_fsm.o -ci_hdrc-$(CONFIG_USB_CHIPIDEA_ULPI) += ulpi.o # Glue/Bridge layers go here diff --git a/drivers/usb/chipidea/ci.h b/drivers/usb/chipidea/ci.h index 0bf244d50544..6a2cc5cd0281 100644 --- a/drivers/usb/chipidea/ci.h +++ b/drivers/usb/chipidea/ci.h @@ -240,10 +240,8 @@ struct ci_hdrc { struct ci_hdrc_platform_data *platdata; int vbus_active; -#ifdef CONFIG_USB_CHIPIDEA_ULPI struct ulpi *ulpi; struct ulpi_ops ulpi_ops; -#endif struct phy *phy; /* old usb_phy interface */ struct usb_phy *usb_phy; @@ -426,15 +424,9 @@ static inline bool ci_otg_is_fsm_mode(struct ci_hdrc *ci) #endif } -#if IS_ENABLED(CONFIG_USB_CHIPIDEA_ULPI) int ci_ulpi_init(struct ci_hdrc *ci); void ci_ulpi_exit(struct ci_hdrc *ci); int ci_ulpi_resume(struct ci_hdrc *ci); -#else -static inline int ci_ulpi_init(struct ci_hdrc *ci) { return 0; } -static inline void ci_ulpi_exit(struct ci_hdrc *ci) { } -static inline int ci_ulpi_resume(struct ci_hdrc *ci) { return 0; } -#endif u32 hw_read_intr_enable(struct ci_hdrc *ci); diff --git a/drivers/usb/chipidea/ulpi.c b/drivers/usb/chipidea/ulpi.c index 6da42dcd2888..dfec07e8ae1d 100644 --- a/drivers/usb/chipidea/ulpi.c +++ b/drivers/usb/chipidea/ulpi.c @@ -95,6 +95,9 @@ int ci_ulpi_resume(struct ci_hdrc *ci) { int cnt = 100000; + if (ci->platdata->phy_mode != USBPHY_INTERFACE_MODE_ULPI) + return 0; + while (cnt-- > 0) { if (hw_read(ci, OP_ULPI_VIEWPORT, ULPI_SYNC_STATE)) return 0; diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 998b32d0167e..75c4623ad779 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1831,6 +1831,9 @@ static const struct usb_device_id acm_ids[] = { { USB_DEVICE(0x09d8, 0x0320), /* Elatec GmbH TWN3 */ .driver_info = NO_UNION_NORMAL, /* has misplaced union descriptor */ }, + { USB_DEVICE(0x0ca6, 0xa050), /* Castles VEGA3000 */ + .driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */ + }, { USB_DEVICE(0x2912, 0x0001), /* ATOL FPrint */ .driver_info = CLEAR_HALT_CONDITIONS, diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index fcae521df29b..1fb266809966 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -1142,10 +1142,14 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) if (!udev || udev->state == USB_STATE_NOTATTACHED) { /* Tell hub_wq to disconnect the device or - * check for a new connection + * check for a new connection or over current condition. + * Based on USB2.0 Spec Section 11.12.5, + * C_PORT_OVER_CURRENT could be set while + * PORT_OVER_CURRENT is not. So check for any of them. */ if (udev || (portstatus & USB_PORT_STAT_CONNECTION) || - (portstatus & USB_PORT_STAT_OVERCURRENT)) + (portstatus & USB_PORT_STAT_OVERCURRENT) || + (portchange & USB_PORT_STAT_C_OVERCURRENT)) set_bit(port1, hub->change_bits); } else if (portstatus & USB_PORT_STAT_ENABLE) { diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index a0f82cca2d9a..cefc99ae69b2 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -3430,7 +3430,7 @@ static void dwc2_gadget_handle_incomplete_isoc_in(struct dwc2_hsotg *hsotg) for (idx = 1; idx < hsotg->num_of_eps; idx++) { hs_ep = hsotg->eps_in[idx]; /* Proceed only unmasked ISOC EPs */ - if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk)) + if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous) continue; epctrl = dwc2_readl(hsotg->regs + DIEPCTL(idx)); @@ -3476,7 +3476,7 @@ static void dwc2_gadget_handle_incomplete_isoc_out(struct dwc2_hsotg *hsotg) for (idx = 1; idx < hsotg->num_of_eps; idx++) { hs_ep = hsotg->eps_out[idx]; /* Proceed only unmasked ISOC EPs */ - if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk)) + if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous) continue; epctrl = dwc2_readl(hsotg->regs + DOEPCTL(idx)); @@ -3650,7 +3650,7 @@ irq_retry: for (idx = 1; idx < hsotg->num_of_eps; idx++) { hs_ep = hsotg->eps_out[idx]; /* Proceed only unmasked ISOC EPs */ - if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk)) + if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous) continue; epctrl = dwc2_readl(hsotg->regs + DOEPCTL(idx)); diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c index b1104be3429c..6e2cdd7b93d4 100644 --- a/drivers/usb/dwc2/hcd.c +++ b/drivers/usb/dwc2/hcd.c @@ -2665,34 +2665,35 @@ static int dwc2_alloc_split_dma_aligned_buf(struct dwc2_hsotg *hsotg, #define DWC2_USB_DMA_ALIGN 4 -struct dma_aligned_buffer { - void *kmalloc_ptr; - void *old_xfer_buffer; - u8 data[0]; -}; - static void dwc2_free_dma_aligned_buffer(struct urb *urb) { - struct dma_aligned_buffer *temp; + void *stored_xfer_buffer; + size_t length; if (!(urb->transfer_flags & URB_ALIGNED_TEMP_BUFFER)) return; - temp = container_of(urb->transfer_buffer, - struct dma_aligned_buffer, data); + /* Restore urb->transfer_buffer from the end of the allocated area */ + memcpy(&stored_xfer_buffer, urb->transfer_buffer + + urb->transfer_buffer_length, sizeof(urb->transfer_buffer)); - if (usb_urb_dir_in(urb)) - memcpy(temp->old_xfer_buffer, temp->data, - urb->transfer_buffer_length); - urb->transfer_buffer = temp->old_xfer_buffer; - kfree(temp->kmalloc_ptr); + if (usb_urb_dir_in(urb)) { + if (usb_pipeisoc(urb->pipe)) + length = urb->transfer_buffer_length; + else + length = urb->actual_length; + + memcpy(stored_xfer_buffer, urb->transfer_buffer, length); + } + kfree(urb->transfer_buffer); + urb->transfer_buffer = stored_xfer_buffer; urb->transfer_flags &= ~URB_ALIGNED_TEMP_BUFFER; } static int dwc2_alloc_dma_aligned_buffer(struct urb *urb, gfp_t mem_flags) { - struct dma_aligned_buffer *temp, *kmalloc_ptr; + void *kmalloc_ptr; size_t kmalloc_size; if (urb->num_sgs || urb->sg || @@ -2700,22 +2701,29 @@ static int dwc2_alloc_dma_aligned_buffer(struct urb *urb, gfp_t mem_flags) !((uintptr_t)urb->transfer_buffer & (DWC2_USB_DMA_ALIGN - 1))) return 0; - /* Allocate a buffer with enough padding for alignment */ + /* + * Allocate a buffer with enough padding for original transfer_buffer + * pointer. This allocation is guaranteed to be aligned properly for + * DMA + */ kmalloc_size = urb->transfer_buffer_length + - sizeof(struct dma_aligned_buffer) + DWC2_USB_DMA_ALIGN - 1; + sizeof(urb->transfer_buffer); kmalloc_ptr = kmalloc(kmalloc_size, mem_flags); if (!kmalloc_ptr) return -ENOMEM; - /* Position our struct dma_aligned_buffer such that data is aligned */ - temp = PTR_ALIGN(kmalloc_ptr + 1, DWC2_USB_DMA_ALIGN) - 1; - temp->kmalloc_ptr = kmalloc_ptr; - temp->old_xfer_buffer = urb->transfer_buffer; + /* + * Position value of original urb->transfer_buffer pointer to the end + * of allocation for later referencing + */ + memcpy(kmalloc_ptr + urb->transfer_buffer_length, + &urb->transfer_buffer, sizeof(urb->transfer_buffer)); + if (usb_urb_dir_out(urb)) - memcpy(temp->data, urb->transfer_buffer, + memcpy(kmalloc_ptr, urb->transfer_buffer, urb->transfer_buffer_length); - urb->transfer_buffer = temp->data; + urb->transfer_buffer = kmalloc_ptr; urb->transfer_flags |= URB_ALIGNED_TEMP_BUFFER; diff --git a/drivers/usb/dwc2/hcd_intr.c b/drivers/usb/dwc2/hcd_intr.c index ed7f05cf4906..8ce10caf3e19 100644 --- a/drivers/usb/dwc2/hcd_intr.c +++ b/drivers/usb/dwc2/hcd_intr.c @@ -1231,7 +1231,10 @@ static void dwc2_hc_nak_intr(struct dwc2_hsotg *hsotg, * avoid interrupt storms we'll wait before retrying if we've got * several NAKs. If we didn't do this we'd retry directly from the * interrupt handler and could end up quickly getting another - * interrupt (another NAK), which we'd retry. + * interrupt (another NAK), which we'd retry. Note that we do not + * delay retries for IN parts of control requests, as those are expected + * to complete fairly quickly, and if we delay them we risk confusing + * the device and cause it issue STALL. * * Note that in DMA mode software only gets involved to re-send NAKed * transfers for split transactions, so we only need to apply this @@ -1244,7 +1247,9 @@ static void dwc2_hc_nak_intr(struct dwc2_hsotg *hsotg, qtd->error_count = 0; qtd->complete_split = 0; qtd->num_naks++; - qtd->qh->want_wait = qtd->num_naks >= DWC2_NAKS_BEFORE_DELAY; + qtd->qh->want_wait = qtd->num_naks >= DWC2_NAKS_BEFORE_DELAY && + !(chan->ep_type == USB_ENDPOINT_XFER_CONTROL && + chan->ep_is_in); dwc2_halt_channel(hsotg, chan, qtd, DWC2_HC_XFER_NAK); goto handle_nak_done; } diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index c77ff50a88a2..8efde178eef4 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -973,15 +973,12 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc, ret = dwc3_ep0_start_trans(dep); } else if (IS_ALIGNED(req->request.length, dep->endpoint.maxpacket) && req->request.length && req->request.zero) { - u32 maxpacket; ret = usb_gadget_map_request_by_dev(dwc->sysdev, &req->request, dep->number); if (ret) return; - maxpacket = dep->endpoint.maxpacket; - /* prepare normal TRB */ dwc3_ep0_prepare_one_trb(dep, req->request.dma, req->request.length, diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index d2fa071c21b1..b8a15840b4ff 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -1819,7 +1819,6 @@ unknown: if (cdev->use_os_string && cdev->os_desc_config && (ctrl->bRequestType & USB_TYPE_VENDOR) && ctrl->bRequest == cdev->b_vendor_code) { - struct usb_request *req; struct usb_configuration *os_desc_cfg; u8 *buf; int interface; diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 33e2030503fa..3ada83d81bda 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3263,7 +3263,7 @@ static int ffs_func_setup(struct usb_function *f, __ffs_event_add(ffs, FUNCTIONFS_SETUP); spin_unlock_irqrestore(&ffs->ev.waitq.lock, flags); - return USB_GADGET_DELAYED_STATUS; + return creq->wLength == 0 ? USB_GADGET_DELAYED_STATUS : 0; } static bool ffs_func_req_match(struct usb_function *f, diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c index d2dc1f00180b..d582921f7257 100644 --- a/drivers/usb/gadget/function/f_uac2.c +++ b/drivers/usb/gadget/function/f_uac2.c @@ -438,14 +438,14 @@ static struct usb_descriptor_header *hs_audio_desc[] = { }; struct cntrl_cur_lay3 { - __u32 dCUR; + __le32 dCUR; }; struct cntrl_range_lay3 { - __u16 wNumSubRanges; - __u32 dMIN; - __u32 dMAX; - __u32 dRES; + __le16 wNumSubRanges; + __le32 dMIN; + __le32 dMAX; + __le32 dRES; } __packed; static void set_ep_max_packet_size(const struct f_uac2_opts *uac2_opts, @@ -559,13 +559,13 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn) agdev->out_ep = usb_ep_autoconfig(gadget, &fs_epout_desc); if (!agdev->out_ep) { dev_err(dev, "%s:%d Error!\n", __func__, __LINE__); - return ret; + return -ENODEV; } agdev->in_ep = usb_ep_autoconfig(gadget, &fs_epin_desc); if (!agdev->in_ep) { dev_err(dev, "%s:%d Error!\n", __func__, __LINE__); - return ret; + return -ENODEV; } agdev->in_ep_maxpsize = max_t(u16, @@ -703,9 +703,9 @@ in_rq_cur(struct usb_function *fn, const struct usb_ctrlrequest *cr) memset(&c, 0, sizeof(struct cntrl_cur_lay3)); if (entity_id == USB_IN_CLK_ID) - c.dCUR = p_srate; + c.dCUR = cpu_to_le32(p_srate); else if (entity_id == USB_OUT_CLK_ID) - c.dCUR = c_srate; + c.dCUR = cpu_to_le32(c_srate); value = min_t(unsigned, w_length, sizeof c); memcpy(req->buf, &c, value); @@ -742,15 +742,15 @@ in_rq_range(struct usb_function *fn, const struct usb_ctrlrequest *cr) if (control_selector == UAC2_CS_CONTROL_SAM_FREQ) { if (entity_id == USB_IN_CLK_ID) - r.dMIN = p_srate; + r.dMIN = cpu_to_le32(p_srate); else if (entity_id == USB_OUT_CLK_ID) - r.dMIN = c_srate; + r.dMIN = cpu_to_le32(c_srate); else return -EOPNOTSUPP; r.dMAX = r.dMIN; r.dRES = 0; - r.wNumSubRanges = 1; + r.wNumSubRanges = cpu_to_le16(1); value = min_t(unsigned, w_length, sizeof r); memcpy(req->buf, &r, value); diff --git a/drivers/usb/gadget/function/u_audio.c b/drivers/usb/gadget/function/u_audio.c index a72295c953bb..fb5ed97572e5 100644 --- a/drivers/usb/gadget/function/u_audio.c +++ b/drivers/usb/gadget/function/u_audio.c @@ -32,9 +32,6 @@ struct uac_req { struct uac_rtd_params { struct snd_uac_chip *uac; /* parent chip */ bool ep_enabled; /* if the ep is enabled */ - /* Size of the ring buffer */ - size_t dma_bytes; - unsigned char *dma_area; struct snd_pcm_substream *ss; @@ -43,8 +40,6 @@ struct uac_rtd_params { void *rbuf; - size_t period_size; - unsigned max_psize; /* MaxPacketSize of endpoint */ struct uac_req *ureq; @@ -84,12 +79,12 @@ static const struct snd_pcm_hardware uac_pcm_hardware = { static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req) { unsigned pending; - unsigned long flags; + unsigned long flags, flags2; unsigned int hw_ptr; - bool update_alsa = false; int status = req->status; struct uac_req *ur = req->context; struct snd_pcm_substream *substream; + struct snd_pcm_runtime *runtime; struct uac_rtd_params *prm = ur->pp; struct snd_uac_chip *uac = prm->uac; @@ -111,6 +106,14 @@ static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req) if (!substream) goto exit; + snd_pcm_stream_lock_irqsave(substream, flags2); + + runtime = substream->runtime; + if (!runtime || !snd_pcm_running(substream)) { + snd_pcm_stream_unlock_irqrestore(substream, flags2); + goto exit; + } + spin_lock_irqsave(&prm->lock, flags); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { @@ -137,43 +140,46 @@ static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req) req->actual = req->length; } - pending = prm->hw_ptr % prm->period_size; - pending += req->actual; - if (pending >= prm->period_size) - update_alsa = true; - hw_ptr = prm->hw_ptr; - prm->hw_ptr = (prm->hw_ptr + req->actual) % prm->dma_bytes; spin_unlock_irqrestore(&prm->lock, flags); /* Pack USB load in ALSA ring buffer */ - pending = prm->dma_bytes - hw_ptr; + pending = runtime->dma_bytes - hw_ptr; if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { if (unlikely(pending < req->actual)) { - memcpy(req->buf, prm->dma_area + hw_ptr, pending); - memcpy(req->buf + pending, prm->dma_area, + memcpy(req->buf, runtime->dma_area + hw_ptr, pending); + memcpy(req->buf + pending, runtime->dma_area, req->actual - pending); } else { - memcpy(req->buf, prm->dma_area + hw_ptr, req->actual); + memcpy(req->buf, runtime->dma_area + hw_ptr, + req->actual); } } else { if (unlikely(pending < req->actual)) { - memcpy(prm->dma_area + hw_ptr, req->buf, pending); - memcpy(prm->dma_area, req->buf + pending, + memcpy(runtime->dma_area + hw_ptr, req->buf, pending); + memcpy(runtime->dma_area, req->buf + pending, req->actual - pending); } else { - memcpy(prm->dma_area + hw_ptr, req->buf, req->actual); + memcpy(runtime->dma_area + hw_ptr, req->buf, + req->actual); } } + spin_lock_irqsave(&prm->lock, flags); + /* update hw_ptr after data is copied to memory */ + prm->hw_ptr = (hw_ptr + req->actual) % runtime->dma_bytes; + hw_ptr = prm->hw_ptr; + spin_unlock_irqrestore(&prm->lock, flags); + snd_pcm_stream_unlock_irqrestore(substream, flags2); + + if ((hw_ptr % snd_pcm_lib_period_bytes(substream)) < req->actual) + snd_pcm_period_elapsed(substream); + exit: if (usb_ep_queue(ep, req, GFP_ATOMIC)) dev_err(uac->card->dev, "%d Error!\n", __LINE__); - - if (update_alsa) - snd_pcm_period_elapsed(substream); } static int uac_pcm_trigger(struct snd_pcm_substream *substream, int cmd) @@ -236,40 +242,12 @@ static snd_pcm_uframes_t uac_pcm_pointer(struct snd_pcm_substream *substream) static int uac_pcm_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *hw_params) { - struct snd_uac_chip *uac = snd_pcm_substream_chip(substream); - struct uac_rtd_params *prm; - int err; - - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - prm = &uac->p_prm; - else - prm = &uac->c_prm; - - err = snd_pcm_lib_malloc_pages(substream, + return snd_pcm_lib_malloc_pages(substream, params_buffer_bytes(hw_params)); - if (err >= 0) { - prm->dma_bytes = substream->runtime->dma_bytes; - prm->dma_area = substream->runtime->dma_area; - prm->period_size = params_period_bytes(hw_params); - } - - return err; } static int uac_pcm_hw_free(struct snd_pcm_substream *substream) { - struct snd_uac_chip *uac = snd_pcm_substream_chip(substream); - struct uac_rtd_params *prm; - - if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) - prm = &uac->p_prm; - else - prm = &uac->c_prm; - - prm->dma_area = NULL; - prm->dma_bytes = 0; - prm->period_size = 0; - return snd_pcm_lib_free_pages(substream); } @@ -595,15 +573,15 @@ int g_audio_setup(struct g_audio *g_audio, const char *pcm_name, if (err < 0) goto snd_fail; - strcpy(pcm->name, pcm_name); + strlcpy(pcm->name, pcm_name, sizeof(pcm->name)); pcm->private_data = uac; uac->pcm = pcm; snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &uac_pcm_ops); snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &uac_pcm_ops); - strcpy(card->driver, card_name); - strcpy(card->shortname, card_name); + strlcpy(card->driver, card_name, sizeof(card->driver)); + strlcpy(card->shortname, card_name, sizeof(card->shortname)); sprintf(card->longname, "%s %i", card_name, card->dev->id); snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_CONTINUOUS, diff --git a/drivers/usb/gadget/udc/aspeed-vhub/ep0.c b/drivers/usb/gadget/udc/aspeed-vhub/ep0.c index 20ffb03ff6ac..e2927fb083cf 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/ep0.c +++ b/drivers/usb/gadget/udc/aspeed-vhub/ep0.c @@ -108,6 +108,13 @@ void ast_vhub_ep0_handle_setup(struct ast_vhub_ep *ep) /* Check our state, cancel pending requests if needed */ if (ep->ep0.state != ep0_state_token) { EPDBG(ep, "wrong state\n"); + ast_vhub_nuke(ep, -EIO); + + /* + * Accept the packet regardless, this seems to happen + * when stalling a SETUP packet that has an OUT data + * phase. + */ ast_vhub_nuke(ep, 0); goto stall; } @@ -212,6 +219,8 @@ static void ast_vhub_ep0_do_send(struct ast_vhub_ep *ep, if (chunk && req->req.buf) memcpy(ep->buf, req->req.buf + req->req.actual, chunk); + vhub_dma_workaround(ep->buf); + /* Remember chunk size and trigger send */ reg = VHUB_EP0_SET_TX_LEN(chunk); writel(reg, ep->ep0.ctlstat); @@ -224,7 +233,7 @@ static void ast_vhub_ep0_rx_prime(struct ast_vhub_ep *ep) EPVDBG(ep, "rx prime\n"); /* Prime endpoint for receiving data */ - writel(VHUB_EP0_RX_BUFF_RDY, ep->ep0.ctlstat + AST_VHUB_EP0_CTRL); + writel(VHUB_EP0_RX_BUFF_RDY, ep->ep0.ctlstat); } static void ast_vhub_ep0_do_receive(struct ast_vhub_ep *ep, struct ast_vhub_req *req, diff --git a/drivers/usb/gadget/udc/aspeed-vhub/epn.c b/drivers/usb/gadget/udc/aspeed-vhub/epn.c index 80c9feac5147..5939eb1e97f2 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/epn.c +++ b/drivers/usb/gadget/udc/aspeed-vhub/epn.c @@ -66,11 +66,16 @@ static void ast_vhub_epn_kick(struct ast_vhub_ep *ep, struct ast_vhub_req *req) if (!req->req.dma) { /* For IN transfers, copy data over first */ - if (ep->epn.is_in) + if (ep->epn.is_in) { memcpy(ep->buf, req->req.buf + act, chunk); + vhub_dma_workaround(ep->buf); + } writel(ep->buf_dma, ep->epn.regs + AST_VHUB_EP_DESC_BASE); - } else + } else { + if (ep->epn.is_in) + vhub_dma_workaround(req->req.buf); writel(req->req.dma + act, ep->epn.regs + AST_VHUB_EP_DESC_BASE); + } /* Start DMA */ req->active = true; @@ -161,6 +166,7 @@ static inline unsigned int ast_vhub_count_free_descs(struct ast_vhub_ep *ep) static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep, struct ast_vhub_req *req) { + struct ast_vhub_desc *desc = NULL; unsigned int act = req->act_count; unsigned int len = req->req.length; unsigned int chunk; @@ -177,7 +183,6 @@ static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep, /* While we can create descriptors */ while (ast_vhub_count_free_descs(ep) && req->last_desc < 0) { - struct ast_vhub_desc *desc; unsigned int d_num; /* Grab next free descriptor */ @@ -227,6 +232,9 @@ static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep, req->act_count = act = act + chunk; } + if (likely(desc)) + vhub_dma_workaround(desc); + /* Tell HW about new descriptors */ writel(VHUB_EP_DMA_SET_CPU_WPTR(ep->epn.d_next), ep->epn.regs + AST_VHUB_EP_DESC_STATUS); diff --git a/drivers/usb/gadget/udc/aspeed-vhub/vhub.h b/drivers/usb/gadget/udc/aspeed-vhub/vhub.h index 2b040257bc1f..4ed03d33a5a9 100644 --- a/drivers/usb/gadget/udc/aspeed-vhub/vhub.h +++ b/drivers/usb/gadget/udc/aspeed-vhub/vhub.h @@ -462,6 +462,39 @@ enum std_req_rc { #define DDBG(d, fmt, ...) do { } while(0) #endif +static inline void vhub_dma_workaround(void *addr) +{ + /* + * This works around a confirmed HW issue with the Aspeed chip. + * + * The core uses a different bus to memory than the AHB going to + * the USB device controller. Due to the latter having a higher + * priority than the core for arbitration on that bus, it's + * possible for an MMIO to the device, followed by a DMA by the + * device from memory to all be performed and services before + * a previous store to memory gets completed. + * + * This the following scenario can happen: + * + * - Driver writes to a DMA descriptor (Mbus) + * - Driver writes to the MMIO register to start the DMA (AHB) + * - The gadget sees the second write and sends a read of the + * descriptor to the memory controller (Mbus) + * - The gadget hits memory before the descriptor write + * causing it to read an obsolete value. + * + * Thankfully the problem is limited to the USB gadget device, other + * masters in the SoC all have a lower priority than the core, thus + * ensuring that the store by the core arrives first. + * + * The workaround consists of using a dummy read of the memory before + * doing the MMIO writes. This will ensure that the previous writes + * have been "pushed out". + */ + mb(); + (void)__raw_readl((void __iomem *)addr); +} + /* core.c */ void ast_vhub_done(struct ast_vhub_ep *ep, struct ast_vhub_req *req, int status); diff --git a/drivers/usb/gadget/udc/r8a66597-udc.c b/drivers/usb/gadget/udc/r8a66597-udc.c index a3ecce62662b..11e25a3f4f1f 100644 --- a/drivers/usb/gadget/udc/r8a66597-udc.c +++ b/drivers/usb/gadget/udc/r8a66597-udc.c @@ -832,11 +832,11 @@ static void init_controller(struct r8a66597 *r8a66597) r8a66597_bset(r8a66597, XCKE, SYSCFG0); - msleep(3); + mdelay(3); r8a66597_bset(r8a66597, PLLC, SYSCFG0); - msleep(1); + mdelay(1); r8a66597_bset(r8a66597, SCKE, SYSCFG0); @@ -1190,7 +1190,7 @@ __acquires(r8a66597->lock) r8a66597->ep0_req->length = 2; /* AV: what happens if we get called again before that gets through? */ spin_unlock(&r8a66597->lock); - r8a66597_queue(r8a66597->gadget.ep0, r8a66597->ep0_req, GFP_KERNEL); + r8a66597_queue(r8a66597->gadget.ep0, r8a66597->ep0_req, GFP_ATOMIC); spin_lock(&r8a66597->lock); } diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 2f4850f25e82..68e6132aa8b2 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -3051,6 +3051,7 @@ static void xhci_endpoint_reset(struct usb_hcd *hcd, if (!list_empty(&ep->ring->td_list)) { dev_err(&udev->dev, "EP not empty, refuse reset\n"); spin_unlock_irqrestore(&xhci->lock, flags); + xhci_free_command(xhci, cfg_cmd); goto cleanup; } xhci_queue_stop_endpoint(xhci, stop_cmd, udev->slot_id, ep_index, 0); diff --git a/drivers/usb/phy/phy-fsl-usb.c b/drivers/usb/phy/phy-fsl-usb.c index 900875f326d7..f7c96d209eda 100644 --- a/drivers/usb/phy/phy-fsl-usb.c +++ b/drivers/usb/phy/phy-fsl-usb.c @@ -861,6 +861,7 @@ int usb_otg_start(struct platform_device *pdev) if (pdata->init && pdata->init(pdev) != 0) return -EINVAL; +#ifdef CONFIG_PPC32 if (pdata->big_endian_mmio) { _fsl_readl = _fsl_readl_be; _fsl_writel = _fsl_writel_be; @@ -868,6 +869,7 @@ int usb_otg_start(struct platform_device *pdev) _fsl_readl = _fsl_readl_le; _fsl_writel = _fsl_writel_le; } +#endif /* request irq */ p_otg->irq = platform_get_irq(pdev, 0); @@ -958,7 +960,7 @@ int usb_otg_start(struct platform_device *pdev) /* * state file in sysfs */ -static int show_fsl_usb2_otg_state(struct device *dev, +static ssize_t show_fsl_usb2_otg_state(struct device *dev, struct device_attribute *attr, char *buf) { struct otg_fsm *fsm = &fsl_otg_dev->fsm; diff --git a/drivers/usb/typec/tcpm.c b/drivers/usb/typec/tcpm.c index 150f43668bec..d1d20252bad8 100644 --- a/drivers/usb/typec/tcpm.c +++ b/drivers/usb/typec/tcpm.c @@ -2140,7 +2140,7 @@ static unsigned int tcpm_pd_select_pps_apdo(struct tcpm_port *port) * PPS APDO. Again skip the first sink PDO as this will * always be 5V 3A. */ - for (j = i; j < port->nr_snk_pdo; j++) { + for (j = 1; j < port->nr_snk_pdo; j++) { pdo = port->snk_pdo[j]; switch (pdo_type(pdo)) { diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 6b237e3f4983..3988c0914322 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -513,7 +513,9 @@ static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info, tell_host(vb, vb->inflate_vq); /* balloon's page migration 2nd step -- deflate "page" */ + spin_lock_irqsave(&vb_dev_info->pages_lock, flags); balloon_page_delete(page); + spin_unlock_irqrestore(&vb_dev_info->pages_lock, flags); vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE; set_page_pfns(vb, vb->pfns, page); tell_host(vb, vb->deflate_vq); diff --git a/fs/block_dev.c b/fs/block_dev.c index 0dd87aaeb39a..aba25414231a 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -221,7 +221,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, ret = bio_iov_iter_get_pages(&bio, iter); if (unlikely(ret)) - return ret; + goto out; ret = bio.bi_iter.bi_size; if (iov_iter_rw(iter) == READ) { @@ -250,12 +250,13 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, put_page(bvec->bv_page); } - if (vecs != inline_vecs) - kfree(vecs); - if (unlikely(bio.bi_status)) ret = blk_status_to_errno(bio.bi_status); +out: + if (vecs != inline_vecs) + kfree(vecs); + bio_uninit(&bio); return ret; diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c index d9f001078e08..4a717d400807 100644 --- a/fs/cachefiles/bind.c +++ b/fs/cachefiles/bind.c @@ -218,7 +218,8 @@ static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache) "%s", fsdef->dentry->d_sb->s_id); - fscache_object_init(&fsdef->fscache, NULL, &cache->cache); + fscache_object_init(&fsdef->fscache, &fscache_fsdef_index, + &cache->cache); ret = fscache_add_cache(&cache->cache, &fsdef->fscache, cache->tag); if (ret < 0) diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index ab0bbe93b398..af2b17b21b94 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -186,12 +186,12 @@ try_again: * need to wait for it to be destroyed */ wait_for_old_object: trace_cachefiles_wait_active(object, dentry, xobject); + clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags); if (fscache_object_is_live(&xobject->fscache)) { pr_err("\n"); pr_err("Error: Unexpected object collision\n"); cachefiles_printk_object(object, xobject); - BUG(); } atomic_inc(&xobject->usage); write_unlock(&cache->active_lock); @@ -248,7 +248,6 @@ wait_for_old_object: goto try_again; requeue: - clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags); cache->cache.ops->put_object(&xobject->fscache, cachefiles_obj_put_wait_timeo); _leave(" = -ETIMEDOUT"); return -ETIMEDOUT; diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 5082c8a49686..40f7595aad10 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -27,6 +27,7 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode, struct cachefiles_one_read *monitor = container_of(wait, struct cachefiles_one_read, monitor); struct cachefiles_object *object; + struct fscache_retrieval *op = monitor->op; struct wait_bit_key *key = _key; struct page *page = wait->private; @@ -51,16 +52,22 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode, list_del(&wait->entry); /* move onto the action list and queue for FS-Cache thread pool */ - ASSERT(monitor->op); + ASSERT(op); - object = container_of(monitor->op->op.object, - struct cachefiles_object, fscache); + /* We need to temporarily bump the usage count as we don't own a ref + * here otherwise cachefiles_read_copier() may free the op between the + * monitor being enqueued on the op->to_do list and the op getting + * enqueued on the work queue. + */ + fscache_get_retrieval(op); + object = container_of(op->op.object, struct cachefiles_object, fscache); spin_lock(&object->work_lock); - list_add_tail(&monitor->op_link, &monitor->op->to_do); + list_add_tail(&monitor->op_link, &op->to_do); spin_unlock(&object->work_lock); - fscache_enqueue_retrieval(monitor->op); + fscache_enqueue_retrieval(op); + fscache_put_retrieval(op); return 0; } diff --git a/fs/exec.c b/fs/exec.c index 72e961a62adb..bdd0eacefdf5 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -293,6 +293,7 @@ static int __bprm_mm_init(struct linux_binprm *bprm) bprm->vma = vma = vm_area_alloc(mm); if (!vma) return -ENOMEM; + vma_set_anonymous(vma); if (down_write_killable(&mm->mmap_sem)) { err = -EINTR; diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index e68cefe08261..aa52d87985aa 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -368,6 +368,8 @@ static int ext4_validate_block_bitmap(struct super_block *sb, return -EFSCORRUPTED; ext4_lock_group(sb, block_group); + if (buffer_verified(bh)) + goto verified; if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group, desc, bh))) { ext4_unlock_group(sb, block_group); @@ -386,6 +388,7 @@ static int ext4_validate_block_bitmap(struct super_block *sb, return -EFSCORRUPTED; } set_buffer_verified(bh); +verified: ext4_unlock_group(sb, block_group); return 0; } diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index fb83750c1a14..f336cbc6e932 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -90,6 +90,8 @@ static int ext4_validate_inode_bitmap(struct super_block *sb, return -EFSCORRUPTED; ext4_lock_group(sb, block_group); + if (buffer_verified(bh)) + goto verified; blk = ext4_inode_bitmap(sb, desc); if (!ext4_inode_bitmap_csum_verify(sb, block_group, desc, bh, EXT4_INODES_PER_GROUP(sb) / 8)) { @@ -101,6 +103,7 @@ static int ext4_validate_inode_bitmap(struct super_block *sb, return -EFSBADCRC; } set_buffer_verified(bh); +verified: ext4_unlock_group(sb, block_group); return 0; } @@ -1385,7 +1388,10 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, ext4_itable_unused_count(sb, gdp)), sbi->s_inodes_per_block); - if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group)) { + if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group) || + ((group == 0) && ((EXT4_INODES_PER_GROUP(sb) - + ext4_itable_unused_count(sb, gdp)) < + EXT4_FIRST_INO(sb)))) { ext4_error(sb, "Something is wrong with group %u: " "used itable blocks: %d; " "itable unused count: %u", diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index e55a8bc870bd..3543fe80a3c4 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -682,6 +682,10 @@ int ext4_try_to_write_inline_data(struct address_space *mapping, goto convert; } + ret = ext4_journal_get_write_access(handle, iloc.bh); + if (ret) + goto out; + flags |= AOP_FLAG_NOFS; page = grab_cache_page_write_begin(mapping, 0, flags); @@ -710,7 +714,7 @@ int ext4_try_to_write_inline_data(struct address_space *mapping, out_up_read: up_read(&EXT4_I(inode)->xattr_sem); out: - if (handle) + if (handle && (ret != 1)) ext4_journal_stop(handle); brelse(iloc.bh); return ret; @@ -752,6 +756,7 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, ext4_write_unlock_xattr(inode, &no_expand); brelse(iloc.bh); + mark_inode_dirty(inode); out: return copied; } @@ -898,7 +903,6 @@ retry_journal: goto out; } - page = grab_cache_page_write_begin(mapping, 0, flags); if (!page) { ret = -ENOMEM; @@ -916,6 +920,9 @@ retry_journal: if (ret < 0) goto out_release_page; } + ret = ext4_journal_get_write_access(handle, iloc.bh); + if (ret) + goto out_release_page; up_read(&EXT4_I(inode)->xattr_sem); *pagep = page; @@ -936,7 +943,6 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len, unsigned copied, struct page *page) { - int i_size_changed = 0; int ret; ret = ext4_write_inline_data_end(inode, pos, len, copied, page); @@ -954,10 +960,8 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, * But it's important to update i_size while still holding page lock: * page writeout could otherwise come in and zero beyond i_size. */ - if (pos+copied > inode->i_size) { + if (pos+copied > inode->i_size) i_size_write(inode, pos+copied); - i_size_changed = 1; - } unlock_page(page); put_page(page); @@ -967,8 +971,7 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos, * ordering of page lock and transaction start for journaling * filesystems. */ - if (i_size_changed) - mark_inode_dirty(inode); + mark_inode_dirty(inode); return copied; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 7d6c10017bdf..4efe77286ecd 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1389,9 +1389,10 @@ static int ext4_write_end(struct file *file, loff_t old_size = inode->i_size; int ret = 0, ret2; int i_size_changed = 0; + int inline_data = ext4_has_inline_data(inode); trace_ext4_write_end(inode, pos, len, copied); - if (ext4_has_inline_data(inode)) { + if (inline_data) { ret = ext4_write_inline_data_end(inode, pos, len, copied, page); if (ret < 0) { @@ -1419,7 +1420,7 @@ static int ext4_write_end(struct file *file, * ordering of page lock and transaction start for journaling * filesystems. */ - if (i_size_changed) + if (i_size_changed || inline_data) ext4_mark_inode_dirty(handle, inode); if (pos + len > inode->i_size && ext4_can_truncate(inode)) @@ -1493,6 +1494,7 @@ static int ext4_journalled_write_end(struct file *file, int partial = 0; unsigned from, to; int size_changed = 0; + int inline_data = ext4_has_inline_data(inode); trace_ext4_journalled_write_end(inode, pos, len, copied); from = pos & (PAGE_SIZE - 1); @@ -1500,7 +1502,7 @@ static int ext4_journalled_write_end(struct file *file, BUG_ON(!ext4_handle_valid(handle)); - if (ext4_has_inline_data(inode)) { + if (inline_data) { ret = ext4_write_inline_data_end(inode, pos, len, copied, page); if (ret < 0) { @@ -1531,7 +1533,7 @@ static int ext4_journalled_write_end(struct file *file, if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); - if (size_changed) { + if (size_changed || inline_data) { ret2 = ext4_mark_inode_dirty(handle, inode); if (!ret) ret = ret2; @@ -2028,11 +2030,7 @@ static int __ext4_journalled_writepage(struct page *page, } if (inline_data) { - BUFFER_TRACE(inode_bh, "get write access"); - ret = ext4_journal_get_write_access(handle, inode_bh); - - err = ext4_handle_dirty_metadata(handle, inode, inode_bh); - + ret = ext4_mark_inode_dirty(handle, inode); } else { ret = ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL, do_journal_get_write_access); diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 27b9a76a0dfa..638ad4743477 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -186,11 +186,8 @@ static int kmmpd(void *data) goto exit_thread; } - if (sb_rdonly(sb)) { - ext4_warning(sb, "kmmpd being stopped since filesystem " - "has been remounted as readonly."); - goto exit_thread; - } + if (sb_rdonly(sb)) + break; diff = jiffies - last_update_time; if (diff < mmp_update_interval * HZ) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ba2396a7bd04..b7f7922061be 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2342,7 +2342,7 @@ static int ext4_check_descriptors(struct super_block *sb, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block); ext4_fsblk_t last_block; - ext4_fsblk_t last_bg_block = sb_block + ext4_bg_num_gdb(sb, 0) + 1; + ext4_fsblk_t last_bg_block = sb_block + ext4_bg_num_gdb(sb, 0); ext4_fsblk_t block_bitmap; ext4_fsblk_t inode_bitmap; ext4_fsblk_t inode_table; @@ -3141,14 +3141,8 @@ static ext4_group_t ext4_has_uninit_itable(struct super_block *sb) if (!gdp) continue; - if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED)) - continue; - if (group != 0) + if (!(gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_ZEROED))) break; - ext4_error(sb, "Inode table for bg 0 marked as " - "needing zeroing"); - if (sb_rdonly(sb)) - return ngroups; } return group; @@ -4085,14 +4079,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount2; } } + sbi->s_gdb_count = db_count; if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) { ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); ret = -EFSCORRUPTED; goto failed_mount2; } - sbi->s_gdb_count = db_count; - timer_setup(&sbi->s_err_report, print_daily_error_info, 0); /* Register extent status tree shrinker */ @@ -5213,6 +5206,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (sbi->s_journal) ext4_mark_recovery_complete(sb, es); + if (sbi->s_mmp_tsk) + kthread_stop(sbi->s_mmp_tsk); } else { /* Make sure we can mount this feature set readwrite */ if (ext4_has_feature_readonly(sb) || diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index c184c5a356ff..cdcb376ef8df 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -220,6 +220,7 @@ int fscache_add_cache(struct fscache_cache *cache, { struct fscache_cache_tag *tag; + ASSERTCMP(ifsdef->cookie, ==, &fscache_fsdef_index); BUG_ON(!cache->ops); BUG_ON(!ifsdef); @@ -248,7 +249,6 @@ int fscache_add_cache(struct fscache_cache *cache, if (!cache->kobj) goto error; - ifsdef->cookie = &fscache_fsdef_index; ifsdef->cache = cache; cache->fsdef = ifsdef; diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 97137d7ec5ee..83bfe04456b6 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -516,6 +516,7 @@ static int fscache_alloc_object(struct fscache_cache *cache, goto error; } + ASSERTCMP(object->cookie, ==, cookie); fscache_stat(&fscache_n_object_alloc); object->debug_id = atomic_inc_return(&fscache_object_debug_id); @@ -571,6 +572,8 @@ static int fscache_attach_object(struct fscache_cookie *cookie, _enter("{%s},{OBJ%x}", cookie->def->name, object->debug_id); + ASSERTCMP(object->cookie, ==, cookie); + spin_lock(&cookie->lock); /* there may be multiple initial creations of this object, but we only @@ -610,9 +613,7 @@ static int fscache_attach_object(struct fscache_cookie *cookie, spin_unlock(&cache->object_list_lock); } - /* attach to the cookie */ - object->cookie = cookie; - fscache_cookie_get(cookie, fscache_cookie_get_attach_object); + /* Attach to the cookie. The object already has a ref on it. */ hlist_add_head(&object->cookie_link, &cookie->backing_objects); fscache_objlist_add(object); diff --git a/fs/fscache/object.c b/fs/fscache/object.c index 20e0d0a4dc8c..9edc920f651f 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -327,6 +327,7 @@ void fscache_object_init(struct fscache_object *object, object->store_limit_l = 0; object->cache = cache; object->cookie = cookie; + fscache_cookie_get(cookie, fscache_cookie_get_attach_object); object->parent = NULL; #ifdef CONFIG_FSCACHE_OBJECT_LIST RB_CLEAR_NODE(&object->objlist_link); diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c index e30c5975ea58..8d265790374c 100644 --- a/fs/fscache/operation.c +++ b/fs/fscache/operation.c @@ -70,7 +70,8 @@ void fscache_enqueue_operation(struct fscache_operation *op) ASSERT(op->processor != NULL); ASSERT(fscache_object_is_available(op->object)); ASSERTCMP(atomic_read(&op->usage), >, 0); - ASSERTCMP(op->state, ==, FSCACHE_OP_ST_IN_PROGRESS); + ASSERTIFCMP(op->state != FSCACHE_OP_ST_IN_PROGRESS, + op->state, ==, FSCACHE_OP_ST_CANCELLED); fscache_stat(&fscache_n_op_enqueue); switch (op->flags & FSCACHE_OP_TYPE) { @@ -499,7 +500,8 @@ void fscache_put_operation(struct fscache_operation *op) struct fscache_cache *cache; _enter("{OBJ%x OP%x,%d}", - op->object->debug_id, op->debug_id, atomic_read(&op->usage)); + op->object ? op->object->debug_id : 0, + op->debug_id, atomic_read(&op->usage)); ASSERTCMP(atomic_read(&op->usage), >, 0); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index d508c7844681..40d4c66c7751 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -411,6 +411,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, bool truncate_op = (lend == LLONG_MAX); memset(&pseudo_vma, 0, sizeof(struct vm_area_struct)); + vma_init(&pseudo_vma, current->mm); pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED); pagevec_init(&pvec); next = start; @@ -595,6 +596,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, * as input to create an allocation policy. */ memset(&pseudo_vma, 0, sizeof(struct vm_area_struct)); + vma_init(&pseudo_vma, mm); pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED); pseudo_vma.vm_file = file; diff --git a/fs/iomap.c b/fs/iomap.c index 77397b5a96ef..0d0bd8845586 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -1443,7 +1443,7 @@ iomap_bmap(struct address_space *mapping, sector_t bno, const struct iomap_ops *ops) { struct inode *inode = mapping->host; - loff_t pos = bno >> inode->i_blkbits; + loff_t pos = bno << inode->i_blkbits; unsigned blocksize = i_blocksize(inode); if (filemap_write_and_wait(mapping)) diff --git a/fs/jfs/jfs_dinode.h b/fs/jfs/jfs_dinode.h index 395c4c0d0f06..1682a87c00b2 100644 --- a/fs/jfs/jfs_dinode.h +++ b/fs/jfs/jfs_dinode.h @@ -115,6 +115,13 @@ struct dinode { dxd_t _dxd; /* 16: */ union { __le32 _rdev; /* 4: */ + /* + * The fast symlink area + * is expected to overflow + * into _inlineea when + * needed (which will clear + * INLINEEA). + */ u8 _fastsymlink[128]; } _u; u8 _inlineea[128]; diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h index 1f26d1910409..9940a1e04cbf 100644 --- a/fs/jfs/jfs_incore.h +++ b/fs/jfs/jfs_incore.h @@ -87,6 +87,7 @@ struct jfs_inode_info { struct { unchar _unused[16]; /* 16: */ dxd_t _dxd; /* 16: */ + /* _inline may overflow into _inline_ea when needed */ unchar _inline[128]; /* 128: inline symlink */ /* _inline_ea may overlay the last part of * file._xtroot if maxentry = XTROOTINITSLOT diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 1b9264fd54b6..f08571433aba 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -967,8 +967,7 @@ static int __init init_jfs_fs(void) jfs_inode_cachep = kmem_cache_create_usercopy("jfs_ip", sizeof(struct jfs_inode_info), 0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|SLAB_ACCOUNT, - offsetof(struct jfs_inode_info, i_inline), - sizeof_field(struct jfs_inode_info, i_inline), + offsetof(struct jfs_inode_info, i_inline), IDATASIZE, init_once); if (jfs_inode_cachep == NULL) return -ENOMEM; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 6dd146885da9..f6c4ccd693f4 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -6466,34 +6466,34 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) if (data->arg.new_lock && !data->cancelled) { data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS); if (locks_lock_inode_wait(lsp->ls_state->inode, &data->fl) < 0) - break; + goto out_restart; } - if (data->arg.new_lock_owner != 0) { nfs_confirm_seqid(&lsp->ls_seqid, 0); nfs4_stateid_copy(&lsp->ls_stateid, &data->res.stateid); set_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags); - goto out_done; - } else if (nfs4_update_lock_stateid(lsp, &data->res.stateid)) - goto out_done; - + } else if (!nfs4_update_lock_stateid(lsp, &data->res.stateid)) + goto out_restart; break; case -NFS4ERR_BAD_STATEID: case -NFS4ERR_OLD_STATEID: case -NFS4ERR_STALE_STATEID: case -NFS4ERR_EXPIRED: if (data->arg.new_lock_owner != 0) { - if (nfs4_stateid_match(&data->arg.open_stateid, + if (!nfs4_stateid_match(&data->arg.open_stateid, &lsp->ls_state->open_stateid)) - goto out_done; - } else if (nfs4_stateid_match(&data->arg.lock_stateid, + goto out_restart; + } else if (!nfs4_stateid_match(&data->arg.lock_stateid, &lsp->ls_stateid)) - goto out_done; + goto out_restart; } - if (!data->cancelled) - rpc_restart_call_prepare(task); out_done: dprintk("%s: done, ret = %d!\n", __func__, data->rpc_status); + return; +out_restart: + if (!data->cancelled) + rpc_restart_call_prepare(task); + goto out_done; } static void nfs4_lock_release(void *calldata) @@ -6502,7 +6502,7 @@ static void nfs4_lock_release(void *calldata) dprintk("%s: begin!\n", __func__); nfs_free_seqid(data->arg.open_seqid); - if (data->cancelled) { + if (data->cancelled && data->rpc_status == 0) { struct rpc_task *task; task = nfs4_do_unlck(&data->fl, data->ctx, data->lsp, data->arg.lock_seqid); diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index 2751476e6b6e..f098b9f1c396 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -167,6 +167,8 @@ int squashfs_read_data(struct super_block *sb, u64 index, int length, } if (compressed) { + if (!msblk->stream) + goto read_failure; length = squashfs_decompress(msblk, bh, b, offset, length, output); if (length < 0) diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c index 23813c078cc9..0839efa720b3 100644 --- a/fs/squashfs/cache.c +++ b/fs/squashfs/cache.c @@ -350,6 +350,9 @@ int squashfs_read_metadata(struct super_block *sb, void *buffer, TRACE("Entered squashfs_read_metadata [%llx:%x]\n", *block, *offset); + if (unlikely(length < 0)) + return -EIO; + while (length) { entry = squashfs_cache_get(sb, msblk->block_cache, *block, 0); if (entry->error) { diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c index 13d80947bf9e..f1c1430ae721 100644 --- a/fs/squashfs/file.c +++ b/fs/squashfs/file.c @@ -194,7 +194,11 @@ static long long read_indexes(struct super_block *sb, int n, } for (i = 0; i < blocks; i++) { - int size = le32_to_cpu(blist[i]); + int size = squashfs_block_size(blist[i]); + if (size < 0) { + err = size; + goto failure; + } block += SQUASHFS_COMPRESSED_SIZE_BLOCK(size); } n -= blocks; @@ -367,7 +371,24 @@ static int read_blocklist(struct inode *inode, int index, u64 *block) sizeof(size)); if (res < 0) return res; - return le32_to_cpu(size); + return squashfs_block_size(size); +} + +void squashfs_fill_page(struct page *page, struct squashfs_cache_entry *buffer, int offset, int avail) +{ + int copied; + void *pageaddr; + + pageaddr = kmap_atomic(page); + copied = squashfs_copy_data(pageaddr, buffer, offset, avail); + memset(pageaddr + copied, 0, PAGE_SIZE - copied); + kunmap_atomic(pageaddr); + + flush_dcache_page(page); + if (copied == avail) + SetPageUptodate(page); + else + SetPageError(page); } /* Copy data into page cache */ @@ -376,7 +397,6 @@ void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer, { struct inode *inode = page->mapping->host; struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; - void *pageaddr; int i, mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1; int start_index = page->index & ~mask, end_index = start_index | mask; @@ -402,12 +422,7 @@ void squashfs_copy_cache(struct page *page, struct squashfs_cache_entry *buffer, if (PageUptodate(push_page)) goto skip_page; - pageaddr = kmap_atomic(push_page); - squashfs_copy_data(pageaddr, buffer, offset, avail); - memset(pageaddr + avail, 0, PAGE_SIZE - avail); - kunmap_atomic(pageaddr); - flush_dcache_page(push_page); - SetPageUptodate(push_page); + squashfs_fill_page(push_page, buffer, offset, avail); skip_page: unlock_page(push_page); if (i != page->index) @@ -416,10 +431,9 @@ skip_page: } /* Read datablock stored packed inside a fragment (tail-end packed block) */ -static int squashfs_readpage_fragment(struct page *page) +static int squashfs_readpage_fragment(struct page *page, int expected) { struct inode *inode = page->mapping->host; - struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; struct squashfs_cache_entry *buffer = squashfs_get_fragment(inode->i_sb, squashfs_i(inode)->fragment_block, squashfs_i(inode)->fragment_size); @@ -430,23 +444,16 @@ static int squashfs_readpage_fragment(struct page *page) squashfs_i(inode)->fragment_block, squashfs_i(inode)->fragment_size); else - squashfs_copy_cache(page, buffer, i_size_read(inode) & - (msblk->block_size - 1), + squashfs_copy_cache(page, buffer, expected, squashfs_i(inode)->fragment_offset); squashfs_cache_put(buffer); return res; } -static int squashfs_readpage_sparse(struct page *page, int index, int file_end) +static int squashfs_readpage_sparse(struct page *page, int expected) { - struct inode *inode = page->mapping->host; - struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; - int bytes = index == file_end ? - (i_size_read(inode) & (msblk->block_size - 1)) : - msblk->block_size; - - squashfs_copy_cache(page, NULL, bytes, 0); + squashfs_copy_cache(page, NULL, expected, 0); return 0; } @@ -456,6 +463,9 @@ static int squashfs_readpage(struct file *file, struct page *page) struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info; int index = page->index >> (msblk->block_log - PAGE_SHIFT); int file_end = i_size_read(inode) >> msblk->block_log; + int expected = index == file_end ? + (i_size_read(inode) & (msblk->block_size - 1)) : + msblk->block_size; int res; void *pageaddr; @@ -474,11 +484,11 @@ static int squashfs_readpage(struct file *file, struct page *page) goto error_out; if (bsize == 0) - res = squashfs_readpage_sparse(page, index, file_end); + res = squashfs_readpage_sparse(page, expected); else - res = squashfs_readpage_block(page, block, bsize); + res = squashfs_readpage_block(page, block, bsize, expected); } else - res = squashfs_readpage_fragment(page); + res = squashfs_readpage_fragment(page, expected); if (!res) return 0; diff --git a/fs/squashfs/file_cache.c b/fs/squashfs/file_cache.c index f2310d2a2019..a9ba8d96776a 100644 --- a/fs/squashfs/file_cache.c +++ b/fs/squashfs/file_cache.c @@ -20,7 +20,7 @@ #include "squashfs.h" /* Read separately compressed datablock and memcopy into page cache */ -int squashfs_readpage_block(struct page *page, u64 block, int bsize) +int squashfs_readpage_block(struct page *page, u64 block, int bsize, int expected) { struct inode *i = page->mapping->host; struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb, @@ -31,7 +31,7 @@ int squashfs_readpage_block(struct page *page, u64 block, int bsize) ERROR("Unable to read page, block %llx, size %x\n", block, bsize); else - squashfs_copy_cache(page, buffer, buffer->length, 0); + squashfs_copy_cache(page, buffer, expected, 0); squashfs_cache_put(buffer); return res; diff --git a/fs/squashfs/file_direct.c b/fs/squashfs/file_direct.c index cb485d8e0e91..80db1b86a27c 100644 --- a/fs/squashfs/file_direct.c +++ b/fs/squashfs/file_direct.c @@ -21,10 +21,11 @@ #include "page_actor.h" static int squashfs_read_cache(struct page *target_page, u64 block, int bsize, - int pages, struct page **page); + int pages, struct page **page, int bytes); /* Read separately compressed datablock directly into page cache */ -int squashfs_readpage_block(struct page *target_page, u64 block, int bsize) +int squashfs_readpage_block(struct page *target_page, u64 block, int bsize, + int expected) { struct inode *inode = target_page->mapping->host; @@ -83,7 +84,7 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize) * using an intermediate buffer. */ res = squashfs_read_cache(target_page, block, bsize, pages, - page); + page, expected); if (res < 0) goto mark_errored; @@ -95,6 +96,11 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize) if (res < 0) goto mark_errored; + if (res != expected) { + res = -EIO; + goto mark_errored; + } + /* Last page may have trailing bytes not filled */ bytes = res % PAGE_SIZE; if (bytes) { @@ -138,13 +144,12 @@ out: static int squashfs_read_cache(struct page *target_page, u64 block, int bsize, - int pages, struct page **page) + int pages, struct page **page, int bytes) { struct inode *i = target_page->mapping->host; struct squashfs_cache_entry *buffer = squashfs_get_datablock(i->i_sb, block, bsize); - int bytes = buffer->length, res = buffer->error, n, offset = 0; - void *pageaddr; + int res = buffer->error, n, offset = 0; if (res) { ERROR("Unable to read page, block %llx, size %x\n", block, @@ -159,12 +164,7 @@ static int squashfs_read_cache(struct page *target_page, u64 block, int bsize, if (page[n] == NULL) continue; - pageaddr = kmap_atomic(page[n]); - squashfs_copy_data(pageaddr, buffer, offset, avail); - memset(pageaddr + avail, 0, PAGE_SIZE - avail); - kunmap_atomic(pageaddr); - flush_dcache_page(page[n]); - SetPageUptodate(page[n]); + squashfs_fill_page(page[n], buffer, offset, avail); unlock_page(page[n]); if (page[n] != target_page) put_page(page[n]); diff --git a/fs/squashfs/fragment.c b/fs/squashfs/fragment.c index 0ed6edbc5c71..0681feab4a84 100644 --- a/fs/squashfs/fragment.c +++ b/fs/squashfs/fragment.c @@ -49,11 +49,16 @@ int squashfs_frag_lookup(struct super_block *sb, unsigned int fragment, u64 *fragment_block) { struct squashfs_sb_info *msblk = sb->s_fs_info; - int block = SQUASHFS_FRAGMENT_INDEX(fragment); - int offset = SQUASHFS_FRAGMENT_INDEX_OFFSET(fragment); - u64 start_block = le64_to_cpu(msblk->fragment_index[block]); + int block, offset, size; struct squashfs_fragment_entry fragment_entry; - int size; + u64 start_block; + + if (fragment >= msblk->fragments) + return -EIO; + block = SQUASHFS_FRAGMENT_INDEX(fragment); + offset = SQUASHFS_FRAGMENT_INDEX_OFFSET(fragment); + + start_block = le64_to_cpu(msblk->fragment_index[block]); size = squashfs_read_metadata(sb, &fragment_entry, &start_block, &offset, sizeof(fragment_entry)); @@ -61,9 +66,7 @@ int squashfs_frag_lookup(struct super_block *sb, unsigned int fragment, return size; *fragment_block = le64_to_cpu(fragment_entry.start_block); - size = le32_to_cpu(fragment_entry.size); - - return size; + return squashfs_block_size(fragment_entry.size); } diff --git a/fs/squashfs/squashfs.h b/fs/squashfs/squashfs.h index 887d6d270080..f89f8a74c6ce 100644 --- a/fs/squashfs/squashfs.h +++ b/fs/squashfs/squashfs.h @@ -67,11 +67,12 @@ extern __le64 *squashfs_read_fragment_index_table(struct super_block *, u64, u64, unsigned int); /* file.c */ +void squashfs_fill_page(struct page *, struct squashfs_cache_entry *, int, int); void squashfs_copy_cache(struct page *, struct squashfs_cache_entry *, int, int); /* file_xxx.c */ -extern int squashfs_readpage_block(struct page *, u64, int); +extern int squashfs_readpage_block(struct page *, u64, int, int); /* id.c */ extern int squashfs_get_id(struct super_block *, unsigned int, unsigned int *); diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h index 24d12fd14177..4e6853f084d0 100644 --- a/fs/squashfs/squashfs_fs.h +++ b/fs/squashfs/squashfs_fs.h @@ -129,6 +129,12 @@ #define SQUASHFS_COMPRESSED_BLOCK(B) (!((B) & SQUASHFS_COMPRESSED_BIT_BLOCK)) +static inline int squashfs_block_size(__le32 raw) +{ + u32 size = le32_to_cpu(raw); + return (size >> 25) ? -EIO : size; +} + /* * Inode number ops. Inodes consist of a compressed block number, and an * uncompressed offset within that block diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h index 1da565cb50c3..ef69c31947bf 100644 --- a/fs/squashfs/squashfs_fs_sb.h +++ b/fs/squashfs/squashfs_fs_sb.h @@ -75,6 +75,7 @@ struct squashfs_sb_info { unsigned short block_log; long long bytes_used; unsigned int inodes; + unsigned int fragments; int xattr_ids; }; #endif diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 8a73b97217c8..40e657386fa5 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -175,6 +175,7 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) msblk->inode_table = le64_to_cpu(sblk->inode_table_start); msblk->directory_table = le64_to_cpu(sblk->directory_table_start); msblk->inodes = le32_to_cpu(sblk->inodes); + msblk->fragments = le32_to_cpu(sblk->fragments); flags = le16_to_cpu(sblk->flags); TRACE("Found valid superblock on %pg\n", sb->s_bdev); @@ -185,7 +186,7 @@ static int squashfs_fill_super(struct super_block *sb, void *data, int silent) TRACE("Filesystem size %lld bytes\n", msblk->bytes_used); TRACE("Block size %d\n", msblk->block_size); TRACE("Number of inodes %d\n", msblk->inodes); - TRACE("Number of fragments %d\n", le32_to_cpu(sblk->fragments)); + TRACE("Number of fragments %d\n", msblk->fragments); TRACE("Number of ids %d\n", le16_to_cpu(sblk->no_ids)); TRACE("sblk->inode_table_start %llx\n", msblk->inode_table); TRACE("sblk->directory_table_start %llx\n", msblk->directory_table); @@ -272,7 +273,7 @@ allocate_id_index_table: sb->s_export_op = &squashfs_export_ops; handle_fragments: - fragments = le32_to_cpu(sblk->fragments); + fragments = msblk->fragments; if (fragments == 0) goto check_directory_table; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 594d192b2331..bad9cea37f12 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -633,8 +633,10 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, /* the various vma->vm_userfaultfd_ctx still points to it */ down_write(&mm->mmap_sem); for (vma = mm->mmap; vma; vma = vma->vm_next) - if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) + if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; + vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING); + } up_write(&mm->mmap_sem); userfaultfd_ctx_put(release_new_ctx); diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index eef466260d43..75dbdc14c45f 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -223,12 +223,13 @@ xfs_alloc_get_rec( error = xfs_btree_get_rec(cur, &rec, stat); if (error || !(*stat)) return error; - if (rec->alloc.ar_blockcount == 0) - goto out_bad_rec; *bno = be32_to_cpu(rec->alloc.ar_startblock); *len = be32_to_cpu(rec->alloc.ar_blockcount); + if (*len == 0) + goto out_bad_rec; + /* check for valid extent range, including overflow */ if (!xfs_verify_agbno(mp, agno, *bno)) goto out_bad_rec; diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 33dc34655ac3..30d1d60f1d46 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -731,7 +731,8 @@ xfs_inode_validate_extsize( if ((hint_flag || inherit_flag) && extsize == 0) return __this_address; - if (!(hint_flag || inherit_flag) && extsize != 0) + /* free inodes get flags set to zero but extsize remains */ + if (mode && !(hint_flag || inherit_flag) && extsize != 0) return __this_address; if (extsize_bytes % blocksize_bytes) @@ -777,7 +778,8 @@ xfs_inode_validate_cowextsize( if (hint_flag && cowextsize == 0) return __this_address; - if (!hint_flag && cowextsize != 0) + /* free inodes get flags set to zero but cowextsize remains */ + if (mode && !hint_flag && cowextsize != 0) return __this_address; if (hint_flag && rt_flag) diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index e3147eb74222..ca3f2c2edd85 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -287,6 +287,20 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); void blk_mq_quiesce_queue_nowait(struct request_queue *q); +/** + * blk_mq_mark_complete() - Set request state to complete + * @rq: request to set to complete state + * + * Returns true if request state was successfully set to complete. If + * successful, the caller is responsibile for seeing this request is ended, as + * blk_mq_complete_request will not work again. + */ +static inline bool blk_mq_mark_complete(struct request *rq) +{ + return cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) == + MQ_RQ_IN_FLIGHT; +} + /* * Driver command data is immediately after the request. So subtract request * size to get back to the original request, add request size to get the PDU. diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h index 687b1760bb9f..f02cee0225d4 100644 --- a/include/linux/bpfilter.h +++ b/include/linux/bpfilter.h @@ -5,10 +5,10 @@ #include <uapi/linux/bpfilter.h> struct sock; -int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char *optval, +int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen); -int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char *optval, - int *optlen); +int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval, + int __user *optlen); extern int (*bpfilter_process_sockopt)(struct sock *sk, int optname, char __user *optval, unsigned int optlen, bool is_set); diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index e6c0448ebcc7..31c865d1842e 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -124,7 +124,7 @@ static inline void delayacct_blkio_start(void) static inline void delayacct_blkio_end(struct task_struct *p) { - if (current->delays) + if (p->delays) __delayacct_blkio_end(p); delayacct_clear_flag(DELAYACCT_PF_BLKIO); } diff --git a/include/linux/dmar.h b/include/linux/dmar.h index e2433bc50210..843a41ba7e28 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -265,11 +265,6 @@ static inline void dmar_copy_shared_irte(struct irte *dst, struct irte *src) #define PDA_LOW_BIT 26 #define PDA_HIGH_BIT 32 -enum { - IRQ_REMAP_XAPIC_MODE, - IRQ_REMAP_X2APIC_MODE, -}; - /* Can't use the common MSI interrupt functions * since DMAR is not a pci device */ diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index 7094718b653b..ffcc7724ca21 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -11,6 +11,7 @@ #include <linux/fcntl.h> #include <linux/wait.h> +#include <linux/err.h> /* * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index ef169d67df92..28004d74ae04 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -31,6 +31,7 @@ #include <linux/list.h> #include <linux/iommu.h> #include <linux/io-64-nonatomic-lo-hi.h> +#include <linux/dmar.h> #include <asm/cacheflush.h> #include <asm/iommu.h> @@ -114,6 +115,7 @@ * Extended Capability Register */ +#define ecap_dit(e) ((e >> 41) & 0x1) #define ecap_pasid(e) ((e >> 40) & 0x1) #define ecap_pss(e) ((e >> 35) & 0x1f) #define ecap_eafs(e) ((e >> 34) & 0x1) @@ -284,6 +286,7 @@ enum { #define QI_DEV_IOTLB_SID(sid) ((u64)((sid) & 0xffff) << 32) #define QI_DEV_IOTLB_QDEP(qdep) (((qdep) & 0x1f) << 16) #define QI_DEV_IOTLB_ADDR(addr) ((u64)(addr) & VTD_PAGE_MASK) +#define QI_DEV_IOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | ((u64)(pfsid & 0xfff) << 52)) #define QI_DEV_IOTLB_SIZE 1 #define QI_DEV_IOTLB_MAX_INVS 32 @@ -308,6 +311,7 @@ enum { #define QI_DEV_EIOTLB_PASID(p) (((u64)p) << 32) #define QI_DEV_EIOTLB_SID(sid) ((u64)((sid) & 0xffff) << 16) #define QI_DEV_EIOTLB_QDEP(qd) ((u64)((qd) & 0x1f) << 4) +#define QI_DEV_EIOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | ((u64)(pfsid & 0xfff) << 52)) #define QI_DEV_EIOTLB_MAX_INVS 32 #define QI_PGRP_IDX(idx) (((u64)(idx)) << 55) @@ -385,6 +389,42 @@ struct pasid_entry; struct pasid_state_entry; struct page_req_dsc; +struct dmar_domain { + int nid; /* node id */ + + unsigned iommu_refcnt[DMAR_UNITS_SUPPORTED]; + /* Refcount of devices per iommu */ + + + u16 iommu_did[DMAR_UNITS_SUPPORTED]; + /* Domain ids per IOMMU. Use u16 since + * domain ids are 16 bit wide according + * to VT-d spec, section 9.3 */ + + bool has_iotlb_device; + struct list_head devices; /* all devices' list */ + struct iova_domain iovad; /* iova's that belong to this domain */ + + struct dma_pte *pgd; /* virtual address */ + int gaw; /* max guest address width */ + + /* adjusted guest address width, 0 is level 2 30-bit */ + int agaw; + + int flags; /* flags to find out type of domain */ + + int iommu_coherency;/* indicate coherency of iommu access */ + int iommu_snooping; /* indicate snooping control feature*/ + int iommu_count; /* reference count of iommu */ + int iommu_superpage;/* Level of superpages supported: + 0 == 4KiB (no superpages), 1 == 2MiB, + 2 == 1GiB, 3 == 512GiB, 4 == 1TiB */ + u64 max_addr; /* maximum mapped address */ + + struct iommu_domain domain; /* generic domain data structure for + iommu core */ +}; + struct intel_iommu { void __iomem *reg; /* Pointer to hardware regs, virtual addr */ u64 reg_phys; /* physical address of hw register set */ @@ -414,11 +454,9 @@ struct intel_iommu { * devices away to userspace processes (e.g. for DPDK) and don't * want to trust that userspace will use *only* the PASID it was * told to. But while it's all driver-arbitrated, we're fine. */ - struct pasid_entry *pasid_table; struct pasid_state_entry *pasid_state_table; struct page_req_dsc *prq; unsigned char prq_name[16]; /* Name for PRQ interrupt */ - struct idr pasid_idr; u32 pasid_max; #endif struct q_inval *qi; /* Queued invalidation info */ @@ -434,6 +472,27 @@ struct intel_iommu { u32 flags; /* Software defined flags */ }; +/* PCI domain-device relationship */ +struct device_domain_info { + struct list_head link; /* link to domain siblings */ + struct list_head global; /* link to global list */ + struct list_head table; /* link to pasid table */ + u8 bus; /* PCI bus number */ + u8 devfn; /* PCI devfn number */ + u16 pfsid; /* SRIOV physical function source ID */ + u8 pasid_supported:3; + u8 pasid_enabled:1; + u8 pri_supported:1; + u8 pri_enabled:1; + u8 ats_supported:1; + u8 ats_enabled:1; + u8 ats_qdep; + struct device *dev; /* it's NULL for PCIe-to-PCI bridge */ + struct intel_iommu *iommu; /* IOMMU used by this device */ + struct dmar_domain *domain; /* pointer to domain */ + struct pasid_table *pasid_table; /* pasid table */ +}; + static inline void __iommu_flush_cache( struct intel_iommu *iommu, void *addr, int size) { @@ -453,16 +512,22 @@ extern void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm, u64 type); extern void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr, unsigned int size_order, u64 type); -extern void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 qdep, - u64 addr, unsigned mask); - +extern void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid, + u16 qdep, u64 addr, unsigned mask); extern int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu); extern int dmar_ir_support(void); +struct dmar_domain *get_valid_domain_for_dev(struct device *dev); +void *alloc_pgtable_page(int node); +void free_pgtable_page(void *vaddr); +struct intel_iommu *domain_get_iommu(struct dmar_domain *domain); +int for_each_device_domain(int (*fn)(struct device_domain_info *info, + void *data), void *data); + #ifdef CONFIG_INTEL_IOMMU_SVM -extern int intel_svm_alloc_pasid_tables(struct intel_iommu *iommu); -extern int intel_svm_free_pasid_tables(struct intel_iommu *iommu); +int intel_svm_init(struct intel_iommu *iommu); +int intel_svm_exit(struct intel_iommu *iommu); extern int intel_svm_enable_prq(struct intel_iommu *iommu); extern int intel_svm_finish_prq(struct intel_iommu *iommu); @@ -486,6 +551,7 @@ struct intel_svm { int flags; int pasid; struct list_head devs; + struct list_head list; }; extern int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sdev); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 19938ee6eb31..87994c265bf5 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -166,8 +166,6 @@ struct iommu_resv_region { * @detach_dev: detach device from an iommu domain * @map: map a physically contiguous memory region to an iommu domain * @unmap: unmap a physically contiguous memory region from an iommu domain - * @map_sg: map a scatter-gather list of physically contiguous memory chunks - * to an iommu domain * @flush_tlb_all: Synchronously flush all hardware TLBs for this domain * @tlb_range_add: Add a given iova range to the flush queue for this domain * @tlb_sync: Flush all queued ranges from the hardware TLBs and empty flush @@ -201,8 +199,6 @@ struct iommu_ops { phys_addr_t paddr, size_t size, int prot); size_t (*unmap)(struct iommu_domain *domain, unsigned long iova, size_t size); - size_t (*map_sg)(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg, unsigned int nents, int prot); void (*flush_iotlb_all)(struct iommu_domain *domain); void (*iotlb_range_add)(struct iommu_domain *domain, unsigned long iova, size_t size); @@ -303,9 +299,8 @@ extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size); extern size_t iommu_unmap_fast(struct iommu_domain *domain, unsigned long iova, size_t size); -extern size_t default_iommu_map_sg(struct iommu_domain *domain, unsigned long iova, - struct scatterlist *sg,unsigned int nents, - int prot); +extern size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, + struct scatterlist *sg,unsigned int nents, int prot); extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova); extern void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token); @@ -378,13 +373,6 @@ static inline void iommu_tlb_sync(struct iommu_domain *domain) domain->ops->iotlb_sync(domain); } -static inline size_t iommu_map_sg(struct iommu_domain *domain, - unsigned long iova, struct scatterlist *sg, - unsigned int nents, int prot) -{ - return domain->ops->map_sg(domain, iova, sg, nents, prot); -} - /* PCI device grouping function */ extern struct iommu_group *pci_device_group(struct device *dev); /* Generic device grouping function */ @@ -698,4 +686,11 @@ const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode) #endif /* CONFIG_IOMMU_API */ +#ifdef CONFIG_IOMMU_DEBUGFS +extern struct dentry *iommu_debugfs_dir; +void iommu_debugfs_setup(void); +#else +static inline void iommu_debugfs_setup(void) {} +#endif + #endif /* __LINUX_IOMMU_H */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 80cbb7fdce4a..83957920653a 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -358,6 +358,7 @@ struct mlx5_frag_buf_ctrl { struct mlx5_frag_buf frag_buf; u32 sz_m1; u32 frag_sz_m1; + u32 strides_offset; u8 log_sz; u8 log_stride; u8 log_frag_strides; @@ -983,14 +984,22 @@ static inline u32 mlx5_base_mkey(const u32 key) return key & 0xffffff00u; } -static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz, - struct mlx5_frag_buf_ctrl *fbc) +static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz, + u32 strides_offset, + struct mlx5_frag_buf_ctrl *fbc) { fbc->log_stride = log_stride; fbc->log_sz = log_sz; fbc->sz_m1 = (1 << fbc->log_sz) - 1; fbc->log_frag_strides = PAGE_SHIFT - fbc->log_stride; fbc->frag_sz_m1 = (1 << fbc->log_frag_strides) - 1; + fbc->strides_offset = strides_offset; +} + +static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz, + struct mlx5_frag_buf_ctrl *fbc) +{ + mlx5_fill_fbc_offset(log_stride, log_sz, 0, fbc); } static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc, @@ -1004,7 +1013,10 @@ static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc, static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc, u32 ix) { - unsigned int frag = (ix >> fbc->log_frag_strides); + unsigned int frag; + + ix += fbc->strides_offset; + frag = ix >> fbc->log_frag_strides; return fbc->frag_buf.frags[frag].buf + ((fbc->frag_sz_m1 & ix) << fbc->log_stride); diff --git a/include/linux/mm.h b/include/linux/mm.h index d3a3842316b8..68a5121694ef 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -452,6 +452,23 @@ struct vm_operations_struct { unsigned long addr); }; +static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) +{ + static const struct vm_operations_struct dummy_vm_ops = {}; + + vma->vm_mm = mm; + vma->vm_ops = &dummy_vm_ops; + INIT_LIST_HEAD(&vma->anon_vma_chain); +} + +static inline void vma_set_anonymous(struct vm_area_struct *vma) +{ + vma->vm_ops = NULL; +} + +/* flush_tlb_range() takes a vma, not a mm, and can care about flags */ +#define TLB_FLUSH_VMA(mm,flags) { .vm_mm = (mm), .vm_flags = (flags) } + struct mmu_gather; struct inode; diff --git a/include/linux/pci.h b/include/linux/pci.h index abd5d5e17aee..c133ccfa002e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -368,7 +368,6 @@ struct pci_dev { unsigned int transparent:1; /* Subtractive decode bridge */ unsigned int multifunction:1; /* Multi-function device */ - unsigned int is_added:1; unsigned int is_busmaster:1; /* Is busmaster */ unsigned int no_msi:1; /* May not use MSI */ unsigned int no_64bit_msi:1; /* May only use 32-bit MSIs */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1fa12887ec02..87f6db437e4a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1130,6 +1130,7 @@ extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct extern struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark); +extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); diff --git a/include/linux/platform_data/sh_ipmmu.h b/include/linux/platform_data/sh_ipmmu.h deleted file mode 100644 index 39f7405cdac5..000000000000 --- a/include/linux/platform_data/sh_ipmmu.h +++ /dev/null @@ -1,18 +0,0 @@ -/* sh_ipmmu.h - * - * Copyright (C) 2012 Hideki EIRAKU - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; version 2 of the License. - */ - -#ifndef __SH_IPMMU_H__ -#define __SH_IPMMU_H__ - -struct shmobile_ipmmu_platform_data { - const char * const *dev_names; - unsigned int num_dev_names; -}; - -#endif /* __SH_IPMMU_H__ */ diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index b72ebdff0b77..003d09ab308d 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -165,6 +165,7 @@ void ring_buffer_record_enable(struct ring_buffer *buffer); void ring_buffer_record_off(struct ring_buffer *buffer); void ring_buffer_record_on(struct ring_buffer *buffer); int ring_buffer_record_is_on(struct ring_buffer *buffer); +int ring_buffer_record_is_set_on(struct ring_buffer *buffer); void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu); void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu); diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 1b92a28dd672..6fd615a0eea9 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -106,7 +106,14 @@ static inline int rt_mutex_is_locked(struct rt_mutex *lock) extern void __rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock_class_key *key); extern void rt_mutex_destroy(struct rt_mutex *lock); +#ifdef CONFIG_DEBUG_LOCK_ALLOC +extern void rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass); +#define rt_mutex_lock(lock) rt_mutex_lock_nested(lock, 0) +#else extern void rt_mutex_lock(struct rt_mutex *lock); +#define rt_mutex_lock_nested(lock, subclass) rt_mutex_lock(lock) +#endif + extern int rt_mutex_lock_interruptible(struct rt_mutex *lock); extern int rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 5fbfe61f41c6..1beb3ead0385 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5835,10 +5835,11 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, /** * cfg80211_rx_control_port - notification about a received control port frame * @dev: The device the frame matched to - * @buf: control port frame - * @len: length of the frame data - * @addr: The peer from which the frame was received - * @proto: frame protocol, typically PAE or Pre-authentication + * @skb: The skbuf with the control port frame. It is assumed that the skbuf + * is 802.3 formatted (with 802.3 header). The skb can be non-linear. + * This function does not take ownership of the skb, so the caller is + * responsible for any cleanup. The caller must also ensure that + * skb->protocol is set appropriately. * @unencrypted: Whether the frame was received unencrypted * * This function is used to inform userspace about a received control port @@ -5851,8 +5852,7 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, * Return: %true if the frame was passed to userspace */ bool cfg80211_rx_control_port(struct net_device *dev, - const u8 *buf, size_t len, - const u8 *addr, u16 proto, bool unencrypted); + struct sk_buff *skb, bool unencrypted); /** * cfg80211_cqm_rssi_notify - connection quality monitoring rssi event diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 71b9043aa0e7..3d4930528db0 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -281,6 +281,11 @@ static inline void fib6_info_hold(struct fib6_info *f6i) atomic_inc(&f6i->fib6_ref); } +static inline bool fib6_info_hold_safe(struct fib6_info *f6i) +{ + return atomic_inc_not_zero(&f6i->fib6_ref); +} + static inline void fib6_info_release(struct fib6_info *f6i) { if (f6i && atomic_dec_and_test(&f6i->fib6_ref)) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 08c005ce56e9..dc417ef0a0c5 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -150,6 +150,7 @@ static inline void nft_data_debug(const struct nft_data *data) * @portid: netlink portID of the original message * @seq: netlink sequence number * @family: protocol family + * @level: depth of the chains * @report: notify via unicast netlink message */ struct nft_ctx { @@ -160,6 +161,7 @@ struct nft_ctx { u32 portid; u32 seq; u8 family; + u8 level; bool report; }; @@ -865,7 +867,6 @@ enum nft_chain_flags { * @table: table that this chain belongs to * @handle: chain handle * @use: number of jump references to this chain - * @level: length of longest path to this chain * @flags: bitmask of enum nft_chain_flags * @name: name of the chain */ @@ -878,7 +879,6 @@ struct nft_chain { struct nft_table *table; u64 handle; u32 use; - u16 level; u8 flags:6, genmask:2; char *name; @@ -1124,7 +1124,6 @@ struct nft_flowtable { u32 genmask:2, use:30; u64 handle; - char *dev_name[NFT_FLOWTABLE_DEVICE_MAX]; /* runtime data below here */ struct nf_hook_ops *ops ____cacheline_aligned; struct nf_flowtable data; diff --git a/include/net/tcp.h b/include/net/tcp.h index 3482d13d655b..cd3ecda9386a 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -342,6 +342,7 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); +void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks); static inline void tcp_dec_quickack_mode(struct sock *sk, const unsigned int pkts) { @@ -539,6 +540,7 @@ void tcp_send_fin(struct sock *sk); void tcp_send_active_reset(struct sock *sk, gfp_t priority); int tcp_send_synack(struct sock *); void tcp_push_one(struct sock *, unsigned int mss_now); +void __tcp_send_ack(struct sock *sk, u32 rcv_nxt); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); void tcp_send_loss_probe(struct sock *sk); @@ -839,6 +841,11 @@ static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb) */ static inline int tcp_v6_iif(const struct sk_buff *skb) { + return TCP_SKB_CB(skb)->header.h6.iif; +} + +static inline int tcp_v6_iif_l3_slave(const struct sk_buff *skb) +{ bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags); return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif; diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index 0b5ddbe135a4..972265f32871 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -76,7 +76,7 @@ struct btf_type { */ #define BTF_INT_ENCODING(VAL) (((VAL) & 0x0f000000) >> 24) #define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16) -#define BTF_INT_BITS(VAL) ((VAL) & 0x0000ffff) +#define BTF_INT_BITS(VAL) ((VAL) & 0x000000ff) /* Attributes stored in the BTF_INT_ENCODING */ #define BTF_INT_SIGNED (1 << 0) diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index b8e288a1f740..eeb787b1c53c 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -143,6 +143,8 @@ enum perf_event_sample_format { PERF_SAMPLE_PHYS_ADDR = 1U << 19, PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */ + + __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, }; /* diff --git a/ipc/sem.c b/ipc/sem.c index 5af1943ad782..76e95e4f3aa2 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -2118,7 +2118,7 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, } do { - queue.status = -EINTR; + WRITE_ONCE(queue.status, -EINTR); queue.sleeper = current; __set_current_state(TASK_INTERRUPTIBLE); diff --git a/ipc/shm.c b/ipc/shm.c index 051a3e1fb8df..fefa00d310fb 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -427,6 +427,17 @@ static int shm_split(struct vm_area_struct *vma, unsigned long addr) return 0; } +static unsigned long shm_pagesize(struct vm_area_struct *vma) +{ + struct file *file = vma->vm_file; + struct shm_file_data *sfd = shm_file_data(file); + + if (sfd->vm_ops->pagesize) + return sfd->vm_ops->pagesize(vma); + + return PAGE_SIZE; +} + #ifdef CONFIG_NUMA static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *new) { @@ -554,6 +565,7 @@ static const struct vm_operations_struct shm_vm_ops = { .close = shm_close, /* callback for when the vm-area is released */ .fault = shm_fault, .split = shm_split, + .pagesize = shm_pagesize, #if defined(CONFIG_NUMA) .set_policy = shm_set_policy, .get_policy = shm_get_policy, diff --git a/kernel/auditsc.c b/kernel/auditsc.c index ceb1c4596c51..80d672a11088 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1279,8 +1279,12 @@ static void show_special(struct audit_context *context, int *call_panic) break; case AUDIT_KERN_MODULE: audit_log_format(ab, "name="); - audit_log_untrustedstring(ab, context->module.name); - kfree(context->module.name); + if (context->module.name) { + audit_log_untrustedstring(ab, context->module.name); + kfree(context->module.name); + } else + audit_log_format(ab, "(null)"); + break; } audit_log_end(ab); @@ -2411,8 +2415,9 @@ void __audit_log_kern_module(char *name) { struct audit_context *context = audit_context(); - context->module.name = kmalloc(strlen(name) + 1, GFP_KERNEL); - strcpy(context->module.name, name); + context->module.name = kstrdup(name, GFP_KERNEL); + if (!context->module.name) + audit_log_lost("out of memory in __audit_log_kern_module"); context->type = AUDIT_KERN_MODULE; } diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 544e58f5f642..2aa55d030c77 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -378,7 +378,7 @@ static int array_map_check_btf(const struct bpf_map *map, const struct btf *btf, return -EINVAL; value_type = btf_type_id_size(btf, &btf_value_id, &value_size); - if (!value_type || value_size > map->value_size) + if (!value_type || value_size != map->value_size) return -EINVAL; return 0; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index e016ac3afa24..2590700237c1 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -450,7 +450,7 @@ static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) */ static bool btf_type_int_is_regular(const struct btf_type *t) { - u16 nr_bits, nr_bytes; + u8 nr_bits, nr_bytes; u32 int_data; int_data = btf_type_int(t); @@ -993,12 +993,16 @@ static void btf_int_bits_seq_show(const struct btf *btf, { u16 left_shift_bits, right_shift_bits; u32 int_data = btf_type_int(t); - u16 nr_bits = BTF_INT_BITS(int_data); - u16 total_bits_offset; - u16 nr_copy_bytes; - u16 nr_copy_bits; + u8 nr_bits = BTF_INT_BITS(int_data); + u8 total_bits_offset; + u8 nr_copy_bytes; + u8 nr_copy_bits; u64 print_num; + /* + * bits_offset is at most 7. + * BTF_INT_OFFSET() cannot exceed 64 bits. + */ total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data); data += BITS_ROUNDDOWN_BYTES(total_bits_offset); bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset); @@ -1028,7 +1032,7 @@ static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t, u32 int_data = btf_type_int(t); u8 encoding = BTF_INT_ENCODING(int_data); bool sign = encoding & BTF_INT_SIGNED; - u32 nr_bits = BTF_INT_BITS(int_data); + u8 nr_bits = BTF_INT_BITS(int_data); if (bits_offset || BTF_INT_OFFSET(int_data) || BITS_PER_BYTE_MASKED(nr_bits)) { @@ -1515,9 +1519,9 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, { bool is_union = BTF_INFO_KIND(t->info) == BTF_KIND_UNION; const struct btf_member *member; + u32 meta_needed, last_offset; struct btf *btf = env->btf; u32 struct_size = t->size; - u32 meta_needed; u16 i; meta_needed = btf_type_vlen(t) * sizeof(*member); @@ -1530,6 +1534,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, btf_verifier_log_type(env, t, NULL); + last_offset = 0; for_each_member(i, t, member) { if (!btf_name_offset_valid(btf, member->name_off)) { btf_verifier_log_member(env, t, member, @@ -1551,6 +1556,16 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, return -EINVAL; } + /* + * ">" instead of ">=" because the last member could be + * "char a[0];" + */ + if (last_offset > member->offset) { + btf_verifier_log_member(env, t, member, + "Invalid member bits_offset"); + return -EINVAL; + } + if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) { btf_verifier_log_member(env, t, member, "Memmber bits_offset exceeds its struct size"); @@ -1558,6 +1573,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, } btf_verifier_log_member(env, t, member, NULL); + last_offset = member->offset; } return meta_needed; diff --git a/kernel/events/core.c b/kernel/events/core.c index 8f0434a9951a..eec2d5fb676b 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6343,7 +6343,7 @@ static u64 perf_virt_to_phys(u64 virt) static struct perf_callchain_entry __empty_callchain = { .nr = 0, }; -static struct perf_callchain_entry * +struct perf_callchain_entry * perf_callchain(struct perf_event *event, struct pt_regs *regs) { bool kernel = !event->attr.exclude_callchain_kernel; @@ -6382,7 +6382,9 @@ void perf_prepare_sample(struct perf_event_header *header, if (sample_type & PERF_SAMPLE_CALLCHAIN) { int size = 1; - data->callchain = perf_callchain(event, regs); + if (!(sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY)) + data->callchain = perf_callchain(event, regs); + size += data->callchain->nr; header->size += size * sizeof(u64); @@ -7335,6 +7337,10 @@ static bool perf_addr_filter_match(struct perf_addr_filter *filter, struct file *file, unsigned long offset, unsigned long size) { + /* d_inode(NULL) won't be equal to any mapped user-space file */ + if (!filter->path.dentry) + return false; + if (d_inode(filter->path.dentry) != file_inode(file)) return false; diff --git a/kernel/fork.c b/kernel/fork.c index a191c05e757d..1b27babc4c78 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -312,10 +312,8 @@ struct vm_area_struct *vm_area_alloc(struct mm_struct *mm) { struct vm_area_struct *vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL); - if (vma) { - vma->vm_mm = mm; - INIT_LIST_HEAD(&vma->anon_vma_chain); - } + if (vma) + vma_init(vma, mm); return vma; } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index daeabd791d58..9a8b7ba9aa88 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1068,6 +1068,13 @@ static int irq_setup_forced_threading(struct irqaction *new) if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT)) return 0; + /* + * No further action required for interrupts which are requested as + * threaded interrupts already + */ + if (new->handler == irq_default_primary_handler) + return 0; + new->flags |= IRQF_ONESHOT; /* @@ -1075,7 +1082,7 @@ static int irq_setup_forced_threading(struct irqaction *new) * thread handler. We force thread them as well by creating a * secondary action. */ - if (new->handler != irq_default_primary_handler && new->thread_fn) { + if (new->handler && new->thread_fn) { /* Allocate the secondary action */ new->secondary = kzalloc(sizeof(struct irqaction), GFP_KERNEL); if (!new->secondary) diff --git a/kernel/kthread.c b/kernel/kthread.c index 750cb8082694..486dedbd9af5 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -325,8 +325,14 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), task = create->result; if (!IS_ERR(task)) { static const struct sched_param param = { .sched_priority = 0 }; + char name[TASK_COMM_LEN]; - vsnprintf(task->comm, sizeof(task->comm), namefmt, args); + /* + * task is already visible to other tasks, so updating + * COMM must be protected. + */ + vsnprintf(name, sizeof(name), namefmt, args); + set_task_comm(task, name); /* * root may have changed our (kthreadd's) priority or CPU mask. * The kernel thread should not inherit these properties. diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 4f014be7a4b8..2823d4163a37 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1465,6 +1465,29 @@ rt_mutex_fastunlock(struct rt_mutex *lock, rt_mutex_postunlock(&wake_q); } +static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass) +{ + might_sleep(); + + mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); +} + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +/** + * rt_mutex_lock_nested - lock a rt_mutex + * + * @lock: the rt_mutex to be locked + * @subclass: the lockdep subclass + */ +void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass) +{ + __rt_mutex_lock(lock, subclass); +} +EXPORT_SYMBOL_GPL(rt_mutex_lock_nested); +#endif + +#ifndef CONFIG_DEBUG_LOCK_ALLOC /** * rt_mutex_lock - lock a rt_mutex * @@ -1472,12 +1495,10 @@ rt_mutex_fastunlock(struct rt_mutex *lock, */ void __sched rt_mutex_lock(struct rt_mutex *lock) { - might_sleep(); - - mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); - rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); + __rt_mutex_lock(lock, 0); } EXPORT_SYMBOL_GPL(rt_mutex_lock); +#endif /** * rt_mutex_lock_interruptible - lock a rt_mutex interruptible diff --git a/kernel/memremap.c b/kernel/memremap.c index 5857267a4af5..38283363da06 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -176,10 +176,27 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) unsigned long pfn, pgoff, order; pgprot_t pgprot = PAGE_KERNEL; int error, nid, is_ram; + struct dev_pagemap *conflict_pgmap; align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) - align_start; + align_end = align_start + align_size - 1; + + conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_start), NULL); + if (conflict_pgmap) { + dev_WARN(dev, "Conflicting mapping in same section\n"); + put_dev_pagemap(conflict_pgmap); + return ERR_PTR(-ENOMEM); + } + + conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_end), NULL); + if (conflict_pgmap) { + dev_WARN(dev, "Conflicting mapping in same section\n"); + put_dev_pagemap(conflict_pgmap); + return ERR_PTR(-ENOMEM); + } + is_ram = region_intersects(align_start, align_size, IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); @@ -199,7 +216,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) mutex_lock(&pgmap_lock); error = 0; - align_end = align_start + align_size - 1; foreach_order_pgoff(res, order, pgoff) { error = __radix_tree_insert(&pgmap_radix, @@ -305,7 +321,7 @@ EXPORT_SYMBOL_GPL(get_dev_pagemap); #ifdef CONFIG_DEV_PAGEMAP_OPS DEFINE_STATIC_KEY_FALSE(devmap_managed_key); -EXPORT_SYMBOL_GPL(devmap_managed_key); +EXPORT_SYMBOL(devmap_managed_key); static atomic_t devmap_enable; /* @@ -346,5 +362,5 @@ void __put_devmap_managed_page(struct page *page) } else if (!count) __put_page(page); } -EXPORT_SYMBOL_GPL(__put_devmap_managed_page); +EXPORT_SYMBOL(__put_devmap_managed_page); #endif /* CONFIG_DEV_PAGEMAP_OPS */ diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 10c7b51c0d1f..b5fbdde6afa9 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2090,8 +2090,14 @@ retry: sub_rq_bw(&next_task->dl, &rq->dl); set_task_cpu(next_task, later_rq->cpu); add_rq_bw(&next_task->dl, &later_rq->dl); + + /* + * Update the later_rq clock here, because the clock is used + * by the cpufreq_update_util() inside __add_running_bw(). + */ + update_rq_clock(later_rq); add_running_bw(&next_task->dl, &later_rq->dl); - activate_task(later_rq, next_task, 0); + activate_task(later_rq, next_task, ENQUEUE_NOCLOCK); ret = 1; resched_curr(later_rq); diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 572567078b60..eaaec8364f96 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -836,6 +836,8 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) * can be time-consuming. Try to avoid it when possible. */ raw_spin_lock(&rt_rq->rt_runtime_lock); + if (!sched_feat(RT_RUNTIME_SHARE) && rt_rq->rt_runtime != RUNTIME_INF) + rt_rq->rt_runtime = rt_b->rt_runtime; skip = !rt_rq->rt_time && !rt_rq->rt_nr_running; raw_spin_unlock(&rt_rq->rt_runtime_lock); if (skip) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 05a831427bc7..56a0fed30c0a 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -47,7 +47,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) { printk(KERN_ERR "ERROR: domain->span does not contain CPU%d\n", cpu); } - if (!cpumask_test_cpu(cpu, sched_group_span(group))) { + if (group && !cpumask_test_cpu(cpu, sched_group_span(group))) { printk(KERN_ERR "ERROR: domain->groups does not contain CPU%d\n", cpu); } diff --git a/kernel/softirq.c b/kernel/softirq.c index 75ffc1d1a2e0..6f584861d329 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -390,7 +390,7 @@ static inline void tick_irq_exit(void) /* Make sure that timer wheel updates are propagated */ if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) { - if (!in_interrupt()) + if (!in_irq()) tick_nohz_irq_exit(); } #endif diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 1ff523dae6e2..e190d1ef3a23 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -260,6 +260,15 @@ retry: err = 0; __cpu_stop_queue_work(stopper1, work1, &wakeq); __cpu_stop_queue_work(stopper2, work2, &wakeq); + /* + * The waking up of stopper threads has to happen + * in the same scheduling context as the queueing. + * Otherwise, there is a possibility of one of the + * above stoppers being woken up by another CPU, + * and preempting us. This will cause us to n ot + * wake up the other stopper forever. + */ + preempt_disable(); unlock: raw_spin_unlock(&stopper2->lock); raw_spin_unlock_irq(&stopper1->lock); @@ -271,7 +280,6 @@ unlock: } if (!err) { - preempt_disable(); wake_up_q(&wakeq); preempt_enable(); } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index da9455a6b42b..5b33e2f5c0ed 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -642,7 +642,7 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) static inline bool local_timer_softirq_pending(void) { - return local_softirq_pending() & TIMER_SOFTIRQ; + return local_softirq_pending() & BIT(TIMER_SOFTIRQ); } static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 6a46af21765c..0b0b688ea166 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3227,6 +3227,22 @@ int ring_buffer_record_is_on(struct ring_buffer *buffer) } /** + * ring_buffer_record_is_set_on - return true if the ring buffer is set writable + * @buffer: The ring buffer to see if write is set enabled + * + * Returns true if the ring buffer is set writable by ring_buffer_record_on(). + * Note that this does NOT mean it is in a writable state. + * + * It may return true when the ring buffer has been disabled by + * ring_buffer_record_disable(), as that is a temporary disabling of + * the ring buffer. + */ +int ring_buffer_record_is_set_on(struct ring_buffer *buffer) +{ + return !(atomic_read(&buffer->record_disabled) & RB_BUFFER_OFF); +} + +/** * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer * @buffer: The ring buffer to stop writes to. * @cpu: The CPU buffer to stop diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 87cf25171fb8..823687997b01 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1373,6 +1373,12 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) arch_spin_lock(&tr->max_lock); + /* Inherit the recordable setting from trace_buffer */ + if (ring_buffer_record_is_set_on(tr->trace_buffer.buffer)) + ring_buffer_record_on(tr->max_buffer.buffer); + else + ring_buffer_record_off(tr->max_buffer.buffer); + swap(tr->trace_buffer.buffer, tr->max_buffer.buffer); __update_max_tr(tr, tsk, cpu); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index d18249683682..5dea177cef53 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -679,6 +679,8 @@ event_trigger_callback(struct event_command *cmd_ops, goto out_free; out_reg: + /* Up the trigger_data count to make sure reg doesn't free it on failure */ + event_trigger_init(trigger_ops, trigger_data); ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file); /* * The above returns on success the # of functions enabled, @@ -686,11 +688,13 @@ event_trigger_callback(struct event_command *cmd_ops, * Consider no functions a failure too. */ if (!ret) { + cmd_ops->unreg(glob, trigger_ops, trigger_data, file); ret = -ENOENT; - goto out_free; - } else if (ret < 0) - goto out_free; - ret = 0; + } else if (ret > 0) + ret = 0; + + /* Down the counter of trigger_data or free it if not used anymore */ + event_trigger_free(trigger_ops, trigger_data); out: return ret; @@ -1416,6 +1420,9 @@ int event_enable_trigger_func(struct event_command *cmd_ops, goto out; } + /* Up the trigger_data count to make sure nothing frees it on failure */ + event_trigger_init(trigger_ops, trigger_data); + if (trigger) { number = strsep(&trigger, ":"); @@ -1466,6 +1473,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops, goto out_disable; /* Just return zero, not the number of enabled functions */ ret = 0; + event_trigger_free(trigger_ops, trigger_data); out: return ret; @@ -1476,7 +1484,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops, out_free: if (cmd_ops->set_filter) cmd_ops->set_filter(NULL, trigger_data, NULL); - kfree(trigger_data); + event_trigger_free(trigger_ops, trigger_data); kfree(enable_data); goto out; } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 21f718472942..6b71860f3998 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -400,11 +400,10 @@ static struct trace_kprobe *find_trace_kprobe(const char *event, static int enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) { + struct event_file_link *link = NULL; int ret = 0; if (file) { - struct event_file_link *link; - link = kmalloc(sizeof(*link), GFP_KERNEL); if (!link) { ret = -ENOMEM; @@ -424,6 +423,18 @@ enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file) else ret = enable_kprobe(&tk->rp.kp); } + + if (ret) { + if (file) { + /* Notice the if is true on not WARN() */ + if (!WARN_ON_ONCE(!link)) + list_del_rcu(&link->list); + kfree(link); + tk->tp.flags &= ~TP_FLAG_TRACE; + } else { + tk->tp.flags &= ~TP_FLAG_PROFILE; + } + } out: return ret; } diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index c253c1b46c6b..befb127507c0 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -5,7 +5,7 @@ if HAVE_ARCH_KASAN config KASAN bool "KASan: runtime memory debugger" - depends on SLUB || (SLAB && !DEBUG_SLAB) + depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB) select SLUB_DEBUG if SLUB select CONSTRUCTORS select STACKDEPOT diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 039ddbc574e9..3103099f64fd 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3167,6 +3167,13 @@ static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf) return 0; } +/* + * When a new function is introduced to vm_operations_struct and added + * to hugetlb_vm_ops, please consider adding the function to shm_vm_ops. + * This is because under System V memory model, mappings created via + * shmget/shmat with "huge page" specified are backed by hugetlbfs files, + * their original vm_ops are overwritten with shm_vm_ops. + */ const struct vm_operations_struct hugetlb_vm_ops = { .fault = hugetlb_vm_op_fault, .open = hugetlb_vm_op_open, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 8c0280b3143e..b2173f7e5164 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4037,6 +4037,14 @@ static struct cftype mem_cgroup_legacy_files[] = { static DEFINE_IDR(mem_cgroup_idr); +static void mem_cgroup_id_remove(struct mem_cgroup *memcg) +{ + if (memcg->id.id > 0) { + idr_remove(&mem_cgroup_idr, memcg->id.id); + memcg->id.id = 0; + } +} + static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n) { VM_BUG_ON(atomic_read(&memcg->id.ref) <= 0); @@ -4047,8 +4055,7 @@ static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n) { VM_BUG_ON(atomic_read(&memcg->id.ref) < n); if (atomic_sub_and_test(n, &memcg->id.ref)) { - idr_remove(&mem_cgroup_idr, memcg->id.id); - memcg->id.id = 0; + mem_cgroup_id_remove(memcg); /* Memcg ID pins CSS */ css_put(&memcg->css); @@ -4185,8 +4192,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void) idr_replace(&mem_cgroup_idr, memcg, memcg->id.id); return memcg; fail: - if (memcg->id.id > 0) - idr_remove(&mem_cgroup_idr, memcg->id.id); + mem_cgroup_id_remove(memcg); __mem_cgroup_free(memcg); return NULL; } @@ -4245,6 +4251,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) return &memcg->css; fail: + mem_cgroup_id_remove(memcg); mem_cgroup_free(memcg); return ERR_PTR(-ENOMEM); } diff --git a/mm/memory.c b/mm/memory.c index 7206a634270b..dab1511294ad 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1417,11 +1417,9 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, do { next = pmd_addr_end(addr, end); if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { - if (next - addr != HPAGE_PMD_SIZE) { - VM_BUG_ON_VMA(vma_is_anonymous(vma) && - !rwsem_is_locked(&tlb->mm->mmap_sem), vma); + if (next - addr != HPAGE_PMD_SIZE) __split_huge_pmd(vma, pmd, addr, false, NULL); - } else if (zap_huge_pmd(tlb, vma, pmd, addr)) + else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* fall through */ } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 9ac49ef17b4e..01f1a14facc4 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2505,6 +2505,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) /* Create pseudo-vma that contains just the policy */ memset(&pvma, 0, sizeof(struct vm_area_struct)); + vma_init(&pvma, NULL); pvma.vm_end = TASK_SIZE; /* policy covers entire file */ mpol_set_shared_policy(sp, &pvma, new); /* adds ref */ diff --git a/mm/mmap.c b/mm/mmap.c index ff1944d8d458..17bbf4d3e24f 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1778,6 +1778,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr, error = shmem_zero_setup(vma); if (error) goto free_vma; + } else { + vma_set_anonymous(vma); } vma_link(mm, vma, prev, rb_link, rb_parent); @@ -2983,6 +2985,7 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla return -ENOMEM; } + vma_set_anonymous(vma); vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_pgoff = pgoff; diff --git a/mm/nommu.c b/mm/nommu.c index 1d22fdbf7d7c..9fc9e43335b6 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1145,6 +1145,8 @@ static int do_mmap_private(struct vm_area_struct *vma, if (ret < len) memset(base + ret, 0, len - ret); + } else { + vma_set_anonymous(vma); } return 0; diff --git a/mm/shmem.c b/mm/shmem.c index 2cab84403055..41b9bbf24e16 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1421,6 +1421,7 @@ static void shmem_pseudo_vma_init(struct vm_area_struct *vma, { /* Create a pseudo vma that just contains the policy */ memset(vma, 0, sizeof(*vma)); + vma_init(vma, NULL); /* Bias interleave by inode number to distribute better across nodes */ vma->vm_pgoff = index + info->vfs_inode.i_ino; vma->vm_policy = mpol_shared_policy_lookup(&info->policy, index); diff --git a/mm/zswap.c b/mm/zswap.c index 7d34e69507e3..cd91fd9d96b8 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1026,6 +1026,15 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, ret = -ENOMEM; goto reject; } + + /* A second zswap_is_full() check after + * zswap_shrink() to make sure it's now + * under the max_pool_percent + */ + if (zswap_is_full()) { + ret = -ENOMEM; + goto reject; + } } /* allocate entry */ diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index e0adcd123f48..711d7156efd8 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -131,8 +131,10 @@ static void caif_flow_cb(struct sk_buff *skb) caifd = caif_get(skb->dev); WARN_ON(caifd == NULL); - if (caifd == NULL) + if (!caifd) { + rcu_read_unlock(); return; + } caifd_hold(caifd); rcu_read_unlock(); diff --git a/net/core/dev.c b/net/core/dev.c index a5aa1c7444e6..559a91271f82 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7149,16 +7149,19 @@ int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len) dev->tx_queue_len = new_len; res = call_netdevice_notifiers(NETDEV_CHANGE_TX_QUEUE_LEN, dev); res = notifier_to_errno(res); - if (res) { - netdev_err(dev, - "refused to change device tx_queue_len\n"); - dev->tx_queue_len = orig_len; - return res; - } - return dev_qdisc_change_tx_queue_len(dev); + if (res) + goto err_rollback; + res = dev_qdisc_change_tx_queue_len(dev); + if (res) + goto err_rollback; } return 0; + +err_rollback: + netdev_err(dev, "refused to change device tx_queue_len\n"); + dev->tx_queue_len = orig_len; + return res; } /** diff --git a/net/core/filter.c b/net/core/filter.c index 06da770f543f..9dfd145eedcc 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1712,24 +1712,26 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = { BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb, u32, offset, void *, to, u32, len, u32, start_header) { + u8 *end = skb_tail_pointer(skb); + u8 *net = skb_network_header(skb); + u8 *mac = skb_mac_header(skb); u8 *ptr; - if (unlikely(offset > 0xffff || len > skb_headlen(skb))) + if (unlikely(offset > 0xffff || len > (end - mac))) goto err_clear; switch (start_header) { case BPF_HDR_START_MAC: - ptr = skb_mac_header(skb) + offset; + ptr = mac + offset; break; case BPF_HDR_START_NET: - ptr = skb_network_header(skb) + offset; + ptr = net + offset; break; default: goto err_clear; } - if (likely(ptr >= skb_mac_header(skb) && - ptr + len <= skb_tail_pointer(skb))) { + if (likely(ptr >= mac && ptr + len <= end)) { memcpy(to, ptr, len); return 0; } diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index e7e626fb87bb..e45098593dc0 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -217,7 +217,7 @@ static int bpf_parse_prog(struct nlattr *attr, struct bpf_lwt_prog *prog, if (!tb[LWT_BPF_PROG_FD] || !tb[LWT_BPF_PROG_NAME]) return -EINVAL; - prog->name = nla_memdup(tb[LWT_BPF_PROG_NAME], GFP_KERNEL); + prog->name = nla_memdup(tb[LWT_BPF_PROG_NAME], GFP_ATOMIC); if (!prog->name) return -ENOMEM; diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 68bf07206744..43a932cb609b 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -269,7 +269,7 @@ static void __page_pool_empty_ring(struct page_pool *pool) struct page *page; /* Empty recycle ring */ - while ((page = ptr_ring_consume(&pool->ring))) { + while ((page = ptr_ring_consume_bh(&pool->ring))) { /* Verify the refcnt invariant of cached pages */ if (!(page_ref_count(page) == 1)) pr_crit("%s() page_pool refcnt %d violation\n", diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5ef61222fdef..e3f743c141b3 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2759,9 +2759,12 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) return err; } - dev->rtnl_link_state = RTNL_LINK_INITIALIZED; - - __dev_notify_flags(dev, old_flags, ~0U); + if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) { + __dev_notify_flags(dev, old_flags, 0U); + } else { + dev->rtnl_link_state = RTNL_LINK_INITIALIZED; + __dev_notify_flags(dev, old_flags, ~0U); + } return 0; } EXPORT_SYMBOL(rtnl_configure_link); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 8e51f8555e11..fb35b62af272 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3720,6 +3720,7 @@ normal: net_warn_ratelimited( "skb_segment: too many frags: %u %u\n", pos, mss); + err = -EINVAL; goto err; } @@ -3753,11 +3754,10 @@ skip_fraglist: perform_csum_check: if (!csum) { - if (skb_has_shared_frag(nskb)) { - err = __skb_linearize(nskb); - if (err) - goto err; - } + if (skb_has_shared_frag(nskb) && + __skb_linearize(nskb)) + goto err; + if (!nskb->remcsum_offload) nskb->ip_summed = CHECKSUM_NONE; SKB_GSO_CB(nskb)->csum = diff --git a/net/core/sock.c b/net/core/sock.c index 9e8f65585b81..bc2d7a37297f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2277,9 +2277,9 @@ int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg, pfrag->offset += use; sge = sg + sg_curr - 1; - if (sg_curr > first_coalesce && sg_page(sg) == pfrag->page && - sg->offset + sg->length == orig_offset) { - sg->length += use; + if (sg_curr > first_coalesce && sg_page(sge) == pfrag->page && + sge->offset + sge->length == orig_offset) { + sge->length += use; } else { sge = sg + sg_curr; sg_unmark_end(sge); diff --git a/net/core/xdp.c b/net/core/xdp.c index 9d1f22072d5d..6771f1855b96 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -345,7 +345,8 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, rcu_read_lock(); /* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */ xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); - xa->zc_alloc->free(xa->zc_alloc, handle); + if (!WARN_ON_ONCE(!xa)) + xa->zc_alloc->free(xa->zc_alloc, handle); rcu_read_unlock(); default: /* Not possible, checked in xdp_rxq_info_reg_mem_model() */ diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 1e3b6a6d8a40..732369c80644 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1248,6 +1248,9 @@ int dsa_slave_suspend(struct net_device *slave_dev) { struct dsa_port *dp = dsa_slave_to_port(slave_dev); + if (!netif_running(slave_dev)) + return 0; + netif_device_detach(slave_dev); rtnl_lock(); @@ -1261,6 +1264,9 @@ int dsa_slave_resume(struct net_device *slave_dev) { struct dsa_port *dp = dsa_slave_to_port(slave_dev); + if (!netif_running(slave_dev)) + return 0; + netif_device_attach(slave_dev); rtnl_lock(); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index e46cdd310e5f..2998b0e47d4b 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -292,19 +292,19 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) return ip_hdr(skb)->daddr; in_dev = __in_dev_get_rcu(dev); - BUG_ON(!in_dev); net = dev_net(dev); scope = RT_SCOPE_UNIVERSE; if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) { + bool vmark = in_dev && IN_DEV_SRC_VMARK(in_dev); struct flowi4 fl4 = { .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_oif = l3mdev_master_ifindex_rcu(dev), .daddr = ip_hdr(skb)->saddr, .flowi4_tos = RT_TOS(ip_hdr(skb)->tos), .flowi4_scope = scope, - .flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0, + .flowi4_mark = vmark ? skb->mark : 0, }; if (!fib_lookup(net, &fl4, &res, 0)) return FIB_RES_PREFSRC(net, res); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index b3c899a630a0..75151be21413 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1200,8 +1200,7 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) spin_lock_bh(&im->lock); if (pmc) { im->interface = pmc->interface; - im->sfmode = pmc->sfmode; - if (pmc->sfmode == MCAST_INCLUDE) { + if (im->sfmode == MCAST_INCLUDE) { im->tomb = pmc->tomb; im->sources = pmc->sources; for (psf = im->sources; psf; psf = psf->sf_next) @@ -1388,7 +1387,8 @@ static void ip_mc_hash_remove(struct in_device *in_dev, /* * A socket has joined a multicast group on device dev. */ -void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, unsigned int mode) +static void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, + unsigned int mode) { struct ip_mc_list *im; #ifdef CONFIG_IP_MULTICAST diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 1e4cf3ab560f..0d70608cc2e1 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -157,9 +157,6 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, { struct inet_frag_queue *q; - if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) - return NULL; - q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC); if (!q) return NULL; @@ -204,6 +201,9 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key) { struct inet_frag_queue *fq; + if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) + return NULL; + rcu_read_lock(); fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 8e9528ebaa8e..d14d741fb05e 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -383,11 +383,16 @@ found: int i = end - next->ip_defrag_offset; /* overlap is 'i' bytes */ if (i < next->len) { + int delta = -next->truesize; + /* Eat head of the next overlapped fragment * and leave the loop. The next ones cannot overlap. */ if (!pskb_pull(next, i)) goto err; + delta += next->truesize; + if (delta) + add_frag_mem_limit(qp->q.net, delta); next->ip_defrag_offset += i; qp->q.meat -= i; if (next->ip_summed != CHECKSUM_UNNECESSARY) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index b3308e9d9762..0e3edd25f881 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -523,6 +523,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->dev = from->dev; to->mark = from->mark; + skb_copy_hash(to, from); + /* Copy the flags to each fragment. */ IPCB(to)->flags = IPCB(from)->flags; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 64c76dcf7386..c0fe5ad996f2 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -150,15 +150,18 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) { struct sockaddr_in sin; const struct iphdr *iph = ip_hdr(skb); - __be16 *ports = (__be16 *)skb_transport_header(skb); + __be16 *ports; + int end; - if (skb_transport_offset(skb) + 4 > (int)skb->len) + end = skb_transport_offset(skb) + 4; + if (end > 0 && !pskb_may_pull(skb, end)) return; /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ + ports = (__be16 *)skb_transport_header(skb); sin.sin_family = AF_INET; sin.sin_addr.s_addr = iph->daddr; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 58e2f479ffb4..4bfff3c87e8e 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -354,6 +354,10 @@ static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain) /* Reduce delayed ACKs by rounding up cwnd to the next even number. */ cwnd = (cwnd + 1) & ~1U; + /* Ensure gain cycling gets inflight above BDP even for small BDPs. */ + if (bbr->mode == BBR_PROBE_BW && gain > BBR_UNIT) + cwnd += 2; + return cwnd; } diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 5869f89ca656..8b637f9f23a2 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -129,24 +129,14 @@ static void dctcp_ce_state_0_to_1(struct sock *sk) struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); - /* State has changed from CE=0 to CE=1 and delayed - * ACK has not sent yet. - */ - if (!ca->ce_state && - inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) { - u32 tmp_rcv_nxt; - - /* Save current rcv_nxt. */ - tmp_rcv_nxt = tp->rcv_nxt; - - /* Generate previous ack with CE=0. */ - tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; - tp->rcv_nxt = ca->prior_rcv_nxt; - - tcp_send_ack(sk); - - /* Recover current rcv_nxt. */ - tp->rcv_nxt = tmp_rcv_nxt; + if (!ca->ce_state) { + /* State has changed from CE=0 to CE=1, force an immediate + * ACK to reflect the new CE state. If an ACK was delayed, + * send that first to reflect the prior CE state. + */ + if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) + __tcp_send_ack(sk, ca->prior_rcv_nxt); + tcp_enter_quickack_mode(sk, 1); } ca->prior_rcv_nxt = tp->rcv_nxt; @@ -160,24 +150,14 @@ static void dctcp_ce_state_1_to_0(struct sock *sk) struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); - /* State has changed from CE=1 to CE=0 and delayed - * ACK has not sent yet. - */ - if (ca->ce_state && - inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) { - u32 tmp_rcv_nxt; - - /* Save current rcv_nxt. */ - tmp_rcv_nxt = tp->rcv_nxt; - - /* Generate previous ack with CE=1. */ - tp->ecn_flags |= TCP_ECN_DEMAND_CWR; - tp->rcv_nxt = ca->prior_rcv_nxt; - - tcp_send_ack(sk); - - /* Recover current rcv_nxt. */ - tp->rcv_nxt = tmp_rcv_nxt; + if (ca->ce_state) { + /* State has changed from CE=1 to CE=0, force an immediate + * ACK to reflect the new CE state. If an ACK was delayed, + * send that first to reflect the prior CE state. + */ + if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) + __tcp_send_ack(sk, ca->prior_rcv_nxt); + tcp_enter_quickack_mode(sk, 1); } ca->prior_rcv_nxt = tp->rcv_nxt; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 8e5522c6833a..f9dcb29be12d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -215,7 +215,7 @@ static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks) icsk->icsk_ack.quick = quickacks; } -static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) +void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -223,6 +223,7 @@ static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) icsk->icsk_ack.pingpong = 0; icsk->icsk_ack.ato = TCP_ATO_MIN; } +EXPORT_SYMBOL(tcp_enter_quickack_mode); /* Send ACKs quickly, if "quick" count is not exhausted * and the session is not interactive. @@ -245,8 +246,15 @@ static void tcp_ecn_queue_cwr(struct tcp_sock *tp) static void tcp_ecn_accept_cwr(struct tcp_sock *tp, const struct sk_buff *skb) { - if (tcp_hdr(skb)->cwr) + if (tcp_hdr(skb)->cwr) { tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; + + /* If the sender is telling us it has entered CWR, then its + * cwnd may be very low (even just 1 packet), so we should ACK + * immediately. + */ + tcp_enter_quickack_mode((struct sock *)tp, 2); + } } static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp) @@ -4357,6 +4365,23 @@ static bool tcp_try_coalesce(struct sock *sk, return true; } +static bool tcp_ooo_try_coalesce(struct sock *sk, + struct sk_buff *to, + struct sk_buff *from, + bool *fragstolen) +{ + bool res = tcp_try_coalesce(sk, to, from, fragstolen); + + /* In case tcp_drop() is called later, update to->gso_segs */ + if (res) { + u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) + + max_t(u16, 1, skb_shinfo(from)->gso_segs); + + skb_shinfo(to)->gso_segs = min_t(u32, gso_segs, 0xFFFF); + } + return res; +} + static void tcp_drop(struct sock *sk, struct sk_buff *skb) { sk_drops_add(sk, skb); @@ -4480,8 +4505,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) /* In the typical case, we are adding an skb to the end of the list. * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup. */ - if (tcp_try_coalesce(sk, tp->ooo_last_skb, - skb, &fragstolen)) { + if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb, + skb, &fragstolen)) { coalesce_done: tcp_grow_window(sk, skb); kfree_skb_partial(skb, fragstolen); @@ -4509,7 +4534,7 @@ coalesce_done: /* All the bits are present. Drop. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - __kfree_skb(skb); + tcp_drop(sk, skb); skb = NULL; tcp_dsack_set(sk, seq, end_seq); goto add_sack; @@ -4528,11 +4553,11 @@ coalesce_done: TCP_SKB_CB(skb1)->end_seq); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - __kfree_skb(skb1); + tcp_drop(sk, skb1); goto merge_right; } - } else if (tcp_try_coalesce(sk, skb1, - skb, &fragstolen)) { + } else if (tcp_ooo_try_coalesce(sk, skb1, + skb, &fragstolen)) { goto coalesce_done; } p = &parent->rb_right; @@ -4901,6 +4926,7 @@ end: static void tcp_collapse_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + u32 range_truesize, sum_tiny = 0; struct sk_buff *skb, *head; u32 start, end; @@ -4912,6 +4938,7 @@ new_range: } start = TCP_SKB_CB(skb)->seq; end = TCP_SKB_CB(skb)->end_seq; + range_truesize = skb->truesize; for (head = skb;;) { skb = skb_rb_next(skb); @@ -4922,11 +4949,20 @@ new_range: if (!skb || after(TCP_SKB_CB(skb)->seq, end) || before(TCP_SKB_CB(skb)->end_seq, start)) { - tcp_collapse(sk, NULL, &tp->out_of_order_queue, - head, skb, start, end); + /* Do not attempt collapsing tiny skbs */ + if (range_truesize != head->truesize || + end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) { + tcp_collapse(sk, NULL, &tp->out_of_order_queue, + head, skb, start, end); + } else { + sum_tiny += range_truesize; + if (sum_tiny > sk->sk_rcvbuf >> 3) + return; + } goto new_range; } + range_truesize += skb->truesize; if (unlikely(before(TCP_SKB_CB(skb)->seq, start))) start = TCP_SKB_CB(skb)->seq; if (after(TCP_SKB_CB(skb)->end_seq, end)) @@ -4941,6 +4977,7 @@ new_range: * 2) not add too big latencies if thousands of packets sit there. * (But if application shrinks SO_RCVBUF, we could still end up * freeing whole queue here) + * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks. * * Return true if queue has shrunk. */ @@ -4948,20 +4985,26 @@ static bool tcp_prune_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct rb_node *node, *prev; + int goal; if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) return false; NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED); + goal = sk->sk_rcvbuf >> 3; node = &tp->ooo_last_skb->rbnode; do { prev = rb_prev(node); rb_erase(node, &tp->out_of_order_queue); + goal -= rb_to_skb(node)->truesize; tcp_drop(sk, rb_to_skb(node)); - sk_mem_reclaim(sk); - if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && - !tcp_under_memory_pressure(sk)) - break; + if (!prev || goal <= 0) { + sk_mem_reclaim(sk); + if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && + !tcp_under_memory_pressure(sk)) + break; + goal = sk->sk_rcvbuf >> 3; + } node = prev; } while (node); tp->ooo_last_skb = rb_to_skb(prev); @@ -4996,6 +5039,9 @@ static int tcp_prune_queue(struct sock *sk) else if (tcp_under_memory_pressure(sk)) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); + if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) + return 0; + tcp_collapse_ofo_queue(sk); if (!skb_queue_empty(&sk->sk_receive_queue)) tcp_collapse(sk, &sk->sk_receive_queue, NULL, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 00e5a300ddb9..c4172c1fb198 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -160,7 +160,8 @@ static void tcp_event_data_sent(struct tcp_sock *tp, } /* Account for an ACK we sent. */ -static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts) +static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, + u32 rcv_nxt) { struct tcp_sock *tp = tcp_sk(sk); @@ -171,6 +172,9 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts) if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1) __sock_put(sk); } + + if (unlikely(rcv_nxt != tp->rcv_nxt)) + return; /* Special ACK sent by DCTCP to reflect ECN */ tcp_dec_quickack_mode(sk, pkts); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } @@ -1023,8 +1027,8 @@ static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb) * We are working here with either a clone of the original * SKB, or a fresh unique copy made by the retransmit engine. */ -static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, - gfp_t gfp_mask) +static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, + int clone_it, gfp_t gfp_mask, u32 rcv_nxt) { const struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet; @@ -1100,7 +1104,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, th->source = inet->inet_sport; th->dest = inet->inet_dport; th->seq = htonl(tcb->seq); - th->ack_seq = htonl(tp->rcv_nxt); + th->ack_seq = htonl(rcv_nxt); *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | tcb->tcp_flags); @@ -1141,7 +1145,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, icsk->icsk_af_ops->send_check(sk, skb); if (likely(tcb->tcp_flags & TCPHDR_ACK)) - tcp_event_ack_sent(sk, tcp_skb_pcount(skb)); + tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt); if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); @@ -1178,6 +1182,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, return err; } +static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, + gfp_t gfp_mask) +{ + return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask, + tcp_sk(sk)->rcv_nxt); +} + /* This routine just queues the buffer for sending. * * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames, @@ -3571,7 +3582,7 @@ void tcp_send_delayed_ack(struct sock *sk) } /* This routine sends an ack and also updates the window. */ -void tcp_send_ack(struct sock *sk) +void __tcp_send_ack(struct sock *sk, u32 rcv_nxt) { struct sk_buff *buff; @@ -3604,9 +3615,14 @@ void tcp_send_ack(struct sock *sk) skb_set_tcp_pure_ack(buff); /* Send it off, this clears delayed acks for us. */ - tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0); + __tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt); +} +EXPORT_SYMBOL_GPL(__tcp_send_ack); + +void tcp_send_ack(struct sock *sk) +{ + __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt); } -EXPORT_SYMBOL_GPL(tcp_send_ack); /* This routine sends a packet with an out of date sequence * number. It assumes the other end will try to ack it. diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 91580c62bb86..f66a1cae3366 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2374,7 +2374,8 @@ static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, continue; if ((rt->fib6_flags & noflags) != 0) continue; - fib6_info_hold(rt); + if (!fib6_info_hold_safe(rt)) + continue; break; } out: diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 2ee08b6a86a4..1a1f876f8e28 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -700,13 +700,16 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, } if (np->rxopt.bits.rxorigdstaddr) { struct sockaddr_in6 sin6; - __be16 *ports = (__be16 *) skb_transport_header(skb); + __be16 *ports; + int end; - if (skb_transport_offset(skb) + 4 <= (int)skb->len) { + end = skb_transport_offset(skb) + 4; + if (end <= 0 || pskb_may_pull(skb, end)) { /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ + ports = (__be16 *)skb_transport_header(skb); sin6.sin6_family = AF_INET6; sin6.sin6_addr = ipv6_hdr(skb)->daddr; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 97513f35bcc5..88a7579c23bd 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -669,8 +669,10 @@ skip_cow: sg_init_table(sg, nfrags); ret = skb_to_sgvec(skb, sg, 0, skb->len); - if (unlikely(ret < 0)) + if (unlikely(ret < 0)) { + kfree(tmp); goto out; + } skb->ip_summed = CHECKSUM_NONE; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index be491bf6ab6e..ef2505aefc15 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -402,9 +402,10 @@ static int icmp6_iif(const struct sk_buff *skb) /* for local traffic to local address, skb dev is the loopback * device. Check if there is a dst attached to the skb and if so - * get the real device index. + * get the real device index. Same is needed for replies to a link + * local address on a device enslaved to an L3 master device */ - if (unlikely(iif == LOOPBACK_IFINDEX)) { + if (unlikely(iif == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) { const struct rt6_info *rt6 = skb_rt6_info(skb); if (rt6) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a14fb4fcdf18..3168847c30d1 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -570,6 +570,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->dev = from->dev; to->mark = from->mark; + skb_copy_hash(to, from); + #ifdef CONFIG_NET_SCHED to->tc_index = from->tc_index; #endif diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index b7f28deddaea..c72ae3a4fe09 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -480,10 +480,6 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) goto tx_err_dst_release; } - skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); - skb_dst_set(skb, dst); - skb->dev = skb_dst(skb)->dev; - mtu = dst_mtu(dst); if (!skb->ignore_df && skb->len > mtu) { skb_dst_update_pmtu(skb, mtu); @@ -498,9 +494,14 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) htonl(mtu)); } - return -EMSGSIZE; + err = -EMSGSIZE; + goto tx_err_dst_release; } + skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); + skb_dst_set(skb, dst); + skb->dev = skb_dst(skb)->dev; + err = dst_output(t->net, skb->sk, skb); if (net_xmit_eval(err) == 0) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 2699be7202be..f60f310785fd 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -790,8 +790,7 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) spin_lock_bh(&im->mca_lock); if (pmc) { im->idev = pmc->idev; - im->mca_sfmode = pmc->mca_sfmode; - if (pmc->mca_sfmode == MCAST_INCLUDE) { + if (im->mca_sfmode == MCAST_INCLUDE) { im->mca_tomb = pmc->mca_tomb; im->mca_sources = pmc->mca_sources; for (psf = im->mca_sources; psf; psf = psf->sf_next) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 2ce0bd17de4f..ec18b3ce8b6d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -972,10 +972,10 @@ static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort) rt->dst.lastuse = jiffies; } +/* Caller must already hold reference to @from */ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from) { rt->rt6i_flags &= ~RTF_EXPIRES; - fib6_info_hold(from); rcu_assign_pointer(rt->from, from); dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true); if (from->fib6_metrics != &dst_default_metrics) { @@ -984,6 +984,7 @@ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from) } } +/* Caller must already hold reference to @ort */ static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort) { struct net_device *dev = fib6_info_nh_dev(ort); @@ -1044,9 +1045,14 @@ static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt) struct net_device *dev = rt->fib6_nh.nh_dev; struct rt6_info *nrt; + if (!fib6_info_hold_safe(rt)) + return NULL; + nrt = ip6_dst_alloc(dev_net(dev), dev, flags); if (nrt) ip6_rt_copy_init(nrt, rt); + else + fib6_info_release(rt); return nrt; } @@ -1178,10 +1184,15 @@ static struct rt6_info *ip6_rt_cache_alloc(struct fib6_info *ort, * Clone the route. */ + if (!fib6_info_hold_safe(ort)) + return NULL; + dev = ip6_rt_get_dev_rcu(ort); rt = ip6_dst_alloc(dev_net(dev), dev, 0); - if (!rt) + if (!rt) { + fib6_info_release(ort); return NULL; + } ip6_rt_copy_init(rt, ort); rt->rt6i_flags |= RTF_CACHE; @@ -1210,12 +1221,17 @@ static struct rt6_info *ip6_rt_pcpu_alloc(struct fib6_info *rt) struct net_device *dev; struct rt6_info *pcpu_rt; + if (!fib6_info_hold_safe(rt)) + return NULL; + rcu_read_lock(); dev = ip6_rt_get_dev_rcu(rt); pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags); rcu_read_unlock(); - if (!pcpu_rt) + if (!pcpu_rt) { + fib6_info_release(rt); return NULL; + } ip6_rt_copy_init(pcpu_rt, rt); pcpu_rt->rt6i_flags |= RTF_PCPU; return pcpu_rt; @@ -2486,7 +2502,7 @@ restart: out: if (ret) - dst_hold(&ret->dst); + ip6_hold_safe(net, &ret, true); else ret = ip6_create_rt_rcu(rt); @@ -3303,7 +3319,8 @@ static int ip6_route_del(struct fib6_config *cfg, continue; if (cfg->fc_protocol && cfg->fc_protocol != rt->fib6_protocol) continue; - fib6_info_hold(rt); + if (!fib6_info_hold_safe(rt)) + continue; rcu_read_unlock(); /* if gateway was specified only delete the one hop */ @@ -3409,6 +3426,9 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu rcu_read_lock(); from = rcu_dereference(rt->from); + /* This fib6_info_hold() is safe here because we hold reference to rt + * and rt already holds reference to fib6_info. + */ fib6_info_hold(from); rcu_read_unlock(); @@ -3470,7 +3490,8 @@ static struct fib6_info *rt6_get_route_info(struct net *net, continue; if (!ipv6_addr_equal(&rt->fib6_nh.nh_gw, gwaddr)) continue; - fib6_info_hold(rt); + if (!fib6_info_hold_safe(rt)) + continue; break; } out: @@ -3530,8 +3551,8 @@ struct fib6_info *rt6_get_dflt_router(struct net *net, ipv6_addr_equal(&rt->fib6_nh.nh_gw, addr)) break; } - if (rt) - fib6_info_hold(rt); + if (rt && !fib6_info_hold_safe(rt)) + rt = NULL; rcu_read_unlock(); return rt; } @@ -3579,8 +3600,8 @@ restart: struct inet6_dev *idev = dev ? __in6_dev_get(dev) : NULL; if (rt->fib6_flags & (RTF_DEFAULT | RTF_ADDRCONF) && - (!idev || idev->cnf.accept_ra != 2)) { - fib6_info_hold(rt); + (!idev || idev->cnf.accept_ra != 2) && + fib6_info_hold_safe(rt)) { rcu_read_unlock(); ip6_del_rt(net, rt); goto restart; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7efa9fd7e109..03e6b7a2bc53 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -938,7 +938,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) &tcp_hashinfo, NULL, 0, &ipv6h->saddr, th->source, &ipv6h->daddr, - ntohs(th->source), tcp_v6_iif(skb), + ntohs(th->source), + tcp_v6_iif_l3_slave(skb), tcp_v6_sdif(skb)); if (!sk1) goto out; @@ -1609,7 +1610,8 @@ do_time_wait: skb, __tcp_hdrlen(th), &ipv6_hdr(skb)->saddr, th->source, &ipv6_hdr(skb)->daddr, - ntohs(th->dest), tcp_v6_iif(skb), + ntohs(th->dest), + tcp_v6_iif_l3_slave(skb), sdif); if (sk2) { struct inet_timewait_sock *tw = inet_twsk(sk); diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index e398797878a9..cf6cca260e7b 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1201,13 +1201,18 @@ static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel, l2tp_session_get(sock_net(sk), tunnel, stats.session_id); - if (session && session->pwtype == L2TP_PWTYPE_PPP) { - err = pppol2tp_session_ioctl(session, cmd, - arg); + if (!session) { + err = -EBADR; + break; + } + if (session->pwtype != L2TP_PWTYPE_PPP) { l2tp_session_dec_refcount(session); - } else { err = -EBADR; + break; } + + err = pppol2tp_session_ioctl(session, cmd, arg); + l2tp_session_dec_refcount(session); break; } #ifdef CONFIG_XFRM diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 0a38cc1cbebc..932985ca4e66 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2254,11 +2254,8 @@ static void ieee80211_deliver_skb_to_local_stack(struct sk_buff *skb, sdata->control_port_over_nl80211)) { struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); bool noencrypt = status->flag & RX_FLAG_DECRYPTED; - struct ethhdr *ehdr = eth_hdr(skb); - cfg80211_rx_control_port(dev, skb->data, skb->len, - ehdr->h_source, - be16_to_cpu(skb->protocol), noencrypt); + cfg80211_rx_control_port(dev, skb, noencrypt); dev_kfree_skb(skb); } else { /* deliver to local stack */ diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 5e2e511c4a6f..d02fbfec3783 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2111,7 +2111,8 @@ int ieee80211_reconfig(struct ieee80211_local *local) if (!sta->uploaded) continue; - if (sta->sdata->vif.type != NL80211_IFTYPE_AP) + if (sta->sdata->vif.type != NL80211_IFTYPE_AP && + sta->sdata->vif.type != NL80211_IFTYPE_AP_VLAN) continue; for (state = IEEE80211_STA_NOTEXIST; diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index abe647d5b8c6..9ce6336d1e55 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -243,14 +243,14 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = * We currently ignore Sync packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ - sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG, + sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, [DCCP_PKT_SYNCACK] = { /* * We currently ignore SyncAck packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ - sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG, + sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, }, [CT_DCCP_ROLE_SERVER] = { @@ -371,14 +371,14 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = * We currently ignore Sync packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ - sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG, + sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, [DCCP_PKT_SYNCACK] = { /* * We currently ignore SyncAck packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ - sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG, + sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, }, }; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 896d4a36081d..f5745e4c6513 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -75,6 +75,7 @@ static void nft_ctx_init(struct nft_ctx *ctx, { ctx->net = net; ctx->family = family; + ctx->level = 0; ctx->table = table; ctx->chain = chain; ctx->nla = nla; @@ -1597,7 +1598,6 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, struct nft_base_chain *basechain; struct nft_stats *stats = NULL; struct nft_chain_hook hook; - const struct nlattr *name; struct nf_hook_ops *ops; struct nft_trans *trans; int err; @@ -1645,12 +1645,11 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, return PTR_ERR(stats); } + err = -ENOMEM; trans = nft_trans_alloc(ctx, NFT_MSG_NEWCHAIN, sizeof(struct nft_trans_chain)); - if (trans == NULL) { - free_percpu(stats); - return -ENOMEM; - } + if (trans == NULL) + goto err; nft_trans_chain_stats(trans) = stats; nft_trans_chain_update(trans) = true; @@ -1660,19 +1659,37 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, else nft_trans_chain_policy(trans) = -1; - name = nla[NFTA_CHAIN_NAME]; - if (nla[NFTA_CHAIN_HANDLE] && name) { - nft_trans_chain_name(trans) = - nla_strdup(name, GFP_KERNEL); - if (!nft_trans_chain_name(trans)) { - kfree(trans); - free_percpu(stats); - return -ENOMEM; + if (nla[NFTA_CHAIN_HANDLE] && + nla[NFTA_CHAIN_NAME]) { + struct nft_trans *tmp; + char *name; + + err = -ENOMEM; + name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL); + if (!name) + goto err; + + err = -EEXIST; + list_for_each_entry(tmp, &ctx->net->nft.commit_list, list) { + if (tmp->msg_type == NFT_MSG_NEWCHAIN && + tmp->ctx.table == table && + nft_trans_chain_update(tmp) && + nft_trans_chain_name(tmp) && + strcmp(name, nft_trans_chain_name(tmp)) == 0) { + kfree(name); + goto err; + } } + + nft_trans_chain_name(trans) = name; } list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; +err: + free_percpu(stats); + kfree(trans); + return err; } static int nf_tables_newchain(struct net *net, struct sock *nlsk, @@ -2254,6 +2271,39 @@ done: return skb->len; } +static int nf_tables_dump_rules_start(struct netlink_callback *cb) +{ + const struct nlattr * const *nla = cb->data; + struct nft_rule_dump_ctx *ctx = NULL; + + if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) { + ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); + if (!ctx) + return -ENOMEM; + + if (nla[NFTA_RULE_TABLE]) { + ctx->table = nla_strdup(nla[NFTA_RULE_TABLE], + GFP_ATOMIC); + if (!ctx->table) { + kfree(ctx); + return -ENOMEM; + } + } + if (nla[NFTA_RULE_CHAIN]) { + ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN], + GFP_ATOMIC); + if (!ctx->chain) { + kfree(ctx->table); + kfree(ctx); + return -ENOMEM; + } + } + } + + cb->data = ctx; + return 0; +} + static int nf_tables_dump_rules_done(struct netlink_callback *cb) { struct nft_rule_dump_ctx *ctx = cb->data; @@ -2283,38 +2333,13 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start= nf_tables_dump_rules_start, .dump = nf_tables_dump_rules, .done = nf_tables_dump_rules_done, .module = THIS_MODULE, + .data = (void *)nla, }; - if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) { - struct nft_rule_dump_ctx *ctx; - - ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); - if (!ctx) - return -ENOMEM; - - if (nla[NFTA_RULE_TABLE]) { - ctx->table = nla_strdup(nla[NFTA_RULE_TABLE], - GFP_ATOMIC); - if (!ctx->table) { - kfree(ctx); - return -ENOMEM; - } - } - if (nla[NFTA_RULE_CHAIN]) { - ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN], - GFP_ATOMIC); - if (!ctx->chain) { - kfree(ctx->table); - kfree(ctx); - return -ENOMEM; - } - } - c.data = ctx; - } - return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -2384,6 +2409,9 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) struct nft_rule *rule; int err; + if (ctx->level == NFT_JUMP_STACK_SIZE) + return -EMLINK; + list_for_each_entry(rule, &chain->rules, list) { if (!nft_is_active_next(ctx->net, rule)) continue; @@ -3161,6 +3189,18 @@ done: return skb->len; } +static int nf_tables_dump_sets_start(struct netlink_callback *cb) +{ + struct nft_ctx *ctx_dump = NULL; + + ctx_dump = kmemdup(cb->data, sizeof(*ctx_dump), GFP_ATOMIC); + if (ctx_dump == NULL) + return -ENOMEM; + + cb->data = ctx_dump; + return 0; +} + static int nf_tables_dump_sets_done(struct netlink_callback *cb) { kfree(cb->data); @@ -3188,18 +3228,12 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = nf_tables_dump_sets_start, .dump = nf_tables_dump_sets, .done = nf_tables_dump_sets_done, + .data = &ctx, .module = THIS_MODULE, }; - struct nft_ctx *ctx_dump; - - ctx_dump = kmalloc(sizeof(*ctx_dump), GFP_ATOMIC); - if (ctx_dump == NULL) - return -ENOMEM; - - *ctx_dump = ctx; - c.data = ctx_dump; return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -3849,6 +3883,15 @@ nla_put_failure: return -ENOSPC; } +static int nf_tables_dump_set_start(struct netlink_callback *cb) +{ + struct nft_set_dump_ctx *dump_ctx = cb->data; + + cb->data = kmemdup(dump_ctx, sizeof(*dump_ctx), GFP_ATOMIC); + + return cb->data ? 0 : -ENOMEM; +} + static int nf_tables_dump_set_done(struct netlink_callback *cb) { kfree(cb->data); @@ -4002,20 +4045,17 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = nf_tables_dump_set_start, .dump = nf_tables_dump_set, .done = nf_tables_dump_set_done, .module = THIS_MODULE, }; - struct nft_set_dump_ctx *dump_ctx; - - dump_ctx = kmalloc(sizeof(*dump_ctx), GFP_ATOMIC); - if (!dump_ctx) - return -ENOMEM; - - dump_ctx->set = set; - dump_ctx->ctx = ctx; + struct nft_set_dump_ctx dump_ctx = { + .set = set, + .ctx = ctx, + }; - c.data = dump_ctx; + c.data = &dump_ctx; return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -4975,38 +5015,42 @@ done: return skb->len; } -static int nf_tables_dump_obj_done(struct netlink_callback *cb) +static int nf_tables_dump_obj_start(struct netlink_callback *cb) { - struct nft_obj_filter *filter = cb->data; + const struct nlattr * const *nla = cb->data; + struct nft_obj_filter *filter = NULL; - if (filter) { - kfree(filter->table); - kfree(filter); + if (nla[NFTA_OBJ_TABLE] || nla[NFTA_OBJ_TYPE]) { + filter = kzalloc(sizeof(*filter), GFP_ATOMIC); + if (!filter) + return -ENOMEM; + + if (nla[NFTA_OBJ_TABLE]) { + filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC); + if (!filter->table) { + kfree(filter); + return -ENOMEM; + } + } + + if (nla[NFTA_OBJ_TYPE]) + filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); } + cb->data = filter; return 0; } -static struct nft_obj_filter * -nft_obj_filter_alloc(const struct nlattr * const nla[]) +static int nf_tables_dump_obj_done(struct netlink_callback *cb) { - struct nft_obj_filter *filter; - - filter = kzalloc(sizeof(*filter), GFP_ATOMIC); - if (!filter) - return ERR_PTR(-ENOMEM); + struct nft_obj_filter *filter = cb->data; - if (nla[NFTA_OBJ_TABLE]) { - filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC); - if (!filter->table) { - kfree(filter); - return ERR_PTR(-ENOMEM); - } + if (filter) { + kfree(filter->table); + kfree(filter); } - if (nla[NFTA_OBJ_TYPE]) - filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - return filter; + return 0; } /* called with rcu_read_lock held */ @@ -5027,21 +5071,13 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = nf_tables_dump_obj_start, .dump = nf_tables_dump_obj, .done = nf_tables_dump_obj_done, .module = THIS_MODULE, + .data = (void *)nla, }; - if (nla[NFTA_OBJ_TABLE] || - nla[NFTA_OBJ_TYPE]) { - struct nft_obj_filter *filter; - - filter = nft_obj_filter_alloc(nla); - if (IS_ERR(filter)) - return -ENOMEM; - - c.data = filter; - } return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -5320,8 +5356,6 @@ static int nf_tables_flowtable_parse_hook(const struct nft_ctx *ctx, flowtable->ops[i].priv = &flowtable->data; flowtable->ops[i].hook = flowtable->data.type->hook; flowtable->ops[i].dev = dev_array[i]; - flowtable->dev_name[i] = kstrdup(dev_array[i]->name, - GFP_KERNEL); } return err; @@ -5479,10 +5513,8 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, err6: i = flowtable->ops_len; err5: - for (k = i - 1; k >= 0; k--) { - kfree(flowtable->dev_name[k]); + for (k = i - 1; k >= 0; k--) nf_unregister_net_hook(net, &flowtable->ops[k]); - } kfree(flowtable->ops); err4: @@ -5581,9 +5613,10 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, goto nla_put_failure; for (i = 0; i < flowtable->ops_len; i++) { - if (flowtable->dev_name[i][0] && - nla_put_string(skb, NFTA_DEVICE_NAME, - flowtable->dev_name[i])) + const struct net_device *dev = READ_ONCE(flowtable->ops[i].dev); + + if (dev && + nla_put_string(skb, NFTA_DEVICE_NAME, dev->name)) goto nla_put_failure; } nla_nest_end(skb, nest_devs); @@ -5650,37 +5683,39 @@ done: return skb->len; } -static int nf_tables_dump_flowtable_done(struct netlink_callback *cb) +static int nf_tables_dump_flowtable_start(struct netlink_callback *cb) { - struct nft_flowtable_filter *filter = cb->data; + const struct nlattr * const *nla = cb->data; + struct nft_flowtable_filter *filter = NULL; - if (!filter) - return 0; + if (nla[NFTA_FLOWTABLE_TABLE]) { + filter = kzalloc(sizeof(*filter), GFP_ATOMIC); + if (!filter) + return -ENOMEM; - kfree(filter->table); - kfree(filter); + filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE], + GFP_ATOMIC); + if (!filter->table) { + kfree(filter); + return -ENOMEM; + } + } + cb->data = filter; return 0; } -static struct nft_flowtable_filter * -nft_flowtable_filter_alloc(const struct nlattr * const nla[]) +static int nf_tables_dump_flowtable_done(struct netlink_callback *cb) { - struct nft_flowtable_filter *filter; + struct nft_flowtable_filter *filter = cb->data; - filter = kzalloc(sizeof(*filter), GFP_ATOMIC); if (!filter) - return ERR_PTR(-ENOMEM); + return 0; - if (nla[NFTA_FLOWTABLE_TABLE]) { - filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE], - GFP_ATOMIC); - if (!filter->table) { - kfree(filter); - return ERR_PTR(-ENOMEM); - } - } - return filter; + kfree(filter->table); + kfree(filter); + + return 0; } /* called with rcu_read_lock held */ @@ -5700,20 +5735,13 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = nf_tables_dump_flowtable_start, .dump = nf_tables_dump_flowtable, .done = nf_tables_dump_flowtable_done, .module = THIS_MODULE, + .data = (void *)nla, }; - if (nla[NFTA_FLOWTABLE_TABLE]) { - struct nft_flowtable_filter *filter; - - filter = nft_flowtable_filter_alloc(nla); - if (IS_ERR(filter)) - return -ENOMEM; - - c.data = filter; - } return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -5783,6 +5811,7 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) kfree(flowtable->name); flowtable->data.type->free(&flowtable->data); module_put(flowtable->data.type->owner); + kfree(flowtable); } static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, @@ -5825,7 +5854,6 @@ static void nft_flowtable_event(unsigned long event, struct net_device *dev, continue; nf_unregister_net_hook(dev_net(dev), &flowtable->ops[i]); - flowtable->dev_name[i][0] = '\0'; flowtable->ops[i].dev = NULL; break; } @@ -6086,6 +6114,9 @@ static void nft_commit_release(struct nft_trans *trans) case NFT_MSG_DELTABLE: nf_tables_table_destroy(&trans->ctx); break; + case NFT_MSG_NEWCHAIN: + kfree(nft_trans_chain_name(trans)); + break; case NFT_MSG_DELCHAIN: nf_tables_chain_destroy(&trans->ctx); break; @@ -6315,13 +6346,15 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_table_notify(&trans->ctx, NFT_MSG_DELTABLE); break; case NFT_MSG_NEWCHAIN: - if (nft_trans_chain_update(trans)) + if (nft_trans_chain_update(trans)) { nft_chain_commit_update(trans); - else + nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN); + /* trans destroyed after rcu grace period */ + } else { nft_clear(net, trans->ctx.chain); - - nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN); - nft_trans_destroy(trans); + nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN); + nft_trans_destroy(trans); + } break; case NFT_MSG_DELCHAIN: nft_chain_del(trans->ctx.chain); @@ -6471,7 +6504,7 @@ static int __nf_tables_abort(struct net *net) case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) { free_percpu(nft_trans_chain_stats(trans)); - + kfree(nft_trans_chain_name(trans)); nft_trans_destroy(trans); } else { trans->ctx.table->use--; @@ -6837,13 +6870,6 @@ int nft_validate_register_store(const struct nft_ctx *ctx, err = nf_tables_check_loops(ctx, data->verdict.chain); if (err < 0) return err; - - if (ctx->chain->level + 1 > - data->verdict.chain->level) { - if (ctx->chain->level + 1 == NFT_JUMP_STACK_SIZE) - return -EMLINK; - data->verdict.chain->level = ctx->chain->level + 1; - } } return 0; diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 15adf8ca82c3..0777a93211e2 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -98,6 +98,7 @@ static int nft_immediate_validate(const struct nft_ctx *ctx, const struct nft_data **d) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); + struct nft_ctx *pctx = (struct nft_ctx *)ctx; const struct nft_data *data; int err; @@ -109,9 +110,11 @@ static int nft_immediate_validate(const struct nft_ctx *ctx, switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: + pctx->level++; err = nft_chain_validate(ctx, data->verdict.chain); if (err < 0) return err; + pctx->level--; break; default: break; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 42e6fadf1417..c2a1d84cdfc4 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -155,7 +155,9 @@ static int nft_lookup_validate_setelem(const struct nft_ctx *ctx, struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + struct nft_ctx *pctx = (struct nft_ctx *)ctx; const struct nft_data *data; + int err; if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) @@ -165,10 +167,17 @@ static int nft_lookup_validate_setelem(const struct nft_ctx *ctx, switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: - return nft_chain_validate(ctx, data->verdict.chain); + pctx->level++; + err = nft_chain_validate(ctx, data->verdict.chain); + if (err < 0) + return err; + pctx->level--; + break; default: - return 0; + break; } + + return 0; } static int nft_lookup_validate(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 72ef35b51cac..90c3e7e6cacb 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -387,6 +387,7 @@ static void nft_rhash_destroy(const struct nft_set *set) struct nft_rhash *priv = nft_set_priv(set); cancel_delayed_work_sync(&priv->gc_work); + rcu_barrier(); rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy, (void *)set); } diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 1f8f257cb518..9873d734b494 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -381,7 +381,7 @@ static void nft_rbtree_gc(struct work_struct *work) gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); if (!gcb) - goto out; + break; atomic_dec(&set->nelems); nft_set_gc_batch_add(gcb, rbe); @@ -390,10 +390,12 @@ static void nft_rbtree_gc(struct work_struct *work) rbe = rb_entry(prev, struct nft_rbtree_elem, node); atomic_dec(&set->nelems); nft_set_gc_batch_add(gcb, rbe); + prev = NULL; } node = rb_next(node); + if (!node) + break; } -out: if (gcb) { for (i = 0; i < gcb->head.cnt; i++) { rbe = gcb->elems[i]; @@ -440,6 +442,7 @@ static void nft_rbtree_destroy(const struct nft_set *set) struct rb_node *node; cancel_delayed_work_sync(&priv->gc_work); + rcu_barrier(); while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 393573a99a5a..56704d95f82d 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -63,6 +63,7 @@ #include <linux/hash.h> #include <linux/genetlink.h> #include <linux/net_namespace.h> +#include <linux/nospec.h> #include <net/net_namespace.h> #include <net/netns/generic.h> @@ -679,6 +680,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, if (protocol < 0 || protocol >= MAX_LINKS) return -EPROTONOSUPPORT; + protocol = array_index_nospec(protocol, MAX_LINKS); netlink_lock_table(); #ifdef CONFIG_MODULES @@ -1009,6 +1011,11 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, return err; } + if (nlk->ngroups == 0) + groups = 0; + else if (nlk->ngroups < 8*sizeof(groups)) + groups &= (1UL << nlk->ngroups) - 1; + bound = nlk->bound; if (bound) { /* Ensure nlk->portid is up-to-date. */ diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index b891a91577f8..c038e021a591 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -211,6 +211,7 @@ static struct dp_meter *dp_meter_create(struct nlattr **a) if (!meter) return ERR_PTR(-ENOMEM); + meter->id = nla_get_u32(a[OVS_METER_ATTR_ID]); meter->used = div_u64(ktime_get_ns(), 1000 * 1000); meter->kbps = a[OVS_METER_ATTR_KBPS] ? 1 : 0; meter->keep_stats = !a[OVS_METER_ATTR_CLEAR]; @@ -280,6 +281,10 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info) u32 meter_id; bool failed; + if (!a[OVS_METER_ATTR_ID]) { + return -ENODEV; + } + meter = dp_meter_create(a); if (IS_ERR_OR_NULL(meter)) return PTR_ERR(meter); @@ -298,11 +303,6 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info) goto exit_unlock; } - if (!a[OVS_METER_ATTR_ID]) { - err = -ENODEV; - goto exit_unlock; - } - meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]); /* Cannot fail after this. */ diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c index 48332a6ed738..d152e48ea371 100644 --- a/net/rds/ib_frmr.c +++ b/net/rds/ib_frmr.c @@ -344,6 +344,11 @@ struct rds_ib_mr *rds_ib_reg_frmr(struct rds_ib_device *rds_ibdev, struct rds_ib_frmr *frmr; int ret; + if (!ic) { + /* TODO: Add FRWR support for RDS_GET_MR using proxy qp*/ + return ERR_PTR(-EOPNOTSUPP); + } + do { if (ibmr) rds_ib_free_frmr(ibmr, true); diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h index 0ea4ab017a8c..655f01d427fe 100644 --- a/net/rds/ib_mr.h +++ b/net/rds/ib_mr.h @@ -115,7 +115,8 @@ void rds_ib_get_mr_info(struct rds_ib_device *rds_ibdev, struct rds_info_rdma_connection *iinfo); void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *); void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, - struct rds_sock *rs, u32 *key_ret); + struct rds_sock *rs, u32 *key_ret, + struct rds_connection *conn); void rds_ib_sync_mr(void *trans_private, int dir); void rds_ib_free_mr(void *trans_private, int invalidate); void rds_ib_flush_mrs(void); diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index e678699268a2..2e49a40a5e11 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -537,11 +537,12 @@ void rds_ib_flush_mrs(void) } void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, - struct rds_sock *rs, u32 *key_ret) + struct rds_sock *rs, u32 *key_ret, + struct rds_connection *conn) { struct rds_ib_device *rds_ibdev; struct rds_ib_mr *ibmr = NULL; - struct rds_ib_connection *ic = rs->rs_conn->c_transport_data; + struct rds_ib_connection *ic = NULL; int ret; rds_ibdev = rds_ib_get_device(rs->rs_bound_addr); @@ -550,6 +551,9 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, goto out; } + if (conn) + ic = conn->c_transport_data; + if (!rds_ibdev->mr_8k_pool || !rds_ibdev->mr_1m_pool) { ret = -ENODEV; goto out; @@ -559,17 +563,18 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, ibmr = rds_ib_reg_frmr(rds_ibdev, ic, sg, nents, key_ret); else ibmr = rds_ib_reg_fmr(rds_ibdev, sg, nents, key_ret); - if (ibmr) - rds_ibdev = NULL; - - out: - if (!ibmr) + if (IS_ERR(ibmr)) { + ret = PTR_ERR(ibmr); pr_warn("RDS/IB: rds_ib_get_mr failed (errno=%d)\n", ret); + } else { + return ibmr; + } + out: if (rds_ibdev) rds_ib_dev_put(rds_ibdev); - return ibmr; + return ERR_PTR(ret); } void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *pool) diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 634cfcb7bba6..80920e47f2c7 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -170,7 +170,8 @@ static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages, } static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, - u64 *cookie_ret, struct rds_mr **mr_ret) + u64 *cookie_ret, struct rds_mr **mr_ret, + struct rds_conn_path *cp) { struct rds_mr *mr = NULL, *found; unsigned int nr_pages; @@ -269,7 +270,8 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, * Note that dma_map() implies that pending writes are * flushed to RAM, so no dma_sync is needed here. */ trans_private = rs->rs_transport->get_mr(sg, nents, rs, - &mr->r_key); + &mr->r_key, + cp ? cp->cp_conn : NULL); if (IS_ERR(trans_private)) { for (i = 0 ; i < nents; i++) @@ -330,7 +332,7 @@ int rds_get_mr(struct rds_sock *rs, char __user *optval, int optlen) sizeof(struct rds_get_mr_args))) return -EFAULT; - return __rds_rdma_map(rs, &args, NULL, NULL); + return __rds_rdma_map(rs, &args, NULL, NULL, NULL); } int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen) @@ -354,7 +356,7 @@ int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen) new_args.cookie_addr = args.cookie_addr; new_args.flags = args.flags; - return __rds_rdma_map(rs, &new_args, NULL, NULL); + return __rds_rdma_map(rs, &new_args, NULL, NULL, NULL); } /* @@ -782,7 +784,8 @@ int rds_cmsg_rdma_map(struct rds_sock *rs, struct rds_message *rm, rm->m_rdma_cookie != 0) return -EINVAL; - return __rds_rdma_map(rs, CMSG_DATA(cmsg), &rm->m_rdma_cookie, &rm->rdma.op_rdma_mr); + return __rds_rdma_map(rs, CMSG_DATA(cmsg), &rm->m_rdma_cookie, + &rm->rdma.op_rdma_mr, rm->m_conn_path); } /* diff --git a/net/rds/rds.h b/net/rds/rds.h index f2272fb8cd45..60b3b787fbdb 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -464,6 +464,8 @@ struct rds_message { struct scatterlist *op_sg; } data; }; + + struct rds_conn_path *m_conn_path; }; /* @@ -544,7 +546,8 @@ struct rds_transport { unsigned int avail); void (*exit)(void); void *(*get_mr)(struct scatterlist *sg, unsigned long nr_sg, - struct rds_sock *rs, u32 *key_ret); + struct rds_sock *rs, u32 *key_ret, + struct rds_connection *conn); void (*sync_mr)(void *trans_private, int direction); void (*free_mr)(void *trans_private, int invalidate); void (*flush_mrs)(void); diff --git a/net/rds/send.c b/net/rds/send.c index 94c7f74909be..59f17a2335f4 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1169,6 +1169,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) rs->rs_conn = conn; } + if (conn->c_trans->t_mp_capable) + cpath = &conn->c_path[rds_send_mprds_hash(rs, conn)]; + else + cpath = &conn->c_path[0]; + + rm->m_conn_path = cpath; + /* Parse any control messages the user may have included. */ ret = rds_cmsg_send(rs, rm, msg, &allocated_mr); if (ret) { @@ -1192,11 +1199,6 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) goto out; } - if (conn->c_trans->t_mp_capable) - cpath = &conn->c_path[rds_send_mprds_hash(rs, conn)]; - else - cpath = &conn->c_path[0]; - if (rds_destroy_pending(conn)) { ret = -EAGAIN; goto out; diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index a9a9be5519b9..9d1e298b784c 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -116,9 +116,9 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, while (*pp) { parent = *pp; xcall = rb_entry(parent, struct rxrpc_call, sock_node); - if (user_call_ID < call->user_call_ID) + if (user_call_ID < xcall->user_call_ID) pp = &(*pp)->rb_left; - else if (user_call_ID > call->user_call_ID) + else if (user_call_ID > xcall->user_call_ID) pp = &(*pp)->rb_right; else goto id_in_use; diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index a7e8d63fc8ae..9bde1e4ca288 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -233,7 +233,8 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc, /* force immediate tx of current consumer cursor, but * under send_lock to guarantee arrival in seqno-order */ - smc_tx_sndbuf_nonempty(conn); + if (smc->sk.sk_state != SMC_INIT) + smc_tx_sndbuf_nonempty(conn); } } diff --git a/net/socket.c b/net/socket.c index 85633622c94d..8c24d5dc4bc8 100644 --- a/net/socket.c +++ b/net/socket.c @@ -89,6 +89,7 @@ #include <linux/magic.h> #include <linux/slab.h> #include <linux/xattr.h> +#include <linux/nospec.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -2522,6 +2523,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) if (call < 1 || call > SYS_SENDMMSG) return -EINVAL; + call = array_index_nospec(call, SYS_SENDMMSG + 1); len = nargs[call]; if (len > sizeof(a)) @@ -2688,7 +2690,8 @@ EXPORT_SYMBOL(sock_unregister); bool sock_is_registered(int family) { - return family < NPROTO && rcu_access_pointer(net_families[family]); + return family < NPROTO && + rcu_access_pointer(net_families[array_index_nospec(family, NPROTO)]); } static int __init sock_init(void) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 4618f1c31137..1f3d9789af30 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -646,6 +646,9 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int flags, return NULL; } + if (sk->sk_shutdown & RCV_SHUTDOWN) + return NULL; + if (sock_flag(sk, SOCK_DONE)) return NULL; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 4eece06be1e7..80bc986c79e5 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4409,6 +4409,7 @@ static int parse_station_flags(struct genl_info *info, params->sta_flags_mask = BIT(NL80211_STA_FLAG_AUTHENTICATED) | BIT(NL80211_STA_FLAG_MFP) | BIT(NL80211_STA_FLAG_AUTHORIZED); + break; default: return -EINVAL; } @@ -14923,20 +14924,24 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, EXPORT_SYMBOL(cfg80211_mgmt_tx_status); static int __nl80211_rx_control_port(struct net_device *dev, - const u8 *buf, size_t len, - const u8 *addr, u16 proto, + struct sk_buff *skb, bool unencrypted, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct ethhdr *ehdr = eth_hdr(skb); + const u8 *addr = ehdr->h_source; + u16 proto = be16_to_cpu(skb->protocol); struct sk_buff *msg; void *hdr; + struct nlattr *frame; + u32 nlportid = READ_ONCE(wdev->conn_owner_nlportid); if (!nlportid) return -ENOENT; - msg = nlmsg_new(100 + len, gfp); + msg = nlmsg_new(100 + skb->len, gfp); if (!msg) return -ENOMEM; @@ -14950,13 +14955,17 @@ static int __nl80211_rx_control_port(struct net_device *dev, nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || nla_put_u64_64bit(msg, NL80211_ATTR_WDEV, wdev_id(wdev), NL80211_ATTR_PAD) || - nla_put(msg, NL80211_ATTR_FRAME, len, buf) || nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, addr) || nla_put_u16(msg, NL80211_ATTR_CONTROL_PORT_ETHERTYPE, proto) || (unencrypted && nla_put_flag(msg, NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT))) goto nla_put_failure; + frame = nla_reserve(msg, NL80211_ATTR_FRAME, skb->len); + if (!frame) + goto nla_put_failure; + + skb_copy_bits(skb, 0, nla_data(frame), skb->len); genlmsg_end(msg, hdr); return genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, nlportid); @@ -14967,14 +14976,12 @@ static int __nl80211_rx_control_port(struct net_device *dev, } bool cfg80211_rx_control_port(struct net_device *dev, - const u8 *buf, size_t len, - const u8 *addr, u16 proto, bool unencrypted) + struct sk_buff *skb, bool unencrypted) { int ret; - trace_cfg80211_rx_control_port(dev, buf, len, addr, proto, unencrypted); - ret = __nl80211_rx_control_port(dev, buf, len, addr, proto, - unencrypted, GFP_ATOMIC); + trace_cfg80211_rx_control_port(dev, skb, unencrypted); + ret = __nl80211_rx_control_port(dev, skb, unencrypted, GFP_ATOMIC); trace_cfg80211_return_bool(ret == 0); return ret == 0; } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index bbe6298e4bb9..4fc66a117b7d 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2240,7 +2240,9 @@ static void wiphy_update_regulatory(struct wiphy *wiphy, * as some drivers used this to restore its orig_* reg domain. */ if (initiator == NL80211_REGDOM_SET_BY_CORE && - wiphy->regulatory_flags & REGULATORY_CUSTOM_REG) + wiphy->regulatory_flags & REGULATORY_CUSTOM_REG && + !(wiphy->regulatory_flags & + REGULATORY_WIPHY_SELF_MANAGED)) reg_call_notifier(wiphy, lr); return; } @@ -2787,26 +2789,6 @@ static void notify_self_managed_wiphys(struct regulatory_request *request) } } -static bool reg_only_self_managed_wiphys(void) -{ - struct cfg80211_registered_device *rdev; - struct wiphy *wiphy; - bool self_managed_found = false; - - ASSERT_RTNL(); - - list_for_each_entry(rdev, &cfg80211_rdev_list, list) { - wiphy = &rdev->wiphy; - if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) - self_managed_found = true; - else - return false; - } - - /* make sure at least one self-managed wiphy exists */ - return self_managed_found; -} - /* * Processes regulatory hints, this is all the NL80211_REGDOM_SET_BY_* * Regulatory hints come on a first come first serve basis and we @@ -2839,10 +2821,6 @@ static void reg_process_pending_hints(void) spin_unlock(®_requests_lock); notify_self_managed_wiphys(reg_request); - if (reg_only_self_managed_wiphys()) { - reg_free_request(reg_request); - return; - } reg_process_hint(reg_request); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 2b417a2fe63f..7c73510b161f 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2627,23 +2627,25 @@ TRACE_EVENT(cfg80211_mgmt_tx_status, ); TRACE_EVENT(cfg80211_rx_control_port, - TP_PROTO(struct net_device *netdev, const u8 *buf, size_t len, - const u8 *addr, u16 proto, bool unencrypted), - TP_ARGS(netdev, buf, len, addr, proto, unencrypted), + TP_PROTO(struct net_device *netdev, struct sk_buff *skb, + bool unencrypted), + TP_ARGS(netdev, skb, unencrypted), TP_STRUCT__entry( NETDEV_ENTRY - MAC_ENTRY(addr) + __field(int, len) + MAC_ENTRY(from) __field(u16, proto) __field(bool, unencrypted) ), TP_fast_assign( NETDEV_ASSIGN; - MAC_ASSIGN(addr, addr); - __entry->proto = proto; + __entry->len = skb->len; + MAC_ASSIGN(from, eth_hdr(skb)->h_source); + __entry->proto = be16_to_cpu(skb->protocol); __entry->unencrypted = unencrypted; ), - TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT " proto: 0x%x, unencrypted: %s", - NETDEV_PR_ARG, MAC_PR_ARG(addr), + TP_printk(NETDEV_PR_FMT ", len=%d, " MAC_PR_FMT ", proto: 0x%x, unencrypted: %s", + NETDEV_PR_ARG, __entry->len, MAC_PR_ARG(from), __entry->proto, BOOL_TO_STR(__entry->unencrypted)) ); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 72335c2e8108..4e937cd7c17d 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -84,10 +84,8 @@ static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) { int err = xskq_produce_batch_desc(xs->rx, (u64)xdp->handle, len); - if (err) { - xdp_return_buff(xdp); + if (err) xs->rx_dropped++; - } return err; } diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 52ecaf770642..8a64b150be54 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -250,7 +250,7 @@ static inline bool xskq_full_desc(struct xsk_queue *q) static inline bool xskq_empty_desc(struct xsk_queue *q) { - return xskq_nb_free(q, q->prod_tail, 1) == q->nentries; + return xskq_nb_free(q, q->prod_tail, q->nentries) == q->nentries; } void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 5f48251c1319..7c5e8978aeaa 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2286,6 +2286,9 @@ struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE) return make_blackhole(net, dst_orig->ops->family, dst_orig); + if (IS_ERR(dst)) + dst_release(dst_orig); + return dst; } EXPORT_SYMBOL(xfrm_lookup_route); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 080035f056d9..33878e6e0d0a 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1025,10 +1025,12 @@ static inline int xfrm_nlmsg_multicast(struct net *net, struct sk_buff *skb, { struct sock *nlsk = rcu_dereference(net->xfrm.nlsk); - if (nlsk) - return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC); - else - return -1; + if (!nlsk) { + kfree_skb(skb); + return -EPIPE; + } + + return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC); } static inline unsigned int xfrm_spdinfo_msgsize(void) @@ -1671,9 +1673,11 @@ static inline unsigned int userpolicy_type_attrsize(void) #ifdef CONFIG_XFRM_SUB_POLICY static int copy_to_user_policy_type(u8 type, struct sk_buff *skb) { - struct xfrm_userpolicy_type upt = { - .type = type, - }; + struct xfrm_userpolicy_type upt; + + /* Sadly there are two holes in struct xfrm_userpolicy_type */ + memset(&upt, 0, sizeof(upt)); + upt.type = type; return nla_put(skb, XFRMA_POLICY_TYPE, sizeof(upt), &upt); } diff --git a/tools/arch/powerpc/include/uapi/asm/unistd.h b/tools/arch/powerpc/include/uapi/asm/unistd.h index ac5ba55066dd..985534d0b448 100644 --- a/tools/arch/powerpc/include/uapi/asm/unistd.h +++ b/tools/arch/powerpc/include/uapi/asm/unistd.h @@ -399,5 +399,6 @@ #define __NR_pkey_free 385 #define __NR_pkey_mprotect 386 #define __NR_rseq 387 +#define __NR_io_pgetevents 388 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */ diff --git a/tools/arch/x86/include/asm/mcsafe_test.h b/tools/arch/x86/include/asm/mcsafe_test.h new file mode 100644 index 000000000000..2ccd588fbad4 --- /dev/null +++ b/tools/arch/x86/include/asm/mcsafe_test.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _MCSAFE_TEST_H_ +#define _MCSAFE_TEST_H_ + +.macro MCSAFE_TEST_CTL +.endm + +.macro MCSAFE_TEST_SRC reg count target +.endm + +.macro MCSAFE_TEST_DST reg count target +.endm +#endif /* _MCSAFE_TEST_H_ */ diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S index 9a53a06e5a3e..298ef1479240 100644 --- a/tools/arch/x86/lib/memcpy_64.S +++ b/tools/arch/x86/lib/memcpy_64.S @@ -3,6 +3,7 @@ #include <linux/linkage.h> #include <asm/errno.h> #include <asm/cpufeatures.h> +#include <asm/mcsafe_test.h> #include <asm/alternative-asm.h> #include <asm/export.h> @@ -183,12 +184,15 @@ ENTRY(memcpy_orig) ENDPROC(memcpy_orig) #ifndef CONFIG_UML + +MCSAFE_TEST_CTL + /* - * memcpy_mcsafe_unrolled - memory copy with machine check exception handling + * __memcpy_mcsafe - memory copy with machine check exception handling * Note that we only catch machine checks when reading the source addresses. * Writes to target are posted and don't generate machine checks. */ -ENTRY(memcpy_mcsafe_unrolled) +ENTRY(__memcpy_mcsafe) cmpl $8, %edx /* Less than 8 bytes? Go to byte copy loop */ jb .L_no_whole_words @@ -204,58 +208,33 @@ ENTRY(memcpy_mcsafe_unrolled) subl $8, %ecx negl %ecx subl %ecx, %edx -.L_copy_leading_bytes: +.L_read_leading_bytes: movb (%rsi), %al + MCSAFE_TEST_SRC %rsi 1 .E_leading_bytes + MCSAFE_TEST_DST %rdi 1 .E_leading_bytes +.L_write_leading_bytes: movb %al, (%rdi) incq %rsi incq %rdi decl %ecx - jnz .L_copy_leading_bytes + jnz .L_read_leading_bytes .L_8byte_aligned: - /* Figure out how many whole cache lines (64-bytes) to copy */ - movl %edx, %ecx - andl $63, %edx - shrl $6, %ecx - jz .L_no_whole_cache_lines - - /* Loop copying whole cache lines */ -.L_cache_w0: movq (%rsi), %r8 -.L_cache_w1: movq 1*8(%rsi), %r9 -.L_cache_w2: movq 2*8(%rsi), %r10 -.L_cache_w3: movq 3*8(%rsi), %r11 - movq %r8, (%rdi) - movq %r9, 1*8(%rdi) - movq %r10, 2*8(%rdi) - movq %r11, 3*8(%rdi) -.L_cache_w4: movq 4*8(%rsi), %r8 -.L_cache_w5: movq 5*8(%rsi), %r9 -.L_cache_w6: movq 6*8(%rsi), %r10 -.L_cache_w7: movq 7*8(%rsi), %r11 - movq %r8, 4*8(%rdi) - movq %r9, 5*8(%rdi) - movq %r10, 6*8(%rdi) - movq %r11, 7*8(%rdi) - leaq 64(%rsi), %rsi - leaq 64(%rdi), %rdi - decl %ecx - jnz .L_cache_w0 - - /* Are there any trailing 8-byte words? */ -.L_no_whole_cache_lines: movl %edx, %ecx andl $7, %edx shrl $3, %ecx jz .L_no_whole_words - /* Copy trailing words */ -.L_copy_trailing_words: +.L_read_words: movq (%rsi), %r8 - mov %r8, (%rdi) - leaq 8(%rsi), %rsi - leaq 8(%rdi), %rdi + MCSAFE_TEST_SRC %rsi 8 .E_read_words + MCSAFE_TEST_DST %rdi 8 .E_write_words +.L_write_words: + movq %r8, (%rdi) + addq $8, %rsi + addq $8, %rdi decl %ecx - jnz .L_copy_trailing_words + jnz .L_read_words /* Any trailing bytes? */ .L_no_whole_words: @@ -264,38 +243,55 @@ ENTRY(memcpy_mcsafe_unrolled) /* Copy trailing bytes */ movl %edx, %ecx -.L_copy_trailing_bytes: +.L_read_trailing_bytes: movb (%rsi), %al + MCSAFE_TEST_SRC %rsi 1 .E_trailing_bytes + MCSAFE_TEST_DST %rdi 1 .E_trailing_bytes +.L_write_trailing_bytes: movb %al, (%rdi) incq %rsi incq %rdi decl %ecx - jnz .L_copy_trailing_bytes + jnz .L_read_trailing_bytes /* Copy successful. Return zero */ .L_done_memcpy_trap: xorq %rax, %rax ret -ENDPROC(memcpy_mcsafe_unrolled) -EXPORT_SYMBOL_GPL(memcpy_mcsafe_unrolled) +ENDPROC(__memcpy_mcsafe) +EXPORT_SYMBOL_GPL(__memcpy_mcsafe) .section .fixup, "ax" - /* Return -EFAULT for any failure */ -.L_memcpy_mcsafe_fail: - mov $-EFAULT, %rax + /* + * Return number of bytes not copied for any failure. Note that + * there is no "tail" handling since the source buffer is 8-byte + * aligned and poison is cacheline aligned. + */ +.E_read_words: + shll $3, %ecx +.E_leading_bytes: + addl %edx, %ecx +.E_trailing_bytes: + mov %ecx, %eax ret + /* + * For write fault handling, given the destination is unaligned, + * we handle faults on multi-byte writes with a byte-by-byte + * copy up to the write-protected page. + */ +.E_write_words: + shll $3, %ecx + addl %edx, %ecx + movl %ecx, %edx + jmp mcsafe_handle_tail + .previous - _ASM_EXTABLE_FAULT(.L_copy_leading_bytes, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w0, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w1, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w2, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w3, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w4, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w5, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w6, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_cache_w7, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_copy_trailing_words, .L_memcpy_mcsafe_fail) - _ASM_EXTABLE_FAULT(.L_copy_trailing_bytes, .L_memcpy_mcsafe_fail) + _ASM_EXTABLE_FAULT(.L_read_leading_bytes, .E_leading_bytes) + _ASM_EXTABLE_FAULT(.L_read_words, .E_read_words) + _ASM_EXTABLE_FAULT(.L_read_trailing_bytes, .E_trailing_bytes) + _ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes) + _ASM_EXTABLE(.L_write_words, .E_write_words) + _ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes) #endif diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 32f9e397a6c0..3f140eff039f 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -217,6 +217,14 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)) int err; int fd; + if (argc < 3) { + p_err("too few arguments, id ID and FILE path is required"); + return -1; + } else if (argc > 3) { + p_err("too many arguments"); + return -1; + } + if (!is_prefix(*argv, "id")) { p_err("expected 'id' got %s", *argv); return -1; @@ -230,9 +238,6 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)) } NEXT_ARG(); - if (argc != 1) - usage(); - fd = get_fd_by_id(id); if (fd < 0) { p_err("can't get prog by id (%u): %s", id, strerror(errno)); diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 097b1a5e046b..f74a8bcbda87 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -36,6 +36,7 @@ #include <assert.h> #include <errno.h> #include <fcntl.h> +#include <linux/kernel.h> #include <stdbool.h> #include <stdio.h> #include <stdlib.h> @@ -90,7 +91,8 @@ static bool map_is_map_of_progs(__u32 type) static void *alloc_value(struct bpf_map_info *info) { if (map_is_per_cpu(info->type)) - return malloc(info->value_size * get_possible_cpus()); + return malloc(round_up(info->value_size, 8) * + get_possible_cpus()); else return malloc(info->value_size); } @@ -161,9 +163,10 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key, jsonw_name(json_wtr, "value"); print_hex_data_json(value, info->value_size); } else { - unsigned int i, n; + unsigned int i, n, step; n = get_possible_cpus(); + step = round_up(info->value_size, 8); jsonw_name(json_wtr, "key"); print_hex_data_json(key, info->key_size); @@ -176,7 +179,7 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key, jsonw_int_field(json_wtr, "cpu", i); jsonw_name(json_wtr, "value"); - print_hex_data_json(value + i * info->value_size, + print_hex_data_json(value + i * step, info->value_size); jsonw_end_object(json_wtr); @@ -207,9 +210,10 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, printf("\n"); } else { - unsigned int i, n; + unsigned int i, n, step; n = get_possible_cpus(); + step = round_up(info->value_size, 8); printf("key:\n"); fprint_hex(stdout, key, info->key_size, " "); @@ -217,7 +221,7 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, for (i = 0; i < n; i++) { printf("value (CPU %02d):%c", i, info->value_size > 16 ? '\n' : ' '); - fprint_hex(stdout, value + i * info->value_size, + fprint_hex(stdout, value + i * step, info->value_size, " "); printf("\n"); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 59b19b6a40d7..b7db3261c62d 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1857,7 +1857,8 @@ union bpf_attr { * is resolved), the nexthop address is returned in ipv4_dst * or ipv6_dst based on family, smac is set to mac address of * egress device, dmac is set to nexthop mac address, rt_metric - * is set to metric from route (IPv4/IPv6 only). + * is set to metric from route (IPv4/IPv6 only), and ifindex + * is set to the device index of the nexthop from the FIB lookup. * * *plen* argument is the size of the passed in struct. * *flags* argument can be a combination of one or more of the @@ -1873,9 +1874,10 @@ union bpf_attr { * *ctx* is either **struct xdp_md** for XDP programs or * **struct sk_buff** tc cls_act programs. * Return - * Egress device index on success, 0 if packet needs to continue - * up the stack for further processing or a negative error in case - * of failure. + * * < 0 if any input argument is invalid + * * 0 on success (packet is forwarded, nexthop neighbor exists) + * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the + * * packet is not forwarded or needs assist from full stack * * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags) * Description @@ -2612,6 +2614,18 @@ struct bpf_raw_tracepoint_args { #define BPF_FIB_LOOKUP_DIRECT BIT(0) #define BPF_FIB_LOOKUP_OUTPUT BIT(1) +enum { + BPF_FIB_LKUP_RET_SUCCESS, /* lookup successful */ + BPF_FIB_LKUP_RET_BLACKHOLE, /* dest is blackholed; can be dropped */ + BPF_FIB_LKUP_RET_UNREACHABLE, /* dest is unreachable; can be dropped */ + BPF_FIB_LKUP_RET_PROHIBIT, /* dest not allowed; can be dropped */ + BPF_FIB_LKUP_RET_NOT_FWDED, /* packet is not forwarded */ + BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */ + BPF_FIB_LKUP_RET_UNSUPP_LWT, /* fwd requires encapsulation */ + BPF_FIB_LKUP_RET_NO_NEIGH, /* no neighbor entry for nh */ + BPF_FIB_LKUP_RET_FRAG_NEEDED, /* fragmentation required to fwd */ +}; + struct bpf_fib_lookup { /* input: network family for lookup (AF_INET, AF_INET6) * output: network family of egress nexthop @@ -2625,7 +2639,11 @@ struct bpf_fib_lookup { /* total length of packet from network header - used for MTU check */ __u16 tot_len; - __u32 ifindex; /* L3 device index for lookup */ + + /* input: L3 device index for lookup + * output: device index from FIB lookup + */ + __u32 ifindex; union { /* inputs to lookup */ diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index 0b5ddbe135a4..972265f32871 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -76,7 +76,7 @@ struct btf_type { */ #define BTF_INT_ENCODING(VAL) (((VAL) & 0x0f000000) >> 24) #define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16) -#define BTF_INT_BITS(VAL) ((VAL) & 0x0000ffff) +#define BTF_INT_BITS(VAL) ((VAL) & 0x000000ff) /* Attributes stored in the BTF_INT_ENCODING */ #define BTF_INT_SIGNED (1 << 0) diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index b8e288a1f740..eeb787b1c53c 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -143,6 +143,8 @@ enum perf_event_sample_format { PERF_SAMPLE_PHYS_ADDR = 1U << 19, PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */ + + __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, }; /* diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 8c54a4b6f187..2d270c560df3 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -2,7 +2,6 @@ /* Copyright (c) 2018 Facebook */ #include <stdlib.h> -#include <stdint.h> #include <string.h> #include <unistd.h> #include <errno.h> @@ -27,13 +26,13 @@ struct btf { struct btf_type **types; const char *strings; void *nohdr_data; - uint32_t nr_types; - uint32_t types_size; - uint32_t data_size; + __u32 nr_types; + __u32 types_size; + __u32 data_size; int fd; }; -static const char *btf_name_by_offset(const struct btf *btf, uint32_t offset) +static const char *btf_name_by_offset(const struct btf *btf, __u32 offset) { if (offset < btf->hdr->str_len) return &btf->strings[offset]; @@ -45,7 +44,7 @@ static int btf_add_type(struct btf *btf, struct btf_type *t) { if (btf->types_size - btf->nr_types < 2) { struct btf_type **new_types; - u32 expand_by, new_size; + __u32 expand_by, new_size; if (btf->types_size == BTF_MAX_NR_TYPES) return -E2BIG; @@ -72,7 +71,7 @@ static int btf_add_type(struct btf *btf, struct btf_type *t) static int btf_parse_hdr(struct btf *btf, btf_print_fn_t err_log) { const struct btf_header *hdr = btf->hdr; - u32 meta_left; + __u32 meta_left; if (btf->data_size < sizeof(struct btf_header)) { elog("BTF header not found\n"); @@ -151,7 +150,7 @@ static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log) while (next_type < end_type) { struct btf_type *t = next_type; - uint16_t vlen = BTF_INFO_VLEN(t->info); + __u16 vlen = BTF_INFO_VLEN(t->info); int err; next_type += sizeof(*t); @@ -190,8 +189,7 @@ static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log) return 0; } -static const struct btf_type *btf_type_by_id(const struct btf *btf, - uint32_t type_id) +const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id) { if (type_id > btf->nr_types) return NULL; @@ -209,7 +207,7 @@ static bool btf_type_is_void_or_null(const struct btf_type *t) return !t || btf_type_is_void(t); } -static int64_t btf_type_size(const struct btf_type *t) +static __s64 btf_type_size(const struct btf_type *t) { switch (BTF_INFO_KIND(t->info)) { case BTF_KIND_INT: @@ -226,15 +224,15 @@ static int64_t btf_type_size(const struct btf_type *t) #define MAX_RESOLVE_DEPTH 32 -int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id) +__s64 btf__resolve_size(const struct btf *btf, __u32 type_id) { const struct btf_array *array; const struct btf_type *t; - uint32_t nelems = 1; - int64_t size = -1; + __u32 nelems = 1; + __s64 size = -1; int i; - t = btf_type_by_id(btf, type_id); + t = btf__type_by_id(btf, type_id); for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t); i++) { size = btf_type_size(t); @@ -259,7 +257,7 @@ int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id) return -EINVAL; } - t = btf_type_by_id(btf, type_id); + t = btf__type_by_id(btf, type_id); } if (size < 0) @@ -271,9 +269,9 @@ int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id) return nelems * size; } -int32_t btf__find_by_name(const struct btf *btf, const char *type_name) +__s32 btf__find_by_name(const struct btf *btf, const char *type_name) { - uint32_t i; + __u32 i; if (!strcmp(type_name, "void")) return 0; @@ -302,10 +300,9 @@ void btf__free(struct btf *btf) free(btf); } -struct btf *btf__new(uint8_t *data, uint32_t size, - btf_print_fn_t err_log) +struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log) { - uint32_t log_buf_size = 0; + __u32 log_buf_size = 0; char *log_buf = NULL; struct btf *btf; int err; diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 74bb344035bb..e2a09a155f84 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -4,19 +4,21 @@ #ifndef __BPF_BTF_H #define __BPF_BTF_H -#include <stdint.h> +#include <linux/types.h> #define BTF_ELF_SEC ".BTF" struct btf; +struct btf_type; typedef int (*btf_print_fn_t)(const char *, ...) __attribute__((format(printf, 1, 2))); void btf__free(struct btf *btf); -struct btf *btf__new(uint8_t *data, uint32_t size, btf_print_fn_t err_log); -int32_t btf__find_by_name(const struct btf *btf, const char *type_name); -int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id); +struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log); +__s32 btf__find_by_name(const struct btf *btf, const char *type_name); +const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id); +__s64 btf__resolve_size(const struct btf *btf, __u32 type_id); int btf__fd(const struct btf *btf); #endif diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index a1e96b5de5ff..1aafdbe827fe 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -36,6 +36,7 @@ #include <linux/err.h> #include <linux/kernel.h> #include <linux/bpf.h> +#include <linux/btf.h> #include <linux/list.h> #include <linux/limits.h> #include <sys/stat.h> @@ -216,8 +217,8 @@ struct bpf_map { size_t offset; int map_ifindex; struct bpf_map_def def; - uint32_t btf_key_type_id; - uint32_t btf_value_type_id; + __u32 btf_key_type_id; + __u32 btf_value_type_id; void *priv; bpf_map_clear_priv_t clear_priv; }; @@ -1014,68 +1015,72 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf) { + const struct btf_type *container_type; + const struct btf_member *key, *value; struct bpf_map_def *def = &map->def; const size_t max_name = 256; - int64_t key_size, value_size; - int32_t key_id, value_id; - char name[max_name]; + char container_name[max_name]; + __s64 key_size, value_size; + __s32 container_id; - /* Find key type by name from BTF */ - if (snprintf(name, max_name, "%s_key", map->name) == max_name) { - pr_warning("map:%s length of BTF key_type:%s_key is too long\n", + if (snprintf(container_name, max_name, "____btf_map_%s", map->name) == + max_name) { + pr_warning("map:%s length of '____btf_map_%s' is too long\n", map->name, map->name); return -EINVAL; } - key_id = btf__find_by_name(btf, name); - if (key_id < 0) { - pr_debug("map:%s key_type:%s cannot be found in BTF\n", - map->name, name); - return key_id; + container_id = btf__find_by_name(btf, container_name); + if (container_id < 0) { + pr_debug("map:%s container_name:%s cannot be found in BTF. Missing BPF_ANNOTATE_KV_PAIR?\n", + map->name, container_name); + return container_id; } - key_size = btf__resolve_size(btf, key_id); - if (key_size < 0) { - pr_warning("map:%s key_type:%s cannot get the BTF type_size\n", - map->name, name); - return key_size; + container_type = btf__type_by_id(btf, container_id); + if (!container_type) { + pr_warning("map:%s cannot find BTF type for container_id:%u\n", + map->name, container_id); + return -EINVAL; } - if (def->key_size != key_size) { - pr_warning("map:%s key_type:%s has BTF type_size:%u != key_size:%u\n", - map->name, name, (unsigned int)key_size, def->key_size); + if (BTF_INFO_KIND(container_type->info) != BTF_KIND_STRUCT || + BTF_INFO_VLEN(container_type->info) < 2) { + pr_warning("map:%s container_name:%s is an invalid container struct\n", + map->name, container_name); return -EINVAL; } - /* Find value type from BTF */ - if (snprintf(name, max_name, "%s_value", map->name) == max_name) { - pr_warning("map:%s length of BTF value_type:%s_value is too long\n", - map->name, map->name); - return -EINVAL; + key = (struct btf_member *)(container_type + 1); + value = key + 1; + + key_size = btf__resolve_size(btf, key->type); + if (key_size < 0) { + pr_warning("map:%s invalid BTF key_type_size\n", + map->name); + return key_size; } - value_id = btf__find_by_name(btf, name); - if (value_id < 0) { - pr_debug("map:%s value_type:%s cannot be found in BTF\n", - map->name, name); - return value_id; + if (def->key_size != key_size) { + pr_warning("map:%s btf_key_type_size:%u != map_def_key_size:%u\n", + map->name, (__u32)key_size, def->key_size); + return -EINVAL; } - value_size = btf__resolve_size(btf, value_id); + value_size = btf__resolve_size(btf, value->type); if (value_size < 0) { - pr_warning("map:%s value_type:%s cannot get the BTF type_size\n", - map->name, name); + pr_warning("map:%s invalid BTF value_type_size\n", map->name); return value_size; } if (def->value_size != value_size) { - pr_warning("map:%s value_type:%s has BTF type_size:%u != value_size:%u\n", - map->name, name, (unsigned int)value_size, def->value_size); + pr_warning("map:%s btf_value_type_size:%u != map_def_value_size:%u\n", + map->name, (__u32)value_size, def->value_size); return -EINVAL; } - map->btf_key_type_id = key_id; - map->btf_value_type_id = value_id; + map->btf_key_type_id = key->type; + map->btf_value_type_id = value->type; return 0; } @@ -2089,12 +2094,12 @@ const char *bpf_map__name(struct bpf_map *map) return map ? map->name : NULL; } -uint32_t bpf_map__btf_key_type_id(const struct bpf_map *map) +__u32 bpf_map__btf_key_type_id(const struct bpf_map *map) { return map ? map->btf_key_type_id : 0; } -uint32_t bpf_map__btf_value_type_id(const struct bpf_map *map) +__u32 bpf_map__btf_value_type_id(const struct bpf_map *map) { return map ? map->btf_value_type_id : 0; } @@ -2268,8 +2273,8 @@ bpf_perf_event_read_simple(void *mem, unsigned long size, volatile struct perf_event_mmap_page *header = mem; __u64 data_tail = header->data_tail; __u64 data_head = header->data_head; + int ret = LIBBPF_PERF_EVENT_ERROR; void *base, *begin, *end; - int ret; asm volatile("" ::: "memory"); /* in real code it should be smp_rmb() */ if (data_head == data_tail) diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 09976531aa74..b33ae02f7d0e 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -244,8 +244,8 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj); int bpf_map__fd(struct bpf_map *map); const struct bpf_map_def *bpf_map__def(struct bpf_map *map); const char *bpf_map__name(struct bpf_map *map); -uint32_t bpf_map__btf_key_type_id(const struct bpf_map *map); -uint32_t bpf_map__btf_value_type_id(const struct bpf_map *map); +__u32 bpf_map__btf_key_type_id(const struct bpf_map *map); +__u32 bpf_map__btf_value_type_id(const struct bpf_map *map); typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); int bpf_map__set_priv(struct bpf_map *map, void *priv, diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c index 63a74c32ddc5..e33ef5bc31c5 100644 --- a/tools/perf/arch/x86/util/pmu.c +++ b/tools/perf/arch/x86/util/pmu.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <string.h> +#include <linux/stddef.h> #include <linux/perf_event.h> #include "../../util/intel-pt.h" diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c index 06bae7023a51..950539f9a4f7 100644 --- a/tools/perf/arch/x86/util/tsc.c +++ b/tools/perf/arch/x86/util/tsc.c @@ -2,6 +2,7 @@ #include <stdbool.h> #include <errno.h> +#include <linux/stddef.h> #include <linux/perf_event.h> #include "../../perf.h" diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build index 60bf11943047..eafce1a130a1 100644 --- a/tools/perf/bench/Build +++ b/tools/perf/bench/Build @@ -7,6 +7,7 @@ perf-y += futex-wake-parallel.o perf-y += futex-requeue.o perf-y += futex-lock-pi.o +perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-lib.o perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S index b43f8d2a34ec..9ad015a1e202 100644 --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S @@ -6,6 +6,7 @@ #define altinstr_replacement text #define globl p2align 4; .globl #define _ASM_EXTABLE_FAULT(x, y) +#define _ASM_EXTABLE(x, y) #include "../../arch/x86/lib/memcpy_64.S" /* diff --git a/tools/perf/bench/mem-memcpy-x86-64-lib.c b/tools/perf/bench/mem-memcpy-x86-64-lib.c new file mode 100644 index 000000000000..4130734dde84 --- /dev/null +++ b/tools/perf/bench/mem-memcpy-x86-64-lib.c @@ -0,0 +1,24 @@ +/* + * From code in arch/x86/lib/usercopy_64.c, copied to keep tools/ copy + * of the kernel's arch/x86/lib/memcpy_64.s used in 'perf bench mem memcpy' + * happy. + */ +#include <linux/types.h> + +unsigned long __memcpy_mcsafe(void *dst, const void *src, size_t cnt); +unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len); + +unsigned long mcsafe_handle_tail(char *to, char *from, unsigned len) +{ + for (; len; --len, to++, from++) { + /* + * Call the assembly routine back directly since + * memcpy_mcsafe() may silently fallback to memcpy. + */ + unsigned long rem = __memcpy_mcsafe(to, from, 1); + + if (rem) + break; + } + return len; +} diff --git a/tools/perf/perf.h b/tools/perf/perf.h index a1a97956136f..d215714f48df 100644 --- a/tools/perf/perf.h +++ b/tools/perf/perf.h @@ -5,6 +5,7 @@ #include <time.h> #include <stdbool.h> #include <linux/types.h> +#include <linux/stddef.h> #include <linux/perf_event.h> extern bool test_attr__enabled; diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index 90d4577a92dc..6d7fe44aadc0 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -2,6 +2,7 @@ #ifndef __PERF_HEADER_H #define __PERF_HEADER_H +#include <linux/stddef.h> #include <linux/perf_event.h> #include <sys/types.h> #include <stdbool.h> diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h index 760558dcfd18..cae1a9a39722 100644 --- a/tools/perf/util/namespaces.h +++ b/tools/perf/util/namespaces.h @@ -10,6 +10,7 @@ #define __PERF_NAMESPACES_H #include <sys/types.h> +#include <linux/stddef.h> #include <linux/perf_event.h> #include <linux/refcount.h> #include <linux/types.h> diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index d39e4ff7d0bf..a6db83a88e85 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -106,7 +106,7 @@ The system configuration dump (if --quiet is not used) is followed by statistics \fBC1%, C2%, C3%\fP The residency percentage that Linux requested C1, C2, C3.... The system summary is the average of all CPUs in the system. Note that these are software, reflecting what was requested. The hardware counters reflect what was actually achieved. \fBCPU%c1, CPU%c3, CPU%c6, CPU%c7\fP show the percentage residency in hardware core idle states. These numbers are from hardware residency counters. \fBCoreTmp\fP Degrees Celsius reported by the per-core Digital Thermal Sensor. -\fBPkgTtmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor. +\fBPkgTmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor. \fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms. \fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz. \fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states. These numbers are from hardware residency counters. @@ -114,7 +114,7 @@ The system configuration dump (if --quiet is not used) is followed by statistics \fBCorWatt\fP Watts consumed by the core part of the package. \fBGFXWatt\fP Watts consumed by the Graphics part of the package -- available only on client processors. \fBRAMWatt\fP Watts consumed by the DRAM DIMMS -- available only on server processors. -\fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package. +\fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package. Note that the system summary is the sum of the package throttling time, and thus may be higher than 100% on a multi-package system. Note that the meaning of this field is model specific. For example, some hardware increments this counter when RAPL responds to thermal limits, but does not increment this counter when RAPL responds to power limits. Comparing PkgWatt and PkgTmp to system limits is necessary. \fBRAM_%\fP percent of the interval that RAPL throttling was active on DRAM. .fi .SH TOO MUCH INFORMATION EXAMPLE diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 4d14bbbf9b63..980bd9d20646 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -1163,9 +1163,7 @@ void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_ if (!printed || !summary_only) print_header("\t"); - if (topo.num_cpus > 1) - format_counters(&average.threads, &average.cores, - &average.packages); + format_counters(&average.threads, &average.cores, &average.packages); printed = 1; @@ -1692,7 +1690,7 @@ void get_apic_id(struct thread_data *t) t->x2apic_id = edx; if (debug && (t->apic_id != t->x2apic_id)) - fprintf(stderr, "cpu%d: apic 0x%x x2apic 0x%x\n", t->cpu_id, t->apic_id, t->x2apic_id); + fprintf(outf, "cpu%d: apic 0x%x x2apic 0x%x\n", t->cpu_id, t->apic_id, t->x2apic_id); } /* @@ -2473,55 +2471,43 @@ int get_core_id(int cpu) void set_node_data(void) { - char path[80]; - FILE *filep; - int pkg, node, cpu; - - struct pkg_node_info { - int count; - int min; - } *pni; - - pni = calloc(topo.num_packages, sizeof(struct pkg_node_info)); - if (!pni) - err(1, "calloc pkg_node_count"); - - for (pkg = 0; pkg < topo.num_packages; pkg++) - pni[pkg].min = topo.num_cpus; - - for (node = 0; node <= topo.max_node_num; node++) { - /* find the "first" cpu in the node */ - sprintf(path, "/sys/bus/node/devices/node%d/cpulist", node); - filep = fopen(path, "r"); - if (!filep) - continue; - fscanf(filep, "%d", &cpu); - fclose(filep); - - pkg = cpus[cpu].physical_package_id; - pni[pkg].count++; - - if (node < pni[pkg].min) - pni[pkg].min = node; - } - - for (pkg = 0; pkg < topo.num_packages; pkg++) - if (pni[pkg].count > topo.nodes_per_pkg) - topo.nodes_per_pkg = pni[0].count; - - /* Fake 1 node per pkg for machines that don't - * expose nodes and thus avoid -nan results - */ - if (topo.nodes_per_pkg == 0) - topo.nodes_per_pkg = 1; - - for (cpu = 0; cpu < topo.num_cpus; cpu++) { - pkg = cpus[cpu].physical_package_id; - node = cpus[cpu].physical_node_id; - cpus[cpu].logical_node_id = node - pni[pkg].min; + int pkg, node, lnode, cpu, cpux; + int cpu_count; + + /* initialize logical_node_id */ + for (cpu = 0; cpu <= topo.max_cpu_num; ++cpu) + cpus[cpu].logical_node_id = -1; + + cpu_count = 0; + for (pkg = 0; pkg < topo.num_packages; pkg++) { + lnode = 0; + for (cpu = 0; cpu <= topo.max_cpu_num; ++cpu) { + if (cpus[cpu].physical_package_id != pkg) + continue; + /* find a cpu with an unset logical_node_id */ + if (cpus[cpu].logical_node_id != -1) + continue; + cpus[cpu].logical_node_id = lnode; + node = cpus[cpu].physical_node_id; + cpu_count++; + /* + * find all matching cpus on this pkg and set + * the logical_node_id + */ + for (cpux = cpu; cpux <= topo.max_cpu_num; cpux++) { + if ((cpus[cpux].physical_package_id == pkg) && + (cpus[cpux].physical_node_id == node)) { + cpus[cpux].logical_node_id = lnode; + cpu_count++; + } + } + lnode++; + if (lnode > topo.nodes_per_pkg) + topo.nodes_per_pkg = lnode; + } + if (cpu_count >= topo.max_cpu_num) + break; } - free(pni); - } int get_physical_node_id(struct cpu_topology *thiscpu) @@ -4471,7 +4457,9 @@ void process_cpuid() family = (fms >> 8) & 0xf; model = (fms >> 4) & 0xf; stepping = fms & 0xf; - if (family == 6 || family == 0xf) + if (family == 0xf) + family += (fms >> 20) & 0xff; + if (family >= 6) model += ((fms >> 16) & 0xf) << 4; if (!quiet) { @@ -4840,16 +4828,8 @@ void topology_probe() siblings = get_thread_siblings(&cpus[i]); if (siblings > max_siblings) max_siblings = siblings; - if (cpus[i].thread_id != -1) + if (cpus[i].thread_id == 0) topo.num_cores++; - - if (debug > 1) - fprintf(outf, - "cpu %d pkg %d node %d core %d thread %d\n", - i, cpus[i].physical_package_id, - cpus[i].physical_node_id, - cpus[i].physical_core_id, - cpus[i].thread_id); } topo.cores_per_node = max_core_id + 1; @@ -4875,6 +4855,20 @@ void topology_probe() topo.threads_per_core = max_siblings; if (debug > 1) fprintf(outf, "max_siblings %d\n", max_siblings); + + if (debug < 1) + return; + + for (i = 0; i <= topo.max_cpu_num; ++i) { + fprintf(outf, + "cpu %d pkg %d node %d lnode %d core %d thread %d\n", + i, cpus[i].physical_package_id, + cpus[i].physical_node_id, + cpus[i].logical_node_id, + cpus[i].physical_core_id, + cpus[i].thread_id); + } + } void @@ -5102,7 +5096,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(outf, "turbostat version 18.06.20" + fprintf(outf, "turbostat version 18.07.27" " - Len Brown <lenb@kernel.org>\n"); } diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 7a6214e9ae58..a362e3d7abc6 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -105,7 +105,7 @@ $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris) BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF) -BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --version 2>&1 | grep LLVM) +BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm') ifneq ($(BTF_LLC_PROBE),) ifneq ($(BTF_PAHOLE_PROBE),) diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index f2f28b6c8915..810de20e8e26 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -158,6 +158,15 @@ struct bpf_map_def { unsigned int numa_node; }; +#define BPF_ANNOTATE_KV_PAIR(name, type_key, type_val) \ + struct ____btf_map_##name { \ + type_key key; \ + type_val value; \ + }; \ + struct ____btf_map_##name \ + __attribute__ ((section(".maps." #name), used)) \ + ____btf_map_##name = { } + static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) = (void *) BPF_FUNC_skb_load_bytes; static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from, int len, int flags) = diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 3619f3023088..ffdd27737c9e 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -247,6 +247,34 @@ static struct btf_raw_test raw_tests[] = { .max_entries = 4, }, +{ + .descr = "struct test #3 Invalid member offset", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* int64 */ /* [2] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 64, 8), + + /* struct A { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 16), + BTF_MEMBER_ENC(NAME_TBD, 1, 64), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* int64 n; */ + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n\0", + .str_sec_size = sizeof("\0A\0m\0n\0"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "struct_test3_map", + .key_size = sizeof(int), + .value_size = 16, + .key_type_id = 1, + .value_type_id = 3, + .max_entries = 4, + .btf_load_err = true, + .err_str = "Invalid member bits_offset", +}, + /* Test member exceeds the size of struct. * * struct A { @@ -479,7 +507,7 @@ static struct btf_raw_test raw_tests[] = { .key_size = sizeof(int), .value_size = sizeof(void *) * 4, .key_type_id = 1, - .value_type_id = 4, + .value_type_id = 5, .max_entries = 4, }, @@ -1264,6 +1292,88 @@ static struct btf_raw_test raw_tests[] = { .err_str = "type != 0", }, +{ + .descr = "arraymap invalid btf key (a bit field)", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* 32 bit int with 32 bit offset */ /* [2] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 32, 32, 8), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_map_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 2, + .value_type_id = 1, + .max_entries = 4, + .map_create_err = true, +}, + +{ + .descr = "arraymap invalid btf key (!= 32 bits)", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* 16 bit int with 0 bit offset */ /* [2] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 16, 2), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_map_check_btf", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_type_id = 2, + .value_type_id = 1, + .max_entries = 4, + .map_create_err = true, +}, + +{ + .descr = "arraymap invalid btf value (too small)", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_map_check_btf", + .key_size = sizeof(int), + /* btf_value_size < map->value_size */ + .value_size = sizeof(__u64), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .map_create_err = true, +}, + +{ + .descr = "arraymap invalid btf value (too big)", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "array_map_check_btf", + .key_size = sizeof(int), + /* btf_value_size > map->value_size */ + .value_size = sizeof(__u16), + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 4, + .map_create_err = true, +}, + }; /* struct btf_raw_test raw_tests[] */ static const char *get_next_str(const char *start, const char *end) @@ -2023,7 +2133,7 @@ static struct btf_raw_test pprint_test = { BTF_ENUM_ENC(NAME_TBD, 2), BTF_ENUM_ENC(NAME_TBD, 3), /* struct pprint_mapv */ /* [16] */ - BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 8), 28), + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 8), 32), BTF_MEMBER_ENC(NAME_TBD, 11, 0), /* uint32_t ui32 */ BTF_MEMBER_ENC(NAME_TBD, 10, 32), /* uint16_t ui16 */ BTF_MEMBER_ENC(NAME_TBD, 12, 64), /* int32_t si32 */ diff --git a/tools/testing/selftests/bpf/test_btf_haskv.c b/tools/testing/selftests/bpf/test_btf_haskv.c index 8c7ca096ecf2..b21b876f475d 100644 --- a/tools/testing/selftests/bpf/test_btf_haskv.c +++ b/tools/testing/selftests/bpf/test_btf_haskv.c @@ -10,11 +10,6 @@ struct ipv_counts { unsigned int v6; }; -typedef int btf_map_key; -typedef struct ipv_counts btf_map_value; -btf_map_key dumm_key; -btf_map_value dummy_value; - struct bpf_map_def SEC("maps") btf_map = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(int), @@ -22,6 +17,8 @@ struct bpf_map_def SEC("maps") btf_map = { .max_entries = 4, }; +BPF_ANNOTATE_KV_PAIR(btf_map, int, struct ipv_counts); + struct dummy_tracepoint_args { unsigned long long pad; struct sock *sock; diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh index 270fa8f49573..785eabf2a593 100755 --- a/tools/testing/selftests/bpf/test_lwt_seg6local.sh +++ b/tools/testing/selftests/bpf/test_lwt_seg6local.sh @@ -115,14 +115,14 @@ ip netns exec ns2 ip -6 route add fb00::6 encap bpf in obj test_lwt_seg6local.o ip netns exec ns2 ip -6 route add fd00::1 dev veth3 via fb00::43 scope link ip netns exec ns3 ip -6 route add fc42::1 dev veth5 via fb00::65 -ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF obj test_lwt_seg6local.o sec add_egr_x dev veth4 +ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec add_egr_x dev veth4 -ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF obj test_lwt_seg6local.o sec pop_egr dev veth6 +ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec pop_egr dev veth6 ip netns exec ns4 ip -6 addr add fc42::1 dev lo ip netns exec ns4 ip -6 route add fd00::3 dev veth7 via fb00::87 ip netns exec ns5 ip -6 route add fd00::4 table 117 dev veth9 via fb00::109 -ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF obj test_lwt_seg6local.o sec inspect_t dev veth8 +ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF endpoint obj test_lwt_seg6local.o sec inspect_t dev veth8 ip netns exec ns6 ip -6 addr add fb00::6/16 dev lo ip netns exec ns6 ip -6 addr add fd00::4/16 dev lo diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index f5f7bcc96046..41106d9d5cc7 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -12005,6 +12005,46 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_XDP, }, { + "xadd/w check whether src/dst got mangled, 1", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_0, -8), + BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_0, 3), + BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_10, 2), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .retval = 3, + }, + { + "xadd/w check whether src/dst got mangled, 2", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_10), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -8), + BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -8), + BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -8), + BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_0, 3), + BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_10, 2), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -8), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .retval = 3, + }, + { "bpf_get_stack return R0 within range", .insns = { BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), diff --git a/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc b/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc new file mode 100644 index 000000000000..3b1f45e13a2e --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc @@ -0,0 +1,28 @@ +#!/bin/sh +# description: Snapshot and tracing setting +# flags: instance + +[ ! -f snapshot ] && exit_unsupported + +echo "Set tracing off" +echo 0 > tracing_on + +echo "Allocate and take a snapshot" +echo 1 > snapshot + +# Since trace buffer is empty, snapshot is also empty, but allocated +grep -q "Snapshot is allocated" snapshot + +echo "Ensure keep tracing off" +test `cat tracing_on` -eq 0 + +echo "Set tracing on" +echo 1 > tracing_on + +echo "Take a snapshot again" +echo 1 > snapshot + +echo "Ensure keep tracing on" +test `cat tracing_on` -eq 1 + +exit 0 diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index 77f762780199..e8c5dff448eb 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -402,7 +402,7 @@ int main(int argc, char *argv[]) exit(1); } - fd = socket(AF_INET6, SOCK_STREAM, 0); + fd = socket(cfg_family, SOCK_STREAM, 0); if (fd == -1) { perror("socket"); exit(1); diff --git a/tools/usb/ffs-test.c b/tools/usb/ffs-test.c index 95dd14648ba5..0f395dfb7774 100644 --- a/tools/usb/ffs-test.c +++ b/tools/usb/ffs-test.c @@ -44,12 +44,25 @@ /******************** Little Endian Handling ********************************/ -#define cpu_to_le16(x) htole16(x) -#define cpu_to_le32(x) htole32(x) +/* + * cpu_to_le16/32 are used when initializing structures, a context where a + * function call is not allowed. To solve this, we code cpu_to_le16/32 in a way + * that allows them to be used when initializing structures. + */ + +#if __BYTE_ORDER == __LITTLE_ENDIAN +#define cpu_to_le16(x) (x) +#define cpu_to_le32(x) (x) +#else +#define cpu_to_le16(x) ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8)) +#define cpu_to_le32(x) \ + ((((x) & 0xff000000u) >> 24) | (((x) & 0x00ff0000u) >> 8) | \ + (((x) & 0x0000ff00u) << 8) | (((x) & 0x000000ffu) << 24)) +#endif + #define le32_to_cpu(x) le32toh(x) #define le16_to_cpu(x) le16toh(x) - /******************** Messages and Errors ***********************************/ static const char argv0[] = "ffs-test"; diff --git a/tools/virtio/asm/barrier.h b/tools/virtio/asm/barrier.h index 0ac3caf90877..d0351f83aebe 100644 --- a/tools/virtio/asm/barrier.h +++ b/tools/virtio/asm/barrier.h @@ -13,8 +13,8 @@ } while (0); /* Weak barriers should be used. If not - it's a bug */ # define mb() abort() -# define rmb() abort() -# define wmb() abort() +# define dma_rmb() abort() +# define dma_wmb() abort() #else #error Please fill in barrier macros #endif diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index fca8381bbe04..fb22bccfbc8a 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -52,6 +52,11 @@ static inline void *kmalloc(size_t s, gfp_t gfp) return __kmalloc_fake; return malloc(s); } +static inline void *kmalloc_array(unsigned n, size_t s, gfp_t gfp) +{ + return kmalloc(n * s, gfp); +} + static inline void *kzalloc(size_t s, gfp_t gfp) { void *p = kmalloc(s, gfp); |